beef up tests

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/branches/lucene4765@1446990 13f79535-47bb-0310-9956-ffa450edef68

lucene/core/src/test/org/apache/lucene/index/TestDocValuesIndexing.java

@@ -28,6 +28,7 @@ import org.apache.lucene.document.Document;
 import org.apache.lucene.document.Field;
 import org.apache.lucene.document.NumericDocValuesField;
 import org.apache.lucene.document.SortedDocValuesField;
+import org.apache.lucene.document.SortedSetDocValuesField;
 import org.apache.lucene.document.TextField;
 import org.apache.lucene.search.FieldCache;
 import org.apache.lucene.store.Directory;
@@ -372,6 +373,30 @@ public class TestDocValuesIndexing extends LuceneTestCase {
     iwriter.close();
     directory.close();
   }
+  
+  public void testTooLargeTermSortedSetBytes() throws IOException {
+    assumeTrue("codec does not support SORTED_SET", defaultCodecSupportsSortedSet());
+    Analyzer analyzer = new MockAnalyzer(random());
+
+    Directory directory = newDirectory();
+    // we don't use RandomIndexWriter because it might add more docvalues than we expect !!!!1
+    IndexWriterConfig iwc = newIndexWriterConfig(TEST_VERSION_CURRENT, analyzer);
+    iwc.setMergePolicy(newLogMergePolicy());
+    IndexWriter iwriter = new IndexWriter(directory, iwc);
+    Document doc = new Document();
+    byte bytes[] = new byte[100000];
+    BytesRef b = new BytesRef(bytes);
+    random().nextBytes(bytes);
+    doc.add(new SortedSetDocValuesField("dv", b));
+    try {
+      iwriter.addDocument(doc);
+      fail("did not get expected exception");
+    } catch (IllegalArgumentException expected) {
+      // expected
+    }
+    iwriter.close();
+    directory.close();
+  }
 
   // Two documents across segments
   public void testMixedTypesDifferentSegments() throws Exception {

lucene/core/src/test/org/apache/lucene/index/TestIndexWriter.java

@@ -40,6 +40,7 @@ import org.apache.lucene.document.Field;
 import org.apache.lucene.document.FieldType;
 import org.apache.lucene.document.NumericDocValuesField;
 import org.apache.lucene.document.SortedDocValuesField;
+import org.apache.lucene.document.SortedSetDocValuesField;
 import org.apache.lucene.document.StoredField;
 import org.apache.lucene.document.StringField;
 import org.apache.lucene.document.TextField;
@@ -1023,6 +1024,10 @@ public class TestIndexWriter extends LuceneTestCase {
       doc.add(new BinaryDocValuesField("binarydv", new BytesRef("500")));
       doc.add(new NumericDocValuesField("numericdv", 500));
       doc.add(new SortedDocValuesField("sorteddv", new BytesRef("500")));
+      if (defaultCodecSupportsSortedSet()) {
+        doc.add(new SortedSetDocValuesField("sortedsetdv", new BytesRef("one")));
+        doc.add(new SortedSetDocValuesField("sortedsetdv", new BytesRef("two")));
+      }
       w.addDocument(doc);
       doc = new Document();
       doc.add(newStringField(random, "id", "501", Field.Store.NO));
@@ -1030,6 +1035,10 @@ public class TestIndexWriter extends LuceneTestCase {
       doc.add(new BinaryDocValuesField("binarydv", new BytesRef("501")));
       doc.add(new NumericDocValuesField("numericdv", 501));
       doc.add(new SortedDocValuesField("sorteddv", new BytesRef("501")));
+      if (defaultCodecSupportsSortedSet()) {
+        doc.add(new SortedSetDocValuesField("sortedsetdv", new BytesRef("two")));
+        doc.add(new SortedSetDocValuesField("sortedsetdv", new BytesRef("three")));
+      }
       w.addDocument(doc);
       w.deleteDocuments(new Term("id", "500"));
       w.close();
@@ -1057,16 +1066,21 @@ public class TestIndexWriter extends LuceneTestCase {
             Field binaryDVField = new BinaryDocValuesField("binarydv", new BytesRef());
             Field numericDVField = new NumericDocValuesField("numericdv", 0);
             Field sortedDVField = new SortedDocValuesField("sorteddv", new BytesRef());
+            Field sortedSetDVField = new SortedSetDocValuesField("sortedsetdv", new BytesRef());
             doc.add(idField);
             doc.add(newField(random, "field", "some text contents", storedTextType));
             doc.add(binaryDVField);
             doc.add(numericDVField);
             doc.add(sortedDVField);
+            if (defaultCodecSupportsSortedSet()) {
+              doc.add(sortedSetDVField);
+            }
             for(int i=0;i<100;i++) {
               idField.setStringValue(Integer.toString(i));
               binaryDVField.setBytesValue(new BytesRef(idField.stringValue()));
               numericDVField.setLongValue(i);
               sortedDVField.setBytesValue(new BytesRef(idField.stringValue()));
+              sortedSetDVField.setBytesValue(new BytesRef(idField.stringValue()));
               int action = random.nextInt(100);
               if (action == 17) {
                 w.addIndexes(adder);

lucene/core/src/test/org/apache/lucene/index/TestIndexWriterExceptions.java

@@ -33,6 +33,7 @@ import org.apache.lucene.document.Field;
 import org.apache.lucene.document.FieldType;
 import org.apache.lucene.document.NumericDocValuesField;
 import org.apache.lucene.document.SortedDocValuesField;
+import org.apache.lucene.document.SortedSetDocValuesField;
 import org.apache.lucene.document.StringField;
 import org.apache.lucene.document.TextField;
 import org.apache.lucene.index.IndexWriterConfig.OpenMode;
@@ -143,6 +144,10 @@ public class TestIndexWriterExceptions extends LuceneTestCase {
       doc.add(new NumericDocValuesField("numericdv", 5));
       doc.add(new BinaryDocValuesField("binarydv", new BytesRef("hello")));
       doc.add(new SortedDocValuesField("sorteddv", new BytesRef("world")));
+      if (defaultCodecSupportsSortedSet()) {
+        doc.add(new SortedSetDocValuesField("sortedsetdv", new BytesRef("hellllo")));
+        doc.add(new SortedSetDocValuesField("sortedsetdv", new BytesRef("again")));
+      }
 
       doc.add(newField(r, "content7", "aaa bbb ccc ddd", DocCopyIterator.custom4));
 

lucene/core/src/test/org/apache/lucene/index/TestMultiDocValues.java

@@ -17,11 +17,14 @@ package org.apache.lucene.index;
  * limitations under the License.
  */
 
+import java.util.ArrayList;
+
 import org.apache.lucene.document.BinaryDocValuesField;
 import org.apache.lucene.document.Document;
 import org.apache.lucene.document.Field;
 import org.apache.lucene.document.NumericDocValuesField;
 import org.apache.lucene.document.SortedDocValuesField;
+import org.apache.lucene.document.SortedSetDocValuesField;
 import org.apache.lucene.store.Directory;
 import org.apache.lucene.util.BytesRef;
 import org.apache.lucene.util.LuceneTestCase;
@@ -189,4 +192,133 @@ public class TestMultiDocValues extends LuceneTestCase {
     ir2.close();
     dir.close();
   }
+  
+  public void testSortedSet() throws Exception {
+    assumeTrue("codec does not support SORTED_SET", defaultCodecSupportsSortedSet());
+    Directory dir = newDirectory();
+    
+    IndexWriterConfig iwc = newIndexWriterConfig(random(), TEST_VERSION_CURRENT, null);
+    iwc.setMergePolicy(newLogMergePolicy());
+    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, iwc);
+
+    int numDocs = atLeast(500);
+    for (int i = 0; i < numDocs; i++) {
+      Document doc = new Document();
+      int numValues = random().nextInt(5);
+      for (int j = 0; j < numValues; j++) {
+        doc.add(new SortedSetDocValuesField("bytes", new BytesRef(_TestUtil.randomUnicodeString(random()))));
+      }
+      iw.addDocument(doc);
+      if (random().nextInt(17) == 0) {
+        iw.commit();
+      }
+    }
+    DirectoryReader ir = iw.getReader();
+    iw.forceMerge(1);
+    DirectoryReader ir2 = iw.getReader();
+    AtomicReader merged = getOnlySegmentReader(ir2);
+    iw.close();
+    
+    SortedSetDocValues multi = MultiDocValues.getSortedSetValues(ir, "bytes");
+    SortedSetDocValues single = merged.getSortedSetDocValues("bytes");
+    if (multi == null) {
+      assertNull(single);
+    } else {
+      assertEquals(single.getValueCount(), multi.getValueCount());
+      BytesRef actual = new BytesRef();
+      BytesRef expected = new BytesRef();
+      // check values
+      for (long i = 0; i < single.getValueCount(); i++) {
+        single.lookupOrd(i, expected);
+        multi.lookupOrd(i, actual);
+        assertEquals(expected, actual);
+      }
+      // check ord list
+      for (int i = 0; i < numDocs; i++) {
+        single.setDocument(i);
+        ArrayList<Long> expectedList = new ArrayList<Long>();
+        long ord;
+        while ((ord = single.nextOrd()) != SortedSetDocValues.NO_MORE_ORDS) {
+          expectedList.add(ord);
+        }
+        
+        multi.setDocument(i);
+        int upto = 0;
+        while ((ord = multi.nextOrd()) != SortedSetDocValues.NO_MORE_ORDS) {
+          assertEquals(expectedList.get(upto).longValue(), ord);
+          upto++;
+        }
+        assertEquals(expectedList.size(), upto);
+      }
+    }
+    
+    ir.close();
+    ir2.close();
+    dir.close();
+  }
+  
+  // tries to make more dups than testSortedSet
+  public void testSortedSetWithDups() throws Exception {
+    assumeTrue("codec does not support SORTED_SET", defaultCodecSupportsSortedSet());
+    Directory dir = newDirectory();
+    
+    IndexWriterConfig iwc = newIndexWriterConfig(random(), TEST_VERSION_CURRENT, null);
+    iwc.setMergePolicy(newLogMergePolicy());
+    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, iwc);
+
+    int numDocs = atLeast(500);
+    for (int i = 0; i < numDocs; i++) {
+      Document doc = new Document();
+      int numValues = random().nextInt(5);
+      for (int j = 0; j < numValues; j++) {
+        doc.add(new SortedSetDocValuesField("bytes", new BytesRef(_TestUtil.randomSimpleString(random(), 2))));
+      }
+      iw.addDocument(doc);
+      if (random().nextInt(17) == 0) {
+        iw.commit();
+      }
+    }
+    DirectoryReader ir = iw.getReader();
+    iw.forceMerge(1);
+    DirectoryReader ir2 = iw.getReader();
+    AtomicReader merged = getOnlySegmentReader(ir2);
+    iw.close();
+    
+    SortedSetDocValues multi = MultiDocValues.getSortedSetValues(ir, "bytes");
+    SortedSetDocValues single = merged.getSortedSetDocValues("bytes");
+    if (multi == null) {
+      assertNull(single);
+    } else {
+      assertEquals(single.getValueCount(), multi.getValueCount());
+      BytesRef actual = new BytesRef();
+      BytesRef expected = new BytesRef();
+      // check values
+      for (long i = 0; i < single.getValueCount(); i++) {
+        single.lookupOrd(i, expected);
+        multi.lookupOrd(i, actual);
+        assertEquals(expected, actual);
+      }
+      // check ord list
+      for (int i = 0; i < numDocs; i++) {
+        single.setDocument(i);
+        ArrayList<Long> expectedList = new ArrayList<Long>();
+        long ord;
+        while ((ord = single.nextOrd()) != SortedSetDocValues.NO_MORE_ORDS) {
+          expectedList.add(ord);
+        }
+        
+        multi.setDocument(i);
+        int upto = 0;
+        while ((ord = multi.nextOrd()) != SortedSetDocValues.NO_MORE_ORDS) {
+          assertEquals(expectedList.get(upto).longValue(), ord);
+          upto++;
+        }
+        assertEquals(expectedList.size(), upto);
+      }
+    }
+    
+    ir.close();
+    ir2.close();
+    dir.close();
+  }
 }