File manager - Edit - /home/newsbmcs.com/public_html/static/img/logo/pyparsing.zip
Back
PK )��Z�߀�� � * tools/__pycache__/__init__.cpython-310.pycnu �[��� o �h � @ s d S )N� r r r �K/usr/local/CyberCP/lib/python3.10/site-packages/pyparsing/tools/__init__.py�<module> s PK )��ZN�U : tools/__pycache__/cvt_pyparsing_pep8_names.cpython-310.pycnu �[��� o �h� � @ s� d dl mZ d dlZedd�dedefdd��Zd�� Zd d d d d d ddd�Zd�� Z ej edd�Z e � dd� � ej edd�Z e � dd� � e�ej�e �� d��Ze� dd� � e e B eB Zedk�rId dlZd dlmZ d dlZejdd �Zejd d d d d!� ejd"d d#d$d%� ejd&d'd d(d!� ejd)ed*d+d,� ejd-d.d d/d!� ejd0d1d2d3� e�� Z d4d5� Z d Z e j D ]�Z e� �!e �D ]wZ"ee"��#� s�q�zKee"�j$e j%d6�Z&e�'e&�Z(e(e&k�r e j)r�ee"�j*e(e j%d6� e+d7e"� �� ne+d8e"� �� e j,�re e&e(� e+� d9Z n e j-�re+d:e"� �� W q� e.�y: Z/ ze+d;e"� d<e0e/�j� d<e/� �� W Y dZ/[/q�dZ/[/ww q�e�1e j2�sDe nd � dS dS )=� )� lru_cacheN)�maxsize�s�returnc C s d� dd� | D ���d�S )z* Convert CamelCase to snake_case. � c s s( � | ]}|� � rd |�� n|V qdS )�_N)�isupper�lower)�.0�c� r �[/usr/local/CyberCP/lib/python3.10/site-packages/pyparsing/tools/cvt_pyparsing_pep8_names.py� <genexpr> s �& z!camel_to_snake.<locals>.<genexpr>r )�join�lstrip)r r r r �camel_to_snake s r a� addCondition addParseAction anyCloseTag anyOpenTag asDict asList cStyleComment canParseNext conditionAsParseAction convertToDate convertToDatetime convertToFloat convertToInteger countedArray cppStyleComment dblQuotedString dblSlashComment defaultName dictOf disableMemoization downcaseTokens enableLeftRecursion enablePackrat getName htmlComment ignoreWhitespace indentedBlock infixNotation inlineLiteralsUsing javaStyleComment leaveWhitespace lineEnd lineStart locatedExpr matchOnlyAtCol matchPreviousExpr matchPreviousLiteral nestedExpr nullDebugAction oneOf originalTextFor parseFile parseString parseWithTabs pythonStyleComment quotedString removeQuotes replaceWith resetCache restOfLine runTests scanString searchString setBreak setDebug setDebugActions setDefaultWhitespaceChars setFailAction setName setParseAction setResultsName setWhitespaceChars sglQuotedString stringEnd stringStart tokenMap traceParseAction transformString tryParse unicodeString upcaseTokens withAttribute withClass �OpAssoc� DelimitedList�replace_html_entity�make_html_tags� make_xml_tags�common_html_entity�strip_html_tags)�opAssoc� delimitedList�delimited_list�replaceHTMLEntity� makeHTMLTags� makeXMLTags�commonHTMLEntity� stripHTMLTagsa� parseAll maxMatches listAllMatches callDuringTry includeSeparators fullDump printResults failureTests postParse matchString identChars maxMismatches initChars bodyChars asKeyword excludeChars asGroupList asMatch quoteChar escChar escQuote unquoteResults endQuoteChar convertWhitespaceEscapes notChars wordChars stopOn failOn joinString markerString intExpr useRegex asString ignoreExprT)� as_keywordc C � t | d �S �Nr �r ��tr r r �<lambda>* � r' c C s t | d S r# )�special_changesr% r r r r' , r( z\s*=c C r" r# r$ r% r r r r' 1 r( �__main__)�Pathz�Utility to convert Python pyparsing scripts using legacy camelCase names to use PEP8 snake_case names. By default, this script will only show whether this script would make any changes.)� descriptionz --verbosez-v� store_truez&Show unified diff for each source file)�action�helpz-vv�verbose2zSShow unified diff for each source file, plus names of scanned files with no changes)r. �destr/ z--updatez-uz Update source files in-placez --encodingzutf-8z)Encoding of source files (default: utf-8))�type�defaultr/ z--exit-zero-even-if-changedz-exit0z1Exit with status code 0 even if changes were made�source_filename�+zESource filenames or filename patterns of Python files to be converted)�nargsr/ c C s: dd l }|j| �� |�� dd�}tj�dd� |D �� d S )Nr r )�linetermc s s � | ]}|� d �V qdS )� Nr )r � diff_liner r r r P s � z show_diffs.<locals>.<genexpr>)�difflib� unified_diff� splitlines�sys�stdout� writelines)�original�modifiedr: �diffr r r � show_diffsJ s �rC )�encodingz Converted zFound required changes in � zNo required changes in zFailed to convert z: )3� functoolsr � pyparsing�pp�strr �split�pre_pep8_method_namesr) �pre_pep8_arg_names�one_of�pre_pep8_method_name�set_parse_action�special_pre_pep8_name�Regex�util�make_compressed_re�pre_pep8_arg_name�pep8_converter�__name__�argparse�pathlibr+ r= �ArgumentParser� argparser� add_argument� parse_args�argsrC � exit_statusr4 �filename_pattern�glob�filename�is_file� read_textrD �original_contents�transform_string�modified_contents�update� write_text�print�verboser0 � Exception�er2 �exit�exit_zero_even_if_changedr r r r �<module> s� � � �� � � �,��� �PK )��Zp�TH� � ! tools/cvt_pyparsing_pep8_names.pynu �[��� from functools import lru_cache import pyparsing as pp @lru_cache(maxsize=None) def camel_to_snake(s: str) -> str: """ Convert CamelCase to snake_case. """ return "".join("_" + c.lower() if c.isupper() else c for c in s).lstrip("_") pre_pep8_method_names = """ addCondition addParseAction anyCloseTag anyOpenTag asDict asList cStyleComment canParseNext conditionAsParseAction convertToDate convertToDatetime convertToFloat convertToInteger countedArray cppStyleComment dblQuotedString dblSlashComment defaultName dictOf disableMemoization downcaseTokens enableLeftRecursion enablePackrat getName htmlComment ignoreWhitespace indentedBlock infixNotation inlineLiteralsUsing javaStyleComment leaveWhitespace lineEnd lineStart locatedExpr matchOnlyAtCol matchPreviousExpr matchPreviousLiteral nestedExpr nullDebugAction oneOf originalTextFor parseFile parseString parseWithTabs pythonStyleComment quotedString removeQuotes replaceWith resetCache restOfLine runTests scanString searchString setBreak setDebug setDebugActions setDefaultWhitespaceChars setFailAction setName setParseAction setResultsName setWhitespaceChars sglQuotedString stringEnd stringStart tokenMap traceParseAction transformString tryParse unicodeString upcaseTokens withAttribute withClass """.split() special_changes = { "opAssoc": "OpAssoc", "delimitedList": "DelimitedList", "delimited_list": "DelimitedList", "replaceHTMLEntity": "replace_html_entity", "makeHTMLTags": "make_html_tags", "makeXMLTags": "make_xml_tags", "commonHTMLEntity": "common_html_entity", "stripHTMLTags": "strip_html_tags", } pre_pep8_arg_names = """parseAll maxMatches listAllMatches callDuringTry includeSeparators fullDump printResults failureTests postParse matchString identChars maxMismatches initChars bodyChars asKeyword excludeChars asGroupList asMatch quoteChar escChar escQuote unquoteResults endQuoteChar convertWhitespaceEscapes notChars wordChars stopOn failOn joinString markerString intExpr useRegex asString ignoreExpr""".split() pre_pep8_method_name = pp.one_of(pre_pep8_method_names, as_keyword=True) pre_pep8_method_name.set_parse_action(lambda t: camel_to_snake(t[0])) special_pre_pep8_name = pp.one_of(special_changes, as_keyword=True) special_pre_pep8_name.set_parse_action(lambda t: special_changes[t[0]]) # only replace arg names if part of an arg list pre_pep8_arg_name = pp.Regex( rf"{pp.util.make_compressed_re(pre_pep8_arg_names)}\s*=" ) pre_pep8_arg_name.set_parse_action(lambda t: camel_to_snake(t[0])) pep8_converter = pre_pep8_method_name | special_pre_pep8_name | pre_pep8_arg_name if __name__ == "__main__": import argparse from pathlib import Path import sys argparser = argparse.ArgumentParser( description = ( "Utility to convert Python pyparsing scripts using legacy" " camelCase names to use PEP8 snake_case names." "\nBy default, this script will only show whether this script would make any changes." ) ) argparser.add_argument("--verbose", "-v", action="store_true", help="Show unified diff for each source file") argparser.add_argument("-vv", action="store_true", dest="verbose2", help="Show unified diff for each source file, plus names of scanned files with no changes") argparser.add_argument("--update", "-u", action="store_true", help="Update source files in-place") argparser.add_argument("--encoding", type=str, default="utf-8", help="Encoding of source files (default: utf-8)") argparser.add_argument("--exit-zero-even-if-changed", "-exit0", action="store_true", help="Exit with status code 0 even if changes were made") argparser.add_argument("source_filename", nargs="+", help="Source filenames or filename patterns of Python files to be converted") args = argparser.parse_args() def show_diffs(original, modified): import difflib diff = difflib.unified_diff( original.splitlines(), modified.splitlines(), lineterm="" ) sys.stdout.writelines(f"{diff_line}\n" for diff_line in diff) exit_status = 0 for filename_pattern in args.source_filename: for filename in Path().glob(filename_pattern): if not Path(filename).is_file(): continue try: original_contents = Path(filename).read_text(encoding=args.encoding) modified_contents = pep8_converter.transform_string( original_contents ) if modified_contents != original_contents: if args.update: Path(filename).write_text(modified_contents, encoding=args.encoding) print(f"Converted {filename}") else: print(f"Found required changes in {filename}") if args.verbose: show_diffs(original_contents, modified_contents) print() exit_status = 1 else: if args.verbose2: print(f"No required changes in {filename}") except Exception as e: print(f"Failed to convert {filename}: {type(e).__name__}: {e}") sys.exit(exit_status if not args.exit_zero_even_if_changed else 0) PK )��Z tools/__init__.pynu �[��� PK )��Z�2 �2 # __pycache__/testing.cpython-310.pycnu �[��� o �hZ9 � @ sJ d dl mZ d dlZd dlZddlmZmZmZmZm Z G dd� d�Z dS )� )�contextmanagerN� )� ParserElement�ParseException�Keyword�__diag__� __compat__c @ s� e Zd ZdZG dd� d�ZG dd� d�Ze dd dd �d ed ej e d ej e de dedej e dej e dej ee f de defdd��Z dS )�pyparsing_testzB namespace class for classes useful in writing unit tests c @ s@ e Zd ZdZdd� Zdd� Zdd� Zdd � Zd d � Zd d � Z dS )z&pyparsing_test.reset_pyparsing_contexta� Context manager to be used when writing unit tests that modify pyparsing config values: - packrat parsing - bounded recursion parsing - default whitespace characters. - default keyword characters - literal string auto-conversion class - __diag__ settings Example:: with reset_pyparsing_context(): # test that literals used to construct a grammar are automatically suppressed ParserElement.inlineLiteralsUsing(Suppress) term = Word(alphas) | Word(nums) group = Group('(' + term[...] + ')') # assert that the '()' characters are not included in the parsed tokens self.assertParseAndCheckList(group, "(abc 123 def)", ['abc', '123', 'def']) # after exiting context manager, literals are converted to Literal expressions again c C s i | _ d S �N)� _save_context��self� r �D/usr/local/CyberCP/lib/python3.10/site-packages/pyparsing/testing.py�__init__/ s z/pyparsing_test.reset_pyparsing_context.__init__c C s� t j| jd< tj| jd< t j| jd< t j| jd< t j| jd< t jr)t jj | jd< nd | jd< t j | jd< t j | jd< d d � t j D �| jd < d tji| jd < | S )N�default_whitespace�default_keyword_chars�literal_string_class�verbose_stacktrace�packrat_enabled�packrat_cache_size� packrat_parse�recursion_enabledc S s i | ]}|t t|��qS r )�getattrr )�.0�namer r r � <dictcomp>H s �z?pyparsing_test.reset_pyparsing_context.save.<locals>.<dictcomp>r �collect_all_And_tokensr )r �DEFAULT_WHITE_CHARSr r �DEFAULT_KEYWORD_CHARS�_literalStringClassr �_packratEnabled� packrat_cache�size�_parse�_left_recursion_enabledr � _all_namesr r r r r r �save2 s& � � � � �z+pyparsing_test.reset_pyparsing_context.savec C s� t j| jd krt �| jd � | jd t _| jd t_t �| jd � | jd �� D ]\}}|r4t j nt j |� q+dt _ | jd rKt � | jd � n| jd t _| jd t _| jd t_| S ) Nr r r r r Fr r r r r )r r r � set_default_whitespace_charsr r r �inlineLiteralsUsing�itemsr �enable�disabler! �enable_packratr$ r% r r )r r �valuer r r �restoreR s, �� � � z.pyparsing_test.reset_pyparsing_context.restorec C s t | �� }|j�| j� |S r )�typer �update)r �retr r r �copys s z+pyparsing_test.reset_pyparsing_context.copyc C s | � � S r )r' r r r r � __enter__x s z0pyparsing_test.reset_pyparsing_context.__enter__c G s | � � d S r )r/ )r �argsr r r �__exit__{ s z/pyparsing_test.reset_pyparsing_context.__exit__N) �__name__� __module__� __qualname__�__doc__r r' r/ r3 r4 r6 r r r r �reset_pyparsing_context s ! r; c @ sT e Zd ZdZ ddd�Z ddd�Z ddd �Z dd d �Zee ddfd d ��Z dS )z&pyparsing_test.TestParseResultsAssertszk A mixin class to add parse results assertion methods to normal unittest.TestCase classes. Nc C s@ |dur| j ||�� |d� |dur | j ||�� |d� dS dS )z� Unit test assertion to compare a :class:`ParseResults` object with an optional ``expected_list``, and compare any defined results names with an optional ``expected_dict``. N��msg)� assertEqual�as_list�as_dict)r �result� expected_list� expected_dictr= r r r �assertParseResultsEquals� s �z?pyparsing_test.TestParseResultsAsserts.assertParseResultsEqualsTc C �@ |j |dd�}|rt|�� � nt|�� � | j|||d� dS )z� Convenience wrapper assert to test a parser element and input string, and assert that the resulting ``ParseResults.asList()`` is equal to the ``expected_list``. T)� parse_all)rB r= N�� parse_string�print�dumpr? rD )r �expr� test_stringrB r= �verboserA r r r �assertParseAndCheckList� � z>pyparsing_test.TestParseResultsAsserts.assertParseAndCheckListc C rE )z� Convenience wrapper assert to test a parser element and input string, and assert that the resulting ``ParseResults.asDict()`` is equal to the ``expected_dict``. T)�parseAll)rC r= NrG )r rK rL rC r= rM rA r r r �assertParseAndCheckDict� rO z>pyparsing_test.TestParseResultsAsserts.assertParseAndCheckDictc C s< |\}}|du r| j ||dur|ndd� dS dd� t||�D �}|D ]k\}}} tdd� | D �d�} tdd� | D �d�} | dura| j| | pF|d �� t|t�rQ|�W d � n1 s[w Y q#td d� | D �d�} td d� | D �d�} | | fd kr�| j|| | | p�|d � q#td|��� q#| j ||dur�|ndd� dS )ah Unit test assertion to evaluate output of ``ParserElement.runTests()``. If a list of list-dict tuples is given as the ``expected_parse_results`` argument, then these are zipped with the report tuples returned by ``runTests`` and evaluated using ``assertParseResultsEquals``. Finally, asserts that the overall ``runTests()`` success value is ``True``. :param run_tests_report: tuple(bool, [tuple(str, ParseResults or Exception)]) returned from runTests :param expected_parse_results (optional): [tuple(str, list, dict, Exception)] Nzfailed runTestsr< c S s g | ] \}}g |�|�R �qS r r )r �rpt�expectedr r r � <listcomp>� s ��zOpyparsing_test.TestParseResultsAsserts.assertRunTestResults.<locals>.<listcomp>c s � � | ] }t |t�r|V qd S r )� isinstance�str�r �expr r r � <genexpr>� � � zNpyparsing_test.TestParseResultsAsserts.assertRunTestResults.<locals>.<genexpr>c s s( � | ]}t |t�rt|t�r|V qd S r )rV r0 � issubclass� ExceptionrX r r r rZ � s � �� �)�expected_exceptionr= c s rU r )rV �listrX r r r rZ � r[ c s rU r )rV �dictrX r r r rZ � r[ �NN)rB rC r= zno validation for )� assertTrue�zip�next� assertRaisesrV r] rD rI )r �run_tests_report�expected_parse_resultsr= �run_test_success�run_test_results�mergedrL rA rS �fail_msgr^ rB rC r r r �assertRunTestResults� sV ����� � ���� � �z;pyparsing_test.TestParseResultsAsserts.assertRunTestResultsc c s� � |d ur-t |t�rt�|�}| j|||d�� }|V W d � d S 1 s&w Y d S | j||d�� }|V W d � d S 1 sCw Y d S )Nr< )rV rW �re�escape�assertRaisesRegexre )r �exc_type� expected_msgr= �ctxr r r �assertRaisesParseException� s � "�"�zApyparsing_test.TestParseResultsAsserts.assertRaisesParseException)NNN)NTra ) r7 r8 r9 r: rD rN rQ rl r r rs r r r r �TestParseResultsAsserts~ s � � � �B�rt NT�|� )�indent�base_1�s� start_line�end_line� expand_tabs�eol_mark� mark_spaces� mark_controlrw rx �returnc s� |r| � � } t�t�rd� ��� � �|durZt�t|�}|dkr=dd� ttdd�tdd ��D �} d | d < t�| �} d � nt |��t��fd d�t tdd��d g D ��} | � | �} |durz|dkrz|dkrtt�ddd��} | � | �} n| � d|�} |du r�d}|du r�t | �}t|t | ��}ttd|�|�}|dkr�| �� || |� } ndd� | �d�|| |� D �} | s�d S t t|���tdd� | D ��} �d�d } | dkr�| |r�d nd d �dd� t|r�dndt| d d��D �� d }nd }|r�d nd| d �d d� t| d �D �� d }d }| |�rd nd || d d }|| d�� ��fd d�t| || d!�D �� d S )"u� Helpful method for debugging a parser - prints a string with line and column numbers. (Line and column numbers are 1-based by default - if debugging a parse action, pass base_1=False, to correspond to the loc value passed to the parse action.) :param s: tuple(bool, str - string to be printed with line and column numbers :param start_line: int - (optional) starting line number in s to print (default=1) :param end_line: int - (optional) ending line number in s to print (default=len(s)) :param expand_tabs: bool - (optional) expand tabs to spaces, to match the pyparsing default :param eol_mark: str - (optional) string to mark the end of lines, helps visualize trailing spaces (default="|") :param mark_spaces: str - (optional) special character to display in place of spaces :param mark_control: str - (optional) convert non-printing control characters to a placeholding character; valid values: - "unicode" - replaces control chars with Unicode symbols, such as "␍" and "␊" - any single character string - replace control characters with given string - None (default) - string is displayed as-is :param indent: str | int - (optional) string to indent with line and column numbers; if an int is passed, converted to " " * indent :param base_1: bool - (optional) whether to label string using base 1; if False, string will be labeled based at 0 (default=True) :return: str - input string with leading line numbers and column number headers � N�unicodec S s i | ]\}}||�qS r r )r �c�ur r r r ' s �z4pyparsing_test.with_line_numbers.<locals>.<dictcomp>r �! i $ i3$ i!$ � rv c s i | ]}|� �qS r r )r r� )�ord_mark_controlr r r 0 s � i $ i#$ )� r� c S s g | ]}|d �qS )� ␊r �r �liner r r rT C s �z4pyparsing_test.with_line_numbers.<locals>.<listcomp>r� c s s � | ]}t |�V qd S r )�lenr� r r r rZ J s � z3pyparsing_test.with_line_numbers.<locals>.<genexpr>r �c c s s$ � | ] }d � |d d � �V qdS )zc r �d Nr �r �ir r r rZ P s � � �r� � c s s" � | ] }d |d d � �V qdS )z r � Nr r� r r r rZ [ s � r� � 1234567890�0c 3 s2 � | ]\}}�� |�� d ��d|� � � �V qdS )�d�:Nr )r r� r� )r} rw � lineno_widthr r rZ e s � � �)�start)� expandtabsrV �int�typing�castrW rc �range� maketrans�ordr_ � translate�replacer� �min�max� splitlines�split�join� enumerate)ry rz r{ r| r} r~ r rw rx �transtable_map�tbl�s_lines� max_line_len�lead�header0�header1�digits�header2r )r} rw r� r� r �with_line_numbers� s� $ � � � � ���� � ���$������z pyparsing_test.with_line_numbers)NNTru NN)r7 r8 r9 r: r; rt � staticmethodrW r� �Optionalr� �bool�Unionr� r r r r r sF h}� �������� � � �r ) � contextlibr rm r� �corer r r r r r r r r r �<module> s PK )��Z疁�� � # __pycache__/helpers.cpython-310.pycnu �[��� o �hۜ � @ s� U d dl Zd dlZd dlZd dlZd dlZddlmZ ddlT ddl m Z m Z m Z m Z mZ dxdd�dedeje d eje d efd d �Zded efd d�Zded efdd�Z dyddd�deeje ef dededededed efdd�Zd ed ed efd d �Z dzdd �ded!ed"ed efd#d$�Zded efd%d&�Z ded efd'd(�Z e � Z d)d*de fe d+�d,eeef d-eeef d.eje d/ed0ed ef d1d2�Z e!d3�e!d4�fd5d6�Z"d7eeef d e#eef fd8d9�Z$d7eeef d e#eef fd:d;�Z%ee&d<< ee&d=< e$e'e(e)d> ��*d?��\Z+Z,d@dA� ej-j.�/� D �Z0dB�1dCdD�Z2e3dEdF� ��*dG�Z4dHdI� Z5G dJdK� dKe6�Z7eeee#eeef eeef f f Z8ee#e8e9e7eje: f e#e8e9e7f f Z;e!d)�e!d*�fdLedMe<e; dNeeef dOeeef d e=f dPdQ�Z>dg fdRdS�Z?e3dT��*dU�Z@ e3dV��*dW�ZA e3dX��B� �*dY�ZCe3dZ��*d[�ZD e3d\��*d]�ZE eEZF e3d^��*d_�ZG d`da� eH� �I� D �ZJe<e e&db< c d{ddd�deeef deeeef dfedgeje9 dheje9 died efdjdk�ZKe7ZLe+ZMe,ZNe4ZOe@ZPeAZQeCZReDZSeEZTeFZUeGZVedleW�ZXedkeW�ZKedme�ZYedne�ZZedoe�Z[edpe�Z\edqe�Z]edre�Z^edse �Z_edte$�Z`edue%�Zaedve5�Zbedwe>�ZcdS )|� N� )�__diag__)�*)�_bslash�_flatten�_escape_regex_range_chars�make_compressed_re�replaced_by_pep8)�intExpr�expr�int_exprr �returnc sn |p|}t � � � �fdd�}|du r tt��dd� �}n|�� }|�d� |j|dd� |� �d �� d ��S ) a~ Helper to define a counted list of expressions. This helper defines a pattern of the form:: integer expr expr expr... where the leading integer tells how many expr expressions follow. The matched tokens returns the array of expr tokens as a list - the leading count token is suppressed. If ``int_expr`` is specified, it should be a pyparsing expression that produces an integer value. Example:: counted_array(Word(alphas)).parse_string('2 ab cd ef') # -> ['ab', 'cd'] # in this parser, the leading integer value is given in binary, # '10' indicating that 2 values are in the array binary_constant = Word('01').set_parse_action(lambda t: int(t[0], 2)) counted_array(Word(alphas), int_expr=binary_constant).parse_string('10 ab cd ef') # -> ['ab', 'cd'] # if other fields must be parsed after the count but before the # list items, give the fields results names and they will # be preserved in the returned ParseResults: count_with_metadata = integer + Word(alphas)("type") typed_array = counted_array(Word(alphanums), int_expr=count_with_metadata)("items") result = typed_array.parse_string("3 bool True True False") print(result.dump()) # prints # ['True', 'True', 'False'] # - items: ['True', 'True', 'False'] # - type: 'bool' c s, |d }� |r �| nt � K � |d d �= d S �Nr )�Empty)�s�l�t�n�� array_exprr � �D/usr/local/CyberCP/lib/python3.10/site-packages/pyparsing/helpers.py�count_field_parse_actionB s z/counted_array.<locals>.count_field_parse_actionNc S s t | d �S r )�int�r r r r �<lambda>J � z counted_array.<locals>.<lambda>�arrayLenT)�call_during_tryz(len) z...)�Forward�Word�nums�set_parse_action�copy�set_name�add_parse_action)r r r r r r r � counted_array s ) r& c s6 t � � � fdd�}| j|dd� � �dt| � � � S )a9 Helper to define an expression that is indirectly defined from the tokens matched in a previous expression, that is, it looks for a 'repeat' of a previous expression. For example:: first = Word(nums) second = match_previous_literal(first) match_expr = first + ":" + second will match ``"1:1"``, but not ``"1:2"``. Because this matches a previous literal, will also match the leading ``"1:1"`` in ``"1:10"``. If this is not desired, use :class:`match_previous_expr`. Do *not* use with packrat parsing enabled. c sT |s � t � > d S t|�dkr� |d > d S t|�� �}� tdd� |D ��> d S )Nr r c s � � | ]}t |�V qd S �N)�Literal)�.0�ttr r r � <genexpr>n � � zImatch_previous_literal.<locals>.copy_token_to_repeater.<locals>.<genexpr>)r �lenr �as_list�And)r r r �tflat��repr r �copy_token_to_repeaterc s z6match_previous_literal.<locals>.copy_token_to_repeaterT�� callDuringTry�(prev) )r r% r$ �str)r r4 r r2 r �match_previous_literalR s r9 c sF t � � | �� }� |K � � fdd�}| j|dd� � �dt| � � � S )aW Helper to define an expression that is indirectly defined from the tokens matched in a previous expression, that is, it looks for a 'repeat' of a previous expression. For example:: first = Word(nums) second = match_previous_expr(first) match_expr = first + ":" + second will match ``"1:1"``, but not ``"1:2"``. Because this matches by expressions, will *not* match the leading ``"1:1"`` in ``"1:10"``; the expressions are evaluated first, and then compared, so ``"1"`` is compared with ``"10"``. Do *not* use with packrat parsing enabled. c s* t |�� �� � fdd�}�j|dd� d S )Nc s0 t |�� �}|� krt| |d� � d|� ���d S )Nz Expected z, found)r r/ �ParseException)r r r � theseTokens�� matchTokensr r �must_match_these_tokens� s ��zTmatch_previous_expr.<locals>.copy_token_to_repeater.<locals>.must_match_these_tokensTr5 )r r/ r" )r r r r> r2 r< r r4 � s z3match_previous_expr.<locals>.copy_token_to_repeaterTr5 r7 )r r# r% r$ r8 )r �e2r4 r r2 r �match_previous_expru s r@ FT)�useRegex� asKeyword�strs�caseless� use_regex� as_keywordrA rB c sz |p|}|o|}t |t�rtjrtjddd� |r"dd� }dd� }ntj}dd� }t | t�r9t� t | �} | � � }nt | t �rCt | �}ntd��|sLt� S d } | t|�d k r�|| } t|| d d � �D ].\} } || | �rv|| | d = n!t| �t| �kr�|| | �r�|| | d = |�| | � nqd| d 7 } | t|�d k sV|�r|r�tjnd } zRtd d � |D ��r�dd�dd � |D ��� d�}n d�dd � |D ��}|r�d|� d�}t|| d�}|�d�dd � |D ��� |r�dd� |D ��|��fdd�� |W S tj�y tjd dd� Y nw d }}||ft|| ft | |ft | | ft i||f � t � fd d �|D ���d�|��S ) a! Helper to quickly define a set of alternative :class:`Literal` s, and makes sure to do longest-first testing when there is a conflict, regardless of the input order, but returns a :class:`MatchFirst` for best performance. Parameters: - ``strs`` - a string of space-delimited literals, or a collection of string literals - ``caseless`` - treat all literals as caseless - (default= ``False``) - ``use_regex`` - as an optimization, will generate a :class:`Regex` object; otherwise, will generate a :class:`MatchFirst` object (if ``caseless=True`` or ``as_keyword=True``, or if creating a :class:`Regex` raises an exception) - (default= ``True``) - ``as_keyword`` - enforce :class:`Keyword`-style matching on the generated expressions - (default= ``False``) - ``asKeyword`` and ``useRegex`` are retained for pre-PEP8 compatibility, but will be removed in a future release Example:: comp_oper = one_of("< = > <= >= !=") var = Word(alphas) number = Word(nums) term = var | number comparison_expr = term + comp_oper + term print(comparison_expr.search_string("B = 12 AA=23 B<=AA AA>12")) prints:: [['B', '=', '12'], ['AA', '=', '23'], ['B', '<=', 'AA'], ['AA', '>', '12']] z�warn_on_multiple_string_args_to_oneof: More than one string argument passed to one_of, pass choices as a list or space-delimited string� )� stacklevelc S s | � � |� � kS r( )�upper��a�br r r r � � zone_of.<locals>.<lambda>c S s |� � �| � � �S r( )rI � startswithrJ r r r r � s c S s |� | �S r( )rN rJ r r r r � s z7Invalid argument to one_of, expected string or iterabler r Nc s s � | ] }t |�d kV qdS )r N)r. �r* �symr r r r, � s � zone_of.<locals>.<genexpr>�[� c s r' r( )r rO r r r r, � r- �]�|c s � � | ]}t �|�V qd S r( ��re�escaperO r r r r, � � � z\b(?:z)\b)�flagsz | c s rU r( rV )r* r r r r r, rY c S s i | ]}|� � |�qS r ��lowerrO r r r � <dictcomp> � zone_of.<locals>.<dictcomp>c s � |d � � S r r[ �r r r )� symbol_mapr r r rM z8Exception creating Regex for one_of, building MatchFirstTc 3 s � | ]}� |�V qd S r( r rO )�parse_element_classr r r, r- ) � isinstance�str_typer �%warn_on_multiple_string_args_to_oneof�warnings�warn�operator�eq�typing�castr8 �split�Iterable�list� TypeError�NoMatchr. � enumerate�insertrW � IGNORECASE�all�join�Regexr$ r% �error�CaselessKeyword�CaselessLiteral�Keywordr) � MatchFirst)rC rD rE rF rA rB �is_equal�masks�symbols�i�cur�j�other�re_flags�patt�ret�CASELESS�KEYWORDr )ra r` r �one_of� s� )��� �� �� ���r� �key�valuec C s t tt| | ���S )a� Helper to easily and clearly define a dictionary by specifying the respective patterns for the key and value. Takes care of defining the :class:`Dict`, :class:`ZeroOrMore`, and :class:`Group` tokens in the proper order. The key pattern can include delimiting markers or punctuation, as long as they are suppressed, thereby leaving the significant key text. The value pattern can include named results, so that the :class:`Dict` results can include named token fields. Example:: text = "shape: SQUARE posn: upper left color: light blue texture: burlap" attr_expr = (label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) print(attr_expr[1, ...].parse_string(text).dump()) attr_label = label attr_value = Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join) # similar to Dict, but simpler call format result = dict_of(attr_label, attr_value).parse_string(text) print(result.dump()) print(result['shape']) print(result.shape) # object attribute access works too print(result.as_dict()) prints:: [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']] - color: 'light blue' - posn: 'upper left' - shape: 'SQUARE' - texture: 'burlap' SQUARE SQUARE {'color': 'light blue', 'shape': 'SQUARE', 'posn': 'upper left', 'texture': 'burlap'} )�Dict� OneOrMore�Group)r� r� r r r �dict_of s %r� )�asString� as_stringr� c C sr |o|}t � �dd� �}|�� }d|_|d�| |d� }|r$dd� }ndd� }|�|� | j|_|�tj� |S ) a Helper to return the original, untokenized text for a given expression. Useful to restore the parsed fields of an HTML start tag into the raw tag text itself, or to revert separate tokens with intervening whitespace back to the original matching input text. By default, returns a string containing the original parsed text. If the optional ``as_string`` argument is passed as ``False``, then the return value is a :class:`ParseResults` containing any results names that were originally matched, and a single token containing the original matched text from the input string. So if the expression passed to :class:`original_text_for` contains expressions with defined results names, you must set ``as_string`` to ``False`` if you want to preserve those results name values. The ``asString`` pre-PEP8 argument is retained for compatibility, but will be removed in a future release. Example:: src = "this is test <b> bold <i>text</i> </b> normal text " for tag in ("b", "i"): opener, closer = make_html_tags(tag) patt = original_text_for(opener + ... + closer) print(patt.search_string(src)[0]) prints:: ['<b> bold <i>text</i> </b>'] ['<i>text</i>'] c S � |S r( r )r �locr r r r r j � z#original_text_for.<locals>.<lambda>F�_original_start� _original_endc S s | |j |j� S r( )r� r� r_ r r r r o rM c S s& | |� d�|� d�� g|d d �< d S )Nr� r� ��popr_ r r r � extractTextr s &z&original_text_for.<locals>.extractText)r r" r# � callPreparse� ignoreExprs�suppress_warning� Diagnostics�)warn_ungrouped_named_tokens_in_collection)r r� r� � locMarker� endlocMarker� matchExprr� r r r �original_text_forF s " r� c C s t | ��dd� �S )zkHelper to undo pyparsing's default grouping of And expressions, even if all but one are non-empty. c S s | d S r r r r r r r s zungroup.<locals>.<lambda>)�TokenConverterr% )r r r r �ungroup{ s r� c C s4 t � �dd� �}t|d�| d� |�� �� d� �S )a (DEPRECATED - future code should use the :class:`Located` class) Helper to decorate a returned token with its starting and ending locations in the input string. This helper adds the following results names: - ``locn_start`` - location where matched expression begins - ``locn_end`` - location where matched expression ends - ``value`` - the actual parsed results Be careful if the input text contains ``<TAB>`` characters, you may want to call :class:`ParserElement.parse_with_tabs` Example:: wd = Word(alphas) for match in locatedExpr(wd).search_string("ljsdf123lksdjjf123lkkjj1222"): print(match) prints:: [[0, 'ljsdf', 5]] [[8, 'lksdjjf', 15]] [[18, 'lkkjj', 23]] c S r� r( r )�ss�llr+ r r r r � r� z locatedExpr.<locals>.<lambda>� locn_startr� �locn_end)r r" r� r# �leaveWhitespace)r �locatorr r r � locatedExpr� s ���r� �(�))� ignoreExpr�opener�closer�content� ignore_exprr� c C s� ||kr |t u r |n|}|t u rt� }| |krtd��|du r�t| t�r�t|t�r�t�t| �} t�t|�}t| �dkrgt|�dkrg|durXt t | t | | t j dd� ��}nFt t� t | | t j � �}n7|dur�t t | t| � t|� t t j dd� ��}nt t t| � t|� t t j dd� ��}ntd��t j r�|�dd� � t� }|dur�|tt| �t||B |B � t|� �K }n|tt| �t||B � t|� �K }|�d| � |� d �� d|_|S ) a& Helper method for defining nested lists enclosed in opening and closing delimiters (``"("`` and ``")"`` are the default). Parameters: - ``opener`` - opening character for a nested list (default= ``"("``); can also be a pyparsing expression - ``closer`` - closing character for a nested list (default= ``")"``); can also be a pyparsing expression - ``content`` - expression for items within the nested lists (default= ``None``) - ``ignore_expr`` - expression for ignoring opening and closing delimiters (default= :class:`quoted_string`) - ``ignoreExpr`` - this pre-PEP8 argument is retained for compatibility but will be removed in a future release If an expression is not provided for the content argument, the nested expression will capture all whitespace-delimited content between delimiters as a list of separate values. Use the ``ignore_expr`` argument to define expressions that may contain opening or closing characters that should not be treated as opening or closing characters for nesting, such as quoted_string or a comment expression. Specify multiple expressions using an :class:`Or` or :class:`MatchFirst`. The default is :class:`quoted_string`, but if no expressions are to be ignored, then pass ``None`` for this argument. Example:: data_type = one_of("void int short long char float double") decl_data_type = Combine(data_type + Opt(Word('*'))) ident = Word(alphas+'_', alphanums+'_') number = pyparsing_common.number arg = Group(decl_data_type + ident) LPAR, RPAR = map(Suppress, "()") code_body = nested_expr('{', '}', ignore_expr=(quoted_string | c_style_comment)) c_function = (decl_data_type("type") + ident("name") + LPAR + Opt(DelimitedList(arg), [])("args") + RPAR + code_body("body")) c_function.ignore(c_style_comment) source_code = ''' int is_odd(int x) { return (x%2); } int dec_to_hex(char hchar) { if (hchar >= '0' && hchar <= '9') { return (ord(hchar)-ord('0')); } else { return (10+ord(hchar)-ord('A')); } } ''' for func in c_function.search_string(source_code): print("%(name)s (%(type)s) args: %(args)s" % func) prints:: is_odd (int) args: [['int', 'x']] dec_to_hex (int) args: [['char', 'hchar']] z.opening and closing strings cannot be the sameNr )�exactzOopening and closing arguments must be strings if no content expression is givenc S s | d � tj�S r )�strip� ParserElement�DEFAULT_WHITE_CHARSr r r r r . rM z nested_expr.<locals>.<lambda>znested z expression)�_NO_IGNORE_EXPR_GIVEN� quoted_string� ValueErrorrb rc ri rj r8 r. �Combiner� � CharsNotInr� r� r r) r" r r� �Suppress� ZeroOrMorer$ �errmsg)r� r� r� r� r� r� r r r � nested_expr� s� K ���� ����� ��� � ����� �$r� �<�>c s� t | t�r| � t| | d�} n| j� tttd �}|rGt�� � t �}|| d� t t t |td� | ��� tddgd�d�� d d � � | }n8t�� � t �ttd d �B }|| d� t t t |� d d � �ttd�| � ��� tddgd�d�� dd � � | }ttd�| d dd�}|�d� � d �� |�� fdd �� |dd�� �dd��� �� � ��d� � d ��}� |_� |_t|� �|_ ||fS )zRInternal helper to construct opening and closing tag expressions, given a tag name)rD z_-:�tag�=�/F)�default�emptyc S � |d dkS �Nr r� r r_ r r r r P r z_makeTags.<locals>.<lambda>r� )� exclude_charsc S s | d � � S r r[ r r r r r ^ r c S r� r� r r_ r r r r d r z</)�adjacentr� c s* | � dd�� �dd��� �� � | �� �S )N�startrR �:� )� __setitem__rt �replace�titlerk r# r ��resnamer r r m s "��endrR r� r� ) rb rc ry �namer �alphas� alphanums�dbl_quoted_stringr# r" � remove_quotesr� r� r� r� �Optr� � printablesr� r) r$ r% rt r� r� rk r� �SkipTo�tag_body)�tagStr�xml� suppress_LT� suppress_GT� tagAttrName� tagAttrValue�openTag�closeTagr r� r � _makeTags@ sp ������ �� ����� �� �� � �� r� �tag_strc C � t | d�S )aP Helper to construct opening and closing tag expressions for HTML, given a tag name. Matches tags in either upper or lower case, attributes with namespaces and with quoted or unquoted values. Example:: text = '<td>More info at the <a href="https://github.com/pyparsing/pyparsing/wiki">pyparsing</a> wiki page</td>' # make_html_tags returns pyparsing expressions for the opening and # closing tags as a 2-tuple a, a_end = make_html_tags("A") link_expr = a + SkipTo(a_end)("link_text") + a_end for link in link_expr.search_string(text): # attributes in the <A> tag (like "href" shown here) are # also accessible as named results print(link.link_text, '->', link.href) prints:: pyparsing -> https://github.com/pyparsing/pyparsing/wiki F�r� �r� r r r �make_html_tagsz s r� c C r� )z�Helper to construct opening and closing tag expressions for XML, given a tag name. Matches tags only in the given upper/lower case. Example: similar to :class:`make_html_tags` Tr� r� r r r � make_xml_tags� s r� � any_open_tag� any_close_tagz_:zany tagc C s i | ] \}}|� d �|�qS )�;)�rstrip)r* �k�vr r r r] � s r] z-nbsp lt gt amp quot apos cent pound euro copyr� rT c C s dt � dtt�� d�S )Nz &(?P<entity>rT z);)�_most_common_entitiesr �_htmlEntityMapr r r r r � r^ r zcommon HTML entityc C s t �|j�S )zRHelper parser action to replace common HTML entities with their special characters)r� �get�entityr_ r r r �replace_html_entity� s r� c @ s e Zd ZdZdZdZdS )�OpAssoczvEnumeration of operator associativity - used in constructing InfixNotationOperatorSpec for :class:`infix_notation`r rG N)�__name__� __module__� __qualname__�__doc__�LEFT�RIGHTr r r r r� � s r� � base_expr�op_list�lpar�rparc C sz G dd� dt �}d|_t� }|�| j� d�� t|t�r t|�}t|t�r)t|�}|| | �d| j� ��}t|t�r@t|t�sG| t|�B }n| |B }|D �]h}|d dd� \} } } } t| t �rft � | �} t � t | �} | d kr�t| ttf�r}t| �d kr�td ��| \} }| � |� d �}n| � d �}d | kr�d ks�td�� td��| tjtjfvr�td��t� �|�}t � t|�}tg �}| tju �r"| d kr�||| �}t|| d �}n�| d k�r| dur�||| | �}t|| | d �}n�||| �}t|d �}n�| d k�r!||| | | | �}t|| | | | d �}nl| tju �r�| d k�rEt| t��s7t| �} || j| �}t| | �}nI| d k�rq| du�rb||| | �}t|| | d �}n,||| �}t||d �}n | d k�r�||| | | | �}t|| | | | �}d|_|| }| �r�t| ttf��r�|j| � n|�| � |||B �|�K }|}qM||K }|S )a� Helper method for constructing grammars of expressions made up of operators working in a precedence hierarchy. Operators may be unary or binary, left- or right-associative. Parse actions can also be attached to operator expressions. The generated parser will also recognize the use of parentheses to override operator precedences (see example below). Note: if you define a deep operator list, you may see performance issues when using infix_notation. See :class:`ParserElement.enable_packrat` for a mechanism to potentially improve your parser performance. Parameters: - ``base_expr`` - expression representing the most basic operand to be used in the expression - ``op_list`` - list of tuples, one for each operator precedence level in the expression grammar; each tuple is of the form ``(op_expr, num_operands, right_left_assoc, (optional)parse_action)``, where: - ``op_expr`` is the pyparsing expression for the operator; may also be a string, which will be converted to a Literal; if ``num_operands`` is 3, ``op_expr`` is a tuple of two expressions, for the two operators separating the 3 terms - ``num_operands`` is the number of terms for this operator (must be 1, 2, or 3) - ``right_left_assoc`` is the indicator whether the operator is right or left associative, using the pyparsing-defined constants ``OpAssoc.RIGHT`` and ``OpAssoc.LEFT``. - ``parse_action`` is the parse action to be associated with expressions matching this operator expression (the parse action tuple member may be omitted); if the parse action is passed a tuple or list of functions, this is equivalent to calling ``set_parse_action(*fn)`` (:class:`ParserElement.set_parse_action`) - ``lpar`` - expression for matching left-parentheses; if passed as a str, then will be parsed as ``Suppress(lpar)``. If lpar is passed as an expression (such as ``Literal('(')``), then it will be kept in the parsed results, and grouped with them. (default= ``Suppress('(')``) - ``rpar`` - expression for matching right-parentheses; if passed as a str, then will be parsed as ``Suppress(rpar)``. If rpar is passed as an expression (such as ``Literal(')')``), then it will be kept in the parsed results, and grouped with them. (default= ``Suppress(')')``) Example:: # simple example of four-function arithmetic with ints and # variable names integer = pyparsing_common.signed_integer varname = pyparsing_common.identifier arith_expr = infix_notation(integer | varname, [ ('-', 1, OpAssoc.RIGHT), (one_of('* /'), 2, OpAssoc.LEFT), (one_of('+ -'), 2, OpAssoc.LEFT), ]) arith_expr.run_tests(''' 5+3*6 (5+3)*6 -2--11 ''', full_dump=False) prints:: 5+3*6 [[5, '+', [3, '*', 6]]] (5+3)*6 [[[5, '+', 3], '*', 6]] (5+x)*y [[[5, '+', 'x'], '*', 'y']] -2--11 [[['-', 2], '-', ['-', 11]]] c @ s e Zd Zddd�ZdS )zinfix_notation.<locals>._FBTc S s | j �||� |g fS r( )r � try_parse)�self�instringr� � doActionsr r r � parseImpl% s z%infix_notation.<locals>._FB.parseImplN�T)r� r� r� r r r r r �_FB$ s r z FollowedBy>� _expression�nested_r( N� � rG z@if numterms=3, opExpr must be a tuple or list of two expressionsz operationsr z6operator must be unary (1), binary (2), or ternary (3)z2operator must indicate right or left associativity)r .)rG .F)� FollowedByr� r r$ r� rb r8 r� r� rc r� �_literalStringClassri rj �tuplerm r. r� r� r� r� r0 r� r �show_in_diagramr" �setName)r� r� r� r� r r� r� �lastExpr�operDef�opExpr�arity�rightLeftAssoc�pa�opExpr1�opExpr2� term_name�thisExpr�match_lookaheadr� r r r �infix_notation� s� V � � ��� � r c s0 � � �dd� � � �fdd���fdd�}�fdd�}�fdd �}tt� �d ��� �}t� t� �|� �d �}t� �|��d �} t� �|��d �} |rctt |�| t| t| � t |� � | �} ntt |�t| t| � t |� � t | � �} | � � fdd�� | � �fdd�� | � t t� � | �d�S )a� (DEPRECATED - use :class:`IndentedBlock` class instead) Helper method for defining space-delimited indentation blocks, such as those used to define block statements in Python source code. Parameters: - ``blockStatementExpr`` - expression defining syntax of statement that is repeated within the indented block - ``indentStack`` - list created by caller to manage indentation stack (multiple ``statementWithIndentedBlock`` expressions within a single grammar should share a common ``indentStack``) - ``indent`` - boolean indicating whether block must be indented beyond the current level; set to ``False`` for block of left-most statements (default= ``True``) A valid block must contain at least one ``blockStatement``. (Note that indentedBlock uses internal parse actions which make it incompatible with packrat parsing.) Example:: data = ''' def A(z): A1 B = 100 G = A2 A2 A3 B def BB(a,b,c): BB1 def BBA(): bba1 bba2 bba3 C D def spam(x,y): def eggs(z): pass ''' indentStack = [1] stmt = Forward() identifier = Word(alphas, alphanums) funcDecl = ("def" + identifier + Group("(" + Opt(delimitedList(identifier)) + ")") + ":") func_body = indentedBlock(stmt, indentStack) funcDef = Group(funcDecl + func_body) rvalue = Forward() funcCall = Group(identifier + "(" + Opt(delimitedList(rvalue)) + ")") rvalue << (funcCall | identifier | Word(nums)) assignment = Group(identifier + "=" + rvalue) stmt << (funcDef | assignment | identifier) module_body = stmt[1, ...] parseTree = module_body.parseString(data) parseTree.pprint() prints:: [['def', 'A', ['(', 'z', ')'], ':', [['A1'], [['B', '=', '100']], [['G', '=', 'A2']], ['A2'], ['A3']]], 'B', ['def', 'BB', ['(', 'a', 'b', 'c', ')'], ':', [['BB1'], [['def', 'BBA', ['(', ')'], ':', [['bba1'], ['bba2'], ['bba3']]]]]], 'C', 'D', ['def', 'spam', ['(', 'x', 'y', ')'], ':', [[['def', 'eggs', ['(', 'z', ')'], ':', [['pass']]]]]]] Nc s � d �d d �< d S �N���r r )� backup_stacks� indentStackr r � reset_stack� s z"indentedBlock.<locals>.reset_stackc sN |t | �krd S t|| �}|� d kr%|� d kr t| |d��t| |d��d S )Nr zillegal nestingznot a peer entry)r. �colr: �r r r �curCol�r r r �checkPeerIndent� s �z&indentedBlock.<locals>.checkPeerIndentc s0 t || �}|� d kr� �|� d S t| |d��)Nr znot a subentry)r! �appendr: r" r$ r r �checkSubIndent� s z%indentedBlock.<locals>.checkSubIndentc sN |t | �krd S t|| �}� r|� v st| |d��|� d k r%� �� d S d S )Nznot an unindentr )r. r! r: r� r" r$ r r � checkUnindent� s �z$indentedBlock.<locals>.checkUnindentz �INDENTrR �UNINDENTc s � r � � d�od S d S r r� r )r r r r r^ z indentedBlock.<locals>.<lambda>c s � � S r( r )rK rL �c�d)r r r r s zindented block)r& r� �LineEnd�set_whitespace_chars�suppressr r" r$ r� r� r% �set_fail_action�ignorer ) �blockStatementExprr �indentr r% r' r( �NLr) �PEER�UNDENT�smExprr )r r r r � indentedBlock� s@ V ������� � r8 z/\*(?:[^*]|\*(?!/))*\*\/zC style commentz<!--[\s\S]*?-->z HTML commentz.*z rest of linez//(?:\\\n|[^\n])*z // commentz2(?:/\*(?:[^*]|\*(?!/))*\*\/)|(?://(?:\\\n|[^\n])*)zC++ style commentz#.*zPython style commentc C s g | ] }t |t�r|�qS r )rb r� )r* r� r r r � <listcomp>< s ��r9 �_builtin_exprs�,��allow_trailing_delim�delim�combine�min�maxr= c C s t | |||||d�S )z/(DEPRECATED - use :class:`DelimitedList` class)r< )� DelimitedList)r r> r? r@ rA r= r r r �delimited_listB s �rC � delimitedList� countedArray�matchPreviousLiteral�matchPreviousExpr�oneOf�dictOf�originalTextFor� nestedExpr� makeHTMLTags� makeXMLTags�replaceHTMLEntity� infixNotationr( )FTFr )r; FNN)d� html.entities�htmlrg rW �sysri rR r �core�utilr r r r r r� �Optionalr& r9 r@ �Unionrl r8 �boolr� r� r� r� r� r� ro r� r� r� r� r r� r� �__annotations__r r� r� r$ r� r� �entities�html5�itemsr� r� r� ru �common_html_entityr� �Enumr� � InfixNotationOperatorArgTyper � ParseAction�InfixNotationOperatorSpecrm r r r8 �c_style_comment� html_comment�leave_whitespace� rest_of_line�dbl_slash_comment�cpp_style_comment�java_style_comment�python_style_comment�vars�valuesr: rC �opAssoc� anyOpenTag� anyCloseTag�commonHTMLEntity� cStyleComment� htmlComment� restOfLine�dblSlashComment�cppStyleComment�javaStyleComment�pythonStyleCommentrB rD rE rF rG rH rI rJ rK rL rM rN rO r r r r �<module> s� ����� �<#&�������� � )����� �5%�� � ���� � : � � � � ���� ���������� � � � F ����� � ����� � PK )��Z��9H7 H7 __pycache__/util.cpython-310.pycnu �[��� o �h8 � @ s� d dl Z d dlZd dlmZmZ d dlZd dlZd dlZd dlm Z m Z m Z m Z m Z d dlZed�Ze de d�ZG dd� d�Zed d �d ed ed efdd��Zed d �d ed ed efdd��Zed d �d ed ed efdd��ZG dd� d�ZG dd� d�ZG dd� d�ZG dd� de�Z d ed efd d �Z G d d � d �Z !d5d e ee e f d"e d efd#d$�Z d%e d e!fd&d'�Z" (d6d!d)d*�d+e e d,ed-e d.ed ef d/d0�Z#d1ed2ed efd3d4�Z$dS )7� N)� lru_cache�wraps)�Callable�Union�Iterable�TypeVar�cast�\ �C)�boundc @ sZ e Zd ZU dZg Zee ed< g Zee ed< dZ e dd� �Z e dd� �Z e d d� �Z d S ) �__config_flagsz=Internal class for defining compatibility and debugging flags� _all_names� _fixed_names� configurationc C sv || j v r#tj| j� d|� d| j� dtt| |���� � d�dd� d S || jv r0t | ||� d S t d| j� d|����)N�.� z is z and cannot be overridden� )� stacklevelzno such ) r �warnings�warn�__name__� _type_desc�str�getattr�upperr �setattr� ValueError)�cls�dname�value� r �A/usr/local/CyberCP/lib/python3.10/site-packages/pyparsing/util.py�_set s ,� z__config_flags._setc C � | � |d�S )NT�r" �r �namer r r! �<lambda>$ � z__config_flags.<lambda>c C r# )NFr$ r% r r r! r' % r( N)r � __module__� __qualname__�__doc__r �listr �__annotations__r r � classmethodr" �enable�disabler r r r! r s r � )�maxsize�loc�strg�returnc C sF |}d| k rt |�k rn n || d dkrdS | |�dd| � S )a� Returns current column within a string, counting newlines as line separators. The first column is number 1. Note: the default parsing behavior is to expand tabs in the input string before starting the parsing process. See :class:`ParserElement.parse_string` for more information on parsing strings containing ``<TAB>`` s, and suggested methods to maintain a consistent view of the parsed string, the parse location, and line and column positions within the parsed string. r � � )�len�rfind)r3 r4 �sr r r! �col( s Br; c C s |� dd| �d S )a� Returns current line number within a string, counting newlines as line separators. The first line is number 1. Note - the default parsing behavior is to expand tabs in the input string before starting the parsing process. See :class:`ParserElement.parse_string` for more information on parsing strings containing ``<TAB>`` s, and suggested methods to maintain a consistent view of the parsed string, the parse location, and line and column positions within the parsed string. r7 r r6 )�count)r3 r4 r r r! �lineno9 s r= c C sB |� dd| �}|�d| �}|dkr||d |� S ||d d� S )zh Returns the line of text containing loc within a string, counting newlines as line separators. r7 r r6 N)r9 �find)r3 r4 �last_cr�next_crr r r! �lineG s (rA c @ � e Zd Zdd� ZdS )�_UnboundedCachec sp i � � j �t� | _���fdd�}� fdd�}� fdd�}d | _t�|| �| _ t�|| �| _t�|| �| _d S )Nc � � |��S �Nr ��_�key�� cache_get� not_in_cacher r! �getW � z%_UnboundedCache.__init__.<locals>.getc s |� |< d S rE r �rG rH r ��cacher r! �set_Z � z&_UnboundedCache.__init__.<locals>.set_c � � � � d S rE ��clear�rG rO r r! rU ] rR z'_UnboundedCache.__init__.<locals>.clear)rL �objectrK �size�types� MethodType�setrU )�selfrL rQ rU r )rP rJ rK r! �__init__R s z_UnboundedCache.__init__N�r r) r* r] r r r r! rC Q � rC c @ rB )� _FifoCachec sz i � �| _ t� | _�� j�� j���fdd�}� ��fdd�}� fdd�}t�|| �| _t�|| �| _t�|| �| _d S )Nc rD rE r rF rI r r! rL n rM z _FifoCache.__init__.<locals>.getc s8 |� |< t � ��kr�tt� ��� t � ��ks d S d S rE )r8 �next�iterrN )rP � cache_poprX r r! rQ q s �z!_FifoCache.__init__.<locals>.set_c rS rE rT rV rO r r! rU w rR z"_FifoCache.__init__.<locals>.clear) rX rW rK rL �poprY rZ r[ rU )r\ rX rL rQ rU r )rP rJ rc rK rX r! r] g s z_FifoCache.__init__Nr^ r r r r! r` f r_ r` c @ s8 e Zd ZdZdd� Zdd� Zdd� Zdd � Zd d � Zd S ) �LRUMemoz� A memoizing mapping that retains `capacity` deleted items The memo tracks retained items by their access order; once `capacity` items are retained, the least recently used item is discarded. c C s || _ i | _i | _d S rE )� _capacity�_active�_memory)r\ �capacityr r r! r] � s zLRUMemo.__init__c C s< z| j | W S ty | j�|�| j|< | j| Y S w rE )rg �KeyErrorrh rd �r\ rH r r r! � __getitem__� s �zLRUMemo.__getitem__c C s | j �|d � || j|< d S rE )rh rd rg )r\ rH r r r r! � __setitem__� s zLRUMemo.__setitem__c C sd z| j �|�}W n ty Y d S w t| j�d | jd � }|D ]}| j�|� q"|| j|< d S �Nr6 )rg rd rj r, rh rf )r\ rH r � oldest_keys� key_to_deleter r r! � __delitem__� s �zLRUMemo.__delitem__c C s | j �� | j�� d S rE )rg rU rh �r\ r r r! rU � s z LRUMemo.clearN) r r) r* r+ r] rl rm rq rU r r r r! re s re c @ s e Zd ZdZdd� ZdS )� UnboundedMemoz< A memoizing mapping that retains all deleted items c C s d S rE r rk r r r! rq � � zUnboundedMemo.__delitem__N)r r) r* r+ rq r r r r! rs � s rs r: c C s: dD ] }| � |t| �} q| � dd�} | � dd�} t| �S )Nz\^-[]r7 z\n� z\t)�replace�_bslashr )r: �cr r r! �_escape_regex_range_chars� s ry c @ s, e Zd ZdZd dd�Zdedefdd�ZdS ) �_GroupConsecutiveaQ Used as a callable `key` for itertools.groupby to group characters that are consecutive: itertools.groupby("abcdejkmpqrs", key=IsConsecutive()) yields: (0, iter(['a', 'b', 'c', 'd', 'e'])) (1, iter(['j', 'k'])) (2, iter(['m'])) (3, iter(['p', 'q', 'r', 's'])) r5 Nc C s d| _ t�� | _d| _d S )Nr ���)�prev� itertoolsr< �counterr rr r r r! r] � s z_GroupConsecutive.__init__�charc C s4 t |�}|| j| _}|| dkrt| j�| _| jS rn )�ordr| ra r~ r )r\ r �c_intr| r r r! �__call__� s z_GroupConsecutive.__call__)r5 N)r r) r* r+ r] r �intr� r r r r! rz � s rz T� re_escapec s$ dt dt fdd�� dt dt fdd�}|s|� g }tt| ��}t|�dkr�tj|t� d�D ]V\}}t|� }}t� t �� |�^ }}W d � n1 sKw Y ||kr\|� � |�� q,|t t |�d �krt|� � |�� � |�� �� q,|� � |�� d � |�� �� q,n � fd d �|D �}d�|�S )a Take a string or list of single-character strings, and return a string of the consecutive characters in that string collapsed into groups, as might be used in a regular expression '[a-z]' character set: 'a' -> 'a' -> '[a]' 'bc' -> 'bc' -> '[bc]' 'defgh' -> 'd-h' -> '[d-h]' 'fdgeh' -> 'd-h' -> '[d-h]' 'jklnpqrtu' -> 'j-lnp-rtu' -> '[j-lnp-rtu]' Duplicates get collapsed out: 'aaa' -> 'a' -> '[a]' 'bcbccb' -> 'bc' -> '[bc]' 'defghhgf' -> 'd-h' -> '[d-h]' 'jklnpqrjjjtu' -> 'j-lnp-rtu' -> '[j-lnp-rtu]' Spaces are preserved: 'ab c' -> ' a-c' -> '[ a-c]' Characters that are significant when defining regex ranges get escaped: 'acde[]-' -> r'\-\[\]ac-e' -> r'[\-\[\]ac-e]' rx r5 c S s | dv rd| S | S )Nz\^-][�\r �rx r r r! �escape_re_range_char� s z8_collapse_string_to_ranges.<locals>.escape_re_range_charc S s | S rE r r� r r r! �no_escape_re_range_char� rt z;_collapse_string_to_ranges.<locals>.no_escape_re_range_char� �rH Nr6 �-c s g | ]}� |��qS r r )�.0rx �r� r r! � <listcomp>! s z._collapse_string_to_ranges.<locals>.<listcomp>� )r �sortedr[ r8 r} �groupbyrz ra � contextlib�suppressr �append�chrr� �join) r: r� r� �ret�s_charsrG �chars�first�lastr r� r! �_collapse_string_to_ranges� s, � �� r� �llc C sN g }g | �}|r%|� d�}t|t�r t|t�s ||d d�< n|�|� |s|S )Nr )rd � isinstancer r r� )r� r� �to_visit�ir r r! �_flatten& s �r� r� r6 ��non_capturing_groups�_level� word_list� max_levelr� r� c C sz dt t fdd�}|dkr | std��d| v rtd��n| s dS t i �| ��} |dkrQtd d � | D ��rCd �td d � | D �tdd��S dd�dd � | D ��� d�S g }d}|rYdnd}|t| ��D ]�\}} |�|� d }t � |�}d} d| v r~d} | � d� t| �dk�rt dd � | D ��r�|�|� dd�dd � | D ��� d| � �� qa||k r�t t| �|||d d�} |�|� d|� | � d| � �� qat dd � | D ��r�|�|� dd�dd � | D ��� d| � �� qa| jtdd� |�|� d|� d �d d � | D ��� d| � �� qa| �r2t � | d �} t| �dk�r&| �r&|�|� d|� | � d| � �� qa|�|� | � | � �� qa|�|� qad�|�S ) z� Create a regular expression string from a list of words, collapsing by common prefixes and optional suffixes. Calls itself recursively to build nested sublists for each group of suffixes that have a shared prefix. �namelistc s sp � t | �dkr&tj| dd� d�D ]\}}|tdd� |D �t dd�fV qd S | d d | d dd � gfV d S ) Nr6 c S s | d d� S rn r )r: r r r! r' C r( zOmake_compressed_re.<locals>.get_suffixes_from_common_prefixes.<locals>.<lambda>r� c S s g | ]}|d d� �qS �r6 Nr �r� r: r r r! r� D s zQmake_compressed_re.<locals>.get_suffixes_from_common_prefixes.<locals>.<listcomp>T�rH �reverser )r8 r} r� r� )r� �prefix�suffixesr r r! �!get_suffixes_from_common_prefixesA s � �$z=make_compressed_re.<locals>.get_suffixes_from_common_prefixesr6 z&no words given to make_compressed_re()r� z%word list cannot contain empty stringr c s s � | ] }t |�d kV qdS r� �r8 �r� �wdr r r! � <genexpr>W � � z%make_compressed_re.<locals>.<genexpr>�|c S s g | ]}t �|��qS r ��re�escaper� r r r! r� Y s z&make_compressed_re.<locals>.<listcomp>Tr� �[c s � � | ]}t |�V qd S rE �ry r� r r r! r� \ � � �]z?:�?c s � � | ] }t |�d kV qdS r� r� r� r r r! r� n r� c s r� rE r� r� r r r! r� p r� r� �(�)c s r� r� r� r� r r r! r� | r� c s r� rE r� r� r r r! r� ~ r� c s s � | ]}t �|�V qd S rE r� r� r r r! r� � s � )r, r r �fromkeys�anyr� r� r8 r� r� r� �remove�all�make_compressed_re�sort) r� r� r� r� r� r� �sep�ncgroup�initialr� �trailing� suffix_re�suffixr r r! r� 2 sn �� "�� "�&� r� � compat_name�fnc s� t � d� �� dgtt�� �j�d d� kr t� �� fdd��}n t� �� fdd��}d� j� d�|_| |_� j|_t � t j �rD� j |_ nt � t �rTt� d �rT� jj |_ nd |_ � j|_tt|�S ) N�__func__r\ r6 c s � | g|�R i |��S rE r )r\ �args�kwargs�r� r r! �_inner� s z replaced_by_pep8.<locals>._innerc s � | i |��S rE r )r� r� r� r r! r� � s zDeprecated - use :class:`�`r] )r r, �inspect� signature� parametersr r r+ r- r� rY � FunctionType�__kwdefaults__�type�hasattrr] r* r r )r� r� r� r r� r! �replaced_by_pep8� s r� )T)r� )%r� r� � functoolsr r r� r} rY �typingr r r r r r r� rw r r r� r r; r= rA rC r` re �dictrs ry rz �boolr� r, r� r� r� r r r r! �<module> s` ( ��� �T������ �_PK )��Z�q( q( & __pycache__/exceptions.cpython-310.pycnu �[��� o �h�& � @ s� d dl mZ d dlZd dlZd dlZd dlZd dlmZ ddlm Z ddl m Z m Z mZmZmZ G dd� de je je je je j�Ze ej�Ze�d e d �ZG d d � d e�Z G d d� de �Z G dd� de �Z G dd� de �Z G dd� de�Z dS )� )� annotationsN)�cached_property� )�pyparsing_unicode)�_collapse_string_to_ranges�col�line�lineno�replaced_by_pep8c @ s e Zd ZdS )�_ExceptionWordUnicodeSetN)�__name__� __module__� __qualname__� r r �G/usr/local/CyberCP/lib/python3.10/site-packages/pyparsing/exceptions.pyr s r z([z ]{1,16})|.c @ s e Zd ZU dZded< ded< ded< ded< d ed < d Z d9d:dd�Zed;d<dd��Ze d=dd��Z e d>dd ��Z e d?d d ��Z e d?d d ��Ze d?d!d"��Ze d>d#d$��Zed%d&� �Zejd'd&� �Zd(d)� Zd>d*d+�Zd>d,d-�Zd.d/� Z d@d0d1�dAd4d5�Zd;dBd6d7�Zed8e�Zd S )C�ParseBaseExceptionz7base exception class for all parsing runtime exceptions�int�loc�str�msg�pstrz typing.Any�parser_elementz%tuple[str, int, typing.Optional[str]]�args�r r r r r r N�typing.Optional[str]�return�Nonec C s: |d u r |d}}|| _ || _|| _|| _|||f| _d S )N� r )�selfr r r �elemr r r �__init__1 s zParseBaseException.__init__� �exc� Exception�depthc C s� ddl }ddlm} |du rt�� }g }t| t�r*|�| j� |�dd| j � ��� |�t | �j � d| � �� |dks@| j du rEd� |�S |j| j |d �}t� }|| d� D ]h}|d }|j�d d�} t| |�r�|jj�d �sqqWt| �|v rxqW|�t| �� t | �} |�| j� d | j � d | � �� n$| dur�t | �} |�| j� d | j � �� n|j} | jdv r�qW|�| j� |d8 }|s� nqWd� |�S )a� Method to take an exception and translate the Python internal traceback into a list of the pyparsing expressions that caused the exception to be raised. Parameters: - exc - exception raised during parsing (need not be a ParseException, in support of Python exceptions that might be raised in a parse action) - depth (default=16) - number of levels back in the stack trace to list expression and function names; if None, the full stack trace names will be listed; if 0, only the failing input line, marker, and exception string will be shown Returns a multi-line string listing the ParserElements and/or function names in the exception's stack trace. r Nr )� ParserElement�^�>z: � )�contextr )� parseImpl� _parseNoCache�.z - )�wrapperz<module>)�inspect�corer% �sys�getrecursionlimit� isinstancer �appendr �column�typer � __traceback__�join�getinnerframes�set�f_locals�get�f_code�co_name� startswith�id�addr ) r" r$ r. r% �ret�callers�seen�ff�frm�f_self� self_type�coder r r �explain_exceptionA sH � z$ParseBaseException.explain_exceptionc C s | |j |j|j|j�S )z� internal factory method to simplify creating one type of ParseException from another - avoids having __init__ signature conflicts among subclasses )r r r r )�cls�per r r �_from_exception� s z"ParseBaseException._from_exceptionc C � t | j| j�S )zG Return the line of text where the exception occurred. )r r r �r r r r r � � zParseBaseException.linec C rM )zV Return the 1-based line number of text where the exception occurred. )r r r rN r r r r � rO zParseBaseException.linenoc C rM �z] Return the 1-based column on the line of text where the exception occurred. �r r r rN r r r r � rO zParseBaseException.colc C rM rP rQ rN r r r r4 � rO zParseBaseException.columnc C sh | j sdS | jt| j �krdS t�| j | j�}|d ur!|�d�}n | j | j| jd � }t|��dd�S )Nr z end of textr r z\\�\)r r �len�_exception_word_extractor�match�group�repr�replace)r � found_match� found_textr r r �found� s zParseBaseException.foundc C s | j S �N�r rN r r r � parserElement� s z ParseBaseException.parserElementc C � || _ d S r\ r] )r r r r r r^ � s c C s t � | �S r\ )�copyrN r r r r` � � zParseBaseException.copyc C s> | j r d| j � �nd}| j� |� d| j� d| j� d| j� d� S )Nz, found r z (at char z ), (line:z, col:�))r[ r r r r4 )r � found_phraser r r �formatted_message� s (z$ParseBaseException.formatted_messagec C s | � � S r\ )rd rN r r r �__str__� � zParseBaseException.__str__c C s t | �S r\ )r rN r r r �__repr__� rf zParseBaseException.__repr__z>!<)� markerString� marker_stringrh c C sL |dur|n|}| j }| jd }|r"|d|� � |� ||d� � �}|�� S )z� Extracts the exception line from the input string, and marks the location of the exception with a special symbol. Nr )r r4 �strip)r ri rh �line_str� line_columnr r r �mark_input_line� s z"ParseBaseException.mark_input_linec C s | � | |�S )a� Method to translate the Python internal traceback into a list of the pyparsing expressions that caused the exception to be raised. Parameters: - depth (default=16) - number of levels back in the stack trace to list expression and function names; if None, the full stack trace names will be listed; if 0, only the failing input line, marker, and exception string will be shown Returns a multi-line string listing the ParserElements and/or function names in the exception's stack trace. Example:: # an expression to parse 3 integers expr = pp.Word(pp.nums) * 3 try: # a failing parse - the third integer is prefixed with "A" expr.parse_string("123 456 A789") except pp.ParseException as pe: print(pe.explain(depth=0)) prints:: 123 456 A789 ^ ParseException: Expected W:(0-9), found 'A' (at char 8), (line:1, col:9) Note: the diagnostic output will include string representations of the expressions that failed to parse. These representations will be more helpful if you use `set_name` to give identifiable names to your expressions. Otherwise they will use the default string forms, which may be cryptic to read. Note: pyparsing's default truncation of exception tracebacks may also truncate the stack of expressions that are displayed in the ``explain`` output. To get the full listing of parser expressions, you may have to set ``ParserElement.verbose_stacktrace = True`` )rI )r r$ r r r �explain� s 'zParseBaseException.explain� markInputline)r NN)r r r r r r r r )r! )r" r# r$ r r r )r r �r r )r r r\ )ri r rh r r r )r$ r r r ) r r r �__doc__�__annotations__� __slots__r � staticmethodrI � classmethodrL r r r r r4 r[ �propertyr^ �setterr` rd re rg rm rn r ro r r r r r sP �? �� +r c @ � e Zd ZdZdS )�ParseExceptionaw Exception thrown when a parse expression doesn't match the input string Example:: integer = Word(nums).set_name("integer") try: integer.parse_string("ABC") except ParseException as pe: print(pe, f"column: {pe.column}") prints:: Expected integer, found 'ABC' (at char 0), (line:1, col:1) column: 1 N�r r r rq r r r r ry � ry c @ rx )�ParseFatalExceptionzu User-throwable exception thrown when inconsistent parse content is found; stops all parsing immediately Nrz r r r r r| r{ r| c @ rx )�ParseSyntaxExceptionz� Just like :class:`ParseFatalException`, but thrown internally when an :class:`ErrorStop<And._ErrorStop>` ('-' operator) indicates that parsing is to stop immediately because an unbacktrackable syntax error has been found. Nrz r r r r r} # r{ r} c @ s$ e Zd ZdZd dd�Zd dd�Zd S ) �RecursiveGrammarExceptiona6 Exception thrown by :class:`ParserElement.validate` if the grammar could be left-recursive; parser may need to enable left recursion using :class:`ParserElement.enable_left_recursion<ParserElement.enable_left_recursion>` Deprecated: only used by deprecated method ParserElement.validate. r r c C r_ r\ ��parseElementTrace)r �parseElementListr r r r 5 ra z"RecursiveGrammarException.__init__r c C s d| j � �S )NzRecursiveGrammarException: r rN r r r re 8 s z!RecursiveGrammarException.__str__N)r r rp )r r r rq r re r r r r r~ , s r~ )!� __future__r r` �rer0 �typing� functoolsr �unicoder �ppu�utilr r r r r �Latin1�LatinA�LatinB�Greek�Cyrillicr � alphanums�_extract_alphanums�compilerT r# r ry r| r} r~ r r r r �<module> s& � l PK )��ZV�YS�� �� __pycache__/core.cpython-310.pycnu �[��� o �h� � @ s4 U d dl mZ d dlZd dlmZ d dlZd dlZd dlmZmZm Z m Z m Z m Z m Z mZ d dlmZmZ d dlmZ d dlZd dlZd dlZd dlZd dlZd dlmZ d dlZd dlZd dl m Z d d l m Z d d l m!Z! d d l"m#Z# d d l$m%Z%m&Z&m'Z'm(Z(m)Z)m*Z*m+Z,m-Z.m/Z/ d dl0T d dl1T d dl2m3Z3m4Z4 d dl5m6Z6 ej7Z8e9e:fZ;de<d< d dl m=Z= G dd� de'�Z>G dd� de'�Z?G dd� de�Z@d�d d �ZAd�d d �ZB�d d!d"�ZC['�dd(d)�ZDeDejEejF�Gd*��r�eC� eHeIeJeKeLeMeNeOePeQeRh ZSejTZUeMeVef ZWe e3e e3 f ZXe eg eYf ee3geYf eeVe3geYf ee9eVe3geYf f ZZee9eVd+e[gdf Z\ee9eVd+eYgdf Z]ee9eVeVd+e3eYgdf Z^ee9eVd+e[eYgdf Z_ej`eja Zbd,e<d-< e6jcjdZdd,e<d.< e6jcjeZed,e<d/< d0Zfd,e<d1< efd2 Zgd,e<d3< ebef Zhd,e<d4< d5�id6d7� ejjD ��Zkd,e<d8< G d9d:� d:e[�Zldamd;e<d<< d=an�dd?d@�Zo A�d�ddGdH�Zp A�d�ddNdO�Zq A�d�ddTdU�Zr A�d�ddXdY�ZsdZd[� ZtG d\d+� d+e�ZuG d]d^� d^eu�ZvG d_d`� d`eu�ZwG dadb� dbew�ZxG dcdd� ddew�ZyG dedf� dfey�ZzG dgdh� dhey�Z{eyeu_|G didj� djew�Z}G dkdl� dley�Z~G dmdn� dne}�ZG dodp� dpew�Z�G dqdr� drew�Z�G dsdt� dte��Z�G dudv� dvew�Z�G dwdx� dxew�Z�G dydz� dzew�Z�G d{d|� d|ew�Z�G d}d~� d~ew�Z�G dd�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�ew�Z�G d�d�� d�eu�Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�eu�Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d��Z�G d�d�� d�e��Z�e�Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d�� d�e��Z�G d�d d�e��Z��d d�dńZ�ez� ��dơZ�e�� ��dǡZ�e�� ��dȡZ�e�� ��dɡZ�e�� ��dʡZ�e�d˃��d�d̈́ �Z�e�d��d�d̈́ �Z�e�dЃ��d�d̈́ �Z�e�e�B e�B e�d�d dӍB Z�e�e�e�dԃ e� �Z�eydՃe�dփ��dס e�e�e�e�B ����dء eydك Z��d d�d܄Z��d d�dބZ��d d�d�Z�e�e�d�d� ���d�Z�e�e�d�d� ���d�Z�e�e�d�d� ��d�e�d�d� ��d�B ���d�Z�e�e�d�ej�d�d� ��d�e�d�ej�d�d� ��d�A e�d�d� ��d�A e�d�d� ��d�A ���d�Z�e�d�e��� ���d��Z�e�d��Z�e�d��Z�d�d7� eŃ �ơ D �Z�d�e<d�< e�Z�e�Z�e�Z�e�Z�e�Z�e�Z�e�Z�e�Z�e/d�et�Z�e/d�e��Z�e/d�ep�Z�e/d�e��Z�dS ( � )� annotationsN)�deque)�Any�Callable� Generator� NamedTuple�Sequence�TextIO�Union�cast)�ABC�abstractmethod)�Enum)�Iterable)� itemgetter)�wraps)�RLock)�Path� ) � _FifoCache�_UnboundedCache�__config_flags�_collapse_string_to_ranges�_escape_regex_range_chars�_flatten�LRUMemo� UnboundedMemo�replaced_by_pep8)�*)� ParseResults�_ParseResultsWithOffset)�pyparsing_unicodeztuple[type, ...]�str_type)�cached_propertyc @ s0 e Zd ZdZdZdZdd� e� D �Zd�� Z dS )� __compat__aJ A cross-version compatibility configuration for pyparsing features that will be released in a future version. By setting values in this configuration to True, those features can be enabled in prior versions for compatibility development and testing. - ``collect_all_And_tokens`` - flag to enable fix for Issue #63 that fixes erroneous grouping of results names when an :class:`And` expression is nested within an :class:`Or` or :class:`MatchFirst`; maintained for compatibility, but setting to ``False`` no longer restores pre-2.3.1 behavior � compatibilityTc C � g | ] }|� d �s|�qS ��_�� startswith��.0�__� r. �A/usr/local/CyberCP/lib/python3.10/site-packages/pyparsing/core.py� <listcomp>a � z__compat__.<listcomp>z( collect_all_And_tokens N) �__name__� __module__� __qualname__�__doc__� _type_desc�collect_all_And_tokens�locals� _all_names�split� _fixed_namesr. r. r. r/ r$ P s �r$ c @ sj e Zd ZdZdZdZdZdZdZdZ dZ dZ dd� e � D �Z dd� e D �Zdd� e D �Zed d d ��Zd S ) �__diag__� diagnosticFc C r& r' r) r+ r. r. r/ r0 s r1 z__diag__.<listcomp>c C � g | ] }|� d �r|�qS )�warnr) �r, �namer. r. r/ r0 t r1 c C r> )� enable_debugr) r@ r. r. r/ r0 u r1 �return�Nonec C s | j D ]}| �|� qd S �N)�_warning_names�enable)�clsrA r. r. r/ �enable_all_warningsw s �z __diag__.enable_all_warningsN�rC rD )r2 r3 r4 r6 �)warn_multiple_tokens_in_named_alternation�)warn_ungrouped_named_tokens_in_collection� warn_name_set_on_empty_Forward�!warn_on_parse_using_empty_Forward� warn_on_assignment_to_Forward�%warn_on_multiple_string_args_to_oneof�(warn_on_match_first_with_lshift_operator�!enable_debug_on_named_expressionsr8 r9 rF � _debug_names� classmethodrI r. r. r. r/ r< g s r< c @ s0 e Zd ZdZdZdZdZdZdZdZ dZ d Z d S ) � Diagnosticsa� Diagnostic configuration (all default to disabled) - ``warn_multiple_tokens_in_named_alternation`` - flag to enable warnings when a results name is defined on a :class:`MatchFirst` or :class:`Or` expression with one or more :class:`And` subexpressions - ``warn_ungrouped_named_tokens_in_collection`` - flag to enable warnings when a results name is defined on a containing expression with ungrouped subexpressions that also have results names - ``warn_name_set_on_empty_Forward`` - flag to enable warnings when a :class:`Forward` is defined with a results name, but has no contents defined - ``warn_on_parse_using_empty_Forward`` - flag to enable warnings when a :class:`Forward` is defined in a grammar but has never had an expression attached to it - ``warn_on_assignment_to_Forward`` - flag to enable warnings when a :class:`Forward` is defined but is overwritten by assigning using ``'='`` instead of ``'<<='`` or ``'<<'`` - ``warn_on_multiple_string_args_to_oneof`` - flag to enable warnings when :class:`one_of` is incorrectly called with multiple str arguments - ``enable_debug_on_named_expressions`` - flag to auto-enable debug on all subsequent calls to :class:`ParserElement.set_name` Diagnostics are enabled/disabled by calling :class:`enable_diag` and :class:`disable_diag`. All warnings can be enabled by calling :class:`enable_all_warnings`. r r � � � � � � N) r2 r3 r4 r5 rK rL rM rN rO rP rQ rR r. r. r. r/ rU } s rU � diag_enumrC rD c C � t �| j� dS )zO Enable a global pyparsing diagnostic flag (see :class:`Diagnostics`). N)r< rG rA �r\ r. r. r/ � enable_diag� � r_ c C r] )zP Disable a global pyparsing diagnostic flag (see :class:`Diagnostics`). N)r< �disablerA r^ r. r. r/ � disable_diag� r` rb c C s t �� dS )zU Enable all global pyparsing diagnostic warnings (see :class:`Diagnostics`). N)r< rI r. r. r. r/ rI � s rI �cmd_line_warn_options�typing.Iterable[str]� warn_env_var�typing.Optional[str]�boolc C sx t |�}| D ]3}|d �d�d d� \}}}}}|�� �d�s,|s%|s%|r)|dkr,d}q|�� �d�r9|dv r9d}q|S ) Nz::::�:rY �i� pyparsingT)rj � F)rg r: �lowerr* ) rc re rG �warn_opt�w_action� w_message� w_category�w_module�w_liner. r. r/ �_should_enable_warnings� s( ������rs �PYPARSINGENABLEALLWARNINGS� ParserElement�str�alphas� identchars�identbodychars� 0123456789�nums� ABCDEFabcdef�hexnums� alphanumsrk c C s g | ] }|t jvr|�qS r. )�string� whitespace�r, �cr. r. r/ r0 � r1 r0 � printablesc @ s e Zd ZdZd dd �Zd S ) �_ParseActionIndexErrorz� Internal wrapper around IndexError so that IndexErrors raised inside parse actions aren't misinterpreted as IndexErrors raised inside ParserElement parseImpl methods. �msgrv �exc� BaseExceptionrC rD c C s || _ || _d S rE )r� r� )�selfr� r� r. r. r/ �__init__� s z _ParseActionIndexError.__init__N)r� rv r� r� rC rD )r2 r3 r4 r5 r� r. r. r. r/ r� � s r� ztraceback.StackSummary�_trim_arity_call_liner. rW c s� �t v r �fdd�S d�d� d}tptjdd�d atp%td td | fa� ���fd d �}t�d t�d �j�}||_�j|_|S )zAdecorator to trim function calls to match the arity of the targetc s � |�S rE r. ��s�l�t)�funcr. r/ �<lambda> � z _trim_arity.<locals>.<lambda>r F� rV ��limit���r c s� � r �| �d � � S z �| �d � � }d� |W S t yV } z2� r#� |j}tj|dd�}|d }|d d� gd d d� tk}~|rQ��k rQ�d7 �W Y d }~q � d }~w tyi } ztd|��d ��d }~ww )Nr TrV r� r� z!IndexError raised in parse action)� TypeError� __traceback__� traceback� extract_tb�pa_call_line_synth� IndexErrorr� �with_traceback)�args�ret�te�tb�frames� frame_summary�trim_arity_type_error�ie�� found_arityr� r� � max_limitr. r/ �wrapper s< � �����z _trim_arity.<locals>.wrapperr2 � __class__)�_single_arg_builtinsr� r� � extract_stackr� �getattrr2 r5 )r� r� � LINE_DIFFr� � func_namer. r� r/ � _trim_arity s %r� F�fn�ParseCondition�message�fatal� ParseActionc s@ |dur|nd�|r t nt� t���t��� ��fdd��}|S )aC Function to convert a simple predicate function that returns ``True`` or ``False`` into a parse action. Can be used in places when a parse action is required and :class:`ParserElement.add_condition` cannot be used (such as when adding a condition to an operator level in :class:`infix_notation`). Optional keyword arguments: - ``message`` - define a custom message to be used in the raised exception - ``fatal`` - if True, will raise :class:`ParseFatalException` to stop parsing immediately; otherwise will raise :class:`ParseException` Nz failed user-defined conditionc s t �| ||��s� | |���d S rE )rg r� ��exc_typer� r� r. r/ �paU s �z%condition_as_parse_action.<locals>.pa)�ParseFatalException�ParseExceptionr� r )r� r� r� r� r. r� r/ �condition_as_parse_actionA s r� �instring�loc�int�expr� cache_hitc C s` |rdnd}t |� d|� d|� dt|| �� dt|| �� dt|| �� dd d t|| �� ��� � d S ) Nr rk �Match z at loc �(�,z) z �^�>)�print�lineno�col�line)r� r� r� r� � cache_hit_strr. r. r/ �_default_start_debug_action] s *�����r� �startloc�endloc�toksr c C s, |rdnd}t |� d|� d|�� � �� d S )Nr rk zMatched z -> )r� �as_list)r� r� r� r� r� r� r� r. r. r/ � _default_success_debug_actionj s r� r� � Exceptionc C s4 |rdnd}t |� d|� dt|�j� d|� �� d S )Nr rk r� z failed, z raised: )r� �typer2 )r� r� r� r� r� r� r. r. r/ � _default_exception_debug_actionv s (r� c G � dS )zG'Do-nothing' debug action, to suppress debugging output during parsing.Nr. )r� r. r. r/ �null_debug_action� � r� c @ st e Zd ZU dZdZded< dZded< dZd ed < e�d dd��Z e�d dd��Z e dd� �Z G dd� de �Z�d!�d"dd�Zedd� �Zejd d� �Z�d#d d �Zd!d"� Z�d$d#d$�Z �d!dd%��d%d)d*�Z�d!�d$d+d,�Z�d&�d'd/d0�Z�d(d5d6�Z�d(d7d8�Z�d)d:d;�Z�d*d>d?�Z �d+dCdD�Z �d+dEdF�Z �d&�d,dHdI�Z dJdK� Z -�d-�d.dMdN�Z!dddO��d/dRdS�Z"�d!�d0dTdU�Z#e$� Z%i Z&dVedW< G dXdY� dYe'j(�Z)G dZd[� d[e*�Z+e+� Z,dYed\< e$� Z-d]d]gZ. -�d-�d.d^d_�Z/e!Z0e�d1d`da��Z1dZ2dZ3e�d1dbdc��Z4e �d2ddd��d3dgdh��Z5e i�d4ddd��d5dldm��Z6 �d!ddn��d6drds�Z7e8dd-fde8dt��d7dzd{�Z9dd|��d8d}d~�Z:e8fde8dt��d9dd��Z;e8dfdd���d:d�d��Z<�d$d�d��Z=�d$d�d��Z>�d$d�d��Z?�d$d�d��Z@�d$d�d��ZA�d$d�d��ZB�d$d�d��ZC�d$d�d��ZD�d$d�d��ZE�d$d�d��ZF�d$d�d��ZG�d$d�d��ZH�d$d�d��ZIdZJd�d�� ZK�d2�d;d�d��ZL�d$d�d��ZM�d&�d<d�d��ZN�d&�d<d�d��ZO �d!�d=d�d��ZP�d$d�d��ZQ�d>d�d��ZR�d?d�d��ZS�d@�dAd�d��ZTe�dBd�dÄ�ZUeV�dBd�dń�ZW�d;d�dDŽZXe�dBd�dɄ�ZYeYj�d1d�dɄ�ZY�dBd�d̄ZZ�dBd�d΄Z[�d$d�dЄZ\�dCd�dӄZ]d�dՄ Z^�d2�d1d�dׄZ_ � �dDddn��dEd�d݄Z`d�d߄ Zad�d� Zb -�d&d-dn��dFd�d�Zc - � - - �dGd-d-d-ddd��dHd�d��Zd � �dI�dJ�d�d�Zeeef�de ��Zgeef�de ��Zheef�de4��Zieef�de5��Zjeef�de6��Zkeef�d e1��Zlef�d e�Zmef�d e�Znef�d e�Zoef�d e�Zpef�de�Zqef�de �Zref�de"�Zsef�de7�Ztef�de9�Zuef�de:�Zvef�de;�Zwef�deN�Zxef�deO�Zyef�deP�Zzef�deQ�Z{ef�deS�Z|ef�deT�Z}ef�deX�Z~ef�d e`�Zef�d ed�Z�ef�d e#�Z�eUZ�dS (K ru z)Abstract base level parser element class.z rv �DEFAULT_WHITE_CHARSFrg �verbose_stacktraceNr� �_literalStringClass�charsrC rD c C s$ | t _tD ] }|jrt| �|_qdS )a� Overrides the default whitespace chars Example:: # default whitespace chars are space, <TAB> and newline Word(alphas)[1, ...].parse_string("abc def\nghi jkl") # -> ['abc', 'def', 'ghi', 'jkl'] # change to just treat newline as significant ParserElement.set_default_whitespace_chars(" \t") Word(alphas)[1, ...].parse_string("abc def\nghi jkl") # -> ['abc', 'def'] N)ru r� �_builtin_exprs�copyDefaultWhiteChars�set� whiteChars)r� r� r. r. r/ � set_default_whitespace_chars� s ��z*ParserElement.set_default_whitespace_charsrH c C � | t _dS )al Set class to be used for inclusion of string literals into a parser. Example:: # default literal class used is Literal integer = Word(nums) date_str = integer("year") + '/' + integer("month") + '/' + integer("day") date_str.parse_string("1999/12/31") # -> ['1999', '/', '12', '/', '31'] # change to Suppress ParserElement.inline_literals_using(Suppress) date_str = integer("year") + '/' + integer("month") + '/' + integer("day") date_str.parse_string("1999/12/31") # -> ['1999', '12', '31'] N)ru r� )rH r. r. r/ �inline_literals_using� s z#ParserElement.inline_literals_usingc + s � � �fdd�|D �E dH dS )z� Yields a sequence of ``class(obj, **class_kwargs)`` for obj in seq. Example:: LPAR, RPAR, LBRACE, RBRACE, SEMI = Suppress.using_each("(){};") c 3 s � | ] }�|fi � ��V qd S rE r. )r, �obj�� class_kwargsrH r. r/ � <genexpr>� � � z+ParserElement.using_each.<locals>.<genexpr>Nr. )rH �seqr� r. r� r/ � using_each� s � zParserElement.using_eachc @ s& e Zd ZU ded< ded< ded< dS )zParserElement.DebugActionsz!typing.Optional[DebugStartAction]� debug_tryz#typing.Optional[DebugSuccessAction]� debug_matchz%typing.Optional[DebugExceptionAction]� debug_failN)r2 r3 r4 �__annotations__r. r. r. r/ � DebugActions� s r� �savelistc C s� t � | _d | _d | _d | _d | _|| _d| _tt j �| _ d| _ d| _ d| _t � | _d| _d| _d| _d| _d| _| �d d d �| _d| _d| _g | _d| _d S )NTFrk )�list� parseAction� failAction� customName� _defaultName� resultsName� saveAsList�skipWhitespacer� ru r� r� r� �_may_return_empty�keepTabs� ignoreExprs�debug� streamlined� mayIndexError�errmsg� modalResultsr� � debugActions� callPreparse� callDuringTry�suppress_warnings_�show_in_diagram)r� r� r. r. r/ r� � s, zParserElement.__init__c C � | j S rE �r� �r� r. r. r/ �mayReturnEmpty� s z ParserElement.mayReturnEmptyc C � || _ d S rE r �r� �valuer. r. r/ r � � � warning_typerU c C s | j �|� | S )aZ Suppress warnings emitted for a particular diagnostic on this expression. Example:: base = pp.Forward() base.suppress_warning(Diagnostics.warn_on_parse_using_empty_Forward) # statement would normally raise a warning, but is now suppressed print(base.parse_string("x")) )r �append)r� r r. r. r/ �suppress_warning� s z ParserElement.suppress_warningc c sR � t | g�}t� }|r'|�� }||v rq |�|� |�|�� � |V |s dS dS )z�General-purpose method to yield all expressions and sub-expressions in a grammar. Typically just for internal use. N)r r� �popleft�add�extend�recurse)r� �to_visit�seen�curr. r. r/ � visit_all� s � �zParserElement.visit_allc C s@ t � | �}| jdd� |_| jdd� |_| jr ttj�|_|S )a7 Make a copy of this :class:`ParserElement`. Useful for defining different parse actions for the same parsing pattern, using copies of the original parse element. Example:: integer = Word(nums).set_parse_action(lambda toks: int(toks[0])) integerK = integer.copy().add_parse_action(lambda toks: toks[0] * 1024) + Suppress("K") integerM = integer.copy().add_parse_action(lambda toks: toks[0] * 1024 * 1024) + Suppress("M") print((integerK | integerM | integer)[1, ...].parse_string("5K 100 640K 256M")) prints:: [5120, 100, 655360, 268435456] Equivalent form of ``expr.copy()`` is just ``expr()``:: integerM = integer().add_parse_action(lambda toks: toks[0] * 1024 * 1024) + Suppress("M") N)�copyr� r� r� r� ru r� r� )r� �cpyr. r. r/ r s zParserElement.copy)�listAllMatchesrA �list_all_matchesr c C s |p|}| � ||�S )a� Define name for referencing matching tokens as a nested attribute of the returned parse results. Normally, results names are assigned as you would assign keys in a dict: any existing value is overwritten by later values. If it is necessary to keep all values captured for a particular results name, call ``set_results_name`` with ``list_all_matches`` = True. NOTE: ``set_results_name`` returns a *copy* of the original :class:`ParserElement` object; this is so that the client can define a basic element, such as an integer, and reference it in multiple places with different names. You can also set results names using the abbreviated syntax, ``expr("name")`` in place of ``expr.set_results_name("name")`` - see :class:`__call__`. If ``list_all_matches`` is required, use ``expr("name*")``. Example:: integer = Word(nums) date_str = (integer.set_results_name("year") + '/' + integer.set_results_name("month") + '/' + integer.set_results_name("day")) # equivalent form: date_str = integer("year") + '/' + integer("month") + '/' + integer("day") )�_setResultsName)r� rA r r r. r. r/ �set_results_name+ s z ParserElement.set_results_namec C s@ |d u r| S | � � }|�d�r|d d� }d}||_| |_|S )Nr r� T)r �endswithr� r� )r� rA r �newselfr. r. r/ r M s z ParserElement._setResultsNameT� break_flagc sB |r| j � d� fdd� }� |_|| _ | S t| j d�r | j j| _ | S )z� Method to invoke the Python pdb debugger when this element is about to be parsed. Set ``break_flag`` to ``True`` to enable, ``False`` to disable. Tc s t � � | |||�S rE )� breakpoint)r� r� � do_actions� callPreParse�� _parseMethodr. r/ �breakera s z(ParserElement.set_break.<locals>.breaker�_originalParseMethodN�TT)�_parser% �hasattr)r� r r$ r. r" r/ � set_breakX s � zParserElement.set_break�fnsr� �kwargsr c O sh t |�dgkr| j�� | S tdd� |D ��std��dd� |D �| jdd�< |�d|�dd ��| _| S ) a� Define one or more actions to perform when successfully matching parse element definition. Parse actions can be called to perform data conversions, do extra validation, update external data structures, or enhance or replace the parsed tokens. Each parse action ``fn`` is a callable method with 0-3 arguments, called as ``fn(s, loc, toks)`` , ``fn(loc, toks)`` , ``fn(toks)`` , or just ``fn()`` , where: - ``s`` = the original string being parsed (see note below) - ``loc`` = the location of the matching substring - ``toks`` = a list of the matched tokens, packaged as a :class:`ParseResults` object The parsed tokens are passed to the parse action as ParseResults. They can be modified in place using list-style append, extend, and pop operations to update the parsed list elements; and with dictionary-style item set and del operations to add, update, or remove any named results. If the tokens are modified in place, it is not necessary to return them with a return statement. Parse actions can also completely replace the given tokens, with another ``ParseResults`` object, or with some entirely different object (common for parse actions that perform data conversions). A convenient way to build a new parse result is to define the values using a dict, and then create the return value using :class:`ParseResults.from_dict`. If None is passed as the ``fn`` parse action, all previously added parse actions for this expression are cleared. Optional keyword arguments: - ``call_during_try`` = (default= ``False``) indicate if parse action should be run during lookaheads and alternate testing. For parse actions that have side effects, it is important to only call the parse action once it is determined that it is being called as part of a successful parse. For parse actions that perform additional validation, then call_during_try should be passed as True, so that the validation code is included in the preliminary "try" parses. Note: the default parsing behavior is to expand tabs in the input string before starting the parsing process. See :class:`parse_string` for more information on parsing strings containing ``<TAB>`` s, and suggested methods to maintain a consistent view of the parsed string, the parse location, and line and column positions within the parsed string. Example:: # parse dates in the form YYYY/MM/DD # use parse action to convert toks from str to int at parse time def convert_to_int(toks): return int(toks[0]) # use a parse action to verify that the date is a valid date def is_valid_date(instring, loc, toks): from datetime import date year, month, day = toks[::2] try: date(year, month, day) except ValueError: raise ParseException(instring, loc, "invalid date given") integer = Word(nums) date_str = integer + '/' + integer + '/' + integer # add parse actions integer.set_parse_action(convert_to_int) date_str.set_parse_action(is_valid_date) # note that integer fields are now ints, not strings date_str.run_tests(''' # successful parse - note that integer fields were converted to ints 1999/12/31 # fail - invalid date 1999/13/31 ''') Nc s � � | ]}t |�V qd S rE )�callable�r, r� r. r. r/ r� � � � z1ParserElement.set_parse_action.<locals>.<genexpr>z parse actions must be callablec S � g | ]}t |��qS r. �r� r. r. r. r/ r0 � � z2ParserElement.set_parse_action.<locals>.<listcomp>�call_during_tryr F)r� r� �clear�allr� �getr �r� r* r+ r. r. r/ �set_parse_actionl s K �z ParserElement.set_parse_actionc O s8 | j dd� |D �7 _ | jp|�d|�dd��| _| S )z� Add one or more parse actions to expression's list of parse actions. See :class:`set_parse_action`. See examples in :class:`copy`. c S r0 r. r1 r. r. r. r/ r0 � r2 z2ParserElement.add_parse_action.<locals>.<listcomp>r3 r F)r� r r6 r7 r. r. r/ �add_parse_action� s �z ParserElement.add_parse_actionr� c O sV |D ]}| j �t|t|�d��t|�dd��d�� q| jp'|�d|�dd��| _| S )a� Add a boolean predicate function to expression's list of parse actions. See :class:`set_parse_action` for function call signatures. Unlike ``set_parse_action``, functions passed to ``add_condition`` need to return boolean success/fail of the condition. Optional keyword arguments: - ``message`` = define a custom message to be used in the raised exception - ``fatal`` = if True, will raise ParseFatalException to stop parsing immediately; otherwise will raise ParseException - ``call_during_try`` = boolean to indicate if this method should be called during internal tryParse calls, default=False Example:: integer = Word(nums).set_parse_action(lambda toks: int(toks[0])) year_int = integer.copy() year_int.add_condition(lambda toks: toks[0] >= 2000, message="Only support years 2000 and later") date_str = year_int + '/' + integer + '/' + integer result = date_str.parse_string("1999/12/31") # -> Exception: Only support years 2000 and later (at char 0), (line:1, col:1) r� r� F)r� r� r3 r )r� r r� rv r6 rg r )r� r* r+ r� r. r. r/ � add_condition� s �� �zParserElement.add_conditionr� �ParseFailActionc C s || _ | S )a Define action to perform if parsing fails at this expression. Fail acton fn is a callable function that takes the arguments ``fn(s, loc, expr, err)`` where: - ``s`` = string being parsed - ``loc`` = location where expression match was attempted and failed - ``expr`` = the parse expression that failed - ``err`` = the exception thrown The function returns no value. It may throw :class:`ParseFatalException` if it is desired to stop parsing immediately.)r� )r� r� r. r. r/ �set_fail_action� s z ParserElement.set_fail_actionr� r� r� c C sv | j s|S d}dd� | j D �}|}|r9d}|D ]}z |||�\}}d}q ty- Y qw ||kr5 |S |}|s|S )NTc S s g | ]}|j �qS r. )r' �r, �er. r. r/ r0 s z1ParserElement._skipIgnorables.<locals>.<listcomp>F)r� r� )r� r� r� � exprsFound�ignore_expr_fns�last_loc� ignore_fn�dummyr. r. r/ �_skipIgnorables s, � ��� z ParserElement._skipIgnorablesc C sZ | j r | �||�}| jr+t|�}| j}||k r+|| |v r+|d7 }||k r+|| |v s |S �Nr )r� rD r� �lenr� )r� r� r� �instrlen� white_charsr. r. r/ �preParse s �zParserElement.preParse�ParseImplReturnTypec C � |g fS rE r. �r� r� r� r r. r. r/ � parseImpl& � zParserElement.parseImplc C s |S rE r. �r� r� r� � tokenlistr. r. r/ � postParse) � zParserElement.postParse�tuple[int, ParseResults]c C s | j }t|�}|s | jr}zJ|r| jr| �||�}n|}|}| jjr*| j�||| d� | js1||krLz | �|||�\}} W n t yK t ||| j | ��w | �|||�\}} W na t y| } z| jj rl| j� ||| | d� | jrw| �||| | � � d } ~ ww |r�| jr�| �||�}n|}|}| js�||kr�z | �|||�\}} W n t y� t ||| j | ��w | �|||�\}} | �||| �} t| | j| j| jd�} | j�rw|s�| j�rw|�r6zA| jD ];} z| ||| �} W n t y� } zt d�}|| �d } ~ ww | d u�r| | u�rt| | j| j�ot| ttf�| jd�} q�W n^ t �y5 } z| jj �r0| j� ||| | d� � d } ~ ww | jD ]=} z| ||| �} W n t �yW } zt d�}|| �d } ~ ww | d u�ru| | u�rut| | j| j�opt| ttf�| jd�} �q9|�r�| jj�r�| j�|||| | d� || fS )NF)�asList�modalz exception raised in parse action)r� rF r� r� rI r� r� r� rM r� r� r� r� r� rQ r r� r� r� r� r � isinstancer� r� )r� r� r� r r! � debugging� len_instring�pre_loc� tokens_start�tokens�err� ret_tokensr� �parse_action_excr� r. r. r/ � _parseNoCache- s� �� ��� �� �� ��� ��� �� �� �zParserElement._parseNoCache)� raise_fatalr r` r c C s< z | j |||d�d W S ty |r� t||| j| ��w )N�r r )r' r� r� r� )r� r� r� r` r r. r. r/ � try_parse� s �zParserElement.try_parsec C s0 z | j |||d� W dS ttfy Y dS w )Nra FT)rb r� r� rL r. r. r/ �can_parse_next� s ��z ParserElement.can_parse_nextzecollections.abc.MutableMapping[tuple[int, Forward, bool], tuple[int, Union[ParseResults, Exception]]]�recursion_memosc @ s8 e Zd ZU dZded< ddd�Zdd d �Zdd d �Zd S )zParserElement._CacheTypezm Class to be used for packrat and left-recursion cacheing of results and exceptions. rg � not_in_cacherC � typing.Anyc G � d S rE r. �r� r� r. r. r/ r6 � r� z ParserElement._CacheType.getrD c G rg rE r. rh r. r. r/ r� � r� z ParserElement._CacheType.setc C rg rE r. r r. r. r/ r4 � r� z ParserElement._CacheType.clearN�rC rf rJ )r2 r3 r4 r5 r� r6 r� r4 r. r. r. r/ � _CacheType� s rj c @ s< e Zd ZU dZdZded< ddd�Zdd d �Zdd d �ZdS )zParserElement.NullCachez� A null cache type for initialization of the packrat_cache class variable. If/when enable_packrat() is called, this null cache will be replaced by a proper _CacheType class instance. Trg re rC rf c G rg rE r. rh r. r. r/ r6 � r� zParserElement.NullCache.getrD c G rg rE r. rh r. r. r/ r� � r� zParserElement.NullCache.setc C rg rE r. r r. r. r/ r4 � r� z ParserElement.NullCache.clearNri rJ ) r2 r3 r4 r5 re r� r6 r� r4 r. r. r. r/ � NullCache� s rk � packrat_cacher c C s� d\}}| ||||f}t j�� t j}|�|�} | |ju r_t j| d7 < z | �||||�} W n tyF } z |�|| j | j � � � d } ~ ww |�|| d | d � � |f� | W d � S t j| d7 < | j r�| j jr�z | j j||| dd� W n ty� Y nw t| t�r�| j r�| j jr�z| j j||| | dd� W | � ty� Y | �w | �tttttf | �} | d | d � � | d } } } | j r�| j jr�z| j j|| | | | dd� W n ty� Y nw | | fW d � S 1 s�w Y d S )N)r r r r T)r� rV )ru �packrat_cache_lockrl r6 re �packrat_cache_statsr_ �ParseBaseExceptionr� r� r� r r� r� r� r� rV r� r� r �tupler� r r� )r� r� r� r r! �HIT�MISS�lookup�cacher �pe�loc_�resultr� r. r. r/ � _parseCache� s` �� � � � �� � �$�zParserElement._parseCachec C s2 t j�� dgtt j� t jd d �< t j�� d S �Nr )ru rl r4 rF rn rd r. r. r. r/ � reset_cache s �zParserElement.reset_cachec C s t �� dt _dt _t jt _dS )a$ Disables active Packrat or Left Recursion parsing and their memoization This method also works if neither Packrat nor Left Recursion are enabled. This makes it safe to call before activating Packrat nor Left Recursion to clear any previous settings. FN)ru rz �_left_recursion_enabled�_packratEnabledr_ r' r. r. r. r/ �disable_memoization s z!ParserElement.disable_memoization)�force�cache_size_limit�typing.Optional[int]c C s\ |rt �� nt jrtd��| du rt� t _n| dkr"t| d�t _ntd| � ���dt _dS )a' Enables "bounded recursion" parsing, which allows for both direct and indirect left-recursion. During parsing, left-recursive :class:`Forward` elements are repeatedly matched with a fixed recursion depth that is gradually increased until finding the longest match. Example:: import pyparsing as pp pp.ParserElement.enable_left_recursion() E = pp.Forward("E") num = pp.Word(pp.nums) # match `num`, or `num '+' num`, or `num '+' num '+' num`, ... E <<= E + '+' - num | num print(E.parse_string("1+2+3")) Recursion search naturally memoizes matches of ``Forward`` elements and may thus skip reevaluation of parse actions during backtracking. This may break programs with parse actions which rely on strict ordering of side-effects. Parameters: - ``cache_size_limit`` - (default=``None``) - memoize at most this many ``Forward`` elements during matching; if ``None`` (the default), memoize all ``Forward`` elements. Bounded Recursion parsing works similar but not identical to Packrat parsing, thus the two cannot be used together. Use ``force=True`` to disable any previous, conflicting settings. �0Packrat and Bounded Recursion are not compatibleNr )�capacityz Memo size of T) ru r} r| � RuntimeError�_UnboundedMemord �_LRUMemo�NotImplementedErrorr{ �r r~ r. r. r/ �enable_left_recursion s $ z#ParserElement.enable_left_recursion� �Union[int, None]r~ c C sT |rt �� nt jrtd��t jrdS dt _| du r t� t _nt| �t _t jt _ dS )aj Enables "packrat" parsing, which adds memoizing to the parsing logic. Repeated parse attempts at the same string location (which happens often in many complex grammars) can immediately return a cached value, instead of re-executing parsing/validating code. Memoizing is done of both valid results and parsing exceptions. Parameters: - ``cache_size_limit`` - (default= ``128``) - if an integer value is provided will limit the size of the packrat cache; if None is passed, then the cache size will be unbounded; if 0 is passed, the cache will be effectively disabled. This speedup may break existing programs that use parse actions that have side-effects. For this reason, packrat parsing is disabled when you first import pyparsing. To activate the packrat feature, your program must call the class method :class:`ParserElement.enable_packrat`. For best results, call ``enable_packrat()`` immediately after importing pyparsing. Example:: import pyparsing pyparsing.ParserElement.enable_packrat() Packrat parsing works similar but not identical to Bounded Recursion parsing, thus the two cannot be used together. Use ``force=True`` to disable any previous, conflicting settings. r� NT) ru r} r{ r� r| r rl r rx r' r� r. r. r/ �enable_packratO s " z ParserElement.enable_packrat)�parseAll� parse_allr� r c C s� |p|}t �� | js| �� | jD ]}|�� q| js |�� }z%| �|d�\}}|rC| �||�}t � t � � d� }|�||� W |S W |S t yT } z|j �d}~w tyh } z t jr_� | �d��d} ~ ww )a8 Parse a string with respect to the parser definition. This function is intended as the primary interface to the client code. :param instring: The input string to be parsed. :param parse_all: If set, the entire input string must match the grammar. :param parseAll: retained for pre-PEP8 compatibility, will be removed in a future release. :raises ParseException: Raised if ``parse_all`` is set and the input string does not match the whole grammar. :returns: the parsed data as a :class:`ParseResults` object, which may be accessed as a `list`, a `dict`, or an object with attributes if the given parser includes results names. If the input string is required to match the entire grammar, ``parse_all`` flag must be set to ``True``. This is also equivalent to ending the grammar with :class:`StringEnd`\ (). To report proper column numbers, ``parse_string`` operates on a copy of the input string where all tabs are converted to spaces (8 spaces per tab, as per the default in ``string.expandtabs``). If the input string contains tabs and the grammar uses parse actions that use the ``loc`` argument to index into the string being parsed, one can ensure a consistent view of the input string by doing one of the following: - calling ``parse_with_tabs`` on your grammar before calling ``parse_string`` (see :class:`parse_with_tabs`), - define your parse action using the full ``(s,loc,toks)`` signature, and reference the input string using the parse action's ``s`` argument, or - explicitly expand the tabs in your input string before calling ``parse_string``. Examples: By default, partial matches are OK. >>> res = Word('a').parse_string('aaaaabaaa') >>> print(res) ['aaaaa'] The parsing behavior varies by the inheriting class of this abstract class. Please refer to the children directly to see more examples. It raises an exception if parse_all flag is set and instring does not match the whole grammar. >>> res = Word('a').parse_string('aaaaabaaa', parse_all=True) Traceback (most recent call last): ... pyparsing.ParseException: Expected end of text, found 'b' (at char 5), (line:1, col:6) r FN)ru rz r� � streamliner� r� � expandtabsr' rI �Empty� StringEnd� set_debugr� r� ro r� r� ) r� r� r� r� r> r� r[ �se�pa_excr� r. r. r/ � parse_string� s4 - � �� ��zParserElement.parse_string)r� � maxMatches� max_matches�overlapr� r� �4Generator[tuple[ParseResults, int, int], None, None]c c s� � t ||�}| js | �� | jD ]}|�� q| js t|��� }t|�}d} |r7t� } | j| _| j | _ | j } n| j } | j } t � � d} zn| |kr�| |k r�z| || �}| ||dd�\}}W n tyi |d } Y n5w || kr�| d7 } |r~t|�� ||d�� |||fV |r�| || �}|| kr�|} n | d7 } n|} n|d } | |kr�| |k sLW dS W dS W dS W dS ty� } z t jr�� |�d��d}~ww )at Scan the input string for expression matches. Each match will return the matching tokens, start location, and end location. May be called with optional ``max_matches`` argument, to clip scanning after 'n' matches are found. If ``overlap`` is specified, then overlapping matches will be reported. Note that the start and end locations are reported relative to the string being parsed. See :class:`parse_string` for more information on parsing strings with embedded tabs. Example:: source = "sldjf123lsdjjkf345sldkjf879lkjsfd987" print(source) for tokens, start, end in Word(alphas).scan_string(source): print(' '*start + '^'*(end-start)) print(' '*start + tokens[0]) prints:: sldjf123lsdjjkf345sldkjf879lkjsfd987 ^^^^^ sldjf ^^^^^^^ lsdjjkf ^^^^^^ sldkjf ^^^^^^ lkjsfd r F�r! r )r[ �start�endN)�minr� r� r� r� rv r� rF r� r� rI r' ru � resetCacher� r� rT ro r� r� )r� r� r� r� �always_skip_whitespacer� r� r> rG r� � preparser� preparseFn�parseFn�matches�preloc�nextLocr[ �nextlocr� r. r. r/ � scan_string� sf � ( ��� (� ��zParserElement.scan_string�r� c C s� g }d}d| _ z]| j||d�D ]8\}}}||kr!|�|||� � |}|s&qt|t�r2||�� 7 }qt|t�rBt|t�sB|�|� q|�|� q|�||d� � dd� |D �}d� dd� t |�D ��W S t yy } z t j rp� |�d��d}~ww ) ab Extension to :class:`scan_string`, to modify matching text with modified tokens that may be returned from a parse action. To use ``transform_string``, define a grammar and attach a parse action to it that modifies the returned token list. Invoking ``transform_string()`` on a target string will then scan for matches, and replace the matched text patterns according to the logic in the parse action. ``transform_string()`` returns the resulting transformed string. Example:: wd = Word(alphas) wd.set_parse_action(lambda toks: toks[0].title()) print(wd.transform_string("now is the winter of our discontent made glorious summer by this sun of york.")) prints:: Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York. r Tr� Nc S s g | ]}|r|�qS r. r. �r, �or. r. r/ r0 S r2 z2ParserElement.transform_string.<locals>.<listcomp>rk c S r0 r. �rv )r, r� r. r. r/ r0 T r2 )r� r� r rV r r� r r" r �joinr ro ru r� r� ) r� r� r� �out�lastEr� r� r> r� r. r. r/ �transform_string) s0 ��z ParserElement.transform_stringc C sX t ||�}ztdd� | j||d|d�D ��W S ty+ } z tjr"� |�d��d}~ww )a� Another extension to :class:`scan_string`, simplifying the access to the tokens found to match the given parse expression. May be called with optional ``max_matches`` argument, to clip searching after 'n' matches are found. Example:: # a capitalized word starts with an uppercase letter, followed by zero or more lowercase letters cap_word = Word(alphas.upper(), alphas.lower()) print(cap_word.search_string("More than Iron, more than Lead, more than Gold I need Electricity")) # the sum() builtin can be used to merge results into a single ParseResults object print(sum(cap_word.search_string("More than Iron, more than Lead, more than Gold I need Electricity"))) prints:: [['More'], ['Iron'], ['Lead'], ['Gold'], ['I'], ['Electricity']] ['More', 'Iron', 'Lead', 'Gold', 'I', 'Electricity'] c S s g | ]\}}}|�qS r. r. )r, r� r� r> r. r. r/ r0 { s ��z/ParserElement.search_string.<locals>.<listcomp>F)r� r� N)r� r r� ro ru r� r� )r� r� r� r� r� r� r. r. r/ � search_string\ s ��� ��zParserElement.search_string)�includeSeparators�maxsplit�include_separators�Generator[str, None, None]c c sZ � |p|}d}| j ||d�D ]\}}}|||� V |r!|d V |}q||d� V dS )aT Generator method to split a string using the given expression as a separator. May be called with optional ``maxsplit`` argument, to limit the number of splits; and the optional ``include_separators`` argument (default= ``False``), if the separating matching text should be included in the split results. Example:: punc = one_of(list(".,;:/-!?")) print(list(punc.split("This, this?, this sentence, is badly punctuated!"))) prints:: ['This', ' this', '', ' this sentence', ' is badly punctuated', ''] r )r� N)r� ) r� r� r� r� r� �lastr� r� r> r. r. r/ r: � s � zParserElement.splitc C s> |t u rt| �S t|t�r| �|�}t|t�stS t| |g�S )al Implementation of ``+`` operator - returns :class:`And`. Adding strings to a :class:`ParserElement` converts them to :class:`Literal`\ s by default. Example:: greet = Word(alphas) + "," + Word(alphas) + "!" hello = "Hello, World!" print(hello, "->", greet.parse_string(hello)) prints:: Hello, World! -> ['Hello', ',', 'World', '!'] ``...`` may be used as a parse expression as a short form of :class:`SkipTo`:: Literal('start') + ... + Literal('end') is equivalent to:: Literal('start') + SkipTo('end')("_skipped*") + Literal('end') Note that the skipped text is returned with '_skipped' as a results name, and to support having multiple skips in the same parser, the value returned is a list of all skipped text. )�Ellipsis� _PendingSkiprV r" r� ru �NotImplemented�And�r� �otherr. r. r/ �__add__� s zParserElement.__add__c C sB |t u r t| �d�| S t|t�r| �|�}t|t�s tS || S )zd Implementation of ``+`` operator when left operand is not a :class:`ParserElement` � _skipped*)r� �SkipTorV r" r� ru r� r� r. r. r/ �__radd__� s zParserElement.__radd__c C s2 t |t�r | �|�}t |t�stS | t�� | S )zX Implementation of ``-`` operator, returns :class:`And` with error stop )rV r" r� ru r� r� � _ErrorStopr� r. r. r/ �__sub__� s zParserElement.__sub__c C s* t |t�r | �|�}t |t�stS || S )zd Implementation of ``-`` operator when left operand is not a :class:`ParserElement` �rV r" r� ru r� r� r. r. r/ �__rsub__� � zParserElement.__rsub__c s� |t u rd}n t|t�r#|dd� t fkr#d|dd� d dd� }t|ttf�s,tS t|t�r7|d}}natdd � |D ��}|d dd� }|d du rTd|d f}t|d t�r|d du r|d dkrkt��S |d dkrut��S �|d t�� S t|d t�r�t|d t�r�|\}}||8 }ntS |dk r�td ��|dk r�td ��|| kr�dkr�tg �S |r� �fd d�� |r�|dkr͈� |� }|S t�g| �� |� }|S � |�}|S |dkr�}|S t�g| �}|S )a� Implementation of ``*`` operator, allows use of ``expr * 3`` in place of ``expr + expr + expr``. Expressions may also be multiplied by a 2-integer tuple, similar to ``{min, max}`` multipliers in regular expressions. Tuples may also include ``None`` as in: - ``expr*(n, None)`` or ``expr*(n, )`` is equivalent to ``expr*n + ZeroOrMore(expr)`` (read as "at least n instances of ``expr``") - ``expr*(None, n)`` is equivalent to ``expr*(0, n)`` (read as "0 to n instances of ``expr``") - ``expr*(None, None)`` is equivalent to ``ZeroOrMore(expr)`` - ``expr*(1, None)`` is equivalent to ``OneOrMore(expr)`` Note that ``expr*(None, n)`` does not raise an exception if more than n exprs exist in the input stream; that is, ``expr*(None, n)`` does not enforce a maximum number of expr occurrences. If this behavior is desired, then write ``expr*(None, n) + ~expr`` )r NNr �r rE rV r c s s � | ] }|t ur |nd V qd S rE )r� r� r. r. r/ r� r� z(ParserElement.__mul__.<locals>.<genexpr>)NNz/cannot multiply ParserElement by negative valuez@second tuple value must be greater or equal to first tuple valuec s$ | dkrt �� | d � �S t ��S rE )�Opt)�n��makeOptionalListr� r. r/ r� * s z/ParserElement.__mul__.<locals>.makeOptionalList) r� rV rp r� r� � ZeroOrMore� OneOrMore� ValueErrorr� )r� r� � minElements� optElementsr� r. r� r/ �__mul__� s\ �� ����zParserElement.__mul__c C s | � |�S rE )r� r� r. r. r/ �__rmul__> � zParserElement.__rmul__c C sR |t u r t| dd�S t|t�r |dkrt| �S | �|�}t|t�s#tS t| |g�S )zP Implementation of ``|`` operator - returns :class:`MatchFirst` T)� must_skiprk ) r� r� rV r" r� r� ru r� � MatchFirstr� r. r. r/ �__or__A s zParserElement.__or__c C s* t |t�r | �|�}t |t�stS || B S )zd Implementation of ``|`` operator when left operand is not a :class:`ParserElement` r� r� r. r. r/ �__ror__Q r� zParserElement.__ror__c C �. t |t�r | �|�}t |t�stS t| |g�S )zH Implementation of ``^`` operator - returns :class:`Or` )rV r" r� ru r� �Orr� r. r. r/ �__xor__[ � zParserElement.__xor__c C s* t |t�r | �|�}t |t�stS || A S )zd Implementation of ``^`` operator when left operand is not a :class:`ParserElement` r� r� r. r. r/ �__rxor__e r� zParserElement.__rxor__c C r� )zJ Implementation of ``&`` operator - returns :class:`Each` )rV r" r� ru r� �Eachr� r. r. r/ �__and__o r� zParserElement.__and__c C s* t |t�r | �|�}t |t�stS || @ S )zd Implementation of ``&`` operator when left operand is not a :class:`ParserElement` r� r� r. r. r/ �__rand__y r� zParserElement.__rand__c C � t | �S )zL Implementation of ``~`` operator - returns :class:`NotAny` )�NotAnyr r. r. r/ � __invert__� s zParserElement.__invert__c C s d}t � }t|t�r|j|j}}|du rd}d}n t|t�r7t|d t�r7|d |d jf|d j}}d}t|t�r?|f}zt|� W n tyR ||f}Y nw t |�dkrutd |dd � � t |�d krod t |�� d �nd � d���| t|dd� � }t � t |�}|r�|� |� |S )a� use ``[]`` indexing notation as a short form for expression repetition: - ``expr[n]`` is equivalent to ``expr*n`` - ``expr[m, n]`` is equivalent to ``expr*(m, n)`` - ``expr[n, ...]`` or ``expr[n,]`` is equivalent to ``expr*n + ZeroOrMore(expr)`` (read as "at least n instances of ``expr``") - ``expr[..., n]`` is equivalent to ``expr*(0, n)`` (read as "0 to n instances of ``expr``") - ``expr[...]`` and ``expr[0, ...]`` are equivalent to ``ZeroOrMore(expr)`` - ``expr[1, ...]`` is equivalent to ``OneOrMore(expr)`` ``None`` may be used in place of ``...``. Note that ``expr[..., n]`` and ``expr[m, n]`` do not raise an exception if more than ``n`` ``expr``\ s exist in the input stream. If this behavior is desired, then write ``expr[..., n] + ~expr``. For repetition with a stop_on expression, use slice notation: - ``expr[...: end_expr]`` and ``expr[0, ...: end_expr]`` are equivalent to ``ZeroOrMore(expr, stop_on=end_expr)`` - ``expr[1, ...: end_expr]`` is equivalent to ``OneOrMore(expr, stop_on=end_expr)`` FN.Tr� r r rV z'only 1 or 2 index arguments supported (rY z... [�]rk �))�NoMatchrV �slicer� �stoprp r" �iterr� rF �typingr �_MultipleMatch�stopOn)r� �key�stop_on_defined�stop_onr� r. r. r/ � __getitem__� s4 � 2� zParserElement.__getitem__rf c C s |dur | � |�S | �� S )a Shortcut for :class:`set_results_name`, with ``list_all_matches=False``. If ``name`` is given with a trailing ``'*'`` character, then ``list_all_matches`` will be passed as ``True``. If ``name`` is omitted, same as calling :class:`copy`. Example:: # these are equivalent userdata = Word(alphas).set_results_name("name") + Word(nums + "-").set_results_name("socsecno") userdata = Word(alphas)("name") + Word(nums + "-")("socsecno") N)r r �r� rA r. r. r/ �__call__� s zParserElement.__call__c C r� )z� Suppresses the output of this :class:`ParserElement`; useful to keep punctuation from cluttering up returned output. )�Suppressr r. r. r/ �suppress� s zParserElement.suppress� recursivec C � d| _ | S )z� Enables the skipping of whitespace before matching the characters in the :class:`ParserElement`'s defined pattern. :param recursive: If ``True`` (the default), also enable whitespace skipping in child elements (if any) T�r� �r� r� r. r. r/ �ignore_whitespace� s z ParserElement.ignore_whitespacec C r� )a| Disables the skipping of whitespace before matching the characters in the :class:`ParserElement`'s defined pattern. This is normally only used internally by the pyparsing module, but may be needed in some whitespace-sensitive grammars. :param recursive: If true (the default), also disable whitespace skipping in child elements (if any) Fr� r� r. r. r/ �leave_whitespace� s z ParserElement.leave_whitespace�Union[set[str], str]� copy_defaultsc C s d| _ t|�| _|| _| S )z8 Overrides the default whitespace chars T)r� r� r� r� )r� r� r� r. r. r/ �set_whitespace_chars� s z"ParserElement.set_whitespace_charsc C r� )z� Overrides default behavior to expand ``<TAB>`` s to spaces before parsing the input string. Must be called before ``parse_string`` when the input grammar contains elements that match ``<TAB>`` characters. T)r� r r. r. r/ �parse_with_tabs s z ParserElement.parse_with_tabsr� c C sN t |t�r t|�}t |t�r|| jvr| j�|� | S | j�t|�� �� | S )a� Define expression to be ignored (e.g., comments) while doing pattern matching; may be called repeatedly, to define multiple comment or other ignorable patterns. Example:: patt = Word(alphas)[...] patt.parse_string('ablaj /* comment */ lskjd') # -> ['ablaj'] patt.ignore(c_style_comment) patt.parse_string('ablaj /* comment */ lskjd') # -> ['ablaj', 'lskjd'] )rV r" r� r� r r r� r. r. r/ �ignore s �zParserElement.ignore� start_action�DebugStartAction�success_action�DebugSuccessAction�exception_action�DebugExceptionActionc C s& | � |pt|pt|p t�| _d| _| S )a Customize display of debugging messages while doing pattern matching: - ``start_action`` - method to be called when an expression is about to be parsed; should have the signature ``fn(input_string: str, location: int, expression: ParserElement, cache_hit: bool)`` - ``success_action`` - method to be called when an expression has successfully parsed; should have the signature ``fn(input_string: str, start_location: int, end_location: int, expression: ParserELement, parsed_tokens: ParseResults, cache_hit: bool)`` - ``exception_action`` - method to be called when expression fails to parse; should have the signature ``fn(input_string: str, location: int, expression: ParserElement, exception: Exception, cache_hit: bool)`` T)r� r� r� r� r� r� )r� r� r� r r. r. r/ �set_debug_actions' s �z ParserElement.set_debug_actions�flagr c C sD |r| � � D ] }|j|dd� q| S |r | �ttt� | S d| _| S )a Enable display of debugging messages while doing pattern matching. Set ``flag`` to ``True`` to enable, ``False`` to disable. Set ``recurse`` to ``True`` to set the debug flag on this expression and all sub-expressions. Example:: wd = Word(alphas).set_name("alphaword") integer = Word(nums).set_name("numword") term = wd | integer # turn on debugging for wd wd.set_debug() term[1, ...].parse_string("abc 123 xyz 890") prints:: Match alphaword at loc 0(1,1) Matched alphaword -> ['abc'] Match alphaword at loc 3(1,4) Exception raised:Expected alphaword (at char 4), (line:1, col:5) Match alphaword at loc 7(1,8) Matched alphaword -> ['xyz'] Match alphaword at loc 11(1,12) Exception raised:Expected alphaword (at char 12), (line:1, col:13) Match alphaword at loc 15(1,16) Exception raised:Expected alphaword (at char 15), (line:1, col:16) The output shown is that produced by the default debug actions - custom debug actions can be specified using :class:`set_debug_actions`. Prior to attempting to match the ``wd`` expression, the debugging message ``"Match <exprname> at loc <n>(<line>,<col>)"`` is shown. Then if the parse succeeds, a ``"Matched"`` message is shown, or an ``"Exception raised"`` message is shown. Also note the use of :class:`set_name` to assign a human-readable name to the expression, which makes debugging and exception messages easier to understand - for instance, the default name created for the :class:`Word` expression without calling ``set_name`` is ``"W:(A-Za-z)"``. F)r )r r� r r� r� r� r� )r� r r r� r. r. r/ r� A s & ��zParserElement.set_debugc C s | j d u r | �� | _ | j S rE )r� �_generateDefaultNamer r. r. r/ � default_namev s zParserElement.default_namec C r� )zg Child classes must define this method, which defines how the ``default_name`` is set. Nr. r r. r. r/ r | r� z"ParserElement._generateDefaultNamec C s. || _ dt| �� �| _tjr| �|du� | S )a� Define name for this expression, makes debugging and exception messages clearer. If `__diag__.enable_debug_on_named_expressions` is set to True, setting a name will also enable debug for this expression. If `name` is None, clears any custom name for this expression, and clears the debug flag is it was enabled via `__diag__.enable_debug_on_named_expressions`. Example:: integer = Word(nums) integer.parse_string("ABC") # -> Exception: Expected W:(0-9) (at char 0), (line:1, col:1) integer.set_name("integer") integer.parse_string("ABC") # -> Exception: Expected integer (at char 0), (line:1, col:1) � Expected N)r� rv r� r< rR r� r� r. r. r/ �set_name� s zParserElement.set_namec C s | j d ur| j S | jS rE )r� r r r. r. r/ rA � s zParserElement.namec C s | � |� d S rE )r )r� �new_namer. r. r/ rA � s c C r rE �rA r r. r. r/ �__str__� � zParserElement.__str__c C r� rE r� r r. r. r/ �__repr__� rN zParserElement.__repr__c C s d| _ d | _| S �NT)r� r� r r. r. r/ r� � s zParserElement.streamline�list[ParserElement]c C � g S rE r. r r. r. r/ r � rR zParserElement.recursec C s. |d d � | g }| � � D ]}|�|� q d S rE )r �_checkRecursion�r� �parseElementList�subRecCheckListr> r. r. r/ r � s �z ParserElement._checkRecursionc C s t jdtdd� | �g � dS )zj Check defined expressions for valid structure, check for infinite recursive definitions. �ZParserElement.validate() is deprecated, and should not be used to check for left recursionrV �� stacklevelN)�warningsr? �DeprecationWarningr )r� � validateTracer. r. r/ �validate� s �zParserElement.validate�utf-8�file_or_filename�Union[str, Path, TextIO]�encodingc C s� |p|}z t �t|�}|�� }W n* ty: t �t|�}t|d|d�� }|�� }W d � n1 s3w Y Y nw z| �||�W S tyW } z t j rN� |� d��d}~ww )z� Execute the parse expression on the given file or filename. If a filename is specified (instead of a file object), the entire file is opened, read, and closed before parsing. �r�r N) r� r r �read�AttributeErrorrv �openr� ro ru r� r� )r� r r r� r� � file_contents�fr� r. r. r/ � parse_file� s& ��� ��zParserElement.parse_filec C sB | |u rdS t |t�r| j|dd�S t |t�r t| �t|�kS dS )NT�r� F)rV r" r� ru �varsr� r. r. r/ �__eq__� s zParserElement.__eq__c C r� rE )�idr r. r. r/ �__hash__� rN zParserElement.__hash__� test_stringc C s6 |o|}z | j t|�|d� W dS ty Y dS w )a� Method for quick testing of a parser against a test string. Good for simple inline microtests of sub expressions while building up larger parser. Parameters: - ``test_string`` - to test against this expression for a match - ``parse_all`` - (default= ``True``) - flag to pass to :class:`parse_string` when running tests Example:: expr = Word(nums) assert expr.matches("100") r( TF)r� rv ro )r� r- r� r� r. r. r/ r� � s �zParserElement.matches�#)r� �fullDump� printResults� failureTestsrQ �tests�Union[str, list[str]]�comment�*typing.Optional[Union[ParserElement, str]]� full_dump� print_results� failure_tests� post_parse�Dtyping.Optional[Callable[[str, ParseResults], typing.Optional[str]]]�file�typing.Optional[TextIO]�with_line_numbersr/ r0 r1 rQ �=tuple[bool, list[tuple[str, Union[ParseResults, Exception]]]]c & s� ddl m} | o |} | o |} | o|} | p|} |p|}t|t�r7t�t|�}t|�j� � fdd�|� � � � D �}|du}|rLt|t�rLt�t|�}t |�}t�t |�}|du rYt j}|j}g }g }d}t d��td���t�}d }d}|D �]n}|r|�|d �s�|r�|s�|�| r�|�|�n|� qt|s�qt|� |r�|�|�nd � �| r�|�|�n|g}|�� z|�|�|��}| j|| d �}W n� t y� } z2t|t �r�d nd } |�|� � � |�d| � |� �� t j r�|� t!�"|j#�� |o�| }|}W Y d}~n�d}~w t$�ya } zYd} | j#} t%t!�&| ��} | D ] \}!}"|!j'j(|"ft)k�r1t*| �d }#| d|#j'j+�d�7 } n�q|�| � dt| �j,� d| � �� t j �rP|� t!�"| j#�� |�oT| }| }W Y d} ~ npd} ~ ww |�og| }|du�r�z)|||�}$|$du�r�t|$t-��r�|�|$�.� � n|�t|$�� n|�|�.� � W n6 t$�y� }% z |�|j.| d�� |�|j,� dt|%�j,� d|%� �� W Y d}%~%nd}%~%ww |�|j.| d�� |�d � | �r�|d�|�� |�||f� qt||fS )a� Execute the parse expression on a series of test strings, showing each test, the parsed results or where the parse failed. Quick and easy way to run a parse expression against a list of sample strings. Parameters: - ``tests`` - a list of separate test strings, or a multiline string of test strings - ``parse_all`` - (default= ``True``) - flag to pass to :class:`parse_string` when running tests - ``comment`` - (default= ``'#'``) - expression for indicating embedded comments in the test string; pass None to disable comment filtering - ``full_dump`` - (default= ``True``) - dump results as list followed by results names in nested outline; if False, only dump nested list - ``print_results`` - (default= ``True``) prints test output to stdout - ``failure_tests`` - (default= ``False``) indicates if these tests are expected to fail parsing - ``post_parse`` - (default= ``None``) optional callback for successful parse results; called as `fn(test_string, parse_results)` and returns a string to be added to the test output - ``file`` - (default= ``None``) optional file-like object to which test output will be written; if None, will default to ``sys.stdout`` - ``with_line_numbers`` - default= ``False``) show test strings with line and column numbers Returns: a (success, results) tuple, where success indicates that all tests succeeded (or failed if ``failure_tests`` is True), and the results contain a list of lines of each test's output Example:: number_expr = pyparsing_common.number.copy() result = number_expr.run_tests(''' # unsigned integer 100 # negative integer -100 # float with scientific notation 6.02e23 # integer with scientific notation 1e-12 ''') print("Success" if result[0] else "Failed!") result = number_expr.run_tests(''' # stray character 100Z # missing leading digit before '.' -.100 # too many '.' 3.14.159 ''', failure_tests=True) print("Success" if result[0] else "Failed!") prints:: # unsigned integer 100 [100] # negative integer -100 [-100] # float with scientific notation 6.02e23 [6.02e+23] # integer with scientific notation 1e-12 [1e-12] Success # stray character 100Z ^ FAIL: Expected end of text (at char 3), (line:1, col:4) # missing leading digit before '.' -.100 ^ FAIL: Expected {real number with scientific notation | real number | signed integer} (at char 0), (line:1, col:1) # too many '.' 3.14.159 ^ FAIL: Expected end of text (at char 4), (line:1, col:5) Success Each test string must be on a single line. If you want to test a string that spans multiple lines, create a test like this:: expr.run_tests(r"this is a test\n of strings that spans \n 3 lines") (Note that this is a raw string literal, you must include the leading ``'r'``.) r )�pyparsing_testc s g | ]}� |��qS r. r. )r, � test_line�� line_stripr. r/ r0 � r2 z+ParserElement.run_tests.<locals>.<listcomp>NT�\n� u Frk r( z(FATAL) zFAIL: zFAIL-EXCEPTIONr z (raised in parse action r� �: )�fullz failed: )/�testingr? rV r" r� r rv r� �strip�rstrip� splitlines�Literalru �sys�stdout�writer9 � replace_withr� � quoted_stringr� r r= r� r4 r� �lstripr� ro r� �explainr� r r� � format_tbr� r� r� �walk_tb�f_code� co_filenamer� �next�co_namer2 r �dump)&r� r2 r� r4 r6 r7 r8 r9 r; r= r� r/ r0 r1 rQ r? �comment_specified�print_� allResults�comments�success�NL�BOM�nlstrr� r� rw ru r� r� �tagr� �itr& r� �next_f�pp_valuer> r. rA r/ � run_tests s� u ��� � �� ���� zParserElement.run_testsrW � output_html�Union[TextIO, Path, str]�vertical�show_results_names� show_groups�embed� show_hiddenc K s� z ddl m}m} W n ty } ztd�| �d} ~ ww | �� || |||||d�} t|ttf�s@|� | | fd|i|��� dS t |ddd ��} | � | | fd|i|��� W d � dS 1 s`w Y dS ) a� Create a railroad diagram for the parser. Parameters: - ``output_html`` (str or file-like object) - output target for generated diagram HTML - ``vertical`` (int) - threshold for formatting multiple alternatives vertically instead of horizontally (default=3) - ``show_results_names`` - bool flag whether diagram should show annotations for defined results names - ``show_groups`` - bool flag whether groups should be highlighted with an unlabeled surrounding box - ``show_hidden`` - bool flag to show diagram elements for internal elements that are usually hidden - ``embed`` - bool flag whether generated HTML should omit <HEAD>, <BODY>, and <DOCTYPE> tags to embed the resulting HTML in an enclosing HTML source - ``head`` - str containing additional HTML to insert into the <HEAD> section of the generated code; can be used to insert custom CSS styling - ``body`` - str containing additional HTML to insert at the beginning of the <BODY> section of the generated code Additional diagram-formatting keyword arguments can also be included; see railroad.Diagram class. r )� to_railroad�railroad_to_htmlzMmust ``pip install pyparsing[diagrams]`` to generate parser railroad diagramsN)ri rj rk rm �diagram_kwargsrl �wr r! ) �diagramrn ro � ImportErrorr� r� rV rv r rN r$ ) r� rg ri rj rk rl rm r+ rn ro r� �railroad� diag_filer. r. r/ �create_diagram� s2 "����� "�z ParserElement.create_diagram�inlineLiteralsUsing�setDefaultWhitespaceChars�disableMemoization�enableLeftRecursion� enablePackratr� �setResultsName�setBreak�setParseAction�addParseAction� addCondition� setFailAction�tryParse� parseString� scanString�transformString� searchString�ignoreWhitespace�leaveWhitespace�setWhitespaceChars� parseWithTabs�setDebugActions�setDebug�setName� parseFile�runTests� canParseNext)r� rv rC rD )rH r� rC rD �F)r� rg rC rD )r rU rC ru �rC ru )rA rv r rg r rg rC ru �T)r rg rC ru )r* r� r+ r rC ru )r* r� r+ r rC ru )r� r; rC ru �r� rv r� r� rC r� �rC rJ r& )rC rS ) r� rv r� r� r` rg r rg rC r� )r� rv r� r� r rg rC rg rJ rE )r r� rC rD )r� )r r� r~ rg rC rD )r� rv r� rg r� rg rC r ) r� rv r� r� r� rg r� rg r� r� rC r� )r� rv r� rg rC rv ) r� rv r� r� r� rg r� r� rC r )r� rv r� r� r� rg rC r� )rA rf rC ru �r� rg rC ru )r� r� r� rg rC ru )r� ru rC ru )r� r� r� r r r rC ru )TF)r rg r rg rC ru �rC rv �rC r )r F) r r r rv r� rg r� rg rC r )r- rv r� rg r� rg rC rg )Tr. TTFNNF) r2 r3 r� rg r4 r5 r6 rg r7 rg r8 rg r9 r: r; r< r= rg r� rg r/ rg r0 rg r1 rg rQ r: rC r> )rW FFFF)rg rh ri r� rj rg rk rg rl rg rm rg rC rD )�r2 r3 r4 r5 r� r� r� r� � staticmethodr� r� rT r� r r� r� �propertyr �setterr r r r r r) r8 r9 r: r< rD rI rM rQ r_ rb rc r �recursion_lockrd r� �Protocolrj �dictrk rl rm rn rx r' rz r| r{ r} r� r� r� �_MAX_INTr� r� r� r: r� r� r� r� r� r� r� r� r� r� r� r� r� �__iter__r� r� r� r� r� r� r� r� r r� r r r r rA r r r� r r r r' r* r, r� rf rv r rw rx ry rz r{ r� r| r} r~ r r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� � defaultNamer. r. r. r/ ru � s� ��" X % �j� ��0 ��/��1��J��b6��0�� $ P < � 5 �� ���� [�=� c sF e Zd Zdd� fdd � Zdd d �Zdd d�Zdd� Zddd�Z� ZS )r� Fr� ru r� rg rC rD c s t � �� || _|| _d S rE )�superr� �anchorr� )r� r� r� �r� r. r/ r� = � z_PendingSkip.__init__rv c C s t | jt� ��dd�S )Nr� �...)rv r� r� �replacer r. r. r/ r B � z!_PendingSkip._generateDefaultNamec s\ t |��d�d�}� jr'dd� }� fdd�}� j|� �|� |� �|�B | S � j| | S )Nr� r� c S s0 | j r | j �� dgkr| d= | �dd � d S d S )Nrk r �_skipped)r� r� �pop�r� r. r. r/ r� I s �z'_PendingSkip.__add__.<locals>.must_skipc s< | j �� dd � dgkr | �d� d� j�d�| d< d S d S )Nr� rk r� z missing <r� )r� r� r� r� r� r r. r/ � show_skipN s �z'_PendingSkip.__add__.<locals>.show_skip)r� r r� r� r9 )r� r� �skipperr� r� r. r r/ r� E s ��z_PendingSkip.__add__c C r rE )r� r r. r. r/ r Z r z_PendingSkip.__repr__rJ c G s t d��)NzBuse of `...` expression without following SkipTo target expression)r� rh r. r. r/ rM ] s �z_PendingSkip.parseImplr� )r� ru r� rg rC rD r� r� r� ) r2 r3 r4 r� r r� r rM � __classcell__r. r. r� r/ r� : s r� c s, e Zd ZdZd � fdd� Zd dd�Z� ZS ) �TokenzYAbstract :class:`ParserElement` subclass, for defining atomic matching patterns. rC rD c s t � jdd� d S )NF�r� �r� r� r r� r. r/ r� h � zToken.__init__rv c C s t | �jS rE )r� r2 r r. r. r/ r k r� zToken._generateDefaultNamerJ r� )r2 r3 r4 r5 r� r r� r. r. r� r/ r� c s r� c �. e Zd ZdZd � fdd� Zd d dd �Z� ZS ) r� z( A token that will never match. rC rD c s t � �� d| _d| _d| _d S )NTFzUnmatchable token)r� r� r� r� r� r r� r. r/ r� t s zNoMatch.__init__TrJ c C s t ||| j| ��rE )r� r� rL r. r. r/ rM z � zNoMatch.parseImplrJ r� r� �r2 r3 r4 r5 r� rM r� r. r. r� r/ r� o � r� c s^ e Zd ZdZddd�d� fdd�Zd d � Zddd�d� fd d�Zddd�Zdddd�Z� Z S )rK a� Token to exactly match a specified string. Example:: Literal('abc').parse_string('abc') # -> ['abc'] Literal('abc').parse_string('abcdef') # -> ['abc'] Literal('abc').parse_string('ab') # -> Exception: Expected "abc" For case-insensitive matching, use :class:`CaselessLiteral`. For keyword matching (force word break before and after the matched string), use :class:`Keyword` or :class:`CaselessKeyword`. rk �� matchString� match_stringrv r� c sD | t u r |p|}|st� �t�S t|�dkr t� �t�S t� �| �S rE )rK r� �__new__r� rF �_SingleCharLiteral)rH r� r� r� r. r/ r� � s zLiteral.__new__c C s | j fS rE )�matchr r. r. r/ �__getnewargs__� rN zLiteral.__getnewargs__rC rD c sN t � �� |p|}|| _t|�| _|d d� | _d| j� �| _d| _d| _ d S )Nr r F) r� r� r� rF �matchLen�firstMatchCharrA r� r� r� �r� r� r� r� r. r/ r� � s zLiteral.__init__c C � t | j�S rE ��reprr� r r. r. r/ r � r� z Literal._generateDefaultNameTrJ c C s< || | j kr|�| j|�r|| j | jfS t||| j| ��rE )r� r* r� r� r� r� rL r. r. r/ rM � s �zLiteral.parseImpl�rk )r� rv r� rv �r� rv r� rv rC rD r� r� r� ) r2 r3 r4 r5 r� r� r� r rM r� r. r. r� r/ rK ~ s rK c s@ e Zd ZdZddd�d� fdd�Zdd d �Zddd d�Z� ZS )r� z, An empty token, will always match. rk r� rC rD c s t � �d� d| _d| _d S )Nrk TF�r� r� r� r� r� r� r. r/ r� � � zEmpty.__init__rv c C r� )Nr� r. r r. r. r/ r � rR zEmpty._generateDefaultNameTrJ c C rK rE r. rL r. r. r/ rM � rN zEmpty.parseImplr� rJ r� r� r� �r2 r3 r4 r5 r� r rM r� r. r. r� r/ r� � s r� c @ s e Zd Zdddd�ZdS ) r� TrC rJ c C s, || | j kr|d | jfS t||| j| ��rE )r� r� r� r� rL r. r. r/ rM � s z _SingleCharLiteral.parseImplNr� r� )r2 r3 r4 rM r. r. r. r/ r� � s r� c sl e Zd ZdZed Z d ddd�d � fdd�Zd dd�Zd d dd�Ze d!dd��Z e e de ��Z � Z S )"�Keyworda� Token to exactly match a specified string as a keyword, that is, it must be immediately preceded and followed by whitespace or non-keyword characters. Compare with :class:`Literal`: - ``Literal("if")`` will match the leading ``'if'`` in ``'ifAndOnlyIf'``. - ``Keyword("if")`` will not; it will only match the leading ``'if'`` in ``'if x=1'``, or ``'if(y==2)'`` Accepts two optional constructor arguments in addition to the keyword string: - ``ident_chars`` is a string of characters that would be valid identifier characters, defaulting to all alphanumerics + "_" and "$" - ``caseless`` allows case-insensitive matching, default is ``False``. Example:: Keyword("start").parse_string("start") # -> ['start'] Keyword("start").parse_string("starting") # -> Exception For case-insensitive matching, use :class:`CaselessKeyword`. z_$rk NF�r� � identCharsr� rv � ident_charsrf �caselessrg r� r� rC rD c s� t � �� |p|}|d u rtj}|p|}|| _t|�| _|d d� | _| js*td��dt | �j � d| j � �| _ d| _ d| _|| _|rK|�� | _|�� }t|�| _d S )Nr z2null string passed to Keyword; use Empty() insteadr � F)r� r� r� �DEFAULT_KEYWORD_CHARSr� rF r� r� r� r� r2 rA r� r� r� r� �upper� caselessmatchr� r� )r� r� r� r� r� r� r� r. r/ r� � s$ zKeyword.__init__c C r� rE r� r r. r. r/ r r� z Keyword._generateDefaultNameTrJ c C sV | j pd}|}| jrW|||| j � �� | jkrV|dks'||d �� | jvrN|t|�| j ks<||| j �� | jvrD|| j | jfS |d7 }|| j }nV|d7 }|d }nM|| | jkrc| jdksj|� | j|�r�|dksw||d | jvr�|t|�| j ks�||| j | jvr�|| j | jfS |d7 }|| j }n|d7 }|d }t |||| ��)Nrk r r z/, was immediately followed by keyword characterz7, keyword was immediately preceded by keyword characterz7, keyword was immediately followed by keyword character) r� r� r� r� r� r� rF r� r� r* r� )r� r� r� r r� �errlocr. r. r/ rM s4 � � zKeyword.parseImplc C r� )zX Overrides the default characters used by :class:`Keyword` expressions. N)r� r� )r� r. r. r/ �set_default_keyword_chars6 s z!Keyword.set_default_keyword_chars�setDefaultKeywordChars)rk NF) r� rv r� rf r� rg r� rv r� rf rC rD r� r� r� rJ )r2 r3 r4 r5 r~ r� r� r rM r� r� r r� r� r. r. r� r/ r� � s" �� , �r� c s6 e Zd ZdZddd�d� fd d �Zddd d�Z� ZS )�CaselessLiteralaq Token to match a specified string, ignoring case of letters. Note: the matched results will always be in the case of the given match string, NOT the case of the input text. Example:: CaselessLiteral("CMD")[1, ...].parse_string("cmd CMD Cmd10") # -> ['CMD', 'CMD', 'CMD'] (Contrast with example for :class:`CaselessKeyword`.) rk r� r� rv r� rC rD c s0 |p|}t � �|�� � || _d| j� �| _d S )Nr )r� r� r� � returnStringrA r� r� r� r. r/ r� Q s zCaselessLiteral.__init__TrJ c C s< |||| j � �� | jkr|| j | jfS t||| j| ��rE )r� r� r� r� r� r� rL r. r. r/ rM X s zCaselessLiteral.parseImplr� r� r� r� r� r. r. r� r/ r� C s r� c s0 e Zd ZdZ dddd�d� fd d�Z� ZS )�CaselessKeywordz� Caseless version of :class:`Keyword`. Example:: CaselessKeyword("CMD")[1, ...].parse_string("cmd CMD Cmd10") # -> ['CMD', 'CMD'] (Contrast with example for :class:`CaselessLiteral`.) rk Nr� r� rv r� rf r� r� rC rD c s& |p|}|p|}t � j||dd� d S )NT)r� r� )r� r� r� r� r� r� r. r/ r� j s zCaselessKeyword.__init__)rk N) r� rv r� rf r� rv r� rf rC rD �r2 r3 r4 r5 r� r� r. r. r� r/ r� ^ s ��r� c sD e Zd ZdZ dddd�d� fdd�Zddd�Zdddd�Z� ZS )� CloseMatcha� A variation on :class:`Literal` which matches "close" matches, that is, strings with at most 'n' mismatching characters. :class:`CloseMatch` takes parameters: - ``match_string`` - string to be matched - ``caseless`` - a boolean indicating whether to ignore casing when comparing characters - ``max_mismatches`` - (``default=1``) maximum number of mismatches allowed to count as a match The results from a successful parse will contain the matched text from the input string and the following named results: - ``mismatches`` - a list of the positions within the match_string where mismatches were found - ``original`` - the original match_string used to compare against the input string If ``mismatches`` is an empty list, then the match was an exact match. Example:: patt = CloseMatch("ATCATCGAATGGA") patt.parse_string("ATCATCGAAXGGA") # -> (['ATCATCGAAXGGA'], {'mismatches': [[9]], 'original': ['ATCATCGAATGGA']}) patt.parse_string("ATCAXCGAAXGGA") # -> Exception: Expected 'ATCATCGAATGGA' (with up to 1 mismatches) (at char 0), (line:1, col:1) # exact match patt.parse_string("ATCATCGAATGGA") # -> (['ATCATCGAATGGA'], {'mismatches': [[]], 'original': ['ATCATCGAATGGA']}) # close match allowing up to 2 mismatches patt = CloseMatch("ATCATCGAATGGA", max_mismatches=2) patt.parse_string("ATCAXCGAAXGGA") # -> (['ATCAXCGAAXGGA'], {'mismatches': [[4, 9]], 'original': ['ATCATCGAATGGA']}) Nr F)� maxMismatchesr� r� rv �max_mismatchesr� r� r� rC rD c sT |d ur|n|}t � �� || _|| _d| j�d| j� d�| _|| _d| _d| _d S )Nr z (with up to z mismatches)F)r� r� r� r� r� r� r� r� )r� r� r� r� r� r� r. r/ r� � s zCloseMatch.__init__c C s t | �j� d| j��S )Nrh )r� r2 r� r r. r. r/ r � � z CloseMatch._generateDefaultNameTrJ c C s� |}t |�}|t | j� }||krg| j}d}g } | j} tt|||� |��D ]%\}} | \} } | jr:| �� | �� } } | | krK| �|� t | �| krK n q&|| d }t|||� g�}||d< | |d< ||fS t ||| j | ��)Nr r �original� mismatches) rF r� r� � enumerate�zipr� rl r r r� r� )r� r� r� r r� rG �maxlocr� �match_stringlocr� r� �s_m�src�mat�resultsr. r. r/ rM � s2 � � zCloseMatch.parseImplrE )r� rv r� r� r� r� rC rD r� r� r� r� r. r. r� r/ r� w s %�� r� c s` e Zd ZdZ d#ddddd�d$� fdd�Zd%dd �Zd&d'd d �Zd&d'd!d"�Z� ZS )(�Worda> Token for matching words composed of allowed character sets. Parameters: - ``init_chars`` - string of all characters that should be used to match as a word; "ABC" will match "AAA", "ABAB", "CBAC", etc.; if ``body_chars`` is also specified, then this is the string of initial characters - ``body_chars`` - string of characters that can be used for matching after a matched initial character as given in ``init_chars``; if omitted, same as the initial characters (default=``None``) - ``min`` - minimum number of characters to match (default=1) - ``max`` - maximum number of characters to match (default=0) - ``exact`` - exact number of characters to match (default=0) - ``as_keyword`` - match as a keyword (default=``False``) - ``exclude_chars`` - characters that might be found in the input ``body_chars`` string but which should not be accepted for matching ;useful to define a word of all printables except for one or two characters, for instance (default=``None``) :class:`srange` is useful for defining custom character set strings for defining :class:`Word` expressions, using range notation from regular expression character sets. A common mistake is to use :class:`Word` to match a specific literal string, as in ``Word("Address")``. Remember that :class:`Word` uses the string argument to define *sets* of matchable characters. This expression would match "Add", "AAA", "dAred", or any other word made up of the characters 'A', 'd', 'r', 'e', and 's'. To match an exact literal string, use :class:`Literal` or :class:`Keyword`. pyparsing includes helper strings for building Words: - :class:`alphas` - :class:`nums` - :class:`alphanums` - :class:`hexnums` - :class:`alphas8bit` (alphabetic characters in ASCII range 128-255 - accented, tilded, umlauted, etc.) - :class:`punc8bit` (non-alphabetic characters in ASCII range 128-255 - currency, symbols, superscripts, diacriticals, etc.) - :class:`printables` (any non-whitespace character) ``alphas``, ``nums``, and ``printables`` are also defined in several Unicode sets - see :class:`pyparsing_unicode``. Example:: # a word composed of digits integer = Word(nums) # equivalent to Word("0123456789") or Word(srange("0-9")) # a word with a leading capital, and zero or more lowercase capitalized_word = Word(alphas.upper(), alphas.lower()) # hostnames are alphanumeric, with leading alpha, and '-' hostname = Word(alphas, alphanums + '-') # roman numeral (not a strict parser, accepts invalid mix of characters) roman = Word("IVXLCDM") # any string of non-whitespace characters, except for ',' csv_value = Word(printables, exclude_chars=",") rk Nr r F)� initChars� bodyChars� asKeyword� excludeChars� init_charsrv � body_charsrf r� r� �max�exact� as_keywordrg � exclude_charsr� r� r� r� rC rD c sZ |p|}| p|} | p |} | p|} t � �� |s"tdt| �j� d���t|�} | r;t| �} | | 8 } | r;d�t| �| �} | | _d�t| ��| _ | rVt| �| _ d�t| ��| _ n| | _ | j | _ |dk| _ |dk rjtd��| j r|||kr|td|� d|� d ���|| _ |dkr�|| _nt| _|dkr�| }}|| _|| _ d | j� �| _d | _| | _| jr�| jd 7 _d | j| j B v�r�t| j�dkr�t�| j �}n dt| j�� d�}| j | jk�r|dkr�| j dkr�d}n(|dkr�d}n!| j | jk�rd| j � d| jtkr�dn| j� d�}nd| j � d�}|� |� �| _ni|dk�r d}d}nVdt| j �� d�}|dk�r3| j dk�r3d}n?|dk�rB|dk�r?dnd}n0||k�rcd|dk�rQ|d nd� d|dk�r]|d nd� d�}nd|dk�rm|d nd� d�}|� |� |� �| _| j�r�d| j� d�| _z t�| j�| _W n tj�y� d | _Y d S w | jj| _ | j | _ d S d S )Nzinvalid z", initChars cannot be empty stringrk r r zUcannot specify a minimum length < 1; use Opt(Word()) if zero-length word is permittedzDinvalid args, if min and max both specified min must be <= max (min=z, max=r� r Fz as a keywordr� �[r� �+�{r� �}r rV �?z\b) r� r� r� r� r2 r� r� r� �sorted� initCharsOrigr� � bodyCharsOrig� maxSpecified�minLen�maxLenr� rA r� r� r� rF �re�escaper �reString�compile�errorr� �re_match�parseImpl_regexrM )r� r� r� r� r� r� r� r� r� r� r� r� � initChars_set�excludeChars_set�re_leading_fragment�repeat�re_body_fragmentr� r. r/ r� s� � ��& 8 � �z Word.__init__c C s� dd� }| j | jkrd|| j �� d|| j�� d�}n d|| j �� d�}| jdks-| jtkrb| j| jkrG| jdkr>|dd � S |d| j� d � S | jtkrU|d| j� d � S |d| j� d | j� d � S |S ) Nc S s4 d}t | dd�} t| �|kr| d |d � d S | S )N� F)� re_escaperW r� )r rF )r� � max_repr_lenr. r. r/ � charsAsStr� s z-Word._generateDefaultName.<locals>.charsAsStrzW:(�, r� r rV r� r� z,...}r� )r� r� r� r� r� )r� r �baser. r. r/ r � s zWord._generateDefaultNameTrJ c C s || | j vrt||| j| ��|}|d7 }t|�}| j}|| j }t||�}||k r>|| |v r>|d7 }||k r>|| |v s0d}|| | jk rJd}n+| jrZ||k rZ|| |v rZd}n| j ru|dkri||d |v ss||k ru|| |v rud}|rt||| j| ��||||� fS )Nr FTr ) r� r� r� rF r� r� r� r� r� r� ) r� r� r� r r� rG r� r� �throw_exceptionr. r. r/ rM � s. �zWord.parseImplc C s4 | � ||�}|st||| j| ��|�� }||�� fS rE )r r� r� r� �group)r� r� r� r rw r. r. r/ r � s zWord.parseImpl_regex)rk Nr r r FN)r� rv r� rf r� r� r� r� r� r� r� rg r� rf r� rf r� rf r� rg r� rf rC rD r� r� r� ) r2 r3 r4 r5 r� r rM r r� r. r. r� r/ r� � s$ D� � v r� c s0 e Zd ZdZ dddd�d� fdd�Z� ZS )�Charz�A short-cut class for defining :class:`Word` ``(characters, exact=1)``, when defining a match of any single character in a string of characters. FN)r� r� �charsetrv r� rg r� rf r� r� rC rD c s( |p|}|p|}t � j|d||d� d S )Nr )r� r� r� r� )r� r r� r� r� r� r� r. r/ r� � s �z Char.__init__)FN) r rv r� rg r� rf r� rg r� rf rC rD r� r. r. r� r/ r � s ��r c s� e Zd ZdZ d*ddd�d+� fdd�Zed,dd��Zed-dd��Zedd� �Z e j dd� �Z d.d d �Z d/d0d d!�Z d/d"d#�Z d/d$d%�Zd1d(d)�Z� ZS )2�Regexa� Token for matching strings that match a given regular expression. Defined with string specifying the regular expression in a form recognized by the stdlib Python `re module <https://docs.python.org/3/library/re.html>`_. If the given regex contains named groups (defined using ``(?P<name>...)``), these will be preserved as named :class:`ParseResults`. If instead of the Python stdlib ``re`` module you wish to use a different RE module (such as the ``regex`` module), you can do so by building your ``Regex`` object with a compiled RE that was compiled using ``regex``. Example:: realnum = Regex(r"[+-]?\d+\.\d*") # ref: https://stackoverflow.com/questions/267399/how-do-you-match-only-valid-roman-numerals-with-a-regular-expression roman = Regex(r"M{0,4}(CM|CD|D?{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})") # named fields in a regex will be returned as named results date = Regex(r'(?P<year>\d{4})-(?P<month>\d\d?)-(?P<day>\d\d?)') # the Regex class will accept re's compiled using the regex module import regex parser = pp.Regex(regex.compile(r'[0-9]')) r F)� asGroupList�asMatch�patternr �flags�Union[re.RegexFlag, int]� as_group_listrg �as_matchr r rC rD c s� t � �� |p|}|p |}t|t�r%|std��d| _d| _| | _| _n*t |d�r=t |d�r=|| _d| _|j | _| _nt |�rK|| _d| _d| _nt d��|| _ d| j � �| _d| _|| _|| _| jri| j| _| jrr| j| _dS dS )a The parameters ``pattern`` and ``flags`` are passed to the ``re.compile()`` function as-is. See the Python `re module <https://docs.python.org/3/library/re.html>`_ module for an explanation of the acceptable patterns and flags. z0null string passed to Regex; use Empty() insteadNr r� z�Regex may only be constructed with a string or a compiled RE object, or a callable that takes no arguments and returns a string or a compiled RE objectr F)r� r� rV r" r� �_rer� r� r r( r- r� r rA r� r� r r �parseImplAsGroupListrM �parseImplAsMatch)r� r r r r r r r� r. r/ r� � s< � �zRegex.__init__� re.Patternc C s� | j r| j S t| j�r8ttg tf | j�� | _t| jd�r8t| jd�r8ttjt | j�| _ | j j | _| _ | j S z t� | j| j �| _ W n tj yT t d| j�d���w | jjddd�d u| _| j S )Nr r� zinvalid pattern (z) passed to Regexrk r )�pos)r r- r r r rv r( r� �Patternr� r r r r� r� r� r r. r. r/ r� / s �zRegex.re�Callable[[str, int], Any]c C s | j jS rE )r� r� r r. r. r/ r F s zRegex.re_matchc C s | j d u r| j | j S rE )r� r� r r. r. r/ r J s zRegex.mayReturnEmptyc C r rE r r r. r. r/ r Q r rv c C s t | j��dd�}d|� d�S )Nz\\�\zRe:(r� )r� r r� )r� � unescapedr. r. r/ r U � zRegex._generateDefaultNameTrJ c C s� |t |�kr| jrt||| j| ��| �||�}|s!t||| j| ��|�� }t|�� �}|�� }|� � D ]\}}|||< q3||fS rE ) rF r r� r� r r� r r � groupdict�items) r� r� r� r rw r� �d�k�vr. r. r/ rM Y s zRegex.parseImplc C sZ |t |�kr| jrt||| j| ��| �||�}|s!t||| j| ��|�� }|�� }||fS rE )rF r r� r� r r� �groups�r� r� r� r rw r� r. r. r/ r m s zRegex.parseImplAsGroupListc C sV |t |�kr| jrt||| j| ��| �||�}|s!t||| j| ��|�� }|}||fS rE )rF r r� r� r r� r+ r. r. r/ r y s zRegex.parseImplAsMatch�replru c sP �j rtd���jrt� �rtd���jr � fdd�}n� �fdd�}��|�S )a� Return :class:`Regex` with an attached parse action to transform the parsed result as if called using `re.sub(expr, repl, string) <https://docs.python.org/3/library/re.html#re.sub>`_. Example:: make_html = Regex(r"(\w+):(.*?):").sub(r"<\1>\2</\1>") print(make_html.transform_string("h1:main title:")) # prints "<h1>main title</h1>" z/cannot use sub() with Regex(as_group_list=True)z:cannot use sub() with a callable with Regex(as_match=True)c s | d � � �S ry )�expand�r[ )r, r. r/ r� � � zRegex.sub.<locals>.pac s �j �� | d �S ry )r� �subr. �r, r� r. r/ r� � r� )r r� r r- r9 )r� r, r� r. r1 r/ r0 � s � z Regex.sub)r FF)r r r r r rg r rg r rg r rg rC rD )rC r )rC r! r� r� r� )r, rv rC ru )r2 r3 r4 r5 r� r# r� r r� r r� r rM r r r0 r� r. r. r� r/ r � s, ��7 r c s` e Zd ZdZed�Z d!ddddddd�d"� fdd�Zd#d d �Zd$d%d d �Z� Z S )&� QuotedStringa Token for matching strings that are delimited by quoting characters. Defined with the following parameters: - ``quote_char`` - string of one or more characters defining the quote delimiting string - ``esc_char`` - character to re_escape quotes, typically backslash (default= ``None``) - ``esc_quote`` - special quote sequence to re_escape an embedded quote string (such as SQL's ``""`` to re_escape an embedded ``"``) (default= ``None``) - ``multiline`` - boolean indicating whether quotes can span multiple lines (default= ``False``) - ``unquote_results`` - boolean indicating whether the matched text should be unquoted (default= ``True``) - ``end_quote_char`` - string of one or more characters defining the end of the quote delimited string (default= ``None`` => same as quote_char) - ``convert_whitespace_escapes`` - convert escaped whitespace (``'\t'``, ``'\n'``, etc.) to actual whitespace (default= ``True``) Example:: qs = QuotedString('"') print(qs.search_string('lsjdf "This is the quote" sldjf')) complex_qs = QuotedString('{{', end_quote_char='}}') print(complex_qs.search_string('lsjdf {{This is the "quote"}} sldjf')) sql_qs = QuotedString('"', esc_quote='""') print(sql_qs.search_string('lsjdf "This is the quote with ""embedded"" quotes" sldjf')) prints:: [['This is the quote']] [['This is the "quote"']] [['This is the quote with "embedded" quotes']] ))z\t� )rC rD )z\f� )z\r� rk NFT)� quoteChar�escChar�escQuote�unquoteResults� endQuoteChar�convertWhitespaceEscapes� quote_charrv �esc_charrf � esc_quote� multilinerg �unquote_results�end_quote_char�convert_whitespace_escapesr6 r7 r8 r9 r: r; rC rD c s� t � �� | p|}| p |}| o|}| p|}| o|}|p |}|�� }|s'td��|d u r.|}n |�� }|s8td��|� _t|�� _|d � _|� _t|�� _ |pPd� _ |d u� _ |pZd� _ |� _ |� _|� _t�d�� _g }|r{|�dt�|�� d�� |r�|�dt�|�� d�� t� j�dkr�|�dd �� fd d �tt� j�d dd �D �� d � � jrӈ jtjtjB O _|�d t� jd �� � j r�t� j �nd� d�� n|�d t� jd �� d� j r�t� j �nd� d�� d�t�� j�dd �|�dt�� j�g�� _� j �rB� j�r1tjdd �dd � � j D ��� dd� dd� dd� dt�� j �� d� � jd�� _ ntjdt�� j �� d�� jd�� _ zt�� j� j�� _� j� _ � jj � _ W n tj!�yh td � j�d ���w d � j"� �� _#d � _$d � _%d S )!Nz%quote_char cannot be the empty stringz)end_quote_char cannot be the empty stringr rk �(?:r� z.)r �|c 3 sB � | ] }d t �� jd|� �� dt �� j|d� �� d�V qdS )rC Nz(?!z)))r� r� rA )r, ri r r. r/ r� s � 0� �z(QuotedString.__init__.<locals>.<genexpr>r� z(?:[^z])z\n\rz)*r� c s s � | ]}t �|�V qd S rE )r� r� )r, r( r. r. r/ r� 0 � � z )|(\\[0-7]rW z|\\0|\\x[0-9a-fA-F]rV z|\\u[0-9a-fA-F]rX z)|(z .)|(\n|.)�r zinvalid pattern z passed to Regexr FT)&r� r� rH r� r< rF �quote_char_len�first_quote_charrA �end_quote_char_lenr= � has_esc_charr> r@ rB r? r� � RegexFlag�re_flagsr r� r� �range� MULTILINE�DOTALLr r r �ws_map�unquote_scan_rer� r� r r rA r� r� r� )r� r< r= r> r? r@ rA rB r6 r7 r8 r9 r: r; � inner_patternr� r r/ r� � s� � ���� ���� �� ��� � ��� zQuotedString.__init__c C s8 | j | jkrt| j t�rd| j ��S d| j � d| j� �S )Nzstring enclosed in z quoted string, starting with z ending with )r< rA rV r" r r. r. r/ r I s � z!QuotedString._generateDefaultNamerJ c s� || �j kr ��||�pd }|st||�j���|�� }|�� }d dd�� �jre|�j�j � }t |t �re�j rLd� � �fdd��j �|�D ��}nd� d d� �j �|�D ��}�jre|��j�j�}||fS ) Nr� rv rC c S sV | dkrdS | � � rt| �dkrtt| dd��S | �d�r)tt| dd � dd��S | S ) N�0� rW � )r )�u�xr r )�isdigitrF �chrr� r* )r� r. r. r/ �convert_escaped_numerics` s z8QuotedString.parseImpl.<locals>.convert_escaped_numericsrk c 3 sl � | ]1}|� d �r�j|� d � n |� d�r!� |� d�d d� �n|� d�r-|� d�d n|� d�V qdS )r rV NrW r� rX )r rP �r, r� �rZ r� r. r/ r� t s � � �z)QuotedString.parseImpl.<locals>.<genexpr>c s s2 � | ]}|� d �r|� d �d n|� d�V qdS )r r� rV N)r r[ r. r. r/ r� � s � � ��r� rv rC rv )rH r r� r� r� r r@ rG rI rV r" rB r� rQ �finditerr> r� rA r+ r. r\ r/ rM Q s. �� � � zQuotedString.parseImpl)rk NNFTNT) r< rv r= rf r> rf r? rg r@ rg rA rf rB rg r6 rv r7 rf r8 rf r9 rg r: rf r; rg rC rD r� r� r� ) r2 r3 r4 r5 r� rP r� r rM r� r. r. r� r/ r2 � s( '� � zr2 c sH e Zd ZdZ ddd�d� fdd�Zddd�Zdddd�Z� ZS ) � CharsNotIna� Token for matching words composed of characters *not* in a given set (will include whitespace in matched characters if not listed in the provided exclusion set - see example). Defined with string containing all disallowed characters, and an optional minimum, maximum, and/or exact length. The default value for ``min`` is 1 (a minimum value < 1 is not valid); the default values for ``max`` and ``exact`` are 0, meaning no maximum or exact length restriction. Example:: # define a comma-separated-value as anything that is not a ',' csv_value = CharsNotIn(',') print(DelimitedList(csv_value).parse_string("dkls,lsdkjf,s12 34,@!#,213")) prints:: ['dkls', 'lsdkjf', 's12 34', '@!#', '213'] rk r r )�notChars� not_charsrv r� r� r� r� r` rC rD c s� t � �� d| _|p || _t| j�| _|dk rtd��|| _|dkr&|| _nt | _|dkr3|| _|| _d| j � �| _ | jdk| _ d| _ d S )NFr zacannot specify a minimum length < 1; use Opt(CharsNotIn()) if zero-length char group is permittedr r )r� r� r� r` r� � notCharsSetr� r� r� r� rA r� r� r� )r� ra r� r� r� r` r� r. r/ r� � s$ � zCharsNotIn.__init__c C s: t | j�}t|�dkrd| jd d� � d�S d| j� d�S )Nr z!W:(� z...)r� )r r` rF )r� � not_chars_strr. r. r/ r � s z CharsNotIn._generateDefaultNameTrJ c C s� | j }|| |v rt||| j| ��|}|d7 }t|| j t|��}||k r9|| |vr9|d7 }||k r9|| |vs+|| | jk rHt||| j| ��||||� fS rE )rb r� r� r� r� rF r� )r� r� r� r �notcharsr� �maxlenr. r. r/ rM � s �zCharsNotIn.parseImpl)rk r r r ) ra rv r� r� r� r� r� r� r` rv rC rD r� r� r� r� r. r. r� r/ r_ � s �� #r_ c s� e Zd ZdZi dd�dd�dd�dd �d d �d d �dd�dd�dd�dd�dd�dd�dd�d d �d d �d d!�d"d#�d$d%d&d'd(d)d*��Z -d>d?� fd6d7� Zd@d8d9�ZdAdBd<d=�Z� ZS )C�Whitea� Special matching class for matching whitespace. Normally, whitespace is ignored by pyparsing grammars. This class is included when some whitespace structures are significant. Define with a string containing the whitespace characters to be matched; default is ``" \t\r\n"``. Also takes optional ``min``, ``max``, and ``exact`` arguments, as defined for the :class:`Word` class. r� z<SP>r3 z<TAB>rD z<LF>r5 z<CR>r4 z<FF>� z<NBSP>u z<OGHAM_SPACE_MARK>u z<MONGOLIAN_VOWEL_SEPARATOR>u z <EN_QUAD>u z <EM_QUAD>u z <EN_SPACE>u z <EM_SPACE>u z<THREE-PER-EM_SPACE>u z<FOUR-PER-EM_SPACE>u z<SIX-PER-EM_SPACE>u z<FIGURE_SPACE>u z<PUNCTUATION_SPACE>z <THIN_SPACE>z <HAIR_SPACE>z<ZERO_WIDTH_SPACE>z<NNBSP>z<MMSP>z<IDEOGRAPHIC_SPACE>)u u u u u u � r r �wsrv r� r� r� r� rC rD c s� t � �� |� _� jd�� fdd�� jD ��dd� d� _d� j� �� _|� _ |dkr/|� _ nt � _ |dkr>|� _ |� _ d S d S )Nrk c 3 s � | ] }|� j vr|V qd S rE )� matchWhiter� r r. r/ r� s � z!White.__init__.<locals>.<genexpr>T�r� r r ) r� r� rk r� r� � whiteStrsr� rA r� r� r� r� )r� rj r� r� r� r� r r/ r� s � �zWhite.__init__c C s d� dd� | jD ��S )Nrk c s s � | ]}t j| V qd S rE )rg rm r� r. r. r/ r� rE z-White._generateDefaultName.<locals>.<genexpr>)r� rk r r. r. r/ r r� zWhite._generateDefaultNameTrJ c C s� || | j vrt||| j| ��|}|d7 }|| j }t|t|��}||k r;|| | j v r;|d7 }||k r;|| | j v s,|| | jk rJt||| j| ��||||� fS rE )rk r� r� r� r� rF r� )r� r� r� r r� r� r. r. r/ rM s �zWhite.parseImpl)ri r r r ) rj rv r� r� r� r� r� r� rC rD r� r� r� ) r2 r3 r4 r5 rm r� r rM r� r. r. r� r/ rg � s` �������� � � � � ������� rg c s e Zd Zd� fdd� Z� ZS )� PositionTokenrC rD c s t � �� d| _d| _d S �NTFr� r r� r. r/ r� 1 r� zPositionToken.__init__rJ �r2 r3 r4 r� r� r. r. r� r/ rn 0 � rn c s8 e Zd ZdZd� fdd� Zdd d �Zdddd�Z� ZS )� GoToColumnzaToken to advance to a specific column of input text; useful for tabular report scraping. �colnor� rC rD c s t � �� || _d S rE )r� r� r� )r� rs r� r. r/ r� < s zGoToColumn.__init__r� rv r� c C s� t ||�| j kr |S t|�}| jr| �||�}||k r?|| �� r?t ||�| j kr?|d7 }||k r?|| �� r?t ||�| j ks)|S rE )r� rF r� rD �isspace)r� r� r� rG r. r. r/ rI @ s �� �zGoToColumn.preParseTrJ c C sD t ||�}|| j krt||d| ��|| j | }|||� }||fS )NzText not in expected column)r� r� )r� r� r� r �thiscol�newlocr� r. r. r/ rM P s zGoToColumn.parseImpl)rs r� rC rD r� r� r� �r2 r3 r4 r5 r� rI rM r� r. r. r� r/ rr 7 s rr c s8 e Zd ZdZd� fdd� Zdd d �Zdddd�Z� ZS )� LineStarta� Matches if current position is at the beginning of a line within the parse string Example:: test = '''\ AAA this line AAA and this line AAA but not this one B AAA and definitely not this one ''' for t in (LineStart() + 'AAA' + rest_of_line).search_string(test): print(t) prints:: ['AAA', ' this line'] ['AAA', ' and this line'] rC rD c sJ t � �� | �� t� | jB | _| j�d� t� �| j�| _ | � d� d S )NrD z start of line) r� r� r� r� r� �orig_whiteChars�discardr� r� r� r r r� r. r/ r� p s zLineStart.__init__r� rv r� r� c C sb |dkr|S | j �||�}d| jv r/|||d � dkr/| j �||d �}|||d � dks |S )Nr rD r )r� rI ry )r� r� r� r� r. r. r/ rI x s �zLineStart.preParseTrJ c C s& t ||�dkr |g fS t||| j| ��rE )r� r� r� rL r. r. r/ rM � s zLineStart.parseImplrJ r� r� r� rw r. r. r� r/ rx Y s rx c r� ) �LineEndzTMatches if current position is at the end of a line within the parse string rC rD c s4 t � �� | j�d� | j| jdd� | �d� d S )NrD Frl z end of line)r� r� r� rz r� r r r� r. r/ r� � s zLineEnd.__init__TrJ c C s\ |t |�k r|| dkr|d dfS t||| j| ��|t |�kr&|d g fS t||| j| ��)NrD r �rF r� r� rL r. r. r/ rM � s zLineEnd.parseImplrJ r� r� r� r. r. r� r/ r{ � r� r{ c r� ) � StringStartzLMatches if current position is at the beginning of the parse string rC rD c � t � �� | �d� d S )Nz start of text�r� r� r r r� r. r/ r� � � zStringStart.__init__TrJ c C s0 |dkr|| � |d�krt||| j| ��|g fS ry )rI r� r� rL r. r. r/ rM � s zStringStart.parseImplrJ r� r� r� r. r. r� r/ r} � � r} c r� ) r� zG Matches if current position is at the end of the parse string rC rD c r~ )Nz end of textr r r� r. r/ r� � r� zStringEnd.__init__TrJ c C sX |t |�k rt||| j| ��|t |�kr|d g fS |t |�kr$|g fS t||| j| ��rE r| rL r. r. r/ rM � s zStringEnd.parseImplrJ r� r� r� r. r. r� r/ r� � r� r� c �8 e Zd ZdZefed�d� fdd �Zddd d �Z� ZS )� WordStarta� Matches if the current position is at the beginning of a :class:`Word`, and is not preceded by any character in a given set of ``word_chars`` (default= ``printables``). To emulate the ```` behavior of regular expressions, use ``WordStart(alphanums)``. ``WordStart`` will also match at the beginning of the string being parsed, or at the beginning of a line. �� wordChars� word_charsrv r� rC rD c s2 |t kr|n|}t� �� t|�| _| �d� d S )Nzstart of a word)r� r� r� r� r� r �r� r� r� r� r. r/ r� � s zWordStart.__init__TrJ c C s@ |dkr ||d | j v s|| | j vr t||| j| ��|g fS �Nr r )r� r� r� rL r. r. r/ rM � s zWordStart.parseImpl�r� rv r� rv rC rD r� r� �r2 r3 r4 r5 r� r� rM r� r. r. r� r/ r� � s ��r� c r� )�WordEndai Matches if the current position is at the end of a :class:`Word`, and is not followed by any character in a given set of ``word_chars`` (default= ``printables``). To emulate the ```` behavior of regular expressions, use ``WordEnd(alphanums)``. ``WordEnd`` will also match at the end of the string being parsed, or at the end of a line. r� r� rv r� rC rD c s8 |t kr|n|}t� �� t|�| _d| _| �d� d S )NFz end of a word)r� r� r� r� r� r� r r� r� r. r/ r� � s zWordEnd.__init__TrJ c C sP t |�}|dkr$||k r$|| | jv s ||d | jvr$t||| j| ��|g fS r� )rF r� r� r� )r� r� r� r rG r. r. r/ rM � s zWordEnd.parseImplr� r� r� r� r. r. r� r/ r� � s �� r� c s8 e Zd ZdZdd� fd d � Zdd d�Zddd�Z� ZS )�Tagax A meta-element for inserting a named result into the parsed tokens that may be checked later in a parse action or while processing the parsed results. Accepts an optional tag value, defaulting to `True`. Example:: end_punc = "." | ("!" + Tag("enthusiastic"))) greeting = "Hello," + Word(alphas) + end_punc result = greeting.parse_string("Hello, World.") print(result.dump()) result = greeting.parse_string("Hello, World!") print(result.dump()) prints:: ['Hello,', 'World', '.'] ['Hello,', 'World', '!'] - enthusiastic: True T�tag_namerv r r rC rD c s@ t � �� d| _d| _| �� || _|| _| �| j� d| _ d S ro ) r� r� r� r� r� r� � tag_valuer9 �_add_tagr )r� r� r r� r. r/ r� s z Tag.__init__r[ r c C s | j || j< d S rE )r� r� )r� r[ r. r. r/ r� # r� z Tag._add_tagc C s t | �j� d| j� d| j��S )Nrh �=)r� r2 r� r� r r. r. r/ r & � zTag._generateDefaultNamer� )r� rv r r rC rD )r[ r r� )r2 r3 r4 r5 r� r� r r� r. r. r� r/ r� � s r� c s� e Zd ZdZ d'd(� fd d � Zd)d d �Zd*dd�Zd+d,� fdd� Zd+d,� fdd� Zd*� fdd� Z d-dd�Z d*� fd d � Z d.d/d d �Z d*� fd!d"� Z d'd*� fd#d$� Zed%e�Zed&e�Z� ZS )0�ParseExpressionz]Abstract subclass of ParserElement, for combining and post-processing parsed tokens. F�exprs� typing.Iterable[ParserElement]r� rg rC rD c s� t � �|� � t|t�rt|�}t|t�r � �|�g� _n@t|t�r(|g� _n6t|t �rIt|�}t dd� |D ��rC� fdd�|D �}t|�� _nzt|�� _W n t y] |g� _Y nw d� _ d S )Nc s s � | ]}t |t�V qd S rE )rV r" )r, r� r. r. r/ r� > rE z+ParseExpression.__init__.<locals>.<genexpr>c 3 s( � | ]}t |t�r� �|�n|V qd S rE )rV r" r� r= r r. r/ r� ? s � � �F) r� r� rV �_generatorTyper� r" r� r� ru r �anyr� r� �r� r� r� r� r r/ r� / s* � � zParseExpression.__init__r c C s | j d d � S rE )r� r r. r. r/ r K r/ zParseExpression.recurseru c C s | j �|� d | _| S rE )r� r r� r� r. r. r/ r N s zParseExpression.appendTr� c �< t � �|� |r dd� | jD �| _| jD ]}|�|� q| S )z� Extends ``leave_whitespace`` defined in base class, and also invokes ``leave_whitespace`` on all contained expressions. c S � g | ]}|� � �qS r. �r r= r. r. r/ r0 [ r2 z4ParseExpression.leave_whitespace.<locals>.<listcomp>)r� r� r� �r� r� r> r� r. r/ r� S s z ParseExpression.leave_whitespacec r� )z� Extends ``ignore_whitespace`` defined in base class, and also invokes ``leave_whitespace`` on all contained expressions. c S r� r. r� r= r. r. r/ r0 g r2 z5ParseExpression.ignore_whitespace.<locals>.<listcomp>)r� r� r� r� r� r. r/ r� ` s z!ParseExpression.ignore_whitespacec sl t |t�r || jvr t� �|� | jD ] }|�| jd � q| S t� �|� | jD ] }|�| jd � q)| S �Nr� )rV r� r� r� r� r� )r� r� r> r� r. r/ r� l s � zParseExpression.ignorerv c C � t | �j� d| j� d�S �Nz:(r� )r� r2 r� r r. r. r/ r x r� z$ParseExpression._generateDefaultNamec s$ | j r| S t� �� | jD ]}|�� q t| j�dkr�| jd }t|| j�rR|jsR|jd u rR|j sR|jd d � | jd g | _d | _ | j |j O _ | j |j O _ | jd }t|| j�r�|js�|jd u r�|j s�| jd d� |jd d � | _d | _ | j |j O _ | j |j O _ d| � �| _| S )NrV r r r� r )r� r� r� r� rF rV r� r� r� r� r� r� r r� r� )r� r> r� r� r. r/ r� { s@ �� � �� � zParseExpression.streamlineNc C sR t jdtdd� |d ur|ng d d � | g }| jD ]}|�|� q| �g � d S �Nr rV r )r r? r r� r r )r� r �tmpr> r. r. r/ r � s � zParseExpression.validatec s, t � �� }t�t|�}dd� | jD �|_|S )Nc S r� r. r� r= r. r. r/ r0 � r2 z(ParseExpression.copy.<locals>.<listcomp>)r� r r� r r� r� �r� r� r� r. r/ r � s zParseExpression.copyc s� t jr tj| jvst� �||�S | jD ])}t|t�r<|j r<tj|jvr<d|�dt | �j � d|j �d�}t j |dd� nqt� �||�S �Nz@warn_ungrouped_named_tokens_in_collection: setting results name � on z expression collides with z on contained expressionrW r )r< rL rU r r� r r� rV ru r� r� r2 r r? �r� rA r r> �warningr� r. r/ r � s4 �� ��������z ParseExpression._setResultsNamer� r� r� �r� r� r� rg rC rD r� r� r� r� r� rE rJ )r2 r3 r4 r5 r� r r r� r� r� r r� r r r r r� r� r� r. r. r� r/ r� * s � ) r� c sh e Zd ZdZG dd� de�Z dd� fd d � Zd� fdd� Zddd�Zdd� Z dd� Z d dd�Z � Z S ) r� a Requires all given :class:`ParserElement` s to be found in the given order. Expressions may be separated by whitespace. May be constructed using the ``'+'`` operator. May also be constructed using the ``'-'`` operator, which will suppress backtracking. Example:: integer = Word(nums) name_expr = Word(alphas)[1, ...] expr = And([integer("id"), name_expr("name"), integer("age")]) # more easily written as: expr = integer("id") + name_expr("name") + integer("age") c s( e Zd Zd� fdd� Zd dd�Z� ZS ) zAnd._ErrorStoprC rD c s t � j|i |�� | �� d S rE )r� r� r� )r� r� r+ r� r. r/ r� � r$ zAnd._ErrorStop.__init__rv c C r� )N�-r. r r. r. r/ r � rR z#And._ErrorStop._generateDefaultNamerJ r� �r2 r3 r4 r� r r� r. r. r� r/ r� � s r� T� exprs_arg�*typing.Iterable[Union[ParserElement, str]]r� rg rC rD c s � fdd�|D �}t |v r@|d t u rtd��g }t||dd � �D ]\}}|t u r4|�t|�d�� q"|�|� q"||d d�< t� �||� � jrxtdd� � jD ��� _ t � jd t �st� j � jd j � jd jd � � jd j� _nd � _nd � _ d � _d S ) Nc s$ g | ]}t |t�r� �|�n|�qS r. )rV rv r� r= r r. r/ r0 � s �z And.__init__.<locals>.<listcomp>r� z0cannot construct And with sequence ending in ...r r� c s � � | ]}|j V qd S rE �r r= r. r. r/ r� � � z And.__init__.<locals>.<genexpr>r rl FT)r� r� r� r r� r� r� r� r5 r� rV rg r� r� r� r� r� )r� r� r� r� r� �cur_expr� next_exprr� r r/ r� � s0 � � z And.__init__ru c sd | j rXtdd� | j d d� D ��rXt� � t| j d d� �D ]/\}}|� u r&q t|t�rL|j rLt|j d t�rL|j d | j |d |j d< � | j |d < q � fdd�| j D �| _ t� �� t | j | j dd � �D ]<\}}t � } t |�|v rwn-|� t |�� t|t �r�|�|fdd �� n|�� }tt|�d �}|d u r�nt�t|�}qpqhtd d� | j D ��| _| S ) Nc s s0 � | ]}t |t�o|jot |jd t�V qdS �r� N)rV r� r� r� r= r. r. r/ r� s � �� �z!And.streamline.<locals>.<genexpr>r� r c s g | ]}|� ur|�qS r. r. r= ��deleted_expr_markerr. r/ r0 - � z"And.streamline.<locals>.<listcomp>Tc S s t |dt|| ��S )N� parent_anchor)�setattrr� )r� r� r� �cur_r. r. r/ r� > s �z And.streamline.<locals>.<lambda>c s r� rE r� r= r. r. r/ r� I r� )r� r� r� r� rV r� r� r� r� r� r� r+ r � IndentedBlockr9 r rW r� r� r ru r5 r� )r� ri r> �prevr r �subs� next_firstr� r� r/ r� sL ���� � � ��zAnd.streamlinec C s� | j d j|||dd�\}}d}| j dd � D ]R}t|�tju r#d}q|r\z |�|||�\}}W n4 ty8 � tyK } zd |_t�|��d }~w t y[ t|t |�| j | ��w |�|||�\}}||7 }q||fS )Nr Fr� r T) r� r' r� r� r� �ParseSyntaxExceptionro r� �_from_exceptionr� rF r� ) r� r� r� r � resultlist� errorStopr> � exprtokensru r. r. r/ rM L s2 � � �� z And.parseImplc C �, t |t�r | �|�}t |t�stS | �|�S rE �rV r" r� ru r� r r� r. r. r/ �__iadd__i � z And.__iadd__c C s8 |d d � | g }| j D ] }|�|� |js d S q d S rE )r� r r r r. r. r/ r p s ��zAnd._checkRecursionrv c C sz d� dd� | jD ��}t|�dkr7|dd t|�d � dkr7|dd� }t|�dkr7|dd t|�d � dks d|� d �S ) Nr� c s r, rE r� r= r. r. r/ r� x r/ z+And._generateDefaultName.<locals>.<genexpr>r r �{}r� r� r� )r� r� rF �r� �innerr. r. r/ r w s & &� zAnd._generateDefaultNamer� )r� r� r� rg rC rD r� r� ) r2 r3 r4 r5 r� r� r� r� rM r� r r r� r. r. r� r/ r� � s �) 2 r� c �b e Zd ZdZ dd� fd d � Zd� fd d � Zd d dd�Zdd� Zd dd�Zdd� fdd� Z � Z S ) r� a� Requires that at least one :class:`ParserElement` is found. If two expressions match, the expression that matches the longest string will be used. May be constructed using the ``'^'`` operator. Example:: # construct Or using '^' operator number = Word(nums) ^ Combine(Word(nums) + '.' + Word(nums)) print(number.search_string("123 3.1416 789")) prints:: [['123'], ['3.1416'], ['789']] Fr� r� r� rg rC rD c �N t � �||� | jr"tdd� | jD ��| _tdd� | jD ��| _d S d| _d S )Nc s r� rE r� r= r. r. r/ r� � r� z Or.__init__.<locals>.<genexpr>c s r� rE r� r= r. r. r/ r� � r� T�r� r� r� r� r� r5 r� r� r� r. r/ r� � � z Or.__init__ru c s` t � �� | jr+tdd� | jD ��| _tdd� | jD ��| _tdd� | jD ��| _| S d| _| S )Nc s r� rE r� r= r. r. r/ r� � r� z Or.streamline.<locals>.<genexpr>c s r� rE �r� r= r. r. r/ r� � r� c s �" � | ] }|j o t|t� V qd S rE �r� rV rg r= r. r. r/ r� � � � �F)r� r� r� r� r� r� r5 r� r r� r. r/ r� � s ��z Or.streamlineTrJ c C s� d}d }g }g }t dd� | jD ��r| �||�}| jD ]q}z |j||dd�} W n] tyH } zd | _|| _|�| � d }d}W Y d } ~ qd } ~ w tyh } z|s^d | _| j |kr^| }| j }W Y d } ~ qd } ~ w t y� t |�|kr�t|t |�|j | �}t |�}Y qw |�| |f� q|r�|j td�dd� |s�|d d } | �|||�S d } |D ]M\}}|| d kr�| S z |�|||�\} }W n ty� } zd | _| j |kr�| }| j }W Y d } ~ q�d } ~ ww | |kr�| |f S | | d kr�| |f} q�| d kr�| S |�r*t |�dk�r$|j d d � d � |d j |d j k�r$|j d d � d � |d }|�|d u�rC| �||�}||k�rA| j �p?d|_|�t||d| ��)Nr� c s r� rE )r� r= r. r. r/ r� � r� z Or.parseImpl.<locals>.<genexpr>T�r` r )r� �reverser r� c S � | j S rE �r� �r> r. r. r/ r� � r� z Or.parseImpl.<locals>.<lambda>�r� c S � | j tt| j�� fS rE �r� rF rv �parser_elementr� r. r. r/ r� � r� rk � no defined alternatives to match)r5 r� rI rb r� r� r� r r� r� r� rF r� �sortr r' r� )r� r� r� r � maxExcLoc� maxExceptionr� �fatalsr> �loc2�pfer\ � best_expr�longest�loc1�expr1r� � max_fatal�parse_start_locr. r. r/ rM � s� � � ��� �� � z Or.parseImplc C r� rE r� r� r. r. r/ �__ixor__� r� z Or.__ixor__rv c C � dd� dd� | jD ��� d�S )Nr� z ^ c s r, rE r� r= r. r. r/ r� r/ z*Or._generateDefaultName.<locals>.<genexpr>r� �r� r� r r. r. r/ r r� zOr._generateDefaultNamec �Z t jr&tj| jvr&tdd� | jD ��r&d|�dt| �j� d�}tj |dd� t � � ||�S )Nc s �& � | ]}t |t�otj|jvV qd S rE �rV r� rU rK r r= r. r. r/ r� � � �� �z%Or._setResultsName.<locals>.<genexpr>�@warn_multiple_tokens_in_named_alternation: setting results name r� �� expression will return a list of all parsed tokens in an And alternative, in prior versions only the first token was returned; enclose contained argument in GrouprW r � r< rK rU r r� r� r� r2 r r? r� r �r� rA r r� r� r. r/ r � ������zOr._setResultsNamer� r� r� r� r� r� ) r2 r3 r4 r5 r� r� rM r� r r r� r. r. r� r/ r� s � T r� c r� ) r� a� Requires that at least one :class:`ParserElement` is found. If more than one expression matches, the first one listed is the one that will match. May be constructed using the ``'|'`` operator. Example:: # construct MatchFirst using '|' operator # watch the order of expressions to match number = Word(nums) | Combine(Word(nums) + '.' + Word(nums)) print(number.search_string("123 3.1416 789")) # Fail! -> [['123'], ['3'], ['1416'], ['789']] # put more selective expression first number = Combine(Word(nums) + '.' + Word(nums)) | Word(nums) print(number.search_string("123 3.1416 789")) # Better -> [['123'], ['3.1416'], ['789']] Fr� r� r� rg rC rD c r� )Nc s r� rE r� r= r. r. r/ r� 4 r� z&MatchFirst.__init__.<locals>.<genexpr>c s r� rE r� r= r. r. r/ r� 5 r� Tr� r� r� r. r/ r� / r� zMatchFirst.__init__ru c sp | j r| S t� �� | jr0tdd� | jD ��| _tdd� | jD ��| _tdd� | jD ��| _| S d| _d| _| S )Nc s r� rE r� r= r. r. r/ r� ? r� z(MatchFirst.streamline.<locals>.<genexpr>c s r� rE r� r= r. r. r/ r� @ r� c s r� rE r� r= r. r. r/ r� A r� FT) r� r� r� r� r� r� r� r5 r� r r� r. r/ r� 9 s ��zMatchFirst.streamlineTrJ c C s� d}d }| j D ]V}z |�|||�W S ty& } zd |_||_� d }~w tyA } z|j|kr7|}|j}W Y d }~qd }~w ty] t|�|kr[t|t|�|j | �}t|�}Y qw |d urt| � ||�} || krr| j ppd|_ |�t||d| ��)Nr� rk r� ) r� r' r� r� r� r� r� r� rF r� rI r� ) r� r� r� r r� r� r> r� r\ r� r. r. r/ rM I s: � � ��� zMatchFirst.parseImplc C r� rE r� r� r. r. r/ �__ior__i r� zMatchFirst.__ior__rv c C r� )Nr� z | c s r, rE r� r= r. r. r/ r� q r/ z2MatchFirst._generateDefaultName.<locals>.<genexpr>r� r� r r. r. r/ r p r� z MatchFirst._generateDefaultNamec r� )Nc s r� rE r� r= r. r. r/ r� y r� z-MatchFirst._setResultsName.<locals>.<genexpr>r� r� r� rW r r� r� r� r. r/ r s r� zMatchFirst._setResultsNamer� r� r� r� r� r� ) r2 r3 r4 r5 r� r� rM r� r r r� r. r. r� r/ r� s � r� c sR e Zd ZdZ dd� fd d � Zd d � Zd� fdd� Zdddd�Zddd�Z� Z S )r� aj Requires all given :class:`ParserElement` s to be found, but in any order. Expressions may be separated by whitespace. May be constructed using the ``'&'`` operator. Example:: color = one_of("RED ORANGE YELLOW GREEN BLUE PURPLE BLACK WHITE BROWN") shape_type = one_of("SQUARE CIRCLE TRIANGLE STAR HEXAGON OCTAGON") integer = Word(nums) shape_attr = "shape:" + shape_type("shape") posn_attr = "posn:" + Group(integer("x") + ',' + integer("y"))("posn") color_attr = "color:" + color("color") size_attr = "size:" + integer("size") # use Each (using operator '&') to accept attributes in any order # (shape and posn are required, color and size are optional) shape_spec = shape_attr & posn_attr & Opt(color_attr) & Opt(size_attr) shape_spec.run_tests(''' shape: SQUARE color: BLACK posn: 100, 120 shape: CIRCLE size: 50 color: BLUE posn: 50,80 color:GREEN size:20 shape:TRIANGLE posn:20,40 ''' ) prints:: shape: SQUARE color: BLACK posn: 100, 120 ['shape:', 'SQUARE', 'color:', 'BLACK', 'posn:', ['100', ',', '120']] - color: BLACK - posn: ['100', ',', '120'] - x: 100 - y: 120 - shape: SQUARE shape: CIRCLE size: 50 color: BLUE posn: 50,80 ['shape:', 'CIRCLE', 'size:', '50', 'color:', 'BLUE', 'posn:', ['50', ',', '80']] - color: BLUE - posn: ['50', ',', '80'] - x: 50 - y: 80 - shape: CIRCLE - size: 50 color: GREEN size: 20 shape: TRIANGLE posn: 20,40 ['color:', 'GREEN', 'size:', '20', 'shape:', 'TRIANGLE', 'posn:', ['20', ',', '40']] - color: GREEN - posn: ['20', ',', '40'] - x: 20 - y: 40 - shape: TRIANGLE - size: 20 Tr� r� r� rg rC rD c sH t � �||� | jrtdd� | jD ��| _nd| _d| _d| _d| _d S )Nc s r� rE r� r= r. r. r/ r� � r� z Each.__init__.<locals>.<genexpr>T)r� r� r� r5 r� r� �initExprGroupsr� r� r� r. r/ r� � s z Each.__init__c C r� rE r� r� r. r. r/ �__iand__� r� z Each.__iand__ru c s4 t � �� | jrtdd� | jD ��| _| S d| _| S )Nc s r� rE r� r= r. r. r/ r� � r� z"Each.streamline.<locals>.<genexpr>T)r� r� r� r5 r� r r� r. r/ r� � s �zEach.streamlinerJ c s� | j rItdd� | jD ��| _dd� | jD �}dd� | jD �}|| | _dd� | jD �| _dd� | jD �| _dd� | jD �| _| j| j7 _d | _ |}| jd d � }| jd d � � | jd d � }g } d } g } g } | r�|� | } | �� | �� | D ][}z |j ||d d �}W n/ t y� } zd |_ ||_ | � |� | � |� W Y d }~qzd }~w ty� | � |� Y qzw | � | j�t|�|�� ||v r�|�|� qz|� v rՈ �|� qzt| �t| �kr�d } | sj| �r t| �d k�r| jd d� d� | d j| d jk�r| jdd� d� | d }|�|�r$d�dd� |D ��}t||d|� d���| � fdd�| jD �7 } tg �}| D ]}|�|||�\}}||7 }�q6||fS )Nc s s( � | ]}t |t�rt|j�|fV qd S rE )rV r� r+ r� r= r. r. r/ r� � s � � �z!Each.parseImpl.<locals>.<genexpr>c S s g | ] }t |t�r|j�qS r. �rV r� r� r= r. r. r/ r0 � � z"Each.parseImpl.<locals>.<listcomp>c S s& g | ]}|j rt|tttf�s|�qS r. )r rV r� r r� r= r. r. r/ r0 � s ���c S �( g | ]}t |t�r|jj|jd d��qS �T)r )rV r� r� r r� r= r. r. r/ r0 � � ��c S r� r� )rV r� r� r r� r= r. r. r/ r0 � r� c S s g | ] }t |tttf�s|�qS r. )rV r� r� r� r= r. r. r/ r0 � s ��FTr� r c S r� rE r� r� r. r. r/ r� r� z Each.parseImpl.<locals>.<lambda>r� r c S r� rE r� r� r. r. r/ r� ! r� r c S r0 r. r� r= r. r. r/ r0 & r2 z'Missing one or more required elements (r� c s$ g | ]}t |t�r|j� v r|�qS r. r� r= ��tmpOptr. r/ r0 . s $ )r� r� r� �opt1map� optionals�multioptionals� multirequired�requiredr4 rb r� r� r� r r� r6 r+ �removerF r� r� r� r r' )r� r� r� r �opt1�opt2�tmpLoc�tmpReqd�multis� matchOrder� keepMatching�failedr� �tmpExprsr> r� r� �missing� total_resultsr� r. r� r/ rM � s� �� ��� � � �� � zEach.parseImplrv c C r� )Nr� z & c s r, rE r� r= r. r. r/ r� 8 r/ z,Each._generateDefaultName.<locals>.<genexpr>r� r� r r. r. r/ r 7 r� zEach._generateDefaultNamer� r� r� r� r� ) r2 r3 r4 r5 r� r� r� rM r r� r. r. r� r/ r� � s :� Wr� c s� e Zd ZdZd%d&� fd d � Zd'd d �Zd(dd�Zd(d)� fdd� Zd(d)� fdd� Zd*� fdd� Z d*� fdd� Z dd � Z d+d,d d �Z d-d!d"�Z ed#e�Zed$e�Z� ZS ).�ParseElementEnhancezfAbstract subclass of :class:`ParserElement`, for combining and post-processing parsed tokens. Fr� �Union[ParserElement, str]r� rg rC rD c s� t � �|� t|t�r1t�t|�}t| jt �r | �|�}ntt | �| j�r*t |�}n| �t |��}t�t |�}|| _ |d urd|j| _|j| _| j|j|jd� |j| _|j| _|j| _| j�|j� d S d S )Nrl )r� r� rV r" r� r rv � issubclassr� r� r� rK ru r� r� r r� r� r� r� r� r� r� r� r )r� r� r� �expr_strr� r. r/ r� @ s* ��z ParseElementEnhance.__init__r c C s | j d ur | j gS g S rE �r� r r. r. r/ r W r� zParseElementEnhance.recurseTc C s� | j d u r t||d| ��z | j j|||dd�W S ty � tyN } z$|jp*||_|jp0||_|jp6| |_t| t �sI| j d urI| j rI| j |_ � d }~ww )NzNo expression definedFr� ) r� r� r' r� ro �pstrr� r� rV �Forwardr� r� r� )r� r� r� r �pber. r. r/ rM Z s ��z ParseElementEnhance.parseImplr� ru c �6 t � �|� |r| jd ur| j�� | _| j�|� | S rE )r� r� r� r r� r� r. r/ r� k � z$ParseElementEnhance.leave_whitespacec r rE )r� r� r� r r� r� r. r/ r� t r z%ParseElementEnhance.ignore_whitespacec s@ t |t�r || jvr t� �|� | jd ur | j�| jd � | S r� )rV r� r� r� r� r� r� r� r. r/ r� } s zParseElementEnhance.ignorec s" t � �� | jd ur| j�� | S rE )r� r� r� r r� r. r/ r� � s z ParseElementEnhance.streamlinec C sF | |v r t || g ��|d d � | g }| jd ur!| j�|� d S d S rE )�RecursiveGrammarExceptionr� r )r� r r r. r. r/ r � s �z#ParseElementEnhance._checkRecursionNc C sR t jdtdd� |d u rg }|d d � | g }| jd ur"| j�|� | �g � d S r� �r r? r r� r r �r� r r� r. r. r/ r � s � z ParseElementEnhance.validaterv c C r� r� )r� r2 r� r r. r. r/ r � r� z(ParseElementEnhance._generateDefaultNamer� r� r� �r� r r� rg rC rD r� r� r� r� rE rJ r� )r2 r3 r4 r5 r� r rM r� r� r� r� r r r r r� r� r� r. r. r� r/ r ; s r c sV e Zd ZdZG dd� de�ZG dd� de�Zddd�d� fdd�Zdddd�Z� Z S )r� z� Expression to match one or more expressions at a given indentation level. Useful for parsing text where structure is implied by indentation (like Python source code). c � e Zd Zd� fdd� Z� ZS )zIndentedBlock._Indent�ref_colr� rC rD c �, t � �� d� � �| _| �� fdd�� d S )Nzexpected indent at column c s t || �� kS rE �r� r� �r r. r/ r� � � z0IndentedBlock._Indent.__init__.<locals>.<lambda>�r� r� r� r: �r� r r� r r/ r� � � z IndentedBlock._Indent.__init__�r r� rC rD rp r. r. r� r/ �_Indent� rq r$ c r )z IndentedBlock._IndentGreaterr r� rC rD c r )Nz'expected indent at column greater than c s t || �� kS rE r r� r r. r/ r� � r z7IndentedBlock._IndentGreater.__init__.<locals>.<lambda>r r! r� r r/ r� � r" z%IndentedBlock._IndentGreater.__init__r# rp r. r. r� r/ �_IndentGreater� rq r% FT�r� �groupedr� ru r� rg r' rC rD c s& t � j|dd� || _|| _d| _d S )NTr� r )r� r� � _recursive�_groupedr� )r� r� r� r' r� r. r/ r� � s zIndentedBlock.__init__rJ c C s� t � �||�}| jj|||d� t||�}| �|�}t � | | j }| jrE| �|�}t| j| j| j d�} | � | j � || _ |t || �7 }|�dtt|��dd � �� � d|� �� t|�} | �| j �t� B } | j rmt} ndd� } | | �t| � �|||�S )Nra r& zinner ����@c S � | S rE r. r r. r. r/ r� � r� z)IndentedBlock.parseImpl.<locals>.<lambda>)r� rI r� rb r� r$ r( r% r� r) r� r� r� r� r �hexr+ r� r� r� �Group�OptionalrM ) r� r� r� r � anchor_loc� indent_col�peer_detect_expr� inner_expr� sub_indent� nested_block�block�trailing_undentr� r. r. r/ rM � s, � *�zIndentedBlock.parseImpl)r� ru r� rg r' rg rC rD r� r� ) r2 r3 r4 r5 r� r$ r% r� rM r� r. r. r� r/ r� � s � r� c �2 e Zd ZdZd � fdd� Zd d� fd d � Z� ZS )� AtStringStartz�Matches if expression matches at the beginning of the parse string:: AtStringStart(Word(nums)).parse_string("123") # prints ["123"] AtStringStart(Word(nums)).parse_string(" 123") # raises ParseException r� r rC rD c � t � �|� d| _d S �NF�r� r� r� �r� r� r� r. r/ r� � � zAtStringStart.__init__TrJ c s$ |dkr t ||d��t� �|||�S )Nr znot found at string start)r� r� rM rL r� r. r/ rM � s zAtStringStart.parseImpl�r� r rC rD r� r� r� r. r. r� r/ r9 � s r9 c r8 )� AtLineStarta� Matches if an expression matches at the beginning of a line within the parse string Example:: test = '''\ AAA this line AAA and this line AAA but not this one B AAA and definitely not this one ''' for t in (AtLineStart('AAA') + rest_of_line).search_string(test): print(t) prints:: ['AAA', ' this line'] ['AAA', ' and this line'] r� r rC rD c r: r; r< r= r� r. r/ r� r> zAtLineStart.__init__TrJ c s* t ||�dkr t||d��t� �|||�S )Nr znot found at line start)r� r� r� rM rL r� r. r/ rM s zAtLineStart.parseImplr? r� r� r� r. r. r� r/ r@ � s r@ c s. e Zd ZdZd � fdd� Zd dd d �Z� ZS )� FollowedByac Lookahead matching of the given parse expression. ``FollowedBy`` does *not* advance the parsing position within the input string, it only verifies that the specified parse expression matches at the current position. ``FollowedBy`` always returns a null token list. If any results names are defined in the lookahead expression, those *will* be returned for access by name. Example:: # use FollowedBy to match a label only if it is followed by a ':' data_word = Word(alphas) label = data_word + FollowedBy(':') attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) attr_expr[1, ...].parse_string("shape: SQUARE color: BLACK posn: upper left").pprint() prints:: [['shape', 'SQUARE'], ['color', 'BLACK'], ['posn', 'upper left']] r� r rC rD c r: r �r� r� r� r= r� r. r/ r� 6 r> zFollowedBy.__init__TrJ c C s( | j j|||d�\}}|d d �= ||fS �Nra )r� r' )r� r� r� r r( r� r. r. r/ rM : s zFollowedBy.parseImplr? r� r� r� r. r. r� r/ rA s rA c s0 e Zd ZdZdd� fd d � Zddd d�Z� ZS )� PrecededBya� Lookbehind matching of the given parse expression. ``PrecededBy`` does not advance the parsing position within the input string, it only verifies that the specified parse expression matches prior to the current position. ``PrecededBy`` always returns a null token list, but if a results name is defined on the given expression, it is returned. Parameters: - ``expr`` - expression that must match prior to the current parse location - ``retreat`` - (default= ``None``) - (int) maximum number of characters to lookbehind prior to the current parse location If the lookbehind expression is a string, :class:`Literal`, :class:`Keyword`, or a :class:`Word` or :class:`CharsNotIn` with a specified exact or maximum length, then the retreat parameter is not required. Otherwise, retreat must be specified to give a maximum number of characters to look back from the current parse position for a lookbehind match. Example:: # VB-style variable names with type prefixes int_var = PrecededBy("#") + pyparsing_common.identifier str_var = PrecededBy("$") + pyparsing_common.identifier r r� r �retreatr� rC rD c s� t � �|� | �� �� | _d| _d| _d| _t|t�r)t � t |�}t |�}d| _n+t|t tf�r7|j}d| _n t|ttf�rJ|jtkrJ|j}d| _n t|t�rTd}d| _|| _d|� �| _d| _| j�dd� � d S )NTFr znot preceded by c S s |� td d ��S rE )� __delitem__r� r� r. r. r/ r� w s z%PrecededBy.__init__.<locals>.<lambda>)r� r� r� r� r� r� r� rV r" r� r rv rF rK r� r� r� r_ r� r� rn rE r� r� r� r )r� r� rE r� r. r/ r� a s, zPrecededBy.__init__TrJ c C s� | j r"|| jk rt||| j| ��|| j }| j�||�\}}||fS | jt� }|td|| j �|� }t||| j| �} tdt || jd �d �D ])} z|�|t |�| �\}}W n t ym } z| } W Y d } ~ qId } ~ ww ||fS | �r� ) r� rE r� r� r� r' r� r� rM r� rF ro ) r� r� r� r r� r( r� � test_expr�instring_slice� last_expr�offsetr r. r. r/ rM y s& ���zPrecededBy.parseImplr� )r� r rE r� rC rD )r Tr� r� r. r. r� r/ rD C s rD c @ s e Zd ZdZdd dd�ZdS ) �Locateda� Decorates a returned token with its starting and ending locations in the input string. This helper adds the following results names: - ``locn_start`` - location where matched expression begins - ``locn_end`` - location where matched expression ends - ``value`` - the actual parsed results Be careful if the input text contains ``<TAB>`` characters, you may want to call :class:`ParserElement.parse_with_tabs` Example:: wd = Word(alphas) for match in Located(wd).search_string("ljsdf123lksdjjf123lkkjj1222"): print(match) prints:: [0, ['ljsdf'], 5] [8, ['lksdjjf'], 15] [18, ['lkkjj'], 23] TrC rJ c C sZ |}| j j|||dd�\}}t|||g�}||d< ||d< ||d< | jr)||gfS ||fS )NFr� � locn_startr �locn_end)r� r' r r� )r� r� r� r r� r[ r] r. r. r/ rM � s zLocated.parseImplNr� r� )r2 r3 r4 r5 rM r. r. r. r/ rK � s rK c s8 e Zd ZdZd� fdd� Zddd d �Zdd d�Z� ZS )r� a� Lookahead to disallow matching with the given parse expression. ``NotAny`` does *not* advance the parsing position within the input string, it only verifies that the specified parse expression does *not* match at the current position. Also, ``NotAny`` does *not* skip over leading whitespace. ``NotAny`` always returns a null token list. May be constructed using the ``'~'`` operator. Example:: AND, OR, NOT = map(CaselessKeyword, "AND OR NOT".split()) # take care not to mistake keywords for identifiers ident = ~(AND | OR | NOT) + Word(alphas) boolean_term = Opt(NOT) + ident # very crude boolean expression - to support parenthesis groups and # operation hierarchy, use infix_notation boolean_expr = boolean_term + ((AND | OR) + boolean_term)[...] # integers that are followed by "." are actually floats integer = Word(nums) + ~Char(".") r� r rC rD c s* t � �|� d| _d| _d| j� �| _d S )NFTzFound unwanted token, )r� r� r� r� r� r� r= r� r. r/ r� � s zNotAny.__init__TrJ c C s* | j j|||d�rt||| j| ��|g fS rC )r� rc r� r� rL r. r. r/ rM � s zNotAny.parseImplrv c C � d| j � d�S )Nz~{r� r r r. r. r/ r � r/ zNotAny._generateDefaultNamer? r� r� r� �r2 r3 r4 r5 r� rM r r� r. r. r� r/ r� � s r� c sN e Zd Z ddd�d� fd d �Zdd d�Zdddd�Zdd� fdd� Z� ZS ) r� N�r� r� �Union[str, ParserElement]r� r5 r� rC rD c s@ t � �|� |p |}d| _|}t|t�r| �|�}| �|� d S r )r� r� r� rV r" r� r� )r� r� r� r� �enderr� r. r/ r� � s z_MultipleMatch.__init__ru c C s2 t |t�r | �|�}|d ur| | _| S d | _| S rE )rV r" r� � not_ender)r� rR r. r. r/ r� � s �z_MultipleMatch.stopOnTrJ c C s� | j j}| j}d}| jd ur| jj}d}|r|||� ||||�\}}z$| j } |r1|||� | r9|||�} n|} ||| |�\}} || 7 }q* ttfyU Y ||fS w )NFT)r� r' rD rS rb r� r� r� ) r� r� r� r �self_expr_parse�self_skip_ignorables� check_ender� try_not_enderr[ �hasIgnoreExprsr� � tmptokensr. r. r/ rM � s0 � �z_MultipleMatch.parseImplFc s� t jr<tj| jvr<| jg| j�� D ])}t|t�r;|jr;tj|jvr;d|�dt | �j � d|j�d�}t j |dd� nqt � �||�S r� )r< rL rU r r� r rV ru r� r� r2 r r? r� r r� r� r. r/ r s2 ����������z _MultipleMatch._setResultsNamerE �r� rQ r� r5 r� r5 rC rD r� r� r� r� )r2 r3 r4 r� r� rM r r� r. r. r� r/ r� � s �� r� c @ s e Zd ZdZddd�ZdS )r� au Repetition of one or more of the given expression. Parameters: - ``expr`` - expression that must match one or more times - ``stop_on`` - (default= ``None``) - expression for a terminating sentinel (only required if the sentinel would ordinarily match the repetition expression) Example:: data_word = Word(alphas) label = data_word + FollowedBy(':') attr_expr = Group(label + Suppress(':') + OneOrMore(data_word).set_parse_action(' '.join)) text = "shape: SQUARE posn: upper left color: BLACK" attr_expr[1, ...].parse_string(text).pprint() # Fail! read 'color' as data instead of next label -> [['shape', 'SQUARE color']] # use stop_on attribute for OneOrMore to avoid reading label string as part of the data attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) OneOrMore(attr_expr).parse_string(text).pprint() # Better -> [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'BLACK']] # could also be written as (attr_expr * (1,)).parse_string(text).pprint() rC rv c C rN )Nr� z}...r r r. r. r/ r R r/ z OneOrMore._generateDefaultNameNr� )r2 r3 r4 r5 r r. r. r. r/ r� 6 s r� c sF e Zd ZdZ ddd�d� fd d �Zdd� fdd� Zddd�Z� ZS )r� ap Optional repetition of zero or more of the given expression. Parameters: - ``expr`` - expression that must match zero or more times - ``stop_on`` - expression for a terminating sentinel (only required if the sentinel would ordinarily match the repetition expression) - (default= ``None``) Example: similar to :class:`OneOrMore` NrP r� rQ r� r5 r� rC rD c s t � j||p|d� d| _d S )NrP TrB )r� r� r� r� r� r. r/ r� d s zZeroOrMore.__init__TrJ c s< z t � �|||�W S ttfy |tg | jd�f Y S w )Nr )r� rM r� r� r r� rL r� r. r/ rM n s �zZeroOrMore.parseImplrv c C rN )Nr� �]...r r r. r. r/ r t r/ z ZeroOrMore._generateDefaultNamerE rZ r� r� r� rO r. r. r� r/ r� V s �� r� c s8 e Zd Z ddd�d� fdd�Zddd�Z� ZS )� DelimitedListr� FN)�allow_trailing_delimr� rQ �delim�combinerg r� r� r� r] rC rD c s t |t�r t�|�}t�t|�}|dur |dk r td��|dur,|dur,||k r,td��|| _t|�| _ || _ || _ |sAt |�| _ |pDd| _ || _|| _| j| j | j | j d | jdu r^dn| jd f }| jrp|t| j �7 }| j rwt|�}t� j|dd� dS )aa Helper to define a delimited list of expressions - the delimiter defaults to ','. By default, the list elements and delimiters can have intervening whitespace, and comments, but this can be overridden by passing ``combine=True`` in the constructor. If ``combine`` is set to ``True``, the matching tokens are returned as a single token string, with the delimiters included; otherwise, the matching tokens are returned as a list of tokens, with the delimiters suppressed. If ``allow_trailing_delim`` is set to True, then the list may end with a delimiter. Example:: DelimitedList(Word(alphas)).parse_string("aa,bb,cc") # -> ['aa', 'bb', 'cc'] DelimitedList(Word(hexnums), delim=':', combine=True).parse_string("AA:BB:CC:DD:EE") # -> ['AA:BB:CC:DD:EE'] Nr zmin must be greater than 0z)max must be greater than, or equal to minTr� )rV r" ru r� r� r r� �contentrv � raw_delimr^ r_ r� r� r� r] r� �Combiner� r� )r� r� r^ r_ r� r� r] �delim_list_exprr� r. r/ r� y s2 �zDelimitedList.__init__rv c C s" | j �� }|� d| j� d|� d�S )Nz [r� r[ )r` r� ra )r� � content_exprr. r. r/ r � s z"DelimitedList._generateDefaultName)r� FNN)r� rQ r^ rQ r_ rg r� r� r� r� r] rg rC rD r� r� r. r. r� r/ r\ x s ��;r\ c @ s e Zd Zdd� Zdd� ZdS )� _NullTokenc C r� r; r. r r. r. r/ �__bool__� rR z_NullToken.__bool__c C r� )Nrk r. r r. r. r/ r � rR z_NullToken.__str__N)r2 r3 r4 rf r r. r. r. r/ re � s re c sB e Zd ZdZe� Zefd� fdd � Zddd d �Zddd�Z� Z S )r� aO Optional matching of the given expression. Parameters: - ``expr`` - expression that must match zero or more times - ``default`` (optional) - value to be returned if the optional expression is not found. Example:: # US postal code can be a 5-digit zip, plus optional 4-digit qualifier zip = Combine(Word(nums, exact=5) + Opt('-' + Word(nums, exact=4))) zip.run_tests(''' # traditional ZIP code 12345 # ZIP+4 form 12101-0001 # invalid ZIP 98765- ''') prints:: # traditional ZIP code 12345 ['12345'] # ZIP+4 form 12101-0001 ['12101-0001'] # invalid ZIP 98765- ^ FAIL: Expected end of text (at char 5), (line:1, col:6) r� r �defaultr rC rD c s* t � j|dd� | jj| _|| _d| _d S )NFr� T)r� r� r� r� � defaultValuer� )r� r� rg r� r. r/ r� � s z Opt.__init__TrJ c C s� | j }z|j|||dd�\}}W ||fS ttfyG | j}|| jur6|jr2t|g�}|||j< n|g}ng }Y ||fS Y ||fS Y ||fS w )NFr� )r� r' r� r� rh �_Opt__optionalNotMatchedr� r )r� r� r� r � self_exprr[ � default_valuer. r. r/ rM � s( � � ���z Opt.parseImplrv c C sn t | j�}t|�dkr1|dd t|�d � dkr1|dd� }t|�dkr1|dd t|�d � dksd|� d�S )Nr r r� r� r� r� )rv r� rF r� r. r. r/ r s & &� zOpt._generateDefaultName)r� r rg r rC rD r� r� r� ) r2 r3 r4 r5 re ri r� rM r r� r. r. r� r/ r� � s '� r� c sN e Zd ZdZ ddd�d� fdd�Zdd� Z� fdd�Zddd�Z� ZS )r� a+ Token for skipping over all undefined text until the matched expression is found. Parameters: - ``expr`` - target expression marking the end of the data to be skipped - ``include`` - if ``True``, the target expression is also parsed (the skipped text and target expression are returned as a 2-element list) (default= ``False``). - ``ignore`` - (default= ``None``) used to define grammars (typically quoted strings and comments) that might contain false matches to the target expression - ``fail_on`` - (default= ``None``) define expressions that are not allowed to be included in the skipped test; if found before the target expression is found, the :class:`SkipTo` is not a match Example:: report = ''' Outstanding Issues Report - 1 Jan 2000 # | Severity | Description | Days Open -----+----------+-------------------------------------------+----------- 101 | Critical | Intermittent system crash | 6 94 | Cosmetic | Spelling error on Login ('log|n') | 14 79 | Minor | System slow when running too many reports | 47 ''' integer = Word(nums) SEP = Suppress('|') # use SkipTo to simply match everything up until the next SEP # - ignore quoted strings, so that a '|' character inside a quoted string does not match # - parse action will call token.strip() for each matched token, i.e., the description body string_data = SkipTo(SEP, ignore=quoted_string) string_data.set_parse_action(token_map(str.strip)) ticket_expr = (integer("issue_num") + SEP + string_data("sev") + SEP + string_data("desc") + SEP + integer("days_open")) for tkt in ticket_expr.search_string(report): print tkt.dump() prints:: ['101', 'Critical', 'Intermittent system crash', '6'] - days_open: '6' - desc: 'Intermittent system crash' - issue_num: '101' - sev: 'Critical' ['94', 'Cosmetic', "Spelling error on Login ('log|n')", '14'] - days_open: '14' - desc: "Spelling error on Login ('log|n')" - issue_num: '94' - sev: 'Cosmetic' ['79', 'Minor', 'System slow when running too many reports', '47'] - days_open: '47' - desc: 'System slow when running too many reports' - issue_num: '79' - sev: 'Minor' FN)�failOnr� r �includerg r� r5 �fail_onrl rC rD c sv t � �|� |p |}|| _d| _d| _|| _d| _t|t�r%| � |�| _ n|| _ d| j � �| _ t � �� | _| �� d S )NTFzNo match found for )r� r� � ignoreExprr� r� � includeMatchr� rV r" r� rl r� r� r� r� �ignorer�_update_ignorer)r� r� rm r� rn rl r� r. r/ r� N s zSkipTo.__init__c C sB | j j�� | jjD ]}| j �|� q | jr | j �| j� d S d S rE )rq r� r4 r� r� ro )r� r> r. r. r/ rr f s �zSkipTo._update_ignorerc s t � �|� | �� d S rE )r� r� rr r= r� r. r/ r� n s z SkipTo.ignoreTc C s. |}t |�}| jj}| jd ur| jjnd }| jjr | jjnd }|} | |krn|d ur/||| �r/nG|d urO| } z||| �} W n tyF Y n w | | krLn| } q6z ||| ddd� W n t t fyh | d7 } Y nw n | |ks%t ||| j | ��| }|||� } t | �} | j r�||||dd�\}} | | 7 } || fS )Nr F)r r! r� )rF r� r' rl r� rq r� rb ro r� r� r� r rp )r� r� r� r r� rG rT �self_failOn_canParseNext�ignorer_try_parse�tmploc� prev_tmploc�skiptext� skipresultr� r. r. r/ rM r sL � �� �� zSkipTo.parseImpl)FNN) r� r rm rg r� r5 rn r5 rl r5 rC rD r� ) r2 r3 r4 r5 r� rr r� rM r� r. r. r� r/ r� s @�� r� c s� e Zd ZdZ d*d+� fdd� Zd,d d �Zd,d d �Zd-� fdd� Zdd� Zd.d/� fdd� Z d.d0dd�Z d.d0dd�Z d-d d �Z d*d1d d �Z d2d!d"�Zd-� fd#d$� Zd3d-� fd&d'� Zed(e �Zed)e �Z� ZS )4r aw Forward declaration of an expression to be defined later - used for recursive grammars, such as algebraic infix notation. When the expression is known, it is assigned to the ``Forward`` variable using the ``'<<'`` operator. Note: take care when assigning to ``Forward`` not to overlook precedence of operators. Specifically, ``'|'`` has a lower precedence than ``'<<'``, so that:: fwd_expr << a | b | c will actually be evaluated as:: (fwd_expr << a) | b | c thereby leaving b and c out as parseable alternatives. It is recommended that you explicitly group the values inserted into the ``Forward``:: fwd_expr << (a | b | c) Converting to use the ``'<<='`` operator instead will avoid this problem. See :class:`ParseResults.pprint` for an example of a recursive parser created using ``Forward``. Nr� r5 rC rD c s, t jdd�d | _t� j|dd� d | _d S )NrV r� r Fr� )r� r� � caller_framer� r� � lshift_liner� r� r. r/ r� � s zForward.__init__c C s� t | d�r| `t|t�r| �|�}t|t�stS || _|j| _| jj | _ | jj | _ | j | jj | jjd� | jj| _| jj| _| j�| jj� tjdd�d | _| S )Nry rl rV r� ���)r( ry rV r" r� ru r� r� r� r� r r� r� r� r� r� r� r� r r� r� rz r� r. r. r/ � __lshift__� s$ � zForward.__lshift__c C s t |t�stS | |> S rE )rV ru r� r� r. r. r/ � __ilshift__� s zForward.__ilshift__ru c sJ t jdd�d }tjr || jkr tj| jvr tjddd� t � � |�}|S )NrV r� r{ zfwarn_on_match_first_with_lshift_operator: using '<<' operator with '|' is probably an error, use '<<='r ) r� r� r< rQ rz rU r r r? r� r� )r� r� � caller_liner� r� r. r/ r� � s � �� zForward.__or__c C sF | j d u r tjr tj| jvr!tjdt| jj | jj d� d S d S d S d S )Nzhwarn_on_assignment_to_Forward: Forward defined here but no expression attached later using '<<=' or '<<')�filenamer� ) r� r< rO rU r r � warn_explicit� UserWarningry r r� r r. r. r/ �__del__� s � ��zForward.__del__TrJ c sX | j d u r7tjr7tj| jvr7d}tjdd�}tt|�dd�D ]\}}|j |v r-|d } nq d}t j d|d� t j sBt� �|||�S t j�� t j} z | || |f \} } t| t�rZ| �| | �� fW W d � S t�y || d f} || d f} |d t||d | �f \} }| | < |r�| | | | < z t� �||d �\}}W n ty� t|t�r�� | |}}Y nw || kr�|r�| | \} } | | < | | = | | = | t�| �f Y W d � S | | = | t�|�f Y W d � S |�rz t� �||d �| | < W n t�y } z ||f | | < | | < � d }~ww ||f \} }| | < q�w 1 �s%w Y d S ) N)r� r� r� r� �� r� r )r� rV zjwarn_on_parse_using_empty_Forward: Forward expression was never assigned a value, will not parse any inputr TFz#Forward recursion without base case)r� r< rN rU r r� r� r� �reversedrA r r? ru r{ r� rM r� rd rV r� r �KeyErrorr� )r� r� r� r � parse_fnsr� ri �frmr �memo�prev_loc� prev_result�act_key�peek_key� prev_peek�new_loc�new_peekr> r� r. r/ rM s� �� �� � �� � �%�(�����zForward.parseImplr� rg c C r� r; r� r� r. r. r/ r� f � zForward.leave_whitespacec C r� r r� r� r. r. r/ r� j r� zForward.ignore_whitespacec C s$ | j sd| _ | jd ur| j�� | S r )r� r� r� r r. r. r/ r� n s zForward.streamlinec C sZ t jdtdd� |d u rg }| |vr&|d d � | g }| jd ur&| j�|� | �g � d S r� r r r. r. r/ r u s � zForward.validaterv c C sd | j }d| _ z| jd urt| j�d d� }nd}W n ty$ d}Y nw || _ t| �j� d|� �S )Nz: ...i� rD r� rE )r� r� rv r� r� r2 )r� �save_default_name� ret_stringr. r. r/ r � s � �z Forward._generateDefaultNamec s& | j d ur t� �� S t� }|| K }|S rE )r� r� r r r� r� r. r/ r � s z Forward.copyFc sP t jr!tj| jvr!| jd u r!d|�dt| �j� d�}tj|dd� t � � ||�S )Nz5warn_name_set_on_empty_Forward: setting results name r� z, expression that has no contained expressionrW r ) r< rM rU r r� r� r2 r r? r� r r� r� r. r/ r � s � ���zForward._setResultsNamer� r� rE )r� r5 rC rD )rC r r� r� r� r� rJ r� r� )r2 r3 r4 r5 r� r| r} r� r� rM r� r� r� r r r r r r� r� r� r. r. r� r/ r � s$ � _ r c s$ e Zd ZdZd d � fdd� Z� ZS ) �TokenConverterz[ Abstract subclass of :class:`ParseElementEnhance`, for converting parsed results. Fr� r rC rD c r: r; )r� r� r� �r� r� r� r� r. r/ r� � r> zTokenConverter.__init__r� r? r� r. r. r� r/ r� � s r� c sD e Zd ZdZ ddd�d� fdd�Zd� fdd� Zdd� Z� ZS )rb a� Converter to concatenate all matching tokens to a single string. By default, the matching patterns must also be contiguous in the input string; this can be disabled by specifying ``'adjacent=False'`` in the constructor. Example:: real = Word(nums) + '.' + Word(nums) print(real.parse_string('3.1416')) # -> ['3', '.', '1416'] # will also erroneously match the following print(real.parse_string('3. 1416')) # -> ['3', '.', '1416'] real = Combine(Word(nums) + '.' + Word(nums)) print(real.parse_string('3.1416')) # -> ['3.1416'] # no match when there are internal spaces print(real.parse_string('3. 1416')) # -> Exception: Expected W:(0123...) rk TN)� joinStringr� ru � join_stringrv �adjacentrg r� rf rC rD c sD t � �|� |d ur |n|}|r| �� || _d| _|| _d| _d S r )r� r� r� r� r� r� r� )r� r� r� r� r� r� r. r/ r� � s zCombine.__init__c s& | j r t�| |� | S t� �|� | S rE )r� ru r� r� r� r� r. r/ r� � s �zCombine.ignorec C sL |� � }|d d �= |td�|�| j��g| jd�7 }| jr$|�� r$|gS |S )Nrk )rU )r r r� � _asStringListr� r� r� �haskeys)r� r� r� rP �retToksr. r. r/ rQ � s �zCombine.postParse)rk T) r� ru r� rv r� rg r� rf rC rD r� )r2 r3 r4 r5 r� r� rQ r� r. r. r� r/ rb � s ��rb c �, e Zd ZdZd d� fd d � Zd d � Z� ZS )r. a� Converter to return the matched tokens as a list - useful for returning tokens of :class:`ZeroOrMore` and :class:`OneOrMore` expressions. The optional ``aslist`` argument when set to True will return the parsed tokens as a Python list instead of a pyparsing ParseResults. Example:: ident = Word(alphas) num = Word(nums) term = ident | num func = ident + Opt(DelimitedList(term)) print(func.parse_string("fn a, b, 100")) # -> ['fn', 'a', 'b', '100'] func = ident + Group(Opt(DelimitedList(term))) print(func.parse_string("fn a, b, 100")) # -> ['fn', ['a', 'b', '100']] Fr� ru �aslistrg rC rD c � t � �|� d| _|| _d S r )r� r� r� � _asPythonList)r� r� r� r� r. r/ r� r� zGroup.__init__c C s. | j rt�t|t�r|�� �S t|��S |gS rE )r� r �ListrV rT r� rO r. r. r/ rQ s ���zGroup.postParser� )r� ru r� rg rC rD �r2 r3 r4 r5 r� rQ r� r. r. r� r/ r. � s r. c r� )�Dictar Converter to return a repetitive expression as a list, but also as a dictionary. Each element can also be referenced using the first token in the expression as its key. Useful for tabular report scraping when the first column can be used as a item key. The optional ``asdict`` argument when set to True will return the parsed tokens as a Python dict instead of a pyparsing ParseResults. Example:: data_word = Word(alphas) label = data_word + FollowedBy(':') text = "shape: SQUARE posn: upper left color: light blue texture: burlap" attr_expr = (label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) # print attributes as plain groups print(attr_expr[1, ...].parse_string(text).dump()) # instead of OneOrMore(expr), parse using Dict(Group(expr)[1, ...]) - Dict will auto-assign names result = Dict(Group(attr_expr)[1, ...]).parse_string(text) print(result.dump()) # access named fields as dict entries, or output as dict print(result['shape']) print(result.as_dict()) prints:: ['shape', 'SQUARE', 'posn', 'upper left', 'color', 'light blue', 'texture', 'burlap'] [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']] - color: 'light blue' - posn: 'upper left' - shape: 'SQUARE' - texture: 'burlap' SQUARE {'color': 'light blue', 'posn': 'upper left', 'texture': 'burlap', 'shape': 'SQUARE'} See more examples at :class:`ParseResults` of accessing fields by results name. Fr� ru �asdictrg rC rD c r� r )r� r� r� � _asPythonDict)r� r� r� r� r. r/ r� G r� z Dict.__init__c C s& t |�D ]w\}}t|�dkrq|d }t|t�r t|��� }t|�dkr,td|�||< qt|�dkrCt|d t�sCt|d |�||< qz|�� }W n t yW t d�}|d �w |d= t|�dksjt|t�rr|� � rrt||�||< qt|d |�||< q| j r�| j r�|�� gS |�� S | j r�|gS |S )Nr r rk rV zdcould not extract dict values from parsed results - Dict expression must contain Grouped expressions)r� rF rV r� rv rH r r r r� r� r� r� r� �as_dict) r� r� r� rP ri �tok�ikey� dictvaluer� r. r. r/ rQ L s: �� ��zDict.postParser� )r� ru r� rg rC rD r� r. r. r� r/ r� s )r� c sR e Zd ZdZdd� fd d � Zd� fd d � Zd� fdd� Zdd� Zddd�Z� Z S )r� a� Converter for ignoring the results of a parsed expression. Example:: source = "a, b, c,d" wd = Word(alphas) wd_list1 = wd + (',' + wd)[...] print(wd_list1.parse_string(source)) # often, delimiters that are useful during parsing are just in the # way afterward - use Suppress to keep them out of the parsed output wd_list2 = wd + (Suppress(',') + wd)[...] print(wd_list2.parse_string(source)) # Skipped text (using '...') can be suppressed as well source = "lead in START relevant text END trailing text" start_marker = Keyword("START") end_marker = Keyword("END") find_body = Suppress(...) + start_marker + ... + end_marker print(find_body.parse_string(source) prints:: ['a', ',', 'b', ',', 'c', ',', 'd'] ['a', 'b', 'c', 'd'] ['START', 'relevant text ', 'END'] (See also :class:`DelimitedList`.) Fr� r r� rg rC rD c s" |du r t t� �}t� �|� d S )N.)r� r� r� r� r� r� r. r/ r� � s zSuppress.__init__ru c s( t | jt�rtt|��| S t� �|�S rE )rV r� r� r� r� r� r� r� r� r. r/ r� � � zSuppress.__add__c s( t | jt�rtt|��| S t� �|�S rE )rV r� r� r� r� r� r� r� r� r. r/ r� � r� zSuppress.__sub__c C r rE r. rO r. r. r/ rQ � rR zSuppress.postParsec C r, rE r. r r. r. r/ r� � rR zSuppress.suppressr� r r� ) r2 r3 r4 r5 r� r� r� rQ r� r� r. r. r� r/ r� t s r� r& c s t � �� � fdd�}� j|_|S )as Decorator for debugging parse actions. When the parse action is called, this decorator will print ``">> entering method-name(line:<current_source_line>, <parse_location>, <matched_tokens>)"``. When the parse action completes, the decorator will print ``"<<"`` followed by the returned value, or any exception that the parse action raised. Example:: wd = Word(alphas) @trace_parse_action def remove_duplicate_chars(tokens): return ''.join(sorted(set(''.join(tokens)))) wds = wd[1, ...].set_parse_action(remove_duplicate_chars) print(wds.parse_string("slkdjs sld sldd sdlf sdljf")) prints:: >>entering remove_duplicate_chars(line: 'slkdjs sld sldd sdlf sdljf', 0, (['slkdjs', 'sld', 'sldd', 'sdlf', 'sdljf'], {})) <<leaving remove_duplicate_chars (ret: 'dfjkls') ['dfjkls'] c s� � j }| dd � \}}}t| �dkr t| d �j � d|� �}tj�d|� dt||��d|� d|�d� � z� | � }W n tyZ } ztj�d |� d t|�j � d |� d�� � d }~ww tj�d |� d |�d�� |S ) N���rW r �.z >>entering z(line: r z) z <<leaving z (exception: rE z (ret: )r2 rF r� rL �stderrrN r� r� )�paArgs�thisFuncr� r� r� r� r� �r& r. r/ �z� s , ���z trace_parse_action.<locals>.z)r� r2 )r& r� r. r� r/ �trace_parse_action� s r� �empty� line_start�line_end� string_start� string_endz \\[\\[\]\/\-\*\.\$\+\^\?()~ ]c C s |d d S r� r. r� r. r. r/ r� � s r� z\\0?[xX][0-9a-fA-F]+c C s t t|d �d�d��S )Nr z\0xr )rY r� rQ r� r. r. r/ r� � r� z \\0[0-7]+c C s t t|d dd � d��S )Nr r rU )rY r� r� r. r. r/ r� � r1 z\])r� r� r� r� �negate�bodyr� r� c sR dd� � zd� � fdd�t�| �jD ��W S ty( } zW Y d}~dS d}~ww )a Helper to easily define string ranges for use in :class:`Word` construction. Borrows syntax from regexp ``'[]'`` string range definitions:: srange("[0-9]") -> "0123456789" srange("[a-z]") -> "abcdefghijklmnopqrstuvwxyz" srange("[a-z$_]") -> "abcdefghijklmnopqrstuvwxyz$_" The input string must be enclosed in []'s, and the returned string is the expanded character set joined into a single string. The values enclosed in the []'s may be: - a single character - an escaped character with a leading backslash (such as ``\-`` or ``\]``) - an escaped hex character with a leading ``'\x'`` (``\x21``, which is a ``'!'`` character) (``\0x##`` is also supported for backwards compatibility) - an escaped octal character with a leading ``'\0'`` (``\041``, which is a ``'!'`` character) - a range of any of the above, separated by a dash (``'a-z'``, etc.) - any combination of the above (``'aeiouy'``, ``'a-zA-Z0-9_$'``, etc.) c s sH � t | t�r dd� tt| d �t| d �d �D �E d H d S | V d S )Nc s r, rE )rY r� r. r. r/ r� r/ z,srange.<locals>._expanded.<locals>.<genexpr>r r )rV r rM �ord)�pr. r. r/ � _expanded s � 2 zsrange.<locals>._expandedrk c s g | ] }� |�D ]}|�qqS r. r. )r, �partr� �r� r. r/ r0 s zsrange.<locals>.<listcomp>N)r� �_reBracketExprr� r� r� )r� r> r. r� r/ �srange� s ���r� c s, � �fdd�}t �dt �d�j�}||_|S )a^ Helper to define a parse action by mapping a function to all elements of a :class:`ParseResults` list. If any additional args are passed, they are forwarded to the given function as additional arguments after the token, as in ``hex_integer = Word(hexnums).set_parse_action(token_map(int, 16))``, which will convert the parsed data to an integer using base 16. Example (compare the last to example in :class:`ParserElement.transform_string`:: hex_ints = Word(hexnums)[1, ...].set_parse_action(token_map(int, 16)) hex_ints.run_tests(''' 00 11 22 aa FF 0a 0d 1a ''') upperword = Word(alphas).set_parse_action(token_map(str.upper)) upperword[1, ...].run_tests(''' my kingdom for a horse ''') wd = Word(alphas).set_parse_action(token_map(str.title)) wd[1, ...].set_parse_action(' '.join).run_tests(''' now is the winter of our discontent made glorious summer by this sun of york ''') prints:: 00 11 22 aa FF 0a 0d 1a [0, 17, 34, 170, 255, 10, 13, 26] my kingdom for a horse ['MY', 'KINGDOM', 'FOR', 'A', 'HORSE'] now is the winter of our discontent made glorious summer by this sun of york ['Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York'] c s � �fdd�|D �S )Nc s g | ] }�|g� �R � �qS r. r. )r, �tokn�r� r� r. r/ r0 E r� z)token_map.<locals>.pa.<locals>.<listcomp>r. r� r� r. r/ r� D s ztoken_map.<locals>.par2 r� )r� r2 )r� r� r� r� r. r� r/ � token_map s %r� c C sd t tddd� �} | d�}|du rdS t�tj|�}|j�� D ]\}}t|t �r/|j s/|� |� q dS )zy Utility to simplify mass-naming of parser elements, for generating railroad diagram with named subdiagrams. � _getframec S rg rE r. r' r. r. r/ r� T r� z#autoname_elements.<locals>.<lambda>r N) r� rL r� r �types� FrameType�f_localsr& rV ru r� r )� getframe_fn� calling_framerA �varr. r. r/ �autoname_elementsM s ��r� z4"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*�"z string enclosed in double quotesz4'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*�'z string enclosed in single quoteszdouble quoted stringzsingle quoted stringz+quoted string using single or double quotesz""""(?:[^"\\]|""(?!")|"(?!"")|\\.)*rF z"""z multiline double quoted stringz"'''(?:[^'\\]|''(?!')|'(?!'')|\\.)*z'''z multiline single quoted stringz5"(?:[^"\n\r\\]|(?:\\")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*z5'(?:[^'\n\r\\]|(?:\\')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*zPython quoted stringrV zunicode string literalz#[\0xc0-\0xd6\0xd8-\0xf6\0xf8-\0xff]z[\0xa1-\0xbf\0xd7\0xf7]c C s g | ] }t |t�r|�qS r. )rV ru )r, r) r. r. r/ r0 � s ��r r� �nullDebugAction�traceParseAction�conditionAsParseAction�tokenMap)r\ rU rC rD rJ )rc rd re rf rC rg )rW r; )r� r� r� rf r� rg rC r� r� )r� rv r� r� r� ru r� rg ) r� rv r� r� r� r� r� ru r� r r� rg ) r� rv r� r� r� ru r� r� r� rg )r& r� rC r� r] )rC r� )�� __future__r �collections.abc� collectionsr �osr� r r r r r r r r �abcr r �enumr r r r r� rL r r� r� �operatorr � functoolsr � threadingr �pathlibr �utilr r r r r r r r� r r� r � exceptions�actionsr� r r �unicoder! �maxsizer� rv �bytesr" r� r# r$ r< rU r_ rb rI rs � warnoptions�environr6 �sumrF r� r� r� rp r� r� r5 r� r� r� � GeneratorTyper� r� rJ �PostParseReturnTyperg r� r� r; r� r r �ascii_uppercase�ascii_lowercaserw �Latin1rx ry r{ r} r~ r� � printabler� r� r� r� r� r� r� r� r� r� ru r� r� r� rK r� r� r� r� r� r� r� r� r r r2 r_ rg rn rr rx r{ r} r� r� r� r� r� r� r� r� r� r r� r9 r@ rA rD rK r� r� r� r� r\ re r� r/ r� r r� rb r. r� r� r� r r� r� r� r� r� r8 � _escapedPunc�_escapedHexChar�_escapedOctChar� _singleChar� _charRanger r� r� r� r� �dbl_quoted_string�sgl_quoted_stringrP rN �python_quoted_string�unicode_string� alphas8bit�punc8bitr) �valuesr� �sglQuotedString�dblQuotedString� quotedString� unicodeString� lineStart�lineEnd� stringStart� stringEndr� r� r� r� r. r. r. r/ �<module> s� ( , " �� ��� A� ��� D) 5uW | G mPO"1 + . ) n 1n@!$Q*+M "AL 9%W 7 0 ���� ���� ) . �� �� � ���� �� �� ��� �� PK )��Z�h�� � $ __pycache__/__init__.cpython-310.pycnu �[��� o �hN# � @ s d Z ddlmZ G dd� de�Zeddddd�Zd ZejZeZd Zdd l T dd l T dd l T dd l m Z mZ dd lT dd l T dd l mZ dd lT dd lmZ ddlmZmZmZ ddlmZ ddlmZmZ de � vrleZde � vrseZde � vrzeZee e 7 Zg d�Z dS )a pyparsing module - Classes and methods to define and execute parsing grammars ============================================================================= The pyparsing module is an alternative approach to creating and executing simple grammars, vs. the traditional lex/yacc approach, or the use of regular expressions. With pyparsing, you don't need to learn a new syntax for defining grammars or matching expressions - the parsing module provides a library of classes that you use to construct the grammar directly in Python. Here is a program to parse "Hello, World!" (or any greeting of the form ``"<salutation>, <addressee>!"``), built up using :class:`Word`, :class:`Literal`, and :class:`And` elements (the :meth:`'+'<ParserElement.__add__>` operators create :class:`And` expressions, and the strings are auto-converted to :class:`Literal` expressions):: from pyparsing import Word, alphas # define grammar of a greeting greet = Word(alphas) + "," + Word(alphas) + "!" hello = "Hello, World!" print(hello, "->", greet.parse_string(hello)) The program outputs the following:: Hello, World! -> ['Hello', ',', 'World', '!'] The Python representation of the grammar is quite readable, owing to the self-explanatory class names, and the use of :class:`'+'<And>`, :class:`'|'<MatchFirst>`, :class:`'^'<Or>` and :class:`'&'<Each>` operators. The :class:`ParseResults` object returned from :class:`ParserElement.parse_string` can be accessed as a nested list, a dictionary, or an object with named attributes. The pyparsing module handles some of the problems that are typically vexing when writing text parsers: - extra or missing whitespace (the above program will also handle "Hello,World!", "Hello , World !", etc.) - quoted strings - embedded comments Getting Started - ----------------- Visit the classes :class:`ParserElement` and :class:`ParseResults` to see the base classes that most other pyparsing classes inherit from. Use the docstrings for examples of how to: - construct literal match expressions from :class:`Literal` and :class:`CaselessLiteral` classes - construct character word-group expressions using the :class:`Word` class - see how to create repetitive expressions using :class:`ZeroOrMore` and :class:`OneOrMore` classes - use :class:`'+'<And>`, :class:`'|'<MatchFirst>`, :class:`'^'<Or>`, and :class:`'&'<Each>` operators to combine simple expressions into more complex ones - associate names with your parsed results using :class:`ParserElement.set_results_name` - access the parsed data, which is returned as a :class:`ParseResults` object - find some helpful expression short-cuts like :class:`DelimitedList` and :class:`one_of` - find more useful common expressions in the :class:`pyparsing_common` namespace class � )� NamedTuplec @ sR e Zd ZU eed< eed< eed< eed< eed< edd� �Zdd � Zd d � Z d S ) � version_info�major�minor�micro� releaselevel�serialc C sR | j � d| j� d| j� �| jd dkrdnd� | jd � | j� �df| jdk S )N�.r �c�r� �final)r r r r r ��self� r �E/usr/local/CyberCP/lib/python3.10/site-packages/pyparsing/__init__.py� __version__j s (����zversion_info.__version__c C s t � d| j� dt� �S )N� z / )�__name__r �__version_time__r r r r �__str__t s zversion_info.__str__c C s4 t � dt| �j � dd�dd� t| j| �D ��� d�S )Nr �(z, c s s � | ]}d j |� V qdS )z{}={!r}N)�format)�.0�nvr r r � <genexpr>x s � z(version_info.__repr__.<locals>.<genexpr>�))r �type�join�zip�_fieldsr r r r �__repr__w s 4zversion_info.__repr__N) r � __module__� __qualname__�int�__annotations__�str�propertyr r r! r r r r r c s r � � r � z25 Mar 2025 01:38 UTCz+Paul McGuire <ptmcg.gm+pyparsing@gmail.com>)�*)�__diag__� __compat__)�_builtin_exprs)� unicode_set�UnicodeRangeList�pyparsing_unicode)�pyparsing_test)�pyparsing_commonr. r1 r3 r2 )�r r � __author__r- r, �And� AtLineStart� AtStringStart�CaselessKeyword�CaselessLiteral� CharsNotIn� CloseMatch�Combine� DelimitedList�Dict�Each�Empty� FollowedBy�Forward� GoToColumn�Group� IndentedBlock�Keyword�LineEnd� LineStart�Literal�Located� PrecededBy� MatchFirst�NoMatch�NotAny� OneOrMore�OnlyOnce�OpAssoc�Opt�Optional�Or�ParseBaseException�ParseElementEnhance�ParseException�ParseExpression�ParseFatalException� ParseResults�ParseSyntaxException� ParserElement� PositionToken� QuotedString�RecursiveGrammarException�Regex�SkipTo� StringEnd� StringStart�Suppress�Tag�Token�TokenConverter�White�Word�WordEnd� WordStart� ZeroOrMore�Char� alphanums�alphas� alphas8bit� any_close_tag� any_open_tag�autoname_elements�c_style_comment�col�common_html_entity�condition_as_parse_action� counted_array�cpp_style_comment�dbl_quoted_string�dbl_slash_comment�delimited_list�dict_of�empty�hexnums� html_comment� identchars�identbodychars�infix_notation�java_style_comment�line�line_end� line_start�lineno�make_html_tags� make_xml_tags�match_only_at_col�match_previous_expr�match_previous_literal� nested_expr�null_debug_action�nums�one_of�original_text_for� printables�punc8bitr3 r2 r1 �python_style_comment� quoted_string� remove_quotes� replace_with�replace_html_entity� rest_of_line�sgl_quoted_string�srange� string_end� string_start� token_map�trace_parse_action�ungroupr/ �unicode_string�with_attribute� with_class�__versionTime__� anyCloseTag� anyOpenTag� cStyleComment�commonHTMLEntity�conditionAsParseAction� countedArray�cppStyleComment�dblQuotedString�dblSlashComment� delimitedList�dictOf� htmlComment� indentedBlock� infixNotation�javaStyleComment�lineEnd� lineStart� locatedExpr� makeHTMLTags� makeXMLTags�matchOnlyAtCol�matchPreviousExpr�matchPreviousLiteral� nestedExpr�nullDebugAction�oneOf�opAssoc�originalTextFor�pythonStyleComment� quotedString� removeQuotes�replaceHTMLEntity� replaceWith� restOfLine�sglQuotedString� stringEnd� stringStart�tokenMap�traceParseAction� unicodeString� withAttribute� withClass�common�unicode�testingN) �__doc__�typingr r �__version_info__r r r� r4 �util� exceptions�actions�corer, r- �resultsr. �core_builtin_exprs�helpers�helper_builtin_exprsr� r/ r0 r1 r� r2 r� r3 �common_builtin_exprs�globals�__all__r r r r �<module> s8 G PK )��Z�j�J # __pycache__/actions.cpython-310.pycnu �[��� o �ha � @ s d dl mZ d dlmZmZmZ ddlmZ ddlm Z m Z ddl m Z eeg ef ee gef ee e gef eee e gef f ZG dd� d�Zd)d d�Zd*dd�Zd+dd�Zd,d d �Ze� e_d-d.d!d"�Ze d#e�Ze d$e�Ze d%e�Ze d&e�Ze d'e�Z d(S )/� )� annotations)�Union�Callable�Any� )�ParseException)�col�replaced_by_pep8)� ParseResultsc @ s, e Zd ZdZddd�Zddd�Zdd� ZdS )�OnlyOncez� Wrapper for parse actions, to ensure they are only called once. Note: parse action signature must include all 3 arguments. � method_call�'Callable[[str, int, ParseResults], Any]�return�Nonec C s ddl m} ||�| _d| _d S )Nr )� _trim_arityF)�corer �callable�called)�selfr r � r �D/usr/local/CyberCP/lib/python3.10/site-packages/pyparsing/actions.py�__init__ s zOnlyOnce.__init__�s�str�l�int�tr c C s* | j s| �|||�}d| _ |S t||d��)NTz.OnlyOnce obj called multiple times w/out reset)r r r )r r r r �resultsr r r �__call__ s zOnlyOnce.__call__c C s d| _ dS )zK Allow the associated parse action to be called once more. FN)r )r r r r �reset& s zOnlyOnce.resetN)r r r r )r r r r r r r r )�__name__� __module__� __qualname__�__doc__r r r r r r r r s r �nr r � ParseActionc s d � fd d � }|S ) zt Helper method for defining parse actions that require matching at a specific column in the input text. �strgr �locnr �toksr r r c s$ t || �� krt| |d� � ���d S )Nz matched token not at column )r r )r& r' r( �r$ r r � verify_col4 s �z%match_only_at_col.<locals>.verify_colN)r& r r' r r( r r r r )r$ r* r r) r �match_only_at_col. s r+ �repl_strr c s � fdd�S )a� Helper method for common parse actions that simply return a literal value. Especially useful when used with :class:`transform_string<ParserElement.transform_string>` (). Example:: num = Word(nums).set_parse_action(lambda toks: int(toks[0])) na = one_of("N/A NA").set_parse_action(replace_with(math.nan)) term = na | num term[1, ...].parse_string("324 234 N/A 234") # -> [324, 234, nan, 234] c s � gS )Nr �r r r �r, r r �<lambda>I s z replace_with.<locals>.<lambda>r r. r r. r � replace_with; s r0 r r r r r c C s |d dd� S )a# Helper parse action for removing quotation marks from parsed quoted strings. Example:: # by default, quotation marks are included in parsed results quoted_string.parse_string("'Now is the Winter of our Discontent'") # -> ["'Now is the Winter of our Discontent'"] # use remove_quotes to strip quotation marks from parsed results quoted_string.set_parse_action(remove_quotes) quoted_string.parse_string("'Now is the Winter of our Discontent'") # -> ["Now is the Winter of our Discontent"] r r ���r r- r r r � remove_quotesL s r2 �args�tuple[str, str]c s4 g � | r � � | � n� � |�� � d � fd d � }|S ) aJ Helper to create a validating parse action to be used with start tags created with :class:`make_xml_tags` or :class:`make_html_tags`. Use ``with_attribute`` to qualify a starting tag with a required attribute value, to avoid false matches on common tags such as ``<TD>`` or ``<DIV>``. Call ``with_attribute`` with a series of attribute names and values. Specify the list of filter attributes names and values as: - keyword arguments, as in ``(align="right")``, or - as an explicit dict with ``**`` operator, when an attribute name is also a Python reserved word, as in ``**{"class":"Customer", "align":"right"}`` - a list of name-value tuples, as in ``(("ns1:class", "Customer"), ("ns2:align", "right"))`` For attribute names with a namespace prefix, you must use the second form. Attribute names are matched insensitive to upper/lower case. If just testing for ``class`` (with or without a namespace), use :class:`with_class`. To verify that the attribute exists, but without specifying a value, pass ``with_attribute.ANY_VALUE`` as the value. Example:: html = ''' <div> Some text <div type="grid">1 4 0 1 0</div> <div type="graph">1,3 2,3 1,1</div> <div>this has no type</div> </div> ''' div,div_end = make_html_tags("div") # only match div tag having a type attribute with value "grid" div_grid = div().set_parse_action(with_attribute(type="grid")) grid_expr = div_grid + SkipTo(div | div_end)("body") for grid_header in grid_expr.search_string(html): print(grid_header.body) # construct a match with any div tag having a type attribute, regardless of the value div_any_type = div().set_parse_action(with_attribute(type=with_attribute.ANY_VALUE)) div_expr = div_any_type + SkipTo(div | div_end)("body") for div_header in div_expr.search_string(html): print(div_header.body) prints:: 1 4 0 1 0 1 4 0 1 0 1,3 2,3 1,1 r r r r �tokensr r r c sb � D ],\}}||vrt | |d| ��|tjkr.|| |kr.t | |d|�d|| �d|����qd S )Nzno matching attribute z attribute z has value z , must be )r �with_attribute� ANY_VALUE)r r r5 �attrName� attrValue�� attrs_listr r �pa� s ���zwith_attribute.<locals>.paN)r r r r r5 r r r )�extend�items)r3 � attr_dictr< r r: r r6 ] s 8 r6 � � classname� namespacec C s$ |r|� d�nd}t di || i��S )a� Simplified version of :class:`with_attribute` when matching on a div class - made difficult because ``class`` is a reserved word in Python. Example:: html = ''' <div> Some text <div class="grid">1 4 0 1 0</div> <div class="graph">1,3 2,3 1,1</div> <div>this <div> has no class</div> </div> ''' div,div_end = make_html_tags("div") div_grid = div().set_parse_action(with_class("grid")) grid_expr = div_grid + SkipTo(div | div_end)("body") for grid_header in grid_expr.search_string(html): print(grid_header.body) div_any_type = div().set_parse_action(with_class(withAttribute.ANY_VALUE)) div_expr = div_any_type + SkipTo(div | div_end)("body") for div_header in div_expr.search_string(html): print(div_header.body) prints:: 1 4 0 1 0 1 4 0 1 0 1,3 2,3 1,1 z:class�classNr )r6 )rA rB � classattrr r r � with_class� s $rE � replaceWith� removeQuotes� withAttribute� withClass�matchOnlyAtColN)r$ r r r% )r, r r r% )r r r r r r r r )r3 r4 r r% )r@ )rA r rB r r r% ) � __future__r �typingr r r � exceptionsr �utilr r r r r r r% r r+ r0 r2 r6 �objectr7 rE rF rG rH rI rJ r r r r �<module> s0 �� L * PK )��Z��b�f �f # __pycache__/results.cpython-310.pycnu �[��� o �h�f � @ s� U d dl mZ d dlZd dlmZmZmZmZmZ d dl Z d dl m Z ddl m Z eefZded< ed d � d D ��ZG d d � d �ZG dd� d�Ze�e� e�e� dS )� )� annotationsN)�MutableMapping�Mapping�MutableSequence�Iterator�Iterable)�Any� )�replaced_by_pep8ztuple[type, ...]�str_typec c s � | ]}|V qd S �N� )�.0�_r r �D/usr/local/CyberCP/lib/python3.10/site-packages/pyparsing/results.py� <genexpr> s � r r c @ s> e Zd ZU ded< dgZdd d �Zd d � Zd d� Zdd� ZdS )�_ParseResultsWithOffsetztuple[ParseResults, int]�tup�p1� ParseResults�p2�int�return�Nonec C s ||f| _ d S r �r )�selfr r r r r �__init__ � z _ParseResultsWithOffset.__init__c C s | j | S r r �r �ir r r � __getitem__ � z#_ParseResultsWithOffset.__getitem__c C s | j S r r �r r r r � __getstate__ s z$_ParseResultsWithOffset.__getstate__c G s |d | _ d S �Nr r )r �argsr r r � __setstate__# r z$_ParseResultsWithOffset.__setstate__N)r r r r r r ) �__name__� __module__� __qualname__�__annotations__� __slots__r r r# r& r r r r r s r c @ s� e Zd ZU dZdg dfZded< ded< d ed< d ed < d ed < d ed< ded< dZG dd� de�Zdpdd�Z dddde fdqdd�Z dd � Z e fd d �Z d d � Zdrd!d"�Zdsd$d%�Zdrd&d'�Zdtd)d*�Zdtd+d,�Zd-d.� Zd/d0� Zd1d2� Zdrd3d4�Zd5d6� Zdud7d8�Zd9d:� Zd;d<� Zd=d>� Z d?d@� Z dAdB� Z dvdDdE�Z dvdFdG�Z dwdHdI�Z!dxdJdK�Z"dxdLdM�Z#dydOdP�Z$dQdR�dzdUdV�Z%d{dXdY�Z&dwdZd[�Z'dwd\d]�Z(d|d_d`�Z)d}dxdbdc�Z*ddde� Z+dfdg� Z,dhdi� Z-djdk� Z.dldm� Z/e0dudwdndo��Z1e%Z2 e&Z3 e)Z4dS )~r a{ Structured parse results, to provide multiple means of access to the parsed data: - as a list (``len(results)``) - by list index (``results[0], results[1]``, etc.) - by attribute (``results.<results_name>`` - see :class:`ParserElement.set_results_name`) Example:: integer = Word(nums) date_str = (integer.set_results_name("year") + '/' + integer.set_results_name("month") + '/' + integer.set_results_name("day")) # equivalent form: # date_str = (integer("year") + '/' # + integer("month") + '/' # + integer("day")) # parse_string returns a ParseResults object result = date_str.parse_string("1999/12/31") def test(s, fn=repr): print(f"{s} -> {fn(eval(s))}") test("list(result)") test("result[0]") test("result['month']") test("result.day") test("'month' in result") test("'minutes' in result") test("result.dump()", str) prints:: list(result) -> ['1999', '/', '12', '/', '31'] result[0] -> '1999' result['month'] -> '12' result.day -> '31' 'month' in result -> True 'minutes' in result -> False result.dump() -> ['1999', '/', '12', '/', '31'] - day: '31' - month: '12' - year: '1999' Nr ztuple[Any, ...]� _null_values�str�_name�_parentzset[str]� _all_names�bool�_modalz list[Any]�_toklistzdict[str, Any]�_tokdict)r. r/ r0 r2 r3 r4 c @ s e Zd ZdZddd�ZdS )zParseResults.Lista� Simple wrapper class to distinguish parsed list results that should be preserved as actual Python lists, instead of being converted to :class:`ParseResults`:: LBRACK, RBRACK = map(pp.Suppress, "[]") element = pp.Forward() item = ppc.integer element_list = LBRACK + pp.DelimitedList(element) + RBRACK # add parse actions to convert from ParseResults to actual Python collection types def as_python_list(t): return pp.ParseResults.List(t.as_list()) element_list.add_parse_action(as_python_list) element <<= item | element_list element.run_tests(''' 100 [2,3,4] [[2, 1],3,4] [(2, 1),3,4] (2,3,4) ''', post_parse=lambda s, r: (r[0], type(r[0]))) prints:: 100 (100, <class 'int'>) [2,3,4] ([2, 3, 4], <class 'list'>) [[2, 1],3,4] ([[2, 1], 3, 4], <class 'list'>) (Used internally by :class:`Group` when `aslist=True`.) Nc C s: |d u rg }t |t�st| j� dt|�j� ���t�| �S )Nz* may only be constructed with a list, not )� isinstance�list� TypeErrorr' �type�__new__)�cls� containedr r r r9 � s � zParseResults.List.__new__r )r' r( r) �__doc__r9 r r r r �Listg s &r= c K s� t |t�r|S t�| �}d |_d |_t� |_|d u r g |_n t |t t f�r8t |tj �r2|d d � gnt |�|_n|g|_t � |_ |S r )r5 r �objectr9 r. r/ �setr0 r3 r6 �_generator_typer= �dictr4 )r: �toklist�name�kwargsr r r r r9 � s ��zParseResults.__new__Tr r c C s� | || _ |d u s |dkrd S ||t�rt|�}|s |h| _|| _|| jv r(d S ||ttf�r2|g}|rV||t�rDt t|j �d�| |< n t t|d �d�| |< || | _d S z |d | |< W d S t t t fyz || urt|| |< Y d S || _Y d S w )N� r )r2 r r- r0 r. r, r r8 r r r3 �KeyErrorr7 � IndexError)r rB rC �asList�modalr5 r r r r � s4 �zParseResults.__init__c C sL t |ttf�r | j| S || jvr| j| d d S tdd� | j| D ��S )N���r c S s g | ]}|d �qS )r r �r �vr r r � <listcomp>� � z,ParseResults.__getitem__.<locals>.<listcomp>)r5 r �slicer3 r0 r4 r r r r r r � s zParseResults.__getitem__c C s� ||t �r| j�|t� �|g | j|< |d }n!||ttf�r'|| j|< |}n| j�|g �t |d�g | j|< |}||t�rC| |_d S d S r$ ) r r4 �getr6 r rO r3 r r/ )r �krL r5 �subr r r � __setitem__� s � �zParseResults.__setitem__c C s� t |ttf�s | j|= d S t| j�}| j|= t |t�r*|dk r#||7 }t||d �}tt|�|�� �}|� � | j� � D ] }|D ]}t |�D ]\}\}}t ||||k �||< qFq@q<d S )Nr r ) r5 r rO r4 �lenr3 r6 �range�indices�reverse�values� enumerater ) r r �mylen�removed� occurrences�jrQ �value�positionr r r � __delitem__� s( ����zParseResults.__delitem__c C s || j v S r �r4 )r rQ r r r � __contains__ r! zParseResults.__contains__r c C � t | j�S r )rT r3 r" r r r �__len__ r! zParseResults.__len__c C s | j p| j S r )r3 r4 r" r r r �__bool__ s zParseResults.__bool__r c C rc r ��iterr3 r" r r r �__iter__ r! zParseResults.__iter__c C s t | jd d d� �S �NrJ rf r" r r r � __reversed__ s zParseResults.__reversed__c C rc r )rg r4 r" r r r �keys r! zParseResults.keysc � � fdd�� � � D �S )Nc 3 s � | ]}� | V qd S r r �r rQ r" r r r s � z&ParseResults.values.<locals>.<genexpr>�rk r" r r" r rX � zParseResults.valuesc rl )Nc 3 s � | ] }|� | fV qd S r r rm r" r r r s � z%ParseResults.items.<locals>.<genexpr>rn r" r r" r �items ro zParseResults.itemsc C s | j S )z� Since ``keys()`` returns an iterator, this method is helpful in bypassing code that looks for the existence of any defined results names.ra r" r r r �haskeys s zParseResults.haskeysc O s� |sdg}|� � D ]\}}|dkr|d |f}q td|����t|d t�s2t|�dks2|d | v r?|d }| | }| |= |S |d }|S )a� Removes and returns item at specified index (default= ``last``). Supports both ``list`` and ``dict`` semantics for ``pop()``. If passed no argument or an integer argument, it will use ``list`` semantics and pop tokens from the list of parsed tokens. If passed a non-integer argument (most likely a string), it will use ``dict`` semantics and pop the corresponding value from any defined results names. A second default return value argument is supported, just as in ``dict.pop()``. Example:: numlist = Word(nums)[...] print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321'] def remove_first(tokens): tokens.pop(0) numlist.add_parse_action(remove_first) print(numlist.parse_string("0 123 321")) # -> ['123', '321'] label = Word(alphas) patt = label("LABEL") + Word(nums)[1, ...] print(patt.parse_string("AAB 123 321").dump()) # Use pop() in a parse action to remove named result (note that corresponding value is not # removed from list form of results) def remove_LABEL(tokens): tokens.pop("LABEL") return tokens patt.add_parse_action(remove_LABEL) print(patt.parse_string("AAB 123 321").dump()) prints:: ['AAB', '123', '321'] - LABEL: 'AAB' ['AAB', '123', '321'] rJ �defaultr z)pop() got an unexpected keyword argument r )rp r7 r5 r rT )r r% rD rQ rL �index�ret� defaultvaluer r r �pop% s (&zParseResults.popc C s || v r| | S |S )a^ Returns named result matching the given key, or if there is no such name, then returns the given ``default_value`` or ``None`` if no ``default_value`` is specified. Similar to ``dict.get()``. Example:: integer = Word(nums) date_str = integer("year") + '/' + integer("month") + '/' + integer("day") result = date_str.parse_string("1999/12/31") print(result.get("year")) # -> '1999' print(result.get("hour", "not specified")) # -> 'not specified' print(result.get("hour")) # -> None r )r �key� default_valuer r r rP ] s zParseResults.getc C sN | j �||� | j�� D ]}t|�D ]\}\}}t||||k �||< qq dS )a; Inserts new element at location index in the list of parsed tokens. Similar to ``list.insert()``. Example:: numlist = Word(nums)[...] print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321'] # use a parse action to insert the parse location in the front of the parsed results def insert_locn(locn, tokens): tokens.insert(0, locn) numlist.add_parse_action(insert_locn) print(numlist.parse_string("0 123 321")) # -> [0, '0', '123', '321'] N)r3 �insertr4 rX rY r )r rs � ins_stringr\ rQ r^ r_ r r r ry t s ���zParseResults.insertc C s | j �|� dS )a Add single element to end of ``ParseResults`` list of elements. Example:: numlist = Word(nums)[...] print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321'] # use a parse action to compute the sum of the parsed integers, and add it to the end def append_sum(tokens): tokens.append(sum(map(int, tokens))) numlist.add_parse_action(append_sum) print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321', 444] N)r3 �append)r �itemr r r r{ � s zParseResults.appendc C s( t |t�r | �|� dS | j�|� dS )a Add sequence of elements to end of ``ParseResults`` list of elements. Example:: patt = Word(alphas)[1, ...] # use a parse action to append the reverse of the matched strings, to make a palindrome def make_palindrome(tokens): tokens.extend(reversed([t[::-1] for t in tokens])) return ''.join(tokens) patt.add_parse_action(make_palindrome) print(patt.parse_string("lskdj sdlkjf lksd")) # -> 'lskdjsdlkjflksddsklfjkldsjdksl' N)r5 r �__iadd__r3 �extend)r �itemseqr r r r~ � s zParseResults.extendc C s | j dd�= | j�� dS )z7 Clear all elements and results names. N)r3 r4 �clearr" r r r r� � s zParseResults.clearc C s2 z| | W S t y |�d�rt|��Y dS w )N�__rE )rF � startswith�AttributeError)r rC r r r � __getattr__� s �zParseResults.__getattr__�otherc C s | � � }||7 }|S r )�copy)r r� rt r r r �__add__� s zParseResults.__add__c s� |s| S |j r7t| j���fdd�� |j �� }� fdd�|D �}|D ]\}}|| |< t|d t�r6| |d _q"| j|j7 _| j|jO _| S )Nc s | dk r� S | � S r$ r )�a)�offsetr r �<lambda>� rN z'ParseResults.__iadd__.<locals>.<lambda>c s4 g | ]\}}|D ]}|t |d � |d ��f�qqS )r r )r )r rQ �vlistrL )� addoffsetr r rM � s ���z)ParseResults.__iadd__.<locals>.<listcomp>r )r4 rT r3 rp r5 r r/ r0 )r r� � otheritems�otherdictitemsrQ rL r )r� r� r r} � s" � �zParseResults.__iadd__c C s" t |t�r |dkr | �� S || S r$ )r5 r r� )r r� r r r �__radd__� s zParseResults.__radd__c C s" t | �j� d| j�d| �� � d�S )N�(�, �))r8 r' r3 �as_dictr" r r r �__repr__� s "zParseResults.__repr__c C s dd� dd� | jD �� d S )N�[r� c S s& g | ]}t |t�r t|�nt|��qS r )r5 r r- �repr)r r r r r rM � s ��z(ParseResults.__str__.<locals>.<listcomp>�])�joinr3 r" r r r �__str__� s �����zParseResults.__str__rE c C sL g }| j D ] }|r|r|�|� t|t�r ||�� 7 }q|�t|�� q|S r )r3 r{ r5 r � _asStringListr- )r �sep�outr| r r r r� � s zParseResults._asStringListF)�flattenr� r6 c s, � fdd�}|rg |� ��S dd� � j D �S )a� Returns the parse results as a nested list of matching tokens, all converted to strings. If flatten is True, all the nesting levels in the returned list are collapsed. Example:: patt = Word(alphas)[1, ...] result = patt.parse_string("sldkj lsdkj sldkj") # even though the result prints in string-like form, it is actually a pyparsing ParseResults print(type(result), result) # -> <class 'pyparsing.ParseResults'> ['sldkj', 'lsdkj', 'sldkj'] # Use as_list() to create an actual list result_list = result.as_list() print(type(result_list), result_list) # -> <class 'list'> ['sldkj', 'lsdkj', 'sldkj'] c 3 sN � t �g � ��}|r%|�� }t|t�r |�|d d d� � n|V |s d S d S ri )� collections�deque�popleftr5 r � extendleft)�pr�to_visit�to_dor" r r � flattened s � �z'ParseResults.as_list.<locals>.flattenedc S s" g | ] }t |t�r |�� n|�qS r )r5 r �as_list)r �resr r r rM s ��z(ParseResults.as_list.<locals>.<listcomp>)r3 )r r� r� r r" r r� � s �zParseResults.as_listrA c s& � fdd�� t � fdd�| �� D ��S )a� Returns the named parse results as a nested dictionary. Example:: integer = Word(nums) date_str = integer("year") + '/' + integer("month") + '/' + integer("day") result = date_str.parse_string('12/31/1999') print(type(result), repr(result)) # -> <class 'pyparsing.ParseResults'> (['12', '/', '31', '/', '1999'], {'day': [('1999', 4)], 'year': [('12', 0)], 'month': [('31', 2)]}) result_dict = result.as_dict() print(type(result_dict), repr(result_dict)) # -> <class 'dict'> {'day': '1999', 'year': '12', 'month': '31'} # even though a ParseResults supports dict-like access, sometime you just need to have a dict import json print(json.dumps(result)) # -> Exception: TypeError: ... is not JSON serializable print(json.dumps(result.as_dict())) # -> {"month": "31", "day": "1999", "year": "12"} c s0 t | t�r| �� r | �� S � fdd�| D �S | S )Nc s g | ]}� |��qS r r rK ��to_itemr r rM 7 rN z9ParseResults.as_dict.<locals>.to_item.<locals>.<listcomp>)r5 r rq r� ��objr� r r r� 5 s "z%ParseResults.as_dict.<locals>.to_itemc 3 s � | ] \}}|� |�fV qd S r r �r rQ rL r� r r r ; � � z'ParseResults.as_dict.<locals>.<genexpr>)rA rp r" r r� r r� s zParseResults.as_dictc C s: t | j�}| j�� |_| j|_| j| jO _| j|_|S )a Returns a new shallow copy of a :class:`ParseResults` object. `ParseResults` items contained within the source are shared with the copy. Use :class:`ParseResults.deepcopy()` to create a copy with its own separate content values. )r r3 r4 r� r/ r0 r. )r rt r r r r� = s zParseResults.copyc C s� | � � }t| j�D ]R\}}t|t�r|�� |j|< q t|ttf�r"q t|t�rHt |�� |j|< }|� � D ]\}}t|t�rB|�� n|||< q5q t|t �r[t |�dd� |D ��|j|< q |S )zL Returns a new deep copy of a :class:`ParseResults` object. c s s& � | ]}t |t�r |�� n|V qd S r )r5 r �deepcopyrK r r r r [ s � �z(ParseResults.deepcopy.<locals>.<genexpr>) r� rY r3 r5 r r� r- �bytesr r8 rp r )r rt r r� �destrQ rL r r r r� K s" � ��zParseResults.deepcopy� str | Nonec s� � j r� j S � jr � j}|j�� }t� fdd�|D �d�S t� �dkrBt� j�dkrBtt� j�� ��d d dv rBtt� j�� ��S dS )a Returns the results name for this token expression. Useful when several different expressions might match at a particular location. Example:: integer = Word(nums) ssn_expr = Regex(r"\d\d\d-\d\d-\d\d\d\d") house_number_expr = Suppress('#') + Word(nums, alphanums) user_data = (Group(house_number_expr)("house_number") | Group(ssn_expr)("ssn") | Group(integer)("age")) user_info = user_data[1, ...] result = user_info.parse_string("22 111-22-3333 #221B") for item in result: print(item.get_name(), ':', item[0]) prints:: age : 22 ssn : 111-22-3333 house_number : 221B c 3 s. � | ]\}}|D ] \}}|� u r|V qqd S r r )r rQ r� rL �locr" r r r s � ���z(ParseResults.get_name.<locals>.<genexpr>Nr r )r rJ ) r. r/ r4 rp �nextrT rg rX rk )r �par�parent_tokdict_itemsr r" r �get_name` s �� zParseResults.get_namer c C s� g }d}|� |r|t| �� � nd� |sd�|�S | �� rktdd� | �� D ��}|D ]?\}} |r6|� |� |� |� d| � d|� d�� t| t�sR|� t | �� q+| s\|� t| �� q+|� | j ||||d d �� q+t d d� | D ��syd�|�S | } d} d} t | �D ]O\} } t| t�r�| j ||||d d �}|� | � |� | | � d | � d | � |� | |d � |� � � q�|� | � |� | | � d | � d | � |� | |d � | � � � q�d�|�S ) aM Diagnostic method for listing out the contents of a :class:`ParseResults`. Accepts an optional ``indent`` argument so that this string can be embedded in a nested display of other data. Example:: integer = Word(nums) date_str = integer("year") + '/' + integer("month") + '/' + integer("day") result = date_str.parse_string('1999/12/31') print(result.dump()) prints:: ['1999', '/', '12', '/', '31'] - day: '31' - month: '12' - year: '1999' � rE c s s � | ] \}}t |�|fV qd S r )r- r� r r r r � r� z$ParseResults.dump.<locals>.<genexpr>z z- z: r )�indent�full� include_list�_depthc s s � | ]}t |t�V qd S r )r5 r )r �vvr r r r � s � r� z]:) r{ r- r� r� rq �sortedrp r5 r r� �dump�anyrY )r r� r� r� r� r� �NLrp rQ rL �incr�nlr r� �vv_dumpr r r r� � sZ �� �2�2� zParseResults.dumpc O s t j | �� g|�R i |�� dS )a$ Pretty-printer for parsed results as a list, using the `pprint <https://docs.python.org/3/library/pprint.html>`_ module. Accepts additional positional or keyword args as defined for `pprint.pprint <https://docs.python.org/3/library/pprint.html#pprint.pprint>`_ . Example:: ident = Word(alphas, alphanums) num = Word(nums) func = Forward() term = ident | num | Group('(' + func + ')') func <<= ident + Group(Optional(DelimitedList(term))) result = func.parse_string("fna a,b,(fnb c,d,200),100") result.pprint(width=40) prints:: ['fna', ['a', 'b', ['(', 'fnb', ['c', 'd', '200'], ')'], '100']] N)�pprintr� )r r% rD r r r r� � s zParseResults.pprintc C s | j | j�� d | j| jffS r )r3 r4 r� r0 r. r" r r r r# � s ��zParseResults.__getstate__c C s* |\| _ \| _}}| _t|�| _d | _d S r )r3 r4 r. r? r0 r/ )r �stater� � inAccumNamesr r r r& s zParseResults.__setstate__c C s | j | jfS r )r3 r. r" r r r �__getnewargs__ s zParseResults.__getnewargs__c C s t t| ��t| �� � S r )�dirr8 r6 rk r" r r r �__dir__ s zParseResults.__dir__c C sr dd� }| g �}|� � D ] \}}t|t�r || j||d�7 }q || |g|||�d�7 }q |dur7| |g|d�}|S )z� Helper classmethod to construct a ``ParseResults`` from a ``dict``, preserving the name-value relations as results names. If an optional ``name`` argument is given, a nested ``ParseResults`` will be returned. c S s. zt | � W n ty Y dS w t| t� S )NF)rg � Exceptionr5 r r� r r r � is_iterable s � z+ParseResults.from_dict.<locals>.is_iterable)rC )rC rH N)rp r5 r � from_dict)r: r� rC r� rt rQ rL r r r r� s zParseResults.from_dict)NN)r r )r r1 )r r )r r r )r� r r r )r r )r r- )rE )r� r1 r r6 )r rA )r r� )rE TTr )5r' r( r) r< r, r* r+ r6 r= r9 r5 r r rS r` rb rd re rh rj rk rX rp rq rv rP ry r{ r~ r� r� r� r} r� r� r� r� r� r� r� r� r� r� r� r# r& r� r� � classmethodr� rH �asDict�getNamer r r r r ' st - 2 �' 8 " 0J r )� __future__r r� �collections.abcr r r r r r� �typingr �utilr r- r� r r* r8 r@ r r �registerr r r r �<module> s$ PK )��Z�9.( ( # __pycache__/unicode.cpython-310.pycnu �[��� o �hv) � @ sl d dl Z d dlmZ d dlmZ G dd� d�Zeeeeef ee f Z G dd� d�Z G dd � d e �Z dS ) � N)� filterfalse)�Unionc @ s e Zd Zdd� Zdd� ZdS )�_lazyclasspropertyc C s || _ |j| _|j| _d S �N)�fn�__doc__�__name__)�selfr � r �D/usr/local/CyberCP/lib/python3.10/site-packages/pyparsing/unicode.py�__init__ s z_lazyclassproperty.__init__c sl � d u rt |�� t� d�r t� fdd�� jdd � D ��r i � _| jj}|� jvr1| �� �� j|< � j| S )N�_internc 3 s" � | ] }� j t|d g �u V qdS )r N)r �getattr)�.0� superclass��clsr r � <genexpr> s � � �z-_lazyclassproperty.__get__.<locals>.<genexpr>� )�type�hasattr�any�__mro__r r r )r �objr �attrnamer r r �__get__ s � z_lazyclassproperty.__get__N)r � __module__� __qualname__r r r r r r r s r c @ s� e Zd ZU dZg Zeed< edee fdd��Z ede fdd��Z ede fdd ��Z ede fd d ��Z ede fd d ��Zede fdd��Zede fdd��Zedd� �ZdS )� unicode_seta� A set of Unicode characters, for language-specific strings for ``alphas``, ``nums``, ``alphanums``, and ``printables``. A unicode_set is defined by a list of ranges in the Unicode character set, in a class attribute ``_ranges``. Ranges can be specified using 2-tuples or a 1-tuple, such as:: _ranges = [ (0x0020, 0x007e), (0x00a0, 0x00ff), (0x0100,), ] Ranges are left- and right-inclusive. A 1-tuple of (x,) is treated as (x, x). A unicode set can also be defined using multiple inheritance of other unicode sets:: class CJK(Chinese, Japanese, Korean): pass �_ranges�returnc C s` g }| j D ] }|tu r nt|dd�D ]}|�t|d |d d �� qqtdd� t|�D ��S )Nr r r ���r c s s � | ]}t |�V qd S r )�chr�r �cr r r r ? s � z0unicode_set._chars_for_ranges.<locals>.<genexpr>)r r r �extend�range�sorted�set)r �ret�cc�rrr r r �_chars_for_ranges7 s �z unicode_set._chars_for_rangesc C � d� ttj| j��S )z+all non-whitespace characters in this range� )�joinr �str�isspacer, r r r r � printablesA � zunicode_set.printablesc C r- )z'all alphabetic characters in this ranger. )r/ �filterr0 �isalphar, r r r r �alphasF r3 zunicode_set.alphasc C r- )z*all numeric digit characters in this ranger. )r/ r4 r0 �isdigitr, r r r r �numsK r3 zunicode_set.numsc C s | j | j S )z)all alphanumeric characters in this range)r6 r8 r r r r � alphanumsP s zunicode_set.alphanumsc C s$ d� ttttj| j��td�B ��S )zVall characters in this range that are valid identifier characters, plus underscore '_'r. u� ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyzªµºÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ_)r/ r' r( r4 r0 � isidentifierr, r r r r � identcharsU s ����zunicode_set.identcharsc C s4 t dd� | jD ��}d�t|t | j�B t d�B ��S )u� all characters in this range that are valid identifier body characters, plus the digits 0-9, and · (Unicode MIDDLE DOT) c s s � | ] }d | � � r|V qdS )�_N)r: r# r r r r i s � � �z-unicode_set.identbodychars.<locals>.<genexpr>r. u 0123456789·)r( r, r/ r' r; )r �identifier_charsr r r �identbodycharsc s ��zunicode_set.identbodycharsc C s ddl m} || j| j�S )z� a pyparsing Word expression for an identifier using this range's definitions for identchars and identbodychars r )�Word)� pyparsingr? r; r> )r r? r r r � identifierp s zunicode_set.identifierN)r r r r r �UnicodeRangeList�__annotations__r �listr0 r, r2 r6 r8 r9 r; r> rA r r r r r s& r c @ s6 e Zd ZU dZdejfgZeed< G dd� de �Z G dd� de �Z G dd � d e �Z G d d � d e �Z G d d � d e �ZG dd� de �ZG dd� de �ZG dd� de �ZG dd� de �ZeZG dd� deee�ZG dd� de �ZG dd� de �ZG d d � d e �ZG d d � d e �Ze ZeZeZeZ eZ eZ eZ eZ eZ!eZ"d S )!�pyparsing_unicodezF A namespace class for defining common language unicode_sets. � r c @ � e Zd ZU dZdgZeed< dS )z(pyparsing_unicode.BasicMultilingualPlanez,Unicode set for the Basic Multilingual Plane)rF i�� r N�r r r r r rB rC r r r r �BasicMultilingualPlane� � �rI c @ �" e Zd ZU dZddgZeed< dS )zpyparsing_unicode.Latin1z/Unicode set for Latin-1 Unicode Character Range)rF �~ )� � r NrH r r r r �Latin1� � �rO c @ rG )zpyparsing_unicode.LatinAz/Unicode set for Latin-A Unicode Character Range)� i r NrH r r r r �LatinA� rJ rR c @ rG )zpyparsing_unicode.LatinBz/Unicode set for Latin-B Unicode Character Range)i� iO r NrH r r r r �LatinB� rJ rS c @ �" e Zd ZU dZg d�Zeed< dS )zpyparsing_unicode.Greekz.Unicode set for Greek Unicode Character Ranges)#)iB iE )ip iw )iz i )i� i� )i� )i� i� )i� i� )i� i� )i& i* )i^ )i` )if ij )i i )i i )i iE )iH iM )iP iW )iY )i[ )i] )i_ i} )i� i� )i� i� )i� i� )i� i� )i� i� )i� i� )i� i� )i)! )i' i' )ie� )i@ i� )i� )i � iE� )i�� i�� r NrH r r r r �Greek� � rU c @ rT )zpyparsing_unicode.Cyrillicz0Unicode set for Cyrillic Unicode Character Range))i i/ )i� i� )i+ )ix )i�- i�- )i@� ir� )it� i�� )i.� i/� r NrH r r r r �Cyrillic� rV rW c @ rT )zpyparsing_unicode.Chinesez/Unicode set for Chinese Unicode Character Range))i�. i�. )i�. i�. )i�1 i�1 )i 4 i�M )� N i� )i � i� )i � im� )ip� i� )i�o i�o )i� i� )i� i;� )i@� iH� )i i֦ )i � i4� )i@� i � )i � i�� )i�� i�� )i � i � r NrH r r r r �Chinese� rV rY c @ s^ e Zd ZdZG dd� de�ZG dd� de�ZG dd� de�ZeZeZ eZ ej ej ej Z dS ) zpyparsing_unicode.Japanesez`Unicode set for Japanese Unicode Character Range, combining Kanji, Hiragana, and Katakana rangesc @ rK )z pyparsing_unicode.Japanese.Kanjiz-Unicode set for Kanji Unicode Character Range)rX i�� )i 0 i?0 r NrH r r r r �Kanji� rP rZ c @ rT )z#pyparsing_unicode.Japanese.Hiraganaz0Unicode set for Hiragana Unicode Character Range))iA0 i�0 )�0 �0 )i�0 )ip� )i� )iP� iR� )i � r NrH r r r r �Hiragana� rV r] c @ rT )z#pyparsing_unicode.Japanese.Katakanaz1Unicode set for Katakana Unicode Character Range) )r[ i�0 )r\ i�0 )i�1 i�1 )i�2 i�2 )ie� i�� )i � )id� ig� )i� i� )i� r NrH r r r r �Katakana rV r^ N) r r r r r rZ r] r^ � 漢字� カタカナ� ひらがなr r r r r �Japanese� s ���rb c @ rT )zpyparsing_unicode.Hangulz7Unicode set for Hangul (Korean) Unicode Character Range))i i� )i.0 i/0 )i11 i�1 )i 2 i 2 )i`2 i{2 )i~2 )i`� i|� )i � i�� )i�� i�� )i�� i�� )i�� i�� )i� i� )i� i� )i� i� )i� i� r NrH r r r r �Hangul rV rc c @ s e Zd ZdZdS )zpyparsing_unicode.CJKzTUnicode set for combined Chinese, Japanese, and Korean (CJK) Unicode Character RangeN)r r r r r r r r �CJK0 s rd c @ rK )zpyparsing_unicode.Thaiz,Unicode set for Thai Unicode Character Range)i i: )i? i[ r NrH r r r r �Thai3 rP re c @ rT )zpyparsing_unicode.Arabicz.Unicode set for Arabic Unicode Character Range))i i )i i� )i i r NrH r r r r �Arabic: rV rf c @ rT )zpyparsing_unicode.Hebrewz.Unicode set for Hebrew Unicode Character Range) )i� i� )i� i� )i� i� )i � i6� )i8� i<� )i>� )i@� iA� )iC� iD� )iF� iO� r NrH r r r r �HebrewB rV rg c @ rK )z pyparsing_unicode.Devanagariz2Unicode set for Devanagari Unicode Character Range)i i )i� i�� r NrH r r r r � DevanagariP rP rh N)#r r r r �sys� maxunicoder rB rC r rI rO rR rS rU rW rY rb rc �Koreanrd re rf rg rh �BMP� العربية� 中文� кириллица� Ελληνικά� עִברִית� 日本語� 한국어� ไทย� देवनागरीr r r r rE { s: �( .rE ) ri � itertoolsr �typingr r rD �tuple�intrB r rE r r r r �<module> s \PK )��Z]A��l( l( " __pycache__/common.cpython-310.pycnu �[��� o �hi5 � @ sP d dl T d dlmZmZmZ ddlmZ G dd� d�Zdd� ee��� D �Z d S ) � )�*)� DelimitedList� any_open_tag� any_close_tag� )�datetimec @ s� e Zd ZdZee�Z ee�Z e e �� d�� e�Z e e�� d�� eed��Z ed�� d�� e�Z e� � e�d e� � e� � d�Z e�d d � � eeeed ��� e � B � d �Z e�e� ed �� d�� e�Z ed�� d�� e�Z eeB eB � d��� Z ed�� d�� e�Z ed�� d�� e�Z e e e �� d�Z ed�� d�Z! ed�� d�Z"e"de" d � d �Z#ee"de" d �d ee"de" d � � d �Z$e$�%d!d � � d"e! � d#�Z&e'e#e&B e$B � d$��� d$�Z( ed%�� d&�Z) e*dLd(e+fd)d*��Z,e*dMd(e+fd,d-��Z-ed.�� d/�Z. ed0�� d1�Z/ ed2�� d3�Z0 e1�� e2�� B Z3e*d4e+d5ed6e4fd7d8��Z5e'e6e7d9� e8� e e9d9d:� ee:d;�e;e8� d9B � � ���� � d<�Z<e=ee>�?� e<B d=d>��� d?�Z@ e*ed@d � ��ZA e*edAd � ��ZB edB�� dC�ZC e*eDdDe��ZEe*eDdEe��ZFe*eDdFe,��ZGe*eDdGe-��ZHe*eDdHe5��ZIe*eDdIeA��ZJe*eDdJeB��ZKdKS )N�pyparsing_commona7 Here are some common low-level expressions that may be useful in jump-starting parser development: - numeric forms (:class:`integers<integer>`, :class:`reals<real>`, :class:`scientific notation<sci_real>`) - common :class:`programming identifiers<identifier>` - network addresses (:class:`MAC<mac_address>`, :class:`IPv4<ipv4_address>`, :class:`IPv6<ipv6_address>`) - ISO8601 :class:`dates<iso8601_date>` and :class:`datetime<iso8601_datetime>` - :class:`UUID<uuid>` - :class:`comma-separated list<comma_separated_list>` - :class:`url` Parse actions: - :class:`convert_to_integer` - :class:`convert_to_float` - :class:`convert_to_date` - :class:`convert_to_datetime` - :class:`strip_html_tags` - :class:`upcase_tokens` - :class:`downcase_tokens` Example:: pyparsing_common.number.run_tests(''' # any int or real number, returned as the appropriate type 100 -100 +100 3.14159 6.02e23 1e-12 ''') pyparsing_common.fnumber.run_tests(''' # any int or real number, returned as float 100 -100 +100 3.14159 6.02e23 1e-12 ''') pyparsing_common.hex_integer.run_tests(''' # hex numbers 100 FF ''') pyparsing_common.fraction.run_tests(''' # fractions 1/2 -3/4 ''') pyparsing_common.mixed_integer.run_tests(''' # mixed fractions 1 1/2 -3/4 1-3/4 ''') import uuid pyparsing_common.uuid.set_parse_action(token_map(uuid.UUID)) pyparsing_common.uuid.run_tests(''' # uuid 12345678-1234-5678-1234-567812345678 ''') prints:: # any int or real number, returned as the appropriate type 100 [100] -100 [-100] +100 [100] 3.14159 [3.14159] 6.02e23 [6.02e+23] 1e-12 [1e-12] # any int or real number, returned as float 100 [100.0] -100 [-100.0] +100 [100.0] 3.14159 [3.14159] 6.02e23 [6.02e+23] 1e-12 [1e-12] # hex numbers 100 [256] FF [255] # fractions 1/2 [0.5] -3/4 [-0.75] # mixed fractions 1 [1] 1/2 [0.5] -3/4 [-0.75] 1-3/4 [1.75] # uuid 12345678-1234-5678-1234-567812345678 [UUID('12345678-1234-5678-1234-567812345678')] �integerz hex integer� z[+-]?\d+zsigned integer�/�fractionc C s | d | d S )Nr ���� )�ttr r �C/usr/local/CyberCP/lib/python3.10/site-packages/pyparsing/common.py�<lambda>� s zpyparsing_common.<lambda>�-z"fraction or mixed integer-fractionz[+-]?(?:\d+\.\d*|\.\d+)z real numberz@[+-]?(?:\d+(?:[eE][+-]?\d+)|(?:\d+\.\d*|\.\d+)(?:[eE][+-]?\d+)?)z$real number with scientific notation�numberz [+-]?\d+\.?\d*(?:[eE][+-]?\d+)?�fnumberz;(?i:[+-]?(?:(?:\d+\.?\d*(?:e[+-]?\d+)?)|nan|inf(?:inity)?))� ieee_float� identifierzK(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})(\.(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})){3}z IPv4 addressz[0-9a-fA-F]{1,4}� hex_integer�:� zfull IPv6 address)r � z::zshort IPv6 addressc C s t dd� | D ��dk S )Nc s s � | ] }t j�|�rd V qdS )r N)r � _ipv6_part�matches)�.0r r r r � <genexpr>� s � z,pyparsing_common.<lambda>.<locals>.<genexpr>� )�sum��tr r r r � s z::ffff:zmixed IPv6 addressz IPv6 addressz:[0-9a-fA-F]{2}([:.-])[0-9a-fA-F]{2}(?:\1[0-9a-fA-F]{2}){4}z MAC address�%Y-%m-%d�fmtc � � fdd�}|S )a� Helper to create a parse action for converting parsed date string to Python datetime.date Params - - fmt - format to be passed to datetime.strptime (default= ``"%Y-%m-%d"``) Example:: date_expr = pyparsing_common.iso8601_date.copy() date_expr.set_parse_action(pyparsing_common.convert_to_date()) print(date_expr.parse_string("1999-12-31")) prints:: [datetime.date(1999, 12, 31)] c s@ z t �|d � ��� W S ty } zt| |t|���d }~ww �Nr )r �strptime�date� ValueError�ParseException�str)�ss�llr �ve�r$ r r �cvt_fn s ��z0pyparsing_common.convert_to_date.<locals>.cvt_fnr �r$ r0 r r/ r �convert_to_date � z pyparsing_common.convert_to_date�%Y-%m-%dT%H:%M:%S.%fc r% )a Helper to create a parse action for converting parsed datetime string to Python datetime.datetime Params - - fmt - format to be passed to datetime.strptime (default= ``"%Y-%m-%dT%H:%M:%S.%f"``) Example:: dt_expr = pyparsing_common.iso8601_datetime.copy() dt_expr.set_parse_action(pyparsing_common.convert_to_datetime()) print(dt_expr.parse_string("1999-12-31T23:59:59.999")) prints:: [datetime.datetime(1999, 12, 31, 23, 59, 59, 999000)] c s< z t �|d � �W S ty } zt| |t|���d }~ww r& )r r' r) r* r+ )�s�lr" r. r/ r r r0 1 s ��z4pyparsing_common.convert_to_datetime.<locals>.cvt_fnr r1 r r/ r �convert_to_datetime r3 z$pyparsing_common.convert_to_datetimez7(?P<year>\d{4})(?:-(?P<month>\d\d)(?:-(?P<day>\d\d))?)?z ISO8601 datez�(?P<year>\d{4})-(?P<month>\d\d)-(?P<day>\d\d)[T ](?P<hour>\d\d):(?P<minute>\d\d)(:(?P<second>\d\d(\.\d*)?)?)?(?P<tz>Z|[+-]\d\d:?\d\d)?zISO8601 datetimez2[0-9a-fA-F]{8}(-[0-9a-fA-F]{4}){3}-[0-9a-fA-F]{12}�UUIDr5 r6 �tokensc C s t j�|d �S )a Parse action to remove HTML tags from web page HTML source Example:: # strip HTML links from normal text text = '<td>More info at the <a href="https://github.com/pyparsing/pyparsing/wiki">pyparsing</a> wiki page</td>' td, td_end = make_html_tags("TD") table_text = td + SkipTo(td_end).set_parse_action(pyparsing_common.strip_html_tags)("body") + td_end print(table_text.parse_string(text).body) Prints:: More info at the pyparsing wiki page r )r �_html_stripper�transform_string)r5 r6 r9 r r r �strip_html_tagsH s z pyparsing_common.strip_html_tags�,)� exclude_charsz � commaItem� )�defaultzcomma separated listc C � | � � S �N)�upperr! r r r r k � c C rB rC )�lowerr! r r r r n rE a� (?P<url>(?:(?:(?P<scheme>https?|ftp):)?\/\/)(?:(?P<auth>\S+(?::\S*)?)@)?(?P<host>(?!(?:10|127)(?:\.\d{1,3}){3})(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[a-z0-9\u00a1-\uffff][a-z0-9\u00a1-\uffff_-]{0,62})?[a-z0-9\u00a1-\uffff]\.)+(?:[a-z\u00a1-\uffff]{2,}\.?))(:(?P<port>\d{2,5}))?(?P<path>\/[^?# ]*)?(\?(?P<query>[^#]*))?(#(?P<fragment>\S*))?)�url�convertToInteger�convertToFloat� convertToDate�convertToDatetime� stripHTMLTags� upcaseTokens�downcaseTokensN)r# )r4 )L�__name__� __module__� __qualname__�__doc__� token_map�int�convert_to_integer�float�convert_to_float�Word�nums�set_name�set_parse_actionr �hexnumsr �Regex�signed_integerr �add_parse_action�Opt�suppress� mixed_integerr �real�sci_real� streamliner r r � identchars�identbodycharsr � ipv4_addressr �_full_ipv6_address�_short_ipv6_address� add_condition�_mixed_ipv6_address�Combine� ipv6_address� mac_address� staticmethodr+ r2 r7 � iso8601_date�iso8601_datetime�uuidr r r: � ParseResultsr< � OneOrMore�Literal�LineEnd� printables�White� FollowedBy� _commasepitemr � quoted_string�copy�comma_separated_list� upcase_tokens�downcase_tokensrG �replaced_by_pep8rH rI rJ rK rL rM rN r r r r r s( �� � ��� ����������� ���������� ����� ���.�/r c C s g | ] }t |t�r|�qS r )� isinstance� ParserElement)r �vr r r � <listcomp>� s ��r� N) �core�helpersr r r r r �vars�values�_builtin_exprsr r r r �<module> s + �PK )��Z "�-� � core.pynu �[��� # # core.py # from __future__ import annotations import collections.abc from collections import deque import os import typing from typing import ( Any, Callable, Generator, NamedTuple, Sequence, TextIO, Union, cast, ) from abc import ABC, abstractmethod from enum import Enum import string import copy import warnings import re import sys from collections.abc import Iterable import traceback import types from operator import itemgetter from functools import wraps from threading import RLock from pathlib import Path from .util import ( _FifoCache, _UnboundedCache, __config_flags, _collapse_string_to_ranges, _escape_regex_range_chars, _flatten, LRUMemo as _LRUMemo, UnboundedMemo as _UnboundedMemo, replaced_by_pep8, ) from .exceptions import * from .actions import * from .results import ParseResults, _ParseResultsWithOffset from .unicode import pyparsing_unicode _MAX_INT = sys.maxsize str_type: tuple[type, ...] = (str, bytes) # # Copyright (c) 2003-2022 Paul T. McGuire # # Permission is hereby granted, free of charge, to any person obtaining # a copy of this software and associated documentation files (the # "Software"), to deal in the Software without restriction, including # without limitation the rights to use, copy, modify, merge, publish, # distribute, sublicense, and/or sell copies of the Software, and to # permit persons to whom the Software is furnished to do so, subject to # the following conditions: # # The above copyright notice and this permission notice shall be # included in all copies or substantial portions of the Software. # # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, # EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF # MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. # IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY # CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. # from functools import cached_property class __compat__(__config_flags): """ A cross-version compatibility configuration for pyparsing features that will be released in a future version. By setting values in this configuration to True, those features can be enabled in prior versions for compatibility development and testing. - ``collect_all_And_tokens`` - flag to enable fix for Issue #63 that fixes erroneous grouping of results names when an :class:`And` expression is nested within an :class:`Or` or :class:`MatchFirst`; maintained for compatibility, but setting to ``False`` no longer restores pre-2.3.1 behavior """ _type_desc = "compatibility" collect_all_And_tokens = True _all_names = [__ for __ in locals() if not __.startswith("_")] _fixed_names = """ collect_all_And_tokens """.split() class __diag__(__config_flags): _type_desc = "diagnostic" warn_multiple_tokens_in_named_alternation = False warn_ungrouped_named_tokens_in_collection = False warn_name_set_on_empty_Forward = False warn_on_parse_using_empty_Forward = False warn_on_assignment_to_Forward = False warn_on_multiple_string_args_to_oneof = False warn_on_match_first_with_lshift_operator = False enable_debug_on_named_expressions = False _all_names = [__ for __ in locals() if not __.startswith("_")] _warning_names = [name for name in _all_names if name.startswith("warn")] _debug_names = [name for name in _all_names if name.startswith("enable_debug")] @classmethod def enable_all_warnings(cls) -> None: for name in cls._warning_names: cls.enable(name) class Diagnostics(Enum): """ Diagnostic configuration (all default to disabled) - ``warn_multiple_tokens_in_named_alternation`` - flag to enable warnings when a results name is defined on a :class:`MatchFirst` or :class:`Or` expression with one or more :class:`And` subexpressions - ``warn_ungrouped_named_tokens_in_collection`` - flag to enable warnings when a results name is defined on a containing expression with ungrouped subexpressions that also have results names - ``warn_name_set_on_empty_Forward`` - flag to enable warnings when a :class:`Forward` is defined with a results name, but has no contents defined - ``warn_on_parse_using_empty_Forward`` - flag to enable warnings when a :class:`Forward` is defined in a grammar but has never had an expression attached to it - ``warn_on_assignment_to_Forward`` - flag to enable warnings when a :class:`Forward` is defined but is overwritten by assigning using ``'='`` instead of ``'<<='`` or ``'<<'`` - ``warn_on_multiple_string_args_to_oneof`` - flag to enable warnings when :class:`one_of` is incorrectly called with multiple str arguments - ``enable_debug_on_named_expressions`` - flag to auto-enable debug on all subsequent calls to :class:`ParserElement.set_name` Diagnostics are enabled/disabled by calling :class:`enable_diag` and :class:`disable_diag`. All warnings can be enabled by calling :class:`enable_all_warnings`. """ warn_multiple_tokens_in_named_alternation = 0 warn_ungrouped_named_tokens_in_collection = 1 warn_name_set_on_empty_Forward = 2 warn_on_parse_using_empty_Forward = 3 warn_on_assignment_to_Forward = 4 warn_on_multiple_string_args_to_oneof = 5 warn_on_match_first_with_lshift_operator = 6 enable_debug_on_named_expressions = 7 def enable_diag(diag_enum: Diagnostics) -> None: """ Enable a global pyparsing diagnostic flag (see :class:`Diagnostics`). """ __diag__.enable(diag_enum.name) def disable_diag(diag_enum: Diagnostics) -> None: """ Disable a global pyparsing diagnostic flag (see :class:`Diagnostics`). """ __diag__.disable(diag_enum.name) def enable_all_warnings() -> None: """ Enable all global pyparsing diagnostic warnings (see :class:`Diagnostics`). """ __diag__.enable_all_warnings() # hide abstract class del __config_flags def _should_enable_warnings( cmd_line_warn_options: typing.Iterable[str], warn_env_var: typing.Optional[str] ) -> bool: enable = bool(warn_env_var) for warn_opt in cmd_line_warn_options: w_action, w_message, w_category, w_module, w_line = (warn_opt + "::::").split( ":" )[:5] if not w_action.lower().startswith("i") and ( not (w_message or w_category or w_module) or w_module == "pyparsing" ): enable = True elif w_action.lower().startswith("i") and w_module in ("pyparsing", ""): enable = False return enable if _should_enable_warnings( sys.warnoptions, os.environ.get("PYPARSINGENABLEALLWARNINGS") ): enable_all_warnings() # build list of single arg builtins, that can be used as parse actions # fmt: off _single_arg_builtins = { sum, len, sorted, reversed, list, tuple, set, any, all, min, max } # fmt: on _generatorType = types.GeneratorType ParseImplReturnType = tuple[int, Any] PostParseReturnType = Union[ParseResults, Sequence[ParseResults]] ParseCondition = Union[ Callable[[], bool], Callable[[ParseResults], bool], Callable[[int, ParseResults], bool], Callable[[str, int, ParseResults], bool], ] ParseFailAction = Callable[[str, int, "ParserElement", Exception], None] DebugStartAction = Callable[[str, int, "ParserElement", bool], None] DebugSuccessAction = Callable[ [str, int, int, "ParserElement", ParseResults, bool], None ] DebugExceptionAction = Callable[[str, int, "ParserElement", Exception, bool], None] alphas: str = string.ascii_uppercase + string.ascii_lowercase identchars: str = pyparsing_unicode.Latin1.identchars identbodychars: str = pyparsing_unicode.Latin1.identbodychars nums: str = "0123456789" hexnums: str = nums + "ABCDEFabcdef" alphanums: str = alphas + nums printables: str = "".join([c for c in string.printable if c not in string.whitespace]) class _ParseActionIndexError(Exception): """ Internal wrapper around IndexError so that IndexErrors raised inside parse actions aren't misinterpreted as IndexErrors raised inside ParserElement parseImpl methods. """ def __init__(self, msg: str, exc: BaseException) -> None: self.msg: str = msg self.exc: BaseException = exc _trim_arity_call_line: traceback.StackSummary = None # type: ignore[assignment] pa_call_line_synth = () def _trim_arity(func, max_limit=3): """decorator to trim function calls to match the arity of the target""" global _trim_arity_call_line, pa_call_line_synth if func in _single_arg_builtins: return lambda s, l, t: func(t) limit = 0 found_arity = False # synthesize what would be returned by traceback.extract_stack at the call to # user's parse action 'func', so that we don't incur call penalty at parse time # fmt: off LINE_DIFF = 9 # IF ANY CODE CHANGES, EVEN JUST COMMENTS OR BLANK LINES, BETWEEN THE NEXT LINE AND # THE CALL TO FUNC INSIDE WRAPPER, LINE_DIFF MUST BE MODIFIED!!!! _trim_arity_call_line = _trim_arity_call_line or traceback.extract_stack(limit=2)[-1] pa_call_line_synth = pa_call_line_synth or (_trim_arity_call_line[0], _trim_arity_call_line[1] + LINE_DIFF) def wrapper(*args): nonlocal found_arity, limit if found_arity: return func(*args[limit:]) while 1: try: ret = func(*args[limit:]) found_arity = True return ret except TypeError as te: # re-raise TypeErrors if they did not come from our arity testing if found_arity: raise else: tb = te.__traceback__ frames = traceback.extract_tb(tb, limit=2) frame_summary = frames[-1] trim_arity_type_error = ( [frame_summary[:2]][-1][:2] == pa_call_line_synth ) del tb if trim_arity_type_error: if limit < max_limit: limit += 1 continue raise except IndexError as ie: # wrap IndexErrors inside a _ParseActionIndexError raise _ParseActionIndexError( "IndexError raised in parse action", ie ).with_traceback(None) # fmt: on # copy func name to wrapper for sensible debug output # (can't use functools.wraps, since that messes with function signature) func_name = getattr(func, "__name__", getattr(func, "__class__").__name__) wrapper.__name__ = func_name wrapper.__doc__ = func.__doc__ return wrapper def condition_as_parse_action( fn: ParseCondition, message: typing.Optional[str] = None, fatal: bool = False ) -> ParseAction: """ Function to convert a simple predicate function that returns ``True`` or ``False`` into a parse action. Can be used in places when a parse action is required and :class:`ParserElement.add_condition` cannot be used (such as when adding a condition to an operator level in :class:`infix_notation`). Optional keyword arguments: - ``message`` - define a custom message to be used in the raised exception - ``fatal`` - if True, will raise :class:`ParseFatalException` to stop parsing immediately; otherwise will raise :class:`ParseException` """ msg = message if message is not None else "failed user-defined condition" exc_type = ParseFatalException if fatal else ParseException fn = _trim_arity(fn) @wraps(fn) def pa(s, l, t): if not bool(fn(s, l, t)): raise exc_type(s, l, msg) return pa def _default_start_debug_action( instring: str, loc: int, expr: ParserElement, cache_hit: bool = False ): cache_hit_str = "*" if cache_hit else "" print( ( f"{cache_hit_str}Match {expr} at loc {loc}({lineno(loc, instring)},{col(loc, instring)})\n" f" {line(loc, instring)}\n" f" {'^':>{col(loc, instring)}}" ) ) def _default_success_debug_action( instring: str, startloc: int, endloc: int, expr: ParserElement, toks: ParseResults, cache_hit: bool = False, ): cache_hit_str = "*" if cache_hit else "" print(f"{cache_hit_str}Matched {expr} -> {toks.as_list()}") def _default_exception_debug_action( instring: str, loc: int, expr: ParserElement, exc: Exception, cache_hit: bool = False, ): cache_hit_str = "*" if cache_hit else "" print(f"{cache_hit_str}Match {expr} failed, {type(exc).__name__} raised: {exc}") def null_debug_action(*args): """'Do-nothing' debug action, to suppress debugging output during parsing.""" class ParserElement(ABC): """Abstract base level parser element class.""" DEFAULT_WHITE_CHARS: str = " \n\t\r" verbose_stacktrace: bool = False _literalStringClass: type = None # type: ignore[assignment] @staticmethod def set_default_whitespace_chars(chars: str) -> None: r""" Overrides the default whitespace chars Example:: # default whitespace chars are space, <TAB> and newline Word(alphas)[1, ...].parse_string("abc def\nghi jkl") # -> ['abc', 'def', 'ghi', 'jkl'] # change to just treat newline as significant ParserElement.set_default_whitespace_chars(" \t") Word(alphas)[1, ...].parse_string("abc def\nghi jkl") # -> ['abc', 'def'] """ ParserElement.DEFAULT_WHITE_CHARS = chars # update whitespace all parse expressions defined in this module for expr in _builtin_exprs: if expr.copyDefaultWhiteChars: expr.whiteChars = set(chars) @staticmethod def inline_literals_using(cls: type) -> None: """ Set class to be used for inclusion of string literals into a parser. Example:: # default literal class used is Literal integer = Word(nums) date_str = integer("year") + '/' + integer("month") + '/' + integer("day") date_str.parse_string("1999/12/31") # -> ['1999', '/', '12', '/', '31'] # change to Suppress ParserElement.inline_literals_using(Suppress) date_str = integer("year") + '/' + integer("month") + '/' + integer("day") date_str.parse_string("1999/12/31") # -> ['1999', '12', '31'] """ ParserElement._literalStringClass = cls @classmethod def using_each(cls, seq, **class_kwargs): """ Yields a sequence of ``class(obj, **class_kwargs)`` for obj in seq. Example:: LPAR, RPAR, LBRACE, RBRACE, SEMI = Suppress.using_each("(){};") """ yield from (cls(obj, **class_kwargs) for obj in seq) class DebugActions(NamedTuple): debug_try: typing.Optional[DebugStartAction] debug_match: typing.Optional[DebugSuccessAction] debug_fail: typing.Optional[DebugExceptionAction] def __init__(self, savelist: bool = False) -> None: self.parseAction: list[ParseAction] = list() self.failAction: typing.Optional[ParseFailAction] = None self.customName: str = None # type: ignore[assignment] self._defaultName: typing.Optional[str] = None self.resultsName: str = None # type: ignore[assignment] self.saveAsList = savelist self.skipWhitespace = True self.whiteChars = set(ParserElement.DEFAULT_WHITE_CHARS) self.copyDefaultWhiteChars = True # used when checking for left-recursion self._may_return_empty = False self.keepTabs = False self.ignoreExprs: list[ParserElement] = list() self.debug = False self.streamlined = False # optimize exception handling for subclasses that don't advance parse index self.mayIndexError = True self.errmsg: Union[str, None] = "" # mark results names as modal (report only last) or cumulative (list all) self.modalResults = True # custom debug actions self.debugActions = self.DebugActions(None, None, None) # avoid redundant calls to preParse self.callPreparse = True self.callDuringTry = False self.suppress_warnings_: list[Diagnostics] = [] self.show_in_diagram = True @property def mayReturnEmpty(self): return self._may_return_empty @mayReturnEmpty.setter def mayReturnEmpty(self, value): self._may_return_empty = value def suppress_warning(self, warning_type: Diagnostics) -> ParserElement: """ Suppress warnings emitted for a particular diagnostic on this expression. Example:: base = pp.Forward() base.suppress_warning(Diagnostics.warn_on_parse_using_empty_Forward) # statement would normally raise a warning, but is now suppressed print(base.parse_string("x")) """ self.suppress_warnings_.append(warning_type) return self def visit_all(self): """General-purpose method to yield all expressions and sub-expressions in a grammar. Typically just for internal use. """ to_visit = deque([self]) seen = set() while to_visit: cur = to_visit.popleft() # guard against looping forever through recursive grammars if cur in seen: continue seen.add(cur) to_visit.extend(cur.recurse()) yield cur def copy(self) -> ParserElement: """ Make a copy of this :class:`ParserElement`. Useful for defining different parse actions for the same parsing pattern, using copies of the original parse element. Example:: integer = Word(nums).set_parse_action(lambda toks: int(toks[0])) integerK = integer.copy().add_parse_action(lambda toks: toks[0] * 1024) + Suppress("K") integerM = integer.copy().add_parse_action(lambda toks: toks[0] * 1024 * 1024) + Suppress("M") print((integerK | integerM | integer)[1, ...].parse_string("5K 100 640K 256M")) prints:: [5120, 100, 655360, 268435456] Equivalent form of ``expr.copy()`` is just ``expr()``:: integerM = integer().add_parse_action(lambda toks: toks[0] * 1024 * 1024) + Suppress("M") """ cpy = copy.copy(self) cpy.parseAction = self.parseAction[:] cpy.ignoreExprs = self.ignoreExprs[:] if self.copyDefaultWhiteChars: cpy.whiteChars = set(ParserElement.DEFAULT_WHITE_CHARS) return cpy def set_results_name( self, name: str, list_all_matches: bool = False, *, listAllMatches: bool = False ) -> ParserElement: """ Define name for referencing matching tokens as a nested attribute of the returned parse results. Normally, results names are assigned as you would assign keys in a dict: any existing value is overwritten by later values. If it is necessary to keep all values captured for a particular results name, call ``set_results_name`` with ``list_all_matches`` = True. NOTE: ``set_results_name`` returns a *copy* of the original :class:`ParserElement` object; this is so that the client can define a basic element, such as an integer, and reference it in multiple places with different names. You can also set results names using the abbreviated syntax, ``expr("name")`` in place of ``expr.set_results_name("name")`` - see :class:`__call__`. If ``list_all_matches`` is required, use ``expr("name*")``. Example:: integer = Word(nums) date_str = (integer.set_results_name("year") + '/' + integer.set_results_name("month") + '/' + integer.set_results_name("day")) # equivalent form: date_str = integer("year") + '/' + integer("month") + '/' + integer("day") """ listAllMatches = listAllMatches or list_all_matches return self._setResultsName(name, listAllMatches) def _setResultsName(self, name, list_all_matches=False) -> ParserElement: if name is None: return self newself = self.copy() if name.endswith("*"): name = name[:-1] list_all_matches = True newself.resultsName = name newself.modalResults = not list_all_matches return newself def set_break(self, break_flag: bool = True) -> ParserElement: """ Method to invoke the Python pdb debugger when this element is about to be parsed. Set ``break_flag`` to ``True`` to enable, ``False`` to disable. """ if break_flag: _parseMethod = self._parse def breaker(instring, loc, do_actions=True, callPreParse=True): # this call to breakpoint() is intentional, not a checkin error breakpoint() return _parseMethod(instring, loc, do_actions, callPreParse) breaker._originalParseMethod = _parseMethod # type: ignore [attr-defined] self._parse = breaker # type: ignore [method-assign] elif hasattr(self._parse, "_originalParseMethod"): self._parse = self._parse._originalParseMethod # type: ignore [method-assign] return self def set_parse_action(self, *fns: ParseAction, **kwargs: Any) -> ParserElement: """ Define one or more actions to perform when successfully matching parse element definition. Parse actions can be called to perform data conversions, do extra validation, update external data structures, or enhance or replace the parsed tokens. Each parse action ``fn`` is a callable method with 0-3 arguments, called as ``fn(s, loc, toks)`` , ``fn(loc, toks)`` , ``fn(toks)`` , or just ``fn()`` , where: - ``s`` = the original string being parsed (see note below) - ``loc`` = the location of the matching substring - ``toks`` = a list of the matched tokens, packaged as a :class:`ParseResults` object The parsed tokens are passed to the parse action as ParseResults. They can be modified in place using list-style append, extend, and pop operations to update the parsed list elements; and with dictionary-style item set and del operations to add, update, or remove any named results. If the tokens are modified in place, it is not necessary to return them with a return statement. Parse actions can also completely replace the given tokens, with another ``ParseResults`` object, or with some entirely different object (common for parse actions that perform data conversions). A convenient way to build a new parse result is to define the values using a dict, and then create the return value using :class:`ParseResults.from_dict`. If None is passed as the ``fn`` parse action, all previously added parse actions for this expression are cleared. Optional keyword arguments: - ``call_during_try`` = (default= ``False``) indicate if parse action should be run during lookaheads and alternate testing. For parse actions that have side effects, it is important to only call the parse action once it is determined that it is being called as part of a successful parse. For parse actions that perform additional validation, then call_during_try should be passed as True, so that the validation code is included in the preliminary "try" parses. Note: the default parsing behavior is to expand tabs in the input string before starting the parsing process. See :class:`parse_string` for more information on parsing strings containing ``<TAB>`` s, and suggested methods to maintain a consistent view of the parsed string, the parse location, and line and column positions within the parsed string. Example:: # parse dates in the form YYYY/MM/DD # use parse action to convert toks from str to int at parse time def convert_to_int(toks): return int(toks[0]) # use a parse action to verify that the date is a valid date def is_valid_date(instring, loc, toks): from datetime import date year, month, day = toks[::2] try: date(year, month, day) except ValueError: raise ParseException(instring, loc, "invalid date given") integer = Word(nums) date_str = integer + '/' + integer + '/' + integer # add parse actions integer.set_parse_action(convert_to_int) date_str.set_parse_action(is_valid_date) # note that integer fields are now ints, not strings date_str.run_tests(''' # successful parse - note that integer fields were converted to ints 1999/12/31 # fail - invalid date 1999/13/31 ''') """ if list(fns) == [None]: self.parseAction.clear() return self if not all(callable(fn) for fn in fns): raise TypeError("parse actions must be callable") self.parseAction[:] = [_trim_arity(fn) for fn in fns] self.callDuringTry = kwargs.get( "call_during_try", kwargs.get("callDuringTry", False) ) return self def add_parse_action(self, *fns: ParseAction, **kwargs: Any) -> ParserElement: """ Add one or more parse actions to expression's list of parse actions. See :class:`set_parse_action`. See examples in :class:`copy`. """ self.parseAction += [_trim_arity(fn) for fn in fns] self.callDuringTry = self.callDuringTry or kwargs.get( "call_during_try", kwargs.get("callDuringTry", False) ) return self def add_condition(self, *fns: ParseCondition, **kwargs: Any) -> ParserElement: """Add a boolean predicate function to expression's list of parse actions. See :class:`set_parse_action` for function call signatures. Unlike ``set_parse_action``, functions passed to ``add_condition`` need to return boolean success/fail of the condition. Optional keyword arguments: - ``message`` = define a custom message to be used in the raised exception - ``fatal`` = if True, will raise ParseFatalException to stop parsing immediately; otherwise will raise ParseException - ``call_during_try`` = boolean to indicate if this method should be called during internal tryParse calls, default=False Example:: integer = Word(nums).set_parse_action(lambda toks: int(toks[0])) year_int = integer.copy() year_int.add_condition(lambda toks: toks[0] >= 2000, message="Only support years 2000 and later") date_str = year_int + '/' + integer + '/' + integer result = date_str.parse_string("1999/12/31") # -> Exception: Only support years 2000 and later (at char 0), (line:1, col:1) """ for fn in fns: self.parseAction.append( condition_as_parse_action( fn, message=str(kwargs.get("message")), fatal=bool(kwargs.get("fatal", False)), ) ) self.callDuringTry = self.callDuringTry or kwargs.get( "call_during_try", kwargs.get("callDuringTry", False) ) return self def set_fail_action(self, fn: ParseFailAction) -> ParserElement: """ Define action to perform if parsing fails at this expression. Fail acton fn is a callable function that takes the arguments ``fn(s, loc, expr, err)`` where: - ``s`` = string being parsed - ``loc`` = location where expression match was attempted and failed - ``expr`` = the parse expression that failed - ``err`` = the exception thrown The function returns no value. It may throw :class:`ParseFatalException` if it is desired to stop parsing immediately.""" self.failAction = fn return self def _skipIgnorables(self, instring: str, loc: int) -> int: if not self.ignoreExprs: return loc exprsFound = True ignore_expr_fns = [e._parse for e in self.ignoreExprs] last_loc = loc while exprsFound: exprsFound = False for ignore_fn in ignore_expr_fns: try: while 1: loc, dummy = ignore_fn(instring, loc) exprsFound = True except ParseException: pass # check if all ignore exprs matched but didn't actually advance the parse location if loc == last_loc: break last_loc = loc return loc def preParse(self, instring: str, loc: int) -> int: if self.ignoreExprs: loc = self._skipIgnorables(instring, loc) if self.skipWhitespace: instrlen = len(instring) white_chars = self.whiteChars while loc < instrlen and instring[loc] in white_chars: loc += 1 return loc def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: return loc, [] def postParse(self, instring, loc, tokenlist): return tokenlist # @profile def _parseNoCache( self, instring, loc, do_actions=True, callPreParse=True ) -> tuple[int, ParseResults]: debugging = self.debug # and do_actions) len_instring = len(instring) if debugging or self.failAction: # print("Match {} at loc {}({}, {})".format(self, loc, lineno(loc, instring), col(loc, instring))) try: if callPreParse and self.callPreparse: pre_loc = self.preParse(instring, loc) else: pre_loc = loc tokens_start = pre_loc if self.debugActions.debug_try: self.debugActions.debug_try(instring, tokens_start, self, False) if self.mayIndexError or pre_loc >= len_instring: try: loc, tokens = self.parseImpl(instring, pre_loc, do_actions) except IndexError: raise ParseException(instring, len_instring, self.errmsg, self) else: loc, tokens = self.parseImpl(instring, pre_loc, do_actions) except Exception as err: # print("Exception raised:", err) if self.debugActions.debug_fail: self.debugActions.debug_fail( instring, tokens_start, self, err, False ) if self.failAction: self.failAction(instring, tokens_start, self, err) raise else: if callPreParse and self.callPreparse: pre_loc = self.preParse(instring, loc) else: pre_loc = loc tokens_start = pre_loc if self.mayIndexError or pre_loc >= len_instring: try: loc, tokens = self.parseImpl(instring, pre_loc, do_actions) except IndexError: raise ParseException(instring, len_instring, self.errmsg, self) else: loc, tokens = self.parseImpl(instring, pre_loc, do_actions) tokens = self.postParse(instring, loc, tokens) ret_tokens = ParseResults( tokens, self.resultsName, asList=self.saveAsList, modal=self.modalResults ) if self.parseAction and (do_actions or self.callDuringTry): if debugging: try: for fn in self.parseAction: try: tokens = fn(instring, tokens_start, ret_tokens) # type: ignore [call-arg, arg-type] except IndexError as parse_action_exc: exc = ParseException("exception raised in parse action") raise exc from parse_action_exc if tokens is not None and tokens is not ret_tokens: ret_tokens = ParseResults( tokens, self.resultsName, asList=self.saveAsList and isinstance(tokens, (ParseResults, list)), modal=self.modalResults, ) except Exception as err: # print "Exception raised in user parse action:", err if self.debugActions.debug_fail: self.debugActions.debug_fail( instring, tokens_start, self, err, False ) raise else: for fn in self.parseAction: try: tokens = fn(instring, tokens_start, ret_tokens) # type: ignore [call-arg, arg-type] except IndexError as parse_action_exc: exc = ParseException("exception raised in parse action") raise exc from parse_action_exc if tokens is not None and tokens is not ret_tokens: ret_tokens = ParseResults( tokens, self.resultsName, asList=self.saveAsList and isinstance(tokens, (ParseResults, list)), modal=self.modalResults, ) if debugging: # print("Matched", self, "->", ret_tokens.as_list()) if self.debugActions.debug_match: self.debugActions.debug_match( instring, tokens_start, loc, self, ret_tokens, False ) return loc, ret_tokens def try_parse( self, instring: str, loc: int, *, raise_fatal: bool = False, do_actions: bool = False, ) -> int: try: return self._parse(instring, loc, do_actions=do_actions)[0] except ParseFatalException: if raise_fatal: raise raise ParseException(instring, loc, self.errmsg, self) def can_parse_next(self, instring: str, loc: int, do_actions: bool = False) -> bool: try: self.try_parse(instring, loc, do_actions=do_actions) except (ParseException, IndexError): return False else: return True # cache for left-recursion in Forward references recursion_lock = RLock() recursion_memos: collections.abc.MutableMapping[ tuple[int, Forward, bool], tuple[int, Union[ParseResults, Exception]] ] = {} class _CacheType(typing.Protocol): """ Class to be used for packrat and left-recursion cacheing of results and exceptions. """ not_in_cache: bool def get(self, *args) -> typing.Any: ... def set(self, *args) -> None: ... def clear(self) -> None: ... class NullCache(dict): """ A null cache type for initialization of the packrat_cache class variable. If/when enable_packrat() is called, this null cache will be replaced by a proper _CacheType class instance. """ not_in_cache: bool = True def get(self, *args) -> typing.Any: ... def set(self, *args) -> None: ... def clear(self) -> None: ... # class-level argument cache for optimizing repeated calls when backtracking # through recursive expressions packrat_cache: _CacheType = NullCache() packrat_cache_lock = RLock() packrat_cache_stats = [0, 0] # this method gets repeatedly called during backtracking with the same arguments - # we can cache these arguments and save ourselves the trouble of re-parsing the contained expression def _parseCache( self, instring, loc, do_actions=True, callPreParse=True ) -> tuple[int, ParseResults]: HIT, MISS = 0, 1 lookup = (self, instring, loc, callPreParse, do_actions) with ParserElement.packrat_cache_lock: cache = ParserElement.packrat_cache value = cache.get(lookup) if value is cache.not_in_cache: ParserElement.packrat_cache_stats[MISS] += 1 try: value = self._parseNoCache(instring, loc, do_actions, callPreParse) except ParseBaseException as pe: # cache a copy of the exception, without the traceback cache.set(lookup, pe.__class__(*pe.args)) raise else: cache.set(lookup, (value[0], value[1].copy(), loc)) return value else: ParserElement.packrat_cache_stats[HIT] += 1 if self.debug and self.debugActions.debug_try: try: self.debugActions.debug_try(instring, loc, self, cache_hit=True) # type: ignore [call-arg] except TypeError: pass if isinstance(value, Exception): if self.debug and self.debugActions.debug_fail: try: self.debugActions.debug_fail( instring, loc, self, value, cache_hit=True # type: ignore [call-arg] ) except TypeError: pass raise value value = cast(tuple[int, ParseResults, int], value) loc_, result, endloc = value[0], value[1].copy(), value[2] if self.debug and self.debugActions.debug_match: try: self.debugActions.debug_match( instring, loc_, endloc, self, result, cache_hit=True # type: ignore [call-arg] ) except TypeError: pass return loc_, result _parse = _parseNoCache @staticmethod def reset_cache() -> None: ParserElement.packrat_cache.clear() ParserElement.packrat_cache_stats[:] = [0] * len( ParserElement.packrat_cache_stats ) ParserElement.recursion_memos.clear() _packratEnabled = False _left_recursion_enabled = False @staticmethod def disable_memoization() -> None: """ Disables active Packrat or Left Recursion parsing and their memoization This method also works if neither Packrat nor Left Recursion are enabled. This makes it safe to call before activating Packrat nor Left Recursion to clear any previous settings. """ ParserElement.reset_cache() ParserElement._left_recursion_enabled = False ParserElement._packratEnabled = False ParserElement._parse = ParserElement._parseNoCache @staticmethod def enable_left_recursion( cache_size_limit: typing.Optional[int] = None, *, force=False ) -> None: """ Enables "bounded recursion" parsing, which allows for both direct and indirect left-recursion. During parsing, left-recursive :class:`Forward` elements are repeatedly matched with a fixed recursion depth that is gradually increased until finding the longest match. Example:: import pyparsing as pp pp.ParserElement.enable_left_recursion() E = pp.Forward("E") num = pp.Word(pp.nums) # match `num`, or `num '+' num`, or `num '+' num '+' num`, ... E <<= E + '+' - num | num print(E.parse_string("1+2+3")) Recursion search naturally memoizes matches of ``Forward`` elements and may thus skip reevaluation of parse actions during backtracking. This may break programs with parse actions which rely on strict ordering of side-effects. Parameters: - ``cache_size_limit`` - (default=``None``) - memoize at most this many ``Forward`` elements during matching; if ``None`` (the default), memoize all ``Forward`` elements. Bounded Recursion parsing works similar but not identical to Packrat parsing, thus the two cannot be used together. Use ``force=True`` to disable any previous, conflicting settings. """ if force: ParserElement.disable_memoization() elif ParserElement._packratEnabled: raise RuntimeError("Packrat and Bounded Recursion are not compatible") if cache_size_limit is None: ParserElement.recursion_memos = _UnboundedMemo() elif cache_size_limit > 0: ParserElement.recursion_memos = _LRUMemo(capacity=cache_size_limit) # type: ignore[assignment] else: raise NotImplementedError(f"Memo size of {cache_size_limit}") ParserElement._left_recursion_enabled = True @staticmethod def enable_packrat( cache_size_limit: Union[int, None] = 128, *, force: bool = False ) -> None: """ Enables "packrat" parsing, which adds memoizing to the parsing logic. Repeated parse attempts at the same string location (which happens often in many complex grammars) can immediately return a cached value, instead of re-executing parsing/validating code. Memoizing is done of both valid results and parsing exceptions. Parameters: - ``cache_size_limit`` - (default= ``128``) - if an integer value is provided will limit the size of the packrat cache; if None is passed, then the cache size will be unbounded; if 0 is passed, the cache will be effectively disabled. This speedup may break existing programs that use parse actions that have side-effects. For this reason, packrat parsing is disabled when you first import pyparsing. To activate the packrat feature, your program must call the class method :class:`ParserElement.enable_packrat`. For best results, call ``enable_packrat()`` immediately after importing pyparsing. Example:: import pyparsing pyparsing.ParserElement.enable_packrat() Packrat parsing works similar but not identical to Bounded Recursion parsing, thus the two cannot be used together. Use ``force=True`` to disable any previous, conflicting settings. """ if force: ParserElement.disable_memoization() elif ParserElement._left_recursion_enabled: raise RuntimeError("Packrat and Bounded Recursion are not compatible") if ParserElement._packratEnabled: return ParserElement._packratEnabled = True if cache_size_limit is None: ParserElement.packrat_cache = _UnboundedCache() else: ParserElement.packrat_cache = _FifoCache(cache_size_limit) ParserElement._parse = ParserElement._parseCache def parse_string( self, instring: str, parse_all: bool = False, *, parseAll: bool = False ) -> ParseResults: """ Parse a string with respect to the parser definition. This function is intended as the primary interface to the client code. :param instring: The input string to be parsed. :param parse_all: If set, the entire input string must match the grammar. :param parseAll: retained for pre-PEP8 compatibility, will be removed in a future release. :raises ParseException: Raised if ``parse_all`` is set and the input string does not match the whole grammar. :returns: the parsed data as a :class:`ParseResults` object, which may be accessed as a `list`, a `dict`, or an object with attributes if the given parser includes results names. If the input string is required to match the entire grammar, ``parse_all`` flag must be set to ``True``. This is also equivalent to ending the grammar with :class:`StringEnd`\\ (). To report proper column numbers, ``parse_string`` operates on a copy of the input string where all tabs are converted to spaces (8 spaces per tab, as per the default in ``string.expandtabs``). If the input string contains tabs and the grammar uses parse actions that use the ``loc`` argument to index into the string being parsed, one can ensure a consistent view of the input string by doing one of the following: - calling ``parse_with_tabs`` on your grammar before calling ``parse_string`` (see :class:`parse_with_tabs`), - define your parse action using the full ``(s,loc,toks)`` signature, and reference the input string using the parse action's ``s`` argument, or - explicitly expand the tabs in your input string before calling ``parse_string``. Examples: By default, partial matches are OK. >>> res = Word('a').parse_string('aaaaabaaa') >>> print(res) ['aaaaa'] The parsing behavior varies by the inheriting class of this abstract class. Please refer to the children directly to see more examples. It raises an exception if parse_all flag is set and instring does not match the whole grammar. >>> res = Word('a').parse_string('aaaaabaaa', parse_all=True) Traceback (most recent call last): ... pyparsing.ParseException: Expected end of text, found 'b' (at char 5), (line:1, col:6) """ parseAll = parse_all or parseAll ParserElement.reset_cache() if not self.streamlined: self.streamline() for e in self.ignoreExprs: e.streamline() if not self.keepTabs: instring = instring.expandtabs() try: loc, tokens = self._parse(instring, 0) if parseAll: loc = self.preParse(instring, loc) se = Empty() + StringEnd().set_debug(False) se._parse(instring, loc) except _ParseActionIndexError as pa_exc: raise pa_exc.exc except ParseBaseException as exc: if ParserElement.verbose_stacktrace: raise # catch and re-raise exception from here, clearing out pyparsing internal stack trace raise exc.with_traceback(None) else: return tokens def scan_string( self, instring: str, max_matches: int = _MAX_INT, overlap: bool = False, always_skip_whitespace=True, *, debug: bool = False, maxMatches: int = _MAX_INT, ) -> Generator[tuple[ParseResults, int, int], None, None]: """ Scan the input string for expression matches. Each match will return the matching tokens, start location, and end location. May be called with optional ``max_matches`` argument, to clip scanning after 'n' matches are found. If ``overlap`` is specified, then overlapping matches will be reported. Note that the start and end locations are reported relative to the string being parsed. See :class:`parse_string` for more information on parsing strings with embedded tabs. Example:: source = "sldjf123lsdjjkf345sldkjf879lkjsfd987" print(source) for tokens, start, end in Word(alphas).scan_string(source): print(' '*start + '^'*(end-start)) print(' '*start + tokens[0]) prints:: sldjf123lsdjjkf345sldkjf879lkjsfd987 ^^^^^ sldjf ^^^^^^^ lsdjjkf ^^^^^^ sldkjf ^^^^^^ lkjsfd """ maxMatches = min(maxMatches, max_matches) if not self.streamlined: self.streamline() for e in self.ignoreExprs: e.streamline() if not self.keepTabs: instring = str(instring).expandtabs() instrlen = len(instring) loc = 0 if always_skip_whitespace: preparser = Empty() preparser.ignoreExprs = self.ignoreExprs preparser.whiteChars = self.whiteChars preparseFn = preparser.preParse else: preparseFn = self.preParse parseFn = self._parse ParserElement.resetCache() matches = 0 try: while loc <= instrlen and matches < maxMatches: try: preloc: int = preparseFn(instring, loc) nextLoc: int tokens: ParseResults nextLoc, tokens = parseFn(instring, preloc, callPreParse=False) except ParseException: loc = preloc + 1 else: if nextLoc > loc: matches += 1 if debug: print( { "tokens": tokens.asList(), "start": preloc, "end": nextLoc, } ) yield tokens, preloc, nextLoc if overlap: nextloc = preparseFn(instring, loc) if nextloc > loc: loc = nextLoc else: loc += 1 else: loc = nextLoc else: loc = preloc + 1 except ParseBaseException as exc: if ParserElement.verbose_stacktrace: raise # catch and re-raise exception from here, clears out pyparsing internal stack trace raise exc.with_traceback(None) def transform_string(self, instring: str, *, debug: bool = False) -> str: """ Extension to :class:`scan_string`, to modify matching text with modified tokens that may be returned from a parse action. To use ``transform_string``, define a grammar and attach a parse action to it that modifies the returned token list. Invoking ``transform_string()`` on a target string will then scan for matches, and replace the matched text patterns according to the logic in the parse action. ``transform_string()`` returns the resulting transformed string. Example:: wd = Word(alphas) wd.set_parse_action(lambda toks: toks[0].title()) print(wd.transform_string("now is the winter of our discontent made glorious summer by this sun of york.")) prints:: Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York. """ out: list[str] = [] lastE = 0 # force preservation of <TAB>s, to minimize unwanted transformation of string, and to # keep string locs straight between transform_string and scan_string self.keepTabs = True try: for t, s, e in self.scan_string(instring, debug=debug): if s > lastE: out.append(instring[lastE:s]) lastE = e if not t: continue if isinstance(t, ParseResults): out += t.as_list() elif isinstance(t, Iterable) and not isinstance(t, str_type): out.extend(t) else: out.append(t) out.append(instring[lastE:]) out = [o for o in out if o] return "".join([str(s) for s in _flatten(out)]) except ParseBaseException as exc: if ParserElement.verbose_stacktrace: raise # catch and re-raise exception from here, clears out pyparsing internal stack trace raise exc.with_traceback(None) def search_string( self, instring: str, max_matches: int = _MAX_INT, *, debug: bool = False, maxMatches: int = _MAX_INT, ) -> ParseResults: """ Another extension to :class:`scan_string`, simplifying the access to the tokens found to match the given parse expression. May be called with optional ``max_matches`` argument, to clip searching after 'n' matches are found. Example:: # a capitalized word starts with an uppercase letter, followed by zero or more lowercase letters cap_word = Word(alphas.upper(), alphas.lower()) print(cap_word.search_string("More than Iron, more than Lead, more than Gold I need Electricity")) # the sum() builtin can be used to merge results into a single ParseResults object print(sum(cap_word.search_string("More than Iron, more than Lead, more than Gold I need Electricity"))) prints:: [['More'], ['Iron'], ['Lead'], ['Gold'], ['I'], ['Electricity']] ['More', 'Iron', 'Lead', 'Gold', 'I', 'Electricity'] """ maxMatches = min(maxMatches, max_matches) try: return ParseResults( [ t for t, s, e in self.scan_string( instring, maxMatches, always_skip_whitespace=False, debug=debug ) ] ) except ParseBaseException as exc: if ParserElement.verbose_stacktrace: raise # catch and re-raise exception from here, clears out pyparsing internal stack trace raise exc.with_traceback(None) def split( self, instring: str, maxsplit: int = _MAX_INT, include_separators: bool = False, *, includeSeparators=False, ) -> Generator[str, None, None]: """ Generator method to split a string using the given expression as a separator. May be called with optional ``maxsplit`` argument, to limit the number of splits; and the optional ``include_separators`` argument (default= ``False``), if the separating matching text should be included in the split results. Example:: punc = one_of(list(".,;:/-!?")) print(list(punc.split("This, this?, this sentence, is badly punctuated!"))) prints:: ['This', ' this', '', ' this sentence', ' is badly punctuated', ''] """ includeSeparators = includeSeparators or include_separators last = 0 for t, s, e in self.scan_string(instring, max_matches=maxsplit): yield instring[last:s] if includeSeparators: yield t[0] last = e yield instring[last:] def __add__(self, other) -> ParserElement: """ Implementation of ``+`` operator - returns :class:`And`. Adding strings to a :class:`ParserElement` converts them to :class:`Literal`\\ s by default. Example:: greet = Word(alphas) + "," + Word(alphas) + "!" hello = "Hello, World!" print(hello, "->", greet.parse_string(hello)) prints:: Hello, World! -> ['Hello', ',', 'World', '!'] ``...`` may be used as a parse expression as a short form of :class:`SkipTo`:: Literal('start') + ... + Literal('end') is equivalent to:: Literal('start') + SkipTo('end')("_skipped*") + Literal('end') Note that the skipped text is returned with '_skipped' as a results name, and to support having multiple skips in the same parser, the value returned is a list of all skipped text. """ if other is Ellipsis: return _PendingSkip(self) if isinstance(other, str_type): other = self._literalStringClass(other) if not isinstance(other, ParserElement): return NotImplemented return And([self, other]) def __radd__(self, other) -> ParserElement: """ Implementation of ``+`` operator when left operand is not a :class:`ParserElement` """ if other is Ellipsis: return SkipTo(self)("_skipped*") + self if isinstance(other, str_type): other = self._literalStringClass(other) if not isinstance(other, ParserElement): return NotImplemented return other + self def __sub__(self, other) -> ParserElement: """ Implementation of ``-`` operator, returns :class:`And` with error stop """ if isinstance(other, str_type): other = self._literalStringClass(other) if not isinstance(other, ParserElement): return NotImplemented return self + And._ErrorStop() + other def __rsub__(self, other) -> ParserElement: """ Implementation of ``-`` operator when left operand is not a :class:`ParserElement` """ if isinstance(other, str_type): other = self._literalStringClass(other) if not isinstance(other, ParserElement): return NotImplemented return other - self def __mul__(self, other) -> ParserElement: """ Implementation of ``*`` operator, allows use of ``expr * 3`` in place of ``expr + expr + expr``. Expressions may also be multiplied by a 2-integer tuple, similar to ``{min, max}`` multipliers in regular expressions. Tuples may also include ``None`` as in: - ``expr*(n, None)`` or ``expr*(n, )`` is equivalent to ``expr*n + ZeroOrMore(expr)`` (read as "at least n instances of ``expr``") - ``expr*(None, n)`` is equivalent to ``expr*(0, n)`` (read as "0 to n instances of ``expr``") - ``expr*(None, None)`` is equivalent to ``ZeroOrMore(expr)`` - ``expr*(1, None)`` is equivalent to ``OneOrMore(expr)`` Note that ``expr*(None, n)`` does not raise an exception if more than n exprs exist in the input stream; that is, ``expr*(None, n)`` does not enforce a maximum number of expr occurrences. If this behavior is desired, then write ``expr*(None, n) + ~expr`` """ if other is Ellipsis: other = (0, None) elif isinstance(other, tuple) and other[:1] == (Ellipsis,): other = ((0,) + other[1:] + (None,))[:2] if not isinstance(other, (int, tuple)): return NotImplemented if isinstance(other, int): minElements, optElements = other, 0 else: other = tuple(o if o is not Ellipsis else None for o in other) other = (other + (None, None))[:2] if other[0] is None: other = (0, other[1]) if isinstance(other[0], int) and other[1] is None: if other[0] == 0: return ZeroOrMore(self) if other[0] == 1: return OneOrMore(self) else: return self * other[0] + ZeroOrMore(self) elif isinstance(other[0], int) and isinstance(other[1], int): minElements, optElements = other optElements -= minElements else: return NotImplemented if minElements < 0: raise ValueError("cannot multiply ParserElement by negative value") if optElements < 0: raise ValueError( "second tuple value must be greater or equal to first tuple value" ) if minElements == optElements == 0: return And([]) if optElements: def makeOptionalList(n): if n > 1: return Opt(self + makeOptionalList(n - 1)) else: return Opt(self) if minElements: if minElements == 1: ret = self + makeOptionalList(optElements) else: ret = And([self] * minElements) + makeOptionalList(optElements) else: ret = makeOptionalList(optElements) else: if minElements == 1: ret = self else: ret = And([self] * minElements) return ret def __rmul__(self, other) -> ParserElement: return self.__mul__(other) def __or__(self, other) -> ParserElement: """ Implementation of ``|`` operator - returns :class:`MatchFirst` """ if other is Ellipsis: return _PendingSkip(self, must_skip=True) if isinstance(other, str_type): # `expr | ""` is equivalent to `Opt(expr)` if other == "": return Opt(self) other = self._literalStringClass(other) if not isinstance(other, ParserElement): return NotImplemented return MatchFirst([self, other]) def __ror__(self, other) -> ParserElement: """ Implementation of ``|`` operator when left operand is not a :class:`ParserElement` """ if isinstance(other, str_type): other = self._literalStringClass(other) if not isinstance(other, ParserElement): return NotImplemented return other | self def __xor__(self, other) -> ParserElement: """ Implementation of ``^`` operator - returns :class:`Or` """ if isinstance(other, str_type): other = self._literalStringClass(other) if not isinstance(other, ParserElement): return NotImplemented return Or([self, other]) def __rxor__(self, other) -> ParserElement: """ Implementation of ``^`` operator when left operand is not a :class:`ParserElement` """ if isinstance(other, str_type): other = self._literalStringClass(other) if not isinstance(other, ParserElement): return NotImplemented return other ^ self def __and__(self, other) -> ParserElement: """ Implementation of ``&`` operator - returns :class:`Each` """ if isinstance(other, str_type): other = self._literalStringClass(other) if not isinstance(other, ParserElement): return NotImplemented return Each([self, other]) def __rand__(self, other) -> ParserElement: """ Implementation of ``&`` operator when left operand is not a :class:`ParserElement` """ if isinstance(other, str_type): other = self._literalStringClass(other) if not isinstance(other, ParserElement): return NotImplemented return other & self def __invert__(self) -> ParserElement: """ Implementation of ``~`` operator - returns :class:`NotAny` """ return NotAny(self) # disable __iter__ to override legacy use of sequential access to __getitem__ to # iterate over a sequence __iter__ = None def __getitem__(self, key): """ use ``[]`` indexing notation as a short form for expression repetition: - ``expr[n]`` is equivalent to ``expr*n`` - ``expr[m, n]`` is equivalent to ``expr*(m, n)`` - ``expr[n, ...]`` or ``expr[n,]`` is equivalent to ``expr*n + ZeroOrMore(expr)`` (read as "at least n instances of ``expr``") - ``expr[..., n]`` is equivalent to ``expr*(0, n)`` (read as "0 to n instances of ``expr``") - ``expr[...]`` and ``expr[0, ...]`` are equivalent to ``ZeroOrMore(expr)`` - ``expr[1, ...]`` is equivalent to ``OneOrMore(expr)`` ``None`` may be used in place of ``...``. Note that ``expr[..., n]`` and ``expr[m, n]`` do not raise an exception if more than ``n`` ``expr``\\ s exist in the input stream. If this behavior is desired, then write ``expr[..., n] + ~expr``. For repetition with a stop_on expression, use slice notation: - ``expr[...: end_expr]`` and ``expr[0, ...: end_expr]`` are equivalent to ``ZeroOrMore(expr, stop_on=end_expr)`` - ``expr[1, ...: end_expr]`` is equivalent to ``OneOrMore(expr, stop_on=end_expr)`` """ stop_on_defined = False stop_on = NoMatch() if isinstance(key, slice): key, stop_on = key.start, key.stop if key is None: key = ... stop_on_defined = True elif isinstance(key, tuple) and isinstance(key[-1], slice): key, stop_on = (key[0], key[1].start), key[1].stop stop_on_defined = True # convert single arg keys to tuples if isinstance(key, str_type): key = (key,) try: iter(key) except TypeError: key = (key, key) if len(key) > 2: raise TypeError( f"only 1 or 2 index arguments supported ({key[:5]}{f'... [{len(key)}]' if len(key) > 5 else ''})" ) # clip to 2 elements ret = self * tuple(key[:2]) ret = typing.cast(_MultipleMatch, ret) if stop_on_defined: ret.stopOn(stop_on) return ret def __call__(self, name: typing.Optional[str] = None) -> ParserElement: """ Shortcut for :class:`set_results_name`, with ``list_all_matches=False``. If ``name`` is given with a trailing ``'*'`` character, then ``list_all_matches`` will be passed as ``True``. If ``name`` is omitted, same as calling :class:`copy`. Example:: # these are equivalent userdata = Word(alphas).set_results_name("name") + Word(nums + "-").set_results_name("socsecno") userdata = Word(alphas)("name") + Word(nums + "-")("socsecno") """ if name is not None: return self._setResultsName(name) return self.copy() def suppress(self) -> ParserElement: """ Suppresses the output of this :class:`ParserElement`; useful to keep punctuation from cluttering up returned output. """ return Suppress(self) def ignore_whitespace(self, recursive: bool = True) -> ParserElement: """ Enables the skipping of whitespace before matching the characters in the :class:`ParserElement`'s defined pattern. :param recursive: If ``True`` (the default), also enable whitespace skipping in child elements (if any) """ self.skipWhitespace = True return self def leave_whitespace(self, recursive: bool = True) -> ParserElement: """ Disables the skipping of whitespace before matching the characters in the :class:`ParserElement`'s defined pattern. This is normally only used internally by the pyparsing module, but may be needed in some whitespace-sensitive grammars. :param recursive: If true (the default), also disable whitespace skipping in child elements (if any) """ self.skipWhitespace = False return self def set_whitespace_chars( self, chars: Union[set[str], str], copy_defaults: bool = False ) -> ParserElement: """ Overrides the default whitespace chars """ self.skipWhitespace = True self.whiteChars = set(chars) self.copyDefaultWhiteChars = copy_defaults return self def parse_with_tabs(self) -> ParserElement: """ Overrides default behavior to expand ``<TAB>`` s to spaces before parsing the input string. Must be called before ``parse_string`` when the input grammar contains elements that match ``<TAB>`` characters. """ self.keepTabs = True return self def ignore(self, other: ParserElement) -> ParserElement: """ Define expression to be ignored (e.g., comments) while doing pattern matching; may be called repeatedly, to define multiple comment or other ignorable patterns. Example:: patt = Word(alphas)[...] patt.parse_string('ablaj /* comment */ lskjd') # -> ['ablaj'] patt.ignore(c_style_comment) patt.parse_string('ablaj /* comment */ lskjd') # -> ['ablaj', 'lskjd'] """ if isinstance(other, str_type): other = Suppress(other) if isinstance(other, Suppress): if other not in self.ignoreExprs: self.ignoreExprs.append(other) else: self.ignoreExprs.append(Suppress(other.copy())) return self def set_debug_actions( self, start_action: DebugStartAction, success_action: DebugSuccessAction, exception_action: DebugExceptionAction, ) -> ParserElement: """ Customize display of debugging messages while doing pattern matching: - ``start_action`` - method to be called when an expression is about to be parsed; should have the signature ``fn(input_string: str, location: int, expression: ParserElement, cache_hit: bool)`` - ``success_action`` - method to be called when an expression has successfully parsed; should have the signature ``fn(input_string: str, start_location: int, end_location: int, expression: ParserELement, parsed_tokens: ParseResults, cache_hit: bool)`` - ``exception_action`` - method to be called when expression fails to parse; should have the signature ``fn(input_string: str, location: int, expression: ParserElement, exception: Exception, cache_hit: bool)`` """ self.debugActions = self.DebugActions( start_action or _default_start_debug_action, # type: ignore[truthy-function] success_action or _default_success_debug_action, # type: ignore[truthy-function] exception_action or _default_exception_debug_action, # type: ignore[truthy-function] ) self.debug = True return self def set_debug(self, flag: bool = True, recurse: bool = False) -> ParserElement: """ Enable display of debugging messages while doing pattern matching. Set ``flag`` to ``True`` to enable, ``False`` to disable. Set ``recurse`` to ``True`` to set the debug flag on this expression and all sub-expressions. Example:: wd = Word(alphas).set_name("alphaword") integer = Word(nums).set_name("numword") term = wd | integer # turn on debugging for wd wd.set_debug() term[1, ...].parse_string("abc 123 xyz 890") prints:: Match alphaword at loc 0(1,1) Matched alphaword -> ['abc'] Match alphaword at loc 3(1,4) Exception raised:Expected alphaword (at char 4), (line:1, col:5) Match alphaword at loc 7(1,8) Matched alphaword -> ['xyz'] Match alphaword at loc 11(1,12) Exception raised:Expected alphaword (at char 12), (line:1, col:13) Match alphaword at loc 15(1,16) Exception raised:Expected alphaword (at char 15), (line:1, col:16) The output shown is that produced by the default debug actions - custom debug actions can be specified using :class:`set_debug_actions`. Prior to attempting to match the ``wd`` expression, the debugging message ``"Match <exprname> at loc <n>(<line>,<col>)"`` is shown. Then if the parse succeeds, a ``"Matched"`` message is shown, or an ``"Exception raised"`` message is shown. Also note the use of :class:`set_name` to assign a human-readable name to the expression, which makes debugging and exception messages easier to understand - for instance, the default name created for the :class:`Word` expression without calling ``set_name`` is ``"W:(A-Za-z)"``. """ if recurse: for expr in self.visit_all(): expr.set_debug(flag, recurse=False) return self if flag: self.set_debug_actions( _default_start_debug_action, _default_success_debug_action, _default_exception_debug_action, ) else: self.debug = False return self @property def default_name(self) -> str: if self._defaultName is None: self._defaultName = self._generateDefaultName() return self._defaultName @abstractmethod def _generateDefaultName(self) -> str: """ Child classes must define this method, which defines how the ``default_name`` is set. """ def set_name(self, name: typing.Optional[str]) -> ParserElement: """ Define name for this expression, makes debugging and exception messages clearer. If `__diag__.enable_debug_on_named_expressions` is set to True, setting a name will also enable debug for this expression. If `name` is None, clears any custom name for this expression, and clears the debug flag is it was enabled via `__diag__.enable_debug_on_named_expressions`. Example:: integer = Word(nums) integer.parse_string("ABC") # -> Exception: Expected W:(0-9) (at char 0), (line:1, col:1) integer.set_name("integer") integer.parse_string("ABC") # -> Exception: Expected integer (at char 0), (line:1, col:1) """ self.customName = name # type: ignore[assignment] self.errmsg = f"Expected {str(self)}" if __diag__.enable_debug_on_named_expressions: self.set_debug(name is not None) return self @property def name(self) -> str: # This will use a user-defined name if available, but otherwise defaults back to the auto-generated name return self.customName if self.customName is not None else self.default_name @name.setter def name(self, new_name) -> None: self.set_name(new_name) def __str__(self) -> str: return self.name def __repr__(self) -> str: return str(self) def streamline(self) -> ParserElement: self.streamlined = True self._defaultName = None return self def recurse(self) -> list[ParserElement]: return [] def _checkRecursion(self, parseElementList): subRecCheckList = parseElementList[:] + [self] for e in self.recurse(): e._checkRecursion(subRecCheckList) def validate(self, validateTrace=None) -> None: """ Check defined expressions for valid structure, check for infinite recursive definitions. """ warnings.warn( "ParserElement.validate() is deprecated, and should not be used to check for left recursion", DeprecationWarning, stacklevel=2, ) self._checkRecursion([]) def parse_file( self, file_or_filename: Union[str, Path, TextIO], encoding: str = "utf-8", parse_all: bool = False, *, parseAll: bool = False, ) -> ParseResults: """ Execute the parse expression on the given file or filename. If a filename is specified (instead of a file object), the entire file is opened, read, and closed before parsing. """ parseAll = parseAll or parse_all try: file_or_filename = typing.cast(TextIO, file_or_filename) file_contents = file_or_filename.read() except AttributeError: file_or_filename = typing.cast(str, file_or_filename) with open(file_or_filename, "r", encoding=encoding) as f: file_contents = f.read() try: return self.parse_string(file_contents, parseAll) except ParseBaseException as exc: if ParserElement.verbose_stacktrace: raise # catch and re-raise exception from here, clears out pyparsing internal stack trace raise exc.with_traceback(None) def __eq__(self, other): if self is other: return True elif isinstance(other, str_type): return self.matches(other, parse_all=True) elif isinstance(other, ParserElement): return vars(self) == vars(other) return False def __hash__(self): return id(self) def matches( self, test_string: str, parse_all: bool = True, *, parseAll: bool = True ) -> bool: """ Method for quick testing of a parser against a test string. Good for simple inline microtests of sub expressions while building up larger parser. Parameters: - ``test_string`` - to test against this expression for a match - ``parse_all`` - (default= ``True``) - flag to pass to :class:`parse_string` when running tests Example:: expr = Word(nums) assert expr.matches("100") """ parseAll = parseAll and parse_all try: self.parse_string(str(test_string), parse_all=parseAll) return True except ParseBaseException: return False def run_tests( self, tests: Union[str, list[str]], parse_all: bool = True, comment: typing.Optional[Union[ParserElement, str]] = "#", full_dump: bool = True, print_results: bool = True, failure_tests: bool = False, post_parse: typing.Optional[ Callable[[str, ParseResults], typing.Optional[str]] ] = None, file: typing.Optional[TextIO] = None, with_line_numbers: bool = False, *, parseAll: bool = True, fullDump: bool = True, printResults: bool = True, failureTests: bool = False, postParse: typing.Optional[ Callable[[str, ParseResults], typing.Optional[str]] ] = None, ) -> tuple[bool, list[tuple[str, Union[ParseResults, Exception]]]]: """ Execute the parse expression on a series of test strings, showing each test, the parsed results or where the parse failed. Quick and easy way to run a parse expression against a list of sample strings. Parameters: - ``tests`` - a list of separate test strings, or a multiline string of test strings - ``parse_all`` - (default= ``True``) - flag to pass to :class:`parse_string` when running tests - ``comment`` - (default= ``'#'``) - expression for indicating embedded comments in the test string; pass None to disable comment filtering - ``full_dump`` - (default= ``True``) - dump results as list followed by results names in nested outline; if False, only dump nested list - ``print_results`` - (default= ``True``) prints test output to stdout - ``failure_tests`` - (default= ``False``) indicates if these tests are expected to fail parsing - ``post_parse`` - (default= ``None``) optional callback for successful parse results; called as `fn(test_string, parse_results)` and returns a string to be added to the test output - ``file`` - (default= ``None``) optional file-like object to which test output will be written; if None, will default to ``sys.stdout`` - ``with_line_numbers`` - default= ``False``) show test strings with line and column numbers Returns: a (success, results) tuple, where success indicates that all tests succeeded (or failed if ``failure_tests`` is True), and the results contain a list of lines of each test's output Example:: number_expr = pyparsing_common.number.copy() result = number_expr.run_tests(''' # unsigned integer 100 # negative integer -100 # float with scientific notation 6.02e23 # integer with scientific notation 1e-12 ''') print("Success" if result[0] else "Failed!") result = number_expr.run_tests(''' # stray character 100Z # missing leading digit before '.' -.100 # too many '.' 3.14.159 ''', failure_tests=True) print("Success" if result[0] else "Failed!") prints:: # unsigned integer 100 [100] # negative integer -100 [-100] # float with scientific notation 6.02e23 [6.02e+23] # integer with scientific notation 1e-12 [1e-12] Success # stray character 100Z ^ FAIL: Expected end of text (at char 3), (line:1, col:4) # missing leading digit before '.' -.100 ^ FAIL: Expected {real number with scientific notation | real number | signed integer} (at char 0), (line:1, col:1) # too many '.' 3.14.159 ^ FAIL: Expected end of text (at char 4), (line:1, col:5) Success Each test string must be on a single line. If you want to test a string that spans multiple lines, create a test like this:: expr.run_tests(r"this is a test\\n of strings that spans \\n 3 lines") (Note that this is a raw string literal, you must include the leading ``'r'``.) """ from .testing import pyparsing_test parseAll = parseAll and parse_all fullDump = fullDump and full_dump printResults = printResults and print_results failureTests = failureTests or failure_tests postParse = postParse or post_parse if isinstance(tests, str_type): tests = typing.cast(str, tests) line_strip = type(tests).strip tests = [line_strip(test_line) for test_line in tests.rstrip().splitlines()] comment_specified = comment is not None if comment_specified: if isinstance(comment, str_type): comment = typing.cast(str, comment) comment = Literal(comment) comment = typing.cast(ParserElement, comment) if file is None: file = sys.stdout print_ = file.write result: Union[ParseResults, Exception] allResults: list[tuple[str, Union[ParseResults, Exception]]] = [] comments: list[str] = [] success = True NL = Literal(r"\n").add_parse_action(replace_with("\n")).ignore(quoted_string) BOM = "\ufeff" nlstr = "\n" for t in tests: if comment_specified and comment.matches(t, False) or comments and not t: comments.append( pyparsing_test.with_line_numbers(t) if with_line_numbers else t ) continue if not t: continue out = [ f"{nlstr}{nlstr.join(comments) if comments else ''}", pyparsing_test.with_line_numbers(t) if with_line_numbers else t, ] comments.clear() try: # convert newline marks to actual newlines, and strip leading BOM if present t = NL.transform_string(t.lstrip(BOM)) result = self.parse_string(t, parse_all=parseAll) except ParseBaseException as pe: fatal = "(FATAL) " if isinstance(pe, ParseFatalException) else "" out.append(pe.explain()) out.append(f"FAIL: {fatal}{pe}") if ParserElement.verbose_stacktrace: out.extend(traceback.format_tb(pe.__traceback__)) success = success and failureTests result = pe except Exception as exc: tag = "FAIL-EXCEPTION" # see if this exception was raised in a parse action tb = exc.__traceback__ it = iter(traceback.walk_tb(tb)) for f, line in it: if (f.f_code.co_filename, line) == pa_call_line_synth: next_f = next(it)[0] tag += f" (raised in parse action {next_f.f_code.co_name!r})" break out.append(f"{tag}: {type(exc).__name__}: {exc}") if ParserElement.verbose_stacktrace: out.extend(traceback.format_tb(exc.__traceback__)) success = success and failureTests result = exc else: success = success and not failureTests if postParse is not None: try: pp_value = postParse(t, result) if pp_value is not None: if isinstance(pp_value, ParseResults): out.append(pp_value.dump()) else: out.append(str(pp_value)) else: out.append(result.dump()) except Exception as e: out.append(result.dump(full=fullDump)) out.append( f"{postParse.__name__} failed: {type(e).__name__}: {e}" ) else: out.append(result.dump(full=fullDump)) out.append("") if printResults: print_("\n".join(out)) allResults.append((t, result)) return success, allResults def create_diagram( self, output_html: Union[TextIO, Path, str], vertical: int = 3, show_results_names: bool = False, show_groups: bool = False, embed: bool = False, show_hidden: bool = False, **kwargs, ) -> None: """ Create a railroad diagram for the parser. Parameters: - ``output_html`` (str or file-like object) - output target for generated diagram HTML - ``vertical`` (int) - threshold for formatting multiple alternatives vertically instead of horizontally (default=3) - ``show_results_names`` - bool flag whether diagram should show annotations for defined results names - ``show_groups`` - bool flag whether groups should be highlighted with an unlabeled surrounding box - ``show_hidden`` - bool flag to show diagram elements for internal elements that are usually hidden - ``embed`` - bool flag whether generated HTML should omit <HEAD>, <BODY>, and <DOCTYPE> tags to embed the resulting HTML in an enclosing HTML source - ``head`` - str containing additional HTML to insert into the <HEAD> section of the generated code; can be used to insert custom CSS styling - ``body`` - str containing additional HTML to insert at the beginning of the <BODY> section of the generated code Additional diagram-formatting keyword arguments can also be included; see railroad.Diagram class. """ try: from .diagram import to_railroad, railroad_to_html except ImportError as ie: raise Exception( "must ``pip install pyparsing[diagrams]`` to generate parser railroad diagrams" ) from ie self.streamline() railroad = to_railroad( self, vertical=vertical, show_results_names=show_results_names, show_groups=show_groups, show_hidden=show_hidden, diagram_kwargs=kwargs, ) if not isinstance(output_html, (str, Path)): # we were passed a file-like object, just write to it output_html.write(railroad_to_html(railroad, embed=embed, **kwargs)) return with open(output_html, "w", encoding="utf-8") as diag_file: diag_file.write(railroad_to_html(railroad, embed=embed, **kwargs)) # Compatibility synonyms # fmt: off inlineLiteralsUsing = staticmethod(replaced_by_pep8("inlineLiteralsUsing", inline_literals_using)) setDefaultWhitespaceChars = staticmethod(replaced_by_pep8( "setDefaultWhitespaceChars", set_default_whitespace_chars )) disableMemoization = staticmethod(replaced_by_pep8("disableMemoization", disable_memoization)) enableLeftRecursion = staticmethod(replaced_by_pep8("enableLeftRecursion", enable_left_recursion)) enablePackrat = staticmethod(replaced_by_pep8("enablePackrat", enable_packrat)) resetCache = staticmethod(replaced_by_pep8("resetCache", reset_cache)) setResultsName = replaced_by_pep8("setResultsName", set_results_name) setBreak = replaced_by_pep8("setBreak", set_break) setParseAction = replaced_by_pep8("setParseAction", set_parse_action) addParseAction = replaced_by_pep8("addParseAction", add_parse_action) addCondition = replaced_by_pep8("addCondition", add_condition) setFailAction = replaced_by_pep8("setFailAction", set_fail_action) tryParse = replaced_by_pep8("tryParse", try_parse) parseString = replaced_by_pep8("parseString", parse_string) scanString = replaced_by_pep8("scanString", scan_string) transformString = replaced_by_pep8("transformString", transform_string) searchString = replaced_by_pep8("searchString", search_string) ignoreWhitespace = replaced_by_pep8("ignoreWhitespace", ignore_whitespace) leaveWhitespace = replaced_by_pep8("leaveWhitespace", leave_whitespace) setWhitespaceChars = replaced_by_pep8("setWhitespaceChars", set_whitespace_chars) parseWithTabs = replaced_by_pep8("parseWithTabs", parse_with_tabs) setDebugActions = replaced_by_pep8("setDebugActions", set_debug_actions) setDebug = replaced_by_pep8("setDebug", set_debug) setName = replaced_by_pep8("setName", set_name) parseFile = replaced_by_pep8("parseFile", parse_file) runTests = replaced_by_pep8("runTests", run_tests) canParseNext = replaced_by_pep8("canParseNext", can_parse_next) defaultName = default_name # fmt: on class _PendingSkip(ParserElement): # internal placeholder class to hold a place were '...' is added to a parser element, # once another ParserElement is added, this placeholder will be replaced with a SkipTo def __init__(self, expr: ParserElement, must_skip: bool = False) -> None: super().__init__() self.anchor = expr self.must_skip = must_skip def _generateDefaultName(self) -> str: return str(self.anchor + Empty()).replace("Empty", "...") def __add__(self, other) -> ParserElement: skipper = SkipTo(other).set_name("...")("_skipped*") if self.must_skip: def must_skip(t): if not t._skipped or t._skipped.as_list() == [""]: del t[0] t.pop("_skipped", None) def show_skip(t): if t._skipped.as_list()[-1:] == [""]: t.pop("_skipped") t["_skipped"] = f"missing <{self.anchor!r}>" return ( self.anchor + skipper().add_parse_action(must_skip) | skipper().add_parse_action(show_skip) ) + other return self.anchor + skipper + other def __repr__(self): return self.defaultName def parseImpl(self, *args) -> ParseImplReturnType: raise Exception( "use of `...` expression without following SkipTo target expression" ) class Token(ParserElement): """Abstract :class:`ParserElement` subclass, for defining atomic matching patterns. """ def __init__(self) -> None: super().__init__(savelist=False) def _generateDefaultName(self) -> str: return type(self).__name__ class NoMatch(Token): """ A token that will never match. """ def __init__(self) -> None: super().__init__() self._may_return_empty = True self.mayIndexError = False self.errmsg = "Unmatchable token" def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: raise ParseException(instring, loc, self.errmsg, self) class Literal(Token): """ Token to exactly match a specified string. Example:: Literal('abc').parse_string('abc') # -> ['abc'] Literal('abc').parse_string('abcdef') # -> ['abc'] Literal('abc').parse_string('ab') # -> Exception: Expected "abc" For case-insensitive matching, use :class:`CaselessLiteral`. For keyword matching (force word break before and after the matched string), use :class:`Keyword` or :class:`CaselessKeyword`. """ def __new__(cls, match_string: str = "", *, matchString: str = ""): # Performance tuning: select a subclass with optimized parseImpl if cls is Literal: match_string = matchString or match_string if not match_string: return super().__new__(Empty) if len(match_string) == 1: return super().__new__(_SingleCharLiteral) # Default behavior return super().__new__(cls) # Needed to make copy.copy() work correctly if we customize __new__ def __getnewargs__(self): return (self.match,) def __init__(self, match_string: str = "", *, matchString: str = "") -> None: super().__init__() match_string = matchString or match_string self.match = match_string self.matchLen = len(match_string) self.firstMatchChar = match_string[:1] self.errmsg = f"Expected {self.name}" self._may_return_empty = False self.mayIndexError = False def _generateDefaultName(self) -> str: return repr(self.match) def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: if instring[loc] == self.firstMatchChar and instring.startswith( self.match, loc ): return loc + self.matchLen, self.match raise ParseException(instring, loc, self.errmsg, self) class Empty(Literal): """ An empty token, will always match. """ def __init__(self, match_string="", *, matchString="") -> None: super().__init__("") self._may_return_empty = True self.mayIndexError = False def _generateDefaultName(self) -> str: return "Empty" def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: return loc, [] class _SingleCharLiteral(Literal): def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: if instring[loc] == self.firstMatchChar: return loc + 1, self.match raise ParseException(instring, loc, self.errmsg, self) ParserElement._literalStringClass = Literal class Keyword(Token): """ Token to exactly match a specified string as a keyword, that is, it must be immediately preceded and followed by whitespace or non-keyword characters. Compare with :class:`Literal`: - ``Literal("if")`` will match the leading ``'if'`` in ``'ifAndOnlyIf'``. - ``Keyword("if")`` will not; it will only match the leading ``'if'`` in ``'if x=1'``, or ``'if(y==2)'`` Accepts two optional constructor arguments in addition to the keyword string: - ``ident_chars`` is a string of characters that would be valid identifier characters, defaulting to all alphanumerics + "_" and "$" - ``caseless`` allows case-insensitive matching, default is ``False``. Example:: Keyword("start").parse_string("start") # -> ['start'] Keyword("start").parse_string("starting") # -> Exception For case-insensitive matching, use :class:`CaselessKeyword`. """ DEFAULT_KEYWORD_CHARS = alphanums + "_$" def __init__( self, match_string: str = "", ident_chars: typing.Optional[str] = None, caseless: bool = False, *, matchString: str = "", identChars: typing.Optional[str] = None, ) -> None: super().__init__() identChars = identChars or ident_chars if identChars is None: identChars = Keyword.DEFAULT_KEYWORD_CHARS match_string = matchString or match_string self.match = match_string self.matchLen = len(match_string) self.firstMatchChar = match_string[:1] if not self.firstMatchChar: raise ValueError("null string passed to Keyword; use Empty() instead") self.errmsg = f"Expected {type(self).__name__} {self.name}" self._may_return_empty = False self.mayIndexError = False self.caseless = caseless if caseless: self.caselessmatch = match_string.upper() identChars = identChars.upper() self.identChars = set(identChars) def _generateDefaultName(self) -> str: return repr(self.match) def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: errmsg = self.errmsg or "" errloc = loc if self.caseless: if instring[loc : loc + self.matchLen].upper() == self.caselessmatch: if loc == 0 or instring[loc - 1].upper() not in self.identChars: if ( loc >= len(instring) - self.matchLen or instring[loc + self.matchLen].upper() not in self.identChars ): return loc + self.matchLen, self.match # followed by keyword char errmsg += ", was immediately followed by keyword character" errloc = loc + self.matchLen else: # preceded by keyword char errmsg += ", keyword was immediately preceded by keyword character" errloc = loc - 1 # else no match just raise plain exception elif ( instring[loc] == self.firstMatchChar and self.matchLen == 1 or instring.startswith(self.match, loc) ): if loc == 0 or instring[loc - 1] not in self.identChars: if ( loc >= len(instring) - self.matchLen or instring[loc + self.matchLen] not in self.identChars ): return loc + self.matchLen, self.match # followed by keyword char errmsg += ", keyword was immediately followed by keyword character" errloc = loc + self.matchLen else: # preceded by keyword char errmsg += ", keyword was immediately preceded by keyword character" errloc = loc - 1 # else no match just raise plain exception raise ParseException(instring, errloc, errmsg, self) @staticmethod def set_default_keyword_chars(chars) -> None: """ Overrides the default characters used by :class:`Keyword` expressions. """ Keyword.DEFAULT_KEYWORD_CHARS = chars # Compatibility synonyms setDefaultKeywordChars = staticmethod( replaced_by_pep8("setDefaultKeywordChars", set_default_keyword_chars) ) class CaselessLiteral(Literal): """ Token to match a specified string, ignoring case of letters. Note: the matched results will always be in the case of the given match string, NOT the case of the input text. Example:: CaselessLiteral("CMD")[1, ...].parse_string("cmd CMD Cmd10") # -> ['CMD', 'CMD', 'CMD'] (Contrast with example for :class:`CaselessKeyword`.) """ def __init__(self, match_string: str = "", *, matchString: str = "") -> None: match_string = matchString or match_string super().__init__(match_string.upper()) # Preserve the defining literal. self.returnString = match_string self.errmsg = f"Expected {self.name}" def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: if instring[loc : loc + self.matchLen].upper() == self.match: return loc + self.matchLen, self.returnString raise ParseException(instring, loc, self.errmsg, self) class CaselessKeyword(Keyword): """ Caseless version of :class:`Keyword`. Example:: CaselessKeyword("CMD")[1, ...].parse_string("cmd CMD Cmd10") # -> ['CMD', 'CMD'] (Contrast with example for :class:`CaselessLiteral`.) """ def __init__( self, match_string: str = "", ident_chars: typing.Optional[str] = None, *, matchString: str = "", identChars: typing.Optional[str] = None, ) -> None: identChars = identChars or ident_chars match_string = matchString or match_string super().__init__(match_string, identChars, caseless=True) class CloseMatch(Token): """A variation on :class:`Literal` which matches "close" matches, that is, strings with at most 'n' mismatching characters. :class:`CloseMatch` takes parameters: - ``match_string`` - string to be matched - ``caseless`` - a boolean indicating whether to ignore casing when comparing characters - ``max_mismatches`` - (``default=1``) maximum number of mismatches allowed to count as a match The results from a successful parse will contain the matched text from the input string and the following named results: - ``mismatches`` - a list of the positions within the match_string where mismatches were found - ``original`` - the original match_string used to compare against the input string If ``mismatches`` is an empty list, then the match was an exact match. Example:: patt = CloseMatch("ATCATCGAATGGA") patt.parse_string("ATCATCGAAXGGA") # -> (['ATCATCGAAXGGA'], {'mismatches': [[9]], 'original': ['ATCATCGAATGGA']}) patt.parse_string("ATCAXCGAAXGGA") # -> Exception: Expected 'ATCATCGAATGGA' (with up to 1 mismatches) (at char 0), (line:1, col:1) # exact match patt.parse_string("ATCATCGAATGGA") # -> (['ATCATCGAATGGA'], {'mismatches': [[]], 'original': ['ATCATCGAATGGA']}) # close match allowing up to 2 mismatches patt = CloseMatch("ATCATCGAATGGA", max_mismatches=2) patt.parse_string("ATCAXCGAAXGGA") # -> (['ATCAXCGAAXGGA'], {'mismatches': [[4, 9]], 'original': ['ATCATCGAATGGA']}) """ def __init__( self, match_string: str, max_mismatches: typing.Optional[int] = None, *, maxMismatches: int = 1, caseless=False, ) -> None: maxMismatches = max_mismatches if max_mismatches is not None else maxMismatches super().__init__() self.match_string = match_string self.maxMismatches = maxMismatches self.errmsg = f"Expected {self.match_string!r} (with up to {self.maxMismatches} mismatches)" self.caseless = caseless self.mayIndexError = False self._may_return_empty = False def _generateDefaultName(self) -> str: return f"{type(self).__name__}:{self.match_string!r}" def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: start = loc instrlen = len(instring) maxloc = start + len(self.match_string) if maxloc <= instrlen: match_string = self.match_string match_stringloc = 0 mismatches = [] maxMismatches = self.maxMismatches for match_stringloc, s_m in enumerate( zip(instring[loc:maxloc], match_string) ): src, mat = s_m if self.caseless: src, mat = src.lower(), mat.lower() if src != mat: mismatches.append(match_stringloc) if len(mismatches) > maxMismatches: break else: loc = start + match_stringloc + 1 results = ParseResults([instring[start:loc]]) results["original"] = match_string results["mismatches"] = mismatches return loc, results raise ParseException(instring, loc, self.errmsg, self) class Word(Token): """Token for matching words composed of allowed character sets. Parameters: - ``init_chars`` - string of all characters that should be used to match as a word; "ABC" will match "AAA", "ABAB", "CBAC", etc.; if ``body_chars`` is also specified, then this is the string of initial characters - ``body_chars`` - string of characters that can be used for matching after a matched initial character as given in ``init_chars``; if omitted, same as the initial characters (default=``None``) - ``min`` - minimum number of characters to match (default=1) - ``max`` - maximum number of characters to match (default=0) - ``exact`` - exact number of characters to match (default=0) - ``as_keyword`` - match as a keyword (default=``False``) - ``exclude_chars`` - characters that might be found in the input ``body_chars`` string but which should not be accepted for matching ;useful to define a word of all printables except for one or two characters, for instance (default=``None``) :class:`srange` is useful for defining custom character set strings for defining :class:`Word` expressions, using range notation from regular expression character sets. A common mistake is to use :class:`Word` to match a specific literal string, as in ``Word("Address")``. Remember that :class:`Word` uses the string argument to define *sets* of matchable characters. This expression would match "Add", "AAA", "dAred", or any other word made up of the characters 'A', 'd', 'r', 'e', and 's'. To match an exact literal string, use :class:`Literal` or :class:`Keyword`. pyparsing includes helper strings for building Words: - :class:`alphas` - :class:`nums` - :class:`alphanums` - :class:`hexnums` - :class:`alphas8bit` (alphabetic characters in ASCII range 128-255 - accented, tilded, umlauted, etc.) - :class:`punc8bit` (non-alphabetic characters in ASCII range 128-255 - currency, symbols, superscripts, diacriticals, etc.) - :class:`printables` (any non-whitespace character) ``alphas``, ``nums``, and ``printables`` are also defined in several Unicode sets - see :class:`pyparsing_unicode``. Example:: # a word composed of digits integer = Word(nums) # equivalent to Word("0123456789") or Word(srange("0-9")) # a word with a leading capital, and zero or more lowercase capitalized_word = Word(alphas.upper(), alphas.lower()) # hostnames are alphanumeric, with leading alpha, and '-' hostname = Word(alphas, alphanums + '-') # roman numeral (not a strict parser, accepts invalid mix of characters) roman = Word("IVXLCDM") # any string of non-whitespace characters, except for ',' csv_value = Word(printables, exclude_chars=",") """ def __init__( self, init_chars: str = "", body_chars: typing.Optional[str] = None, min: int = 1, max: int = 0, exact: int = 0, as_keyword: bool = False, exclude_chars: typing.Optional[str] = None, *, initChars: typing.Optional[str] = None, bodyChars: typing.Optional[str] = None, asKeyword: bool = False, excludeChars: typing.Optional[str] = None, ) -> None: initChars = initChars or init_chars bodyChars = bodyChars or body_chars asKeyword = asKeyword or as_keyword excludeChars = excludeChars or exclude_chars super().__init__() if not initChars: raise ValueError( f"invalid {type(self).__name__}, initChars cannot be empty string" ) initChars_set = set(initChars) if excludeChars: excludeChars_set = set(excludeChars) initChars_set -= excludeChars_set if bodyChars: bodyChars = "".join(set(bodyChars) - excludeChars_set) self.initChars = initChars_set self.initCharsOrig = "".join(sorted(initChars_set)) if bodyChars: self.bodyChars = set(bodyChars) self.bodyCharsOrig = "".join(sorted(bodyChars)) else: self.bodyChars = initChars_set self.bodyCharsOrig = self.initCharsOrig self.maxSpecified = max > 0 if min < 1: raise ValueError( "cannot specify a minimum length < 1; use Opt(Word()) if zero-length word is permitted" ) if self.maxSpecified and min > max: raise ValueError( f"invalid args, if min and max both specified min must be <= max (min={min}, max={max})" ) self.minLen = min if max > 0: self.maxLen = max else: self.maxLen = _MAX_INT if exact > 0: min = max = exact self.maxLen = exact self.minLen = exact self.errmsg = f"Expected {self.name}" self.mayIndexError = False self.asKeyword = asKeyword if self.asKeyword: self.errmsg += " as a keyword" # see if we can make a regex for this Word if " " not in (self.initChars | self.bodyChars): if len(self.initChars) == 1: re_leading_fragment = re.escape(self.initCharsOrig) else: re_leading_fragment = f"[{_collapse_string_to_ranges(self.initChars)}]" if self.bodyChars == self.initChars: if max == 0 and self.minLen == 1: repeat = "+" elif max == 1: repeat = "" else: if self.minLen != self.maxLen: repeat = f"{{{self.minLen},{'' if self.maxLen == _MAX_INT else self.maxLen}}}" else: repeat = f"{{{self.minLen}}}" self.reString = f"{re_leading_fragment}{repeat}" else: if max == 1: re_body_fragment = "" repeat = "" else: re_body_fragment = f"[{_collapse_string_to_ranges(self.bodyChars)}]" if max == 0 and self.minLen == 1: repeat = "*" elif max == 2: repeat = "?" if min <= 1 else "" else: if min != max: repeat = f"{{{min - 1 if min > 0 else ''},{max - 1 if max > 0 else ''}}}" else: repeat = f"{{{min - 1 if min > 0 else ''}}}" self.reString = f"{re_leading_fragment}{re_body_fragment}{repeat}" if self.asKeyword: self.reString = rf"\b{self.reString}\b" try: self.re = re.compile(self.reString) except re.error: self.re = None # type: ignore[assignment] else: self.re_match = self.re.match self.parseImpl = self.parseImpl_regex # type: ignore[method-assign] def _generateDefaultName(self) -> str: def charsAsStr(s): max_repr_len = 16 s = _collapse_string_to_ranges(s, re_escape=False) if len(s) > max_repr_len: return s[: max_repr_len - 3] + "..." return s if self.initChars != self.bodyChars: base = f"W:({charsAsStr(self.initChars)}, {charsAsStr(self.bodyChars)})" else: base = f"W:({charsAsStr(self.initChars)})" # add length specification if self.minLen > 1 or self.maxLen != _MAX_INT: if self.minLen == self.maxLen: if self.minLen == 1: return base[2:] else: return base + f"{{{self.minLen}}}" elif self.maxLen == _MAX_INT: return base + f"{{{self.minLen},...}}" else: return base + f"{{{self.minLen},{self.maxLen}}}" return base def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: if instring[loc] not in self.initChars: raise ParseException(instring, loc, self.errmsg, self) start = loc loc += 1 instrlen = len(instring) body_chars: set[str] = self.bodyChars maxloc = start + self.maxLen maxloc = min(maxloc, instrlen) while loc < maxloc and instring[loc] in body_chars: loc += 1 throw_exception = False if loc - start < self.minLen: throw_exception = True elif self.maxSpecified and loc < instrlen and instring[loc] in body_chars: throw_exception = True elif self.asKeyword and ( (start > 0 and instring[start - 1] in body_chars) or (loc < instrlen and instring[loc] in body_chars) ): throw_exception = True if throw_exception: raise ParseException(instring, loc, self.errmsg, self) return loc, instring[start:loc] def parseImpl_regex(self, instring, loc, do_actions=True) -> ParseImplReturnType: result = self.re_match(instring, loc) if not result: raise ParseException(instring, loc, self.errmsg, self) loc = result.end() return loc, result.group() class Char(Word): """A short-cut class for defining :class:`Word` ``(characters, exact=1)``, when defining a match of any single character in a string of characters. """ def __init__( self, charset: str, as_keyword: bool = False, exclude_chars: typing.Optional[str] = None, *, asKeyword: bool = False, excludeChars: typing.Optional[str] = None, ) -> None: asKeyword = asKeyword or as_keyword excludeChars = excludeChars or exclude_chars super().__init__( charset, exact=1, as_keyword=asKeyword, exclude_chars=excludeChars ) class Regex(Token): r"""Token for matching strings that match a given regular expression. Defined with string specifying the regular expression in a form recognized by the stdlib Python `re module <https://docs.python.org/3/library/re.html>`_. If the given regex contains named groups (defined using ``(?P<name>...)``), these will be preserved as named :class:`ParseResults`. If instead of the Python stdlib ``re`` module you wish to use a different RE module (such as the ``regex`` module), you can do so by building your ``Regex`` object with a compiled RE that was compiled using ``regex``. Example:: realnum = Regex(r"[+-]?\d+\.\d*") # ref: https://stackoverflow.com/questions/267399/how-do-you-match-only-valid-roman-numerals-with-a-regular-expression roman = Regex(r"M{0,4}(CM|CD|D?{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})") # named fields in a regex will be returned as named results date = Regex(r'(?P<year>\d{4})-(?P<month>\d\d?)-(?P<day>\d\d?)') # the Regex class will accept re's compiled using the regex module import regex parser = pp.Regex(regex.compile(r'[0-9]')) """ def __init__( self, pattern: Any, flags: Union[re.RegexFlag, int] = 0, as_group_list: bool = False, as_match: bool = False, *, asGroupList: bool = False, asMatch: bool = False, ) -> None: """The parameters ``pattern`` and ``flags`` are passed to the ``re.compile()`` function as-is. See the Python `re module <https://docs.python.org/3/library/re.html>`_ module for an explanation of the acceptable patterns and flags. """ super().__init__() asGroupList = asGroupList or as_group_list asMatch = asMatch or as_match if isinstance(pattern, str_type): if not pattern: raise ValueError("null string passed to Regex; use Empty() instead") self._re = None self._may_return_empty = None # type: ignore [assignment] self.reString = self.pattern = pattern elif hasattr(pattern, "pattern") and hasattr(pattern, "match"): self._re = pattern self._may_return_empty = None # type: ignore [assignment] self.pattern = self.reString = pattern.pattern elif callable(pattern): # defer creating this pattern until we really need it self.pattern = pattern self._may_return_empty = None # type: ignore [assignment] self._re = None else: raise TypeError( "Regex may only be constructed with a string or a compiled RE object," " or a callable that takes no arguments and returns a string or a" " compiled RE object" ) self.flags = flags self.errmsg = f"Expected {self.name}" self.mayIndexError = False self.asGroupList = asGroupList self.asMatch = asMatch if self.asGroupList: self.parseImpl = self.parseImplAsGroupList # type: ignore [method-assign] if self.asMatch: self.parseImpl = self.parseImplAsMatch # type: ignore [method-assign] @cached_property def re(self) -> re.Pattern: if self._re: return self._re if callable(self.pattern): # replace self.pattern with the string returned by calling self.pattern() self.pattern = cast(Callable[[], str], self.pattern)() # see if we got a compiled RE back instead of a str - if so, we're done if hasattr(self.pattern, "pattern") and hasattr(self.pattern, "match"): self._re = cast(re.Pattern[str], self.pattern) self.pattern = self.reString = self._re.pattern return self._re try: self._re = re.compile(self.pattern, self.flags) except re.error: raise ValueError(f"invalid pattern ({self.pattern!r}) passed to Regex") else: self._may_return_empty = self.re.match("", pos=0) is not None return self._re @cached_property def re_match(self) -> Callable[[str, int], Any]: return self.re.match @property def mayReturnEmpty(self): if self._may_return_empty is None: # force compile of regex pattern, to set may_return_empty flag self.re # noqa return self._may_return_empty @mayReturnEmpty.setter def mayReturnEmpty(self, value): self._may_return_empty = value def _generateDefaultName(self) -> str: unescaped = repr(self.pattern).replace("\\\\", "\\") return f"Re:({unescaped})" def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: # explicit check for matching past the length of the string; # this is done because the re module will not complain about # a match with `pos > len(instring)`, it will just return "" if loc > len(instring) and self.mayReturnEmpty: raise ParseException(instring, loc, self.errmsg, self) result = self.re_match(instring, loc) if not result: raise ParseException(instring, loc, self.errmsg, self) loc = result.end() ret = ParseResults(result.group()) d = result.groupdict() for k, v in d.items(): ret[k] = v return loc, ret def parseImplAsGroupList(self, instring, loc, do_actions=True): if loc > len(instring) and self.mayReturnEmpty: raise ParseException(instring, loc, self.errmsg, self) result = self.re_match(instring, loc) if not result: raise ParseException(instring, loc, self.errmsg, self) loc = result.end() ret = result.groups() return loc, ret def parseImplAsMatch(self, instring, loc, do_actions=True): if loc > len(instring) and self.mayReturnEmpty: raise ParseException(instring, loc, self.errmsg, self) result = self.re_match(instring, loc) if not result: raise ParseException(instring, loc, self.errmsg, self) loc = result.end() ret = result return loc, ret def sub(self, repl: str) -> ParserElement: r""" Return :class:`Regex` with an attached parse action to transform the parsed result as if called using `re.sub(expr, repl, string) <https://docs.python.org/3/library/re.html#re.sub>`_. Example:: make_html = Regex(r"(\w+):(.*?):").sub(r"<\1>\2</\1>") print(make_html.transform_string("h1:main title:")) # prints "<h1>main title</h1>" """ if self.asGroupList: raise TypeError("cannot use sub() with Regex(as_group_list=True)") if self.asMatch and callable(repl): raise TypeError( "cannot use sub() with a callable with Regex(as_match=True)" ) if self.asMatch: def pa(tokens): return tokens[0].expand(repl) else: def pa(tokens): return self.re.sub(repl, tokens[0]) return self.add_parse_action(pa) class QuotedString(Token): r""" Token for matching strings that are delimited by quoting characters. Defined with the following parameters: - ``quote_char`` - string of one or more characters defining the quote delimiting string - ``esc_char`` - character to re_escape quotes, typically backslash (default= ``None``) - ``esc_quote`` - special quote sequence to re_escape an embedded quote string (such as SQL's ``""`` to re_escape an embedded ``"``) (default= ``None``) - ``multiline`` - boolean indicating whether quotes can span multiple lines (default= ``False``) - ``unquote_results`` - boolean indicating whether the matched text should be unquoted (default= ``True``) - ``end_quote_char`` - string of one or more characters defining the end of the quote delimited string (default= ``None`` => same as quote_char) - ``convert_whitespace_escapes`` - convert escaped whitespace (``'\t'``, ``'\n'``, etc.) to actual whitespace (default= ``True``) Example:: qs = QuotedString('"') print(qs.search_string('lsjdf "This is the quote" sldjf')) complex_qs = QuotedString('{{', end_quote_char='}}') print(complex_qs.search_string('lsjdf {{This is the "quote"}} sldjf')) sql_qs = QuotedString('"', esc_quote='""') print(sql_qs.search_string('lsjdf "This is the quote with ""embedded"" quotes" sldjf')) prints:: [['This is the quote']] [['This is the "quote"']] [['This is the quote with "embedded" quotes']] """ ws_map = dict(((r"\t", "\t"), (r"\n", "\n"), (r"\f", "\f"), (r"\r", "\r"))) def __init__( self, quote_char: str = "", esc_char: typing.Optional[str] = None, esc_quote: typing.Optional[str] = None, multiline: bool = False, unquote_results: bool = True, end_quote_char: typing.Optional[str] = None, convert_whitespace_escapes: bool = True, *, quoteChar: str = "", escChar: typing.Optional[str] = None, escQuote: typing.Optional[str] = None, unquoteResults: bool = True, endQuoteChar: typing.Optional[str] = None, convertWhitespaceEscapes: bool = True, ) -> None: super().__init__() esc_char = escChar or esc_char esc_quote = escQuote or esc_quote unquote_results = unquoteResults and unquote_results end_quote_char = endQuoteChar or end_quote_char convert_whitespace_escapes = ( convertWhitespaceEscapes and convert_whitespace_escapes ) quote_char = quoteChar or quote_char # remove white space from quote chars quote_char = quote_char.strip() if not quote_char: raise ValueError("quote_char cannot be the empty string") if end_quote_char is None: end_quote_char = quote_char else: end_quote_char = end_quote_char.strip() if not end_quote_char: raise ValueError("end_quote_char cannot be the empty string") self.quote_char: str = quote_char self.quote_char_len: int = len(quote_char) self.first_quote_char: str = quote_char[0] self.end_quote_char: str = end_quote_char self.end_quote_char_len: int = len(end_quote_char) self.esc_char: str = esc_char or "" self.has_esc_char: bool = esc_char is not None self.esc_quote: str = esc_quote or "" self.unquote_results: bool = unquote_results self.convert_whitespace_escapes: bool = convert_whitespace_escapes self.multiline = multiline self.re_flags = re.RegexFlag(0) # fmt: off # build up re pattern for the content between the quote delimiters inner_pattern: list[str] = [] if esc_quote: inner_pattern.append(rf"(?:{re.escape(esc_quote)})") if esc_char: inner_pattern.append(rf"(?:{re.escape(esc_char)}.)") if len(self.end_quote_char) > 1: inner_pattern.append( "(?:" + "|".join( f"(?:{re.escape(self.end_quote_char[:i])}(?!{re.escape(self.end_quote_char[i:])}))" for i in range(len(self.end_quote_char) - 1, 0, -1) ) + ")" ) if self.multiline: self.re_flags |= re.MULTILINE | re.DOTALL inner_pattern.append( rf"(?:[^{_escape_regex_range_chars(self.end_quote_char[0])}" rf"{(_escape_regex_range_chars(self.esc_char) if self.has_esc_char else '')}])" ) else: inner_pattern.append( rf"(?:[^{_escape_regex_range_chars(self.end_quote_char[0])}\n\r" rf"{(_escape_regex_range_chars(self.esc_char) if self.has_esc_char else '')}])" ) self.pattern = "".join( [ re.escape(self.quote_char), "(?:", '|'.join(inner_pattern), ")*", re.escape(self.end_quote_char), ] ) if self.unquote_results: if self.convert_whitespace_escapes: self.unquote_scan_re = re.compile( rf"({'|'.join(re.escape(k) for k in self.ws_map)})" rf"|(\\[0-7]{3}|\\0|\\x[0-9a-fA-F]{2}|\\u[0-9a-fA-F]{4})" rf"|({re.escape(self.esc_char)}.)" rf"|(\n|.)", flags=self.re_flags, ) else: self.unquote_scan_re = re.compile( rf"({re.escape(self.esc_char)}.)" rf"|(\n|.)", flags=self.re_flags ) # fmt: on try: self.re = re.compile(self.pattern, self.re_flags) self.reString = self.pattern self.re_match = self.re.match except re.error: raise ValueError(f"invalid pattern {self.pattern!r} passed to Regex") self.errmsg = f"Expected {self.name}" self.mayIndexError = False self._may_return_empty = True def _generateDefaultName(self) -> str: if self.quote_char == self.end_quote_char and isinstance( self.quote_char, str_type ): return f"string enclosed in {self.quote_char!r}" return f"quoted string, starting with {self.quote_char} ending with {self.end_quote_char}" def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: # check first character of opening quote to see if that is a match # before doing the more complicated regex match result = ( instring[loc] == self.first_quote_char and self.re_match(instring, loc) or None ) if not result: raise ParseException(instring, loc, self.errmsg, self) # get ending loc and matched string from regex matching result loc = result.end() ret = result.group() def convert_escaped_numerics(s: str) -> str: if s == "0": return "\0" if s.isdigit() and len(s) == 3: return chr(int(s, base=8)) elif s.startswith(("u", "x")): return chr(int(s[1:], base=16)) else: return s if self.unquote_results: # strip off quotes ret = ret[self.quote_char_len : -self.end_quote_char_len] if isinstance(ret, str_type): # fmt: off if self.convert_whitespace_escapes: # as we iterate over matches in the input string, # collect from whichever match group of the unquote_scan_re # regex matches (only 1 group will match at any given time) ret = "".join( # match group 1 matches \t, \n, etc. self.ws_map[match.group(1)] if match.group(1) # match group 2 matches escaped octal, null, hex, and Unicode # sequences else convert_escaped_numerics(match.group(2)[1:]) if match.group(2) # match group 3 matches escaped characters else match.group(3)[-1] if match.group(3) # match group 4 matches any character else match.group(4) for match in self.unquote_scan_re.finditer(ret) ) else: ret = "".join( # match group 1 matches escaped characters match.group(1)[-1] if match.group(1) # match group 2 matches any character else match.group(2) for match in self.unquote_scan_re.finditer(ret) ) # fmt: on # replace escaped quotes if self.esc_quote: ret = ret.replace(self.esc_quote, self.end_quote_char) return loc, ret class CharsNotIn(Token): """Token for matching words composed of characters *not* in a given set (will include whitespace in matched characters if not listed in the provided exclusion set - see example). Defined with string containing all disallowed characters, and an optional minimum, maximum, and/or exact length. The default value for ``min`` is 1 (a minimum value < 1 is not valid); the default values for ``max`` and ``exact`` are 0, meaning no maximum or exact length restriction. Example:: # define a comma-separated-value as anything that is not a ',' csv_value = CharsNotIn(',') print(DelimitedList(csv_value).parse_string("dkls,lsdkjf,s12 34,@!#,213")) prints:: ['dkls', 'lsdkjf', 's12 34', '@!#', '213'] """ def __init__( self, not_chars: str = "", min: int = 1, max: int = 0, exact: int = 0, *, notChars: str = "", ) -> None: super().__init__() self.skipWhitespace = False self.notChars = not_chars or notChars self.notCharsSet = set(self.notChars) if min < 1: raise ValueError( "cannot specify a minimum length < 1; use" " Opt(CharsNotIn()) if zero-length char group is permitted" ) self.minLen = min if max > 0: self.maxLen = max else: self.maxLen = _MAX_INT if exact > 0: self.maxLen = exact self.minLen = exact self.errmsg = f"Expected {self.name}" self._may_return_empty = self.minLen == 0 self.mayIndexError = False def _generateDefaultName(self) -> str: not_chars_str = _collapse_string_to_ranges(self.notChars) if len(not_chars_str) > 16: return f"!W:({self.notChars[: 16 - 3]}...)" else: return f"!W:({self.notChars})" def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: notchars = self.notCharsSet if instring[loc] in notchars: raise ParseException(instring, loc, self.errmsg, self) start = loc loc += 1 maxlen = min(start + self.maxLen, len(instring)) while loc < maxlen and instring[loc] not in notchars: loc += 1 if loc - start < self.minLen: raise ParseException(instring, loc, self.errmsg, self) return loc, instring[start:loc] class White(Token): """Special matching class for matching whitespace. Normally, whitespace is ignored by pyparsing grammars. This class is included when some whitespace structures are significant. Define with a string containing the whitespace characters to be matched; default is ``" \\t\\r\\n"``. Also takes optional ``min``, ``max``, and ``exact`` arguments, as defined for the :class:`Word` class. """ whiteStrs = { " ": "<SP>", "\t": "<TAB>", "\n": "<LF>", "\r": "<CR>", "\f": "<FF>", "\u00A0": "<NBSP>", "\u1680": "<OGHAM_SPACE_MARK>", "\u180E": "<MONGOLIAN_VOWEL_SEPARATOR>", "\u2000": "<EN_QUAD>", "\u2001": "<EM_QUAD>", "\u2002": "<EN_SPACE>", "\u2003": "<EM_SPACE>", "\u2004": "<THREE-PER-EM_SPACE>", "\u2005": "<FOUR-PER-EM_SPACE>", "\u2006": "<SIX-PER-EM_SPACE>", "\u2007": "<FIGURE_SPACE>", "\u2008": "<PUNCTUATION_SPACE>", "\u2009": "<THIN_SPACE>", "\u200A": "<HAIR_SPACE>", "\u200B": "<ZERO_WIDTH_SPACE>", "\u202F": "<NNBSP>", "\u205F": "<MMSP>", "\u3000": "<IDEOGRAPHIC_SPACE>", } def __init__( self, ws: str = " \t\r\n", min: int = 1, max: int = 0, exact: int = 0 ) -> None: super().__init__() self.matchWhite = ws self.set_whitespace_chars( "".join(c for c in self.whiteStrs if c not in self.matchWhite), copy_defaults=True, ) # self.leave_whitespace() self._may_return_empty = True self.errmsg = f"Expected {self.name}" self.minLen = min if max > 0: self.maxLen = max else: self.maxLen = _MAX_INT if exact > 0: self.maxLen = exact self.minLen = exact def _generateDefaultName(self) -> str: return "".join(White.whiteStrs[c] for c in self.matchWhite) def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: if instring[loc] not in self.matchWhite: raise ParseException(instring, loc, self.errmsg, self) start = loc loc += 1 maxloc = start + self.maxLen maxloc = min(maxloc, len(instring)) while loc < maxloc and instring[loc] in self.matchWhite: loc += 1 if loc - start < self.minLen: raise ParseException(instring, loc, self.errmsg, self) return loc, instring[start:loc] class PositionToken(Token): def __init__(self) -> None: super().__init__() self._may_return_empty = True self.mayIndexError = False class GoToColumn(PositionToken): """Token to advance to a specific column of input text; useful for tabular report scraping. """ def __init__(self, colno: int) -> None: super().__init__() self.col = colno def preParse(self, instring: str, loc: int) -> int: if col(loc, instring) == self.col: return loc instrlen = len(instring) if self.ignoreExprs: loc = self._skipIgnorables(instring, loc) while ( loc < instrlen and instring[loc].isspace() and col(loc, instring) != self.col ): loc += 1 return loc def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: thiscol = col(loc, instring) if thiscol > self.col: raise ParseException(instring, loc, "Text not in expected column", self) newloc = loc + self.col - thiscol ret = instring[loc:newloc] return newloc, ret class LineStart(PositionToken): r"""Matches if current position is at the beginning of a line within the parse string Example:: test = '''\ AAA this line AAA and this line AAA but not this one B AAA and definitely not this one ''' for t in (LineStart() + 'AAA' + rest_of_line).search_string(test): print(t) prints:: ['AAA', ' this line'] ['AAA', ' and this line'] """ def __init__(self) -> None: super().__init__() self.leave_whitespace() self.orig_whiteChars = set() | self.whiteChars self.whiteChars.discard("\n") self.skipper = Empty().set_whitespace_chars(self.whiteChars) self.set_name("start of line") def preParse(self, instring: str, loc: int) -> int: if loc == 0: return loc ret = self.skipper.preParse(instring, loc) if "\n" in self.orig_whiteChars: while instring[ret : ret + 1] == "\n": ret = self.skipper.preParse(instring, ret + 1) return ret def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: if col(loc, instring) == 1: return loc, [] raise ParseException(instring, loc, self.errmsg, self) class LineEnd(PositionToken): """Matches if current position is at the end of a line within the parse string """ def __init__(self) -> None: super().__init__() self.whiteChars.discard("\n") self.set_whitespace_chars(self.whiteChars, copy_defaults=False) self.set_name("end of line") def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: if loc < len(instring): if instring[loc] == "\n": return loc + 1, "\n" else: raise ParseException(instring, loc, self.errmsg, self) elif loc == len(instring): return loc + 1, [] else: raise ParseException(instring, loc, self.errmsg, self) class StringStart(PositionToken): """Matches if current position is at the beginning of the parse string """ def __init__(self) -> None: super().__init__() self.set_name("start of text") def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: # see if entire string up to here is just whitespace and ignoreables if loc != 0 and loc != self.preParse(instring, 0): raise ParseException(instring, loc, self.errmsg, self) return loc, [] class StringEnd(PositionToken): """ Matches if current position is at the end of the parse string """ def __init__(self) -> None: super().__init__() self.set_name("end of text") def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: if loc < len(instring): raise ParseException(instring, loc, self.errmsg, self) if loc == len(instring): return loc + 1, [] if loc > len(instring): return loc, [] raise ParseException(instring, loc, self.errmsg, self) class WordStart(PositionToken): """Matches if the current position is at the beginning of a :class:`Word`, and is not preceded by any character in a given set of ``word_chars`` (default= ``printables``). To emulate the ``\b`` behavior of regular expressions, use ``WordStart(alphanums)``. ``WordStart`` will also match at the beginning of the string being parsed, or at the beginning of a line. """ def __init__( self, word_chars: str = printables, *, wordChars: str = printables ) -> None: wordChars = word_chars if wordChars == printables else wordChars super().__init__() self.wordChars = set(wordChars) self.set_name("start of a word") def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: if loc != 0: if ( instring[loc - 1] in self.wordChars or instring[loc] not in self.wordChars ): raise ParseException(instring, loc, self.errmsg, self) return loc, [] class WordEnd(PositionToken): """Matches if the current position is at the end of a :class:`Word`, and is not followed by any character in a given set of ``word_chars`` (default= ``printables``). To emulate the ``\b`` behavior of regular expressions, use ``WordEnd(alphanums)``. ``WordEnd`` will also match at the end of the string being parsed, or at the end of a line. """ def __init__( self, word_chars: str = printables, *, wordChars: str = printables ) -> None: wordChars = word_chars if wordChars == printables else wordChars super().__init__() self.wordChars = set(wordChars) self.skipWhitespace = False self.set_name("end of a word") def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: instrlen = len(instring) if instrlen > 0 and loc < instrlen: if ( instring[loc] in self.wordChars or instring[loc - 1] not in self.wordChars ): raise ParseException(instring, loc, self.errmsg, self) return loc, [] class Tag(Token): """ A meta-element for inserting a named result into the parsed tokens that may be checked later in a parse action or while processing the parsed results. Accepts an optional tag value, defaulting to `True`. Example:: end_punc = "." | ("!" + Tag("enthusiastic"))) greeting = "Hello," + Word(alphas) + end_punc result = greeting.parse_string("Hello, World.") print(result.dump()) result = greeting.parse_string("Hello, World!") print(result.dump()) prints:: ['Hello,', 'World', '.'] ['Hello,', 'World', '!'] - enthusiastic: True """ def __init__(self, tag_name: str, value: Any = True) -> None: super().__init__() self._may_return_empty = True self.mayIndexError = False self.leave_whitespace() self.tag_name = tag_name self.tag_value = value self.add_parse_action(self._add_tag) self.show_in_diagram = False def _add_tag(self, tokens: ParseResults): tokens[self.tag_name] = self.tag_value def _generateDefaultName(self) -> str: return f"{type(self).__name__}:{self.tag_name}={self.tag_value!r}" class ParseExpression(ParserElement): """Abstract subclass of ParserElement, for combining and post-processing parsed tokens. """ def __init__( self, exprs: typing.Iterable[ParserElement], savelist: bool = False ) -> None: super().__init__(savelist) self.exprs: list[ParserElement] if isinstance(exprs, _generatorType): exprs = list(exprs) if isinstance(exprs, str_type): self.exprs = [self._literalStringClass(exprs)] elif isinstance(exprs, ParserElement): self.exprs = [exprs] elif isinstance(exprs, Iterable): exprs = list(exprs) # if sequence of strings provided, wrap with Literal if any(isinstance(expr, str_type) for expr in exprs): exprs = ( self._literalStringClass(e) if isinstance(e, str_type) else e for e in exprs ) self.exprs = list(exprs) else: try: self.exprs = list(exprs) except TypeError: self.exprs = [exprs] self.callPreparse = False def recurse(self) -> list[ParserElement]: return self.exprs[:] def append(self, other) -> ParserElement: self.exprs.append(other) self._defaultName = None return self def leave_whitespace(self, recursive: bool = True) -> ParserElement: """ Extends ``leave_whitespace`` defined in base class, and also invokes ``leave_whitespace`` on all contained expressions. """ super().leave_whitespace(recursive) if recursive: self.exprs = [e.copy() for e in self.exprs] for e in self.exprs: e.leave_whitespace(recursive) return self def ignore_whitespace(self, recursive: bool = True) -> ParserElement: """ Extends ``ignore_whitespace`` defined in base class, and also invokes ``leave_whitespace`` on all contained expressions. """ super().ignore_whitespace(recursive) if recursive: self.exprs = [e.copy() for e in self.exprs] for e in self.exprs: e.ignore_whitespace(recursive) return self def ignore(self, other) -> ParserElement: if isinstance(other, Suppress): if other not in self.ignoreExprs: super().ignore(other) for e in self.exprs: e.ignore(self.ignoreExprs[-1]) else: super().ignore(other) for e in self.exprs: e.ignore(self.ignoreExprs[-1]) return self def _generateDefaultName(self) -> str: return f"{type(self).__name__}:({self.exprs})" def streamline(self) -> ParserElement: if self.streamlined: return self super().streamline() for e in self.exprs: e.streamline() # collapse nested :class:`And`'s of the form ``And(And(And(a, b), c), d)`` to ``And(a, b, c, d)`` # but only if there are no parse actions or resultsNames on the nested And's # (likewise for :class:`Or`'s and :class:`MatchFirst`'s) if len(self.exprs) == 2: other = self.exprs[0] if ( isinstance(other, self.__class__) and not other.parseAction and other.resultsName is None and not other.debug ): self.exprs = other.exprs[:] + [self.exprs[1]] self._defaultName = None self._may_return_empty |= other.mayReturnEmpty self.mayIndexError |= other.mayIndexError other = self.exprs[-1] if ( isinstance(other, self.__class__) and not other.parseAction and other.resultsName is None and not other.debug ): self.exprs = self.exprs[:-1] + other.exprs[:] self._defaultName = None self._may_return_empty |= other.mayReturnEmpty self.mayIndexError |= other.mayIndexError self.errmsg = f"Expected {self}" return self def validate(self, validateTrace=None) -> None: warnings.warn( "ParserElement.validate() is deprecated, and should not be used to check for left recursion", DeprecationWarning, stacklevel=2, ) tmp = (validateTrace if validateTrace is not None else [])[:] + [self] for e in self.exprs: e.validate(tmp) self._checkRecursion([]) def copy(self) -> ParserElement: ret = super().copy() ret = typing.cast(ParseExpression, ret) ret.exprs = [e.copy() for e in self.exprs] return ret def _setResultsName(self, name, list_all_matches=False) -> ParserElement: if not ( __diag__.warn_ungrouped_named_tokens_in_collection and Diagnostics.warn_ungrouped_named_tokens_in_collection not in self.suppress_warnings_ ): return super()._setResultsName(name, list_all_matches) for e in self.exprs: if ( isinstance(e, ParserElement) and e.resultsName and ( Diagnostics.warn_ungrouped_named_tokens_in_collection not in e.suppress_warnings_ ) ): warning = ( "warn_ungrouped_named_tokens_in_collection:" f" setting results name {name!r} on {type(self).__name__} expression" f" collides with {e.resultsName!r} on contained expression" ) warnings.warn(warning, stacklevel=3) break return super()._setResultsName(name, list_all_matches) # Compatibility synonyms # fmt: off leaveWhitespace = replaced_by_pep8("leaveWhitespace", leave_whitespace) ignoreWhitespace = replaced_by_pep8("ignoreWhitespace", ignore_whitespace) # fmt: on class And(ParseExpression): """ Requires all given :class:`ParserElement` s to be found in the given order. Expressions may be separated by whitespace. May be constructed using the ``'+'`` operator. May also be constructed using the ``'-'`` operator, which will suppress backtracking. Example:: integer = Word(nums) name_expr = Word(alphas)[1, ...] expr = And([integer("id"), name_expr("name"), integer("age")]) # more easily written as: expr = integer("id") + name_expr("name") + integer("age") """ class _ErrorStop(Empty): def __init__(self, *args, **kwargs) -> None: super().__init__(*args, **kwargs) self.leave_whitespace() def _generateDefaultName(self) -> str: return "-" def __init__( self, exprs_arg: typing.Iterable[Union[ParserElement, str]], savelist: bool = True, ) -> None: # instantiate exprs as a list, converting strs to ParserElements exprs: list[ParserElement] = [ self._literalStringClass(e) if isinstance(e, str) else e for e in exprs_arg ] # convert any Ellipsis elements to SkipTo if Ellipsis in exprs: # Ellipsis cannot be the last element if exprs[-1] is Ellipsis: raise Exception("cannot construct And with sequence ending in ...") tmp: list[ParserElement] = [] for cur_expr, next_expr in zip(exprs, exprs[1:]): if cur_expr is Ellipsis: tmp.append(SkipTo(next_expr)("_skipped*")) else: tmp.append(cur_expr) exprs[:-1] = tmp super().__init__(exprs, savelist) if self.exprs: self._may_return_empty = all(e.mayReturnEmpty for e in self.exprs) if not isinstance(self.exprs[0], White): self.set_whitespace_chars( self.exprs[0].whiteChars, copy_defaults=self.exprs[0].copyDefaultWhiteChars, ) self.skipWhitespace = self.exprs[0].skipWhitespace else: self.skipWhitespace = False else: self._may_return_empty = True self.callPreparse = True def streamline(self) -> ParserElement: # collapse any _PendingSkip's if self.exprs and any( isinstance(e, ParseExpression) and e.exprs and isinstance(e.exprs[-1], _PendingSkip) for e in self.exprs[:-1] ): deleted_expr_marker = NoMatch() for i, e in enumerate(self.exprs[:-1]): if e is deleted_expr_marker: continue if ( isinstance(e, ParseExpression) and e.exprs and isinstance(e.exprs[-1], _PendingSkip) ): e.exprs[-1] = e.exprs[-1] + self.exprs[i + 1] self.exprs[i + 1] = deleted_expr_marker self.exprs = [e for e in self.exprs if e is not deleted_expr_marker] super().streamline() # link any IndentedBlocks to the prior expression prev: ParserElement cur: ParserElement for prev, cur in zip(self.exprs, self.exprs[1:]): # traverse cur or any first embedded expr of cur looking for an IndentedBlock # (but watch out for recursive grammar) seen = set() while True: if id(cur) in seen: break seen.add(id(cur)) if isinstance(cur, IndentedBlock): prev.add_parse_action( lambda s, l, t, cur_=cur: setattr( cur_, "parent_anchor", col(l, s) ) ) break subs = cur.recurse() next_first = next(iter(subs), None) if next_first is None: break cur = typing.cast(ParserElement, next_first) self._may_return_empty = all(e.mayReturnEmpty for e in self.exprs) return self def parseImpl(self, instring, loc, do_actions=True): # pass False as callPreParse arg to _parse for first element, since we already # pre-parsed the string as part of our And pre-parsing loc, resultlist = self.exprs[0]._parse( instring, loc, do_actions, callPreParse=False ) errorStop = False for e in self.exprs[1:]: # if isinstance(e, And._ErrorStop): if type(e) is And._ErrorStop: errorStop = True continue if errorStop: try: loc, exprtokens = e._parse(instring, loc, do_actions) except ParseSyntaxException: raise except ParseBaseException as pe: pe.__traceback__ = None raise ParseSyntaxException._from_exception(pe) except IndexError: raise ParseSyntaxException( instring, len(instring), self.errmsg, self ) else: loc, exprtokens = e._parse(instring, loc, do_actions) resultlist += exprtokens return loc, resultlist def __iadd__(self, other): if isinstance(other, str_type): other = self._literalStringClass(other) if not isinstance(other, ParserElement): return NotImplemented return self.append(other) # And([self, other]) def _checkRecursion(self, parseElementList): subRecCheckList = parseElementList[:] + [self] for e in self.exprs: e._checkRecursion(subRecCheckList) if not e.mayReturnEmpty: break def _generateDefaultName(self) -> str: inner = " ".join(str(e) for e in self.exprs) # strip off redundant inner {}'s while len(inner) > 1 and inner[0 :: len(inner) - 1] == "{}": inner = inner[1:-1] return f"{{{inner}}}" class Or(ParseExpression): """Requires that at least one :class:`ParserElement` is found. If two expressions match, the expression that matches the longest string will be used. May be constructed using the ``'^'`` operator. Example:: # construct Or using '^' operator number = Word(nums) ^ Combine(Word(nums) + '.' + Word(nums)) print(number.search_string("123 3.1416 789")) prints:: [['123'], ['3.1416'], ['789']] """ def __init__( self, exprs: typing.Iterable[ParserElement], savelist: bool = False ) -> None: super().__init__(exprs, savelist) if self.exprs: self._may_return_empty = any(e.mayReturnEmpty for e in self.exprs) self.skipWhitespace = all(e.skipWhitespace for e in self.exprs) else: self._may_return_empty = True def streamline(self) -> ParserElement: super().streamline() if self.exprs: self._may_return_empty = any(e.mayReturnEmpty for e in self.exprs) self.saveAsList = any(e.saveAsList for e in self.exprs) self.skipWhitespace = all( e.skipWhitespace and not isinstance(e, White) for e in self.exprs ) else: self.saveAsList = False return self def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: maxExcLoc = -1 maxException = None matches: list[tuple[int, ParserElement]] = [] fatals: list[ParseFatalException] = [] if all(e.callPreparse for e in self.exprs): loc = self.preParse(instring, loc) for e in self.exprs: try: loc2 = e.try_parse(instring, loc, raise_fatal=True) except ParseFatalException as pfe: pfe.__traceback__ = None pfe.parser_element = e fatals.append(pfe) maxException = None maxExcLoc = -1 except ParseException as err: if not fatals: err.__traceback__ = None if err.loc > maxExcLoc: maxException = err maxExcLoc = err.loc except IndexError: if len(instring) > maxExcLoc: maxException = ParseException( instring, len(instring), e.errmsg, self ) maxExcLoc = len(instring) else: # save match among all matches, to retry longest to shortest matches.append((loc2, e)) if matches: # re-evaluate all matches in descending order of length of match, in case attached actions # might change whether or how much they match of the input. matches.sort(key=itemgetter(0), reverse=True) if not do_actions: # no further conditions or parse actions to change the selection of # alternative, so the first match will be the best match best_expr = matches[0][1] return best_expr._parse(instring, loc, do_actions) longest: tuple[int, typing.Optional[ParseResults]] = -1, None for loc1, expr1 in matches: if loc1 <= longest[0]: # already have a longer match than this one will deliver, we are done return longest try: loc2, toks = expr1._parse(instring, loc, do_actions) except ParseException as err: err.__traceback__ = None if err.loc > maxExcLoc: maxException = err maxExcLoc = err.loc else: if loc2 >= loc1: return loc2, toks # didn't match as much as before elif loc2 > longest[0]: longest = loc2, toks if longest != (-1, None): return longest if fatals: if len(fatals) > 1: fatals.sort(key=lambda e: -e.loc) if fatals[0].loc == fatals[1].loc: fatals.sort(key=lambda e: (-e.loc, -len(str(e.parser_element)))) max_fatal = fatals[0] raise max_fatal if maxException is not None: # infer from this check that all alternatives failed at the current position # so emit this collective error message instead of any single error message parse_start_loc = self.preParse(instring, loc) if maxExcLoc == parse_start_loc: maxException.msg = self.errmsg or "" raise maxException raise ParseException(instring, loc, "no defined alternatives to match", self) def __ixor__(self, other): if isinstance(other, str_type): other = self._literalStringClass(other) if not isinstance(other, ParserElement): return NotImplemented return self.append(other) # Or([self, other]) def _generateDefaultName(self) -> str: return f"{{{' ^ '.join(str(e) for e in self.exprs)}}}" def _setResultsName(self, name, list_all_matches=False) -> ParserElement: if ( __diag__.warn_multiple_tokens_in_named_alternation and Diagnostics.warn_multiple_tokens_in_named_alternation not in self.suppress_warnings_ ): if any( isinstance(e, And) and Diagnostics.warn_multiple_tokens_in_named_alternation not in e.suppress_warnings_ for e in self.exprs ): warning = ( "warn_multiple_tokens_in_named_alternation:" f" setting results name {name!r} on {type(self).__name__} expression" " will return a list of all parsed tokens in an And alternative," " in prior versions only the first token was returned; enclose" " contained argument in Group" ) warnings.warn(warning, stacklevel=3) return super()._setResultsName(name, list_all_matches) class MatchFirst(ParseExpression): """Requires that at least one :class:`ParserElement` is found. If more than one expression matches, the first one listed is the one that will match. May be constructed using the ``'|'`` operator. Example:: # construct MatchFirst using '|' operator # watch the order of expressions to match number = Word(nums) | Combine(Word(nums) + '.' + Word(nums)) print(number.search_string("123 3.1416 789")) # Fail! -> [['123'], ['3'], ['1416'], ['789']] # put more selective expression first number = Combine(Word(nums) + '.' + Word(nums)) | Word(nums) print(number.search_string("123 3.1416 789")) # Better -> [['123'], ['3.1416'], ['789']] """ def __init__( self, exprs: typing.Iterable[ParserElement], savelist: bool = False ) -> None: super().__init__(exprs, savelist) if self.exprs: self._may_return_empty = any(e.mayReturnEmpty for e in self.exprs) self.skipWhitespace = all(e.skipWhitespace for e in self.exprs) else: self._may_return_empty = True def streamline(self) -> ParserElement: if self.streamlined: return self super().streamline() if self.exprs: self.saveAsList = any(e.saveAsList for e in self.exprs) self._may_return_empty = any(e.mayReturnEmpty for e in self.exprs) self.skipWhitespace = all( e.skipWhitespace and not isinstance(e, White) for e in self.exprs ) else: self.saveAsList = False self._may_return_empty = True return self def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: maxExcLoc = -1 maxException = None for e in self.exprs: try: return e._parse(instring, loc, do_actions) except ParseFatalException as pfe: pfe.__traceback__ = None pfe.parser_element = e raise except ParseException as err: if err.loc > maxExcLoc: maxException = err maxExcLoc = err.loc except IndexError: if len(instring) > maxExcLoc: maxException = ParseException( instring, len(instring), e.errmsg, self ) maxExcLoc = len(instring) if maxException is not None: # infer from this check that all alternatives failed at the current position # so emit this collective error message instead of any individual error message parse_start_loc = self.preParse(instring, loc) if maxExcLoc == parse_start_loc: maxException.msg = self.errmsg or "" raise maxException raise ParseException(instring, loc, "no defined alternatives to match", self) def __ior__(self, other): if isinstance(other, str_type): other = self._literalStringClass(other) if not isinstance(other, ParserElement): return NotImplemented return self.append(other) # MatchFirst([self, other]) def _generateDefaultName(self) -> str: return f"{{{' | '.join(str(e) for e in self.exprs)}}}" def _setResultsName(self, name, list_all_matches=False) -> ParserElement: if ( __diag__.warn_multiple_tokens_in_named_alternation and Diagnostics.warn_multiple_tokens_in_named_alternation not in self.suppress_warnings_ ): if any( isinstance(e, And) and Diagnostics.warn_multiple_tokens_in_named_alternation not in e.suppress_warnings_ for e in self.exprs ): warning = ( "warn_multiple_tokens_in_named_alternation:" f" setting results name {name!r} on {type(self).__name__} expression" " will return a list of all parsed tokens in an And alternative," " in prior versions only the first token was returned; enclose" " contained argument in Group" ) warnings.warn(warning, stacklevel=3) return super()._setResultsName(name, list_all_matches) class Each(ParseExpression): """Requires all given :class:`ParserElement` s to be found, but in any order. Expressions may be separated by whitespace. May be constructed using the ``'&'`` operator. Example:: color = one_of("RED ORANGE YELLOW GREEN BLUE PURPLE BLACK WHITE BROWN") shape_type = one_of("SQUARE CIRCLE TRIANGLE STAR HEXAGON OCTAGON") integer = Word(nums) shape_attr = "shape:" + shape_type("shape") posn_attr = "posn:" + Group(integer("x") + ',' + integer("y"))("posn") color_attr = "color:" + color("color") size_attr = "size:" + integer("size") # use Each (using operator '&') to accept attributes in any order # (shape and posn are required, color and size are optional) shape_spec = shape_attr & posn_attr & Opt(color_attr) & Opt(size_attr) shape_spec.run_tests(''' shape: SQUARE color: BLACK posn: 100, 120 shape: CIRCLE size: 50 color: BLUE posn: 50,80 color:GREEN size:20 shape:TRIANGLE posn:20,40 ''' ) prints:: shape: SQUARE color: BLACK posn: 100, 120 ['shape:', 'SQUARE', 'color:', 'BLACK', 'posn:', ['100', ',', '120']] - color: BLACK - posn: ['100', ',', '120'] - x: 100 - y: 120 - shape: SQUARE shape: CIRCLE size: 50 color: BLUE posn: 50,80 ['shape:', 'CIRCLE', 'size:', '50', 'color:', 'BLUE', 'posn:', ['50', ',', '80']] - color: BLUE - posn: ['50', ',', '80'] - x: 50 - y: 80 - shape: CIRCLE - size: 50 color: GREEN size: 20 shape: TRIANGLE posn: 20,40 ['color:', 'GREEN', 'size:', '20', 'shape:', 'TRIANGLE', 'posn:', ['20', ',', '40']] - color: GREEN - posn: ['20', ',', '40'] - x: 20 - y: 40 - shape: TRIANGLE - size: 20 """ def __init__( self, exprs: typing.Iterable[ParserElement], savelist: bool = True ) -> None: super().__init__(exprs, savelist) if self.exprs: self._may_return_empty = all(e.mayReturnEmpty for e in self.exprs) else: self._may_return_empty = True self.skipWhitespace = True self.initExprGroups = True self.saveAsList = True def __iand__(self, other): if isinstance(other, str_type): other = self._literalStringClass(other) if not isinstance(other, ParserElement): return NotImplemented return self.append(other) # Each([self, other]) def streamline(self) -> ParserElement: super().streamline() if self.exprs: self._may_return_empty = all(e.mayReturnEmpty for e in self.exprs) else: self._may_return_empty = True return self def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: if self.initExprGroups: self.opt1map = dict( (id(e.expr), e) for e in self.exprs if isinstance(e, Opt) ) opt1 = [e.expr for e in self.exprs if isinstance(e, Opt)] opt2 = [ e for e in self.exprs if e.mayReturnEmpty and not isinstance(e, (Opt, Regex, ZeroOrMore)) ] self.optionals = opt1 + opt2 self.multioptionals = [ e.expr.set_results_name(e.resultsName, list_all_matches=True) for e in self.exprs if isinstance(e, _MultipleMatch) ] self.multirequired = [ e.expr.set_results_name(e.resultsName, list_all_matches=True) for e in self.exprs if isinstance(e, OneOrMore) ] self.required = [ e for e in self.exprs if not isinstance(e, (Opt, ZeroOrMore, OneOrMore)) ] self.required += self.multirequired self.initExprGroups = False tmpLoc = loc tmpReqd = self.required[:] tmpOpt = self.optionals[:] multis = self.multioptionals[:] matchOrder: list[ParserElement] = [] keepMatching = True failed: list[ParserElement] = [] fatals: list[ParseFatalException] = [] while keepMatching: tmpExprs = tmpReqd + tmpOpt + multis failed.clear() fatals.clear() for e in tmpExprs: try: tmpLoc = e.try_parse(instring, tmpLoc, raise_fatal=True) except ParseFatalException as pfe: pfe.__traceback__ = None pfe.parser_element = e fatals.append(pfe) failed.append(e) except ParseException: failed.append(e) else: matchOrder.append(self.opt1map.get(id(e), e)) if e in tmpReqd: tmpReqd.remove(e) elif e in tmpOpt: tmpOpt.remove(e) if len(failed) == len(tmpExprs): keepMatching = False # look for any ParseFatalExceptions if fatals: if len(fatals) > 1: fatals.sort(key=lambda e: -e.loc) if fatals[0].loc == fatals[1].loc: fatals.sort(key=lambda e: (-e.loc, -len(str(e.parser_element)))) max_fatal = fatals[0] raise max_fatal if tmpReqd: missing = ", ".join([str(e) for e in tmpReqd]) raise ParseException( instring, loc, f"Missing one or more required elements ({missing})", ) # add any unmatched Opts, in case they have default values defined matchOrder += [e for e in self.exprs if isinstance(e, Opt) and e.expr in tmpOpt] total_results = ParseResults([]) for e in matchOrder: loc, results = e._parse(instring, loc, do_actions) total_results += results return loc, total_results def _generateDefaultName(self) -> str: return f"{{{' & '.join(str(e) for e in self.exprs)}}}" class ParseElementEnhance(ParserElement): """Abstract subclass of :class:`ParserElement`, for combining and post-processing parsed tokens. """ def __init__(self, expr: Union[ParserElement, str], savelist: bool = False) -> None: super().__init__(savelist) if isinstance(expr, str_type): expr_str = typing.cast(str, expr) if issubclass(self._literalStringClass, Token): expr = self._literalStringClass(expr_str) # type: ignore[call-arg] elif issubclass(type(self), self._literalStringClass): expr = Literal(expr_str) else: expr = self._literalStringClass(Literal(expr_str)) # type: ignore[assignment, call-arg] expr = typing.cast(ParserElement, expr) self.expr = expr if expr is not None: self.mayIndexError = expr.mayIndexError self._may_return_empty = expr.mayReturnEmpty self.set_whitespace_chars( expr.whiteChars, copy_defaults=expr.copyDefaultWhiteChars ) self.skipWhitespace = expr.skipWhitespace self.saveAsList = expr.saveAsList self.callPreparse = expr.callPreparse self.ignoreExprs.extend(expr.ignoreExprs) def recurse(self) -> list[ParserElement]: return [self.expr] if self.expr is not None else [] def parseImpl(self, instring, loc, do_actions=True): if self.expr is None: raise ParseException(instring, loc, "No expression defined", self) try: return self.expr._parse(instring, loc, do_actions, callPreParse=False) except ParseSyntaxException: raise except ParseBaseException as pbe: pbe.pstr = pbe.pstr or instring pbe.loc = pbe.loc or loc pbe.parser_element = pbe.parser_element or self if not isinstance(self, Forward) and self.customName is not None: if self.errmsg: pbe.msg = self.errmsg raise def leave_whitespace(self, recursive: bool = True) -> ParserElement: super().leave_whitespace(recursive) if recursive: if self.expr is not None: self.expr = self.expr.copy() self.expr.leave_whitespace(recursive) return self def ignore_whitespace(self, recursive: bool = True) -> ParserElement: super().ignore_whitespace(recursive) if recursive: if self.expr is not None: self.expr = self.expr.copy() self.expr.ignore_whitespace(recursive) return self def ignore(self, other) -> ParserElement: if not isinstance(other, Suppress) or other not in self.ignoreExprs: super().ignore(other) if self.expr is not None: self.expr.ignore(self.ignoreExprs[-1]) return self def streamline(self) -> ParserElement: super().streamline() if self.expr is not None: self.expr.streamline() return self def _checkRecursion(self, parseElementList): if self in parseElementList: raise RecursiveGrammarException(parseElementList + [self]) subRecCheckList = parseElementList[:] + [self] if self.expr is not None: self.expr._checkRecursion(subRecCheckList) def validate(self, validateTrace=None) -> None: warnings.warn( "ParserElement.validate() is deprecated, and should not be used to check for left recursion", DeprecationWarning, stacklevel=2, ) if validateTrace is None: validateTrace = [] tmp = validateTrace[:] + [self] if self.expr is not None: self.expr.validate(tmp) self._checkRecursion([]) def _generateDefaultName(self) -> str: return f"{type(self).__name__}:({self.expr})" # Compatibility synonyms # fmt: off leaveWhitespace = replaced_by_pep8("leaveWhitespace", leave_whitespace) ignoreWhitespace = replaced_by_pep8("ignoreWhitespace", ignore_whitespace) # fmt: on class IndentedBlock(ParseElementEnhance): """ Expression to match one or more expressions at a given indentation level. Useful for parsing text where structure is implied by indentation (like Python source code). """ class _Indent(Empty): def __init__(self, ref_col: int) -> None: super().__init__() self.errmsg = f"expected indent at column {ref_col}" self.add_condition(lambda s, l, t: col(l, s) == ref_col) class _IndentGreater(Empty): def __init__(self, ref_col: int) -> None: super().__init__() self.errmsg = f"expected indent at column greater than {ref_col}" self.add_condition(lambda s, l, t: col(l, s) > ref_col) def __init__( self, expr: ParserElement, *, recursive: bool = False, grouped: bool = True ) -> None: super().__init__(expr, savelist=True) # if recursive: # raise NotImplementedError("IndentedBlock with recursive is not implemented") self._recursive = recursive self._grouped = grouped self.parent_anchor = 1 def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: # advance parse position to non-whitespace by using an Empty() # this should be the column to be used for all subsequent indented lines anchor_loc = Empty().preParse(instring, loc) # see if self.expr matches at the current location - if not it will raise an exception # and no further work is necessary self.expr.try_parse(instring, anchor_loc, do_actions=do_actions) indent_col = col(anchor_loc, instring) peer_detect_expr = self._Indent(indent_col) inner_expr = Empty() + peer_detect_expr + self.expr if self._recursive: sub_indent = self._IndentGreater(indent_col) nested_block = IndentedBlock( self.expr, recursive=self._recursive, grouped=self._grouped ) nested_block.set_debug(self.debug) nested_block.parent_anchor = indent_col inner_expr += Opt(sub_indent + nested_block) inner_expr.set_name(f"inner {hex(id(inner_expr))[-4:].upper()}@{indent_col}") block = OneOrMore(inner_expr) trailing_undent = self._Indent(self.parent_anchor) | StringEnd() if self._grouped: wrapper = Group else: wrapper = lambda expr: expr # type: ignore[misc, assignment] return (wrapper(block) + Optional(trailing_undent)).parseImpl( instring, anchor_loc, do_actions ) class AtStringStart(ParseElementEnhance): """Matches if expression matches at the beginning of the parse string:: AtStringStart(Word(nums)).parse_string("123") # prints ["123"] AtStringStart(Word(nums)).parse_string(" 123") # raises ParseException """ def __init__(self, expr: Union[ParserElement, str]) -> None: super().__init__(expr) self.callPreparse = False def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: if loc != 0: raise ParseException(instring, loc, "not found at string start") return super().parseImpl(instring, loc, do_actions) class AtLineStart(ParseElementEnhance): r"""Matches if an expression matches at the beginning of a line within the parse string Example:: test = '''\ AAA this line AAA and this line AAA but not this one B AAA and definitely not this one ''' for t in (AtLineStart('AAA') + rest_of_line).search_string(test): print(t) prints:: ['AAA', ' this line'] ['AAA', ' and this line'] """ def __init__(self, expr: Union[ParserElement, str]) -> None: super().__init__(expr) self.callPreparse = False def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: if col(loc, instring) != 1: raise ParseException(instring, loc, "not found at line start") return super().parseImpl(instring, loc, do_actions) class FollowedBy(ParseElementEnhance): """Lookahead matching of the given parse expression. ``FollowedBy`` does *not* advance the parsing position within the input string, it only verifies that the specified parse expression matches at the current position. ``FollowedBy`` always returns a null token list. If any results names are defined in the lookahead expression, those *will* be returned for access by name. Example:: # use FollowedBy to match a label only if it is followed by a ':' data_word = Word(alphas) label = data_word + FollowedBy(':') attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) attr_expr[1, ...].parse_string("shape: SQUARE color: BLACK posn: upper left").pprint() prints:: [['shape', 'SQUARE'], ['color', 'BLACK'], ['posn', 'upper left']] """ def __init__(self, expr: Union[ParserElement, str]) -> None: super().__init__(expr) self._may_return_empty = True def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: # by using self._expr.parse and deleting the contents of the returned ParseResults list # we keep any named results that were defined in the FollowedBy expression _, ret = self.expr._parse(instring, loc, do_actions=do_actions) del ret[:] return loc, ret class PrecededBy(ParseElementEnhance): """Lookbehind matching of the given parse expression. ``PrecededBy`` does not advance the parsing position within the input string, it only verifies that the specified parse expression matches prior to the current position. ``PrecededBy`` always returns a null token list, but if a results name is defined on the given expression, it is returned. Parameters: - ``expr`` - expression that must match prior to the current parse location - ``retreat`` - (default= ``None``) - (int) maximum number of characters to lookbehind prior to the current parse location If the lookbehind expression is a string, :class:`Literal`, :class:`Keyword`, or a :class:`Word` or :class:`CharsNotIn` with a specified exact or maximum length, then the retreat parameter is not required. Otherwise, retreat must be specified to give a maximum number of characters to look back from the current parse position for a lookbehind match. Example:: # VB-style variable names with type prefixes int_var = PrecededBy("#") + pyparsing_common.identifier str_var = PrecededBy("$") + pyparsing_common.identifier """ def __init__(self, expr: Union[ParserElement, str], retreat: int = 0) -> None: super().__init__(expr) self.expr = self.expr().leave_whitespace() self._may_return_empty = True self.mayIndexError = False self.exact = False if isinstance(expr, str_type): expr = typing.cast(str, expr) retreat = len(expr) self.exact = True elif isinstance(expr, (Literal, Keyword)): retreat = expr.matchLen self.exact = True elif isinstance(expr, (Word, CharsNotIn)) and expr.maxLen != _MAX_INT: retreat = expr.maxLen self.exact = True elif isinstance(expr, PositionToken): retreat = 0 self.exact = True self.retreat = retreat self.errmsg = f"not preceded by {expr}" self.skipWhitespace = False self.parseAction.append(lambda s, l, t: t.__delitem__(slice(None, None))) def parseImpl(self, instring, loc=0, do_actions=True) -> ParseImplReturnType: if self.exact: if loc < self.retreat: raise ParseException(instring, loc, self.errmsg, self) start = loc - self.retreat _, ret = self.expr._parse(instring, start) return loc, ret # retreat specified a maximum lookbehind window, iterate test_expr = self.expr + StringEnd() instring_slice = instring[max(0, loc - self.retreat) : loc] last_expr: ParseBaseException = ParseException(instring, loc, self.errmsg, self) for offset in range(1, min(loc, self.retreat + 1) + 1): try: # print('trying', offset, instring_slice, repr(instring_slice[loc - offset:])) _, ret = test_expr._parse(instring_slice, len(instring_slice) - offset) except ParseBaseException as pbe: last_expr = pbe else: break else: raise last_expr return loc, ret class Located(ParseElementEnhance): """ Decorates a returned token with its starting and ending locations in the input string. This helper adds the following results names: - ``locn_start`` - location where matched expression begins - ``locn_end`` - location where matched expression ends - ``value`` - the actual parsed results Be careful if the input text contains ``<TAB>`` characters, you may want to call :class:`ParserElement.parse_with_tabs` Example:: wd = Word(alphas) for match in Located(wd).search_string("ljsdf123lksdjjf123lkkjj1222"): print(match) prints:: [0, ['ljsdf'], 5] [8, ['lksdjjf'], 15] [18, ['lkkjj'], 23] """ def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: start = loc loc, tokens = self.expr._parse(instring, start, do_actions, callPreParse=False) ret_tokens = ParseResults([start, tokens, loc]) ret_tokens["locn_start"] = start ret_tokens["value"] = tokens ret_tokens["locn_end"] = loc if self.resultsName: # must return as a list, so that the name will be attached to the complete group return loc, [ret_tokens] else: return loc, ret_tokens class NotAny(ParseElementEnhance): """ Lookahead to disallow matching with the given parse expression. ``NotAny`` does *not* advance the parsing position within the input string, it only verifies that the specified parse expression does *not* match at the current position. Also, ``NotAny`` does *not* skip over leading whitespace. ``NotAny`` always returns a null token list. May be constructed using the ``'~'`` operator. Example:: AND, OR, NOT = map(CaselessKeyword, "AND OR NOT".split()) # take care not to mistake keywords for identifiers ident = ~(AND | OR | NOT) + Word(alphas) boolean_term = Opt(NOT) + ident # very crude boolean expression - to support parenthesis groups and # operation hierarchy, use infix_notation boolean_expr = boolean_term + ((AND | OR) + boolean_term)[...] # integers that are followed by "." are actually floats integer = Word(nums) + ~Char(".") """ def __init__(self, expr: Union[ParserElement, str]) -> None: super().__init__(expr) # do NOT use self.leave_whitespace(), don't want to propagate to exprs # self.leave_whitespace() self.skipWhitespace = False self._may_return_empty = True self.errmsg = f"Found unwanted token, {self.expr}" def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: if self.expr.can_parse_next(instring, loc, do_actions=do_actions): raise ParseException(instring, loc, self.errmsg, self) return loc, [] def _generateDefaultName(self) -> str: return f"~{{{self.expr}}}" class _MultipleMatch(ParseElementEnhance): def __init__( self, expr: Union[str, ParserElement], stop_on: typing.Optional[Union[ParserElement, str]] = None, *, stopOn: typing.Optional[Union[ParserElement, str]] = None, ) -> None: super().__init__(expr) stopOn = stopOn or stop_on self.saveAsList = True ender = stopOn if isinstance(ender, str_type): ender = self._literalStringClass(ender) self.stopOn(ender) def stopOn(self, ender) -> ParserElement: if isinstance(ender, str_type): ender = self._literalStringClass(ender) self.not_ender = ~ender if ender is not None else None return self def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: self_expr_parse = self.expr._parse self_skip_ignorables = self._skipIgnorables check_ender = False if self.not_ender is not None: try_not_ender = self.not_ender.try_parse check_ender = True # must be at least one (but first see if we are the stopOn sentinel; # if so, fail) if check_ender: try_not_ender(instring, loc) loc, tokens = self_expr_parse(instring, loc, do_actions) try: hasIgnoreExprs = not not self.ignoreExprs while 1: if check_ender: try_not_ender(instring, loc) if hasIgnoreExprs: preloc = self_skip_ignorables(instring, loc) else: preloc = loc loc, tmptokens = self_expr_parse(instring, preloc, do_actions) tokens += tmptokens except (ParseException, IndexError): pass return loc, tokens def _setResultsName(self, name, list_all_matches=False) -> ParserElement: if ( __diag__.warn_ungrouped_named_tokens_in_collection and Diagnostics.warn_ungrouped_named_tokens_in_collection not in self.suppress_warnings_ ): for e in [self.expr] + self.expr.recurse(): if ( isinstance(e, ParserElement) and e.resultsName and ( Diagnostics.warn_ungrouped_named_tokens_in_collection not in e.suppress_warnings_ ) ): warning = ( "warn_ungrouped_named_tokens_in_collection:" f" setting results name {name!r} on {type(self).__name__} expression" f" collides with {e.resultsName!r} on contained expression" ) warnings.warn(warning, stacklevel=3) break return super()._setResultsName(name, list_all_matches) class OneOrMore(_MultipleMatch): """ Repetition of one or more of the given expression. Parameters: - ``expr`` - expression that must match one or more times - ``stop_on`` - (default= ``None``) - expression for a terminating sentinel (only required if the sentinel would ordinarily match the repetition expression) Example:: data_word = Word(alphas) label = data_word + FollowedBy(':') attr_expr = Group(label + Suppress(':') + OneOrMore(data_word).set_parse_action(' '.join)) text = "shape: SQUARE posn: upper left color: BLACK" attr_expr[1, ...].parse_string(text).pprint() # Fail! read 'color' as data instead of next label -> [['shape', 'SQUARE color']] # use stop_on attribute for OneOrMore to avoid reading label string as part of the data attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) OneOrMore(attr_expr).parse_string(text).pprint() # Better -> [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'BLACK']] # could also be written as (attr_expr * (1,)).parse_string(text).pprint() """ def _generateDefaultName(self) -> str: return f"{{{self.expr}}}..." class ZeroOrMore(_MultipleMatch): """ Optional repetition of zero or more of the given expression. Parameters: - ``expr`` - expression that must match zero or more times - ``stop_on`` - expression for a terminating sentinel (only required if the sentinel would ordinarily match the repetition expression) - (default= ``None``) Example: similar to :class:`OneOrMore` """ def __init__( self, expr: Union[str, ParserElement], stop_on: typing.Optional[Union[ParserElement, str]] = None, *, stopOn: typing.Optional[Union[ParserElement, str]] = None, ) -> None: super().__init__(expr, stopOn=stopOn or stop_on) self._may_return_empty = True def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: try: return super().parseImpl(instring, loc, do_actions) except (ParseException, IndexError): return loc, ParseResults([], name=self.resultsName) def _generateDefaultName(self) -> str: return f"[{self.expr}]..." class DelimitedList(ParseElementEnhance): def __init__( self, expr: Union[str, ParserElement], delim: Union[str, ParserElement] = ",", combine: bool = False, min: typing.Optional[int] = None, max: typing.Optional[int] = None, *, allow_trailing_delim: bool = False, ) -> None: """Helper to define a delimited list of expressions - the delimiter defaults to ','. By default, the list elements and delimiters can have intervening whitespace, and comments, but this can be overridden by passing ``combine=True`` in the constructor. If ``combine`` is set to ``True``, the matching tokens are returned as a single token string, with the delimiters included; otherwise, the matching tokens are returned as a list of tokens, with the delimiters suppressed. If ``allow_trailing_delim`` is set to True, then the list may end with a delimiter. Example:: DelimitedList(Word(alphas)).parse_string("aa,bb,cc") # -> ['aa', 'bb', 'cc'] DelimitedList(Word(hexnums), delim=':', combine=True).parse_string("AA:BB:CC:DD:EE") # -> ['AA:BB:CC:DD:EE'] """ if isinstance(expr, str_type): expr = ParserElement._literalStringClass(expr) expr = typing.cast(ParserElement, expr) if min is not None and min < 1: raise ValueError("min must be greater than 0") if max is not None and min is not None and max < min: raise ValueError("max must be greater than, or equal to min") self.content = expr self.raw_delim = str(delim) self.delim = delim self.combine = combine if not combine: self.delim = Suppress(delim) self.min = min or 1 self.max = max self.allow_trailing_delim = allow_trailing_delim delim_list_expr = self.content + (self.delim + self.content) * ( self.min - 1, None if self.max is None else self.max - 1, ) if self.allow_trailing_delim: delim_list_expr += Opt(self.delim) if self.combine: delim_list_expr = Combine(delim_list_expr) super().__init__(delim_list_expr, savelist=True) def _generateDefaultName(self) -> str: content_expr = self.content.streamline() return f"{content_expr} [{self.raw_delim} {content_expr}]..." class _NullToken: def __bool__(self): return False def __str__(self): return "" class Opt(ParseElementEnhance): """ Optional matching of the given expression. Parameters: - ``expr`` - expression that must match zero or more times - ``default`` (optional) - value to be returned if the optional expression is not found. Example:: # US postal code can be a 5-digit zip, plus optional 4-digit qualifier zip = Combine(Word(nums, exact=5) + Opt('-' + Word(nums, exact=4))) zip.run_tests(''' # traditional ZIP code 12345 # ZIP+4 form 12101-0001 # invalid ZIP 98765- ''') prints:: # traditional ZIP code 12345 ['12345'] # ZIP+4 form 12101-0001 ['12101-0001'] # invalid ZIP 98765- ^ FAIL: Expected end of text (at char 5), (line:1, col:6) """ __optionalNotMatched = _NullToken() def __init__( self, expr: Union[ParserElement, str], default: Any = __optionalNotMatched ) -> None: super().__init__(expr, savelist=False) self.saveAsList = self.expr.saveAsList self.defaultValue = default self._may_return_empty = True def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: self_expr = self.expr try: loc, tokens = self_expr._parse( instring, loc, do_actions, callPreParse=False ) except (ParseException, IndexError): default_value = self.defaultValue if default_value is not self.__optionalNotMatched: if self_expr.resultsName: tokens = ParseResults([default_value]) tokens[self_expr.resultsName] = default_value else: tokens = [default_value] # type: ignore[assignment] else: tokens = [] # type: ignore[assignment] return loc, tokens def _generateDefaultName(self) -> str: inner = str(self.expr) # strip off redundant inner {}'s while len(inner) > 1 and inner[0 :: len(inner) - 1] == "{}": inner = inner[1:-1] return f"[{inner}]" Optional = Opt class SkipTo(ParseElementEnhance): """ Token for skipping over all undefined text until the matched expression is found. Parameters: - ``expr`` - target expression marking the end of the data to be skipped - ``include`` - if ``True``, the target expression is also parsed (the skipped text and target expression are returned as a 2-element list) (default= ``False``). - ``ignore`` - (default= ``None``) used to define grammars (typically quoted strings and comments) that might contain false matches to the target expression - ``fail_on`` - (default= ``None``) define expressions that are not allowed to be included in the skipped test; if found before the target expression is found, the :class:`SkipTo` is not a match Example:: report = ''' Outstanding Issues Report - 1 Jan 2000 # | Severity | Description | Days Open -----+----------+-------------------------------------------+----------- 101 | Critical | Intermittent system crash | 6 94 | Cosmetic | Spelling error on Login ('log|n') | 14 79 | Minor | System slow when running too many reports | 47 ''' integer = Word(nums) SEP = Suppress('|') # use SkipTo to simply match everything up until the next SEP # - ignore quoted strings, so that a '|' character inside a quoted string does not match # - parse action will call token.strip() for each matched token, i.e., the description body string_data = SkipTo(SEP, ignore=quoted_string) string_data.set_parse_action(token_map(str.strip)) ticket_expr = (integer("issue_num") + SEP + string_data("sev") + SEP + string_data("desc") + SEP + integer("days_open")) for tkt in ticket_expr.search_string(report): print tkt.dump() prints:: ['101', 'Critical', 'Intermittent system crash', '6'] - days_open: '6' - desc: 'Intermittent system crash' - issue_num: '101' - sev: 'Critical' ['94', 'Cosmetic', "Spelling error on Login ('log|n')", '14'] - days_open: '14' - desc: "Spelling error on Login ('log|n')" - issue_num: '94' - sev: 'Cosmetic' ['79', 'Minor', 'System slow when running too many reports', '47'] - days_open: '47' - desc: 'System slow when running too many reports' - issue_num: '79' - sev: 'Minor' """ def __init__( self, other: Union[ParserElement, str], include: bool = False, ignore: typing.Optional[Union[ParserElement, str]] = None, fail_on: typing.Optional[Union[ParserElement, str]] = None, *, failOn: typing.Optional[Union[ParserElement, str]] = None, ) -> None: super().__init__(other) failOn = failOn or fail_on self.ignoreExpr = ignore self._may_return_empty = True self.mayIndexError = False self.includeMatch = include self.saveAsList = False if isinstance(failOn, str_type): self.failOn = self._literalStringClass(failOn) else: self.failOn = failOn self.errmsg = f"No match found for {self.expr}" self.ignorer = Empty().leave_whitespace() self._update_ignorer() def _update_ignorer(self): # rebuild internal ignore expr from current ignore exprs and assigned ignoreExpr self.ignorer.ignoreExprs.clear() for e in self.expr.ignoreExprs: self.ignorer.ignore(e) if self.ignoreExpr: self.ignorer.ignore(self.ignoreExpr) def ignore(self, expr): super().ignore(expr) self._update_ignorer() def parseImpl(self, instring, loc, do_actions=True): startloc = loc instrlen = len(instring) self_expr_parse = self.expr._parse self_failOn_canParseNext = ( self.failOn.canParseNext if self.failOn is not None else None ) ignorer_try_parse = self.ignorer.try_parse if self.ignorer.ignoreExprs else None tmploc = loc while tmploc <= instrlen: if self_failOn_canParseNext is not None: # break if failOn expression matches if self_failOn_canParseNext(instring, tmploc): break if ignorer_try_parse is not None: # advance past ignore expressions prev_tmploc = tmploc while 1: try: tmploc = ignorer_try_parse(instring, tmploc) except ParseBaseException: break # see if all ignorers matched, but didn't actually ignore anything if tmploc == prev_tmploc: break prev_tmploc = tmploc try: self_expr_parse(instring, tmploc, do_actions=False, callPreParse=False) except (ParseException, IndexError): # no match, advance loc in string tmploc += 1 else: # matched skipto expr, done break else: # ran off the end of the input string without matching skipto expr, fail raise ParseException(instring, loc, self.errmsg, self) # build up return values loc = tmploc skiptext = instring[startloc:loc] skipresult = ParseResults(skiptext) if self.includeMatch: loc, mat = self_expr_parse(instring, loc, do_actions, callPreParse=False) skipresult += mat return loc, skipresult class Forward(ParseElementEnhance): """ Forward declaration of an expression to be defined later - used for recursive grammars, such as algebraic infix notation. When the expression is known, it is assigned to the ``Forward`` variable using the ``'<<'`` operator. Note: take care when assigning to ``Forward`` not to overlook precedence of operators. Specifically, ``'|'`` has a lower precedence than ``'<<'``, so that:: fwd_expr << a | b | c will actually be evaluated as:: (fwd_expr << a) | b | c thereby leaving b and c out as parseable alternatives. It is recommended that you explicitly group the values inserted into the ``Forward``:: fwd_expr << (a | b | c) Converting to use the ``'<<='`` operator instead will avoid this problem. See :class:`ParseResults.pprint` for an example of a recursive parser created using ``Forward``. """ def __init__( self, other: typing.Optional[Union[ParserElement, str]] = None ) -> None: self.caller_frame = traceback.extract_stack(limit=2)[0] super().__init__(other, savelist=False) # type: ignore[arg-type] self.lshift_line = None def __lshift__(self, other) -> Forward: if hasattr(self, "caller_frame"): del self.caller_frame if isinstance(other, str_type): other = self._literalStringClass(other) if not isinstance(other, ParserElement): return NotImplemented self.expr = other self.streamlined = other.streamlined self.mayIndexError = self.expr.mayIndexError self._may_return_empty = self.expr.mayReturnEmpty self.set_whitespace_chars( self.expr.whiteChars, copy_defaults=self.expr.copyDefaultWhiteChars ) self.skipWhitespace = self.expr.skipWhitespace self.saveAsList = self.expr.saveAsList self.ignoreExprs.extend(self.expr.ignoreExprs) self.lshift_line = traceback.extract_stack(limit=2)[-2] # type: ignore[assignment] return self def __ilshift__(self, other) -> Forward: if not isinstance(other, ParserElement): return NotImplemented return self << other def __or__(self, other) -> ParserElement: caller_line = traceback.extract_stack(limit=2)[-2] if ( __diag__.warn_on_match_first_with_lshift_operator and caller_line == self.lshift_line and Diagnostics.warn_on_match_first_with_lshift_operator not in self.suppress_warnings_ ): warnings.warn( "warn_on_match_first_with_lshift_operator:" " using '<<' operator with '|' is probably an error, use '<<='", stacklevel=2, ) ret = super().__or__(other) return ret def __del__(self): # see if we are getting dropped because of '=' reassignment of var instead of '<<=' or '<<' if ( self.expr is None and __diag__.warn_on_assignment_to_Forward and Diagnostics.warn_on_assignment_to_Forward not in self.suppress_warnings_ ): warnings.warn_explicit( "warn_on_assignment_to_Forward:" " Forward defined here but no expression attached later using '<<=' or '<<'", UserWarning, filename=self.caller_frame.filename, lineno=self.caller_frame.lineno, ) def parseImpl(self, instring, loc, do_actions=True) -> ParseImplReturnType: if ( self.expr is None and __diag__.warn_on_parse_using_empty_Forward and Diagnostics.warn_on_parse_using_empty_Forward not in self.suppress_warnings_ ): # walk stack until parse_string, scan_string, search_string, or transform_string is found parse_fns = ( "parse_string", "scan_string", "search_string", "transform_string", ) tb = traceback.extract_stack(limit=200) for i, frm in enumerate(reversed(tb), start=1): if frm.name in parse_fns: stacklevel = i + 1 break else: stacklevel = 2 warnings.warn( "warn_on_parse_using_empty_Forward:" " Forward expression was never assigned a value, will not parse any input", stacklevel=stacklevel, ) if not ParserElement._left_recursion_enabled: return super().parseImpl(instring, loc, do_actions) # ## Bounded Recursion algorithm ## # Recursion only needs to be processed at ``Forward`` elements, since they are # the only ones that can actually refer to themselves. The general idea is # to handle recursion stepwise: We start at no recursion, then recurse once, # recurse twice, ..., until more recursion offers no benefit (we hit the bound). # # The "trick" here is that each ``Forward`` gets evaluated in two contexts # - to *match* a specific recursion level, and # - to *search* the bounded recursion level # and the two run concurrently. The *search* must *match* each recursion level # to find the best possible match. This is handled by a memo table, which # provides the previous match to the next level match attempt. # # See also "Left Recursion in Parsing Expression Grammars", Medeiros et al. # # There is a complication since we not only *parse* but also *transform* via # actions: We do not want to run the actions too often while expanding. Thus, # we expand using `do_actions=False` and only run `do_actions=True` if the next # recursion level is acceptable. with ParserElement.recursion_lock: memo = ParserElement.recursion_memos try: # we are parsing at a specific recursion expansion - use it as-is prev_loc, prev_result = memo[loc, self, do_actions] if isinstance(prev_result, Exception): raise prev_result return prev_loc, prev_result.copy() except KeyError: act_key = (loc, self, True) peek_key = (loc, self, False) # we are searching for the best recursion expansion - keep on improving # both `do_actions` cases must be tracked separately here! prev_loc, prev_peek = memo[peek_key] = ( loc - 1, ParseException( instring, loc, "Forward recursion without base case", self ), ) if do_actions: memo[act_key] = memo[peek_key] while True: try: new_loc, new_peek = super().parseImpl(instring, loc, False) except ParseException: # we failed before getting any match - do not hide the error if isinstance(prev_peek, Exception): raise new_loc, new_peek = prev_loc, prev_peek # the match did not get better: we are done if new_loc <= prev_loc: if do_actions: # replace the match for do_actions=False as well, # in case the action did backtrack prev_loc, prev_result = memo[peek_key] = memo[act_key] del memo[peek_key], memo[act_key] return prev_loc, copy.copy(prev_result) del memo[peek_key] return prev_loc, copy.copy(prev_peek) # the match did get better: see if we can improve further if do_actions: try: memo[act_key] = super().parseImpl(instring, loc, True) except ParseException as e: memo[peek_key] = memo[act_key] = (new_loc, e) raise prev_loc, prev_peek = memo[peek_key] = new_loc, new_peek def leave_whitespace(self, recursive: bool = True) -> ParserElement: self.skipWhitespace = False return self def ignore_whitespace(self, recursive: bool = True) -> ParserElement: self.skipWhitespace = True return self def streamline(self) -> ParserElement: if not self.streamlined: self.streamlined = True if self.expr is not None: self.expr.streamline() return self def validate(self, validateTrace=None) -> None: warnings.warn( "ParserElement.validate() is deprecated, and should not be used to check for left recursion", DeprecationWarning, stacklevel=2, ) if validateTrace is None: validateTrace = [] if self not in validateTrace: tmp = validateTrace[:] + [self] if self.expr is not None: self.expr.validate(tmp) self._checkRecursion([]) def _generateDefaultName(self) -> str: # Avoid infinite recursion by setting a temporary _defaultName save_default_name = self._defaultName self._defaultName = ": ..." # Use the string representation of main expression. try: if self.expr is not None: ret_string = str(self.expr)[:1000] else: ret_string = "None" except Exception: ret_string = "..." self._defaultName = save_default_name return f"{type(self).__name__}: {ret_string}" def copy(self) -> ParserElement: if self.expr is not None: return super().copy() else: ret = Forward() ret <<= self return ret def _setResultsName(self, name, list_all_matches=False) -> ParserElement: # fmt: off if ( __diag__.warn_name_set_on_empty_Forward and Diagnostics.warn_name_set_on_empty_Forward not in self.suppress_warnings_ and self.expr is None ): warning = ( "warn_name_set_on_empty_Forward:" f" setting results name {name!r} on {type(self).__name__} expression" " that has no contained expression" ) warnings.warn(warning, stacklevel=3) # fmt: on return super()._setResultsName(name, list_all_matches) # Compatibility synonyms # fmt: off leaveWhitespace = replaced_by_pep8("leaveWhitespace", leave_whitespace) ignoreWhitespace = replaced_by_pep8("ignoreWhitespace", ignore_whitespace) # fmt: on class TokenConverter(ParseElementEnhance): """ Abstract subclass of :class:`ParseElementEnhance`, for converting parsed results. """ def __init__(self, expr: Union[ParserElement, str], savelist=False) -> None: super().__init__(expr) # , savelist) self.saveAsList = False class Combine(TokenConverter): """Converter to concatenate all matching tokens to a single string. By default, the matching patterns must also be contiguous in the input string; this can be disabled by specifying ``'adjacent=False'`` in the constructor. Example:: real = Word(nums) + '.' + Word(nums) print(real.parse_string('3.1416')) # -> ['3', '.', '1416'] # will also erroneously match the following print(real.parse_string('3. 1416')) # -> ['3', '.', '1416'] real = Combine(Word(nums) + '.' + Word(nums)) print(real.parse_string('3.1416')) # -> ['3.1416'] # no match when there are internal spaces print(real.parse_string('3. 1416')) # -> Exception: Expected W:(0123...) """ def __init__( self, expr: ParserElement, join_string: str = "", adjacent: bool = True, *, joinString: typing.Optional[str] = None, ) -> None: super().__init__(expr) joinString = joinString if joinString is not None else join_string # suppress whitespace-stripping in contained parse expressions, but re-enable it on the Combine itself if adjacent: self.leave_whitespace() self.adjacent = adjacent self.skipWhitespace = True self.joinString = joinString self.callPreparse = True def ignore(self, other) -> ParserElement: if self.adjacent: ParserElement.ignore(self, other) else: super().ignore(other) return self def postParse(self, instring, loc, tokenlist): retToks = tokenlist.copy() del retToks[:] retToks += ParseResults( ["".join(tokenlist._asStringList(self.joinString))], modal=self.modalResults ) if self.resultsName and retToks.haskeys(): return [retToks] else: return retToks class Group(TokenConverter): """Converter to return the matched tokens as a list - useful for returning tokens of :class:`ZeroOrMore` and :class:`OneOrMore` expressions. The optional ``aslist`` argument when set to True will return the parsed tokens as a Python list instead of a pyparsing ParseResults. Example:: ident = Word(alphas) num = Word(nums) term = ident | num func = ident + Opt(DelimitedList(term)) print(func.parse_string("fn a, b, 100")) # -> ['fn', 'a', 'b', '100'] func = ident + Group(Opt(DelimitedList(term))) print(func.parse_string("fn a, b, 100")) # -> ['fn', ['a', 'b', '100']] """ def __init__(self, expr: ParserElement, aslist: bool = False) -> None: super().__init__(expr) self.saveAsList = True self._asPythonList = aslist def postParse(self, instring, loc, tokenlist): if self._asPythonList: return ParseResults.List( tokenlist.asList() if isinstance(tokenlist, ParseResults) else list(tokenlist) ) return [tokenlist] class Dict(TokenConverter): """Converter to return a repetitive expression as a list, but also as a dictionary. Each element can also be referenced using the first token in the expression as its key. Useful for tabular report scraping when the first column can be used as a item key. The optional ``asdict`` argument when set to True will return the parsed tokens as a Python dict instead of a pyparsing ParseResults. Example:: data_word = Word(alphas) label = data_word + FollowedBy(':') text = "shape: SQUARE posn: upper left color: light blue texture: burlap" attr_expr = (label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) # print attributes as plain groups print(attr_expr[1, ...].parse_string(text).dump()) # instead of OneOrMore(expr), parse using Dict(Group(expr)[1, ...]) - Dict will auto-assign names result = Dict(Group(attr_expr)[1, ...]).parse_string(text) print(result.dump()) # access named fields as dict entries, or output as dict print(result['shape']) print(result.as_dict()) prints:: ['shape', 'SQUARE', 'posn', 'upper left', 'color', 'light blue', 'texture', 'burlap'] [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']] - color: 'light blue' - posn: 'upper left' - shape: 'SQUARE' - texture: 'burlap' SQUARE {'color': 'light blue', 'posn': 'upper left', 'texture': 'burlap', 'shape': 'SQUARE'} See more examples at :class:`ParseResults` of accessing fields by results name. """ def __init__(self, expr: ParserElement, asdict: bool = False) -> None: super().__init__(expr) self.saveAsList = True self._asPythonDict = asdict def postParse(self, instring, loc, tokenlist): for i, tok in enumerate(tokenlist): if len(tok) == 0: continue ikey = tok[0] if isinstance(ikey, int): ikey = str(ikey).strip() if len(tok) == 1: tokenlist[ikey] = _ParseResultsWithOffset("", i) elif len(tok) == 2 and not isinstance(tok[1], ParseResults): tokenlist[ikey] = _ParseResultsWithOffset(tok[1], i) else: try: dictvalue = tok.copy() # ParseResults(i) except Exception: exc = TypeError( "could not extract dict values from parsed results" " - Dict expression must contain Grouped expressions" ) raise exc from None del dictvalue[0] if len(dictvalue) != 1 or ( isinstance(dictvalue, ParseResults) and dictvalue.haskeys() ): tokenlist[ikey] = _ParseResultsWithOffset(dictvalue, i) else: tokenlist[ikey] = _ParseResultsWithOffset(dictvalue[0], i) if self._asPythonDict: return [tokenlist.as_dict()] if self.resultsName else tokenlist.as_dict() return [tokenlist] if self.resultsName else tokenlist class Suppress(TokenConverter): """Converter for ignoring the results of a parsed expression. Example:: source = "a, b, c,d" wd = Word(alphas) wd_list1 = wd + (',' + wd)[...] print(wd_list1.parse_string(source)) # often, delimiters that are useful during parsing are just in the # way afterward - use Suppress to keep them out of the parsed output wd_list2 = wd + (Suppress(',') + wd)[...] print(wd_list2.parse_string(source)) # Skipped text (using '...') can be suppressed as well source = "lead in START relevant text END trailing text" start_marker = Keyword("START") end_marker = Keyword("END") find_body = Suppress(...) + start_marker + ... + end_marker print(find_body.parse_string(source) prints:: ['a', ',', 'b', ',', 'c', ',', 'd'] ['a', 'b', 'c', 'd'] ['START', 'relevant text ', 'END'] (See also :class:`DelimitedList`.) """ def __init__(self, expr: Union[ParserElement, str], savelist: bool = False) -> None: if expr is ...: expr = _PendingSkip(NoMatch()) super().__init__(expr) def __add__(self, other) -> ParserElement: if isinstance(self.expr, _PendingSkip): return Suppress(SkipTo(other)) + other return super().__add__(other) def __sub__(self, other) -> ParserElement: if isinstance(self.expr, _PendingSkip): return Suppress(SkipTo(other)) - other return super().__sub__(other) def postParse(self, instring, loc, tokenlist): return [] def suppress(self) -> ParserElement: return self def trace_parse_action(f: ParseAction) -> ParseAction: """Decorator for debugging parse actions. When the parse action is called, this decorator will print ``">> entering method-name(line:<current_source_line>, <parse_location>, <matched_tokens>)"``. When the parse action completes, the decorator will print ``"<<"`` followed by the returned value, or any exception that the parse action raised. Example:: wd = Word(alphas) @trace_parse_action def remove_duplicate_chars(tokens): return ''.join(sorted(set(''.join(tokens)))) wds = wd[1, ...].set_parse_action(remove_duplicate_chars) print(wds.parse_string("slkdjs sld sldd sdlf sdljf")) prints:: >>entering remove_duplicate_chars(line: 'slkdjs sld sldd sdlf sdljf', 0, (['slkdjs', 'sld', 'sldd', 'sdlf', 'sdljf'], {})) <<leaving remove_duplicate_chars (ret: 'dfjkls') ['dfjkls'] """ f = _trim_arity(f) def z(*paArgs): thisFunc = f.__name__ s, l, t = paArgs[-3:] if len(paArgs) > 3: thisFunc = f"{type(paArgs[0]).__name__}.{thisFunc}" sys.stderr.write(f">>entering {thisFunc}(line: {line(l, s)!r}, {l}, {t!r})\n") try: ret = f(*paArgs) except Exception as exc: sys.stderr.write( f"<<leaving {thisFunc} (exception: {type(exc).__name__}: {exc})\n" ) raise sys.stderr.write(f"<<leaving {thisFunc} (ret: {ret!r})\n") return ret z.__name__ = f.__name__ return z # convenience constants for positional expressions empty = Empty().set_name("empty") line_start = LineStart().set_name("line_start") line_end = LineEnd().set_name("line_end") string_start = StringStart().set_name("string_start") string_end = StringEnd().set_name("string_end") _escapedPunc = Regex(r"\\[\\[\]\/\-\*\.\$\+\^\?()~ ]").set_parse_action( lambda s, l, t: t[0][1] ) _escapedHexChar = Regex(r"\\0?[xX][0-9a-fA-F]+").set_parse_action( lambda s, l, t: chr(int(t[0].lstrip(r"\0x"), 16)) ) _escapedOctChar = Regex(r"\\0[0-7]+").set_parse_action( lambda s, l, t: chr(int(t[0][1:], 8)) ) _singleChar = ( _escapedPunc | _escapedHexChar | _escapedOctChar | CharsNotIn(r"\]", exact=1) ) _charRange = Group(_singleChar + Suppress("-") + _singleChar) _reBracketExpr = ( Literal("[") + Opt("^").set_results_name("negate") + Group(OneOrMore(_charRange | _singleChar)).set_results_name("body") + Literal("]") ) def srange(s: str) -> str: r"""Helper to easily define string ranges for use in :class:`Word` construction. Borrows syntax from regexp ``'[]'`` string range definitions:: srange("[0-9]") -> "0123456789" srange("[a-z]") -> "abcdefghijklmnopqrstuvwxyz" srange("[a-z$_]") -> "abcdefghijklmnopqrstuvwxyz$_" The input string must be enclosed in []'s, and the returned string is the expanded character set joined into a single string. The values enclosed in the []'s may be: - a single character - an escaped character with a leading backslash (such as ``\-`` or ``\]``) - an escaped hex character with a leading ``'\x'`` (``\x21``, which is a ``'!'`` character) (``\0x##`` is also supported for backwards compatibility) - an escaped octal character with a leading ``'\0'`` (``\041``, which is a ``'!'`` character) - a range of any of the above, separated by a dash (``'a-z'``, etc.) - any combination of the above (``'aeiouy'``, ``'a-zA-Z0-9_$'``, etc.) """ def _expanded(p): if isinstance(p, ParseResults): yield from (chr(c) for c in range(ord(p[0]), ord(p[1]) + 1)) else: yield p try: return "".join( [c for part in _reBracketExpr.parse_string(s).body for c in _expanded(part)] ) except Exception as e: return "" def token_map(func, *args) -> ParseAction: """Helper to define a parse action by mapping a function to all elements of a :class:`ParseResults` list. If any additional args are passed, they are forwarded to the given function as additional arguments after the token, as in ``hex_integer = Word(hexnums).set_parse_action(token_map(int, 16))``, which will convert the parsed data to an integer using base 16. Example (compare the last to example in :class:`ParserElement.transform_string`:: hex_ints = Word(hexnums)[1, ...].set_parse_action(token_map(int, 16)) hex_ints.run_tests(''' 00 11 22 aa FF 0a 0d 1a ''') upperword = Word(alphas).set_parse_action(token_map(str.upper)) upperword[1, ...].run_tests(''' my kingdom for a horse ''') wd = Word(alphas).set_parse_action(token_map(str.title)) wd[1, ...].set_parse_action(' '.join).run_tests(''' now is the winter of our discontent made glorious summer by this sun of york ''') prints:: 00 11 22 aa FF 0a 0d 1a [0, 17, 34, 170, 255, 10, 13, 26] my kingdom for a horse ['MY', 'KINGDOM', 'FOR', 'A', 'HORSE'] now is the winter of our discontent made glorious summer by this sun of york ['Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York'] """ def pa(s, l, t): return [func(tokn, *args) for tokn in t] func_name = getattr(func, "__name__", getattr(func, "__class__").__name__) pa.__name__ = func_name return pa def autoname_elements() -> None: """ Utility to simplify mass-naming of parser elements, for generating railroad diagram with named subdiagrams. """ # guard against _getframe not being implemented in the current Python getframe_fn = getattr(sys, "_getframe", lambda _: None) calling_frame = getframe_fn(1) if calling_frame is None: return # find all locals in the calling frame that are ParserElements calling_frame = typing.cast(types.FrameType, calling_frame) for name, var in calling_frame.f_locals.items(): # if no custom name defined, set the name to the var name if isinstance(var, ParserElement) and not var.customName: var.set_name(name) dbl_quoted_string = Combine( Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*') + '"' ).set_name("string enclosed in double quotes") sgl_quoted_string = Combine( Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*") + "'" ).set_name("string enclosed in single quotes") quoted_string = Combine( (Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*') + '"').set_name( "double quoted string" ) | (Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*") + "'").set_name( "single quoted string" ) ).set_name("quoted string using single or double quotes") python_quoted_string = Combine( (Regex(r'"""(?:[^"\\]|""(?!")|"(?!"")|\\.)*', flags=re.MULTILINE) + '"""').set_name( "multiline double quoted string" ) ^ ( Regex(r"'''(?:[^'\\]|''(?!')|'(?!'')|\\.)*", flags=re.MULTILINE) + "'''" ).set_name("multiline single quoted string") ^ (Regex(r'"(?:[^"\n\r\\]|(?:\\")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*') + '"').set_name( "double quoted string" ) ^ (Regex(r"'(?:[^'\n\r\\]|(?:\\')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*") + "'").set_name( "single quoted string" ) ).set_name("Python quoted string") unicode_string = Combine("u" + quoted_string.copy()).set_name("unicode string literal") alphas8bit = srange(r"[\0xc0-\0xd6\0xd8-\0xf6\0xf8-\0xff]") punc8bit = srange(r"[\0xa1-\0xbf\0xd7\0xf7]") # build list of built-in expressions, for future reference if a global default value # gets updated _builtin_exprs: list[ParserElement] = [ v for v in vars().values() if isinstance(v, ParserElement) ] # Compatibility synonyms # fmt: off sglQuotedString = sgl_quoted_string dblQuotedString = dbl_quoted_string quotedString = quoted_string unicodeString = unicode_string lineStart = line_start lineEnd = line_end stringStart = string_start stringEnd = string_end nullDebugAction = replaced_by_pep8("nullDebugAction", null_debug_action) traceParseAction = replaced_by_pep8("traceParseAction", trace_parse_action) conditionAsParseAction = replaced_by_pep8("conditionAsParseAction", condition_as_parse_action) tokenMap = replaced_by_pep8("tokenMap", token_map) # fmt: on PK )��ZT��a a actions.pynu �[��� # actions.py from __future__ import annotations from typing import Union, Callable, Any from .exceptions import ParseException from .util import col, replaced_by_pep8 from .results import ParseResults ParseAction = Union[ Callable[[], Any], Callable[[ParseResults], Any], Callable[[int, ParseResults], Any], Callable[[str, int, ParseResults], Any], ] class OnlyOnce: """ Wrapper for parse actions, to ensure they are only called once. Note: parse action signature must include all 3 arguments. """ def __init__(self, method_call: Callable[[str, int, ParseResults], Any]) -> None: from .core import _trim_arity self.callable = _trim_arity(method_call) self.called = False def __call__(self, s: str, l: int, t: ParseResults) -> ParseResults: if not self.called: results = self.callable(s, l, t) self.called = True return results raise ParseException(s, l, "OnlyOnce obj called multiple times w/out reset") def reset(self): """ Allow the associated parse action to be called once more. """ self.called = False def match_only_at_col(n: int) -> ParseAction: """ Helper method for defining parse actions that require matching at a specific column in the input text. """ def verify_col(strg: str, locn: int, toks: ParseResults) -> None: if col(locn, strg) != n: raise ParseException(strg, locn, f"matched token not at column {n}") return verify_col def replace_with(repl_str: str) -> ParseAction: """ Helper method for common parse actions that simply return a literal value. Especially useful when used with :class:`transform_string<ParserElement.transform_string>` (). Example:: num = Word(nums).set_parse_action(lambda toks: int(toks[0])) na = one_of("N/A NA").set_parse_action(replace_with(math.nan)) term = na | num term[1, ...].parse_string("324 234 N/A 234") # -> [324, 234, nan, 234] """ return lambda s, l, t: [repl_str] def remove_quotes(s: str, l: int, t: ParseResults) -> Any: """ Helper parse action for removing quotation marks from parsed quoted strings. Example:: # by default, quotation marks are included in parsed results quoted_string.parse_string("'Now is the Winter of our Discontent'") # -> ["'Now is the Winter of our Discontent'"] # use remove_quotes to strip quotation marks from parsed results quoted_string.set_parse_action(remove_quotes) quoted_string.parse_string("'Now is the Winter of our Discontent'") # -> ["Now is the Winter of our Discontent"] """ return t[0][1:-1] def with_attribute(*args: tuple[str, str], **attr_dict) -> ParseAction: """ Helper to create a validating parse action to be used with start tags created with :class:`make_xml_tags` or :class:`make_html_tags`. Use ``with_attribute`` to qualify a starting tag with a required attribute value, to avoid false matches on common tags such as ``<TD>`` or ``<DIV>``. Call ``with_attribute`` with a series of attribute names and values. Specify the list of filter attributes names and values as: - keyword arguments, as in ``(align="right")``, or - as an explicit dict with ``**`` operator, when an attribute name is also a Python reserved word, as in ``**{"class":"Customer", "align":"right"}`` - a list of name-value tuples, as in ``(("ns1:class", "Customer"), ("ns2:align", "right"))`` For attribute names with a namespace prefix, you must use the second form. Attribute names are matched insensitive to upper/lower case. If just testing for ``class`` (with or without a namespace), use :class:`with_class`. To verify that the attribute exists, but without specifying a value, pass ``with_attribute.ANY_VALUE`` as the value. Example:: html = ''' <div> Some text <div type="grid">1 4 0 1 0</div> <div type="graph">1,3 2,3 1,1</div> <div>this has no type</div> </div> ''' div,div_end = make_html_tags("div") # only match div tag having a type attribute with value "grid" div_grid = div().set_parse_action(with_attribute(type="grid")) grid_expr = div_grid + SkipTo(div | div_end)("body") for grid_header in grid_expr.search_string(html): print(grid_header.body) # construct a match with any div tag having a type attribute, regardless of the value div_any_type = div().set_parse_action(with_attribute(type=with_attribute.ANY_VALUE)) div_expr = div_any_type + SkipTo(div | div_end)("body") for div_header in div_expr.search_string(html): print(div_header.body) prints:: 1 4 0 1 0 1 4 0 1 0 1,3 2,3 1,1 """ attrs_list: list[tuple[str, str]] = [] if args: attrs_list.extend(args) else: attrs_list.extend(attr_dict.items()) def pa(s: str, l: int, tokens: ParseResults) -> None: for attrName, attrValue in attrs_list: if attrName not in tokens: raise ParseException(s, l, "no matching attribute " + attrName) if attrValue != with_attribute.ANY_VALUE and tokens[attrName] != attrValue: # type: ignore [attr-defined] raise ParseException( s, l, f"attribute {attrName!r} has value {tokens[attrName]!r}, must be {attrValue!r}", ) return pa with_attribute.ANY_VALUE = object() # type: ignore [attr-defined] def with_class(classname: str, namespace: str = "") -> ParseAction: """ Simplified version of :class:`with_attribute` when matching on a div class - made difficult because ``class`` is a reserved word in Python. Example:: html = ''' <div> Some text <div class="grid">1 4 0 1 0</div> <div class="graph">1,3 2,3 1,1</div> <div>this <div> has no class</div> </div> ''' div,div_end = make_html_tags("div") div_grid = div().set_parse_action(with_class("grid")) grid_expr = div_grid + SkipTo(div | div_end)("body") for grid_header in grid_expr.search_string(html): print(grid_header.body) div_any_type = div().set_parse_action(with_class(withAttribute.ANY_VALUE)) div_expr = div_any_type + SkipTo(div | div_end)("body") for div_header in div_expr.search_string(html): print(div_header.body) prints:: 1 4 0 1 0 1 4 0 1 0 1,3 2,3 1,1 """ classattr = f"{namespace}:class" if namespace else "class" return with_attribute(**{classattr: classname}) # Compatibility synonyms # fmt: off replaceWith = replaced_by_pep8("replaceWith", replace_with) removeQuotes = replaced_by_pep8("removeQuotes", remove_quotes) withAttribute = replaced_by_pep8("withAttribute", with_attribute) withClass = replaced_by_pep8("withClass", with_class) matchOnlyAtCol = replaced_by_pep8("matchOnlyAtCol", match_only_at_col) # fmt: on PK )��Z py.typednu �[��� PK )��Z �dv) v) unicode.pynu �[��� # unicode.py import sys from itertools import filterfalse from typing import Union class _lazyclassproperty: def __init__(self, fn): self.fn = fn self.__doc__ = fn.__doc__ self.__name__ = fn.__name__ def __get__(self, obj, cls): if cls is None: cls = type(obj) if not hasattr(cls, "_intern") or any( cls._intern is getattr(superclass, "_intern", []) for superclass in cls.__mro__[1:] ): cls._intern = {} attrname = self.fn.__name__ if attrname not in cls._intern: cls._intern[attrname] = self.fn(cls) return cls._intern[attrname] UnicodeRangeList = list[Union[tuple[int, int], tuple[int]]] class unicode_set: """ A set of Unicode characters, for language-specific strings for ``alphas``, ``nums``, ``alphanums``, and ``printables``. A unicode_set is defined by a list of ranges in the Unicode character set, in a class attribute ``_ranges``. Ranges can be specified using 2-tuples or a 1-tuple, such as:: _ranges = [ (0x0020, 0x007e), (0x00a0, 0x00ff), (0x0100,), ] Ranges are left- and right-inclusive. A 1-tuple of (x,) is treated as (x, x). A unicode set can also be defined using multiple inheritance of other unicode sets:: class CJK(Chinese, Japanese, Korean): pass """ _ranges: UnicodeRangeList = [] @_lazyclassproperty def _chars_for_ranges(cls) -> list[str]: ret: list[int] = [] for cc in cls.__mro__: # type: ignore[attr-defined] if cc is unicode_set: break for rr in getattr(cc, "_ranges", ()): ret.extend(range(rr[0], rr[-1] + 1)) return sorted(chr(c) for c in set(ret)) @_lazyclassproperty def printables(cls) -> str: """all non-whitespace characters in this range""" return "".join(filterfalse(str.isspace, cls._chars_for_ranges)) @_lazyclassproperty def alphas(cls) -> str: """all alphabetic characters in this range""" return "".join(filter(str.isalpha, cls._chars_for_ranges)) @_lazyclassproperty def nums(cls) -> str: """all numeric digit characters in this range""" return "".join(filter(str.isdigit, cls._chars_for_ranges)) @_lazyclassproperty def alphanums(cls) -> str: """all alphanumeric characters in this range""" return cls.alphas + cls.nums @_lazyclassproperty def identchars(cls) -> str: """all characters in this range that are valid identifier characters, plus underscore '_'""" return "".join( sorted( set(filter(str.isidentifier, cls._chars_for_ranges)) | set( "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyzªµº" "ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ" "_" ) ) ) @_lazyclassproperty def identbodychars(cls) -> str: """ all characters in this range that are valid identifier body characters, plus the digits 0-9, and · (Unicode MIDDLE DOT) """ identifier_chars = set( c for c in cls._chars_for_ranges if ("_" + c).isidentifier() ) return "".join( sorted(identifier_chars | set(cls.identchars) | set("0123456789·")) ) @_lazyclassproperty def identifier(cls): """ a pyparsing Word expression for an identifier using this range's definitions for identchars and identbodychars """ from pyparsing import Word return Word(cls.identchars, cls.identbodychars) class pyparsing_unicode(unicode_set): """ A namespace class for defining common language unicode_sets. """ # fmt: off # define ranges in language character sets _ranges: UnicodeRangeList = [ (0x0020, sys.maxunicode), ] class BasicMultilingualPlane(unicode_set): """Unicode set for the Basic Multilingual Plane""" _ranges: UnicodeRangeList = [ (0x0020, 0xFFFF), ] class Latin1(unicode_set): """Unicode set for Latin-1 Unicode Character Range""" _ranges: UnicodeRangeList = [ (0x0020, 0x007E), (0x00A0, 0x00FF), ] class LatinA(unicode_set): """Unicode set for Latin-A Unicode Character Range""" _ranges: UnicodeRangeList = [ (0x0100, 0x017F), ] class LatinB(unicode_set): """Unicode set for Latin-B Unicode Character Range""" _ranges: UnicodeRangeList = [ (0x0180, 0x024F), ] class Greek(unicode_set): """Unicode set for Greek Unicode Character Ranges""" _ranges: UnicodeRangeList = [ (0x0342, 0x0345), (0x0370, 0x0377), (0x037A, 0x037F), (0x0384, 0x038A), (0x038C,), (0x038E, 0x03A1), (0x03A3, 0x03E1), (0x03F0, 0x03FF), (0x1D26, 0x1D2A), (0x1D5E,), (0x1D60,), (0x1D66, 0x1D6A), (0x1F00, 0x1F15), (0x1F18, 0x1F1D), (0x1F20, 0x1F45), (0x1F48, 0x1F4D), (0x1F50, 0x1F57), (0x1F59,), (0x1F5B,), (0x1F5D,), (0x1F5F, 0x1F7D), (0x1F80, 0x1FB4), (0x1FB6, 0x1FC4), (0x1FC6, 0x1FD3), (0x1FD6, 0x1FDB), (0x1FDD, 0x1FEF), (0x1FF2, 0x1FF4), (0x1FF6, 0x1FFE), (0x2129,), (0x2719, 0x271A), (0xAB65,), (0x10140, 0x1018D), (0x101A0,), (0x1D200, 0x1D245), (0x1F7A1, 0x1F7A7), ] class Cyrillic(unicode_set): """Unicode set for Cyrillic Unicode Character Range""" _ranges: UnicodeRangeList = [ (0x0400, 0x052F), (0x1C80, 0x1C88), (0x1D2B,), (0x1D78,), (0x2DE0, 0x2DFF), (0xA640, 0xA672), (0xA674, 0xA69F), (0xFE2E, 0xFE2F), ] class Chinese(unicode_set): """Unicode set for Chinese Unicode Character Range""" _ranges: UnicodeRangeList = [ (0x2E80, 0x2E99), (0x2E9B, 0x2EF3), (0x31C0, 0x31E3), (0x3400, 0x4DB5), (0x4E00, 0x9FEF), (0xA700, 0xA707), (0xF900, 0xFA6D), (0xFA70, 0xFAD9), (0x16FE2, 0x16FE3), (0x1F210, 0x1F212), (0x1F214, 0x1F23B), (0x1F240, 0x1F248), (0x20000, 0x2A6D6), (0x2A700, 0x2B734), (0x2B740, 0x2B81D), (0x2B820, 0x2CEA1), (0x2CEB0, 0x2EBE0), (0x2F800, 0x2FA1D), ] class Japanese(unicode_set): """Unicode set for Japanese Unicode Character Range, combining Kanji, Hiragana, and Katakana ranges""" class Kanji(unicode_set): "Unicode set for Kanji Unicode Character Range" _ranges: UnicodeRangeList = [ (0x4E00, 0x9FBF), (0x3000, 0x303F), ] class Hiragana(unicode_set): """Unicode set for Hiragana Unicode Character Range""" _ranges: UnicodeRangeList = [ (0x3041, 0x3096), (0x3099, 0x30A0), (0x30FC,), (0xFF70,), (0x1B001,), (0x1B150, 0x1B152), (0x1F200,), ] class Katakana(unicode_set): """Unicode set for Katakana Unicode Character Range""" _ranges: UnicodeRangeList = [ (0x3099, 0x309C), (0x30A0, 0x30FF), (0x31F0, 0x31FF), (0x32D0, 0x32FE), (0xFF65, 0xFF9F), (0x1B000,), (0x1B164, 0x1B167), (0x1F201, 0x1F202), (0x1F213,), ] 漢字 = Kanji カタカナ = Katakana ひらがな = Hiragana _ranges = ( Kanji._ranges + Hiragana._ranges + Katakana._ranges ) class Hangul(unicode_set): """Unicode set for Hangul (Korean) Unicode Character Range""" _ranges: UnicodeRangeList = [ (0x1100, 0x11FF), (0x302E, 0x302F), (0x3131, 0x318E), (0x3200, 0x321C), (0x3260, 0x327B), (0x327E,), (0xA960, 0xA97C), (0xAC00, 0xD7A3), (0xD7B0, 0xD7C6), (0xD7CB, 0xD7FB), (0xFFA0, 0xFFBE), (0xFFC2, 0xFFC7), (0xFFCA, 0xFFCF), (0xFFD2, 0xFFD7), (0xFFDA, 0xFFDC), ] Korean = Hangul class CJK(Chinese, Japanese, Hangul): """Unicode set for combined Chinese, Japanese, and Korean (CJK) Unicode Character Range""" class Thai(unicode_set): """Unicode set for Thai Unicode Character Range""" _ranges: UnicodeRangeList = [ (0x0E01, 0x0E3A), (0x0E3F, 0x0E5B) ] class Arabic(unicode_set): """Unicode set for Arabic Unicode Character Range""" _ranges: UnicodeRangeList = [ (0x0600, 0x061B), (0x061E, 0x06FF), (0x0700, 0x077F), ] class Hebrew(unicode_set): """Unicode set for Hebrew Unicode Character Range""" _ranges: UnicodeRangeList = [ (0x0591, 0x05C7), (0x05D0, 0x05EA), (0x05EF, 0x05F4), (0xFB1D, 0xFB36), (0xFB38, 0xFB3C), (0xFB3E,), (0xFB40, 0xFB41), (0xFB43, 0xFB44), (0xFB46, 0xFB4F), ] class Devanagari(unicode_set): """Unicode set for Devanagari Unicode Character Range""" _ranges: UnicodeRangeList = [ (0x0900, 0x097F), (0xA8E0, 0xA8FF) ] BMP = BasicMultilingualPlane # add language identifiers using language Unicode العربية = Arabic 中文 = Chinese кириллица = Cyrillic Ελληνικά = Greek עִברִית = Hebrew 日本語 = Japanese 한국어 = Korean ไทย = Thai देवनागरी = Devanagari # fmt: on PK )��Z �}Z9 Z9 testing.pynu �[��� # testing.py from contextlib import contextmanager import re import typing from .core import ( ParserElement, ParseException, Keyword, __diag__, __compat__, ) class pyparsing_test: """ namespace class for classes useful in writing unit tests """ class reset_pyparsing_context: """ Context manager to be used when writing unit tests that modify pyparsing config values: - packrat parsing - bounded recursion parsing - default whitespace characters. - default keyword characters - literal string auto-conversion class - __diag__ settings Example:: with reset_pyparsing_context(): # test that literals used to construct a grammar are automatically suppressed ParserElement.inlineLiteralsUsing(Suppress) term = Word(alphas) | Word(nums) group = Group('(' + term[...] + ')') # assert that the '()' characters are not included in the parsed tokens self.assertParseAndCheckList(group, "(abc 123 def)", ['abc', '123', 'def']) # after exiting context manager, literals are converted to Literal expressions again """ def __init__(self): self._save_context = {} def save(self): self._save_context["default_whitespace"] = ParserElement.DEFAULT_WHITE_CHARS self._save_context["default_keyword_chars"] = Keyword.DEFAULT_KEYWORD_CHARS self._save_context["literal_string_class"] = ( ParserElement._literalStringClass ) self._save_context["verbose_stacktrace"] = ParserElement.verbose_stacktrace self._save_context["packrat_enabled"] = ParserElement._packratEnabled if ParserElement._packratEnabled: self._save_context["packrat_cache_size"] = ( ParserElement.packrat_cache.size ) else: self._save_context["packrat_cache_size"] = None self._save_context["packrat_parse"] = ParserElement._parse self._save_context["recursion_enabled"] = ( ParserElement._left_recursion_enabled ) self._save_context["__diag__"] = { name: getattr(__diag__, name) for name in __diag__._all_names } self._save_context["__compat__"] = { "collect_all_And_tokens": __compat__.collect_all_And_tokens } return self def restore(self): # reset pyparsing global state if ( ParserElement.DEFAULT_WHITE_CHARS != self._save_context["default_whitespace"] ): ParserElement.set_default_whitespace_chars( self._save_context["default_whitespace"] ) ParserElement.verbose_stacktrace = self._save_context["verbose_stacktrace"] Keyword.DEFAULT_KEYWORD_CHARS = self._save_context["default_keyword_chars"] ParserElement.inlineLiteralsUsing( self._save_context["literal_string_class"] ) for name, value in self._save_context["__diag__"].items(): (__diag__.enable if value else __diag__.disable)(name) ParserElement._packratEnabled = False if self._save_context["packrat_enabled"]: ParserElement.enable_packrat(self._save_context["packrat_cache_size"]) else: ParserElement._parse = self._save_context["packrat_parse"] ParserElement._left_recursion_enabled = self._save_context[ "recursion_enabled" ] __compat__.collect_all_And_tokens = self._save_context["__compat__"] return self def copy(self): ret = type(self)() ret._save_context.update(self._save_context) return ret def __enter__(self): return self.save() def __exit__(self, *args): self.restore() class TestParseResultsAsserts: """ A mixin class to add parse results assertion methods to normal unittest.TestCase classes. """ def assertParseResultsEquals( self, result, expected_list=None, expected_dict=None, msg=None ): """ Unit test assertion to compare a :class:`ParseResults` object with an optional ``expected_list``, and compare any defined results names with an optional ``expected_dict``. """ if expected_list is not None: self.assertEqual(expected_list, result.as_list(), msg=msg) if expected_dict is not None: self.assertEqual(expected_dict, result.as_dict(), msg=msg) def assertParseAndCheckList( self, expr, test_string, expected_list, msg=None, verbose=True ): """ Convenience wrapper assert to test a parser element and input string, and assert that the resulting ``ParseResults.asList()`` is equal to the ``expected_list``. """ result = expr.parse_string(test_string, parse_all=True) if verbose: print(result.dump()) else: print(result.as_list()) self.assertParseResultsEquals(result, expected_list=expected_list, msg=msg) def assertParseAndCheckDict( self, expr, test_string, expected_dict, msg=None, verbose=True ): """ Convenience wrapper assert to test a parser element and input string, and assert that the resulting ``ParseResults.asDict()`` is equal to the ``expected_dict``. """ result = expr.parse_string(test_string, parseAll=True) if verbose: print(result.dump()) else: print(result.as_list()) self.assertParseResultsEquals(result, expected_dict=expected_dict, msg=msg) def assertRunTestResults( self, run_tests_report, expected_parse_results=None, msg=None ): """ Unit test assertion to evaluate output of ``ParserElement.runTests()``. If a list of list-dict tuples is given as the ``expected_parse_results`` argument, then these are zipped with the report tuples returned by ``runTests`` and evaluated using ``assertParseResultsEquals``. Finally, asserts that the overall ``runTests()`` success value is ``True``. :param run_tests_report: tuple(bool, [tuple(str, ParseResults or Exception)]) returned from runTests :param expected_parse_results (optional): [tuple(str, list, dict, Exception)] """ run_test_success, run_test_results = run_tests_report if expected_parse_results is None: self.assertTrue( run_test_success, msg=msg if msg is not None else "failed runTests" ) return merged = [ (*rpt, expected) for rpt, expected in zip(run_test_results, expected_parse_results) ] for test_string, result, expected in merged: # expected should be a tuple containing a list and/or a dict or an exception, # and optional failure message string # an empty tuple will skip any result validation fail_msg = next((exp for exp in expected if isinstance(exp, str)), None) expected_exception = next( ( exp for exp in expected if isinstance(exp, type) and issubclass(exp, Exception) ), None, ) if expected_exception is not None: with self.assertRaises( expected_exception=expected_exception, msg=fail_msg or msg ): if isinstance(result, Exception): raise result else: expected_list = next( (exp for exp in expected if isinstance(exp, list)), None ) expected_dict = next( (exp for exp in expected if isinstance(exp, dict)), None ) if (expected_list, expected_dict) != (None, None): self.assertParseResultsEquals( result, expected_list=expected_list, expected_dict=expected_dict, msg=fail_msg or msg, ) else: # warning here maybe? print(f"no validation for {test_string!r}") # do this last, in case some specific test results can be reported instead self.assertTrue( run_test_success, msg=msg if msg is not None else "failed runTests" ) @contextmanager def assertRaisesParseException( self, exc_type=ParseException, expected_msg=None, msg=None ): if expected_msg is not None: if isinstance(expected_msg, str): expected_msg = re.escape(expected_msg) with self.assertRaisesRegex(exc_type, expected_msg, msg=msg) as ctx: yield ctx else: with self.assertRaises(exc_type, msg=msg) as ctx: yield ctx @staticmethod def with_line_numbers( s: str, start_line: typing.Optional[int] = None, end_line: typing.Optional[int] = None, expand_tabs: bool = True, eol_mark: str = "|", mark_spaces: typing.Optional[str] = None, mark_control: typing.Optional[str] = None, *, indent: typing.Union[str, int] = "", base_1: bool = True, ) -> str: """ Helpful method for debugging a parser - prints a string with line and column numbers. (Line and column numbers are 1-based by default - if debugging a parse action, pass base_1=False, to correspond to the loc value passed to the parse action.) :param s: tuple(bool, str - string to be printed with line and column numbers :param start_line: int - (optional) starting line number in s to print (default=1) :param end_line: int - (optional) ending line number in s to print (default=len(s)) :param expand_tabs: bool - (optional) expand tabs to spaces, to match the pyparsing default :param eol_mark: str - (optional) string to mark the end of lines, helps visualize trailing spaces (default="|") :param mark_spaces: str - (optional) special character to display in place of spaces :param mark_control: str - (optional) convert non-printing control characters to a placeholding character; valid values: - "unicode" - replaces control chars with Unicode symbols, such as "␍" and "␊" - any single character string - replace control characters with given string - None (default) - string is displayed as-is :param indent: str | int - (optional) string to indent with line and column numbers; if an int is passed, converted to " " * indent :param base_1: bool - (optional) whether to label string using base 1; if False, string will be labeled based at 0 (default=True) :return: str - input string with leading line numbers and column number headers """ if expand_tabs: s = s.expandtabs() if isinstance(indent, int): indent = " " * indent indent = indent.expandtabs() if mark_control is not None: mark_control = typing.cast(str, mark_control) if mark_control == "unicode": transtable_map = { c: u for c, u in zip(range(0, 33), range(0x2400, 0x2433)) } transtable_map[127] = 0x2421 tbl = str.maketrans(transtable_map) eol_mark = "" else: ord_mark_control = ord(mark_control) tbl = str.maketrans( {c: ord_mark_control for c in list(range(0, 32)) + [127]} ) s = s.translate(tbl) if mark_spaces is not None and mark_spaces != " ": if mark_spaces == "unicode": tbl = str.maketrans({9: 0x2409, 32: 0x2423}) s = s.translate(tbl) else: s = s.replace(" ", mark_spaces) if start_line is None: start_line = 0 if end_line is None: end_line = len(s) end_line = min(end_line, len(s)) start_line = min(max(0, start_line), end_line) if mark_control != "unicode": s_lines = s.splitlines()[start_line - base_1 : end_line] else: s_lines = [ line + "␊" for line in s.split("␊")[start_line - base_1 : end_line] ] if not s_lines: return "" lineno_width = len(str(end_line)) max_line_len = max(len(line) for line in s_lines) lead = indent + " " * (lineno_width + 1) if max_line_len >= 99: header0 = ( lead + ("" if base_1 else " ") + "".join( f"{' ' * 99}{(i + 1) % 100}" for i in range(1 if base_1 else 0, max(max_line_len // 100, 1)) ) + "\n" ) else: header0 = "" header1 = ( ("" if base_1 else " ") + lead + "".join(f" {(i + 1) % 10}" for i in range(-(-max_line_len // 10))) + "\n" ) digits = "1234567890" header2 = ( lead + ("" if base_1 else "0") + digits * (-(-max_line_len // 10)) + "\n" ) return ( header1 + header2 + "\n".join( f"{indent}{i:{lineno_width}d}:{line}{eol_mark}" for i, line in enumerate(s_lines, start=start_line + base_1) ) + "\n" ) PK )��Z���8 8 util.pynu �[��� # util.py import contextlib import re from functools import lru_cache, wraps import inspect import itertools import types from typing import Callable, Union, Iterable, TypeVar, cast import warnings _bslash = chr(92) C = TypeVar("C", bound=Callable) class __config_flags: """Internal class for defining compatibility and debugging flags""" _all_names: list[str] = [] _fixed_names: list[str] = [] _type_desc = "configuration" @classmethod def _set(cls, dname, value): if dname in cls._fixed_names: warnings.warn( f"{cls.__name__}.{dname} {cls._type_desc} is {str(getattr(cls, dname)).upper()}" f" and cannot be overridden", stacklevel=3, ) return if dname in cls._all_names: setattr(cls, dname, value) else: raise ValueError(f"no such {cls._type_desc} {dname!r}") enable = classmethod(lambda cls, name: cls._set(name, True)) disable = classmethod(lambda cls, name: cls._set(name, False)) @lru_cache(maxsize=128) def col(loc: int, strg: str) -> int: """ Returns current column within a string, counting newlines as line separators. The first column is number 1. Note: the default parsing behavior is to expand tabs in the input string before starting the parsing process. See :class:`ParserElement.parse_string` for more information on parsing strings containing ``<TAB>`` s, and suggested methods to maintain a consistent view of the parsed string, the parse location, and line and column positions within the parsed string. """ s = strg return 1 if 0 < loc < len(s) and s[loc - 1] == "\n" else loc - s.rfind("\n", 0, loc) @lru_cache(maxsize=128) def lineno(loc: int, strg: str) -> int: """Returns current line number within a string, counting newlines as line separators. The first line is number 1. Note - the default parsing behavior is to expand tabs in the input string before starting the parsing process. See :class:`ParserElement.parse_string` for more information on parsing strings containing ``<TAB>`` s, and suggested methods to maintain a consistent view of the parsed string, the parse location, and line and column positions within the parsed string. """ return strg.count("\n", 0, loc) + 1 @lru_cache(maxsize=128) def line(loc: int, strg: str) -> str: """ Returns the line of text containing loc within a string, counting newlines as line separators. """ last_cr = strg.rfind("\n", 0, loc) next_cr = strg.find("\n", loc) return strg[last_cr + 1 : next_cr] if next_cr >= 0 else strg[last_cr + 1 :] class _UnboundedCache: def __init__(self): cache = {} cache_get = cache.get self.not_in_cache = not_in_cache = object() def get(_, key): return cache_get(key, not_in_cache) def set_(_, key, value): cache[key] = value def clear(_): cache.clear() self.size = None self.get = types.MethodType(get, self) self.set = types.MethodType(set_, self) self.clear = types.MethodType(clear, self) class _FifoCache: def __init__(self, size): cache = {} self.size = size self.not_in_cache = not_in_cache = object() cache_get = cache.get cache_pop = cache.pop def get(_, key): return cache_get(key, not_in_cache) def set_(_, key, value): cache[key] = value while len(cache) > size: # pop oldest element in cache by getting the first key cache_pop(next(iter(cache))) def clear(_): cache.clear() self.get = types.MethodType(get, self) self.set = types.MethodType(set_, self) self.clear = types.MethodType(clear, self) class LRUMemo: """ A memoizing mapping that retains `capacity` deleted items The memo tracks retained items by their access order; once `capacity` items are retained, the least recently used item is discarded. """ def __init__(self, capacity): self._capacity = capacity self._active = {} self._memory = {} def __getitem__(self, key): try: return self._active[key] except KeyError: self._memory[key] = self._memory.pop(key) return self._memory[key] def __setitem__(self, key, value): self._memory.pop(key, None) self._active[key] = value def __delitem__(self, key): try: value = self._active.pop(key) except KeyError: pass else: oldest_keys = list(self._memory)[: -(self._capacity + 1)] for key_to_delete in oldest_keys: self._memory.pop(key_to_delete) self._memory[key] = value def clear(self): self._active.clear() self._memory.clear() class UnboundedMemo(dict): """ A memoizing mapping that retains all deleted items """ def __delitem__(self, key): pass def _escape_regex_range_chars(s: str) -> str: # escape these chars: ^-[] for c in r"\^-[]": s = s.replace(c, _bslash + c) s = s.replace("\n", r"\n") s = s.replace("\t", r"\t") return str(s) class _GroupConsecutive: """ Used as a callable `key` for itertools.groupby to group characters that are consecutive: itertools.groupby("abcdejkmpqrs", key=IsConsecutive()) yields: (0, iter(['a', 'b', 'c', 'd', 'e'])) (1, iter(['j', 'k'])) (2, iter(['m'])) (3, iter(['p', 'q', 'r', 's'])) """ def __init__(self) -> None: self.prev = 0 self.counter = itertools.count() self.value = -1 def __call__(self, char: str) -> int: c_int = ord(char) self.prev, prev = c_int, self.prev if c_int - prev > 1: self.value = next(self.counter) return self.value def _collapse_string_to_ranges( s: Union[str, Iterable[str]], re_escape: bool = True ) -> str: r""" Take a string or list of single-character strings, and return a string of the consecutive characters in that string collapsed into groups, as might be used in a regular expression '[a-z]' character set: 'a' -> 'a' -> '[a]' 'bc' -> 'bc' -> '[bc]' 'defgh' -> 'd-h' -> '[d-h]' 'fdgeh' -> 'd-h' -> '[d-h]' 'jklnpqrtu' -> 'j-lnp-rtu' -> '[j-lnp-rtu]' Duplicates get collapsed out: 'aaa' -> 'a' -> '[a]' 'bcbccb' -> 'bc' -> '[bc]' 'defghhgf' -> 'd-h' -> '[d-h]' 'jklnpqrjjjtu' -> 'j-lnp-rtu' -> '[j-lnp-rtu]' Spaces are preserved: 'ab c' -> ' a-c' -> '[ a-c]' Characters that are significant when defining regex ranges get escaped: 'acde[]-' -> r'\-\[\]ac-e' -> r'[\-\[\]ac-e]' """ # Developer notes: # - Do not optimize this code assuming that the given input string # or internal lists will be short (such as in loading generators into # lists to make it easier to find the last element); this method is also # used to generate regex ranges for character sets in the pyparsing.unicode # classes, and these can be _very_ long lists of strings def escape_re_range_char(c: str) -> str: return "\\" + c if c in r"\^-][" else c def no_escape_re_range_char(c: str) -> str: return c if not re_escape: escape_re_range_char = no_escape_re_range_char ret = [] # reduce input string to remove duplicates, and put in sorted order s_chars: list[str] = sorted(set(s)) if len(s_chars) > 2: # find groups of characters that are consecutive (can be collapsed # down to "<first>-<last>") for _, chars in itertools.groupby(s_chars, key=_GroupConsecutive()): # _ is unimportant, is just used to identify groups # chars is an iterator of one or more consecutive characters # that comprise the current group first = last = next(chars) with contextlib.suppress(ValueError): *_, last = chars if first == last: # there was only a single char in this group ret.append(escape_re_range_char(first)) elif last == chr(ord(first) + 1): # there were only 2 characters in this group # 'a','b' -> 'ab' ret.append(f"{escape_re_range_char(first)}{escape_re_range_char(last)}") else: # there were > 2 characters in this group, make into a range # 'c','d','e' -> 'c-e' ret.append( f"{escape_re_range_char(first)}-{escape_re_range_char(last)}" ) else: # only 1 or 2 chars were given to form into groups # 'a' -> ['a'] # 'bc' -> ['b', 'c'] # 'dg' -> ['d', 'g'] # no need to list them with "-", just return as a list # (after escaping) ret = [escape_re_range_char(c) for c in s_chars] return "".join(ret) def _flatten(ll: Iterable) -> list: ret = [] to_visit = [*ll] while to_visit: i = to_visit.pop(0) if isinstance(i, Iterable) and not isinstance(i, str): to_visit[:0] = i else: ret.append(i) return ret def make_compressed_re( word_list: Iterable[str], max_level: int = 2, *, non_capturing_groups: bool = True, _level: int = 1, ) -> str: """ Create a regular expression string from a list of words, collapsing by common prefixes and optional suffixes. Calls itself recursively to build nested sublists for each group of suffixes that have a shared prefix. """ def get_suffixes_from_common_prefixes(namelist: list[str]): if len(namelist) > 1: for prefix, suffixes in itertools.groupby(namelist, key=lambda s: s[:1]): yield prefix, sorted([s[1:] for s in suffixes], key=len, reverse=True) else: yield namelist[0][0], [namelist[0][1:]] if _level == 1: if not word_list: raise ValueError("no words given to make_compressed_re()") if "" in word_list: raise ValueError("word list cannot contain empty string") else: # internal recursive call, just return empty string if no words if not word_list: return "" # dedupe the word list word_list = list({}.fromkeys(word_list)) if max_level == 0: if any(len(wd) > 1 for wd in word_list): return "|".join( sorted([re.escape(wd) for wd in word_list], key=len, reverse=True) ) else: return f"[{''.join(_escape_regex_range_chars(wd) for wd in word_list)}]" ret = [] sep = "" ncgroup = "?:" if non_capturing_groups else "" for initial, suffixes in get_suffixes_from_common_prefixes(sorted(word_list)): ret.append(sep) sep = "|" initial = re.escape(initial) trailing = "" if "" in suffixes: trailing = "?" suffixes.remove("") if len(suffixes) > 1: if all(len(s) == 1 for s in suffixes): ret.append( f"{initial}[{''.join(_escape_regex_range_chars(s) for s in suffixes)}]{trailing}" ) else: if _level < max_level: suffix_re = make_compressed_re( sorted(suffixes), max_level, non_capturing_groups=non_capturing_groups, _level=_level + 1, ) ret.append(f"{initial}({ncgroup}{suffix_re}){trailing}") else: if all(len(s) == 1 for s in suffixes): ret.append( f"{initial}[{''.join(_escape_regex_range_chars(s) for s in suffixes)}]{trailing}" ) else: suffixes.sort(key=len, reverse=True) ret.append( f"{initial}({ncgroup}{'|'.join(re.escape(s) for s in suffixes)}){trailing}" ) else: if suffixes: suffix = re.escape(suffixes[0]) if len(suffix) > 1 and trailing: ret.append(f"{initial}({ncgroup}{suffix}){trailing}") else: ret.append(f"{initial}{suffix}{trailing}") else: ret.append(initial) return "".join(ret) def replaced_by_pep8(compat_name: str, fn: C) -> C: # In a future version, uncomment the code in the internal _inner() functions # to begin emitting DeprecationWarnings. # Unwrap staticmethod/classmethod fn = getattr(fn, "__func__", fn) # (Presence of 'self' arg in signature is used by explain_exception() methods, so we take # some extra steps to add it if present in decorated function.) if ["self"] == list(inspect.signature(fn).parameters)[:1]: @wraps(fn) def _inner(self, *args, **kwargs): # warnings.warn( # f"Deprecated - use {fn.__name__}", DeprecationWarning, stacklevel=2 # ) return fn(self, *args, **kwargs) else: @wraps(fn) def _inner(*args, **kwargs): # warnings.warn( # f"Deprecated - use {fn.__name__}", DeprecationWarning, stacklevel=2 # ) return fn(*args, **kwargs) _inner.__doc__ = f"""Deprecated - use :class:`{fn.__name__}`""" _inner.__name__ = compat_name _inner.__annotations__ = fn.__annotations__ if isinstance(fn, types.FunctionType): _inner.__kwdefaults__ = fn.__kwdefaults__ # type: ignore [attr-defined] elif isinstance(fn, type) and hasattr(fn, "__init__"): _inner.__kwdefaults__ = fn.__init__.__kwdefaults__ # type: ignore [misc,attr-defined] else: _inner.__kwdefaults__ = None # type: ignore [attr-defined] _inner.__qualname__ = fn.__qualname__ return cast(C, _inner) PK )��Z� a8�& �& exceptions.pynu �[��� # exceptions.py from __future__ import annotations import copy import re import sys import typing from functools import cached_property from .unicode import pyparsing_unicode as ppu from .util import ( _collapse_string_to_ranges, col, line, lineno, replaced_by_pep8, ) class _ExceptionWordUnicodeSet( ppu.Latin1, ppu.LatinA, ppu.LatinB, ppu.Greek, ppu.Cyrillic ): pass _extract_alphanums = _collapse_string_to_ranges(_ExceptionWordUnicodeSet.alphanums) _exception_word_extractor = re.compile("([" + _extract_alphanums + "]{1,16})|.") class ParseBaseException(Exception): """base exception class for all parsing runtime exceptions""" loc: int msg: str pstr: str parser_element: typing.Any # "ParserElement" args: tuple[str, int, typing.Optional[str]] __slots__ = ( "loc", "msg", "pstr", "parser_element", "args", ) # Performance tuning: we construct a *lot* of these, so keep this # constructor as small and fast as possible def __init__( self, pstr: str, loc: int = 0, msg: typing.Optional[str] = None, elem=None, ) -> None: if msg is None: msg, pstr = pstr, "" self.loc = loc self.msg = msg self.pstr = pstr self.parser_element = elem self.args = (pstr, loc, msg) @staticmethod def explain_exception(exc: Exception, depth: int = 16) -> str: """ Method to take an exception and translate the Python internal traceback into a list of the pyparsing expressions that caused the exception to be raised. Parameters: - exc - exception raised during parsing (need not be a ParseException, in support of Python exceptions that might be raised in a parse action) - depth (default=16) - number of levels back in the stack trace to list expression and function names; if None, the full stack trace names will be listed; if 0, only the failing input line, marker, and exception string will be shown Returns a multi-line string listing the ParserElements and/or function names in the exception's stack trace. """ import inspect from .core import ParserElement if depth is None: depth = sys.getrecursionlimit() ret: list[str] = [] if isinstance(exc, ParseBaseException): ret.append(exc.line) ret.append(f"{'^':>{exc.column}}") ret.append(f"{type(exc).__name__}: {exc}") if depth <= 0 or exc.__traceback__ is None: return "\n".join(ret) callers = inspect.getinnerframes(exc.__traceback__, context=depth) seen: set[int] = set() for ff in callers[-depth:]: frm = ff[0] f_self = frm.f_locals.get("self", None) if isinstance(f_self, ParserElement): if not frm.f_code.co_name.startswith(("parseImpl", "_parseNoCache")): continue if id(f_self) in seen: continue seen.add(id(f_self)) self_type = type(f_self) ret.append(f"{self_type.__module__}.{self_type.__name__} - {f_self}") elif f_self is not None: self_type = type(f_self) ret.append(f"{self_type.__module__}.{self_type.__name__}") else: code = frm.f_code if code.co_name in ("wrapper", "<module>"): continue ret.append(code.co_name) depth -= 1 if not depth: break return "\n".join(ret) @classmethod def _from_exception(cls, pe) -> ParseBaseException: """ internal factory method to simplify creating one type of ParseException from another - avoids having __init__ signature conflicts among subclasses """ return cls(pe.pstr, pe.loc, pe.msg, pe.parser_element) @cached_property def line(self) -> str: """ Return the line of text where the exception occurred. """ return line(self.loc, self.pstr) @cached_property def lineno(self) -> int: """ Return the 1-based line number of text where the exception occurred. """ return lineno(self.loc, self.pstr) @cached_property def col(self) -> int: """ Return the 1-based column on the line of text where the exception occurred. """ return col(self.loc, self.pstr) @cached_property def column(self) -> int: """ Return the 1-based column on the line of text where the exception occurred. """ return col(self.loc, self.pstr) @cached_property def found(self) -> str: if not self.pstr: return "" if self.loc >= len(self.pstr): return "end of text" # pull out next word at error location found_match = _exception_word_extractor.match(self.pstr, self.loc) if found_match is not None: found_text = found_match.group(0) else: found_text = self.pstr[self.loc : self.loc + 1] return repr(found_text).replace(r"\\", "\\") # pre-PEP8 compatibility @property def parserElement(self): return self.parser_element @parserElement.setter def parserElement(self, elem): self.parser_element = elem def copy(self): return copy.copy(self) def formatted_message(self) -> str: found_phrase = f", found {self.found}" if self.found else "" return f"{self.msg}{found_phrase} (at char {self.loc}), (line:{self.lineno}, col:{self.column})" def __str__(self) -> str: return self.formatted_message() def __repr__(self): return str(self) def mark_input_line( self, marker_string: typing.Optional[str] = None, *, markerString: str = ">!<" ) -> str: """ Extracts the exception line from the input string, and marks the location of the exception with a special symbol. """ markerString = marker_string if marker_string is not None else markerString line_str = self.line line_column = self.column - 1 if markerString: line_str = f"{line_str[:line_column]}{markerString}{line_str[line_column:]}" return line_str.strip() def explain(self, depth: int = 16) -> str: """ Method to translate the Python internal traceback into a list of the pyparsing expressions that caused the exception to be raised. Parameters: - depth (default=16) - number of levels back in the stack trace to list expression and function names; if None, the full stack trace names will be listed; if 0, only the failing input line, marker, and exception string will be shown Returns a multi-line string listing the ParserElements and/or function names in the exception's stack trace. Example:: # an expression to parse 3 integers expr = pp.Word(pp.nums) * 3 try: # a failing parse - the third integer is prefixed with "A" expr.parse_string("123 456 A789") except pp.ParseException as pe: print(pe.explain(depth=0)) prints:: 123 456 A789 ^ ParseException: Expected W:(0-9), found 'A' (at char 8), (line:1, col:9) Note: the diagnostic output will include string representations of the expressions that failed to parse. These representations will be more helpful if you use `set_name` to give identifiable names to your expressions. Otherwise they will use the default string forms, which may be cryptic to read. Note: pyparsing's default truncation of exception tracebacks may also truncate the stack of expressions that are displayed in the ``explain`` output. To get the full listing of parser expressions, you may have to set ``ParserElement.verbose_stacktrace = True`` """ return self.explain_exception(self, depth) # Compatibility synonyms # fmt: off markInputline = replaced_by_pep8("markInputline", mark_input_line) # fmt: on class ParseException(ParseBaseException): """ Exception thrown when a parse expression doesn't match the input string Example:: integer = Word(nums).set_name("integer") try: integer.parse_string("ABC") except ParseException as pe: print(pe, f"column: {pe.column}") prints:: Expected integer, found 'ABC' (at char 0), (line:1, col:1) column: 1 """ class ParseFatalException(ParseBaseException): """ User-throwable exception thrown when inconsistent parse content is found; stops all parsing immediately """ class ParseSyntaxException(ParseFatalException): """ Just like :class:`ParseFatalException`, but thrown internally when an :class:`ErrorStop<And._ErrorStop>` ('-' operator) indicates that parsing is to stop immediately because an unbacktrackable syntax error has been found. """ class RecursiveGrammarException(Exception): """ Exception thrown by :class:`ParserElement.validate` if the grammar could be left-recursive; parser may need to enable left recursion using :class:`ParserElement.enable_left_recursion<ParserElement.enable_left_recursion>` Deprecated: only used by deprecated method ParserElement.validate. """ def __init__(self, parseElementList) -> None: self.parseElementTrace = parseElementList def __str__(self) -> str: return f"RecursiveGrammarException: {self.parseElementTrace}" PK )��ZQS��ۜ ۜ helpers.pynu �[��� # helpers.py import html.entities import operator import re import sys import typing from . import __diag__ from .core import * from .util import ( _bslash, _flatten, _escape_regex_range_chars, make_compressed_re, replaced_by_pep8, ) # # global helpers # def counted_array( expr: ParserElement, int_expr: typing.Optional[ParserElement] = None, *, intExpr: typing.Optional[ParserElement] = None, ) -> ParserElement: """Helper to define a counted list of expressions. This helper defines a pattern of the form:: integer expr expr expr... where the leading integer tells how many expr expressions follow. The matched tokens returns the array of expr tokens as a list - the leading count token is suppressed. If ``int_expr`` is specified, it should be a pyparsing expression that produces an integer value. Example:: counted_array(Word(alphas)).parse_string('2 ab cd ef') # -> ['ab', 'cd'] # in this parser, the leading integer value is given in binary, # '10' indicating that 2 values are in the array binary_constant = Word('01').set_parse_action(lambda t: int(t[0], 2)) counted_array(Word(alphas), int_expr=binary_constant).parse_string('10 ab cd ef') # -> ['ab', 'cd'] # if other fields must be parsed after the count but before the # list items, give the fields results names and they will # be preserved in the returned ParseResults: count_with_metadata = integer + Word(alphas)("type") typed_array = counted_array(Word(alphanums), int_expr=count_with_metadata)("items") result = typed_array.parse_string("3 bool True True False") print(result.dump()) # prints # ['True', 'True', 'False'] # - items: ['True', 'True', 'False'] # - type: 'bool' """ intExpr = intExpr or int_expr array_expr = Forward() def count_field_parse_action(s, l, t): nonlocal array_expr n = t[0] array_expr <<= (expr * n) if n else Empty() # clear list contents, but keep any named results del t[:] if intExpr is None: intExpr = Word(nums).set_parse_action(lambda t: int(t[0])) else: intExpr = intExpr.copy() intExpr.set_name("arrayLen") intExpr.add_parse_action(count_field_parse_action, call_during_try=True) return (intExpr + array_expr).set_name(f"(len) {expr}...") def match_previous_literal(expr: ParserElement) -> ParserElement: """Helper to define an expression that is indirectly defined from the tokens matched in a previous expression, that is, it looks for a 'repeat' of a previous expression. For example:: first = Word(nums) second = match_previous_literal(first) match_expr = first + ":" + second will match ``"1:1"``, but not ``"1:2"``. Because this matches a previous literal, will also match the leading ``"1:1"`` in ``"1:10"``. If this is not desired, use :class:`match_previous_expr`. Do *not* use with packrat parsing enabled. """ rep = Forward() def copy_token_to_repeater(s, l, t): if not t: rep << Empty() return if len(t) == 1: rep << t[0] return # flatten t tokens tflat = _flatten(t.as_list()) rep << And(Literal(tt) for tt in tflat) expr.add_parse_action(copy_token_to_repeater, callDuringTry=True) rep.set_name("(prev) " + str(expr)) return rep def match_previous_expr(expr: ParserElement) -> ParserElement: """Helper to define an expression that is indirectly defined from the tokens matched in a previous expression, that is, it looks for a 'repeat' of a previous expression. For example:: first = Word(nums) second = match_previous_expr(first) match_expr = first + ":" + second will match ``"1:1"``, but not ``"1:2"``. Because this matches by expressions, will *not* match the leading ``"1:1"`` in ``"1:10"``; the expressions are evaluated first, and then compared, so ``"1"`` is compared with ``"10"``. Do *not* use with packrat parsing enabled. """ rep = Forward() e2 = expr.copy() rep <<= e2 def copy_token_to_repeater(s, l, t): matchTokens = _flatten(t.as_list()) def must_match_these_tokens(s, l, t): theseTokens = _flatten(t.as_list()) if theseTokens != matchTokens: raise ParseException( s, l, f"Expected {matchTokens}, found{theseTokens}" ) rep.set_parse_action(must_match_these_tokens, callDuringTry=True) expr.add_parse_action(copy_token_to_repeater, callDuringTry=True) rep.set_name("(prev) " + str(expr)) return rep def one_of( strs: Union[typing.Iterable[str], str], caseless: bool = False, use_regex: bool = True, as_keyword: bool = False, *, useRegex: bool = True, asKeyword: bool = False, ) -> ParserElement: """Helper to quickly define a set of alternative :class:`Literal` s, and makes sure to do longest-first testing when there is a conflict, regardless of the input order, but returns a :class:`MatchFirst` for best performance. Parameters: - ``strs`` - a string of space-delimited literals, or a collection of string literals - ``caseless`` - treat all literals as caseless - (default= ``False``) - ``use_regex`` - as an optimization, will generate a :class:`Regex` object; otherwise, will generate a :class:`MatchFirst` object (if ``caseless=True`` or ``as_keyword=True``, or if creating a :class:`Regex` raises an exception) - (default= ``True``) - ``as_keyword`` - enforce :class:`Keyword`-style matching on the generated expressions - (default= ``False``) - ``asKeyword`` and ``useRegex`` are retained for pre-PEP8 compatibility, but will be removed in a future release Example:: comp_oper = one_of("< = > <= >= !=") var = Word(alphas) number = Word(nums) term = var | number comparison_expr = term + comp_oper + term print(comparison_expr.search_string("B = 12 AA=23 B<=AA AA>12")) prints:: [['B', '=', '12'], ['AA', '=', '23'], ['B', '<=', 'AA'], ['AA', '>', '12']] """ asKeyword = asKeyword or as_keyword useRegex = useRegex and use_regex if ( isinstance(caseless, str_type) and __diag__.warn_on_multiple_string_args_to_oneof ): warnings.warn( "warn_on_multiple_string_args_to_oneof:" " More than one string argument passed to one_of, pass" " choices as a list or space-delimited string", stacklevel=2, ) if caseless: is_equal = lambda a, b: a.upper() == b.upper() masks = lambda a, b: b.upper().startswith(a.upper()) else: is_equal = operator.eq masks = lambda a, b: b.startswith(a) symbols: list[str] if isinstance(strs, str_type): strs = typing.cast(str, strs) symbols = strs.split() elif isinstance(strs, Iterable): symbols = list(strs) else: raise TypeError("Invalid argument to one_of, expected string or iterable") if not symbols: return NoMatch() # reorder given symbols to take care to avoid masking longer choices with shorter ones # (but only if the given symbols are not just single characters) i = 0 while i < len(symbols) - 1: cur = symbols[i] for j, other in enumerate(symbols[i + 1 :]): if is_equal(other, cur): del symbols[i + j + 1] break if len(other) > len(cur) and masks(cur, other): del symbols[i + j + 1] symbols.insert(i, other) break else: i += 1 if useRegex: re_flags: int = re.IGNORECASE if caseless else 0 try: if all(len(sym) == 1 for sym in symbols): # symbols are just single characters, create range regex pattern patt = f"[{''.join(_escape_regex_range_chars(sym) for sym in symbols)}]" else: patt = "|".join(re.escape(sym) for sym in symbols) # wrap with \b word break markers if defining as keywords if asKeyword: patt = rf"\b(?:{patt})\b" ret = Regex(patt, flags=re_flags) ret.set_name(" | ".join(re.escape(s) for s in symbols)) if caseless: # add parse action to return symbols as specified, not in random # casing as found in input string symbol_map = {sym.lower(): sym for sym in symbols} ret.add_parse_action(lambda s, l, t: symbol_map[t[0].lower()]) return ret except re.error: warnings.warn( "Exception creating Regex for one_of, building MatchFirst", stacklevel=2 ) # last resort, just use MatchFirst of Token class corresponding to caseless # and asKeyword settings CASELESS = KEYWORD = True parse_element_class = { (CASELESS, KEYWORD): CaselessKeyword, (CASELESS, not KEYWORD): CaselessLiteral, (not CASELESS, KEYWORD): Keyword, (not CASELESS, not KEYWORD): Literal, }[(caseless, asKeyword)] return MatchFirst(parse_element_class(sym) for sym in symbols).set_name( " | ".join(symbols) ) def dict_of(key: ParserElement, value: ParserElement) -> Dict: """Helper to easily and clearly define a dictionary by specifying the respective patterns for the key and value. Takes care of defining the :class:`Dict`, :class:`ZeroOrMore`, and :class:`Group` tokens in the proper order. The key pattern can include delimiting markers or punctuation, as long as they are suppressed, thereby leaving the significant key text. The value pattern can include named results, so that the :class:`Dict` results can include named token fields. Example:: text = "shape: SQUARE posn: upper left color: light blue texture: burlap" attr_expr = (label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) print(attr_expr[1, ...].parse_string(text).dump()) attr_label = label attr_value = Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join) # similar to Dict, but simpler call format result = dict_of(attr_label, attr_value).parse_string(text) print(result.dump()) print(result['shape']) print(result.shape) # object attribute access works too print(result.as_dict()) prints:: [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']] - color: 'light blue' - posn: 'upper left' - shape: 'SQUARE' - texture: 'burlap' SQUARE SQUARE {'color': 'light blue', 'shape': 'SQUARE', 'posn': 'upper left', 'texture': 'burlap'} """ return Dict(OneOrMore(Group(key + value))) def original_text_for( expr: ParserElement, as_string: bool = True, *, asString: bool = True ) -> ParserElement: """Helper to return the original, untokenized text for a given expression. Useful to restore the parsed fields of an HTML start tag into the raw tag text itself, or to revert separate tokens with intervening whitespace back to the original matching input text. By default, returns a string containing the original parsed text. If the optional ``as_string`` argument is passed as ``False``, then the return value is a :class:`ParseResults` containing any results names that were originally matched, and a single token containing the original matched text from the input string. So if the expression passed to :class:`original_text_for` contains expressions with defined results names, you must set ``as_string`` to ``False`` if you want to preserve those results name values. The ``asString`` pre-PEP8 argument is retained for compatibility, but will be removed in a future release. Example:: src = "this is test <b> bold <i>text</i> </b> normal text " for tag in ("b", "i"): opener, closer = make_html_tags(tag) patt = original_text_for(opener + ... + closer) print(patt.search_string(src)[0]) prints:: ['<b> bold <i>text</i> </b>'] ['<i>text</i>'] """ asString = asString and as_string locMarker = Empty().set_parse_action(lambda s, loc, t: loc) endlocMarker = locMarker.copy() endlocMarker.callPreparse = False matchExpr = locMarker("_original_start") + expr + endlocMarker("_original_end") if asString: extractText = lambda s, l, t: s[t._original_start : t._original_end] else: def extractText(s, l, t): t[:] = [s[t.pop("_original_start") : t.pop("_original_end")]] matchExpr.set_parse_action(extractText) matchExpr.ignoreExprs = expr.ignoreExprs matchExpr.suppress_warning(Diagnostics.warn_ungrouped_named_tokens_in_collection) return matchExpr def ungroup(expr: ParserElement) -> ParserElement: """Helper to undo pyparsing's default grouping of And expressions, even if all but one are non-empty. """ return TokenConverter(expr).add_parse_action(lambda t: t[0]) def locatedExpr(expr: ParserElement) -> ParserElement: """ (DEPRECATED - future code should use the :class:`Located` class) Helper to decorate a returned token with its starting and ending locations in the input string. This helper adds the following results names: - ``locn_start`` - location where matched expression begins - ``locn_end`` - location where matched expression ends - ``value`` - the actual parsed results Be careful if the input text contains ``<TAB>`` characters, you may want to call :class:`ParserElement.parse_with_tabs` Example:: wd = Word(alphas) for match in locatedExpr(wd).search_string("ljsdf123lksdjjf123lkkjj1222"): print(match) prints:: [[0, 'ljsdf', 5]] [[8, 'lksdjjf', 15]] [[18, 'lkkjj', 23]] """ locator = Empty().set_parse_action(lambda ss, ll, tt: ll) return Group( locator("locn_start") + expr("value") + locator.copy().leaveWhitespace()("locn_end") ) # define special default value to permit None as a significant value for # ignore_expr _NO_IGNORE_EXPR_GIVEN = NoMatch() def nested_expr( opener: Union[str, ParserElement] = "(", closer: Union[str, ParserElement] = ")", content: typing.Optional[ParserElement] = None, ignore_expr: ParserElement = _NO_IGNORE_EXPR_GIVEN, *, ignoreExpr: ParserElement = _NO_IGNORE_EXPR_GIVEN, ) -> ParserElement: """Helper method for defining nested lists enclosed in opening and closing delimiters (``"("`` and ``")"`` are the default). Parameters: - ``opener`` - opening character for a nested list (default= ``"("``); can also be a pyparsing expression - ``closer`` - closing character for a nested list (default= ``")"``); can also be a pyparsing expression - ``content`` - expression for items within the nested lists (default= ``None``) - ``ignore_expr`` - expression for ignoring opening and closing delimiters (default= :class:`quoted_string`) - ``ignoreExpr`` - this pre-PEP8 argument is retained for compatibility but will be removed in a future release If an expression is not provided for the content argument, the nested expression will capture all whitespace-delimited content between delimiters as a list of separate values. Use the ``ignore_expr`` argument to define expressions that may contain opening or closing characters that should not be treated as opening or closing characters for nesting, such as quoted_string or a comment expression. Specify multiple expressions using an :class:`Or` or :class:`MatchFirst`. The default is :class:`quoted_string`, but if no expressions are to be ignored, then pass ``None`` for this argument. Example:: data_type = one_of("void int short long char float double") decl_data_type = Combine(data_type + Opt(Word('*'))) ident = Word(alphas+'_', alphanums+'_') number = pyparsing_common.number arg = Group(decl_data_type + ident) LPAR, RPAR = map(Suppress, "()") code_body = nested_expr('{', '}', ignore_expr=(quoted_string | c_style_comment)) c_function = (decl_data_type("type") + ident("name") + LPAR + Opt(DelimitedList(arg), [])("args") + RPAR + code_body("body")) c_function.ignore(c_style_comment) source_code = ''' int is_odd(int x) { return (x%2); } int dec_to_hex(char hchar) { if (hchar >= '0' && hchar <= '9') { return (ord(hchar)-ord('0')); } else { return (10+ord(hchar)-ord('A')); } } ''' for func in c_function.search_string(source_code): print("%(name)s (%(type)s) args: %(args)s" % func) prints:: is_odd (int) args: [['int', 'x']] dec_to_hex (int) args: [['char', 'hchar']] """ if ignoreExpr != ignore_expr: ignoreExpr = ignore_expr if ignoreExpr is _NO_IGNORE_EXPR_GIVEN else ignoreExpr if ignoreExpr is _NO_IGNORE_EXPR_GIVEN: ignoreExpr = quoted_string() if opener == closer: raise ValueError("opening and closing strings cannot be the same") if content is None: if isinstance(opener, str_type) and isinstance(closer, str_type): opener = typing.cast(str, opener) closer = typing.cast(str, closer) if len(opener) == 1 and len(closer) == 1: if ignoreExpr is not None: content = Combine( OneOrMore( ~ignoreExpr + CharsNotIn( opener + closer + ParserElement.DEFAULT_WHITE_CHARS, exact=1, ) ) ) else: content = Combine( Empty() + CharsNotIn( opener + closer + ParserElement.DEFAULT_WHITE_CHARS ) ) else: if ignoreExpr is not None: content = Combine( OneOrMore( ~ignoreExpr + ~Literal(opener) + ~Literal(closer) + CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS, exact=1) ) ) else: content = Combine( OneOrMore( ~Literal(opener) + ~Literal(closer) + CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS, exact=1) ) ) else: raise ValueError( "opening and closing arguments must be strings if no content expression is given" ) # for these internally-created context expressions, simulate whitespace-skipping if ParserElement.DEFAULT_WHITE_CHARS: content.set_parse_action( lambda t: t[0].strip(ParserElement.DEFAULT_WHITE_CHARS) ) ret = Forward() if ignoreExpr is not None: ret <<= Group( Suppress(opener) + ZeroOrMore(ignoreExpr | ret | content) + Suppress(closer) ) else: ret <<= Group(Suppress(opener) + ZeroOrMore(ret | content) + Suppress(closer)) ret.set_name(f"nested {opener}{closer} expression") # don't override error message from content expressions ret.errmsg = None return ret def _makeTags(tagStr, xml, suppress_LT=Suppress("<"), suppress_GT=Suppress(">")): """Internal helper to construct opening and closing tag expressions, given a tag name""" if isinstance(tagStr, str_type): resname = tagStr tagStr = Keyword(tagStr, caseless=not xml) else: resname = tagStr.name tagAttrName = Word(alphas, alphanums + "_-:") if xml: tagAttrValue = dbl_quoted_string.copy().set_parse_action(remove_quotes) openTag = ( suppress_LT + tagStr("tag") + Dict(ZeroOrMore(Group(tagAttrName + Suppress("=") + tagAttrValue))) + Opt("/", default=[False])("empty").set_parse_action( lambda s, l, t: t[0] == "/" ) + suppress_GT ) else: tagAttrValue = quoted_string.copy().set_parse_action(remove_quotes) | Word( printables, exclude_chars=">" ) openTag = ( suppress_LT + tagStr("tag") + Dict( ZeroOrMore( Group( tagAttrName.set_parse_action(lambda t: t[0].lower()) + Opt(Suppress("=") + tagAttrValue) ) ) ) + Opt("/", default=[False])("empty").set_parse_action( lambda s, l, t: t[0] == "/" ) + suppress_GT ) closeTag = Combine(Literal("</") + tagStr + ">", adjacent=False) openTag.set_name(f"<{resname}>") # add start<tagname> results name in parse action now that ungrouped names are not reported at two levels openTag.add_parse_action( lambda t: t.__setitem__( "start" + "".join(resname.replace(":", " ").title().split()), t.copy() ) ) closeTag = closeTag( "end" + "".join(resname.replace(":", " ").title().split()) ).set_name(f"</{resname}>") openTag.tag = resname closeTag.tag = resname openTag.tag_body = SkipTo(closeTag()) return openTag, closeTag def make_html_tags( tag_str: Union[str, ParserElement], ) -> tuple[ParserElement, ParserElement]: """Helper to construct opening and closing tag expressions for HTML, given a tag name. Matches tags in either upper or lower case, attributes with namespaces and with quoted or unquoted values. Example:: text = '<td>More info at the <a href="https://github.com/pyparsing/pyparsing/wiki">pyparsing</a> wiki page</td>' # make_html_tags returns pyparsing expressions for the opening and # closing tags as a 2-tuple a, a_end = make_html_tags("A") link_expr = a + SkipTo(a_end)("link_text") + a_end for link in link_expr.search_string(text): # attributes in the <A> tag (like "href" shown here) are # also accessible as named results print(link.link_text, '->', link.href) prints:: pyparsing -> https://github.com/pyparsing/pyparsing/wiki """ return _makeTags(tag_str, False) def make_xml_tags( tag_str: Union[str, ParserElement], ) -> tuple[ParserElement, ParserElement]: """Helper to construct opening and closing tag expressions for XML, given a tag name. Matches tags only in the given upper/lower case. Example: similar to :class:`make_html_tags` """ return _makeTags(tag_str, True) any_open_tag: ParserElement any_close_tag: ParserElement any_open_tag, any_close_tag = make_html_tags( Word(alphas, alphanums + "_:").set_name("any tag") ) _htmlEntityMap = {k.rstrip(";"): v for k, v in html.entities.html5.items()} _most_common_entities = "nbsp lt gt amp quot apos cent pound euro copy".replace( " ", "|" ) common_html_entity = Regex( lambda: f"&(?P<entity>{_most_common_entities}|{make_compressed_re(_htmlEntityMap)});" ).set_name("common HTML entity") def replace_html_entity(s, l, t): """Helper parser action to replace common HTML entities with their special characters""" return _htmlEntityMap.get(t.entity) class OpAssoc(Enum): """Enumeration of operator associativity - used in constructing InfixNotationOperatorSpec for :class:`infix_notation`""" LEFT = 1 RIGHT = 2 InfixNotationOperatorArgType = Union[ ParserElement, str, tuple[Union[ParserElement, str], Union[ParserElement, str]] ] InfixNotationOperatorSpec = Union[ tuple[ InfixNotationOperatorArgType, int, OpAssoc, typing.Optional[ParseAction], ], tuple[ InfixNotationOperatorArgType, int, OpAssoc, ], ] def infix_notation( base_expr: ParserElement, op_list: list[InfixNotationOperatorSpec], lpar: Union[str, ParserElement] = Suppress("("), rpar: Union[str, ParserElement] = Suppress(")"), ) -> Forward: """Helper method for constructing grammars of expressions made up of operators working in a precedence hierarchy. Operators may be unary or binary, left- or right-associative. Parse actions can also be attached to operator expressions. The generated parser will also recognize the use of parentheses to override operator precedences (see example below). Note: if you define a deep operator list, you may see performance issues when using infix_notation. See :class:`ParserElement.enable_packrat` for a mechanism to potentially improve your parser performance. Parameters: - ``base_expr`` - expression representing the most basic operand to be used in the expression - ``op_list`` - list of tuples, one for each operator precedence level in the expression grammar; each tuple is of the form ``(op_expr, num_operands, right_left_assoc, (optional)parse_action)``, where: - ``op_expr`` is the pyparsing expression for the operator; may also be a string, which will be converted to a Literal; if ``num_operands`` is 3, ``op_expr`` is a tuple of two expressions, for the two operators separating the 3 terms - ``num_operands`` is the number of terms for this operator (must be 1, 2, or 3) - ``right_left_assoc`` is the indicator whether the operator is right or left associative, using the pyparsing-defined constants ``OpAssoc.RIGHT`` and ``OpAssoc.LEFT``. - ``parse_action`` is the parse action to be associated with expressions matching this operator expression (the parse action tuple member may be omitted); if the parse action is passed a tuple or list of functions, this is equivalent to calling ``set_parse_action(*fn)`` (:class:`ParserElement.set_parse_action`) - ``lpar`` - expression for matching left-parentheses; if passed as a str, then will be parsed as ``Suppress(lpar)``. If lpar is passed as an expression (such as ``Literal('(')``), then it will be kept in the parsed results, and grouped with them. (default= ``Suppress('(')``) - ``rpar`` - expression for matching right-parentheses; if passed as a str, then will be parsed as ``Suppress(rpar)``. If rpar is passed as an expression (such as ``Literal(')')``), then it will be kept in the parsed results, and grouped with them. (default= ``Suppress(')')``) Example:: # simple example of four-function arithmetic with ints and # variable names integer = pyparsing_common.signed_integer varname = pyparsing_common.identifier arith_expr = infix_notation(integer | varname, [ ('-', 1, OpAssoc.RIGHT), (one_of('* /'), 2, OpAssoc.LEFT), (one_of('+ -'), 2, OpAssoc.LEFT), ]) arith_expr.run_tests(''' 5+3*6 (5+3)*6 -2--11 ''', full_dump=False) prints:: 5+3*6 [[5, '+', [3, '*', 6]]] (5+3)*6 [[[5, '+', 3], '*', 6]] (5+x)*y [[[5, '+', 'x'], '*', 'y']] -2--11 [[['-', 2], '-', ['-', 11]]] """ # captive version of FollowedBy that does not do parse actions or capture results names class _FB(FollowedBy): def parseImpl(self, instring, loc, doActions=True): self.expr.try_parse(instring, loc) return loc, [] _FB.__name__ = "FollowedBy>" ret = Forward() ret.set_name(f"{base_expr.name}_expression") if isinstance(lpar, str): lpar = Suppress(lpar) if isinstance(rpar, str): rpar = Suppress(rpar) nested_expr = (lpar + ret + rpar).set_name(f"nested_{base_expr.name}") # if lpar and rpar are not suppressed, wrap in group if not (isinstance(lpar, Suppress) and isinstance(rpar, Suppress)): lastExpr = base_expr | Group(nested_expr) else: lastExpr = base_expr | nested_expr arity: int rightLeftAssoc: opAssoc pa: typing.Optional[ParseAction] opExpr1: ParserElement opExpr2: ParserElement matchExpr: ParserElement match_lookahead: ParserElement for operDef in op_list: opExpr, arity, rightLeftAssoc, pa = (operDef + (None,))[:4] # type: ignore[assignment] if isinstance(opExpr, str_type): opExpr = ParserElement._literalStringClass(opExpr) opExpr = typing.cast(ParserElement, opExpr) if arity == 3: if not isinstance(opExpr, (tuple, list)) or len(opExpr) != 2: raise ValueError( "if numterms=3, opExpr must be a tuple or list of two expressions" ) opExpr1, opExpr2 = opExpr term_name = f"{opExpr1}{opExpr2} operations" else: term_name = f"{opExpr} operations" if not 1 <= arity <= 3: raise ValueError("operator must be unary (1), binary (2), or ternary (3)") if rightLeftAssoc not in (OpAssoc.LEFT, OpAssoc.RIGHT): raise ValueError("operator must indicate right or left associativity") thisExpr: ParserElement = Forward().set_name(term_name) thisExpr = typing.cast(Forward, thisExpr) match_lookahead = And([]) if rightLeftAssoc is OpAssoc.LEFT: if arity == 1: match_lookahead = _FB(lastExpr + opExpr) matchExpr = Group(lastExpr + opExpr[1, ...]) elif arity == 2: if opExpr is not None: match_lookahead = _FB(lastExpr + opExpr + lastExpr) matchExpr = Group(lastExpr + (opExpr + lastExpr)[1, ...]) else: match_lookahead = _FB(lastExpr + lastExpr) matchExpr = Group(lastExpr[2, ...]) elif arity == 3: match_lookahead = _FB( lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr ) matchExpr = Group( lastExpr + (opExpr1 + lastExpr + opExpr2 + lastExpr)[1, ...] ) elif rightLeftAssoc is OpAssoc.RIGHT: if arity == 1: # try to avoid LR with this extra test if not isinstance(opExpr, Opt): opExpr = Opt(opExpr) match_lookahead = _FB(opExpr.expr + thisExpr) matchExpr = Group(opExpr + thisExpr) elif arity == 2: if opExpr is not None: match_lookahead = _FB(lastExpr + opExpr + thisExpr) matchExpr = Group(lastExpr + (opExpr + thisExpr)[1, ...]) else: match_lookahead = _FB(lastExpr + thisExpr) matchExpr = Group(lastExpr + thisExpr[1, ...]) elif arity == 3: match_lookahead = _FB( lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr ) matchExpr = Group(lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr) # suppress lookahead expr from railroad diagrams match_lookahead.show_in_diagram = False # TODO - determine why this statement can't be included in the following # if pa block matchExpr = match_lookahead + matchExpr if pa: if isinstance(pa, (tuple, list)): matchExpr.set_parse_action(*pa) else: matchExpr.set_parse_action(pa) thisExpr <<= (matchExpr | lastExpr).setName(term_name) lastExpr = thisExpr ret <<= lastExpr return ret def indentedBlock(blockStatementExpr, indentStack, indent=True, backup_stacks=[]): """ (DEPRECATED - use :class:`IndentedBlock` class instead) Helper method for defining space-delimited indentation blocks, such as those used to define block statements in Python source code. Parameters: - ``blockStatementExpr`` - expression defining syntax of statement that is repeated within the indented block - ``indentStack`` - list created by caller to manage indentation stack (multiple ``statementWithIndentedBlock`` expressions within a single grammar should share a common ``indentStack``) - ``indent`` - boolean indicating whether block must be indented beyond the current level; set to ``False`` for block of left-most statements (default= ``True``) A valid block must contain at least one ``blockStatement``. (Note that indentedBlock uses internal parse actions which make it incompatible with packrat parsing.) Example:: data = ''' def A(z): A1 B = 100 G = A2 A2 A3 B def BB(a,b,c): BB1 def BBA(): bba1 bba2 bba3 C D def spam(x,y): def eggs(z): pass ''' indentStack = [1] stmt = Forward() identifier = Word(alphas, alphanums) funcDecl = ("def" + identifier + Group("(" + Opt(delimitedList(identifier)) + ")") + ":") func_body = indentedBlock(stmt, indentStack) funcDef = Group(funcDecl + func_body) rvalue = Forward() funcCall = Group(identifier + "(" + Opt(delimitedList(rvalue)) + ")") rvalue << (funcCall | identifier | Word(nums)) assignment = Group(identifier + "=" + rvalue) stmt << (funcDef | assignment | identifier) module_body = stmt[1, ...] parseTree = module_body.parseString(data) parseTree.pprint() prints:: [['def', 'A', ['(', 'z', ')'], ':', [['A1'], [['B', '=', '100']], [['G', '=', 'A2']], ['A2'], ['A3']]], 'B', ['def', 'BB', ['(', 'a', 'b', 'c', ')'], ':', [['BB1'], [['def', 'BBA', ['(', ')'], ':', [['bba1'], ['bba2'], ['bba3']]]]]], 'C', 'D', ['def', 'spam', ['(', 'x', 'y', ')'], ':', [[['def', 'eggs', ['(', 'z', ')'], ':', [['pass']]]]]]] """ backup_stacks.append(indentStack[:]) def reset_stack(): indentStack[:] = backup_stacks[-1] def checkPeerIndent(s, l, t): if l >= len(s): return curCol = col(l, s) if curCol != indentStack[-1]: if curCol > indentStack[-1]: raise ParseException(s, l, "illegal nesting") raise ParseException(s, l, "not a peer entry") def checkSubIndent(s, l, t): curCol = col(l, s) if curCol > indentStack[-1]: indentStack.append(curCol) else: raise ParseException(s, l, "not a subentry") def checkUnindent(s, l, t): if l >= len(s): return curCol = col(l, s) if not (indentStack and curCol in indentStack): raise ParseException(s, l, "not an unindent") if curCol < indentStack[-1]: indentStack.pop() NL = OneOrMore(LineEnd().set_whitespace_chars("\t ").suppress()) INDENT = (Empty() + Empty().set_parse_action(checkSubIndent)).set_name("INDENT") PEER = Empty().set_parse_action(checkPeerIndent).set_name("") UNDENT = Empty().set_parse_action(checkUnindent).set_name("UNINDENT") if indent: smExpr = Group( Opt(NL) + INDENT + OneOrMore(PEER + Group(blockStatementExpr) + Opt(NL)) + UNDENT ) else: smExpr = Group( Opt(NL) + OneOrMore(PEER + Group(blockStatementExpr) + Opt(NL)) + Opt(UNDENT) ) # add a parse action to remove backup_stack from list of backups smExpr.add_parse_action( lambda: backup_stacks.pop(-1) and None if backup_stacks else None ) smExpr.set_fail_action(lambda a, b, c, d: reset_stack()) blockStatementExpr.ignore(_bslash + LineEnd()) return smExpr.set_name("indented block") # it's easy to get these comment structures wrong - they're very common, # so may as well make them available c_style_comment = Regex(r"/\*(?:[^*]|\*(?!/))*\*\/").set_name("C style comment") "Comment of the form ``/* ... */``" html_comment = Regex(r"<!--[\s\S]*?-->").set_name("HTML comment") "Comment of the form ``<!-- ... -->``" rest_of_line = Regex(r".*").leave_whitespace().set_name("rest of line") dbl_slash_comment = Regex(r"//(?:\\\n|[^\n])*").set_name("// comment") "Comment of the form ``// ... (to end of line)``" cpp_style_comment = Regex( r"(?:/\*(?:[^*]|\*(?!/))*\*\/)|(?://(?:\\\n|[^\n])*)" ).set_name("C++ style comment") "Comment of either form :class:`c_style_comment` or :class:`dbl_slash_comment`" java_style_comment = cpp_style_comment "Same as :class:`cpp_style_comment`" python_style_comment = Regex(r"#.*").set_name("Python style comment") "Comment of the form ``# ... (to end of line)``" # build list of built-in expressions, for future reference if a global default value # gets updated _builtin_exprs: list[ParserElement] = [ v for v in vars().values() if isinstance(v, ParserElement) ] # compatibility function, superseded by DelimitedList class def delimited_list( expr: Union[str, ParserElement], delim: Union[str, ParserElement] = ",", combine: bool = False, min: typing.Optional[int] = None, max: typing.Optional[int] = None, *, allow_trailing_delim: bool = False, ) -> ParserElement: """(DEPRECATED - use :class:`DelimitedList` class)""" return DelimitedList( expr, delim, combine, min, max, allow_trailing_delim=allow_trailing_delim ) # Compatibility synonyms # fmt: off opAssoc = OpAssoc anyOpenTag = any_open_tag anyCloseTag = any_close_tag commonHTMLEntity = common_html_entity cStyleComment = c_style_comment htmlComment = html_comment restOfLine = rest_of_line dblSlashComment = dbl_slash_comment cppStyleComment = cpp_style_comment javaStyleComment = java_style_comment pythonStyleComment = python_style_comment delimitedList = replaced_by_pep8("delimitedList", DelimitedList) delimited_list = replaced_by_pep8("delimited_list", DelimitedList) countedArray = replaced_by_pep8("countedArray", counted_array) matchPreviousLiteral = replaced_by_pep8("matchPreviousLiteral", match_previous_literal) matchPreviousExpr = replaced_by_pep8("matchPreviousExpr", match_previous_expr) oneOf = replaced_by_pep8("oneOf", one_of) dictOf = replaced_by_pep8("dictOf", dict_of) originalTextFor = replaced_by_pep8("originalTextFor", original_text_for) nestedExpr = replaced_by_pep8("nestedExpr", nested_expr) makeHTMLTags = replaced_by_pep8("makeHTMLTags", make_html_tags) makeXMLTags = replaced_by_pep8("makeXMLTags", make_xml_tags) replaceHTMLEntity = replaced_by_pep8("replaceHTMLEntity", replace_html_entity) infixNotation = replaced_by_pep8("infixNotation", infix_notation) # fmt: on PK )��Z�tK#�J �J , diagram/__pycache__/__init__.cpython-310.pycnu �[��� o �h`i � @ s� d dl mZ d dlZd dlZd dlZd dlZd dlZd dlmZmZm Z m Z d dl m Z d dl mZ d dlZd dlZdZe e�Zi Zejdd�ZdFd d �ZdGdd�ZejG dd� d��Zed�ZG dd� dej�Z G dd� dej�Z G dd� dee �Z dHdId d �Z dJd!d"�Z # dKdLd.d/�Z!dMd3d4�Z"ejG d5d6� d6��Z#G d7d8� d8�Z$dNd9d:�Z%d;d<� Z&dOd=d>�Z'e& dPdQdDdE��Z(dS )R� )� annotationsN)�Generic�TypeVar�Callable�Iterable)�Template)�StringIOa� {% if not embed %} <!DOCTYPE html> <html> <head> {% endif %} {% if not head %} <style> .railroad-heading { font-family: monospace; } </style> {% else %} {{ head | safe }} {% endif %} {% if not embed %} </head> <body> {% endif %} <meta charset="UTF-8"/> {{ body | safe }} {% for diagram in diagrams %} <div class="railroad-group"> <h1 class="railroad-heading" id="{{ diagram.bookmark }}">{{ diagram.title }}</h1> <div class="railroad-description">{{ diagram.text }}</div> <div class="railroad-svg"> {{ diagram.svg }} </div> </div> {% endfor %} {% if not embed %} </body> </html> {% endif %} � )�start�s�str�returnc C sf | t v rt | S t�dd| �}|dd� �� s d|� �}|�� �d�}|� dtt�d�� t | < }|S )zK Converts a string into a valid HTML bookmark (ID or anchor name). z[^a-zA-Z0-9-]+�-Nr �z�04d)�_bookmark_lookup�re�sub�isalpha�lower�strip�next� _bookmark_ids)r �bookmark� r �M/usr/local/CyberCP/lib/python3.10/site-packages/pyparsing/diagram/__init__.py�_make_bookmark? s r � regex_strc C s2 d| vr| S t �d��� �| �}t�dd|�}|S )N� z#.*$z\s*\n\s*� )� pyparsing�Regex�suppress�transform_stringr r )r � collapsedr r r �_collapse_verbose_regexU s r% c @ s: e Zd ZU dZded< ded< dZded< ed d � �ZdS ) � NamedDiagramzK A simple structure for associating a name with a railroad diagram r �name�int�indexNzrailroad.DiagramItem�diagramc C s t | j�}|S �N)r r' )�selfr r r r r g s zNamedDiagram.bookmark)�__name__� __module__� __qualname__�__doc__�__annotations__r* �propertyr r r r r r& ] s r& �Tc s& e Zd ZdZdZd� fdd� Z� ZS )�EachItemz� Custom railroad item to compose a: - Group containing a - OneOrMore containing a - Choice of the elements in the Each with the group label indicating that all must be matched z[ALL]r �Nonec s< t jt|�d g|�R � }t j|d�}t� j|| jd� d S )Nr ��item)�label)�railroad�Choice�len� OneOrMore�super�__init__� all_label)r, �items� choice_item�one_or_more_item�� __class__r r r> { s zEachItem.__init__)r r5 )r- r. r/ r0 r? r> � __classcell__r r rC r r4 p s r4 c s" e Zd ZdZd� fdd� Z� ZS ) � AnnotatedItemzC Simple subclass of Group that creates an annotation label r8 r r r5 c s$ t � j||r d|� d�ndd� d S )N�[�]r �r7 r8 )r= r> )r, r8 r7 rC r r r> � s $zAnnotatedItem.__init__)r8 r r r5 )r- r. r/ r0 r> rE r r rC r rF � s rF c @ s> e Zd ZdZdd d �Zedd d��Zedd� �Zddd�Z dS )�EditablePartialz� Acts like a functools.partial, but can be edited. In other words, it represents a type that hasn't yet been constructed. �func�Callable[..., T]�args�list�kwargs�dictr r5 c C s || _ || _|| _d S r+ �rK rM rO )r, rK rM rO r r r r> � s zEditablePartial.__init__�EditablePartial[T]c O s t |t|�|d�S )z� If you call this function in the same way that you would call the constructor, it will store the arguments as you expect. For example EditablePartial.from_call(Fraction, 1, 3)() == Fraction(1, 3) rQ )rJ rN )�clsrK rM rO r r r � from_call� s zEditablePartial.from_callc C s | j d S )Nr' )rO �r, r r r r' � s zEditablePartial.namer3 c C sL | j �� }| j�� }t�| j�}|j| jv r ||�|j�7 }| j|i |��S )z< Evaluate the partial and return the result )rM �copyrO �inspect�getfullargspecrK �varargs�pop)r, rM rO �arg_specr r r �__call__� s zEditablePartial.__call__N)rK rL rM rN rO rP r r5 )rK rL r rR )r r3 ) r- r. r/ r0 r> � classmethodrT r2 r' r\ r r r r rJ � s rJ F�diagrams�list[NamedDiagram]c K s� g }| D ]E}|j du r qt� }z|�d�}|j j|j|d� W n ty/ |j �|j� Y nw |j}|jdkr<|d7 }|� |d|� � |j d�� qt j d ||d�|��S ) z� Given a list of NamedDiagram, produce a single HTML string that visualises those diagrams :params kwargs: kwargs to be passed in to the template N�css)r` r z (root)r )�title�text�svgr )r^ �embedr )r* r �get�writeStandalone�write�AttributeError�writeSvgr' r) �append�getvaluer �template�render)r^ rd rO �datar* �ior` ra r r r �railroad_to_html� s& � ��rp �partialrR c C s` t | t�rt| j�| _t| j�| _| � S t | t�r dd� | D �S t | t�r.dd� | �� D �S | S )zS Recursively resolves a collection of Partials into whatever type they are c S � g | ]}t |��qS r ��resolve_partial)�.0�xr r r � <listcomp>� � z#resolve_partial.<locals>.<listcomp>c S s i | ] \}}|t |��qS r rs )ru �keyrv r r r � <dictcomp>� s z#resolve_partial.<locals>.<dictcomp>)� isinstancerJ rt rM rO rN rP r@ )rq r r r rt � s rt � �element�pyparsing.ParserElement�diagram_kwargs�typing.Optional[dict]�verticalr( �show_results_names�bool� show_groups� show_hiddenc C s� t |pi d�}t| |d||||d� t| �}||v r,| js"d|| _|| j||dd� t|j�� �}t |�dkrft � } g } |D ] } | jdkrHq@| jdur]| j| vr]| � | j� | � | � q@d d � | D �} nd d � |D �} t | d d � d�S )a< Convert a pyparsing element tree into a list of diagrams. This is the recommended entrypoint to diagram creation if you want to access the Railroad tree before it is converted to HTML :param element: base element of the parser being diagrammed :param diagram_kwargs: kwargs to pass to the Diagram() constructor :param vertical: (optional) - int - limit at which number of alternatives should be shown vertically instead of horizontally :param show_results_names - bool to indicate whether results name annotations should be included in the diagram :param show_groups - bool to indicate whether groups should be highlighted with an unlabeled surrounding box :param show_hidden - bool to indicate whether internal elements that are typically hidden should be shown )r N)�lookup�parentr� r� r� r� r T)�forcer z...c S rr r rs �ru rq r r r rw rx z to_railroad.<locals>.<listcomp>c S rr r rs r� r r r rw rx c S s | j S r+ �r) )�diagr r r �<lambda> s z to_railroad.<locals>.<lambda>)ry )�ConverterState�_to_diagram_element�id� customNamer' �mark_for_extractionrN r^ �valuesr; �set�addrj �sorted) r} r r� r� r� r� r� �root_id�diags�seen� deduped_diags�d�resolvedr r r � to_railroad� s: � �r� � specification�exprs�!Iterable[pyparsing.ParserElement]c C s | du rdS t t|��| kS )zF Returns true if we should return a vertical list of elements NF)r; �_visible_exprs)r� r� r r r �_should_vertical s r� c @ sp e Zd ZU dZded< ded< ded< ded< d Zd ed < d Zd ed < dZded< dZded< dddd�Z d S )� ElementStatez< State recorded for an individual pyparsing Element r~ r} rJ � convertedr� r( �numberNr r' ztyping.Optional[int]� parent_indexFr� �extract�complete�el_id�stater� r� c C s\ d| _ | js|r || _n | jjr| jj| _nd| _|s#| jr*t| j�r,|�|� dS dS dS )a� Called when this instance has been seen twice, and thus should eventually be extracted into a sub-diagram :param el_id: id of the element :param state: element/diagram state tracker :param name: name to use for this element's text :param force: If true, force extraction now, regardless of the state of this. Only useful for extracting the root element when we know we're finished Tr N)r� r' r} r� r� �_worth_extracting�extract_into_diagram)r, r� r� r' r� r r r r� @ s �z ElementState.mark_for_extraction)NF)r� r( r� r� r' r r� r� ) r- r. r/ r0 r1 r' r� r� r� r� r r r r r� ) s �r� c @ sl e Zd ZdZd d dd�Zd d d�Zd!dd�Zd"dd�Zd"dd�Zd dd�Z d#dd�Z d#dd�Z d$d d �Z dS )%r� zR Stores some state that persists between recursions into the element tree Nr r� r r5 c C s. i | _ i | _d| _d| _|pi | _t� | _d S )Nr r )�_element_diagram_statesr^ � unnamed_indexr) r r� �extracted_diagram_names)r, r r r r r> c s zConverterState.__init__ry r( �valuer� c C s || j |< d S r+ �r� )r, ry r� r r r � __setitem__p s zConverterState.__setitem__c C s | j | S r+ r� �r, ry r r r � __getitem__s � zConverterState.__getitem__c C s | j |= d S r+ r� r� r r r � __delitem__v s zConverterState.__delitem__c C s || j v S r+ r� r� r r r � __contains__y r� zConverterState.__contains__c C s" z| | W S t y | Y S w r+ )�KeyError)r, ry �defaultr r r re | s �zConverterState.getc C � | j d7 _ | j S )zT Generate a number used in the name of an otherwise unnamed diagram r )r� rU r r r �generate_unnamed� � z ConverterState.generate_unnamedc C r� )z; Generate a number used to index a diagram r r� rU r r r �generate_index� r� z ConverterState.generate_indexr� c C s� | | }|j r5dt|j�� �}tjtj|j|d�}d|j jv r&||j jd< nd|j jv r5||j jd |j< |j j tj krC|j jd }n|j }tjt |jtjtj |fi | j��|jd�| j|< | |= dS )z� Used when we encounter the same token twice in the same tree. When this happens, we replace all instances of that token with a terminal, and create a new subdiagram for the token �#�rb �hrefr7 r@ )r' r* r) N)r� r r' rJ rT r9 � NonTerminalrO r� r� rK �Groupr& �Diagramr r� r^ )r, r� �positionr� �ret�contentr r r r� � s, �� � z#ConverterState.extract_into_diagramr+ )r r� r r5 )ry r( r� r� )ry r( r r� )ry r( )r r( )r� r( ) r- r. r/ r0 r> r� r� r� r� re r� r� r� r r r r r� ^ s r� c C s | � � }tdd� |D ��S )z� Returns true if this element is worth having its own sub-diagram. Simply, if any of its children themselves have children, then its complex enough to extract c s s � | ]}|� � V qd S r+ )�recurse)ru �childr r r � <genexpr>� s � z$_worth_extracting.<locals>.<genexpr>)r� �any)r} �childrenr r r r� � s r� c s" dd� fdd� }|S )z� decorator to ensure enhancements to a diagram item (such as results name annotations) get applied on return from _to_diagram_element (we do this since there are several returns in _to_diagram_element) Nr Fr} r~ r� � typing.Optional[EditablePartial]r� r� r� r( r) � name_hintr r� r� r� r� r c s^ � | ||||||||� } |r-| d ur-| j } | r-| jr dnd} tjtj| t| �� | � �d�} | S )Nr �*rI )� resultsName� modalResultsrJ rT r9 r� �repr) r} r� r� r� r) r� r� r� r� r� �element_results_name� modal_tag��fnr r �_inner� s* � �z0_apply_diagram_item_enhancements.<locals>._inner�NNr NFFF�r} r~ r� r� r� r� r� r( r) r( r� r r� r� r� r� r� r� r r� r )r� r� r r� r � _apply_diagram_item_enhancements� s �%r� c s$ t jt jt jjf� � fdd�| D �S )Nc s g | ] }t |� �s|�qS r )r{ �ru �e��non_diagramming_exprsr r rw � s ��z"_visible_exprs.<locals>.<listcomp>)r �ParseElementEnhance� PositionToken�And� _ErrorStop)r� r r� r r� � s � �r� r� r� r� r) r� c C sn | � � } |p | jp t| �j} t| �} | j} | js;t| tjtj f�r;| r;| d js+| } nd} t | j ||||| |||d� S t | �r�|� | �}|rg|jdurg|j| ||d� dt|j�� �}tjtj|j|d�}|S | |jv r�|j| jd }tjtj|dt|�� �d�}|S | js�|s�dS t| tj�r�| s�dS ttdd � | D ���d kr�t| �d kr�tjtjd t t| ��d �}�n�t || �r�tjtj g d�}�n�tjtj g d�}�n�t| tj tj!f�r�| s�dS t || �r�tjtj"dg d�}�nmtjtj#g d�}�nct| tj$��r | �sdS tjt%g d�}�nNt| tj&��r tjt'dd d�}�n=t| tj(��r.tjt'dd d�}�n,t| tj)��r?tjt'dd d�}�nt| tj*��r]|�rStjt'd d d�}�ntjtj*d| d�}n�t| tj+��r�t| �j�,� }|dk�rytjtj g d�}n�tjt'|d d�}n�t| tj-��r�tjtj.d d�}n�t| tj��r�| j/du�r�||||||||g}t | j/j | j d �0| j�g|�R � S tjtjdd�}n�t| tj1��r�| j/du�r�||||||||g}t | j/j | j d �0| j�g|�R � S tjtj1d d�}n`t| tj2��r| j�sd}nRt| tj3��rtjtj g d�}nBt| �dk�r,| �s,tjtj*d | d�}n.t| tj4��r@t5| j6�}t�tj7|�}nt| �dk�rPtjtj g d�}n t�tj7| j8�}|}|du �radS t9| ||||�:� d�|| < | j�r||| �| || j� d}| D ]O}d|jv �r�|jd �;|d� t ||||||||d�}|du�r�d|jv �r�||jd< �q�d|jv �r�||jd |< |d 7 }�q�d|jv �r�|jd |= �q�|�r�d|jv �r�t|jd �dk�s�d|jv �r�|jd du �r�t�tj7| �}| |v �rd || _<| |v �r5|| j=�r5|| j<�r5|�>| � |du�r5|j| jd }dt|�� �}tjtj||d�}|S ) a� Recursively converts a PyParsing Element to a railroad Element :param lookup: The shared converter state that keeps track of useful things :param index: The index of this element within the parent :param parent: The parent of this element in the output tree :param vertical: Controls at what point we make a list of elements vertical. If this is an integer (the default), it sets the threshold of the number of items before we go vertical. If True, always go vertical, if False, never do so :param name_hint: If provided, this will override the generated name :param show_results_names: bool flag indicating whether to add annotations for results names :param show_groups: bool flag indicating whether to show groups using bounding box :param show_hidden: bool flag indicating whether to show elements that are typically hidden :returns: The converted version of the input element, but as a Partial that hasn't yet been constructed r N)r� r� r� r) r� r� r� r� )r' r� r� r' c s s � | ] }|j |jfV qd S r+ )r' r� r� r r r r� Y s � z&_to_diagram_element.<locals>.<genexpr>r � r )r7 �repeat)r@ �NOT)r8 r7 � LOOKAHEAD� LOOKBEHINDrI �tokenconverterr6 )r ..)r} r� r� r� r� r@ )r� r� r� r) r� r� r� r7 T)?r� r� �typer- r� r� r{ r �Forward�Locatedr� �exprr� re r' r� r rJ rT r9 r� r^ rO �show_in_diagramr� r; r� r< r r� �Stack�Sequence�Or� MatchFirstr: �HorizontalChoice�Eachr4 �NotAnyrF � FollowedBy� PrecededByr� �TokenConverterr �Opt�Optional� not_ender�set_name� ZeroOrMore�Emptyr� r! r% �pattern�Terminal� defaultNamer� r� �insertr� r� r� )r} r� r� r� r) r� r� r� r� r� r' r� r� �propagated_name� looked_upr� r� rb r8 rM �collapsed_patt�terminal�ir� r7 r r r r� � sb �� � � & � � � �� � �� � � � � " �r� )r r r r )r r r r )F)r^ r_ r r )rq rR r r3 )Nr| FFF)r} r~ r r� r� r( r� r� r� r� r� r� r r_ )r� r( r� r� r r� )r} r~ r r� )r� r� r� r� ))� __future__r � itertoolsr9 r � dataclasses�typingr r r r �jinja2r ro r rW r �jinja2_template_sourcerl r �countr r r% � dataclassr& r3 r� r4 rF rJ rp rt r� r� r� r� r� r� r� r� r r r r �<module> s^ $ * � > 4 U / �PK )��Z��p�`i `i diagram/__init__.pynu �[��� # mypy: ignore-errors from __future__ import annotations import itertools import railroad import pyparsing import dataclasses import typing from typing import ( Generic, TypeVar, Callable, Iterable, ) from jinja2 import Template from io import StringIO import inspect import re jinja2_template_source = """\ {% if not embed %} <!DOCTYPE html> <html> <head> {% endif %} {% if not head %} <style> .railroad-heading { font-family: monospace; } </style> {% else %} {{ head | safe }} {% endif %} {% if not embed %} </head> <body> {% endif %} <meta charset="UTF-8"/> {{ body | safe }} {% for diagram in diagrams %} <div class="railroad-group"> <h1 class="railroad-heading" id="{{ diagram.bookmark }}">{{ diagram.title }}</h1> <div class="railroad-description">{{ diagram.text }}</div> <div class="railroad-svg"> {{ diagram.svg }} </div> </div> {% endfor %} {% if not embed %} </body> </html> {% endif %} """ template = Template(jinja2_template_source) _bookmark_lookup = {} _bookmark_ids = itertools.count(start=1) def _make_bookmark(s: str) -> str: """ Converts a string into a valid HTML bookmark (ID or anchor name). """ if s in _bookmark_lookup: return _bookmark_lookup[s] # Replace invalid characters with hyphens and ensure only valid characters bookmark = re.sub(r'[^a-zA-Z0-9-]+', '-', s) # Ensure it starts with a letter by adding 'z' if necessary if not bookmark[:1].isalpha(): bookmark = f"z{bookmark}" # Convert to lowercase and strip hyphens bookmark = bookmark.lower().strip('-') _bookmark_lookup[s] = bookmark = f"{bookmark}-{next(_bookmark_ids):04d}" return bookmark def _collapse_verbose_regex(regex_str: str) -> str: if "\n" not in regex_str: return regex_str collapsed = pyparsing.Regex(r"#.*$").suppress().transform_string(regex_str) collapsed = re.sub(r"\s*\n\s*", "", collapsed) return collapsed @dataclasses.dataclass class NamedDiagram: """ A simple structure for associating a name with a railroad diagram """ name: str index: int diagram: railroad.DiagramItem = None @property def bookmark(self): bookmark = _make_bookmark(self.name) return bookmark T = TypeVar("T") class EachItem(railroad.Group): """ Custom railroad item to compose a: - Group containing a - OneOrMore containing a - Choice of the elements in the Each with the group label indicating that all must be matched """ all_label = "[ALL]" def __init__(self, *items) -> None: choice_item = railroad.Choice(len(items) - 1, *items) one_or_more_item = railroad.OneOrMore(item=choice_item) super().__init__(one_or_more_item, label=self.all_label) class AnnotatedItem(railroad.Group): """ Simple subclass of Group that creates an annotation label """ def __init__(self, label: str, item) -> None: super().__init__(item=item, label=f"[{label}]" if label else "") class EditablePartial(Generic[T]): """ Acts like a functools.partial, but can be edited. In other words, it represents a type that hasn't yet been constructed. """ # We need this here because the railroad constructors actually transform the data, so can't be called until the # entire tree is assembled def __init__(self, func: Callable[..., T], args: list, kwargs: dict) -> None: self.func = func self.args = args self.kwargs = kwargs @classmethod def from_call(cls, func: Callable[..., T], *args, **kwargs) -> EditablePartial[T]: """ If you call this function in the same way that you would call the constructor, it will store the arguments as you expect. For example EditablePartial.from_call(Fraction, 1, 3)() == Fraction(1, 3) """ return EditablePartial(func=func, args=list(args), kwargs=kwargs) @property def name(self): return self.kwargs["name"] def __call__(self) -> T: """ Evaluate the partial and return the result """ args = self.args.copy() kwargs = self.kwargs.copy() # This is a helpful hack to allow you to specify varargs parameters (e.g. *args) as keyword args (e.g. # args=['list', 'of', 'things']) arg_spec = inspect.getfullargspec(self.func) if arg_spec.varargs in self.kwargs: args += kwargs.pop(arg_spec.varargs) return self.func(*args, **kwargs) def railroad_to_html(diagrams: list[NamedDiagram], embed=False, **kwargs) -> str: """ Given a list of NamedDiagram, produce a single HTML string that visualises those diagrams :params kwargs: kwargs to be passed in to the template """ data = [] for diagram in diagrams: if diagram.diagram is None: continue io = StringIO() try: css = kwargs.get("css") diagram.diagram.writeStandalone(io.write, css=css) except AttributeError: diagram.diagram.writeSvg(io.write) title = diagram.name if diagram.index == 0: title += " (root)" data.append( { "title": title, "text": "", "svg": io.getvalue(), "bookmark": diagram.bookmark } ) return template.render(diagrams=data, embed=embed, **kwargs) def resolve_partial(partial: EditablePartial[T]) -> T: """ Recursively resolves a collection of Partials into whatever type they are """ if isinstance(partial, EditablePartial): partial.args = resolve_partial(partial.args) partial.kwargs = resolve_partial(partial.kwargs) return partial() elif isinstance(partial, list): return [resolve_partial(x) for x in partial] elif isinstance(partial, dict): return {key: resolve_partial(x) for key, x in partial.items()} else: return partial def to_railroad( element: pyparsing.ParserElement, diagram_kwargs: typing.Optional[dict] = None, vertical: int = 3, show_results_names: bool = False, show_groups: bool = False, show_hidden: bool = False, ) -> list[NamedDiagram]: """ Convert a pyparsing element tree into a list of diagrams. This is the recommended entrypoint to diagram creation if you want to access the Railroad tree before it is converted to HTML :param element: base element of the parser being diagrammed :param diagram_kwargs: kwargs to pass to the Diagram() constructor :param vertical: (optional) - int - limit at which number of alternatives should be shown vertically instead of horizontally :param show_results_names - bool to indicate whether results name annotations should be included in the diagram :param show_groups - bool to indicate whether groups should be highlighted with an unlabeled surrounding box :param show_hidden - bool to indicate whether internal elements that are typically hidden should be shown """ # Convert the whole tree underneath the root lookup = ConverterState(diagram_kwargs=diagram_kwargs or {}) _to_diagram_element( element, lookup=lookup, parent=None, vertical=vertical, show_results_names=show_results_names, show_groups=show_groups, show_hidden=show_hidden, ) root_id = id(element) # Convert the root if it hasn't been already if root_id in lookup: if not element.customName: lookup[root_id].name = "" lookup[root_id].mark_for_extraction(root_id, lookup, force=True) # Now that we're finished, we can convert from intermediate structures into Railroad elements diags = list(lookup.diagrams.values()) if len(diags) > 1: # collapse out duplicate diags with the same name seen = set() deduped_diags = [] for d in diags: # don't extract SkipTo elements, they are uninformative as subdiagrams if d.name == "...": continue if d.name is not None and d.name not in seen: seen.add(d.name) deduped_diags.append(d) resolved = [resolve_partial(partial) for partial in deduped_diags] else: # special case - if just one diagram, always display it, even if # it has no name resolved = [resolve_partial(partial) for partial in diags] return sorted(resolved, key=lambda diag: diag.index) def _should_vertical( specification: int, exprs: Iterable[pyparsing.ParserElement] ) -> bool: """ Returns true if we should return a vertical list of elements """ if specification is None: return False else: return len(_visible_exprs(exprs)) >= specification @dataclasses.dataclass class ElementState: """ State recorded for an individual pyparsing Element """ #: The pyparsing element that this represents element: pyparsing.ParserElement #: The output Railroad element in an unconverted state converted: EditablePartial #: The parent Railroad element, which we store so that we can extract this if it's duplicated parent: EditablePartial #: The order in which we found this element, used for sorting diagrams if this is extracted into a diagram number: int #: The name of the element name: str = None #: The index of this inside its parent parent_index: typing.Optional[int] = None #: If true, we should extract this out into a subdiagram extract: bool = False #: If true, all of this element's children have been filled out complete: bool = False def mark_for_extraction( self, el_id: int, state: ConverterState, name: str = None, force: bool = False ): """ Called when this instance has been seen twice, and thus should eventually be extracted into a sub-diagram :param el_id: id of the element :param state: element/diagram state tracker :param name: name to use for this element's text :param force: If true, force extraction now, regardless of the state of this. Only useful for extracting the root element when we know we're finished """ self.extract = True # Set the name if not self.name: if name: # Allow forcing a custom name self.name = name elif self.element.customName: self.name = self.element.customName else: self.name = "" # Just because this is marked for extraction doesn't mean we can do it yet. We may have to wait for children # to be added # Also, if this is just a string literal etc, don't bother extracting it if force or (self.complete and _worth_extracting(self.element)): state.extract_into_diagram(el_id) class ConverterState: """ Stores some state that persists between recursions into the element tree """ def __init__(self, diagram_kwargs: typing.Optional[dict] = None) -> None: #: A dictionary mapping ParserElements to state relating to them self._element_diagram_states: dict[int, ElementState] = {} #: A dictionary mapping ParserElement IDs to subdiagrams generated from them self.diagrams: dict[int, EditablePartial[NamedDiagram]] = {} #: The index of the next unnamed element self.unnamed_index: int = 1 #: The index of the next element. This is used for sorting self.index: int = 0 #: Shared kwargs that are used to customize the construction of diagrams self.diagram_kwargs: dict = diagram_kwargs or {} self.extracted_diagram_names: set[str] = set() def __setitem__(self, key: int, value: ElementState): self._element_diagram_states[key] = value def __getitem__(self, key: int) -> ElementState: return self._element_diagram_states[key] def __delitem__(self, key: int): del self._element_diagram_states[key] def __contains__(self, key: int): return key in self._element_diagram_states def get(self, key, default=None): try: return self[key] except KeyError: return default def generate_unnamed(self) -> int: """ Generate a number used in the name of an otherwise unnamed diagram """ self.unnamed_index += 1 return self.unnamed_index def generate_index(self) -> int: """ Generate a number used to index a diagram """ self.index += 1 return self.index def extract_into_diagram(self, el_id: int): """ Used when we encounter the same token twice in the same tree. When this happens, we replace all instances of that token with a terminal, and create a new subdiagram for the token """ position = self[el_id] # Replace the original definition of this element with a regular block if position.parent: href = f"#{_make_bookmark(position.name)}" ret = EditablePartial.from_call(railroad.NonTerminal, text=position.name, href=href) if "item" in position.parent.kwargs: position.parent.kwargs["item"] = ret elif "items" in position.parent.kwargs: position.parent.kwargs["items"][position.parent_index] = ret # If the element we're extracting is a group, skip to its content but keep the title if position.converted.func == railroad.Group: content = position.converted.kwargs["item"] else: content = position.converted self.diagrams[el_id] = EditablePartial.from_call( NamedDiagram, name=position.name, diagram=EditablePartial.from_call( railroad.Diagram, content, **self.diagram_kwargs ), index=position.number, ) del self[el_id] def _worth_extracting(element: pyparsing.ParserElement) -> bool: """ Returns true if this element is worth having its own sub-diagram. Simply, if any of its children themselves have children, then its complex enough to extract """ children = element.recurse() return any(child.recurse() for child in children) def _apply_diagram_item_enhancements(fn): """ decorator to ensure enhancements to a diagram item (such as results name annotations) get applied on return from _to_diagram_element (we do this since there are several returns in _to_diagram_element) """ def _inner( element: pyparsing.ParserElement, parent: typing.Optional[EditablePartial], lookup: ConverterState = None, vertical: int = None, index: int = 0, name_hint: str = None, show_results_names: bool = False, show_groups: bool = False, show_hidden: bool = False, ) -> typing.Optional[EditablePartial]: ret = fn( element, parent, lookup, vertical, index, name_hint, show_results_names, show_groups, show_hidden, ) # apply annotation for results name, if present if show_results_names and ret is not None: element_results_name = element.resultsName if element_results_name: # add "*" to indicate if this is a "list all results" name modal_tag = "" if element.modalResults else "*" ret = EditablePartial.from_call( railroad.Group, item=ret, label=f"{repr(element_results_name)}{modal_tag}", ) return ret return _inner def _visible_exprs(exprs: Iterable[pyparsing.ParserElement]): non_diagramming_exprs = ( pyparsing.ParseElementEnhance, pyparsing.PositionToken, pyparsing.And._ErrorStop, ) return [ e for e in exprs if not isinstance(e, non_diagramming_exprs) ] @_apply_diagram_item_enhancements def _to_diagram_element( element: pyparsing.ParserElement, parent: typing.Optional[EditablePartial], lookup: ConverterState = None, vertical: int = None, index: int = 0, name_hint: str = None, show_results_names: bool = False, show_groups: bool = False, show_hidden: bool = False, ) -> typing.Optional[EditablePartial]: """ Recursively converts a PyParsing Element to a railroad Element :param lookup: The shared converter state that keeps track of useful things :param index: The index of this element within the parent :param parent: The parent of this element in the output tree :param vertical: Controls at what point we make a list of elements vertical. If this is an integer (the default), it sets the threshold of the number of items before we go vertical. If True, always go vertical, if False, never do so :param name_hint: If provided, this will override the generated name :param show_results_names: bool flag indicating whether to add annotations for results names :param show_groups: bool flag indicating whether to show groups using bounding box :param show_hidden: bool flag indicating whether to show elements that are typically hidden :returns: The converted version of the input element, but as a Partial that hasn't yet been constructed """ exprs = element.recurse() name = name_hint or element.customName or type(element).__name__ # Python's id() is used to provide a unique identifier for elements el_id = id(element) element_results_name = element.resultsName # Here we basically bypass processing certain wrapper elements if they contribute nothing to the diagram if not element.customName: if isinstance( element, ( # pyparsing.TokenConverter, pyparsing.Forward, pyparsing.Located, ), ): # However, if this element has a useful custom name, and its child does not, we can pass it on to the child if exprs: if not exprs[0].customName: propagated_name = name else: propagated_name = None return _to_diagram_element( element.expr, parent=parent, lookup=lookup, vertical=vertical, index=index, name_hint=propagated_name, show_results_names=show_results_names, show_groups=show_groups, show_hidden=show_hidden, ) # If the element isn't worth extracting, we always treat it as the first time we say it if _worth_extracting(element): looked_up = lookup.get(el_id) if looked_up and looked_up.name is not None: # If we've seen this element exactly once before, we are only just now finding out that it's a duplicate, # so we have to extract it into a new diagram. looked_up.mark_for_extraction(el_id, lookup, name=name_hint) href = f"#{_make_bookmark(looked_up.name)}" ret = EditablePartial.from_call(railroad.NonTerminal, text=looked_up.name, href=href) return ret elif el_id in lookup.diagrams: # If we have seen the element at least twice before, and have already extracted it into a subdiagram, we # just put in a marker element that refers to the sub-diagram text = lookup.diagrams[el_id].kwargs["name"] ret = EditablePartial.from_call( railroad.NonTerminal, text=text, href=f"#{_make_bookmark(text)}" ) return ret # Recursively convert child elements # Here we find the most relevant Railroad element for matching pyparsing Element # We use ``items=[]`` here to hold the place for where the child elements will go once created # see if this element is normally hidden, and whether hidden elements are desired # if not, just return None if not element.show_in_diagram and not show_hidden: return None if isinstance(element, pyparsing.And): # detect And's created with ``expr*N`` notation - for these use a OneOrMore with a repeat # (all will have the same name, and resultsName) if not exprs: return None if len(set((e.name, e.resultsName) for e in exprs)) == 1 and len(exprs) > 2: ret = EditablePartial.from_call( railroad.OneOrMore, item="", repeat=str(len(exprs)) ) elif _should_vertical(vertical, exprs): ret = EditablePartial.from_call(railroad.Stack, items=[]) else: ret = EditablePartial.from_call(railroad.Sequence, items=[]) elif isinstance(element, (pyparsing.Or, pyparsing.MatchFirst)): if not exprs: return None if _should_vertical(vertical, exprs): ret = EditablePartial.from_call(railroad.Choice, 0, items=[]) else: ret = EditablePartial.from_call(railroad.HorizontalChoice, items=[]) elif isinstance(element, pyparsing.Each): if not exprs: return None ret = EditablePartial.from_call(EachItem, items=[]) elif isinstance(element, pyparsing.NotAny): ret = EditablePartial.from_call(AnnotatedItem, label="NOT", item="") elif isinstance(element, pyparsing.FollowedBy): ret = EditablePartial.from_call(AnnotatedItem, label="LOOKAHEAD", item="") elif isinstance(element, pyparsing.PrecededBy): ret = EditablePartial.from_call(AnnotatedItem, label="LOOKBEHIND", item="") elif isinstance(element, pyparsing.Group): if show_groups: ret = EditablePartial.from_call(AnnotatedItem, label="", item="") else: ret = EditablePartial.from_call( railroad.Group, item=None, label=element_results_name ) elif isinstance(element, pyparsing.TokenConverter): label = type(element).__name__.lower() if label == "tokenconverter": ret = EditablePartial.from_call(railroad.Sequence, items=[]) else: ret = EditablePartial.from_call(AnnotatedItem, label=label, item="") elif isinstance(element, pyparsing.Opt): ret = EditablePartial.from_call(railroad.Optional, item="") elif isinstance(element, pyparsing.OneOrMore): if element.not_ender is not None: args = [ parent, lookup, vertical, index, name_hint, show_results_names, show_groups, show_hidden, ] return _to_diagram_element( (~element.not_ender.expr + element.expr)[1, ...].set_name(element.name), *args, ) ret = EditablePartial.from_call(railroad.OneOrMore, item=None) elif isinstance(element, pyparsing.ZeroOrMore): if element.not_ender is not None: args = [ parent, lookup, vertical, index, name_hint, show_results_names, show_groups, show_hidden, ] return _to_diagram_element( (~element.not_ender.expr + element.expr)[...].set_name(element.name), *args, ) ret = EditablePartial.from_call(railroad.ZeroOrMore, item="") elif isinstance(element, pyparsing.Empty) and not element.customName: # Skip unnamed "Empty" elements ret = None elif isinstance(element, pyparsing.ParseElementEnhance): ret = EditablePartial.from_call(railroad.Sequence, items=[]) elif len(exprs) > 0 and not element_results_name: ret = EditablePartial.from_call(railroad.Group, item="", label=name) elif isinstance(element, pyparsing.Regex): collapsed_patt = _collapse_verbose_regex(element.pattern) ret = EditablePartial.from_call(railroad.Terminal, collapsed_patt) elif len(exprs) > 0: ret = EditablePartial.from_call(railroad.Sequence, items=[]) else: terminal = EditablePartial.from_call(railroad.Terminal, element.defaultName) ret = terminal if ret is None: return # Indicate this element's position in the tree so we can extract it if necessary lookup[el_id] = ElementState( element=element, converted=ret, parent=parent, parent_index=index, number=lookup.generate_index(), ) if element.customName: lookup[el_id].mark_for_extraction(el_id, lookup, element.customName) i = 0 for expr in exprs: # Add a placeholder index in case we have to extract the child before we even add it to the parent if "items" in ret.kwargs: ret.kwargs["items"].insert(i, None) item = _to_diagram_element( expr, parent=ret, lookup=lookup, vertical=vertical, index=i, show_results_names=show_results_names, show_groups=show_groups, show_hidden=show_hidden, ) # Some elements don't need to be shown in the diagram if item is not None: if "item" in ret.kwargs: ret.kwargs["item"] = item elif "items" in ret.kwargs: # If we've already extracted the child, don't touch this index, since it's occupied by a nonterminal ret.kwargs["items"][i] = item i += 1 elif "items" in ret.kwargs: # If we're supposed to skip this element, remove it from the parent del ret.kwargs["items"][i] # If all this items children are none, skip this item if ret and ( ("items" in ret.kwargs and len(ret.kwargs["items"]) == 0) or ("item" in ret.kwargs and ret.kwargs["item"] is None) ): ret = EditablePartial.from_call(railroad.Terminal, name) # Mark this element as "complete", ie it has all of its children if el_id in lookup: lookup[el_id].complete = True if el_id in lookup and lookup[el_id].extract and lookup[el_id].complete: lookup.extract_into_diagram(el_id) if ret is not None: text = lookup.diagrams[el_id].kwargs["name"] href = f"#{_make_bookmark(text)}" ret = EditablePartial.from_call( railroad.NonTerminal, text=text, href=href ) return ret PK )��Z�� �i5 i5 common.pynu �[��� # common.py from .core import * from .helpers import DelimitedList, any_open_tag, any_close_tag from datetime import datetime # some other useful expressions - using lower-case class name since we are really using this as a namespace class pyparsing_common: """Here are some common low-level expressions that may be useful in jump-starting parser development: - numeric forms (:class:`integers<integer>`, :class:`reals<real>`, :class:`scientific notation<sci_real>`) - common :class:`programming identifiers<identifier>` - network addresses (:class:`MAC<mac_address>`, :class:`IPv4<ipv4_address>`, :class:`IPv6<ipv6_address>`) - ISO8601 :class:`dates<iso8601_date>` and :class:`datetime<iso8601_datetime>` - :class:`UUID<uuid>` - :class:`comma-separated list<comma_separated_list>` - :class:`url` Parse actions: - :class:`convert_to_integer` - :class:`convert_to_float` - :class:`convert_to_date` - :class:`convert_to_datetime` - :class:`strip_html_tags` - :class:`upcase_tokens` - :class:`downcase_tokens` Example:: pyparsing_common.number.run_tests(''' # any int or real number, returned as the appropriate type 100 -100 +100 3.14159 6.02e23 1e-12 ''') pyparsing_common.fnumber.run_tests(''' # any int or real number, returned as float 100 -100 +100 3.14159 6.02e23 1e-12 ''') pyparsing_common.hex_integer.run_tests(''' # hex numbers 100 FF ''') pyparsing_common.fraction.run_tests(''' # fractions 1/2 -3/4 ''') pyparsing_common.mixed_integer.run_tests(''' # mixed fractions 1 1/2 -3/4 1-3/4 ''') import uuid pyparsing_common.uuid.set_parse_action(token_map(uuid.UUID)) pyparsing_common.uuid.run_tests(''' # uuid 12345678-1234-5678-1234-567812345678 ''') prints:: # any int or real number, returned as the appropriate type 100 [100] -100 [-100] +100 [100] 3.14159 [3.14159] 6.02e23 [6.02e+23] 1e-12 [1e-12] # any int or real number, returned as float 100 [100.0] -100 [-100.0] +100 [100.0] 3.14159 [3.14159] 6.02e23 [6.02e+23] 1e-12 [1e-12] # hex numbers 100 [256] FF [255] # fractions 1/2 [0.5] -3/4 [-0.75] # mixed fractions 1 [1] 1/2 [0.5] -3/4 [-0.75] 1-3/4 [1.75] # uuid 12345678-1234-5678-1234-567812345678 [UUID('12345678-1234-5678-1234-567812345678')] """ convert_to_integer = token_map(int) """ Parse action for converting parsed integers to Python int """ convert_to_float = token_map(float) """ Parse action for converting parsed numbers to Python float """ integer = Word(nums).set_name("integer").set_parse_action(convert_to_integer) """expression that parses an unsigned integer, returns an int""" hex_integer = ( Word(hexnums).set_name("hex integer").set_parse_action(token_map(int, 16)) ) """expression that parses a hexadecimal integer, returns an int""" signed_integer = ( Regex(r"[+-]?\d+") .set_name("signed integer") .set_parse_action(convert_to_integer) ) """expression that parses an integer with optional leading sign, returns an int""" fraction = ( signed_integer().set_parse_action(convert_to_float) + "/" + signed_integer().set_parse_action(convert_to_float) ).set_name("fraction") """fractional expression of an integer divided by an integer, returns a float""" fraction.add_parse_action(lambda tt: tt[0] / tt[-1]) mixed_integer = ( fraction | signed_integer + Opt(Opt("-").suppress() + fraction) ).set_name("fraction or mixed integer-fraction") """mixed integer of the form 'integer - fraction', with optional leading integer, returns float""" mixed_integer.add_parse_action(sum) real = ( Regex(r"[+-]?(?:\d+\.\d*|\.\d+)") .set_name("real number") .set_parse_action(convert_to_float) ) """expression that parses a floating point number and returns a float""" sci_real = ( Regex(r"[+-]?(?:\d+(?:[eE][+-]?\d+)|(?:\d+\.\d*|\.\d+)(?:[eE][+-]?\d+)?)") .set_name("real number with scientific notation") .set_parse_action(convert_to_float) ) """expression that parses a floating point number with optional scientific notation and returns a float""" # streamlining this expression makes the docs nicer-looking number = (sci_real | real | signed_integer).set_name("number").streamline() """any numeric expression, returns the corresponding Python type""" fnumber = ( Regex(r"[+-]?\d+\.?\d*(?:[eE][+-]?\d+)?") .set_name("fnumber") .set_parse_action(convert_to_float) ) """any int or real number, returned as float""" ieee_float = ( Regex(r"(?i:[+-]?(?:(?:\d+\.?\d*(?:e[+-]?\d+)?)|nan|inf(?:inity)?))") .set_name("ieee_float") .set_parse_action(convert_to_float) ) """any floating-point literal (int, real number, infinity, or NaN), returned as float""" identifier = Word(identchars, identbodychars).set_name("identifier") """typical code identifier (leading alpha or '_', followed by 0 or more alphas, nums, or '_')""" ipv4_address = Regex( r"(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})(\.(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})){3}" ).set_name("IPv4 address") "IPv4 address (``0.0.0.0 - 255.255.255.255``)" _ipv6_part = Regex(r"[0-9a-fA-F]{1,4}").set_name("hex_integer") _full_ipv6_address = (_ipv6_part + (":" + _ipv6_part) * 7).set_name( "full IPv6 address" ) _short_ipv6_address = ( Opt(_ipv6_part + (":" + _ipv6_part) * (0, 6)) + "::" + Opt(_ipv6_part + (":" + _ipv6_part) * (0, 6)) ).set_name("short IPv6 address") _short_ipv6_address.add_condition( lambda t: sum(1 for tt in t if pyparsing_common._ipv6_part.matches(tt)) < 8 ) _mixed_ipv6_address = ("::ffff:" + ipv4_address).set_name("mixed IPv6 address") ipv6_address = Combine( (_full_ipv6_address | _mixed_ipv6_address | _short_ipv6_address).set_name( "IPv6 address" ) ).set_name("IPv6 address") "IPv6 address (long, short, or mixed form)" mac_address = Regex( r"[0-9a-fA-F]{2}([:.-])[0-9a-fA-F]{2}(?:\1[0-9a-fA-F]{2}){4}" ).set_name("MAC address") "MAC address xx:xx:xx:xx:xx (may also have '-' or '.' delimiters)" @staticmethod def convert_to_date(fmt: str = "%Y-%m-%d"): """ Helper to create a parse action for converting parsed date string to Python datetime.date Params - - fmt - format to be passed to datetime.strptime (default= ``"%Y-%m-%d"``) Example:: date_expr = pyparsing_common.iso8601_date.copy() date_expr.set_parse_action(pyparsing_common.convert_to_date()) print(date_expr.parse_string("1999-12-31")) prints:: [datetime.date(1999, 12, 31)] """ def cvt_fn(ss, ll, tt): try: return datetime.strptime(tt[0], fmt).date() except ValueError as ve: raise ParseException(ss, ll, str(ve)) return cvt_fn @staticmethod def convert_to_datetime(fmt: str = "%Y-%m-%dT%H:%M:%S.%f"): """Helper to create a parse action for converting parsed datetime string to Python datetime.datetime Params - - fmt - format to be passed to datetime.strptime (default= ``"%Y-%m-%dT%H:%M:%S.%f"``) Example:: dt_expr = pyparsing_common.iso8601_datetime.copy() dt_expr.set_parse_action(pyparsing_common.convert_to_datetime()) print(dt_expr.parse_string("1999-12-31T23:59:59.999")) prints:: [datetime.datetime(1999, 12, 31, 23, 59, 59, 999000)] """ def cvt_fn(s, l, t): try: return datetime.strptime(t[0], fmt) except ValueError as ve: raise ParseException(s, l, str(ve)) return cvt_fn iso8601_date = Regex( r"(?P<year>\d{4})(?:-(?P<month>\d\d)(?:-(?P<day>\d\d))?)?" ).set_name("ISO8601 date") "ISO8601 date (``yyyy-mm-dd``)" iso8601_datetime = Regex( r"(?P<year>\d{4})-(?P<month>\d\d)-(?P<day>\d\d)[T ](?P<hour>\d\d):(?P<minute>\d\d)(:(?P<second>\d\d(\.\d*)?)?)?(?P<tz>Z|[+-]\d\d:?\d\d)?" ).set_name("ISO8601 datetime") "ISO8601 datetime (``yyyy-mm-ddThh:mm:ss.s(Z|+-00:00)``) - trailing seconds, milliseconds, and timezone optional; accepts separating ``'T'`` or ``' '``" uuid = Regex(r"[0-9a-fA-F]{8}(-[0-9a-fA-F]{4}){3}-[0-9a-fA-F]{12}").set_name("UUID") "UUID (``xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx``)" _html_stripper = any_open_tag.suppress() | any_close_tag.suppress() @staticmethod def strip_html_tags(s: str, l: int, tokens: ParseResults): """Parse action to remove HTML tags from web page HTML source Example:: # strip HTML links from normal text text = '<td>More info at the <a href="https://github.com/pyparsing/pyparsing/wiki">pyparsing</a> wiki page</td>' td, td_end = make_html_tags("TD") table_text = td + SkipTo(td_end).set_parse_action(pyparsing_common.strip_html_tags)("body") + td_end print(table_text.parse_string(text).body) Prints:: More info at the pyparsing wiki page """ return pyparsing_common._html_stripper.transform_string(tokens[0]) _commasepitem = ( Combine( OneOrMore( ~Literal(",") + ~LineEnd() + Word(printables, exclude_chars=",") + Opt(White(" \t") + ~FollowedBy(LineEnd() | ",")) ) ) .streamline() .set_name("commaItem") ) comma_separated_list = DelimitedList( Opt(quoted_string.copy() | _commasepitem, default="") ).set_name("comma separated list") """Predefined expression of 1 or more printable words or quoted strings, separated by commas.""" upcase_tokens = staticmethod(token_map(lambda t: t.upper())) """Parse action to convert tokens to upper case.""" downcase_tokens = staticmethod(token_map(lambda t: t.lower())) """Parse action to convert tokens to lower case.""" # fmt: off url = Regex( # https://mathiasbynens.be/demo/url-regex # https://gist.github.com/dperini/729294 r"(?P<url>" + # protocol identifier (optional) # short syntax // still required r"(?:(?:(?P<scheme>https?|ftp):)?\/\/)" + # user:pass BasicAuth (optional) r"(?:(?P<auth>\S+(?::\S*)?)@)?" + r"(?P<host>" + # IP address exclusion # private & local networks r"(?!(?:10|127)(?:\.\d{1,3}){3})" + r"(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})" + r"(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})" + # IP address dotted notation octets # excludes loopback network 0.0.0.0 # excludes reserved space >= 224.0.0.0 # excludes network & broadcast addresses # (first & last IP address of each class) r"(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])" + r"(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}" + r"(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))" + r"|" + # host & domain names, may end with dot # can be replaced by a shortest alternative # (?![-_])(?:[-\w\u00a1-\uffff]{0,63}[^-_]\.)+ r"(?:" + r"(?:" + r"[a-z0-9\u00a1-\uffff]" + r"[a-z0-9\u00a1-\uffff_-]{0,62}" + r")?" + r"[a-z0-9\u00a1-\uffff]\." + r")+" + # TLD identifier name, may end with dot r"(?:[a-z\u00a1-\uffff]{2,}\.?)" + r")" + # port number (optional) r"(:(?P<port>\d{2,5}))?" + # resource path (optional) r"(?P<path>\/[^?# ]*)?" + # query string (optional) r"(\?(?P<query>[^#]*))?" + # fragment (optional) r"(#(?P<fragment>\S*))?" + r")" ).set_name("url") """URL (http/https/ftp scheme)""" # fmt: on # pre-PEP8 compatibility names # fmt: off convertToInteger = staticmethod(replaced_by_pep8("convertToInteger", convert_to_integer)) convertToFloat = staticmethod(replaced_by_pep8("convertToFloat", convert_to_float)) convertToDate = staticmethod(replaced_by_pep8("convertToDate", convert_to_date)) convertToDatetime = staticmethod(replaced_by_pep8("convertToDatetime", convert_to_datetime)) stripHTMLTags = staticmethod(replaced_by_pep8("stripHTMLTags", strip_html_tags)) upcaseTokens = staticmethod(replaced_by_pep8("upcaseTokens", upcase_tokens)) downcaseTokens = staticmethod(replaced_by_pep8("downcaseTokens", downcase_tokens)) # fmt: on _builtin_exprs = [ v for v in vars(pyparsing_common).values() if isinstance(v, ParserElement) ] PK )��Z���'�f �f results.pynu �[��� # results.py from __future__ import annotations import collections from collections.abc import ( MutableMapping, Mapping, MutableSequence, Iterator, Iterable, ) import pprint from typing import Any from .util import replaced_by_pep8 str_type: tuple[type, ...] = (str, bytes) _generator_type = type((_ for _ in ())) class _ParseResultsWithOffset: tup: tuple[ParseResults, int] __slots__ = ["tup"] def __init__(self, p1: ParseResults, p2: int) -> None: self.tup: tuple[ParseResults, int] = (p1, p2) def __getitem__(self, i): return self.tup[i] def __getstate__(self): return self.tup def __setstate__(self, *args): self.tup = args[0] class ParseResults: """Structured parse results, to provide multiple means of access to the parsed data: - as a list (``len(results)``) - by list index (``results[0], results[1]``, etc.) - by attribute (``results.<results_name>`` - see :class:`ParserElement.set_results_name`) Example:: integer = Word(nums) date_str = (integer.set_results_name("year") + '/' + integer.set_results_name("month") + '/' + integer.set_results_name("day")) # equivalent form: # date_str = (integer("year") + '/' # + integer("month") + '/' # + integer("day")) # parse_string returns a ParseResults object result = date_str.parse_string("1999/12/31") def test(s, fn=repr): print(f"{s} -> {fn(eval(s))}") test("list(result)") test("result[0]") test("result['month']") test("result.day") test("'month' in result") test("'minutes' in result") test("result.dump()", str) prints:: list(result) -> ['1999', '/', '12', '/', '31'] result[0] -> '1999' result['month'] -> '12' result.day -> '31' 'month' in result -> True 'minutes' in result -> False result.dump() -> ['1999', '/', '12', '/', '31'] - day: '31' - month: '12' - year: '1999' """ _null_values: tuple[Any, ...] = (None, [], ()) _name: str _parent: ParseResults _all_names: set[str] _modal: bool _toklist: list[Any] _tokdict: dict[str, Any] __slots__ = ( "_name", "_parent", "_all_names", "_modal", "_toklist", "_tokdict", ) class List(list): """ Simple wrapper class to distinguish parsed list results that should be preserved as actual Python lists, instead of being converted to :class:`ParseResults`:: LBRACK, RBRACK = map(pp.Suppress, "[]") element = pp.Forward() item = ppc.integer element_list = LBRACK + pp.DelimitedList(element) + RBRACK # add parse actions to convert from ParseResults to actual Python collection types def as_python_list(t): return pp.ParseResults.List(t.as_list()) element_list.add_parse_action(as_python_list) element <<= item | element_list element.run_tests(''' 100 [2,3,4] [[2, 1],3,4] [(2, 1),3,4] (2,3,4) ''', post_parse=lambda s, r: (r[0], type(r[0]))) prints:: 100 (100, <class 'int'>) [2,3,4] ([2, 3, 4], <class 'list'>) [[2, 1],3,4] ([[2, 1], 3, 4], <class 'list'>) (Used internally by :class:`Group` when `aslist=True`.) """ def __new__(cls, contained=None): if contained is None: contained = [] if not isinstance(contained, list): raise TypeError( f"{cls.__name__} may only be constructed with a list, not {type(contained).__name__}" ) return list.__new__(cls) def __new__(cls, toklist=None, name=None, **kwargs): if isinstance(toklist, ParseResults): return toklist self = object.__new__(cls) self._name = None self._parent = None self._all_names = set() if toklist is None: self._toklist = [] elif isinstance(toklist, (list, _generator_type)): self._toklist = ( [toklist[:]] if isinstance(toklist, ParseResults.List) else list(toklist) ) else: self._toklist = [toklist] self._tokdict = dict() return self # Performance tuning: we construct a *lot* of these, so keep this # constructor as small and fast as possible def __init__( self, toklist=None, name=None, asList=True, modal=True, isinstance=isinstance ) -> None: self._tokdict: dict[str, _ParseResultsWithOffset] self._modal = modal if name is None or name == "": return if isinstance(name, int): name = str(name) if not modal: self._all_names = {name} self._name = name if toklist in self._null_values: return if isinstance(toklist, (str_type, type)): toklist = [toklist] if asList: if isinstance(toklist, ParseResults): self[name] = _ParseResultsWithOffset(ParseResults(toklist._toklist), 0) else: self[name] = _ParseResultsWithOffset(ParseResults(toklist[0]), 0) self[name]._name = name return try: self[name] = toklist[0] except (KeyError, TypeError, IndexError): if toklist is not self: self[name] = toklist else: self._name = name def __getitem__(self, i): if isinstance(i, (int, slice)): return self._toklist[i] if i not in self._all_names: return self._tokdict[i][-1][0] return ParseResults([v[0] for v in self._tokdict[i]]) def __setitem__(self, k, v, isinstance=isinstance): if isinstance(v, _ParseResultsWithOffset): self._tokdict[k] = self._tokdict.get(k, list()) + [v] sub = v[0] elif isinstance(k, (int, slice)): self._toklist[k] = v sub = v else: self._tokdict[k] = self._tokdict.get(k, []) + [ _ParseResultsWithOffset(v, 0) ] sub = v if isinstance(sub, ParseResults): sub._parent = self def __delitem__(self, i): if not isinstance(i, (int, slice)): del self._tokdict[i] return mylen = len(self._toklist) del self._toklist[i] # convert int to slice if isinstance(i, int): if i < 0: i += mylen i = slice(i, i + 1) # get removed indices removed = list(range(*i.indices(mylen))) removed.reverse() # fixup indices in token dictionary for occurrences in self._tokdict.values(): for j in removed: for k, (value, position) in enumerate(occurrences): occurrences[k] = _ParseResultsWithOffset( value, position - (position > j) ) def __contains__(self, k) -> bool: return k in self._tokdict def __len__(self) -> int: return len(self._toklist) def __bool__(self) -> bool: return not not (self._toklist or self._tokdict) def __iter__(self) -> Iterator: return iter(self._toklist) def __reversed__(self) -> Iterator: return iter(self._toklist[::-1]) def keys(self): return iter(self._tokdict) def values(self): return (self[k] for k in self.keys()) def items(self): return ((k, self[k]) for k in self.keys()) def haskeys(self) -> bool: """ Since ``keys()`` returns an iterator, this method is helpful in bypassing code that looks for the existence of any defined results names.""" return not not self._tokdict def pop(self, *args, **kwargs): """ Removes and returns item at specified index (default= ``last``). Supports both ``list`` and ``dict`` semantics for ``pop()``. If passed no argument or an integer argument, it will use ``list`` semantics and pop tokens from the list of parsed tokens. If passed a non-integer argument (most likely a string), it will use ``dict`` semantics and pop the corresponding value from any defined results names. A second default return value argument is supported, just as in ``dict.pop()``. Example:: numlist = Word(nums)[...] print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321'] def remove_first(tokens): tokens.pop(0) numlist.add_parse_action(remove_first) print(numlist.parse_string("0 123 321")) # -> ['123', '321'] label = Word(alphas) patt = label("LABEL") + Word(nums)[1, ...] print(patt.parse_string("AAB 123 321").dump()) # Use pop() in a parse action to remove named result (note that corresponding value is not # removed from list form of results) def remove_LABEL(tokens): tokens.pop("LABEL") return tokens patt.add_parse_action(remove_LABEL) print(patt.parse_string("AAB 123 321").dump()) prints:: ['AAB', '123', '321'] - LABEL: 'AAB' ['AAB', '123', '321'] """ if not args: args = [-1] for k, v in kwargs.items(): if k == "default": args = (args[0], v) else: raise TypeError(f"pop() got an unexpected keyword argument {k!r}") if isinstance(args[0], int) or len(args) == 1 or args[0] in self: index = args[0] ret = self[index] del self[index] return ret else: defaultvalue = args[1] return defaultvalue def get(self, key, default_value=None): """ Returns named result matching the given key, or if there is no such name, then returns the given ``default_value`` or ``None`` if no ``default_value`` is specified. Similar to ``dict.get()``. Example:: integer = Word(nums) date_str = integer("year") + '/' + integer("month") + '/' + integer("day") result = date_str.parse_string("1999/12/31") print(result.get("year")) # -> '1999' print(result.get("hour", "not specified")) # -> 'not specified' print(result.get("hour")) # -> None """ if key in self: return self[key] else: return default_value def insert(self, index, ins_string): """ Inserts new element at location index in the list of parsed tokens. Similar to ``list.insert()``. Example:: numlist = Word(nums)[...] print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321'] # use a parse action to insert the parse location in the front of the parsed results def insert_locn(locn, tokens): tokens.insert(0, locn) numlist.add_parse_action(insert_locn) print(numlist.parse_string("0 123 321")) # -> [0, '0', '123', '321'] """ self._toklist.insert(index, ins_string) # fixup indices in token dictionary for occurrences in self._tokdict.values(): for k, (value, position) in enumerate(occurrences): occurrences[k] = _ParseResultsWithOffset( value, position + (position > index) ) def append(self, item): """ Add single element to end of ``ParseResults`` list of elements. Example:: numlist = Word(nums)[...] print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321'] # use a parse action to compute the sum of the parsed integers, and add it to the end def append_sum(tokens): tokens.append(sum(map(int, tokens))) numlist.add_parse_action(append_sum) print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321', 444] """ self._toklist.append(item) def extend(self, itemseq): """ Add sequence of elements to end of ``ParseResults`` list of elements. Example:: patt = Word(alphas)[1, ...] # use a parse action to append the reverse of the matched strings, to make a palindrome def make_palindrome(tokens): tokens.extend(reversed([t[::-1] for t in tokens])) return ''.join(tokens) patt.add_parse_action(make_palindrome) print(patt.parse_string("lskdj sdlkjf lksd")) # -> 'lskdjsdlkjflksddsklfjkldsjdksl' """ if isinstance(itemseq, ParseResults): self.__iadd__(itemseq) else: self._toklist.extend(itemseq) def clear(self): """ Clear all elements and results names. """ del self._toklist[:] self._tokdict.clear() def __getattr__(self, name): try: return self[name] except KeyError: if name.startswith("__"): raise AttributeError(name) return "" def __add__(self, other: ParseResults) -> ParseResults: ret = self.copy() ret += other return ret def __iadd__(self, other: ParseResults) -> ParseResults: if not other: return self if other._tokdict: offset = len(self._toklist) addoffset = lambda a: offset if a < 0 else a + offset otheritems = other._tokdict.items() otherdictitems = [ (k, _ParseResultsWithOffset(v[0], addoffset(v[1]))) for k, vlist in otheritems for v in vlist ] for k, v in otherdictitems: self[k] = v if isinstance(v[0], ParseResults): v[0]._parent = self self._toklist += other._toklist self._all_names |= other._all_names return self def __radd__(self, other) -> ParseResults: if isinstance(other, int) and other == 0: # useful for merging many ParseResults using sum() builtin return self.copy() else: # this may raise a TypeError - so be it return other + self def __repr__(self) -> str: return f"{type(self).__name__}({self._toklist!r}, {self.as_dict()})" def __str__(self) -> str: return ( "[" + ", ".join( [ str(i) if isinstance(i, ParseResults) else repr(i) for i in self._toklist ] ) + "]" ) def _asStringList(self, sep=""): out = [] for item in self._toklist: if out and sep: out.append(sep) if isinstance(item, ParseResults): out += item._asStringList() else: out.append(str(item)) return out def as_list(self, *, flatten: bool = False) -> list: """ Returns the parse results as a nested list of matching tokens, all converted to strings. If flatten is True, all the nesting levels in the returned list are collapsed. Example:: patt = Word(alphas)[1, ...] result = patt.parse_string("sldkj lsdkj sldkj") # even though the result prints in string-like form, it is actually a pyparsing ParseResults print(type(result), result) # -> <class 'pyparsing.ParseResults'> ['sldkj', 'lsdkj', 'sldkj'] # Use as_list() to create an actual list result_list = result.as_list() print(type(result_list), result_list) # -> <class 'list'> ['sldkj', 'lsdkj', 'sldkj'] """ def flattened(pr): to_visit = collections.deque([*self]) while to_visit: to_do = to_visit.popleft() if isinstance(to_do, ParseResults): to_visit.extendleft(to_do[::-1]) else: yield to_do if flatten: return [*flattened(self)] else: return [ res.as_list() if isinstance(res, ParseResults) else res for res in self._toklist ] def as_dict(self) -> dict: """ Returns the named parse results as a nested dictionary. Example:: integer = Word(nums) date_str = integer("year") + '/' + integer("month") + '/' + integer("day") result = date_str.parse_string('12/31/1999') print(type(result), repr(result)) # -> <class 'pyparsing.ParseResults'> (['12', '/', '31', '/', '1999'], {'day': [('1999', 4)], 'year': [('12', 0)], 'month': [('31', 2)]}) result_dict = result.as_dict() print(type(result_dict), repr(result_dict)) # -> <class 'dict'> {'day': '1999', 'year': '12', 'month': '31'} # even though a ParseResults supports dict-like access, sometime you just need to have a dict import json print(json.dumps(result)) # -> Exception: TypeError: ... is not JSON serializable print(json.dumps(result.as_dict())) # -> {"month": "31", "day": "1999", "year": "12"} """ def to_item(obj): if isinstance(obj, ParseResults): return obj.as_dict() if obj.haskeys() else [to_item(v) for v in obj] else: return obj return dict((k, to_item(v)) for k, v in self.items()) def copy(self) -> ParseResults: """ Returns a new shallow copy of a :class:`ParseResults` object. `ParseResults` items contained within the source are shared with the copy. Use :class:`ParseResults.deepcopy()` to create a copy with its own separate content values. """ ret = ParseResults(self._toklist) ret._tokdict = self._tokdict.copy() ret._parent = self._parent ret._all_names |= self._all_names ret._name = self._name return ret def deepcopy(self) -> ParseResults: """ Returns a new deep copy of a :class:`ParseResults` object. """ ret = self.copy() # replace values with copies if they are of known mutable types for i, obj in enumerate(self._toklist): if isinstance(obj, ParseResults): ret._toklist[i] = obj.deepcopy() elif isinstance(obj, (str, bytes)): pass elif isinstance(obj, MutableMapping): ret._toklist[i] = dest = type(obj)() for k, v in obj.items(): dest[k] = v.deepcopy() if isinstance(v, ParseResults) else v elif isinstance(obj, Iterable): ret._toklist[i] = type(obj)( v.deepcopy() if isinstance(v, ParseResults) else v for v in obj # type: ignore[call-arg] ) return ret def get_name(self) -> str | None: r""" Returns the results name for this token expression. Useful when several different expressions might match at a particular location. Example:: integer = Word(nums) ssn_expr = Regex(r"\d\d\d-\d\d-\d\d\d\d") house_number_expr = Suppress('#') + Word(nums, alphanums) user_data = (Group(house_number_expr)("house_number") | Group(ssn_expr)("ssn") | Group(integer)("age")) user_info = user_data[1, ...] result = user_info.parse_string("22 111-22-3333 #221B") for item in result: print(item.get_name(), ':', item[0]) prints:: age : 22 ssn : 111-22-3333 house_number : 221B """ if self._name: return self._name elif self._parent: par: ParseResults = self._parent parent_tokdict_items = par._tokdict.items() return next( ( k for k, vlist in parent_tokdict_items for v, loc in vlist if v is self ), None, ) elif ( len(self) == 1 and len(self._tokdict) == 1 and next(iter(self._tokdict.values()))[0][1] in (0, -1) ): return next(iter(self._tokdict.keys())) else: return None def dump(self, indent="", full=True, include_list=True, _depth=0) -> str: """ Diagnostic method for listing out the contents of a :class:`ParseResults`. Accepts an optional ``indent`` argument so that this string can be embedded in a nested display of other data. Example:: integer = Word(nums) date_str = integer("year") + '/' + integer("month") + '/' + integer("day") result = date_str.parse_string('1999/12/31') print(result.dump()) prints:: ['1999', '/', '12', '/', '31'] - day: '31' - month: '12' - year: '1999' """ out = [] NL = "\n" out.append(indent + str(self.as_list()) if include_list else "") if not full: return "".join(out) if self.haskeys(): items = sorted((str(k), v) for k, v in self.items()) for k, v in items: if out: out.append(NL) out.append(f"{indent}{(' ' * _depth)}- {k}: ") if not isinstance(v, ParseResults): out.append(repr(v)) continue if not v: out.append(str(v)) continue out.append( v.dump( indent=indent, full=full, include_list=include_list, _depth=_depth + 1, ) ) if not any(isinstance(vv, ParseResults) for vv in self): return "".join(out) v = self incr = " " nl = "\n" for i, vv in enumerate(v): if isinstance(vv, ParseResults): vv_dump = vv.dump( indent=indent, full=full, include_list=include_list, _depth=_depth + 1, ) out.append( f"{nl}{indent}{incr * _depth}[{i}]:{nl}{indent}{incr * (_depth + 1)}{vv_dump}" ) else: out.append( f"{nl}{indent}{incr * _depth}[{i}]:{nl}{indent}{incr * (_depth + 1)}{vv}" ) return "".join(out) def pprint(self, *args, **kwargs): """ Pretty-printer for parsed results as a list, using the `pprint <https://docs.python.org/3/library/pprint.html>`_ module. Accepts additional positional or keyword args as defined for `pprint.pprint <https://docs.python.org/3/library/pprint.html#pprint.pprint>`_ . Example:: ident = Word(alphas, alphanums) num = Word(nums) func = Forward() term = ident | num | Group('(' + func + ')') func <<= ident + Group(Optional(DelimitedList(term))) result = func.parse_string("fna a,b,(fnb c,d,200),100") result.pprint(width=40) prints:: ['fna', ['a', 'b', ['(', 'fnb', ['c', 'd', '200'], ')'], '100']] """ pprint.pprint(self.as_list(), *args, **kwargs) # add support for pickle protocol def __getstate__(self): return ( self._toklist, ( self._tokdict.copy(), None, self._all_names, self._name, ), ) def __setstate__(self, state): self._toklist, (self._tokdict, par, inAccumNames, self._name) = state self._all_names = set(inAccumNames) self._parent = None def __getnewargs__(self): return self._toklist, self._name def __dir__(self): return dir(type(self)) + list(self.keys()) @classmethod def from_dict(cls, other, name=None) -> ParseResults: """ Helper classmethod to construct a ``ParseResults`` from a ``dict``, preserving the name-value relations as results names. If an optional ``name`` argument is given, a nested ``ParseResults`` will be returned. """ def is_iterable(obj): try: iter(obj) except Exception: return False # str's are iterable, but in pyparsing, we don't want to iterate over them else: return not isinstance(obj, str_type) ret = cls([]) for k, v in other.items(): if isinstance(v, Mapping): ret += cls.from_dict(v, name=k) else: ret += cls([v], name=k, asList=is_iterable(v)) if name is not None: ret = cls([ret], name=name) return ret asList = as_list """Deprecated - use :class:`as_list`""" asDict = as_dict """Deprecated - use :class:`as_dict`""" getName = get_name """Deprecated - use :class:`get_name`""" MutableMapping.register(ParseResults) MutableSequence.register(ParseResults) PK )��Z���N# N# __init__.pynu �[��� # module pyparsing.py # # Copyright (c) 2003-2022 Paul T. McGuire # # Permission is hereby granted, free of charge, to any person obtaining # a copy of this software and associated documentation files (the # "Software"), to deal in the Software without restriction, including # without limitation the rights to use, copy, modify, merge, publish, # distribute, sublicense, and/or sell copies of the Software, and to # permit persons to whom the Software is furnished to do so, subject to # the following conditions: # # The above copyright notice and this permission notice shall be # included in all copies or substantial portions of the Software. # # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, # EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF # MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. # IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY # CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. # __doc__ = """ pyparsing module - Classes and methods to define and execute parsing grammars ============================================================================= The pyparsing module is an alternative approach to creating and executing simple grammars, vs. the traditional lex/yacc approach, or the use of regular expressions. With pyparsing, you don't need to learn a new syntax for defining grammars or matching expressions - the parsing module provides a library of classes that you use to construct the grammar directly in Python. Here is a program to parse "Hello, World!" (or any greeting of the form ``"<salutation>, <addressee>!"``), built up using :class:`Word`, :class:`Literal`, and :class:`And` elements (the :meth:`'+'<ParserElement.__add__>` operators create :class:`And` expressions, and the strings are auto-converted to :class:`Literal` expressions):: from pyparsing import Word, alphas # define grammar of a greeting greet = Word(alphas) + "," + Word(alphas) + "!" hello = "Hello, World!" print(hello, "->", greet.parse_string(hello)) The program outputs the following:: Hello, World! -> ['Hello', ',', 'World', '!'] The Python representation of the grammar is quite readable, owing to the self-explanatory class names, and the use of :class:`'+'<And>`, :class:`'|'<MatchFirst>`, :class:`'^'<Or>` and :class:`'&'<Each>` operators. The :class:`ParseResults` object returned from :class:`ParserElement.parse_string` can be accessed as a nested list, a dictionary, or an object with named attributes. The pyparsing module handles some of the problems that are typically vexing when writing text parsers: - extra or missing whitespace (the above program will also handle "Hello,World!", "Hello , World !", etc.) - quoted strings - embedded comments Getting Started - ----------------- Visit the classes :class:`ParserElement` and :class:`ParseResults` to see the base classes that most other pyparsing classes inherit from. Use the docstrings for examples of how to: - construct literal match expressions from :class:`Literal` and :class:`CaselessLiteral` classes - construct character word-group expressions using the :class:`Word` class - see how to create repetitive expressions using :class:`ZeroOrMore` and :class:`OneOrMore` classes - use :class:`'+'<And>`, :class:`'|'<MatchFirst>`, :class:`'^'<Or>`, and :class:`'&'<Each>` operators to combine simple expressions into more complex ones - associate names with your parsed results using :class:`ParserElement.set_results_name` - access the parsed data, which is returned as a :class:`ParseResults` object - find some helpful expression short-cuts like :class:`DelimitedList` and :class:`one_of` - find more useful common expressions in the :class:`pyparsing_common` namespace class """ from typing import NamedTuple class version_info(NamedTuple): major: int minor: int micro: int releaselevel: str serial: int @property def __version__(self): return ( f"{self.major}.{self.minor}.{self.micro}" + ( f"{'r' if self.releaselevel[0] == 'c' else ''}{self.releaselevel[0]}{self.serial}", "", )[self.releaselevel == "final"] ) def __str__(self): return f"{__name__} {self.__version__} / {__version_time__}" def __repr__(self): return f"{__name__}.{type(self).__name__}({', '.join('{}={!r}'.format(*nv) for nv in zip(self._fields, self))})" __version_info__ = version_info(3, 2, 3, "final", 1) __version_time__ = "25 Mar 2025 01:38 UTC" __version__ = __version_info__.__version__ __versionTime__ = __version_time__ __author__ = "Paul McGuire <ptmcg.gm+pyparsing@gmail.com>" from .util import * from .exceptions import * from .actions import * from .core import __diag__, __compat__ from .results import * from .core import * from .core import _builtin_exprs as core_builtin_exprs from .helpers import * from .helpers import _builtin_exprs as helper_builtin_exprs from .unicode import unicode_set, UnicodeRangeList, pyparsing_unicode as unicode from .testing import pyparsing_test as testing from .common import ( pyparsing_common as common, _builtin_exprs as common_builtin_exprs, ) # Compatibility synonyms if "pyparsing_unicode" not in globals(): pyparsing_unicode = unicode # type: ignore[misc] if "pyparsing_common" not in globals(): pyparsing_common = common if "pyparsing_test" not in globals(): pyparsing_test = testing core_builtin_exprs += common_builtin_exprs + helper_builtin_exprs __all__ = [ "__version__", "__version_time__", "__author__", "__compat__", "__diag__", "And", "AtLineStart", "AtStringStart", "CaselessKeyword", "CaselessLiteral", "CharsNotIn", "CloseMatch", "Combine", "DelimitedList", "Dict", "Each", "Empty", "FollowedBy", "Forward", "GoToColumn", "Group", "IndentedBlock", "Keyword", "LineEnd", "LineStart", "Literal", "Located", "PrecededBy", "MatchFirst", "NoMatch", "NotAny", "OneOrMore", "OnlyOnce", "OpAssoc", "Opt", "Optional", "Or", "ParseBaseException", "ParseElementEnhance", "ParseException", "ParseExpression", "ParseFatalException", "ParseResults", "ParseSyntaxException", "ParserElement", "PositionToken", "QuotedString", "RecursiveGrammarException", "Regex", "SkipTo", "StringEnd", "StringStart", "Suppress", "Tag", "Token", "TokenConverter", "White", "Word", "WordEnd", "WordStart", "ZeroOrMore", "Char", "alphanums", "alphas", "alphas8bit", "any_close_tag", "any_open_tag", "autoname_elements", "c_style_comment", "col", "common_html_entity", "condition_as_parse_action", "counted_array", "cpp_style_comment", "dbl_quoted_string", "dbl_slash_comment", "delimited_list", "dict_of", "empty", "hexnums", "html_comment", "identchars", "identbodychars", "infix_notation", "java_style_comment", "line", "line_end", "line_start", "lineno", "make_html_tags", "make_xml_tags", "match_only_at_col", "match_previous_expr", "match_previous_literal", "nested_expr", "null_debug_action", "nums", "one_of", "original_text_for", "printables", "punc8bit", "pyparsing_common", "pyparsing_test", "pyparsing_unicode", "python_style_comment", "quoted_string", "remove_quotes", "replace_with", "replace_html_entity", "rest_of_line", "sgl_quoted_string", "srange", "string_end", "string_start", "token_map", "trace_parse_action", "ungroup", "unicode_set", "unicode_string", "with_attribute", "with_class", # pre-PEP8 compatibility names "__versionTime__", "anyCloseTag", "anyOpenTag", "cStyleComment", "commonHTMLEntity", "conditionAsParseAction", "countedArray", "cppStyleComment", "dblQuotedString", "dblSlashComment", "delimitedList", "dictOf", "htmlComment", "indentedBlock", "infixNotation", "javaStyleComment", "lineEnd", "lineStart", "locatedExpr", "makeHTMLTags", "makeXMLTags", "matchOnlyAtCol", "matchPreviousExpr", "matchPreviousLiteral", "nestedExpr", "nullDebugAction", "oneOf", "opAssoc", "originalTextFor", "pythonStyleComment", "quotedString", "removeQuotes", "replaceHTMLEntity", "replaceWith", "restOfLine", "sglQuotedString", "stringEnd", "stringStart", "tokenMap", "traceParseAction", "unicodeString", "withAttribute", "withClass", "common", "unicode", "testing", ] PK )��Z�߀�� � * tools/__pycache__/__init__.cpython-310.pycnu �[��� PK )��ZN�U : tools/__pycache__/cvt_pyparsing_pep8_names.cpython-310.pycnu �[��� PK )��Zp�TH� � ! y tools/cvt_pyparsing_pep8_names.pynu �[��� PK )��Z �* tools/__init__.pynu �[��� PK )��Z�2 �2 # + __pycache__/testing.cpython-310.pycnu �[��� PK )��Z疁�� � # /^ __pycache__/helpers.cpython-310.pycnu �[��� PK )��Z��9H7 H7 �� __pycache__/util.cpython-310.pycnu �[��� PK )��Z�q( q( & __pycache__/exceptions.cpython-310.pycnu �[��� PK )��ZV�YS�� �� �F __pycache__/core.cpython-310.pycnu �[��� PK )��Z�h�� � $ 9 __pycache__/__init__.cpython-310.pycnu �[��� PK )��Z�j�J # U __pycache__/actions.cpython-310.pycnu �[��� PK )��Z��b�f �f # mt __pycache__/results.cpython-310.pycnu �[��� PK )��Z�9.( ( # E� __pycache__/unicode.cpython-310.pycnu �[��� PK )��Z]A��l( l( " � __pycache__/common.cpython-310.pycnu �[��� PK )��Z "�-� � h, core.pynu �[��� PK )��ZT��a a �� actions.pynu �[��� PK )��Z N� py.typednu �[��� PK )��Z �dv) v) �� unicode.pynu �[��� PK )��Z �}Z9 Z9 6 testing.pynu �[��� PK )��Z���8 8 �A util.pynu �[��� PK )��Z� a8�& �& z exceptions.pynu �[��� PK )��ZQS��ۜ ۜ � helpers.pynu �[��� PK )��Z�tK#�J �J , �= diagram/__pycache__/__init__.cpython-310.pycnu �[��� PK )��Z��p�`i `i R� diagram/__init__.pynu �[��� PK )��Z�� �i5 i5 �� common.pynu �[��� PK )��Z���'�f �f �( results.pynu �[��� PK )��Z���N# N# _� __init__.pynu �[��� PK Y �
| ver. 1.4 |
Github
|
.
| PHP 8.2.28 | Generation time: 0.04 |
proxy
|
phpinfo
|
Settings