fixup! feat(writer): support partition writer (#16)

fix tests failure, caused by apache#907

Signed-off-by: xxchan <xxchan22f@gmail.com>

Author: xxchan

crates/iceberg/src/writer/function_writer/fanout_partition_writer.rs

@@ -145,13 +145,15 @@ impl<B: IcebergWriterBuilder> IcebergWriter for FanoutPartitionWriter<B> {
 
 #[cfg(test)]
 mod test {
+    use std::collections::HashMap;
     use std::sync::Arc;
 
     use arrow_array::{Int64Array, RecordBatch, StringArray};
     use arrow_schema::{DataType, Field, Schema as ArrowSchema};
     use arrow_select::concat::concat_batches;
     use itertools::Itertools;
     use parquet::arrow::arrow_reader::ParquetRecordBatchReaderBuilder;
+    use parquet::arrow::PARQUET_FIELD_ID_META_KEY;
     use parquet::file::properties::WriterProperties;
     use tempfile::TempDir;
 
@@ -225,8 +227,14 @@ mod test {
 
         // prepare data
         let schema = Arc::new(ArrowSchema::new(vec![
-            Field::new("id", DataType::Int64, true),
-            Field::new("data", DataType::Utf8, true),
+            Field::new("id", DataType::Int64, true).with_metadata(HashMap::from([(
+                PARQUET_FIELD_ID_META_KEY.to_string(),
+                1.to_string(),
+            )])),
+            Field::new("data", DataType::Utf8, true).with_metadata(HashMap::from([(
+                PARQUET_FIELD_ID_META_KEY.to_string(),
+                2.to_string(),
+            )])),
         ]));
         let id_array = Int64Array::from(vec![1, 2, 1, 3, 2, 3, 1]);
         let data_array = StringArray::from(vec!["a", "b", "c", "d", "e", "f", "g"]);

crates/iceberg/src/writer/function_writer/precompute_partition_writer.rs

@@ -140,13 +140,15 @@ impl<B: IcebergWriterBuilder> IcebergWriter<(StructArray, RecordBatch)>
 
 #[cfg(test)]
 mod test {
+    use std::collections::HashMap;
     use std::sync::Arc;
 
     use arrow_array::{ArrayRef, Int64Array, RecordBatch, StringArray, StructArray};
     use arrow_schema::{DataType, Field, Schema as ArrowSchema};
     use arrow_select::concat::concat_batches;
     use itertools::Itertools;
     use parquet::arrow::arrow_reader::ParquetRecordBatchReaderBuilder;
+    use parquet::arrow::PARQUET_FIELD_ID_META_KEY;
     use parquet::file::properties::WriterProperties;
     use tempfile::TempDir;
 
@@ -219,8 +221,14 @@ mod test {
 
         // prepare data
         let schema = Arc::new(ArrowSchema::new(vec![
-            Field::new("id", DataType::Int64, true),
-            Field::new("data", DataType::Utf8, true),
+            Field::new("id", DataType::Int64, true).with_metadata(HashMap::from([(
+                PARQUET_FIELD_ID_META_KEY.to_string(),
+                1.to_string(),
+            )])),
+            Field::new("data", DataType::Utf8, true).with_metadata(HashMap::from([(
+                PARQUET_FIELD_ID_META_KEY.to_string(),
+                2.to_string(),
+            )])),
         ]));
         let id_array = Int64Array::from(vec![1, 2, 1, 3, 2, 3, 1]);
         let data_array = StringArray::from(vec!["a", "b", "c", "d", "e", "f", "g"]);