[arrow-rs] branch master updated: Short-circuit on exhausted page in skip_records (#4320)

[tustvold]

This is an automated email from the ASF dual-hosted git repository.

tustvold pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/arrow-rs.git


The following commit(s) were added to refs/heads/master by this push:
     new c295b172b Short-circuit on exhausted page in skip_records (#4320)
c295b172b is described below

commit c295b172b37902d5fa41ef275ff5b86caf9fde75
Author: Raphael Taylor-Davies <1781103+tustv...@users.noreply.github.com>
AuthorDate: Wed May 31 15:03:25 2023 +0100

    Short-circuit on exhausted page in skip_records (#4320)
---
 parquet/src/column/reader.rs | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/parquet/src/column/reader.rs b/parquet/src/column/reader.rs
index f63b1e60a..0bb6e0024 100644
--- a/parquet/src/column/reader.rs
+++ b/parquet/src/column/reader.rs
@@ -333,6 +333,14 @@ where
                 None => (to_read, to_read),
             };
 
+            self.num_decoded_values += rep_levels_read as u32;
+            remaining -= records_read;
+
+            if self.num_buffered_values == self.num_decoded_values {
+                // Exhausted buffered page - no need to advance other decoders
+                continue;
+            }
+
             let (values_read, def_levels_read) = match 
self.def_level_decoder.as_mut() {
                 Some(decoder) => decoder
                     .skip_def_levels(rep_levels_read, 
self.descr.max_def_level())?,
@@ -355,9 +363,6 @@ where
                     values_read
                 ));
             }
-
-            self.num_decoded_values += rep_levels_read as u32;
-            remaining -= records_read;
         }
         Ok(num_records - remaining)
     }