build: refine CMakeLists.txt by removing unnecessary conditions and options

- Eliminated the default installation prefix condition to streamline the configuration.
- Simplified the test build logic by ensuring tests are enabled only for top-level projects.
- Cleaned up redundant code for better readability and maintainability.

.github/workflows/cmake-arm64.yml

@@ -0,0 +1,40 @@
+name: CMake Windows ARM64
+
+on:
+  push:
+  pull_request:
+  workflow_dispatch:  
+
+env:
+  BUILD_TYPE: Release
+
+jobs:
+  build-windows-arm64:
+    runs-on: windows-2022
+    strategy:
+      matrix:
+        cpp_version: [11, 14, 17, 20]
+
+    steps:
+      - name: Check out repository code
+        uses: actions/checkout@v2
+        with:
+            submodules: recursive
+
+      - name: Configure CMake
+        # Configure CMake in a 'build' subdirectory. `CMAKE_BUILD_TYPE` is only required if you are using a single-configuration generator such as make.
+        # See https://cmake.org/cmake/help/latest/variable/CMAKE_BUILD_TYPE.html?highlight=cmake_build_type
+        # run: cmake -B ${{github.workspace}}/build -DCMAKE_BUILD_TYPE=${{env.BUILD_TYPE}}
+        run: cmake -B ${{github.workspace}}/build -DBUILD_TESTING=ON -DCMAKE_CXX_STANDARD=${{matrix.cpp_version}} -DCMAKE_BUILD_TYPE=${{env.BUILD_TYPE}}
+
+      - name: Build
+        # Build your program with the given configuration
+        # run: cmake --build ${{github.workspace}}/build --config ${{env.BUILD_TYPE}}
+        run: cmake --build ${{github.workspace}}/build --config ${{env.BUILD_TYPE}}
+
+      - name: Test
+        working-directory: ${{github.workspace}}/build
+        # Execute tests defined by the CMake configuration.  
+        # See https://cmake.org/cmake/help/latest/manual/ctest.1.html for more detail
+        run: ctest -C ${{env.BUILD_TYPE}} --verbose
+      

.github/workflows/cmake.yml

@@ -17,13 +17,14 @@ jobs:
     strategy:
       matrix:
         os: [ 
-          ubuntu-20.04, 
           ubuntu-22.04,
-          macos-12,
+          ubuntu-latest,
           macos-13,
           macos-14,
+          macos-latest,
           windows-2019,
           windows-2022,
+          windows-latest,
         ]  
         cpp_version: [11, 14, 17, 20]
 
@@ -48,5 +49,5 @@ jobs:
         working-directory: ${{github.workspace}}/build
         # Execute tests defined by the CMake configuration.  
         # See https://cmake.org/cmake/help/latest/manual/ctest.1.html for more detail
-        run: ctest -C ${{env.BUILD_TYPE}}
+        run: ctest -C ${{env.BUILD_TYPE}} --verbose
       

.github/workflows/stale-issues.yml

@@ -2,7 +2,8 @@ name: Close Stale Issues
 
 on:
   schedule:
-    - cron: '0 0 * * 0'  # Run weekly on Sunday at midnight
+    - cron: '0 0 3 */3 *'  # Every three months on the 3rd day at midnight  
+
 
 jobs:
   stale:

.gitignore

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

CHANGELOG.md

@@ -1,5 +1,20 @@
 # CHANGELOG
 
+## v5.5.0
+
++ feat: add Windows ARM64 build support
++ build: upgrade googletest from 1.11.0 to 1.12.1
++ build: update CMake minimum version requirement to 3.10
++ fix: make namespaces explicit and fix missing includes
++ ci: update stale-issues workflow configuration
+
+## v5.4.0
+
++ unittest: class Jiaba add default argument input
++ class Jieba: support default dictpath
++ cmake: avoid testing when FetchContent by other project
++ class DictTrie: removed unused var
+
 ## v5.3.2
 
 + removed test/demo.cpp and linked https://github.com/yanyiwu/cppjieba-demo

CMakeLists.txt

@@ -1,25 +1,31 @@
-CMAKE_MINIMUM_REQUIRED (VERSION 3.5)
+CMAKE_MINIMUM_REQUIRED (VERSION 3.10)
 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()
 set(CMAKE_CXX_STANDARD_REQUIRED ON)
 set(CMAKE_CXX_EXTENSIONS OFF)
 
-ADD_DEFINITIONS(-O3 -Wall -g)
+ADD_DEFINITIONS(-O3 -g)
 
-ADD_SUBDIRECTORY(test)
+# Define a variable to check if this is the top-level project
+if(NOT DEFINED CPPJIEBA_TOP_LEVEL_PROJECT)
+    if(CMAKE_CURRENT_SOURCE_DIR STREQUAL CMAKE_SOURCE_DIR)
+        set(CPPJIEBA_TOP_LEVEL_PROJECT ON)
+    else()
+        set(CPPJIEBA_TOP_LEVEL_PROJECT OFF)
+    endif()
+endif()
 
-ENABLE_TESTING()
-if(NOT MSVC)
+if(CPPJIEBA_TOP_LEVEL_PROJECT)
+  ENABLE_TESTING()
+
+  message(STATUS "MSVC value: ${MSVC}")
+  ADD_SUBDIRECTORY(test)
   ADD_TEST(NAME ./test/test.run COMMAND ./test/test.run)
   ADD_TEST(NAME ./load_test COMMAND ./load_test)
 endif()

README.md

@@ -10,22 +10,25 @@
 
 CppJieba是"结巴(Jieba)"中文分词的C++版本
 
-## 特性
+### 主要特点
 
-+ 源代码都写进头文件`include/cppjieba/*.hpp`里，`include`即可使用。
-+ 支持`utf8`编码。
-+ 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。
-+ 支持载自定义用户词典，多路径时支持分隔符'|'或者';'分隔。
-+ 支持 `Linux` , `Mac OSX`, `Windows` 操作系统。
+- 🚀 高性能：经过线上环境验证的稳定性和性能表现
+- 📦 易集成：源代码以头文件形式提供 (`include/cppjieba/*.hpp`)，包含即可使用
+- 🔍 多种分词模式：支持精确模式、全模式、搜索引擎模式等
+- 📚 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）
+- 💻 跨平台：支持 Linux、macOS、Windows 操作系统
+- 🌈 UTF-8编码：原生支持 UTF-8 编码的中文处理
 
-## 用法
+## 快速开始
 
-### 依赖软件
+### 环境要求
 
-* `g++ (version >= 4.1 is recommended) or clang++`;
-* `cmake (version >= 2.6 is recommended)`;
+- C++ 编译器：
+  - g++ (推荐 4.1 以上版本)
+  - 或 clang++
+- cmake (推荐 2.6 以上版本)
 
-### 下载和编译
+### 安装步骤
 
 ```sh
 git clone https://github.com/yanyiwu/cppjieba.git
@@ -36,15 +39,11 @@ mkdir build
 cd build
 cmake ..
 make
-```
 
-有兴趣的可以跑跑测试(可选):
-
-```
 make test
 ```
 
-## Demo
+## 使用示例
 
 ```
 ./demo
@@ -210,71 +209,37 @@ For more details, please see [demo](https://github.com/yanyiwu/cppjieba-demo).
 
 + [dict.367W.utf8] iLife(562193561 at qq.com)
 
-## 应用
+## 生态系统
 
-+ [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。
+CppJieba 已经被广泛应用于各种编程语言的分词实现中：
 
-## 性能评测
+- [GoJieba](https://github.com/yanyiwu/gojieba) - Go 语言版本
+- [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
 
-[Jieba中文分词系列性能评测]
+### 应用项目
 
-## Sponsorship
+- [simhash](https://github.com/yanyiwu/simhash) - 中文文档相似度计算
+- [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
 
-[![sponsorship](http://images.gitads.io/cppjieba)](https://tracking.gitads.io/?campaign=gitads&repo=cppjieba&redirect=gitads.io)
+## 贡献指南
 
-## Contributors
+我们欢迎各种形式的贡献，包括但不限于：
 
-### Code Contributors
-
-This project exists thanks to all the people who contribute.
-<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
-[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
+- 提交问题和建议
+- 改进文档
+- 提交代码修复
+- 添加新功能
+
+
+如果您觉得 CppJieba 对您有帮助，欢迎 star ⭐️ 支持项目！
 
 

deps/limonp

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

dict/jieba.dict.utf8

@@ -312698,7 +312698,6 @@ 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

include/cppjieba/DictTrie.hpp

@@ -1,15 +1,15 @@
 #ifndef CPPJIEBA_DICT_TRIE_HPP
 #define CPPJIEBA_DICT_TRIE_HPP
 
-#include <iostream>
+#include <algorithm>
 #include <fstream>
-#include <map>
-#include <string>
 #include <cstring>
 #include <cstdlib>
-#include <stdint.h>
 #include <cmath>
-#include <limits>
+#include <deque>
+#include <set>
+#include <string>
+#include <unordered_set>
 #include "limonp/StringUtil.hpp"
 #include "limonp/Logging.hpp"
 #include "Unicode.hpp"
@@ -17,8 +17,6 @@
 
 namespace cppjieba {
 
-using namespace limonp;
-
 const double MIN_DOUBLE = -3.14e+100;
 const double MAX_DOUBLE = 3.14e+100;
 const size_t DICT_COLUMN_NUM = 3;
@@ -32,7 +30,7 @@ class DictTrie {
     WordWeightMax,
   }; // enum UserWordWeightOption
 
-  DictTrie(const string& dict_path, const string& user_dict_paths = "", UserWordWeightOption user_word_weight_opt = WordWeightMedian) {
+  DictTrie(const std::string& dict_path, const std::string& user_dict_paths = "", UserWordWeightOption user_word_weight_opt = WordWeightMedian) {
     Init(dict_path, user_dict_paths, user_word_weight_opt);
   }
 
@@ -40,7 +38,7 @@ class DictTrie {
     delete trie_;
   }
 
-  bool InsertUserWord(const string& word, const string& tag = UNKNOWN_TAG) {
+  bool InsertUserWord(const std::string& word, const std::string& tag = UNKNOWN_TAG) {
     DictUnit node_info;
     if (!MakeNodeInfo(node_info, word, user_word_default_weight_, tag)) {
       return false;
@@ -50,7 +48,7 @@ class DictTrie {
     return true;
   }
 
-  bool InsertUserWord(const string& word,int freq, const string& tag = UNKNOWN_TAG) {
+  bool InsertUserWord(const std::string& word,int freq, const std::string& tag = UNKNOWN_TAG) {
     DictUnit node_info;
     double weight = freq ? log(1.0 * freq / freq_sum_) : user_word_default_weight_ ;
     if (!MakeNodeInfo(node_info, word, weight , tag)) {
@@ -61,7 +59,7 @@ class DictTrie {
     return true;
   }
 
-  bool DeleteUserWord(const string& word, const string& tag = UNKNOWN_TAG) {
+  bool DeleteUserWord(const std::string& word, const std::string& tag = UNKNOWN_TAG) {
     DictUnit node_info;
     if (!MakeNodeInfo(node_info, word, user_word_default_weight_, tag)) {
       return false;
@@ -76,16 +74,16 @@ class DictTrie {
 
   void Find(RuneStrArray::const_iterator begin,
         RuneStrArray::const_iterator end,
-        vector<struct Dag>&res,
+        std::vector<struct Dag>&res,
         size_t max_word_len = MAX_WORD_LENGTH) const {
     trie_->Find(begin, end, res, max_word_len);
   }
 
-  bool Find(const string& word)
+  bool Find(const std::string& word)
   {
     const DictUnit *tmp = NULL;
     RuneStrArray runes;
-    if (!DecodeRunesInString(word, runes))
+    if (!DecodeUTF8RunesInString(word, runes))
     {
       XLOG(ERROR) << "Decode failed.";
     }
@@ -108,10 +106,10 @@ class DictTrie {
     return min_weight_;
   }
 
-  void InserUserDictNode(const string& line) {
-    vector<string> buf;
+  void InserUserDictNode(const std::string& line) {
+    std::vector<std::string> buf;
     DictUnit node_info;
-    Split(line, buf, " ");
+    limonp::Split(line, buf, " ");
     if(buf.size() == 1){
           MakeNodeInfo(node_info,
                 buf[0],
@@ -134,28 +132,27 @@ class DictTrie {
         }
   }
 
-  void LoadUserDict(const vector<string>& buf) {
+  void LoadUserDict(const std::vector<std::string>& buf) {
     for (size_t i = 0; i < buf.size(); i++) {
       InserUserDictNode(buf[i]);
     }
   }
 
-   void LoadUserDict(const set<string>& buf) {
-    std::set<string>::const_iterator iter;
+   void LoadUserDict(const std::set<std::string>& buf) {
+    std::set<std::string>::const_iterator iter;
     for (iter = buf.begin(); iter != buf.end(); iter++){
       InserUserDictNode(*iter);
     }
   }
 
-  void LoadUserDict(const string& filePaths) {
-    vector<string> files = limonp::Split(filePaths, "|;");
-    size_t lineno = 0;
+  void LoadUserDict(const std::string& filePaths) {
+    std::vector<std::string> files = limonp::Split(filePaths, "|;");
     for (size_t i = 0; i < files.size(); i++) {
-      ifstream ifs(files[i].c_str());
+      std::ifstream ifs(files[i].c_str());
       XCHECK(ifs.is_open()) << "open " << files[i] << " failed";
-      string line;
+      std::string line;
 
-      for (; getline(ifs, line); lineno++) {
+      while(getline(ifs, line)) {
         if (line.size() == 0) {
           continue;
         }
@@ -166,7 +163,7 @@ class DictTrie {
 
 
  private:
-  void Init(const string& dict_path, const string& user_dict_paths, UserWordWeightOption user_word_weight_opt) {
+  void Init(const std::string& dict_path, const std::string& user_dict_paths, UserWordWeightOption user_word_weight_opt) {
     LoadDict(dict_path);
     freq_sum_ = CalcFreqSum(static_node_infos_);
     CalculateWeight(static_node_infos_, freq_sum_);
@@ -179,10 +176,10 @@ class DictTrie {
     CreateTrie(static_node_infos_);
   }
 
-  void CreateTrie(const vector<DictUnit>& dictUnits) {
+  void CreateTrie(const std::vector<DictUnit>& dictUnits) {
     assert(dictUnits.size());
-    vector<Unicode> words;
-    vector<const DictUnit*> valuePointers;
+    std::vector<Unicode> words;
+    std::vector<const DictUnit*> valuePointers;
     for (size_t i = 0 ; i < dictUnits.size(); i ++) {
       words.push_back(dictUnits[i].word);
       valuePointers.push_back(&dictUnits[i]);
@@ -191,15 +188,12 @@ class DictTrie {
     trie_ = new Trie(words, valuePointers);
   }
 
-  
-
-
   bool MakeNodeInfo(DictUnit& node_info,
-        const string& word, 
+        const std::string& word,
         double weight,
-        const string& tag) {
-    if (!DecodeRunesInString(word, node_info.word)) {
-      XLOG(ERROR) << "Decode " << word << " failed.";
+        const std::string& tag) {
+    if (!DecodeUTF8RunesInString(word, node_info.word)) {
+      XLOG(ERROR) << "UTF-8 decode failed for dict word: " << word;
       return false;
     }
     node_info.weight = weight;
@@ -207,15 +201,15 @@ class DictTrie {
     return true;
   }
 
-  void LoadDict(const string& filePath) {
-    ifstream ifs(filePath.c_str());
+  void LoadDict(const std::string& filePath) {
+    std::ifstream ifs(filePath.c_str());
     XCHECK(ifs.is_open()) << "open " << filePath << " failed.";
-    string line;
-    vector<string> buf;
+    std::string line;
+    std::vector<std::string> buf;
 
     DictUnit node_info;
-    for (size_t lineno = 0; getline(ifs, line); lineno++) {
-      Split(line, buf, " ");
+    while (getline(ifs, line)) {
+      limonp::Split(line, buf, " ");
       XCHECK(buf.size() == DICT_COLUMN_NUM) << "split result illegal, line:" << line;
       MakeNodeInfo(node_info,
             buf[0],
@@ -231,8 +225,8 @@ class DictTrie {
 
   void SetStaticWordWeights(UserWordWeightOption option) {
     XCHECK(!static_node_infos_.empty());
-    vector<DictUnit> x = static_node_infos_;
-    sort(x.begin(), x.end(), WeightCompare);
+    std::vector<DictUnit> x = static_node_infos_;
+    std::sort(x.begin(), x.end(), WeightCompare);
     min_weight_ = x[0].weight;
     max_weight_ = x[x.size() - 1].weight;
     median_weight_ = x[x.size() / 2].weight;
@@ -249,7 +243,7 @@ class DictTrie {
     }
   }
 
-  double CalcFreqSum(const vector<DictUnit>& node_infos) const {
+  double CalcFreqSum(const std::vector<DictUnit>& node_infos) const {
     double sum = 0.0;
     for (size_t i = 0; i < node_infos.size(); i++) {
       sum += node_infos[i].weight;
@@ -257,7 +251,7 @@ class DictTrie {
     return sum;
   }
 
-  void CalculateWeight(vector<DictUnit>& node_infos, double sum) const {
+  void CalculateWeight(std::vector<DictUnit>& node_infos, double sum) const {
     assert(sum > 0.0);
     for (size_t i = 0; i < node_infos.size(); i++) {
       DictUnit& node_info = node_infos[i];
@@ -266,12 +260,12 @@ class DictTrie {
     }
   }
 
-  void Shrink(vector<DictUnit>& units) const {
-    vector<DictUnit>(units.begin(), units.end()).swap(units);
+  void Shrink(std::vector<DictUnit>& units) const {
+    std::vector<DictUnit>(units.begin(), units.end()).swap(units);
   }
 
-  vector<DictUnit> static_node_infos_;
-  deque<DictUnit> active_node_infos_; // must not be vector
+  std::vector<DictUnit> static_node_infos_;
+  std::deque<DictUnit> active_node_infos_; // must not be std::vector
   Trie * trie_;
 
   double freq_sum_;
@@ -279,7 +273,7 @@ class DictTrie {
   double max_weight_;
   double median_weight_;
   double user_word_default_weight_;
-  unordered_set<Rune> user_dict_single_chinese_word_;
+  std::unordered_set<Rune> user_dict_single_chinese_word_;
 };
 }
 

include/cppjieba/HMMModel.hpp

@@ -105,7 +105,7 @@ struct HMMModel {
         XLOG(ERROR) << "emitProb illegal.";
         return false;
       }
-      if (!DecodeRunesInString(tmp2[0], unicode) || unicode.size() != 1) {
+      if (!DecodeUTF8RunesInString(tmp2[0], unicode) || unicode.size() != 1) {
         XLOG(ERROR) << "TransCode failed.";
         return false;
       }

include/cppjieba/Jieba.hpp

@@ -8,19 +8,21 @@ namespace cppjieba {
 
 class Jieba {
  public:
-  Jieba(const string& dict_path, 
-        const string& model_path,
-        const string& user_dict_path, 
-        const string& idfPath, 
-        const string& stopWordPath) 
-    : dict_trie_(dict_path, user_dict_path),
-      model_(model_path),
+  Jieba(const string& dict_path = "", 
+        const string& model_path = "",
+        const string& user_dict_path = "", 
+        const string& idf_path = "", 
+        const string& stop_word_path = "") 
+    : dict_trie_(getPath(dict_path, "jieba.dict.utf8"), getPath(user_dict_path, "user.dict.utf8")),
+      model_(getPath(model_path, "hmm_model.utf8")),
       mp_seg_(&dict_trie_),
       hmm_seg_(&model_),
       mix_seg_(&dict_trie_, &model_),
       full_seg_(&dict_trie_),
       query_seg_(&dict_trie_, &model_),
-      extractor(&dict_trie_, &model_, idfPath, stopWordPath) {
+      extractor(&dict_trie_, &model_, 
+                getPath(idf_path, "idf.utf8"), 
+                getPath(stop_word_path, "stop_words.utf8")) {
   }
   ~Jieba() {
   }
@@ -115,6 +117,39 @@ class Jieba {
   }
 
  private:
+  static string pathJoin(const string& dir, const string& filename) {
+    if (dir.empty()) {
+        return filename;
+    }
+    
+    char last_char = dir[dir.length() - 1];
+    if (last_char == '/' || last_char == '\\') {
+        return dir + filename;
+    } else {
+        #ifdef _WIN32
+        return dir + '\\' + filename;
+        #else
+        return dir + '/' + filename;
+        #endif
+    }
+  }
+
+  static string getCurrentDirectory() {
+    string path(__FILE__);
+    size_t pos = path.find_last_of("/\\");
+    return (pos == string::npos) ? "" : path.substr(0, pos);
+  }
+
+  static string getPath(const string& path, const string& default_file) {
+    if (path.empty()) {
+      string current_dir = getCurrentDirectory();
+      string parent_dir = current_dir.substr(0, current_dir.find_last_of("/\\"));
+      string grandparent_dir = parent_dir.substr(0, parent_dir.find_last_of("/\\"));
+      return pathJoin(pathJoin(grandparent_dir, "dict"), default_file);
+    }
+    return path;
+  }
+
   DictTrie dict_trie_;
   HMMModel model_;
   

include/cppjieba/KeywordExtractor.hpp

@@ -1,37 +1,35 @@
 #ifndef CPPJIEBA_KEYWORD_EXTRACTOR_H
 #define CPPJIEBA_KEYWORD_EXTRACTOR_H
 
-#include <cmath>
-#include <set>
+#include <algorithm>
+#include <unordered_map>
+#include <unordered_set>
 #include "MixSegment.hpp"
 
 namespace cppjieba {
 
-using namespace limonp;
-using namespace std;
-
 /*utf8*/
 class KeywordExtractor {
  public:
   struct Word {
-    string word;
-    vector<size_t> offsets;
+    std::string word;
+    std::vector<size_t> offsets;
     double weight;
   }; // struct Word
 
-  KeywordExtractor(const string& dictPath, 
-        const string& hmmFilePath, 
-        const string& idfPath, 
-        const string& stopWordPath, 
-        const string& userDict = "") 
+  KeywordExtractor(const std::string& dictPath, 
+        const std::string& hmmFilePath, 
+        const std::string& idfPath, 
+        const std::string& stopWordPath, 
+        const std::string& userDict = "") 
     : segment_(dictPath, hmmFilePath, userDict) {
     LoadIdfDict(idfPath);
     LoadStopWordDict(stopWordPath);
   }
   KeywordExtractor(const DictTrie* dictTrie, 
         const HMMModel* model,
-        const string& idfPath, 
-        const string& stopWordPath) 
+        const std::string& idfPath, 
+        const std::string& stopWordPath) 
     : segment_(dictTrie, model) {
     LoadIdfDict(idfPath);
     LoadStopWordDict(stopWordPath);
@@ -39,27 +37,27 @@ class KeywordExtractor {
   ~KeywordExtractor() {
   }
 
-  void Extract(const string& sentence, vector<string>& keywords, size_t topN) const {
-    vector<Word> topWords;
+  void Extract(const std::string& sentence, std::vector<std::string>& keywords, size_t topN) const {
+    std::vector<Word> topWords;
     Extract(sentence, topWords, topN);
     for (size_t i = 0; i < topWords.size(); i++) {
       keywords.push_back(topWords[i].word);
     }
   }
 
-  void Extract(const string& sentence, vector<pair<string, double> >& keywords, size_t topN) const {
-    vector<Word> topWords;
+  void Extract(const std::string& sentence, std::vector<pair<std::string, double> >& keywords, size_t topN) const {
+    std::vector<Word> topWords;
     Extract(sentence, topWords, topN);
     for (size_t i = 0; i < topWords.size(); i++) {
-      keywords.push_back(pair<string, double>(topWords[i].word, topWords[i].weight));
+      keywords.push_back(pair<std::string, double>(topWords[i].word, topWords[i].weight));
     }
   }
 
-  void Extract(const string& sentence, vector<Word>& keywords, size_t topN) const {
-    vector<string> words;
+  void Extract(const std::string& sentence, std::vector<Word>& keywords, size_t topN) const {
+    std::vector<std::string> words;
     segment_.Cut(sentence, words);
 
-    map<string, Word> wordmap;
+    std::map<std::string, Word> wordmap;
     size_t offset = 0;
     for (size_t i = 0; i < words.size(); ++i) {
       size_t t = offset;
@@ -77,8 +75,8 @@ class KeywordExtractor {
 
     keywords.clear();
     keywords.reserve(wordmap.size());
-    for (map<string, Word>::iterator itr = wordmap.begin(); itr != wordmap.end(); ++itr) {
-      unordered_map<string, double>::const_iterator cit = idfMap_.find(itr->first);
+    for (std::map<std::string, Word>::iterator itr = wordmap.begin(); itr != wordmap.end(); ++itr) {
+      std::unordered_map<std::string, double>::const_iterator cit = idfMap_.find(itr->first);
       if (cit != idfMap_.end()) {
         itr->second.weight *= cit->second;
       } else {
@@ -88,15 +86,15 @@ class KeywordExtractor {
       keywords.push_back(itr->second);
     }
     topN = min(topN, keywords.size());
-    partial_sort(keywords.begin(), keywords.begin() + topN, keywords.end(), Compare);
+    std::partial_sort(keywords.begin(), keywords.begin() + topN, keywords.end(), Compare);
     keywords.resize(topN);
   }
  private:
-  void LoadIdfDict(const string& idfPath) {
-    ifstream ifs(idfPath.c_str());
+  void LoadIdfDict(const std::string& idfPath) {
+    std::ifstream ifs(idfPath.c_str());
     XCHECK(ifs.is_open()) << "open " << idfPath << " failed";
-    string line ;
-    vector<string> buf;
+    std::string line ;
+    std::vector<std::string> buf;
     double idf = 0.0;
     double idfSum = 0.0;
     size_t lineno = 0;
@@ -106,7 +104,7 @@ class KeywordExtractor {
         XLOG(ERROR) << "lineno: " << lineno << " empty. skipped.";
         continue;
       }
-      Split(line, buf, " ");
+      limonp::Split(line, buf, " ");
       if (buf.size() != 2) {
         XLOG(ERROR) << "line: " << line << ", lineno: " << lineno << " empty. skipped.";
         continue;
@@ -121,10 +119,10 @@ class KeywordExtractor {
     idfAverage_ = idfSum / lineno;
     assert(idfAverage_ > 0.0);
   }
-  void LoadStopWordDict(const string& filePath) {
-    ifstream ifs(filePath.c_str());
+  void LoadStopWordDict(const std::string& filePath) {
+    std::ifstream ifs(filePath.c_str());
     XCHECK(ifs.is_open()) << "open " << filePath << " failed";
-    string line ;
+    std::string line ;
     while (getline(ifs, line)) {
       stopWords_.insert(line);
     }
@@ -136,18 +134,16 @@ class KeywordExtractor {
   }
 
   MixSegment segment_;
-  unordered_map<string, double> idfMap_;
+  std::unordered_map<std::string, double> idfMap_;
   double idfAverage_;
 
-  unordered_set<string> stopWords_;
+  std::unordered_set<std::string> stopWords_;
 }; // class KeywordExtractor
 
-inline ostream& operator << (ostream& os, const KeywordExtractor::Word& word) {
+inline std::ostream& operator << (std::ostream& os, const KeywordExtractor::Word& word) {
   return os << "{\"word\": \"" << word.word << "\", \"offset\": " << word.offsets << ", \"weight\": " << word.weight << "}"; 
 }
 
 } // namespace cppjieba
 
 #endif
-
-

include/cppjieba/PosTagger.hpp

@@ -34,8 +34,8 @@ class PosTagger {
     RuneStrArray runes;
     const DictTrie * dict = segment.GetDictTrie();
     assert(dict != NULL);
-      if (!DecodeRunesInString(str, runes)) {
-        XLOG(ERROR) << "Decode failed.";
+      if (!DecodeUTF8RunesInString(str, runes)) {
+        XLOG(ERROR) << "UTF-8 decode failed for word: " << str;
         return POS_X;
       }
       tmp = dict->Find(runes.begin(), runes.end());

include/cppjieba/PreFilter.hpp

@@ -17,8 +17,8 @@ class PreFilter {
   PreFilter(const unordered_set<Rune>& symbols, 
         const string& sentence)
     : symbols_(symbols) {
-    if (!DecodeRunesInString(sentence, sentence_)) {
-      XLOG(ERROR) << "decode failed. "; 
+    if (!DecodeUTF8RunesInString(sentence, sentence_)) {
+      XLOG(ERROR) << "UTF-8 decode failed for input sentence"; 
     }
     cursor_ = sentence_.begin();
   }

include/cppjieba/SegmentBase.hpp

@@ -25,8 +25,8 @@ class SegmentBase {
   bool ResetSeparators(const string& s) {
     symbols_.clear();
     RuneStrArray runes;
-    if (!DecodeRunesInString(s, runes)) {
-      XLOG(ERROR) << "decode " << s << " failed";
+    if (!DecodeUTF8RunesInString(s, runes)) {
+      XLOG(ERROR) << "UTF-8 decode failed for separators: " << s;
       return false;
     }
     for (size_t i = 0; i < runes.size(); i++) {

include/cppjieba/Unicode.hpp

@@ -84,7 +84,7 @@ struct RuneStrLite {
   }
 }; // struct RuneStrLite
 
-inline RuneStrLite DecodeRuneInString(const char* str, size_t len) {
+inline RuneStrLite DecodeUTF8ToRune(const char* str, size_t len) {
   RuneStrLite rp(0, 0);
   if (str == NULL || len == 0) {
     return rp;
@@ -139,11 +139,11 @@ inline RuneStrLite DecodeRuneInString(const char* str, size_t len) {
   return rp;
 }
 
-inline bool DecodeRunesInString(const char* s, size_t len, RuneStrArray& runes) {
+inline bool DecodeUTF8RunesInString(const char* s, size_t len, RuneStrArray& runes) {
   runes.clear();
   runes.reserve(len / 2);
   for (uint32_t i = 0, j = 0; i < len;) {
-    RuneStrLite rp = DecodeRuneInString(s + i, len - i);
+    RuneStrLite rp = DecodeUTF8ToRune(s + i, len - i);
     if (rp.len == 0) {
       runes.clear();
       return false;
@@ -156,14 +156,14 @@ inline bool DecodeRunesInString(const char* s, size_t len, RuneStrArray& runes)
   return true;
 }
 
-inline bool DecodeRunesInString(const string& s, RuneStrArray& runes) {
-  return DecodeRunesInString(s.c_str(), s.size(), runes);
+inline bool DecodeUTF8RunesInString(const string& s, RuneStrArray& runes) {
+  return DecodeUTF8RunesInString(s.c_str(), s.size(), runes);
 }
 
-inline bool DecodeRunesInString(const char* s, size_t len, Unicode& unicode) {
+inline bool DecodeUTF8RunesInString(const char* s, size_t len, Unicode& unicode) {
   unicode.clear();
   RuneStrArray runes;
-  if (!DecodeRunesInString(s, len, runes)) {
+  if (!DecodeUTF8RunesInString(s, len, runes)) {
     return false;
   }
   unicode.reserve(runes.size());
@@ -174,17 +174,17 @@ inline bool DecodeRunesInString(const char* s, size_t len, Unicode& unicode) {
 }
 
 inline bool IsSingleWord(const string& str) {
-  RuneStrLite rp = DecodeRuneInString(str.c_str(), str.size());
+  RuneStrLite rp = DecodeUTF8ToRune(str.c_str(), str.size());
   return rp.len == str.size();
 }
 
-inline bool DecodeRunesInString(const string& s, Unicode& unicode) {
-  return DecodeRunesInString(s.c_str(), s.size(), unicode);
+inline bool DecodeUTF8RunesInString(const string& s, Unicode& unicode) {
+  return DecodeUTF8RunesInString(s.c_str(), s.size(), unicode);
 }
 
-inline Unicode DecodeRunesInString(const string& s) {
+inline Unicode DecodeUTF8RunesInString(const string& s) {
   Unicode result;
-  DecodeRunesInString(s, result);
+  DecodeUTF8RunesInString(s, result);
   return result;
 }
 

test/CMakeLists.txt

@@ -1,6 +1,12 @@
 SET(EXECUTABLE_OUTPUT_PATH ${PROJECT_BINARY_DIR})
 
-if(NOT MSVC)
-	ADD_EXECUTABLE(load_test load_test.cpp)
-	ADD_SUBDIRECTORY(unittest)
-endif()
+# 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

@@ -6,14 +6,15 @@
 #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/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 +30,13 @@ 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();

test/test_paths.h.in

@@ -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 

test/unittest/CMakeLists.txt

@@ -1,6 +1,8 @@
+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)
@@ -8,7 +10,7 @@ include(FetchContent)
 FetchContent_Declare(
   googletest
   GIT_REPOSITORY https://github.com/google/googletest.git
-  GIT_TAG release-1.11.0
+  GIT_TAG release-1.12.1
 )
 FetchContent_MakeAvailable(googletest)
 
@@ -18,6 +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 

test/unittest/jieba_test.cpp

@@ -1,14 +1,11 @@
 #include "cppjieba/Jieba.hpp"
 #include "gtest/gtest.h"
+#include "test_paths.h"
 
 using namespace cppjieba;
 
-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");
+TEST(JiebaTest, Test0) {
+  cppjieba::Jieba jieba;
   vector<string> words;
   string result;
 
@@ -38,14 +35,51 @@ 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, Test1) {
+  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;
+
+  jieba.Cut("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);
+
+  jieba.Cut("我来自北京邮电大学。", words, false);
+  result << words;
+  ASSERT_EQ("[\"我\", \"来自\", \"北京邮电大学\", \"。\"]", result);
+
+  jieba.CutSmall("南京市长江大桥", words, 3);
+  ASSERT_EQ("[\"南京市\", \"长江\", \"大桥\"]", result << words);
+
+  jieba.CutHMM("我来自北京邮电大学。。。学号123456", words);
+  result << words;
+  ASSERT_EQ("[\"我来\", \"自北京\", \"邮电大学\", \"。\", \"。\", \"。\", \"学号\", \"123456\"]", result);
+
+  jieba.Cut("我来自北京邮电大学。。。学号123456，用AK47", words);
+  result << words;
+  ASSERT_EQ("[\"我\", \"来自\", \"北京邮电大学\", \"。\", \"。\", \"。\", \"学号\", \"123456\", \"，\", \"用\", \"AK47\"]", result);
+
+  jieba.CutAll("我来自北京邮电大学", words);
+  result << words;
+  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\"]");
+
+  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;
 
@@ -83,11 +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;
 

test/unittest/keyword_extractor_test.cpp

@@ -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");

test/unittest/pos_tagger_test.cpp

@@ -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);

test/unittest/segments_test.cpp

@@ -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/。");

test/unittest/textrank_test.cpp

@@ -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");

test/unittest/trie_test.cpp

@@ -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;
@@ -15,7 +16,7 @@ TEST(TrieTest, Empty) {
 TEST(TrieTest, Construct) {
   vector<Unicode> keys;
   vector<const DictUnit*> values;
-  keys.push_back(DecodeRunesInString("你"));
+  keys.push_back(DecodeUTF8RunesInString("你"));
   values.push_back((const DictUnit*)(NULL));
   Trie trie(keys, values);
 }
@@ -32,13 +33,7 @@ TEST(DictTrieTest, Test1) {
   ASSERT_LT(trie.GetMinWeight() + 15.6479, 0.001);
   string word("来到");
   cppjieba::RuneStrArray uni;
-  ASSERT_TRUE(DecodeRunesInString(word, uni));
-  //DictUnit nodeInfo;
-  //nodeInfo.word = uni;
-  //nodeInfo.tag = "v";
-  //nodeInfo.weight = -8.87033;
-  //s1 << nodeInfo;
-  //s2 << (*trie.Find(uni.begin(), uni.end()));
+  ASSERT_TRUE(DecodeUTF8RunesInString(word, uni));
   const DictUnit* du = trie.Find(uni.begin(), uni.end());
   ASSERT_TRUE(du != NULL);
   ASSERT_EQ(2u, du->word.size());
@@ -47,45 +42,42 @@ 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(DecodeRunesInString(words[i], uni));
+    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;
-  ASSERT_TRUE(DecodeRunesInString(word, uni));
+  ASSERT_TRUE(DecodeUTF8RunesInString(word, uni));
   trie.Find(uni.begin(), uni.end(), dags);
   ASSERT_EQ(dags.size(), uni.size());
   ASSERT_NE(dags.size(), 0u);
   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(DecodeRunesInString(word, unicode));
+  ASSERT_TRUE(DecodeUTF8RunesInString(word, unicode));
   const DictUnit * unit = trie.Find(unicode.begin(), unicode.end());
   ASSERT_TRUE(unit != NULL);
   ASSERT_NEAR(unit->weight, -14.100, 0.001);
 
   word = "蓝翔";
-  ASSERT_TRUE(DecodeRunesInString(word, unicode));
+  ASSERT_TRUE(DecodeUTF8RunesInString(word, unicode));
   unit = trie.Find(unicode.begin(), unicode.end());
   ASSERT_TRUE(unit != NULL);
   ASSERT_EQ(unit->tag, "nz");
   ASSERT_NEAR(unit->weight, -14.100, 0.001);
 
   word = "区块链";
-  ASSERT_TRUE(DecodeRunesInString(word, unicode));
+  ASSERT_TRUE(DecodeUTF8RunesInString(word, unicode));
   unit = trie.Find(unicode.begin(), unicode.end());
   ASSERT_TRUE(unit != NULL);
   ASSERT_EQ(unit->tag, "nz");
@@ -93,22 +85,22 @@ 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(DecodeRunesInString(word, unicode));
+  ASSERT_TRUE(DecodeUTF8RunesInString(word, unicode));
   const DictUnit * unit = trie.Find(unicode.begin(), unicode.end());
   ASSERT_TRUE(unit);
   ASSERT_NEAR(unit->weight, -2.975, 0.001);
 }
 
 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";
     cppjieba::RuneStrArray unicode;
-    ASSERT_TRUE(DecodeRunesInString(word, unicode));
+    ASSERT_TRUE(DecodeUTF8RunesInString(word, unicode));
     vector<struct Dag> res;
     trie.Find(unicode.begin(), unicode.end(), res);
 
@@ -122,7 +114,7 @@ TEST(DictTrieTest, Dag) {
   {
     string word = "北京邮电大学";
     cppjieba::RuneStrArray unicode;
-    ASSERT_TRUE(DecodeRunesInString(word, unicode));
+    ASSERT_TRUE(DecodeUTF8RunesInString(word, unicode));
     vector<struct Dag> res;
     trie.Find(unicode.begin(), unicode.end(), res);
 
@@ -136,7 +128,7 @@ TEST(DictTrieTest, Dag) {
   {
     string word = "长江大桥";
     cppjieba::RuneStrArray unicode;
-    ASSERT_TRUE(DecodeRunesInString(word, unicode));
+    ASSERT_TRUE(DecodeUTF8RunesInString(word, unicode));
     vector<struct Dag> res;
     trie.Find(unicode.begin(), unicode.end(), res);
 
@@ -150,7 +142,7 @@ TEST(DictTrieTest, Dag) {
   {
     string word = "长江大桥";
     cppjieba::RuneStrArray unicode;
-    ASSERT_TRUE(DecodeRunesInString(word, unicode));
+    ASSERT_TRUE(DecodeUTF8RunesInString(word, unicode));
     vector<struct Dag> res;
     trie.Find(unicode.begin(), unicode.end(), res, 3);
 
@@ -164,7 +156,7 @@ TEST(DictTrieTest, Dag) {
   {
     string word = "长江大桥";
     cppjieba::RuneStrArray unicode;
-    ASSERT_TRUE(DecodeRunesInString(word, unicode));
+    ASSERT_TRUE(DecodeUTF8RunesInString(word, unicode));
     vector<struct Dag> res;
     trie.Find(unicode.begin(), unicode.end(), res, 4);
 

test/unittest/unicode_test.cpp

@@ -8,7 +8,7 @@ using namespace std;
 TEST(UnicodeTest, Test1) {
   string s = "你好世界";
   RuneStrArray runes;
-  ASSERT_TRUE(DecodeRunesInString(s, runes));
+  ASSERT_TRUE(DecodeUTF8RunesInString(s, runes));
   string actual;
   string expected = "[\"{\"rune\": \"20320\", \"offset\": 0, \"len\": 3}\", \"{\"rune\": \"22909\", \"offset\": 3, \"len\": 3}\", \"{\"rune\": \"19990\", \"offset\": 6, \"len\": 3}\", \"{\"rune\": \"30028\", \"offset\": 9, \"len\": 3}\"]";
   actual << runes;
@@ -18,7 +18,7 @@ TEST(UnicodeTest, Test1) {
 TEST(UnicodeTest, Illegal) {
   string s = "123\x80";
   RuneStrArray runes;
-  ASSERT_FALSE(DecodeRunesInString(s, runes));
+  ASSERT_FALSE(DecodeUTF8RunesInString(s, runes));
   string actual;
   string expected = "[]";
   actual << runes;
@@ -38,6 +38,6 @@ TEST(UnicodeTest, Rand) {
       s[rand() % len] = rand();
     }
     RuneStrArray runes;
-    DecodeRunesInString(s, runes);
+    DecodeUTF8RunesInString(s, runes);
   }
 }