All pull requests

Pull requests

• feat: push local TopK thresholds into Parquet readers

  area:joinsenhancement
  #6263·pingzh opened Sep 27, 2026Contributor·

  ·

• test: compare in-memory caches with independent answers

  enhancementtest
  #6262·LinSimon-901101 opened Sep 27, 2026Contributor·

  ·
  1

• fix: return a native plan's memory before its Spark task ends

  area:memorybugrun-iceberg-testsrun-spark-4.1-tests
  #6261·andygrove opened Sep 26, 2026Member·

  ·
  1

  2

• feat: report JVM Arrow memory in the executor memory usage log

  enhancement
  #6250·andygrove opened Sep 26, 2026Member·

  ·

• fix: match Spark ANSI integral overflow errors (#6217)

  area:expressionsbug
  #6249·LinSimon-901101 opened Sep 26, 2026Contributor·

  ·
  1

• feat: charge native write buffers to the task's memory pool

  area:Icebergarea:memoryarea:writerenhancement
  #6247·andygrove opened Sep 26, 2026Member·

  ·
  2

• fix: support binaryAsString in the native Parquet scan

  area:joinsarea:scanbug
  #6246·manuzhang opened Sep 26, 2026Member·

  ·
  1

• fix: rethrow the exception a JVM input throws instead of a CometNativeException

  area:Icebergbug
  #6243·andygrove opened Sep 26, 2026Member·

  ·
  1

• test: backport the upstream fix for a flaky Iceberg 1.9.1 rewrite test

  area:Icebergenhancementrun-iceberg-teststest
  #6242·andygrove opened Sep 26, 2026Member·

  ·

• perf: choose dictionary encoding like iceberg-java in the native Iceberg writer

  area:Icebergarea:writerenhancementperformance
  #6241·andygrove opened Sep 26, 2026Member·

  ·
  1

  3

• fix: match iceberg-java for Iceberg partitions past year 262142 in the native writer

  area:expressionsarea:Icebergarea:writerbug
  #6239·andygrove opened Sep 26, 2026Member·

  ·
  1

• fix: compact already-sliced batches before the native Iceberg writer counts NaNs

  area:Icebergarea:writerbugrun-iceberg-tests
  #6238·andygrove opened Sep 26, 2026Member·

  ·
  1

• fix: Let DataFusion handles global aggregate with no grouping keys instead of falling back to Spark

  bug
  #6235·hsiang-c opened Sep 25, 2026Contributor·

  ·
  1

• fix: [branch-1.0] check each fair_unified reservation against its own share (#6205)

  area:memorybug
  #6228·andygrove opened Sep 25, 2026Member·

  ·
  1

• ci: run every tier on release-branch pull requests, and the full suite before an RC

  backport-1.1documentation
  #6218·andygrove opened Sep 25, 2026Member·

  ·
  6

• fix: decline native Iceberg writes with a custom location provider

  area:Icebergarea:writerbug
  #6216·liupoyi-1031 opened Sep 25, 2026Contributor·

  ·
  1

  4

• chore(deps): bump the codeql-actions group with 2 updates

  area:cidependencies
  #6215·dependabot[bot] opened Sep 25, 2026Bot·

  ·

• fix: reject non-default collations in all sort keys

  area:expressionsbug
  #6206·LinSimon-901101 opened Sep 24, 2026Contributor·

  ·
  1

  2

• feat: support AtLeastNNonNulls natively

  area:expressionsenhancement
  #6180·rich7420 opened Sep 24, 2026Contributor·

  ·
  1

• fix: fall back to Spark for a TRY cast of a map key that can fail

  area:expressionsbug
  #6179·Smallfu666 opened Sep 24, 2026Contributor·

  ·
  1

• fix: refuse codegen dispatch for a TRY cast that can put a null key in a map

  area:expressionsbug
  #6178·Smallfu666 opened Sep 24, 2026Contributor·

  ·
  1

• test: add Java-generated RLIKE parity fixtures for regex upgrades

  area:expressionsenhancementtest
  #6173·mizulun opened Sep 24, 2026Contributor·

  ·
  1

  5

• feat: evaluate UTF8 array extrema collations natively

  area:expressionsenhancementrun-all-spark-profilesrun-spark-4.1-tests
  #6170·sunchao opened Sep 24, 2026Member·

  ·
  6

• fix: preserve DPP filters during transition revert

  bug
  #6137·sam-1112 opened Sep 23, 2026Contributor·

  ·
  1

• refactor: remove unused cast compatibility flag

  area:expressionsarea:Icebergarea:scanenhancement
  #6135·sam-1112 opened Sep 23, 2026Contributor·

  ·
  1

  3