/**
* 合并数字
* @param termList
*/
protected void mergeNumberQuantifier(LinkedList <Vertex> termList, WordNet wordNetAll, Config config)
{
if (termList.Count < 4)
{
return;
}
StringBuilder sbQuantifier = new StringBuilder();
LinkedList <Vertex> .Enumerator iterator = termList.GetEnumerator();
//iterator.next();
int line = 1;
while (iterator.MoveNext())
{
Vertex pre = iterator.Current;
if (pre.hasNature(Nature.m))
{
sbQuantifier.Append(pre.realWord);
Vertex cur = null;
while (iterator.MoveNext() && (cur = iterator.Current).hasNature(Nature.m))
{
sbQuantifier.Append(cur.realWord);
//iterator.remove();
removeFromWordNet(cur, wordNetAll, line, sbQuantifier.Length);
}
if (cur != null)
{
if ((cur.hasNature(Nature.q) || cur.hasNature(Nature.qv) || cur.hasNature(Nature.qt)))
{
if (config.indexMode)
{
wordNetAll.add(line, new Vertex(sbQuantifier.ToString(), new CoreDictionary.Attribute(Nature.m)));
}
sbQuantifier.Append(cur.realWord);
//iterator.remove();
removeFromWordNet(cur, wordNetAll, line, sbQuantifier.Length);
}
else
{
line += cur.realWord.Length; // (cur = iterator.next()).hasNature(Nature.m) 最后一个next可能不含q词性
}
}
if (sbQuantifier.Length != pre.realWord.Length)
{
pre.realWord = sbQuantifier.ToString();
pre.word = Predefine.TAG_NUMBER;
pre.attribute = new CoreDictionary.Attribute(Nature.mq);
pre.wordID = CoreDictionary.M_WORD_ID;
sbQuantifier.Length = 0;
}
}
sbQuantifier.Length = 0;
line += pre.realWord.Length;
}
// System.out.println(wordNetAll);
}
/**
* 生成一元词网
*
* @param wordNetStorage
*/
protected void GenerateWordNet(WordNet wordNetStorage)
{
char[] charArray = wordNetStorage.charArray;
// 核心词典查询
DoubleArrayTrie <CoreDictionary.Attribute> .Searcher searcher = CoreDictionary.trie.getSearcher(charArray, 0);
while (searcher.next())
{
wordNetStorage.add(searcher.begin + 1, new Vertex(new String(charArray, searcher.begin, searcher.length), searcher.value, searcher.index));
}
// 用户词典查询
// if (config.useCustomDictionary)
// {
// searcher = CustomDictionary.dat.getSearcher(charArray, 0);
// while (searcher.next())
// {
// wordNetStorage.add(searcher.begin + 1, new Vertex(new String(charArray, searcher.begin, searcher.length), searcher.value));
// }
// }
// 原子分词，保证图连通
//List<Vertex>[] vertexes = wordNetStorage.getVertexes();
List <Vertex>[] vertexes = wordNetStorage.getVertexes();
for (int i = 1; i < vertexes.Length;)
{
if (vertexes[i].Count == 0)
{
int j = i + 1;
for (; j < vertexes.Length - 1; ++j)
{
if (!(vertexes[j].Count == 0))
{
break;
}
}
wordNetStorage.add(i, quickAtomSegment(charArray, i - 1, j - 1));
i = j;
}
else
{
i += vertexes[i][vertexes[i].Count - 1].realWord.Length;
}
}
}