nastra commented on code in PR #3626:
URL: https://github.com/apache/parquet-java/pull/3626#discussion_r3452669407


##########
parquet-variant/src/test/java/org/apache/parquet/variant/TestVariantObjectBuilder.java:
##########
@@ -277,6 +277,72 @@ public void testDuplicateKeys() {
     Assert.assertEquals(1, v.getFieldByKey("duplicate").getLong());
   }
 
+  @Test
+  public void testDuplicateKeysKeptValueLarger() {
+    // The retained (last-written) value is larger than the first occurrence. 
The data size must be
+    // computed from the retained value, otherwise the encoded object is 
truncated/corrupt.
+    VariantBuilder b = new VariantBuilder();
+    VariantObjectBuilder objBuilder = b.startObject();
+    objBuilder.appendKey("duplicate");
+    objBuilder.appendInt(1); // 5 bytes
+    objBuilder.appendKey("duplicate");
+    objBuilder.appendString("hello"); // 6 bytes
+    b.endObject();
+    VariantTestUtil.testVariant(b.build(), v -> {
+      VariantTestUtil.checkType(v, VariantUtil.OBJECT, Variant.Type.OBJECT);
+      Assert.assertEquals(1, v.numObjectElements());
+      Variant variant = v.getFieldByKey("duplicate");
+      VariantTestUtil.checkType(variant, VariantUtil.SHORT_STR, 
Variant.Type.STRING);
+      Assert.assertEquals("hello", variant.getString());
+    });
+  }
+
+  @Test
+  public void testDuplicateKeysKeptValueSmaller() {
+    // The retained (last-written) value is smaller than the first occurrence. 
The data size must be
+    // computed from the retained value, otherwise the encoded object reserves 
stale trailing bytes.
+    VariantBuilder b = new VariantBuilder();
+    VariantObjectBuilder objBuilder = b.startObject();
+    objBuilder.appendKey("duplicate");
+    objBuilder.appendString("hello"); // 6 bytes
+    objBuilder.appendKey("duplicate");
+    objBuilder.appendInt(1); // 5 bytes
+    b.endObject();
+    VariantTestUtil.testVariant(b.build(), v -> {
+      VariantTestUtil.checkType(v, VariantUtil.OBJECT, Variant.Type.OBJECT);
+      Assert.assertEquals(1, v.numObjectElements());
+      Variant variant = v.getFieldByKey("duplicate");
+      VariantTestUtil.checkType(variant, VariantUtil.PRIMITIVE, 
Variant.Type.INT);
+      Assert.assertEquals(1, variant.getInt());
+    });
+  }
+
+  @Test
+  public void testDuplicateKeysDifferentSizesAcrossMultipleKeys() {

Review Comment:
   without the fix this test would fail with 
`java.lang.IllegalArgumentException: Invalid byte-array offset (25). length: 22`



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to