File manager - Edit - /home/newsbmcs.com/public_html/static/img/logo/pgen2.tar
Back
literals.py 0000644 00000003143 15027553031 0006737 0 ustar 00 # Copyright 2004-2005 Elemental Security, Inc. All Rights Reserved. # Licensed to PSF under a Contributor Agreement. """Safely evaluate Python string literals without using eval().""" import re simple_escapes = {"a": "\a", "b": "\b", "f": "\f", "n": "\n", "r": "\r", "t": "\t", "v": "\v", "'": "'", '"': '"', "\\": "\\"} def escape(m): all, tail = m.group(0, 1) assert all.startswith("\\") esc = simple_escapes.get(tail) if esc is not None: return esc if tail.startswith("x"): hexes = tail[1:] if len(hexes) < 2: raise ValueError("invalid hex string escape ('\\%s')" % tail) try: i = int(hexes, 16) except ValueError: raise ValueError("invalid hex string escape ('\\%s')" % tail) from None else: try: i = int(tail, 8) except ValueError: raise ValueError("invalid octal string escape ('\\%s')" % tail) from None return chr(i) def evalString(s): assert s.startswith("'") or s.startswith('"'), repr(s[:1]) q = s[0] if s[:3] == q*3: q = q*3 assert s.endswith(q), repr(s[-len(q):]) assert len(s) >= 2*len(q) s = s[len(q):-len(q)] return re.sub(r"\\(\'|\"|\\|[abfnrtv]|x.{0,2}|[0-7]{1,3})", escape, s) def test(): for i in range(256): c = chr(i) s = repr(c) e = evalString(s) if e != c: print(i, c, s, e) if __name__ == "__main__": test() grammar.py 0000644 00000012635 15027553031 0006554 0 ustar 00 # Copyright 2004-2005 Elemental Security, Inc. All Rights Reserved. # Licensed to PSF under a Contributor Agreement. """This module defines the data structures used to represent a grammar. These are a bit arcane because they are derived from the data structures used by Python's 'pgen' parser generator. There's also a table here mapping operators to their names in the token module; the Python tokenize module reports all operators as the fallback token code OP, but the parser needs the actual token code. """ # Python imports import pickle # Local imports from . import token class Grammar(object): """Pgen parsing tables conversion class. Once initialized, this class supplies the grammar tables for the parsing engine implemented by parse.py. The parsing engine accesses the instance variables directly. The class here does not provide initialization of the tables; several subclasses exist to do this (see the conv and pgen modules). The load() method reads the tables from a pickle file, which is much faster than the other ways offered by subclasses. The pickle file is written by calling dump() (after loading the grammar tables using a subclass). The report() method prints a readable representation of the tables to stdout, for debugging. The instance variables are as follows: symbol2number -- a dict mapping symbol names to numbers. Symbol numbers are always 256 or higher, to distinguish them from token numbers, which are between 0 and 255 (inclusive). number2symbol -- a dict mapping numbers to symbol names; these two are each other's inverse. states -- a list of DFAs, where each DFA is a list of states, each state is a list of arcs, and each arc is a (i, j) pair where i is a label and j is a state number. The DFA number is the index into this list. (This name is slightly confusing.) Final states are represented by a special arc of the form (0, j) where j is its own state number. dfas -- a dict mapping symbol numbers to (DFA, first) pairs, where DFA is an item from the states list above, and first is a set of tokens that can begin this grammar rule (represented by a dict whose values are always 1). labels -- a list of (x, y) pairs where x is either a token number or a symbol number, and y is either None or a string; the strings are keywords. The label number is the index in this list; label numbers are used to mark state transitions (arcs) in the DFAs. start -- the number of the grammar's start symbol. keywords -- a dict mapping keyword strings to arc labels. tokens -- a dict mapping token numbers to arc labels. """ def __init__(self): self.symbol2number = {} self.number2symbol = {} self.states = [] self.dfas = {} self.labels = [(0, "EMPTY")] self.keywords = {} self.tokens = {} self.symbol2label = {} self.start = 256 def dump(self, filename): """Dump the grammar tables to a pickle file.""" with open(filename, "wb") as f: pickle.dump(self.__dict__, f, pickle.HIGHEST_PROTOCOL) def load(self, filename): """Load the grammar tables from a pickle file.""" with open(filename, "rb") as f: d = pickle.load(f) self.__dict__.update(d) def loads(self, pkl): """Load the grammar tables from a pickle bytes object.""" self.__dict__.update(pickle.loads(pkl)) def copy(self): """ Copy the grammar. """ new = self.__class__() for dict_attr in ("symbol2number", "number2symbol", "dfas", "keywords", "tokens", "symbol2label"): setattr(new, dict_attr, getattr(self, dict_attr).copy()) new.labels = self.labels[:] new.states = self.states[:] new.start = self.start return new def report(self): """Dump the grammar tables to standard output, for debugging.""" from pprint import pprint print("s2n") pprint(self.symbol2number) print("n2s") pprint(self.number2symbol) print("states") pprint(self.states) print("dfas") pprint(self.dfas) print("labels") pprint(self.labels) print("start", self.start) # Map from operator to number (since tokenize doesn't do this) opmap_raw = """ ( LPAR ) RPAR [ LSQB ] RSQB : COLON , COMMA ; SEMI + PLUS - MINUS * STAR / SLASH | VBAR & AMPER < LESS > GREATER = EQUAL . DOT % PERCENT ` BACKQUOTE { LBRACE } RBRACE @ AT @= ATEQUAL == EQEQUAL != NOTEQUAL <> NOTEQUAL <= LESSEQUAL >= GREATEREQUAL ~ TILDE ^ CIRCUMFLEX << LEFTSHIFT >> RIGHTSHIFT ** DOUBLESTAR += PLUSEQUAL -= MINEQUAL *= STAREQUAL /= SLASHEQUAL %= PERCENTEQUAL &= AMPEREQUAL |= VBAREQUAL ^= CIRCUMFLEXEQUAL <<= LEFTSHIFTEQUAL >>= RIGHTSHIFTEQUAL **= DOUBLESTAREQUAL // DOUBLESLASH //= DOUBLESLASHEQUAL -> RARROW := COLONEQUAL """ opmap = {} for line in opmap_raw.splitlines(): if line: op, name = line.split() opmap[op] = getattr(token, name) tokenize.py 0000644 00000051177 15027553031 0006762 0 ustar 00 # Copyright (c) 2001, 2002, 2003, 2004, 2005, 2006 Python Software Foundation. # All rights reserved. """Tokenization help for Python programs. generate_tokens(readline) is a generator that breaks a stream of text into Python tokens. It accepts a readline-like method which is called repeatedly to get the next line of input (or "" for EOF). It generates 5-tuples with these members: the token type (see token.py) the token (a string) the starting (row, column) indices of the token (a 2-tuple of ints) the ending (row, column) indices of the token (a 2-tuple of ints) the original line (string) It is designed to match the working of the Python tokenizer exactly, except that it produces COMMENT tokens for comments and gives type OP for all operators Older entry points tokenize_loop(readline, tokeneater) tokenize(readline, tokeneater=printtoken) are the same, except instead of generating tokens, tokeneater is a callback function to which the 5 fields described above are passed as 5 arguments, each time a new token is found.""" __author__ = 'Ka-Ping Yee <ping@lfw.org>' __credits__ = \ 'GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro' import string, re from codecs import BOM_UTF8, lookup from lib2to3.pgen2.token import * from . import token __all__ = [x for x in dir(token) if x[0] != '_'] + ["tokenize", "generate_tokens", "untokenize"] del token try: bytes except NameError: # Support bytes type in Python <= 2.5, so 2to3 turns itself into # valid Python 3 code. bytes = str def group(*choices): return '(' + '|'.join(choices) + ')' def any(*choices): return group(*choices) + '*' def maybe(*choices): return group(*choices) + '?' def _combinations(*l): return set( x + y for x in l for y in l + ("",) if x.casefold() != y.casefold() ) Whitespace = r'[ \f\t]*' Comment = r'#[^\r\n]*' Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment) Name = r'\w+' Binnumber = r'0[bB]_?[01]+(?:_[01]+)*' Hexnumber = r'0[xX]_?[\da-fA-F]+(?:_[\da-fA-F]+)*[lL]?' Octnumber = r'0[oO]?_?[0-7]+(?:_[0-7]+)*[lL]?' Decnumber = group(r'[1-9]\d*(?:_\d+)*[lL]?', '0[lL]?') Intnumber = group(Binnumber, Hexnumber, Octnumber, Decnumber) Exponent = r'[eE][-+]?\d+(?:_\d+)*' Pointfloat = group(r'\d+(?:_\d+)*\.(?:\d+(?:_\d+)*)?', r'\.\d+(?:_\d+)*') + maybe(Exponent) Expfloat = r'\d+(?:_\d+)*' + Exponent Floatnumber = group(Pointfloat, Expfloat) Imagnumber = group(r'\d+(?:_\d+)*[jJ]', Floatnumber + r'[jJ]') Number = group(Imagnumber, Floatnumber, Intnumber) # Tail end of ' string. Single = r"[^'\\]*(?:\\.[^'\\]*)*'" # Tail end of " string. Double = r'[^"\\]*(?:\\.[^"\\]*)*"' # Tail end of ''' string. Single3 = r"[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''" # Tail end of """ string. Double3 = r'[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""' _litprefix = r"(?:[uUrRbBfF]|[rR][fFbB]|[fFbBuU][rR])?" Triple = group(_litprefix + "'''", _litprefix + '"""') # Single-line ' or " string. String = group(_litprefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*'", _litprefix + r'"[^\n"\\]*(?:\\.[^\n"\\]*)*"') # Because of leftmost-then-longest match semantics, be sure to put the # longest operators first (e.g., if = came before ==, == would get # recognized as two instances of =). Operator = group(r"\*\*=?", r">>=?", r"<<=?", r"<>", r"!=", r"//=?", r"->", r"[+\-*/%&@|^=<>]=?", r"~") Bracket = '[][(){}]' Special = group(r'\r?\n', r':=', r'[:;.,`@]') Funny = group(Operator, Bracket, Special) PlainToken = group(Number, Funny, String, Name) Token = Ignore + PlainToken # First (or only) line of ' or " string. ContStr = group(_litprefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*" + group("'", r'\\\r?\n'), _litprefix + r'"[^\n"\\]*(?:\\.[^\n"\\]*)*' + group('"', r'\\\r?\n')) PseudoExtras = group(r'\\\r?\n', Comment, Triple) PseudoToken = Whitespace + group(PseudoExtras, Number, Funny, ContStr, Name) tokenprog, pseudoprog, single3prog, double3prog = map( re.compile, (Token, PseudoToken, Single3, Double3)) _strprefixes = ( _combinations('r', 'R', 'f', 'F') | _combinations('r', 'R', 'b', 'B') | {'u', 'U', 'ur', 'uR', 'Ur', 'UR'} ) endprogs = {"'": re.compile(Single), '"': re.compile(Double), "'''": single3prog, '"""': double3prog, **{f"{prefix}'''": single3prog for prefix in _strprefixes}, **{f'{prefix}"""': double3prog for prefix in _strprefixes}, **{prefix: None for prefix in _strprefixes}} triple_quoted = ( {"'''", '"""'} | {f"{prefix}'''" for prefix in _strprefixes} | {f'{prefix}"""' for prefix in _strprefixes} ) single_quoted = ( {"'", '"'} | {f"{prefix}'" for prefix in _strprefixes} | {f'{prefix}"' for prefix in _strprefixes} ) tabsize = 8 class TokenError(Exception): pass class StopTokenizing(Exception): pass def printtoken(type, token, xxx_todo_changeme, xxx_todo_changeme1, line): # for testing (srow, scol) = xxx_todo_changeme (erow, ecol) = xxx_todo_changeme1 print("%d,%d-%d,%d:\t%s\t%s" % \ (srow, scol, erow, ecol, tok_name[type], repr(token))) def tokenize(readline, tokeneater=printtoken): """ The tokenize() function accepts two parameters: one representing the input stream, and one providing an output mechanism for tokenize(). The first parameter, readline, must be a callable object which provides the same interface as the readline() method of built-in file objects. Each call to the function should return one line of input as a string. The second parameter, tokeneater, must also be a callable object. It is called once for each token, with five arguments, corresponding to the tuples generated by generate_tokens(). """ try: tokenize_loop(readline, tokeneater) except StopTokenizing: pass # backwards compatible interface def tokenize_loop(readline, tokeneater): for token_info in generate_tokens(readline): tokeneater(*token_info) class Untokenizer: def __init__(self): self.tokens = [] self.prev_row = 1 self.prev_col = 0 def add_whitespace(self, start): row, col = start assert row <= self.prev_row col_offset = col - self.prev_col if col_offset: self.tokens.append(" " * col_offset) def untokenize(self, iterable): for t in iterable: if len(t) == 2: self.compat(t, iterable) break tok_type, token, start, end, line = t self.add_whitespace(start) self.tokens.append(token) self.prev_row, self.prev_col = end if tok_type in (NEWLINE, NL): self.prev_row += 1 self.prev_col = 0 return "".join(self.tokens) def compat(self, token, iterable): startline = False indents = [] toks_append = self.tokens.append toknum, tokval = token if toknum in (NAME, NUMBER): tokval += ' ' if toknum in (NEWLINE, NL): startline = True for tok in iterable: toknum, tokval = tok[:2] if toknum in (NAME, NUMBER, ASYNC, AWAIT): tokval += ' ' if toknum == INDENT: indents.append(tokval) continue elif toknum == DEDENT: indents.pop() continue elif toknum in (NEWLINE, NL): startline = True elif startline and indents: toks_append(indents[-1]) startline = False toks_append(tokval) cookie_re = re.compile(r'^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)', re.ASCII) blank_re = re.compile(br'^[ \t\f]*(?:[#\r\n]|$)', re.ASCII) def _get_normal_name(orig_enc): """Imitates get_normal_name in tokenizer.c.""" # Only care about the first 12 characters. enc = orig_enc[:12].lower().replace("_", "-") if enc == "utf-8" or enc.startswith("utf-8-"): return "utf-8" if enc in ("latin-1", "iso-8859-1", "iso-latin-1") or \ enc.startswith(("latin-1-", "iso-8859-1-", "iso-latin-1-")): return "iso-8859-1" return orig_enc def detect_encoding(readline): """ The detect_encoding() function is used to detect the encoding that should be used to decode a Python source file. It requires one argument, readline, in the same way as the tokenize() generator. It will call readline a maximum of twice, and return the encoding used (as a string) and a list of any lines (left as bytes) it has read in. It detects the encoding from the presence of a utf-8 bom or an encoding cookie as specified in pep-0263. If both a bom and a cookie are present, but disagree, a SyntaxError will be raised. If the encoding cookie is an invalid charset, raise a SyntaxError. Note that if a utf-8 bom is found, 'utf-8-sig' is returned. If no encoding is specified, then the default of 'utf-8' will be returned. """ bom_found = False encoding = None default = 'utf-8' def read_or_stop(): try: return readline() except StopIteration: return bytes() def find_cookie(line): try: line_string = line.decode('ascii') except UnicodeDecodeError: return None match = cookie_re.match(line_string) if not match: return None encoding = _get_normal_name(match.group(1)) try: codec = lookup(encoding) except LookupError: # This behaviour mimics the Python interpreter raise SyntaxError("unknown encoding: " + encoding) if bom_found: if codec.name != 'utf-8': # This behaviour mimics the Python interpreter raise SyntaxError('encoding problem: utf-8') encoding += '-sig' return encoding first = read_or_stop() if first.startswith(BOM_UTF8): bom_found = True first = first[3:] default = 'utf-8-sig' if not first: return default, [] encoding = find_cookie(first) if encoding: return encoding, [first] if not blank_re.match(first): return default, [first] second = read_or_stop() if not second: return default, [first] encoding = find_cookie(second) if encoding: return encoding, [first, second] return default, [first, second] def untokenize(iterable): """Transform tokens back into Python source code. Each element returned by the iterable must be a token sequence with at least two elements, a token number and token value. If only two tokens are passed, the resulting output is poor. Round-trip invariant for full input: Untokenized source will match input source exactly Round-trip invariant for limited input: # Output text will tokenize the back to the input t1 = [tok[:2] for tok in generate_tokens(f.readline)] newcode = untokenize(t1) readline = iter(newcode.splitlines(1)).next t2 = [tok[:2] for tokin generate_tokens(readline)] assert t1 == t2 """ ut = Untokenizer() return ut.untokenize(iterable) def generate_tokens(readline): """ The generate_tokens() generator requires one argument, readline, which must be a callable object which provides the same interface as the readline() method of built-in file objects. Each call to the function should return one line of input as a string. Alternately, readline can be a callable function terminating with StopIteration: readline = open(myfile).next # Example of alternate readline The generator produces 5-tuples with these members: the token type; the token string; a 2-tuple (srow, scol) of ints specifying the row and column where the token begins in the source; a 2-tuple (erow, ecol) of ints specifying the row and column where the token ends in the source; and the line on which the token was found. The line passed is the physical line. """ lnum = parenlev = continued = 0 contstr, needcont = '', 0 contline = None indents = [0] # 'stashed' and 'async_*' are used for async/await parsing stashed = None async_def = False async_def_indent = 0 async_def_nl = False while 1: # loop over lines in stream try: line = readline() except StopIteration: line = '' lnum = lnum + 1 pos, max = 0, len(line) if contstr: # continued string if not line: raise TokenError("EOF in multi-line string", strstart) endmatch = endprog.match(line) if endmatch: pos = end = endmatch.end(0) yield (STRING, contstr + line[:end], strstart, (lnum, end), contline + line) contstr, needcont = '', 0 contline = None elif needcont and line[-2:] != '\\\n' and line[-3:] != '\\\r\n': yield (ERRORTOKEN, contstr + line, strstart, (lnum, len(line)), contline) contstr = '' contline = None continue else: contstr = contstr + line contline = contline + line continue elif parenlev == 0 and not continued: # new statement if not line: break column = 0 while pos < max: # measure leading whitespace if line[pos] == ' ': column = column + 1 elif line[pos] == '\t': column = (column//tabsize + 1)*tabsize elif line[pos] == '\f': column = 0 else: break pos = pos + 1 if pos == max: break if stashed: yield stashed stashed = None if line[pos] in '#\r\n': # skip comments or blank lines if line[pos] == '#': comment_token = line[pos:].rstrip('\r\n') nl_pos = pos + len(comment_token) yield (COMMENT, comment_token, (lnum, pos), (lnum, pos + len(comment_token)), line) yield (NL, line[nl_pos:], (lnum, nl_pos), (lnum, len(line)), line) else: yield ((NL, COMMENT)[line[pos] == '#'], line[pos:], (lnum, pos), (lnum, len(line)), line) continue if column > indents[-1]: # count indents or dedents indents.append(column) yield (INDENT, line[:pos], (lnum, 0), (lnum, pos), line) while column < indents[-1]: if column not in indents: raise IndentationError( "unindent does not match any outer indentation level", ("<tokenize>", lnum, pos, line)) indents = indents[:-1] if async_def and async_def_indent >= indents[-1]: async_def = False async_def_nl = False async_def_indent = 0 yield (DEDENT, '', (lnum, pos), (lnum, pos), line) if async_def and async_def_nl and async_def_indent >= indents[-1]: async_def = False async_def_nl = False async_def_indent = 0 else: # continued statement if not line: raise TokenError("EOF in multi-line statement", (lnum, 0)) continued = 0 while pos < max: pseudomatch = pseudoprog.match(line, pos) if pseudomatch: # scan for tokens start, end = pseudomatch.span(1) spos, epos, pos = (lnum, start), (lnum, end), end token, initial = line[start:end], line[start] if initial in string.digits or \ (initial == '.' and token != '.'): # ordinary number yield (NUMBER, token, spos, epos, line) elif initial in '\r\n': newline = NEWLINE if parenlev > 0: newline = NL elif async_def: async_def_nl = True if stashed: yield stashed stashed = None yield (newline, token, spos, epos, line) elif initial == '#': assert not token.endswith("\n") if stashed: yield stashed stashed = None yield (COMMENT, token, spos, epos, line) elif token in triple_quoted: endprog = endprogs[token] endmatch = endprog.match(line, pos) if endmatch: # all on one line pos = endmatch.end(0) token = line[start:pos] if stashed: yield stashed stashed = None yield (STRING, token, spos, (lnum, pos), line) else: strstart = (lnum, start) # multiple lines contstr = line[start:] contline = line break elif initial in single_quoted or \ token[:2] in single_quoted or \ token[:3] in single_quoted: if token[-1] == '\n': # continued string strstart = (lnum, start) endprog = (endprogs[initial] or endprogs[token[1]] or endprogs[token[2]]) contstr, needcont = line[start:], 1 contline = line break else: # ordinary string if stashed: yield stashed stashed = None yield (STRING, token, spos, epos, line) elif initial.isidentifier(): # ordinary name if token in ('async', 'await'): if async_def: yield (ASYNC if token == 'async' else AWAIT, token, spos, epos, line) continue tok = (NAME, token, spos, epos, line) if token == 'async' and not stashed: stashed = tok continue if token in ('def', 'for'): if (stashed and stashed[0] == NAME and stashed[1] == 'async'): if token == 'def': async_def = True async_def_indent = indents[-1] yield (ASYNC, stashed[1], stashed[2], stashed[3], stashed[4]) stashed = None if stashed: yield stashed stashed = None yield tok elif initial == '\\': # continued stmt # This yield is new; needed for better idempotency: if stashed: yield stashed stashed = None yield (NL, token, spos, (lnum, pos), line) continued = 1 else: if initial in '([{': parenlev = parenlev + 1 elif initial in ')]}': parenlev = parenlev - 1 if stashed: yield stashed stashed = None yield (OP, token, spos, epos, line) else: yield (ERRORTOKEN, line[pos], (lnum, pos), (lnum, pos+1), line) pos = pos + 1 if stashed: yield stashed stashed = None for indent in indents[1:]: # pop remaining indent levels yield (DEDENT, '', (lnum, 0), (lnum, 0), '') yield (ENDMARKER, '', (lnum, 0), (lnum, 0), '') if __name__ == '__main__': # testing import sys if len(sys.argv) > 1: tokenize(open(sys.argv[1]).readline) else: tokenize(sys.stdin.readline) __pycache__/parse.cpython-310.pyc 0000644 00000014561 15027553031 0012577 0 ustar 00 o ��bc� � @ s4 d Z ddlmZ G dd� de�ZG dd� de�ZdS )z�Parser engine for the grammar tables generated by pgen. The grammar table must be loaded first. See Parser/parser.c in the Python distribution for additional info on how this parsing engine works. � )�tokenc @ s e Zd ZdZdd� Zdd� ZdS )� ParseErrorz(Exception to signal the parser is stuck.c C s4 t �| d||||f � || _|| _|| _|| _d S )Nz!%s: type=%r, value=%r, context=%r)� Exception�__init__�msg�type�value�context)�selfr r r r � r �*/usr/lib/python3.10/lib2to3/pgen2/parse.pyr s � zParseError.__init__c C s t | �| j| j | j| jffS �N)r r r r )r r r r � __reduce__ s zParseError.__reduce__N)�__name__� __module__� __qualname__�__doc__r r r r r r r s r c @ sL e Zd ZdZddd�Zddd�Zdd� Zd d � Zd d � Zd d� Z dd� Z dS )�Parsera5 Parser engine. The proper usage sequence is: p = Parser(grammar, [converter]) # create instance p.setup([start]) # prepare for parsing <for each input token>: if p.addtoken(...): # parse a token; may raise ParseError break root = p.rootnode # root of abstract syntax tree A Parser instance may be reused by calling setup() repeatedly. A Parser instance contains state pertaining to the current token sequence, and should not be used concurrently by different threads to parse separate token sequences. See driver.py for how to get input tokens by tokenizing a file or string. Parsing is complete when addtoken() returns True; the root of the abstract syntax tree can then be retrieved from the rootnode instance variable. When a syntax error occurs, addtoken() raises the ParseError exception. There is no error recovery; the parser cannot be used after a syntax error was reported (but it can be reinitialized by calling setup()). Nc C s || _ |pdd� | _dS )a� Constructor. The grammar argument is a grammar.Grammar instance; see the grammar module for more information. The parser is not ready yet for parsing; you must call the setup() method to get it started. The optional convert argument is a function mapping concrete syntax tree nodes to abstract syntax tree nodes. If not given, no conversion is done and the syntax tree produced is the concrete syntax tree. If given, it must be a function of two arguments, the first being the grammar (a grammar.Grammar instance), and the second being the concrete syntax tree node to be converted. The syntax tree is converted from the bottom up. A concrete syntax tree node is a (type, value, context, nodes) tuple, where type is the node type (a token or symbol number), value is None for symbols and a string for tokens, context is None or an opaque value used for error reporting (typically a (lineno, offset) pair), and nodes is a list of children for symbols, and None for tokens. An abstract syntax tree node may be anything; this is entirely up to the converter function. c S s |S r r )�grammar�noder r r �<lambda>Z s z!Parser.__init__.<locals>.<lambda>N)r �convert)r r r r r r r < s zParser.__init__c C sH |du r| j j}|ddg f}| j j| d|f}|g| _d| _t� | _dS )a� Prepare for parsing. This *must* be called before starting to parse. The optional argument is an alternative start symbol; it defaults to the grammar's start symbol. You can use a Parser instance to parse any number of programs; each time you call setup() the parser is reset to an initial state determined by the (implicit or explicit) start symbol. N� )r �start�dfas�stack�rootnode�set� used_names)r r �newnode� stackentryr r r �setup\ s z Parser.setupc C sF | � |||�} | jd \}}}|\}} || } | D ]k\} } | jj| \} }|| kre| dk s0J �| �||| |� | }|| d|fgkrb| �� | jsM dS | jd \}}}|\}} || d|fgksC dS | dkr�| jj| }|\}}||v r�| �| | jj| | |� n qd|f| v r�| �� | js�td|||��ntd|||��q)z<Add a token; return True iff this is the end of the program.T���� r Fztoo much inputz bad input) �classifyr r �labels�shift�popr �pushr )r r r r �ilabel�dfa�stater �states�first�arcs�i�newstate�t�v�itsdfa� itsstates�itsfirstr r r �addtokent sF � � ���zParser.addtokenc C sX |t jkr| j�|� | jj�|�}|dur|S | jj�|�}|du r*td|||��|S )z&Turn a token into a label. (Internal)Nz bad token) r �NAMEr �addr �keywords�get�tokensr )r r r r r) r r r r$ � s zParser.classifyc C sT | j d \}}}|||df}| �| j|�}|dur |d �|� |||f| j d< dS )zShift a token. (Internal)r" N)r r r �append) r r r r0 r r* r+ r r r r r r& � s z Parser.shiftc C sB | j d \}}}|d|g f}|||f| j d< | j �|d|f� dS )z Push a nonterminal. (Internal)r" Nr )r r< ) r r �newdfar0 r r* r+ r r r r r r( � s z Parser.pushc C sf | j �� \}}}| �| j|�}|dur1| j r'| j d \}}}|d �|� dS || _| j| j_dS dS )z Pop a nonterminal. (Internal)Nr" )r r' r r r< r r )r �popdfa�popstate�popnoder r* r+ r r r r r' � s �z Parser.popr ) r r r r r r! r6 r$ r& r( r' r r r r r s 0 r N)r � r r r �objectr r r r r �<module> s __pycache__/__init__.cpython-310.pyc 0000644 00000000250 15027553031 0013212 0 ustar 00 o ��bc� � @ s d Z dS )zThe pgen2 package.N)�__doc__� r r �-/usr/lib/python3.10/lib2to3/pgen2/__init__.py�<module> s __pycache__/conv.cpython-310.pyc 0000644 00000015546 15027553031 0012436 0 ustar 00 o ��bc�% � @ s2 d Z ddlZddlmZmZ G dd� dej�ZdS )a� Convert graminit.[ch] spit out by pgen to Python code. Pgen is the Python parser generator. It is useful to quickly create a parser from a grammar file in Python's grammar notation. But I don't want my parsers to be written in C (yet), so I'm translating the parsing tables to Python data structures and writing a Python parse engine. Note that the token numbers are constants determined by the standard Python tokenizer. The standard token module defines these numbers and their names (the names are not used much). The token numbers are hardcoded into the Python tokenizer and into pgen. A Python implementation of the Python tokenizer is also available, in the standard tokenize module. On the other hand, symbol numbers (representing the grammar's non-terminals) are assigned by pgen based on the actual grammar input. Note: this module is pretty much obsolete; the pgen module generates equivalent grammar tables directly from the Grammar.txt input file without having to invoke the Python pgen C program. � N)�grammar�tokenc @ s0 e Zd ZdZdd� Zdd� Zdd� Zdd � Zd S ) � Convertera2 Grammar subclass that reads classic pgen output files. The run() method reads the tables as produced by the pgen parser generator, typically contained in two C files, graminit.h and graminit.c. The other methods are for internal use only. See the base class for more documentation. c C s | � |� | �|� | �� dS )z<Load the grammar tables from the text files written by pgen.N)�parse_graminit_h�parse_graminit_c� finish_off)�self� graminit_h� graminit_c� r �)/usr/lib/python3.10/lib2to3/pgen2/conv.py�run/ s z Converter.runc C s� zt |�}W n ty! } ztd||f � W Y d}~dS d}~ww i | _i | _d}|D ]@}|d7 }t�d|�}|sJ|�� rJtd|||�� f � q,|�� \}}t |�}|| jvs[J �|| jvsbJ �|| j|< || j|< q,dS ) z�Parse the .h file written by pgen. (Internal) This file is a sequence of #define statements defining the nonterminals of the grammar as numbers. We build two tables mapping the numbers to names and back. �Can't open %s: %sNFr � z^#define\s+(\w+)\s+(\d+)$z%s(%s): can't parse %sT) �open�OSError�print� symbol2number� number2symbol�re�match�strip�groups�int) r �filename�f�err�lineno�line�mo�symbol�numberr r r r 5 s0 �� � zConverter.parse_graminit_hc ! C sJ zt |�}W n ty! } ztd||f � W Y d}~dS d}~ww d}|d t|�}}|dks7J ||f��|d t|�}}|dksJJ ||f��|d t|�}}i }g }|�d��rg|�d�r�t�d |�}|spJ ||f��ttt |� � ��\} } } g } t | �D ]+} |d t|�}}t�d |�}|s�J ||f��ttt |� � ��\}}| � ||f� q�|d t|�}}|d ks�J ||f��| || | f< |d t|�}}|�d�sbt�d |�}|s�J ||f��ttt |� � ��\}}|t |�ks�J ||f��g }t |�D ]?} |d t|�}}t�d |�}|�sJ ||f��ttt |� � ��\} } } || | f } | t | �k�s9J ||f��|� | � �q |� |� |d t|�}}|d k�sYJ ||f��|d t|�}}|�d�s]|| _i }t�d|�}|�s{J ||f��t |�d��}t |�D ]�}|d t|�}}t�d|�}|�s�J ||f��|�d�}ttt |�dddd���\}}}}| j| |k�s�J ||f��| j| |k�s�J ||f��|dk�s�J ||f��|| }|t |�k�s�J ||f��|d t|�}}t�d|�}|�sJ ||f��i }t|�d��}t|�D ] \}} t| �} t d�D ]}| d|> @ �r0d||d | < �q �q||f||< �q�|d t|�}}|d k�sPJ ||f��|| _g } |d t|�}}t�d|�}|�smJ ||f��t |�d��} t | �D ]8}|d t|�}}t�d|�}|�s�J ||f��|� � \}}t |�}|dk�r�d}nt|�}| � ||f� �qx|d t|�}}|d k�s�J ||f��| | _|d t|�}}|dk�s�J ||f��|d t|�}}t�d|�}|�s�J ||f��t |�d��}|t | j�k�sJ �|d t|�}}|dk�sJ ||f��|d t|�}}t�d |�}|�s1J ||f��t |�d��} | t | j�k�sFJ ||f��|d t|�}}t�d |�}|�s^J ||f��t |�d��} | | jv �sqJ ||f��| | _|d t|�}}|d k�s�J ||f��z |d t|�}}W n t�y� Y dS w J ||f��) a� Parse the .c file written by pgen. (Internal) The file looks as follows. The first two lines are always this: #include "pgenheaders.h" #include "grammar.h" After that come four blocks: 1) one or more state definitions 2) a table defining dfas 3) a table defining labels 4) a struct defining the grammar A state definition has the following form: - one or more arc arrays, each of the form: static arc arcs_<n>_<m>[<k>] = { {<i>, <j>}, ... }; - followed by a state array, of the form: static state states_<s>[<t>] = { {<k>, arcs_<n>_<m>}, ... }; r NFr r z#include "pgenheaders.h" z#include "grammar.h" z static arc z)static arc arcs_(\d+)_(\d+)\[(\d+)\] = {$z\s+{(\d+), (\d+)},$z}; z'static state states_(\d+)\[(\d+)\] = {$z \s+{(\d+), arcs_(\d+)_(\d+)},$z static dfa dfas\[(\d+)\] = {$z0\s+{(\d+), "(\w+)", (\d+), (\d+), states_(\d+),$� � � � z\s+("(?:\\\d\d\d)*")},$� z!static label labels\[(\d+)\] = {$z\s+{(\d+), (0|"\w+")},$�0z grammar _PyParser_Grammar = { z \s+(\d+),$z dfas, z\s+{(\d+), labels},$z \s+(\d+)$)r r r �next� startswithr r �list�mapr r �range�append�len�states�groupr r �eval� enumerate�ord�dfas�labels�start� StopIteration)!r r r r r r �allarcsr/ r �n�m�k�arcs�_�i�j�s�t�stater4 �ndfasr r! �x�y�z�first� rawbitset�c�byter5 �nlabelsr6 r r r r T s �� � � �" � " �� � zConverter.parse_graminit_cc C sX i | _ i | _t| j�D ] \}\}}|tjkr |dur || j |< q |du r)|| j|< q dS )z1Create additional useful structures. (Internal).N)�keywords�tokensr2 r5 r �NAME)r �ilabel�type�valuer r r r � s ��zConverter.finish_offN)�__name__� __module__� __qualname__�__doc__r r r r r r r r r $ s &r )rU r �pgen2r r �Grammarr r r r r �<module> s __pycache__/tokenize.cpython-310.pyc 0000644 00000035374 15027553031 0013322 0 ustar 00 o ��bcR � @ s� d Z dZdZddlZddlZddlmZmZ ddlT ddl m Z d d � e e �D �g d � Z [ ze W n ey= eZ Y nw d d � Zdd� Zdd� Zdd� ZdZdZeede � ee� ZdZdZdZdZedd �Zeeeee�Z d Z ed d �ee � Z d e Z ee e �Z ed!e d" �Z!ee!e e �Z"d#Z#d$Z$d%Z%d&Z&d'Z'ee'd( e'd) �Z(ee'd* e'd+ �Z)ed,d-d.d/d0d1d2d3d4� Z*d5Z+ed6d7d8�Z,ee*e+e,�Z-ee"e-e)e�Z.ee. Z/ee'd9 ed:d� e'd; ed<d� �Z0edee(�Z1eee1e"e-e0e� Z2e3ej4e/e2e%e&f�\Z5Z6Z7Z8ed=d>d?d@�ed=d>dAdB�B h dC�B Z9e�4e#�e�4e$�e7e8dD�dEdF� e9D ��dGdF� e9D ��dHdF� e9D ��Z:d(d)hdIdJ� e9D �B dKdJ� e9D �B Z;d:d<hdLdJ� e9D �B dMdJ� e9D �B Z<dNZ=G dOdP� dPe>�Z?G dQdR� dRe>�Z@dSdT� ZAeAfdUdV�ZBdWdX� ZCG dYdZ� dZ�ZDe�4d[ejE�ZFe�4d\ejE�ZGd]d^� ZHd_d`� ZIdadb� ZJdcdd� ZKeLdek�r�ddlMZMeNeMjO�dk�r�eBePeMjOd �jQ� dS eBeMjRjQ� dS dS )fa� Tokenization help for Python programs. generate_tokens(readline) is a generator that breaks a stream of text into Python tokens. It accepts a readline-like method which is called repeatedly to get the next line of input (or "" for EOF). It generates 5-tuples with these members: the token type (see token.py) the token (a string) the starting (row, column) indices of the token (a 2-tuple of ints) the ending (row, column) indices of the token (a 2-tuple of ints) the original line (string) It is designed to match the working of the Python tokenizer exactly, except that it produces COMMENT tokens for comments and gives type OP for all operators Older entry points tokenize_loop(readline, tokeneater) tokenize(readline, tokeneater=printtoken) are the same, except instead of generating tokens, tokeneater is a callback function to which the 5 fields described above are passed as 5 arguments, each time a new token is found.zKa-Ping Yee <ping@lfw.org>z@GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro� N)�BOM_UTF8�lookup)�*� )�tokenc C s g | ] }|d dkr|�qS )r �_� )�.0�xr r �-/usr/lib/python3.10/lib2to3/pgen2/tokenize.py� <listcomp>% s r )�tokenize�generate_tokens� untokenizec G s dd� | � d S )N�(�|�))�join��choicesr r r �group0 � r c G � t | � d S )Nr �r r r r r �any1 � r c G r )N�?r r r r r �maybe2 r r c s t � fdd�� D ��S )Nc 3 s6 � | ]}� d D ]}|� � |� � kr|| V qqdS ))� N)�casefold)r r �y��lr r � <genexpr>4 s � � �z _combinations.<locals>.<genexpr>)�setr! r r! r � _combinations3 s �r% z[ \f\t]*z #[^\r\n]*z\\\r?\nz\w+z0[bB]_?[01]+(?:_[01]+)*z(0[xX]_?[\da-fA-F]+(?:_[\da-fA-F]+)*[lL]?z 0[oO]?_?[0-7]+(?:_[0-7]+)*[lL]?z[1-9]\d*(?:_\d+)*[lL]?z0[lL]?z[eE][-+]?\d+(?:_\d+)*z \d+(?:_\d+)*\.(?:\d+(?:_\d+)*)?z\.\d+(?:_\d+)*z \d+(?:_\d+)*z\d+(?:_\d+)*[jJ]z[jJ]z[^'\\]*(?:\\.[^'\\]*)*'z[^"\\]*(?:\\.[^"\\]*)*"z%[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''z%[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""z'(?:[uUrRbBfF]|[rR][fFbB]|[fFbBuU][rR])?�'''�"""z '[^\n'\\]*(?:\\.[^\n'\\]*)*'z "[^\n"\\]*(?:\\.[^\n"\\]*)*"z\*\*=?z>>=?z<<=?z<>z!=z//=?z->z[+\-*/%&@|^=<>]=?�~z[][(){}]z\r?\nz:=z[:;.,`@]z'[^\n'\\]*(?:\\.[^\n'\\]*)*�'z"[^\n"\\]*(?:\\.[^\n"\\]*)*�"�r�R�f�F�b�B> �U�u�UR�Ur�uR�ur)r) r* r& r' c C � i | ]}|� d �t �qS �r& )� single3prog�r �prefixr r r � <dictcomp>y � r< c C r7 �r' )� double3progr: r r r r< z r= c C s i | ]}|d �qS �Nr r: r r r r< { r c C � h | ]}|� d ��qS r8 r r: r r r � <setcomp> � rB c C rA r> r r: r r r rB � rC c C rA )r) r r: r r r rB � rC c C rA )r* r r: r r r rB � rC � c @ � e Zd ZdS )� TokenErrorN��__name__� __module__� __qualname__r r r r rF � r rF c @ rE )�StopTokenizingNrG r r r r rK � r rK c C s4 |\}}|\}}t d||||t| t|�f � d S )Nz%d,%d-%d,%d: %s %s)�print�tok_name�repr) �typer �xxx_todo_changeme�xxx_todo_changeme1�line�srow�scol�erow�ecolr r r � printtoken� s �rW c C s& zt | |� W dS ty Y dS w )a: The tokenize() function accepts two parameters: one representing the input stream, and one providing an output mechanism for tokenize(). The first parameter, readline, must be a callable object which provides the same interface as the readline() method of built-in file objects. Each call to the function should return one line of input as a string. The second parameter, tokeneater, must also be a callable object. It is called once for each token, with five arguments, corresponding to the tuples generated by generate_tokens(). N)� tokenize_looprK )�readline� tokeneaterr r r r � s �r c C s t | �D ]}||� qd S r@ )r )rY rZ � token_infor r r rX � s �rX c @ s, e Zd Zdd� Zdd� Zdd� Zdd� Zd S ) � Untokenizerc C s g | _ d| _d| _d S )Nr r )�tokens�prev_row�prev_col)�selfr r r �__init__� s zUntokenizer.__init__c C s< |\}}|| j ks J �|| j }|r | j�d| � d S d S )N� )r^ r_ r] �append)r` �start�row�col� col_offsetr r r �add_whitespace� s �zUntokenizer.add_whitespacec C s� |D ]8}t |�dkr| �||� n)|\}}}}}| �|� | j�|� |\| _| _|ttfv r:| jd7 _d| _qd� | j�S )N� r r r ) �len�compatrh r] rc r^ r_ �NEWLINE�NLr )r` �iterable�t�tok_typer rd �endrR r r r r � s � zUntokenizer.untokenizec C s� d}g }| j j}|\}}|ttfv r|d7 }|ttfv r d}|D ]B}|d d� \}}|ttttfv r6|d7 }|tkr@|�|� q |t krI|� � q |ttfv rRd}n |r^|r^||d � d}||� q d S )NFrb Tri ���) r] rc �NAME�NUMBERrl rm �ASYNC�AWAIT�INDENT�DEDENT�pop) r` r rn � startline�indents� toks_append�toknum�tokval�tokr r r rk � s2 �zUntokenizer.compatN)rH rI rJ ra rh r rk r r r r r\ � s r\ z&^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)s ^[ \t\f]*(?:[#\r\n]|$)c C sH | dd� � � �dd�}|dks|�d�rdS |dv s |�d�r"d S | S ) z(Imitates get_normal_name in tokenizer.c.N� r �-�utf-8zutf-8-)zlatin-1� iso-8859-1z iso-latin-1)zlatin-1-z iso-8859-1-z iso-latin-1-r� )�lower�replace� startswith)�orig_enc�encr r r �_get_normal_name� s �r� c s� d� d}d}�fdd�}� fdd�}|� }|� t�r$d� |d d� }d }|s*|g fS ||�}|r5||gfS t�|�s?||gfS |� }|sI||gfS ||�}|rU|||gfS |||gfS ) a The detect_encoding() function is used to detect the encoding that should be used to decode a Python source file. It requires one argument, readline, in the same way as the tokenize() generator. It will call readline a maximum of twice, and return the encoding used (as a string) and a list of any lines (left as bytes) it has read in. It detects the encoding from the presence of a utf-8 bom or an encoding cookie as specified in pep-0263. If both a bom and a cookie are present, but disagree, a SyntaxError will be raised. If the encoding cookie is an invalid charset, raise a SyntaxError. Note that if a utf-8 bom is found, 'utf-8-sig' is returned. If no encoding is specified, then the default of 'utf-8' will be returned. FNr� c s" z� � W S t y t� Y S w r@ )� StopIteration�bytesr )rY r r � read_or_stop s �z%detect_encoding.<locals>.read_or_stopc s� z| � d�}W n ty Y d S w t�|�}|sd S t|�d��}zt|�}W n ty5 td| ��w � rE|j dkrAtd��|d7 }|S )N�asciir zunknown encoding: r� zencoding problem: utf-8z-sig) �decode�UnicodeDecodeError� cookie_re�matchr� r r � LookupError� SyntaxError�name)rR � line_stringr� �encoding�codec)� bom_foundr r � find_cookie s& � � z$detect_encoding.<locals>.find_cookieT� z utf-8-sig)r� r �blank_rer� )rY r� �defaultr� r� �first�secondr )r� rY r �detect_encoding� s0 r� c C s t � }|�| �S )a� Transform tokens back into Python source code. Each element returned by the iterable must be a token sequence with at least two elements, a token number and token value. If only two tokens are passed, the resulting output is poor. Round-trip invariant for full input: Untokenized source will match input source exactly Round-trip invariant for limited input: # Output text will tokenize the back to the input t1 = [tok[:2] for tok in generate_tokens(f.readline)] newcode = untokenize(t1) readline = iter(newcode.splitlines(1)).next t2 = [tok[:2] for tokin generate_tokens(readline)] assert t1 == t2 )r\ r )rn �utr r r r : s r c c s� � d } }}d\}}d}dg}d}d} d} d} z| � } W n t y) d} Y nw |d }dt| �} }|r�| s>td|��|�| �}|rf|�d� } }t|| d|� |||f|| fV d\}}d}�nN|r�| dd� d kr�| d d� d kr�t|| ||t| �f|fV d}d}q|| }|| }q|dk�r�|�s�| s��n�d}| |k r�| | d kr�|d }n| | d kr�|t d t }n | | dkr�d}nn| d } | |k s�| |krؐn�|r�|V d}| | dv �r:| | dk�r | | d� �d�}| t|� }t ||| f|| t|� f| fV t | |d� ||f|t| �f| fV nt t f| | dk | | d� || f|t| �f| fV q||d k�rV|� |� t | d| � |df|| f| fV ||d k �r�||v�rkt dd|| | f��|dd� }| �r�| |d k�r�d} d} d} td|| f|| f| fV ||d k �s]| �r�| �r�| |d k�r�d} d} d} n | �s�td|df��d}| |k �r�t�| | �}|�r}|�d�\}}||f||f|}}} | ||� | | }}|tjv �s�|dk�r�|dk�r�t|||| fV �n�|dv �r t} |dk�r t } n| �rd} |�r|V d}| |||| fV �nq|dk�r?|�d��r-J �|�r5|V d}t |||| fV �nR|tv �r~t| }|�| | �}|�rp|�d�} | || � }|�rd|V d}t|||| f| fV �n!||f}| |d� }| }�n|tv �s�|dd� tv �s�|dd� tv �r�|d dk�r�||f}t| �p�t|d �p�t|d }| |d� d}}| }n�|�r�|V d}t|||| fV n�|�� �r?|dv �r�| �r�|d k�r�tnt|||| fV �q�t |||| f} |d k�r |�s | }�q�|d v �r3|�r3|d t k�r3|d d k�r3|d k�r!d} |d } t|d |d |d |d fV d}|�r;|V d}| V nR|d k�rY|�rL|V d}t |||| f| fV d}n8|d!v �rc|d }n |d"v �rl|d }|�rt|V d}t |||| fV nt| | || f|| d f| fV | d } | |k �s�q|�r�|V d}|dd� D ]} td|df|dfdfV �q�t d|df|dfdfV dS )#a4 The generate_tokens() generator requires one argument, readline, which must be a callable object which provides the same interface as the readline() method of built-in file objects. Each call to the function should return one line of input as a string. Alternately, readline can be a callable function terminating with StopIteration: readline = open(myfile).next # Example of alternate readline The generator produces 5-tuples with these members: the token type; the token string; a 2-tuple (srow, scol) of ints specifying the row and column where the token begins in the source; a 2-tuple (erow, ecol) of ints specifying the row and column where the token ends in the source; and the line on which the token was found. The line passed is the physical line. r )r r NFr r zEOF in multi-line string���z\ ���z\ rb � � z# �#z rr z3unindent does not match any outer indentation levelz <tokenize>zEOF in multi-line statement�.T� ri r� )�async�awaitr� )�def�forr� � �\z([{z)]}) r� rj rF r� rq �STRING� ERRORTOKEN�tabsize�rstrip�COMMENTrm rc rw �IndentationErrorrx � pseudoprog�span�string�digitsrt rl �endswith� triple_quoted�endprogs� single_quoted� isidentifierru rv rs �OP� ENDMARKER) rY �lnum�parenlev� continued�contstr�needcont�contliner{ �stashed� async_def�async_def_indent� async_def_nlrR �pos�max�strstart�endprog�endmatchrq �column� comment_token�nl_pos� pseudomatchrd �spos�eposr �initial�newliner �indentr r r r O s� � � �$� � � � � � �� � � � � �� @ r �__main__)S�__doc__� __author__� __credits__r� �re�codecsr r �lib2to3.pgen2.tokenr r �dir�__all__r� � NameError�strr r r r% � Whitespace�Comment�Ignore�Name� Binnumber� Hexnumber� Octnumber� Decnumber� Intnumber�Exponent� Pointfloat�Expfloat� Floatnumber� Imagnumber�Number�Single�Double�Single3�Double3� _litprefix�Triple�String�Operator�Bracket�Special�Funny� PlainToken�Token�ContStr� PseudoExtras� PseudoToken�map�compile� tokenprogr� r9 r? � _strprefixesr� r� r� r� � ExceptionrF rK rW r rX r\ �ASCIIr� r� r� r� r r rH �sysrj �argv�openrY �stdinr r r r �<module> s� � � � � ��� � ���� � � � � �� � �� 8 I c(� __pycache__/literals.cpython-310.pyc 0000644 00000003006 15027553031 0013274 0 ustar 00 o ��bcc � @ sT d Z ddlZddddddd d d d d � Zdd� Zdd� Zdd� Zedkr(e� dS dS )z<Safely evaluate Python string literals without using eval().� N��� � � � � �'�"�\) �a�b�f�n�r�t�vr r r c C s� | � dd�\}}|�d�sJ �t�|�}|d ur|S |�d�rJ|dd � }t|�dk r1td| ��z t|d�}W t|�S tyI td| �d �w z t|d�}W t|�S tyb td | �d �w ) Nr � r �x� z!invalid hex string escape ('\%s')� � z#invalid octal string escape ('\%s'))�group� startswith�simple_escapes�get�len� ValueError�int�chr)�m�all�tail�esc�hexes�i� r& �-/usr/lib/python3.10/lib2to3/pgen2/literals.py�escape s* �� ��r( c C s� | � d�s| � d�sJ t| d d� ���| d }| d d� |d kr&|d }| �|�s8J t| t|� d � ���t| �dt|� ksDJ �| t|�t|� � } t�dt| �S )Nr r r r � r z)\\(\'|\"|\\|[abfnrtv]|x.{0,2}|[0-7]{1,3}))r �repr�endswithr �re�subr( )�s�qr& r& r' � evalString( s ($r0 c C s@ t d�D ]} t| �}t|�}t|�}||kr t| |||� qd S )N� )�ranger r* r0 �print)r% �cr. �er& r& r' �test2 s ��r6 �__main__)�__doc__r, r r( r0 r6 �__name__r& r& r& r' �<module> s& � � __pycache__/pgen.cpython-310.pyc 0000644 00000023171 15027553031 0012413 0 ustar 00 o ��bc6 � @ sd d dl mZmZmZ G dd� dej�ZG dd� de�ZG dd� de�ZG dd � d e�Z dd d �Z d S )� )�grammar�token�tokenizec @ s e Zd ZdS )� PgenGrammarN)�__name__� __module__� __qualname__� r r �)/usr/lib/python3.10/lib2to3/pgen2/pgen.pyr s r c @ s� e Zd Zd&dd�Zdd� Zdd� Zdd � Zd d � Zd d � Zdd� Z dd� Z dd� Z dd� Z dd� Z dd� Zdd� Zd d � Zd d � Zd&d d!�Zd"d#� Zd$d%� ZdS )'�ParserGeneratorNc C sp d }|d u rt |dd�}|j}|| _|| _t�|j�| _| �� | � � \| _ | _ |d ur/|� i | _ | � � d S )Nzutf-8)�encoding)�open�close�filename�streamr �generate_tokens�readline� generator�gettoken�parse�dfas� startsymbol�first� addfirstsets)�selfr r � close_streamr r r �__init__ s zParserGenerator.__init__c C s t � }t| j�� �}|�� |�| j� |�d| j� |D ]}dt|j � }||j |< ||j |< q |D ]P}| j| }g }|D ]0}g }t |j � � �D ]\} } |�| �|| �|�| �f� qI|jri|�d|�|�f� |�|� q>|j�|� || �||�f|j|j | < q3|j | j |_|S )N� � )r �listr �keys�sort�remover �insert�len� symbol2number� number2symbol�sorted�arcs�items�append� make_label�index�isfinal�states� make_first�start) r �c�names�name�i�dfar. �stater( �label�nextr r r � make_grammar s. z ParserGenerator.make_grammarc C s4 | j | }i }t|�D ] }| �||�}d||< q |S �Nr )r r' r+ )r r1 r3 �rawfirstr r7 �ilabelr r r r/ 4 s zParserGenerator.make_firstc C sR t |j�}|d �� r]||jv r,||jv r|j| S |j�|j| d f� ||j|< |S tt|d �}t|t �s;J |��|tj v sDJ |��||j v rN|j | S |j�|d f� ||j |< |S |d dv sgJ |��t |�}|d �� r�||j v r{|j | S |j�tj|f� ||j |< |S tj| }||j v r�|j | S |j�|d f� ||j |< |S )Nr )�"�')r$ �labels�isalphar% � symbol2labelr* �getattrr � isinstance�int�tok_name�tokens�eval�keywords�NAMEr �opmap)r r1 r7 r< �itoken�valuer r r r+ = s< zParserGenerator.make_labelc C s8 t | j�� �}|�� |D ] }|| jvr| �|� q d S �N)r r r r! r � calcfirst)r r2 r3 r r r r k s ��z ParserGenerator.addfirstsetsc C s� | j | }d | j|< |d }i }i }|j�� D ]<\}}|| j v rI|| jv r5| j| }|d u r4td| ��n | �|� | j| }|�|� |||< qd||< |di||< qi } |�� D ] \}} | D ]} | | v rrtd|| || | f ��|| | < q`qZ|| j|< d S )Nr zrecursion for rule %rr zArule %s is ambiguous; %s is in the first sets of %s as well as %s)r r r( r) � ValueErrorrN �update) r r3 r5 r6 �totalset� overlapcheckr7 r8 �fset�inverse�itsfirst�symbolr r r rN s s8 � � �zParserGenerator.calcfirstc C s� i }d }| j tjkrV| j tjkr| �� | j tjks| �tj�}| �tjd� | �� \}}| �tj� | � ||�}t |�}| � |� t |�}|||< |d u rP|}| j tjks ||fS )N�:) �typer � ENDMARKER�NEWLINEr �expectrI �OP� parse_rhs�make_dfar$ � simplify_dfa) r r r r3 �a�zr5 �oldlen�newlenr r r r � s& � �zParserGenerator.parsec s� t |t�sJ �t |t�sJ �� fdd�}� fdd�� t||�|�g}|D ]F}i }|jD ]}|jD ]\}} |d urA� | |�|i �� q0q+t|�� �D ] \}} |D ] } | j| krX n qOt| |�} |�| � |� | |� qIq$|S )Nc s i }� | |� |S rM r )r6 �base�� addclosurer r �closure� s z)ParserGenerator.make_dfa.<locals>.closurec sH t | t�sJ �| |v r d S d|| < | jD ] \}}|d u r!� ||� qd S r: )rC �NFAStater( )r6 rd r7 r8 re r r rf � s ��z,ParserGenerator.make_dfa.<locals>.addclosure) rC rh �DFAState�nfasetr( � setdefaultr' r) r* �addarc) r r0 �finishrg r. r6 r( �nfastater7 r8 rj �str re r r^ � s. �� � �zParserGenerator.make_dfac C s� t d|� |g}t|�D ]>\}}t d|||u rdpd� |jD ]*\}}||v r-|�|�} n t|�} |�|� |d u rAt d| � q t d|| f � q q d S )NzDump of NFA for� State�(final)� z -> %d� %s -> %d)�print� enumerater( r, r$ r* ) r r3 r0 rm �todor4 r6 r7 r8 �jr r r �dump_nfa� s ��zParserGenerator.dump_nfac C sd t d|� t|�D ]&\}}t d||jrdpd� t|j�� �D ]\}}t d||�|�f � q q d S )NzDump of DFA forrp rq rr rs )rt ru r- r' r( r) r, )r r3 r5 r4 r6 r7 r8 r r r �dump_dfa� s ��zParserGenerator.dump_dfac C sv d}|r9d}t |�D ]*\}}t|d t|��D ] }|| }||kr3||= |D ]}|�||� q&d} nqq |sd S d S )NTFr )ru �ranger$ � unifystate)r r5 �changesr4 �state_irw �state_jr6 r r r r_ � s �� �z ParserGenerator.simplify_dfac C s� | � � \}}| jdkr||fS t� }t� }|�|� |�|� | jdkr=| �� | � � \}}|�|� |�|� | jdks$||fS )N�|)� parse_altrL rh rl r )r r` ra �aa�zzr r r r] � s �zParserGenerator.parse_rhsc C sf | � � \}}| jdv s| jtjtjfv r/| � � \}}|�|� |}| jdv s| jtjtjfv s||fS )N)�(�[)� parse_itemrL rX r rI �STRINGrl )r r` �br1 �dr r r r� s �zParserGenerator.parse_altc C s� | j dkr | �� | �� \}}| �tjd� |�|� ||fS | �� \}}| j }|dvr0||fS | �� |�|� |dkrA||fS ||fS )Nr� �])�+�*r� )rL r r] r[ r r\ rl � parse_atom)r r` ra rL r r r r� s zParserGenerator.parse_itemc C s� | j dkr| �� | �� \}}| �tjd� ||fS | jtjtjfv r8t � }t � }|� || j � | �� ||fS | � d| j| j � d S )Nr� �)z+expected (...) or NAME or STRING, got %s/%s) rL r r] r[ r r\ rX rI r� rh rl � raise_error)r r` ra r r r r� ( s �zParserGenerator.parse_atomc C sD | j |ks|d ur| j|kr| �d||| j | j� | j}| �� |S )Nzexpected %s/%s, got %s/%s)rX rL r� r )r rX rL r r r r[ 9 s �zParserGenerator.expectc C sX t | j�}|d tjtjfv r t | j�}|d tjtjfv s|\| _| _| _| _| _ d S )Nr ) r8 r r �COMMENT�NLrX rL �begin�end�line)r �tupr r r r A s � zParserGenerator.gettokenc G sV |rz|| }W n d� |gttt|�� �}Y t|| j| jd | jd | jf��)N� r r )�joinr �map�str� SyntaxErrorr r� r� )r �msg�argsr r r r� H s �zParserGenerator.raise_errorrM )r r r r r9 r/ r+ r rN r r^ rx ry r_ r] r� r� r� r[ r r� r r r r r s& . $ r c @ s e Zd Zdd� Zddd�ZdS )rh c C s g | _ d S rM )r( )r r r r r S s zNFAState.__init__Nc C s8 |d u s t |t�s J �t |t�sJ �| j�||f� d S rM )rC r� rh r( r* �r r8 r7 r r r rl V s zNFAState.addarcrM )r r r r rl r r r r rh Q s rh c @ s0 e Zd Zdd� Zdd� Zdd� Zdd� Zd Zd S ) ri c C sL t |t�sJ �t tt|��t�sJ �t |t�sJ �|| _||v | _i | _d S rM )rC �dictr8 �iterrh rj r- r( )r rj �finalr r r r ] s zDFAState.__init__c C s8 t |t�sJ �|| jvsJ �t |t�sJ �|| j|< d S rM )rC r� r( ri r� r r r rl e s zDFAState.addarcc C s* | j �� D ] \}}||u r|| j |< qd S rM )r( r) )r �old�newr7 r8 r r r r{ k s ��zDFAState.unifystatec C sd t |t�sJ �| j|jkrdS t| j�t|j�krdS | j�� D ]\}}||j�|�ur/ dS q dS )NFT)rC ri r- r$ r( r) �get)r �otherr7 r8 r r r �__eq__p s �zDFAState.__eq__N)r r r r rl r{ r� �__hash__r r r r ri [ s ri � Grammar.txtc C s t | �}|�� S rM )r r9 )r �pr r r �generate_grammar� s r� N)r� ) rr r r r �Grammarr �objectr rh ri r� r r r r �<module> s I % __pycache__/grammar.cpython-310.pyc 0000644 00000013130 15027553031 0013102 0 ustar 00 o ��bc� � @ s` d Z ddlZddlmZ G dd� de�ZdZi Ze�� D ]Z e r-e � � \Z Z e ee �ee < q dS )a� This module defines the data structures used to represent a grammar. These are a bit arcane because they are derived from the data structures used by Python's 'pgen' parser generator. There's also a table here mapping operators to their names in the token module; the Python tokenize module reports all operators as the fallback token code OP, but the parser needs the actual token code. � N� )�tokenc @ s@ e Zd ZdZdd� Zdd� Zdd� Zdd � Zd d � Zd d � Z dS )�Grammara� Pgen parsing tables conversion class. Once initialized, this class supplies the grammar tables for the parsing engine implemented by parse.py. The parsing engine accesses the instance variables directly. The class here does not provide initialization of the tables; several subclasses exist to do this (see the conv and pgen modules). The load() method reads the tables from a pickle file, which is much faster than the other ways offered by subclasses. The pickle file is written by calling dump() (after loading the grammar tables using a subclass). The report() method prints a readable representation of the tables to stdout, for debugging. The instance variables are as follows: symbol2number -- a dict mapping symbol names to numbers. Symbol numbers are always 256 or higher, to distinguish them from token numbers, which are between 0 and 255 (inclusive). number2symbol -- a dict mapping numbers to symbol names; these two are each other's inverse. states -- a list of DFAs, where each DFA is a list of states, each state is a list of arcs, and each arc is a (i, j) pair where i is a label and j is a state number. The DFA number is the index into this list. (This name is slightly confusing.) Final states are represented by a special arc of the form (0, j) where j is its own state number. dfas -- a dict mapping symbol numbers to (DFA, first) pairs, where DFA is an item from the states list above, and first is a set of tokens that can begin this grammar rule (represented by a dict whose values are always 1). labels -- a list of (x, y) pairs where x is either a token number or a symbol number, and y is either None or a string; the strings are keywords. The label number is the index in this list; label numbers are used to mark state transitions (arcs) in the DFAs. start -- the number of the grammar's start symbol. keywords -- a dict mapping keyword strings to arc labels. tokens -- a dict mapping token numbers to arc labels. c C s< i | _ i | _g | _i | _dg| _i | _i | _i | _d| _d S )N)r �EMPTY� ) � symbol2number� number2symbol�states�dfas�labels�keywords�tokens� symbol2label�start)�self� r �,/usr/lib/python3.10/lib2to3/pgen2/grammar.py�__init__L s zGrammar.__init__c C sB t |d��}t�| j|tj� W d � dS 1 sw Y dS )z)Dump the grammar tables to a pickle file.�wbN)�open�pickle�dump�__dict__�HIGHEST_PROTOCOL)r �filename�fr r r r W s "�z Grammar.dumpc C sD t |d�� }t�|�}W d � n1 sw Y | j�|� dS )z+Load the grammar tables from a pickle file.�rbN)r r �loadr �update)r r r �dr r r r \ s �z Grammar.loadc C s | j �t�|�� dS )z3Load the grammar tables from a pickle bytes object.N)r r r �loads)r �pklr r r r b s z Grammar.loadsc C sT | � � }dD ] }t||t| |��� � q| jdd� |_| jdd� |_| j|_|S )z# Copy the grammar. )r r r r r r N)� __class__�setattr�getattr�copyr r r )r �new� dict_attrr r r r% f s z Grammar.copyc C sv ddl m } td� || j� td� || j� td� || j� td� || j� td� || j� td| j� d S ) z:Dump the grammar tables to standard output, for debugging.r )�pprint�s2n�n2sr r r r N)r( �printr r r r r r )r r( r r r �reports s zGrammar.reportN) �__name__� __module__� __qualname__�__doc__r r r r r% r, r r r r r s 5 r a ( LPAR ) RPAR [ LSQB ] RSQB : COLON , COMMA ; SEMI + PLUS - MINUS * STAR / SLASH | VBAR & AMPER < LESS > GREATER = EQUAL . DOT % PERCENT ` BACKQUOTE { LBRACE } RBRACE @ AT @= ATEQUAL == EQEQUAL != NOTEQUAL <> NOTEQUAL <= LESSEQUAL >= GREATEREQUAL ~ TILDE ^ CIRCUMFLEX << LEFTSHIFT >> RIGHTSHIFT ** DOUBLESTAR += PLUSEQUAL -= MINEQUAL *= STAREQUAL /= SLASHEQUAL %= PERCENTEQUAL &= AMPEREQUAL |= VBAREQUAL ^= CIRCUMFLEXEQUAL <<= LEFTSHIFTEQUAL >>= RIGHTSHIFTEQUAL **= DOUBLESTAREQUAL // DOUBLESLASH //= DOUBLESLASHEQUAL -> RARROW := COLONEQUAL )r0 r � r �objectr � opmap_raw�opmap� splitlines�line�split�op�namer$ r r r r �<module> s o3 �� __pycache__/driver.cpython-310.pyc 0000644 00000011575 15027553031 0012762 0 ustar 00 o ��bc! � @ s� d Z dZddgZddlZddlZddlZddlZddlZddlm Z m Z m Z m Z m Z G dd� de�Zd d � Z ddd�Zdd� Zdd� Zdd� ZedkrXe�ee� �� dS dS )zZParser driver. This provides a high-level interface to parse a file into a syntax tree. z#Guido van Rossum <guido@python.org>�Driver� load_grammar� N� )�grammar�parse�token�tokenize�pgenc @ sH e Zd Zddd�Zddd�Zddd�Zdd d �Zdd d �Zdd d�ZdS )r Nc C s& || _ |d u r t�� }|| _|| _d S )N)r �logging� getLogger�logger�convert)�selfr r r � r �+/usr/lib/python3.10/lib2to3/pgen2/driver.py�__init__ s zDriver.__init__Fc C s� t �| j| j�}|�� d}d}d } } } } } d} |D ]�} | \}}}} } |||fkr]||f|ks;J ||f|f��|\} }|| k rO| d| | 7 } | }d}||k r]| | ||� 7 } |}|tjtjfv ry| |7 } | \}}|�d�rx|d7 }d}q |t j kr�tj | }|r�| j � dt j| || � |�||| |f�r�|r�| j � d� |jS d} | \}}|�d�r�|d7 }d}q t �d||| |f��) z4Parse a series of tokens and return the syntax tree.r r N� � z%s %r (prefix=%r)zStop.zincomplete input)r �Parserr r �setupr �COMMENT�NL�endswithr �OP�opmapr �debug�tok_name�addtoken� ParseError�rootnode)r �tokensr �p�lineno�column�type�value�start�end� line_text�prefix� quintuple�s_lineno�s_columnr r r � parse_tokens& sZ � � � �zDriver.parse_tokensc C s t �|j�}| �||�S �z*Parse a stream and return the syntax tree.)r �generate_tokens�readliner- )r �streamr r r r r �parse_stream_rawV s zDriver.parse_stream_rawc C s | � ||�S r. )r2 )r r1 r r r r � parse_stream[ s zDriver.parse_streamc C s@ t j|d|d��}| �||�W d � S 1 sw Y dS )z(Parse a file and return the syntax tree.�r)�encodingN)�io�openr3 )r �filenamer5 r r1 r r r � parse_file_ s $�zDriver.parse_filec C s t �t�|�j�}| �||�S )z*Parse a string and return the syntax tree.)r r/ r6 �StringIOr0 r- )r �textr r r r r � parse_stringd s zDriver.parse_string)NN)F)NF) �__name__� __module__� __qualname__r r- r2 r3 r9 r< r r r r r s 0 c C s: t j�| �\}}|dkrd}|| d�tttj�� d S )Nz.txtr �.z.pickle)�os�path�splitext�join�map�str�sys� version_info)�gt�head�tailr r r �_generate_pickle_namej s rL � Grammar.txtTFc C sd |du rt �� }|du rt| �n|}|st|| �s'|�d| � t�| �} |S t � � }|� |� |S )z'Load the grammar (maybe from a pickle).Nz!Generating grammar tables from %s) r r rL �_newer�infor �generate_grammar�dump�OSErrorr �Grammar�load)rI �gp�save�forcer �g�er r r r q s � c C s8 t j�| �sdS t j�|�sdS t j�| �t j�|�kS )z0Inquire whether file a was written since file b.FT)rA rB �exists�getmtime)�a�br r r rN � s rN c C sF t j�|�r t|�S tt j�|��}t�| |�}t� � }|� |� |S )a� Normally, loads a pickled grammar by doing pkgutil.get_data(package, pickled_grammar) where *pickled_grammar* is computed from *grammar_source* by adding the Python version and using a ``.pickle`` extension. However, if *grammar_source* is an extant file, load_grammar(grammar_source) is called instead. This facilitates using a packaged grammar file when needed but preserves load_grammar's automatic regeneration behavior when possible. ) rA rB �isfiler rL �basename�pkgutil�get_datar rS �loads)�package�grammar_source� pickled_name�datarX r r r �load_packaged_grammar� s rg c G sB | s t jdd� } tjtjt jdd� | D ] }t|ddd� qdS )z�Main program, when run as a script: produce grammar pickle files. Calls load_grammar for each argument, a path to a grammar text file. r Nz %(message)s)�levelr1 �formatT)rV rW )rG �argvr � basicConfig�INFO�stdoutr )�argsrI r r r �main� s �ro �__main__)rM NTFN)�__doc__� __author__�__all__r6 rA r r` rG r r r r r r �objectr rL r rN rg ro r= �exit�intr r r r �<module> s( M � � __pycache__/token.cpython-310.pyc 0000644 00000003534 15027553031 0012603 0 ustar 00 o ��bc � @ sL d Z dZdZdZdZdZdZdZdZd Z d Z d Z d Z d Z dZdZdZdZdZdZdZdZdZdZdZdZdZdZd Z d Z d Z d Z d Z d!Z!d"Z"d#Z#d$Z$d%Z%d&Z&d'Z'd(Z(d)Z)d*Z*d+Z+d,Z,d-Z-d.Z.d/Z/d0Z0d1Z1d2Z2d3Z3d4Z4d5Z5d6Z6d7Z7d8Z8d9Z9d:Z:d;Z;d<Z<d=Z=d>Z>i Z?e@eA� �B� �D ]\ZCZDeEeD�eEd�u r�eCe?eD< q�d?d@� ZFdAdB� ZGdCdD� ZHdES )Fz!Token constants (from "token.h").� � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � �! �" �# �$ �% �& �' �( �) �* �+ �, �- �. �/ �0 �1 �2 �3 �4 �5 �6 �7 �8 �9 �: �; �< � c C s | t k S �N�� NT_OFFSET��x� rD �*/usr/lib/python3.10/lib2to3/pgen2/token.py� ISTERMINALO � rF c C s | t kS r? r@ rB rD rD rE � ISNONTERMINALR rG rH c C s | t kS r? )� ENDMARKERrB rD rD rE �ISEOFU rG rJ N)I�__doc__rI �NAME�NUMBER�STRING�NEWLINE�INDENT�DEDENT�LPAR�RPAR�LSQB�RSQB�COLON�COMMA�SEMI�PLUS�MINUS�STAR�SLASH�VBAR�AMPER�LESS�GREATER�EQUAL�DOT�PERCENT� BACKQUOTE�LBRACE�RBRACE�EQEQUAL�NOTEQUAL� LESSEQUAL� GREATEREQUAL�TILDE� CIRCUMFLEX� LEFTSHIFT� RIGHTSHIFT� DOUBLESTAR� PLUSEQUAL�MINEQUAL� STAREQUAL� SLASHEQUAL� PERCENTEQUAL� AMPEREQUAL� VBAREQUAL�CIRCUMFLEXEQUAL�LEFTSHIFTEQUAL�RIGHTSHIFTEQUAL�DOUBLESTAREQUAL� DOUBLESLASH�DOUBLESLASHEQUAL�AT�ATEQUAL�OP�COMMENT�NL�RARROW�AWAIT�ASYNC� ERRORTOKEN� COLONEQUAL�N_TOKENSrA �tok_name�list�globals�items�_name�_value�typerF rH rJ rD rD rD rE �<module> s� � driver.py 0000644 00000014041 15027553031 0006412 0 ustar 00 # Copyright 2004-2005 Elemental Security, Inc. All Rights Reserved. # Licensed to PSF under a Contributor Agreement. # Modifications: # Copyright 2006 Google, Inc. All Rights Reserved. # Licensed to PSF under a Contributor Agreement. """Parser driver. This provides a high-level interface to parse a file into a syntax tree. """ __author__ = "Guido van Rossum <guido@python.org>" __all__ = ["Driver", "load_grammar"] # Python imports import io import os import logging import pkgutil import sys # Pgen imports from . import grammar, parse, token, tokenize, pgen class Driver(object): def __init__(self, grammar, convert=None, logger=None): self.grammar = grammar if logger is None: logger = logging.getLogger() self.logger = logger self.convert = convert def parse_tokens(self, tokens, debug=False): """Parse a series of tokens and return the syntax tree.""" # XXX Move the prefix computation into a wrapper around tokenize. p = parse.Parser(self.grammar, self.convert) p.setup() lineno = 1 column = 0 type = value = start = end = line_text = None prefix = "" for quintuple in tokens: type, value, start, end, line_text = quintuple if start != (lineno, column): assert (lineno, column) <= start, ((lineno, column), start) s_lineno, s_column = start if lineno < s_lineno: prefix += "\n" * (s_lineno - lineno) lineno = s_lineno column = 0 if column < s_column: prefix += line_text[column:s_column] column = s_column if type in (tokenize.COMMENT, tokenize.NL): prefix += value lineno, column = end if value.endswith("\n"): lineno += 1 column = 0 continue if type == token.OP: type = grammar.opmap[value] if debug: self.logger.debug("%s %r (prefix=%r)", token.tok_name[type], value, prefix) if p.addtoken(type, value, (prefix, start)): if debug: self.logger.debug("Stop.") break prefix = "" lineno, column = end if value.endswith("\n"): lineno += 1 column = 0 else: # We never broke out -- EOF is too soon (how can this happen???) raise parse.ParseError("incomplete input", type, value, (prefix, start)) return p.rootnode def parse_stream_raw(self, stream, debug=False): """Parse a stream and return the syntax tree.""" tokens = tokenize.generate_tokens(stream.readline) return self.parse_tokens(tokens, debug) def parse_stream(self, stream, debug=False): """Parse a stream and return the syntax tree.""" return self.parse_stream_raw(stream, debug) def parse_file(self, filename, encoding=None, debug=False): """Parse a file and return the syntax tree.""" with io.open(filename, "r", encoding=encoding) as stream: return self.parse_stream(stream, debug) def parse_string(self, text, debug=False): """Parse a string and return the syntax tree.""" tokens = tokenize.generate_tokens(io.StringIO(text).readline) return self.parse_tokens(tokens, debug) def _generate_pickle_name(gt): head, tail = os.path.splitext(gt) if tail == ".txt": tail = "" return head + tail + ".".join(map(str, sys.version_info)) + ".pickle" def load_grammar(gt="Grammar.txt", gp=None, save=True, force=False, logger=None): """Load the grammar (maybe from a pickle).""" if logger is None: logger = logging.getLogger() gp = _generate_pickle_name(gt) if gp is None else gp if force or not _newer(gp, gt): logger.info("Generating grammar tables from %s", gt) g = pgen.generate_grammar(gt) # the pickle files mismatch, when built on different architectures. # don't save these for now. An alternative solution might be to # include the multiarch triplet into the file name if False: logger.info("Writing grammar tables to %s", gp) try: g.dump(gp) except OSError as e: logger.info("Writing failed: %s", e) else: g = grammar.Grammar() g.load(gp) return g def _newer(a, b): """Inquire whether file a was written since file b.""" if not os.path.exists(a): return False if not os.path.exists(b): return True return os.path.getmtime(a) >= os.path.getmtime(b) def load_packaged_grammar(package, grammar_source): """Normally, loads a pickled grammar by doing pkgutil.get_data(package, pickled_grammar) where *pickled_grammar* is computed from *grammar_source* by adding the Python version and using a ``.pickle`` extension. However, if *grammar_source* is an extant file, load_grammar(grammar_source) is called instead. This facilitates using a packaged grammar file when needed but preserves load_grammar's automatic regeneration behavior when possible. """ if os.path.isfile(grammar_source): return load_grammar(grammar_source) pickled_name = _generate_pickle_name(os.path.basename(grammar_source)) data = pkgutil.get_data(package, pickled_name) g = grammar.Grammar() g.loads(data) return g def main(*args): """Main program, when run as a script: produce grammar pickle files. Calls load_grammar for each argument, a path to a grammar text file. """ if not args: args = sys.argv[1:] logging.basicConfig(level=logging.INFO, stream=sys.stdout, format='%(message)s') for gt in args: load_grammar(gt, save=True, force=True) return True if __name__ == "__main__": sys.exit(int(not main())) token.py 0000755 00000002426 15027553031 0006246 0 ustar 00 #! /usr/bin/env python3 """Token constants (from "token.h").""" # Taken from Python (r53757) and modified to include some tokens # originally monkeypatched in by pgen2.tokenize #--start constants-- ENDMARKER = 0 NAME = 1 NUMBER = 2 STRING = 3 NEWLINE = 4 INDENT = 5 DEDENT = 6 LPAR = 7 RPAR = 8 LSQB = 9 RSQB = 10 COLON = 11 COMMA = 12 SEMI = 13 PLUS = 14 MINUS = 15 STAR = 16 SLASH = 17 VBAR = 18 AMPER = 19 LESS = 20 GREATER = 21 EQUAL = 22 DOT = 23 PERCENT = 24 BACKQUOTE = 25 LBRACE = 26 RBRACE = 27 EQEQUAL = 28 NOTEQUAL = 29 LESSEQUAL = 30 GREATEREQUAL = 31 TILDE = 32 CIRCUMFLEX = 33 LEFTSHIFT = 34 RIGHTSHIFT = 35 DOUBLESTAR = 36 PLUSEQUAL = 37 MINEQUAL = 38 STAREQUAL = 39 SLASHEQUAL = 40 PERCENTEQUAL = 41 AMPEREQUAL = 42 VBAREQUAL = 43 CIRCUMFLEXEQUAL = 44 LEFTSHIFTEQUAL = 45 RIGHTSHIFTEQUAL = 46 DOUBLESTAREQUAL = 47 DOUBLESLASH = 48 DOUBLESLASHEQUAL = 49 AT = 50 ATEQUAL = 51 OP = 52 COMMENT = 53 NL = 54 RARROW = 55 AWAIT = 56 ASYNC = 57 ERRORTOKEN = 58 COLONEQUAL = 59 N_TOKENS = 60 NT_OFFSET = 256 #--end constants-- tok_name = {} for _name, _value in list(globals().items()): if type(_value) is type(0): tok_name[_value] = _name def ISTERMINAL(x): return x < NT_OFFSET def ISNONTERMINAL(x): return x >= NT_OFFSET def ISEOF(x): return x == ENDMARKER parse.py 0000644 00000017733 15027553031 0006244 0 ustar 00 # Copyright 2004-2005 Elemental Security, Inc. All Rights Reserved. # Licensed to PSF under a Contributor Agreement. """Parser engine for the grammar tables generated by pgen. The grammar table must be loaded first. See Parser/parser.c in the Python distribution for additional info on how this parsing engine works. """ # Local imports from . import token class ParseError(Exception): """Exception to signal the parser is stuck.""" def __init__(self, msg, type, value, context): Exception.__init__(self, "%s: type=%r, value=%r, context=%r" % (msg, type, value, context)) self.msg = msg self.type = type self.value = value self.context = context def __reduce__(self): return type(self), (self.msg, self.type, self.value, self.context) class Parser(object): """Parser engine. The proper usage sequence is: p = Parser(grammar, [converter]) # create instance p.setup([start]) # prepare for parsing <for each input token>: if p.addtoken(...): # parse a token; may raise ParseError break root = p.rootnode # root of abstract syntax tree A Parser instance may be reused by calling setup() repeatedly. A Parser instance contains state pertaining to the current token sequence, and should not be used concurrently by different threads to parse separate token sequences. See driver.py for how to get input tokens by tokenizing a file or string. Parsing is complete when addtoken() returns True; the root of the abstract syntax tree can then be retrieved from the rootnode instance variable. When a syntax error occurs, addtoken() raises the ParseError exception. There is no error recovery; the parser cannot be used after a syntax error was reported (but it can be reinitialized by calling setup()). """ def __init__(self, grammar, convert=None): """Constructor. The grammar argument is a grammar.Grammar instance; see the grammar module for more information. The parser is not ready yet for parsing; you must call the setup() method to get it started. The optional convert argument is a function mapping concrete syntax tree nodes to abstract syntax tree nodes. If not given, no conversion is done and the syntax tree produced is the concrete syntax tree. If given, it must be a function of two arguments, the first being the grammar (a grammar.Grammar instance), and the second being the concrete syntax tree node to be converted. The syntax tree is converted from the bottom up. A concrete syntax tree node is a (type, value, context, nodes) tuple, where type is the node type (a token or symbol number), value is None for symbols and a string for tokens, context is None or an opaque value used for error reporting (typically a (lineno, offset) pair), and nodes is a list of children for symbols, and None for tokens. An abstract syntax tree node may be anything; this is entirely up to the converter function. """ self.grammar = grammar self.convert = convert or (lambda grammar, node: node) def setup(self, start=None): """Prepare for parsing. This *must* be called before starting to parse. The optional argument is an alternative start symbol; it defaults to the grammar's start symbol. You can use a Parser instance to parse any number of programs; each time you call setup() the parser is reset to an initial state determined by the (implicit or explicit) start symbol. """ if start is None: start = self.grammar.start # Each stack entry is a tuple: (dfa, state, node). # A node is a tuple: (type, value, context, children), # where children is a list of nodes or None, and context may be None. newnode = (start, None, None, []) stackentry = (self.grammar.dfas[start], 0, newnode) self.stack = [stackentry] self.rootnode = None self.used_names = set() # Aliased to self.rootnode.used_names in pop() def addtoken(self, type, value, context): """Add a token; return True iff this is the end of the program.""" # Map from token to label ilabel = self.classify(type, value, context) # Loop until the token is shifted; may raise exceptions while True: dfa, state, node = self.stack[-1] states, first = dfa arcs = states[state] # Look for a state with this label for i, newstate in arcs: t, v = self.grammar.labels[i] if ilabel == i: # Look it up in the list of labels assert t < 256 # Shift a token; we're done with it self.shift(type, value, newstate, context) # Pop while we are in an accept-only state state = newstate while states[state] == [(0, state)]: self.pop() if not self.stack: # Done parsing! return True dfa, state, node = self.stack[-1] states, first = dfa # Done with this token return False elif t >= 256: # See if it's a symbol and if we're in its first set itsdfa = self.grammar.dfas[t] itsstates, itsfirst = itsdfa if ilabel in itsfirst: # Push a symbol self.push(t, self.grammar.dfas[t], newstate, context) break # To continue the outer while loop else: if (0, state) in arcs: # An accepting state, pop it and try something else self.pop() if not self.stack: # Done parsing, but another token is input raise ParseError("too much input", type, value, context) else: # No success finding a transition raise ParseError("bad input", type, value, context) def classify(self, type, value, context): """Turn a token into a label. (Internal)""" if type == token.NAME: # Keep a listing of all used names self.used_names.add(value) # Check for reserved words ilabel = self.grammar.keywords.get(value) if ilabel is not None: return ilabel ilabel = self.grammar.tokens.get(type) if ilabel is None: raise ParseError("bad token", type, value, context) return ilabel def shift(self, type, value, newstate, context): """Shift a token. (Internal)""" dfa, state, node = self.stack[-1] newnode = (type, value, context, None) newnode = self.convert(self.grammar, newnode) if newnode is not None: node[-1].append(newnode) self.stack[-1] = (dfa, newstate, node) def push(self, type, newdfa, newstate, context): """Push a nonterminal. (Internal)""" dfa, state, node = self.stack[-1] newnode = (type, None, context, []) self.stack[-1] = (dfa, newstate, node) self.stack.append((newdfa, 0, newnode)) def pop(self): """Pop a nonterminal. (Internal)""" popdfa, popstate, popnode = self.stack.pop() newnode = self.convert(self.grammar, popnode) if newnode is not None: if self.stack: dfa, state, node = self.stack[-1] node[-1].append(newnode) else: self.rootnode = newnode self.rootnode.used_names = self.used_names pgen.py 0000644 00000033006 15027553031 0006052 0 ustar 00 # Copyright 2004-2005 Elemental Security, Inc. All Rights Reserved. # Licensed to PSF under a Contributor Agreement. # Pgen imports from . import grammar, token, tokenize class PgenGrammar(grammar.Grammar): pass class ParserGenerator(object): def __init__(self, filename, stream=None): close_stream = None if stream is None: stream = open(filename, encoding="utf-8") close_stream = stream.close self.filename = filename self.stream = stream self.generator = tokenize.generate_tokens(stream.readline) self.gettoken() # Initialize lookahead self.dfas, self.startsymbol = self.parse() if close_stream is not None: close_stream() self.first = {} # map from symbol name to set of tokens self.addfirstsets() def make_grammar(self): c = PgenGrammar() names = list(self.dfas.keys()) names.sort() names.remove(self.startsymbol) names.insert(0, self.startsymbol) for name in names: i = 256 + len(c.symbol2number) c.symbol2number[name] = i c.number2symbol[i] = name for name in names: dfa = self.dfas[name] states = [] for state in dfa: arcs = [] for label, next in sorted(state.arcs.items()): arcs.append((self.make_label(c, label), dfa.index(next))) if state.isfinal: arcs.append((0, dfa.index(state))) states.append(arcs) c.states.append(states) c.dfas[c.symbol2number[name]] = (states, self.make_first(c, name)) c.start = c.symbol2number[self.startsymbol] return c def make_first(self, c, name): rawfirst = self.first[name] first = {} for label in sorted(rawfirst): ilabel = self.make_label(c, label) ##assert ilabel not in first # XXX failed on <> ... != first[ilabel] = 1 return first def make_label(self, c, label): # XXX Maybe this should be a method on a subclass of converter? ilabel = len(c.labels) if label[0].isalpha(): # Either a symbol name or a named token if label in c.symbol2number: # A symbol name (a non-terminal) if label in c.symbol2label: return c.symbol2label[label] else: c.labels.append((c.symbol2number[label], None)) c.symbol2label[label] = ilabel return ilabel else: # A named token (NAME, NUMBER, STRING) itoken = getattr(token, label, None) assert isinstance(itoken, int), label assert itoken in token.tok_name, label if itoken in c.tokens: return c.tokens[itoken] else: c.labels.append((itoken, None)) c.tokens[itoken] = ilabel return ilabel else: # Either a keyword or an operator assert label[0] in ('"', "'"), label value = eval(label) if value[0].isalpha(): # A keyword if value in c.keywords: return c.keywords[value] else: c.labels.append((token.NAME, value)) c.keywords[value] = ilabel return ilabel else: # An operator (any non-numeric token) itoken = grammar.opmap[value] # Fails if unknown token if itoken in c.tokens: return c.tokens[itoken] else: c.labels.append((itoken, None)) c.tokens[itoken] = ilabel return ilabel def addfirstsets(self): names = list(self.dfas.keys()) names.sort() for name in names: if name not in self.first: self.calcfirst(name) #print name, self.first[name].keys() def calcfirst(self, name): dfa = self.dfas[name] self.first[name] = None # dummy to detect left recursion state = dfa[0] totalset = {} overlapcheck = {} for label, next in state.arcs.items(): if label in self.dfas: if label in self.first: fset = self.first[label] if fset is None: raise ValueError("recursion for rule %r" % name) else: self.calcfirst(label) fset = self.first[label] totalset.update(fset) overlapcheck[label] = fset else: totalset[label] = 1 overlapcheck[label] = {label: 1} inverse = {} for label, itsfirst in overlapcheck.items(): for symbol in itsfirst: if symbol in inverse: raise ValueError("rule %s is ambiguous; %s is in the" " first sets of %s as well as %s" % (name, symbol, label, inverse[symbol])) inverse[symbol] = label self.first[name] = totalset def parse(self): dfas = {} startsymbol = None # MSTART: (NEWLINE | RULE)* ENDMARKER while self.type != token.ENDMARKER: while self.type == token.NEWLINE: self.gettoken() # RULE: NAME ':' RHS NEWLINE name = self.expect(token.NAME) self.expect(token.OP, ":") a, z = self.parse_rhs() self.expect(token.NEWLINE) #self.dump_nfa(name, a, z) dfa = self.make_dfa(a, z) #self.dump_dfa(name, dfa) oldlen = len(dfa) self.simplify_dfa(dfa) newlen = len(dfa) dfas[name] = dfa #print name, oldlen, newlen if startsymbol is None: startsymbol = name return dfas, startsymbol def make_dfa(self, start, finish): # To turn an NFA into a DFA, we define the states of the DFA # to correspond to *sets* of states of the NFA. Then do some # state reduction. Let's represent sets as dicts with 1 for # values. assert isinstance(start, NFAState) assert isinstance(finish, NFAState) def closure(state): base = {} addclosure(state, base) return base def addclosure(state, base): assert isinstance(state, NFAState) if state in base: return base[state] = 1 for label, next in state.arcs: if label is None: addclosure(next, base) states = [DFAState(closure(start), finish)] for state in states: # NB states grows while we're iterating arcs = {} for nfastate in state.nfaset: for label, next in nfastate.arcs: if label is not None: addclosure(next, arcs.setdefault(label, {})) for label, nfaset in sorted(arcs.items()): for st in states: if st.nfaset == nfaset: break else: st = DFAState(nfaset, finish) states.append(st) state.addarc(st, label) return states # List of DFAState instances; first one is start def dump_nfa(self, name, start, finish): print("Dump of NFA for", name) todo = [start] for i, state in enumerate(todo): print(" State", i, state is finish and "(final)" or "") for label, next in state.arcs: if next in todo: j = todo.index(next) else: j = len(todo) todo.append(next) if label is None: print(" -> %d" % j) else: print(" %s -> %d" % (label, j)) def dump_dfa(self, name, dfa): print("Dump of DFA for", name) for i, state in enumerate(dfa): print(" State", i, state.isfinal and "(final)" or "") for label, next in sorted(state.arcs.items()): print(" %s -> %d" % (label, dfa.index(next))) def simplify_dfa(self, dfa): # This is not theoretically optimal, but works well enough. # Algorithm: repeatedly look for two states that have the same # set of arcs (same labels pointing to the same nodes) and # unify them, until things stop changing. # dfa is a list of DFAState instances changes = True while changes: changes = False for i, state_i in enumerate(dfa): for j in range(i+1, len(dfa)): state_j = dfa[j] if state_i == state_j: #print " unify", i, j del dfa[j] for state in dfa: state.unifystate(state_j, state_i) changes = True break def parse_rhs(self): # RHS: ALT ('|' ALT)* a, z = self.parse_alt() if self.value != "|": return a, z else: aa = NFAState() zz = NFAState() aa.addarc(a) z.addarc(zz) while self.value == "|": self.gettoken() a, z = self.parse_alt() aa.addarc(a) z.addarc(zz) return aa, zz def parse_alt(self): # ALT: ITEM+ a, b = self.parse_item() while (self.value in ("(", "[") or self.type in (token.NAME, token.STRING)): c, d = self.parse_item() b.addarc(c) b = d return a, b def parse_item(self): # ITEM: '[' RHS ']' | ATOM ['+' | '*'] if self.value == "[": self.gettoken() a, z = self.parse_rhs() self.expect(token.OP, "]") a.addarc(z) return a, z else: a, z = self.parse_atom() value = self.value if value not in ("+", "*"): return a, z self.gettoken() z.addarc(a) if value == "+": return a, z else: return a, a def parse_atom(self): # ATOM: '(' RHS ')' | NAME | STRING if self.value == "(": self.gettoken() a, z = self.parse_rhs() self.expect(token.OP, ")") return a, z elif self.type in (token.NAME, token.STRING): a = NFAState() z = NFAState() a.addarc(z, self.value) self.gettoken() return a, z else: self.raise_error("expected (...) or NAME or STRING, got %s/%s", self.type, self.value) def expect(self, type, value=None): if self.type != type or (value is not None and self.value != value): self.raise_error("expected %s/%s, got %s/%s", type, value, self.type, self.value) value = self.value self.gettoken() return value def gettoken(self): tup = next(self.generator) while tup[0] in (tokenize.COMMENT, tokenize.NL): tup = next(self.generator) self.type, self.value, self.begin, self.end, self.line = tup #print token.tok_name[self.type], repr(self.value) def raise_error(self, msg, *args): if args: try: msg = msg % args except: msg = " ".join([msg] + list(map(str, args))) raise SyntaxError(msg, (self.filename, self.end[0], self.end[1], self.line)) class NFAState(object): def __init__(self): self.arcs = [] # list of (label, NFAState) pairs def addarc(self, next, label=None): assert label is None or isinstance(label, str) assert isinstance(next, NFAState) self.arcs.append((label, next)) class DFAState(object): def __init__(self, nfaset, final): assert isinstance(nfaset, dict) assert isinstance(next(iter(nfaset)), NFAState) assert isinstance(final, NFAState) self.nfaset = nfaset self.isfinal = final in nfaset self.arcs = {} # map from label to DFAState def addarc(self, next, label): assert isinstance(label, str) assert label not in self.arcs assert isinstance(next, DFAState) self.arcs[label] = next def unifystate(self, old, new): for label, next in self.arcs.items(): if next is old: self.arcs[label] = new def __eq__(self, other): # Equality test -- ignore the nfaset instance variable assert isinstance(other, DFAState) if self.isfinal != other.isfinal: return False # Can't just return self.arcs == other.arcs, because that # would invoke this method recursively, with cycles... if len(self.arcs) != len(other.arcs): return False for label, next in self.arcs.items(): if next is not other.arcs.get(label): return False return True __hash__ = None # For Py3 compatibility. def generate_grammar(filename="Grammar.txt"): p = ParserGenerator(filename) return p.make_grammar() conv.py 0000644 00000022652 15027553031 0006073 0 ustar 00 # Copyright 2004-2005 Elemental Security, Inc. All Rights Reserved. # Licensed to PSF under a Contributor Agreement. """Convert graminit.[ch] spit out by pgen to Python code. Pgen is the Python parser generator. It is useful to quickly create a parser from a grammar file in Python's grammar notation. But I don't want my parsers to be written in C (yet), so I'm translating the parsing tables to Python data structures and writing a Python parse engine. Note that the token numbers are constants determined by the standard Python tokenizer. The standard token module defines these numbers and their names (the names are not used much). The token numbers are hardcoded into the Python tokenizer and into pgen. A Python implementation of the Python tokenizer is also available, in the standard tokenize module. On the other hand, symbol numbers (representing the grammar's non-terminals) are assigned by pgen based on the actual grammar input. Note: this module is pretty much obsolete; the pgen module generates equivalent grammar tables directly from the Grammar.txt input file without having to invoke the Python pgen C program. """ # Python imports import re # Local imports from pgen2 import grammar, token class Converter(grammar.Grammar): """Grammar subclass that reads classic pgen output files. The run() method reads the tables as produced by the pgen parser generator, typically contained in two C files, graminit.h and graminit.c. The other methods are for internal use only. See the base class for more documentation. """ def run(self, graminit_h, graminit_c): """Load the grammar tables from the text files written by pgen.""" self.parse_graminit_h(graminit_h) self.parse_graminit_c(graminit_c) self.finish_off() def parse_graminit_h(self, filename): """Parse the .h file written by pgen. (Internal) This file is a sequence of #define statements defining the nonterminals of the grammar as numbers. We build two tables mapping the numbers to names and back. """ try: f = open(filename) except OSError as err: print("Can't open %s: %s" % (filename, err)) return False self.symbol2number = {} self.number2symbol = {} lineno = 0 for line in f: lineno += 1 mo = re.match(r"^#define\s+(\w+)\s+(\d+)$", line) if not mo and line.strip(): print("%s(%s): can't parse %s" % (filename, lineno, line.strip())) else: symbol, number = mo.groups() number = int(number) assert symbol not in self.symbol2number assert number not in self.number2symbol self.symbol2number[symbol] = number self.number2symbol[number] = symbol return True def parse_graminit_c(self, filename): """Parse the .c file written by pgen. (Internal) The file looks as follows. The first two lines are always this: #include "pgenheaders.h" #include "grammar.h" After that come four blocks: 1) one or more state definitions 2) a table defining dfas 3) a table defining labels 4) a struct defining the grammar A state definition has the following form: - one or more arc arrays, each of the form: static arc arcs_<n>_<m>[<k>] = { {<i>, <j>}, ... }; - followed by a state array, of the form: static state states_<s>[<t>] = { {<k>, arcs_<n>_<m>}, ... }; """ try: f = open(filename) except OSError as err: print("Can't open %s: %s" % (filename, err)) return False # The code below essentially uses f's iterator-ness! lineno = 0 # Expect the two #include lines lineno, line = lineno+1, next(f) assert line == '#include "pgenheaders.h"\n', (lineno, line) lineno, line = lineno+1, next(f) assert line == '#include "grammar.h"\n', (lineno, line) # Parse the state definitions lineno, line = lineno+1, next(f) allarcs = {} states = [] while line.startswith("static arc "): while line.startswith("static arc "): mo = re.match(r"static arc arcs_(\d+)_(\d+)\[(\d+)\] = {$", line) assert mo, (lineno, line) n, m, k = list(map(int, mo.groups())) arcs = [] for _ in range(k): lineno, line = lineno+1, next(f) mo = re.match(r"\s+{(\d+), (\d+)},$", line) assert mo, (lineno, line) i, j = list(map(int, mo.groups())) arcs.append((i, j)) lineno, line = lineno+1, next(f) assert line == "};\n", (lineno, line) allarcs[(n, m)] = arcs lineno, line = lineno+1, next(f) mo = re.match(r"static state states_(\d+)\[(\d+)\] = {$", line) assert mo, (lineno, line) s, t = list(map(int, mo.groups())) assert s == len(states), (lineno, line) state = [] for _ in range(t): lineno, line = lineno+1, next(f) mo = re.match(r"\s+{(\d+), arcs_(\d+)_(\d+)},$", line) assert mo, (lineno, line) k, n, m = list(map(int, mo.groups())) arcs = allarcs[n, m] assert k == len(arcs), (lineno, line) state.append(arcs) states.append(state) lineno, line = lineno+1, next(f) assert line == "};\n", (lineno, line) lineno, line = lineno+1, next(f) self.states = states # Parse the dfas dfas = {} mo = re.match(r"static dfa dfas\[(\d+)\] = {$", line) assert mo, (lineno, line) ndfas = int(mo.group(1)) for i in range(ndfas): lineno, line = lineno+1, next(f) mo = re.match(r'\s+{(\d+), "(\w+)", (\d+), (\d+), states_(\d+),$', line) assert mo, (lineno, line) symbol = mo.group(2) number, x, y, z = list(map(int, mo.group(1, 3, 4, 5))) assert self.symbol2number[symbol] == number, (lineno, line) assert self.number2symbol[number] == symbol, (lineno, line) assert x == 0, (lineno, line) state = states[z] assert y == len(state), (lineno, line) lineno, line = lineno+1, next(f) mo = re.match(r'\s+("(?:\\\d\d\d)*")},$', line) assert mo, (lineno, line) first = {} rawbitset = eval(mo.group(1)) for i, c in enumerate(rawbitset): byte = ord(c) for j in range(8): if byte & (1<<j): first[i*8 + j] = 1 dfas[number] = (state, first) lineno, line = lineno+1, next(f) assert line == "};\n", (lineno, line) self.dfas = dfas # Parse the labels labels = [] lineno, line = lineno+1, next(f) mo = re.match(r"static label labels\[(\d+)\] = {$", line) assert mo, (lineno, line) nlabels = int(mo.group(1)) for i in range(nlabels): lineno, line = lineno+1, next(f) mo = re.match(r'\s+{(\d+), (0|"\w+")},$', line) assert mo, (lineno, line) x, y = mo.groups() x = int(x) if y == "0": y = None else: y = eval(y) labels.append((x, y)) lineno, line = lineno+1, next(f) assert line == "};\n", (lineno, line) self.labels = labels # Parse the grammar struct lineno, line = lineno+1, next(f) assert line == "grammar _PyParser_Grammar = {\n", (lineno, line) lineno, line = lineno+1, next(f) mo = re.match(r"\s+(\d+),$", line) assert mo, (lineno, line) ndfas = int(mo.group(1)) assert ndfas == len(self.dfas) lineno, line = lineno+1, next(f) assert line == "\tdfas,\n", (lineno, line) lineno, line = lineno+1, next(f) mo = re.match(r"\s+{(\d+), labels},$", line) assert mo, (lineno, line) nlabels = int(mo.group(1)) assert nlabels == len(self.labels), (lineno, line) lineno, line = lineno+1, next(f) mo = re.match(r"\s+(\d+)$", line) assert mo, (lineno, line) start = int(mo.group(1)) assert start in self.number2symbol, (lineno, line) self.start = start lineno, line = lineno+1, next(f) assert line == "};\n", (lineno, line) try: lineno, line = lineno+1, next(f) except StopIteration: pass else: assert 0, (lineno, line) def finish_off(self): """Create additional useful structures. (Internal).""" self.keywords = {} # map from keyword strings to arc labels self.tokens = {} # map from numeric token values to arc labels for ilabel, (type, value) in enumerate(self.labels): if type == token.NAME and value is not None: self.keywords[value] = ilabel elif value is None: self.tokens[type] = ilabel __init__.py 0000644 00000000217 15027553031 0006656 0 ustar 00 # Copyright 2004-2005 Elemental Security, Inc. All Rights Reserved. # Licensed to PSF under a Contributor Agreement. """The pgen2 package."""
| ver. 1.4 |
Github
|
.
| PHP 8.2.28 | Generation time: 0.02 |
proxy
|
phpinfo
|
Settings