7

Lucene 4.3.1 荧光笔是如何工作的？我想从文档中打印出搜索结果（作为搜索词和该词之后的 8 个词）。我怎样才能使用 Highlighter 类来做到这一点？我已将完整的 txt、html 和 xml 文档添加到文件中，并将它们添加到我的索引中，现在我有了一个搜索公式，我可能会从中添加荧光笔功能：

String index = "index";
String field = "contents";
String queries = null;
int repeat = 1;
boolean raw = true; //not sure what raw really does???
String queryString = null; //keep null, prompt user later for it
int hitsPerPage = 10; //leave it at 10, go from there later

//need to add all files to same directory
index = "C:\\Users\\plib\\Documents\\index";
repeat = 4;


IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(index)));
IndexSearcher searcher = new IndexSearcher(reader);
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_43);

BufferedReader in = null;
if (queries != null) {
  in = new BufferedReader(new InputStreamReader(new FileInputStream(queries), "UTF-8"));
} else {
  in = new BufferedReader(new InputStreamReader(System.in, "UTF-8"));
}
QueryParser parser = new QueryParser(Version.LUCENE_43, field, analyzer);
while (true) {
  if (queries == null && queryString == null) {                        // prompt the user
    System.out.println("Enter query. 'quit' = quit: ");
  }

  String line = queryString != null ? queryString : in.readLine();

  if (line == null || line.length() == -1) {
    break;
  }

  line = line.trim();
  if (line.length() == 0 || line.equalsIgnoreCase("quit")) {
    break;
  }

  Query query = parser.parse(line);
  System.out.println("Searching for: " + query.toString(field));

  if (repeat > 0) {                           // repeat & time as benchmark
    Date start = new Date();
    for (int i = 0; i < repeat; i++) {
      searcher.search(query, null, 100);
    }
    Date end = new Date();
    System.out.println("Time: "+(end.getTime()-start.getTime())+"ms");
  }

  doPagingSearch(in, searcher, query, hitsPerPage, raw, queries == null && queryString == null);

  if (queryString != null) {
    break;
  }
}
reader.close();

}

4

2 回答 2

9

我有同样的问题，最后偶然发现了这篇文章。

http://vnarcher.blogspot.ca/2012/04/highlighting-text-with-lucene.html

关键部分是，当您迭代结果时，将调用getHighlightedField您想要突出显示的结果值。

private String getHighlightedField(Query query, Analyzer analyzer, String fieldName, String fieldValue) throws IOException, InvalidTokenOffsetsException {
    Formatter formatter = new SimpleHTMLFormatter("<span class="\"MatchedText\"">", "</span>");
    QueryScorer queryScorer = new QueryScorer(query);
    Highlighter highlighter = new Highlighter(formatter, queryScorer);
    highlighter.setTextFragmenter(new SimpleSpanFragmenter(queryScorer, Integer.MAX_VALUE));
    highlighter.setMaxDocCharsToAnalyze(Integer.MAX_VALUE);
    return highlighter.getBestFragment(this.analyzer, fieldName, fieldValue);
}

在这种情况下，它假设输出将是 html，并且它只是<span>使用 .css 类的 css 类来包装突出显示的文本MatchedText。然后，您可以定义一个自定义 css 规则来做任何您想做的突出显示。

于 2013-10-04T20:06:22.827 回答
7

要使 Lucene 荧光笔正常工作，您需要在要索引的文档中添加两个字段。一个字段应启用术语向量，而另一个字段应不使用术语向量。为简单起见，我向您展示了一个代码片段：

    FieldType type = new FieldType();
    type.setIndexed(true);
    type.setIndexOptions(FieldInfo.IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
    type.setStored(true);
    type.setStoreTermVectors(true);
    type.setTokenized(true);
    type.setStoreTermVectorOffsets(true);
    Field field = new Field("content", "This is fragment. Highlters", type);
    doc.add(field);  //this field has term Vector enabled.

    //without term vector enabled.
    doc.add(new StringField("ncontent","This is fragment. Highlters", Field.Store.YES));

启用它们后，将该文档添加到您的索引中。现在使用 lucene 荧光笔使用下面给出的方法（它使用 Lucene 4.2，我没有用 Lucene 4.3.1 测试过）：

         public void highLighter() throws IOException, ParseException, InvalidTokenOffsetsException {
    IndexReader reader = DirectoryReader.open(FSDirectory.open(new File("INDEXDIRECTORY")));
    Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_42);
    IndexSearcher searcher = new IndexSearcher(reader);
    QueryParser parser = new QueryParser(Version.LUCENE_42, "content", analyzer);
    Query query = parser.parse("Highlters"); //your search keyword
    TopDocs hits = searcher.search(query, reader.maxDoc());
    System.out.println(hits.totalHits);
    SimpleHTMLFormatter htmlFormatter = new SimpleHTMLFormatter();
    Highlighter highlighter = new Highlighter(htmlFormatter, new QueryScorer(query));
    for (int i = 0; i < reader.maxDoc(); i++) {
        int id = hits.scoreDocs[i].doc;
        Document doc = searcher.doc(id);
        String text = doc.get("ncontent");
        TokenStream tokenStream = TokenSources.getAnyTokenStream(searcher.getIndexReader(), id, "ncontent", analyzer);
        TextFragment[] frag = highlighter.getBestTextFragments(tokenStream, text, false, 4);
        for (int j = 0; j < frag.length; j++) {
            if ((frag[j] != null) && (frag[j].getScore() > 0)) {
                System.out.println((frag[j].toString()));
            }
        }
        //Term vector
        text = doc.get("content");
        tokenStream = TokenSources.getAnyTokenStream(searcher.getIndexReader(), hits.scoreDocs[i].doc, "content", analyzer);
        frag = highlighter.getBestTextFragments(tokenStream, text, false, 10);
        for (int j = 0; j < frag.length; j++) {
            if ((frag[j] != null) && (frag[j].getScore() > 0)) {
                System.out.println((frag[j].toString()));
            }
        }

        System.out.println("-------------");
    }
}
于 2013-07-15T10:23:13.937 回答