mirror of
https://github.com/yanyiwu/cppjieba.git
synced 2025-07-18 00:00:12 +08:00
Update TextRankExtractor.hpp
remove unused function which using c++11 keyword `auto`
This commit is contained in:
parent
0f66a923b3
commit
6d105a864d
@ -1,4 +1,4 @@
|
|||||||
#ifndef CPPJIEBA_TEXTRANK_EXTRACTOR_H
|
#ifndef CPPJIEBA_TEXTRANK_EXTRACTOR_H
|
||||||
#define CPPJIEBA_TEXTRANK_EXTRACTOR_H
|
#define CPPJIEBA_TEXTRANK_EXTRACTOR_H
|
||||||
|
|
||||||
#include <cmath>
|
#include <cmath>
|
||||||
@ -82,40 +82,40 @@ namespace cppjieba {
|
|||||||
}
|
}
|
||||||
};
|
};
|
||||||
|
|
||||||
public:
|
public:
|
||||||
TextRankExtractor(const string& dictPath,
|
TextRankExtractor(const string& dictPath,
|
||||||
const string& hmmFilePath,
|
const string& hmmFilePath,
|
||||||
const string& stopWordPath,
|
const string& stopWordPath,
|
||||||
const string& userDict = "")
|
const string& userDict = "")
|
||||||
: segment_(dictPath, hmmFilePath, userDict) {
|
: segment_(dictPath, hmmFilePath, userDict) {
|
||||||
LoadStopWordDict(stopWordPath);
|
LoadStopWordDict(stopWordPath);
|
||||||
}
|
}
|
||||||
TextRankExtractor(const DictTrie* dictTrie,
|
TextRankExtractor(const DictTrie* dictTrie,
|
||||||
const HMMModel* model,
|
const HMMModel* model,
|
||||||
const string& stopWordPath)
|
const string& stopWordPath)
|
||||||
: segment_(dictTrie, model) {
|
: segment_(dictTrie, model) {
|
||||||
LoadStopWordDict(stopWordPath);
|
LoadStopWordDict(stopWordPath);
|
||||||
}
|
}
|
||||||
TextRankExtractor(const Jieba& jieba, const string& stopWordPath) : segment_(jieba.GetDictTrie(), jieba.GetHMMModel()) {
|
TextRankExtractor(const Jieba& jieba, const string& stopWordPath) : segment_(jieba.GetDictTrie(), jieba.GetHMMModel()) {
|
||||||
LoadStopWordDict(stopWordPath);
|
LoadStopWordDict(stopWordPath);
|
||||||
}
|
}
|
||||||
~TextRankExtractor() {
|
~TextRankExtractor() {
|
||||||
}
|
}
|
||||||
|
|
||||||
void Extract(const string& sentence, vector<string>& keywords, size_t topN) const {
|
void Extract(const string& sentence, vector<string>& keywords, size_t topN) const {
|
||||||
vector<Word> topWords;
|
vector<Word> topWords;
|
||||||
Extract(sentence, topWords, topN);
|
Extract(sentence, topWords, topN);
|
||||||
for (size_t i = 0; i < topWords.size(); i++) {
|
for (size_t i = 0; i < topWords.size(); i++) {
|
||||||
keywords.push_back(topWords[i].word);
|
keywords.push_back(topWords[i].word);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
void Extract(const string& sentence, vector<pair<string, double> >& keywords, size_t topN) const {
|
void Extract(const string& sentence, vector<pair<string, double> >& keywords, size_t topN) const {
|
||||||
vector<Word> topWords;
|
vector<Word> topWords;
|
||||||
Extract(sentence, topWords, topN);
|
Extract(sentence, topWords, topN);
|
||||||
for (size_t i = 0; i < topWords.size(); i++) {
|
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<string, double>(topWords[i].word, topWords[i].weight));
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
void Extract(const string& sentence, vector<Word>& keywords, size_t topN, size_t span=5,size_t rankTime=10) const {
|
void Extract(const string& sentence, vector<Word>& keywords, size_t topN, size_t span=5,size_t rankTime=10) const {
|
||||||
@ -176,13 +176,6 @@ namespace cppjieba {
|
|||||||
return false;
|
return false;
|
||||||
}
|
}
|
||||||
|
|
||||||
static void sortMapValue(WordMap &map,vector<Word>& result,size_t topN){
|
|
||||||
for(auto i=map.begin();i!=map.end();i++){
|
|
||||||
result.push_back(i->second);
|
|
||||||
}
|
|
||||||
partial_sort(result.begin(),result.begin()+topN,result.end(),Compare);
|
|
||||||
}
|
|
||||||
|
|
||||||
static bool Compare(const Word &x,const Word &y){
|
static bool Compare(const Word &x,const Word &y){
|
||||||
return x.weight > y.weight;
|
return x.weight > y.weight;
|
||||||
}
|
}
|
||||||
@ -190,9 +183,9 @@ namespace cppjieba {
|
|||||||
MixSegment segment_;
|
MixSegment segment_;
|
||||||
unordered_set<string> stopWords_;
|
unordered_set<string> stopWords_;
|
||||||
};
|
};
|
||||||
|
|
||||||
inline ostream& operator << (ostream& os, const TextRankExtractor::Word& word) {
|
inline ostream& operator << (ostream& os, const TextRankExtractor::Word& word) {
|
||||||
return os << word.word << '|' << word.offsets << '|' << word.weight;
|
return os << word.word << '|' << word.offsets << '|' << word.weight;
|
||||||
}
|
}
|
||||||
} // namespace cppjieba
|
} // namespace cppjieba
|
||||||
|
|
||||||
|
Loading…
x
Reference in New Issue
Block a user