third_codes/cppjieba
1
0
Fork 0
mirror of https://github.com/yanyiwu/cppjieba.git synced 2025-07-18 00:00:12 +08:00
Code Issues Packages Projects Releases Wiki Activity

merge some testfile into one testfile to reduce compiler cost

Browse Source
This commit is contained in:
wyy 2014-03-21 11:18:34 +08:00
parent 52b6c61326
commit d2d6868b75
9 changed files with 140 additions and 156 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ChangeLog.md
View File

@ -1,3 +1,7 @@
## v2.3.5
1. 修改一些测试用例的文件，减少测试时编译的时间。
## v2.3.4
1. 修改了设计上的问题，删除了`TrieManager`这个类，以避免造成一些可能的隐患。

2
test/unittest/CMakeLists.txt
View File

@ -6,7 +6,7 @@ SET(GTEST_ROOT_DIR gtest-1.6.0)
ADD_DEFINITIONS(-DLOGGER_LEVEL=LL_WARN)
INCLUDE_DIRECTORIES(${GTEST_ROOT_DIR} ${GTEST_ROOT_DIR}/include ${PROJECT_SOURCE_DIR})
ADD_LIBRARY(gtest STATIC ${GTEST_ROOT_DIR}/src/gtest-all.cc)
ADD_EXECUTABLE(test.run gtest_main.cpp TKeywordExtractor.cpp TMPSegment.cpp TTrie.cpp TFullSegment.cpp TQuerySegment.cpp THMMSegment.cpp TMixSegment.cpp TSegmentBase.cpp)
ADD_EXECUTABLE(test.run gtest_main.cpp TKeywordExtractor.cpp TTrie.cpp TSegments.cpp )
TARGET_LINK_LIBRARIES(gtest pthread)
TARGET_LINK_LIBRARIES(test.run gtest pthread)

18
test/unittest/TFullSegment.cpp
View File

@ -1,18 +0,0 @@
#include "src/FullSegment.hpp"
#include "gtest/gtest.h"
using namespace CppJieba;
TEST(FullSegment, Test1)
{
FullSegment segment("../dict/extra_dict/jieba.dict.small.utf8");
const char* str = "我来自北京邮电大学。。。 学号 123456";
vector<string> words;
ASSERT_EQ(segment.cut(str, words), true);
string s;
s << words;
ASSERT_EQ(s, "[\"我\", \"来自\", \"北京\", \"北京邮电大学\", \"邮电\", \"电大\", \"大学\", \"。\", \"。\", \"。\", \" \", \"学\", \"号\", \" 123456\"]");
}

19
test/unittest/THMMSegment.cpp
View File

@ -1,19 +0,0 @@
#include "src/HMMSegment.hpp"
#include "gtest/gtest.h"
using namespace CppJieba;
TEST(HMMSegmentTest, Test1)
{
HMMSegment segment("../dict/hmm_model.utf8");;
const char* str = "我来自北京邮电大学。。。 学号 123456";
const char* res[] = {"我来", "自北京", "邮电大学", "。", "。", "。", " ", "学号", " 123456"};
//string s;
//vector<string> buf(res, res + sizeof(res)/sizeof(res[0]));
vector<string> words;
ASSERT_TRUE(segment);
ASSERT_TRUE(segment.cut(str, words));
//print(words);
EXPECT_EQ(words, vector<string>(res, res + sizeof(res)/sizeof(res[0])));
}

46
test/unittest/TMPSegment.cpp
View File

@ -1,46 +0,0 @@
#include "src/MPSegment.hpp"
#include "src/Limonp/io_functs.hpp"
#include "gtest/gtest.h"
using namespace CppJieba;
using namespace Limonp;
TEST(MPSegmentTest, Test1)
{
MPSegment segment("../dict/extra_dict/jieba.dict.small.utf8");;
const char* str = "我来自北京邮电大学。。。 学号 123456";
const char* res[] = {"我", "来自", "北京邮电大学", "。","。","。"," ","学","号", " 123456"};
vector<string> words;
ASSERT_TRUE(segment);
ASSERT_TRUE(segment.cut(str, words));
//print(words);
EXPECT_EQ(words, vector<string>(res, res + sizeof(res)/sizeof(res[0])));
}
TEST(MPSegmentTest, Test2)
{
MPSegment segment("../dict/extra_dict/jieba.dict.small.utf8");
string line;
ifstream ifs("../test/testdata/review.100");
vector<string> words;
string eRes;
loadFile2Str("../test/testdata/review.100.res", eRes);
string res;
while(getline(ifs, line))
{
res += line;
res += '\n';
words.clear();
segment.cut(line, words);
string s;
s << words;
res += s;
res += '\n';
}
WriteStr2File("../test/testdata/review.100.res", res.c_str(), "w");
//ASSERT_EQ(res, eRes);
}

16
test/unittest/TMixSegment.cpp
View File

@ -1,16 +0,0 @@
#include "src/MixSegment.hpp"
#include "gtest/gtest.h"
using namespace CppJieba;
TEST(MixSegmentTest, Test1)
{
MixSegment segment("../dict/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8");;
const char* str = "我来自北京邮电大学。。。 学号 123456";
const char* res[] = {"我", "来自", "北京邮电大学", "。","。","。"," ","学号", " 123456"};
vector<string> words;
ASSERT_TRUE(segment);
ASSERT_TRUE(segment.cut(str, words));
EXPECT_EQ(words, vector<string>(res, res + sizeof(res)/sizeof(res[0])));
}

20
test/unittest/TQuerySegment.cpp
View File

@ -1,20 +0,0 @@
#include "src/QuerySegment.hpp"
#include "gtest/gtest.h"
using namespace CppJieba;
TEST(QuerySegment, Test1)
{
QuerySegment segment("../dict/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", 3);
const char* str = "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";
vector<string> words;
ASSERT_TRUE(segment.cut(str, words));
string s1, s2;
s1 << words;
s2 = "[\"小明\", \"硕士\", \"毕业\", \"于\", \"中国\", \"中国科学院\", \"科学\", \"科学院\", \"学院\", \"计算所\", \"，\", \"后\", \"在\", \"日本\", \"京都\", \"京都大学\", \"大学\", \"深造\"]";
ASSERT_EQ(s1, s2);
}

36
test/unittest/TSegmentBase.cpp
View File

@ -1,36 +0,0 @@
#include "src/SegmentBase.hpp"
#include "gtest/gtest.h"
using namespace CppJieba;
TEST(SegmentBaseTest, Test1)
{
const char* str = "heheh你好...hh";
string s;
vector<string> buf;
buf.push_back("heheh");
buf.push_back("你好");
buf.push_back("...hh");
vector<string> res;
size_t size = strlen(str);
size_t offset = 0;
while(offset < size)
{
size_t len = 0;
const char* t = str + offset;
SegmentBase::filterAscii(t, size - offset, len);
s.assign(t, len);
res.push_back(s);
//cout<<s<<","<<ret<<","<<len<<endl;
//cout<<str<<endl;
offset += len;
}
EXPECT_EQ(res, buf);
}
//int main(int argc, char** argv)
//{
// //ChineseFilter chFilter;
// return 0;
//}

135
test/unittest/TSegments.cpp Normal file
View File

@ -0,0 +1,135 @@
#include "src/SegmentBase.hpp"
#include "src/MixSegment.hpp"
#include "src/MPSegment.hpp"
#include "src/HMMSegment.hpp"
#include "src/Limonp/io_functs.hpp"
#include "src/FullSegment.hpp"
#include "src/QuerySegment.hpp"
#include "gtest/gtest.h"
using namespace CppJieba;
TEST(SegmentBaseTest, Test1)
{
const char* str = "heheh你好...hh";
string s;
vector<string> buf;
buf.push_back("heheh");
buf.push_back("你好");
buf.push_back("...hh");
vector<string> res;
size_t size = strlen(str);
size_t offset = 0;
while(offset < size)
{
size_t len = 0;
const char* t = str + offset;
SegmentBase::filterAscii(t, size - offset, len);
s.assign(t, len);
res.push_back(s);
//cout<<s<<","<<ret<<","<<len<<endl;
//cout<<str<<endl;
offset += len;
}
EXPECT_EQ(res, buf);
}
//int main(int argc, char** argv)
//{
// //ChineseFilter chFilter;
// return 0;
//}
TEST(MixSegmentTest, Test1)
{
MixSegment segment("../dict/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8");;
const char* str = "我来自北京邮电大学。。。 学号 123456";
const char* res[] = {"我", "来自", "北京邮电大学", "。","。","。"," ","学号", " 123456"};
vector<string> words;
ASSERT_TRUE(segment);
ASSERT_TRUE(segment.cut(str, words));
EXPECT_EQ(words, vector<string>(res, res + sizeof(res)/sizeof(res[0])));
}
TEST(MPSegmentTest, Test1)
{
MPSegment segment("../dict/extra_dict/jieba.dict.small.utf8");;
const char* str = "我来自北京邮电大学。。。 学号 123456";
const char* res[] = {"我", "来自", "北京邮电大学", "。","。","。"," ","学","号", " 123456"};
vector<string> words;
ASSERT_TRUE(segment);
ASSERT_TRUE(segment.cut(str, words));
//print(words);
EXPECT_EQ(words, vector<string>(res, res + sizeof(res)/sizeof(res[0])));
}
TEST(MPSegmentTest, Test2)
{
MPSegment segment("../dict/extra_dict/jieba.dict.small.utf8");
string line;
ifstream ifs("../test/testdata/review.100");
vector<string> words;
string eRes;
loadFile2Str("../test/testdata/review.100.res", eRes);
string res;
while(getline(ifs, line))
{
res += line;
res += '\n';
words.clear();
segment.cut(line, words);
string s;
s << words;
res += s;
res += '\n';
}
WriteStr2File("../test/testdata/review.100.res", res.c_str(), "w");
//ASSERT_EQ(res, eRes);
}
TEST(HMMSegmentTest, Test1)
{
HMMSegment segment("../dict/hmm_model.utf8");;
const char* str = "我来自北京邮电大学。。。 学号 123456";
const char* res[] = {"我来", "自北京", "邮电大学", "。", "。", "。", " ", "学号", " 123456"};
//string s;
//vector<string> buf(res, res + sizeof(res)/sizeof(res[0]));
vector<string> words;
ASSERT_TRUE(segment);
ASSERT_TRUE(segment.cut(str, words));
//print(words);
EXPECT_EQ(words, vector<string>(res, res + sizeof(res)/sizeof(res[0])));
}
TEST(FullSegment, Test1)
{
FullSegment segment("../dict/extra_dict/jieba.dict.small.utf8");
const char* str = "我来自北京邮电大学。。。 学号 123456";
vector<string> words;
ASSERT_EQ(segment.cut(str, words), true);
string s;
s << words;
ASSERT_EQ(s, "[\"我\", \"来自\", \"北京\", \"北京邮电大学\", \"邮电\", \"电大\", \"大学\", \"。\", \"。\", \"。\", \" \", \"学\", \"号\", \" 123456\"]");
}
TEST(QuerySegment, Test1)
{
QuerySegment segment("../dict/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", 3);
const char* str = "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";
vector<string> words;
ASSERT_TRUE(segment.cut(str, words));
string s1, s2;
s1 << words;
s2 = "[\"小明\", \"硕士\", \"毕业\", \"于\", \"中国\", \"中国科学院\", \"科学\", \"科学院\", \"学院\", \"计算所\", \"，\", \"后\", \"在\", \"日本\", \"京都\", \"京都大学\", \"大学\", \"深造\"]";
ASSERT_EQ(s1, s2);
}