/// <summary>
/// 将给定句子分词
/// </summary>
/// <param name="sentence"></param>
/// <returns></returns>
public override List <Term> SegSentence(char[] sentence)
{
var wordNetAll = new WordNet(sentence);
//-------------------- 生成一元词网 --------------------------
GenerateWordNet(wordNetAll);
// 使用Viterbi分词
var list = Viterbi(wordNetAll);
if (config.useCustomDict) // 需要使用自定义词典
{
if (config.indexMode) // 开启索引模式
{
CombineByCustomDict(list, wordNetAll);
}
else
{
CombineByCustomDict(list);
}
}
if (config.numQuantRecognize) // 数量词识别
{
CombineNumQuant(list, wordNetAll, config);
}
if (config.nameEntityRecognize) // 命名实体识别
{
var wordNetOptimum = new WordNet(sentence, list); //
var preSize = wordNetOptimum.Size;
if (config.chsNameRecognize) // 中文人名识别
{
ChsNameRecognition.Recognition(list, wordNetOptimum, wordNetAll);
}
if (config.translatedNameRecognize)
{
TranslatedPersonRecognition.Recognition(list, wordNetOptimum, wordNetAll);
}
if (config.jpNameRecognize)
{
}
if (config.placeRecognize)
{
}
if (config.orgRecognize)
{
list = Viterbi(wordNetOptimum);
wordNetOptimum.Clear();
wordNetOptimum.AddAll(list);
preSize = wordNetOptimum.Size;
OrgRecognition.Recognition(list, wordNetOptimum, wordNetAll);
}
if (wordNetOptimum.Size != preSize)
{
list = Viterbi(wordNetOptimum);
}
}
return(Convert(list, config.offset));
}
protected override List <Term> segSentence(char[] sentence)
{
// long start = System.currentTimeMillis();
WordNet wordNetAll = new WordNet(sentence);
////////////////生成词网////////////////////
GenerateWordNet(wordNetAll);
///////////////生成词图////////////////////
// System.out.println("构图：" + (System.currentTimeMillis() - start));
if (HanLP.Config.DEBUG)
{
//System.out.printf("粗分词网：\n%s\n", wordNetAll);
}
// start = System.currentTimeMillis();
LinkedList <Vertex> vertexList = viterbi(wordNetAll);
// System.out.println("最短路：" + (System.currentTimeMillis() - start));
if (config.useCustomDictionary)
{
combineByCustomDictionary(vertexList);
}
if (HanLP.Config.DEBUG)
{
//System.out.println("粗分结果" + convert(vertexList, false));
}
// 数字识别
if (config.numberQuantifierRecognize)
{
mergeNumberQuantifier(vertexList, wordNetAll, config);
}
// 实体命名识别
if (config.ner)
{
WordNet wordNetOptimum = new WordNet(sentence, vertexList);
int preSize = wordNetOptimum.Size();
if (config.nameRecognize)
{
PersonRecognition.Recognition(vertexList, wordNetOptimum, wordNetAll);
}
if (config.translatedNameRecognize)
{
TranslatedPersonRecognition.Recognition(vertexList, wordNetOptimum, wordNetAll);
}
if (config.japaneseNameRecognize)
{
JapanesePersonRecognition.Recognition(vertexList, wordNetOptimum, wordNetAll);
}
if (config.placeRecognize)
{
PlaceRecognition.Recognition(vertexList, wordNetOptimum, wordNetAll);
}
if (config.organizationRecognize)
{
// 层叠隐马模型——生成输出作为下一级隐马输入
vertexList = viterbi(wordNetOptimum);
wordNetOptimum.clear();
wordNetOptimum.addAll(vertexList);
preSize = wordNetOptimum.Size();
OrganizationRecognition.Recognition(vertexList, wordNetOptimum, wordNetAll);
}
if (wordNetOptimum.Size() != preSize)
{
vertexList = viterbi(wordNetOptimum);
if (HanLP.Config.DEBUG)
{
Console.WriteLine("细分词网：\n%s\n", wordNetOptimum);
}
}
}
// 如果是索引模式则全切分
if (config.indexMode)
{
//return decorateResultForIndexMode(vertexList, wordNetAll);
}
// 是否标注词性
if (config.speechTagging)
{
//speechTagging(vertexList);
}
return(convert(vertexList, config.offset));
}
