List of usage examples for org.apache.lucene.index Fields terms
public abstract Terms terms(String field) throws IOException;
From source file:org.dkpro.tc.features.pair.core.ngram.meta.LuceneNGramCPMetaCollectorTest.java
License:Apache License
@Test public void combinedNgramPairMetaCollectorTest() throws Exception { File tmpDir = folder.newFolder(); CollectionReaderDescription reader = CollectionReaderFactory.createReaderDescription(TestPairReader.class, TestPairReader.PARAM_INPUT_FILE, "src/test/resources/data/textpairs.txt"); AnalysisEngineDescription segmenter = AnalysisEngineFactory .createEngineDescription(BreakIteratorSegmenter.class); AnalysisEngineDescription doc = AnalysisEngineFactory.createEngineDescription(DocumentModeAnnotator.class, DocumentModeAnnotator.PARAM_FEATURE_MODE, Constants.FM_PAIR); AggregateBuilder builder = new AggregateBuilder(); builder.add(segmenter, Constants.INITIAL_VIEW, Constants.PART_ONE); builder.add(doc, Constants.INITIAL_VIEW, Constants.PART_ONE); builder.add(segmenter, Constants.INITIAL_VIEW, Constants.PART_TWO); builder.add(doc, Constants.INITIAL_VIEW, Constants.PART_TWO); AnalysisEngineDescription metaCollector = AnalysisEngineFactory.createEngineDescription( LuceneNGramCPMetaCollector.class, LuceneNGramCPFE.PARAM_UNIQUE_EXTRACTOR_NAME, "123", LuceneNGramCPFE.PARAM_SOURCE_LOCATION, tmpDir, LuceneNGramPMetaCollector.PARAM_TARGET_LOCATION, tmpDir);/*from w w w . jav a 2s . c o m*/ // test fails if for-loop removed for (@SuppressWarnings("unused") JCas jcas : new JCasIterable(reader, builder.createAggregateDescription(), metaCollector)) { // System.out.println(jcas.getDocumentText().length()); } int i = 0; IndexReader index; try { index = DirectoryReader.open(FSDirectory.open(tmpDir)); Fields fields = MultiFields.getFields(index); if (fields != null) { Terms terms = fields.terms(LuceneNGramCPFE.LUCENE_NGRAM_FIELDCOMBO); if (terms != null) { TermsEnum termsEnum = terms.iterator(null); BytesRef text = null; while ((text = termsEnum.next()) != null) { // System.out.println(text.utf8ToString() + " - " + // termsEnum.totalTermFreq()); // System.out.println(termsEnum.docFreq()); // if there were multiple instances of the same ngram, // then this would be relevant if (text.utf8ToString().equals("mice_ANDcats_.")) { assertEquals(1, termsEnum.docFreq()); assertEquals(1, termsEnum.totalTermFreq()); } i++; } } } } catch (Exception e) { throw new ResourceInitializationException(e); } assertEquals(65, i); }
From source file:org.dkpro.tc.features.pair.core.ngram.meta.LuceneNGramPMetaCollectorTest.java
License:Apache License
@Test public void lucenePairNgramMetaCollectorTest() throws Exception { File tmpDir = folder.newFolder(); CollectionReaderDescription reader = CollectionReaderFactory.createReaderDescription(TestPairReader.class, TestPairReader.PARAM_INPUT_FILE, "src/test/resources/data/textpairs.txt"); AnalysisEngineDescription segmenter = AnalysisEngineFactory .createEngineDescription(BreakIteratorSegmenter.class); AnalysisEngineDescription doc = AnalysisEngineFactory.createEngineDescription(DocumentModeAnnotator.class, DocumentModeAnnotator.PARAM_FEATURE_MODE, Constants.FM_PAIR); AggregateBuilder builder = new AggregateBuilder(); builder.add(segmenter, Constants.INITIAL_VIEW, Constants.PART_ONE); builder.add(doc, Constants.INITIAL_VIEW, Constants.PART_ONE); builder.add(segmenter, Constants.INITIAL_VIEW, Constants.PART_TWO); builder.add(doc, Constants.INITIAL_VIEW, Constants.PART_TWO); AnalysisEngineDescription metaCollector = AnalysisEngineFactory.createEngineDescription( LuceneNGramPMetaCollector.class, LuceneNGramPFE.PARAM_UNIQUE_EXTRACTOR_NAME, "123", LuceneNGramPFE.PARAM_SOURCE_LOCATION, tmpDir, LuceneNGramPMetaCollector.PARAM_TARGET_LOCATION, tmpDir);/*from w w w . ja va 2 s . c o m*/ // test fails if for-loop removed for (@SuppressWarnings("unused") JCas jcas : new JCasIterable(reader, builder.createAggregateDescription(), metaCollector)) { // System.out.println(jcas.getDocumentText().length()); } int i = 0; IndexReader index; try { index = DirectoryReader.open(FSDirectory.open(tmpDir)); Fields fields = MultiFields.getFields(index); if (fields != null) { Terms terms = fields.terms(LuceneNGram.LUCENE_NGRAM_FIELD); if (terms != null) { TermsEnum termsEnum = terms.iterator(null); BytesRef text = null; while ((text = termsEnum.next()) != null) { // System.out.println(text.utf8ToString() + " - " + // termsEnum.totalTermFreq()); // System.out.println(termsEnum.docFreq()); if (text.utf8ToString().equals("this")) { assertEquals(2, termsEnum.docFreq()); assertEquals(3, termsEnum.totalTermFreq()); } i++; } } } } catch (Exception e) { throw new ResourceInitializationException(e); } assertEquals(16, i); }
From source file:org.elasticsearch.action.termlist.TransportTermlistAction.java
License:Apache License
@Override protected ShardTermlistResponse shardOperation(ShardTermlistRequest request) throws ElasticSearchException { synchronized (termlistMutex) { InternalIndexShard indexShard = (InternalIndexShard) indicesService.indexServiceSafe(request.index()) .shardSafe(request.shardId()); indexShard.store().directory();/*www .j a va 2 s .c om*/ Engine.Searcher searcher = indexShard.searcher(); try { Set<String> set = new CompactHashSet(); Fields fields = MultiFields.getFields(searcher.reader()); if (fields != null) { for (Iterator<String> it = fields.iterator(); it.hasNext();) { String field = it.next(); if (field.charAt(0) == '_') { continue; } if (request.getField() == null || field.equals(request.getField())) { Terms terms = fields.terms(field); if (terms != null) { TermsEnum termsEnum = terms.iterator(null); BytesRef text; while ((text = termsEnum.next()) != null) { set.add(text.utf8ToString()); System.out.println("field=" + field + "; text=" + text.utf8ToString()); } } } } } return new ShardTermlistResponse(request.index(), request.shardId(), set); } catch (IOException ex) { throw new ElasticSearchException(ex.getMessage(), ex); } } }
From source file:org.elasticsearch.action.termvector.AbstractTermVectorTests.java
License:Apache License
protected void validateResponse(TermVectorResponse esResponse, Fields luceneFields, TestConfig testConfig) throws IOException { TestDoc testDoc = testConfig.doc;//from w w w . ja v a2 s .c o m HashSet<String> selectedFields = testConfig.selectedFields == null ? null : new HashSet<String>(Arrays.asList(testConfig.selectedFields)); Fields esTermVectorFields = esResponse.getFields(); for (TestFieldSetting field : testDoc.fieldSettings) { Terms esTerms = esTermVectorFields.terms(field.name); if (selectedFields != null && !selectedFields.contains(field.name)) { assertNull(esTerms); continue; } assertNotNull(esTerms); Terms luceneTerms = luceneFields.terms(field.name); TermsEnum esTermEnum = esTerms.iterator(null); TermsEnum luceneTermEnum = luceneTerms.iterator(null); while (esTermEnum.next() != null) { assertNotNull(luceneTermEnum.next()); assertThat(esTermEnum.totalTermFreq(), equalTo(luceneTermEnum.totalTermFreq())); DocsAndPositionsEnum esDocsPosEnum = esTermEnum.docsAndPositions(null, null, 0); DocsAndPositionsEnum luceneDocsPosEnum = luceneTermEnum.docsAndPositions(null, null, 0); if (luceneDocsPosEnum == null) { // test we expect that... assertFalse(field.storedOffset); assertFalse(field.storedPayloads); assertFalse(field.storedPositions); continue; } String currentTerm = esTermEnum.term().utf8ToString(); assertThat("Token mismatch for field: " + field.name, currentTerm, equalTo(luceneTermEnum.term().utf8ToString())); esDocsPosEnum.nextDoc(); luceneDocsPosEnum.nextDoc(); int freq = esDocsPosEnum.freq(); assertThat(freq, equalTo(luceneDocsPosEnum.freq())); for (int i = 0; i < freq; i++) { String failDesc = " (field:" + field.name + " term:" + currentTerm + ")"; int lucenePos = luceneDocsPosEnum.nextPosition(); int esPos = esDocsPosEnum.nextPosition(); if (field.storedPositions && testConfig.requestPositions) { assertThat("Position test failed" + failDesc, lucenePos, equalTo(esPos)); } else { assertThat("Missing position test failed" + failDesc, esPos, equalTo(-1)); } if (field.storedOffset && testConfig.requestOffsets) { assertThat("Offset test failed" + failDesc, luceneDocsPosEnum.startOffset(), equalTo(esDocsPosEnum.startOffset())); assertThat("Offset test failed" + failDesc, luceneDocsPosEnum.endOffset(), equalTo(esDocsPosEnum.endOffset())); } else { assertThat("Missing offset test failed" + failDesc, esDocsPosEnum.startOffset(), equalTo(-1)); assertThat("Missing offset test failed" + failDesc, esDocsPosEnum.endOffset(), equalTo(-1)); } if (field.storedPayloads && testConfig.requestPayloads) { assertThat("Payload test failed" + failDesc, luceneDocsPosEnum.getPayload(), equalTo(esDocsPosEnum.getPayload())); } else { assertThat("Missing payload test failed" + failDesc, esDocsPosEnum.getPayload(), equalTo(null)); } } } assertNull("Es returned terms are done but lucene isn't", luceneTermEnum.next()); } }
From source file:org.elasticsearch.action.termvector.dfs.DfsOnlyRequest.java
License:Apache License
public DfsOnlyRequest(Fields termVectorFields, String[] indices, String[] types, Set<String> selectedFields) throws IOException { super(indices); // build a search request with a query of all the terms final BoolQueryBuilder boolBuilder = boolQuery(); TermsEnum iterator = null;/*from w w w . j a va 2s . c o m*/ for (String fieldName : termVectorFields) { if ((selectedFields != null) && (!selectedFields.contains(fieldName))) { continue; } Terms terms = termVectorFields.terms(fieldName); iterator = terms.iterator(iterator); while (iterator.next() != null) { String text = iterator.term().utf8ToString(); boolBuilder.should(QueryBuilders.termQuery(fieldName, text)); } } // wrap a search request object this.searchRequest = new SearchRequest(indices).types(types) .source(new SearchSourceBuilder().query(boolBuilder)); }
From source file:org.elasticsearch.action.termvector.GetTermVectorCheckDocFreqTests.java
License:Apache License
private void checkWithoutFieldStatistics(int numDocs, String[] values, int[] freq, int[][] pos, int[][] startOffset, int[][] endOffset, int i) throws IOException { TermVectorRequestBuilder resp = client().prepareTermVector("test", "type1", Integer.toString(i)) .setPayloads(true).setOffsets(true).setPositions(true).setTermStatistics(true) .setFieldStatistics(false).setSelectedFields(); TermVectorResponse response = resp.execute().actionGet(); assertThat("doc id: " + i + " doesn't exists but should", response.isExists(), equalTo(true)); Fields fields = response.getFields(); assertThat(fields.size(), equalTo(1)); Terms terms = fields.terms("field"); assertThat(terms.size(), equalTo(8l)); assertThat(terms.getSumTotalTermFreq(), Matchers.equalTo((long) -1)); assertThat(terms.getDocCount(), Matchers.equalTo(-1)); assertThat(terms.getSumDocFreq(), equalTo((long) -1)); TermsEnum iterator = terms.iterator(null); for (int j = 0; j < values.length; j++) { String string = values[j]; BytesRef next = iterator.next(); assertThat(next, Matchers.notNullValue()); assertThat("expected " + string, string, equalTo(next.utf8ToString())); assertThat(next, Matchers.notNullValue()); if (string.equals("the")) { assertThat("expected ttf of " + string, numDocs * 2, equalTo((int) iterator.totalTermFreq())); } else {//from ww w . j ava2 s . c om assertThat("expected ttf of " + string, numDocs, equalTo((int) iterator.totalTermFreq())); } DocsAndPositionsEnum docsAndPositions = iterator.docsAndPositions(null, null); assertThat(docsAndPositions.nextDoc(), equalTo(0)); assertThat(freq[j], equalTo(docsAndPositions.freq())); assertThat(iterator.docFreq(), equalTo(numDocs)); int[] termPos = pos[j]; int[] termStartOffset = startOffset[j]; int[] termEndOffset = endOffset[j]; assertThat(termPos.length, equalTo(freq[j])); assertThat(termStartOffset.length, equalTo(freq[j])); assertThat(termEndOffset.length, equalTo(freq[j])); for (int k = 0; k < freq[j]; k++) { int nextPosition = docsAndPositions.nextPosition(); assertThat("term: " + string, nextPosition, equalTo(termPos[k])); assertThat("term: " + string, docsAndPositions.startOffset(), equalTo(termStartOffset[k])); assertThat("term: " + string, docsAndPositions.endOffset(), equalTo(termEndOffset[k])); assertThat("term: " + string, docsAndPositions.getPayload(), equalTo(new BytesRef("word"))); } } assertThat(iterator.next(), Matchers.nullValue()); XContentBuilder xBuilder = new XContentFactory().jsonBuilder(); response.toXContent(xBuilder, null); BytesStream bytesStream = xBuilder.bytesStream(); String utf8 = bytesStream.bytes().toUtf8(); String expectedString = "{\"_index\":\"test\",\"_type\":\"type1\",\"_id\":\"" + i + "\",\"_version\":1,\"found\":true,\"term_vectors\":{\"field\":{\"terms\":{\"brown\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":2,\"start_offset\":10,\"end_offset\":15,\"payload\":\"d29yZA==\"}]},\"dog\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":8,\"start_offset\":40,\"end_offset\":43,\"payload\":\"d29yZA==\"}]},\"fox\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":3,\"start_offset\":16,\"end_offset\":19,\"payload\":\"d29yZA==\"}]},\"jumps\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":4,\"start_offset\":20,\"end_offset\":25,\"payload\":\"d29yZA==\"}]},\"lazy\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":7,\"start_offset\":35,\"end_offset\":39,\"payload\":\"d29yZA==\"}]},\"over\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":5,\"start_offset\":26,\"end_offset\":30,\"payload\":\"d29yZA==\"}]},\"quick\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":1,\"start_offset\":4,\"end_offset\":9,\"payload\":\"d29yZA==\"}]},\"the\":{\"doc_freq\":15,\"ttf\":30,\"term_freq\":2,\"tokens\":[{\"position\":0,\"start_offset\":0,\"end_offset\":3,\"payload\":\"d29yZA==\"},{\"position\":6,\"start_offset\":31,\"end_offset\":34,\"payload\":\"d29yZA==\"}]}}}}}"; assertThat(utf8, equalTo(expectedString)); }
From source file:org.elasticsearch.action.termvector.GetTermVectorCheckDocFreqTests.java
License:Apache License
private void checkWithoutTermStatistics(int numDocs, String[] values, int[] freq, int[][] pos, int[][] startOffset, int[][] endOffset, int i) throws IOException { TermVectorRequestBuilder resp = client().prepareTermVector("test", "type1", Integer.toString(i)) .setPayloads(true).setOffsets(true).setPositions(true).setTermStatistics(false) .setFieldStatistics(true).setSelectedFields(); assertThat(resp.request().termStatistics(), equalTo(false)); TermVectorResponse response = resp.execute().actionGet(); assertThat("doc id: " + i + " doesn't exists but should", response.isExists(), equalTo(true)); Fields fields = response.getFields(); assertThat(fields.size(), equalTo(1)); Terms terms = fields.terms("field"); assertThat(terms.size(), equalTo(8l)); assertThat(terms.getSumTotalTermFreq(), Matchers.equalTo((long) (9 * numDocs))); assertThat(terms.getDocCount(), Matchers.equalTo(numDocs)); assertThat(terms.getSumDocFreq(), equalTo((long) numDocs * values.length)); TermsEnum iterator = terms.iterator(null); for (int j = 0; j < values.length; j++) { String string = values[j]; BytesRef next = iterator.next(); assertThat(next, Matchers.notNullValue()); assertThat("expected " + string, string, equalTo(next.utf8ToString())); assertThat(next, Matchers.notNullValue()); assertThat("expected ttf of " + string, -1, equalTo((int) iterator.totalTermFreq())); DocsAndPositionsEnum docsAndPositions = iterator.docsAndPositions(null, null); assertThat(docsAndPositions.nextDoc(), equalTo(0)); assertThat(freq[j], equalTo(docsAndPositions.freq())); assertThat(iterator.docFreq(), equalTo(-1)); int[] termPos = pos[j]; int[] termStartOffset = startOffset[j]; int[] termEndOffset = endOffset[j]; assertThat(termPos.length, equalTo(freq[j])); assertThat(termStartOffset.length, equalTo(freq[j])); assertThat(termEndOffset.length, equalTo(freq[j])); for (int k = 0; k < freq[j]; k++) { int nextPosition = docsAndPositions.nextPosition(); assertThat("term: " + string, nextPosition, equalTo(termPos[k])); assertThat("term: " + string, docsAndPositions.startOffset(), equalTo(termStartOffset[k])); assertThat("term: " + string, docsAndPositions.endOffset(), equalTo(termEndOffset[k])); assertThat("term: " + string, docsAndPositions.getPayload(), equalTo(new BytesRef("word"))); }//from ww w . jav a 2 s. c o m } assertThat(iterator.next(), Matchers.nullValue()); XContentBuilder xBuilder = new XContentFactory().jsonBuilder(); response.toXContent(xBuilder, null); BytesStream bytesStream = xBuilder.bytesStream(); String utf8 = bytesStream.bytes().toUtf8(); String expectedString = "{\"_index\":\"test\",\"_type\":\"type1\",\"_id\":\"" + i + "\",\"_version\":1,\"found\":true,\"term_vectors\":{\"field\":{\"field_statistics\":{\"sum_doc_freq\":120,\"doc_count\":15,\"sum_ttf\":135},\"terms\":{\"brown\":{\"term_freq\":1,\"tokens\":[{\"position\":2,\"start_offset\":10,\"end_offset\":15,\"payload\":\"d29yZA==\"}]},\"dog\":{\"term_freq\":1,\"tokens\":[{\"position\":8,\"start_offset\":40,\"end_offset\":43,\"payload\":\"d29yZA==\"}]},\"fox\":{\"term_freq\":1,\"tokens\":[{\"position\":3,\"start_offset\":16,\"end_offset\":19,\"payload\":\"d29yZA==\"}]},\"jumps\":{\"term_freq\":1,\"tokens\":[{\"position\":4,\"start_offset\":20,\"end_offset\":25,\"payload\":\"d29yZA==\"}]},\"lazy\":{\"term_freq\":1,\"tokens\":[{\"position\":7,\"start_offset\":35,\"end_offset\":39,\"payload\":\"d29yZA==\"}]},\"over\":{\"term_freq\":1,\"tokens\":[{\"position\":5,\"start_offset\":26,\"end_offset\":30,\"payload\":\"d29yZA==\"}]},\"quick\":{\"term_freq\":1,\"tokens\":[{\"position\":1,\"start_offset\":4,\"end_offset\":9,\"payload\":\"d29yZA==\"}]},\"the\":{\"term_freq\":2,\"tokens\":[{\"position\":0,\"start_offset\":0,\"end_offset\":3,\"payload\":\"d29yZA==\"},{\"position\":6,\"start_offset\":31,\"end_offset\":34,\"payload\":\"d29yZA==\"}]}}}}}"; assertThat(utf8, equalTo(expectedString)); }
From source file:org.elasticsearch.action.termvector.GetTermVectorCheckDocFreqTests.java
License:Apache License
private void checkAllInfo(int numDocs, String[] values, int[] freq, int[][] pos, int[][] startOffset, int[][] endOffset, int i) throws IOException { TermVectorRequestBuilder resp = client().prepareTermVector("test", "type1", Integer.toString(i)) .setPayloads(true).setOffsets(true).setPositions(true).setFieldStatistics(true) .setTermStatistics(true).setSelectedFields(); assertThat(resp.request().fieldStatistics(), equalTo(true)); TermVectorResponse response = resp.execute().actionGet(); assertThat("doc id: " + i + " doesn't exists but should", response.isExists(), equalTo(true)); Fields fields = response.getFields(); assertThat(fields.size(), equalTo(1)); Terms terms = fields.terms("field"); assertThat(terms.size(), equalTo(8l)); assertThat(terms.getSumTotalTermFreq(), Matchers.equalTo((long) (9 * numDocs))); assertThat(terms.getDocCount(), Matchers.equalTo(numDocs)); assertThat(terms.getSumDocFreq(), equalTo((long) numDocs * values.length)); TermsEnum iterator = terms.iterator(null); for (int j = 0; j < values.length; j++) { String string = values[j]; BytesRef next = iterator.next(); assertThat(next, Matchers.notNullValue()); assertThat("expected " + string, string, equalTo(next.utf8ToString())); assertThat(next, Matchers.notNullValue()); if (string.equals("the")) { assertThat("expected ttf of " + string, numDocs * 2, equalTo((int) iterator.totalTermFreq())); } else {/*from w w w .j a va2 s. com*/ assertThat("expected ttf of " + string, numDocs, equalTo((int) iterator.totalTermFreq())); } DocsAndPositionsEnum docsAndPositions = iterator.docsAndPositions(null, null); assertThat(docsAndPositions.nextDoc(), equalTo(0)); assertThat(freq[j], equalTo(docsAndPositions.freq())); assertThat(iterator.docFreq(), equalTo(numDocs)); int[] termPos = pos[j]; int[] termStartOffset = startOffset[j]; int[] termEndOffset = endOffset[j]; assertThat(termPos.length, equalTo(freq[j])); assertThat(termStartOffset.length, equalTo(freq[j])); assertThat(termEndOffset.length, equalTo(freq[j])); for (int k = 0; k < freq[j]; k++) { int nextPosition = docsAndPositions.nextPosition(); assertThat("term: " + string, nextPosition, equalTo(termPos[k])); assertThat("term: " + string, docsAndPositions.startOffset(), equalTo(termStartOffset[k])); assertThat("term: " + string, docsAndPositions.endOffset(), equalTo(termEndOffset[k])); assertThat("term: " + string, docsAndPositions.getPayload(), equalTo(new BytesRef("word"))); } } assertThat(iterator.next(), Matchers.nullValue()); XContentBuilder xBuilder = new XContentFactory().jsonBuilder(); response.toXContent(xBuilder, null); BytesStream bytesStream = xBuilder.bytesStream(); String utf8 = bytesStream.bytes().toUtf8(); String expectedString = "{\"_index\":\"test\",\"_type\":\"type1\",\"_id\":\"" + i + "\",\"_version\":1,\"found\":true,\"term_vectors\":{\"field\":{\"field_statistics\":{\"sum_doc_freq\":120,\"doc_count\":15,\"sum_ttf\":135},\"terms\":{\"brown\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":2,\"start_offset\":10,\"end_offset\":15,\"payload\":\"d29yZA==\"}]},\"dog\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":8,\"start_offset\":40,\"end_offset\":43,\"payload\":\"d29yZA==\"}]},\"fox\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":3,\"start_offset\":16,\"end_offset\":19,\"payload\":\"d29yZA==\"}]},\"jumps\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":4,\"start_offset\":20,\"end_offset\":25,\"payload\":\"d29yZA==\"}]},\"lazy\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":7,\"start_offset\":35,\"end_offset\":39,\"payload\":\"d29yZA==\"}]},\"over\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":5,\"start_offset\":26,\"end_offset\":30,\"payload\":\"d29yZA==\"}]},\"quick\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":1,\"start_offset\":4,\"end_offset\":9,\"payload\":\"d29yZA==\"}]},\"the\":{\"doc_freq\":15,\"ttf\":30,\"term_freq\":2,\"tokens\":[{\"position\":0,\"start_offset\":0,\"end_offset\":3,\"payload\":\"d29yZA==\"},{\"position\":6,\"start_offset\":31,\"end_offset\":34,\"payload\":\"d29yZA==\"}]}}}}}"; assertThat(utf8, equalTo(expectedString)); }
From source file:org.elasticsearch.action.termvector.GetTermVectorTests.java
License:Apache License
@Test public void testSimpleTermVectors() throws ElasticsearchException, IOException { XContentBuilder mapping = XContentFactory.jsonBuilder().startObject().startObject("type1") .startObject("properties").startObject("field").field("type", "string") .field("term_vector", "with_positions_offsets_payloads").field("analyzer", "tv_test").endObject() .endObject().endObject().endObject(); ElasticsearchAssertions.assertAcked(prepareCreate("test").addMapping("type1", mapping) .setSettings(ImmutableSettings.settingsBuilder() .put("index.analysis.analyzer.tv_test.tokenizer", "whitespace") .putArray("index.analysis.analyzer.tv_test.filter", "type_as_payload", "lowercase"))); ensureYellow();//w w w. j a va 2s . c om for (int i = 0; i < 10; i++) { client().prepareIndex("test", "type1", Integer.toString(i)) .setSource(XContentFactory.jsonBuilder().startObject() .field("field", "the quick brown fox jumps over the lazy dog") // 0the3 4quick9 10brown15 16fox19 20jumps25 26over30 // 31the34 35lazy39 40dog43 .endObject()) .execute().actionGet(); refresh(); } String[] values = { "brown", "dog", "fox", "jumps", "lazy", "over", "quick", "the" }; int[] freq = { 1, 1, 1, 1, 1, 1, 1, 2 }; int[][] pos = { { 2 }, { 8 }, { 3 }, { 4 }, { 7 }, { 5 }, { 1 }, { 0, 6 } }; int[][] startOffset = { { 10 }, { 40 }, { 16 }, { 20 }, { 35 }, { 26 }, { 4 }, { 0, 31 } }; int[][] endOffset = { { 15 }, { 43 }, { 19 }, { 25 }, { 39 }, { 30 }, { 9 }, { 3, 34 } }; for (int i = 0; i < 10; i++) { TermVectorRequestBuilder resp = client().prepareTermVector("test", "type1", Integer.toString(i)) .setPayloads(true).setOffsets(true).setPositions(true).setSelectedFields(); TermVectorResponse response = resp.execute().actionGet(); assertThat("doc id: " + i + " doesn't exists but should", response.isExists(), equalTo(true)); Fields fields = response.getFields(); assertThat(fields.size(), equalTo(1)); Terms terms = fields.terms("field"); assertThat(terms.size(), equalTo(8l)); TermsEnum iterator = terms.iterator(null); for (int j = 0; j < values.length; j++) { String string = values[j]; BytesRef next = iterator.next(); assertThat(next, Matchers.notNullValue()); assertThat("expected " + string, string, equalTo(next.utf8ToString())); assertThat(next, Matchers.notNullValue()); // do not test ttf or doc frequency, because here we have many // shards and do not know how documents are distributed DocsAndPositionsEnum docsAndPositions = iterator.docsAndPositions(null, null); assertThat(docsAndPositions.nextDoc(), equalTo(0)); assertThat(freq[j], equalTo(docsAndPositions.freq())); int[] termPos = pos[j]; int[] termStartOffset = startOffset[j]; int[] termEndOffset = endOffset[j]; assertThat(termPos.length, equalTo(freq[j])); assertThat(termStartOffset.length, equalTo(freq[j])); assertThat(termEndOffset.length, equalTo(freq[j])); for (int k = 0; k < freq[j]; k++) { int nextPosition = docsAndPositions.nextPosition(); assertThat("term: " + string, nextPosition, equalTo(termPos[k])); assertThat("term: " + string, docsAndPositions.startOffset(), equalTo(termStartOffset[k])); assertThat("term: " + string, docsAndPositions.endOffset(), equalTo(termEndOffset[k])); assertThat("term: " + string, docsAndPositions.getPayload(), equalTo(new BytesRef("word"))); } } assertThat(iterator.next(), Matchers.nullValue()); } }
From source file:org.elasticsearch.action.termvector.GetTermVectorTests.java
License:Apache License
@Test public void testRandomSingleTermVectors() throws ElasticsearchException, IOException { FieldType ft = new FieldType(); int config = randomInt(6); boolean storePositions = false; boolean storeOffsets = false; boolean storePayloads = false; boolean storeTermVectors = false; switch (config) { case 0: {//w ww. j av a2 s . c om // do nothing } case 1: { storeTermVectors = true; } case 2: { storeTermVectors = true; storePositions = true; } case 3: { storeTermVectors = true; storeOffsets = true; } case 4: { storeTermVectors = true; storePositions = true; storeOffsets = true; } case 5: { storeTermVectors = true; storePositions = true; storePayloads = true; } case 6: { storeTermVectors = true; storePositions = true; storeOffsets = true; storePayloads = true; } } ft.setStoreTermVectors(storeTermVectors); ft.setStoreTermVectorOffsets(storeOffsets); ft.setStoreTermVectorPayloads(storePayloads); ft.setStoreTermVectorPositions(storePositions); String optionString = AbstractFieldMapper.termVectorOptionsToString(ft); XContentBuilder mapping = XContentFactory.jsonBuilder().startObject().startObject("type1") .startObject("properties").startObject("field").field("type", "string") .field("term_vector", optionString).field("analyzer", "tv_test").endObject().endObject().endObject() .endObject(); ElasticsearchAssertions.assertAcked(prepareCreate("test").addMapping("type1", mapping) .setSettings(ImmutableSettings.settingsBuilder() .put("index.analysis.analyzer.tv_test.tokenizer", "whitespace") .putArray("index.analysis.analyzer.tv_test.filter", "type_as_payload", "lowercase"))); ensureYellow(); for (int i = 0; i < 10; i++) { client().prepareIndex("test", "type1", Integer.toString(i)) .setSource(XContentFactory.jsonBuilder().startObject() .field("field", "the quick brown fox jumps over the lazy dog") // 0the3 4quick9 10brown15 16fox19 20jumps25 26over30 // 31the34 35lazy39 40dog43 .endObject()) .execute().actionGet(); refresh(); } String[] values = { "brown", "dog", "fox", "jumps", "lazy", "over", "quick", "the" }; int[] freq = { 1, 1, 1, 1, 1, 1, 1, 2 }; int[][] pos = { { 2 }, { 8 }, { 3 }, { 4 }, { 7 }, { 5 }, { 1 }, { 0, 6 } }; int[][] startOffset = { { 10 }, { 40 }, { 16 }, { 20 }, { 35 }, { 26 }, { 4 }, { 0, 31 } }; int[][] endOffset = { { 15 }, { 43 }, { 19 }, { 25 }, { 39 }, { 30 }, { 9 }, { 3, 34 } }; boolean isPayloadRequested = randomBoolean(); boolean isOffsetRequested = randomBoolean(); boolean isPositionsRequested = randomBoolean(); String infoString = createInfoString(isPositionsRequested, isOffsetRequested, isPayloadRequested, optionString); for (int i = 0; i < 10; i++) { TermVectorRequestBuilder resp = client().prepareTermVector("test", "type1", Integer.toString(i)) .setPayloads(isPayloadRequested).setOffsets(isOffsetRequested) .setPositions(isPositionsRequested).setSelectedFields(); TermVectorResponse response = resp.execute().actionGet(); assertThat(infoString + "doc id: " + i + " doesn't exists but should", response.isExists(), equalTo(true)); Fields fields = response.getFields(); assertThat(fields.size(), equalTo(ft.storeTermVectors() ? 1 : 0)); if (ft.storeTermVectors()) { Terms terms = fields.terms("field"); assertThat(terms.size(), equalTo(8l)); TermsEnum iterator = terms.iterator(null); for (int j = 0; j < values.length; j++) { String string = values[j]; BytesRef next = iterator.next(); assertThat(infoString, next, Matchers.notNullValue()); assertThat(infoString + "expected " + string, string, equalTo(next.utf8ToString())); assertThat(infoString, next, Matchers.notNullValue()); // do not test ttf or doc frequency, because here we have // many shards and do not know how documents are distributed DocsAndPositionsEnum docsAndPositions = iterator.docsAndPositions(null, null); // docs and pos only returns something if positions or // payloads or offsets are stored / requestd Otherwise use // DocsEnum? assertThat(infoString, docsAndPositions.nextDoc(), equalTo(0)); assertThat(infoString, freq[j], equalTo(docsAndPositions.freq())); int[] termPos = pos[j]; int[] termStartOffset = startOffset[j]; int[] termEndOffset = endOffset[j]; if (isPositionsRequested && storePositions) { assertThat(infoString, termPos.length, equalTo(freq[j])); } if (isOffsetRequested && storeOffsets) { assertThat(termStartOffset.length, equalTo(freq[j])); assertThat(termEndOffset.length, equalTo(freq[j])); } for (int k = 0; k < freq[j]; k++) { int nextPosition = docsAndPositions.nextPosition(); // only return something useful if requested and stored if (isPositionsRequested && storePositions) { assertThat(infoString + "positions for term: " + string, nextPosition, equalTo(termPos[k])); } else { assertThat(infoString + "positions for term: ", nextPosition, equalTo(-1)); } // only return something useful if requested and stored if (isPayloadRequested && storePayloads) { assertThat(infoString + "payloads for term: " + string, docsAndPositions.getPayload(), equalTo(new BytesRef("word"))); } else { assertThat(infoString + "payloads for term: " + string, docsAndPositions.getPayload(), equalTo(null)); } // only return something useful if requested and stored if (isOffsetRequested && storeOffsets) { assertThat(infoString + "startOffsets term: " + string, docsAndPositions.startOffset(), equalTo(termStartOffset[k])); assertThat(infoString + "endOffsets term: " + string, docsAndPositions.endOffset(), equalTo(termEndOffset[k])); } else { assertThat(infoString + "startOffsets term: " + string, docsAndPositions.startOffset(), equalTo(-1)); assertThat(infoString + "endOffsets term: " + string, docsAndPositions.endOffset(), equalTo(-1)); } } } assertThat(iterator.next(), Matchers.nullValue()); } } }