This commit is contained in:
yanyiwu 2024-09-21 17:24:26 +08:00
parent 30aaf7b9ad
commit e521f26456
3 changed files with 0 additions and 82 deletions

View File

@ -19,7 +19,6 @@ ADD_DEFINITIONS(-O3 -Wall -g)
ADD_SUBDIRECTORY(test)
ENABLE_TESTING()
ADD_TEST(NAME ./demo COMMAND ./demo)
if(NOT MSVC)
ADD_TEST(NAME ./test/test.run COMMAND ./test/test.run)
ADD_TEST(NAME ./load_test COMMAND ./load_test)

View File

@ -1,6 +1,5 @@
SET(EXECUTABLE_OUTPUT_PATH ${PROJECT_BINARY_DIR})
ADD_EXECUTABLE(demo demo.cpp)
if(NOT MSVC)
ADD_EXECUTABLE(load_test load_test.cpp)
ADD_SUBDIRECTORY(unittest)

View File

@ -1,80 +0,0 @@
#include "cppjieba/Jieba.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,
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";
cout << s << endl;
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;
s = "我来到北京清华大学";
cout << s << endl;
cout << "[demo] CutAll" << endl;
jieba.CutAll(s, words);
cout << limonp::Join(words.begin(), words.end(), "/") << endl;
s = "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";
cout << s << 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] CutForSearch Word With Offset" << endl;
jieba.CutForSearch(s, jiebawords, true);
cout << jiebawords << endl;
cout << "[demo] Lookup Tag for Single Token" << endl;
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);
}
cout << LookupTagres << endl;
cout << "[demo] Tagging" << endl;
vector<pair<string, string> > tagres;
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。";
jieba.Tag(s, tagres);
cout << s << endl;
cout << tagres << endl;
cout << "[demo] Keyword Extraction" << endl;
const size_t topk = 5;
vector<cppjieba::KeywordExtractor::Word> keywordres;
jieba.extractor.Extract(s, keywordres, topk);
cout << s << endl;
cout << keywordres << endl;
return EXIT_SUCCESS;
}