[core] use paimon checkArgument instead of parquet's (apache#3515)

hzjhjjyy · Jun 13, 2024 · 8b4f3df · 8b4f3df
1 parent 705c959
commit 8b4f3df
Show file tree

Hide file tree

Showing 7 changed files with 15 additions and 15 deletions.
diff --git a/...on-format/src/main/java/org/apache/paimon/format/parquet/reader/AbstractColumnReader.java b/...on-format/src/main/java/org/apache/paimon/format/parquet/reader/AbstractColumnReader.java
@@ -21,7 +21,6 @@
 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.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 AbstractColumnReader(ColumnDescriptor descriptor, PageReader pageReader)
     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/...on-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetDecimalVector.java b/...on-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetDecimalVector.java
@@ -26,7 +26,7 @@
 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 Decimal getDecimal(int i, int precision, int scale) {
             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/...-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetSplitReaderUtil.java b/...-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetSplitReaderUtil.java
@@ -54,7 +54,7 @@
 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/...-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetTimestampVector.java b/...-format/src/main/java/org/apache/paimon/format/parquet/reader/ParquetTimestampVector.java
@@ -23,7 +23,7 @@
 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 Timestamp getTimestamp(int i, int precision) {
         } 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
@@ -21,7 +21,6 @@
 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 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 @@ void initFromStream(int valueCount, ByteBufferInputStream in) throws IOException
 
     /** 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/...n-format/src/main/java/org/apache/paimon/format/parquet/reader/TimestampColumnReader.java b/...n-format/src/main/java/org/apache/paimon/format/parquet/reader/TimestampColumnReader.java
@@ -22,7 +22,6 @@
 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.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 @@ protected void readBatchFromDictionaryIds(
     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
@@ -25,7 +25,6 @@
 
 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.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 @@ private void readVectored(List<ConsecutivePartList> allParts, ChunkListBuilder b
         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);