LUCNE-5675: add failing test

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/branches/lucene5675@1595068 13f79535-47bb-0310-9956-ffa450edef68

lucene/codecs/src/java/org/apache/lucene/codecs/idversion/IDVersionPostingsFormat.java

@@ -28,6 +28,7 @@ import org.apache.lucene.codecs.blocktree.BlockTreeTermsReader;
 import org.apache.lucene.codecs.blocktree.BlockTreeTermsWriter;
 import org.apache.lucene.index.SegmentReadState;
 import org.apache.lucene.index.SegmentWriteState;
+import org.apache.lucene.util.BytesRef;
 import org.apache.lucene.util.IOUtils;
 
 /** A PostingsFormat for primary-key (ID) fields, that associates a
@@ -41,7 +42,7 @@ import org.apache.lucene.util.IOUtils;
  *
  *  @lucene.experimental */
 
-public abstract class IDVersionPostingsFormat extends PostingsFormat {
+public class IDVersionPostingsFormat extends PostingsFormat {
 
   private final int minTermsInBlock;
   private final int maxTermsInBlock;
@@ -93,4 +94,26 @@ public abstract class IDVersionPostingsFormat extends PostingsFormat {
        }
      }
   }
+
+  public static long bytesToLong(BytesRef bytes) {
+    return ((bytes.bytes[bytes.offset]&0xFF) << 56) |
+      ((bytes.bytes[bytes.offset+1]&0xFF) << 48) |
+      ((bytes.bytes[bytes.offset+2]&0xFF) << 40) |
+      ((bytes.bytes[bytes.offset+3]&0xFF) << 32) |
+      ((bytes.bytes[bytes.offset+4]&0xFF) << 24) |
+      ((bytes.bytes[bytes.offset+5]&0xFF) << 16) |
+      ((bytes.bytes[bytes.offset+6]&0xFF) << 8) |
+      (bytes.bytes[bytes.offset+7]&0xFF);
+  }
+
+  public static void longToBytes(long v, BytesRef bytes) {
+    bytes.bytes[0] = (byte) (v >> 56);
+    bytes.bytes[1] = (byte) (v >> 48);
+    bytes.bytes[2] = (byte) (v >> 40);
+    bytes.bytes[3] = (byte) (v >> 32);
+    bytes.bytes[4] = (byte) (v >> 24);
+    bytes.bytes[5] = (byte) (v >> 16);
+    bytes.bytes[6] = (byte) (v >> 8);
+    bytes.bytes[7] = (byte) v;
+  }
 }

lucene/codecs/src/java/org/apache/lucene/codecs/idversion/IDVersionPostingsReader.java

@@ -53,8 +53,8 @@ public final class IDVersionPostingsReader extends PostingsReaderBase {
   public void decodeTerm(long[] longs, DataInput in, FieldInfo fieldInfo, BlockTermState _termState, boolean absolute)
     throws IOException {
     final IDVersionTermState termState = (IDVersionTermState) _termState;
-    termState.idVersion = Long.MAX_VALUE - longs[0];
     termState.docID = in.readVInt();
+    termState.idVersion = in.readVLong();
   }
 
   @Override

lucene/codecs/src/java/org/apache/lucene/codecs/idversion/IDVersionPostingsWriter.java

@@ -92,14 +92,14 @@ public final class IDVersionPostingsWriter extends PushPostingsWriterBase {
     lastPosition = position;
     if (payload == null) {
       // nocommit need test
-      throw new IllegalArgumentException("missing payload");
+      throw new IllegalArgumentException("token doens't have a payload");
     }
-    if (payload.length == 0) {
+    if (payload.length != 8) {
       // nocommit need test
-      throw new IllegalArgumentException("payload.length == 0");
+      throw new IllegalArgumentException("payload.length != 8 (got " + payload.length + ")");
     }
-    // nocommit decode payload to long here ... PayloadHelper!?  or keep as byte[]?
-    lastVersion = 0;
+    
+    lastVersion = IDVersionPostingsFormat.bytesToLong(payload);
   }
 
   @Override

lucene/codecs/src/java/org/apache/lucene/codecs/idversion/IDVersionSegmentTermsEnum.java

@@ -40,7 +40,7 @@ import org.apache.lucene.util.fst.PairOutputs;
 import org.apache.lucene.util.fst.Util;
 
 /** Iterates through terms in this field */
-final class IDVersionSegmentTermsEnum extends TermsEnum {
+public final class IDVersionSegmentTermsEnum extends TermsEnum {
 
   final static Outputs<Pair<BytesRef,Long>> fstOutputs = VersionBlockTreeTermsWriter.getFSTOutputs();
   final static Pair<BytesRef,Long> NO_OUTPUT = fstOutputs.getNoOutput();

lucene/codecs/src/java/org/apache/lucene/codecs/idversion/SingleDocsAndPositionsEnum.java

@@ -27,7 +27,7 @@ class SingleDocsAndPositionsEnum extends DocsAndPositionsEnum {
   private int singleDocID;
   private Bits liveDocs;
   private long version;
-  private final BytesRef payload = new BytesRef();
+  private final BytesRef payload = new BytesRef(8);
 
   /** For reuse */
   public void reset(int singleDocID, long version, Bits liveDocs) {
@@ -79,7 +79,7 @@ class SingleDocsAndPositionsEnum extends DocsAndPositionsEnum {
   public int nextPosition() {
     assert pos == -1;
     pos = 0;
-    // nocommit re-encode version back into payload here:
+    IDVersionPostingsFormat.longToBytes(version, payload);
     return pos;
   }
 

lucene/codecs/src/test/org/apache/lucene/codecs/idversion/TestIDVersionPostingsFormat.java

@@ -0,0 +1,71 @@
+package org.apache.lucene.codecs.idversion;
+
+/*
+ * 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 org.apache.lucene.analysis.CannedTokenStream;
+import org.apache.lucene.analysis.MockAnalyzer;
+import org.apache.lucene.analysis.Token;
+import org.apache.lucene.codecs.Codec;
+import org.apache.lucene.document.Document;
+import org.apache.lucene.document.Field;
+import org.apache.lucene.index.BasePostingsFormatTestCase;
+import org.apache.lucene.index.IndexReader;
+import org.apache.lucene.index.IndexWriterConfig;
+import org.apache.lucene.index.MultiFields;
+import org.apache.lucene.index.RandomIndexWriter;
+import org.apache.lucene.index.TermsEnum;
+import org.apache.lucene.store.Directory;
+import org.apache.lucene.util.BytesRef;
+import org.apache.lucene.util.LuceneTestCase;
+import org.apache.lucene.util.TestUtil;
+
+/**
+ * Basic tests for IDVersionPostingsFormat
+ */
+public class TestIDVersionPostingsFormat extends LuceneTestCase {
+
+  public void testBasic() throws Exception {
+    Directory dir = newDirectory();
+    IndexWriterConfig iwc = newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random()));
+    iwc.setCodec(TestUtil.alwaysPostingsFormat(new IDVersionPostingsFormat()));
+    RandomIndexWriter w = new RandomIndexWriter(random(), dir, iwc);
+    Document doc = new Document();
+    doc.add(makeIDField("id0", 100));
+    w.addDocument(doc);
+    IndexReader r = w.getReader();
+    IDVersionSegmentTermsEnum termsEnum = (IDVersionSegmentTermsEnum) MultiFields.getTerms(r, "id").iterator(null);
+    assertTrue(termsEnum.seekExact(new BytesRef("id0"), 50));
+    assertFalse(termsEnum.seekExact(new BytesRef("id0"), 101));
+    r.close();
+
+    w.close();
+    dir.close();
+  }
+
+  // nocommit need testRandom
+
+  private static Field makeIDField(String id, long version) {
+    Field field = newTextField("id", "", Field.Store.NO);
+    Token token = new Token(id, 0, id.length());
+    BytesRef payload = new BytesRef(8);
+    IDVersionPostingsFormat.longToBytes(100, payload);
+    token.setPayload(payload);
+    field.setTokenStream(new CannedTokenStream(token));
+    return field;
+  }
+}