This is an automated email from the ASF dual-hosted git repository.
uros-b pushed a commit to branch branch-4.x
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-4.x by this push:
new 418db10b6c55 [SPARK-57611][SQL] Reuse JsonFactory instances in the
variant module
418db10b6c55 is described below
commit 418db10b6c558a79dcf2f5479d30165b28923590
Author: YangJie <[email protected]>
AuthorDate: Thu Jun 25 00:17:43 2026 +0200
[SPARK-57611][SQL] Reuse JsonFactory instances in the variant module
### What changes were proposed in this pull request?
This PR reuses a single shared `JsonFactory` in the variant module instead
of allocating a new one on every call. `Variant.escapeJson` and
`VariantBuilder.parseJson` each created a `new JsonFactory()` per invocation;
both now reference a `private static final` instance.
### Why are the changes needed?
`JsonFactory` is thread-safe and designed to be reused. `escapeJson` runs
once per string value and object key while serializing a variant, and
`parseJson` runs once per input JSON value (e.g. per row in `parse_json`), so
creating a fresh factory on each call adds avoidable allocation (including its
symbol tables) on these hot paths. Sharing one instance removes that overhead.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Existing variant tests cover both the parsing and serialization paths.
There is no behavior change: both factories use the default configuration and
are never mutated, so a shared instance produces identical results.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #56691 from LuciferYang/SPARK-variant-escapejson-factory.
Authored-by: YangJie <[email protected]>
Signed-off-by: Uros Bojanic <[email protected]>
(cherry picked from commit ff354ecbf80347b2cda487b417981b6c35d7b0f6)
Signed-off-by: Uros Bojanic <[email protected]>
---
.../src/main/java/org/apache/spark/types/variant/Variant.java | 3 +--
.../main/java/org/apache/spark/types/variant/VariantBuilder.java | 3 +--
.../src/main/java/org/apache/spark/types/variant/VariantUtil.java | 8 ++++++++
3 files changed, 10 insertions(+), 4 deletions(-)
diff --git
a/common/variant/src/main/java/org/apache/spark/types/variant/Variant.java
b/common/variant/src/main/java/org/apache/spark/types/variant/Variant.java
index acb585cb8803..8996caeb364c 100644
--- a/common/variant/src/main/java/org/apache/spark/types/variant/Variant.java
+++ b/common/variant/src/main/java/org/apache/spark/types/variant/Variant.java
@@ -17,7 +17,6 @@
package org.apache.spark.types.variant;
-import com.fasterxml.jackson.core.JsonFactory;
import com.fasterxml.jackson.core.JsonGenerator;
import java.io.CharArrayWriter;
@@ -246,7 +245,7 @@ public final class Variant {
// (4 characters).
static String escapeJson(String str) {
try (CharArrayWriter writer = new CharArrayWriter();
- JsonGenerator gen = new JsonFactory().createGenerator(writer)) {
+ JsonGenerator gen = JSON_FACTORY.createGenerator(writer)) {
gen.writeString(str);
gen.flush();
return writer.toString();
diff --git
a/common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java
b/common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java
index dc0a114706c7..79f869ba6be7 100644
---
a/common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java
+++
b/common/variant/src/main/java/org/apache/spark/types/variant/VariantBuilder.java
@@ -30,7 +30,6 @@ import java.nio.ByteBuffer;
import java.nio.ByteOrder;
import java.util.*;
-import com.fasterxml.jackson.core.JsonFactory;
import com.fasterxml.jackson.core.JsonParser;
import com.fasterxml.jackson.core.JsonParseException;
import com.fasterxml.jackson.core.JsonToken;
@@ -70,7 +69,7 @@ public class VariantBuilder {
*/
public static Variant parseJson(String json, boolean allowDuplicateKeys,
boolean validateUnicodeInJsonParsing) throws IOException {
- try (JsonParser parser = new JsonFactory().createParser(json)) {
+ try (JsonParser parser = JSON_FACTORY.createParser(json)) {
parser.nextToken();
return parseJson(parser, allowDuplicateKeys,
validateUnicodeInJsonParsing);
}
diff --git
a/common/variant/src/main/java/org/apache/spark/types/variant/VariantUtil.java
b/common/variant/src/main/java/org/apache/spark/types/variant/VariantUtil.java
index ac93246991c0..1a3912775a2f 100644
---
a/common/variant/src/main/java/org/apache/spark/types/variant/VariantUtil.java
+++
b/common/variant/src/main/java/org/apache/spark/types/variant/VariantUtil.java
@@ -29,6 +29,8 @@ import java.nio.ByteOrder;
import java.util.Arrays;
import java.util.UUID;
+import com.fasterxml.jackson.core.JsonFactory;
+
/**
* This class defines constants related to the variant format and provides
functions for
* manipulating variant binaries.
@@ -50,6 +52,12 @@ import java.util.UUID;
* - UTF-8 string data.
*/
public class VariantUtil {
+ // Jackson's JsonFactory is thread-safe and intended to be reused, so the
variant module shares a
+ // single instance. Variant.escapeJson (one call per serialized string or
key) and
+ // VariantBuilder.parseJson (one call per parsed JSON value) both use it,
which avoids a per-call
+ // factory allocation (including its symbol tables) and keeps one source of
configuration.
+ static final JsonFactory JSON_FACTORY = new JsonFactory();
+
public static final int BASIC_TYPE_BITS = 2;
public static final int BASIC_TYPE_MASK = 0x3;
public static final int TYPE_INFO_MASK = 0x3F;
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
