blob: 6471635a3192dd7028e991b6c79cb15743e5184c [file] [log] [blame]
xf.li86118912025-03-19 20:07:27 -07001# Copyright 2004-2005 Elemental Security, Inc. All Rights Reserved.
2# Licensed to PSF under a Contributor Agreement.
3
4# Modifications:
5# Copyright 2006 Google, Inc. All Rights Reserved.
6# Licensed to PSF under a Contributor Agreement.
7
8"""Parser driver.
9
10This provides a high-level interface to parse a file into a syntax tree.
11
12"""
13
14__author__ = "Guido van Rossum <guido@python.org>"
15
16__all__ = ["Driver", "load_grammar"]
17
18# Python imports
19import io
20import os
21import logging
22import pkgutil
23import sys
24
25# Pgen imports
26from . import grammar, parse, token, tokenize, pgen
27
28
29class Driver(object):
30
31 def __init__(self, grammar, convert=None, logger=None):
32 self.grammar = grammar
33 if logger is None:
34 logger = logging.getLogger()
35 self.logger = logger
36 self.convert = convert
37
38 def parse_tokens(self, tokens, debug=False):
39 """Parse a series of tokens and return the syntax tree."""
40 # XXX Move the prefix computation into a wrapper around tokenize.
41 p = parse.Parser(self.grammar, self.convert)
42 p.setup()
43 lineno = 1
44 column = 0
45 type = value = start = end = line_text = None
46 prefix = ""
47 for quintuple in tokens:
48 type, value, start, end, line_text = quintuple
49 if start != (lineno, column):
50 assert (lineno, column) <= start, ((lineno, column), start)
51 s_lineno, s_column = start
52 if lineno < s_lineno:
53 prefix += "\n" * (s_lineno - lineno)
54 lineno = s_lineno
55 column = 0
56 if column < s_column:
57 prefix += line_text[column:s_column]
58 column = s_column
59 if type in (tokenize.COMMENT, tokenize.NL):
60 prefix += value
61 lineno, column = end
62 if value.endswith("\n"):
63 lineno += 1
64 column = 0
65 continue
66 if type == token.OP:
67 type = grammar.opmap[value]
68 if debug:
69 self.logger.debug("%s %r (prefix=%r)",
70 token.tok_name[type], value, prefix)
71 if p.addtoken(type, value, (prefix, start)):
72 if debug:
73 self.logger.debug("Stop.")
74 break
75 prefix = ""
76 lineno, column = end
77 if value.endswith("\n"):
78 lineno += 1
79 column = 0
80 else:
81 # We never broke out -- EOF is too soon (how can this happen???)
82 raise parse.ParseError("incomplete input",
83 type, value, (prefix, start))
84 return p.rootnode
85
86 def parse_stream_raw(self, stream, debug=False):
87 """Parse a stream and return the syntax tree."""
88 tokens = tokenize.generate_tokens(stream.readline)
89 return self.parse_tokens(tokens, debug)
90
91 def parse_stream(self, stream, debug=False):
92 """Parse a stream and return the syntax tree."""
93 return self.parse_stream_raw(stream, debug)
94
95 def parse_file(self, filename, encoding=None, debug=False):
96 """Parse a file and return the syntax tree."""
97 with io.open(filename, "r", encoding=encoding) as stream:
98 return self.parse_stream(stream, debug)
99
100 def parse_string(self, text, debug=False):
101 """Parse a string and return the syntax tree."""
102 tokens = tokenize.generate_tokens(io.StringIO(text).readline)
103 return self.parse_tokens(tokens, debug)
104
105
106def _generate_pickle_name(gt):
107 head, tail = os.path.splitext(gt)
108 if tail == ".txt":
109 tail = ""
110 return head + tail + ".".join(map(str, sys.version_info)) + ".pickle"
111
112
113def load_grammar(gt="Grammar.txt", gp=None,
114 save=True, force=False, logger=None):
115 """Load the grammar (maybe from a pickle)."""
116 if logger is None:
117 logger = logging.getLogger()
118 gp = _generate_pickle_name(gt) if gp is None else gp
119 if force or not _newer(gp, gt):
120 logger.info("Generating grammar tables from %s", gt)
121 g = pgen.generate_grammar(gt)
122 if save:
123 logger.info("Writing grammar tables to %s", gp)
124 try:
125 g.dump(gp)
126 except OSError as e:
127 logger.info("Writing failed: %s", e)
128 else:
129 g = grammar.Grammar()
130 g.load(gp)
131 return g
132
133
134def _newer(a, b):
135 """Inquire whether file a was written since file b."""
136 if not os.path.exists(a):
137 return False
138 if not os.path.exists(b):
139 return True
140 return os.path.getmtime(a) >= os.path.getmtime(b)
141
142
143def load_packaged_grammar(package, grammar_source):
144 """Normally, loads a pickled grammar by doing
145 pkgutil.get_data(package, pickled_grammar)
146 where *pickled_grammar* is computed from *grammar_source* by adding the
147 Python version and using a ``.pickle`` extension.
148
149 However, if *grammar_source* is an extant file, load_grammar(grammar_source)
150 is called instead. This facilitates using a packaged grammar file when needed
151 but preserves load_grammar's automatic regeneration behavior when possible.
152
153 """
154 if os.path.isfile(grammar_source):
155 return load_grammar(grammar_source)
156 pickled_name = _generate_pickle_name(os.path.basename(grammar_source))
157 data = pkgutil.get_data(package, pickled_name)
158 g = grammar.Grammar()
159 g.loads(data)
160 return g
161
162
163def main(*args):
164 """Main program, when run as a script: produce grammar pickle files.
165
166 Calls load_grammar for each argument, a path to a grammar text file.
167 """
168 if not args:
169 args = sys.argv[1:]
170 logging.basicConfig(level=logging.INFO, stream=sys.stdout,
171 format='%(message)s')
172 for gt in args:
173 load_grammar(gt, save=True, force=True)
174 return True
175
176if __name__ == "__main__":
177 sys.exit(int(not main()))