private TopDocsName facetsWithSearch(String query) throws IOException, ParseException {
FacetsCollector fc = new FacetsCollector();
ComplexPhraseQueryParser queryParser =
new ComplexPhraseQueryParser("content", new StandardAnalyzer());
Query luceneQuery = queryParser.parse(query);
TopDocs docs = FacetsCollector.search(indexSearcher, luceneQuery, 400, fc);
List<TopDocName> topDocNames = new ArrayList<TopDocName>();
for (ScoreDoc scoreDoc : docs.scoreDocs) {
String filename = indexSearcher.doc(scoreDoc.doc).get("filename");
float score = scoreDoc.score;
TopDocName docname = new TopDocName(score, filename.substring(0, filename.length()));
topDocNames.add(docname);
}
List<FacetResult> facetResults = new ArrayList<FacetResult>();
// Count both "Publish Date" and "Author" dimensions
Facets facets = new FastTaxonomyFacetCounts(taxoReader, taxoConfig, fc);
facetResults.add(facets.getTopChildren(11, "person"));
facetResults.add(facets.getTopChildren(20, "objects"));
TopDocsName results = new TopDocsName(1.0f, topDocNames, facetResults);
return results;
}
/** User runs a query and aggregates facets by summing their association values. */
private List<FacetResult> sumAssociations() throws IOException {
DirectoryReader indexReader = DirectoryReader.open(indexDir);
IndexSearcher searcher = new IndexSearcher(indexReader);
TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
FacetsCollector fc = new FacetsCollector();
// MatchAllDocsQuery is for "browsing" (counts facets
// for all non-deleted docs in the index); normally
// you'd use a "normal" query:
FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, fc);
Facets tags = new TaxonomyFacetSumIntAssociations("$tags", taxoReader, config, fc);
Facets genre = new TaxonomyFacetSumFloatAssociations("$genre", taxoReader, config, fc);
// Retrieve results
List<FacetResult> results = new ArrayList<>();
results.add(tags.getTopChildren(10, "tags"));
results.add(genre.getTopChildren(10, "genre"));
indexReader.close();
taxoReader.close();
return results;
}
private List<FacetResult> facetsOnly() throws IOException {
FacetsCollector fc = new FacetsCollector();
// MatchAllDocsQuery is for "browsing" (counts facets
// for all non-deleted docs in the index); normally
// you'd use a "normal" query:
TopDocs docs = FacetsCollector.search(indexSearcher, new MatchAllDocsQuery(), 10, fc);
// indexSearcher.search(new MatchAllDocsQuery(), null /*Filter */, fc);
// Retrieve results
List<FacetResult> results = new ArrayList<FacetResult>();
System.out.println("results size: " + results.size());
// Count both "Publish Date" and "Author" dimensions
Facets facets = new FastTaxonomyFacetCounts(taxoReader, taxoConfig, fc);
results.add(facets.getTopChildren(20, "objects"));
// results.add(facets.getTopChildren(10, "Publish Date"));
List<FacetResult> result = facets.getAllDims(10);
// indexReader.close();
// taxoReader.close();
return result;
}
private Facets runFacetedSearch(Request req, User user) throws IOException, ParseException {
FacetsCollector fc = new FacetsCollector();
Query query = searchService.getQuery(req);
FacetsCollector.search(getSearcher(req, user), query, req.pageSize, fc);
// TODO: support faceting for sortedsetdocvalue based fields (e.g. from)
Facets facets = new LongRangeFacetCounts(req.trendField.name(), fc, buildRanges(req));
return facets;
}
/**
* Create {@code TaxonomyFacetCounts}, which also counts all facet labels. Use this for a
* non-default {@link OrdinalsReader}; otherwise use {@link FastTaxonomyFacetCounts}.
*/
public TaxonomyFacetCounts(
OrdinalsReader ordinalsReader,
TaxonomyReader taxoReader,
FacetsConfig config,
FacetsCollector fc)
throws IOException {
super(ordinalsReader.getIndexFieldName(), taxoReader, config);
this.ordinalsReader = ordinalsReader;
count(fc.getMatchingDocs());
}
/** User drills down on 'tags/solr'. */
private FacetResult drillDown() throws IOException {
DirectoryReader indexReader = DirectoryReader.open(indexDir);
IndexSearcher searcher = new IndexSearcher(indexReader);
TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
// Passing no baseQuery means we drill down on all
// documents ("browse only"):
DrillDownQuery q = new DrillDownQuery(config);
// Now user drills down on Publish Date/2010:
q.add("tags", "solr");
FacetsCollector fc = new FacetsCollector();
FacetsCollector.search(searcher, q, 10, fc);
// Retrieve results
Facets facets = new TaxonomyFacetSumFloatAssociations("$genre", taxoReader, config, fc);
FacetResult result = facets.getTopChildren(10, "genre");
indexReader.close();
taxoReader.close();
return result;
}
private TopDocsName drillDown(Map<String, String> facets_value) throws IOException {
// Passing no baseQuery means we drill down on all
// documents ("browse only"):
DrillDownQuery q = new DrillDownQuery(taxoConfig);
for (Map.Entry<String, String> entry : facets_value.entrySet()) {
q.add(entry.getKey(), entry.getValue());
}
FacetsCollector fc = new FacetsCollector();
TopDocs docs = FacetsCollector.search(indexSearcher, q, 100000, fc);
List<TopDocName> topDocNames = new ArrayList<TopDocName>();
for (ScoreDoc scoreDoc : docs.scoreDocs) {
String filename = indexSearcher.doc(scoreDoc.doc).get("filename");
String videoID = indexSearcher.doc(scoreDoc.doc).get("videoID");
String frameNumber = indexSearcher.doc(scoreDoc.doc).get("frameNumber");
float score = scoreDoc.score;
TopDocName docname = new TopDocName(score, filename, videoID, frameNumber);
topDocNames.add(docname);
}
List<FacetResult> facetResults = new ArrayList<FacetResult>();
// Count both "Publish Date" and "Author" dimensions
Facets facets = new FastTaxonomyFacetCounts(taxoReader, taxoConfig, fc);
facetResults.add(facets.getTopChildren(11, "person"));
facetResults.add(facets.getTopChildren(20, "objects"));
facetResults.add(facets.getTopChildren(200, "background"));
TopDocsName results = new TopDocsName(1.0f, topDocNames, facetResults);
return results;
}