Example usage for org.apache.lucene.document Field setIntValue

List of usage examples for org.apache.lucene.document Field setIntValue

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.document.*
  5. Field
  6. setIntValue

Introduction

In this page you can find the example usage for org.apache.lucene.document Field setIntValue.

Prototype

public void setIntValue(int value)

Source Link

Document

Expert: change the value of this field.

Usage

From source file:com.bewsia.script.LuceneHandler.java

License:Open Source License

protected void write(SEntity entity, Document doc) {
    String schema = entity.getSchema();
    if (schema == null)
        schema = "";
    String[] fields = schema.split("\\|");
    for (int i = 0; i < fields.length && i + 1 < fields.length; i += 2) {
        String kind = fields[i];//from   w w  w .  jav  a 2s .com
        String fname = fields[i + 1];
        if (SEntity.STRING.equalsIgnoreCase(kind)) {
            Field field = new Field(fname, entity.getString(fname), Store.YES, Index.NOT_ANALYZED_NO_NORMS);
            doc.add(field);
        } else if (SEntity.DOUBLE.equalsIgnoreCase(kind)) {
            NumericField field = new NumericField(fname, Store.YES, true);
            field.setDoubleValue(entity.getDouble(fname));
            doc.add(field);
        } else if (SEntity.FLOAT.equalsIgnoreCase(kind)) {
            NumericField field = new NumericField(fname, Store.YES, true);
            field.setFloatValue(entity.getFloat(fname));
            doc.add(field);
        } else if (SEntity.INTEGER.equalsIgnoreCase(kind)) {
            NumericField field = new NumericField(fname, Store.YES, true);
            field.setIntValue(entity.getInteger(fname));
            doc.add(field);
        } else if (SEntity.LONG.equalsIgnoreCase(kind)) {
            NumericField field = new NumericField(fname, Store.YES, true);
            field.setLongValue(entity.getLong(fname));
            doc.add(field);
        } else if (SEntity.ANALYZED.equalsIgnoreCase(kind)) {
            Field field = new Field(fname, entity.getString(fname), Store.YES, Index.ANALYZED);
            doc.add(field);
        }
    }
}

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);
    //      }//ww  w .  ja  v a 2s.  c o m

    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:de.tudarmstadt.lt.lm.app.GenerateNgramIndex.java

License:Apache License

public void create_ngram_index(File ngram_joined_counts_file) throws IOException {
    File index_dir = new File(_index_dir, "ngram");
    if (index_dir.exists()) {
        LOG.info("Ngram index already exists in directory '{}'.", index_dir.getAbsolutePath());
        if (_overwrite) {
            LOG.info("Overwriting index '{}',", index_dir);
            index_dir.delete();/*from  w  w  w .j a va  2 s  .c  o  m*/
        } else
            return;
    }
    index_dir.mkdirs();

    Analyzer analyzer = new KeywordAnalyzer();
    IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_4_9, analyzer);
    iwc.setOpenMode(OpenMode.CREATE);
    // use 80 percent of the available total memory
    double total_mem_mb = (double) Runtime.getRuntime().maxMemory() / 1e6;
    double percentage_ram_buffer = Properties.ramBufferPercentage();
    if (percentage_ram_buffer > 0) {
        double percentage_ram_buffer_mb = total_mem_mb * percentage_ram_buffer;
        LOG.info(String.format("Setting ram buffer size to %.2f MB (%.2f%% from %.2f MB)",
                percentage_ram_buffer_mb, percentage_ram_buffer * 100, total_mem_mb));
        iwc.setRAMBufferSizeMB(percentage_ram_buffer_mb);
    }

    Directory directory = new MMapDirectory(index_dir);
    IndexWriter writer_ngram = new IndexWriter(directory, iwc);

    InputStream in = new FileInputStream(ngram_joined_counts_file);
    if (ngram_joined_counts_file.getName().endsWith(".gz"))
        in = new GZIPInputStream(in);
    LineIterator iter = new LineIterator(new BufferedReader(new InputStreamReader(in, "UTF-8")));

    Document doc = new Document();
    Field f_ngram = new StringField("ngram", "", Store.YES);
    doc.add(f_ngram);
    Field f_n = new IntField("cardinality", 0, Store.YES);
    doc.add(f_n);
    Field f_word = new StringField("word", "", Store.YES);
    doc.add(f_word);
    Field f_hist = new StringField("history", "", Store.YES);
    doc.add(f_hist);
    Field f_lower = new StringField("lower", "", Store.YES);
    doc.add(f_lower);
    Field f_count = new StoredField("num", 0L);
    doc.add(f_count);

    Field[] f_follow = new Field[4];
    f_follow[0] = new StoredField("nf_s", 0L);
    doc.add(f_follow[0]);
    f_follow[1] = new StoredField("nf_N1", 0L);
    doc.add(f_follow[1]);
    f_follow[2] = new StoredField("nf_N2", 0L);
    doc.add(f_follow[2]);
    f_follow[3] = new StoredField("nf_N3", 0L);
    doc.add(f_follow[3]);
    Field[] f_precede = new Field[4];
    f_precede[0] = new StoredField("np_s", 0L);
    doc.add(f_precede[0]);
    f_precede[1] = new StoredField("np_N1", 0L);
    doc.add(f_precede[1]);
    f_precede[2] = new StoredField("np_N2", 0L);
    doc.add(f_precede[2]);
    f_precede[3] = new StoredField("np_N3", 0L);
    doc.add(f_precede[3]);
    Field[] f_followerprecede = new Field[4];
    f_followerprecede[0] = new StoredField("nfp_s", 0L);
    doc.add(f_followerprecede[0]);
    f_followerprecede[1] = new StoredField("nfp_N1", 0L);
    doc.add(f_followerprecede[1]);
    f_followerprecede[2] = new StoredField("nfp_N2", 0L);
    doc.add(f_followerprecede[2]);
    f_followerprecede[3] = new StoredField("nfp_N3", 0L);
    doc.add(f_followerprecede[3]);

    Long[][] N = new Long[][] { { 0L, 0L, 0L, 0L, 0L, 0L } };
    Long[] S = new Long[] { 0L };
    long c = 0;
    while (iter.hasNext()) {
        if (++c % 100000 == 0)
            LOG.info("Adding {}'th ngram.", c);
        String line = iter.next();
        try {
            String[] splits = de.tudarmstadt.lt.utilities.StringUtils.rtrim(line).split("\t");
            String ngram_str = splits[0];
            if (de.tudarmstadt.lt.utilities.StringUtils.trim(ngram_str).isEmpty()) {
                LOG.warn("Ngram is empty, skipping line {}: '{}' (file '{}').", c, line,
                        ngram_joined_counts_file);
                continue;
            }

            List<String> ngram = Arrays.asList(ngram_str.split(" "));
            long num = Long.parseLong(splits[1]);
            int n = ngram.size();

            f_ngram.setStringValue(ngram_str);
            f_n.setIntValue(n);
            f_word.setStringValue(ngram.get(ngram.size() - 1));
            f_hist.setStringValue(StringUtils.join(ngram.subList(0, ngram.size() - 1), " "));
            f_lower.setStringValue(StringUtils.join(ngram.subList(1, ngram.size()), " "));
            f_count.setLongValue(num);

            for (int j = 0; j < f_follow.length; j++) {
                f_follow[j].setLongValue(0L);
                f_precede[j].setLongValue(0L);
                f_followerprecede[j].setLongValue(0L);
            }

            if (splits.length > 2 && !splits[2].isEmpty()) {
                // precede or follow or followerprecede
                String[] splits_ = splits[2].split(":");
                String type = splits_[0];
                String[] count_values = splits_[1].split(",");
                if (count_values.length > 0) {
                    if ("n_f".equals(type))
                        f_follow[0].setLongValue(Long.parseLong(count_values[0]));
                    else if ("n_p".equals(type))
                        f_precede[0].setLongValue(Long.parseLong(count_values[0]));
                    else if ("n_fp".equals(type))
                        f_followerprecede[0].setLongValue(Long.parseLong(count_values[0]));
                }
                for (int i = 1; i < count_values.length; i++) {
                    if ("n_f".equals(type))
                        f_follow[i].setLongValue(Long.parseLong(count_values[i]));
                    else if ("n_p".equals(type))
                        f_precede[i].setLongValue(Long.parseLong(count_values[i]));
                    else if ("n_fp".equals(type))
                        f_followerprecede[i].setLongValue(Long.parseLong(count_values[i]));
                }
            }
            if (splits.length > 3 && !splits[3].isEmpty()) {
                // should be follow or followerprecede
                String[] splits_ = splits[3].split(":");
                String type = splits_[0];
                String[] count_values = splits_[1].split(",");
                if (count_values.length > 0) {
                    if ("n_f".equals(type))
                        f_follow[0].setLongValue(Long.parseLong(count_values[0]));
                    else if ("n_p".equals(type))
                        f_precede[0].setLongValue(Long.parseLong(count_values[0]));
                    else if ("n_fp".equals(type))
                        f_followerprecede[0].setLongValue(Long.parseLong(count_values[0]));
                }
                for (int i = 1; i < count_values.length; i++) {
                    if ("n_f".equals(type))
                        f_follow[i].setLongValue(Long.parseLong(count_values[i]));
                    else if ("n_p".equals(type))
                        f_precede[i].setLongValue(Long.parseLong(count_values[i]));
                    else if ("n_fp".equals(type))
                        f_followerprecede[i].setLongValue(Long.parseLong(count_values[i]));
                }
            }
            if (splits.length > 4 && !splits[4].isEmpty()) {
                // should be followerprecede
                String[] splits_ = splits[4].split(":");
                String type = splits_[0];
                String[] count_values = splits_[1].split(",");
                if (count_values.length > 0) {
                    if ("n_f".equals(type))
                        f_follow[0].setLongValue(Long.parseLong(count_values[0]));
                    else if ("n_p".equals(type))
                        f_precede[0].setLongValue(Long.parseLong(count_values[0]));
                    else if ("n_fp".equals(type))
                        f_followerprecede[0].setLongValue(Long.parseLong(count_values[0]));
                }
                for (int i = 1; i < count_values.length; i++) {
                    if ("n_f".equals(type))
                        f_follow[i].setLongValue(Long.parseLong(count_values[i]));
                    else if ("n_p".equals(type))
                        f_precede[i].setLongValue(Long.parseLong(count_values[i]));
                    else if ("n_fp".equals(type))
                        f_followerprecede[i].setLongValue(Long.parseLong(count_values[i]));
                }
            }

            writer_ngram.addDocument(doc);

            while (N.length <= n) {
                N = ArrayUtils.getConcatinatedArray(N, new Long[][] { { 0L, 0L, 0L, 0L, 0L, 0L } });
                S = ArrayUtils.getConcatinatedArray(S, new Long[] { 0L });
            }

            if (num == 1L)
                N[n][1]++;
            else if (num == 2L)
                N[n][2]++;
            else if (num == 3L)
                N[n][3]++;
            else if (num == 4L)
                N[n][4]++;
            else
                N[n][5]++;
            N[n][0]++;
            S[n] += num;

        } catch (Exception e) {
            LOG.error("Could not process line '{}' in file '{}:{}', malformed line.", line,
                    ngram_joined_counts_file, c, e);
        }
    }

    writer_ngram.forceMergeDeletes();
    writer_ngram.commit();
    writer_ngram.close();

    StringBuilder b = new StringBuilder(String.format(
            "#%n# Number of times where an ngram occurred: %n#  at_least_once, exactly_once, exactly_twice, exactly_three_times, exactly_four_times, five_times_or_more.%n#%nmax_n=%d%nmax_c=6%n",
            N.length - 1));
    for (int n = 1; n < N.length; n++)
        b.append(String.format("n%d=%s%n", n, StringUtils.join(N[n], ',')));
    for (int n = 1; n < S.length; n++)
        b.append(String.format("s%d=%d%n", n, S[n]));
    FileUtils.writeStringToFile(new File(_index_dir, "__sum_ngrams__"), b.toString());

}

From source file:org.apache.solr.legacy.TestLegacyField.java

License:Apache License

public void testLegacyIntField() throws Exception {
    Field fields[] = new Field[] { new LegacyIntField("foo", 5, Field.Store.NO),
            new LegacyIntField("foo", 5, Field.Store.YES) };

    for (Field field : fields) {
        trySetByteValue(field);// ww w  .j a  v  a  2  s.  c o  m
        trySetBytesValue(field);
        trySetBytesRefValue(field);
        trySetDoubleValue(field);
        field.setIntValue(6); // ok
        trySetFloatValue(field);
        trySetLongValue(field);
        trySetReaderValue(field);
        trySetShortValue(field);
        trySetStringValue(field);
        trySetTokenStreamValue(field);

        assertEquals(6, field.numericValue().intValue());
    }
}

From source file:org.apache.solr.legacy.TestLegacyField.java

License:Apache License

private void trySetIntValue(Field f) {
    expectThrows(IllegalArgumentException.class, () -> {
        f.setIntValue(Integer.MAX_VALUE);
    });//from  w w  w  .  j  ava  2s .  co  m
}

From source file:org.lukhnos.lucenestudy.Indexer.java

License:MIT License

public void addDocuments(List<Document> docs) throws IOException {
    // Reuse doc and field instances. See http://wiki.apache.org/lucene-java/ImproveIndexingSpeed
    Field titleField = new TextField(TITLE_FIELD_NAME, "", Field.Store.YES);
    Field titleDocsValueField = new SortedDocValuesField(TITLE_FIELD_NAME, new BytesRef(0));
    Field yearField = new IntField(YEAR_FIELD_NAME, 0, Field.Store.YES);
    Field yearDocsValueField = new NumericDocValuesField(YEAR_FIELD_NAME, 0L);
    Field ratingField = new IntField(RATING_FIELD_NAME, 0, Field.Store.YES);
    Field ratingDocsValueField = new NumericDocValuesField(RATING_FIELD_NAME, 0L);
    Field positiveField = new IntField(POSITIVE_FIELD_NAME, 0, Field.Store.YES);
    Field reviewField = new TextField(REVIEW_FIELD_NAME, "", Field.Store.YES);
    Field sourceField = new StringField(SOURCE_FIELD_NAME, "", Field.Store.YES);

    for (Document doc : docs) {
        org.apache.lucene.document.Document luceneDoc = new org.apache.lucene.document.Document();

        if (doc.title != null && !doc.title.isEmpty()) {
            titleField.setStringValue(doc.title);
            luceneDoc.add(titleField);//from   w  ww.  j  ava2s.  com

            titleDocsValueField.setBytesValue(new BytesRef(doc.title));
            luceneDoc.add(titleDocsValueField);
        }

        yearField.setIntValue(doc.year);
        luceneDoc.add(yearField);

        yearDocsValueField.setLongValue((long) doc.year);
        luceneDoc.add(yearDocsValueField);

        ratingField.setIntValue(doc.rating);
        luceneDoc.add(ratingField);

        ratingDocsValueField.setLongValue((long) doc.rating);
        luceneDoc.add(ratingDocsValueField);

        positiveField.setIntValue(doc.positive ? 1 : 0);
        luceneDoc.add(positiveField);

        if (doc.review != null && !doc.review.isEmpty()) {
            reviewField.setStringValue(doc.review);
            luceneDoc.add(reviewField);
        }

        if (doc.source != null && !doc.source.isEmpty()) {
            sourceField.setStringValue(doc.source);
            luceneDoc.add(sourceField);
        }

        indexWriter.addDocument(luceneDoc);
    }

    indexWriter.commit();
}

From source file:suonos.lucene.fields.IndexedField.java

License:Apache License

public void setValue(Field field, Object value) {
    if (javaType == String.class) {
        field.setStringValue((String) value);

    } else if (javaType == Double.class) {
        field.setDoubleValue((Double) value);

    } else if (javaType == Float.class) {
        field.setFloatValue((Float) value);

    } else if (javaType == Integer.class) {
        field.setIntValue((Integer) value);

    } else if (javaType == Long.class) {
        field.setLongValue((Long) value);

    } else if (javaType == Boolean.class) {
        field.setStringValue(getBoolValue(value));

    } else if (javaType == Date.class) {
        field.setLongValue(((Date) value).getTime());

    } else if (javaType == Byte[].class) {
        field.setBytesValue((byte[]) value);
    }/*w  w  w.ja  v a  2  s.co  m*/

    throw Validate.notAllowed("");
}

From source file:suonos.lucene.Statement.java

License:Apache License

public void saveObject(StoreObject object) throws IOException {

    openSharedWriter();//from  w  w w  .  j  ava 2s.  c  o m

    Document doc = new Document();
    Field fld;

    if (object.getId() == null) {
        object.setId(Uids.newUID());
        log.debug("New UID {}", object.getId());
    }

    // Update date.
    //
    fld = context.update$_field();
    fld.setIntValue(MTime.fromCurrentTime());
    doc.add(fld);

    // Document type.
    //
    fld = context.type$_field();
    fld.setStringValue(object.getClass().getSimpleName());
    doc.add(fld);

    // Document object serialized in json format and compressed using
    // snappy.
    //
    fld = context.obj$_field();
    fld.setBytesValue(Snappy.compress(serializeToJson(object).getBytes()));
    doc.add(fld);

    ModelType modelType = context.getModelType(object.getClass());

    modelType.saveToLuceneDoc(context, object, doc);

    Term term = new Term("id", object.getId());

    indexWriter().updateDocument(term, doc);

    // commit();
    // object = queryObject(object.getClass(), object.getUid()).getObject();
}