CTTY commented on code in PR #1657:
URL: https://github.com/apache/iceberg-rust/pull/1657#discussion_r2371143498


##########
crates/iceberg/src/writer/base_writer/data_file_writer.rs:
##########
@@ -21,54 +21,65 @@ use arrow_array::RecordBatch;
 use itertools::Itertools;
 
 use crate::Result;
-use crate::spec::{DataContentType, DataFile, Struct};
-use crate::writer::file_writer::{FileWriter, FileWriterBuilder};
+use crate::spec::{DEFAULT_PARTITION_SPEC_ID, DataContentType, DataFile, 
PartitionKey, Struct};
+use crate::writer::file_writer::FileWriterBuilder;
+use crate::writer::file_writer::location_generator::{FileNameGenerator, 
LocationGenerator};
+use crate::writer::file_writer::rolling_writer::RollingFileWriter;
 use crate::writer::{CurrentFileStatus, IcebergWriter, IcebergWriterBuilder};
 
 /// Builder for `DataFileWriter`.
 #[derive(Clone, Debug)]
-pub struct DataFileWriterBuilder<B: FileWriterBuilder> {
-    inner: B,
-    partition_value: Option<Struct>,
-    partition_spec_id: i32,
+pub struct DataFileWriterBuilder<B: FileWriterBuilder, L: LocationGenerator, 
F: FileNameGenerator> {
+    inner_writer: RollingFileWriter<B, L, F>,
+    partition_key: Option<PartitionKey>,
 }
 
-impl<B: FileWriterBuilder> DataFileWriterBuilder<B> {
+impl<B: FileWriterBuilder, L: LocationGenerator, F: FileNameGenerator>
+    DataFileWriterBuilder<B, L, F>
+{
     /// Create a new `DataFileWriterBuilder` using a `FileWriterBuilder`.
-    pub fn new(inner: B, partition_value: Option<Struct>, partition_spec_id: 
i32) -> Self {
+    pub fn new(
+        inner_writer: RollingFileWriter<B, L, F>,
+        partition_key: Option<PartitionKey>,
+    ) -> Self {
         Self {
-            inner,
-            partition_value,
-            partition_spec_id,
+            inner_writer,
+            partition_key,
         }
     }
 }
 
 #[async_trait::async_trait]
-impl<B: FileWriterBuilder> IcebergWriterBuilder for DataFileWriterBuilder<B> {
-    type R = DataFileWriter<B>;
+impl<B: FileWriterBuilder, L: LocationGenerator, F: FileNameGenerator> 
IcebergWriterBuilder
+    for DataFileWriterBuilder<B, L, F>
+{
+    type R = DataFileWriter<B, L, F>;
 
     async fn build(self) -> Result<Self::R> {
         Ok(DataFileWriter {
-            inner_writer: Some(self.inner.clone().build().await?),
-            partition_value: self.partition_value.unwrap_or(Struct::empty()),
-            partition_spec_id: self.partition_spec_id,
+            inner_writer: Some(self.inner_writer), // todo revisit this, 
probably still need a builder for rolling writer
+            partition_key: self.partition_key,
         })
     }
 }
 
 /// A writer write data is within one spec/partition.
 #[derive(Debug)]
-pub struct DataFileWriter<B: FileWriterBuilder> {
-    inner_writer: Option<B::R>,
-    partition_value: Struct,
-    partition_spec_id: i32,
+pub struct DataFileWriter<B: FileWriterBuilder, L: LocationGenerator, F: 
FileNameGenerator> {
+    inner_writer: Option<RollingFileWriter<B, L, F>>,

Review Comment:
   Yeah I agree, it's that we need to `take` the rolling writer when closing 
the `DataFileWriter`, and I haven't found a nice solution to do it without 
`Option`, and I also don't think it makes much sense to implement `Default` for 
`RollingFileWriter`



-- 
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