@Test
public void testVectorHighlighter() throws Exception {
Directory dir = new RAMDirectory();
IndexWriter indexWriter =
new IndexWriter(dir, Lucene.STANDARD_ANALYZER, true, IndexWriter.MaxFieldLength.UNLIMITED);
indexWriter.addDocument(
doc()
.add(field("_id", "1"))
.add(
field(
"content",
"the big bad dog",
Field.Store.YES,
Field.Index.ANALYZED,
Field.TermVector.WITH_POSITIONS_OFFSETS))
.build());
IndexReader reader = indexWriter.getReader();
IndexSearcher searcher = new IndexSearcher(reader);
TopDocs topDocs = searcher.search(new TermQuery(new Term("_id", "1")), 1);
assertThat(topDocs.totalHits, equalTo(1));
FastVectorHighlighter highlighter = new FastVectorHighlighter();
String fragment =
highlighter.getBestFragment(
highlighter.getFieldQuery(new TermQuery(new Term("content", "bad"))),
reader,
topDocs.scoreDocs[0].doc,
"content",
30);
assertThat(fragment, notNullValue());
System.out.println(fragment);
}
/**
* Generates a list of Highlighted query fragments for each item in a list of documents, or
* returns null if highlighting is disabled.
*
* @param docs query results
* @param query the query
* @param req the current request
* @param defaultFields default list of fields to summarize
* @return NamedList containing a NamedList for each document, which in turns contains sets
* (field, summary) pairs.
*/
@Override
@SuppressWarnings("unchecked")
public NamedList<Object> doHighlighting(
DocList docs, Query query, SolrQueryRequest req, String[] defaultFields) throws IOException {
SolrParams params = req.getParams();
if (!isHighlightingEnabled(params)) return null;
SolrIndexSearcher searcher = req.getSearcher();
IndexSchema schema = searcher.getSchema();
NamedList fragments = new SimpleOrderedMap();
String[] fieldNames = getHighlightFields(query, req, defaultFields);
Set<String> fset = new HashSet<String>();
{
// pre-fetch documents using the Searcher's doc cache
for (String f : fieldNames) {
fset.add(f);
}
// fetch unique key if one exists.
SchemaField keyField = schema.getUniqueKeyField();
if (null != keyField) fset.add(keyField.getName());
}
// get FastVectorHighlighter instance out of the processing loop
FastVectorHighlighter fvh =
new FastVectorHighlighter(
// FVH cannot process hl.usePhraseHighlighter parameter per-field basis
params.getBool(HighlightParams.USE_PHRASE_HIGHLIGHTER, true),
// FVH cannot process hl.requireFieldMatch parameter per-field basis
params.getBool(HighlightParams.FIELD_MATCH, false));
fvh.setPhraseLimit(params.getInt(HighlightParams.PHRASE_LIMIT, Integer.MAX_VALUE));
FieldQuery fieldQuery = fvh.getFieldQuery(query, searcher.getIndexReader());
// Highlight each document
DocIterator iterator = docs.iterator();
for (int i = 0; i < docs.size(); i++) {
int docId = iterator.nextDoc();
Document doc = searcher.doc(docId, fset);
NamedList docSummaries = new SimpleOrderedMap();
for (String fieldName : fieldNames) {
fieldName = fieldName.trim();
if (useFastVectorHighlighter(params, schema, fieldName))
doHighlightingByFastVectorHighlighter(
fvh, fieldQuery, req, docSummaries, docId, doc, fieldName);
else doHighlightingByHighlighter(query, req, docSummaries, docId, doc, fieldName);
}
String printId = schema.printableUniqueKey(doc);
fragments.add(printId == null ? null : printId, docSummaries);
}
return fragments;
}
private void doHighlightingByFastVectorHighlighter(
FastVectorHighlighter highlighter,
FieldQuery fieldQuery,
SolrQueryRequest req,
NamedList docSummaries,
int docId,
Document doc,
String fieldName)
throws IOException {
SolrParams params = req.getParams();
SolrFragmentsBuilder solrFb = getSolrFragmentsBuilder(fieldName, params);
String[] snippets =
highlighter.getBestFragments(
fieldQuery,
req.getSearcher().getIndexReader(),
docId,
fieldName,
params.getFieldInt(fieldName, HighlightParams.FRAGSIZE, 100),
params.getFieldInt(fieldName, HighlightParams.SNIPPETS, 1),
getFragListBuilder(fieldName, params),
getFragmentsBuilder(fieldName, params),
solrFb.getPreTags(params, fieldName),
solrFb.getPostTags(params, fieldName),
getEncoder(fieldName, params));
if (snippets != null && snippets.length > 0) docSummaries.add(fieldName, snippets);
else alternateField(docSummaries, params, doc, fieldName);
}
public List<LuceneSearchResult> search(String keyword, boolean highlight, int size)
throws IOException, ParseException {
IndexReader reader = luceneIndex.reader();
try {
IndexSearcher searcher = new IndexSearcher(reader);
Analyzer analyzer = new IKAnalyzer();
MultiFieldQueryParser parser =
new MultiFieldQueryParser(Version.LUCENE_4_9, fields, analyzer, boosts);
// 将关键字包装成Query对象
Query query = parser.parse(keyword);
TopDocs results = searcher.search(query, size);
FragListBuilder fragListBuilder = new SimpleFragListBuilder();
FragmentsBuilder fragmentsBuilder =
new ScoreOrderFragmentsBuilder(
BaseFragmentsBuilder.COLORED_PRE_TAGS, BaseFragmentsBuilder.COLORED_POST_TAGS);
FastVectorHighlighter fvh =
new FastVectorHighlighter(true, true, fragListBuilder, fragmentsBuilder);
FieldQuery fq = fvh.getFieldQuery(query);
// System.out.println("命中--》" + results.totalHits);
List<LuceneSearchResult> searchResults = new ArrayList<LuceneSearchResult>();
for (ScoreDoc sd : results.scoreDocs) {
// 当查询不到高亮信息时，返回内容为Null
// String highContent = fvh.getBestFragment(fq, reader, sd.doc, "content", 100);
// System.out.println("highContent-->" + highContent);
String highTitle = null;
if (highlight) {
fvh.getBestFragment(fq, reader, sd.doc, "title", 100);
if (highTitle == null) {
Document doc = searcher.doc(sd.doc);
/** 如果高亮内容为null，那么表示标题没有需要高亮的内容，那么赋值为原有标题 */
highTitle = doc.get("title");
}
} else {
highTitle = searcher.doc(sd.doc).get("title");
}
String id = searcher.doc(sd.doc).get("id");
searchResults.add(new LuceneSearchResult(id, highTitle));
}
return searchResults;
} finally {
reader.close();
}
}
@Test
public void testVectorHighlighterPrefixQuery() throws Exception {
Directory dir = new RAMDirectory();
IndexWriter indexWriter =
new IndexWriter(dir, Lucene.STANDARD_ANALYZER, true, IndexWriter.MaxFieldLength.UNLIMITED);
indexWriter.addDocument(
doc()
.add(field("_id", "1"))
.add(
field(
"content",
"the big bad dog",
Field.Store.YES,
Field.Index.ANALYZED,
Field.TermVector.WITH_POSITIONS_OFFSETS))
.build());
IndexReader reader = indexWriter.getReader();
IndexSearcher searcher = new IndexSearcher(reader);
TopDocs topDocs = searcher.search(new TermQuery(new Term("_id", "1")), 1);
assertThat(topDocs.totalHits, equalTo(1));
FastVectorHighlighter highlighter = new FastVectorHighlighter();
PrefixQuery prefixQuery = new PrefixQuery(new Term("content", "ba"));
assertThat(
prefixQuery.getRewriteMethod().getClass().getName(),
equalTo(PrefixQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT.getClass().getName()));
String fragment =
highlighter.getBestFragment(
highlighter.getFieldQuery(prefixQuery),
reader,
topDocs.scoreDocs[0].doc,
"content",
30);
assertThat(fragment, nullValue());
prefixQuery.setRewriteMethod(PrefixQuery.SCORING_BOOLEAN_QUERY_REWRITE);
Query rewriteQuery = prefixQuery.rewrite(reader);
fragment =
highlighter.getBestFragment(
highlighter.getFieldQuery(rewriteQuery),
reader,
topDocs.scoreDocs[0].doc,
"content",
30);
assertThat(fragment, notNullValue());
System.out.println(fragment);
// now check with the custom field query
prefixQuery = new PrefixQuery(new Term("content", "ba"));
assertThat(
prefixQuery.getRewriteMethod().getClass().getName(),
equalTo(PrefixQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT.getClass().getName()));
CustomFieldQuery.reader.set(reader);
fragment =
highlighter.getBestFragment(
new CustomFieldQuery(prefixQuery, highlighter),
reader,
topDocs.scoreDocs[0].doc,
"content",
30);
assertThat(fragment, notNullValue());
System.out.println(fragment);
}
