Messages by Thread
-
-
[I] `RewriteSetComparison` is overly aggressive rewriting some set comparison into multiple mark joins [datafusion]
via GitHub
-
Re: [I] SQLQueryTestSuite.ignoreList entries skip the Spark baseline, not just Comet [datafusion-comet]
via GitHub
-
[PR] fix: preserve floating-point percentile interpolation precision [datafusion]
via GitHub
-
Re: [PR] fix: match Spark's duplicate field and field id semantics in parquet field lookup [datafusion-comet]
via GitHub
-
[PR] fix: avoid Float64 percentile_cont interpolation overflow [datafusion]
via GitHub
-
Re: [I] bug: slice crashes on arrays with a non-nullable element field [datafusion-comet]
via GitHub
-
Re: [I] Explain ObjectHashAggregate fallback when Comet shuffle is disabled [datafusion-comet]
via GitHub
-
Re: [I] Expr::apply_children/map_children & LogicalPlan::map_expressions does not correctly map subquery `outer_ref_column` expressions [datafusion]
via GitHub
-
[PR] fix: count each probe row once in HashJoinExec probe_hit_rate and avg_fanout [datafusion]
via GitHub
-
[PR] chore: drop support for JDK 11 [datafusion-comet]
via GitHub
-
[I] Native unix_timestamp returns incorrect results for negative fractional timestamps [datafusion-comet]
via GitHub
-
[PR] test: cover lpad and rpad routing configurations [datafusion-comet]
via GitHub
-
Re: [PR] perf: fuse Comet cache vector reads into Spark codegen [datafusion-comet]
via GitHub
-
[I] Support Iceberg tables on HDFS in the native scan [datafusion-comet]
via GitHub
-
Re: [PR] fix: enforce null-key rejection and mapKeyDedupPolicy in native map construction [datafusion-comet]
via GitHub
-
[PR] Run examples/*.py in CI, fix the broken example, and give silent ones output [datafusion-python]
via GitHub
-
[I] chore: Clear remaining Scala 2.13 warnings under the strict-warnings profile [datafusion-comet]
via GitHub
-
Re: [PR] IN LIST: optimize Utf8View and BinaryView filters [datafusion]
via GitHub
-
[I] PiecewiseMergeJoin classic join materializes O(buffered_len) intermediate batches with no memory accounting on the output path [datafusion]
via GitHub
-
[PR] test: run the libhdfs suite manually instead of in CI [datafusion-comet]
via GitHub
-
[I] Wrong results: filter marked as pushed down at plan time can be silently dropped per-file when schema evolution makes the runtime pushdown checker reject the adapted predicate [datafusion]
via GitHub
-
[I] CollectLeft hash join build holds ~2x build side while charging the memory pool 1x: concat_batches copy is never reserved and superseded batches are never shrunk [datafusion]
via GitHub
-
[I] SortPreservingMerge over-reserves memory by orders of magnitude for Utf8View sort keys: reservation measured before gc(), causing spurious ResourcesExhausted [datafusion]
via GitHub
-
[I] `percentile_cont` overflows while interpolating finite Float64 values [datafusion]
via GitHub
-
[I] `percentile_cont` truncates Float64 interpolation weights to six decimal places [datafusion]
via GitHub
-
[I] Join dynamic filter pushdown through `AggregateExec` can confuse same-named grouping columns [datafusion]
via GitHub
-
[I] Join dynamic filter pushdown through ProjectionExec can map duplicate output aliases to the wrong expression [datafusion]
via GitHub
-
[I] Join dynamic filter pushdown through FilterExec with a projection can discard matching rows with duplicate column names [datafusion]
via GitHub
-
Re: [I] Hashing array<struct<..>> is dominated by per-element slicing and dispatch [datafusion-comet]
via GitHub
-
Re: [PR] fix: `EXISTS`/`IN` subqueries hit the count bug for groupless aggregates [datafusion]
via GitHub
-
[PR] fix: return an error for an invalid CSV null_regex instead of panicking [datafusion]
via GitHub
-
[I] Invalid CSV null_regex panics the query task instead of returning an error [datafusion]
via GitHub
-
[PR] DuckDB: Support CREATE TABLE PARTITIONED BY expressions [datafusion-sqlparser-rs]
via GitHub
-
[PR] fix(executor): drain Flight before shutdown cleanup [datafusion-ballista]
via GitHub
-
Re: [PR] Fix `Numeric` signature coercion to properly handle null types [datafusion]
via GitHub
-
[PR] fix: preserve column indices in join dynamic filter pushdown [datafusion]
via GitHub
-
Re: [I] store partitioning in dynamic filters and remove CASE hash(expr) [datafusion]
via GitHub
-
Re: [I] Nested field access on nullable structs discard parent nulls [datafusion]
via GitHub
-
[I] When performing set comparison subqueries (such as > ANY / > ALL / = ANY, etc.) on the same table (without using aliases), silently returns wrong results (0 rows or all rows). [datafusion]
via GitHub
-
Re: [I] When performing set comparison subqueries (such as > ANY / > ALL / = ANY, etc.) on the same table (without using aliases), silently returns wrong results (0 rows or all rows). [datafusion]
via GitHub
-
Re: [I] When performing set comparison subqueries (such as > ANY / > ALL / = ANY, etc.) on the same table (without using aliases), silently returns wrong results (0 rows or all rows). [datafusion]
via GitHub
-
Re: [I] When performing set comparison subqueries (such as > ANY / > ALL / = ANY, etc.) on the same table (without using aliases), silently returns wrong results (0 rows or all rows). [datafusion]
via GitHub
-
Re: [I] When performing set comparison subqueries (such as > ANY / > ALL / = ANY, etc.) on the same table (without using aliases), silently returns wrong results (0 rows or all rows). [datafusion]
via GitHub
-
Re: [I] When performing set comparison subqueries (such as > ANY / > ALL / = ANY, etc.) on the same table (without using aliases), silently returns wrong results (0 rows or all rows). [datafusion]
via GitHub
-
[PR] chore: Deprecate internal-only APIs in AggregateExec [datafusion]
via GitHub
-
Re: [PR] perf: add direct native reads for broadcast exchange [datafusion-comet]
via GitHub
-
Re: [PR] fix: reject groups accumulator for bit_xor(DISTINCT) [datafusion]
via GitHub
-
Re: [PR] fix: make csv-read-options.py example self-contained (#1728) [datafusion-python]
via GitHub
-
Re: [PR] fix: preserve computed projections in unions_to_filter [datafusion]
via GitHub
-
[PR] ci: share extended test commands through xtask [datafusion]
via GitHub
-
Re: [PR] bench: add a shuffle read benchmark covering the per-block schema parse [datafusion-comet]
via GitHub
-
[PR] feat: transfer parent and dynamic filters across HashJoinExec equi-join keys (inner and semi joins) [datafusion]
via GitHub
-
[PR] fix: apply CSV null_regex when reading, not only when inferring the schema [datafusion]
via GitHub
-
Re: [PR] fix: reject NULL partition keys during partitioned writes [datafusion]
via GitHub
-
[PR] fix: preserve Spark errors for Parquet timestamp overflow [datafusion-comet]
via GitHub
-
Re: [PR] fix: stabilize grouped correlation with centered moments [datafusion]
via GitHub
-
Re: [PR] fix: avoid unsafe set rewrites for compound IN lists [datafusion]
via GitHub
-
Re: [PR] test: cover slice over expression-produced non-null element arrays (#… [datafusion-comet]
via GitHub
-
[I] Treat missing Parquet null counts as zero for files written by parquet-rs < 53.1.0 [datafusion]
via GitHub
-
[PR] test: bound merge fan-in in ordered aggregate spill tests [datafusion]
via GitHub
-
[I] Allow deriving a Parquet file Arrow schema from metadata during lazy opening [datafusion]
via GitHub