summaryrefslogtreecommitdiff
path: root/pygments/lexers/grammar_notation.py
blob: bc715ffa2d74b8b69d11d9b896457099609baa04 (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
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
# -*- coding: utf-8 -*-
"""
    pygments.lexers.grammar_notation
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

    Lexers for grammer notations like BNF.

    :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import re

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

__all__ = ['BnfLexer', 'AbnfLexer', 'JsgfLexer']


class BnfLexer(RegexLexer):
    """
    This lexer is for grammer notations which are similar to
    original BNF.

    In order to maximize a number of targets of this lexer,
    let's decide some designs:

    * We don't distinguish `Terminal Symbol`.

    * We do assume that `NonTerminal Symbol` are always enclosed
      with arrow brackets.

    * We do assume that `NonTerminal Symbol` may include
      any printable characters except arrow brackets and ASCII 0x20.
      This assumption is for `RBNF <http://www.rfc-base.org/txt/rfc-5511.txt>`_.

    * We do assume that target notation doesn't support comment.

    * We don't distinguish any operators and punctuation except
      `::=`.

    Though these desision making might cause too minimal highlighting
    and you might be disappointed, but it is reasonable for us.

    .. versionadded:: 2.1
    """

    name = 'BNF'
    aliases = ['bnf']
    filenames = ['*.bnf']
    mimetypes = ['text/x-bnf']

    tokens = {
        'root': [
            (r'(<)([ -;=?-~]+)(>)',
             bygroups(Punctuation, Name.Class, Punctuation)),

            # an only operator
            (r'::=', Operator),

            # fallback
            (r'[^<>:]+', Text),  # for performance
            (r'.', Text),
        ],
    }


class AbnfLexer(RegexLexer):
    """
    Lexer for `IETF 7405 ABNF
    <http://www.ietf.org/rfc/rfc7405.txt>`_
    (Updates `5234 <http://www.ietf.org/rfc/rfc5234.txt>`_)
    grammars.

    .. versionadded:: 2.1
    """

    name = 'ABNF'
    aliases = ['abnf']
    filenames = ['*.abnf']
    mimetypes = ['text/x-abnf']

    _core_rules = (
        'ALPHA', 'BIT', 'CHAR', 'CR', 'CRLF', 'CTL', 'DIGIT',
        'DQUOTE', 'HEXDIG', 'HTAB', 'LF', 'LWSP', 'OCTET',
        'SP', 'VCHAR', 'WSP')

    tokens = {
        'root': [
            # comment
            (r';.*$', Comment.Single),

            # quoted
            #   double quote itself in this state, it is as '%x22'.
            (r'(%[si])?"[^"]*"', Literal),

            # binary (but i have never seen...)
            (r'%b[01]+\-[01]+\b', Literal),  # range
            (r'%b[01]+(\.[01]+)*\b', Literal),  # concat

            # decimal
            (r'%d[0-9]+\-[0-9]+\b', Literal),  # range
            (r'%d[0-9]+(\.[0-9]+)*\b', Literal),  # concat

            # hexadecimal
            (r'%x[0-9a-fA-F]+\-[0-9a-fA-F]+\b', Literal),  # range
            (r'%x[0-9a-fA-F]+(\.[0-9a-fA-F]+)*\b', Literal),  # concat

            # repetition (<a>*<b>element) including nRule
            (r'\b[0-9]+\*[0-9]+', Operator),
            (r'\b[0-9]+\*', Operator),
            (r'\b[0-9]+', Operator),
            (r'\*', Operator),

            # Strictly speaking, these are not keyword but
            # are called `Core Rule'.
            (words(_core_rules, suffix=r'\b'), Keyword),

            # nonterminals (ALPHA *(ALPHA / DIGIT / "-"))
            (r'[a-zA-Z][a-zA-Z0-9-]+\b', Name.Class),

            # operators
            (r'(=/|=|/)', Operator),

            # punctuation
            (r'[\[\]()]', Punctuation),

            # fallback
            (r'\s+', Text),
            (r'.', Text),
        ],
    }


class JsgfLexer(RegexLexer):
    """
    For `JSpeech Grammar Format <https://www.w3.org/TR/jsgf/>`_
    grammars.

    .. versionadded:: 2.2
    """
    name = 'JSGF'
    aliases = ['jsgf']
    filenames = ['*.jsgf']
    mimetypes = ['application/jsgf', 'application/x-jsgf', 'text/jsgf']

    flags = re.MULTILINE | re.UNICODE

    tokens = {
        'root': [
            include('comments'),
            include('non-comments'),
        ],
        'comments': [
            (r'/\*\*(?!/)', Comment.Multiline, 'documentation comment'),
            (r'/\*[\w\W]*?\*/', Comment.Multiline),
            (r'//.*', Comment.Single),
        ],
        'non-comments': [
            (r'\A#JSGF[^;]*', Comment.Preproc),
            (r'\s+', Text),
            (r';', Punctuation),
            (r'[=|()\[\]*+]', Operator),
            (r'/[^/]+/', Number.Float),
            (r'"', String.Double, 'string'),
            (r'\{', String.Other, 'tag'),
            (words(('import', 'public'), suffix=r'\b'), Keyword.Reserved),
            (r'grammar\b', Keyword.Reserved, 'grammar name'),
            (r'(<)(NULL|VOID)(>)',
             bygroups(Punctuation, Name.Builtin, Punctuation)),
            (r'<', Punctuation, 'rulename'),
            (r'\w+|[^\s;=|()\[\]*+/"{<\w]+', Text),
        ],
        'string': [
            (r'"', String.Double, '#pop'),
            (r'\\.', String.Escape),
            (r'[^\\"]+', String.Double),
        ],
        'tag': [
            (r'\}', String.Other, '#pop'),
            (r'\\.', String.Escape),
            (r'[^\\}]+', String.Other),
        ],
        'grammar name': [
            (r';', Punctuation, '#pop'),
            (r'\s+', Text),
            (r'\.', Punctuation),
            (r'[^;\s.]+', Name.Namespace),
        ],
        'rulename': [
            (r'>', Punctuation, '#pop'),
            (r'\*', Punctuation),
            (r'\s+', Text),
            (r'([^.>]+)(\s*)(\.)', bygroups(Name.Namespace, Text, Punctuation)),
            (r'[^.>]+', Name.Constant),
        ],
        'documentation comment': [
            (r'\*/', Comment.Multiline, '#pop'),
            (r'(^\s*\*?\s*)(@(?:example|see)\s+)'
             r'([\w\W]*?(?=(?:^\s*\*?\s*@|\*/)))',
             bygroups(Comment.Multiline, Comment.Special,
                      using(this, state='example'))),
            (r'(^\s*\*?\s*)(@\S*)',
             bygroups(Comment.Multiline, Comment.Special)),
            (r'[^*\n@]+|\w|\W', Comment.Multiline),
        ],
        'example': [
            (r'\n\s*\*', Comment.Multiline),
            include('non-comments'),
            (r'.', Comment.Multiline),
        ],
    }