mirror of
https://github.com/yanyiwu/cppjieba.git
synced 2025-07-18 00:00:12 +08:00
73 lines
2.4 KiB
C++
73 lines
2.4 KiB
C++
#include "cppjieba/Jieba.hpp"
|
||
#include "cppjieba/KeywordExtractor.hpp"
|
||
|
||
using namespace std;
|
||
|
||
const char* const DICT_PATH = "../dict/jieba.dict.utf8";
|
||
const char* const HMM_PATH = "../dict/hmm_model.utf8";
|
||
const char* const USER_DICT_PATH = "../dict/user.dict.utf8";
|
||
const char* const IDF_PATH = "../dict/idf.utf8";
|
||
const char* const STOP_WORD_PATH = "../dict/stop_words.utf8";
|
||
|
||
int main(int argc, char** argv) {
|
||
cppjieba::Jieba jieba(DICT_PATH,
|
||
HMM_PATH,
|
||
USER_DICT_PATH);
|
||
vector<string> words;
|
||
string result;
|
||
string s = "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。";
|
||
|
||
cout << "[demo] Cut With HMM" << endl;
|
||
jieba.Cut(s, words, true);
|
||
cout << limonp::Join(words.begin(), words.end(), "/") << endl;
|
||
|
||
cout << "[demo] Cut Without HMM " << endl;
|
||
jieba.Cut(s, words, false);
|
||
cout << limonp::Join(words.begin(), words.end(), "/") << endl;
|
||
|
||
cout << "[demo] CutAll" << endl;
|
||
jieba.CutAll(s, words);
|
||
cout << limonp::Join(words.begin(), words.end(), "/") << endl;
|
||
|
||
cout << "[demo] CutForSearch" << endl;
|
||
jieba.CutForSearch(s, words);
|
||
cout << limonp::Join(words.begin(), words.end(), "/") << endl;
|
||
|
||
cout << "[demo] Insert User Word" << endl;
|
||
jieba.Cut("男默女泪", words);
|
||
cout << limonp::Join(words.begin(), words.end(), "/") << endl;
|
||
jieba.InsertUserWord("男默女泪");
|
||
jieba.Cut("男默女泪", words);
|
||
cout << limonp::Join(words.begin(), words.end(), "/") << endl;
|
||
|
||
//cout << "[demo] Locate Words" << endl;
|
||
//vector<cppjieba::Jieba::LocWord> loc_words;
|
||
//jieba.Cut("南京市长江大桥", words, true);
|
||
//cppjieba::Jieba::Locate(words, loc_words);
|
||
//for (size_t i = 0; i < loc_words.size(); i++) {
|
||
// cout << loc_words[i].word
|
||
// << ", " << loc_words[i].begin
|
||
// << ", " << loc_words[i].end
|
||
// << endl;
|
||
//}
|
||
|
||
cout << "[demo] TAGGING" << endl;
|
||
vector<pair<string, string> > tagres;
|
||
jieba.Tag(s, tagres);
|
||
cout << s << endl;
|
||
cout << tagres << endl;;
|
||
|
||
cppjieba::KeywordExtractor extractor(jieba,
|
||
IDF_PATH,
|
||
STOP_WORD_PATH);
|
||
cout << "[demo] KEYWORD" << endl;
|
||
const size_t topk = 5;
|
||
vector<cppjieba::KeywordExtractor::Word> keywordres;
|
||
extractor.Extract(s, keywordres, topk);
|
||
cout << s << endl;
|
||
for (size_t i = 0; i < keywordres.size(); ++i) {
|
||
cout << keywordres[i].word << "|" << keywordres[i].weight << endl;
|
||
}
|
||
return EXIT_SUCCESS;
|
||
}
|