blob: b7ca9dbca722f82b0a4985d432639762a6f51d11 (
plain)
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
|
:mod:`token` --- Constants used with Python parse trees
=======================================================
.. module:: token
:synopsis: Constants representing terminal nodes of the parse tree.
.. sectionauthor:: Fred L. Drake, Jr. <fdrake@acm.org>
**Source code:** :source:`Lib/token.py`
--------------
This module provides constants which represent the numeric values of leaf nodes
of the parse tree (terminal tokens). Refer to the file :file:`Grammar/Grammar`
in the Python distribution for the definitions of the names in the context of
the language grammar. The specific numeric values which the names map to may
change between Python versions.
The module also provides a mapping from numeric codes to names and some
functions. The functions mirror definitions in the Python C header files.
.. data:: tok_name
Dictionary mapping the numeric values of the constants defined in this module
back to name strings, allowing more human-readable representation of parse trees
to be generated.
.. function:: ISTERMINAL(x)
Return true for terminal token values.
.. function:: ISNONTERMINAL(x)
Return true for non-terminal token values.
.. function:: ISEOF(x)
Return true if *x* is the marker indicating the end of input.
The token constants are:
.. data:: ENDMARKER
NAME
NUMBER
STRING
NEWLINE
INDENT
DEDENT
LPAR
RPAR
LSQB
RSQB
COLON
COMMA
SEMI
PLUS
MINUS
STAR
SLASH
VBAR
AMPER
LESS
GREATER
EQUAL
DOT
PERCENT
LBRACE
RBRACE
EQEQUAL
NOTEQUAL
LESSEQUAL
GREATEREQUAL
TILDE
CIRCUMFLEX
LEFTSHIFT
RIGHTSHIFT
DOUBLESTAR
PLUSEQUAL
MINEQUAL
STAREQUAL
SLASHEQUAL
PERCENTEQUAL
AMPEREQUAL
VBAREQUAL
CIRCUMFLEXEQUAL
LEFTSHIFTEQUAL
RIGHTSHIFTEQUAL
DOUBLESTAREQUAL
DOUBLESLASH
DOUBLESLASHEQUAL
AT
ATEQUAL
RARROW
ELLIPSIS
OP
AWAIT
ASYNC
ERRORTOKEN
N_TOKENS
NT_OFFSET
The following token type values aren't used by the C tokenizer but are needed for
the :mod:`tokenize` module.
.. data:: COMMENT
Token value used to indicate a comment.
.. data:: NL
Token value used to indicate a non-terminating newline. The
:data:`NEWLINE` token indicates the end of a logical line of Python code;
``NL`` tokens are generated when a logical line of code is continued over
multiple physical lines.
.. data:: ENCODING
Token value that indicates the encoding used to decode the source bytes
into text. The first token returned by :func:`tokenize.tokenize` will
always be an ``ENCODING`` token.
.. versionchanged:: 3.5
Added :data:`AWAIT` and :data:`ASYNC` tokens. Starting with
Python 3.7, "async" and "await" will be tokenized as :data:`NAME`
tokens, and :data:`AWAIT` and :data:`ASYNC` will be removed.
.. versionchanged:: 3.7
Added :data:`COMMENT`, :data:`NL` and :data:`ENCODING` tokens.
|
