github  

Messages by Thread

• • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
  • Re: [PR] feat(parquet): runtime row-group early stop via TopK dynamic filter [datafusion] via GitHub
• [PR] Update aws_options.snap [datafusion] via GitHub
  • Re: [PR] Update aws_options.snap [datafusion] via GitHub
• Re: [I] Split proto serialization to encapsulate private state [datafusion] via GitHub
• [PR] [codex] Upgrade Spark 4.1 to 4.1.2 [datafusion-comet] via GitHub
  • Re: [PR] build: upgrade Spark 4.1 to 4.1.2 [datafusion-comet] via GitHub
• Re: [I] Add hdfs experimental support for native iceberg_compat reader [datafusion-comet] via GitHub
  • Re: [I] Add hdfs experimental support for native iceberg_compat reader [datafusion-comet] via GitHub
• Re: [I] Can we avoid JVM round-trips in some cases for `native_iceberg_compat` scans? [datafusion-comet] via GitHub
  • Re: [I] Can we avoid JVM round-trips in some cases for `native_iceberg_compat` scans? [datafusion-comet] via GitHub
• Re: [PR] `MiMalloc` for `sqllogictests` [datafusion] via GitHub
• Re: [PR] feat: support optional threshold parameter for levenshtein function [datafusion] via GitHub
• Re: [I] [iceberg] Comet iceberg requires lazy materialization to be turned off [datafusion-comet] via GitHub
• Re: [I] [iceberg] Iceberg data files not found when Comet vectorized reader is enabled [datafusion-comet] via GitHub
• Re: [I] Various issues with Comet support for HashAggregateExec [datafusion-comet] via GitHub
  • Re: [I] Various issues with Comet support for HashAggregateExec [datafusion-comet] via GitHub
• Re: [I] [EPIC] Improve planning of hash aggregates [datafusion-comet] via GitHub
  • Re: [I] [EPIC] Improve planning of hash aggregates [datafusion-comet] via GitHub
• [PR] feat: Implement TimeType support - Infrastructure - shuffle [datafusion-comet] via GitHub
• [I] perf: Use bulk-NULL builders in split and substring [datafusion-comet] via GitHub
  • Re: [I] perf: Use bulk-NULL builders in split and substring [datafusion-comet] via GitHub
• [I] Implement TimeType support: Infrastructure - shuffle [datafusion-comet] via GitHub
  • Re: [I] Implement TimeType support: Infrastructure - shuffle [datafusion-comet] via GitHub
• [PR] fix: float <-> decimal coercion should coerce to float [datafusion] via GitHub
• Re: [I] Coercion between floating point types and exact numeric types should result in floating point type as the common super type [datafusion] via GitHub
• [I] `recompute_schema()` is broken with `LogicalPlan::Union` [datafusion] via GitHub
  • Re: [I] `recompute_schema()` is broken with `LogicalPlan::Union` [datafusion] via GitHub
• [PR] [branch-54] Fix: compact view buffers in ScalarValue::compact for all container types (#21934) [datafusion] via GitHub
  • Re: [PR] [branch-54] Fix: compact view buffers in ScalarValue::compact for all container types (#21934) [datafusion] via GitHub
• Re: [PR] fix: respect Parquet column order when pruning [datafusion] via GitHub
• Re: [I] ScalarValue::compacted() does not free unused view-buffer memory for Utf8View / BinaryView arrays [datafusion] via GitHub
• [PR] [branch-54] Revert "Add `ExecutionPlan::apply_expressions()` (#20337)" (#22437) [datafusion] via GitHub
  • Re: [PR] [branch-54] Revert "Add `ExecutionPlan::apply_expressions()` (#20337)" (#22437) [datafusion] via GitHub
  • Re: [PR] [branch-54] Revert "Add `ExecutionPlan::apply_expressions()` (#20337)" (#22437) [datafusion] via GitHub
• Re: [I] Add ExistenceJoin support to Comet native execution [datafusion-comet] via GitHub
• [PR] fix: handle `IS TRUE` properly in `EliminateOuterJoin` [datafusion] via GitHub
  • Re: [PR] fix: handle `IS TRUE` correctly in `EliminateOuterJoin` [datafusion] via GitHub
  • Re: [PR] fix: handle `IS TRUE` correctly in `EliminateOuterJoin` [datafusion] via GitHub
  • Re: [PR] fix: handle `IS TRUE` correctly in `EliminateOuterJoin` [datafusion] via GitHub
  • Re: [PR] fix: handle `IS TRUE` correctly in `EliminateOuterJoin` [datafusion] via GitHub
  • Re: [PR] fix: handle `IS TRUE` correctly in `EliminateOuterJoin` [datafusion] via GitHub
  • Re: [PR] fix: handle `IS TRUE` correctly in `EliminateOuterJoin` [datafusion] via GitHub
• [I] Recover q83 broadcast/subquery reuse lost by CometBroadcastExchangeExec.doCanonicalize fix in #4374 [datafusion-comet] via GitHub
  • Re: [I] Recover q83 broadcast/subquery reuse lost by CometBroadcastExchangeExec.doCanonicalize fix in #4374 [datafusion-comet] via GitHub
  • Re: [I] Recover q83 broadcast/subquery reuse lost by CometBroadcastExchangeExec.doCanonicalize fix in #4374 [datafusion-comet] via GitHub
• [PR] chore: Datafusion 54 upgrade [datafusion-comet] via GitHub
  • Re: [PR] chore: Datafusion 54 upgrade [datafusion-comet] via GitHub
• Re: [PR] perf: apply min-alloc split to ByteViewGroupValueBuilder::take_n (follow-up to #22165) [datafusion] via GitHub
  • Re: [PR] perf: apply min-alloc split to ByteViewGroupValueBuilder::take_n (follow-up to #22165) [datafusion] via GitHub
• [PR] [branch-54]: Backport 22404. Fix Spark slice function on negative OOB [datafusion] via GitHub
  • Re: [PR] [branch-54]: Backport 22404. Fix Spark slice function on negative OOB [datafusion] via GitHub
  • Re: [PR] [branch-54]: Backport 22404. Fix Spark slice function on negative OOB [datafusion] via GitHub
• [PR] [df54]: Backport 22404. Fix Spark `slice` function on negative OOB [datafusion] via GitHub
  • Re: [PR] [branch-54]: Backport 22404. Fix Spark `slice` function on negative OOB [datafusion] via GitHub
• [I] Outer join elimination does not handle `IS TRUE` correctly [datafusion] via GitHub
  • Re: [I] Outer join elimination does not handle `IS TRUE` correctly [datafusion] via GitHub
  • Re: [I] Outer join elimination does not handle `IS TRUE` correctly [datafusion] via GitHub
• [PR] feat: enable CometLocalTableScanExec by default [datafusion-comet] via GitHub
  • Re: [PR] feat: enable CometLocalTableScanExec by default [datafusion-comet] via GitHub
• Re: [I] Add support for native custom scalar UDFs [datafusion-comet] via GitHub
  • Re: [I] Add support for native custom scalar UDFs [datafusion-comet] via GitHub
• [PR] Df54 [datafusion-comet] via GitHub
  • Re: [PR] chore: df54 sync [datafusion-comet] via GitHub
• [PR] chore: datafusion 54 sync [datafusion-comet] via GitHub
  • Re: [PR] chore: datafusion 54 sync [datafusion-comet] via GitHub
• [PR] feat: add ExecutionPlan::benefits_from_output_partitioning [datafusion] via GitHub
  • Re: [PR] feat: add ExecutionPlan::benefits_from_output_partitioning [datafusion] via GitHub
  • Re: [PR] feat: add ExecutionPlan::benefits_from_output_partitioning [datafusion] via GitHub
  • Re: [PR] feat: add ExecutionPlan::benefits_from_output_partitioning [datafusion] via GitHub
  • Re: [PR] feat: add ExecutionPlan::benefits_from_output_partitioning [datafusion] via GitHub
  • Re: [PR] feat: add ExecutionPlan::benefits_from_output_partitioning [datafusion] via GitHub
  • Re: [PR] feat: add ExecutionPlan::benefits_from_output_partitioning [datafusion] via GitHub
  • Re: [PR] feat: add ExecutionPlan::benefits_from_output_partitioning [datafusion] via GitHub
• [PR] DF54 follow-ups wave 1: SessionContext APIs, codec typing, test fixes [datafusion-python] via GitHub
  • Re: [PR] feat: expose variety of features from DF54 update [datafusion-python] via GitHub
  • Re: [PR] feat: expose variety of features from DF54 update [datafusion-python] via GitHub
  • Re: [PR] feat: expose variety of features from DF54 update [datafusion-python] via GitHub
• [PR] feat: lower repartition_file_min_size default from 10 MiB to 1 MiB [datafusion] via GitHub
  • Re: [PR] feat: lower repartition_file_min_size default from 10 MiB to 1 MiB [datafusion] via GitHub
  • Re: [PR] feat: lower repartition_file_min_size default from 10 MiB to 1 MiB [datafusion] via GitHub
  • Re: [PR] feat: lower repartition_file_min_size default from 10 MiB to 1 MiB [datafusion] via GitHub
  • Re: [PR] feat: lower repartition_file_min_size default from 10 MiB to 1 MiB [datafusion] via GitHub
  • Re: [PR] feat: lower repartition_file_min_size default from 10 MiB to 1 MiB [datafusion] via GitHub
  • Re: [PR] feat: lower repartition_file_min_size default from 10 MiB to 1 MiB [datafusion] via GitHub
  • Re: [PR] feat: lower repartition_file_min_size default from 10 MiB to 1 MiB [datafusion] via GitHub
• Re: [PR] Support distributed processing by pickling expressions [datafusion-python] via GitHub
  • Re: [PR] Support distributed processing by pickling expressions [datafusion-python] via GitHub
• [PR] feat: disable join dynamic filter pushdown by default [datafusion] via GitHub
  • Re: [PR] feat: disable join dynamic filter pushdown by default [datafusion] via GitHub
  • Re: [PR] feat: disable join dynamic filter pushdown by default [datafusion] via GitHub
  • Re: [PR] feat: disable join dynamic filter pushdown by default [datafusion] via GitHub
  • Re: [PR] feat: disable join dynamic filter pushdown by default [datafusion] via GitHub
  • Re: [PR] feat: disable join dynamic filter pushdown by default [datafusion] via GitHub
  • Re: [PR] feat: disable join dynamic filter pushdown by default [datafusion] via GitHub
  • Re: [PR] feat: disable join dynamic filter pushdown by default [datafusion] via GitHub
• Re: [PR] chore: Add existence (semi / anti ) benchmarks for hashjoinexec [datafusion] via GitHub
  • Re: [PR] chore: Add existence (semi / anti ) benchmarks for hashjoinexec [datafusion] via GitHub
  • Re: [PR] chore: Add existence (semi / anti ) benchmarks for hashjoinexec [datafusion] via GitHub
  • Re: [PR] chore: Add existence (semi / anti ) benchmarks for hashjoinexec [datafusion] via GitHub
  • Re: [PR] chore: Add existence (semi / anti ) benchmarks for hashjoinexec [datafusion] via GitHub
  • Re: [PR] chore: Add existence (semi / anti ) benchmarks for hashjoinexec [datafusion] via GitHub
• [PR] fix: make BloomFilter intermediate buffer Spark-compatible [datafusion-comet] via GitHub
  • Re: [PR] fix: make BloomFilter intermediate buffer Spark-compatible [datafusion-comet] via GitHub
  • Re: [PR] fix: make BloomFilter intermediate buffer Spark-compatible [datafusion-comet] via GitHub
  • Re: [PR] fix: make BloomFilter intermediate buffer Spark-compatible [datafusion-comet] via GitHub
  • Re: [PR] fix: make BloomFilter intermediate buffer Spark-compatible [datafusion-comet] via GitHub
  • Re: [PR] fix: make BloomFilter intermediate buffer Spark-compatible [datafusion-comet] via GitHub
• [PR] Revert "Add `ExecutionPlan::apply_expressions()` (#20337)" [datafusion] via GitHub
  • Re: [PR] Revert "Add `ExecutionPlan::apply_expressions()` (#20337)" [datafusion] via GitHub
  • Re: [PR] Revert "Add `ExecutionPlan::apply_expressions()` (#20337)" [datafusion] via GitHub
  • Re: [PR] Revert "Add `ExecutionPlan::apply_expressions()` (#20337)" [datafusion] via GitHub
• [I] Implement tiered CI approach [datafusion-comet] via GitHub
  • Re: [I] Implement tiered CI approach [datafusion-comet] via GitHub
  • Re: [I] Implement tiered CI approach [datafusion-comet] via GitHub
  • Re: [I] Implement tiered CI approach [datafusion-comet] via GitHub
  • Re: [I] Implement tiered CI approach [datafusion-comet] via GitHub
• Re: [I] Comet falls back to Spark for final hash aggregate in some cases when it could be supported [datafusion-comet] via GitHub
• Re: [I] AQE may materialize a non-supported Final-mode HashAggregate [datafusion-comet] via GitHub
• [PR] Improve accuracy of supports_string_literal_concatenation_with_newline [datafusion-sqlparser-rs] via GitHub
  • Re: [PR] Improve accuracy of supports_string_literal_concatenation_with_newline [datafusion-sqlparser-rs] via GitHub
• [PR] test: fix probeComplexColumn in CometCodegenFuzzSuite [datafusion-comet] via GitHub
  • Re: [PR] test: fix merge conflicts in CodegenFuzzSuite and CodegenSuite [datafusion-comet] via GitHub
• [PR] feat: add user-facing CometUDF registration [datafusion-comet] via GitHub
  • Re: [PR] feat: add user-facing CometUDF registration [experimental] [datafusion-comet] via GitHub
  • Re: [PR] feat: add user-facing CometUDF registration [experimental] [datafusion-comet] via GitHub
  • Re: [PR] feat: add user-facing CometUDF registration [experimental] [datafusion-comet] via GitHub
  • Re: [PR] feat: add user-facing CometUDF registration [experimental] [datafusion-comet] via GitHub
• [PR] [codex] Enable array-to-string cast coverage for float and binary types [datafusion-comet] via GitHub
• Re: [I] design: DataFrame joins (join, joinOn) and the Java Expr question [datafusion-java] via GitHub
• Re: [PR] feat: add user-facing CometUDF registration for custom JVM UDFs [datafusion-comet] via GitHub
• [PR] chore: drop leftover JVM Parquet helpers and the native_datafusion scan name [datafusion-comet] via GitHub
  • Re: [PR] chore: drop leftover JVM Parquet helpers and the native_datafusion scan name [datafusion-comet] via GitHub
• Re: [PR] feat: Add experimental support for accelerated PyArrow UDFs [datafusion-comet] via GitHub
• [I] Add randomised fuzz harness for pyarrow UDF vector-copy path [datafusion-comet] via GitHub
• [PR] minor: move aqe executions plans to a directory [datafusion-ballista] via GitHub
  • Re: [PR] minor: move aqe executions plans to a directory [datafusion-ballista] via GitHub
• [I] Drop the per-batch Comet→Spark buffer copy in CometColumnarPythonInput [datafusion-comet] via GitHub
• [PR] chore: remove dead useDecimal128 plumbing [datafusion-comet] via GitHub
  • Re: [PR] chore: remove dead useDecimal128 plumbing [datafusion-comet] via GitHub
• [PR] Fix: Infer placeholder type from subquery [datafusion] via GitHub
  • Re: [PR] Fix: Infer placeholder type from subquery [datafusion] via GitHub
  • Re: [PR] Fix: Infer placeholder type from subquery [datafusion] via GitHub
  • Re: [PR] Fix: Infer placeholder type from subquery [datafusion] via GitHub
  • Re: [PR] Fix: Infer placeholder type from subquery [datafusion] via GitHub
  • Re: [PR] Fix: Infer placeholder type from subquery [datafusion] via GitHub
  • Re: [PR] Fix: Infer placeholder type from subquery [datafusion] via GitHub
  • Re: [PR] Fix: Infer placeholder type from subquery [datafusion] via GitHub
  • Re: [PR] Fix: Infer placeholder type from subquery [datafusion] via GitHub
  • Re: [PR] Fix: Infer placeholder type from subquery [datafusion] via GitHub
• [PR] MySQL: Add support for group by with rollup [datafusion-sqlparser-rs] via GitHub
  • Re: [PR] MySQL: Add support for group by with rollup [datafusion-sqlparser-rs] via GitHub
• [I] REST API to expose job runtime metrics [datafusion-ballista] via GitHub
  • Re: [I] REST API to expose job runtime metrics [datafusion-ballista] via GitHub
  • Re: [I] REST API to expose job runtime metrics [datafusion-ballista] via GitHub
• Re: [I] Add Parquet column index support [datafusion-comet] via GitHub
  • Re: [I] Add Parquet column index support [datafusion-comet] via GitHub
• Re: [I] perf: only check Parquet type once in NativeBatchReader [datafusion-comet] via GitHub
  • Re: [I] perf: only check Parquet type once in NativeBatchReader [datafusion-comet] via GitHub
• Re: [I] bitpacking is not using SIMD [datafusion-comet] via GitHub
  • Re: [I] bitpacking is not using SIMD [datafusion-comet] via GitHub
• [I] Iceberg 1.11 support [datafusion-comet] via GitHub
• Re: [PR] fix: reject readBatch(0) in ArrowConstantColumnReader [datafusion-comet] via GitHub
  • Re: [PR] fix: reject readBatch(0) in ArrowConstantColumnReader [datafusion-comet] via GitHub
• [I] Upgrade Spark 4.1.1 to 4.1.2 [datafusion-comet] via GitHub
• [I] Port `HashTableLookupExpr` to use `try_to_proto` / `try_from_proto` [datafusion] via GitHub
  • Re: [I] Port `HashTableLookupExpr` to use `try_to_proto` / `try_from_proto` [datafusion] via GitHub
  • Re: [I] Port `HashTableLookupExpr` to use `try_to_proto` / `try_from_proto` [datafusion] via GitHub
  • Re: [I] Port `HashTableLookupExpr` to use `try_to_proto` / `try_from_proto` [datafusion] via GitHub
  • Re: [I] Port `HashTableLookupExpr` to use `try_to_proto` / `try_from_proto` [datafusion] via GitHub
  • Re: [I] Port `HashTableLookupExpr` to use `try_to_proto` / `try_from_proto` [datafusion] via GitHub
• [I] Port `ScalarSubqueryExpr` to use `try_to_proto` / `try_from_proto` [datafusion] via GitHub
  • Re: [I] Port `ScalarSubqueryExpr` to use `try_to_proto` / `try_from_proto` [datafusion] via GitHub
  • Re: [I] Port `ScalarSubqueryExpr` to use `try_to_proto` / `try_from_proto` [datafusion] via GitHub
• [I] Port `DynamicFilterPhysicalExpr` to use `try_to_proto` / `try_from_proto` [datafusion] via GitHub
  • Re: [I] Port `DynamicFilterPhysicalExpr` to use `try_to_proto` / `try_from_proto` [datafusion] via GitHub
  • Re: [I] Port `DynamicFilterPhysicalExpr` to use `try_to_proto` / `try_from_proto` [datafusion] via GitHub
• [I] Port `LikeExpr` to use `try_to_proto` / `try_from_proto` [datafusion] via GitHub
  • Re: [I] Port `LikeExpr` to use `try_to_proto` / `try_from_proto` [datafusion] via GitHub
  • Re: [I] Port `LikeExpr` to use `try_to_proto` / `try_from_proto` [datafusion] via GitHub

• Earlier messages
• Later messages