Messages by Thread
-
-
[PR] fix: match Spark's ANSI bound check for float/double to integral casts [datafusion-comet]
via GitHub
-
Re: [PR] fix: GROUP BY returns two rows for the NULL group with a nullable UNIQUE constraint [datafusion]
via GitHub
-
[PR] fix: correctly rounded decimal to double/float cast matching BigDecimal.doubleValue/floatValue [datafusion-comet]
via GitHub
-
[PR] fix: align string to timestamp parsing with Spark's segment rules [datafusion-comet]
via GitHub
-
[PR] fix: return NULL from rpad/lpad when the length column is NULL instead of panicking [datafusion-comet]
via GitHub
-
[I] Add Ability to Eagerly Prune Parquet Files for Better Statistics [datafusion]
via GitHub
-
[PR] fix: fall back for concat_ws with array arguments instead of failing natively [datafusion-comet]
via GitHub
-
[PR] test: enable the Iceberg split-operator and native write by default to surface test failures [datafusion-comet]
via GitHub
-
Re: [PR] feat: support pivot and unpivot [datafusion]
via GitHub
-
Re: [PR] build: enable Spark SQL tests for released Spark 4.2.0 [datafusion-comet]
via GitHub
-
Re: [I] Current shuffle format has too much overhead with default batch size [datafusion-comet]
via GitHub
-
[I] Investigate: why Comet shuffle files can be larger than Spark's, and whether byte-based block sizing would fix it [datafusion-comet]
via GitHub
-
Re: [I] Natively support regr_sxx, regr_syy, regr_sxy, regr_slope, regr_intercept, regr_r2 aggregates [datafusion-comet]
via GitHub
-
Re: [I] Iceberg write split-operator plan: CI failures when enabled by default [datafusion-comet]
via GitHub
-
[I] Plain `posexplode` evaluates its array argument twice per batch [datafusion-comet]
via GitHub
-
[I] String-to-timestamp cast diverges from Spark's parseTimestampString: rejects 1-digit segments and empty fractions, accepts zone suffixes on date-only strings and 7-digit years [datafusion-comet]
via GitHub
-
[I] Decimal to double/float cast is not correctly rounded: last-digit-wrong results for ordinary DECIMAL(38,18) values [datafusion-comet]
via GitHub
-
[I] ANSI cast of double/float to int/long falsely reports CAST_OVERFLOW for exactly-representable boundary values (2147483647.0, -2147483648.0, ±2^63) [datafusion-comet]
via GitHub
-
[I] rpad/lpad panic (Option::unwrap on None) when the length column contains NULL [datafusion-comet]
via GitHub
-
[I] Nested (struct/list/map) Parquet schema-evolution conversions bypass Spark's type-conversion rules: silent NULLs, string parsing, and a native panic [datafusion-comet]
via GitHub
-
[PR] chore(deps): bump the codeql-actions group with 2 updates [datafusion-comet]
via GitHub
-
[PR] fix(proto): destructure JSON source and sink serde hooks [datafusion]
via GitHub
-
Re: [PR] fix: report native shuffle read metrics [datafusion-comet]
via GitHub
-
Re: [PR] feat: add native distinct-combined collect_list aggregate support [datafusion-comet]
via GitHub
-
[PR] chore(deps): bump tower-http from 0.7.0 to 0.7.1 [datafusion-ballista]
via GitHub
-
[PR] chore(ci): bump taiki-e/install-action from 2.87.2 to 2.87.3 [datafusion-ballista]
via GitHub
-
Re: [I] Destructure proto hooks for lambda physical expressions [datafusion]
via GitHub
-
Re: [I] Unify granularity / field-name parsing across temporal functions [datafusion]
via GitHub
-
Re: [PR] feat: support ASOF JOIN SQL [datafusion]
via GitHub
-
Re: [D] Policy on uptick of LLM PRs from new contributors [datafusion]
via GitHub
-
Re: [PR] Add support for dictionary for approx_distinct [datafusion]
via GitHub
-
[I] Join planning inserts IS NOT NULL filters that provably pass 100% of rows when input statistics report zero nulls [datafusion]
via GitHub
-
Re: [PR] feat: drop provably-true IS NOT NULL conjuncts from FilterExec predicates via input null_count statistics [datafusion]
via GitHub
-
[PR] fix(spark): accept every integer width in `factorial`, matching Spark's implicit cast [datafusion]
via GitHub
-
Re: [PR] fix(spark): accept every integer width in `factorial`, matching Spark's implicit cast [datafusion]
via GitHub
-
Re: [PR] fix(spark): accept every integer width in `factorial`, matching Spark's implicit cast [datafusion]
via GitHub
-
Re: [PR] fix(spark): accept every integer width in `factorial`, matching Spark's implicit cast [datafusion]
via GitHub
-
Re: [PR] fix(spark): accept every integer width in `factorial`, matching Spark's implicit cast [datafusion]
via GitHub
-
Re: [PR] fix(spark): accept every integer width in `factorial`, matching Spark's implicit cast [datafusion]
via GitHub
-
Re: [PR] fix(spark): accept every integer width in `factorial`, matching Spark's implicit cast [datafusion]
via GitHub
-
Re: [PR] fix(spark): accept every integer width in `factorial`, matching Spark's implicit cast [datafusion]
via GitHub
-
Re: [PR] fix(spark): accept every integer width in `factorial`, matching Spark's implicit cast [datafusion]
via GitHub
-
Re: [PR] fix(spark): accept every integer width in `factorial`, matching Spark's implicit cast [datafusion]
via GitHub
-
Re: [PR] fix(spark): accept every integer width in `factorial`, matching Spark's implicit cast [datafusion]
via GitHub
-
Re: [PR] fix(spark): accept every integer width in `factorial`, matching Spark's implicit cast [datafusion]
via GitHub
-
Re: [PR] fix(spark): accept every integer width in `factorial`, matching Spark's implicit cast [datafusion]
via GitHub
-
Re: [PR] fix(spark): accept every integer width in `factorial`, matching Spark's implicit cast [datafusion]
via GitHub
-
Re: [PR] fix(spark): accept every integer width in `factorial`, matching Spark's implicit cast [datafusion]
via GitHub
-
Re: [PR] fix(spark): accept every integer width in `factorial`, matching Spark's implicit cast [datafusion]
via GitHub
-
Re: [I] Proto decode silently truncates limits and sizes to `usize` on 32-bit targets [datafusion]
via GitHub
-
Re: [I] Dictionary-encoded group keys pay 27-37% aggregation tax vs Utf8View in TPC-H (Q2/Q19/Q20), DF 54 & 55 both [datafusion]
via GitHub
-
[I] [Bug] spark factorial rejects STRING, DECIMAL and floating-point inputs that Spark implicitly casts to INT [datafusion]
via GitHub
-
[I] [Bug] spark factorial rejects BIGINT and untyped integer literals that Spark accepts [datafusion]
via GitHub
-
[PR] [Comet] Recover native Celeborn shuffle from oversized rows [datafusion-comet]
via GitHub
-
Re: [I] [Incompatibility] Document array_join null handling differences [datafusion-comet]
via GitHub
-
[PR] fix: preserve Arrow field metadata on scalar subquery expressions [datafusion]
via GitHub
-
Re: [PR] deps: bump DataFusion 55.0 and Arrow/Parquet 59.2 [datafusion-comet]
via GitHub
-
[PR] fix: compare nested list scalars with a dynamic comparator [datafusion]
via GitHub
-
[I] `min` / `max` over a list of lists (or of structs) fails with "Internal error: Uncomparable values" [datafusion]
via GitHub
-
[PR] fix: `make_array` over NULL-typed columns returns one list per row [datafusion]
via GitHub
-
Re: [I] make_array returns wrong row count for null-array input [datafusion]
via GitHub
-
[D] Sharing benchmark observations on decimal floating-point compression: comparing integer mapping with Gorilla/Chimp on time-series datasets [datafusion]
via GitHub
-
[PR] perf: slice the child instead of gathering it when unnesting [datafusion-comet]
via GitHub
-
[I] Emit the final (post-AQE) physical plan to the event log [datafusion-ballista]
via GitHub
-
[PR] fix: cap the field list in "No field named" errors [datafusion]
via GitHub
-
[PR] feat: experiment with `RealUsagePool` [datafusion-comet]
via GitHub
-
[PR] Add reproducing case [datafusion]
via GitHub