File size: 8,043 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 |
"""
pygments.lexers.grammar_notation
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Lexers for grammar notations like BNF.
:copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pygments.lexer import RegexLexer, bygroups, include, this, using, words
from pygments.token import Comment, Keyword, Literal, Name, Number, \
Operator, Punctuation, String, Text, Whitespace
__all__ = ['BnfLexer', 'AbnfLexer', 'JsgfLexer', 'PegLexer']
class BnfLexer(RegexLexer):
"""
This lexer is for grammar 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 decision making might cause too minimal highlighting
and you might be disappointed, but it is reasonable for us.
"""
name = 'BNF'
aliases = ['bnf']
filenames = ['*.bnf']
mimetypes = ['text/x-bnf']
url = 'https://en.wikipedia.org/wiki/Backus%E2%80%93Naur_form'
version_added = '2.1'
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.
(Updates `5234 <http://www.ietf.org/rfc/rfc5234.txt>`_) grammars.
"""
name = 'ABNF'
url = 'http://www.ietf.org/rfc/rfc7405.txt'
aliases = ['abnf']
filenames = ['*.abnf']
mimetypes = ['text/x-abnf']
version_added = '2.1'
_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+', Whitespace),
(r'.', Text),
],
}
class JsgfLexer(RegexLexer):
"""
For JSpeech Grammar Format grammars.
"""
name = 'JSGF'
url = 'https://www.w3.org/TR/jsgf/'
aliases = ['jsgf']
filenames = ['*.jsgf']
mimetypes = ['application/jsgf', 'application/x-jsgf', 'text/jsgf']
version_added = '2.2'
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+', Whitespace),
(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+', Whitespace),
(r'\.', Punctuation),
(r'[^;\s.]+', Name.Namespace),
],
'rulename': [
(r'>', Punctuation, '#pop'),
(r'\*', Punctuation),
(r'\s+', Whitespace),
(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(Whitespace, Comment.Multiline, Whitespace, Comment.Special,
Whitespace, using(this, state='example'))),
(r'(^\s*\*?\s*)(@\S*)',
bygroups(Comment.Multiline, Comment.Special)),
(r'[^*\n@]+|\w|\W', Comment.Multiline),
],
'example': [
(r'(\n\s*)(\*)', bygroups(Whitespace, Comment.Multiline)),
include('non-comments'),
(r'.', Comment.Multiline),
],
}
class PegLexer(RegexLexer):
"""
This lexer is for Parsing Expression Grammars (PEG).
Various implementations of PEG have made different decisions
regarding the syntax, so let's try to be accommodating:
* `<-`, `β`, `:`, and `=` are all accepted as rule operators.
* Both `|` and `/` are choice operators.
* `^`, `β`, and `~` are cut operators.
* A single `a-z` character immediately before a string, or
multiple `a-z` characters following a string, are part of the
string (e.g., `r"..."` or `"..."ilmsuxa`).
"""
name = 'PEG'
url = 'https://bford.info/pub/lang/peg.pdf'
aliases = ['peg']
filenames = ['*.peg']
mimetypes = ['text/x-peg']
version_added = '2.6'
tokens = {
'root': [
# Comments
(r'#.*$', Comment.Single),
# All operators
(r'<-|[β:=/|&!?*+^β~]', Operator),
# Other punctuation
(r'[()]', Punctuation),
# Keywords
(r'\.', Keyword),
# Character classes
(r'(\[)([^\]]*(?:\\.[^\]\\]*)*)(\])',
bygroups(Punctuation, String, Punctuation)),
# Single and double quoted strings (with optional modifiers)
(r'[a-z]?"[^"\\]*(?:\\.[^"\\]*)*"[a-z]*', String.Double),
(r"[a-z]?'[^'\\]*(?:\\.[^'\\]*)*'[a-z]*", String.Single),
# Nonterminals are not whitespace, operators, or punctuation
(r'[^\s<β:=/|&!?*+\^β~()\[\]"\'#]+', Name.Class),
# Fallback
(r'.', Text),
],
}
|