1"""
2 pygments.lexers.diff
3 ~~~~~~~~~~~~~~~~~~~~
4
5 Lexers for diff/patch formats.
6
7 :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
8 :license: BSD, see LICENSE for details.
9"""
10
11import re
12
13from pygments.lexer import RegexLexer, include, bygroups
14from pygments.token import Text, Comment, Operator, Keyword, Name, Generic, \
15 Literal, Whitespace
16
17__all__ = ['DiffLexer', 'DarcsPatchLexer', 'WDiffLexer']
18
19
20class DiffLexer(RegexLexer):
21 """
22 Lexer for unified or context-style diffs or patches.
23 """
24
25 name = 'Diff'
26 aliases = ['diff', 'udiff']
27 filenames = ['*.diff', '*.patch']
28 mimetypes = ['text/x-diff', 'text/x-patch']
29 url = 'https://en.wikipedia.org/wiki/Diff'
30 version_added = ''
31
32 tokens = {
33 'root': [
34 (r'( )(.*)(\n)', bygroups(Whitespace, Text, Whitespace)),
35 (r'(!.*|---)(\n)', bygroups(Generic.Strong, Whitespace)),
36 (r'((?:< |-).*)(\n)', bygroups(Generic.Deleted, Whitespace)),
37 (r'((?:> |\+).*)(\n)', bygroups(Generic.Inserted, Whitespace)),
38 (
39 r'(@.*|\d(?:,\d+)?(?:a|c|d)\d+(?:,\d+)?)(\n)',
40 bygroups(Generic.Subheading, Whitespace),
41 ),
42 (r'((?:[Ii]ndex|diff).*)(\n)', bygroups(Generic.Heading, Whitespace)),
43 (r'(=.*)(\n)', bygroups(Generic.Heading, Whitespace)),
44 (r'(.*)(\n)', bygroups(Text, Whitespace)),
45 ]
46 }
47
48 def analyse_text(text):
49 if text[:7] == 'Index: ':
50 return True
51 if text[:5] == 'diff ':
52 return True
53 if text[:4] == '--- ':
54 return 0.9
55
56
57class DarcsPatchLexer(RegexLexer):
58 """
59 DarcsPatchLexer is a lexer for the various versions of the darcs patch
60 format. Examples of this format are derived by commands such as
61 ``darcs annotate --patch`` and ``darcs send``.
62 """
63
64 name = 'Darcs Patch'
65 aliases = ['dpatch']
66 filenames = ['*.dpatch', '*.darcspatch']
67 url = 'https://darcs.net'
68 version_added = '0.10'
69
70 DPATCH_KEYWORDS = ('hunk', 'addfile', 'adddir', 'rmfile', 'rmdir', 'move',
71 'replace')
72
73 tokens = {
74 'root': [
75 (r'<', Operator),
76 (r'>', Operator),
77 (r'\{', Operator),
78 (r'\}', Operator),
79 (r'(\[)((?:TAG )?)(.*)(\n)(.*)(\*\*)(\d+)(\s?)(\])',
80 bygroups(Operator, Keyword, Name, Whitespace, Name, Operator,
81 Literal.Date, Whitespace, Operator)),
82 (r'(\[)((?:TAG )?)(.*)(\n)(.*)(\*\*)(\d+)(\s?)',
83 bygroups(Operator, Keyword, Name, Whitespace, Name, Operator,
84 Literal.Date, Whitespace), 'comment'),
85 (r'New patches:', Generic.Heading),
86 (r'Context:', Generic.Heading),
87 (r'Patch bundle hash:', Generic.Heading),
88 (r'(\s*)({})(.*)(\n)'.format('|'.join(DPATCH_KEYWORDS)),
89 bygroups(Whitespace, Keyword, Text, Whitespace)),
90 (r'\+', Generic.Inserted, "insert"),
91 (r'-', Generic.Deleted, "delete"),
92 (r'(.*)(\n)', bygroups(Text, Whitespace)),
93 ],
94 'comment': [
95 (r'[^\]].*\n', Comment),
96 (r'\]', Operator, "#pop"),
97 ],
98 'specialText': [ # darcs add [_CODE_] special operators for clarity
99 (r'\n', Whitespace, "#pop"), # line-based
100 (r'\[_[^_]*_]', Operator),
101 ],
102 'insert': [
103 include('specialText'),
104 (r'\[', Generic.Inserted),
105 (r'[^\n\[]+', Generic.Inserted),
106 ],
107 'delete': [
108 include('specialText'),
109 (r'\[', Generic.Deleted),
110 (r'[^\n\[]+', Generic.Deleted),
111 ],
112 }
113
114
115class WDiffLexer(RegexLexer):
116 """
117 A wdiff lexer.
118
119 Note that:
120
121 * It only works with normal output (without options like ``-l``).
122 * If the target files contain "[-", "-]", "{+", or "+}",
123 especially they are unbalanced, the lexer will get confused.
124 """
125
126 name = 'WDiff'
127 url = 'https://www.gnu.org/software/wdiff/'
128 aliases = ['wdiff']
129 filenames = ['*.wdiff']
130 mimetypes = []
131 version_added = '2.2'
132
133 flags = re.MULTILINE | re.DOTALL
134
135 # We can only assume "[-" after "[-" before "-]" is `nested`,
136 # for instance wdiff to wdiff outputs. We have no way to
137 # distinct these marker is of wdiff output from original text.
138
139 ins_op = r"\{\+"
140 ins_cl = r"\+\}"
141 del_op = r"\[\-"
142 del_cl = r"\-\]"
143 normal = r'[^{}[\]+-]+' # for performance
144 tokens = {
145 'root': [
146 (ins_op, Generic.Inserted, 'inserted'),
147 (del_op, Generic.Deleted, 'deleted'),
148 (normal, Text),
149 (r'.', Text),
150 ],
151 'inserted': [
152 (ins_op, Generic.Inserted, '#push'),
153 (del_op, Generic.Inserted, '#push'),
154 (del_cl, Generic.Inserted, '#pop'),
155
156 (ins_cl, Generic.Inserted, '#pop'),
157 (normal, Generic.Inserted),
158 (r'.', Generic.Inserted),
159 ],
160 'deleted': [
161 (del_op, Generic.Deleted, '#push'),
162 (ins_op, Generic.Deleted, '#push'),
163 (ins_cl, Generic.Deleted, '#pop'),
164
165 (del_cl, Generic.Deleted, '#pop'),
166 (normal, Generic.Deleted),
167 (r'.', Generic.Deleted),
168 ],
169 }