| 
									
										
										
										
											2008-03-19 05:04:44 +00:00
										 |  |  | # 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 os | 
					
						
							|  |  |  | import logging | 
					
						
							|  |  |  | import sys | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | # Pgen imports | 
					
						
							| 
									
										
											  
											
												Merged revisions 61724-61725 via svnmerge from
svn+ssh://pythondev@svn.python.org/python/trunk
................
  r61724 | martin.v.loewis | 2008-03-22 01:01:12 +0100 (Sa, 22 Mär 2008) | 49 lines
  Merged revisions 61602-61723 via svnmerge from
  svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3
  ........
    r61626 | david.wolever | 2008-03-19 17:19:16 +0100 (Mi, 19 Mär 2008) | 1 line
    Added fixer for implicit local imports.  See #2414.
  ........
    r61628 | david.wolever | 2008-03-19 17:57:43 +0100 (Mi, 19 Mär 2008) | 1 line
    Added a class for tests which should not run if a particular import is found.
  ........
    r61629 | collin.winter | 2008-03-19 17:58:19 +0100 (Mi, 19 Mär 2008) | 1 line
    Two more relative import fixes in pgen2.
  ........
    r61635 | david.wolever | 2008-03-19 20:16:03 +0100 (Mi, 19 Mär 2008) | 1 line
    Fixed print fixer so it will do the Right Thing when it encounters __future__.print_function.  2to3 gets upset, though, so the tests have been commented out.
  ........
    r61637 | david.wolever | 2008-03-19 21:37:17 +0100 (Mi, 19 Mär 2008) | 3 lines
    Added a fixer for itertools imports (from itertools import imap, ifilterfalse --> from itertools import filterfalse)
  ........
    r61645 | david.wolever | 2008-03-19 23:22:35 +0100 (Mi, 19 Mär 2008) | 1 line
    SVN is happier when you add the files you create... -_-'
  ........
    r61654 | david.wolever | 2008-03-20 01:09:56 +0100 (Do, 20 Mär 2008) | 1 line
    Added an explicit sort order to fixers -- fixes problems like #2427
  ........
    r61664 | david.wolever | 2008-03-20 04:32:40 +0100 (Do, 20 Mär 2008) | 3 lines
    Fixes #2428 -- comments are no longer eatten by __future__ fixer.
  ........
    r61673 | david.wolever | 2008-03-20 17:22:40 +0100 (Do, 20 Mär 2008) | 1 line
    Added 2to3 node pretty-printer
  ........
    r61679 | david.wolever | 2008-03-20 20:50:42 +0100 (Do, 20 Mär 2008) | 1 line
    Made node printing a little bit prettier
  ........
    r61723 | martin.v.loewis | 2008-03-22 00:59:27 +0100 (Sa, 22 Mär 2008) | 2 lines
    Fix whitespace.
  ........
................
  r61725 | martin.v.loewis | 2008-03-22 01:02:41 +0100 (Sa, 22 Mär 2008) | 2 lines
  Install lib2to3.
................
											
										 
											2008-03-22 00:07:09 +00:00
										 |  |  | from . import grammar, parse, token, tokenize, pgen | 
					
						
							| 
									
										
										
										
											2008-03-19 05:04:44 +00:00
										 |  |  | 
 | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 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", t, v, x) | 
					
						
							|  |  |  |         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, debug=False): | 
					
						
							|  |  |  |         """Parse a file and return the syntax tree.""" | 
					
						
							|  |  |  |         stream = open(filename) | 
					
						
							|  |  |  |         try: | 
					
						
							|  |  |  |             return self.parse_stream(stream, debug) | 
					
						
							|  |  |  |         finally: | 
					
						
							|  |  |  |             stream.close() | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  |     def parse_string(self, text, debug=False): | 
					
						
							|  |  |  |         """Parse a string and return the syntax tree.""" | 
					
						
							| 
									
										
										
										
											2008-03-19 05:33:36 +00:00
										 |  |  |         tokens = tokenize.generate_tokens(generate_lines(text).__next__) | 
					
						
							| 
									
										
										
										
											2008-03-19 05:04:44 +00:00
										 |  |  |         return self.parse_tokens(tokens, debug) | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | def generate_lines(text): | 
					
						
							|  |  |  |     """Generator that behaves like readline without using StringIO.""" | 
					
						
							|  |  |  |     for line in text.splitlines(True): | 
					
						
							|  |  |  |         yield line | 
					
						
							|  |  |  |     while True: | 
					
						
							|  |  |  |         yield "" | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 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() | 
					
						
							|  |  |  |     if gp is None: | 
					
						
							|  |  |  |         head, tail = os.path.splitext(gt) | 
					
						
							|  |  |  |         if tail == ".txt": | 
					
						
							|  |  |  |             tail = "" | 
					
						
							|  |  |  |         gp = head + tail + ".".join(map(str, sys.version_info)) + ".pickle" | 
					
						
							|  |  |  |     if force or not _newer(gp, gt): | 
					
						
							|  |  |  |         logger.info("Generating grammar tables from %s", gt) | 
					
						
							|  |  |  |         g = pgen.generate_grammar(gt) | 
					
						
							|  |  |  |         if save: | 
					
						
							|  |  |  |             logger.info("Writing grammar tables to %s", gp) | 
					
						
							| 
									
										
										
										
											2008-05-25 17:22:03 +00:00
										 |  |  |             try: | 
					
						
							|  |  |  |                 g.dump(gp) | 
					
						
							|  |  |  |             except IOError as e: | 
					
						
							|  |  |  |                 logger.info("Writing failed:"+str(e)) | 
					
						
							| 
									
										
										
										
											2008-03-19 05:04:44 +00:00
										 |  |  |     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) |