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
|
# -*- coding: utf-8 -*-
"""
pygments.token
~~~~~~~~~~~~~~
Basic token types and the standard tokens.
:copyright: 2006 by Georg Brandl.
:license: BSD, see LICENSE for more details.
"""
try:
set
except NameError:
from sets import Set as set
class _TokenType(tuple):
parent = None
def split(self):
buf = []
node = self
while node is not None:
buf.append(node)
node = node.parent
buf.reverse()
return buf
def __init__(self, *args, **kwargs):
super(_TokenType, self).__init__(*args, **kwargs)
self.subtokens = set()
def __contains__(self, val):
return self is val or (
type(val) is self.__class__ and
val[:len(self)] == self
)
def __getattr__(self, val):
if not val or not val[0].isupper():
return tuple.__getattribute__(self, val)
new = _TokenType(self + (val,))
setattr(self, val, new)
self.subtokens.add(new)
new.parent = self
return new
def __hash__(self):
return hash(tuple(self))
def __repr__(self):
return 'Token' + (self and '.' or '') + '.'.join(self)
Token = _TokenType()
# Special token types
Text = Token.Text
Error = Token.Error
# Text that doesn't belong to this lexer (e.g. HTML in PHP)
Other = Token.Other
# Common token types for source code
Keyword = Token.Keyword
Name = Token.Name
Literal = Token.Literal
String = Literal.String
Number = Literal.Number
Punctuation = Token.Punctuation
Operator = Token.Operator
Comment = Token.Comment
# Generic types for non-source code
Generic = Token.Generic
# String and some others are not direct childs of Token.
# alias them:
Token.Token = Token
Token.String = String
Token.Number = Number
def is_token_subtype(ttype, other):
"""
Return True if ``ttype`` is a subtype of ``other``.
exists for backwards compatibility. use ``ttype in other`` now.
"""
return ttype in other
def string_to_tokentype(s):
"""
Convert a string into a token type::
>>> string_to_token('String.Double')
Token.Literal.String.Double
>>> string_to_token('Token.Literal.Number')
Token.Literal.Number
>>> string_to_token('')
Token
Tokens that are already tokens are returned unchanged:
>>> string_to_token(String)
Token.Literal.String
"""
if isinstance(s, _TokenType):
return s
if not s:
return Token
node = Token
for item in s.split('.'):
node = getattr(node, item)
return node
# Map standard token types to short names, used in CSS class naming.
# If you add a new item, please be sure to run this file to perform
# a consistency check for duplicate values.
STANDARD_TYPES = {
Token: '',
Text: '',
Error: 'err',
Other: 'x',
Keyword: 'k',
Keyword.Constant: 'kc',
Keyword.Declaration: 'kd',
Keyword.Pseudo: 'kp',
Keyword.Reserved: 'kr',
Keyword.Type: 'kt',
Name: 'n',
Name.Attribute: 'na',
Name.Builtin: 'nb',
Name.Builtin.Pseudo: 'bp',
Name.Class: 'nc',
Name.Constant: 'no',
Name.Decorator: 'nd',
Name.Entity: 'ni',
Name.Exception: 'ne',
Name.Function: 'nf',
Name.Property: 'py',
Name.Label: 'nl',
Name.Namespace: 'nn',
Name.Other: 'nx',
Name.Tag: 'nt',
Name.Variable: 'nv',
Name.Variable.Class: 'vc',
Name.Variable.Global: 'vg',
Name.Variable.Instance: 'vi',
Literal: 'l',
Literal.Date: 'ld',
String: 's',
String.Backtick: 'sb',
String.Char: 'sc',
String.Doc: 'sd',
String.Double: 's2',
String.Escape: 'se',
String.Heredoc: 'sh',
String.Interpol: 'si',
String.Other: 'sx',
String.Regex: 'sr',
String.Single: 's1',
String.Symbol: 'ss',
Number: 'm',
Number.Float: 'mf',
Number.Hex: 'mh',
Number.Integer: 'mi',
Number.Integer.Long: 'il',
Number.Oct: 'mo',
Operator: 'o',
Operator.Word: 'ow',
Punctuation: 'p',
Comment: 'c',
Comment.Multiline: 'cm',
Comment.Preproc: 'cp',
Comment.Single: 'c1',
Comment.Special: 'cs',
Generic: 'g',
Generic.Deleted: 'gd',
Generic.Emph: 'ge',
Generic.Error: 'gr',
Generic.Heading: 'gh',
Generic.Inserted: 'gi',
Generic.Output: 'go',
Generic.Prompt: 'gp',
Generic.Strong: 'gs',
Generic.Subheading: 'gu',
Generic.Traceback: 'gt',
}
if __name__ == '__main__':
import sys
# sanity check for token name dict: no duplicate entries!
s = STANDARD_TYPES.copy()
s[Token] = '---' # Token and Text do conflict, that is okay
t = {}
for k, v in s.iteritems():
t.setdefault(v, []).append(k)
if len(t) == len(s):
print 'Okay!'
sys.exit()
for k, v in t.iteritems():
if len(v) > 1:
print "%r has more than one key: %r" % (k, v)
|
