0 "ˆl–ßi~”*e¶¥8 Ap-\lJbÑ¿Á ƒh¹À¿#ˆl–ßi~” Ji?u2 \¸®õ1hß „ í„ÁÀonline ?÷import re import sys # Reason last stmt is continued (or C_NONE if it's not). (C_NONE, C_BACKSLASH, C_STRING_FIRST_LINE, C_STRING_NEXT_LINES, C_BRACKET) = range(5) if 0: # for throwaway debugging output def dump(*stuff): sys.__stdout__.write(" ".join(map(str, stuff)) + "\n") # Find what looks like the start of a popular stmt. _synchre = re.compile(r""" ^ [ \t]* (?: while | else | def | return | assert | break | class | continue | elif | try | except | raise | import | yield ) \b """, re.VERBOSE | re.MULTILINE).search # Match blank line or non-indenting comment line. _junkre = re.compile(r""" [ \t]* (?: \# \S .* )? \n """, re.VERBOSE).match # Match any flavor of string; the terminating quote is optional # so that we're robust in the face of incomplete program text. _match_stringre = re.compile(r""" \""" [^"\\]* (?: (?: \\. | "(?!"") ) [^"\\]* )* (?: \""" )? | " [^"\\\n]* (?: \\. [^"\\\n]* )* "? | ''' [^'\\]* (?: (?: \\. | '(?!'') ) [^'\\]* )* (?: ''' )? | ' [^'\\\n]* (?: \\. [^'\\\n]* )* '? """, re.VERBOSE | re.DOTALL).match # Match a line that starts with something interesting; # used to find the first item of a bracket structure. _itemre = re.compile(r""" [ \t]* [^\s#\\] # if we match, m.end()-1 is the interesting char """, re.VERBOSE).match # Match start of stmts that should be followed by a dedent. _closere = re.compile(r""" \s* (?: return | break | continue | raise | pass ) \b """, re.VERBOSE).match # Chew up non-special chars as quickly as possible. If match is # successful, m.end() less 1 is the index of the last boring char # matched. If match is unsuccessful, the string starts with an # interesting char. _chew_ordinaryre = re.compile(r""" [^[\](){}#'"\\]+ """, re.VERBOSE).match # Build translation table to map uninteresting chars to "x", open # brackets to "(", and close brackets to ")". _tran = ['x'] * 256 for ch in "({[": _tran[ord(ch)] = '(' for ch in ")}]": _tran[ord(ch)] = ')' for ch in "\"'\\\n#": _tran[ord(ch)] = ch _tran = ''.join(_tran) del ch try: UnicodeType = type(unicode("")) except NameError: UnicodeType = None class Parser: def __init__(self, indentwidth, tabwidth): self.indentwidth = indentwidth self.tabwidth = tabwidth def set_str(self, str): assert len(str) == 0 or str[-1] == '\n' if type(str) is UnicodeType: # The parse functions have no idea what to do with Unicode, so # replace all Unicode characters with "x". This is "safe" # so long as the only characters germane to parsing the structure # of Python are 7-bit ASCII. It's *necessary* because Unicode # strings don't have a .translate() method that supports # deletechars. uniphooey = str str = [] push = str.append for raw in map(ord, uniphooey): push(raw < 127 and chr(raw) or "x") str = "".join(str) self.str = str self.study_level = 0 # Return index of a good place to begin parsing, as close to the # end of the string as possible. This will be the start of some # popular stmt like "if" or "def". Return None if none found: # the caller should pass more prior context then, if possible, or # if not (the entire program text up until the point of interest # has already been tried) pass 0 to set_lo. # # This will be reliable iff given a reliable is_char_in_string # function, meaning that when it says "no", it's absolutely # guaranteed that the char is not in a string. def find_good_parse_start(self, is_char_in_string=None,