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
|
"""Token constants (from "token.h")."""
__all__ = ['tok_name', 'ISTERMINAL', 'ISNONTERMINAL', 'ISEOF']
# This file is automatically generated; please don't muck it up!
#
# To update the symbols in this file, 'cd' to the top directory of
# the python source tree after building the interpreter and run:
#
# ./python Lib/token.py
#--start constants--
ENDMARKER = 0
NAME = 1
NUMBER = 2
STRING = 3
NEWLINE = 4
INDENT = 5
DEDENT = 6
LPAR = 7
RPAR = 8
LSQB = 9
RSQB = 10
COLON = 11
COMMA = 12
SEMI = 13
PLUS = 14
MINUS = 15
STAR = 16
SLASH = 17
VBAR = 18
AMPER = 19
LESS = 20
GREATER = 21
EQUAL = 22
DOT = 23
PERCENT = 24
LBRACE = 25
RBRACE = 26
EQEQUAL = 27
NOTEQUAL = 28
LESSEQUAL = 29
GREATEREQUAL = 30
TILDE = 31
CIRCUMFLEX = 32
LEFTSHIFT = 33
RIGHTSHIFT = 34
DOUBLESTAR = 35
PLUSEQUAL = 36
MINEQUAL = 37
STAREQUAL = 38
SLASHEQUAL = 39
PERCENTEQUAL = 40
AMPEREQUAL = 41
VBAREQUAL = 42
CIRCUMFLEXEQUAL = 43
LEFTSHIFTEQUAL = 44
RIGHTSHIFTEQUAL = 45
DOUBLESTAREQUAL = 46
DOUBLESLASH = 47
DOUBLESLASHEQUAL = 48
AT = 49
ATEQUAL = 50
RARROW = 51
ELLIPSIS = 52
# Don't forget to update the table _PyParser_TokenNames in tokenizer.c!
OP = 53
ERRORTOKEN = 54
# These aren't used by the C tokenizer but are needed for tokenize.py
COMMENT = 55
NL = 56
ENCODING = 57
N_TOKENS = 58
# Special definitions for cooperation with parser
NT_OFFSET = 256
#--end constants--
tok_name = {value: name
for name, value in globals().items()
if isinstance(value, int) and not name.startswith('_')}
__all__.extend(tok_name.values())
def ISTERMINAL(x):
return x < NT_OFFSET
def ISNONTERMINAL(x):
return x >= NT_OFFSET
def ISEOF(x):
return x == ENDMARKER
def _main():
import re
import sys
args = sys.argv[1:]
inFileName = args and args[0] or "Include/token.h"
outFileName = "Lib/token.py"
if len(args) > 1:
outFileName = args[1]
try:
fp = open(inFileName)
except OSError as err:
sys.stdout.write("I/O error: %s\n" % str(err))
sys.exit(1)
with fp:
lines = fp.read().split("\n")
prog = re.compile(
r"#define[ \t][ \t]*([A-Z0-9][A-Z0-9_]*)[ \t][ \t]*([0-9][0-9]*)",
re.IGNORECASE)
comment_regex = re.compile(
r"^\s*/\*\s*(.+?)\s*\*/\s*$",
re.IGNORECASE)
tokens = {}
prev_val = None
for line in lines:
match = prog.match(line)
if match:
name, val = match.group(1, 2)
val = int(val)
tokens[val] = {'token': name} # reverse so we can sort them...
prev_val = val
else:
comment_match = comment_regex.match(line)
if comment_match and prev_val is not None:
comment = comment_match.group(1)
tokens[prev_val]['comment'] = comment
keys = sorted(tokens.keys())
# load the output skeleton from the target:
try:
fp = open(outFileName)
except OSError as err:
sys.stderr.write("I/O error: %s\n" % str(err))
sys.exit(2)
with fp:
format = fp.read().split("\n")
try:
start = format.index("#--start constants--") + 1
end = format.index("#--end constants--")
except ValueError:
sys.stderr.write("target does not contain format markers")
sys.exit(3)
lines = []
for key in keys:
lines.append("%s = %d" % (tokens[key]["token"], key))
if "comment" in tokens[key]:
lines.append("# %s" % tokens[key]["comment"])
format[start:end] = lines
try:
fp = open(outFileName, 'w')
except OSError as err:
sys.stderr.write("I/O error: %s\n" % str(err))
sys.exit(4)
with fp:
fp.write("\n".join(format))
if __name__ == "__main__":
_main()
|
