ukui-search/libchinese-segmentation/cppjieba/MPSegment.hpp

152 lines
4.7 KiB
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.

/*
*
* Copyright (C) 2023, KylinSoft Co., Ltd.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <https://www.gnu.org/licenses/>.
*
*/
#pragma once
#include <algorithm>
#include <set>
#include <cassert>
#include "limonp/Logging.hpp"
#include "segment-trie/segment-trie.h"
//#include "DictTrie.hpp"
#include "SegmentTagged.hpp"
#include "PosTagger.hpp"
namespace cppjieba {
class MPSegment: public SegmentTagged {
public:
MPSegment(const DictTrie* dictTrie)
: dictTrie_(dictTrie) {
assert(dictTrie_);
}
~MPSegment() { }
virtual void Cut(RuneStrArray::const_iterator begin,
RuneStrArray::const_iterator end,
vector<WordRange>& words,
bool, size_t max_word_len) const override {
dictTrie_->FindWordRange(begin, end, words, max_word_len);
}
virtual void CutWithSentence(const string& s, RuneStrArray::const_iterator begin, RuneStrArray::const_iterator end, vector<string>& res, bool hmm,
size_t) const override {
std::ignore = s;
std::ignore = begin;
std::ignore = end;
std::ignore = res;
std::ignore = hmm;
}
virtual void CutWithSentence(const string& s, RuneStrArray::const_iterator begin, RuneStrArray::const_iterator end, unordered_map<string, KeyWord>& res, bool hmm,
size_t) const override {
std::ignore = s;
std::ignore = begin;
std::ignore = end;
std::ignore = res;
std::ignore = hmm;
}
const DictTrie* GetDictTrie() const override {
return dictTrie_;
}
bool Tag(const string& src, vector<pair<string, string> >& res) const override {
return tagger_.Tag(src, res, *this);
}
bool IsUserDictSingleChineseWord(const Rune& value) const {
return dictTrie_->IsUserDictSingleChineseWord(value);
}
private:
/*
void CalcDP(vector<DatDag>& dags) const {
double val(0);
for (auto rit = dags.rbegin(); rit != dags.rend(); rit++) {
rit->max_next = -1;
rit->max_weight = MIN_DOUBLE;
for (const auto & it : rit->nexts) {
const auto nextPos = it.first;
val = dictTrie_->GetMinWeight();
if (nullptr != it.second) {
val = it.second->weight;
}
if (nextPos < dags.size()) {
val += dags[nextPos].max_weight;
}
if ((nextPos <= dags.size()) && (val > rit->max_weight)) {
rit->max_weight = val;
rit->max_next = nextPos;
}
}
}
}
*/
/* 倒叙方式重写CalcDP函数初步测试未发现问题*/
/*
void CalcDP(vector<DatDag>& dags) const {
double val(0);
size_t size = dags.size();
for (size_t i = 0; i < size; i++) {
dags[size - 1 - i].max_next = -1;
dags[size - 1 - i].max_weight = MIN_DOUBLE;
for (const auto & it : dags[size - 1 - i].nexts) {
const auto nextPos = it.first;
if (nullptr != it.second) {
val = it.second->weight;
}
if (nextPos < dags.size()) {
val += dags[nextPos].max_weight;
}
if ((nextPos <= dags.size()) && (val > dags[size - 1 - i].max_weight)) {
dags[size - 1 - i].max_weight = val;
dags[size - 1 - i].max_next = nextPos;
}
}
}
}
void CutByDag(RuneStrArray::const_iterator begin,
RuneStrArray::const_iterator,
const vector<DatDag>& dags,
vector<WordRange>& words) const {
for (size_t i = 0; i < dags.size();) {
const auto next = dags[i].max_next;
assert(next > i);
assert(next <= dags.size());
WordRange wr(begin + i, begin + next - 1);
words.push_back(wr);
i = next;
}
}
*///相关功能已集成到Find函数中
const DictTrie* dictTrie_;
PosTagger tagger_;
}; // class MPSegment
} // namespace cppjieba