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
|
// Copyright 2016 Yahoo Inc. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.
#include <vespa/fastlib/testsuite/test.h>
#include <vespa/fastlib/text/normwordfolder.h>
class WordFoldersTest : public Test
{
bool NormalizeWordFolderConstruction() {
Fast_NormalizeWordFolder::Setup(
Fast_NormalizeWordFolder::DO_ACCENT_REMOVAL
| Fast_NormalizeWordFolder::DO_KATAKANA_TO_HIRAGANA
| Fast_NormalizeWordFolder::DO_SMALL_TO_NORMAL_KANA
| Fast_NormalizeWordFolder::DO_SHARP_S_SUBSTITUTION
| Fast_NormalizeWordFolder::DO_LIGATURE_SUBSTITUTION
| Fast_NormalizeWordFolder::DO_MULTICHAR_EXPANSION);
Fast_NormalizeWordFolder *nwf = new Fast_NormalizeWordFolder();
delete nwf;
return true;
}
bool TokenizeAnnotatedBuffer() {
Fast_NormalizeWordFolder *nwf = new Fast_NormalizeWordFolder();
const char *testinput = "This is a "
"\xEF\xBF\xB9" "café" "\xEF\xBF\xBA" "cafe" "\xEF\xBF\xBB"
" superduperextrafeaturecoolandlongplainword fun "
"\xEF\xBF\xB9" "www" "\xEF\xBF\xBA"
"world wide web extra long annotation block" "\xEF\xBF\xBB"
" test\nIt is cool.\n";
const char *correct[] = {
"this", "is", "a",
"\xEF\xBF\xB9" "café" "\xEF\xBF\xBA" "cafe" "\xEF\xBF\xBB",
"superduperextrafeaturecool", "fun",
"\xEF\xBF\xB9" "www" "\xEF\xBF\xBA" "world wide web ex",
"test", "it", "is", "cool" };
const char *teststart = testinput;
const char *testend = testinput + strlen(testinput);
char destbuf[32];
char *destbufend = destbuf + 32;
const char *origstart = testinput;
size_t tokenlen = 0;
int tokencounter = 0;
bool success = true;
while (
(teststart
= nwf->Tokenize(teststart, testend,
destbuf, destbufend,
origstart, tokenlen)) < testend) {
// printf("found: %s, correct: %s\n", destbuf, correct[tokencounter]);
success &= strcmp(destbuf, correct[tokencounter++]) == 0;
}
delete nwf;
return success;
}
bool TokenizeAnnotatedUCS4Buffer() {
Fast_NormalizeWordFolder *nwf = new Fast_NormalizeWordFolder();
const char *testinput = "This is a "
"\xEF\xBF\xB9" "café" "\xEF\xBF\xBA" "cafe" "\xEF\xBF\xBB"
" superduperextrafeaturecoolandlongplainword fun "
"\xEF\xBF\xB9" "www" "\xEF\xBF\xBA"
"world wide web extra long annotation block" "\xEF\xBF\xBB"
" test\nIt is cool.\n";
const char *correct[] = {
"this", "is", "a",
"\xEF\xBF\xB9" "café" "\xEF\xBF\xBA" "cafe" "\xEF\xBF\xBB",
"superduperextrafeaturecooland", "fun",
"\xEF\xBF\xB9" "www" "\xEF\xBF\xBA" "world wide web extra lon",
"test", "it", "is", "cool" };
const char *teststart = testinput;
const char *testend = testinput + strlen(testinput);
ucs4_t destbuf[32];
ucs4_t *destbufend = destbuf + 32;
const char *origstart = testinput;
size_t tokenlen = 0;
int tokencounter = 0;
bool success = true;
while (
(teststart
= nwf->UCS4Tokenize(teststart, testend,
destbuf, destbufend,
origstart, tokenlen)) < testend) {
success &= Fast_UnicodeUtil::utf8cmp(correct[tokencounter++], destbuf) == 0;
}
delete nwf;
return success;
}
bool AccentRemovalTest() {
auto freefunction = [] (char * ptr) { free(ptr); };
auto input = std::unique_ptr<char, decltype(freefunction)>(Fast_UnicodeUtil::strdupLAT1("����������������������������������������������������������������������������������������������p�!"),
freefunction);
auto yelloutput = std::unique_ptr<char, decltype(freefunction)>(Fast_UnicodeUtil::strdupLAT1("�������������������������������AAAAAEAAAECEEEEIIIIDNOOOOOE�OEUUUUEYTHssaaaaaeaaaeceeeeiiiidnoooooe�oeuuuueythpth!"),
freefunction);
Fast_NormalizeWordFolder wordfolder;
int len = wordfolder.FoldedSizeAsUTF8(input.get());
auto fastliboutput = std::unique_ptr<char[]>(new char[len + 1]);
wordfolder.FoldUTF8WordToUTF8Quick(fastliboutput.get(), input.get());
fastliboutput[len] = '\0';
printf("\n%s\n", yelloutput.get());
printf("%s\n", fastliboutput.get());
return strcasecmp(yelloutput.get(), fastliboutput.get()) == 0;
}
public:
void Run() override {
// do the tests
_test(NormalizeWordFolderConstruction());
_test(TokenizeAnnotatedBuffer());
_test(TokenizeAnnotatedUCS4Buffer());
_test(AccentRemovalTest());
}
};
class WordFoldersTestApp : public FastOS_Application
{
public:
int Main() override;
};
|