github  

Messages by Thread

• [PR] test: More `slt` tests for `iszero` function [datafusion] via GitHub
• [PR] refactor(proto): migrate sort merge join serde [datafusion] via GitHub
  • Re: [PR] refactor(proto): migrate sort merge join serde [datafusion] via GitHub
• Re: [I] Correlated EXISTS with constant-false predicate produces dangling mark column reference [datafusion] via GitHub
• Re: [I] The negation operator escapes type checking at logical planning phase [datafusion] via GitHub
• Re: [I] Scalar subquery (`Expr::ScalarSubquery`) does not fail when subquery is not scalar [datafusion] via GitHub
• Re: [I] panic: date_bin overflows scaling extreme Time64(Microsecond) origin [datafusion] via GitHub
• [PR] perf: optimize LEAD/LAG IGNORE NULLS evaluation [datafusion] via GitHub
  • Re: [PR] perf: optimize LEAD/LAG IGNORE NULLS evaluation [datafusion] via GitHub
• Re: [I] panic: array_repeat list path overflows inner element count multiplication [datafusion] via GitHub
• [PR] refactor(proto): migrate single-child plans [datafusion] via GitHub
  • Re: [PR] refactor(proto): migrate single-child plans [datafusion] via GitHub
  • Re: [PR] refactor(proto): migrate single-child plans [datafusion] via GitHub
• [I] regex_match_dyn (array-array path) does not support Dictionary-encoded needle arrays (SIMILAR TO / ~ operators) [datafusion] via GitHub
• [PR] chore(deps): bump async-trait from 0.1.89 to 0.1.91 [datafusion-ballista] via GitHub
• [PR] chore(deps): bump futures from 0.3.32 to 0.3.33 [datafusion-ballista] via GitHub
• [PR] chore(ci): bump actions/setup-python from 6 to 7 [datafusion-ballista] via GitHub
• [PR] chore(ci): bump taiki-e/install-action from 2.83.3 to 2.83.4 [datafusion-ballista] via GitHub
• [PR] chore(deps): bump serde from 1.0.228 to 1.0.229 [datafusion-ballista] via GitHub
• Re: [I] Preserve CSE for expensive expressions when pushing projections into file scans [datafusion] via GitHub
• [PR] refactor(proto): migrate FilterExec serde [datafusion] via GitHub
  • Re: [PR] refactor(proto): migrate FilterExec serde [datafusion] via GitHub
  • Re: [PR] refactor(proto): migrate FilterExec serde [datafusion] via GitHub
• Re: [I] Grouped first_value/last_value FILTER Incorrectly Includes NULL Predicate Rows [datafusion] via GitHub
• [PR] fix: grouped first_value/last_value FILTER excludes NULL predicate rows [datafusion] via GitHub
  • Re: [PR] fix: grouped first_value/last_value FILTER excludes NULL predicate rows [datafusion] via GitHub
• [PR] fix: prevent LEAD/LAG IGNORE NULLS panic without null bitmap [datafusion] via GitHub
  • Re: [PR] fix: prevent LEAD/LAG IGNORE NULLS panic without null bitmap [datafusion] via GitHub
  • Re: [PR] fix: prevent LEAD/LAG IGNORE NULLS panic without null bitmap [datafusion] via GitHub
• [I] LEAD/LAG IGNORE NULLS panics without a null bitmap [datafusion] via GitHub
  • Re: [I] LEAD/LAG IGNORE NULLS panics without a null bitmap [datafusion] via GitHub
• Re: [PR] feat: TopK stats init + cumulative RG pruning for pure-TopK parquet scans (no-WHERE) [datafusion] via GitHub
• Re: [PR] [PoC] perf: optimize group-only group-by case for primitive cases (clickbench q4) [datafusion] via GitHub
• Re: [I] SIMILAR TO panics ('failed to downcast array') when operand types differ (e.g. NULL pattern, Utf8View vs Utf8) [datafusion] via GitHub
• Re: [PR] feat: add `poll_now_notify` to `poll_loop` and `on_work_available` callback [datafusion-ballista] via GitHub
  • Re: [PR] feat: add `poll_now_notify` to `poll_loop` and `on_work_available` callback [datafusion-ballista] via GitHub
  • Re: [PR] feat: add `poll_now_notify` to `poll_loop` and `on_work_available` callback [datafusion-ballista] via GitHub
  • Re: [PR] feat: add `poll_now_notify` to `poll_loop` and `on_work_available` callback [datafusion-ballista] via GitHub
  • Re: [PR] feat: add `poll_now_notify` to `poll_loop` and `on_work_available` callback [datafusion-ballista] via GitHub
  • Re: [PR] feat: add `poll_now_notify` to `poll_loop` and `on_work_available` callback [datafusion-ballista] via GitHub
  • Re: [PR] feat: add `poll_now_notify` to `poll_loop` and `on_work_available` callback [datafusion-ballista] via GitHub
• Re: [PR] feat: add a broadcast channel for job state event notifications [datafusion-ballista] via GitHub
  • Re: [PR] feat: add a broadcast channel for job state event notifications [datafusion-ballista] via GitHub
• [PR] feat(core): BufferExec — generic flow-control op with a memory-pool Dam mode [datafusion-ballista] via GitHub
  • Re: [PR] feat(core): BufferExec — generic flow-control op with a memory-pool Dam mode [datafusion-ballista] via GitHub
  • Re: [PR] feat(core): BufferExec — generic flow-control op with a memory-pool Dam mode [datafusion-ballista] via GitHub
• [PR] fix: tighten scalar UDF return type hints [datafusion-python] via GitHub
• [PR] feat(core): RuntimeStatsExec — passthrough tap for row counts + quantile sketches [datafusion-ballista] via GitHub
  • Re: [PR] feat(core): RuntimeStatsExec — passthrough tap for row counts + quantile sketches [datafusion-ballista] via GitHub
  • Re: [PR] feat(core): RuntimeStatsExec — passthrough tap for row counts + quantile sketches [datafusion-ballista] via GitHub
• [PR] docs(config): rewrite max_partitions_per_task description to be timeless [datafusion-ballista] via GitHub
  • Re: [PR] docs(config): rewrite max_partitions_per_task description to be timeless [datafusion-ballista] via GitHub
• [PR] fix: Make FilePruner work with constant columns [datafusion] via GitHub
  • Re: [PR] fix: Make FilePruner work with constant columns [datafusion] via GitHub
  • Re: [PR] fix: Make FilePruner work with constant columns [datafusion] via GitHub
  • Re: [PR] fix: Make FilePruner work with constant columns [datafusion] via GitHub
  • Re: [PR] fix: Make FilePruner work with constant columns [datafusion] via GitHub
  • Re: [PR] fix: Make FilePruner work with constant columns [datafusion] via GitHub
  • Re: [PR] fix: Make FilePruner work with constant columns [datafusion] via GitHub
• [PR] refactor: move catalog traits to session crate [datafusion] via GitHub
  • Re: [PR] refactor: move catalog traits to session crate [datafusion] via GitHub
  • Re: [PR] refactor: move catalog traits to session crate [datafusion] via GitHub
• [PR] build(deps): bump github/codeql-action/analyze from 4.36.2 to 4.37.1 [datafusion-python] via GitHub
• [PR] build(deps): bump github/codeql-action/init from 4.36.2 to 4.37.1 [datafusion-python] via GitHub
• [PR] feat: native RANGE window frames with explicit offset on DATE ORDER BY [datafusion-comet] via GitHub
• Re: [PR] Improvement: keep order-preserving repartitions for streaming aggregates [datafusion] via GitHub
• [PR] chore: simplify SortPreservingMergeStream to be as textbook-like as possible [datafusion] via GitHub
  • Re: [PR] chore: simplify SortPreservingMergeStream to be as textbook-like as possible [datafusion] via GitHub
  • Re: [PR] chore: simplify SortPreservingMergeStream to be as textbook-like as possible [datafusion] via GitHub
• Re: [I] [EPIC]: Make `PiecewiseMergeJoin` work in Datafusion [datafusion] via GitHub
  • Re: [I] [EPIC]: Make `PiecewiseMergeJoin` work in Datafusion [datafusion] via GitHub
• [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
  • Re: [PR] WIP: rebase #22384 + tactical split-membership fix for HashJoin dynamic filter [datafusion] via GitHub
• [I] Move lambda evaluation into Physical Planning Context [datafusion] via GitHub
• [PR] perf: passthrough last stream is `SortPreservingMergeStream` [datafusion] via GitHub
• [PR] fix: track the time takes to init loser tree and build last in progress batches [datafusion] via GitHub
  • Re: [PR] fix: track the time takes to init loser tree and build last in progress batches [datafusion] via GitHub
• [I] non-deterministic roundtripping through sessionstatebuilder [datafusion] via GitHub
• [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
  • Re: [PR] perf(parquet): skip RowFilter on statically fully-matched row groups [datafusion] via GitHub
• Re: [PR] perf: fast path for date_part('minute', Timestamp(Second)) [datafusion] via GitHub
• Re: [PR] Implement eager aggregation [datafusion] via GitHub
• Re: [PR] POC: Window function intra-operator parallelism and vectorization (up to 50× faster) [datafusion] via GitHub
• Re: [PR] Js/cherry pick dynamic filter pushdown through aggregations [datafusion] via GitHub
• Re: [PR] feat: DuckDB-compatible glob expressions in listing-table paths (filesystem + s3/gs/http URLs) [datafusion] via GitHub
• [PR] Aggregate byte types internally with i64 offsets [datafusion] via GitHub
  • Re: [PR] Aggregate byte types internally with i64 offsets [datafusion] via GitHub
• [I] Grouping operations on large datasets can overflow i32 offsets [datafusion] via GitHub
• [I] [EPIC] Enable Adaptive Query Execution (AQE) by default [datafusion-ballista] via GitHub
• Re: [PR] Share per-chunk JoinLeftData across right partitions in NLJ memory-limited fallback [datafusion] via GitHub
  • Re: [PR] Share per-chunk JoinLeftData across right partitions in NLJ memory-limited fallback [datafusion] via GitHub
  • Re: [PR] Share per-chunk JoinLeftData across right partitions in NLJ memory-limited fallback [datafusion] via GitHub
• Re: [I] Support more types for `approx_distinct` function [datafusion] via GitHub
  • Re: [I] Support more types for `approx_distinct` function [datafusion] via GitHub
  • Re: [I] Support more types for `approx_distinct` function [datafusion] via GitHub
• [PR] feat: improve sort shuffle write and spill INFO logging [datafusion-ballista] via GitHub
  • Re: [PR] feat: improve sort shuffle write and spill INFO logging [datafusion-ballista] via GitHub
  • Re: [PR] feat: improve sort shuffle write and spill INFO logging [datafusion-ballista] via GitHub
  • Re: [PR] feat: log sort shuffle spills at WARN, keep write completion at DEBUG [datafusion-ballista] via GitHub
  • Re: [PR] feat: log sort shuffle spills at WARN, keep write completion at DEBUG [datafusion-ballista] via GitHub
• [PR] build(deps): bump tokio from 1.52.3 to 1.53.0 [datafusion-python] via GitHub
• [PR] build(deps): bump uuid from 1.23.3 to 1.24.0 [datafusion-python] via GitHub
• Re: [PR] build(deps): bump uuid from 1.23.3 to 1.23.4 [datafusion-python] via GitHub
  • Re: [PR] build(deps): bump uuid from 1.23.3 to 1.23.4 [datafusion-python] via GitHub
• [PR] chore: bump `object_store` to `0.14.1` [datafusion] via GitHub
  • Re: [PR] chore: bump `object_store` to `0.14.1` [datafusion] via GitHub
• [PR] fix: propagate sort shuffle memory_limit_per_task_bytes to executors [datafusion-ballista] via GitHub
  • Re: [PR] fix: propagate sort shuffle memory_limit_per_task_bytes to executors [datafusion-ballista] via GitHub
  • Re: [PR] fix: propagate sort shuffle memory_limit_per_task_bytes to executors [datafusion-ballista] via GitHub
• [I] Sort shuffle writer's memory_limit_per_task_bytes config is not propagated to executors [datafusion-ballista] via GitHub
  • Re: [I] Sort shuffle writer's memory_limit_per_task_bytes config is not propagated to executors [datafusion-ballista] via GitHub
• [I] type_coercion error: multi-condition IS NOT DISTINCT FROM in JOIN ON clause fails [datafusion] via GitHub
  • Re: [I] type_coercion error: multi-condition IS NOT DISTINCT FROM in JOIN ON clause fails [datafusion] via GitHub
  • Re: [I] type_coercion error: multi-condition IS NOT DISTINCT FROM in JOIN ON clause fails [datafusion] via GitHub
• [PR] fix: evaluate struct-returning UDFs once across repeated field accesses [datafusion] via GitHub
• Re: [PR] fix: NOT IN with NULL subquery returns wrong results under SortMergeJoin [datafusion] via GitHub
• Re: [PR] bench: parquet scan with a table schema narrower than a nested column [datafusion] via GitHub
  • Re: [PR] bench: parquet scan with a table schema narrower than a nested column [datafusion] via GitHub
• Re: [PR] fix: avoid panic in array_position start_from near i64::MIN [datafusion] via GitHub
• Re: [I] Add `any_value` aggregate function [datafusion] via GitHub
• [PR] perf(coalesce): make BatchCoalescer bypass threshold configurable (SIGMOD 2025 Binary Compaction) [datafusion] via GitHub
  • Re: [PR] perf(coalesce): make BatchCoalescer bypass threshold configurable (SIGMOD 2025 Binary Compaction) [datafusion] via GitHub
  • Re: [PR] perf(coalesce): make BatchCoalescer bypass threshold configurable (SIGMOD 2025 Binary Compaction) [datafusion] via GitHub
  • Re: [PR] perf(coalesce): make BatchCoalescer bypass threshold configurable (SIGMOD 2025 Binary Compaction) [datafusion] via GitHub
  • Re: [PR] perf(coalesce): make BatchCoalescer bypass threshold configurable (SIGMOD 2025 Binary Compaction) [datafusion] via GitHub
  • Re: [PR] experiment perf(coalesce): make BatchCoalescer bypass threshold configurable (SIGMOD 2025 Binary Compaction) [datafusion] via GitHub
  • Re: [PR] experiment perf(coalesce): make BatchCoalescer bypass threshold configurable (SIGMOD 2025 Binary Compaction) [datafusion] via GitHub
  • Re: [PR] experiment perf(coalesce): make BatchCoalescer bypass threshold configurable (SIGMOD 2025 Binary Compaction) [datafusion] via GitHub
  • Re: [PR] experiment perf(coalesce): make BatchCoalescer bypass threshold configurable (SIGMOD 2025 Binary Compaction) [datafusion] via GitHub
  • Re: [PR] experiment perf(coalesce): make BatchCoalescer bypass threshold configurable (SIGMOD 2025 Binary Compaction) [datafusion] via GitHub
  • Re: [PR] experiment perf(coalesce): make BatchCoalescer bypass threshold configurable (SIGMOD 2025 Binary Compaction) [datafusion] via GitHub
• [PR] [branch-54] chore: Update version 54.1.0, add changelog [datafusion] via GitHub
  • Re: [PR] [branch-54] chore: Update version 54.1.0, add changelog [datafusion] via GitHub
• [PR] Optimize Spark hex null handling [datafusion] via GitHub
  • Re: [PR] Optimize Spark hex null handling [datafusion] via GitHub
• [PR] feat(agg): TopK aggregation for count(*)/count(col) DESC/ASC LIMIT K [datafusion] via GitHub
  • Re: [PR] feat(agg): TopK aggregation for count(*)/count(col) DESC/ASC LIMIT K [datafusion] via GitHub
  • Re: [PR] feat(agg): TopK aggregation for count(*)/count(col) DESC/ASC LIMIT K [datafusion] via GitHub
  • Re: [PR] feat(agg): TopK aggregation for count(*)/count(col) DESC/ASC LIMIT K [datafusion] via GitHub
  • Re: [PR] feat(agg): TopK aggregation for count(*)/count(col) DESC/ASC LIMIT K [datafusion] via GitHub
  • Re: [PR] feat(agg): TopK aggregation for count(*)/count(col) DESC/ASC LIMIT K [datafusion] via GitHub
  • Re: [PR] feat(agg): TopK aggregation for count(*)/count(col) DESC/ASC LIMIT K [datafusion] via GitHub
  • Re: [PR] feat(agg): TopK aggregation for count(*)/count(col) DESC/ASC LIMIT K [datafusion] via GitHub
  • Re: [PR] feat(agg): TopK aggregation for count(*)/count(col) DESC/ASC LIMIT K [datafusion] via GitHub
  • Re: [PR] experiment feat(agg): TopK aggregation for count(*)/count(col) DESC/ASC LIMIT K [datafusion] via GitHub
  • Re: [PR] experiment feat(agg): TopK aggregation for count(*)/count(col) DESC/ASC LIMIT K [datafusion] via GitHub
  • Re: [PR] experiment feat(agg): TopK aggregation for count(*)/count(col) DESC/ASC LIMIT K [datafusion] via GitHub
  • Re: [PR] experiment feat(agg): TopK aggregation for count(*)/count(col) DESC/ASC LIMIT K [datafusion] via GitHub
  • Re: [PR] experiment feat(agg): TopK aggregation for count(*)/count(col) DESC/ASC LIMIT K [datafusion] via GitHub
  • Re: [PR] experiment feat(agg): TopK aggregation for count(*)/count(col) DESC/ASC LIMIT K [datafusion] via GitHub
• [PR] Add schema-aware optimizer child rewrites [datafusion] via GitHub
• [PR] Document decimal AVG wrapping arithmetic [datafusion] via GitHub
• Re: [I] DataFusion drops grouped MIN/MAX rows with NULL sort keys under ORDER BY + LIMIT [datafusion] via GitHub
• [PR] fix: TopK aggregation drops groups whose MIN/MAX value is NULL [datafusion] via GitHub
• [PR] Add DataSource/FileSource proto hooks and FileScanConfig serde [datafusion] via GitHub
  • Re: [PR] Add DataSource/FileSource proto hooks and FileScanConfig serde [datafusion] via GitHub
  • Re: [PR] Add DataSource/FileSource proto hooks and FileScanConfig serde [datafusion] via GitHub

• Earlier messages