This is an automated email from the ASF dual-hosted git repository.
lzljs3620320 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/paimon.git
The following commit(s) were added to refs/heads/master by this push:
new 8b4f3df89 [core] use paimon checkArgument instead of parquet's (#3515)
8b4f3df89 is described below
commit 8b4f3df89d73398c09310434ede8e02009772fd3
Author: Yann Byron <[email protected]>
AuthorDate: Thu Jun 13 23:52:46 2024 +0800
[core] use paimon checkArgument instead of parquet's (#3515)
---
.../apache/paimon/format/parquet/reader/AbstractColumnReader.java | 4 ++--
.../apache/paimon/format/parquet/reader/ParquetDecimalVector.java | 4 ++--
.../apache/paimon/format/parquet/reader/ParquetSplitReaderUtil.java | 2 +-
.../apache/paimon/format/parquet/reader/ParquetTimestampVector.java | 4 ++--
.../org/apache/paimon/format/parquet/reader/RunLengthDecoder.java | 6 +++---
.../apache/paimon/format/parquet/reader/TimestampColumnReader.java | 6 +++---
.../src/main/java/org/apache/parquet/hadoop/ParquetFileReader.java | 4 ++--
7 files changed, 15 insertions(+), 15 deletions(-)
diff --git
a/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/AbstractColumnReader.java
b/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/AbstractColumnReader.java
index dac1ebd0f..7e2ab6d5e 100644
---
a/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/AbstractColumnReader.java
+++
b/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/AbstractColumnReader.java
@@ -21,7 +21,6 @@ package org.apache.paimon.format.parquet.reader;
import org.apache.paimon.data.columnar.writable.WritableColumnVector;
import org.apache.paimon.data.columnar.writable.WritableIntVector;
-import org.apache.parquet.Preconditions;
import org.apache.parquet.bytes.ByteBufferInputStream;
import org.apache.parquet.bytes.BytesInput;
import org.apache.parquet.bytes.BytesUtils;
@@ -44,6 +43,7 @@ import java.io.IOException;
import java.nio.ByteBuffer;
import java.nio.ByteOrder;
+import static org.apache.paimon.utils.Preconditions.checkArgument;
import static org.apache.parquet.column.ValuesType.REPETITION_LEVEL;
/**
@@ -132,7 +132,7 @@ public abstract class AbstractColumnReader<VECTOR extends
WritableColumnVector>
protected void checkTypeName(PrimitiveType.PrimitiveTypeName expectedName)
{
PrimitiveType.PrimitiveTypeName actualName =
descriptor.getPrimitiveType().getPrimitiveTypeName();
- Preconditions.checkArgument(
+ checkArgument(
actualName == expectedName,
"Expected type name: %s, actual type name: %s",
expectedName,
diff --git
a/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetDecimalVector.java
b/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetDecimalVector.java
index a60a9f4f9..d1ab8d660 100644
---
a/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetDecimalVector.java
+++
b/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetDecimalVector.java
@@ -26,7 +26,7 @@ import org.apache.paimon.data.columnar.IntColumnVector;
import org.apache.paimon.data.columnar.LongColumnVector;
import org.apache.paimon.format.parquet.ParquetSchemaConverter;
-import org.apache.parquet.Preconditions;
+import static org.apache.paimon.utils.Preconditions.checkArgument;
/**
* Parquet write decimal as int32 and int64 and binary, this class wrap the
real vector to provide
@@ -49,7 +49,7 @@ public class ParquetDecimalVector implements
DecimalColumnVector {
return Decimal.fromUnscaledLong(
((LongColumnVector) vector).getLong(i), precision, scale);
} else {
- Preconditions.checkArgument(
+ checkArgument(
vector instanceof BytesColumnVector,
"Reading decimal type occur unsupported vector type: %s",
vector.getClass());
diff --git
a/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetSplitReaderUtil.java
b/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetSplitReaderUtil.java
index f963eff58..59af1f391 100644
---
a/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetSplitReaderUtil.java
+++
b/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetSplitReaderUtil.java
@@ -54,7 +54,7 @@ import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
-import static org.apache.parquet.Preconditions.checkArgument;
+import static org.apache.paimon.utils.Preconditions.checkArgument;
/** Util for generating {@link ColumnReader}. */
public class ParquetSplitReaderUtil {
diff --git
a/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetTimestampVector.java
b/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetTimestampVector.java
index 1bc022ab6..f280d03bd 100644
---
a/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetTimestampVector.java
+++
b/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetTimestampVector.java
@@ -23,7 +23,7 @@ import org.apache.paimon.data.columnar.ColumnVector;
import org.apache.paimon.data.columnar.LongColumnVector;
import org.apache.paimon.data.columnar.TimestampColumnVector;
-import org.apache.parquet.Preconditions;
+import static org.apache.paimon.utils.Preconditions.checkArgument;
/**
* Parquet write timestamp precision 0-3 as int64 mills, 4-6 as int64 micros,
7-9 as int96, this
@@ -44,7 +44,7 @@ public class ParquetTimestampVector implements
TimestampColumnVector {
} else if (precision <= 6 && vector instanceof LongColumnVector) {
return Timestamp.fromMicros(((LongColumnVector)
vector).getLong(i));
} else {
- Preconditions.checkArgument(
+ checkArgument(
vector instanceof TimestampColumnVector,
"Reading timestamp type occur unsupported vector type: %s",
vector.getClass());
diff --git
a/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/RunLengthDecoder.java
b/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/RunLengthDecoder.java
index f47baf288..2dd1655d5 100644
---
a/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/RunLengthDecoder.java
+++
b/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/RunLengthDecoder.java
@@ -21,7 +21,6 @@ package org.apache.paimon.format.parquet.reader;
import org.apache.paimon.data.columnar.writable.WritableColumnVector;
import org.apache.paimon.data.columnar.writable.WritableIntVector;
-import org.apache.parquet.Preconditions;
import org.apache.parquet.bytes.ByteBufferInputStream;
import org.apache.parquet.bytes.BytesUtils;
import org.apache.parquet.column.values.bitpacking.BytePacker;
@@ -32,6 +31,8 @@ import org.apache.parquet.io.ParquetDecodingException;
import java.io.IOException;
import java.nio.ByteBuffer;
+import static org.apache.paimon.utils.Preconditions.checkArgument;
+
/**
* Run length decoder for data and dictionary ids. See <a
*
href="https://github.com/apache/parquet-format/blob/master/Encodings.md";>Parquet
Format
@@ -108,8 +109,7 @@ final class RunLengthDecoder {
/** Initializes the internal state for decoding ints of `bitWidth`. */
private void initWidthAndPacker(int bitWidth) {
- Preconditions.checkArgument(
- bitWidth >= 0 && bitWidth <= 32, "bitWidth must be >= 0 and <=
32");
+ checkArgument(bitWidth >= 0 && bitWidth <= 32, "bitWidth must be >= 0
and <= 32");
this.bitWidth = bitWidth;
this.bytesWidth = BytesUtils.paddedByteCountFromBits(bitWidth);
this.packer = Packer.LITTLE_ENDIAN.newBytePacker(bitWidth);
diff --git
a/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/TimestampColumnReader.java
b/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/TimestampColumnReader.java
index 4debbf1b4..4a279ff90 100644
---
a/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/TimestampColumnReader.java
+++
b/paimon-format/src/main/java/org/apache/paimon/format/parquet/reader/TimestampColumnReader.java
@@ -22,7 +22,6 @@ import org.apache.paimon.data.Timestamp;
import org.apache.paimon.data.columnar.writable.WritableIntVector;
import org.apache.paimon.data.columnar.writable.WritableTimestampVector;
-import org.apache.parquet.Preconditions;
import org.apache.parquet.column.ColumnDescriptor;
import org.apache.parquet.column.page.PageReader;
import org.apache.parquet.io.api.Binary;
@@ -33,6 +32,8 @@ import java.nio.ByteBuffer;
import java.nio.ByteOrder;
import java.util.concurrent.TimeUnit;
+import static org.apache.paimon.utils.Preconditions.checkArgument;
+
/**
* Timestamp {@link ColumnReader}. We only support INT96 bytes now,
julianDay(4) + nanosOfDay(8).
* See
https://github.com/apache/parquet-format/blob/master/DataTypes.md#timestamp
TIMESTAMP_MILLIS
@@ -89,8 +90,7 @@ public class TimestampColumnReader extends
AbstractColumnReader<WritableTimestam
public static Timestamp decodeInt96ToTimestamp(
boolean utcTimestamp, org.apache.parquet.column.Dictionary
dictionary, int id) {
Binary binary = dictionary.decodeToBinary(id);
- Preconditions.checkArgument(
- binary.length() == 12, "Timestamp with int96 should be 12
bytes.");
+ checkArgument(binary.length() == 12, "Timestamp with int96 should be
12 bytes.");
ByteBuffer buffer =
binary.toByteBuffer().order(ByteOrder.LITTLE_ENDIAN);
return int96ToTimestamp(utcTimestamp, buffer.getLong(),
buffer.getInt());
}
diff --git
a/paimon-format/src/main/java/org/apache/parquet/hadoop/ParquetFileReader.java
b/paimon-format/src/main/java/org/apache/parquet/hadoop/ParquetFileReader.java
index 76f54f5b9..118ba0087 100644
---
a/paimon-format/src/main/java/org/apache/parquet/hadoop/ParquetFileReader.java
+++
b/paimon-format/src/main/java/org/apache/parquet/hadoop/ParquetFileReader.java
@@ -25,7 +25,6 @@ import org.apache.paimon.fs.VectoredReadable;
import org.apache.hadoop.fs.Path;
import org.apache.parquet.ParquetReadOptions;
-import org.apache.parquet.Preconditions;
import org.apache.parquet.bytes.ByteBufferInputStream;
import org.apache.parquet.bytes.BytesInput;
import org.apache.parquet.column.ColumnDescriptor;
@@ -95,6 +94,7 @@ import java.util.Set;
import java.util.concurrent.ExecutionException;
import java.util.zip.CRC32;
+import static org.apache.paimon.utils.Preconditions.checkArgument;
import static org.apache.parquet.bytes.BytesUtils.readIntLittleEndian;
import static
org.apache.parquet.filter2.compat.RowGroupFilter.FilterLevel.BLOOMFILTER;
import static
org.apache.parquet.filter2.compat.RowGroupFilter.FilterLevel.DICTIONARY;
@@ -565,7 +565,7 @@ public class ParquetFileReader implements Closeable {
long totalSize = 0;
for (ConsecutivePartList consecutiveChunks : allParts) {
final long len = consecutiveChunks.length;
- Preconditions.checkArgument(
+ checkArgument(
len < Integer.MAX_VALUE,
"Invalid length %s for vectored read operation. It must be
less than max integer value.",
len);
