Java 短语查询不工作Lucene 4.5.0

我尝试使用

PhraseQuery

，但无法从搜索中获得点击率。我使用的是

Lucene 4.5.0

我的索引代码

private IndexWriter writer;

public LuceneIndexSF(final String indexDir) throws IOException {
    Analyzer analyzer = new KeywordAnalyzer();
    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_45,
            analyzer);
    Directory directory = FSDirectory.open(new File(indexDir));
    writer = new IndexWriter(directory, config);
}
private Document getDocument(File f, String line, int lineNum)
            throws IOException {
        Document doc = new Document();
        Field field = null;
        if (line != null && line.split(DELIMITER).length >= 5) {
            String[] lineValues = line.split(DELIMITER);
            field = new Field("name", line.split("\t")[1],
                    TextField.TYPE_STORED);
            doc.add(field);
            if (lineValues[2] != null && !lineValues[2].trim().isEmpty()) {
                field = new Field("ref", lineValues[2], TextField.TYPE_STORED);
                doc.add(field);
            }
            field = new Field("type", lineValues[3], TextField.TYPE_STORED);
            doc.add(field);
            field = new LongField("code", Long.parseLong(lineValues[4]),
                    LongField.TYPE_STORED);
            doc.add(field);
            if (lineValues.length == 7 && lineValues[5] != null
                    && !lineValues[5].trim().isEmpty()) {
                field = new Field("alias1", lineValues[5],
                        TextField.TYPE_STORED);
                doc.add(field);
            }
            if (lineValues.length == 7 && lineValues[6] != null
                    && !lineValues[6].trim().isEmpty()) {
                field = new Field("alias2", lineValues[6],
                        TextField.TYPE_STORED);
                doc.add(field);
            }
        }
        field = new IntField("linenum", lineNum, IntField.TYPE_STORED);
        doc.add(field);
        return doc;
    }
.... and other code where i add document in writer using writer.addDocument(doc);

private static void search(String indexDir, String quer) throws IOException,
        ParseException {
    IndexReader inxRead = DirectoryReader.open(FSDirectory.open(new File(
            indexDir)));
    IndexSearcher is = new IndexSearcher(inxRead);
    String[] termArr = quer.split(" ");
    PhraseQuery phraseQuery= new PhraseQuery();
    for(int inx = 0; inx < termArr.length; inx++){
        phraseQuery.add(new Term("name", termArr[inx]));
    }
    phraseQuery.setSlop(4);
    long start = System.currentTimeMillis();
    TopDocs hits = is.search(phraseQuery, 1000);
    long end = System.currentTimeMillis();
    System.err.println("Parser> Found " + hits.totalHits
            + " document(s) (in " + (end - start)
            + " milliseconds) that matched query '" + multiQuery + "':");
    for (ScoreDoc scoreDoc : hits.scoreDocs) {
        Document doc = is.doc(scoreDoc.doc);
        System.out.println("Parser> " + scoreDoc.score + " :: "
                + doc.get("type") + " - " + doc.get("code") + " - "
                + doc.get("name") + ", " + doc.get("linenum"));
    }
    inxRead.close();
}

我的搜索代码

private IndexWriter writer;

public LuceneIndexSF(final String indexDir) throws IOException {
    Analyzer analyzer = new KeywordAnalyzer();
    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_45,
            analyzer);
    Directory directory = FSDirectory.open(new File(indexDir));
    writer = new IndexWriter(directory, config);
}
private Document getDocument(File f, String line, int lineNum)
            throws IOException {
        Document doc = new Document();
        Field field = null;
        if (line != null && line.split(DELIMITER).length >= 5) {
            String[] lineValues = line.split(DELIMITER);
            field = new Field("name", line.split("\t")[1],
                    TextField.TYPE_STORED);
            doc.add(field);
            if (lineValues[2] != null && !lineValues[2].trim().isEmpty()) {
                field = new Field("ref", lineValues[2], TextField.TYPE_STORED);
                doc.add(field);
            }
            field = new Field("type", lineValues[3], TextField.TYPE_STORED);
            doc.add(field);
            field = new LongField("code", Long.parseLong(lineValues[4]),
                    LongField.TYPE_STORED);
            doc.add(field);
            if (lineValues.length == 7 && lineValues[5] != null
                    && !lineValues[5].trim().isEmpty()) {
                field = new Field("alias1", lineValues[5],
                        TextField.TYPE_STORED);
                doc.add(field);
            }
            if (lineValues.length == 7 && lineValues[6] != null
                    && !lineValues[6].trim().isEmpty()) {
                field = new Field("alias2", lineValues[6],
                        TextField.TYPE_STORED);
                doc.add(field);
            }
        }
        field = new IntField("linenum", lineNum, IntField.TYPE_STORED);
        doc.add(field);
        return doc;
    }
.... and other code where i add document in writer using writer.addDocument(doc);

private static void search(String indexDir, String quer) throws IOException,
        ParseException {
    IndexReader inxRead = DirectoryReader.open(FSDirectory.open(new File(
            indexDir)));
    IndexSearcher is = new IndexSearcher(inxRead);
    String[] termArr = quer.split(" ");
    PhraseQuery phraseQuery= new PhraseQuery();
    for(int inx = 0; inx < termArr.length; inx++){
        phraseQuery.add(new Term("name", termArr[inx]));
    }
    phraseQuery.setSlop(4);
    long start = System.currentTimeMillis();
    TopDocs hits = is.search(phraseQuery, 1000);
    long end = System.currentTimeMillis();
    System.err.println("Parser> Found " + hits.totalHits
            + " document(s) (in " + (end - start)
            + " milliseconds) that matched query '" + multiQuery + "':");
    for (ScoreDoc scoreDoc : hits.scoreDocs) {
        Document doc = is.doc(scoreDoc.doc);
        System.out.println("Parser> " + scoreDoc.score + " :: "
                + doc.get("type") + " - " + doc.get("code") + " - "
                + doc.get("name") + ", " + doc.get("linenum"));
    }
    inxRead.close();
}

解决方案

根据Arun的回答，

短语查询

要正常工作，需要Analyzer标记

文档

的

字段

中的每个单词。对于我的案例，我使用了

小写过滤器

，使所有查询都小写，这样它就可以在不区分大小写的情况下工作。并使用用于自动完成目的的

EdgeNGramTokenFilter

public LuceneIndexSF(final String indexDir) throws IOException {
Analyzer analyzer = new Analyzer() {
        @Override
        protected TokenStreamComponents createComponents(String fieldName,
                java.io.Reader reader) {
            Tokenizer source = new StandardTokenizer(Version.LUCENE_45,
                    reader);
            TokenStream result = new StandardFilter(Version.LUCENE_45,
                    source);
            result = new LowerCaseFilter(Version.LUCENE_45, result);
            result = new EdgeNGramTokenFilter(Version.LUCENE_45, result, 1,
                    20);
            return new TokenStreamComponents(source, result);
        }
    };
IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_45,
        analyzer);
Directory directory = FSDirectory.open(new File(indexDir));
writer = new IndexWriter(directory, config);
}

我的最终搜索方法

private static void search(String indexDir, String quer) throws IOException,
    ParseException {
IndexReader inxRead = DirectoryReader.open(FSDirectory.open(new File(
        indexDir)));
IndexSearcher is = new IndexSearcher(inxRead);
String[] termArr = quer.split(" ");
PhraseQuery query1 = new PhraseQuery();
PhraseQuery query2 = new PhraseQuery();
PhraseQuery query3 = new PhraseQuery();
for (int inx = 0; inx < termArr.length; inx++) {
    query1.add(new Term(SchoolFinderConstant.ENTITY_NAME,termArr[inx]),inx);
    query2.add(new Term(SchoolFinderConstant.ENTITY_ALIAS1,termArr[inx]),inx);
    query3.add(new Term(SchoolFinderConstant.ENTITY_ALIAS2,termArr[inx]),inx);
}
BooleanQuery mainQuery = new BooleanQuery();
mainQuery.add(query1, Occur.SHOULD);
mainQuery.add(query2, Occur.SHOULD);
mainQuery.add(query3, Occur.SHOULD);
long start = System.currentTimeMillis();
TopDocs hits = is.search(mainQuery, 1000);
long end = System.currentTimeMillis();
System.err.println("Parser> Found " + hits.totalHits
        + " document(s) (in " + (end - start)
        + " milliseconds) that matched query '" + multiQuery + "':");
for (ScoreDoc scoreDoc : hits.scoreDocs) {
    Document doc = is.doc(scoreDoc.doc);
    System.out.println("Parser> " + scoreDoc.score + " :: "
            + doc.get("type") + " - " + doc.get("code") + " - "
            + doc.get("name") + ", " + doc.get("linenum"));
}
inxRead.close();
}

private static void search（String indexDir，String query）抛出IOException，
语法异常{
IndexReader inxRead=DirectoryReader.open（FSDirectory.open）（新文件(
indexDir),；
IndexSearcher is=新的IndexSearcher（inxRead）；
字符串[]termArr=query.split（“”）；
PhraseQuery query1=新PhraseQuery（）；
PhraseQuery query2=新PhraseQuery（）；
PhraseQuery query3=新PhraseQuery（）；
对于（int-inx=0；inx已找到”+hits.totalHits
+“文件”（在“+”中）（结束-开始）
+匹配查询“+”多重查询“：”）的“毫秒”；
for（ScoreDoc ScoreDoc:hits.scoreDocs）{
单据单据=is.doc（scoreDoc.doc）；
System.out.println（“解析器>”+scoreDoc.score+”：“
+doc.get（“type”）+“-”+doc.get（“code”）+“-”
+doc.get（“name”）+，“+doc.get（“linenum”）；
}
inxRead.close（）；
}

我用KeywordAnalyzer处理了您的代码，显然它不起作用，因为KeywordAnalyzer将整个流“标记”为单个标记。这对于邮政编码、ID和某些产品名称等数据非常有用，要使其工作，您需要在不做任何更改的情况下指定整个令牌

然后我使用了WhitespaceAnalyzer，它可以为您的短语查询找到匹配项。对代码的其余部分没有更改。让我知道这是否对你有效

---

使用MultiFieldQueryParser进行搜索的原因是，在查询与索引匹配的内容时，您必须使用分析器。因此，简而言之，您需要确保索引分析器和查询时间分析器是相似的

是否检查字符串[]lineValues=line.split（分隔符）；field=新字段（“名称”，行分割（“\t”）[1]，TextField.TYPE\u存储）；零件是否发送了您认为是索引的正确值？特别是查看intoline.split（“\t”）[1]，如果evrything good可以将代码的完整Java类发布到某个地方，其中包含一行可用于测试的代码，这样我就可以对它进行旋转，看看有什么问题了吗？@Arun是的，它确实提供了正确的值，我已经检查过了，奇怪的事情是搜索工作符合<代码> MultiFieldQueryParser <代码>，但不符合<代码>短语> <代码>。如果你需要的话，是单线“7044国际中等教育委员会通用证书6 IGCSE，剑桥大学国际考试”。你可以执行测试onok，我今晚会检查它，你能告诉我为什么它不能与

StandardAnalyzer

一起工作吗？StandardAnalyzer会删除函数词，你需要看看它在索引什么。或者，您需要使用Stabdard analyzer查询Parser来运行您的查询，以便以相同的方式处理您的查询。