lyang24 commented on code in PR #9040:
URL: https://github.com/apache/arrow-rs/pull/9040#discussion_r2645569052
##########
arrow-array/src/builder/generic_bytes_view_builder.rs:
##########
@@ -430,6 +430,55 @@ impl<T: ByteViewType + ?Sized> GenericByteViewBuilder<T> {
};
}
+ /// Append the same value `n` times into the builder
+ ///
+ /// This is more efficient than calling [`Self::try_append_value`] `n`
times,
+ /// especially when deduplication is enabled, as it only hashes the value
once.
+ ///
+ /// # Errors
+ ///
+ /// Returns an error if
+ /// - String buffer count exceeds `u32::MAX`
+ /// - String length exceeds `u32::MAX`
+ ///
+ /// # Example
+ /// ```
+ /// # use arrow_array::builder::StringViewBuilder;
+ /// # use arrow_array::Array;
+ /// let mut builder = StringViewBuilder::new().with_deduplicate_strings();
+ ///
+ /// // Append "hello" 1000 times efficiently
+ /// builder.try_append_value_n("hello", 1000)?;
+ ///
+ /// let array = builder.finish();
+ /// assert_eq!(array.len(), 1000);
+ ///
+ /// // All values are "hello"
+ /// for value in array.iter() {
+ /// assert_eq!(value, Some("hello"));
+ /// }
+ /// # Ok::<(), arrow_schema::ArrowError>(())
+ /// ```
+ #[inline]
+ pub fn try_append_value_n(
+ &mut self,
+ value: impl AsRef<T::Native>,
+ n: usize,
+ ) -> Result<(), ArrowError> {
+ if n == 0 {
+ return Ok(());
+ }
+ // Process value once (handles deduplication, buffer management, view
creation)
+ self.try_append_value(value)?;
+ // Reuse the view (n-1) times
+ let view = *self.views_buffer.last().unwrap();
+ for _ in 1..n {
+ self.views_buffer.push(view);
+ }
Review Comment:
good call this is cleaner too!
--
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]
