This is an automated email from the ASF dual-hosted git repository.
dmollitor pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/avro.git
The following commit(s) were added to refs/heads/main by this push:
new 005ee8069 AVRO-4045: Use JDK compare for byte arrays (#3126)
005ee8069 is described below
commit 005ee8069dd69169e5c1842f0849d90373910b18
Author: belugabehr <[email protected]>
AuthorDate: Tue Sep 24 16:14:30 2024 -0400
AVRO-4045: Use JDK compare for byte arrays (#3126)
---
.../java/org/apache/avro/generic/GenericData.java | 2 +-
.../main/java/org/apache/avro/io/BinaryData.java | 28 +++++++++-------------
.../java/org/apache/avro/reflect/ReflectData.java | 3 +--
.../org/apache/avro/specific/SpecificFixed.java | 3 +--
.../src/main/java/org/apache/avro/util/Utf8.java | 3 +--
5 files changed, 15 insertions(+), 24 deletions(-)
diff --git
a/lang/java/avro/src/main/java/org/apache/avro/generic/GenericData.java
b/lang/java/avro/src/main/java/org/apache/avro/generic/GenericData.java
index 6db0a40ee..362ebdc9c 100644
--- a/lang/java/avro/src/main/java/org/apache/avro/generic/GenericData.java
+++ b/lang/java/avro/src/main/java/org/apache/avro/generic/GenericData.java
@@ -545,7 +545,7 @@ public class GenericData {
@Override
public int compareTo(Fixed that) {
- return BinaryData.compareBytes(this.bytes, 0, this.bytes.length,
that.bytes, 0, that.bytes.length);
+ return Arrays.compare(this.bytes, 0, this.bytes.length, that.bytes, 0,
that.bytes.length);
}
}
diff --git a/lang/java/avro/src/main/java/org/apache/avro/io/BinaryData.java
b/lang/java/avro/src/main/java/org/apache/avro/io/BinaryData.java
index f925bcd96..e6fc7086e 100644
--- a/lang/java/avro/src/main/java/org/apache/avro/io/BinaryData.java
+++ b/lang/java/avro/src/main/java/org/apache/avro/io/BinaryData.java
@@ -18,6 +18,7 @@
package org.apache.avro.io;
import java.io.IOException;
+import java.util.Arrays;
import org.apache.avro.Schema;
import org.apache.avro.Schema.Field;
@@ -155,7 +156,8 @@ public class BinaryData {
}
case FIXED: {
int size = schema.getFixedSize();
- int c = compareBytes(d.d1.getBuf(), d.d1.getPos(), size, d.d2.getBuf(),
d.d2.getPos(), size);
+ int c = Arrays.compare(d.d1.getBuf(), d.d1.getPos(), d.d1.getPos() +
size, d.d2.getBuf(), d.d2.getPos(),
+ d.d2.getPos() + size);
d.d1.skipFixed(size);
d.d2.skipFixed(size);
return c;
@@ -164,7 +166,8 @@ public class BinaryData {
case BYTES: {
int l1 = d1.readInt();
int l2 = d2.readInt();
- int c = compareBytes(d.d1.getBuf(), d.d1.getPos(), l1, d.d2.getBuf(),
d.d2.getPos(), l2);
+ int c = Arrays.compare(d.d1.getBuf(), d.d1.getPos(), d.d1.getPos() + l1,
d.d2.getBuf(), d.d2.getPos(),
+ d.d2.getPos() + l2);
d.d1.skipFixed(l1);
d.d2.skipFixed(l2);
return c;
@@ -181,16 +184,7 @@ public class BinaryData {
* return a positive value, if less than return a negative value.
*/
public static int compareBytes(byte[] b1, int s1, int l1, byte[] b2, int s2,
int l2) {
- int end1 = s1 + l1;
- int end2 = s2 + l2;
- for (int i = s1, j = s2; i < end1 && j < end2; i++, j++) {
- int a = (b1[i] & 0xff);
- int b = (b2[j] & 0xff);
- if (a != b) {
- return a - b;
- }
- }
- return l1 - l2;
+ return Arrays.compare(b1, s1, s1 + l1, b2, s2, s2 + l2);
}
private static class HashData {
@@ -298,7 +292,7 @@ public class BinaryData {
/**
* Encode a boolean to the byte array at the given position. Will throw
* IndexOutOfBounds if the position is not valid.
- *
+ *
* @return The number of bytes written to the buffer, 1.
*/
public static int encodeBoolean(boolean b, byte[] buf, int pos) {
@@ -310,7 +304,7 @@ public class BinaryData {
* Encode an integer to the byte array at the given position. Will throw
* IndexOutOfBounds if it overflows. Users should ensure that there are at
least
* 5 bytes left in the buffer before calling this method.
- *
+ *
* @return The number of bytes written to the buffer, between 1 and 5.
*/
public static int encodeInt(int n, byte[] buf, int pos) {
@@ -341,7 +335,7 @@ public class BinaryData {
* Encode a long to the byte array at the given position. Will throw
* IndexOutOfBounds if it overflows. Users should ensure that there are at
least
* 10 bytes left in the buffer before calling this method.
- *
+ *
* @return The number of bytes written to the buffer, between 1 and 10.
*/
public static int encodeLong(long n, byte[] buf, int pos) {
@@ -392,7 +386,7 @@ public class BinaryData {
* Encode a float to the byte array at the given position. Will throw
* IndexOutOfBounds if it overflows. Users should ensure that there are at
least
* 4 bytes left in the buffer before calling this method.
- *
+ *
* @return Returns the number of bytes written to the buffer, 4.
*/
public static int encodeFloat(float f, byte[] buf, int pos) {
@@ -408,7 +402,7 @@ public class BinaryData {
* Encode a double to the byte array at the given position. Will throw
* IndexOutOfBounds if it overflows. Users should ensure that there are at
least
* 8 bytes left in the buffer before calling this method.
- *
+ *
* @return Returns the number of bytes written to the buffer, 8.
*/
public static int encodeDouble(double d, byte[] buf, int pos) {
diff --git
a/lang/java/avro/src/main/java/org/apache/avro/reflect/ReflectData.java
b/lang/java/avro/src/main/java/org/apache/avro/reflect/ReflectData.java
index 95fc9598c..ab702a60e 100644
--- a/lang/java/avro/src/main/java/org/apache/avro/reflect/ReflectData.java
+++ b/lang/java/avro/src/main/java/org/apache/avro/reflect/ReflectData.java
@@ -30,7 +30,6 @@ import org.apache.avro.generic.GenericContainer;
import org.apache.avro.generic.GenericData;
import org.apache.avro.generic.GenericFixed;
import org.apache.avro.generic.IndexedRecord;
-import org.apache.avro.io.BinaryData;
import org.apache.avro.io.DatumReader;
import org.apache.avro.io.DatumWriter;
import org.apache.avro.specific.FixedSize;
@@ -986,7 +985,7 @@ public class ReflectData extends SpecificData {
break;
byte[] b1 = (byte[]) o1;
byte[] b2 = (byte[]) o2;
- return BinaryData.compareBytes(b1, 0, b1.length, b2, 0, b2.length);
+ return Arrays.compare(b1, 0, b1.length, b2, 0, b2.length);
}
return super.compare(o1, o2, s, equals);
}
diff --git
a/lang/java/avro/src/main/java/org/apache/avro/specific/SpecificFixed.java
b/lang/java/avro/src/main/java/org/apache/avro/specific/SpecificFixed.java
index 9984acb56..98a553eec 100644
--- a/lang/java/avro/src/main/java/org/apache/avro/specific/SpecificFixed.java
+++ b/lang/java/avro/src/main/java/org/apache/avro/specific/SpecificFixed.java
@@ -24,7 +24,6 @@ import java.io.IOException;
import java.util.Arrays;
import org.apache.avro.Schema;
import org.apache.avro.generic.GenericFixed;
-import org.apache.avro.io.BinaryData;
/** Base class for generated fixed-sized data classes. */
public abstract class SpecificFixed implements GenericFixed,
Comparable<SpecificFixed>, Externalizable {
@@ -70,7 +69,7 @@ public abstract class SpecificFixed implements GenericFixed,
Comparable<Specific
@Override
public int compareTo(SpecificFixed that) {
- return BinaryData.compareBytes(this.bytes, 0, this.bytes.length,
that.bytes, 0, that.bytes.length);
+ return Arrays.compare(this.bytes, 0, this.bytes.length, that.bytes, 0,
that.bytes.length);
}
@Override
diff --git a/lang/java/avro/src/main/java/org/apache/avro/util/Utf8.java
b/lang/java/avro/src/main/java/org/apache/avro/util/Utf8.java
index 6de9ebb22..b38d237f2 100644
--- a/lang/java/avro/src/main/java/org/apache/avro/util/Utf8.java
+++ b/lang/java/avro/src/main/java/org/apache/avro/util/Utf8.java
@@ -25,7 +25,6 @@ import java.nio.charset.StandardCharsets;
import java.util.Arrays;
import org.apache.avro.SystemLimitException;
-import org.apache.avro.io.BinaryData;
/**
* A Utf8 string. Unlike {@link String}, instances are mutable. This is more
@@ -185,7 +184,7 @@ public class Utf8 implements Comparable<Utf8>,
CharSequence, Externalizable {
@Override
public int compareTo(Utf8 that) {
- return BinaryData.compareBytes(this.bytes, 0, this.length, that.bytes, 0,
that.length);
+ return Arrays.compare(this.bytes, 0, this.length, that.bytes, 0,
that.length);
}
// CharSequence implementation
