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
|
# -*- coding: utf-8 -*-
"""
pygments.lexers.rdf
~~~~~~~~~~~~~~~~~~~
Lexers for semantic web and RDF query languages and markup.
:copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
from pygments.lexer import RegexLexer, bygroups, default
from pygments.token import Keyword, Punctuation, String, Number, Operator, Generic, \
Whitespace, Name, Literal, Comment, Text
__all__ = ['SparqlLexer', 'TurtleLexer']
class SparqlLexer(RegexLexer):
"""
Lexer for `SPARQL <http://www.w3.org/TR/rdf-sparql-query/>`_ query language.
.. versionadded:: 2.0
"""
name = 'SPARQL'
aliases = ['sparql']
filenames = ['*.rq', '*.sparql']
mimetypes = ['application/sparql-query']
flags = re.IGNORECASE
tokens = {
'root': [
(r'\s+', Whitespace),
(r'(select|construct|describe|ask|where|filter|group\s+by|minus|'
r'distinct|reduced|from named|from|order\s+by|limit|'
r'offset|bindings|load|clear|drop|create|add|move|copy|'
r'insert\s+data|delete\s+data|delete\s+where|delete|insert|'
r'using named|using|graph|default|named|all|optional|service|'
r'silent|bind|union|not in|in|as|a)', Keyword),
(r'(prefix|base)(\s+)([a-z][\w-]*)(\s*)(\:)',
bygroups(Keyword, Whitespace, Name.Namespace, Whitespace,
Punctuation)),
(r'\?[a-z_]\w*', Name.Variable),
(r'<[^>]+>', Name.Label),
(r'([a-z][\w-]*)(\:)([a-z][\w-]*)',
bygroups(Name.Namespace, Punctuation, Name.Tag)),
(r'(str|lang|langmatches|datatype|bound|iri|uri|bnode|rand|abs|'
r'ceil|floor|round|concat|strlen|ucase|lcase|encode_for_uri|'
r'contains|strstarts|strends|strbefore|strafter|year|month|day|'
r'hours|minutes|seconds|timezone|tz|now|md5|sha1|sha256|sha384|'
r'sha512|coalesce|if|strlang|strdt|sameterm|isiri|isuri|isblank|'
r'isliteral|isnumeric|regex|substr|replace|exists|not exists|'
r'count|sum|min|max|avg|sample|group_concat|separator)\b',
Name.Function),
(r'(true|false)', Literal),
(r'[+\-]?\d*\.\d+', Number.Float),
(r'[+\-]?\d*(:?\.\d+)?E[+\-]?\d+', Number.Float),
(r'[+\-]?\d+', Number.Integer),
(r'(\|\||&&|=|\*|\-|\+|/)', Operator),
(r'[(){}.;,:^]', Punctuation),
(r'#[^\n]+', Comment),
(r'"""', String, 'triple-double-quoted-string'),
(r'"', String, 'single-double-quoted-string'),
(r"'''", String, 'triple-single-quoted-string'),
(r"'", String, 'single-single-quoted-string'),
],
'triple-double-quoted-string': [
(r'"""', String, 'end-of-string'),
(r'[^\\]+', String),
(r'\\', String, 'string-escape'),
],
'single-double-quoted-string': [
(r'"', String, 'end-of-string'),
(r'[^"\\\n]+', String),
(r'\\', String, 'string-escape'),
],
'triple-single-quoted-string': [
(r"'''", String, 'end-of-string'),
(r'[^\\]+', String),
(r'\\', String, 'string-escape'),
],
'single-single-quoted-string': [
(r"'", String, 'end-of-string'),
(r"[^'\\\n]+", String),
(r'\\', String, 'string-escape'),
],
'string-escape': [
(r'.', String, '#pop'),
],
'end-of-string': [
(r'(@)([a-z]+(:?-[a-z0-9]+)*)',
bygroups(Operator, Name.Function), '#pop:2'),
(r'\^\^', Operator, '#pop:2'),
default('#pop:2'),
],
}
class TurtleLexer(RegexLexer):
"""
Lexer for `Turtle <http://www.w3.org/TR/turtle/>`_ data language.
.. versionadded:: 2.0
"""
name = 'Turtle'
aliases = ['turtle']
filenames = ['*.ttl']
mimetypes = ['text/turtle', 'application/x-turtle']
flags = re.IGNORECASE
patterns = {
'PNAME_NS': r'((?:[a-zA-Z][\w-]*)?\:)', # Simplified character range
'IRIREF': r'(<[^<>"{}|^`\\\x00-\x20]*>)'
}
# PNAME_NS PN_LOCAL (with simplified character range)
patterns['PrefixedName'] = r'%(PNAME_NS)s([a-z][\w-]*)' % patterns
tokens = {
'root': [
(r'\s+', Whitespace),
# Base / prefix
(r'(@base|BASE)(\s+)%(IRIREF)s(\s*)(\.?)' % patterns,
bygroups(Keyword, Whitespace, Name.Variable, Whitespace,
Punctuation)),
(r'(@prefix|PREFIX)(\s+)%(PNAME_NS)s(\s+)%(IRIREF)s(\s*)(\.?)' % patterns,
bygroups(Keyword, Whitespace, Name.Namespace, Whitespace,
Name.Variable, Whitespace, Punctuation)),
# The shorthand predicate 'a'
(r'(?<=\s)a(?=\s)', Keyword.Type),
# IRIREF
(r'%(IRIREF)s' % patterns, Name.Variable),
# PrefixedName
(r'%(PrefixedName)s' % patterns,
bygroups(Name.Namespace, Name.Tag)),
# Comment
(r'#[^\n]+', Comment),
(r'\b(true|false)\b', Literal),
(r'[+\-]?\d*\.\d+', Number.Float),
(r'[+\-]?\d*(:?\.\d+)?E[+\-]?\d+', Number.Float),
(r'[+\-]?\d+', Number.Integer),
(r'[\[\](){}.;,:^]', Punctuation),
(r'"""', String, 'triple-double-quoted-string'),
(r'"', String, 'single-double-quoted-string'),
(r"'''", String, 'triple-single-quoted-string'),
(r"'", String, 'single-single-quoted-string'),
],
'triple-double-quoted-string': [
(r'"""', String, 'end-of-string'),
(r'[^\\]+', String),
(r'\\', String, 'string-escape'),
],
'single-double-quoted-string': [
(r'"', String, 'end-of-string'),
(r'[^"\\\n]+', String),
(r'\\', String, 'string-escape'),
],
'triple-single-quoted-string': [
(r"'''", String, 'end-of-string'),
(r'[^\\]+', String),
(r'\\', String, 'string-escape'),
],
'single-single-quoted-string': [
(r"'", String, 'end-of-string'),
(r"[^'\\\n]+", String),
(r'\\', String, 'string-escape'),
],
'string-escape': [
(r'.', String, '#pop'),
],
'end-of-string': [
(r'(@)([a-zA-Z]+(:?-[a-zA-Z0-9]+)*)',
bygroups(Operator, Generic.Emph), '#pop:2'),
(r'(\^\^)%(IRIREF)s' % patterns, bygroups(Operator, Generic.Emph), '#pop:2'),
(r'(\^\^)%(PrefixedName)s' % patterns, bygroups(Operator, Generic.Emph, Generic.Emph), '#pop:2'),
default('#pop:2'),
],
}
|
