List of usage examples for org.apache.lucene.facet FacetsConfig FacetsConfig
public FacetsConfig()
From source file:com.czw.search.lucene.example.facet.AssociationsFacetsExample.java
License:Apache License
/** Empty constructor */ public AssociationsFacetsExample() { config = new FacetsConfig(); config.setMultiValued("tags", true); config.setIndexFieldName("tags", "$tags"); config.setMultiValued("genre", true); config.setIndexFieldName("genre", "$genre"); }
From source file:com.czw.search.lucene.example.facet.RangeFacetsExample.java
License:Apache License
private FacetsConfig getConfig() { return new FacetsConfig(); }
From source file:com.epam.catgenome.dao.index.FeatureIndexDao.java
License:Open Source License
/** * Stores features from a specified feature file to the specified project's Lucene index * Sample query: featureId:rs44022* AND (variationType:del OR variationType:ins) * * @param featureFileId a FeatureFile, for which features to save * @param projectId a project, for which to write an index * @param entries a list of FeatureIndexEntry to write to index * @throws IOException//from w w w .java 2 s. co m */ public void writeLuceneIndexForProject(final Long featureFileId, final long projectId, final List<? extends FeatureIndexEntry> entries) throws IOException { try (StandardAnalyzer analyzer = new StandardAnalyzer(); Directory index = fileManager.createIndexForProject(projectId); IndexWriter writer = new IndexWriter(index, new IndexWriterConfig(analyzer).setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND))) { FacetsConfig facetsConfig = new FacetsConfig(); facetsConfig.setIndexFieldName(FeatureIndexFields.CHR_ID.getFieldName(), FeatureIndexFields.FACET_CHR_ID.getFieldName()); for (FeatureIndexEntry entry : entries) { Document document = new Document(); addCommonDocumentFields(document, entry, featureFileId); if (entry instanceof VcfIndexEntry) { addVcfDocumentFields(document, entry); } writer.addDocument(facetsConfig.build(document)); } } }
From source file:com.epam.catgenome.dao.index.FeatureIndexDao.java
License:Open Source License
/** * Stores features from a specified feature file to it's Lucene index * Sample query: featureId:rs44022* AND (variationType:del OR variationType:ins) * * @param featureFile a FeatureFile, for which features to save * @param entries a list of FeatureIndexEntry to write to index * @throws IOException/*from w w w . j a va 2 s . c o m*/ */ public void writeLuceneIndexForFile(final FeatureFile featureFile, final List<? extends FeatureIndexEntry> entries) throws IOException { try (StandardAnalyzer analyzer = new StandardAnalyzer(); Directory index = fileManager.createIndexForFile(featureFile); IndexWriter writer = new IndexWriter(index, new IndexWriterConfig(analyzer).setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND))) { FacetsConfig facetsConfig = new FacetsConfig(); facetsConfig.setIndexFieldName(FeatureIndexFields.CHR_ID.getFieldName(), FeatureIndexFields.FACET_CHR_ID.getFieldName()); facetsConfig.setIndexFieldName(FeatureIndexFields.F_UID.getFieldName(), FeatureIndexFields.FACET_UID.getFieldName()); for (FeatureIndexEntry entry : entries) { Document document = new Document(); addCommonDocumentFields(document, entry, featureFile.getId()); if (entry instanceof VcfIndexEntry) { addVcfDocumentFields(document, entry); } writer.addDocument(facetsConfig.build(document)); } } }
From source file:com.qwazr.search.analysis.AnalyzerContext.java
License:Apache License
public AnalyzerContext(Map<String, AnalyzerDefinition> analyzerMap, Map<String, FieldDefinition> fields) throws ServerException { this.fieldTypes = new HashMap<>(); this.facetsConfig = new FacetsConfig(); if (fields == null || fields.size() == 0) { this.indexAnalyzerMap = Collections.<String, Analyzer>emptyMap(); this.queryAnalyzerMap = Collections.<String, Analyzer>emptyMap(); return;/* w w w. j a v a 2s.c o m*/ } this.indexAnalyzerMap = new HashMap<>(); this.queryAnalyzerMap = new HashMap<>(); for (Map.Entry<String, FieldDefinition> field : fields.entrySet()) { final String fieldName = field.getKey(); final FieldDefinition fieldDef = field.getValue(); FieldTypeInterface fieldType = FieldTypeInterface.getInstance(fieldName, fieldDef); fieldTypes.put(fieldName, fieldType); if (fieldDef.template != null) { switch (fieldDef.template) { case FacetField: case SortedSetDocValuesFacetField: facetsConfig.setMultiValued(fieldName, false); facetsConfig.setHierarchical(fieldName, false); break; case MultiFacetField: case SortedSetMultiDocValuesFacetField: facetsConfig.setMultiValued(fieldName, true); facetsConfig.setHierarchical(fieldName, false); break; } } try { final Analyzer indexAnalyzer = StringUtils.isEmpty(fieldDef.analyzer) ? null : findAnalyzer(analyzerMap, fieldDef.analyzer); if (indexAnalyzer != null) indexAnalyzerMap.put(fieldName, indexAnalyzer); final Analyzer queryAnalyzer = StringUtils.isEmpty(fieldDef.query_analyzer) ? indexAnalyzer : findAnalyzer(analyzerMap, fieldDef.query_analyzer); if (queryAnalyzer != null) queryAnalyzerMap.put(fieldName, queryAnalyzer); } catch (ReflectiveOperationException | InterruptedException | IOException e) { throw new ServerException(Response.Status.NOT_ACCEPTABLE, "Class " + fieldDef.analyzer + " not known for the field " + fieldName, e); } } }
From source file:com.searchcode.app.service.CodeIndexer.java
License:Open Source License
/** * Given a queue of documents to index, index them by popping the queue limited to default of 1000 items. * This method must be synchronized as we have not added any logic to deal with multiple threads writing to the * index./* ww w . j a v a 2s .co m*/ * TODO investigate how Lucene deals with multiple writes */ public synchronized void indexDocuments(Queue<CodeIndexDocument> codeIndexDocumentQueue) throws IOException { Directory indexDirectory = FSDirectory.open(this.INDEX_LOCATION); Directory facetDirectory = FSDirectory.open(this.FACET_LOCATION); Analyzer analyzer = new CodeAnalyzer(); IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer); FacetsConfig facetsConfig; indexWriterConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND); IndexWriter writer = new IndexWriter(indexDirectory, indexWriterConfig); TaxonomyWriter taxonomyWriter = new DirectoryTaxonomyWriter(facetDirectory); try { CodeIndexDocument codeIndexDocument = codeIndexDocumentQueue.poll(); int count = 0; while (codeIndexDocument != null) { Singleton.getLogger() .info("Indexing file " + codeIndexDocument.getRepoLocationRepoNameLocationFilename()); this.sharedService.decrementCodeIndexLinesCount(codeIndexDocument.getCodeLines()); facetsConfig = new FacetsConfig(); facetsConfig.setIndexFieldName(Values.LANGUAGENAME, Values.LANGUAGENAME); facetsConfig.setIndexFieldName(Values.REPONAME, Values.REPONAME); facetsConfig.setIndexFieldName(Values.CODEOWNER, Values.CODEOWNER); Document doc = this.buildDocument(codeIndexDocument); writer.updateDocument( new Term(Values.PATH, codeIndexDocument.getRepoLocationRepoNameLocationFilename()), facetsConfig.build(taxonomyWriter, doc)); count++; if (count >= INDEX_QUEUE_BATCH_SIZE) { codeIndexDocument = null; } else { codeIndexDocument = codeIndexDocumentQueue.poll(); } } } finally { try { writer.close(); } finally { taxonomyWriter.close(); } Singleton.getLogger().info("Closing writers"); } }
From source file:com.searchcode.app.service.CodeIndexer.java
License:Open Source License
/** * Given a queue of documents to index, index them by popping the queue limited to 1000 items. * This method must be synchronized as we have not added any logic to deal with multiple threads writing to the * index./* w w w.j a v a 2s .c om*/ * TODO investigate how Lucene deals with multiple writes */ public synchronized void indexTimeDocuments(Queue<CodeIndexDocument> codeIndexDocumentQueue) throws IOException { // Index all documents and commit at the end for performance gains Directory dir = FSDirectory.open(Paths.get( Properties.getProperties().getProperty(Values.TIMEINDEXLOCATION, Values.DEFAULTTIMEINDEXLOCATION))); Directory facetsdir = FSDirectory.open(Paths.get(Properties.getProperties() .getProperty(Values.TIMEINDEXFACETLOCATION, Values.DEFAULTTIMEINDEXFACETLOCATION))); Analyzer analyzer = new CodeAnalyzer(); IndexWriterConfig iwc = new IndexWriterConfig(analyzer); FacetsConfig facetsConfig; iwc.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND); IndexWriter writer = new IndexWriter(dir, iwc); TaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(facetsdir); try { CodeIndexDocument codeIndexDocument = codeIndexDocumentQueue.poll(); int count = 0; while (codeIndexDocument != null) { Singleton.getLogger() .info("Indexing time file " + codeIndexDocument.getRepoLocationRepoNameLocationFilename()); this.sharedService.decrementCodeIndexLinesCount(codeIndexDocument.getCodeLines()); Document doc = new Document(); // Path is the primary key for documents // needs to include repo location, project name and then filepath including file and revision Field pathField = new StringField("path", codeIndexDocument.getRepoLocationRepoNameLocationFilename() + ":" + codeIndexDocument.getRevision(), Field.Store.YES); doc.add(pathField); // Add in facets facetsConfig = new FacetsConfig(); facetsConfig.setIndexFieldName(Values.LANGUAGENAME, Values.LANGUAGENAME); facetsConfig.setIndexFieldName(Values.REPONAME, Values.REPONAME); facetsConfig.setIndexFieldName(Values.CODEOWNER, Values.CODEOWNER); facetsConfig.setIndexFieldName(Values.DATEYEARMONTHDAY, Values.DATEYEARMONTHDAY); facetsConfig.setIndexFieldName(Values.DATEYEARMONTH, Values.DATEYEARMONTH); facetsConfig.setIndexFieldName(Values.DATEYEAR, Values.DATEYEAR); facetsConfig.setIndexFieldName(Values.REVISION, Values.REVISION); facetsConfig.setIndexFieldName(Values.DELETED, Values.DELETED); if (Singleton.getHelpers().isNullEmptyOrWhitespace(codeIndexDocument.getLanguageName()) == false) { doc.add(new SortedSetDocValuesFacetField(Values.LANGUAGENAME, codeIndexDocument.getLanguageName())); } if (Singleton.getHelpers().isNullEmptyOrWhitespace(codeIndexDocument.getRepoName()) == false) { doc.add(new SortedSetDocValuesFacetField(Values.REPONAME, codeIndexDocument.getRepoName())); } if (Singleton.getHelpers().isNullEmptyOrWhitespace(codeIndexDocument.getCodeOwner()) == false) { doc.add(new SortedSetDocValuesFacetField(Values.CODEOWNER, codeIndexDocument.getCodeOwner())); } if (Singleton.getHelpers().isNullEmptyOrWhitespace(codeIndexDocument.getYearMonthDay()) == false) { doc.add(new SortedSetDocValuesFacetField(Values.DATEYEARMONTHDAY, codeIndexDocument.getYearMonthDay())); } if (Singleton.getHelpers().isNullEmptyOrWhitespace(codeIndexDocument.getYearMonthDay()) == false) { doc.add(new SortedSetDocValuesFacetField(Values.DATEYEARMONTH, codeIndexDocument.getYearMonthDay().substring(0, 6))); } if (Singleton.getHelpers().isNullEmptyOrWhitespace(codeIndexDocument.getYearMonthDay()) == false) { doc.add(new SortedSetDocValuesFacetField(Values.DATEYEAR, codeIndexDocument.getYearMonthDay().substring(0, 4))); } if (Singleton.getHelpers().isNullEmptyOrWhitespace(codeIndexDocument.getRevision()) == false) { doc.add(new SortedSetDocValuesFacetField(Values.REVISION, codeIndexDocument.getRevision())); } if (Singleton.getHelpers().isNullEmptyOrWhitespace(codeIndexDocument.isDeleted()) == false) { doc.add(new SortedSetDocValuesFacetField(Values.DELETED, codeIndexDocument.isDeleted())); } String indexContents = Values.EMPTYSTRING; indexContents += this.searchcodeLib.splitKeywords(codeIndexDocument.getContents()); indexContents += this.searchcodeLib.codeCleanPipeline(codeIndexDocument.getContents()); this.searchcodeLib.addToSpellingCorrector(codeIndexDocument.getContents()); // Store in spelling corrector indexContents = indexContents.toLowerCase(); doc.add(new TextField(Values.REPONAME, codeIndexDocument.getRepoName(), Field.Store.YES)); doc.add(new TextField(Values.FILENAME, codeIndexDocument.getFileName(), Field.Store.YES)); doc.add(new TextField(Values.FILELOCATION, codeIndexDocument.getFileLocation(), Field.Store.YES)); doc.add(new TextField(Values.FILELOCATIONFILENAME, codeIndexDocument.getFileLocationFilename(), Field.Store.YES)); doc.add(new TextField(Values.MD5HASH, codeIndexDocument.getMd5hash(), Field.Store.YES)); doc.add(new TextField(Values.LANGUAGENAME, codeIndexDocument.getLanguageName(), Field.Store.YES)); doc.add(new IntField(Values.CODELINES, codeIndexDocument.getCodeLines(), Field.Store.YES)); doc.add(new TextField(Values.CONTENTS, indexContents, Field.Store.NO)); doc.add(new TextField(Values.REPOLOCATION, codeIndexDocument.getRepoRemoteLocation(), Field.Store.YES)); doc.add(new TextField(Values.CODEOWNER, codeIndexDocument.getCodeOwner(), Field.Store.YES)); doc.add(new TextField(Values.REVISION, codeIndexDocument.getRevision(), Field.Store.YES)); doc.add(new TextField(Values.DATEYEARMONTHDAY, codeIndexDocument.getYearMonthDay(), Field.Store.YES)); doc.add(new TextField(Values.DATEYEARMONTH, codeIndexDocument.getYearMonth(), Field.Store.YES)); doc.add(new TextField(Values.DATEYEAR, codeIndexDocument.getYear(), Field.Store.YES)); doc.add(new TextField(Values.MESSAGE, codeIndexDocument.getMessage(), Field.Store.YES)); doc.add(new TextField(Values.DELETED, codeIndexDocument.isDeleted(), Field.Store.YES)); // Extra metadata in this case when it was last indexed doc.add(new LongField(Values.MODIFIED, new Date().getTime(), Field.Store.YES)); writer.updateDocument( new Term(Values.PATH, codeIndexDocument.getRepoLocationRepoNameLocationFilename()), facetsConfig.build(taxoWriter, doc)); count++; if (count >= INDEX_QUEUE_BATCH_SIZE) { codeIndexDocument = null; } else { codeIndexDocument = codeIndexDocumentQueue.poll(); } } } finally { Singleton.getLogger().info("Closing writers"); writer.close(); taxoWriter.close(); } }
From source file:com.tripod.lucene.example.TestExampleLuceneBase.java
License:Apache License
@Before public void setupBase() throws IOException, ParseException { analyzer = new StandardAnalyzer(); directory = new RAMDirectory(); facetsConfig = new FacetsConfig(); facetsConfig.setIndexFieldName(ExampleField.COLOR.getName(), ExampleField.COLOR.getName()); IndexWriterConfig config = new IndexWriterConfig(analyzer); try (IndexWriter writer = new IndexWriter(directory, config)) { final SimpleDateFormat dateFormat = new SimpleDateFormat(DATE_FORMAT); // Doc1/* ww w.j a va 2 s . c o m*/ Document doc1 = new Document(); doc1.add(new Field(ExampleField.ID.getName(), "1", StringField.TYPE_STORED)); doc1.add(new SortedDocValuesField(ExampleField.ID.getName(), new BytesRef("1"))); doc1.add(new Field(ExampleField.TITLE.getName(), "Title 1", TextField.TYPE_STORED)); doc1.add(new Field(ExampleField.BODY.getName(), "Body 1 Solr is cool", TextField.TYPE_STORED)); doc1.add(new Field(ExampleField.COLOR.getName(), "BLUE", StringField.TYPE_STORED)); doc1.add(new SortedSetDocValuesFacetField(ExampleField.COLOR.getName(), "BLUE")); Date createDate1 = dateFormat.parse("2016-10-01T01:00:00Z"); doc1.add(new NumericDocValuesField(ExampleField.CREATE_DATE.getName(), createDate1.getTime())); doc1.add(new StoredField(ExampleField.CREATE_DATE.getName(), createDate1.getTime())); writer.addDocument(facetsConfig.build(doc1)); // Doc2 Document doc2 = new Document(); doc2.add(new Field(ExampleField.ID.getName(), "2", StringField.TYPE_STORED)); doc2.add(new SortedDocValuesField(ExampleField.ID.getName(), new BytesRef("2"))); doc2.add(new Field(ExampleField.TITLE.getName(), "Title 2", TextField.TYPE_STORED)); doc2.add(new Field(ExampleField.BODY.getName(), "Body 2 Lucene is cool", TextField.TYPE_STORED)); doc2.add(new Field(ExampleField.COLOR.getName(), "RED", StringField.TYPE_STORED)); doc2.add(new SortedSetDocValuesFacetField(ExampleField.COLOR.getName(), "RED")); Date createDate2 = dateFormat.parse("2016-10-01T02:00:00Z"); doc2.add(new NumericDocValuesField(ExampleField.CREATE_DATE.getName(), createDate2.getTime())); doc2.add(new StoredField(ExampleField.CREATE_DATE.getName(), createDate2.getTime())); writer.addDocument(facetsConfig.build(doc2)); // Doc3 Document doc3 = new Document(); doc3.add(new Field(ExampleField.ID.getName(), "3", StringField.TYPE_STORED)); doc3.add(new SortedDocValuesField(ExampleField.ID.getName(), new BytesRef("3"))); doc3.add(new Field(ExampleField.TITLE.getName(), "Title 3", TextField.TYPE_STORED)); doc3.add(new Field(ExampleField.BODY.getName(), "Body 3 Solr is Great, Solr is Fun", TextField.TYPE_STORED)); doc3.add(new Field(ExampleField.COLOR.getName(), "GREEN", StringField.TYPE_STORED)); doc3.add(new SortedSetDocValuesFacetField(ExampleField.COLOR.getName(), "GREEN")); Date createDate3 = dateFormat.parse("2016-10-01T03:00:00Z"); doc3.add(new NumericDocValuesField(ExampleField.CREATE_DATE.getName(), createDate3.getTime())); doc3.add(new StoredField(ExampleField.CREATE_DATE.getName(), createDate3.getTime())); writer.addDocument(facetsConfig.build(doc3)); // Doc4 Document doc4 = new Document(); doc4.add(new Field(ExampleField.ID.getName(), "4", StringField.TYPE_STORED)); doc4.add(new SortedDocValuesField(ExampleField.ID.getName(), new BytesRef("4"))); doc4.add(new Field(ExampleField.TITLE.getName(), "Title 4", TextField.TYPE_STORED)); doc4.add(new Field(ExampleField.BODY.getName(), "Body 4", TextField.TYPE_STORED)); doc4.add(new Field(ExampleField.COLOR.getName(), "BLUE", StringField.TYPE_STORED)); doc4.add(new SortedSetDocValuesFacetField(ExampleField.COLOR.getName(), "BLUE")); Date createDate4 = dateFormat.parse("2016-10-01T04:00:00Z"); doc4.add(new NumericDocValuesField(ExampleField.CREATE_DATE.getName(), createDate4.getTime())); doc4.add(new StoredField(ExampleField.CREATE_DATE.getName(), createDate4.getTime())); writer.addDocument(facetsConfig.build(doc4)); // Doc5 Document doc5 = new Document(); doc5.add(new Field(ExampleField.ID.getName(), "5", StringField.TYPE_STORED)); doc5.add(new SortedDocValuesField(ExampleField.ID.getName(), new BytesRef("5"))); doc5.add(new Field(ExampleField.TITLE.getName(), "Title 5", TextField.TYPE_STORED)); doc5.add(new Field(ExampleField.BODY.getName(), "Body 5", TextField.TYPE_STORED)); doc5.add(new Field(ExampleField.COLOR.getName(), "RED", StringField.TYPE_STORED)); doc5.add(new SortedSetDocValuesFacetField(ExampleField.COLOR.getName(), "RED")); Date createDate5 = dateFormat.parse("2016-10-01T05:00:00Z"); doc5.add(new NumericDocValuesField(ExampleField.CREATE_DATE.getName(), createDate5.getTime())); doc5.add(new StoredField(ExampleField.CREATE_DATE.getName(), createDate5.getTime())); writer.addDocument(facetsConfig.build(doc5)); // commit docs writer.commit(); } // needs to be opened after the writer is closed otherwise it won't see the test data searcherManager = new SearcherManager(directory, null); }
From source file:de.mirkosertic.desktopsearch.LuceneIndexHandler.java
License:Open Source License
public LuceneIndexHandler(Configuration aConfiguration, AnalyzerCache aAnalyzerCache, ExecutorPool aExecutorPool, PreviewProcessor aPreviewProcessor) throws IOException { previewProcessor = aPreviewProcessor; configuration = aConfiguration;/*from w ww . j a v a 2 s. c o m*/ analyzerCache = aAnalyzerCache; executorPool = aExecutorPool; contentFieldType = new FieldType(); contentFieldType.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS); contentFieldType.setStored(true); contentFieldType.setTokenized(true); contentFieldType.setStoreTermVectorOffsets(true); contentFieldType.setStoreTermVectorPayloads(true); contentFieldType.setStoreTermVectorPositions(true); contentFieldType.setStoreTermVectors(true); analyzer = analyzerCache.getAnalyzer(); File theIndexDirectory = new File(aConfiguration.getConfigDirectory(), "index"); theIndexDirectory.mkdirs(); Directory theIndexFSDirectory = new NRTCachingDirectory(FSDirectory.open(theIndexDirectory.toPath()), 100, 100); IndexWriterConfig theConfig = new IndexWriterConfig(analyzer); theConfig.setSimilarity(new CustomSimilarity()); indexWriter = new IndexWriter(theIndexFSDirectory, theConfig); searcherManager = new SearcherManager(indexWriter, true, new SearcherFactory()); commitThread = new Thread("Lucene Commit Thread") { @Override public void run() { while (!isInterrupted()) { if (indexWriter.hasUncommittedChanges()) { try { indexWriter.commit(); } catch (IOException e) { throw new RuntimeException(e); } } try { Thread.sleep(2000); } catch (InterruptedException e) { // Do nothing here } } } }; commitThread.start(); facetsConfig = new FacetsConfig(); }
From source file:ir.FacetLucene_1106022654.java
public static void main(String[] args) throws IOException, ParseException { //menyimpan daftar id semua dokume ArrayList idR = new ArrayList(); //menyimpan daftar judul semua dokumen ArrayList judulR = new ArrayList(); //menyimpa daftar teks untuk semua dokumen ArrayList teksR = new ArrayList(); String id = "haha"; String judul = "haha"; String teks = "haha"; String penulis = "haha"; //membaca data semua dokumen File file = new File("D:\\Kuliah\\Sem 9\\Perolehan Informasi\\2015 - 2016\\Tugas\\Tugas 2\\Teks.txt"); BufferedReader br = new BufferedReader(new FileReader(file)); try {/*from w ww . j a v a 2 s . c o m*/ StringBuilder sb = new StringBuilder(); String line = br.readLine(); String gabung = ""; String gabung2 = ""; boolean flag = false; while (line != null) { gabung = gabung + " " + line; gabung2 = gabung2 + " " + line; final Pattern patternID = Pattern.compile("<ID>(.+?)</ID>"); final Pattern patternJ = Pattern.compile("<JUDUL>(.+?)</JUDUL>"); boolean flag2; /** * penjelasan mengenai teknik untagging teks * setiap membaca </DOK> berarti satu dokumen berhasil dibaca sehingga kita bersiap membaca dokumen selanjutnya * flag diset false, karena sebelum membaca <DOK> tidak ada data yang disimpan */ String[] arg = line.trim().split(" "); if (line.equalsIgnoreCase("</DOK>")) { flag2 = false; } /** * setiap membaca <DOK>, kita bersiap untuk menyimpan data satu dokumen, sehingga flag di set menjadi true */ if (line.equalsIgnoreCase("<DOK>")) { flag2 = true; } /** * selama flag di set true, kita membaca dan mengambil semua data yang berada di dalam tagging. * untuk tahap ini, kita membaca id dan judul */ if (flag2 = true) { //untagging <ID></ID> final Matcher matcherD = patternID.matcher(line); if (matcherD.matches()) { id = matcherD.group(1); idR.add(id); //System.out.println("id ---> " + matcherD.group(1)); } //untagging <JUDUL></JUDUL> final Matcher matcherJ = patternJ.matcher(line); if (matcherJ.matches()) { judul = matcherJ.group(1); judulR.add(judul); //System.out.println("Judul ---> " + matcherJ.group(1)); } } /** * setiap selesai membaca judul (artinya program menemukan tagging </JUDUL>) kita bersiap membaca teks * untuk membaca teks, algoritma sedikit berbeda dengan pembacaan id dan judul karena teks terdiri dari beberapa line. * idenya, kita membaca semua line dalam tag <TEKS> terlebih dahulu dan menyimpannya ke dalam variabel tipe string. * setelah menemukan tag </DOK> artinya semua teks dalam satu dokumen selesai di baca, kita menghilangkan tag yang tidak perlu * kemudian menambahkannya ke ArrayList. * variabel gabung merupakan variabel yang digunakan untuk menyimpan line teks yang dibaca, sehingga setelah semua teks dalam satu dokumen * selesai dibaca, program kembali mengeset nilainya menjadi string kosong. */ for (int i = 0; i < arg.length; i++) { if (arg[i].endsWith("</JUDUL>")) { gabung2 = ""; } //untagging <TEKS></TEKS> if (arg[i].compareTo("</DOK>") == 0) { //System.out.println("masuk"); gabung2 = gabung2.replaceAll("<TEKS>", ""); gabung2 = gabung2.replaceAll("</TEKS>", ""); gabung2 = gabung2.replaceAll("</DOK>", ""); teksR.add(gabung2); //System.out.println("Teks ---> " + gabung2); //System.out.println(id+judul+teks); gabung = ""; gabung2 = ""; } } line = br.readLine(); } //menghitung jumlah masing - masing id,teks, dan judul untuk memastikan sudah sama System.out.println("size teks: " + teksR.size()); System.out.println("size id: " + idR.size()); System.out.println("size judul: " + judulR.size()); String everything = sb.toString(); } finally { br.close(); } //inisialisasi direktori untuk menyimpan hasil index , taxonomy, dan fasetConfig Directory indexDir = new RAMDirectory(); Directory taxoDir = new RAMDirectory(); FacetsConfig fasetconfig = new FacetsConfig(); //inisialisasi analyzer StandardAnalyzer analyzer = new StandardAnalyzer(); IndexWriterConfig indexWriterconfigs = new IndexWriterConfig(analyzer); //inisialisasi IndexWriter IndexWriter writer = new IndexWriter(indexDir, indexWriterconfigs); //inisialisasi lokasi penyimpanan index kategori DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir); //menambahkan dokumen kedalam file IndexWriter for (int d = 0; d < idR.size(); d++) { String[] ag = idR.get(d).toString().split("-"); penulis = ag[0]; id = (String) idR.get(d); judul = (String) judulR.get(d); teks = (String) teksR.get(d); // System.out.println("id--->" + id); // System.out.println("judul--->" + judul); // System.out.println("teks--->" + teks); addDok(writer, penulis, id, judul, teks, taxoWriter, fasetconfig); } writer.close(); taxoWriter.close(); //baca file query File fileQ = new File("D:\\Kuliah\\Sem 9\\Perolehan Informasi\\2015 - 2016\\Tugas\\Tugas 2\\Query.txt"); BufferedReader brQ = new BufferedReader(new FileReader(fileQ)); //inisialisasi arraylist untuk menyimpan daftar query ArrayList listQ = new ArrayList(); //menyimpan query yang sedang dibaca String lineQ = brQ.readLine(); while (lineQ != null) { //masukkan query yang sedang dibaca ke daftar query listQ.add(lineQ); lineQ = brQ.readLine(); } //inisialisasi lokasi menyimpan output Writer tulis = new BufferedWriter(new OutputStreamWriter(new FileOutputStream( "D:\\Kuliah\\Sem 9\\Perolehan Informasi\\2015 - 2016\\Tugas\\Tugas 2\\1106022654_Hasil_2.txt"), "utf-8")); //searching jumlah dokumen yang sesuai dengan masing - masing kueri berdasarkan kategori penulis for (int qu = 0; qu < listQ.size(); qu++) { ArrayList<FacetResult> results = new ArrayList<>(); //inisialisasi DirectoryReader indexReader = DirectoryReader.open(indexDir); IndexSearcher searcher = new IndexSearcher(indexReader); TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir); FacetsCollector fc = new FacetsCollector(); String querystr = (String) listQ.get(qu); Query query = new QueryParser("teks", analyzer).parse(querystr); //melakukan pencarian dokumen berdasarkan kueri dan hasilnya dikumpan di FacetCollector searcher.search(query, fc); Facets facets = new FastTaxonomyFacetCounts(taxoReader, fasetconfig, fc); //System.out.print("masuk sini "); //menemukan kategori hasil pencarian dokumen dan melakukan penghitngan jumlah dokumen results.add(facets.getTopChildren(Integer.MAX_VALUE, "penulis")); System.out.println(listQ.get(qu)); tulis.write((String) listQ.get(qu) + "\n"); //menulis hasil pencarian ke dalam dokumen for (int f = 0; f < results.size(); f++) { for (int n = 0; n < (results.get(f)).labelValues.length; n++) { //hanya menyimpan kategori penulis dan jumlah dokumen String hasil = results.get(f).labelValues[n].toString() + "\n"; tulis.write(hasil); System.out.println((results.get(f).labelValues[n])); } } tulis.flush(); // indexReader.close(); // taxoReader.close(); } }