.github/workflows/cmake.yml

@@ -17,14 +17,12 @@ jobs:
     strategy:
       matrix:
         os: [
+          ubuntu-20.04, 
           ubuntu-22.04, 
-          ubuntu-latest,
           macos-13,
           macos-14,
-          macos-latest,
           windows-2019,
           windows-2022,
-          windows-latest,
         ]  
         cpp_version: [11, 14, 17, 20]
 

.gitignore

@@ -15,5 +15,3 @@ tmp
 t.*
 *.pid
 build
-Testing/Temporary/CTestCostData.txt
-Testing/Temporary/LastTest.log

CMakeLists.txt

@@ -4,6 +4,10 @@ PROJECT(CPPJIEBA)
 INCLUDE_DIRECTORIES(${PROJECT_SOURCE_DIR}/deps/limonp/include
   ${PROJECT_SOURCE_DIR}/include)
 
+if (CMAKE_INSTALL_PREFIX_INITIALIZED_TO_DEFAULT)
+    set (CMAKE_INSTALL_PREFIX "/usr/local/cppjieba" CACHE PATH "default install path" FORCE )
+endif()
+
 if(NOT DEFINED CMAKE_CXX_STANDARD)
     set(CMAKE_CXX_STANDARD 11)
 endif()
@@ -21,11 +25,18 @@ if(NOT DEFINED CPPJIEBA_TOP_LEVEL_PROJECT)
     endif()
 endif()
 
-if(CPPJIEBA_TOP_LEVEL_PROJECT)
+
+option(CPPJIEBA_BUILD_TESTS "Build cppjieba tests" ${CPPJIEBA_TOP_LEVEL_PROJECT})
+
+if(CPPJIEBA_BUILD_TESTS)
   ENABLE_TESTING()
 
-  message(STATUS "MSVC value: ${MSVC}")
   ADD_SUBDIRECTORY(test)
+  if(NOT MSVC)
     ADD_TEST(NAME ./test/test.run COMMAND ./test/test.run)
     ADD_TEST(NAME ./load_test COMMAND ./load_test)
   endif()
+endif()
+
+
+# ... other CMake configurations ...

README.md

@@ -10,25 +10,22 @@
 
 CppJieba是"结巴(Jieba)"中文分词的C++版本
 
-### 主要特点
+## 特性
 
-- 🚀 高性能：经过线上环境验证的稳定性和性能表现
++ 源代码都写进头文件`include/cppjieba/*.hpp`里，`include`即可使用。
-- 📦 易集成：源代码以头文件形式提供 (`include/cppjieba/*.hpp`)，包含即可使用
++ 支持`utf8`编码。
-- 🔍 多种分词模式：支持精确模式、全模式、搜索引擎模式等
++ 项目自带较为完善的单元测试，核心功能中文分词(utf8)的稳定性接受过线上环境检验。
-- 📚 自定义词典：支持用户自定义词典，支持多词典路径（使用'|'或';'分隔）
++ 支持载自定义用户词典，多路径时支持分隔符'|'或者';'分隔。
-- 💻 跨平台：支持 Linux、macOS、Windows 操作系统
++ 支持 `Linux` , `Mac OSX`, `Windows` 操作系统。
-- 🌈 UTF-8编码：原生支持 UTF-8 编码的中文处理
 
-## 快速开始
+## 用法
 
-### 环境要求
+### 依赖软件
 
-- C++ 编译器：
+* `g++ (version >= 4.1 is recommended) or clang++`;
-  - g++ (推荐 4.1 以上版本)
+* `cmake (version >= 2.6 is recommended)`;
-  - 或 clang++
-- cmake (推荐 2.6 以上版本)
 
-### 安装步骤
+### 下载和编译
 
 ```sh
 git clone https://github.com/yanyiwu/cppjieba.git
@@ -39,11 +36,15 @@ mkdir build
 cd build
 cmake ..
 make
+```
 
+有兴趣的可以跑跑测试(可选):
+
+```
 make test
 ```
 
-## 使用示例
+## Demo
 
 ```
 ./demo
@@ -209,37 +210,71 @@ For more details, please see [demo](https://github.com/yanyiwu/cppjieba-demo).
 
 + [dict.367W.utf8] iLife(562193561 at qq.com)
 
-## 生态系统
+## 应用
 
-CppJieba 已经被广泛应用于各种编程语言的分词实现中：
++ [GoJieba] go语言版本的结巴中文分词。
++ [NodeJieba] Node.js 版本的结巴中文分词。
++ [simhash] 中文文档的的相似度计算
++ [exjieba] Erlang 版本的结巴中文分词。
++ [jiebaR] R语言版本的结巴中文分词。
++ [cjieba] C语言版本的结巴分词。
++ [jieba_rb] Ruby 版本的结巴分词。
++ [iosjieba] iOS 版本的结巴分词。
++ [SqlJieba] MySQL 全文索引的结巴中文分词插件。
++ [pg_jieba] PostgreSQL 数据库的分词插件。
++ [simple] SQLite3 FTS5 数据库的分词插件。
++ [gitbook-plugin-search-pro] 支持中文搜索的 gitbook 插件。
++ [ngx_http_cppjieba_module] Nginx 分词插件。
++ [cppjiebapy] 由 [jannson] 开发的供 python 模块调用的项目 [cppjiebapy], 相关讨论 [cppjiebapy_discussion] .
++ [cppjieba-py] 由 [bung87] 基于 pybind11 封装的 python 模块,使用体验上接近于原jieba。
++ [KeywordServer] 50行搭建一个中文关键词抽取服务。
++ [cppjieba-server] CppJieba HTTP 服务器。
++ [phpjieba] php版本的结巴分词扩展。
++ [perl5-jieba] Perl版本的结巴分词扩展。
++ [jieba-dlang] D 语言的结巴分词 Deimos Bindings。
 
-- [GoJieba](https://github.com/yanyiwu/gojieba) - Go 语言版本
+## 性能评测
-- [NodeJieba](https://github.com/yanyiwu/nodejieba) - Node.js 版本
-- [CJieba](https://github.com/yanyiwu/cjieba) - C 语言版本
-- [jiebaR](https://github.com/qinwf/jiebaR) - R 语言版本
-- [exjieba](https://github.com/falood/exjieba) - Erlang 版本
-- [jieba_rb](https://github.com/altkatz/jieba_rb) - Ruby 版本
-- [iosjieba](https://github.com/yanyiwu/iosjieba) - iOS 版本
-- [phpjieba](https://github.com/jonnywang/phpjieba) - PHP 版本
-- [perl5-jieba](https://metacpan.org/pod/distribution/Lingua-ZH-Jieba/lib/Lingua/ZH/Jieba.pod) - Perl 版本
 
-### 应用项目
+[Jieba中文分词系列性能评测]
 
-- [simhash](https://github.com/yanyiwu/simhash) - 中文文档相似度计算
+## Sponsorship
-- [pg_jieba](https://github.com/jaiminpan/pg_jieba) - PostgreSQL 分词插件
-- [gitbook-plugin-search-pro](https://plugins.gitbook.com/plugin/search-pro) - Gitbook 中文搜索插件
-- [ngx_http_cppjieba_module](https://github.com/yanyiwu/ngx_http_cppjieba_module) - Nginx 分词插件
 
-## 贡献指南
+[![sponsorship](http://images.gitads.io/cppjieba)](https://tracking.gitads.io/?campaign=gitads&repo=cppjieba&redirect=gitads.io)
 
-我们欢迎各种形式的贡献，包括但不限于：
+## Contributors
 
-- 提交问题和建议
+### Code Contributors
-- 改进文档
+
-- 提交代码修复
+This project exists thanks to all the people who contribute.
-- 添加新功能
+<a href="https://github.com/yanyiwu/cppjieba/graphs/contributors"><img src="https://opencollective.com/cppjieba/contributors.svg?width=890&button=false" /></a>
-
+
-
+[GoJieba]:https://github.com/yanyiwu/gojieba
-如果您觉得 CppJieba 对您有帮助，欢迎 star ⭐️ 支持项目！
+[CppJieba]:https://github.com/yanyiwu/cppjieba
+[jannson]:https://github.com/jannson
+[cppjiebapy]:https://github.com/jannson/cppjiebapy
+[bung87]:https://github.com/bung87
+[cppjieba-py]:https://github.com/bung87/cppjieba-py
+[cppjiebapy_discussion]:https://github.com/yanyiwu/cppjieba/issues/1
+[NodeJieba]:https://github.com/yanyiwu/nodejieba
+[jiebaR]:https://github.com/qinwf/jiebaR
+[simhash]:https://github.com/yanyiwu/simhash
+[代码详解]:https://github.com/yanyiwu/cppjieba/wiki/CppJieba%E4%BB%A3%E7%A0%81%E8%AF%A6%E8%A7%A3
+[issue25]:https://github.com/yanyiwu/cppjieba/issues/25
+[exjieba]:https://github.com/falood/exjieba
+[KeywordServer]:https://github.com/yanyiwu/keyword_server
+[ngx_http_cppjieba_module]:https://github.com/yanyiwu/ngx_http_cppjieba_module
+[dict.367W.utf8]:https://github.com/qinwf/BigDict
+[cjieba]:http://github.com/yanyiwu/cjieba
+[jieba_rb]:https://github.com/altkatz/jieba_rb
+[iosjieba]:https://github.com/yanyiwu/iosjieba
+[SqlJieba]:https://github.com/yanyiwu/sqljieba
+[Jieba中文分词系列性能评测]:http://yanyiwu.com/work/2015/06/14/jieba-series-performance-test.html
+[pg_jieba]:https://github.com/jaiminpan/pg_jieba
+[gitbook-plugin-search-pro]:https://plugins.gitbook.com/plugin/search-pro
+[cppjieba-server]:https://github.com/yanyiwu/cppjieba-server
+[phpjieba]:https://github.com/jonnywang/phpjieba
+[perl5-jieba]:https://metacpan.org/pod/distribution/Lingua-ZH-Jieba/lib/Lingua/ZH/Jieba.pod
+[jieba-dlang]:https://github.com/shove70/jieba
+[simple]:https://github.com/wangfenjin/simple
 
 

deps/limonp

@@ -1 +1 @@
-Subproject commit 5c82a3f17e4e0adc6a5decfe245054b0ed533d1a
+Subproject commit ac32f1f287f65d5ce0ce295010c88026fae060ee

dict/jieba.dict.utf8

@@ -312698,6 +312698,7 @@ T恤 4 n
 部属 1126 n
 部属工作 3 n
 部属院校 3 n
+部手机 33 n
 部族 643 n
 部标 4 n
 部省级 2 n

test/CMakeLists.txt

@@ -1,12 +1,4 @@
 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")
-
-INCLUDE_DIRECTORIES(
-    ${CMAKE_CURRENT_BINARY_DIR}
-    ${CMAKE_BINARY_DIR}/test
-)
-
 ADD_EXECUTABLE(load_test load_test.cpp)
 ADD_SUBDIRECTORY(unittest)

test/load_test.cpp

@@ -6,15 +6,14 @@
 #include "cppjieba/MixSegment.hpp"
 #include "cppjieba/KeywordExtractor.hpp"
 #include "limonp/Colors.hpp"
-#include "test_paths.h"
 
 using namespace cppjieba;
 
 void Cut(size_t times = 50) {
-  MixSegment seg(DICT_DIR "/jieba.dict.utf8", DICT_DIR "/hmm_model.utf8");
+  MixSegment seg("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8");
   vector<string> res;
   string doc;
-  ifstream ifs(TEST_DATA_DIR "/weicheng.utf8");
+  ifstream ifs("../test/testdata/weicheng.utf8");
   assert(ifs);
   doc << ifs;
   long beginTime = clock();
@@ -30,13 +29,10 @@ void Cut(size_t times = 50) {
 }
 
 void Extract(size_t times = 400) {
-  KeywordExtractor Extractor(DICT_DIR "/jieba.dict.utf8", 
+  KeywordExtractor Extractor("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8", "../dict/idf.utf8", "../dict/stop_words.utf8");
-                           DICT_DIR "/hmm_model.utf8", 
-                           DICT_DIR "/idf.utf8", 
-                           DICT_DIR "/stop_words.utf8");
   vector<string> words;
   string doc;
-  ifstream ifs(TEST_DATA_DIR "/review.100");
+  ifstream ifs("../test/testdata/review.100");
   assert(ifs);
   doc << ifs;
   long beginTime = clock();

test/test_paths.h.in

@@ -1,7 +0,0 @@
-#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 

test/unittest/CMakeLists.txt

@@ -1,8 +1,6 @@
-message(STATUS "MSVC value: ${MSVC}")
 if (MSVC)
 	set(CMAKE_MSVC_RUNTIME_LIBRARY "MultiThreadedDebugDLL")
 	set(gtest_force_shared_crt ON CACHE BOOL "" FORCE)
-	add_compile_options(/utf-8)
 endif()
 
 include(FetchContent)
@@ -20,12 +18,6 @@ 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 

test/unittest/jieba_test.cpp

@@ -1,6 +1,5 @@
 #include "cppjieba/Jieba.hpp"
 #include "gtest/gtest.h"
-#include "test_paths.h"
 
 using namespace cppjieba;
 
@@ -38,11 +37,11 @@ TEST(JiebaTest, Test0) {
 }
 
 TEST(JiebaTest, Test1) {
-  cppjieba::Jieba jieba(DICT_DIR "/jieba.dict.utf8",
+  cppjieba::Jieba jieba("../dict/jieba.dict.utf8",
-                        DICT_DIR "/hmm_model.utf8",
+                        "../dict/hmm_model.utf8",
-                        DICT_DIR "/user.dict.utf8",
+                        "../dict/user.dict.utf8",
-                        DICT_DIR "/idf.utf8",
+                        "../dict/idf.utf8",
-                        DICT_DIR "/stop_words.utf8");
+                        "../dict/stop_words.utf8");
   vector<string> words;
   string result;
 
@@ -72,14 +71,14 @@ 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_DIR "/jieba.dict.utf8",
+  cppjieba::Jieba jieba("../dict/jieba.dict.utf8",
-                        DICT_DIR "/hmm_model.utf8",
+                        "../dict/hmm_model.utf8",
-                        DICT_DIR "/user.dict.utf8",
+                        "../dict/user.dict.utf8",
-                        DICT_DIR "/idf.utf8",
+                        "../dict/idf.utf8",
-                        DICT_DIR "/stop_words.utf8");
+                        "../dict/stop_words.utf8");
   vector<Word> words;
   string result;
 
@@ -117,11 +116,11 @@ TEST(JiebaTest, WordTest) {
 }
 
 TEST(JiebaTest, InsertUserWord) {
-  cppjieba::Jieba jieba(DICT_DIR "/jieba.dict.utf8",
+  cppjieba::Jieba jieba("../dict/jieba.dict.utf8",
-                        DICT_DIR "/hmm_model.utf8",
+                        "../dict/hmm_model.utf8",
-                        DICT_DIR "/user.dict.utf8",
+                        "../dict/user.dict.utf8",
-                        DICT_DIR "/idf.utf8",
+                        "../dict/idf.utf8",
-                        DICT_DIR "/stop_words.utf8");
+                        "../dict/stop_words.utf8");
   vector<string> words;
   string result;
 

test/unittest/keyword_extractor_test.cpp

@@ -1,14 +1,10 @@
 #include "cppjieba/KeywordExtractor.hpp"
 #include "gtest/gtest.h"
-#include "test_paths.h"
 
 using namespace cppjieba;
 
 TEST(KeywordExtractorTest, Test1) {
-  KeywordExtractor Extractor(TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8", 
+  KeywordExtractor Extractor("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", "../dict/idf.utf8", "../dict/stop_words.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");
@@ -59,11 +55,7 @@ TEST(KeywordExtractorTest, Test1) {
 }
 
 TEST(KeywordExtractorTest, Test2) {
-  KeywordExtractor Extractor(TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8", 
+  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");
-                            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");

test/unittest/pos_tagger_test.cpp

@@ -1,6 +1,5 @@
 #include "cppjieba/MixSegment.hpp"
 #include "gtest/gtest.h"
-#include "test_paths.h"
 
 using namespace cppjieba;
 
@@ -14,7 +13,7 @@ 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_DIR "/jieba.dict.utf8", DICT_DIR "/hmm_model.utf8");
+  MixSegment tagger("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8");
   {
     vector<pair<string, string> > res;
     tagger.Tag(QUERY_TEST1, res);
@@ -24,7 +23,7 @@ TEST(PosTaggerTest, Test) {
   }
 }
 TEST(PosTagger, TestUserDict) {
-  MixSegment tagger(DICT_DIR "/jieba.dict.utf8", DICT_DIR "/hmm_model.utf8", TEST_DATA_DIR "/userdict.utf8");
+  MixSegment tagger("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8", "../test/testdata/userdict.utf8");
   {
     vector<pair<string, string> > res;
     tagger.Tag(QUERY_TEST2, res);

test/unittest/segments_test.cpp

@@ -5,12 +5,11 @@
 #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_DIR "/jieba.dict.utf8", DICT_DIR "/hmm_model.utf8");
+  MixSegment segment("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8");;
   string sentence;
   vector<string> words;
   string actual;
@@ -50,18 +49,16 @@ TEST(MixSegmentTest, Test1) {
 }
 
 TEST(MixSegmentTest, NoUserDict) {
-  MixSegment segment(TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8", DICT_DIR "/hmm_model.utf8");
+  MixSegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/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_DATA_DIR "/extra_dict/jieba.dict.small.utf8", 
+  MixSegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", "../dict/user.dict.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;
@@ -86,10 +83,9 @@ TEST(MixSegmentTest, UserDict) {
     ASSERT_EQ("[\"IBM\", \",\", \"3.14\"]", res);
   }
 }
-
 TEST(MixSegmentTest, TestUserDict) {
-  MixSegment segment(TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8", DICT_DIR "/hmm_model.utf8", 
+  MixSegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", 
-        TEST_DATA_DIR "/userdict.utf8");
+        "../test/testdata/userdict.utf8");
   vector<string> words;
   string res;
 
@@ -127,8 +123,8 @@ TEST(MixSegmentTest, TestUserDict) {
 }
 
 TEST(MixSegmentTest, TestMultiUserDict) {
-  MixSegment segment(TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8", DICT_DIR "/hmm_model.utf8", 
+  MixSegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", 
-        TEST_DATA_DIR "/userdict.utf8;" TEST_DATA_DIR "/userdict.2.utf8");
+        "../test/testdata/userdict.utf8;../test/testdata/userdict.2.utf8");
   vector<string> words;
   string res;
 
@@ -138,7 +134,7 @@ TEST(MixSegmentTest, TestMultiUserDict) {
 }
 
 TEST(MPSegmentTest, Test1) {
-  MPSegment segment(DICT_DIR "/jieba.dict.utf8");
+  MPSegment segment("../dict/jieba.dict.utf8");;
   string s;
   vector<string> words;
   segment.Cut("我来自北京邮电大学。", words);
@@ -167,7 +163,7 @@ TEST(MPSegmentTest, Test1) {
 }
 
 TEST(HMMSegmentTest, Test1) {
-  HMMSegment segment(DICT_DIR "/hmm_model.utf8");
+  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"};
@@ -186,7 +182,7 @@ TEST(HMMSegmentTest, Test1) {
 }
 
 TEST(FullSegment, Test1) {
-  FullSegment segment(TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8");
+  FullSegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8");
   vector<string> words;
   string s;
 
@@ -201,7 +197,7 @@ TEST(FullSegment, Test1) {
 }
 
 TEST(QuerySegment, Test1) {
-  QuerySegment segment(DICT_DIR "/jieba.dict.utf8", DICT_DIR "/hmm_model.utf8", "");
+  QuerySegment segment("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8", "");
   vector<string> words;
   string s1, s2;
 
@@ -222,9 +218,7 @@ TEST(QuerySegment, Test1) {
 }
 
 TEST(QuerySegment, Test2) {
-  QuerySegment segment(TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8", 
+  QuerySegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", "../test/testdata/userdict.utf8|../test/testdata/userdict.english");
-                      DICT_DIR "/hmm_model.utf8", 
-                      TEST_DATA_DIR "/userdict.utf8|" TEST_DATA_DIR "/userdict.english");
   vector<string> words;
   string s1, s2;
 
@@ -248,13 +242,14 @@ 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_DIR "/jieba.dict.utf8");
+  MPSegment segment("../dict/jieba.dict.utf8");;
   segment.Cut(s, words);
 
   ASSERT_EQ(Join(words.begin(), words.end(), "/"), "天气/很/好/，/🙋/ /我们/去/郊游/。");

test/unittest/textrank_test.cpp

@@ -1,14 +1,13 @@
 #include "cppjieba/TextRankExtractor.hpp"
 #include "gtest/gtest.h"
-#include "test_paths.h"
 
 using namespace cppjieba;
 
 TEST(TextRankExtractorTest, Test1) {
   TextRankExtractor Extractor(
-    TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8",
+    "../test/testdata/extra_dict/jieba.dict.small.utf8",
-    DICT_DIR "/hmm_model.utf8", 
+    "../dict/hmm_model.utf8", 
-    DICT_DIR "/stop_words.utf8");
+    "../dict/stop_words.utf8");
   {
     string s("你好世界世界而且而且");
     string res;
@@ -60,10 +59,10 @@ TEST(TextRankExtractorTest, Test1) {
 
 TEST(TextRankExtractorTest, Test2) {
   TextRankExtractor Extractor(
-    TEST_DATA_DIR "/extra_dict/jieba.dict.small.utf8",
+    "../test/testdata/extra_dict/jieba.dict.small.utf8",
-    DICT_DIR "/hmm_model.utf8",
+    "../dict/hmm_model.utf8",
-    DICT_DIR "/stop_words.utf8",
+    "../dict/stop_words.utf8",
-    TEST_DATA_DIR "/userdict.utf8");
+    "../test/testdata/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");

test/unittest/trie_test.cpp

@@ -1,11 +1,10 @@
 #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_DATA_DIR "/extra_dict/jieba.dict.small.utf8";
+static const char* const DICT_FILE = "../test/testdata/extra_dict/jieba.dict.small.utf8";
 
 TEST(TrieTest, Empty) {
   vector<Unicode> keys;
@@ -34,6 +33,12 @@ 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());
@@ -42,12 +47,14 @@ 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;
@@ -58,10 +65,11 @@ TEST(DictTrieTest, Test1) {
   s1 << res;
   s2 << dags[0].nexts;
   ASSERT_EQ(s1, s2);
+  
 }
 
 TEST(DictTrieTest, UserDict) {
-  DictTrie trie(DICT_FILE, TEST_DATA_DIR "/userdict.utf8");
+  DictTrie trie(DICT_FILE, "../test/testdata/userdict.utf8");
   string word = "云计算";
   cppjieba::RuneStrArray unicode;
   ASSERT_TRUE(DecodeUTF8RunesInString(word, unicode));
@@ -85,7 +93,7 @@ TEST(DictTrieTest, UserDict) {
 }
 
 TEST(DictTrieTest, UserDictWithMaxWeight) {
-  DictTrie trie(DICT_FILE, TEST_DATA_DIR "/userdict.utf8", DictTrie::WordWeightMax);
+  DictTrie trie(DICT_FILE, "../test/testdata/userdict.utf8", DictTrie::WordWeightMax);
   string word = "云计算";
   cppjieba::RuneStrArray unicode;
   ASSERT_TRUE(DecodeUTF8RunesInString(word, unicode));
@@ -95,7 +103,7 @@ TEST(DictTrieTest, UserDictWithMaxWeight) {
 }
 
 TEST(DictTrieTest, Dag) {
-  DictTrie trie(DICT_FILE, TEST_DATA_DIR "/userdict.utf8");
+  DictTrie trie(DICT_FILE, "../test/testdata/userdict.utf8");
 
   {
     string word = "清华大学";