来自：https://github.com/yanyiwu/cppjieba
更新子模块：
git submodule init git submodule update
引用目录：
E:\CPP\lib\04cppjieba\deps\limonp\include E:\CPP\lib\04cppjieba\include
#include <cppjieba/Jieba.hpp> using namespace std;
初始化结巴
QStringList fenci(QString title, bool isHmm = true);
//分词 子酱无圣光 true= (子酱, 无, 圣光) false= (子, 酱, 无, 圣光)
QStringList jjsoft::fenci(QString title, bool isHmm) {
if (jieba == nullptr)//结巴
{
auto dict = QApplication::applicationDirPath() + "/dict/";
const std::string DICT_PATH = QString(dict + "jieba.dict.utf8").toStdString();//最大概率法(MPSegment: Max Probability)分词所使用的词典路径
const std::string HMM_PATH = QString(dict + "hmm_model.utf8").toStdString();//隐式马尔科夫模型(HMMSegment: Hidden Markov Model)分词所使用的词典路径
const std::string USER_DICT_PATH = QString(dict + "user.dict.utf8").toStdString();//用户自定义词典路径
const std::string IDF_PATH = QString(dict + "idf.utf8").toStdString();//IDF路径
const std::string STOP_WORD_PATH = QString(dict + "stop_words.utf8").toStdString();//停用词路径
jieba = new cppjieba::Jieba(DICT_PATH, HMM_PATH, USER_DICT_PATH, IDF_PATH, STOP_WORD_PATH); //创建结巴对象
}
QStringList jg;
//创建结巴类
std::string s;
std::vector<std::string> words;//分词结果
s = title.toStdString();
//qDebug().noquote() << "结巴分词" << title;
jieba->Cut(s, words, isHmm); //标题，分隔保存位置，是否使用HMM切割
for (int i = 0; i < words.size(); i++)
{
jg << QString::fromStdString(words[i]);
}
return jg;
}分词示例：
cppjieba::Jieba jieba(DICT_PATH, HMM_PATH, USER_DICT_PATH, IDF_PATH, STOP_WORD_PATH);
vector<string> words;
vector<cppjieba::Word> jiebawords;
string s;
string result;
s = "他来到了网易杭研大厦";
qDebug().noquote() << "调试s " << QString::fromStdString(s);
qDebug().noquote() << "HMM切割";
jieba.Cut(s, words, true); //标题，分隔保存位置，是否使用HMM切割
for (int i = 0; i < words.size(); i++)
{
qDebug().noquote() << "调试" << QString::fromStdString(words[i]);
}分词方法：
//使用HMM切割
jieba.Cut(s, words, true);
//无HMM切割
jieba.Cut(s, words, false);
//全部剪切
jieba.CutAll(s, words);
//剪切以搜索
jieba.CutForSearch(s, words);
//剪切搜索带偏移量的单词
jieba.CutForSearch(s, jiebawords, true);
//插入用户单词
jieba.InsertUserWord("男默女泪");
//标签
vector<pair<string, string> > tagres;
jieba.Tag(s, tagres);
//关键字提取
const size_t topk = 5;
vector<cppjieba::KeywordExtractor::Word> keywordres;
jieba.extractor.Extract(s, keywordres, topk);
//单个令牌的查找标记
const int DemoTokenMaxLen = 32;
char DemoTokens[][DemoTokenMaxLen] = {"拖拉机", "CEO", "123", "。"};
vector<pair<string, string> > LookupTagres(sizeof(DemoTokens) / DemoTokenMaxLen);
vector<pair<string, string> >::iterator it;
for (it = LookupTagres.begin(); it != LookupTagres.end(); it++) {
it->first = DemoTokens[it - LookupTagres.begin()];
it->second = jieba.LookupTag(it->first);
}结果示例：
[demo] Cut With HMM
他/来到/了/网易/杭研/大厦
[demo] Cut Without HMM
他/来到/了/网易/杭/研/大厦
我来到北京清华大学
[demo] CutAll
我/来到/北京/清华/清华大学/华大/大学
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
[demo] CutForSearch
小明/硕士/毕业/于/中国/科学/学院/科学院/中国科学院/计算/计算所/，/后/在/日本/京都/大学/日本京都大学/深造
[demo] Insert User Word
男默/女泪
男默女泪
[demo] CutForSearch Word With Offset
[{"word": "小明", "offset": 0}, {"word": "硕士", "offset": 6}, {"word": "毕业", "offset": 12}, {"word": "于", "offset": 18}, {"word": "中国", "offset": 21}, {"word": "科学", "offset": 27}, {"word": "学院", "offset": 30}, {"word": "科学院", "offset": 27}, {"word": "中国科学院", "offset": 21}, {"word": "计算", "offset": 36}, {"word": "计算所", "offset": 36}, {"word": "，", "offset": 45}, {"word": "后", "offset": 48}, {"word": "在", "offset": 51}, {"word": "日本", "offset": 54}, {"word": "京都", "offset": 60}, {"word": "大学", "offset": 66}, {"word": "日本京都大学", "offset": 54}, {"word": "深造", "offset": 72}]
[demo] Tagging
我是拖拉机学院手扶拖拉机专业的。不用多久，我就会升职加薪，当上CEO，走上人生巅峰。
[我:r, 是:v, 拖拉机:n, 学院:n, 手扶拖拉机:n, 专业:n, 的:uj, 。:x, 不用:v, 多久:m, ，:x, 我:r, 就:d, 会:v, 升职:v, 加薪:nr, ，:x, 当上:t, CEO:eng, ，:x, 走上:v, 人生:n, 巅峰:n, 。:x]
[demo] Keyword Extraction
我是拖拉机学院手扶拖拉机专业的。不用多久，我就会升职加薪，当上CEO，走上人生巅峰。
[{"word": "CEO", "offset": [93], "weight": 11.7392}, {"word": "升职", "offset": [72], "weight": 10.8562}, {"word": "加薪", "offset": [78], "weight": 10.6426}, {"word": "手扶拖拉机", "offset": [21], "weight": 10.0089}, {"word": "巅峰", "offset": [111], "weight": 9.49396}]