Messages by Thread
-
-
[PR] bench: add dictionary decode coverage [datafusion]
Rich-T-kid (via GitHub) via github
-
[PR] bench: add dictionary replace coverage [datafusion]
Rich-T-kid (via GitHub) via github
-
Re: [I] `GetArrayItem` fails on a non-INT index: `could not cast array of type Int64 ...` [datafusion-comet]
andygrove (via GitHub) via github
-
Re: [PR] fix: cast a non-INT `GetArrayItem` index to INT like Spark [datafusion-comet]
andygrove (via GitHub) via github
-
Re: [PR] refactor: deduplicate spark_ceil and spark_floor [datafusion-comet]
andygrove (via GitHub) via github
-
Re: [I] Deduplicate spark_ceil and spark_floor and port floor's decimal boundary tests to ceil [datafusion-comet]
andygrove (via GitHub) via github
-
Re: [PR] fix(scheduler): report the final stage's schema for adaptive Flight SQL jobs [datafusion-ballista]
andygrove (via GitHub) via github
-
Re: [I] Add `ballista.execution.mode=auto` with a pluggable strategy for choosing `pipelined` or `staged` execution [datafusion-ballista]
villebro (via GitHub) via github
-
[PR] build(deps): bump prost-types from 0.14.4 to 0.14.5 [datafusion-python]
dependabot[bot] (via GitHub) via github
-
Re: [PR] feat(aqe): log which rules change a job's plan, and why they skip [datafusion-ballista]
comphead (via GitHub) via github
-
[PR] build(deps): bump prost from 0.14.4 to 0.14.5 [datafusion-python]
dependabot[bot] (via GitHub) via github
-
Re: [PR] docs: check all contributor guides in the pr-review skill [datafusion-ballista]
andygrove (via GitHub) via github
-
[I] A UNION over a custom data source fails when its stage is split between tasks [datafusion-ballista]
NoahKusaba (via GitHub) via github
-
[I] Adaptive planner: an outer join with an empty side never finishes [datafusion-ballista]
NoahKusaba (via GitHub) via github
-
[PR] Fix window output ordering inference and remove redundant sorts [datafusion]
blaginin (via GitHub) via github
-
Re: [I] Deduplicate execute_query_pull and execute_query_push in DistributedQueryExec [datafusion-ballista]
marvelefe (via GitHub) via github
-
Re: [I] Columnar shuffle rejects range partitioning based on a native-serde check it never uses [datafusion-comet]
andygrove (via GitHub) via github
-
[PR] docs(spark): generate function reference from #[user_doc] [datafusion-spark]
andygrove (via GitHub) via github
-
[PR] fix: mark the commit-message output of Iceberg write nodes as produced [datafusion-comet]
Visorgood (via GitHub) via github
-
[PR] test: check that a bucketed native scan keeps its partitioning [datafusion-comet]
dwsmith1983 (via GitHub) via github
-
Re: [PR] chore: drop Spark 3.4 support [datafusion-comet]
manuzhang (via GitHub) via github
-
[PR] chore: remove remaining Spark 3.4 compatibility code [datafusion-comet]
manuzhang (via GitHub) via github
-
[PR] fix: [branch-1.1] do not resolve DPP subqueries when AQE reads a native scan's partitioning (#6268) [datafusion-comet]
dwsmith1983 (via GitHub) via github
-
[PR] fix: [branch-1.1] keep partition columns in an empty bucket's native scan schema [datafusion-comet]
dwsmith1983 (via GitHub) via github
-
[PR] update devtools [datafusion]
blaginin (via GitHub) via github
-
[PR] feat: fit CLI output to terminal width [datafusion]
blaginin (via GitHub) via github
-
Re: [PR] feat(history): replace the timer-based rescan with a filesystem watch [datafusion-ballista]
milenkovicm (via GitHub) via github
-
[I] `IcebergWriteExec` and `CometIcebergWriteExec` are marked with `!` (missing input) in EXPLAIN [datafusion-comet]
Visorgood (via GitHub) via github
-
Re: [I] Internal error: CAST to an extension-type field over a non-null column, under an aggregate (logical vs physical nullability) [datafusion]
CuteChuanChuan (via GitHub) via github
-
[PR] fix: return an error from the window constructors when there are no window expressions [datafusion]
abp002 (via GitHub) via github
-
Re: [PR] fix: choose the forced shuffled hash join at planning time so Spark keeps its sorts [datafusion-comet]
dwsmith1983 (via GitHub) via github
-
[PR] DRAFT Bench 26609 [datafusion]
kosiew (via GitHub) via github
-
[PR] feat: let CASE reuse the first WHEN operand in ELSE [datafusion]
Pastoray (via GitHub) via github
-
Re: [PR] feat: support Spark 4.2 insert-only MERGE [datafusion-comet]
Visorgood (via GitHub) via github
-
Re: [PR] docs: add nuthatch to known users [datafusion]
cargopete (via GitHub) via github
-
[PR] fix: tighten integer division intervals when a divisor endpoint is zero [datafusion]
Amogh-2404 (via GitHub) via github
-
[PR] Fix/json map null values [datafusion]
Pastoray (via GitHub) via github
-
[PR] fix: carry input requirements across FFI_ExecutionPlan [datafusion]
andygrove (via GitHub) via github
-
Re: [PR] fix: error instead of dropping a pulled up HAVING in scalar subqueries whose result is NULL on empty input [datafusion]
abp002 (via GitHub) via github
-
Re: [I] Enable the split-operator plan and native Iceberg writes by default [datafusion-comet]
Visorgood (via GitHub) via github
-
[I] SQL unparser emits empty filtered-count SELECT lists and out-of-scope qualifiers for filtered LIMIT [datafusion]
geoHeil (via GitHub) via github
-
[I] cargo audit failing on main [datafusion]
alamb (via GitHub) via github
-
Re: [I] Enable TopK per Partition (`datafusion.optimizer.enable_window_topn`) by default [datafusion]
alamb (via GitHub) via github
-
[I] Add an `EXPLAIN` option that shows each physical plan node's orderings, equal expressions and constants [datafusion]
jayzhan211 (via GitHub) via github
-
Re: [I] Add an `EXPLAIN` option that shows each physical plan node's orderings, equal expressions and constants [datafusion]
jayzhan211 (via GitHub) via github
-
Re: [I] Add an `EXPLAIN` option that shows each physical plan node's orderings, equal expressions and constants [datafusion]
alamb (via GitHub) via github
-
Re: [I] Add an `EXPLAIN` option that shows each physical plan node's orderings, equal expressions and constants [datafusion]
jayzhan211 (via GitHub) via github
-
Re: [I] Add an `EXPLAIN` option that shows each physical plan node's orderings, equal expressions and constants [datafusion]
marvelefe (via GitHub) via github
-
Re: [I] Add an `EXPLAIN` option that shows each physical plan node's orderings, equal expressions and constants [datafusion]
marvelefe (via GitHub) via github
-
Re: [I] Add an `EXPLAIN` option that shows each physical plan node's orderings, equal expressions and constants [datafusion]
jayzhan211 (via GitHub) via github
-
Re: [I] Add an `EXPLAIN` option that shows each physical plan node's orderings, equal expressions and constants [datafusion]
jayzhan211 (via GitHub) via github
-
Re: [I] Add an `EXPLAIN` option that shows each physical plan node's orderings, equal expressions and constants [datafusion]
marvelefe (via GitHub) via github
-
Re: [I] Add an `EXPLAIN` option that shows each physical plan node's orderings, equal expressions and constants [datafusion]
marvelefe (via GitHub) via github
-
Re: [I] Add an `EXPLAIN` option that shows each physical plan node's orderings, equal expressions and constants [datafusion]
NGA-TRAN (via GitHub) via github
-
[PR] PostgreSQL: Support subscripts in assignment and insert targets [datafusion-sqlparser-rs]
LucaCappelletti94 (via GitHub) via github
-
[PR] fix: TopK aggregation now uses indices instead of column names for computed projections [datafusion]
vikrantmehta123 (via GitHub) via github
-
[PR] fix: update tpchgen-cli commands for v4 [datafusion]
AnuragRaut08 (via GitHub) via github
-
Re: [PR] Upgrade DataFusion to version 56 [datafusion-python]
andygrove (via GitHub) via github
-
[PR] docs: explain both execution modes in the README introduction [datafusion-ballista]
andygrove (via GitHub) via github
-
[I] Comet Native Executors: raise Spark's exceptions for cluster failures [datafusion-comet]
andygrove (via GitHub) via github
-
Re: [PR] feat: add the Comet Native Executors driver (experimental) [datafusion-comet]
andygrove (via GitHub) via github
-
[PR] ci: use tpchgen-cli 4.x parquet subcommand [datafusion-python]
andygrove (via GitHub) via github
-
[PR] docs: add release process documentation and release scripts [datafusion-spark]
andygrove (via GitHub) via github
-
[I] FFI_ExecutionPlan loses input distribution and ordering requirements, so optimizer rules across FFI produce invalid plans [datafusion]
andygrove (via GitHub) via github
-
Re: [I] TopK aggregation keeps the wrong groups when a computed column reuses the aggregate's name [datafusion]
vikrantmehta123 (via GitHub) via github
-
Re: [PR] chore: comet-native integration branch (testing with Comet native executors) [datafusion-ballista]
andygrove (via GitHub) via github
-
Re: [PR] fix(scheduler): set TCP keepalive on scheduler gRPC connections [datafusion-ballista]
andygrove (via GitHub) via github
-
Re: [I] The scheduler's gRPC listener sets no TCP keepalive (axum path) [datafusion-ballista]
andygrove (via GitHub) via github
-
Re: [PR] feat: let hash shuffles place rows by a client-computed partition id [datafusion-ballista]
andygrove (via GitHub) via github
-
Re: [I] Let hash shuffles assign rows to partitions with a client's own hash function [datafusion-ballista]
andygrove (via GitHub) via github
-
Re: [PR] feat: support map inputs for explode [datafusion-comet]
rich7420 (via GitHub) via github
-
[PR] docs: prepare the documentation for the 56.0.0 release [datafusion-ballista]
andygrove (via GitHub) via github
-
[I] Comparing or adding an integer to a Decimal32/Decimal64 value casts the decimal to Int64 and drops its fraction [datafusion]
jayzhan211 (via GitHub) via github
-
Re: [PR] feat: re-land Decimal filter selectivity, and use the default selectivity for columns without known bounds [datafusion]
jayzhan211 (via GitHub) via github
-
Re: [PR] feat: re-land Decimal filter selectivity, and use the default selectivity for columns without known bounds [datafusion]
jayzhan211 (via GitHub) via github
-
Re: [PR] feat: re-land Decimal filter selectivity, and use the default selectivity for columns without known bounds [datafusion]
adriangbot (via GitHub) via github
-
Re: [PR] feat: re-land Decimal filter selectivity, and use the default selectivity for columns without known bounds [datafusion]
adriangbot (via GitHub) via github
-
Re: [PR] feat: re-land Decimal filter selectivity, and use the default selectivity for columns without known bounds [datafusion]
adriangbot (via GitHub) via github
-
Re: [PR] feat: re-land Decimal filter selectivity, and use the default selectivity for columns without known bounds [datafusion]
adriangbot (via GitHub) via github
-
Re: [PR] feat: re-land Decimal filter selectivity, and use the default selectivity for columns without known bounds [datafusion]
adriangbot (via GitHub) via github
-
Re: [PR] feat: re-land Decimal filter selectivity, and use the default selectivity for columns without known bounds [datafusion]
adriangbot (via GitHub) via github
-
Re: [PR] feat: re-land Decimal filter selectivity, and use the default selectivity for columns without known bounds [datafusion]
adriangbot (via GitHub) via github
-
Re: [PR] feat: re-land Decimal filter selectivity, and use the default selectivity for columns without known bounds [datafusion]
adriangbot (via GitHub) via github
-
Re: [PR] feat: re-land Decimal filter selectivity, and use the default selectivity for columns without known bounds [datafusion]
adriangbot (via GitHub) via github
-
Re: [PR] feat: re-land Decimal filter selectivity, and use the default selectivity for columns without known bounds [datafusion]
adriangbot (via GitHub) via github
-
Re: [PR] feat: re-land Decimal filter selectivity, and use the default selectivity for columns without known bounds [datafusion]
jayzhan211 (via GitHub) via github
-
Re: [PR] feat: re-land Decimal filter selectivity, and use the default selectivity for columns without known bounds [datafusion]
shrivasshankar (via GitHub) via github
-
[PR] feat: add a typed SessionConfigExt setter and getter for the execution mode [datafusion-ballista]
vikrantmehta123 (via GitHub) via github
-
Re: [I] Incorrect join ordering properties can cause required sorts to be removed [datafusion]
jayzhan211 (via GitHub) via github
-
Re: [I] Plain `SELECT` of a Parquet float column returns wrong values: NaN rows are replaced by the statistics constant when min == max [datafusion]
jensholdgaard (via GitHub) via github
-
Re: [I] Wrong results: `ORDER BY ... NULLS LAST` on a running `MAX` window function puts the NULL row first [datafusion]
jayzhan211 (via GitHub) via github
-
[PR] fix: compare expression attributes in equivalence checks [datafusion]
rgbuilds (via GitHub) via github
-
[I] Wrong results: `ORDER BY` on `MAX`/`MIN` over a sliding window frame is skipped [datafusion]
jayzhan211 (via GitHub) via github
-
[PR] fix: restore Bloom pruning for nullable dictionary schemas [datafusion]
fpetkovski (via GitHub) via github
-
Re: [PR] fix: bound WindowAgg and grouped TopK output batches [datafusion]
koriyoshi2041 (via GitHub) via github
-
[I] `EquivalenceGroup::exprs_equal` ignores operators on `BinaryExpr` [datafusion]
galaxytemple (via GitHub) via github
-
Re: [PR] test: move limit fuzz tests to the FuzzTest driver [datafusion]
2010YOUY01 (via GitHub) via github
-
Re: [I] Wrong results: a filter on a constant column keeps the row of an aggregate without GROUP BY [datafusion]
jayzhan211 (via GitHub) via github
-
[PR] chore: update Cargo.lock for security audit [datafusion]
Phoenix500526 (via GitHub) via github
-
[I] Projecting the same volatile expression twice creates a false equivalence and breaks ORDER BY [datafusion]
galaxytemple (via GitHub) via github
-
Re: [PR] fix: skip arithmetic and concat operands that Spark skips under ANSI mode [datafusion-comet]
coderfender (via GitHub) via github
-
Re: [I] Add a typed SessionConfigExt setter for ballista.execution.mode [datafusion-ballista]
vikrantmehta123 (via GitHub) via github
-
[PR] docs: More comments for `LimitedBatchCoalescer` [datafusion]
2010YOUY01 (via GitHub) via github
-
Re: [I] `WITH ... AS MATERIALIZED` returns wrong rows under `ORDER BY ... LIMIT`: top-k aggregation limits the shared CTE body [datafusion]
adriangb (via GitHub) via github
-
Re: [I] Spark window over a doubted input order gets a sort by its own keys only, and operators above it return wrong rows [datafusion-comet]
andygrove (via GitHub) via github
-
Re: [PR] fix: fall back TopK whose later sort key can fail under ANSI [datafusion-comet]
coderfender (via GitHub) via github
-
[PR] fix: `WITH ... AS MATERIALIZED` returns wrong rows under `ORDER BY ... LIMIT` [datafusion]
jayzhan211 (via GitHub) via github
-
Re: [PR] fix: skip SingleDistinctToGroupBy rewrite when single_distinct_prefer_native is set (closes #25932) [datafusion]
jayzhan211 (via GitHub) via github