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
|
# These test special UTF and UCP features of DFA matching. The output is
# different for the different widths.
#subject dfa
# ----------------------------------------------------
# These are a selection of the more comprehensive tests that are run for
# non-DFA matching.
/X/utf
XX\x{d800}
Failed: error -24: UTF-16 error: missing low surrogate at end at offset 2
XX\x{d800}\=offset=3
No match
XX\x{d800}\=no_utf_check
0: X
XX\x{da00}
Failed: error -24: UTF-16 error: missing low surrogate at end at offset 2
XX\x{da00}\=no_utf_check
0: X
XX\x{dc00}
Failed: error -26: UTF-16 error: isolated low surrogate at offset 2
XX\x{dc00}\=no_utf_check
0: X
XX\x{de00}
Failed: error -26: UTF-16 error: isolated low surrogate at offset 2
XX\x{de00}\=no_utf_check
0: X
XX\x{dfff}
Failed: error -26: UTF-16 error: isolated low surrogate at offset 2
XX\x{dfff}\=no_utf_check
0: X
XX\x{110000}
** Failed: character \N{U+110000} is greater than 0x10ffff and therefore cannot be encoded as UTF-16
XX\x{d800}\x{1234}
Failed: error -25: UTF-16 error: invalid low surrogate at offset 2
/badutf/utf
X\xdf
No match
XX\xef
No match
XXX\xef\x80
No match
X\xf7
No match
XX\xf7\x80
No match
XXX\xf7\x80\x80
No match
/shortutf/utf
XX\xdf\=ph
No match
XX\xef\=ph
No match
XX\xef\x80\=ph
No match
\xf7\=ph
No match
\xf7\x80\=ph
No match
# ----------------------------------------------------
# UCP and casing tests - except for the first two, these will all fail in 8-bit
# mode because they are testing UCP without UTF and use characters > 255.
/\x{c1}/i,no_start_optimize
\= Expect no match
\x{e1}
No match
/\x{c1}+\x{e1}/iB,ucp
------------------------------------------------------------------
Bra
/i \x{c1}+
/i \x{e1}
Ket
End
------------------------------------------------------------------
\x{c1}\x{c1}\x{c1}
0: \xc1\xc1\xc1
1: \xc1\xc1
\x{e1}\x{e1}\x{e1}
0: \xe1\xe1\xe1
1: \xe1\xe1
/\x{120}\x{c1}/i,ucp,no_start_optimize
\x{121}\x{e1}
0: \x{121}\xe1
/\x{120}\x{c1}/i,ucp
\x{121}\x{e1}
0: \x{121}\xe1
/[^\x{120}]/i,no_start_optimize
\x{121}
0: \x{121}
/[^\x{120}]/i,ucp,no_start_optimize
\= Expect no match
\x{121}
No match
/[^\x{120}]/i
\x{121}
0: \x{121}
/[^\x{120}]/i,ucp
\= Expect no match
\x{121}
No match
/\x{120}{2}/i,ucp
\x{121}\x{121}
0: \x{121}\x{121}
/[^\x{120}]{2}/i,ucp
\= Expect no match
\x{121}\x{121}
No match
# ----------------------------------------------------
# ----------------------------------------------------
# Tests for handling 0xffffffff in caseless UCP mode. They only apply to 32-bit
# mode; for the other widths they will fail.
/k*\x{ffffffff}/caseless,ucp
Failed: error 134 at offset 13: character code point value in \x{} or \o{} is too large
\x{ffffffff}
/k+\x{ffffffff}/caseless,ucp,no_start_optimize
Failed: error 134 at offset 13: character code point value in \x{} or \o{} is too large
K\x{ffffffff}
\= Expect no match
\x{ffffffff}\x{ffffffff}
/k{2}\x{ffffffff}/caseless,ucp,no_start_optimize
Failed: error 134 at offset 15: character code point value in \x{} or \o{} is too large
\= Expect no match
\x{ffffffff}\x{ffffffff}\x{ffffffff}
/k\x{ffffffff}/caseless,ucp,no_start_optimize
Failed: error 134 at offset 12: character code point value in \x{} or \o{} is too large
K\x{ffffffff}
\= Expect no match
\x{ffffffff}\x{ffffffff}\x{ffffffff}
/k{2,}?Z/caseless,ucp,no_start_optimize,no_auto_possess
\= Expect no match
Kk\x{ffffffff}\x{ffffffff}\x{ffffffff}Z
** Character \x{ffffffff} is greater than 0xffff and UTF-16 mode is not enabled.
** Truncation will probably give the wrong result.
** Character \x{ffffffff} is greater than 0xffff and UTF-16 mode is not enabled.
** Truncation will probably give the wrong result.
** Character \x{ffffffff} is greater than 0xffff and UTF-16 mode is not enabled.
** Truncation will probably give the wrong result.
No match
# ----------------------------------------------------
# End of testinput14
|
