Add Primitive time/timestamp_nanos/timestampntz_nanos/uuid test file

variant/README.md

@@ -69,5 +69,9 @@ resulting in a single `0` byte:
 echo -n 'a' | tr a '\0' > primitive_null.value
 ```
 
+### Modification 2: Created `TimeNTZ/Timestamp with timezone nanos/Timestamp without timezone nanos/UUID` with Iceberg test code
+
+Currently, Spark [does not support](https://github.com/apache/spark/blob/master/common/variant/README.md) Variant values containing UUID, Time, or nanosecond-precision Timestamp. the `primitive_time.[metadata/value]`, `primitive_timestamp_nanos.[metadata/value]`, `primitive_timestampntz_nanos.[metadata/value]` and `primitive_uuid.[metadata/data]` was generated by [Iceberg test code](https://github.com/apache/iceberg/blob/3a4215dbb714477c89681ab94f1197b6ebcbdfff/parquet/src/test/java/org/apache/iceberg/parquet/TestVariantReaders.java#L355)
+
 [Variant]: https://github.com/apache/parquet-format/blob/master/VariantEncoding.md
 [primitive types listed in the spec]: https://github.com/apache/parquet-format/blob/master/VariantEncoding.md#value-data-for-primitive-type-basic_type0

variant/data_dictionary.json

@@ -67,7 +67,11 @@
     "primitive_int8": 42,
     "primitive_null": null,
     "primitive_string": "This string is longer than 64 bytes and therefore does not fit in a short_string and it also includes several non ascii characters such as \ud83d\udc22, \ud83d\udc96, \u2665\ufe0f, \ud83c\udfa3 and \ud83e\udd26!!",
+    "primitive_time": "12:33:54:123456",
     "primitive_timestamp": "2025-04-16 12:34:56.78-04:00",
     "primitive_timestampntz": "2025-04-16 12:34:56.78",
-    "short_string": "Less than 64 bytes (\u2764\ufe0f with utf8)"
-}
+    "primitive_timestamp_nanos": "2024-11-07T12:33:54.123456789+00:00",
+    "primitive_timestampntz_nanos": "2024-11-07T12:33:54.123456789",
+    "primitive_uuid": "f24f9b64-81fa-49d1-b74e-8c09a6e31c56",
+    "short_string": "Less than 64 bytes (\u2764\ufe0f with utf8)",
+}

variant/primitive_timestamp_nanos.value

@@ -0,0 +1 @@
+HA:l��

variant/primitive_timestampntz_nanos.value

@@ -0,0 +1 @@
+LA:l��

variant/primitive_uuid.value

@@ -0,0 +1 @@
+P�O�d��IѷN�	��V

variant/regen.py

@@ -75,12 +75,7 @@
 INSERT INTO T VALUES ('primitive_binary', X'31337deadbeefcafe'::Variant);
 INSERT INTO T VALUES ('primitive_string', 'This string is longer than 64 bytes and therefore does not fit in a short_string and it also includes several non ascii characters such as 🐢, 💖, ♥️, 🎣 and 🤦!!'::Variant);
 
--- https://github.com/apache/parquet-testing/issues/79
--- is not clear how to create the following types using Spark SQL
--- TODO TimeNTZ                    (Type ID 17)
--- TODO 'timestamp with timezone (NANOS)'  (Type ID 18)
--- TODO 'timestamp with time zone (NANOS)' (Type ID 19)
--- TODO 'UUID'                     (Type ID 20)
+-- binary artifacts of 'TimeNTZ'/'timestamp with timezone (NANOS)'/'timestamp without time zone (NANOS)'/'UUID' was generated by the iceberg test code, please ref to https://github.com/apache/parquet-testing/pull/92 for more detail
 
 -------------------------------
 -- Short string (basic_type=1)
@@ -170,4 +165,4 @@
 # Note: It is possible to write the output to a single parquet file, using a command
 # such as:
 # spark.sql("SELECT * FROM output").repartition(1).write.parquet('variant.parquet')
-# At the time of writing, this file does not have the logical type annotation for VARIANT
+# At the time of writing, this file does not have the logical type annotation for VARIANT