summaryrefslogtreecommitdiff
path: root/pygments/lexers/textedit.py
blob: 89417216f88dfb386221baadff912f91a988e427 (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
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
166
167
168
169
# -*- coding: utf-8 -*-
"""
    pygments.lexers.textedit
    ~~~~~~~~~~~~~~~~~~~~~~~~

    Lexers for languages related to text processing.

    :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import re
from bisect import bisect

from pygments.lexer import RegexLexer, include, default, bygroups, using, this
from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
    Number, Punctuation

from pygments.lexers.python import PythonLexer

__all__ = ['AwkLexer', 'VimLexer']


class AwkLexer(RegexLexer):
    """
    For Awk scripts.

    .. versionadded:: 1.5
    """

    name = 'Awk'
    aliases = ['awk', 'gawk', 'mawk', 'nawk']
    filenames = ['*.awk']
    mimetypes = ['application/x-awk']

    tokens = {
        'commentsandwhitespace': [
            (r'\s+', Text),
            (r'#.*$', Comment.Single)
        ],
        'slashstartsregex': [
            include('commentsandwhitespace'),
            (r'/(\\.|[^[/\\\n]|\[(\\.|[^\]\\\n])*])+/'
             r'\B', String.Regex, '#pop'),
            (r'(?=/)', Text, ('#pop', 'badregex')),
            default('#pop')
        ],
        'badregex': [
            (r'\n', Text, '#pop')
        ],
        'root': [
            (r'^(?=\s|/)', Text, 'slashstartsregex'),
            include('commentsandwhitespace'),
            (r'\+\+|--|\|\||&&|in\b|\$|!?~|'
             r'(\*\*|[-<>+*%\^/!=|])=?', Operator, 'slashstartsregex'),
            (r'[{(\[;,]', Punctuation, 'slashstartsregex'),
            (r'[})\].]', Punctuation),
            (r'(break|continue|do|while|exit|for|if|else|'
             r'return)\b', Keyword, 'slashstartsregex'),
            (r'function\b', Keyword.Declaration, 'slashstartsregex'),
            (r'(atan2|cos|exp|int|log|rand|sin|sqrt|srand|gensub|gsub|index|'
             r'length|match|split|sprintf|sub|substr|tolower|toupper|close|'
             r'fflush|getline|next|nextfile|print|printf|strftime|systime|'
             r'delete|system)\b', Keyword.Reserved),
            (r'(ARGC|ARGIND|ARGV|BEGIN|CONVFMT|ENVIRON|END|ERRNO|FIELDWIDTHS|'
             r'FILENAME|FNR|FS|IGNORECASE|NF|NR|OFMT|OFS|ORFS|RLENGTH|RS|'
             r'RSTART|RT|SUBSEP)\b', Name.Builtin),
            (r'[$a-zA-Z_]\w*', Name.Other),
            (r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float),
            (r'0x[0-9a-fA-F]+', Number.Hex),
            (r'[0-9]+', Number.Integer),
            (r'"(\\\\|\\"|[^"])*"', String.Double),
            (r"'(\\\\|\\'|[^'])*'", String.Single),
        ]
    }


class VimLexer(RegexLexer):
    """
    Lexer for VimL script files.

    .. versionadded:: 0.8
    """
    name = 'VimL'
    aliases = ['vim']
    filenames = ['*.vim', '.vimrc', '.exrc', '.gvimrc',
                 '_vimrc', '_exrc', '_gvimrc', 'vimrc', 'gvimrc']
    mimetypes = ['text/x-vim']
    flags = re.MULTILINE

    _python = r'py(?:t(?:h(?:o(?:n)?)?)?)?'

    tokens = {
        'root': [
            (r'^([ \t:]*)(' + _python + r')([ \t]*)(<<)([ \t]*)(.*)((?:\n|.)*)(\6)',
             bygroups(using(this), Keyword, Text, Operator, Text, Text,
                      using(PythonLexer), Text)),
            (r'^([ \t:]*)(' + _python + r')([ \t])(.*)',
             bygroups(using(this), Keyword, Text, using(PythonLexer))),

            (r'^\s*".*', Comment),

            (r'[ \t]+', Text),
            # TODO: regexes can have other delims
            (r'/(\\\\|\\/|[^\n/])*/', String.Regex),
            (r'"(\\\\|\\"|[^\n"])*"', String.Double),
            (r"'(''|[^\n'])*'", String.Single),

            # Who decided that doublequote was a good comment character??
            (r'(?<=\s)"[^\-:.%#=*].*', Comment),
            (r'-?\d+', Number),
            (r'#[0-9a-f]{6}', Number.Hex),
            (r'^:', Punctuation),
            (r'[()<>+=!|,~-]', Punctuation),  # Inexact list.  Looks decent.
            (r'\b(let|if|else|endif|elseif|fun|function|endfunction)\b',
             Keyword),
            (r'\b(NONE|bold|italic|underline|dark|light)\b', Name.Builtin),
            (r'\b\w+\b', Name.Other),  # These are postprocessed below
            (r'.', Text),
        ],
    }

    def __init__(self, **options):
        from pygments.lexers._vim_builtins import command, option, auto
        self._cmd = command
        self._opt = option
        self._aut = auto

        RegexLexer.__init__(self, **options)

    def is_in(self, w, mapping):
        r"""
        It's kind of difficult to decide if something might be a keyword
        in VimL because it allows you to abbreviate them.  In fact,
        'ab[breviate]' is a good example.  :ab, :abbre, or :abbreviate are
        valid ways to call it so rather than making really awful regexps
        like::

            \bab(?:b(?:r(?:e(?:v(?:i(?:a(?:t(?:e)?)?)?)?)?)?)?)?\b

        we match `\b\w+\b` and then call is_in() on those tokens.  See
        `scripts/get_vimkw.py` for how the lists are extracted.
        """
        p = bisect(mapping, (w,))
        if p > 0:
            if mapping[p-1][0] == w[:len(mapping[p-1][0])] and \
               mapping[p-1][1][:len(w)] == w:
                return True
        if p < len(mapping):
            return mapping[p][0] == w[:len(mapping[p][0])] and \
                mapping[p][1][:len(w)] == w
        return False

    def get_tokens_unprocessed(self, text):
        # TODO: builtins are only subsequent tokens on lines
        #       and 'keywords' only happen at the beginning except
        #       for :au ones
        for index, token, value in \
                RegexLexer.get_tokens_unprocessed(self, text):
            if token is Name.Other:
                if self.is_in(value, self._cmd):
                    yield index, Keyword, value
                elif self.is_in(value, self._opt) or \
                        self.is_in(value, self._aut):
                    yield index, Name.Builtin, value
                else:
                    yield index, Text, value
            else:
                yield index, token, value