You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@parquet.apache.org by GitBox <gi...@apache.org> on 2021/02/22 18:57:39 UTC
[GitHub] [parquet-mr] shangxinli commented on a change in pull request #868: PARQUET-1977: Invalid data_page_offset
shangxinli commented on a change in pull request #868:
URL: https://github.com/apache/parquet-mr/pull/868#discussion_r580424903
##########
File path: parquet-hadoop/src/main/java/org/apache/parquet/hadoop/Offsets.java
##########
@@ -0,0 +1,84 @@
+/*
+ * 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.parquet.hadoop;
+
+import java.io.IOException;
+
+import org.apache.parquet.format.PageHeader;
+import org.apache.parquet.format.Util;
+import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData;
+import org.apache.parquet.io.SeekableInputStream;
+
+/**
+ * Class to help gather/calculate the proper values of the dictionary/first data page offset values in a column chunk.
+ */
+class Offsets {
+
+ /**
+ * Returns the offset values for the column chunk to be written.
+ *
+ * @param input the source input stream of the column chunk
+ * @param chunk the column chunk metadata read from the source file
+ * @param newChunkStart the position of the column chunk to be written
+ * @return the offset values
+ * @throws IOException if any I/O error occurs during the reading of the input stream
+ */
+ public static Offsets getOffsets(SeekableInputStream input, ColumnChunkMetaData chunk, long newChunkStart)
+ throws IOException {
+ long firstDataPageOffset;
+ long dictionaryPageOffset;
+ if (chunk.hasDictionaryPage()) {
+ long dictionaryPageSize = chunk.getFirstDataPageOffset() - chunk.getDictionaryPageOffset();
+ if (dictionaryPageSize <= 0) {
+ // The offset values might be invalid so we have to read the size of the dictionary page
Review comment:
if the offset is invalid, should we through exception here?
##########
File path: parquet-hadoop/src/main/java/org/apache/parquet/hadoop/Offsets.java
##########
@@ -0,0 +1,84 @@
+/*
+ * 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.parquet.hadoop;
+
+import java.io.IOException;
+
+import org.apache.parquet.format.PageHeader;
+import org.apache.parquet.format.Util;
+import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData;
+import org.apache.parquet.io.SeekableInputStream;
+
+/**
+ * Class to help gather/calculate the proper values of the dictionary/first data page offset values in a column chunk.
+ */
+class Offsets {
+
+ /**
+ * Returns the offset values for the column chunk to be written.
+ *
+ * @param input the source input stream of the column chunk
+ * @param chunk the column chunk metadata read from the source file
+ * @param newChunkStart the position of the column chunk to be written
+ * @return the offset values
+ * @throws IOException if any I/O error occurs during the reading of the input stream
+ */
+ public static Offsets getOffsets(SeekableInputStream input, ColumnChunkMetaData chunk, long newChunkStart)
+ throws IOException {
+ long firstDataPageOffset;
+ long dictionaryPageOffset;
+ if (chunk.hasDictionaryPage()) {
+ long dictionaryPageSize = chunk.getFirstDataPageOffset() - chunk.getDictionaryPageOffset();
+ if (dictionaryPageSize <= 0) {
+ // The offset values might be invalid so we have to read the size of the dictionary page
+ dictionaryPageSize = readDictionaryPageSize(input, newChunkStart);
+ }
+ firstDataPageOffset = newChunkStart + dictionaryPageSize;
+ dictionaryPageOffset = newChunkStart;
+ } else {
+ firstDataPageOffset = newChunkStart;
+ dictionaryPageOffset = 0;
+ }
+ return new Offsets(firstDataPageOffset, dictionaryPageOffset);
+ }
+
+ private static long readDictionaryPageSize(SeekableInputStream in, long pos) throws IOException {
+ long origPos = -1;
+ try {
+ origPos = in.getPos();
+ // TODO: Do we need to handle encryption here?
+ PageHeader header = Util.readPageHeader(in);
+ long headerSize = in.getPos() - origPos;
+ return headerSize + header.getCompressed_page_size();
+ } finally {
+ if (origPos != -1) {
+ in.seek(origPos);
Review comment:
Why we need seek here?
##########
File path: parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetFileWriter.java
##########
@@ -493,6 +492,9 @@ public void writeDictionaryPage(DictionaryPage dictionaryPage,
dictionaryPage.getBytes().writeAllTo(out); // for encrypted column, dictionary page bytes are already encrypted
encodingStatsBuilder.addDictEncoding(dictionaryPage.getEncoding());
currentEncodings.add(dictionaryPage.getEncoding());
+
+ // First data page comes just after the dictionary page
+ currentChunkFirstDataPage = out.getPos();
Review comment:
The assumption is data page is immediately written after the dictionary page always. This could be true today but later on, if that assumption is changed, it would be hard to find this line of code that need to be changed.
##########
File path: parquet-hadoop/src/main/java/org/apache/parquet/hadoop/Offsets.java
##########
@@ -0,0 +1,84 @@
+/*
+ * 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.parquet.hadoop;
+
+import java.io.IOException;
+
+import org.apache.parquet.format.PageHeader;
+import org.apache.parquet.format.Util;
+import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData;
+import org.apache.parquet.io.SeekableInputStream;
+
+/**
+ * Class to help gather/calculate the proper values of the dictionary/first data page offset values in a column chunk.
+ */
+class Offsets {
+
+ /**
+ * Returns the offset values for the column chunk to be written.
+ *
+ * @param input the source input stream of the column chunk
+ * @param chunk the column chunk metadata read from the source file
+ * @param newChunkStart the position of the column chunk to be written
+ * @return the offset values
+ * @throws IOException if any I/O error occurs during the reading of the input stream
+ */
+ public static Offsets getOffsets(SeekableInputStream input, ColumnChunkMetaData chunk, long newChunkStart)
+ throws IOException {
+ long firstDataPageOffset;
+ long dictionaryPageOffset;
+ if (chunk.hasDictionaryPage()) {
+ long dictionaryPageSize = chunk.getFirstDataPageOffset() - chunk.getDictionaryPageOffset();
+ if (dictionaryPageSize <= 0) {
+ // The offset values might be invalid so we have to read the size of the dictionary page
+ dictionaryPageSize = readDictionaryPageSize(input, newChunkStart);
+ }
+ firstDataPageOffset = newChunkStart + dictionaryPageSize;
+ dictionaryPageOffset = newChunkStart;
+ } else {
+ firstDataPageOffset = newChunkStart;
+ dictionaryPageOffset = 0;
+ }
+ return new Offsets(firstDataPageOffset, dictionaryPageOffset);
+ }
+
+ private static long readDictionaryPageSize(SeekableInputStream in, long pos) throws IOException {
+ long origPos = -1;
+ try {
+ origPos = in.getPos();
+ // TODO: Do we need to handle encryption here?
Review comment:
If it is encrypted, I guess we need decrypt it https://github.com/apache/parquet-mr/blob/master/parquet-format-structures/src/main/java/org/apache/parquet/format/Util.java#L130
##########
File path: parquet-hadoop/src/main/java/org/apache/parquet/hadoop/metadata/ColumnChunkMetaData.java
##########
@@ -566,7 +567,7 @@ public Statistics getStatistics() {
private final ParquetMetadataConverter parquetMetadataConverter;
private final byte[] encryptedMetadata;
private final byte[] columnKeyMetadata;
- private final InternalFileDecryptor fileDecryptor;
Review comment:
This could be changed by IDE, but it is unnecessary.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org