X-Git-Url: https://git.mdrn.pl/pylucene.git/blobdiff_plain/a2e61f0c04805cfcb8706176758d1283c7e3a55c..aaeed5504b982cf3545252ab528713250aa33eed:/lucene-java-3.5.0/lucene/src/test/org/apache/lucene/index/TestTermVectorsWriter.java

diff --git a/lucene-java-3.5.0/lucene/src/test/org/apache/lucene/index/TestTermVectorsWriter.java b/lucene-java-3.5.0/lucene/src/test/org/apache/lucene/index/TestTermVectorsWriter.java
new file mode 100644
index 0000000..77d47ca
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/src/test/org/apache/lucene/index/TestTermVectorsWriter.java
@@ -0,0 +1,475 @@
+package org.apache.lucene.index;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import java.io.IOException;
+import java.io.StringReader;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.CachingTokenFilter;
+import org.apache.lucene.analysis.MockAnalyzer;
+import org.apache.lucene.analysis.TeeSinkTokenFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.WhitespaceAnalyzer;
+import org.apache.lucene.analysis.standard.StandardAnalyzer;
+import org.apache.lucene.document.Document;
+import org.apache.lucene.document.Field;
+import org.apache.lucene.store.Directory;
+import org.apache.lucene.store.MockDirectoryWrapper;
+import org.apache.lucene.store.RAMDirectory;
+import org.apache.lucene.util.LuceneTestCase;
+
+/** tests for writing term vectors */
+public class TestTermVectorsWriter extends LuceneTestCase {
+  // LUCENE-1442
+  public void testDoubleOffsetCounting() throws Exception {
+    Directory dir = newDirectory();
+    IndexWriter w = new IndexWriter(dir, newIndexWriterConfig( 
+        TEST_VERSION_CURRENT, new MockAnalyzer(random)));
+    Document doc = new Document();
+    Field f = newField("field", "abcd", Field.Store.NO, Field.Index.NOT_ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
+    doc.add(f);
+    doc.add(f);
+    Field f2 = newField("field", "", Field.Store.NO, Field.Index.NOT_ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
+    doc.add(f2);
+    doc.add(f);
+    w.addDocument(doc);
+    w.close();
+
+    IndexReader r = IndexReader.open(dir, true);
+    TermVectorOffsetInfo[] termOffsets = ((TermPositionVector) r.getTermFreqVector(0, "field")).getOffsets(0);
+
+    // Token "" occurred once
+    assertEquals(1, termOffsets.length);
+    assertEquals(8, termOffsets[0].getStartOffset());
+    assertEquals(8, termOffsets[0].getEndOffset());
+
+    // Token "abcd" occurred three times
+    termOffsets = ((TermPositionVector) r.getTermFreqVector(0, "field")).getOffsets(1);
+    assertEquals(3, termOffsets.length);
+    assertEquals(0, termOffsets[0].getStartOffset());
+    assertEquals(4, termOffsets[0].getEndOffset());
+    assertEquals(4, termOffsets[1].getStartOffset());
+    assertEquals(8, termOffsets[1].getEndOffset());
+    assertEquals(8, termOffsets[2].getStartOffset());
+    assertEquals(12, termOffsets[2].getEndOffset());
+    r.close();
+    dir.close();
+  }
+
+  // LUCENE-1442
+  public void testDoubleOffsetCounting2() throws Exception {
+    Directory dir = newDirectory();
+    IndexWriter w = new IndexWriter(dir, newIndexWriterConfig( TEST_VERSION_CURRENT, new MockAnalyzer(random)));
+    Document doc = new Document();
+    Field f = newField("field", "abcd", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
+    doc.add(f);
+    doc.add(f);
+    w.addDocument(doc);
+    w.close();
+
+    IndexReader r = IndexReader.open(dir, true);
+    TermVectorOffsetInfo[] termOffsets = ((TermPositionVector) r.getTermFreqVector(0, "field")).getOffsets(0);
+    assertEquals(2, termOffsets.length);
+    assertEquals(0, termOffsets[0].getStartOffset());
+    assertEquals(4, termOffsets[0].getEndOffset());
+    assertEquals(5, termOffsets[1].getStartOffset());
+    assertEquals(9, termOffsets[1].getEndOffset());
+    r.close();
+    dir.close();
+  }
+
+  // LUCENE-1448
+  public void testEndOffsetPositionCharAnalyzer() throws Exception {
+    Directory dir = newDirectory();
+    IndexWriter w = new IndexWriter(dir, newIndexWriterConfig( TEST_VERSION_CURRENT, new MockAnalyzer(random)));
+    Document doc = new Document();
+    Field f = newField("field", "abcd   ", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
+    doc.add(f);
+    doc.add(f);
+    w.addDocument(doc);
+    w.close();
+
+    IndexReader r = IndexReader.open(dir, true);
+    TermVectorOffsetInfo[] termOffsets = ((TermPositionVector) r.getTermFreqVector(0, "field")).getOffsets(0);
+    assertEquals(2, termOffsets.length);
+    assertEquals(0, termOffsets[0].getStartOffset());
+    assertEquals(4, termOffsets[0].getEndOffset());
+    assertEquals(8, termOffsets[1].getStartOffset());
+    assertEquals(12, termOffsets[1].getEndOffset());
+    r.close();
+    dir.close();
+  }
+
+  // LUCENE-1448
+  public void testEndOffsetPositionWithCachingTokenFilter() throws Exception {
+    Directory dir = newDirectory();
+    Analyzer analyzer = new MockAnalyzer(random);
+    IndexWriter w = new IndexWriter(dir, newIndexWriterConfig( TEST_VERSION_CURRENT, analyzer));
+    Document doc = new Document();
+    TokenStream stream = analyzer.tokenStream("field", new StringReader("abcd   "));
+    stream.reset(); // TODO: wierd to reset before wrapping with CachingTokenFilter... correct?
+    stream = new CachingTokenFilter(stream);
+    Field f = new Field("field", stream, Field.TermVector.WITH_POSITIONS_OFFSETS);
+    doc.add(f);
+    doc.add(f);
+    w.addDocument(doc);
+    w.close();
+
+    IndexReader r = IndexReader.open(dir, true);
+    TermVectorOffsetInfo[] termOffsets = ((TermPositionVector) r.getTermFreqVector(0, "field")).getOffsets(0);
+    assertEquals(2, termOffsets.length);
+    assertEquals(0, termOffsets[0].getStartOffset());
+    assertEquals(4, termOffsets[0].getEndOffset());
+    assertEquals(8, termOffsets[1].getStartOffset());
+    assertEquals(12, termOffsets[1].getEndOffset());
+    r.close();
+    dir.close();
+  }
+  
+  // LUCENE-1448
+  public void testEndOffsetPositionWithTeeSinkTokenFilter() throws Exception {
+    MockDirectoryWrapper dir = newDirectory();
+    Analyzer analyzer = new WhitespaceAnalyzer(TEST_VERSION_CURRENT);
+    IndexWriter w = new IndexWriter(dir, new IndexWriterConfig(TEST_VERSION_CURRENT, analyzer));
+    Document doc = new Document();
+    TeeSinkTokenFilter tee = new TeeSinkTokenFilter(analyzer.tokenStream("field", new StringReader("abcd   ")));
+    TokenStream sink = tee.newSinkTokenStream();
+    Field f1 = new Field("field", tee, Field.TermVector.WITH_POSITIONS_OFFSETS);
+    Field f2 = new Field("field", sink, Field.TermVector.WITH_POSITIONS_OFFSETS);
+    doc.add(f1);
+    doc.add(f2);
+    w.addDocument(doc);
+    w.close();
+
+    IndexReader r = IndexReader.open(dir, true);
+    TermVectorOffsetInfo[] termOffsets = ((TermPositionVector) r.getTermFreqVector(0, "field")).getOffsets(0);
+    assertEquals(2, termOffsets.length);
+    assertEquals(0, termOffsets[0].getStartOffset());
+    assertEquals(4, termOffsets[0].getEndOffset());
+    assertEquals(8, termOffsets[1].getStartOffset());
+    assertEquals(12, termOffsets[1].getEndOffset());
+    r.close();
+    dir.close();
+  }
+  
+  // LUCENE-1448
+  public void testEndOffsetPositionStopFilter() throws Exception {
+    Directory dir = newDirectory();
+    IndexWriter w = new IndexWriter(dir, newIndexWriterConfig( 
+        TEST_VERSION_CURRENT, new StandardAnalyzer(TEST_VERSION_CURRENT)));
+    Document doc = new Document();
+    Field f = newField("field", "abcd the", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
+    doc.add(f);
+    doc.add(f);
+    w.addDocument(doc);
+    w.close();
+
+    IndexReader r = IndexReader.open(dir, true);
+    TermVectorOffsetInfo[] termOffsets = ((TermPositionVector) r.getTermFreqVector(0, "field")).getOffsets(0);
+    assertEquals(2, termOffsets.length);
+    assertEquals(0, termOffsets[0].getStartOffset());
+    assertEquals(4, termOffsets[0].getEndOffset());
+    assertEquals(9, termOffsets[1].getStartOffset());
+    assertEquals(13, termOffsets[1].getEndOffset());
+    r.close();
+    dir.close();
+  }
+
+  // LUCENE-1448
+  public void testEndOffsetPositionStandard() throws Exception {
+    Directory dir = newDirectory();
+    IndexWriter w = new IndexWriter(dir, newIndexWriterConfig( 
+        TEST_VERSION_CURRENT, new MockAnalyzer(random)));
+    Document doc = new Document();
+    Field f = newField("field", "abcd the  ", Field.Store.NO,
+        Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
+    Field f2 = newField("field", "crunch man", Field.Store.NO,
+        Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
+    doc.add(f);
+    doc.add(f2);
+    w.addDocument(doc);
+    w.close();
+
+    IndexReader r = IndexReader.open(dir, true);
+    TermPositionVector tpv = ((TermPositionVector) r.getTermFreqVector(0, "field"));
+    TermVectorOffsetInfo[] termOffsets = tpv.getOffsets(0);
+    assertEquals(1, termOffsets.length);
+    assertEquals(0, termOffsets[0].getStartOffset());
+    assertEquals(4, termOffsets[0].getEndOffset());
+    termOffsets = tpv.getOffsets(1);
+    assertEquals(11, termOffsets[0].getStartOffset());
+    assertEquals(17, termOffsets[0].getEndOffset());
+    termOffsets = tpv.getOffsets(2);
+    assertEquals(18, termOffsets[0].getStartOffset());
+    assertEquals(21, termOffsets[0].getEndOffset());
+    r.close();
+    dir.close();
+  }
+
+  // LUCENE-1448
+  public void testEndOffsetPositionStandardEmptyField() throws Exception {
+    Directory dir = newDirectory();
+    IndexWriter w = new IndexWriter(dir, newIndexWriterConfig( 
+        TEST_VERSION_CURRENT, new MockAnalyzer(random)));
+    Document doc = new Document();
+    Field f = newField("field", "", Field.Store.NO,
+                        Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
+    Field f2 = newField("field", "crunch man", Field.Store.NO,
+        Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
+    doc.add(f);
+    doc.add(f2);
+    w.addDocument(doc);
+    w.close();
+
+    IndexReader r = IndexReader.open(dir, true);
+    TermPositionVector tpv = ((TermPositionVector) r.getTermFreqVector(0, "field"));
+    TermVectorOffsetInfo[] termOffsets = tpv.getOffsets(0);
+    assertEquals(1, termOffsets.length);
+    assertEquals(1, termOffsets[0].getStartOffset());
+    assertEquals(7, termOffsets[0].getEndOffset());
+    termOffsets = tpv.getOffsets(1);
+    assertEquals(8, termOffsets[0].getStartOffset());
+    assertEquals(11, termOffsets[0].getEndOffset());
+    r.close();
+    dir.close();
+  }
+
+  // LUCENE-1448
+  public void testEndOffsetPositionStandardEmptyField2() throws Exception {
+    Directory dir = newDirectory();
+    IndexWriter w = new IndexWriter(dir, newIndexWriterConfig( 
+        TEST_VERSION_CURRENT, new MockAnalyzer(random)));
+    Document doc = new Document();
+
+    Field f = newField("field", "abcd", Field.Store.NO,
+                        Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
+    doc.add(f);
+    doc.add(newField("field", "", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS));
+
+    Field f2 = newField("field", "crunch", Field.Store.NO,
+        Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
+    doc.add(f2);
+
+    w.addDocument(doc);
+    w.close();
+
+    IndexReader r = IndexReader.open(dir, true);
+    TermPositionVector tpv = ((TermPositionVector) r.getTermFreqVector(0, "field"));
+    TermVectorOffsetInfo[] termOffsets = tpv.getOffsets(0);
+    assertEquals(1, termOffsets.length);
+    assertEquals(0, termOffsets[0].getStartOffset());
+    assertEquals(4, termOffsets[0].getEndOffset());
+    termOffsets = tpv.getOffsets(1);
+    assertEquals(6, termOffsets[0].getStartOffset());
+    assertEquals(12, termOffsets[0].getEndOffset());
+    r.close();
+    dir.close();
+  }
+  
+  // LUCENE-1168
+  public void testTermVectorCorruption() throws IOException {
+
+    Directory dir = newDirectory();
+    for(int iter=0;iter<2;iter++) {
+      IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(
+          TEST_VERSION_CURRENT, new MockAnalyzer(random))
+          .setMaxBufferedDocs(2).setRAMBufferSizeMB(
+              IndexWriterConfig.DISABLE_AUTO_FLUSH).setMergeScheduler(
+              new SerialMergeScheduler()).setMergePolicy(
+              new LogDocMergePolicy()));
+
+      Document document = new Document();
+
+      Field storedField = newField("stored", "stored", Field.Store.YES,
+                                    Field.Index.NO);
+      document.add(storedField);
+      writer.addDocument(document);
+      writer.addDocument(document);
+
+      document = new Document();
+      document.add(storedField);
+      Field termVectorField = newField("termVector", "termVector",
+                                        Field.Store.NO, Field.Index.NOT_ANALYZED,
+                                        Field.TermVector.WITH_POSITIONS_OFFSETS);
+
+      document.add(termVectorField);
+      writer.addDocument(document);
+      writer.forceMerge(1);
+      writer.close();
+
+      IndexReader reader = IndexReader.open(dir, true);
+      for(int i=0;i<reader.numDocs();i++) {
+        reader.document(i);
+        reader.getTermFreqVectors(i);
+      }
+      reader.close();
+
+      writer = new IndexWriter(dir, newIndexWriterConfig( TEST_VERSION_CURRENT,
+          new MockAnalyzer(random)).setMaxBufferedDocs(2)
+          .setRAMBufferSizeMB(IndexWriterConfig.DISABLE_AUTO_FLUSH)
+          .setMergeScheduler(new SerialMergeScheduler()).setMergePolicy(
+              new LogDocMergePolicy()));
+
+      Directory[] indexDirs = {new MockDirectoryWrapper(random, new RAMDirectory(dir))};
+      writer.addIndexes(indexDirs);
+      writer.forceMerge(1);
+      writer.close();
+    }
+    dir.close();
+  }
+
+  // LUCENE-1168
+  public void testTermVectorCorruption2() throws IOException {
+    Directory dir = newDirectory();
+    for(int iter=0;iter<2;iter++) {
+      IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(
+          TEST_VERSION_CURRENT, new MockAnalyzer(random))
+          .setMaxBufferedDocs(2).setRAMBufferSizeMB(
+              IndexWriterConfig.DISABLE_AUTO_FLUSH).setMergeScheduler(
+              new SerialMergeScheduler()).setMergePolicy(
+              new LogDocMergePolicy()));
+
+      Document document = new Document();
+
+      Field storedField = newField("stored", "stored", Field.Store.YES,
+                                    Field.Index.NO);
+      document.add(storedField);
+      writer.addDocument(document);
+      writer.addDocument(document);
+
+      document = new Document();
+      document.add(storedField);
+      Field termVectorField = newField("termVector", "termVector",
+                                        Field.Store.NO, Field.Index.NOT_ANALYZED,
+                                        Field.TermVector.WITH_POSITIONS_OFFSETS);
+      document.add(termVectorField);
+      writer.addDocument(document);
+      writer.forceMerge(1);
+      writer.close();
+
+      IndexReader reader = IndexReader.open(dir, true);
+      assertTrue(reader.getTermFreqVectors(0)==null);
+      assertTrue(reader.getTermFreqVectors(1)==null);
+      assertTrue(reader.getTermFreqVectors(2)!=null);
+      reader.close();
+    }
+    dir.close();
+  }
+
+  // LUCENE-1168
+  public void testTermVectorCorruption3() throws IOException {
+    Directory dir = newDirectory();
+    IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(
+        TEST_VERSION_CURRENT, new MockAnalyzer(random))
+        .setMaxBufferedDocs(2).setRAMBufferSizeMB(
+            IndexWriterConfig.DISABLE_AUTO_FLUSH).setMergeScheduler(
+            new SerialMergeScheduler()).setMergePolicy(new LogDocMergePolicy()));
+
+    Document document = new Document();
+
+    document = new Document();
+    Field storedField = newField("stored", "stored", Field.Store.YES,
+                                  Field.Index.NO);
+    document.add(storedField);
+    Field termVectorField = newField("termVector", "termVector",
+                                      Field.Store.NO, Field.Index.NOT_ANALYZED,
+                                      Field.TermVector.WITH_POSITIONS_OFFSETS);
+    document.add(termVectorField);
+    for(int i=0;i<10;i++)
+      writer.addDocument(document);
+    writer.close();
+
+    writer = new IndexWriter(dir, newIndexWriterConfig( TEST_VERSION_CURRENT,
+        new MockAnalyzer(random)).setMaxBufferedDocs(2)
+        .setRAMBufferSizeMB(IndexWriterConfig.DISABLE_AUTO_FLUSH)
+        .setMergeScheduler(new SerialMergeScheduler()).setMergePolicy(
+            new LogDocMergePolicy()));
+    for(int i=0;i<6;i++)
+      writer.addDocument(document);
+
+    writer.forceMerge(1);
+    writer.close();
+
+    IndexReader reader = IndexReader.open(dir, true);
+    for(int i=0;i<10;i++) {
+      reader.getTermFreqVectors(i);
+      reader.document(i);
+    }
+    reader.close();
+    dir.close();
+  }
+  
+  // LUCENE-1008
+  public void testNoTermVectorAfterTermVector() throws IOException {
+    Directory dir = newDirectory();
+    IndexWriter iw = new IndexWriter(dir, newIndexWriterConfig(
+        TEST_VERSION_CURRENT, new MockAnalyzer(random)));
+    Document document = new Document();
+    document.add(newField("tvtest", "a b c", Field.Store.NO, Field.Index.ANALYZED,
+        Field.TermVector.YES));
+    iw.addDocument(document);
+    document = new Document();
+    document.add(newField("tvtest", "x y z", Field.Store.NO, Field.Index.ANALYZED,
+                           Field.TermVector.NO));
+    iw.addDocument(document);
+    // Make first segment
+    iw.commit();
+
+    document.add(newField("tvtest", "a b c", Field.Store.NO, Field.Index.ANALYZED,
+        Field.TermVector.YES));
+    iw.addDocument(document);
+    // Make 2nd segment
+    iw.commit();
+
+    iw.forceMerge(1);
+    iw.close();
+    dir.close();
+  }
+
+  // LUCENE-1010
+  public void testNoTermVectorAfterTermVectorMerge() throws IOException {
+    Directory dir = newDirectory();
+    IndexWriter iw = new IndexWriter(dir, newIndexWriterConfig(
+        TEST_VERSION_CURRENT, new MockAnalyzer(random)));
+    Document document = new Document();
+    document.add(newField("tvtest", "a b c", Field.Store.NO, Field.Index.ANALYZED,
+        Field.TermVector.YES));
+    iw.addDocument(document);
+    iw.commit();
+
+    document = new Document();
+    document.add(newField("tvtest", "x y z", Field.Store.NO, Field.Index.ANALYZED,
+                           Field.TermVector.NO));
+    iw.addDocument(document);
+    // Make first segment
+    iw.commit();
+
+    iw.forceMerge(1);
+
+    document.add(newField("tvtest", "a b c", Field.Store.NO, Field.Index.ANALYZED,
+        Field.TermVector.YES));
+    iw.addDocument(document);
+    // Make 2nd segment
+    iw.commit();
+    iw.forceMerge(1);
+
+    iw.close();
+    dir.close();
+  }
+}