summaryrefslogtreecommitdiffstats
path: root/Lib/lib2to3/pgen2/driver.py
blob: e7828ffe160f37c145de6aee16a99b34bd141eda (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
# 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 codecs
import io
import os
import logging
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."""
        stream = codecs.open(filename, "r", encoding)
        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."""
        tokens = tokenize.generate_tokens(io.StringIO(text).readline)
        return self.parse_tokens(tokens, debug)


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)
            try:
                g.dump(gp)
            except IOError as e:
                logger.info("Writing failed:"+str(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)