tustvold commented on code in PR #5796:
URL: https://github.com/apache/arrow-rs/pull/5796#discussion_r1611508221
##########
arrow-array/src/builder/generic_bytes_view_builder.rs:
##########
@@ -62,6 +83,98 @@ impl<T: ByteViewType + ?Sized> GenericByteViewBuilder<T> {
Self { block_size, ..self }
}
+ /// Append a new data block returning the new block offset
+ ///
+ /// Note: this will first flush any in-progress block
+ ///
+ /// This allows appending views from blocks added using
[`Self::append_block`]. See
+ /// [`Self::append_value`] for appending individual values
+ ///
+ /// ```
+ /// # use arrow_array::builder::StringViewBuilder;
+ /// let mut builder = StringViewBuilder::new();
+ ///
+ /// let block = builder.append_block(b"helloworldbingobongo".into());
+ ///
+ /// builder.try_append_view(block, 0, 5).unwrap();
+ /// builder.try_append_view(block, 5, 5).unwrap();
+ /// builder.try_append_view(block, 10, 5).unwrap();
+ /// builder.try_append_view(block, 15, 5).unwrap();
+ /// builder.try_append_view(block, 0, 15).unwrap();
+ /// let array = builder.finish();
+ ///
+ /// let actual: Vec<_> = array.iter().flatten().collect();
+ /// let expected = &["hello", "world", "bingo", "bongo",
"helloworldbingo"];
+ /// assert_eq!(actual, expected);
+ /// ```
+ pub fn append_block(&mut self, buffer: Buffer) -> u32 {
+ assert!(buffer.len() < u32::MAX as usize);
+
+ self.flush_in_progress();
+ let offset = self.completed.len();
+ self.push_completed(buffer);
+ offset as u32
+ }
+
+ /// Try to append a view of the given `block`, `offset` and `length`
+ ///
+ /// See [`Self::append_block`]
+ pub fn try_append_view(&mut self, block: u32, offset: u32, len: u32) ->
Result<(), ArrowError> {
Review Comment:
I don't know what performance impact the validation logic here will have,
but we can always add an unchecked version down the line should it become a
problem.
--
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]
