File size: 3,987 Bytes
9c6594c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""
    pygments.lexers.tablegen
    ~~~~~~~~~~~~~~~~~~~~~~~~

    Lexer for LLVM's TableGen DSL.

    :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

from pygments.lexer import RegexLexer, include, words, using
from pygments.lexers.c_cpp import CppLexer
from pygments.token import Comment, Keyword, Name, Number, Operator, \
    Punctuation, String, Text, Whitespace, Error

__all__ = ['TableGenLexer']

KEYWORDS = (
    'assert',
    'class',
    'code',
    'def',
    'dump',
    'else',
    'foreach',
    'defm',
    'defset',
    'defvar',
    'field',
    'if',
    'in',
    'include',
    'let',
    'multiclass',
    'then',
)

KEYWORDS_CONST = (
    'false',
    'true',
)
KEYWORDS_TYPE = (
    'bit',
    'bits',
    'dag',
    'int',
    'list',
    'string',
)

BANG_OPERATORS = (
    'add',
    'and',
    'cast',
    'con',
    'cond',
    'dag',
    'div',
    'empty',
    'eq',
    'exists',
    'filter',
    'find',
    'foldl',
    'foreach',
    'ge',
    'getdagarg',
    'getdagname',
    'getdagop',
    'gt',
    'head',
    'if',
    'interleave',
    'isa',
    'le',
    'listconcat',
    'listremove',
    'listsplat',
    'logtwo',
    'lt',
    'mul',
    'ne',
    'not',
    'or',
    'range',
    'repr',
    'setdagarg',
    'setdagname',
    'setdagop',
    'shl',
    'size',
    'sra',
    'srl',
    'strconcat',
    'sub',
    'subst',
    'substr',
    'tail',
    'tolower',
    'toupper',
    'xor',
)

class TableGenLexer(RegexLexer):
    """
    Lexer for TableGen
    """

    name = 'TableGen'
    url = 'https://llvm.org/docs/TableGen/ProgRef.html'
    aliases = ['tablegen', 'td']
    filenames = ['*.td']

    version_added = '2.19'

    tokens = {
        'root': [
            (r'\s+', Whitespace),

            (r'/\*', Comment.Multiline, 'comment'),
            (r'//.*?$', Comment.SingleLine),
            (r'#(define|ifdef|ifndef|else|endif)', Comment.Preproc),

            # Binary/hex numbers. Note that these take priority over names,
            # which may begin with numbers.
            (r'0b[10]+', Number.Bin),
            (r'0x[0-9a-fA-F]+', Number.Hex),

            # Keywords
            (words(KEYWORDS, suffix=r'\b'), Keyword),
            (words(KEYWORDS_CONST, suffix=r'\b'), Keyword.Constant),
            (words(KEYWORDS_TYPE, suffix=r'\b'), Keyword.Type),

            # Bang operators
            (words(BANG_OPERATORS, prefix=r'\!', suffix=r'\b'), Operator),
            # Unknown bang operators are an error
            (r'![a-zA-Z]+', Error),

            # Names and identifiers
            (r'[0-9]*[a-zA-Z_][a-zA-Z_0-9]*', Name),
            (r'\$[a-zA-Z_][a-zA-Z_0-9]*', Name.Variable),

            # Place numbers after keywords. Names/identifiers may begin with
            # numbers, and we want to parse 1X as one name token as opposed to
            # a number and a name.
            (r'[-\+]?[0-9]+', Number.Integer),

            # String literals
            (r'"', String, 'dqs'),
            (r'\[\{', Text, 'codeblock'),

            # Misc. punctuation
            (r'[-+\[\]{}()<>\.,;:=?#]+', Punctuation),
        ],
        'comment': [
            (r'[^*/]+', Comment.Multiline),
            (r'/\*', Comment.Multiline, '#push'),
            (r'\*/', Comment.Multiline, '#pop'),
            (r'[*/]', Comment.Multiline)
        ],
        'strings': [
            (r'\\[\\\'"tn]', String.Escape),
            (r'[^\\"]+', String),
        ],
        # Double-quoted string, a la C
        'dqs': [
            (r'"', String, '#pop'),
            include('strings'),
        ],
        # No escaping inside a code block - everything is literal
        # Assume that the code inside a code block is C++. This isn't always
        # true in TableGen, but is the far most common scenario.
        'codeblock': [
            (r'\}\]', Text, '#pop'),
            (r'([^}]+|\}[^]])*', using(CppLexer)),
        ],
    }