(parquet-java) branch master updated: GH-2972: Fix incomplete avro metadata on INT96 schema converter (#3311)

[gangwu]

This is an automated email from the ASF dual-hosted git repository.

gangwu pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/parquet-java.git


The following commit(s) were added to refs/heads/master by this push:
     new f50dd6cb4 GH-2972: Fix incomplete avro metadata on INT96 schema 
converter (#3311)
f50dd6cb4 is described below

commit f50dd6cb4b526cf4b585993c1b69a838cd8151f3
Author: Arnav Balyan <60175178+arnavbal...@users.noreply.github.com>
AuthorDate: Sun Sep 21 19:17:15 2025 +0530

    GH-2972: Fix incomplete avro metadata on INT96 schema converter (#3311)
---
 .../apache/parquet/avro/AvroSchemaConverter.java   |  4 ++-
 .../parquet/avro/TestAvroSchemaConverter.java      | 29 +++++++++++++++++++++-
 2 files changed, 31 insertions(+), 2 deletions(-)

diff --git 
a/parquet-avro/src/main/java/org/apache/parquet/avro/AvroSchemaConverter.java 
b/parquet-avro/src/main/java/org/apache/parquet/avro/AvroSchemaConverter.java
index 58e9c2e19..782c009db 100644
--- 
a/parquet-avro/src/main/java/org/apache/parquet/avro/AvroSchemaConverter.java
+++ 
b/parquet-avro/src/main/java/org/apache/parquet/avro/AvroSchemaConverter.java
@@ -404,7 +404,9 @@ public class AvroSchemaConverter {
             @Override
             public Schema convertINT96(PrimitiveTypeName primitiveTypeName) {
               if (readInt96AsFixed) {
-                return Schema.createFixed("INT96", "INT96 represented as 
byte[12]", null, 12);
+                String name = parquetType.getName();
+                String ns = namespace(name, names);
+                return Schema.createFixed(name, "INT96 represented as 
byte[12]", ns, 12);
               }
               throw new IllegalArgumentException(
                   "INT96 is deprecated. As interim enable READ_INT96_AS_FIXED 
flag to read as byte array.");
diff --git 
a/parquet-avro/src/test/java/org/apache/parquet/avro/TestAvroSchemaConverter.java
 
b/parquet-avro/src/test/java/org/apache/parquet/avro/TestAvroSchemaConverter.java
index d54cd4310..130192e15 100644
--- 
a/parquet-avro/src/test/java/org/apache/parquet/avro/TestAvroSchemaConverter.java
+++ 
b/parquet-avro/src/test/java/org/apache/parquet/avro/TestAvroSchemaConverter.java
@@ -579,7 +579,7 @@ public class TestAvroSchemaConverter {
     enableInt96ReadingConfig.setBoolean(AvroReadSupport.READ_INT96_AS_FIXED, 
true);
 
     Schema schema = Schema.createRecord("myrecord", null, null, false);
-    Schema int96schema = Schema.createFixed("INT96", "INT96 represented as 
byte[12]", null, 12);
+    Schema int96schema = Schema.createFixed("int96_field", "INT96 represented 
as byte[12]", null, 12);
     schema.setFields(Collections.singletonList(new Schema.Field("int96_field", 
int96schema, null, null)));
 
     testParquetToAvroConversion(
@@ -599,6 +599,33 @@ public class TestAvroSchemaConverter {
         () -> new AvroSchemaConverter().convert(parquetSchemaWithInt96));
   }
 
+  @Test
+  public void testMultipleInt96FieldsToStringConversion() throws Exception {
+    Configuration enableInt96ReadingConfig = new Configuration();
+    enableInt96ReadingConfig.setBoolean(AvroReadSupport.READ_INT96_AS_FIXED, 
true);
+
+    Types.MessageTypeBuilder builder = Types.buildMessage();
+    
builder.optional(PrimitiveType.PrimitiveTypeName.INT96).named("timestamp_1");
+    
builder.optional(PrimitiveType.PrimitiveTypeName.INT96).named("timestamp_2");
+    MessageType int96Schema = builder.named("int96Schema");
+
+    AvroSchemaConverter converter = new 
AvroSchemaConverter(enableInt96ReadingConfig);
+    Schema avroSchema = converter.convert(int96Schema);
+
+    String schemaString = avroSchema.toString(true);
+
+    Assert.assertTrue(
+        "First field should have full timestamp_1 definition",
+        schemaString.contains("\"name\" : \"timestamp_1\""));
+    Assert.assertTrue(
+        "Second field should have full timestamp_2 definition",
+        schemaString.contains("\"name\" : \"timestamp_2\""));
+
+    Assert.assertFalse(
+        "Should not reference bare 'INT96' type anymore",
+        schemaString.contains("\"type\" : [ \"null\", \"INT96\" ]"));
+  }
+
   @Test
   public void testDateType() throws Exception {
     Schema date = LogicalTypes.date().addToSchema(Schema.create(INT));