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
|
# -*- coding: utf-8 -*-
#
# Copyright (C) 2008 Edgewall Software
# All rights reserved.
#
# This software is licensed as described in the file COPYING, which
# you should have received as part of this distribution. The terms
# are also available at http://babel.edgewall.org/wiki/License.
#
# This software consists of voluntary contributions made by many
# individuals. For the exact contribution history, see the revision
# history and logs, available at http://babel.edgewall.org/log/.
"""A simple JavaScript 1.5 lexer which is used for the JavaScript
extractor.
"""
import re
from operator import itemgetter
operators = [
'+', '-', '*', '%', '!=', '==', '<', '>', '<=', '>=', '=',
'+=', '-=', '*=', '%=', '<<', '>>', '>>>', '<<=', '>>=',
'>>>=', '&', '&=', '|', '|=', '&&', '||', '^', '^=', '(', ')',
'[', ']', '{', '}', '!', '--', '++', '~', ',', ';', '.', ':'
]
operators.sort(lambda a, b: cmp(-len(a), -len(b)))
escapes = {'b': '\b', 'f': '\f', 'n': '\n', 'r': '\r', 't': '\t'}
rules = [
(None, re.compile(r'\s+(?u)')),
(None, re.compile(r'<!--.*')),
('linecomment', re.compile(r'//.*')),
('multilinecomment', re.compile(r'/\*.*?\*/(?us)')),
('name', re.compile(r'(\$+\w*|[^\W\d]\w*)(?u)')),
('number', re.compile(r'''(?x)(
(?:0|[1-9]\d*)
(\.\d+)?
([eE][-+]?\d+)? |
(0x[a-fA-F0-9]+)
)''')),
('operator', re.compile(r'(%s)' % '|'.join(map(re.escape, operators)))),
('string', re.compile(r'''(?xs)(
'(?:[^'\\]*(?:\\.[^'\\]*)*)' |
"(?:[^"\\]*(?:\\.[^"\\]*)*)"
)'''))
]
division_re = re.compile(r'/=?')
regex_re = re.compile(r'/(?:[^/\\]*(?:\\.[^/\\]*)*)/[a-zA-Z]*(?s)')
line_re = re.compile(r'(\r\n|\n|\r)')
line_join_re = re.compile(r'\\' + line_re.pattern)
uni_escape_re = re.compile(r'[a-fA-F0-9]{1,4}')
class Token(tuple):
"""Represents a token as returned by `tokenize`."""
__slots__ = ()
def __new__(cls, type, value, lineno):
return tuple.__new__(cls, (type, value, lineno))
type = property(itemgetter(0))
value = property(itemgetter(1))
lineno = property(itemgetter(2))
def indicates_division(token):
"""A helper function that helps the tokenizer to decide if the current
token may be followed by a division operator.
"""
if token.type == 'operator':
return token.value in (')', ']', '}', '++', '--')
return token.type in ('name', 'number', 'string', 'regexp')
def unquote_string(string):
"""Unquote a string with JavaScript rules. The string has to start with
string delimiters (``'`` or ``"``.)
:return: a string
"""
assert string and string[0] == string[-1] and string[0] in '"\'', \
'string provided is not properly delimited'
string = line_join_re.sub('\\1', string[1:-1])
result = []
add = result.append
pos = 0
while 1:
# scan for the next escape
escape_pos = string.find('\\', pos)
if escape_pos < 0:
break
add(string[pos:escape_pos])
# check which character is escaped
next_char = string[escape_pos + 1]
if next_char in escapes:
add(escapes[next_char])
# unicode escapes. trie to consume up to four characters of
# hexadecimal characters and try to interpret them as unicode
# character point. If there is no such character point, put
# all the consumed characters into the string.
elif next_char in 'uU':
escaped = uni_escape_re.match(string, escape_pos + 2)
if escaped is not None:
escaped_value = escaped.group()
if len(escaped_value) == 4:
try:
add(unichr(int(escaped_value, 16)))
except ValueError:
pass
else:
pos = escape_pos + 6
continue
add(next_char + escaped_value)
pos = escaped.end()
continue
else:
add(next_char)
# bogus escape. Just remove the backslash.
else:
add(next_char)
pos = escape_pos + 2
if pos < len(string):
add(string[pos:])
return u''.join(result)
def tokenize(source):
"""Tokenize a JavaScript source.
:return: generator of `Token`\s
"""
may_divide = False
pos = 0
lineno = 1
end = len(source)
while pos < end:
# handle regular rules first
for token_type, rule in rules:
match = rule.match(source, pos)
if match is not None:
break
# if we don't have a match we don't give up yet, but check for
# division operators or regular expression literals, based on
# the status of `may_divide` which is determined by the last
# processed non-whitespace token using `indicates_division`.
else:
if may_divide:
match = division_re.match(source, pos)
token_type = 'operator'
else:
match = regex_re.match(source, pos)
token_type = 'regexp'
if match is None:
# woops. invalid syntax. jump one char ahead and try again.
pos += 1
continue
token_value = match.group()
if token_type is not None:
token = Token(token_type, token_value, lineno)
may_divide = indicates_division(token)
yield token
lineno += len(line_re.findall(token_value))
pos = match.end()
|
