-
Notifications
You must be signed in to change notification settings - Fork 69
/
parser.py
209 lines (190 loc) · 6.17 KB
/
parser.py
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
r"""
Parse string to create Regex object.
TODO:
- Support \: \001, \x00, \0, \ \[, \(, \{, etc.
- Support Python extensions: (?:...), (?P<name>...), etc.
- Support \<, \>, \s, \S, \w, \W, \Z <=> $, \d, \D, \A <=> ^, \b, \B, [[:space:]], etc.
"""
from hachoir.regex import (RegexString, RegexEmpty, RegexRepeat,
RegexDot, RegexWord, RegexStart, RegexEnd,
RegexRange, RegexRangeItem, RegexRangeCharacter)
import re
REGEX_COMMAND_CHARACTERS = '.^$[](){}|+?*\\'
def parseRange(text, start):
r"""
>>> parseRange('[a]b', 1)
(<RegexRange '[a]'>, 3)
>>> parseRange('[a-z]b', 1)
(<RegexRange '[a-z]'>, 5)
>>> parseRange('[^a-z-]b', 1)
(<RegexRange '[^a-z-]'>, 7)
>>> parseRange('[^]-]b', 1)
(<RegexRange '[^]-]'>, 5)
>>> parseRange(r'[\]abc]', 1)
(<RegexRange '[]a-c]'>, 7)
>>> parseRange(r'[a\-x]', 1)
(<RegexRange '[ax-]'>, 6)
"""
index = start
char_range = []
exclude = False
if text[index] == '^':
exclude = True
index += 1
if text[index] == ']':
char_range.append(RegexRangeCharacter(']'))
index += 1
while index < len(text) and text[index] != ']':
if index + 1 < len(text) \
and text[index] == '\\':
char_range.append(RegexRangeCharacter(text[index + 1]))
index += 2
elif index + 1 < len(text) \
and text[index] == '-' and text[index + 1] == ']':
break
elif index + 3 < len(text) \
and text[index + 1] == '-' \
and text[index + 2] != ']':
char_range.append(RegexRangeItem(
ord(text[index]), ord(text[index + 2])))
index += 3
else:
char_range.append(RegexRangeCharacter(text[index]))
index += 1
if index < len(text) and text[index] == '-':
char_range.append(RegexRangeCharacter('-'))
index += 1
if index == len(text) or text[index] != ']':
raise SyntaxError('Invalid range: %s' % text[start - 1:index])
return RegexRange(char_range, exclude), index + 1
def parseOr(text, start):
"""
>>> parseOr('(a)', 1)
(<RegexString 'a'>, 3)
>>> parseOr('(a|c)', 1)
(<RegexRange '[ac]'>, 5)
>>> parseOr(' (a|[bc]|d)', 2)
(<RegexRange '[a-d]'>, 11)
"""
index = start
# (?:...): Skip Python prefix '?:'
if text[index:index + 2] == '?:':
index += 2
if text[index] == '?':
raise NotImplementedError("Doesn't support Python extension (?...)")
regex = None
while True:
new_regex, index = _parse(text, index, "|)")
if regex:
regex = regex | new_regex
else:
regex = new_regex
if len(text) <= index:
raise SyntaxError('Missing closing parenthesis')
if text[index] == ')':
break
index += 1
index += 1
if regex is None:
regex = RegexEmpty()
return regex, index
REPEAT_REGEX = re.compile("([0-9]+)(,[0-9]*)?}")
def parseRepeat(text, start):
"""
>>> parseRepeat('a{0,1}b', 2)
(0, 1, 6)
>>> parseRepeat('a{12}', 2)
(12, 12, 5)
"""
match = REPEAT_REGEX.match(text, start)
if not match:
raise SyntaxError('Unable to parse repetition ' + text[start:])
rmin = int(match.group(1))
if match.group(2):
text = match.group(2)[1:]
if text:
rmax = int(text)
else:
rmax = None
else:
rmax = rmin
return (rmin, rmax, match.end(0))
CHAR_TO_FUNC = {'[': parseRange, '(': parseOr}
CHAR_TO_CLASS = {'.': RegexDot, '^': RegexStart, '$': RegexEnd}
CHAR_TO_REPEAT = {'*': (0, None), '?': (0, 1), '+': (1, None)}
def _parse(text, start=0, until=None):
if len(text) == start:
return RegexEmpty(), 0
index = start
regex = RegexEmpty()
last = None
while index < len(text):
char = text[index]
if until and char in until:
break
if char in REGEX_COMMAND_CHARACTERS:
if char in CHAR_TO_FUNC:
new_regex, index = CHAR_TO_FUNC[char](text, index + 1)
elif char in CHAR_TO_CLASS:
new_regex = CHAR_TO_CLASS[char]()
index += 1
elif char == '{':
rmin, rmax, index = parseRepeat(text, index + 1)
new_regex = RegexRepeat(last, rmin, rmax)
last = None
elif char in CHAR_TO_REPEAT:
rmin, rmax = CHAR_TO_REPEAT[char]
if last is None:
raise SyntaxError(
'Repetition character (%s) without previous expression' % text[index])
new_regex = RegexRepeat(last, rmin, rmax)
last = None
index += 1
elif char == "\\":
index += 1
if index == len(text):
raise SyntaxError(
"Antislash (\\) without escaped character")
char = text[index]
if char == 'b':
new_regex = RegexWord()
else:
if not (char in REGEX_COMMAND_CHARACTERS or char in " '"):
raise SyntaxError(
"Operator '\\%s' is not supported" % char)
new_regex = RegexString(char)
index += 1
else:
raise NotImplementedError(
"Operator '%s' is not supported" % char)
if last:
regex = regex + last
last = new_regex
else:
subtext = text[index]
index += 1
if last:
regex = regex + last
last = RegexString(subtext)
if last:
regex = regex + last
return regex, index
def parse(text):
r"""
>>> parse('')
<RegexEmpty ''>
>>> parse('abc')
<RegexString 'abc'>
>>> parse("chats?")
<RegexAnd 'chats?'>
>>> parse('[bc]d')
<RegexAnd '[bc]d'>
>>> parse("\\.")
<RegexString '\.'>
"""
regex, index = _parse(text)
assert index == len(text)
return regex
if __name__ == "__main__":
import doctest
doctest.testmod()