Messages by Thread
-
Re: [PR] docs: fix dead heading anchors and fail the docs build on warnings [datafusion-ballista]
via GitHub
-
[PR] fix(physical-plan): compact view buffers in PartitionedTopK (#26381) [datafusion]
via GitHub
-
[PR] fix(spark): return decimal(8, 6) with fractional seconds for date_part('SECOND', ts) [datafusion]
via GitHub
-
Re: [PR] Brent/query shape viz [datafusion-ballista]
via GitHub
-
[PR] serve_shuffle_partition_via_ipc_passthrough [datafusion-ballista]
via GitHub
-
[PR] add_flight_passthrough_serve_bench [datafusion-ballista]
via GitHub
-
Re: [PR] fix: preserve precision in log() with mixed-width float arguments [datafusion]
via GitHub
-
[PR] feat: add nested benchmark derived from TPC-H [datafusion-comet]
via GitHub
-
[PR] Resolve named windows referenced inside OVER (...) [datafusion]
via GitHub
-
[PR] PostgreSQL: Parse CREATE TRIGGER function arguments as expressions [datafusion-sqlparser-rs]
via GitHub
-
[PR] fix: preserve lambda bindings in nested-loop join projection pushdown [datafusion]
via GitHub
-
[PR] fix: support RunEndEncoded keys in min/max and piecewise merge join (#26363) [datafusion]
via GitHub
-
[PR] fix: keep a constant sort key when a projection reads a duplicate alias [datafusion]
via GitHub
-
Re: [I] Native CSV scan reads every partition through the first partition's object store [datafusion-comet]
via GitHub
-
Re: [I] Native Parquet scan reads files from another bucket when one partition spans buckets [datafusion-comet]
via GitHub
-
[I] ProjectionPushdown fails on a nested-loop join whose lambda captures a column from the other input [datafusion]
via GitHub
-
Re: [I] Cast of a literal that fails under ANSI fails the query at planning time, even in a branch no row reaches [datafusion-comet]
via GitHub
-
Re: [I] Native corr, covariance, variance and stddev return wrong values for a constant fractional column merged from several partitions [datafusion-comet]
via GitHub
-
[PR] fix(parquet): support int96 coercion in legacy list layouts [datafusion]
via GitHub
-
Re: [I] Native Parquet writes report row counts but not row contents to WriteTaskStatsTrackers [datafusion-comet]
via GitHub
-
Re: [I] Reduce retained buffer allocation when list_extract selects short nested arrays [datafusion-comet]
via GitHub
-
[PR] docs: fix SQL examples that the default dialect cannot parse [datafusion]
via GitHub
-
[PR] fix: fall back to Spark when Iceberg reports an output ordering [datafusion-comet]
via GitHub
-
[PR] fix(spark): normalize -0.0 in atan2 like Spark [datafusion]
via GitHub
-
[I] coerce_int96 does not coerce INT96 inside legacy Parquet list layouts (bag/array, two-level lists) [datafusion]
via GitHub
-
[PR] refactor(sql): extract large statement arms from SqlToRel [datafusion]
via GitHub
-
Re: [PR] perf: resolve aliased field once during metadata inference [datafusion]
via GitHub
-
[PR] fix: keep each native panic's backtrace with its own thread [datafusion-comet]
via GitHub
-
[I] SanityCheckPlan error: a constant sort key is lost when a projection reads a duplicate alias [datafusion]
via GitHub
-
[PR] fix(sql): inherit partition and order by when window spec references named window (#26364) [datafusion]
via GitHub
-
[I] Native panic backtrace can be attached to another thread's CometNativeException [datafusion-comet]
via GitHub
-
[I] Push Iceberg residual predicates on struct fields into the native scan [datafusion-comet]
via GitHub
-
Re: [I] Make datafusion support materializing option for CTE [datafusion]
via GitHub
-
[I] Native Iceberg scan fails when a data file omits an optional nested field [datafusion-comet]
via GitHub
-
[I] [EPIC] Nested types in the native Parquet and Iceberg scans: correctness and performance follow-ups [datafusion-comet]
via GitHub
-
[I] Native Parquet scan returns NULL for nested BINARY values that are not valid UTF-8 when they are read as STRING [datafusion-comet]
via GitHub
-
[I] Native Iceberg scan reads every column of a file when it needs none of them [datafusion-comet]
via GitHub
-
[I] Native Parquet scan reads the whole nested column for maps, field ids, case-insensitive names and leaf type changes [datafusion-comet]
via GitHub
-
[I] Native Parquet scan does not prune row groups or pages with predicates on struct fields [datafusion-comet]
via GitHub
-
[I] Native Parquet scan reads TIMESTAMP(NANOS) columns as timestamp where Spark rejects them [datafusion-comet]
via GitHub
-
[I] Native Parquet scan cannot read a file whose schema has a nested encoding arrow-rs rejects, even in a column the query does not read [datafusion-comet]
via GitHub
-
[I] Spark 3.4: native Parquet scan returns NULL for a struct matched by field id under a new name when Spark prunes its fields [datafusion-comet]
via GitHub
-
[I] Native Parquet scan returns a non-null array or struct of NULLs where Spark returns NULL because no requested nested field is in the file [datafusion-comet]
via GitHub
-
[I] Native Parquet scan returns wrong INT96 timestamps inside legacy-format lists [datafusion-comet]
via GitHub
-
Re: [PR] fix: defer throwing literal casts to Spark at runtime [datafusion-comet]
via GitHub
-
[I] PartitionedTopKExec keeps whole Utf8View input buffers alive for the rows it retains [datafusion]
via GitHub
-
[PR] refactor: recompute retained merge-row reservation on release [datafusion]
via GitHub
-
Re: [I] Add documentation for `cast` support for complex types [datafusion-comet]
via GitHub
-
[PR] DRAFT: add a generic test suite for `ExecutionPlan`s [datafusion]
via GitHub
-
[PR] feat: bump iceberg-rust past #3255 and narrow the nested schema evolution fallback [datafusion-comet]
via GitHub
-
Re: [I] Checked TIMESTAMP_MILLIS overflow for nested fields and nested-predicate scans is blocked on DataFusion nested-field pruning [datafusion-comet]
via GitHub
-
[PR] chore: Add Decimal128 benchmarks for gcd [datafusion]
via GitHub
-
Re: [PR] [DO NOT MERGE] Test apache/arrow-rs#10852 (adaptive RowSelection construction) with ClickBench [datafusion]
via GitHub
-
Re: [PR] fix: Do not mark GROUP BY derived unique keys as nullable [datafusion]
via GitHub
-
Re: [PR] WIP: DO NOT REVIEW: Benchmark enabling parquet filter pushdown by default with one-shot row group I/O [datafusion]
via GitHub
-
Re: [PR] WIP: NOT READY FOR REVIEW: Add parquet `progressive_io` option to keep one-shot row group I/O with pushdown filters [datafusion]
via GitHub
-
[PR] fix: fall back for Iceberg write settings that iceberg-java rejects [datafusion-comet]
via GitHub
-
Re: [I] Comet 1.2.0 Release [datafusion-comet]
via GitHub
-
Re: [I] `CASE` with two or more `FixedSizeBinary` WHEN literals panics [datafusion]
via GitHub
-
Re: [PR] perf(aggregate): specialize fully ordered group keys without hashing [datafusion]
via GitHub
-
Re: [PR] feat: serialize LazyMemoryExec through generator hooks [datafusion]
via GitHub
-
[PR] fix [datafusion-comet]
via GitHub
-
[PR] chore(ci): bump taiki-e/install-action from 2.87.27 to 2.87.28 [datafusion-ballista]
via GitHub
-
[I] Extend fully ordered aggregation to temporal, decimal, and fixed-size binary keys [datafusion]
via GitHub
-
[PR] fix: [branch-1.1] fall back from native V2 scans when the plan reads input_file_name (#6754) [datafusion-comet]
via GitHub
-
Re: [PR] feat: native RANGE window frames with explicit offset on " DECIMAL " ORDER BY [datafusion-comet]
via GitHub
-
[PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] perf: Optimize `upper`, `lower`, `translate`, `replace` [datafusion]
via GitHub
-
Re: [PR] feat: native RANGE window frames with explicit offset on DATE ORDER BY [datafusion-comet]
via GitHub
-
Re: [I] Represent Hive/value partitioning without claiming Partitioning::Hash [datafusion]
via GitHub
-
[I] `translate` panics when output would exceed 2GB [datafusion]
via GitHub
-
[PR] WIP: Add parquet `progressive_io` option using `ParquetPushDecoder::scan_plan` (one-shot row group I/O with pushdown filters) [datafusion]
via GitHub
-
[PR] fix: evaluate the array_append item on rows whose array is NULL [datafusion-comet]
via GitHub
-
Re: [PR] fix: wait for the whole NULL peer group before emitting RANGE `N PRECEDING` window results [datafusion]
via GitHub
-
Re: [PR] feat: Support Spark Expression Encode [datafusion-comet]
via GitHub
-
[I] Native decimal cast kernels compute `10^scale` without checking for a negative scale [datafusion-comet]
via GitHub
-
Re: [PR] fix: support binaryAsString in the native Parquet scan [datafusion-comet]
via GitHub
-
[PR] Fuzz window nulls [datafusion]
via GitHub
-
[PR] Fix literal projection distinct count statistics [datafusion]
via GitHub
-
[PR] [DO NOT MERGE] Test DataFusion against arrow-rs main (pre-release testing, 2026-10-15) [datafusion]
via GitHub
-
[PR] fix: fall back to Spark for decimal AVG cases that return wrong results [datafusion-comet]
via GitHub
-
[PR] fix: [branch-1.1] keep one row per key in a native PartialMerge that runs short of memory (#6867) [datafusion-comet]
via GitHub
-
[I] CrossJoinExec buffers the entire left input without spilling (OOM under memory pressure) [datafusion]
via GitHub
-
Re: [PR] fix: declare Hive partitioned scans as Range [datafusion]
via GitHub
-
[PR] fix(spark): return NaN and -Infinity from `pow` where Spark does [datafusion]
via GitHub
-
[I] Support MIN/MAX over StructType in native aggregates [datafusion-comet]
via GitHub
-
Re: [PR] fix: refuse codegen dispatch for a TRY cast that can put a null key in a map [datafusion-comet]
via GitHub
-
[PR] fix(functions-nested): preserve element field in array_repeat [datafusion]
via GitHub
-
Re: [PR] docs: document casts involving arrays, structs, and maps [datafusion-comet]
via GitHub
-
[I] Use one shared check and reason string for negative-scale decimals across the serdes [datafusion-comet]
via GitHub
-
[I] Negative-scale decimal `/`, `div`, `ceil` and `floor` fall back to Spark while `round` dispatches [datafusion-comet]
via GitHub
-
[I] Native Iceberg scan reads its full schema when a partition source is nested in a struct the query prunes [datafusion-comet]
via GitHub
-
Re: [PR] fix: fall back to Spark for negative-scale decimal casts and arithmetic [datafusion-comet]
via GitHub
-
Re: [I] Hash partitioning not falling back to Spark for high precision decimal partition keys [datafusion-comet]
via GitHub
-
Re: [I] Graceful executor shutdown terminates active Flight streams [datafusion-ballista]
via GitHub
-
[PR] docs: correct native Iceberg write docs that drifted from the code [datafusion-comet]
via GitHub
-
[PR] fix(expr): differentiate aggregate functions with and without explicit cast in output schema (#26221) [datafusion]
via GitHub
-
[PR] perf: share one decoded copy of a broadcast among the tasks of an executor [datafusion-comet]
via GitHub
-
[I] Double-negated child check and an always-true guard in the shuffle support logic [datafusion-comet]
via GitHub
-
[PR] refactor(optimizer): deduplicate boolean literal comparison rules [datafusion]
via GitHub
-
[PR] fix: bound Parquet Variant nesting depth [datafusion-comet]
via GitHub
-
Re: [PR] fix: keep nested inner joins with a different null equality in EliminateCrossJoin [datafusion]
via GitHub
-
[I] Substrait producer does not support LogicalPlan::Unnest [datafusion]
via GitHub
-
Re: [PR] fix: make wide date-to-timestamp casts safe [datafusion-comet]
via GitHub
-
Re: [PR] docs: add a regression check against the latest release tag to bug triage [datafusion-comet]
via GitHub
-
Re: [PR] feat: expose per-scan S3 HTTP coverage and retries [datafusion-comet]
via GitHub