cppjieba_rb 0.3.3 → 0.4.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/.travis.yml +3 -0
- data/README.md +1 -1
- data/Rakefile +2 -2
- data/cppjieba_rb.gemspec +4 -4
- data/lib/cppjieba_rb/version.rb +1 -1
- metadata +17 -135
- data/ext/cppjieba/.gitignore +0 -17
- data/ext/cppjieba/.travis.yml +0 -21
- data/ext/cppjieba/CMakeLists.txt +0 -28
- data/ext/cppjieba/ChangeLog.md +0 -236
- data/ext/cppjieba/README.md +0 -292
- data/ext/cppjieba/README_EN.md +0 -113
- data/ext/cppjieba/appveyor.yml +0 -32
- data/ext/cppjieba/deps/CMakeLists.txt +0 -1
- data/ext/cppjieba/deps/gtest/CMakeLists.txt +0 -5
- data/ext/cppjieba/deps/gtest/include/gtest/gtest-death-test.h +0 -283
- data/ext/cppjieba/deps/gtest/include/gtest/gtest-message.h +0 -230
- data/ext/cppjieba/deps/gtest/include/gtest/gtest-param-test.h +0 -1421
- data/ext/cppjieba/deps/gtest/include/gtest/gtest-param-test.h.pump +0 -487
- data/ext/cppjieba/deps/gtest/include/gtest/gtest-printers.h +0 -796
- data/ext/cppjieba/deps/gtest/include/gtest/gtest-spi.h +0 -232
- data/ext/cppjieba/deps/gtest/include/gtest/gtest-test-part.h +0 -176
- data/ext/cppjieba/deps/gtest/include/gtest/gtest-typed-test.h +0 -259
- data/ext/cppjieba/deps/gtest/include/gtest/gtest.h +0 -2155
- data/ext/cppjieba/deps/gtest/include/gtest/gtest_pred_impl.h +0 -358
- data/ext/cppjieba/deps/gtest/include/gtest/gtest_prod.h +0 -58
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-death-test-internal.h +0 -308
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-filepath.h +0 -210
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-internal.h +0 -1226
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-linked_ptr.h +0 -233
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-param-util-generated.h +0 -4822
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-param-util-generated.h.pump +0 -301
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-param-util.h +0 -619
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-port.h +0 -1788
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-string.h +0 -350
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-tuple.h +0 -968
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-tuple.h.pump +0 -336
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-type-util.h +0 -3330
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-type-util.h.pump +0 -296
- data/ext/cppjieba/deps/gtest/src/.deps/.dirstamp +0 -0
- data/ext/cppjieba/deps/gtest/src/.deps/gtest-all.Plo +0 -681
- data/ext/cppjieba/deps/gtest/src/.deps/gtest_main.Plo +0 -509
- data/ext/cppjieba/deps/gtest/src/.dirstamp +0 -0
- data/ext/cppjieba/deps/gtest/src/gtest-all.cc +0 -48
- data/ext/cppjieba/deps/gtest/src/gtest-death-test.cc +0 -1234
- data/ext/cppjieba/deps/gtest/src/gtest-filepath.cc +0 -380
- data/ext/cppjieba/deps/gtest/src/gtest-internal-inl.h +0 -1038
- data/ext/cppjieba/deps/gtest/src/gtest-port.cc +0 -746
- data/ext/cppjieba/deps/gtest/src/gtest-printers.cc +0 -356
- data/ext/cppjieba/deps/gtest/src/gtest-test-part.cc +0 -110
- data/ext/cppjieba/deps/gtest/src/gtest-typed-test.cc +0 -110
- data/ext/cppjieba/deps/gtest/src/gtest.cc +0 -4898
- data/ext/cppjieba/deps/gtest/src/gtest_main.cc +0 -39
- data/ext/cppjieba/deps/limonp/ArgvContext.hpp +0 -70
- data/ext/cppjieba/deps/limonp/BlockingQueue.hpp +0 -49
- data/ext/cppjieba/deps/limonp/BoundedBlockingQueue.hpp +0 -67
- data/ext/cppjieba/deps/limonp/BoundedQueue.hpp +0 -65
- data/ext/cppjieba/deps/limonp/Closure.hpp +0 -206
- data/ext/cppjieba/deps/limonp/Colors.hpp +0 -31
- data/ext/cppjieba/deps/limonp/Condition.hpp +0 -38
- data/ext/cppjieba/deps/limonp/Config.hpp +0 -103
- data/ext/cppjieba/deps/limonp/FileLock.hpp +0 -74
- data/ext/cppjieba/deps/limonp/ForcePublic.hpp +0 -7
- data/ext/cppjieba/deps/limonp/LocalVector.hpp +0 -139
- data/ext/cppjieba/deps/limonp/Logging.hpp +0 -76
- data/ext/cppjieba/deps/limonp/Md5.hpp +0 -411
- data/ext/cppjieba/deps/limonp/MutexLock.hpp +0 -51
- data/ext/cppjieba/deps/limonp/NonCopyable.hpp +0 -21
- data/ext/cppjieba/deps/limonp/StdExtension.hpp +0 -159
- data/ext/cppjieba/deps/limonp/StringUtil.hpp +0 -365
- data/ext/cppjieba/deps/limonp/Thread.hpp +0 -44
- data/ext/cppjieba/deps/limonp/ThreadPool.hpp +0 -86
- data/ext/cppjieba/dict/README.md +0 -31
- data/ext/cppjieba/dict/hmm_model.utf8 +0 -34
- data/ext/cppjieba/dict/idf.utf8 +0 -258826
- data/ext/cppjieba/dict/jieba.dict.utf8 +0 -348982
- data/ext/cppjieba/dict/pos_dict/char_state_tab.utf8 +0 -6653
- data/ext/cppjieba/dict/pos_dict/prob_emit.utf8 +0 -166
- data/ext/cppjieba/dict/pos_dict/prob_start.utf8 +0 -259
- data/ext/cppjieba/dict/pos_dict/prob_trans.utf8 +0 -5222
- data/ext/cppjieba/dict/stop_words.utf8 +0 -1534
- data/ext/cppjieba/dict/user.dict.utf8 +0 -4
- data/ext/cppjieba/include/cppjieba/DictTrie.hpp +0 -277
- data/ext/cppjieba/include/cppjieba/FullSegment.hpp +0 -93
- data/ext/cppjieba/include/cppjieba/HMMModel.hpp +0 -129
- data/ext/cppjieba/include/cppjieba/HMMSegment.hpp +0 -190
- data/ext/cppjieba/include/cppjieba/Jieba.hpp +0 -130
- data/ext/cppjieba/include/cppjieba/KeywordExtractor.hpp +0 -153
- data/ext/cppjieba/include/cppjieba/MPSegment.hpp +0 -137
- data/ext/cppjieba/include/cppjieba/MixSegment.hpp +0 -109
- data/ext/cppjieba/include/cppjieba/PosTagger.hpp +0 -77
- data/ext/cppjieba/include/cppjieba/PreFilter.hpp +0 -54
- data/ext/cppjieba/include/cppjieba/QuerySegment.hpp +0 -90
- data/ext/cppjieba/include/cppjieba/SegmentBase.hpp +0 -46
- data/ext/cppjieba/include/cppjieba/SegmentTagged.hpp +0 -23
- data/ext/cppjieba/include/cppjieba/TextRankExtractor.hpp +0 -190
- data/ext/cppjieba/include/cppjieba/Trie.hpp +0 -174
- data/ext/cppjieba/include/cppjieba/Unicode.hpp +0 -227
- data/ext/cppjieba/test/CMakeLists.txt +0 -5
- data/ext/cppjieba/test/demo.cpp +0 -80
- data/ext/cppjieba/test/load_test.cpp +0 -54
- data/ext/cppjieba/test/testdata/curl.res +0 -1
- data/ext/cppjieba/test/testdata/extra_dict/jieba.dict.small.utf8 +0 -109750
- data/ext/cppjieba/test/testdata/gbk_dict/hmm_model.gbk +0 -34
- data/ext/cppjieba/test/testdata/gbk_dict/jieba.dict.gbk +0 -348982
- data/ext/cppjieba/test/testdata/jieba.dict.0.1.utf8 +0 -93
- data/ext/cppjieba/test/testdata/jieba.dict.0.utf8 +0 -93
- data/ext/cppjieba/test/testdata/jieba.dict.1.utf8 +0 -67
- data/ext/cppjieba/test/testdata/jieba.dict.2.utf8 +0 -64
- data/ext/cppjieba/test/testdata/load_test.urls +0 -2
- data/ext/cppjieba/test/testdata/review.100 +0 -100
- data/ext/cppjieba/test/testdata/review.100.res +0 -200
- data/ext/cppjieba/test/testdata/server.conf +0 -19
- data/ext/cppjieba/test/testdata/testlines.gbk +0 -9
- data/ext/cppjieba/test/testdata/testlines.utf8 +0 -8
- data/ext/cppjieba/test/testdata/userdict.2.utf8 +0 -1
- data/ext/cppjieba/test/testdata/userdict.english +0 -2
- data/ext/cppjieba/test/testdata/userdict.utf8 +0 -8
- data/ext/cppjieba/test/testdata/weicheng.utf8 +0 -247
- data/ext/cppjieba/test/unittest/CMakeLists.txt +0 -24
- data/ext/cppjieba/test/unittest/gtest_main.cpp +0 -39
- data/ext/cppjieba/test/unittest/jieba_test.cpp +0 -133
- data/ext/cppjieba/test/unittest/keyword_extractor_test.cpp +0 -79
- data/ext/cppjieba/test/unittest/pos_tagger_test.cpp +0 -41
- data/ext/cppjieba/test/unittest/pre_filter_test.cpp +0 -43
- data/ext/cppjieba/test/unittest/segments_test.cpp +0 -256
- data/ext/cppjieba/test/unittest/textrank_test.cpp +0 -86
- data/ext/cppjieba/test/unittest/trie_test.cpp +0 -177
- data/ext/cppjieba/test/unittest/unicode_test.cpp +0 -43
@@ -1,79 +0,0 @@
|
|
1
|
-
#include "cppjieba/KeywordExtractor.hpp"
|
2
|
-
#include "gtest/gtest.h"
|
3
|
-
|
4
|
-
using namespace cppjieba;
|
5
|
-
|
6
|
-
TEST(KeywordExtractorTest, Test1) {
|
7
|
-
KeywordExtractor Extractor("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", "../dict/idf.utf8", "../dict/stop_words.utf8");
|
8
|
-
|
9
|
-
{
|
10
|
-
string s("你好世界世界而且而且");
|
11
|
-
string res;
|
12
|
-
size_t topN = 5;
|
13
|
-
|
14
|
-
{
|
15
|
-
vector<string> words;
|
16
|
-
Extractor.Extract(s, words, topN);
|
17
|
-
res << words;
|
18
|
-
ASSERT_EQ(res, "[\"世界\", \"你好\"]");
|
19
|
-
}
|
20
|
-
|
21
|
-
{
|
22
|
-
vector<pair<string, double> > words;
|
23
|
-
Extractor.Extract(s, words, topN);
|
24
|
-
res << words;
|
25
|
-
ASSERT_EQ(res, "[世界:8.73506, 你好:7.95788]");
|
26
|
-
}
|
27
|
-
|
28
|
-
{
|
29
|
-
vector<KeywordExtractor::Word> words;
|
30
|
-
Extractor.Extract(s, words, topN);
|
31
|
-
res << words;
|
32
|
-
ASSERT_EQ(res, "[{\"word\": \"\xE4\xB8\x96\xE7\x95\x8C\", \"offset\": [6, 12], \"weight\": 8.73506}, {\"word\": \"\xE4\xBD\xA0\xE5\xA5\xBD\", \"offset\": [0], \"weight\": 7.95788}]");
|
33
|
-
}
|
34
|
-
}
|
35
|
-
|
36
|
-
{
|
37
|
-
string s("我是拖拉机学院手扶拖拉机专业的。不用多久,我就会升职加薪,当上CEO,走上人生巅峰。");
|
38
|
-
string res;
|
39
|
-
vector<KeywordExtractor::Word> wordweights;
|
40
|
-
size_t topN = 5;
|
41
|
-
Extractor.Extract(s, wordweights, topN);
|
42
|
-
res << wordweights;
|
43
|
-
ASSERT_EQ(res, "[{\"word\": \"CEO\", \"offset\": [93], \"weight\": 11.7392}, {\"word\": \"\xE5\x8D\x87\xE8\x81\x8C\", \"offset\": [72], \"weight\": 10.8562}, {\"word\": \"\xE5\x8A\xA0\xE8\x96\xAA\", \"offset\": [78], \"weight\": 10.6426}, {\"word\": \"\xE6\x89\x8B\xE6\x89\xB6\xE6\x8B\x96\xE6\x8B\x89\xE6\x9C\xBA\", \"offset\": [21], \"weight\": 10.0089}, {\"word\": \"\xE5\xB7\x85\xE5\xB3\xB0\", \"offset\": [111], \"weight\": 9.49396}]");
|
44
|
-
}
|
45
|
-
|
46
|
-
{
|
47
|
-
string s("一部iPhone6");
|
48
|
-
string res;
|
49
|
-
vector<KeywordExtractor::Word> wordweights;
|
50
|
-
size_t topN = 5;
|
51
|
-
Extractor.Extract(s, wordweights, topN);
|
52
|
-
res << wordweights;
|
53
|
-
ASSERT_EQ(res, "[{\"word\": \"iPhone6\", \"offset\": [6], \"weight\": 11.7392}, {\"word\": \"\xE4\xB8\x80\xE9\x83\xA8\", \"offset\": [0], \"weight\": 6.47592}]");
|
54
|
-
}
|
55
|
-
}
|
56
|
-
|
57
|
-
TEST(KeywordExtractorTest, Test2) {
|
58
|
-
KeywordExtractor Extractor("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", "../dict/idf.utf8", "../dict/stop_words.utf8", "../test/testdata/userdict.utf8");
|
59
|
-
|
60
|
-
{
|
61
|
-
string s("蓝翔优秀毕业生");
|
62
|
-
string res;
|
63
|
-
vector<KeywordExtractor::Word> wordweights;
|
64
|
-
size_t topN = 5;
|
65
|
-
Extractor.Extract(s, wordweights, topN);
|
66
|
-
res << wordweights;
|
67
|
-
ASSERT_EQ(res, "[{\"word\": \"\xE8\x93\x9D\xE7\xBF\x94\", \"offset\": [0], \"weight\": 11.7392}, {\"word\": \"\xE6\xAF\x95\xE4\xB8\x9A\xE7\x94\x9F\", \"offset\": [12], \"weight\": 8.13549}, {\"word\": \"\xE4\xBC\x98\xE7\xA7\x80\", \"offset\": [6], \"weight\": 6.78347}]");
|
68
|
-
}
|
69
|
-
|
70
|
-
{
|
71
|
-
string s("一部iPhone6");
|
72
|
-
string res;
|
73
|
-
vector<KeywordExtractor::Word> wordweights;
|
74
|
-
size_t topN = 5;
|
75
|
-
Extractor.Extract(s, wordweights, topN);
|
76
|
-
res << wordweights;
|
77
|
-
ASSERT_EQ(res, "[{\"word\": \"iPhone6\", \"offset\": [6], \"weight\": 11.7392}, {\"word\": \"\xE4\xB8\x80\xE9\x83\xA8\", \"offset\": [0], \"weight\": 6.47592}]");
|
78
|
-
}
|
79
|
-
}
|
@@ -1,41 +0,0 @@
|
|
1
|
-
#include "cppjieba/MixSegment.hpp"
|
2
|
-
#include "gtest/gtest.h"
|
3
|
-
|
4
|
-
using namespace cppjieba;
|
5
|
-
|
6
|
-
static const char * const QUERY_TEST1 = "我是蓝翔技工拖拉机学院手扶拖拉机专业的。不用多久,我就会升职加薪,当上总经理,出任CEO,迎娶白富美,走上人生巅峰。";
|
7
|
-
static const char * const ANS_TEST1 = "[我:r, 是:v, 蓝翔:x, 技工:n, 拖拉机:n, 学院:n, 手扶拖拉机:n, 专业:n, 的:uj, 。:x, 不用:v, 多久:m, ,:x, 我:r, 就:d, 会:v, 升职:v, 加薪:nr, ,:x, 当上:t, 总经理:n, ,:x, 出任:v, CEO:eng, ,:x, 迎娶:v, 白富:x, 美:ns, ,:x, 走上:v, 人生:n, 巅峰:n, 。:x]";
|
8
|
-
static const char * const QUERY_TEST2 = "我是蓝翔技工拖拉机学院手扶拖拉机专业的。不用多久,我就会升职加薪,当上总经理,出任CEO,迎娶白富美,走上人生巅峰。";
|
9
|
-
static const char * const ANS_TEST2 = "[我:r, 是:v, 蓝翔:nz, 技工:n, 拖拉机:n, 学院:n, 手扶拖拉机:n, 专业:n, 的:uj, 。:x, 不用:v, 多久:m, ,:x, 我:r, 就:d, 会:v, 升职:v, 加薪:nr, ,:x, 当上:t, 总经理:n, ,:x, 出任:v, CEO:eng, ,:x, 迎娶:v, 白富:x, 美:ns, ,:x, 走上:v, 人生:n, 巅峰:n, 。:x]";
|
10
|
-
|
11
|
-
static const char * const QUERY_TEST3 = "iPhone6手机的最大特点是很容易弯曲。";
|
12
|
-
static const char * const ANS_TEST3 = "[iPhone6:eng, 手机:n, 的:uj, 最大:a, 特点:n, 是:v, 很:zg, 容易:a, 弯曲:v, 。:x]";
|
13
|
-
//static const char * const ANS_TEST3 = "";
|
14
|
-
|
15
|
-
TEST(PosTaggerTest, Test) {
|
16
|
-
MixSegment tagger("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8");
|
17
|
-
{
|
18
|
-
vector<pair<string, string> > res;
|
19
|
-
tagger.Tag(QUERY_TEST1, res);
|
20
|
-
string s;
|
21
|
-
s << res;
|
22
|
-
ASSERT_TRUE(s == ANS_TEST1);
|
23
|
-
}
|
24
|
-
}
|
25
|
-
TEST(PosTagger, TestUserDict) {
|
26
|
-
MixSegment tagger("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8", "../test/testdata/userdict.utf8");
|
27
|
-
{
|
28
|
-
vector<pair<string, string> > res;
|
29
|
-
tagger.Tag(QUERY_TEST2, res);
|
30
|
-
string s;
|
31
|
-
s << res;
|
32
|
-
ASSERT_EQ(s, ANS_TEST2);
|
33
|
-
}
|
34
|
-
{
|
35
|
-
vector<pair<string, string> > res;
|
36
|
-
tagger.Tag(QUERY_TEST3, res);
|
37
|
-
string s;
|
38
|
-
s << res;
|
39
|
-
ASSERT_EQ(s, ANS_TEST3);
|
40
|
-
}
|
41
|
-
}
|
@@ -1,43 +0,0 @@
|
|
1
|
-
#include "gtest/gtest.h"
|
2
|
-
#include "cppjieba/PreFilter.hpp"
|
3
|
-
#include "limonp/StringUtil.hpp"
|
4
|
-
|
5
|
-
using namespace cppjieba;
|
6
|
-
|
7
|
-
TEST(PreFilterTest, Test1) {
|
8
|
-
unordered_set<Rune> symbol;
|
9
|
-
symbol.insert(65292u); // ","
|
10
|
-
symbol.insert(12290u); // "。"
|
11
|
-
string expected;
|
12
|
-
string res;
|
13
|
-
|
14
|
-
{
|
15
|
-
string s = "你好,美丽的,世界";
|
16
|
-
PreFilter filter(symbol, s);
|
17
|
-
expected = "你好/,/美丽的/,/世界";
|
18
|
-
ASSERT_TRUE(filter.HasNext());
|
19
|
-
vector<string> words;
|
20
|
-
while (filter.HasNext()) {
|
21
|
-
PreFilter::Range range;
|
22
|
-
range = filter.Next();
|
23
|
-
words.push_back(GetStringFromRunes(s, range.begin, range.end - 1));
|
24
|
-
}
|
25
|
-
res = limonp::Join(words.begin(), words.end(), "/");
|
26
|
-
ASSERT_EQ(res, expected);
|
27
|
-
}
|
28
|
-
|
29
|
-
{
|
30
|
-
string s = "我来自北京邮电大学。。。学号123456,用AK47";
|
31
|
-
PreFilter filter(symbol, s);
|
32
|
-
expected = "我来自北京邮电大学/。/。/。/学号123456/,/用AK47";
|
33
|
-
ASSERT_TRUE(filter.HasNext());
|
34
|
-
vector<string> words;
|
35
|
-
while (filter.HasNext()) {
|
36
|
-
PreFilter::Range range;
|
37
|
-
range = filter.Next();
|
38
|
-
words.push_back(GetStringFromRunes(s, range.begin, range.end - 1));
|
39
|
-
}
|
40
|
-
res = limonp::Join(words.begin(), words.end(), "/");
|
41
|
-
ASSERT_EQ(res, expected);
|
42
|
-
}
|
43
|
-
}
|
@@ -1,256 +0,0 @@
|
|
1
|
-
#include "cppjieba/SegmentBase.hpp"
|
2
|
-
#include "cppjieba/MixSegment.hpp"
|
3
|
-
#include "cppjieba/MPSegment.hpp"
|
4
|
-
#include "cppjieba/HMMSegment.hpp"
|
5
|
-
#include "cppjieba/FullSegment.hpp"
|
6
|
-
#include "cppjieba/QuerySegment.hpp"
|
7
|
-
#include "gtest/gtest.h"
|
8
|
-
|
9
|
-
using namespace cppjieba;
|
10
|
-
|
11
|
-
TEST(MixSegmentTest, Test1) {
|
12
|
-
MixSegment segment("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8");;
|
13
|
-
string sentence;
|
14
|
-
vector<string> words;
|
15
|
-
string actual;
|
16
|
-
string expected;
|
17
|
-
|
18
|
-
{
|
19
|
-
sentence = "我来自北京邮电大学。。。学号123456,用AK47";
|
20
|
-
expected = "我/来自/北京邮电大学/。/。/。/学号/123456/,/用/AK47";
|
21
|
-
segment.Cut(sentence, words);
|
22
|
-
actual = Join(words.begin(), words.end(), "/");
|
23
|
-
ASSERT_EQ(actual, expected);
|
24
|
-
}
|
25
|
-
|
26
|
-
{
|
27
|
-
sentence = "B超 T恤";
|
28
|
-
expected = "B超/ /T恤";
|
29
|
-
segment.Cut(sentence, words);
|
30
|
-
actual = Join(words.begin(), words.end(), "/");
|
31
|
-
ASSERT_EQ(actual, expected);
|
32
|
-
}
|
33
|
-
|
34
|
-
{
|
35
|
-
sentence = "他来到了网易杭研大厦";
|
36
|
-
expected = "他/来到/了/网易/杭/研/大厦";
|
37
|
-
segment.Cut(sentence, words, false);
|
38
|
-
actual = Join(words.begin(), words.end(), "/");
|
39
|
-
ASSERT_EQ(actual, expected);
|
40
|
-
}
|
41
|
-
|
42
|
-
{
|
43
|
-
sentence = "他来到了网易杭研大厦";
|
44
|
-
expected = "他/来到/了/网易/杭研/大厦";
|
45
|
-
segment.Cut(sentence, words);
|
46
|
-
actual = Join(words.begin(), words.end(), "/");
|
47
|
-
ASSERT_EQ(actual, expected);
|
48
|
-
}
|
49
|
-
}
|
50
|
-
|
51
|
-
TEST(MixSegmentTest, NoUserDict) {
|
52
|
-
MixSegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8");
|
53
|
-
const char* str = "令狐冲是云计算方面的专家";
|
54
|
-
vector<string> words;
|
55
|
-
segment.Cut(str, words);
|
56
|
-
string res;
|
57
|
-
ASSERT_EQ("[\"令狐冲\", \"是\", \"云\", \"计算\", \"方面\", \"的\", \"专家\"]", res << words);
|
58
|
-
|
59
|
-
}
|
60
|
-
TEST(MixSegmentTest, UserDict) {
|
61
|
-
MixSegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", "../dict/user.dict.utf8");
|
62
|
-
{
|
63
|
-
const char* str = "令狐冲是云计算方面的专家";
|
64
|
-
vector<string> words;
|
65
|
-
segment.Cut(str, words);
|
66
|
-
string res;
|
67
|
-
ASSERT_EQ("[\"令狐冲\", \"是\", \"云计算\", \"方面\", \"的\", \"专家\"]", res << words);
|
68
|
-
}
|
69
|
-
{
|
70
|
-
const char* str = "小明先就职于IBM,后在日本京都大学深造";
|
71
|
-
vector<string> words;
|
72
|
-
segment.Cut(str, words);
|
73
|
-
string res;
|
74
|
-
res << words;
|
75
|
-
ASSERT_EQ("[\"小明\", \"先\", \"就职\", \"于\", \"IBM\", \",\", \"后\", \"在\", \"日本\", \"京都大学\", \"深造\"]", res);
|
76
|
-
}
|
77
|
-
{
|
78
|
-
const char* str = "IBM,3.14";
|
79
|
-
vector<string> words;
|
80
|
-
segment.Cut(str, words);
|
81
|
-
string res;
|
82
|
-
res << words;
|
83
|
-
ASSERT_EQ("[\"IBM\", \",\", \"3.14\"]", res);
|
84
|
-
}
|
85
|
-
}
|
86
|
-
TEST(MixSegmentTest, TestUserDict) {
|
87
|
-
MixSegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8",
|
88
|
-
"../test/testdata/userdict.utf8");
|
89
|
-
vector<string> words;
|
90
|
-
string res;
|
91
|
-
|
92
|
-
segment.Cut("令狐冲是云计算方面的专家", words);
|
93
|
-
ASSERT_EQ("[\"令狐冲\", \"是\", \"云计算\", \"方面\", \"的\", \"专家\"]", res << words);
|
94
|
-
|
95
|
-
segment.Cut("小明先就职于IBM,后在日本京都大学深造", words);
|
96
|
-
res << words;
|
97
|
-
ASSERT_EQ("[\"小明\", \"先\", \"就职\", \"于\", \"I\", \"B\", \"M\", \",\", \"后\", \"在\", \"日本\", \"京都大学\", \"深造\"]", res);
|
98
|
-
|
99
|
-
segment.Cut("IBM,3.14", words);
|
100
|
-
res << words;
|
101
|
-
ASSERT_EQ("[\"I\", \"B\", \"M\", \",\", \"3.14\"]", res);
|
102
|
-
|
103
|
-
segment.Cut("忽如一夜春风来,千树万树梨花开", words);
|
104
|
-
res = limonp::Join(words.begin(), words.end(), "/");
|
105
|
-
ASSERT_EQ("忽如一夜春风来/,/千树/万树/梨花/开", res);
|
106
|
-
|
107
|
-
// rand input
|
108
|
-
{
|
109
|
-
const size_t ITERATION = 16;
|
110
|
-
const size_t MAX_LEN = 256;
|
111
|
-
string s;
|
112
|
-
srand(time(NULL));
|
113
|
-
|
114
|
-
for (size_t i = 0; i < ITERATION; i++) {
|
115
|
-
size_t len = rand() % MAX_LEN;
|
116
|
-
s.resize(len);
|
117
|
-
for (size_t j = 0; j < len; j++) {
|
118
|
-
s[rand() % len] = rand();
|
119
|
-
}
|
120
|
-
segment.Cut(s, words);
|
121
|
-
}
|
122
|
-
}
|
123
|
-
}
|
124
|
-
|
125
|
-
TEST(MixSegmentTest, TestMultiUserDict) {
|
126
|
-
MixSegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8",
|
127
|
-
"../test/testdata/userdict.utf8;../test/testdata/userdict.2.utf8");
|
128
|
-
vector<string> words;
|
129
|
-
string res;
|
130
|
-
|
131
|
-
segment.Cut("忽如一夜春风来,千树万树梨花开", words);
|
132
|
-
res = limonp::Join(words.begin(), words.end(), "/");
|
133
|
-
ASSERT_EQ("忽如一夜春风来/,/千树万树梨花开", res);
|
134
|
-
}
|
135
|
-
|
136
|
-
TEST(MPSegmentTest, Test1) {
|
137
|
-
MPSegment segment("../dict/jieba.dict.utf8");;
|
138
|
-
string s;
|
139
|
-
vector<string> words;
|
140
|
-
segment.Cut("我来自北京邮电大学。", words);
|
141
|
-
ASSERT_EQ("[\"我\", \"来自\", \"北京邮电大学\", \"。\"]", s << words);
|
142
|
-
|
143
|
-
segment.Cut("B超 T恤", words);
|
144
|
-
ASSERT_EQ(s << words, "[\"B超\", \" \", \"T恤\"]");
|
145
|
-
|
146
|
-
segment.Cut("南京市长江大桥", words);
|
147
|
-
ASSERT_EQ("[\"南京市\", \"长江大桥\"]", s << words);
|
148
|
-
|
149
|
-
// MaxWordLen
|
150
|
-
segment.Cut("南京市长江大桥", words, 3);
|
151
|
-
ASSERT_EQ("[\"南京市\", \"长江\", \"大桥\"]", s << words);
|
152
|
-
|
153
|
-
segment.Cut("南京市长江大桥", words, 0);
|
154
|
-
ASSERT_EQ("[\"南\", \"京\", \"市\", \"长\", \"江\", \"大\", \"桥\"]", s << words);
|
155
|
-
|
156
|
-
segment.Cut("湖南长沙市天心区", words);
|
157
|
-
s = Join(words.begin(), words.end(), "/");
|
158
|
-
ASSERT_EQ("湖南长沙市/天心区", s);
|
159
|
-
|
160
|
-
segment.Cut("湖南长沙市天心区", words, 3);
|
161
|
-
s = Join(words.begin(), words.end(), "/");
|
162
|
-
ASSERT_EQ("湖南/长沙市/天心区", s);
|
163
|
-
}
|
164
|
-
|
165
|
-
TEST(HMMSegmentTest, Test1) {
|
166
|
-
HMMSegment segment("../dict/hmm_model.utf8");;
|
167
|
-
{
|
168
|
-
const char* str = "我来自北京邮电大学。。。学号123456";
|
169
|
-
const char* res[] = {"我来", "自北京", "邮电大学", "。", "。", "。", "学号", "123456"};
|
170
|
-
vector<string> words;
|
171
|
-
segment.Cut(str, words);
|
172
|
-
ASSERT_EQ(words, vector<string>(res, res + sizeof(res)/sizeof(res[0])));
|
173
|
-
}
|
174
|
-
|
175
|
-
{
|
176
|
-
const char* str = "IBM,1.2,123";
|
177
|
-
const char* res[] = {"IBM", ",", "1.2", ",", "123"};
|
178
|
-
vector<string> words;
|
179
|
-
segment.Cut(str, words);
|
180
|
-
ASSERT_EQ(words, vector<string>(res, res + sizeof(res)/sizeof(res[0])));
|
181
|
-
}
|
182
|
-
}
|
183
|
-
|
184
|
-
TEST(FullSegment, Test1) {
|
185
|
-
FullSegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8");
|
186
|
-
vector<string> words;
|
187
|
-
string s;
|
188
|
-
|
189
|
-
segment.Cut("我来自北京邮电大学", words);
|
190
|
-
s << words;
|
191
|
-
ASSERT_EQ(s, "[\"我\", \"来自\", \"北京\", \"北京邮电大学\", \"邮电\", \"电大\", \"大学\"]");
|
192
|
-
|
193
|
-
|
194
|
-
segment.Cut("上市公司CEO", words);
|
195
|
-
s << words;
|
196
|
-
ASSERT_EQ(s, "[\"上市\", \"公司\", \"C\", \"E\", \"O\"]");
|
197
|
-
}
|
198
|
-
|
199
|
-
TEST(QuerySegment, Test1) {
|
200
|
-
QuerySegment segment("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8", "");
|
201
|
-
vector<string> words;
|
202
|
-
string s1, s2;
|
203
|
-
|
204
|
-
segment.Cut("小明硕士毕业于中国科学院计算所,后在日本京都大学深造", words);
|
205
|
-
s1 = Join(words.begin(), words.end(), "/");
|
206
|
-
s2 = "小明/硕士/毕业/于/中国/科学/学院/科学院/中国科学院/计算/计算所/,/后/在/日本/京都/大学/日本京都大学/深造";
|
207
|
-
ASSERT_EQ(s1, s2);
|
208
|
-
|
209
|
-
segment.Cut("亲口交代", words);
|
210
|
-
s1 = Join(words.begin(), words.end(), "/");
|
211
|
-
s2 = "亲口/交代";
|
212
|
-
ASSERT_EQ(s1, s2);
|
213
|
-
|
214
|
-
segment.Cut("他心理健康", words);
|
215
|
-
s1 = Join(words.begin(), words.end(), "/");
|
216
|
-
s2 = "他/心理/健康/心理健康";
|
217
|
-
ASSERT_EQ(s1, s2);
|
218
|
-
}
|
219
|
-
|
220
|
-
TEST(QuerySegment, Test2) {
|
221
|
-
QuerySegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", "../test/testdata/userdict.utf8|../test/testdata/userdict.english");
|
222
|
-
vector<string> words;
|
223
|
-
string s1, s2;
|
224
|
-
|
225
|
-
{
|
226
|
-
segment.Cut("小明硕士毕业于中国科学院计算所,后在日本京都大学深造", words);
|
227
|
-
s1 = Join(words.begin(), words.end(), "/");
|
228
|
-
s2 = "小明/硕士/毕业/于/中国/科学/学院/科学院/中国科学院/计算/计算所/,/后/在/日本/京都/大学/京都大学/深造";
|
229
|
-
ASSERT_EQ(s1, s2);
|
230
|
-
}
|
231
|
-
|
232
|
-
{
|
233
|
-
segment.Cut("小明硕士毕业于中国科学院计算所iPhone6", words);
|
234
|
-
s1 = Join(words.begin(), words.end(), "/");
|
235
|
-
s2 = "小明/硕士/毕业/于/中国/科学/学院/科学院/中国科学院/计算/计算所/iPhone6";
|
236
|
-
ASSERT_EQ(s1, s2);
|
237
|
-
}
|
238
|
-
|
239
|
-
{
|
240
|
-
segment.Cut("中国科学院", words);
|
241
|
-
s1 = Join(words.begin(), words.end(), "/");
|
242
|
-
s2 = "中国/科学/学院/科学院/中国科学院";
|
243
|
-
ASSERT_EQ(s1, s2);
|
244
|
-
}
|
245
|
-
|
246
|
-
}
|
247
|
-
|
248
|
-
TEST(MPSegmentTest, Unicode32) {
|
249
|
-
string s("天气很好,🙋 我们去郊游。");
|
250
|
-
vector<string> words;
|
251
|
-
|
252
|
-
MPSegment segment("../dict/jieba.dict.utf8");;
|
253
|
-
segment.Cut(s, words);
|
254
|
-
|
255
|
-
ASSERT_EQ(Join(words.begin(), words.end(), "/"), "天气/很/好/,/🙋/ /我们/去/郊游/。");
|
256
|
-
}
|
@@ -1,86 +0,0 @@
|
|
1
|
-
#include "cppjieba/TextRankExtractor.hpp"
|
2
|
-
#include "gtest/gtest.h"
|
3
|
-
|
4
|
-
using namespace cppjieba;
|
5
|
-
|
6
|
-
TEST(TextRankExtractorTest, Test1) {
|
7
|
-
TextRankExtractor Extractor(
|
8
|
-
"../test/testdata/extra_dict/jieba.dict.small.utf8",
|
9
|
-
"../dict/hmm_model.utf8",
|
10
|
-
"../dict/stop_words.utf8");
|
11
|
-
{
|
12
|
-
string s("你好世界世界而且而且");
|
13
|
-
string res;
|
14
|
-
size_t topN = 5;
|
15
|
-
|
16
|
-
{
|
17
|
-
vector<string> words;
|
18
|
-
Extractor.Extract(s, words, topN);
|
19
|
-
res << words;
|
20
|
-
ASSERT_EQ(res, "[\"世界\", \"你好\"]");
|
21
|
-
}
|
22
|
-
|
23
|
-
{
|
24
|
-
vector<pair<string, double> > words;
|
25
|
-
Extractor.Extract(s, words, topN);
|
26
|
-
res << words;
|
27
|
-
ASSERT_EQ(res, "[世界:1, 你好:0.519787]");
|
28
|
-
}
|
29
|
-
|
30
|
-
{
|
31
|
-
vector<TextRankExtractor::Word> words;
|
32
|
-
Extractor.Extract(s, words, topN);
|
33
|
-
res << words;
|
34
|
-
ASSERT_EQ(res, "[{\"word\": \"世界\", \"offset\": [6, 12], \"weight\": 1}, {\"word\": \"你好\", \"offset\": [0], \"weight\": 0.519787}]");
|
35
|
-
}
|
36
|
-
}
|
37
|
-
|
38
|
-
{
|
39
|
-
string s("\xe6\x88\x91\xe6\x98\xaf\xe6\x8b\x96\xe6\x8b\x89\xe6\x9c\xba\xe5\xad\xa6\xe9\x99\xa2\xe6\x89\x8b\xe6\x89\xb6\xe6\x8b\x96\xe6\x8b\x89\xe6\x9c\xba\xe4\xb8\x93\xe4\xb8\x9a\xe7\x9a\x84\xe3\x80\x82\xe4\xb8\x8d\xe7\x94\xa8\xe5\xa4\x9a\xe4\xb9\x85\xef\xbc\x8c\xe6\x88\x91\xe5\xb0\xb1\xe4\xbc\x9a\xe5\x8d\x87\xe8\x81\x8c\xe5\x8a\xa0\xe8\x96\xaa\xef\xbc\x8c\xe5\xbd\x93\xe4\xb8\x8a CEO\xef\xbc\x8c\xe8\xb5\xb0\xe4\xb8\x8a\xe4\xba\xba\xe7\x94\x9f\xe5\xb7\x85\xe5\xb3\xb0");
|
40
|
-
string res;
|
41
|
-
vector<TextRankExtractor::Word> wordweights;
|
42
|
-
size_t topN = 5;
|
43
|
-
Extractor.Extract(s, wordweights, topN);
|
44
|
-
res << wordweights;
|
45
|
-
ASSERT_EQ(res, "[{\"word\": \"当上\", \"offset\": [87], \"weight\": 1}, {\"word\": \"不用\", \"offset\": [48], \"weight\": 0.989848}, {\"word\": \"多久\", \"offset\": [54], \"weight\": 0.985126}, {\"word\": \"加薪\", \"offset\": [78], \"weight\": 0.983046}, {\"word\": \"升职\", \"offset\": [72], \"weight\": 0.980278}]");
|
46
|
-
//ASSERT_EQ(res, "[{\"word\": \"专业\", \"offset\": [36], \"weight\": 1}, {\"word\": \"CEO\", \"offset\": [94], \"weight\": 0.95375}, {\"word\": \"手扶拖拉机\", \"offset\": [21], \"weight\": 0.801701}, {\"word\": \"当上\", \"offset\": [87], \"weight\": 0.798968}, {\"word\": \"走上\", \"offset\": [100], \"weight\": 0.775505}]");
|
47
|
-
}
|
48
|
-
|
49
|
-
{
|
50
|
-
string s("一部iPhone6");
|
51
|
-
string res;
|
52
|
-
vector<TextRankExtractor::Word> wordweights;
|
53
|
-
size_t topN = 5;
|
54
|
-
Extractor.Extract(s, wordweights, topN);
|
55
|
-
res << wordweights;
|
56
|
-
ASSERT_EQ(res, "[{\"word\": \"一部\", \"offset\": [0], \"weight\": 1}, {\"word\": \"iPhone6\", \"offset\": [6], \"weight\": 0.996126}]");
|
57
|
-
}
|
58
|
-
}
|
59
|
-
|
60
|
-
TEST(TextRankExtractorTest, Test2) {
|
61
|
-
TextRankExtractor Extractor(
|
62
|
-
"../test/testdata/extra_dict/jieba.dict.small.utf8",
|
63
|
-
"../dict/hmm_model.utf8",
|
64
|
-
"../dict/stop_words.utf8",
|
65
|
-
"../test/testdata/userdict.utf8");
|
66
|
-
|
67
|
-
{
|
68
|
-
string s("\xe8\x93\x9d\xe7\xbf\x94\xe4\xbc\x98\xe7\xa7\x80\xe6\xaf\x95\xe4\xb8\x9a\xe7\x94\x9f");
|
69
|
-
string res;
|
70
|
-
vector<TextRankExtractor::Word> wordweights;
|
71
|
-
size_t topN = 5;
|
72
|
-
Extractor.Extract(s, wordweights, topN);
|
73
|
-
res << wordweights;
|
74
|
-
ASSERT_EQ(res, "[{\"word\": \"蓝翔\", \"offset\": [0], \"weight\": 1}, {\"word\": \"毕业生\", \"offset\": [12], \"weight\": 0.996685}, {\"word\": \"优秀\", \"offset\": [6], \"weight\": 0.992994}]");
|
75
|
-
}
|
76
|
-
|
77
|
-
{
|
78
|
-
string s("一部iPhone6");
|
79
|
-
string res;
|
80
|
-
vector<TextRankExtractor::Word> wordweights;
|
81
|
-
size_t topN = 5;
|
82
|
-
Extractor.Extract(s, wordweights, topN);
|
83
|
-
res << wordweights;
|
84
|
-
ASSERT_EQ(res, "[{\"word\": \"一部\", \"offset\": [0], \"weight\": 1}, {\"word\": \"iPhone6\", \"offset\": [6], \"weight\": 0.996126}]");
|
85
|
-
}
|
86
|
-
}
|