Messages by Thread
-
-
[I] Native `NUMERIC_OUT_OF_SUPPORTED_RANGE` error surfaces as `SparkException` instead of `SparkArithmeticException` [datafusion-comet]
via GitHub
-
Re: [PR] fix(cast): fall back for duplicate struct field names [datafusion-comet]
via GitHub
-
Re: [I] Casting to a struct type with repeated field names fails with "ArrowArray struct has 2 children (expected 1)" [datafusion-comet]
via GitHub
-
Re: [PR] fix: end the Delta scan's plan-data key with its plan id [datafusion-comet]
via GitHub
-
Re: [I] Native Delta scan: derive the task injection key from a stable scan identity [datafusion-comet]
via GitHub
-
Re: [PR] Full join output partitioning [datafusion]
via GitHub
-
Re: [PR] perf: reduce retained buffers for nested map lookups [datafusion-comet]
via GitHub
-
[I] Wrong results: order-preserving `RepartitionExec` keeps orderings of its input that do not hold after the merge [datafusion]
via GitHub
-
Re: [PR] feat: run make_interval natively with Spark's full microsecond range and precision [datafusion-comet]
via GitHub
-
[PR] fix(proto): add recursion protection to physical plan and expression serde [datafusion]
via GitHub
-
[PR] fix: Compact scalars during merge [datafusion]
via GitHub
-
Re: [PR] perf: preserve native DV bitmap compression [datafusion-comet]
via GitHub
-
Re: [PR] feat: route date and timestamp interval arithmetic through codegen dispatch [datafusion-comet]
via GitHub
-
Re: [PR] fix: honor the S3 profile name and file and Hadoop's addressing mode for custom endpoints [datafusion-comet]
via GitHub
-
Re: [PR] perf: add opt-in delta encoding for cached longs [datafusion-comet]
via GitHub
-
[I] `DISTINCT ON` with nested payloads can fail memory reservation after spillin [datafusion]
via GitHub
-
Re: [PR] feat: account JVM UDF Arrow allocations in Spark task memory [datafusion-comet]
via GitHub
-
Re: [PR] refactor: use arrow make_comparator for nested structural equality in arrays_overlap and array_position [2/2] [datafusion-comet]
via GitHub
-
Re: [PR] feat: support ANSI interval types in native Parquet scans [datafusion-comet]
via GitHub
-
Re: [PR] feat: support whole-value Variant scan pushdown [datafusion-comet]
via GitHub
-
Re: [PR] fix: enforce null-key rejection and mapKeyDedupPolicy in native map construction [datafusion-comet]
via GitHub
-
[I] REBALANCE followed by GROUP BY or a window returns duplicate groups on skewed data [datafusion-comet]
via GitHub
-
[I] CAST(timestamp_ntz AS TIMESTAMP) fails the task for values beyond year 262143 where Spark returns a value [datafusion-comet]
via GitHub
-
[I] Native Iceberg scan returns NULL for an INT96 column read through a name mapping when other columns are selected [datafusion-comet]
via GitHub
-
[I] String-to-timestamp cast at the far-past range limit uses -08:00 instead of local mean time in America/Los_Angeles [datafusion-comet]
via GitHub
-
[I] Native string-to-timestamp cast rejects zone suffixes Spark accepts (PST, CET, Zulu, Etc/GMT+8, +08:00:00, no space) [datafusion-comet]
via GitHub
-
[I] Native Parquet scan returns NULL for a root column whose file column an unread field-id alias claims [datafusion-comet]
via GitHub
-
[I] Native Parquet scan skips Spark's type check on a root field that loses its file column to a field-id match [datafusion-comet]
via GitHub
-
Re: [PR] fix: run sync catalog calls on a separate runtime [datafusion-iceberg]
via GitHub
-
[PR] fix: compare Duration and Interval as exact elapsed time in comparisons [datafusion]
via GitHub
-
[PR] fix: [branch-1.2] keep Text build sides on Spark by default and add Text conversion configs (#7123) [datafusion-comet]
via GitHub
-
Re: [PR] perf: decode Parquet footers for statistics in parallel during planning [datafusion]
via GitHub
-
Re: [I] substr on Dictionary(_, Utf8) inserts implicit CAST to Utf8View [datafusion]
via GitHub
-
Re: [PR] PostgreSQL: Support CREATE FOREIGN DATA WRAPPER [datafusion-sqlparser-rs]
via GitHub
-
[I] proto: recursion protection for deserializing logical plans [datafusion]
via GitHub
-
[PR] feat: decorrelate correlated scalar subqueries with ORDER BY ... LIMIT 1 [datafusion]
via GitHub
-
Re: [I] MIN/MAX don't unwrap nested encodings inside Dictionary columns [datafusion]
via GitHub
-
Re: [PR] fix: unwrap nested encodings inside Dictionary arguments to MIN/MAX [datafusion]
via GitHub
-
[PR] fix: preserve local TopK limits during exact sort pushdown [datafusion]
via GitHub
-
[I] TopK sort pushdown [datafusion]
via GitHub
-
Re: [PR] Fix changelog generation for unlinked authors [datafusion]
via GitHub
-
Re: [I] Recursive CTE: MIN/MAX aggregate dynamic filter survives reset_state, later iterations return wrong results [datafusion]
via GitHub
-
Re: [PR] feat: report statistics of materialized CTE scans [datafusion]
via GitHub
-
[I] proto: recursion protection for physical plan serde [datafusion]
via GitHub
-
Re: [PR] Enable page-index pruning for Iceberg scans [datafusion-iceberg]
via GitHub
-
Re: [I] Use `ProbeCompletion` in `NestedLoopJoinExec` [datafusion]
via GitHub
-
Re: [I] Dictionary performance improvement tickets [datafusion]
via GitHub
-
[PR] ci: disable incremental compilation correctly [datafusion]
via GitHub
-
Re: [I] Support null-aware (`NOT IN`) anti / mark joins in `SortMergeJoinExec` [datafusion]
via GitHub
-
[PR] fix: spill final hash aggregate output when the pool refuses it [datafusion]
via GitHub
-
Re: [PR] feat: run physical requirement enforcement first, as a PhysicalAnalyzer phase [datafusion]
via GitHub
-
[PR] chore: Move `AggregateExec` optimizer utilities to a new file [datafusion]
via GitHub
-
Re: [PR] perf: stop re-pairing marked build rows in the scope-key null-aware join [datafusion]
via GitHub
-
[PR] docs: link the development setup quick start [datafusion]
via GitHub
-
[PR] docs: link the testing quick start [datafusion]
via GitHub
-
Re: [PR] feature(physical-plan): add NullAwareMode to SortMergeJoinExec [datafusion]
via GitHub
-
Re: [PR] minor: share common state between the three PartitionedTopK operators [datafusion]
via GitHub
-
[PR] fix(optimizer): account for limit skip when pushing fetch into SortPreservingMergeExec [datafusion]
via GitHub
-
Re: [I] Find a solution to prevent processes being OOM killed due to inaccurate memory accounting [datafusion]
via GitHub
-
Re: [PR] perf: read NOT NULL tuple elements of a multi-column NOT IN as scope keys [datafusion]
via GitHub
-
[PR] build(deps): bump virtualenv from 21.7.13 to 21.14.13 [datafusion-python]
via GitHub
-
Re: [PR] fix: keep URL passwords and SAS queries out of Azure and object store errors, keys and logs [datafusion-comet]
via GitHub
-
[PR] test: catch operators that hold input-sized memory without reserving it [datafusion]
via GitHub
-
Re: [PR] test(scheduler): freeze the plan each TPC-H query ends on, under both planners [datafusion-ballista]
via GitHub
-
Re: [PR] perf(scheduler): run one stage when the plan asks for the same stage twice [datafusion-ballista]
via GitHub
-
Re: [PR] feat(scheduler): adopt DataFusion's cost-based join order enumeration [datafusion-ballista]
via GitHub
-
Re: [PR] fix: scope HashJoinExec build_time to hash-table construction only [datafusion]
via GitHub
-
Re: [PR] Datasource: Add file_metadata() to DataSink for per-file write metadata [datafusion]
via GitHub
-
[PR] refactor: replace `normalize_float_scalar` with `ScalarValue::normalize` [datafusion]
via GitHub
-
[I] [EPIC] Regressions in 1.2.0 since 1.1.0 [datafusion-comet]
via GitHub
-
[I] Native ABFS scans fail every task instead of falling back when Hadoop declines the auth type [datafusion-comet]
via GitHub
-
[I] collect_set over floats beside count(DISTINCT) diverges from Spark on signed zeros and NaN [datafusion-comet]
via GitHub
-
[PR] fix: keep RANGE default window frame for nullable UNIQUE ORDER BY keys [datafusion]
via GitHub
-
[PR] fix: release the clustered partial aggregate table on memory pressure under full group clustering [datafusion]
via GitHub
-
[I] Fully sorted partial aggregate still fails with ResourcesExhausted after emitting completed groups, because the table keeps its capacity [datafusion]
via GitHub
-
Re: [PR] fix: preserve unassigned inner join keys [datafusion]
via GitHub
-
Re: [PR] [draft] ci: add pinned Linux CI image recipe and offline validation [datafusion-comet]
via GitHub
-
Re: [PR] fix: propagate projection benefit through extension nodes in OptimizeProjections [datafusion]
via GitHub
-
Re: [PR] perf: reduce Parquet runtime filter schema guard overhead [datafusion-comet]
via GitHub
-
[PR] fix: unparse NULL list, struct, map and union literals as NULL [datafusion]
via GitHub
-
[PR] Point readers at tpchgen-cli for TPCH SLT tests [datafusion]
via GitHub
-
[PR] fix: correlated scalar subquery returns NULL when HAVING filters out the row [datafusion]
via GitHub
-
Re: [PR] perf: charge the local shuffle writer's buffers to the memory pool [datafusion-comet]
via GitHub
-
[I] Window function with nullable UNIQUE ORDER BY key uses ROWS frame and returns wrong results for NULL peers [datafusion]
via GitHub
-
[PR] Title: fix: preserve window inputs when replacing TopK sorts [datafusion]
via GitHub
-
Re: [PR] fix: plan ORDER BY on a source column hidden by a select alias [datafusion]
via GitHub
-
Re: [PR] feat: support DataFrame::cache() with pinned shuffle output and recovery [datafusion-ballista]
via GitHub
-
Re: [PR] feat: support bloom filters in native Iceberg writes [datafusion-comet]
via GitHub
-
[PR] fix: keep -0.0 rows in TopK dynamic filter when the threshold is a float zero [datafusion]
via GitHub
-
[PR] refactor: use `ProbeCompletion` in `NestedLoopJoinExec` [datafusion]
via GitHub
-
[I] [Minor docs update] Known users list, Parseable description is outdated [datafusion]
via GitHub
-
[PR] Update Parseable description in user guide [datafusion]
via GitHub