kosiew commented on code in PR #23223:
URL: https://github.com/apache/datafusion/pull/23223#discussion_r3544770488
##########
datafusion/functions/src/strings.rs:
##########
@@ -818,96 +765,117 @@ impl StringViewArrayBuilder {
.into()
}
- #[inline]
- fn make_long_view(&self, length: u32, offset: u32, prefix_bytes: &[u8]) ->
u128 {
- let buffer_index: u32 = i32::try_from(self.completed.len())
- .expect("buffer count exceeds i32::MAX")
- as u32;
- Self::make_long_view_checked(length, buffer_index, offset,
prefix_bytes)
- }
-
- /// See [`BulkNullStringArrayBuilder::append_byte_map`].
+ /// Fallibly append a row whose bytes are produced by mapping each byte of
+ /// `src` through `map`, in order.
///
/// # Safety
///
/// The bytes produced by applying `map` to each byte of `src`, in order,
/// must form valid UTF-8.
///
- /// # Panics
+ /// # Errors
///
- /// Panics under the same conditions as [`Self::append_value`]: if
- /// `src.len()`, the in-progress buffer offset, or the number of completed
- /// buffers exceeds `i32::MAX`.
+ /// Returns an error under the same conditions as
[`Self::try_append_value`].
#[inline]
- pub unsafe fn append_byte_map<F: FnMut(u8) -> u8>(&mut self, src: &[u8],
mut map: F) {
- let length: u32 =
- i32::try_from(src.len()).expect("value length exceeds i32::MAX")
as u32;
+ pub unsafe fn try_append_byte_map<F: FnMut(u8) -> u8>(
+ &mut self,
+ src: &[u8],
+ mut map: F,
+ ) -> Result<()> {
+ let length = try_string_view_part("value length", src.len())?;
if length <= 12 {
let mut bytes = [0u8; 12];
for (d, &b) in bytes[..src.len()].iter_mut().zip(src) {
*d = map(b);
}
self.views.push(make_view(&bytes[..src.len()], 0, 0));
- return;
+ return Ok(());
}
- self.ensure_long_capacity(length);
+ self.try_ensure_long_capacity(length)?;
let cursor = self.in_progress.len();
- let offset: u32 = i32::try_from(cursor).expect("offset exceeds
i32::MAX") as u32;
+ let offset = try_string_view_part("offset", cursor)?;
+ let buffer_index = try_string_view_part("buffer count",
self.completed.len())?;
self.in_progress.extend(src.iter().map(|&b| map(b)));
- self.views
- .push(self.make_long_view(length, offset,
&self.in_progress[cursor..]));
+ self.views.push(Self::make_long_view_checked(
+ length,
+ buffer_index,
+ offset,
+ &self.in_progress[cursor..],
+ ));
+ Ok(())
+ }
+
+ #[inline]
+ fn push_view_from_writer(
+ &mut self,
+ inline_buf: &[u8; 12],
+ inline_len: u8,
+ spill_cursor: Option<usize>,
+ ) -> Result<()> {
+ match spill_cursor {
+ None => {
+ self.views
+ .push(make_view(&inline_buf[..inline_len as usize], 0, 0));
+ }
+ Some(start) => {
+ let end = self.in_progress.len();
+ let length = try_string_view_part("value length", end -
start)?;
+ let offset = try_string_view_part("offset", start)?;
+ let buffer_index =
+ try_string_view_part("buffer count",
self.completed.len())?;
+ self.views.push(Self::make_long_view_checked(
Review Comment:
Renamed it to `make_long_view_from_checked_parts`
--
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]
