cppjieba_rb 0.2.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +18 -0
- data/.gitmodules +3 -0
- data/.travis.yml +26 -0
- data/Gemfile +3 -0
- data/LICENSE.txt +22 -0
- data/README.md +81 -0
- data/Rakefile +20 -0
- data/cppjieba_rb.gemspec +50 -0
- data/ext/cppjieba/.gitignore +17 -0
- data/ext/cppjieba/.travis.yml +22 -0
- data/ext/cppjieba/CMakeLists.txt +28 -0
- data/ext/cppjieba/ChangeLog.md +236 -0
- data/ext/cppjieba/README.md +285 -0
- data/ext/cppjieba/README_EN.md +111 -0
- data/ext/cppjieba/appveyor.yml +32 -0
- data/ext/cppjieba/deps/CMakeLists.txt +1 -0
- data/ext/cppjieba/deps/gtest/CMakeLists.txt +5 -0
- data/ext/cppjieba/deps/gtest/include/gtest/gtest-death-test.h +283 -0
- data/ext/cppjieba/deps/gtest/include/gtest/gtest-message.h +230 -0
- data/ext/cppjieba/deps/gtest/include/gtest/gtest-param-test.h +1421 -0
- data/ext/cppjieba/deps/gtest/include/gtest/gtest-param-test.h.pump +487 -0
- data/ext/cppjieba/deps/gtest/include/gtest/gtest-printers.h +796 -0
- data/ext/cppjieba/deps/gtest/include/gtest/gtest-spi.h +232 -0
- data/ext/cppjieba/deps/gtest/include/gtest/gtest-test-part.h +176 -0
- data/ext/cppjieba/deps/gtest/include/gtest/gtest-typed-test.h +259 -0
- data/ext/cppjieba/deps/gtest/include/gtest/gtest.h +2155 -0
- data/ext/cppjieba/deps/gtest/include/gtest/gtest_pred_impl.h +358 -0
- data/ext/cppjieba/deps/gtest/include/gtest/gtest_prod.h +58 -0
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-death-test-internal.h +308 -0
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-filepath.h +210 -0
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-internal.h +1226 -0
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-linked_ptr.h +233 -0
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-param-util-generated.h +4822 -0
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-param-util-generated.h.pump +301 -0
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-param-util.h +619 -0
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-port.h +1788 -0
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-string.h +350 -0
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-tuple.h +968 -0
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-tuple.h.pump +336 -0
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-type-util.h +3330 -0
- data/ext/cppjieba/deps/gtest/include/gtest/internal/gtest-type-util.h.pump +296 -0
- data/ext/cppjieba/deps/gtest/src/.deps/.dirstamp +0 -0
- data/ext/cppjieba/deps/gtest/src/.deps/gtest-all.Plo +681 -0
- data/ext/cppjieba/deps/gtest/src/.deps/gtest_main.Plo +509 -0
- data/ext/cppjieba/deps/gtest/src/.dirstamp +0 -0
- data/ext/cppjieba/deps/gtest/src/gtest-all.cc +48 -0
- data/ext/cppjieba/deps/gtest/src/gtest-death-test.cc +1234 -0
- data/ext/cppjieba/deps/gtest/src/gtest-filepath.cc +380 -0
- data/ext/cppjieba/deps/gtest/src/gtest-internal-inl.h +1038 -0
- data/ext/cppjieba/deps/gtest/src/gtest-port.cc +746 -0
- data/ext/cppjieba/deps/gtest/src/gtest-printers.cc +356 -0
- data/ext/cppjieba/deps/gtest/src/gtest-test-part.cc +110 -0
- data/ext/cppjieba/deps/gtest/src/gtest-typed-test.cc +110 -0
- data/ext/cppjieba/deps/gtest/src/gtest.cc +4898 -0
- data/ext/cppjieba/deps/gtest/src/gtest_main.cc +39 -0
- data/ext/cppjieba/deps/limonp/ArgvContext.hpp +70 -0
- data/ext/cppjieba/deps/limonp/BlockingQueue.hpp +49 -0
- data/ext/cppjieba/deps/limonp/BoundedBlockingQueue.hpp +67 -0
- data/ext/cppjieba/deps/limonp/BoundedQueue.hpp +65 -0
- data/ext/cppjieba/deps/limonp/Closure.hpp +206 -0
- data/ext/cppjieba/deps/limonp/Colors.hpp +31 -0
- data/ext/cppjieba/deps/limonp/Condition.hpp +38 -0
- data/ext/cppjieba/deps/limonp/Config.hpp +103 -0
- data/ext/cppjieba/deps/limonp/FileLock.hpp +74 -0
- data/ext/cppjieba/deps/limonp/ForcePublic.hpp +7 -0
- data/ext/cppjieba/deps/limonp/LocalVector.hpp +139 -0
- data/ext/cppjieba/deps/limonp/Logging.hpp +76 -0
- data/ext/cppjieba/deps/limonp/Md5.hpp +411 -0
- data/ext/cppjieba/deps/limonp/MutexLock.hpp +51 -0
- data/ext/cppjieba/deps/limonp/NonCopyable.hpp +21 -0
- data/ext/cppjieba/deps/limonp/StdExtension.hpp +159 -0
- data/ext/cppjieba/deps/limonp/StringUtil.hpp +365 -0
- data/ext/cppjieba/deps/limonp/Thread.hpp +44 -0
- data/ext/cppjieba/deps/limonp/ThreadPool.hpp +86 -0
- data/ext/cppjieba/dict/README.md +31 -0
- data/ext/cppjieba/dict/hmm_model.utf8 +34 -0
- data/ext/cppjieba/dict/idf.utf8 +258826 -0
- data/ext/cppjieba/dict/jieba.dict.utf8 +348982 -0
- data/ext/cppjieba/dict/pos_dict/char_state_tab.utf8 +6653 -0
- data/ext/cppjieba/dict/pos_dict/prob_emit.utf8 +166 -0
- data/ext/cppjieba/dict/pos_dict/prob_start.utf8 +259 -0
- data/ext/cppjieba/dict/pos_dict/prob_trans.utf8 +5222 -0
- data/ext/cppjieba/dict/stop_words.utf8 +1534 -0
- data/ext/cppjieba/dict/user.dict.utf8 +4 -0
- data/ext/cppjieba/include/cppjieba/DictTrie.hpp +227 -0
- data/ext/cppjieba/include/cppjieba/FullSegment.hpp +93 -0
- data/ext/cppjieba/include/cppjieba/HMMModel.hpp +129 -0
- data/ext/cppjieba/include/cppjieba/HMMSegment.hpp +190 -0
- data/ext/cppjieba/include/cppjieba/Jieba.hpp +108 -0
- data/ext/cppjieba/include/cppjieba/KeywordExtractor.hpp +153 -0
- data/ext/cppjieba/include/cppjieba/MPSegment.hpp +137 -0
- data/ext/cppjieba/include/cppjieba/MixSegment.hpp +109 -0
- data/ext/cppjieba/include/cppjieba/PosTagger.hpp +77 -0
- data/ext/cppjieba/include/cppjieba/PreFilter.hpp +54 -0
- data/ext/cppjieba/include/cppjieba/QuerySegment.hpp +90 -0
- data/ext/cppjieba/include/cppjieba/SegmentBase.hpp +46 -0
- data/ext/cppjieba/include/cppjieba/SegmentTagged.hpp +23 -0
- data/ext/cppjieba/include/cppjieba/TextRankExtractor.hpp +190 -0
- data/ext/cppjieba/include/cppjieba/Trie.hpp +174 -0
- data/ext/cppjieba/include/cppjieba/Unicode.hpp +215 -0
- data/ext/cppjieba/test/CMakeLists.txt +5 -0
- data/ext/cppjieba/test/demo.cpp +80 -0
- data/ext/cppjieba/test/load_test.cpp +54 -0
- data/ext/cppjieba/test/testdata/curl.res +1 -0
- data/ext/cppjieba/test/testdata/extra_dict/jieba.dict.small.utf8 +109750 -0
- data/ext/cppjieba/test/testdata/gbk_dict/hmm_model.gbk +34 -0
- data/ext/cppjieba/test/testdata/gbk_dict/jieba.dict.gbk +348982 -0
- data/ext/cppjieba/test/testdata/jieba.dict.0.1.utf8 +93 -0
- data/ext/cppjieba/test/testdata/jieba.dict.0.utf8 +93 -0
- data/ext/cppjieba/test/testdata/jieba.dict.1.utf8 +67 -0
- data/ext/cppjieba/test/testdata/jieba.dict.2.utf8 +64 -0
- data/ext/cppjieba/test/testdata/load_test.urls +2 -0
- data/ext/cppjieba/test/testdata/review.100 +100 -0
- data/ext/cppjieba/test/testdata/review.100.res +200 -0
- data/ext/cppjieba/test/testdata/server.conf +19 -0
- data/ext/cppjieba/test/testdata/testlines.gbk +9 -0
- data/ext/cppjieba/test/testdata/testlines.utf8 +8 -0
- data/ext/cppjieba/test/testdata/userdict.2.utf8 +1 -0
- data/ext/cppjieba/test/testdata/userdict.english +2 -0
- data/ext/cppjieba/test/testdata/userdict.utf8 +8 -0
- data/ext/cppjieba/test/testdata/weicheng.utf8 +247 -0
- data/ext/cppjieba/test/unittest/CMakeLists.txt +24 -0
- data/ext/cppjieba/test/unittest/gtest_main.cpp +39 -0
- data/ext/cppjieba/test/unittest/jieba_test.cpp +133 -0
- data/ext/cppjieba/test/unittest/keyword_extractor_test.cpp +79 -0
- data/ext/cppjieba/test/unittest/pos_tagger_test.cpp +41 -0
- data/ext/cppjieba/test/unittest/pre_filter_test.cpp +43 -0
- data/ext/cppjieba/test/unittest/segments_test.cpp +256 -0
- data/ext/cppjieba/test/unittest/textrank_test.cpp +86 -0
- data/ext/cppjieba/test/unittest/trie_test.cpp +177 -0
- data/ext/cppjieba/test/unittest/unicode_test.cpp +43 -0
- data/ext/cppjieba_rb/cppjieba_rb.c +10 -0
- data/ext/cppjieba_rb/extconf.rb +26 -0
- data/ext/cppjieba_rb/internal.cc +148 -0
- data/lib/cppjieba_rb/segment.rb +20 -0
- data/lib/cppjieba_rb/version.rb +3 -0
- data/lib/cppjieba_rb.rb +34 -0
- data/test/test_keyword.rb +17 -0
- data/test/test_segment.rb +24 -0
- data/test/test_tagging.rb +19 -0
- metadata +244 -0
@@ -0,0 +1,24 @@
|
|
1
|
+
SET(EXECUTABLE_OUTPUT_PATH ${PROJECT_BINARY_DIR}/test)
|
2
|
+
SET(LIBRARY_OUTPUT_PATH ${PROJECT_BINARY_DIR}/lib)
|
3
|
+
|
4
|
+
INCLUDE_DIRECTORIES(${PROJECT_SOURCE_DIR}/deps/gtest/include)
|
5
|
+
|
6
|
+
ADD_DEFINITIONS(-DLOGGING_LEVEL=LL_WARNING)
|
7
|
+
|
8
|
+
ADD_EXECUTABLE(test.run
|
9
|
+
gtest_main.cpp
|
10
|
+
keyword_extractor_test.cpp
|
11
|
+
trie_test.cpp
|
12
|
+
segments_test.cpp
|
13
|
+
pos_tagger_test.cpp
|
14
|
+
jieba_test.cpp
|
15
|
+
pre_filter_test.cpp
|
16
|
+
unicode_test.cpp
|
17
|
+
textrank_test.cpp
|
18
|
+
)
|
19
|
+
|
20
|
+
if(MSVC)
|
21
|
+
TARGET_LINK_LIBRARIES(test.run gtest)
|
22
|
+
else()
|
23
|
+
TARGET_LINK_LIBRARIES(test.run gtest pthread)
|
24
|
+
endif()
|
@@ -0,0 +1,39 @@
|
|
1
|
+
// Copyright 2006, Google Inc.
|
2
|
+
// All rights reserved.
|
3
|
+
//
|
4
|
+
// Redistribution and use in source and binary forms, with or without
|
5
|
+
// modification, are permitted provided that the following conditions are
|
6
|
+
// met:
|
7
|
+
//
|
8
|
+
// * Redistributions of source code must retain the above copyright
|
9
|
+
// notice, this list of conditions and the following disclaimer.
|
10
|
+
// * Redistributions in binary form must reproduce the above
|
11
|
+
// copyright notice, this list of conditions and the following disclaimer
|
12
|
+
// in the documentation and/or other materials provided with the
|
13
|
+
// distribution.
|
14
|
+
// * Neither the name of Google Inc. nor the names of its
|
15
|
+
// contributors may be used to endorse or promote products derived from
|
16
|
+
// this software without specific prior written permission.
|
17
|
+
//
|
18
|
+
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
19
|
+
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
20
|
+
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
21
|
+
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
22
|
+
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
23
|
+
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
24
|
+
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
25
|
+
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
26
|
+
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
27
|
+
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
28
|
+
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
29
|
+
|
30
|
+
#include <iostream>
|
31
|
+
|
32
|
+
#include "gtest/gtest.h"
|
33
|
+
|
34
|
+
GTEST_API_ int main(int argc, char **argv) {
|
35
|
+
std::cout << "Running main() from gtest_main.cc\n";
|
36
|
+
|
37
|
+
testing::InitGoogleTest(&argc, argv);
|
38
|
+
return RUN_ALL_TESTS();
|
39
|
+
}
|
@@ -0,0 +1,133 @@
|
|
1
|
+
#include "cppjieba/Jieba.hpp"
|
2
|
+
#include "gtest/gtest.h"
|
3
|
+
|
4
|
+
using namespace cppjieba;
|
5
|
+
|
6
|
+
TEST(JiebaTest, Test1) {
|
7
|
+
cppjieba::Jieba jieba("../dict/jieba.dict.utf8",
|
8
|
+
"../dict/hmm_model.utf8",
|
9
|
+
"../dict/user.dict.utf8",
|
10
|
+
"../dict/idf.utf8",
|
11
|
+
"../dict/stop_words.utf8");
|
12
|
+
vector<string> words;
|
13
|
+
string result;
|
14
|
+
|
15
|
+
jieba.Cut("他来到了网易杭研大厦", words);
|
16
|
+
result << words;
|
17
|
+
ASSERT_EQ("[\"他\", \"来到\", \"了\", \"网易\", \"杭研\", \"大厦\"]", result);
|
18
|
+
|
19
|
+
jieba.Cut("我来自北京邮电大学。", words, false);
|
20
|
+
result << words;
|
21
|
+
ASSERT_EQ("[\"我\", \"来自\", \"北京邮电大学\", \"。\"]", result);
|
22
|
+
|
23
|
+
jieba.CutSmall("南京市长江大桥", words, 3);
|
24
|
+
ASSERT_EQ("[\"南京市\", \"长江\", \"大桥\"]", result << words);
|
25
|
+
|
26
|
+
jieba.CutHMM("我来自北京邮电大学。。。学号123456", words);
|
27
|
+
result << words;
|
28
|
+
ASSERT_EQ("[\"我来\", \"自北京\", \"邮电大学\", \"。\", \"。\", \"。\", \"学号\", \"123456\"]", result);
|
29
|
+
|
30
|
+
jieba.Cut("我来自北京邮电大学。。。学号123456,用AK47", words);
|
31
|
+
result << words;
|
32
|
+
ASSERT_EQ("[\"我\", \"来自\", \"北京邮电大学\", \"。\", \"。\", \"。\", \"学号\", \"123456\", \",\", \"用\", \"AK47\"]", result);
|
33
|
+
|
34
|
+
jieba.CutAll("我来自北京邮电大学", words);
|
35
|
+
result << words;
|
36
|
+
ASSERT_EQ(result, "[\"我\", \"来自\", \"北京\", \"北京邮电\", \"北京邮电大学\", \"邮电\", \"邮电大学\", \"电大\", \"大学\"]");
|
37
|
+
|
38
|
+
jieba.CutForSearch("他来到了网易杭研大厦", words);
|
39
|
+
result << words;
|
40
|
+
ASSERT_EQ("[\"他\", \"来到\", \"了\", \"网易\", \"杭研\", \"大厦\"]", result);
|
41
|
+
|
42
|
+
}
|
43
|
+
TEST(JiebaTest, WordTest) {
|
44
|
+
cppjieba::Jieba jieba("../dict/jieba.dict.utf8",
|
45
|
+
"../dict/hmm_model.utf8",
|
46
|
+
"../dict/user.dict.utf8",
|
47
|
+
"../dict/idf.utf8",
|
48
|
+
"../dict/stop_words.utf8");
|
49
|
+
vector<Word> words;
|
50
|
+
string result;
|
51
|
+
|
52
|
+
jieba.Cut("他来到了网易杭研大厦", words);
|
53
|
+
result << words;
|
54
|
+
ASSERT_EQ("[{\"word\": \"\xE4\xBB\x96\", \"offset\": 0}, {\"word\": \"\xE6\x9D\xA5\xE5\x88\xB0\", \"offset\": 3}, {\"word\": \"\xE4\xBA\x86\", \"offset\": 9}, {\"word\": \"\xE7\xBD\x91\xE6\x98\x93\", \"offset\": 12}, {\"word\": \"\xE6\x9D\xAD\xE7\xA0\x94\", \"offset\": 18}, {\"word\": \"\xE5\xA4\xA7\xE5\x8E\xA6\", \"offset\": 24}]", result);
|
55
|
+
|
56
|
+
jieba.Cut("我来自北京邮电大学。", words, false);
|
57
|
+
result << words;
|
58
|
+
//ASSERT_EQ("[\"我\", \"来自\", \"北京邮电大学\", \"。\"]", result);
|
59
|
+
ASSERT_EQ("[{\"word\": \"\xE6\x88\x91\", \"offset\": 0}, {\"word\": \"\xE6\x9D\xA5\xE8\x87\xAA\", \"offset\": 3}, {\"word\": \"\xE5\x8C\x97\xE4\xBA\xAC\xE9\x82\xAE\xE7\x94\xB5\xE5\xA4\xA7\xE5\xAD\xA6\", \"offset\": 9}, {\"word\": \"\xE3\x80\x82\", \"offset\": 27}]", result);
|
60
|
+
|
61
|
+
jieba.CutSmall("南京市长江大桥", words, 3);
|
62
|
+
//ASSERT_EQ("[\"南京市\", \"长江\", \"大桥\"]", result << words);
|
63
|
+
ASSERT_EQ("[{\"word\": \"\xE5\x8D\x97\xE4\xBA\xAC\xE5\xB8\x82\", \"offset\": 0}, {\"word\": \"\xE9\x95\xBF\xE6\xB1\x9F\", \"offset\": 9}, {\"word\": \"\xE5\xA4\xA7\xE6\xA1\xA5\", \"offset\": 15}]", result << words);
|
64
|
+
|
65
|
+
jieba.CutHMM("我来自北京邮电大学。。。学号123456", words);
|
66
|
+
result << words;
|
67
|
+
ASSERT_EQ("[{\"word\": \"\xE6\x88\x91\xE6\x9D\xA5\", \"offset\": 0}, {\"word\": \"\xE8\x87\xAA\xE5\x8C\x97\xE4\xBA\xAC\", \"offset\": 6}, {\"word\": \"\xE9\x82\xAE\xE7\x94\xB5\xE5\xA4\xA7\xE5\xAD\xA6\", \"offset\": 15}, {\"word\": \"\xE3\x80\x82\", \"offset\": 27}, {\"word\": \"\xE3\x80\x82\", \"offset\": 30}, {\"word\": \"\xE3\x80\x82\", \"offset\": 33}, {\"word\": \"\xE5\xAD\xA6\xE5\x8F\xB7\", \"offset\": 36}, {\"word\": \"123456\", \"offset\": 42}]", result);
|
68
|
+
|
69
|
+
jieba.Cut("我来自北京邮电大学。。。学号123456,用AK47", words);
|
70
|
+
result << words;
|
71
|
+
//ASSERT_EQ("[\"我\", \"来自\", \"北京邮电大学\", \"。\", \"。\", \"。\", \"学号\", \"123456\", \",\", \"用\", \"AK47\"]", result);
|
72
|
+
ASSERT_EQ("[{\"word\": \"\xE6\x88\x91\", \"offset\": 0}, {\"word\": \"\xE6\x9D\xA5\xE8\x87\xAA\", \"offset\": 3}, {\"word\": \"\xE5\x8C\x97\xE4\xBA\xAC\xE9\x82\xAE\xE7\x94\xB5\xE5\xA4\xA7\xE5\xAD\xA6\", \"offset\": 9}, {\"word\": \"\xE3\x80\x82\", \"offset\": 27}, {\"word\": \"\xE3\x80\x82\", \"offset\": 30}, {\"word\": \"\xE3\x80\x82\", \"offset\": 33}, {\"word\": \"\xE5\xAD\xA6\xE5\x8F\xB7\", \"offset\": 36}, {\"word\": \"123456\", \"offset\": 42}, {\"word\": \"\xEF\xBC\x8C\", \"offset\": 48}, {\"word\": \"\xE7\x94\xA8\", \"offset\": 51}, {\"word\": \"AK47\", \"offset\": 54}]", result);
|
73
|
+
|
74
|
+
jieba.CutAll("我来自北京邮电大学", words);
|
75
|
+
result << words;
|
76
|
+
//ASSERT_EQ(result, "[\"我\", \"来自\", \"北京\", \"北京邮电\", \"北京邮电大学\", \"邮电\", \"邮电大学\", \"电大\", \"大学\"]");
|
77
|
+
ASSERT_EQ("[{\"word\": \"\xE6\x88\x91\", \"offset\": 0}, {\"word\": \"\xE6\x9D\xA5\xE8\x87\xAA\", \"offset\": 3}, {\"word\": \"\xE5\x8C\x97\xE4\xBA\xAC\", \"offset\": 9}, {\"word\": \"\xE5\x8C\x97\xE4\xBA\xAC\xE9\x82\xAE\xE7\x94\xB5\", \"offset\": 9}, {\"word\": \"\xE5\x8C\x97\xE4\xBA\xAC\xE9\x82\xAE\xE7\x94\xB5\xE5\xA4\xA7\xE5\xAD\xA6\", \"offset\": 9}, {\"word\": \"\xE9\x82\xAE\xE7\x94\xB5\", \"offset\": 15}, {\"word\": \"\xE9\x82\xAE\xE7\x94\xB5\xE5\xA4\xA7\xE5\xAD\xA6\", \"offset\": 15}, {\"word\": \"\xE7\x94\xB5\xE5\xA4\xA7\", \"offset\": 18}, {\"word\": \"\xE5\xA4\xA7\xE5\xAD\xA6\", \"offset\": 21}]", result);
|
78
|
+
|
79
|
+
jieba.CutForSearch("他来到了网易杭研大厦", words);
|
80
|
+
result << words;
|
81
|
+
//ASSERT_EQ("[\"他\", \"来到\", \"了\", \"网易\", \"杭研\", \"大厦\"]", result);
|
82
|
+
ASSERT_EQ("[{\"word\": \"\xE4\xBB\x96\", \"offset\": 0}, {\"word\": \"\xE6\x9D\xA5\xE5\x88\xB0\", \"offset\": 3}, {\"word\": \"\xE4\xBA\x86\", \"offset\": 9}, {\"word\": \"\xE7\xBD\x91\xE6\x98\x93\", \"offset\": 12}, {\"word\": \"\xE6\x9D\xAD\xE7\xA0\x94\", \"offset\": 18}, {\"word\": \"\xE5\xA4\xA7\xE5\x8E\xA6\", \"offset\": 24}]", result);
|
83
|
+
}
|
84
|
+
|
85
|
+
TEST(JiebaTest, InsertUserWord) {
|
86
|
+
cppjieba::Jieba jieba("../dict/jieba.dict.utf8",
|
87
|
+
"../dict/hmm_model.utf8",
|
88
|
+
"../dict/user.dict.utf8",
|
89
|
+
"../dict/idf.utf8",
|
90
|
+
"../dict/stop_words.utf8");
|
91
|
+
vector<string> words;
|
92
|
+
string result;
|
93
|
+
|
94
|
+
jieba.Cut("男默女泪", words);
|
95
|
+
result << words;
|
96
|
+
ASSERT_EQ("[\"男默\", \"女泪\"]", result);
|
97
|
+
|
98
|
+
ASSERT_TRUE(jieba.InsertUserWord("男默女泪"));
|
99
|
+
|
100
|
+
jieba.Cut("男默女泪", words);
|
101
|
+
result << words;
|
102
|
+
ASSERT_EQ("[\"男默女泪\"]", result);
|
103
|
+
|
104
|
+
for (size_t i = 0; i < 100; i++) {
|
105
|
+
string newWord;
|
106
|
+
newWord << rand();
|
107
|
+
ASSERT_TRUE(jieba.InsertUserWord(newWord));
|
108
|
+
jieba.Cut(newWord, words);
|
109
|
+
result << words;
|
110
|
+
ASSERT_EQ(result, StringFormat("[\"%s\"]", newWord.c_str()));
|
111
|
+
}
|
112
|
+
|
113
|
+
ASSERT_TRUE(jieba.InsertUserWord("同一个世界,同一个梦想"));
|
114
|
+
jieba.Cut("同一个世界,同一个梦想", words);
|
115
|
+
result = Join(words.begin(), words.end(), "/");
|
116
|
+
ASSERT_EQ(result, "同一个/世界/,/同一个/梦想");
|
117
|
+
|
118
|
+
jieba.ResetSeparators("");
|
119
|
+
|
120
|
+
jieba.Cut("同一个世界,同一个梦想", words);
|
121
|
+
result = Join(words.begin(), words.end(), "/");
|
122
|
+
ASSERT_EQ(result, "同一个世界,同一个梦想");
|
123
|
+
|
124
|
+
{
|
125
|
+
string s("一部iPhone6");
|
126
|
+
string res;
|
127
|
+
vector<KeywordExtractor::Word> wordweights;
|
128
|
+
size_t topN = 5;
|
129
|
+
jieba.extractor.Extract(s, wordweights, topN);
|
130
|
+
res << wordweights;
|
131
|
+
ASSERT_EQ(res, "[{\"word\": \"iPhone6\", \"offset\": [6], \"weight\": 11.7392}, {\"word\": \"\xE4\xB8\x80\xE9\x83\xA8\", \"offset\": [0], \"weight\": 6.47592}]");
|
132
|
+
}
|
133
|
+
}
|
@@ -0,0 +1,79 @@
|
|
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
|
+
}
|
@@ -0,0 +1,41 @@
|
|
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
|
+
}
|
@@ -0,0 +1,43 @@
|
|
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
|
+
}
|
@@ -0,0 +1,256 @@
|
|
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
|
+
}
|