You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@pig.apache.org by ga...@apache.org on 2009/11/21 02:30:24 UTC
svn commit: r882818 - in /hadoop/pig/trunk/contrib/zebra: CHANGES.txt
src/java/org/apache/hadoop/zebra/types/Partition.java
src/test/org/apache/hadoop/zebra/io/TestProjectionOnFullMap.java
Author: gates
Date: Sat Nov 21 01:30:22 2009
New Revision: 882818
URL: http://svn.apache.org/viewvc?rev=882818&view=rev
Log:
PIG-1091 Exception when load with projection of map keys on a map column that is not map split.
Added:
hadoop/pig/trunk/contrib/zebra/src/test/org/apache/hadoop/zebra/io/TestProjectionOnFullMap.java
Modified:
hadoop/pig/trunk/contrib/zebra/CHANGES.txt
hadoop/pig/trunk/contrib/zebra/src/java/org/apache/hadoop/zebra/types/Partition.java
Modified: hadoop/pig/trunk/contrib/zebra/CHANGES.txt
URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/CHANGES.txt?rev=882818&r1=882817&r2=882818&view=diff
==============================================================================
--- hadoop/pig/trunk/contrib/zebra/CHANGES.txt (original)
+++ hadoop/pig/trunk/contrib/zebra/CHANGES.txt Sat Nov 21 01:30:22 2009
@@ -29,6 +29,9 @@
BUG FIXES
+ PIG-1091: Exception when load with projection of map keys on a map column
+ that is not map split (yanz via gates).
+
PIG-1026: [zebra] map split returns null (yanz via pradeepkth)
PIG-1057 Zebra does not support concurrent deletions of column groups now
Modified: hadoop/pig/trunk/contrib/zebra/src/java/org/apache/hadoop/zebra/types/Partition.java
URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/java/org/apache/hadoop/zebra/types/Partition.java?rev=882818&r1=882817&r2=882818&view=diff
==============================================================================
--- hadoop/pig/trunk/contrib/zebra/src/java/org/apache/hadoop/zebra/types/Partition.java (original)
+++ hadoop/pig/trunk/contrib/zebra/src/java/org/apache/hadoop/zebra/types/Partition.java Sat Nov 21 01:30:22 2009
@@ -726,8 +726,6 @@
cgindex = mapentry.getKey();
if (cgindex == null)
throw new AssertionError( "Internal Logical Error: RECORD does not have a CG index.");
- if (mapentry.getValue() != null)
- throw new AssertionError( "Internal Logical Error: RECORD should not have a split key map.");
cgentry = getCGEntry(cgindex.getCGIndex());
parCol = new PartitionedColumn(i, false);
cgentry.addUser(parCol, name);
Added: hadoop/pig/trunk/contrib/zebra/src/test/org/apache/hadoop/zebra/io/TestProjectionOnFullMap.java
URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/org/apache/hadoop/zebra/io/TestProjectionOnFullMap.java?rev=882818&view=auto
==============================================================================
--- hadoop/pig/trunk/contrib/zebra/src/test/org/apache/hadoop/zebra/io/TestProjectionOnFullMap.java (added)
+++ hadoop/pig/trunk/contrib/zebra/src/test/org/apache/hadoop/zebra/io/TestProjectionOnFullMap.java Sat Nov 21 01:30:22 2009
@@ -0,0 +1,137 @@
+/**
+ * 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.
+ */
+package org.apache.hadoop.zebra.io;
+
+import java.io.IOException;
+import java.io.PrintStream;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+
+import junit.framework.Assert;
+import junit.framework.TestCase;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.LocalFileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.fs.RawLocalFileSystem;
+import org.apache.hadoop.io.BytesWritable;
+import org.apache.hadoop.zebra.io.BasicTable;
+import org.apache.hadoop.zebra.io.TableInserter;
+import org.apache.hadoop.zebra.io.TableScanner;
+import org.apache.hadoop.zebra.io.BasicTable.Reader.RangeSplit;
+import org.apache.hadoop.zebra.parser.ParseException;
+import org.apache.hadoop.zebra.schema.Schema;
+import org.apache.hadoop.zebra.types.TypesUtils;
+import org.apache.pig.data.DataBag;
+import org.apache.pig.data.DataByteArray;
+import org.apache.pig.data.Tuple;
+import org.junit.AfterClass;
+import org.junit.BeforeClass;
+import org.junit.Test;
+
+/**
+ *
+ * Test projections on complicated column types.
+ *
+ */
+public class TestProjectionOnFullMap {
+ final static String STR_SCHEMA = "f1:string, f2:map";
+ final static String STR_STORAGE = "[f1]; [f2]";
+ private static Configuration conf;
+ private static Path path;
+ private static FileSystem fs;
+
+ @BeforeClass
+ public static void setUp() throws IOException {
+ conf = new Configuration();
+ conf.setInt("table.output.tfile.minBlock.size", 64 * 1024);
+ conf.setInt("table.input.split.minSize", 64 * 1024);
+ conf.set("table.output.tfile.compression", "none");
+
+ RawLocalFileSystem rawLFS = new RawLocalFileSystem();
+ fs = new LocalFileSystem(rawLFS);
+ path = new Path(fs.getWorkingDirectory(), "TestBasicTableMapSplits");
+ fs = path.getFileSystem(conf);
+ // drop any previous tables
+ BasicTable.drop(path, conf);
+
+ BasicTable.Writer writer = new BasicTable.Writer(path, STR_SCHEMA,
+ STR_STORAGE, conf);
+ writer.finish();
+
+ Schema schema = writer.getSchema();
+ Tuple tuple = TypesUtils.createTuple(schema);
+
+ BasicTable.Writer writer1 = new BasicTable.Writer(path, conf);
+ int part = 0;
+ TableInserter inserter = writer1.getInserter("part" + part, true);
+ TypesUtils.resetTuple(tuple);
+
+ tuple.set(0, "Kitty");
+
+
+ Map<String, String> map = new HashMap<String, String>();
+ map.put("a", "x");
+ map.put("b", "y");
+ map.put("c", "z");
+ tuple.set(1, map);
+
+ int row = 0;
+ inserter.insert(new BytesWritable(String.format("k%d%d", part + 1, row + 1)
+ .getBytes()), tuple);
+ inserter.close();
+ writer1.finish();
+
+ writer.close();
+ }
+
+ @AfterClass
+ public static void tearDownOnce() throws IOException {
+ }
+
+ public void testDescribse() throws IOException {
+
+ BasicTable.dumpInfo(path.toString(), System.out, conf);
+
+ }
+
+ @Test
+ public void test1() throws IOException, ParseException {
+ String projection = new String("f2#{a}");
+ BasicTable.Reader reader = new BasicTable.Reader(path, conf);
+ reader.setProjection(projection);
+ // long totalBytes = reader.getStatus().getSize();
+
+ List<RangeSplit> splits = reader.rangeSplit(1);
+ reader.close();
+ reader = new BasicTable.Reader(path, conf);
+ reader.setProjection(projection);
+ TableScanner scanner = reader.getScanner(splits.get(0), true);
+ BytesWritable key = new BytesWritable();
+ Tuple value = TypesUtils.createTuple(scanner.getSchema());
+
+ scanner.getKey(key);
+ Assert.assertEquals(key, new BytesWritable("k11".getBytes()));
+ scanner.getValue(value);
+
+ Assert.assertEquals("x", ((Map)value.get(0)).get("a"));
+ reader.close();
+ }
+
+}