You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@orc.apache.org by om...@apache.org on 2017/02/15 23:12:47 UTC
orc git commit: ORC-147. Fix backwards compatibility with Hive 2.1.
(omalley)
Repository: orc
Updated Branches:
refs/heads/master 54540c058 -> 60c879c36
ORC-147. Fix backwards compatibility with Hive 2.1. (omalley)
Fixes #92
Signed-off-by: Owen O'Malley <om...@apache.org>
Project: http://git-wip-us.apache.org/repos/asf/orc/repo
Commit: http://git-wip-us.apache.org/repos/asf/orc/commit/60c879c3
Tree: http://git-wip-us.apache.org/repos/asf/orc/tree/60c879c3
Diff: http://git-wip-us.apache.org/repos/asf/orc/diff/60c879c3
Branch: refs/heads/master
Commit: 60c879c369092bafbb00be70b4bf7c5c7f56b5a3
Parents: 54540c0
Author: Owen O'Malley <om...@apache.org>
Authored: Tue Feb 14 13:08:50 2017 -0800
Committer: Owen O'Malley <om...@apache.org>
Committed: Wed Feb 15 15:12:04 2017 -0800
----------------------------------------------------------------------
java/core/pom.xml | 3 ++
.../java/org/apache/orc/impl/MemoryManager.java | 32 +++++++++++++++
.../org/apache/orc/impl/RecordReaderImpl.java | 43 +++++++++++++++++++-
.../org/apache/orc/impl/SchemaEvolution.java | 20 ++++++---
.../apache/orc/impl/TestSchemaEvolution.java | 22 +++++-----
5 files changed, 103 insertions(+), 17 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/orc/blob/60c879c3/java/core/pom.xml
----------------------------------------------------------------------
diff --git a/java/core/pom.xml b/java/core/pom.xml
index abcdd4c..dbe50ac 100644
--- a/java/core/pom.xml
+++ b/java/core/pom.xml
@@ -102,6 +102,9 @@
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-javadoc-plugin</artifactId>
<configuration>
+ <sourceFileExcludes>
+ <exclude>**/OrcProto.java</exclude>
+ </sourceFileExcludes>
<destDir>${project.artifactId}</destDir>
</configuration>
</plugin>
http://git-wip-us.apache.org/repos/asf/orc/blob/60c879c3/java/core/src/java/org/apache/orc/impl/MemoryManager.java
----------------------------------------------------------------------
diff --git a/java/core/src/java/org/apache/orc/impl/MemoryManager.java b/java/core/src/java/org/apache/orc/impl/MemoryManager.java
new file mode 100644
index 0000000..30535bf
--- /dev/null
+++ b/java/core/src/java/org/apache/orc/impl/MemoryManager.java
@@ -0,0 +1,32 @@
+/**
+ * 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.orc.impl;
+
+import org.apache.hadoop.conf.Configuration;
+
+/**
+ * Shim for backwards compatibility with Hive
+ */
+@Deprecated
+public class MemoryManager extends MemoryManagerImpl {
+
+ public MemoryManager(Configuration conf) {
+ super(conf);
+ }
+}
http://git-wip-us.apache.org/repos/asf/orc/blob/60c879c3/java/core/src/java/org/apache/orc/impl/RecordReaderImpl.java
----------------------------------------------------------------------
diff --git a/java/core/src/java/org/apache/orc/impl/RecordReaderImpl.java b/java/core/src/java/org/apache/orc/impl/RecordReaderImpl.java
index 766eb00..f75d70a 100644
--- a/java/core/src/java/org/apache/orc/impl/RecordReaderImpl.java
+++ b/java/core/src/java/org/apache/orc/impl/RecordReaderImpl.java
@@ -138,6 +138,47 @@ public class RecordReaderImpl implements RecordReader {
return result;
}
+ /**
+ * Given a list of column names, find the given column and return the index.
+ *
+ * @param columnNames the list of potential column names
+ * @param columnName the column name to look for
+ * @param rootColumn offset the result with the rootColumn
+ * @return the column number or -1 if the column wasn't found
+ */
+ private static int findColumns(String[] columnNames,
+ String columnName,
+ int rootColumn) {
+ for(int i=0; i < columnNames.length; ++i) {
+ if (columnName.equals(columnNames[i])) {
+ return i + rootColumn;
+ }
+ }
+ return -1;
+ }
+
+ /**
+ * Find the mapping from predicate leaves to columns.
+ * @param sargLeaves the search argument that we need to map
+ * @param columnNames the names of the columns
+ * @param rootColumn the offset of the top level row, which offsets the
+ * result
+ * @return an array mapping the sarg leaves to concrete column numbers
+ * @deprecated Use #mapSargColumnsToOrcInternalColIdx(List, SchemaEvolution)
+ */
+ @Deprecated
+ public static int[] mapSargColumnsToOrcInternalColIdx(List<PredicateLeaf> sargLeaves,
+ String[] columnNames,
+ int rootColumn) {
+ int[] result = new int[sargLeaves.size()];
+ Arrays.fill(result, -1);
+ for(int i=0; i < result.length; ++i) {
+ String colName = sargLeaves.get(i).getColumnName();
+ result[i] = findColumns(columnNames, colName, rootColumn);
+ }
+ return result;
+ }
+
protected RecordReaderImpl(ReaderImpl fileReader,
Reader.Options options) throws IOException {
this.writerVersion = fileReader.getWriterVersion();
@@ -146,7 +187,7 @@ public class RecordReaderImpl implements RecordReader {
LOG.info("Reader schema not provided -- using file schema " +
fileReader.getSchema());
}
- evolution = new SchemaEvolution(fileReader.getSchema(), options);
+ evolution = new SchemaEvolution(fileReader.getSchema(), null, options);
} else {
// Now that we are creating a record reader for a file, validate that
http://git-wip-us.apache.org/repos/asf/orc/blob/60c879c3/java/core/src/java/org/apache/orc/impl/SchemaEvolution.java
----------------------------------------------------------------------
diff --git a/java/core/src/java/org/apache/orc/impl/SchemaEvolution.java b/java/core/src/java/org/apache/orc/impl/SchemaEvolution.java
index a438db3..886d585 100644
--- a/java/core/src/java/org/apache/orc/impl/SchemaEvolution.java
+++ b/java/core/src/java/org/apache/orc/impl/SchemaEvolution.java
@@ -25,6 +25,7 @@ import java.util.List;
import java.util.Map;
import java.util.regex.Pattern;
+import org.apache.hadoop.conf.Configuration;
import org.apache.orc.Reader;
import org.apache.orc.TypeDescription;
import org.slf4j.Logger;
@@ -63,11 +64,6 @@ public class SchemaEvolution {
}
public SchemaEvolution(TypeDescription fileSchema,
- Reader.Options options) {
- this(fileSchema, null, options);
- }
-
- public SchemaEvolution(TypeDescription fileSchema,
TypeDescription readerSchema,
Reader.Options options) {
boolean allowMissingMetadata = options.getTolerateMissingSchema();
@@ -131,6 +127,20 @@ public class SchemaEvolution {
this.ppdSafeConversion = populatePpdSafeConversion();
}
+ @Deprecated
+ public SchemaEvolution(TypeDescription fileSchema, boolean[] readerIncluded) {
+ this(fileSchema, null, readerIncluded);
+ }
+
+ @Deprecated
+ public SchemaEvolution(TypeDescription fileSchema,
+ TypeDescription readerSchema,
+ boolean[] readerIncluded) {
+ this(fileSchema, readerSchema,
+ new Reader.Options(new Configuration())
+ .include(readerIncluded));
+ }
+
// Return true iff all fields have names like _col[0-9]+
private boolean hasColumnNames(TypeDescription fileSchema) {
if (fileSchema.getCategory() != TypeDescription.Category.STRUCT) {
http://git-wip-us.apache.org/repos/asf/orc/blob/60c879c3/java/core/src/test/org/apache/orc/impl/TestSchemaEvolution.java
----------------------------------------------------------------------
diff --git a/java/core/src/test/org/apache/orc/impl/TestSchemaEvolution.java b/java/core/src/test/org/apache/orc/impl/TestSchemaEvolution.java
index ac0115d..82f823a 100644
--- a/java/core/src/test/org/apache/orc/impl/TestSchemaEvolution.java
+++ b/java/core/src/test/org/apache/orc/impl/TestSchemaEvolution.java
@@ -78,7 +78,7 @@ public class TestSchemaEvolution {
.addField("f1", TypeDescription.createInt())
.addField("f2", TypeDescription.createString())
.addField("f3", TypeDescription.createDecimal().withPrecision(38).withScale(10));
- SchemaEvolution same1 = new SchemaEvolution(fileStruct1, options);
+ SchemaEvolution same1 = new SchemaEvolution(fileStruct1, null, options);
assertFalse(same1.hasConversion());
TypeDescription readerStruct1 = TypeDescription.createStruct()
.addField("f1", TypeDescription.createInt())
@@ -113,7 +113,7 @@ public class TestSchemaEvolution {
.addField("f4", TypeDescription.createDouble())
.addField("f5", TypeDescription.createBoolean()))
.addField("f6", TypeDescription.createChar().withMaxLength(100));
- SchemaEvolution same2 = new SchemaEvolution(fileStruct2, options);
+ SchemaEvolution same2 = new SchemaEvolution(fileStruct2, null, options);
assertFalse(same2.hasConversion());
TypeDescription readerStruct2 = TypeDescription.createStruct()
.addField("f1", TypeDescription.createUnion()
@@ -186,7 +186,7 @@ public class TestSchemaEvolution {
.addField("f1", TypeDescription.createInt())
.addField("f2", TypeDescription.createString())
.addField("f3", TypeDescription.createDecimal().withPrecision(38).withScale(10));
- SchemaEvolution same1 = new SchemaEvolution(fileStruct1, options);
+ SchemaEvolution same1 = new SchemaEvolution(fileStruct1, null, options);
assertTrue(same1.isPPDSafeConversion(0));
assertFalse(same1.hasConversion());
TypeDescription readerStruct1 = TypeDescription.createStruct()
@@ -247,7 +247,7 @@ public class TestSchemaEvolution {
// byte -> short -> int -> long
TypeDescription fileSchema = TypeDescription.createStruct()
.addField("f1", TypeDescription.createByte());
- SchemaEvolution schemaEvolution = new SchemaEvolution(fileSchema, options);
+ SchemaEvolution schemaEvolution = new SchemaEvolution(fileSchema, null, options);
assertFalse(schemaEvolution.hasConversion());
// byte -> short
@@ -277,7 +277,7 @@ public class TestSchemaEvolution {
// short -> int -> long
fileSchema = TypeDescription.createStruct()
.addField("f1", TypeDescription.createShort());
- schemaEvolution = new SchemaEvolution(fileSchema, options);
+ schemaEvolution = new SchemaEvolution(fileSchema, null, options);
assertFalse(schemaEvolution.hasConversion());
// unsafe conversion short -> byte
@@ -307,7 +307,7 @@ public class TestSchemaEvolution {
// int -> long
fileSchema = TypeDescription.createStruct()
.addField("f1", TypeDescription.createInt());
- schemaEvolution = new SchemaEvolution(fileSchema, options);
+ schemaEvolution = new SchemaEvolution(fileSchema, null, options);
assertFalse(schemaEvolution.hasConversion());
// unsafe conversion int -> byte
@@ -337,7 +337,7 @@ public class TestSchemaEvolution {
// long
fileSchema = TypeDescription.createStruct()
.addField("f1", TypeDescription.createLong());
- schemaEvolution = new SchemaEvolution(fileSchema, options);
+ schemaEvolution = new SchemaEvolution(fileSchema, null, options);
assertTrue(schemaEvolution.isPPDSafeConversion(0));
assertFalse(schemaEvolution.hasConversion());
@@ -394,7 +394,7 @@ public class TestSchemaEvolution {
public void testSafePpdEvaluationForStrings() throws IOException {
TypeDescription fileSchema = TypeDescription.createStruct()
.addField("f1", TypeDescription.createString());
- SchemaEvolution schemaEvolution = new SchemaEvolution(fileSchema, options);
+ SchemaEvolution schemaEvolution = new SchemaEvolution(fileSchema, null, options);
assertTrue(schemaEvolution.isPPDSafeConversion(0));
assertFalse(schemaEvolution.hasConversion());
@@ -416,7 +416,7 @@ public class TestSchemaEvolution {
fileSchema = TypeDescription.createStruct()
.addField("f1", TypeDescription.createChar());
- schemaEvolution = new SchemaEvolution(fileSchema, options);
+ schemaEvolution = new SchemaEvolution(fileSchema, null, options);
assertTrue(schemaEvolution.isPPDSafeConversion(0));
assertFalse(schemaEvolution.hasConversion());
@@ -438,7 +438,7 @@ public class TestSchemaEvolution {
fileSchema = TypeDescription.createStruct()
.addField("f1", TypeDescription.createVarchar());
- schemaEvolution = new SchemaEvolution(fileSchema, options);
+ schemaEvolution = new SchemaEvolution(fileSchema, null, options);
assertTrue(schemaEvolution.isPPDSafeConversion(0));
assertFalse(schemaEvolution.hasConversion());
@@ -994,7 +994,7 @@ public class TestSchemaEvolution {
public void testFileIncludeWithNoEvolution() {
TypeDescription fileType = TypeDescription.fromString(
"struct<a:int,b:double,c:string>");
- SchemaEvolution evo = new SchemaEvolution(fileType,
+ SchemaEvolution evo = new SchemaEvolution(fileType, null,
options.include(new boolean[]{true, false, true, false}));
assertFalse(evo.isAcid());
assertEquals("struct<a:int,b:double,c:string>",