All pull requests

Pull requests

• fix: fall back to Spark for decimal AVG cases that return wrong results

  area:aggregationbugcorrectnessrun-all-spark-profilesrun-spark-4.1-tests
  #7017·andygrove opened Oct 15, 2026Member·

  ·
  1

• perf: share one decoded copy of a broadcast among the tasks of an executor

  enhancementperformance
  #7016·andygrove opened Oct 15, 2026Member·

  ·
  1

• fix: bound Parquet Variant nesting depth

  area:scanbugrun-spark-4.1-tests
  #7015·manuzhang opened Oct 15, 2026Member·

  ·

• refactor: move MergeRows, Explode, aggregate, join and window planning into dedicated modules

  enhancementrun-iceberg-testsrun-spark-4.1-tests
  #7014·andygrove opened Oct 15, 2026Member·

  ·

• docs: correct native Iceberg write docs that drifted from the code

  area:Icebergdocumentation
  #7009·andygrove opened Oct 15, 2026Member·Queued
  2

• refactor: deduplicate split list-array construction

  area:expressionsenhancement
  #7004·arminazimi opened Oct 15, 2026·

  ·
  1

• build: remove Guava dependency

  area:Icebergarea:scanarea:shufflebuildenhancement
  #7000·andygrove opened Oct 14, 2026Member·

  ·

• build: use a single jni version across the native workspace

  area:ffiarea:shufflebuildenhancement
  #6998·andygrove opened Oct 14, 2026Member·Queued
  2

• fix: fall back for brotli Iceberg writes when Hadoop's BrotliCodec cannot be loaded

  area:Icebergarea:writerbug
  #6996·andygrove opened Oct 14, 2026Member·

  ·
  1

• fix: stop building maps natively when the key type holds a FLOAT or DOUBLE

  area:expressionsbug
  #6992·andygrove opened Oct 14, 2026Member·

  ·
  1

  6

• perf: build an AQE cache that ends in a Spark operator straight into Arrow

  enhancementperformancerun-spark-4.1-tests
  #6991·andygrove opened Oct 14, 2026Member·

  ·
  1

• refactor: share Parquet field-id and name resolution between root and nested fields

  area:scanenhancement
  #6990·andygrove opened Oct 14, 2026Member·

  ·
  1

  6

• fix: treat -0.0 and 0.0 as one value in arrays_overlap on Spark 4.0.5, 4.1.4 and 4.2.1

  area:expressionsbugrun-all-spark-profiles
  #6989·andygrove opened Oct 14, 2026Member·

  ·
  1

• perf: combine small columnar batches before caching them

  enhancementperformancerun-spark-4.1-tests
  #6988·andygrove opened Oct 14, 2026Member·

  ·
  1

  2

• fix: extract bundled native libraries into private directories

  bug
  #6987·manuzhang opened Oct 14, 2026Member·

  ·
  11

• fix: honor subexpression elimination off in the native null short-circuit

  area:expressionsbug
  #6986·dwsmith1983 opened Oct 14, 2026Contributor·

  ·
  1

  4

• perf: write a cached batch under the chunk size into one chunk of its exact size

  enhancementperformance
  #6985·andygrove opened Oct 14, 2026Member·

  ·
  1

• perf: vectorize int, decimal, float and boolean casts to timestamp

  area:expressionsenhancementperformance
  #6969·Ersa-tech opened Oct 14, 2026·

  ·
  1

• fix: preserve Spark nested null ordering in native sort

  area:expressionsbugrun-spark-4.1-tests
  #6968·Weijun-H opened Oct 14, 2026Member·

  ·
  17

• ci: label Delta pull requests with area:Delta

  area:cibuildenhancement
  #6965·dwsmith1983 opened Oct 14, 2026Contributor·

  ·
  1

  2

• docs: record the plan for each native Iceberg write fallback

  area:Icebergdocumentation
  #6961·andygrove opened Oct 14, 2026Member·

  ·
  1

• perf: reuse validity buffers and use unary kernels in native expressions

  area:expressionsenhancementperformance
  #6953·comphead opened Oct 13, 2026Contributor·

  ·
  7

• docs: run Comet SQL in Kubernetes example

  documentation
  #6949·1cbyc opened Oct 13, 2026·

  ·
  1

  8

• Sequence try grow

  area:expressions
  #6948·nat-openai opened Oct 13, 2026Contributor·

  ·

• ci: purge JAR-less POMs that leave out the packaging element

  area:cibuildenhancement
  #6947·andygrove opened Oct 13, 2026Member·

  ·