Messages by Thread
-
[I] make_date can throw on unconsumed rows through PySpark and raw row iterators [datafusion-comet]
pingzh (via GitHub) via github
-
[PR] feat(executor): add a jemalloc feature to use jemalloc as the allocator [datafusion-ballista]
andygrove (via GitHub) via github
-
Re: [PR] fix: stop gating columnar shuffle on native-serde checks it never uses [datafusion-comet]
Visorgood (via GitHub) via github
-
Re: [PR] fix: support integer seed for rand and randn [datafusion-comet]
galaxytemple (via GitHub) via github
-
Re: [PR] Implement Aggregate function `map_agg` [datafusion]
rizzabhdwaj (via GitHub) via github
-
Re: [PR] Deduplicate field-major struct append paths [datafusion-comet]
sakshichitnis27 (via GitHub) via github
-
[I] A failed native `grow` is only logged when the task makes no later `try_grow` [datafusion-comet]
JonSnow1807 (via GitHub) via github
-
Re: [PR] feat: add a jemalloc Maven profile to build Comet with the jemalloc allocator [datafusion-comet]
comphead (via GitHub) via github
-
Re: [PR] feat: trim the native heap when an executor's last native plan finishes [datafusion-comet]
comphead (via GitHub) via github
-
Re: [PR] [DO NOT MERGE] test(executor): exercise DataFusion StageBoundary API [datafusion-ballista]
edmondop (via GitHub) via github
-
Re: [PR] refactor: share one Hinnant civil-date pair across spark-expr and core [datafusion-comet]
comphead (via GitHub) via github
-
[I] Use precomputed divisors in decimal `floor`, `ceil`, and `round`, and in `unix_timestamp` [datafusion-spark]
mbutrovich (via GitHub) via github
-
[I] `mod` and `pmod` expand a scalar divisor to an array, so arrow-rs never takes its scalar divisor path [datafusion-spark]
mbutrovich (via GitHub) via github
-
[I] bench.sh cannot generate TPC-H data with tpchgen-cli 4.0 [datafusion]
mbutrovich (via GitHub) via github
-
Re: [I] DataFrame API: serialize columns to a JSON string column [datafusion]
cj-zhukov (via GitHub) via github
-
[PR] SparkOptions port [datafusion-spark]
rizzabhdwaj (via GitHub) via github
-
[PR] fix: restore Rust 1.100 native UDF loading [datafusion-comet]
1fanwang (via GitHub) via github
-
[PR] feat: enable spillable native grouped integer DISTINCT counts [datafusion]
QinXi-ai (via GitHub) via github
-
Re: [PR] PostgreSQL: Support CREATE OR REPLACE PROCEDURE [datafusion-sqlparser-rs]
codecov-commenter (via GitHub) via github
-
[I] Type numeric literals as Spark does in the sqllogictest files [datafusion-spark]
andygrove (via GitHub) via github
-
[I] [Bug] quote of a TIMESTAMP uses 'T' between date and time, Spark uses a space [datafusion-spark]
andygrove (via GitHub) via github
-
[I] [Bug] format_string formats DECIMAL, DATE and TIMESTAMP arguments differently from Spark [datafusion-spark]
andygrove (via GitHub) via github
-
[PR] PostgreSQL: Read multi-character operator names such as === as one operator [datafusion-sqlparser-rs]
LucaCappelletti94 (via GitHub) via github
-
[I] Move SparkOptions into datafusion-spark as a config extension [datafusion-spark]
andygrove (via GitHub) via github
-
[I] Internal error when two aggregates share an IS TRUE / IS FALSE / IS UNKNOWN argument on a nullable column [datafusion]
leoyvens (via GitHub) via github
-
[I] Add a Spark version setting and derive behavior flags from it [datafusion-spark]
andygrove (via GitHub) via github
-
[I] Support non-default legacy settings in format_string, concat and array() [datafusion-spark]
andygrove (via GitHub) via github
-
[I] [Bug] elt returns a string for binary arguments, Spark returns BINARY [datafusion-spark]
andygrove (via GitHub) via github
-
[I] [Bug] size returns -1 for NULL when ANSI mode is on, Spark returns NULL [datafusion-spark]
andygrove (via GitHub) via github
-
Re: [PR] chore(deps): bump soupsieve from 2.8.3 to 2.9 [datafusion-sandbox]
dependabot[bot] (via GitHub) via github
-
[PR] chore(deps): bump soupsieve from 2.8.3 to 4.0 [datafusion-sandbox]
dependabot[bot] (via GitHub) via github
-
[PR] feat(spark): add EvalMode and use it for parse_url and try_parse_url [datafusion-spark]
andygrove (via GitHub) via github
-
[I] [EPIC] Port Comet's Spark-compatible CAST [datafusion-spark]
andygrove (via GitHub) via github
-
[PR] [branch-54] chore: fix cargo audit (backport #24467, #25309, #26253, #26352, #26550, #26666) [datafusion]
alamb (via GitHub) via github
-
Re: [PR] [branch-54] chore: fix cargo audit (backport #24467, #25309, #26253, #26352, #26550, #26666) [datafusion]
alamb (via GitHub) via github
-
Re: [PR] [branch-54] chore: fix cargo audit (backport #24467, #25309, #26253, #26352, #26550, #26666) [datafusion]
alamb (via GitHub) via github
-
[I] Window functions: bulk evaluation of frames and of runs of small partitions in `BoundedWindowAggExec` (measured prototype) [datafusion]
Sunninsky (via GitHub) via github
-
Re: [PR] chore: pin DataFusion to 56.0.0-rc1 ahead of DataFusion 56 [datafusion-ballista]
milenkovicm (via GitHub) via github
-
[I] [DISCUSSION] How should we test datafusion-spark against Spark? [datafusion-spark]
andygrove (via GitHub) via github
-
Re: [PR] fix(proto): add recursion protection to logical plan deserialization [datafusion]
kosiew (via GitHub) via github
-
Re: [PR] perf: factor common guards out of pruning predicates [datafusion]
github-actions[bot] (via GitHub) via github
-
[I] Research using the Rust Allocator API (stabilized in 1.100) for memory-pool accounting [datafusion-comet]
andygrove (via GitHub) via github
-
[PR] fix(spark): array_contains compares floats the way Spark does [datafusion-spark]
Yupsecous (via GitHub) via github
-
Re: [PR] feat/perf: derive SortMergeJoin sort options from input ordering and allow SMJ for a single partition [datafusion]
bert-beyondloops (via GitHub) via github
-
[PR] to_json: serialize a struct or a set of columns to a JSON string column [datafusion-spark]
cj-zhukov (via GitHub) via github
-
[I] to_json: serialize a struct or a set of columns to a JSON string column [datafusion-spark]
cj-zhukov (via GitHub) via github
-
Re: [PR] perf: compact view arrays before writing Arrow IPC files [datafusion]
kosiew (via GitHub) via github
-
[PR] perf(hash-join): Redesign hash table with contiguous match storage [datafusion]
2010YOUY01 (via GitHub) via github
-
[PR] perf: preserve run-end encoded UTF-8 LIKE operands [datafusion]
asubiotto (via GitHub) via github
-
[PR] fix: split a leaf projection stranded above a limit by a pushed-down OFFSET [datafusion]
cool9850311 (via GitHub) via github
-
[PR] fix(scheduler): fail jobs whose executor-loss rollback fails instead of hanging them [datafusion-ballista]
goingforstudying-ctrl (via GitHub) via github
-
Re: [I] Add Column Match by header flag to datafusion csv [datafusion]
kosiew (via GitHub) via github
-
[I] Implement contiguous match storage for Hash Join indexing [datafusion]
2010YOUY01 (via GitHub) via github
-
[PR] docs: More comments for `preserve_partitioning` field in `SortExec` [datafusion]
2010YOUY01 (via GitHub) via github
-
[PR] chore(deps): bump soupsieve from 2.9 to 4.0 [datafusion]
dependabot[bot] (via GitHub) via github
-
Re: [PR] feat: use exact integer statistics for ordering inference [datafusion]
kosiew (via GitHub) via github
-
[PR] fix(spark): decode unbase64 like Spark's MIME decoder [datafusion-spark]
Wali05 (via GitHub) via github
-
Re: [PR] feat: NestedInputAccess capability for nested read pruning and row group / page pruning [datafusion]
raghuvanshraj (via GitHub) via github
-
[PR] Add blog post: TopK per partition with enable_window_topn [datafusion-site]
Inf1mum (via GitHub) via github
-
[I] Executor-loss recovery hangs every remaining job when one job's stage rollback fails [datafusion-ballista]
goingforstudying-ctrl (via GitHub) via github
-
[PR] Fix clippy lints from Rust 1.100 and 1.101 [datafusion-sqlparser-rs]
LucaCappelletti94 (via GitHub) via github
-
[PR] build(deps): bump libloading from 0.8.9 to 0.9.0 in /native/native-executors [datafusion-comet]
dependabot[bot] (via GitHub) via github
-
[PR] build(deps): bump the all-other-cargo-deps group in /native/native-executors with 2 updates [datafusion-comet]
dependabot[bot] (via GitHub) via github
-
Re: [I] Push sort order into parquet scans for ungrouped MIN/MAX (same visit order as TopK) [datafusion]
galaxytemple (via GitHub) via github
-
[PR] fix(spark): time_trunc unit check [datafusion-spark]
TechWizard9999 (via GitHub) via github
-
Re: [PR] feat: plan Iceberg file tasks before execution [datafusion-iceberg]
NoahKusaba (via GitHub) via github
-
[PR] fix(spark): date_part field check [datafusion-spark]
TechWizard9999 (via GitHub) via github
-
[PR] test: skip the HDFS client settings Iceberg test when Iceberg is unavailable [datafusion-comet]
parthchandra (via GitHub) via github
-
[I] Rust tests fail on Rust 1.100: COMET_TEST_UDFS_LIB points at target/debug/build [datafusion-comet]
dwsmith1983 (via GitHub) via github
-
[PR] test: rewrite escaped-regex error checks as plain text in four .slt files [datafusion-spark]
IG-ABHINAV (via GitHub) via github
-
[PR] test: replace arrow_cast with :: casts where a SQL type is equivalent [datafusion-spark]
andygrove (via GitHub) via github
-
[PR] Fix sink order [datafusion]
2010YOUY01 (via GitHub) via github