github  

Messages by Thread

• • Re: [PR] fix(spark): correct mod ANSI zero divisor and negative zero handling [datafusion] via GitHub
• [PR] chore(deps): bump the all-other-cargo-deps group in /native with 5 updates [datafusion-comet] via GitHub
• [PR] fix: don't report equi-key equivalence for PiecewiseMergeJoin range joins [datafusion] via GitHub
  • Re: [PR] fix: don't report equi-key equivalence for PiecewiseMergeJoin range joins [datafusion] via GitHub
  • Re: [PR] fix: don't report equi-key equivalence for PiecewiseMergeJoin range joins [datafusion] via GitHub
  • Re: [PR] fix: don't report equi-key equivalence for PiecewiseMergeJoin range joins [datafusion] via GitHub
  • Re: [PR] fix: don't report equi-key equivalence for PiecewiseMergeJoin range joins [datafusion] via GitHub
• [I] PiecewiseMergeJoin reports a false equi-key equivalence for INNER range joins, dropping a required sort [datafusion] via GitHub
  • Re: [I] PiecewiseMergeJoin reports a false equi-key equivalence for INNER range joins, dropping a required sort [datafusion] via GitHub
• [PR] fix: guard against silent fail_on_error loss in scalar wiring (#5074) [datafusion-comet] via GitHub
  • Re: [PR] fix: guard against silent fail_on_error loss in scalar wiring (#5074) [datafusion-comet] via GitHub
  • Re: [PR] fix: guard against silent fail_on_error loss in scalar wiring (#5074) [datafusion-comet] via GitHub
  • Re: [PR] fix: guard against silent fail_on_error loss in scalar wiring (#5074) [datafusion-comet] via GitHub
  • Re: [PR] fix: guard against silent fail_on_error loss in scalar wiring (#5074) [datafusion-comet] via GitHub
  • Re: [PR] fix: guard against silent fail_on_error loss in scalar wiring (#5074) [datafusion-comet] via GitHub
  • Re: [PR] fix: guard against silent fail_on_error loss in scalar wiring (#5074) [datafusion-comet] via GitHub
• [PR] fix(parquet): don't runtime-prune row groups while a page-index RowSelection is live (#24355) [datafusion] via GitHub
  • Re: [PR] fix(parquet): don't runtime-prune row groups while a page-index RowSelection is live (#24355) [datafusion] via GitHub
  • Re: [PR] fix(parquet): don't runtime-prune row groups while a page-index RowSelection is live (#24355) [datafusion] via GitHub
  • Re: [PR] fix(parquet): don't runtime-prune row groups while a page-index RowSelection is live (#24355) [datafusion] via GitHub
  • Re: [PR] fix(parquet): don't runtime-prune row groups while a page-index RowSelection is live (#24355) [datafusion] via GitHub
  • Re: [PR] fix(parquet): don't runtime-prune row groups while a page-index RowSelection is live (#24355) [datafusion] via GitHub
  • Re: [PR] fix(parquet): don't runtime-prune row groups while a page-index RowSelection is live (#24355) [datafusion] via GitHub
  • Re: [PR] fix(parquet): don't runtime-prune row groups while a page-index RowSelection is live (#24355) [datafusion] via GitHub
  • Re: [PR] fix(parquet): don't runtime-prune row groups while a page-index RowSelection is live (#24355) [datafusion] via GitHub
  • Re: [PR] fix(parquet): don't runtime-prune row groups while a page-index RowSelection is live (#24355) [datafusion] via GitHub
  • Re: [PR] fix(parquet): don't runtime-prune row groups while a page-index RowSelection is live (#24355) [datafusion] via GitHub
  • Re: [PR] fix(parquet): don't runtime-prune row groups while a page-index RowSelection is live (#24355) [datafusion] via GitHub
  • Re: [PR] fix(parquet): don't runtime-prune row groups while a page-index RowSelection is live (#24355) [datafusion] via GitHub
  • Re: [PR] fix(parquet): don't runtime-prune row groups while a page-index RowSelection is live (#24355) [datafusion] via GitHub
• [PR] chore: drop Spark 3.4 support [datafusion-comet] via GitHub
  • Re: [PR] chore: drop Spark 3.4 support [datafusion-comet] via GitHub
  • Re: [PR] chore: drop Spark 3.4 support [datafusion-comet] via GitHub
• [I] Structurally eliminate rg_plan / RowSelection drift in the parquet runtime prune path (retain_row_groups) [datafusion] via GitHub
  • Re: [I] Structurally eliminate rg_plan / RowSelection drift in the parquet runtime prune path (retain_row_groups) [datafusion] via GitHub
  • Re: [I] Structurally eliminate rg_plan / RowSelection drift in the parquet runtime prune path (retain_row_groups) [datafusion] via GitHub
• [PR] fix: use Spark type names in ANSI abs overflow errors [datafusion-comet] via GitHub
• [PR] fix: Support RANGE window frames over binary ORDER BY keys [datafusion] via GitHub
  • Re: [PR] fix: Support RANGE window frames over binary ORDER BY keys [datafusion] via GitHub
• [I] group uv dependency bumps [datafusion] via GitHub
• [I] Wrong results: dynamic row-group pruning drops row groups without slicing the carried RowSelection [datafusion] via GitHub
  • Re: [I] Wrong results: dynamic row-group pruning drops row groups without slicing the carried RowSelection [datafusion] via GitHub
  • Re: [I] Wrong results: dynamic row-group pruning drops row groups without slicing the carried RowSelection [datafusion] via GitHub
• [PR] Update SQLite expression display expectations [datafusion-testing] via GitHub
• [PR] fix(parquet): sync rg_plan to decoder frontier — fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): sync rg_plan to decoder frontier — fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): sync rg_plan to decoder frontier — fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): sync rg_plan to decoder frontier — fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): sync rg_plan to decoder frontier — fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): sync rg_plan to decoder frontier — fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): sync rg_plan to decoder frontier — fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): sync rg_plan to decoder frontier — fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): sync rg_plan to decoder frontier — fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): sync rg_plan to decoder frontier — fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): sync rg_plan to decoder frontier — fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): sync rg_plan to decoder frontier — fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): sync rg_plan to decoder frontier — fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): sync rg_plan to decoder frontier — fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
• Re: [PR] fix(parquet): skip RowFilter on fully-matched row groups; fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): skip RowFilter on fully-matched row groups; fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): skip RowFilter on fully-matched row groups; fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): skip RowFilter on fully-matched row groups; fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): skip RowFilter on fully-matched row groups; fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): skip RowFilter on fully-matched row groups; fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): skip RowFilter on fully-matched row groups; fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): skip RowFilter on fully-matched row groups; fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): skip RowFilter on fully-matched row groups; fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): skip RowFilter on fully-matched row groups; fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): skip RowFilter on fully-matched row groups; fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
  • Re: [PR] fix(parquet): skip RowFilter on fully-matched row groups; fix wrong TopK results from re-reading already-delivered row groups (#24352) [datafusion] via GitHub
• [PR] fix: flush FilterExec output for unbounded inputs [datafusion] via GitHub
  • Re: [PR] fix: flush FilterExec output for unbounded inputs [datafusion] via GitHub
  • Re: [PR] fix: flush FilterExec output for unbounded inputs [datafusion] via GitHub
  • Re: [PR] fix: flush FilterExec output for unbounded inputs [datafusion] via GitHub
• [I] ANSI `abs` overflow errors use Arrow type names instead of Spark's [datafusion-comet] via GitHub
  • Re: [I] ANSI `abs` overflow errors use Arrow type names instead of Spark's [datafusion-comet] via GitHub
• Re: [PR] PostgreSQL: add support for CREATE TEXT SEARCH CONFIGURATION/DICTIONARY/PARSER/TEMPLATE [datafusion-sqlparser-rs] via GitHub
• Re: [PR] feat: Prune complex/nested predicates via statistics propagation [datafusion] via GitHub
• Re: [PR] fix: rescale decimal results in floor and ceil to scale 0 [datafusion] via GitHub
• Re: [PR] feat: Use NativeType in get_example_type, information schema [datafusion] via GitHub
• Re: [PR] feat(proto): plumb PhysicalProtoConverterExtension into try_encode_expr / try_decode_expr [datafusion] via GitHub
• Re: [PR] feat(physical-plan): add GroupColumn support for FixedSizeList / List / LargeList / Struct in multi-column GROUP BY [datafusion] via GitHub
• Re: [PR] fix: recompute Union schema when field names or types change [datafusion] via GitHub
• Re: [PR] feat: Add max batch size metric to baseline [API Breaking] [datafusion] via GitHub
• [I] Wrong results: TopK dynamic filter + pushdown_filters re-reads already-delivered row groups (duplicate rows displace the true top-k) [datafusion] via GitHub
  • Re: [I] Wrong results: TopK dynamic filter + pushdown_filters re-reads already-delivered row groups (duplicate rows displace the true top-k) [datafusion] via GitHub
  • Re: [I] Wrong results: TopK dynamic filter + pushdown_filters re-reads already-delivered row groups (duplicate rows displace the true top-k) [datafusion] via GitHub
  • Re: [I] Wrong results: TopK dynamic filter + pushdown_filters re-reads already-delivered row groups (duplicate rows displace the true top-k) [datafusion] via GitHub
  • Re: [I] Wrong results: TopK dynamic filter + pushdown_filters re-reads already-delivered row groups (duplicate rows displace the true top-k) [datafusion] via GitHub
  • Re: [I] Wrong results: TopK dynamic filter + pushdown_filters re-reads already-delivered row groups (duplicate rows displace the true top-k) [datafusion] via GitHub
  • Re: [I] Wrong results: TopK dynamic filter + pushdown_filters re-reads already-delivered row groups (duplicate rows displace the true top-k) [datafusion] via GitHub
• [PR] feat(deps): prune unnecessary dependencies [datafusion] via GitHub
  • Re: [PR] feat(deps): prune unnecessary dependencies [datafusion] via GitHub
  • Re: [PR] feat(deps): prune unnecessary dependencies [datafusion] via GitHub
  • Re: [PR] Reduce datafusion-spark dependency footprint [datafusion] via GitHub
  • Re: [PR] Reduce datafusion-spark dependency footprint [datafusion] via GitHub
  • Re: [PR] Reduce datafusion-spark dependency footprint [datafusion] via GitHub
• [PR] fix: preserve inner list field name, nullability and metadata in array_append/array_prepend/array_replace* [datafusion] via GitHub
  • Re: [PR] fix: preserve inner list field name, nullability and metadata in array_append/array_prepend/array_replace* [datafusion] via GitHub
  • Re: [PR] fix: preserve inner list field name, nullability and metadata in array_append/array_prepend/array_replace* [datafusion] via GitHub
• [PR] BigQuery: enable FROM-first SELECT [datafusion-sqlparser-rs] via GitHub
• [I] Investigate: scan + shuffle-write slower than Spark on deeply nested schemas [datafusion-comet] via GitHub
  • Re: [I] Investigate: scan + shuffle-write slower than Spark on deeply nested schemas [datafusion-comet] via GitHub
• [PR] fix: drain all completed batches in classic PiecewiseMergeJoin [datafusion] via GitHub
  • Re: [PR] fix: drain all completed batches in classic PiecewiseMergeJoin [datafusion] via GitHub
  • Re: [PR] fix: drain all completed batches in classic PiecewiseMergeJoin [datafusion] via GitHub
  • Re: [PR] fix: drain all completed batches in classic PiecewiseMergeJoin [datafusion] via GitHub
  • Re: [PR] fix: drain all completed batches in classic PiecewiseMergeJoin [datafusion] via GitHub
  • Re: [PR] fix: drain all completed batches in classic PiecewiseMergeJoin [datafusion] via GitHub
  • Re: [PR] fix: drain all completed batches in classic PiecewiseMergeJoin [datafusion] via GitHub
• [I] PiecewiseMergeJoin drops rows when a stream batch spans multiple output chunks (small batch_size) [datafusion] via GitHub
  • Re: [I] PiecewiseMergeJoin drops rows when a stream batch spans multiple output chunks (small batch_size) [datafusion] via GitHub
  • Re: [I] PiecewiseMergeJoin drops rows when a stream batch spans multiple output chunks (small batch_size) [datafusion] via GitHub
• [I] Run replace natively by default when the search string is a non-empty literal [datafusion-comet] via GitHub
  • Re: [I] Run replace natively by default when the search string is a non-empty literal [datafusion-comet] via GitHub
• [I] Native candidate assessment: upper/lower deferred on the lack of a per-batch defer-to-dispatcher mechanism [datafusion-comet] via GitHub
• [I] Support Apache Celeborn remote shuffle service [datafusion-comet] via GitHub
  • Re: [I] Support Apache Celeborn remote shuffle service [datafusion-comet] via GitHub
  • Re: [I] Support Apache Celeborn remote shuffle service [datafusion-comet] via GitHub
• [I] Run rlike natively by default for patterns that are provably Java-regex equivalent [datafusion-comet] via GitHub
• [I] array_append / array_prepend / array_replace* discard the input list's inner field, contradicting their promised return type [datafusion] via GitHub
  • Re: [I] array_append / array_prepend / array_replace* discard the input list's inner field, contradicting their promised return type [datafusion] via GitHub
  • Re: [I] array_append / array_prepend / array_replace* discard the input list's inner field, contradicting their promised return type [datafusion] via GitHub
• [PR] docs: record native candidate assessments for unbase64 and sequence [datafusion-comet] via GitHub
  • Re: [PR] docs: record native candidate assessments for unbase64 and sequence [datafusion-comet] via GitHub
  • Re: [PR] docs: record native candidate assessments for unbase64 and sequence [datafusion-comet] via GitHub
  • Re: [PR] docs: record native candidate assessments for unbase64 and sequence [datafusion-comet] via GitHub
• [PR] change: fully deprecated the acceptance of value field in VirtualTables [datafusion] via GitHub
  • Re: [PR] change: fully deprecated the acceptance of value field in VirtualTables [datafusion] via GitHub
• [I] Implement sequence natively for integral types instead of JVM codegen dispatch [datafusion-comet] via GitHub
• Re: [PR] fix: avoid extraneous casts for equivalent nested types [datafusion] via GitHub
• [PR] fix: correct list field inner type in array functions [datafusion] via GitHub
  • Re: [PR] fix: correct list field inner type in array functions [datafusion] via GitHub
  • Re: [PR] fix: correct list field inner type in array functions [datafusion] via GitHub
  • Re: [PR] fix: correct list field inner type in array functions [datafusion] via GitHub
  • Re: [PR] fix: correct list field inner type in array functions [datafusion] via GitHub
  • Re: [PR] fix: correct list field inner type in array functions [datafusion] via GitHub
  • Re: [PR] fix: correct list field inner type in array functions [datafusion] via GitHub
  • Re: [PR] fix: correct list field inner type in array functions [datafusion] via GitHub
  • Re: [PR] fix: correct list field inner type in array functions [datafusion] via GitHub
  • Re: [PR] fix: correct list field inner type in array functions [datafusion] via GitHub
• [PR] docs: add suggest-native-expression skill for assessing native expression candidates [datafusion-comet] via GitHub
  • Re: [PR] docs: add suggest-native-expression skill for assessing native expression candidates [datafusion-comet] via GitHub
  • Re: [PR] docs: add suggest-native-expression skill for assessing native expression candidates [datafusion-comet] via GitHub
  • Re: [PR] docs: add suggest-native-expression skill for assessing native expression candidates [datafusion-comet] via GitHub
  • Re: [PR] docs: add suggest-native-expression skill for assessing native expression candidates [datafusion-comet] via GitHub
  • Re: [PR] docs: add suggest-native-expression skill for assessing native expression candidates [datafusion-comet] via GitHub
  • Re: [PR] docs: add suggest-native-expression skill for assessing native expression candidates [datafusion-comet] via GitHub
  • Re: [PR] docs: add suggest-native-expression skill for assessing native expression candidates [datafusion-comet] via GitHub
• [I] Implement unbase64 natively instead of JVM codegen dispatch [datafusion-comet] via GitHub
• [PR] fix: support RANGE window frames with binary ORDER BY (#24327) [datafusion] via GitHub
  • Re: [PR] fix: support RANGE window frames with binary ORDER BY (#24327) [datafusion] via GitHub
  • Re: [PR] fix: support RANGE window frames with binary ORDER BY (#24327) [datafusion] via GitHub
• Re: [PR] fix: preserve global limit for multi-partition fetch [datafusion] via GitHub
  • Re: [PR] fix: preserve global limit for multi-partition fetch [datafusion] via GitHub
  • Re: [PR] fix: preserve global limit for multi-partition fetch [datafusion] via GitHub
• [PR] fix: preserve inner list field name, nullability and metadata in array_slice (#24341) [datafusion] via GitHub
  • Re: [PR] fix: preserve inner list field name, nullability and metadata in array_slice (#24341) [datafusion] via GitHub
  • Re: [PR] fix: preserve inner list field name, nullability and metadata in array_slice (#24341) [datafusion] via GitHub
  • Re: [PR] fix: preserve inner list field name, nullability and metadata in array_slice (#24341) [datafusion] via GitHub
• [I] Tag fallback reasons with structured values instead of pre-formatted strings [datafusion-comet] via GitHub
  • Re: [I] Tag fallback reasons with structured values instead of pre-formatted strings [datafusion-comet] via GitHub
• [I] array_slice discards the input list's inner field (name, nullability, metadata), contradicting its promised return type [datafusion] via GitHub
  • Re: [I] array_slice discards the input list's inner field (name, nullability, metadata), contradicting its promised return type [datafusion] via GitHub
  • Re: [I] array_slice discards the input list's inner field (name, nullability, metadata), contradicting its promised return type [datafusion] via GitHub
  • Re: [I] array_slice discards the input list's inner field (name, nullability, metadata), contradicting its promised return type [datafusion] via GitHub
• [PR] bench(functions): group the 63 bench targets into 9 [datafusion] via GitHub
  • Re: [PR] bench(functions): group the 63 bench targets into 9 [datafusion] via GitHub
• [PR] feat: Add trail mode config for Comet evaluation without native execution [datafusion-comet] via GitHub
  • Re: [PR] feat: Add trail mode config for Comet evaluation without native execution [datafusion-comet] via GitHub
• [PR] Review follow-ups for the DataFusion 55 upgrade [datafusion-ballista] via GitHub
  • Re: [PR] Review follow-ups for the DataFusion 55 upgrade [datafusion-ballista] via GitHub
• [PR] fix: support binary ORDER BY keys in RANGE window frames [datafusion] via GitHub
  • Re: [PR] fix: support binary ORDER BY keys in RANGE window frames [datafusion] via GitHub
  • Re: [PR] fix: support binary ORDER BY keys in RANGE window frames [datafusion] via GitHub
• [PR] build: don't build the doc-generator binaries by default [datafusion] via GitHub
  • Re: [PR] perf(build): don't build the doc-generator binaries by default [datafusion] via GitHub
  • Re: [PR] perf(build): don't build the doc-generator binaries by default [datafusion] via GitHub
• [PR] build: use line-tables-only debug info in the `dev` profile [datafusion] via GitHub
  • Re: [PR] perf(build): use line-tables-only debug info in the `dev` profile [datafusion] via GitHub
  • Re: [PR] perf(build): use line-tables-only debug info in the `dev` profile [datafusion] via GitHub
  • Re: [PR] perf(build): use line-tables-only debug info in the `dev` profile [datafusion] via GitHub
• [I] Support column reference as percentile arg for `percentile_cont` and `approx_percentile_cont` [datafusion] via GitHub
  • Re: [I] Support column reference as percentile arg for `percentile_cont` and `approx_percentile_cont` [datafusion] via GitHub
• [PR] fix: emit unmatched NULL-key right rows in RIGHT/FULL PiecewiseMergeJoin [datafusion] via GitHub
  • Re: [PR] fix: emit unmatched NULL-key right rows in RIGHT/FULL PiecewiseMergeJoin [datafusion] via GitHub
  • Re: [PR] fix: emit unmatched NULL-key right rows in RIGHT/FULL PiecewiseMergeJoin [datafusion] via GitHub
  • Re: [PR] fix: emit unmatched NULL-key right rows in RIGHT/FULL PiecewiseMergeJoin [datafusion] via GitHub
  • Re: [PR] fix: emit unmatched NULL-key right rows in RIGHT/FULL PiecewiseMergeJoin [datafusion] via GitHub
  • Re: [PR] fix: emit unmatched NULL-key right rows in RIGHT/FULL PiecewiseMergeJoin [datafusion] via GitHub
  • Re: [PR] fix: emit unmatched NULL-key right rows in RIGHT/FULL PiecewiseMergeJoin [datafusion] via GitHub
  • Re: [PR] fix: emit unmatched NULL-key right rows in RIGHT/FULL PiecewiseMergeJoin [datafusion] via GitHub
• Re: [PR] chore(deps): Track DataFusion git, pinned to the 55.0.0-rc2 tag [datafusion-ballista] via GitHub
  • Re: [PR] chore(deps): Track DataFusion git, pinned to the 55.0.0-rc2 tag [datafusion-ballista] via GitHub
  • Re: [PR] chore(deps): Track DataFusion git, pinned to the 55.0.0-rc2 tag [datafusion-ballista] via GitHub
  • Re: [PR] chore(deps): Track DataFusion git, pinned to the 55.0.0-rc2 tag [datafusion-ballista] via GitHub
  • Re: [PR] chore(deps): Track DataFusion git, pinned to the 55.0.0-rc2 tag [datafusion-ballista] via GitHub
• [I] PiecewiseMergeJoin drops unmatched NULL-key right rows in RIGHT/FULL joins [datafusion] via GitHub
  • Re: [I] PiecewiseMergeJoin drops unmatched NULL-key right rows in RIGHT/FULL joins [datafusion] via GitHub
• [PR] feat: Add robots.txt and License file [datafusion] via GitHub

• Earlier messages
• Later messages