File size: 7,167 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
"""
    pygments.lexers.typst
    ~~~~~~~~~~~~~~~~~~~~~

    Lexers for Typst language.

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

from pygments.lexer import RegexLexer, words, bygroups, include
from pygments.token import Comment, Keyword, Name, String, Punctuation, \
    Whitespace, Generic, Operator, Number, Text
from pygments.util import get_choice_opt

__all__ = ['TypstLexer']


class TypstLexer(RegexLexer):
    """
    For Typst code.

    Additional options accepted:

    `start`
        Specifies the starting state of the lexer (one of 'markup', 'math',
        'code'). The default is 'markup'.
    """

    name = 'Typst'
    aliases = ['typst']
    filenames = ['*.typ']
    mimetypes = ['text/x-typst']
    url = 'https://typst.app'
    version_added = '2.18'

    MATH_SHORTHANDS = (
        '[|', '|]', '||', '*', ':=', '::=', '...', '\'', '-', '=:', '!=', '>>',
        '>=', '>>>', '<<', '<=', '<<<', '->', '|->', '=>', '|=>', '==>',
        '-->', '~~>', '~>', '>->', '->>', '<-', '<==', '<--', '<~~', '<~',
        '<-<','<<-','<->','<=>','<==>','<-->', '>', '<', '~', ':', '|'
    )

    tokens = {
        'root': [
            include('markup'),
        ],
        # common cases going from math/markup into code mode
        'into_code': [
            (words(('#let', '#set', '#show'), suffix=r'\b'), Keyword.Declaration, 'inline_code'),
            (words(('#import', '#include'), suffix=r'\b'), Keyword.Namespace, 'inline_code'),
            (words(('#if', '#for', '#while', '#export'), suffix=r'\b'), Keyword.Reserved, 'inline_code'),
            (r'#\{', Punctuation, 'code'),
            (r'#\(', Punctuation, 'code'),
            (r'(#[a-zA-Z_][a-zA-Z0-9_-]*)(\[)', bygroups(Name.Function, Punctuation), 'markup'),
            (r'(#[a-zA-Z_][a-zA-Z0-9_-]*)(\()', bygroups(Name.Function, Punctuation), 'code'),
            (words(('#true', '#false', '#none', '#auto'), suffix=r'\b'), Keyword.Constant),
            (r'#[a-zA-Z_][a-zA-Z0-9_]*', Name.Variable),
            (r'#0x[0-9a-fA-F]+', Number.Hex),
            (r'#0b[01]+', Number.Bin),
            (r'#0o[0-7]+', Number.Oct),
            (r'#[0-9]+[\.e][0-9]+', Number.Float),
            (r'#[0-9]+', Number.Integer),
        ],
        'markup': [
            include('comment'),
            (r'^\s*=+.*$', Generic.Heading),
            (r'[*][^*]*[*]', Generic.Strong),
            (r'_[^_]*_', Generic.Emph),
            (r'\$', Punctuation, 'math'),
            (r'`[^`]*`', String.Backtick),  # inline code
            (r'^(\s*)(-)(\s+)', bygroups(Whitespace, Punctuation, Whitespace)),  # unnumbered list
            (r'^(\s*)(\+)(\s+)', bygroups(Whitespace, Punctuation, Whitespace)),  # numbered list
            (r'^(\s*)([0-9]+\.)', bygroups(Whitespace, Punctuation)),  # numbered list variant
            (r'^(\s*)(/)(\s+)([^:]+)(:)', bygroups(Whitespace, Punctuation, Whitespace, Name.Variable, Punctuation)),  # definitions
            (r'<[a-zA-Z_][a-zA-Z0-9_-]*>', Name.Label),  # label
            (r'@[a-zA-Z_][a-zA-Z0-9_-]*', Name.Label),  # reference
            (r'\\#', Text), # escaped
            include('into_code'),
            (r'```(?:.|\n)*?```', String.Backtick),  # code block
            (r'https?://[0-9a-zA-Z~/%#&=\',;.+?]*', Generic.Emph),  # links
            (words(('---', '\\', '~', '--', '...'), suffix=r'\B'), Punctuation),  # special chars shorthand
            (r'\\\[', Punctuation),  # escaped
            (r'\\\]', Punctuation),  # escaped
            (r'\[', Punctuation, '#push'),
            (r'\]', Punctuation, '#pop'),
            (r'[ \t]+\n?|\n', Whitespace),
            (r'((?![*_$`<@\\#\] ]|https?://).)+', Text),
        ],
        'math': [
            include('comment'),
            (words(('\\_', '\\^', '\\&')), Text), # escapes
            (words(('_', '^', '&', ';')), Punctuation),
            (words(('+', '/', '=') + MATH_SHORTHANDS), Operator),
            (r'\\', Punctuation), # line break
            (r'\\\$', Punctuation),  # escaped
            (r'\$', Punctuation, '#pop'),  # end of math mode
            include('into_code'),
            (r'([a-zA-Z][a-zA-Z0-9-]*)(\s*)(\()', bygroups(Name.Function, Whitespace, Punctuation)),
            (r'([a-zA-Z][a-zA-Z0-9-]*)(:)', bygroups(Name.Variable, Punctuation)), # named arguments in math functions
            (r'([a-zA-Z][a-zA-Z0-9-]*)', Name.Variable), # both variables and symbols (_ isn't supported for variables)
            (r'[0-9]+(\.[0-9]+)?', Number),
            (r'\.{1,3}|\(|\)|,|\{|\}', Punctuation),
            (r'"[^"]*"', String.Double),
            (r'[ \t\n]+', Whitespace),
        ],
        'comment': [
            (r'//.*$', Comment.Single),
            (r'/[*](.|\n)*?[*]/', Comment.Multiline),
        ],
        'code': [
            include('comment'),
            (r'\[', Punctuation, 'markup'),
            (r'\(|\{', Punctuation, 'code'),
            (r'\)|\}', Punctuation, '#pop'),
            (r'"[^"]*"', String.Double),
            (r',|\.{1,2}', Punctuation),
            (r'=', Operator),
            (words(('and', 'or', 'not'), suffix=r'\b'), Operator.Word),
            (r'=>|<=|==|!=|>|<|-=|\+=|\*=|/=|\+|-|\\|\*', Operator), # comparisons
            (r'([a-zA-Z_][a-zA-Z0-9_-]*)(:)', bygroups(Name.Variable, Punctuation)),
            (r'([a-zA-Z_][a-zA-Z0-9_-]*)(\()', bygroups(Name.Function, Punctuation), 'code'),
            (words(('as', 'break', 'export', 'continue', 'else', 'for', 'if',
                    'in', 'return', 'while'), suffix=r'\b'),
             Keyword.Reserved),
             (words(('import', 'include'), suffix=r'\b'), Keyword.Namespace),
            (words(('auto', 'none', 'true', 'false'), suffix=r'\b'), Keyword.Constant),
            (r'([0-9.]+)(mm|pt|cm|in|em|fr|%)', bygroups(Number, Keyword.Reserved)),
            (r'0x[0-9a-fA-F]+', Number.Hex),
            (r'0b[01]+', Number.Bin),
            (r'0o[0-7]+', Number.Oct),
            (r'[0-9]+[\.e][0-9]+', Number.Float),
            (r'[0-9]+', Number.Integer),
            (words(('let', 'set', 'show'), suffix=r'\b'), Keyword.Declaration),
            # FIXME: make this work
            ## (r'(import|include)( *)(")([^"])(")',
            ##  bygroups(Keyword.Reserved, Text, Punctuation, String.Double, Punctuation)),
            (r'([a-zA-Z_][a-zA-Z0-9_-]*)', Name.Variable),
            (r'[ \t\n]+', Whitespace),
            (r':', Punctuation), # from imports like "import a: b" or "show: text.with(..)"
        ],
        'inline_code': [
            (r';\b', Punctuation, '#pop'),
            (r'\n', Whitespace, '#pop'),
            include('code'),
        ],
    }

    def __init__(self, **options):
        self.start_state = get_choice_opt(
            options, 'start', ['markup', 'code', 'math'], 'markup', True)

        RegexLexer.__init__(self, **options)

    def get_tokens_unprocessed(self, text):
        stack = ['root']
        if self.start_state != 'markup': # markup is equivalent to root
            stack.append(self.start_state)

        yield from RegexLexer.get_tokens_unprocessed(self, text, stack)