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
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
"""
    pygments.lexers.diff
    ~~~~~~~~~~~~~~~~~~~~

    Lexers for diff/patch formats.

    :copyright: Copyright 2006-2022 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import re

from pygments.lexer import RegexLexer, include, bygroups
from pygments.token import Text, Comment, Operator, Keyword, Name, Generic, \
    Literal, Whitespace

__all__ = ['DiffLexer', 'DarcsPatchLexer', 'WDiffLexer']


class DiffLexer(RegexLexer):
    """
    Lexer for unified or context-style diffs or patches.
    """

    name = 'Diff'
    aliases = ['diff', 'udiff']
    filenames = ['*.diff', '*.patch']
    mimetypes = ['text/x-diff', 'text/x-patch']

    tokens = {
        'root': [
            (r'( )(.*)(\n)', bygroups(Whitespace, Text, Whitespace)),
            (r'(\+.*)(\n)', bygroups(Generic.Inserted, Whitespace)),
            (r'(-.*)(\n)', bygroups(Generic.Deleted, Whitespace)),
            (r'(!.*)(\n)', bygroups(Generic.Strong, Whitespace)),
            (r'(@.*)(\n)', bygroups(Generic.Subheading, Whitespace)),
            (r'((?:[Ii]ndex|diff).*)(\n)', bygroups(Generic.Heading, Whitespace)),
            (r'(=.*)(\n)', bygroups(Generic.Heading, Whitespace)),
            (r'(.*)(\n)', Whitespace),
        ]
    }

    def analyse_text(text):
        if text[:7] == 'Index: ':
            return True
        if text[:5] == 'diff ':
            return True
        if text[:4] == '--- ':
            return 0.9


class DarcsPatchLexer(RegexLexer):
    """
    DarcsPatchLexer is a lexer for the various versions of the darcs patch
    format.  Examples of this format are derived by commands such as
    ``darcs annotate --patch`` and ``darcs send``.

    .. versionadded:: 0.10
    """

    name = 'Darcs Patch'
    aliases = ['dpatch']
    filenames = ['*.dpatch', '*.darcspatch']

    DPATCH_KEYWORDS = ('hunk', 'addfile', 'adddir', 'rmfile', 'rmdir', 'move',
                       'replace')

    tokens = {
        'root': [
            (r'<', Operator),
            (r'>', Operator),
            (r'\{', Operator),
            (r'\}', Operator),
            (r'(\[)((?:TAG )?)(.*)(\n)(.*)(\*\*)(\d+)(\s?)(\])',
             bygroups(Operator, Keyword, Name, Whitespace, Name, Operator,
                      Literal.Date, Whitespace, Operator)),
            (r'(\[)((?:TAG )?)(.*)(\n)(.*)(\*\*)(\d+)(\s?)',
             bygroups(Operator, Keyword, Name, Whitespace, Name, Operator,
                      Literal.Date, Whitespace), 'comment'),
            (r'New patches:', Generic.Heading),
            (r'Context:', Generic.Heading),
            (r'Patch bundle hash:', Generic.Heading),
            (r'(\s*)(%s)(.*)(\n)' % '|'.join(DPATCH_KEYWORDS),
                bygroups(Whitespace, Keyword, Text, Whitespace)),
            (r'\+', Generic.Inserted, "insert"),
            (r'-', Generic.Deleted, "delete"),
            (r'(.*)(\n)', bygroups(Text, Whitespace)),
        ],
        'comment': [
            (r'[^\]].*\n', Comment),
            (r'\]', Operator, "#pop"),
        ],
        'specialText': [            # darcs add [_CODE_] special operators for clarity
            (r'\n', Whitespace, "#pop"),  # line-based
            (r'\[_[^_]*_]', Operator),
        ],
        'insert': [
            include('specialText'),
            (r'\[', Generic.Inserted),
            (r'[^\n\[]+', Generic.Inserted),
        ],
        'delete': [
            include('specialText'),
            (r'\[', Generic.Deleted),
            (r'[^\n\[]+', Generic.Deleted),
        ],
    }


class WDiffLexer(RegexLexer):
    """
    A wdiff lexer.

    Note that:

    * It only works with normal output (without options like ``-l``).
    * If the target files contain "[-", "-]", "{+", or "+}",
      especially they are unbalanced, the lexer will get confused.

    .. versionadded:: 2.2
    """

    name = 'WDiff'
    url = 'https://www.gnu.org/software/wdiff/'
    aliases = ['wdiff']
    filenames = ['*.wdiff']
    mimetypes = []

    flags = re.MULTILINE | re.DOTALL

    # We can only assume "[-" after "[-" before "-]" is `nested`,
    # for instance wdiff to wdiff outputs. We have no way to
    # distinct these marker is of wdiff output from original text.

    ins_op = r"\{\+"
    ins_cl = r"\+\}"
    del_op = r"\[\-"
    del_cl = r"\-\]"
    normal = r'[^{}[\]+-]+'  # for performance
    tokens = {
        'root': [
            (ins_op, Generic.Inserted, 'inserted'),
            (del_op, Generic.Deleted, 'deleted'),
            (normal, Text),
            (r'.', Text),
        ],
        'inserted': [
            (ins_op, Generic.Inserted, '#push'),
            (del_op, Generic.Inserted, '#push'),
            (del_cl, Generic.Inserted, '#pop'),

            (ins_cl, Generic.Inserted, '#pop'),
            (normal, Generic.Inserted),
            (r'.', Generic.Inserted),
        ],
        'deleted': [
            (del_op, Generic.Deleted, '#push'),
            (ins_op, Generic.Deleted, '#push'),
            (ins_cl, Generic.Deleted, '#pop'),

            (del_cl, Generic.Deleted, '#pop'),
            (normal, Generic.Deleted),
            (r'.', Generic.Deleted),
        ],
    }