获取使用通配符搜索时，搜索文档中的条款相匹配 [英] Getting terms matched in a document when searching using a wildcard search

问题描述

我要寻找一种方法来发现使用Lucene的waldcard搜索文档中匹配的条件。我用了解释器，试图找到的条款，但这个失败。 。相关代码的一部分低于

  ScoreDoc [] = myHits myTopDocs.scoreDocs; 
 INT hitsCount = myHits.Length; 
为（INT myCounter = 0; myCounter< hitsCount; myCounter ++）
 {
文档的DOC = searcher.Doc（myHits [myCounter] .DOC）; 
解释解释= searcher.Explain（更改为MyQuery，myCounter）; 
串myExplanation = explanation.ToString（）; 
 ... 
  

当我做说微*搜索，文档被发现它进入循环，但myExplanation包含不匹配，没有其他信息。

我如何得到这是本文档中的术语？

任何帮助将是非常赞赏。

问候

解决方案

 类TVM：TermVectorMapper 
 {
公开名单<串GT; FoundTerms =新的List<串GT;（）; 
的HashSet<串GT; _termTexts =新的HashSet<串GT;（）; 
 
公共TVM（查询Q，的IndexReader R）：基地（）
 {
名单，LT;期限> allTerms =新的List<条款>（）; 
 q.Rewrite（R）.ExtractTerms（allTerms）; 
的foreach（在allTerms期限t）的_termTexts.Add（t.Text（））; 
} 
 
公共覆盖无效SetExpectations（串场，诠释numTerms，布尔storeOffsets，布尔storePositions）
 {
} 
 
公众覆盖无效地图（串词，INT频率，TermVectorOffsetInfo []偏移，INT []位置）
 {
如果（_termTexts.Contains（项））FoundTerms.Add（项）; 
} 
} 
 
无效TermVectorMapperTest（）
 {
 RAMDirectory DIR =新RAMDirectory（）; 
的IndexWriter作家=新的IndexWriter（DIR，新Lucene.Net.Analysis.Standard.StandardAnalyzer（），TRUE）; 
文档D = NULL; 
 
 D =新的文件（）; 
 d.Add（新域（文字，显微镜AAA，Field.Store.YES，Field.Index.ANALYZED，Field.TermVector.WITH_POSITIONS_OFFSETS））; 
 writer.AddDocument（四）; 
 
 D =新的文件（）; 
 d.Add（新域（文字，微软BBB，Field.Store.YES，Field.Index.ANALYZED，Field.TermVector.WITH_POSITIONS_OFFSETS））; 
 writer.AddDocument（四）; 
 
 writer.Close（）; 
 
的IndexReader读卡器= IndexReader.Open（DIR）; 
 IndexSearcher的搜索=新IndexSearcher的（阅读器）; 
 
的QueryParser QueryParser的=新的QueryParser（文字，新Lucene.Net.Analysis.Standard.StandardAnalyzer（））; 
 queryParser.SetMultiTermRewriteMethod（MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE）; 
查询查询= queryParser.Parse（微*）; 
 
 TopDocs结果= searcher.Search（查询，5）; 
 System.Diagnostics.Debug.Assert（results.TotalHits == 2）; 
 
 TVM TVM =新TVM（查询，读卡器）; 
的for（int i = 0; I< results.ScoreDocs.Length;我++）
 {
 Console.Write（DOCID：+ results.ScoreDocs [I] .DOC + >中）; 
 reader.GetTermFreqVector（results.ScoreDocs [I] .DOC，文本，TVM）; 
的foreach（在tvm.FoundTerms串词）Console.Write（项+）; 
 tvm.FoundTerms.Clear（）; 
 Console.WriteLine（）; 
} 
} 
  

I am looking for a way to find the terms that matched in the document using waldcard search in Lucene. I used the explainer to try and find the terms but this failed. A portion of the relevant code is below.

ScoreDoc[] myHits = myTopDocs.scoreDocs;
int hitsCount = myHits.Length;
for (int myCounter = 0; myCounter < hitsCount; myCounter++)
{
    Document doc = searcher.Doc(myHits[myCounter].doc);
    Explanation explanation = searcher.Explain(myQuery, myCounter);
    string myExplanation = explanation.ToString();
    ...

When I do a search on say micro*, documents are found and it enter the loop but myExplanation contains NON-MATCH and no other information.

How do I get the term that was found in this document ?

Any help would be most appreciated.

Regards

解决方案

    class TVM : TermVectorMapper
    {
        public List<string> FoundTerms = new List<string>();
        HashSet<string> _termTexts = new HashSet<string>();

        public TVM(Query q, IndexReader r) : base()
        {
            List<Term> allTerms = new List<Term>();
            q.Rewrite(r).ExtractTerms(allTerms);
            foreach (Term t in allTerms) _termTexts.Add(t.Text());
        }

        public override void SetExpectations(string field, int numTerms, bool storeOffsets, bool storePositions)
        {
        }

        public override void Map(string term, int frequency, TermVectorOffsetInfo[] offsets, int[] positions)
        {
            if (_termTexts.Contains(term)) FoundTerms.Add(term);
        }
    }

    void TermVectorMapperTest()
    {
        RAMDirectory dir = new RAMDirectory();
        IndexWriter writer = new IndexWriter(dir, new Lucene.Net.Analysis.Standard.StandardAnalyzer(), true);
        Document d = null;

        d = new Document();
        d.Add(new Field("text", "microscope aaa", Field.Store.YES, Field.Index.ANALYZED,Field.TermVector.WITH_POSITIONS_OFFSETS));
        writer.AddDocument(d);

        d = new Document();
        d.Add(new Field("text", "microsoft bbb", Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS));
        writer.AddDocument(d);

        writer.Close();

        IndexReader reader = IndexReader.Open(dir);
        IndexSearcher searcher = new IndexSearcher(reader);

        QueryParser queryParser = new QueryParser("text", new Lucene.Net.Analysis.Standard.StandardAnalyzer());
        queryParser.SetMultiTermRewriteMethod(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE); 
        Query query = queryParser.Parse("micro*");

        TopDocs results = searcher.Search(query, 5);
        System.Diagnostics.Debug.Assert(results.TotalHits == 2);

        TVM tvm = new TVM(query, reader);
        for (int i = 0; i < results.ScoreDocs.Length; i++)
        {
            Console.Write("DOCID:" + results.ScoreDocs[i].Doc + " > ");
            reader.GetTermFreqVector(results.ScoreDocs[i].Doc, "text", tvm);
            foreach (string term in tvm.FoundTerms) Console.Write(term + " ");
            tvm.FoundTerms.Clear();
            Console.WriteLine();
        }
    }

这篇关于获取使用通配符搜索时，搜索文档中的条款相匹配的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！