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

build: enhance test configuration and path management

Browse Source 
- Added configuration for test paths in CMake to simplify file references.
- Updated load_test.cpp and various unit tests to use defined path macros for dictionary and test data files.
- Introduced test_paths.h.in to manage directory paths consistently across tests.
This commit is contained in:
Yanyi Wu 2025-05-02 23:33:18 +08:00
parent aa410a69bb
commit 9cd64a1694
10 changed files with 109 additions and 62 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
test/CMakeLists.txt
View File

@ -1,4 +1,7 @@
SET(EXECUTABLE_OUTPUT_PATH ${PROJECT_BINARY_DIR})
# Configure test paths
configure_file("${CMAKE_CURRENT_SOURCE_DIR}/test_paths.h.in" "${CMAKE_BINARY_DIR}/test/test_paths.h")
ADD_EXECUTABLE(load_test load_test.cpp)
ADD_SUBDIRECTORY(unittest)
ADD_SUBDIRECTORY(unittest)

34
test/load_test.cpp
View File

@ -6,14 +6,17 @@
#include "cppjieba/MixSegment.hpp"
#include "cppjieba/KeywordExtractor.hpp"
#include "limonp/Colors.hpp"
#include "cppjieba/Jieba.hpp"
#include "gtest/gtest.h"
#include "test_paths.h"
using namespace cppjieba;
void Cut(size_t times = 50) {
MixSegment seg("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8");
MixSegment seg(DICT_DIR "/jieba.dict.utf8", DICT_DIR "/hmm_model.utf8");
vector<string> res;
string doc;
ifstream ifs("../test/testdata/weicheng.utf8");
ifstream ifs(TEST_DATA_DIR "/weicheng.utf8");
assert(ifs);
doc << ifs;
long beginTime = clock();
@ -29,10 +32,13 @@ void Cut(size_t times = 50) {
}
void Extract(size_t times = 400) {
KeywordExtractor Extractor("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8", "../dict/idf.utf8", "../dict/stop_words.utf8");
KeywordExtractor Extractor(DICT_DIR "/jieba.dict.utf8",
DICT_DIR "/hmm_model.utf8",
DICT_DIR "/idf.utf8",
DICT_DIR "/stop_words.utf8");
vector<string> words;
string doc;
ifstream ifs("../test/testdata/review.100");
ifstream ifs(TEST_DATA_DIR "/review.100");
assert(ifs);
doc << ifs;
long beginTime = clock();
@ -47,8 +53,24 @@ void Extract(size_t times = 400) {
ColorPrintln(GREEN, "Extract: [%.3lf seconds]time consumed.", double(endTime - beginTime)/CLOCKS_PER_SEC);
}
int main(int argc, char ** argv) {
TEST(LoadTest, Test1) {
Jieba jieba(DICT_DIR "/jieba.dict.utf8",
DICT_DIR "/hmm_model.utf8",
DICT_DIR "/user.dict.utf8",
DICT_DIR "/idf.utf8",
DICT_DIR "/stop_words.utf8");
vector<string> words;
string result;
jieba.Cut("他来到了网易杭研大厦", words);
result << words;
string expected = "[\"他\", \"来到\", \"了\", \"网易\", \"杭研\", \"大厦\"]";
ASSERT_EQ(expected, result);
}
int main(int argc, char** argv) {
testing::InitGoogleTest(&argc, argv);
Cut();
Extract();
return EXIT_SUCCESS;
return RUN_ALL_TESTS();
}

7
test/test_paths.h.in Normal file
View File

@ -0,0 +1,7 @@
#ifndef TEST_PATHS_H
#define TEST_PATHS_H
#define TEST_DATA_DIR "@CMAKE_CURRENT_SOURCE_DIR@/testdata"
#define DICT_DIR "@CMAKE_SOURCE_DIR@/dict"
#endif // TEST_PATHS_H

7
test/unittest/CMakeLists.txt
View File

@ -1,3 +1,4 @@
message(STATUS "MSVC value: ${MSVC}")
if (MSVC)
set(CMAKE_MSVC_RUNTIME_LIBRARY "MultiThreadedDebugDLL")
set(gtest_force_shared_crt ON CACHE BOOL "" FORCE)
@ -19,6 +20,12 @@ SET(LIBRARY_OUTPUT_PATH ${PROJECT_BINARY_DIR}/lib)
ADD_DEFINITIONS(-DLOGGING_LEVEL=LL_WARNING)
# Add include directories
INCLUDE_DIRECTORIES(
${CMAKE_CURRENT_BINARY_DIR}
${CMAKE_BINARY_DIR}/test
)
ADD_EXECUTABLE(test.run
gtest_main.cpp
keyword_extractor_test.cpp

33
test/unittest/jieba_test.cpp
View File

@ -1,5 +1,6 @@
#include "cppjieba/Jieba.hpp"
#include "gtest/gtest.h"
#include "test_paths.h"
using namespace cppjieba;
@ -37,11 +38,11 @@ TEST(JiebaTest, Test0) {
}
TEST(JiebaTest, Test1) {
cppjieba::Jieba jieba("../dict/jieba.dict.utf8",
"../dict/hmm_model.utf8",
"../dict/user.dict.utf8",
"../dict/idf.utf8",
"../dict/stop_words.utf8");
cppjieba::Jieba jieba(DICT_DIR "/jieba.dict.utf8",
DICT_DIR "/hmm_model.utf8",
DICT_DIR "/user.dict.utf8",
DICT_DIR "/idf.utf8",
DICT_DIR "/stop_words.utf8");
vector<string> words;
string result;
@ -71,14 +72,14 @@ TEST(JiebaTest, Test1) {
jieba.CutForSearch("他来到了网易杭研大厦", words);
result << words;
ASSERT_EQ("[\"他\", \"来到\", \"了\", \"网易\", \"杭研\", \"大厦\"]", result);
}
TEST(JiebaTest, WordTest) {
cppjieba::Jieba jieba("../dict/jieba.dict.utf8",
"../dict/hmm_model.utf8",
"../dict/user.dict.utf8",
"../dict/idf.utf8",
"../dict/stop_words.utf8");
cppjieba::Jieba jieba(DICT_DIR "/jieba.dict.utf8",
DICT_DIR "/hmm_model.utf8",
DICT_DIR "/user.dict.utf8",
DICT_DIR "/idf.utf8",
DICT_DIR "/stop_words.utf8");
vector<Word> words;
string result;
@ -116,11 +117,11 @@ TEST(JiebaTest, WordTest) {
}
TEST(JiebaTest, InsertUserWord) {
cppjieba::Jieba jieba("../dict/jieba.dict.utf8",
"../dict/hmm_model.utf8",
"../dict/user.dict.utf8",
"../dict/idf.utf8",
"../dict/stop_words.utf8");
cppjieba::Jieba jieba(DICT_DIR "/jieba.dict.utf8",
DICT_DIR "/hmm_model.utf8",
DICT_DIR "/user.dict.utf8",
DICT_DIR "/idf.utf8",
DICT_DIR "/stop_words.utf8");
vector<string> words;
string result;

12
test/unittest/keyword_extractor_test.cpp
View File

@ -1,10 +1,14 @@
#include "cppjieba/KeywordExtractor.hpp"
#include "gtest/gtest.h"
#include "test_paths.h"
using namespace cppjieba;
TEST(KeywordExtractorTest, Test1) {
KeywordExtractor Extractor("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", "../dict/idf.utf8", "../dict/stop_words.utf8");
KeywordExtractor Extractor(TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8",
DICT_DIR "/hmm_model.utf8",
DICT_DIR "/idf.utf8",
DICT_DIR "/stop_words.utf8");
{
string s("你好世界世界而且而且");
@ -55,7 +59,11 @@ TEST(KeywordExtractorTest, Test1) {
}
TEST(KeywordExtractorTest, Test2) {
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");
KeywordExtractor Extractor(TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8",
DICT_DIR "/hmm_model.utf8",
DICT_DIR "/idf.utf8",
DICT_DIR "/stop_words.utf8",
TEST_DATA_DIR "/userdict.utf8");
{
string s("蓝翔优秀毕业生");

5
test/unittest/pos_tagger_test.cpp
View File

@ -1,5 +1,6 @@
#include "cppjieba/MixSegment.hpp"
#include "gtest/gtest.h"
#include "test_paths.h"
using namespace cppjieba;
@ -13,7 +14,7 @@ static const char * const ANS_TEST3 = "[iPhone6:eng, 手机:n, 的:uj, 最大:a,
//static const char * const ANS_TEST3 = "";
TEST(PosTaggerTest, Test) {
MixSegment tagger("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8");
MixSegment tagger(DICT_DIR "/jieba.dict.utf8", DICT_DIR "/hmm_model.utf8");
{
vector<pair<string, string> > res;
tagger.Tag(QUERY_TEST1, res);
@ -23,7 +24,7 @@ TEST(PosTaggerTest, Test) {
}
}
TEST(PosTagger, TestUserDict) {
MixSegment tagger("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8", "../test/testdata/userdict.utf8");
MixSegment tagger(DICT_DIR "/jieba.dict.utf8", DICT_DIR "/hmm_model.utf8", TEST_DATA_DIR "/userdict.utf8");
{
vector<pair<string, string> > res;
tagger.Tag(QUERY_TEST2, res);

35
test/unittest/segments_test.cpp
View File

@ -5,11 +5,12 @@
#include "cppjieba/FullSegment.hpp"
#include "cppjieba/QuerySegment.hpp"
#include "gtest/gtest.h"
#include "test_paths.h"
using namespace cppjieba;
TEST(MixSegmentTest, Test1) {
MixSegment segment("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8");;
MixSegment segment(DICT_DIR "/jieba.dict.utf8", DICT_DIR "/hmm_model.utf8");
string sentence;
vector<string> words;
string actual;
@ -49,16 +50,18 @@ TEST(MixSegmentTest, Test1) {
}
TEST(MixSegmentTest, NoUserDict) {
MixSegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8");
MixSegment segment(TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8", DICT_DIR "/hmm_model.utf8");
const char* str = "令狐冲是云计算方面的专家";
vector<string> words;
segment.Cut(str, words);
string res;
ASSERT_EQ("[\"令狐冲\", \"是\", \"云\", \"计算\", \"方面\", \"的\", \"专家\"]", res << words);
}
TEST(MixSegmentTest, UserDict) {
MixSegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", "../dict/user.dict.utf8");
MixSegment segment(TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8",
DICT_DIR "/hmm_model.utf8",
DICT_DIR "/user.dict.utf8");
{
const char* str = "令狐冲是云计算方面的专家";
vector<string> words;
@ -83,9 +86,10 @@ TEST(MixSegmentTest, UserDict) {
ASSERT_EQ("[\"IBM\", \",\", \"3.14\"]", res);
}
}
TEST(MixSegmentTest, TestUserDict) {
MixSegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8",
"../test/testdata/userdict.utf8");
MixSegment segment(TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8", DICT_DIR "/hmm_model.utf8",
TEST_DATA_DIR "/userdict.utf8");
vector<string> words;
string res;
@ -123,8 +127,8 @@ TEST(MixSegmentTest, TestUserDict) {
}
TEST(MixSegmentTest, TestMultiUserDict) {
MixSegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8",
"../test/testdata/userdict.utf8;../test/testdata/userdict.2.utf8");
MixSegment segment(TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8", DICT_DIR "/hmm_model.utf8",
TEST_DATA_DIR "/userdict.utf8;" TEST_DATA_DIR "/userdict.2.utf8");
vector<string> words;
string res;
@ -134,7 +138,7 @@ TEST(MixSegmentTest, TestMultiUserDict) {
}
TEST(MPSegmentTest, Test1) {
MPSegment segment("../dict/jieba.dict.utf8");;
MPSegment segment(DICT_DIR "/jieba.dict.utf8");
string s;
vector<string> words;
segment.Cut("我来自北京邮电大学。", words);
@ -163,7 +167,7 @@ TEST(MPSegmentTest, Test1) {
}
TEST(HMMSegmentTest, Test1) {
HMMSegment segment("../dict/hmm_model.utf8");;
HMMSegment segment(DICT_DIR "/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"};
@ -182,7 +186,7 @@ TEST(HMMSegmentTest, Test1) {
}
TEST(FullSegment, Test1) {
FullSegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8");
FullSegment segment(TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8");
vector<string> words;
string s;
@ -197,7 +201,7 @@ TEST(FullSegment, Test1) {
}
TEST(QuerySegment, Test1) {
QuerySegment segment("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8", "");
QuerySegment segment(DICT_DIR "/jieba.dict.utf8", DICT_DIR "/hmm_model.utf8", "");
vector<string> words;
string s1, s2;
@ -218,7 +222,9 @@ TEST(QuerySegment, Test1) {
}
TEST(QuerySegment, Test2) {
QuerySegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", "../test/testdata/userdict.utf8|../test/testdata/userdict.english");
QuerySegment segment(TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8",
DICT_DIR "/hmm_model.utf8",
TEST_DATA_DIR "/userdict.utf8|" TEST_DATA_DIR "/userdict.english");
vector<string> words;
string s1, s2;
@ -242,14 +248,13 @@ TEST(QuerySegment, Test2) {
s2 = "中国/科学/学院/科学院/中国科学院";
ASSERT_EQ(s1, s2);
}
}
TEST(MPSegmentTest, Unicode32) {
string s("天气很好，🙋 我们去郊游。");
vector<string> words;
MPSegment segment("../dict/jieba.dict.utf8");;
MPSegment segment(DICT_DIR "/jieba.dict.utf8");
segment.Cut(s, words);
ASSERT_EQ(Join(words.begin(), words.end(), "/"), "天气/很/好/，/🙋/ /我们/去/郊游/。");

15
test/unittest/textrank_test.cpp
View File

@ -1,13 +1,14 @@
#include "cppjieba/TextRankExtractor.hpp"
#include "gtest/gtest.h"
#include "test_paths.h"
using namespace cppjieba;
TEST(TextRankExtractorTest, Test1) {
TextRankExtractor Extractor(
"../test/testdata/extra_dict/jieba.dict.small.utf8",
"../dict/hmm_model.utf8",
"../dict/stop_words.utf8");
TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8",
DICT_DIR "/hmm_model.utf8",
DICT_DIR "/stop_words.utf8");
{
string s("你好世界世界而且而且");
string res;
@ -59,10 +60,10 @@ TEST(TextRankExtractorTest, Test1) {
TEST(TextRankExtractorTest, Test2) {
TextRankExtractor Extractor(
"../test/testdata/extra_dict/jieba.dict.small.utf8",
"../dict/hmm_model.utf8",
"../dict/stop_words.utf8",
"../test/testdata/userdict.utf8");
TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8",
DICT_DIR "/hmm_model.utf8",
DICT_DIR "/stop_words.utf8",
TEST_DATA_DIR "/userdict.utf8");
{
string s("\xe8\x93\x9d\xe7\xbf\x94\xe4\xbc\x98\xe7\xa7\x80\xe6\xaf\x95\xe4\xb8\x9a\xe7\x94\x9f");

18
test/unittest/trie_test.cpp
View File

@ -1,10 +1,11 @@
#include "cppjieba/DictTrie.hpp"
#include "cppjieba/MPSegment.hpp"
#include "gtest/gtest.h"
#include "test_paths.h"
using namespace cppjieba;
static const char* const DICT_FILE = "../test/testdata/extra_dict/jieba.dict.small.utf8";
static const char* const DICT_FILE = TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8";
TEST(TrieTest, Empty) {
vector<Unicode> keys;
@ -33,12 +34,6 @@ TEST(DictTrieTest, Test1) {
string word("来到");
cppjieba::RuneStrArray uni;
ASSERT_TRUE(DecodeUTF8RunesInString(word, uni));
//DictUnit nodeInfo;
//nodeInfo.word = uni;
//nodeInfo.tag = "v";
//nodeInfo.weight = -8.87033;
//s1 << nodeInfo;
//s2 << (*trie.Find(uni.begin(), uni.end()));
const DictUnit* du = trie.Find(uni.begin(), uni.end());
ASSERT_TRUE(du != NULL);
ASSERT_EQ(2u, du->word.size());
@ -47,14 +42,12 @@ TEST(DictTrieTest, Test1) {
ASSERT_EQ("v", du->tag);
ASSERT_NEAR(-8.870, du->weight, 0.001);
//EXPECT_EQ("[\"26469\", \"21040\"] v -8.870", s2);
word = "清华大学";
LocalVector<pair<size_t, const DictUnit*> > res;
const char * words[] = {"清", "清华", "清华大学"};
for (size_t i = 0; i < sizeof(words)/sizeof(words[0]); i++) {
ASSERT_TRUE(DecodeUTF8RunesInString(words[i], uni));
res.push_back(make_pair(uni.size() - 1, trie.Find(uni.begin(), uni.end())));
//resMap[uni.size() - 1] = trie.Find(uni.begin(), uni.end());
}
vector<pair<size_t, const DictUnit*> > vec;
vector<struct Dag> dags;
@ -65,11 +58,10 @@ TEST(DictTrieTest, Test1) {
s1 << res;
s2 << dags[0].nexts;
ASSERT_EQ(s1, s2);
}
TEST(DictTrieTest, UserDict) {
DictTrie trie(DICT_FILE, "../test/testdata/userdict.utf8");
DictTrie trie(DICT_FILE, TEST_DATA_DIR "/userdict.utf8");
string word = "云计算";
cppjieba::RuneStrArray unicode;
ASSERT_TRUE(DecodeUTF8RunesInString(word, unicode));
@ -93,7 +85,7 @@ TEST(DictTrieTest, UserDict) {
}
TEST(DictTrieTest, UserDictWithMaxWeight) {
DictTrie trie(DICT_FILE, "../test/testdata/userdict.utf8", DictTrie::WordWeightMax);
DictTrie trie(DICT_FILE, TEST_DATA_DIR "/userdict.utf8", DictTrie::WordWeightMax);
string word = "云计算";
cppjieba::RuneStrArray unicode;
ASSERT_TRUE(DecodeUTF8RunesInString(word, unicode));
@ -103,7 +95,7 @@ TEST(DictTrieTest, UserDictWithMaxWeight) {
}
TEST(DictTrieTest, Dag) {
DictTrie trie(DICT_FILE, "../test/testdata/userdict.utf8");
DictTrie trie(DICT_FILE, TEST_DATA_DIR "/userdict.utf8");
{
string word = "清华大学";