�&ǐk�@'bJ�h�ۊL'}T� :��'2�Z#$��n�a��� �>a��`��_3d�Qpt�/�P -��#5�,�M��� �pA:©�q�����NW��ډ�A���� �9nʺج���� �TSM��{J6?7��r�@�\����D��� �׶���s�f�TJj?"��D��`?��̒� b�#�%�C*v�$�{�$����5Ծ�F�s��y�e/8��h-�f�̰&(����Gj�L:U� 2�� ����v�_k����Y��gp,�k�WF�R������_C�R��N@���R�@�ߔ?A�w9���F("iNa-S���Q�o�3tDMLh*�#4k�T/iQ��Y*�G��m����)��8�hBm/�I�,g�ﯖ���Z��}�Cz�q@´��d.����L�ŕ�,��1�Z�܌�: ̪���F+J-'��c�tvJ8��]Q-��b��y �6;*J`r_�d ��'�G ~p��)'�C,�%F��E(��2�k�����lР�z�!�=t ��_�0��f7��� ;�p�|�U �%= len(indent): self.tokens.append(indent) self.prev_col = len(indent) startline = False 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): indents = [] toks_append = self.tokens.append startline = token[0] in (NEWLINE, NL) prevstring = False for tok in _itertools.chain([token], iterable): toknum, tokval = tok[:2] if toknum == ENCODING: self.encoding = tokval continue if toknum in (NAME, NUMBER): tokval += ' ' # Insert a space between two consecutive strings if toknum == STRING: if prevstring: tokval = ' ' + tokval prevstring = True else: prevstring = False 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) def untokenize(iterable): """Transform tokens back into Python source code. It returns a bytes object, encoded using the ENCODING token, which is the first token sequence output by tokenize. 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 bytes will tokenize back to the input t1 = [tok[:2] for tok in tokenize(f.readline)] newcode = untokenize(t1) readline = BytesIO(newcode).readline t2 = [tok[:2] for tok in tokenize(readline)] assert t1 == t2 """ ut = Untokenizer() out = ut.untokenize(iterable) if ut.encoding is not None: out = out.encode(ut.encoding) return out 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. """ try: filename = readline.__self__.name except AttributeError: filename = None bom_found = False encoding = None default = 'utf-8' def read_or_stop(): try: return readline() except StopIteration: return b'' def find_cookie(line): try: # Decode as UTF-8. Either the line is an encoding declaration, # in which case it should be pure ASCII, or it must be UTF-8 # per default encoding. line_string = line.decode('utf-8') except UnicodeDecodeError: msg = "invalid or missing encoding declaration" if filename is not None: msg = '{} for {!r}'.format(msg, filename) raise SyntaxError(msg) 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 if filename is None: msg = "unknown encoding: " + encoding else: msg = "unknown encoding for {!r}: {}".format(filename, encoding) raise SyntaxError(msg) if bom_found: if encoding != 'utf-8': # This behaviour mimics the Python interpreter if filename is None: msg = 'encoding problem: utf-8' else: msg = 'encoding problem for {!r}: utf-8'.format(filename) raise SyntaxError(msg) 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 open(filename): """Open a file in read only mode using the encoding detected by detect_encoding(). """ buffer = _builtin_open(filename, 'rb') try: encoding, lines = detect_encoding(buffer.readline) buffer.seek(0) text = TextIOWrapper(buffer, encoding, line_buffering=True) text.mode = 'r' return text except: buffer.close() raise def tokenize(readline): """ The tokenize() 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 bytes. Alternatively, readline can be a callable function terminating with StopIteration: readline = open(myfile, 'rb').__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. The first token sequence will always be an ENCODING token which tells you which encoding was used to decode the bytes stream. """ encoding, consumed = detect_encoding(readline) empty = _itertools.repeat(b"") rl_gen = _itertools.chain(consumed, iter(readline, b""), empty) return _tokenize(rl_gen.__next__, encoding) def _tokenize(readline, encoding): lnum = parenlev = continued = 0 numchars = '0123456789' contstr, needcont = '', 0 contline = None indents = [0] if encoding is not None: if encoding == "utf-8-sig": # BOM will already have been stripped. encoding = "utf-8" yield TokenInfo(ENCODING, encoding, (0, 0), (0, 0), '') last_line = b'' line = b'' while True: # loop over lines in stream try: # We capture the value of the line variable here because # readline uses the empty string '' to signal end of input, # hence `line` itself will always be overwritten at the end # of this loop. last_line = line line = readline() except StopIteration: line = b'' if encoding is not None: line = line.decode(encoding) 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 TokenInfo(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 TokenInfo(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 += 1 elif line[pos] == '\t': column = (column//tabsize + 1)*tabsize elif line[pos] == '\f': column = 0 else: break pos += 1 if pos == max: break if line[pos] in '#\r\n': # skip comments or blank lines if line[pos] == '#': comment_token = line[pos:].rstrip('\r\n') yield TokenInfo(COMMENT, comment_token, (lnum, pos), (lnum, pos + len(comment_token)), line) pos += len(comment_token) yield TokenInfo(NL, line[pos:], (lnum, pos), (lnum, len(line)), line) continue if column > indents[-1]: # count indents or dedents indents.append(column) yield TokenInfo(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", ("", lnum, pos, line)) indents = indents[:-1] yield TokenInfo(DEDENT, '', (lnum, pos), (lnum, pos), line) else: # continued statement if not line: raise TokenError("EOF in multi-line statement", (lnum, 0)) continued = 0 while pos < max: pseudomatch = _compile(PseudoToken).match(line, pos) if pseudomatch: # scan for tokens start, end = pseudomatch.span(1) spos, epos, pos = (lnum, start), (lnum, end), end if start == end: continue token, initial = line[start:end], line[start] if (initial in numchars or # ordinary number (initial == '.' and token != '.' and token != '...')): yield TokenInfo(NUMBER, token, spos, epos, line) elif initial in '\r\n': if parenlev > 0: yield TokenInfo(NL, token, spos, epos, line) else: yield TokenInfo(NEWLINE, token, spos, epos, line) elif initial == '#': assert not token.endswith("\n") yield TokenInfo(COMMENT, token, spos, epos, line) elif token in triple_quoted: endprog = _compile(endpats[token]) endmatch = endprog.match(line, pos) if endmatch: # all on one line pos = endmatch.end(0) token = line[start:pos] yield TokenInfo(STRING, token, spos, (lnum, pos), line) else: strstart = (lnum, start) # multiple lines contstr = line[start:] contline = line break # Check up to the first 3 chars of the token to see if # they're in the single_quoted set. If so, they start # a string. # We're using the first 3, because we're looking for # "rb'" (for example) at the start of the token. If # we switch to longer prefixes, this needs to be # adjusted. # Note that initial == token[:1]. # Also note that single quote checking must come after # triple quote checking (above). 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) # Again, using the first 3 chars of the # token. This is looking for the matching end # regex for the correct type of quote # character. So it's really looking for # endpats["'"] or endpats['"'], by trying to # skip string prefix characters, if any. endprog = _compile(endpats.get(initial) or endpats.get(token[1]) or endpats.get(token[2])) contstr, needcont = line[start:], 1 contline = line break else: # ordinary string yield TokenInfo(STRING, token, spos, epos, line) elif initial.isidentifier(): # ordinary name yield TokenInfo(NAME, token, spos, epos, line) elif initial == '\\': # continued stmt continued = 1 else: if initial in '([{': parenlev += 1 elif initial in ')]}': parenlev -= 1 yield TokenInfo(OP, token, spos, epos, line) else: yield TokenInfo(ERRORTOKEN, line[pos], (lnum, pos), (lnum, pos+1), line) pos += 1 # Add an implicit NEWLINE if the input doesn't end in one if last_line and last_line[-1] not in '\r\n': yield TokenInfo(NEWLINE, '', (lnum - 1, len(last_line)), (lnum - 1, len(last_line) + 1), '') for indent in indents[1:]: # pop remaining indent levels yield TokenInfo(DEDENT, '', (lnum, 0), (lnum, 0), '') yield TokenInfo(ENDMARKER, '', (lnum, 0), (lnum, 0), '') def generate_tokens(readline): """Tokenize a source reading Python code as unicode strings. This has the same API as tokenize(), except that it expects the *readline* callable to return str objects instead of bytes. """ return _tokenize(readline, None) def main(): import argparse # Helper error handling routines def perror(message): sys.stderr.write(message) sys.stderr.write('\n') def error(message, filename=None, location=None): if location: args = (filename,) + location + (message,) perror("%s:%d:%d: error: %s" % args) elif filename: perror("%s: error: %s" % (filename, message)) else: perror("error: %s" % message) sys.exit(1) # Parse the arguments and options parser = argparse.ArgumentParser(prog='python -m tokenize') parser.add_argument(dest='filename', nargs='?', metavar='filename.py', help='the file to tokenize; defaults to stdin') parser.add_argument('-e', '--exact', dest='exact', action='store_true', help='display token names using the exact type') args = parser.parse_args() try: # Tokenize the input if args.filename: filename = args.filename with _builtin_open(filename, 'rb') as f: tokens = list(tokenize(f.readline)) else: filename = "" tokens = _tokenize(sys.stdin.readline, None) # Output the tokenization for token in tokens: token_type = token.type if args.exact: token_type = token.exact_type token_range = "%d,%d-%d,%d:" % (token.start + token.end) print("%-20s%-15s%-15r" % (token_range, tok_name[token_type], token.string)) except IndentationError as err: line, column = err.args[1][1:3] error(err.args[0], filename, (line, column)) except TokenError as err: line, column = err.args[1] error(err.args[0], filename, (line, column)) except SyntaxError as err: error(err, filename) except OSError as err: error(err) except KeyboardInterrupt: print("interrupted\n") except Exception as err: perror("unexpected error: %s" % err) raise if __name__ == "__main__": main()