问Lucene:从String解析的同一个查询和通过query构建的查询不会产生相同的结果

EN

public static void main(String[] args) throws Throwable {
    String[] texts = new String[]{
            "starts_with k mer",
            "starts_with mer",
            "starts_with bleue est mer",
            "starts_with mer est bleue",
            "starts_with mer bla1 bla2 bla3 bla4 bla5",
            "starts_with bleue est la mer",
            "starts_with la mer est bleue",
            "starts_with la mer"
    };


    //write:
    Set<String> stopWords = new HashSet<String>();
    StandardAnalyzer stdAn = new StandardAnalyzer(Version.LUCENE_36, stopWords);
    Directory fsDir = FSDirectory.open(INDEX_DIR);
    IndexWriterConfig iwConf  = new IndexWriterConfig(Version.LUCENE_36,stdAn);
    iwConf.setOpenMode(IndexWriterConfig.OpenMode.CREATE);
    IndexWriter indexWriter = new IndexWriter(fsDir,iwConf);
    for(String text:texts) {
         Document document = new Document();
         document.add(new Field("title",text,Store.YES,Index.ANALYZED));
         indexWriter.addDocument(document);
    }
    indexWriter.commit();

    //read
    IndexReader indexReader = IndexReader.open(fsDir);
    IndexSearcher indexSearcher = new IndexSearcher(indexReader);

    //get query:
    //Query query = getQueryFromString("mer");
    Query query = getQueryFromAPI("mer");

    //explain
    System.out.println("======== Query: "+query+"\n");
    TopDocs hits = indexSearcher.search(query, 10);
    for (ScoreDoc scoreDoc : hits.scoreDocs) {
        Document doc = indexSearcher.doc(scoreDoc.doc);
        System.out.println(">>> "+doc.get("title"));
        System.out.println("Explain:");
        System.out.println(indexSearcher.explain(query, scoreDoc.doc));
    }
}

private static Query getQueryFromString(String searchString) throws Throwable {
    Set<String> stopWords = new HashSet<String>();
    Query query = new QueryParser(Version.LUCENE_36, "title",new StandardAnalyzer(Version.LUCENE_36, stopWords)).parse("("+searchString+") \"STARTS_WITH "+searchString+"\"");
    return query;
}

private static Query getQueryFromAPI(String searchString) throws Throwable {
    Set<String> stopWords = new HashSet<String>();
    Query searchStringTermsMatchTitle = new QueryParser(Version.LUCENE_36, "title", new StandardAnalyzer(Version.LUCENE_36, stopWords)).parse(searchString);

    PhraseQuery titleStartsWithSearchString = new PhraseQuery();
    titleStartsWithSearchString.add(new Term("title","STARTS_WITH".toLowerCase()+" "+searchString));
    BooleanQuery query = new BooleanQuery(true);

    BooleanClause matchClause = new BooleanClause(searchStringTermsMatchTitle, Occur.SHOULD);
    query.add(matchClause);     
    BooleanClause startsWithClause = new BooleanClause(titleStartsWithSearchString, Occur.SHOULD);
    query.add(startsWithClause);

    return query;
}

>>> starts_with mer
Explain:
1.2329358 = (MATCH) sum of:
  0.24658716 = (MATCH) weight(title:mer in 1), product of:
    0.4472136 = queryWeight(title:mer), product of:
      0.882217 = idf(docFreq=8, maxDocs=8)
      0.50692016 = queryNorm
    0.55138564 = (MATCH) fieldWeight(title:mer in 1), product of:
      1.0 = tf(termFreq(title:mer)=1)
      0.882217 = idf(docFreq=8, maxDocs=8)
      0.625 = fieldNorm(field=title, doc=1)
  0.9863486 = (MATCH) weight(title:"starts_with mer" in 1), product of:
    0.8944272 = queryWeight(title:"starts_with mer"), product of:
      1.764434 = idf(title: starts_with=8 mer=8)
      0.50692016 = queryNorm
    1.1027713 = fieldWeight(title:"starts_with mer" in 1), product of:
      1.0 = tf(phraseFreq=1.0)
      1.764434 = idf(title: starts_with=8 mer=8)
      0.625 = fieldNorm(field=title, doc=1)

>>> starts_with mer
Explain:
0.15185544 = (MATCH) sum of:
  0.15185544 = (MATCH) weight(title:mer in 1), product of:
    0.27540696 = queryWeight(title:mer), product of:
      0.882217 = idf(docFreq=8, maxDocs=8)
      0.312176 = queryNorm
    0.55138564 = (MATCH) fieldWeight(title:mer in 1), product of:
      1.0 = tf(termFreq(title:mer)=1)
      0.882217 = idf(docFreq=8, maxDocs=8)
      0.625 = fieldNorm(field=title, doc=1)

private static List<String> getTerms(String text) throws Throwable {
    Analyzer analyzer = getAnalyzer();      
    StringReader textReader = new StringReader(text);
    TokenStream tokenStream = analyzer.tokenStream(FIELD_NAME_TITLE, textReader);
    tokenStream.reset();        
    List<String> terms = new ArrayList<String>();
    CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);
    while (tokenStream.incrementToken()) {
        String term = charTermAttribute.toString();
        terms.add(term);
    }
    textReader.close();
    tokenStream.close();
    analyzer.close();       
    return terms;
}

PhraseQuery titleStartsWithSearchString = new PhraseQuery();
titleStartsWithSearchString.add(new Term("title","STARTS_WITH".toLowerCase()));
for(String term:getTerms(searchString)) {
    titleStartsWithSearchString.add(new Term("title",term));
}