List of usage examples for org.apache.lucene.util BytesRef utf8ToString
public String utf8ToString()
From source file:org.elasticsearch.search.sort.FieldSortIT.java
License:Apache License
public void testRandomSorting() throws IOException, InterruptedException, ExecutionException { Random random = random();// ww w . j a v a 2 s . c o m assertAcked(prepareCreate("test").addMapping("type", XContentFactory.jsonBuilder().startObject().startObject("type").startObject("properties") .startObject("sparse_bytes").field("type", "keyword").endObject().startObject("dense_bytes") .field("type", "keyword").endObject().endObject().endObject().endObject())); ensureGreen(); TreeMap<BytesRef, String> sparseBytes = new TreeMap<>(); TreeMap<BytesRef, String> denseBytes = new TreeMap<>(); int numDocs = randomIntBetween(200, 300); IndexRequestBuilder[] builders = new IndexRequestBuilder[numDocs]; for (int i = 0; i < numDocs; i++) { String docId = Integer.toString(i); BytesRef ref = null; do { ref = new BytesRef(TestUtil.randomRealisticUnicodeString(random)); } while (denseBytes.containsKey(ref)); denseBytes.put(ref, docId); XContentBuilder src = jsonBuilder().startObject().field("dense_bytes", ref.utf8ToString()); if (rarely()) { src.field("sparse_bytes", ref.utf8ToString()); sparseBytes.put(ref, docId); } src.endObject(); builders[i] = client().prepareIndex("test", "type", docId).setSource(src); } indexRandom(true, builders); { int size = between(1, denseBytes.size()); SearchResponse searchResponse = client().prepareSearch("test").setQuery(matchAllQuery()).setSize(size) .addSort("dense_bytes", SortOrder.ASC).execute().actionGet(); assertNoFailures(searchResponse); assertThat(searchResponse.getHits().getTotalHits(), equalTo((long) numDocs)); assertThat(searchResponse.getHits().hits().length, equalTo(size)); Set<Entry<BytesRef, String>> entrySet = denseBytes.entrySet(); Iterator<Entry<BytesRef, String>> iterator = entrySet.iterator(); for (int i = 0; i < size; i++) { assertThat(iterator.hasNext(), equalTo(true)); Entry<BytesRef, String> next = iterator.next(); assertThat("pos: " + i, searchResponse.getHits().getAt(i).id(), equalTo(next.getValue())); assertThat(searchResponse.getHits().getAt(i).sortValues()[0].toString(), equalTo(next.getKey().utf8ToString())); } } if (!sparseBytes.isEmpty()) { int size = between(1, sparseBytes.size()); SearchResponse searchResponse = client().prepareSearch().setQuery(matchAllQuery()) .setPostFilter(QueryBuilders.existsQuery("sparse_bytes")).setSize(size) .addSort("sparse_bytes", SortOrder.ASC).execute().actionGet(); assertNoFailures(searchResponse); assertThat(searchResponse.getHits().getTotalHits(), equalTo((long) sparseBytes.size())); assertThat(searchResponse.getHits().hits().length, equalTo(size)); Set<Entry<BytesRef, String>> entrySet = sparseBytes.entrySet(); Iterator<Entry<BytesRef, String>> iterator = entrySet.iterator(); for (int i = 0; i < size; i++) { assertThat(iterator.hasNext(), equalTo(true)); Entry<BytesRef, String> next = iterator.next(); assertThat(searchResponse.getHits().getAt(i).id(), equalTo(next.getValue())); assertThat(searchResponse.getHits().getAt(i).sortValues()[0].toString(), equalTo(next.getKey().utf8ToString())); } } }
From source file:org.elasticsearch.search.sort.SimpleSortTests.java
License:Apache License
public void testRandomSorting() throws ElasticsearchException, IOException, InterruptedException, ExecutionException { int numberOfShards = between(1, 10); Random random = getRandom();//from www . ja v a 2 s. com prepareCreate("test") .setSettings(ImmutableSettings.builder().put("index.number_of_shards", numberOfShards) .put("index.number_of_replicas", 0)) .addMapping("type", XContentFactory.jsonBuilder().startObject().startObject("type").startObject("properties") .startObject("sparse_bytes").field("type", "string").field("index", "not_analyzed") .endObject().startObject("dense_bytes").field("type", "string") .field("index", "not_analyzed").endObject().endObject().endObject().endObject()) .execute().actionGet(); ensureGreen(); TreeMap<BytesRef, String> sparseBytes = new TreeMap<BytesRef, String>(); TreeMap<BytesRef, String> denseBytes = new TreeMap<BytesRef, String>(); int numDocs = atLeast(200); IndexRequestBuilder[] builders = new IndexRequestBuilder[numDocs]; for (int i = 0; i < numDocs; i++) { String docId = Integer.toString(i); BytesRef ref = null; do { ref = new BytesRef(_TestUtil.randomRealisticUnicodeString(random)); } while (denseBytes.containsKey(ref)); denseBytes.put(ref, docId); XContentBuilder src = jsonBuilder().startObject().field("dense_bytes", ref.utf8ToString()); if (rarely()) { src.field("sparse_bytes", ref.utf8ToString()); sparseBytes.put(ref, docId); } src.endObject(); builders[i] = client().prepareIndex("test", "type", docId).setSource(src); } indexRandom(true, builders); { int size = between(1, denseBytes.size()); SearchResponse searchResponse = client().prepareSearch("test").setQuery(matchAllQuery()).setSize(size) .addSort("dense_bytes", SortOrder.ASC).execute().actionGet(); assertNoFailures(searchResponse); assertThat(searchResponse.getHits().getTotalHits(), equalTo((long) numDocs)); assertThat(searchResponse.getHits().hits().length, equalTo(size)); Set<Entry<BytesRef, String>> entrySet = denseBytes.entrySet(); Iterator<Entry<BytesRef, String>> iterator = entrySet.iterator(); for (int i = 0; i < size; i++) { assertThat(iterator.hasNext(), equalTo(true)); Entry<BytesRef, String> next = iterator.next(); assertThat("pos: " + i, searchResponse.getHits().getAt(i).id(), equalTo(next.getValue())); assertThat(searchResponse.getHits().getAt(i).sortValues()[0].toString(), equalTo(next.getKey().utf8ToString())); } } if (!sparseBytes.isEmpty()) { int size = between(1, sparseBytes.size()); SearchResponse searchResponse = client().prepareSearch().setQuery(matchAllQuery()) .setPostFilter(FilterBuilders.existsFilter("sparse_bytes")).setSize(size) .addSort("sparse_bytes", SortOrder.ASC).execute().actionGet(); assertNoFailures(searchResponse); assertThat(searchResponse.getHits().getTotalHits(), equalTo((long) sparseBytes.size())); assertThat(searchResponse.getHits().hits().length, equalTo(size)); Set<Entry<BytesRef, String>> entrySet = sparseBytes.entrySet(); Iterator<Entry<BytesRef, String>> iterator = entrySet.iterator(); for (int i = 0; i < size; i++) { assertThat(iterator.hasNext(), equalTo(true)); Entry<BytesRef, String> next = iterator.next(); assertThat(searchResponse.getHits().getAt(i).id(), equalTo(next.getValue())); assertThat(searchResponse.getHits().getAt(i).sortValues()[0].toString(), equalTo(next.getKey().utf8ToString())); } } }
From source file:org.elasticsearch.search.suggest.CompletionTokenStreamTest.java
License:Apache License
@Test public void testSuggestTokenFilterProperlyDelegateInputStream() throws Exception { TokenStream tokenStream = new MockTokenizer(new StringReader("mykeyword"), MockTokenizer.WHITESPACE, true); BytesRef payload = new BytesRef("Surface keyword|friggin payload|10"); TokenStream suggestTokenStream = new ByteTermAttrToCharTermAttrFilter( new CompletionTokenStream(tokenStream, payload, new CompletionTokenStream.ToFiniteStrings() { @Override/*ww w .j a va 2 s. com*/ public Set<IntsRef> toFiniteStrings(TokenStream stream) throws IOException { return suggester.toFiniteStrings(suggester.getTokenStreamToAutomaton(), stream); } })); TermToBytesRefAttribute termAtt = suggestTokenStream.getAttribute(TermToBytesRefAttribute.class); BytesRef ref = termAtt.getBytesRef(); assertNotNull(ref); suggestTokenStream.reset(); while (suggestTokenStream.incrementToken()) { termAtt.fillBytesRef(); assertThat(ref.utf8ToString(), equalTo("mykeyword")); } suggestTokenStream.end(); suggestTokenStream.close(); }
From source file:org.elasticsearch.termvectors.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 w w w. j av a 2s .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,\"exists\":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.termvectors.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 . j a v 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,\"exists\":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.termvectors.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 {/*w ww . ja va2s . c o m*/ 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,\"exists\":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.termvectors.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 . ja v a 2s. c o m 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.termvectors.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: {//from ww w .j av a 2s. 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()); } } }
From source file:org.elasticsearch.test.integration.search.sort.SimpleSortTests.java
License:Apache License
public void testRandomSorting() throws ElasticSearchException, IOException, InterruptedException, ExecutionException { int numberOfShards = between(1, 10); Random random = getRandom();//w w w .j ava 2 s . com prepareCreate("test") .setSettings(randomSettingsBuilder().put("index.number_of_shards", numberOfShards) .put("index.number_of_replicas", 0)) .addMapping("type", XContentFactory.jsonBuilder().startObject().startObject("type").startObject("properties") .startObject("sparse_bytes").field("type", "string").field("index", "not_analyzed") .endObject().startObject("dense_bytes").field("type", "string") .field("index", "not_analyzed").endObject().endObject().endObject().endObject()) .execute().actionGet(); ensureGreen(); TreeMap<BytesRef, String> sparseBytes = new TreeMap<BytesRef, String>(); TreeMap<BytesRef, String> denseBytes = new TreeMap<BytesRef, String>(); int numDocs = atLeast(200); IndexRequestBuilder[] builders = new IndexRequestBuilder[numDocs]; for (int i = 0; i < numDocs; i++) { String docId = Integer.toString(i); BytesRef ref = null; do { ref = new BytesRef(_TestUtil.randomRealisticUnicodeString(random)); } while (denseBytes.containsKey(ref)); denseBytes.put(ref, docId); XContentBuilder src = jsonBuilder().startObject().field("dense_bytes", ref.utf8ToString()); if (rarely()) { src.field("sparse_bytes", ref.utf8ToString()); sparseBytes.put(ref, docId); } src.endObject(); builders[i] = client().prepareIndex("test", "type", docId).setSource(src); } indexRandom("test", true, builders); { int size = between(1, denseBytes.size()); SearchResponse searchResponse = client().prepareSearch("test").setQuery(matchAllQuery()).setSize(size) .addSort("dense_bytes", SortOrder.ASC).execute().actionGet(); assertNoFailures(searchResponse); assertThat(searchResponse.getHits().getTotalHits(), equalTo((long) numDocs)); assertThat(searchResponse.getHits().hits().length, equalTo(size)); Set<Entry<BytesRef, String>> entrySet = denseBytes.entrySet(); Iterator<Entry<BytesRef, String>> iterator = entrySet.iterator(); for (int i = 0; i < size; i++) { assertThat(iterator.hasNext(), equalTo(true)); Entry<BytesRef, String> next = iterator.next(); assertThat("pos: " + i, searchResponse.getHits().getAt(i).id(), equalTo(next.getValue())); assertThat(searchResponse.getHits().getAt(i).sortValues()[0].toString(), equalTo(next.getKey().utf8ToString())); } } if (!sparseBytes.isEmpty()) { int size = between(1, sparseBytes.size()); SearchResponse searchResponse = client().prepareSearch().setQuery(matchAllQuery()) .setFilter(FilterBuilders.existsFilter("sparse_bytes")).setSize(size) .addSort("sparse_bytes", SortOrder.ASC).execute().actionGet(); assertNoFailures(searchResponse); assertThat(searchResponse.getHits().getTotalHits(), equalTo((long) sparseBytes.size())); assertThat(searchResponse.getHits().hits().length, equalTo(size)); Set<Entry<BytesRef, String>> entrySet = sparseBytes.entrySet(); Iterator<Entry<BytesRef, String>> iterator = entrySet.iterator(); for (int i = 0; i < size; i++) { assertThat(iterator.hasNext(), equalTo(true)); Entry<BytesRef, String> next = iterator.next(); assertThat(searchResponse.getHits().getAt(i).id(), equalTo(next.getValue())); assertThat(searchResponse.getHits().getAt(i).sortValues()[0].toString(), equalTo(next.getKey().utf8ToString())); } } }
From source file:org.elasticsearch.test.integration.termvectors.GetTermVectorTests.java
License:Apache License
@Test public void testSimpleTermVectors() throws ElasticSearchException, IOException { run(addMapping(prepareCreate("test"), "type1", new Object[] { "field", "type", "string", "term_vector", "with_positions_offsets_payloads", "analyzer", "tv_test" }) .setSettings(ImmutableSettings.settingsBuilder() .put("index.analysis.analyzer.tv_test.tokenizer", "whitespace") .putArray("index.analysis.analyzer.tv_test.filter", "type_as_payload", "lowercase"))); ensureYellow();//from ww w . j a v a 2 s. c o m 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.documentExists(), 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()); } }