cppjieba/test/unittest/TKeywordExtractor.cpp

19 lines
697 B
C++
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

#include "src/KeywordExtractor.hpp"
#include "gtest/gtest.h"
using namespace CppJieba;
TEST(KeywordExtractorTest, Test1)
{
KeywordExtractor extractor("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8", "../dict/idf.utf8");
string s("我是蓝翔技工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总经理出任CEO迎娶白富美走上人生巅峰。");
string res;
vector<pair<string, double> > wordweights;
size_t topN = 5;
extractor.extract(s, wordweights, topN);
res << wordweights;
ASSERT_EQ(res, "[\"CEO:11.7392\", \"蓝翔:11.7392\", \"白富美:11.7392\", \"升职:10.8562\", \"加薪:10.6426\"]");
}