Example usage for org.apache.lucene.facet.taxonomy.directory DirectoryTaxonomyReader DirectoryTaxonomyReader

List of usage examples for org.apache.lucene.facet.taxonomy.directory DirectoryTaxonomyReader DirectoryTaxonomyReader

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.facet.taxonomy.directory.*
  5. DirectoryTaxonomyReader
  6. DirectoryTaxonomyReader

Introduction

In this page you can find the example usage for org.apache.lucene.facet.taxonomy.directory DirectoryTaxonomyReader DirectoryTaxonomyReader.

Prototype

public DirectoryTaxonomyReader(DirectoryTaxonomyWriter taxoWriter) throws IOException

Source Link

Document

Opens a DirectoryTaxonomyReader over the given DirectoryTaxonomyWriter (for NRT).

Usage

From source file:com.chimpler.example.FacetLuceneAdvancedSearcher.java

License:Apache License

public static void main(String args[]) throws Exception {
    if (args.length != 5) {
        System.err.println(/*  w  w w  .  j a va 2s.  co m*/
                "Parameters: [index directory] [taxonomy directory] [query] [field drilldown] [value drilldown]");
        System.exit(1);
    }

    String indexDirectory = args[0];
    String taxonomyDirectory = args[1];
    String query = args[2];
    String fieldDrilldown = args[3];
    String valueDrilldown = args[4];

    IndexReader indexReader = DirectoryReader.open(FSDirectory.open(new File(indexDirectory)));
    IndexSearcher indexSearcher = new IndexSearcher(indexReader);

    TaxonomyReader taxonomyReader = new DirectoryTaxonomyReader(FSDirectory.open(new File(taxonomyDirectory)));

    CategoryPath drillDownCategoryPath = new CategoryPath(fieldDrilldown + "/" + valueDrilldown, '/');

    FacetSearchParams searchParams = new FacetSearchParams();
    searchParams.facetRequests.add(new CountFacetRequest(new CategoryPath("author"), 100));
    searchParams.facetRequests.add(new CountFacetRequest(new CategoryPath("book_category"), 100));
    searchParams.facetRequests.add(new CountFacetRequest(drillDownCategoryPath, 100));

    ComplexPhraseQueryParser queryParser = new ComplexPhraseQueryParser(LUCENE_VERSION, "title",
            new StandardAnalyzer(LUCENE_VERSION));

    Query luceneQuery = queryParser.parse(query);
    //luceneQuery = DrillDownQuery.query(luceneQuery, drillDownCategoryPath);

    // Collectors to get top results and facets
    TopScoreDocCollector topScoreDocCollector = TopScoreDocCollector.create(10, true);
    FacetsCollector facetsCollector = FacetsCollector.create(searchParams, indexReader, taxonomyReader);
    indexSearcher.search(luceneQuery, MultiCollector.wrap(topScoreDocCollector, facetsCollector));
    System.out.println("Found:");

    for (ScoreDoc scoreDoc : topScoreDocCollector.topDocs().scoreDocs) {
        Document document = indexReader.document(scoreDoc.doc);
        System.out.printf("- book: id=%s, title=%s, book_category=%s, authors=%s, score=%f\n",
                document.get("id"), document.get("title"), document.get("book_category"),
                document.get("authors"), scoreDoc.score);
    }

    System.out.println("Facets:");
    for (FacetResult facetResult : facetsCollector.getFacetResults()) {
        System.out.println("- " + facetResult.getFacetResultNode().label);
        for (FacetResultNode facetResultNode : facetResult.getFacetResultNode().subResults) {
            System.out.printf("    - %s (%f)\n", facetResultNode.label.toString(), facetResultNode.value);
            for (FacetResultNode subFacetResultNode : facetResultNode.subResults) {
                System.out.printf("        - %s (%f)\n", subFacetResultNode.label.toString(),
                        subFacetResultNode.value);
            }
        }
    }
    taxonomyReader.close();
    indexReader.close();
}

From source file:com.chimpler.example.FacetLuceneIndexer.java

License:Apache License

public static void main(String args[]) throws Exception {
    //      if (args.length != 3) {
    //         System.err.println("Parameters: [index directory] [taxonomy directory] [json file]");
    //         System.exit(1);
    //      }/* w  w  w. j av a 2s  .  c  om*/

    String indexDirectory = "index";
    String taxonomyDirectory = "taxonomy";
    String jsonFileName = "/home/qiuqiang/workspace/facet-lucene-example/books.json";

    IndexWriterConfig writerConfig = new IndexWriterConfig(LUCENE_VERSION,
            new WhitespaceAnalyzer(LUCENE_VERSION));
    writerConfig.setOpenMode(OpenMode.APPEND);
    IndexWriter indexWriter = new IndexWriter(FSDirectory.open(new File(indexDirectory)), writerConfig);

    TaxonomyWriter taxonomyWriter = new DirectoryTaxonomyWriter(MMapDirectory.open(new File(taxonomyDirectory)),
            OpenMode.APPEND);

    TaxonomyReader taxonomyReader = new DirectoryTaxonomyReader(FSDirectory.open(new File(taxonomyDirectory)));

    String content = IOUtils.toString(new FileInputStream(jsonFileName));
    JSONArray bookArray = new JSONArray(content);

    Field idField = new IntField("id", 0, Store.YES);
    Field titleField = new TextField("title", "", Store.YES);
    Field authorsField = new TextField("authors", "", Store.YES);
    Field bookCategoryField = new TextField("book_category", "", Store.YES);

    indexWriter.deleteAll();

    FacetFields facetFields = new FacetFields(taxonomyWriter);

    for (int i = 0; i < bookArray.length(); i++) {
        Document document = new Document();

        JSONObject book = bookArray.getJSONObject(i);
        int id = book.getInt("id");
        String title = book.getString("title");
        String bookCategory = book.getString("book_category");

        List<CategoryPath> categoryPaths = new ArrayList<CategoryPath>();

        String authorsString = "";
        JSONArray authors = book.getJSONArray("authors");
        for (int j = 0; j < authors.length(); j++) {
            String author = authors.getString(j);
            if (j > 0) {
                authorsString += ", ";
            }
            categoryPaths.add(new CategoryPath("author", author));
            authorsString += author;
        }
        categoryPaths.add(new CategoryPath("book_category" + bookCategory, '/'));

        idField.setIntValue(id);
        titleField.setStringValue(title);
        authorsField.setStringValue(authorsString);
        bookCategoryField.setStringValue(bookCategory);

        facetFields.addFields(document, categoryPaths);

        document.add(idField);
        document.add(titleField);
        document.add(authorsField);
        document.add(bookCategoryField);

        indexWriter.addDocument(document);

        System.out.printf("Book: id=%d, title=%s, book_category=%s, authors=%s\n", id, title, bookCategory,
                authors);
    }

    taxonomyWriter.prepareCommit();
    try {
        taxonomyWriter.commit();
    } catch (Exception e) {
        taxonomyWriter.rollback();
    }

    //      taxonomyWriter.close();
    //      
    //      indexWriter.commit();
    //      indexWriter.close();

    String query = "story";

    IndexReader indexReader = DirectoryReader.open(indexWriter, false);
    IndexReader indexReader2 = DirectoryReader.open(indexWriter, false);
    System.out.println(indexReader == indexReader2);

    IndexSearcher indexSearcher = new IndexSearcher(indexReader);

    TaxonomyReader newTaxonomyReader = DirectoryTaxonomyReader.openIfChanged(taxonomyReader);
    if (newTaxonomyReader != null) {
        TaxonomyReader tmp = taxonomyReader;
        taxonomyReader = newTaxonomyReader;
        tmp.close();
    } else {
        System.out.println("null");
    }

    ArrayList<FacetRequest> facetRequests = new ArrayList<FacetRequest>();
    facetRequests.add(new CountFacetRequest(new CategoryPath("author"), 100));
    facetRequests.add(new CountFacetRequest(new CategoryPath("book_category"), 100));

    FacetSearchParams searchParams = new FacetSearchParams(facetRequests);

    ComplexPhraseQueryParser queryParser = new ComplexPhraseQueryParser(LUCENE_VERSION, "title",
            new StandardAnalyzer(LUCENE_VERSION));
    Query luceneQuery = queryParser.parse(query);

    // Collectors to get top results and facets
    TopScoreDocCollector topScoreDocCollector = TopScoreDocCollector.create(10, true);
    FacetsCollector facetsCollector = FacetsCollector.create(searchParams, indexReader, taxonomyReader);
    indexSearcher.search(luceneQuery, MultiCollector.wrap(topScoreDocCollector, facetsCollector));
    System.out.println("Found:");

    for (ScoreDoc scoreDoc : topScoreDocCollector.topDocs().scoreDocs) {
        Document document = indexReader.document(scoreDoc.doc);
        System.out.printf("- book: id=%s, title=%s, book_category=%s, authors=%s, score=%f\n",
                document.get("id"), document.get("title"), document.get("book_category"),
                document.get("authors"), scoreDoc.score);
    }

    System.out.println("Facets:");
    for (FacetResult facetResult : facetsCollector.getFacetResults()) {
        System.out.println("- " + facetResult.getFacetResultNode().label);
        for (FacetResultNode facetResultNode : facetResult.getFacetResultNode().subResults) {
            System.out.printf("    - %s (%f)\n", facetResultNode.label.toString(), facetResultNode.value);
            for (FacetResultNode subFacetResultNode : facetResultNode.subResults) {
                System.out.printf("        - %s (%f)\n", subFacetResultNode.label.toString(),
                        subFacetResultNode.value);
            }
        }
    }
    taxonomyReader.close();
    indexReader.close();

    taxonomyWriter.commit();
    taxonomyWriter.close();

    indexWriter.commit();
    indexWriter.close();

}

From source file:com.chimpler.example.FacetLuceneSearcher.java

License:Apache License

public static void main(String args[]) throws Exception {
    //      if (args.length != 3) {
    //         System.err.println("Parameters: [index directory] [taxonomy directory] [query]");
    //         System.exit(1);
    //      }//from w  w  w . j  av a  2s .  c o  m

    String indexDirectory = "index";
    String taxonomyDirectory = "taxonomy";
    String query = "story";

    IndexReader indexReader = DirectoryReader.open(FSDirectory.open(new File(indexDirectory)));
    IndexSearcher indexSearcher = new IndexSearcher(indexReader);

    TaxonomyReader taxonomyReader = new DirectoryTaxonomyReader(FSDirectory.open(new File(taxonomyDirectory)));

    ArrayList<FacetRequest> facetRequests = new ArrayList<FacetRequest>();
    facetRequests.add(new CountFacetRequest(new CategoryPath("author"), 100));
    facetRequests.add(new CountFacetRequest(new CategoryPath("book_category"), 100));

    FacetSearchParams searchParams = new FacetSearchParams(facetRequests);

    ComplexPhraseQueryParser queryParser = new ComplexPhraseQueryParser(LUCENE_VERSION, "title",
            new StandardAnalyzer(LUCENE_VERSION));
    Query luceneQuery = queryParser.parse(query);

    // Collectors to get top results and facets
    TopScoreDocCollector topScoreDocCollector = TopScoreDocCollector.create(10, true);
    FacetsCollector facetsCollector = FacetsCollector.create(searchParams, indexReader, taxonomyReader);
    indexSearcher.search(luceneQuery, MultiCollector.wrap(topScoreDocCollector, facetsCollector));
    System.out.println("Found:");

    for (ScoreDoc scoreDoc : topScoreDocCollector.topDocs().scoreDocs) {
        Document document = indexReader.document(scoreDoc.doc);
        System.out.printf("- book: id=%s, title=%s, book_category=%s, authors=%s, score=%f\n",
                document.get("id"), document.get("title"), document.get("book_category"),
                document.get("authors"), scoreDoc.score);
    }

    System.out.println("Facets:");
    for (FacetResult facetResult : facetsCollector.getFacetResults()) {
        System.out.println("- " + facetResult.getFacetResultNode().label);
        for (FacetResultNode facetResultNode : facetResult.getFacetResultNode().subResults) {
            System.out.printf("    - %s (%f)\n", facetResultNode.label.toString(), facetResultNode.value);
            for (FacetResultNode subFacetResultNode : facetResultNode.subResults) {
                System.out.printf("        - %s (%f)\n", subFacetResultNode.label.toString(),
                        subFacetResultNode.value);
            }
        }
    }
    taxonomyReader.close();
    indexReader.close();
}

From source file:com.czw.search.lucene.example.facet.AssociationsFacetsExample.java

License:Apache License

/** 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();//from   w  ww .  j a v  a  2s.c  om
    taxoReader.close();

    return results;
}

From source file:com.czw.search.lucene.example.facet.AssociationsFacetsExample.java

License:Apache License

/** 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();//from   ww  w  .j  ava  2 s .c o  m
    taxoReader.close();

    return result;
}

From source file:com.czw.search.lucene.example.facet.ExpressionAggregationFacetsExample.java

License:Apache License

/** User runs a query and aggregates facets. */
private FacetResult search() throws IOException, ParseException {
    DirectoryReader indexReader = DirectoryReader.open(indexDir);
    IndexSearcher searcher = new IndexSearcher(indexReader);
    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);

    // Aggregate categories by an expression that combines the document's score
    // and its popularity field
    Expression expr = JavascriptCompiler.compile("_score * sqrt(popularity)");
    SimpleBindings bindings = new SimpleBindings();
    bindings.add(new SortField("_score", SortField.Type.SCORE)); // the score of the document
    bindings.add(new SortField("popularity", SortField.Type.LONG)); // the value of the 'popularity' field

    // Aggregates the facet values
    FacetsCollector fc = new FacetsCollector(true);

    // 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);

    // Retrieve results
    Facets facets = new TaxonomyFacetSumValueSource(taxoReader, config, fc,
            expr.getDoubleValuesSource(bindings));
    FacetResult result = facets.getTopChildren(10, "A");

    indexReader.close();/*from   w w w .j  a  v a 2 s.  co  m*/
    taxoReader.close();

    return result;
}

From source file:com.czw.search.lucene.example.facet.MultiCategoryListsFacetsExample.java

License:Apache License

/** User runs a query and counts facets. */
private List<FacetResult> search() 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);

    // Retrieve results
    List<FacetResult> results = new ArrayList<>();

    // Count both "Publish Date" and "Author" dimensions
    Facets author = new FastTaxonomyFacetCounts("author", taxoReader, config, fc);
    results.add(author.getTopChildren(10, "Author"));

    Facets pubDate = new FastTaxonomyFacetCounts("pubdate", taxoReader, config, fc);
    results.add(pubDate.getTopChildren(10, "Publish Date"));

    indexReader.close();/*from w w w. j  a va2  s  .c om*/
    taxoReader.close();

    return results;
}

From source file:com.czw.search.lucene.example.facet.SimpleFacetsExample.java

License:Apache License

/**
 * User runs a query and counts facets.//from   ww  w  .  ja va 2  s. c o  m
 */
private List<FacetResult> facetsWithSearch() 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);

    // Retrieve results
    List<FacetResult> results = new ArrayList<>();

    // Count both "Publish Date" and "Author" dimensions
    Facets facets = new FastTaxonomyFacetCounts(taxoReader, config, fc);
    results.add(facets.getTopChildren(10, "Author"));
    results.add(facets.getTopChildren(10, "Publish Date"));
    results.add(facets.getTopChildren(10, "Category"));

    indexReader.close();
    taxoReader.close();

    return results;
}

From source file:com.czw.search.lucene.example.facet.SimpleFacetsExample.java

License:Apache License

/**
 * User runs a query and counts facets only without collecting the matching documents.
 *///  www  .j a v a2  s  .  c  om
private List<FacetResult> facetsOnly() 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:
    searcher.search(new MatchAllDocsQuery(), fc);

    // Retrieve results
    List<FacetResult> results = new ArrayList<>();

    // Count both "Publish Date" and "Author" dimensions
    Facets facets = new FastTaxonomyFacetCounts(taxoReader, config, fc);

    results.add(facets.getTopChildren(10, "Author"));
    results.add(facets.getTopChildren(10, "Publish Date"));
    results.add(facets.getTopChildren(10, "Category"));

    indexReader.close();
    taxoReader.close();

    return results;
}

From source file:com.czw.search.lucene.example.facet.SimpleFacetsExample.java

License:Apache License

/**
 * User drills down on 'Publish Date/2011', and we
 * return facets for 'Author'//from w ww .  ja  v a 2 s  .c om
 */
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("Publish Date", "2010");
    FacetsCollector fc = new FacetsCollector();
    FacetsCollector.search(searcher, q, 10, fc);

    // Retrieve results
    Facets facets = new FastTaxonomyFacetCounts(taxoReader, config, fc);
    FacetResult result = facets.getTopChildren(10, "Author");

    indexReader.close();
    taxoReader.close();

    return result;
}