All pull requests

Pull requests

• test: migrate required-child hash regressions to SQL fixtures

  enhancementtest
  #6864·rich7420 opened Oct 11, 2026Contributor·

  ·

• test: migrate Java RLIKE semantics and batch coverage to SQL fixtures

  enhancementtest
  #6863·rich7420 opened Oct 11, 2026Contributor·

  ·

• test: cover container field ids next to INT96 timestamps in the native Parquet scan

  enhancementtest
  #6862·dwsmith1983 opened Oct 11, 2026Contributor·

  ·
  1

  1

• perf: presize collections and reuse buffers in native loops

  area:aggregationarea:expressionsarea:ffiarea:Icebergarea:scanarea:shufflearea:udfarea:writerenhancementperformance
  #6861·comphead opened Oct 10, 2026Contributor·

  ·
  1

• perf: generate the in-memory cache reader's class once per executor

  area:ffienhancementperformance
  #6860·andygrove opened Oct 10, 2026Member·

  ·

• feat: add lz4 as an opt-in codec for Comet's in-memory cache

  enhancement
  #6859·andygrove opened Oct 10, 2026Member·

  ·

• perf: generate the columnar-to-row projection once per executor instead of per partition

  area:ffienhancementperformancerun-spark-4.1-tests
  #6858·andygrove opened Oct 10, 2026Member·

  ·
  3

• test: extend C2R and R2C microbenchmarks to cover nested types

  area:shuffleenhancementtest
  #6856·andygrove opened Oct 10, 2026Member·

  ·
  3

  

• perf: read cache statistics null counts from Comet's Arrow vectors

  enhancementperformancerun-benchmark-check
  #6853·andygrove opened Oct 10, 2026Member·

  ·

• fix: preserve columnar output when reverting a cached AQE result stage

  bug
  #6852·andygrove opened Oct 10, 2026Member·

  ·
  1

  3

• feat: bump iceberg-rust and write float and double identity partitions natively

  area:Icebergarea:scanarea:writerenhancementrun-all-spark-profilesrun-iceberg-tests
  #6851·andygrove opened Oct 10, 2026Member·

  ·
  3

• perf: preserve supported Iceberg residual conjuncts

  area:Icebergarea:scanenhancementperformance
  #6847·rich7420 opened Oct 10, 2026Contributor·

  ·
  1

• chore: re-enable unused-parameter warnings in strict profile

  area:aggregationarea:expressionsarea:Icebergarea:scanenhancement
  #6846·rich7420 opened Oct 10, 2026Contributor·

  ·
  1

• perf: reduce retained buffers for nested map lookups

  area:expressionsenhancementperformance
  #6845·rich7420 opened Oct 10, 2026Contributor·

  ·
  1

• fix: cast string to date for years outside chrono's NaiveDate range

  area:expressionsbug
  #6844·viirya opened Oct 10, 2026Member·

  ·
  1

  5

• fix: accept all BMP Unicode decimal digits in cast(string as decimal)

  area:expressionsbug
  #6841·viirya opened Oct 10, 2026Member·

  ·
  1

  3

• fix: read fs.comet.libhdfs.schemes for the scan rule from the Hadoop conf

  area:scanbug
  #6838·dwsmith1983 opened Oct 10, 2026Contributor·

  ·
  1

  1

• test: count the partitions and batches the native cache scan reads

  area:scanenhancementrun-spark-4.1-teststest
  #6836·andygrove opened Oct 10, 2026Member·

  ·

• fix: keep a streamed side sorted outside the native plan in order through outer hash joins

  bug
  #6835·andygrove opened Oct 10, 2026Member·

  ·
  1

• Integral sequence optimisation

  area:expressions
  #6833·nat-openai opened Oct 10, 2026·

  ·

• fix: handle truncation operands in scalar evaluation and rewrites

  area:expressionsbug
  #6831·nat-openai opened Oct 9, 2026·

  ·

• fix: raise DIVIDE_BY_ZERO from native corr on a zero denominator in ANSI mode

  area:aggregationbug
  #6830·kazuyukitanimura opened Oct 9, 2026Contributor·

  ·
  1

  3

• fix: match Spark percentile ordering for negative NaNs

  area:aggregationbug
  #6829·rich7420 opened Oct 9, 2026Contributor·

  ·
  1

• docs: list the S3A settings the Iceberg native-write gate ignores

  area:Icebergdocumentation
  #6828·andygrove opened Oct 9, 2026Member·

  ·

• fix: preserve CASE WHEN struct field names from the first THEN branch

  area:expressionsbug
  #6827·pingzh opened Oct 9, 2026Contributor·

  ·
  1

  9