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
|
Testing some aspects of named groups
=================================================
>>> import re2
>>> re2.set_fallback_notification(re2.FALLBACK_EXCEPTION)
>>> m = re2.match(r"(?P<first_name>\w+) (?P<last_name>\w+)", "Malcolm Reynolds")
>>> m.start("first_name")
0
>>> m.start("last_name")
8
>>> m.span("last_name")
(8, 16)
>>> m.regs
((0, 16), (0, 7), (8, 16))
>>> m = re2.match(u"(?P<first_name>\\w+) (?P<last_name>\\w+)", u"Malcolm Reynolds")
>>> m.start(u"first_name")
0
>>> m.start(u"last_name")
8
>>> m.span(u"last_name")
(8, 16)
>>> m.regs
((0, 16), (0, 7), (8, 16))
Compare patterns with and without unicode
>>> pattern = re2.compile(br"(?P<first_name>\w+) (?P<last_name>\w+)")
>>> print(pattern._dump_pattern().decode('utf8'))
(?P<first_name>\w+) (?P<last_name>\w+)
>>> pattern = re2.compile(u"(?P<first_name>\\w+) (?P<last_name>\\w+)",
... re2.UNICODE)
>>> print(pattern._dump_pattern())
(?P<first_name>[_\p{L}\p{Nd}]+) (?P<last_name>[_\p{L}\p{Nd}]+)
Make sure positions are converted properly for unicode
>>> m = pattern.match(
... u'\u05d9\u05e9\u05e8\u05d0\u05dc \u05e6\u05d3\u05d5\u05e7')
>>> m.start(u"first_name")
0
>>> m.start(u"last_name")
6
>>> m.end(u"last_name")
10
>>> m.regs
((0, 10), (0, 5), (6, 10))
>>> m.span(2)
(6, 10)
>>> m.span(u"last_name")
(6, 10)
>>> re2.set_fallback_notification(re2.FALLBACK_QUIETLY)
|
