|
1 # -*- coding: utf-8 -*- |
|
2 """ |
|
3 pygments.token |
|
4 ~~~~~~~~~~~~~~ |
|
5 |
|
6 Basic token types and the standard tokens. |
|
7 |
|
8 :copyright: Copyright 2006-2009 by the Pygments team, see AUTHORS. |
|
9 :license: BSD, see LICENSE for details. |
|
10 """ |
|
11 try: |
|
12 set |
|
13 except NameError: |
|
14 from sets import Set as set |
|
15 |
|
16 |
|
17 class _TokenType(tuple): |
|
18 parent = None |
|
19 |
|
20 def split(self): |
|
21 buf = [] |
|
22 node = self |
|
23 while node is not None: |
|
24 buf.append(node) |
|
25 node = node.parent |
|
26 buf.reverse() |
|
27 return buf |
|
28 |
|
29 def __init__(self, *args): |
|
30 # no need to call super.__init__ |
|
31 self.subtypes = set() |
|
32 |
|
33 def __contains__(self, val): |
|
34 return self is val or ( |
|
35 type(val) is self.__class__ and |
|
36 val[:len(self)] == self |
|
37 ) |
|
38 |
|
39 def __getattr__(self, val): |
|
40 if not val or not val[0].isupper(): |
|
41 return tuple.__getattribute__(self, val) |
|
42 new = _TokenType(self + (val,)) |
|
43 setattr(self, val, new) |
|
44 self.subtypes.add(new) |
|
45 new.parent = self |
|
46 return new |
|
47 |
|
48 def __hash__(self): |
|
49 return hash(tuple(self)) |
|
50 |
|
51 def __repr__(self): |
|
52 return 'Token' + (self and '.' or '') + '.'.join(self) |
|
53 |
|
54 |
|
55 Token = _TokenType() |
|
56 |
|
57 # Special token types |
|
58 Text = Token.Text |
|
59 Whitespace = Text.Whitespace |
|
60 Error = Token.Error |
|
61 # Text that doesn't belong to this lexer (e.g. HTML in PHP) |
|
62 Other = Token.Other |
|
63 |
|
64 # Common token types for source code |
|
65 Keyword = Token.Keyword |
|
66 Name = Token.Name |
|
67 Literal = Token.Literal |
|
68 String = Literal.String |
|
69 Number = Literal.Number |
|
70 Punctuation = Token.Punctuation |
|
71 Operator = Token.Operator |
|
72 Comment = Token.Comment |
|
73 |
|
74 # Generic types for non-source code |
|
75 Generic = Token.Generic |
|
76 |
|
77 # String and some others are not direct childs of Token. |
|
78 # alias them: |
|
79 Token.Token = Token |
|
80 Token.String = String |
|
81 Token.Number = Number |
|
82 |
|
83 |
|
84 def is_token_subtype(ttype, other): |
|
85 """ |
|
86 Return True if ``ttype`` is a subtype of ``other``. |
|
87 |
|
88 exists for backwards compatibility. use ``ttype in other`` now. |
|
89 """ |
|
90 return ttype in other |
|
91 |
|
92 |
|
93 def string_to_tokentype(s): |
|
94 """ |
|
95 Convert a string into a token type:: |
|
96 |
|
97 >>> string_to_token('String.Double') |
|
98 Token.Literal.String.Double |
|
99 >>> string_to_token('Token.Literal.Number') |
|
100 Token.Literal.Number |
|
101 >>> string_to_token('') |
|
102 Token |
|
103 |
|
104 Tokens that are already tokens are returned unchanged: |
|
105 |
|
106 >>> string_to_token(String) |
|
107 Token.Literal.String |
|
108 """ |
|
109 if isinstance(s, _TokenType): |
|
110 return s |
|
111 if not s: |
|
112 return Token |
|
113 node = Token |
|
114 for item in s.split('.'): |
|
115 node = getattr(node, item) |
|
116 return node |
|
117 |
|
118 |
|
119 # Map standard token types to short names, used in CSS class naming. |
|
120 # If you add a new item, please be sure to run this file to perform |
|
121 # a consistency check for duplicate values. |
|
122 STANDARD_TYPES = { |
|
123 Token: '', |
|
124 |
|
125 Text: '', |
|
126 Whitespace: 'w', |
|
127 Error: 'err', |
|
128 Other: 'x', |
|
129 |
|
130 Keyword: 'k', |
|
131 Keyword.Constant: 'kc', |
|
132 Keyword.Declaration: 'kd', |
|
133 Keyword.Namespace: 'kn', |
|
134 Keyword.Pseudo: 'kp', |
|
135 Keyword.Reserved: 'kr', |
|
136 Keyword.Type: 'kt', |
|
137 |
|
138 Name: 'n', |
|
139 Name.Attribute: 'na', |
|
140 Name.Builtin: 'nb', |
|
141 Name.Builtin.Pseudo: 'bp', |
|
142 Name.Class: 'nc', |
|
143 Name.Constant: 'no', |
|
144 Name.Decorator: 'nd', |
|
145 Name.Entity: 'ni', |
|
146 Name.Exception: 'ne', |
|
147 Name.Function: 'nf', |
|
148 Name.Property: 'py', |
|
149 Name.Label: 'nl', |
|
150 Name.Namespace: 'nn', |
|
151 Name.Other: 'nx', |
|
152 Name.Tag: 'nt', |
|
153 Name.Variable: 'nv', |
|
154 Name.Variable.Class: 'vc', |
|
155 Name.Variable.Global: 'vg', |
|
156 Name.Variable.Instance: 'vi', |
|
157 |
|
158 Literal: 'l', |
|
159 Literal.Date: 'ld', |
|
160 |
|
161 String: 's', |
|
162 String.Backtick: 'sb', |
|
163 String.Char: 'sc', |
|
164 String.Doc: 'sd', |
|
165 String.Double: 's2', |
|
166 String.Escape: 'se', |
|
167 String.Heredoc: 'sh', |
|
168 String.Interpol: 'si', |
|
169 String.Other: 'sx', |
|
170 String.Regex: 'sr', |
|
171 String.Single: 's1', |
|
172 String.Symbol: 'ss', |
|
173 |
|
174 Number: 'm', |
|
175 Number.Float: 'mf', |
|
176 Number.Hex: 'mh', |
|
177 Number.Integer: 'mi', |
|
178 Number.Integer.Long: 'il', |
|
179 Number.Oct: 'mo', |
|
180 |
|
181 Operator: 'o', |
|
182 Operator.Word: 'ow', |
|
183 |
|
184 Punctuation: 'p', |
|
185 |
|
186 Comment: 'c', |
|
187 Comment.Multiline: 'cm', |
|
188 Comment.Preproc: 'cp', |
|
189 Comment.Single: 'c1', |
|
190 Comment.Special: 'cs', |
|
191 |
|
192 Generic: 'g', |
|
193 Generic.Deleted: 'gd', |
|
194 Generic.Emph: 'ge', |
|
195 Generic.Error: 'gr', |
|
196 Generic.Heading: 'gh', |
|
197 Generic.Inserted: 'gi', |
|
198 Generic.Output: 'go', |
|
199 Generic.Prompt: 'gp', |
|
200 Generic.Strong: 'gs', |
|
201 Generic.Subheading: 'gu', |
|
202 Generic.Traceback: 'gt', |
|
203 } |