This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch dependabot/pip/docs/sphinx-9.1.0
in repository https://gitbox.apache.org/repos/asf/datafusion.git
omit 0b393243d4 chore(deps): bump sphinx from 8.2.3 to 9.1.0 in /docs
add 52bbc8afcf chore(deps): bump insta from 1.45.0 to 1.46.0 (#19643)
add 47df535d2c chore(deps): bump taiki-e/install-action from 2.65.11 to
2.65.13 (#19646)
add c8620129f3 chore(deps): bump tracing from 0.1.43 to 0.1.44 (#19644)
add fd79241633 chore(deps): bump syn from 2.0.111 to 2.0.113 (#19645)
add ada0923a39 Respect execution timezone in to_timestamp and related
functions (#19078)
add 9b2505ce6a fix(doc): close #19393, make upgrading guide match v51 api
(#19648)
add 2d56253893 fix(spark): Use wrapping addition/subtraction in
`SparkDateAdd` and `SparkDateSub` (#19377)
add ff38480f22 Refactor `percentile_cont` to clarify support input types
(#19611)
add aee5cd9f35 fix(functions): Make translate function postgres compatible
(#19630)
add adf00a6495 Add a protection to release candidate branch 52 (#19660)
add 5c2ee3650d perf: optimize `HashTableLookupExpr::evaluate` (#19602)
add c3e1c3644a Downgrade aws-smithy-runtime, update `rust_decimal`, ignore
RUSTSEC-2026-0001 to get clean CI (#19657)
add 1037f0aa20 feat: add list_files_cache table function for
`datafusion-cli` (#19388)
add 924037ea04 perf: Improve performance of `split_part` (#19570)
add a2f02f069a fix: Return Int for Date - Date instead of duration (#19563)
add 7942e751cb Update dependencies (#19667)
add ed01b67f2d Refactor PartitionedFile: add ordering field and
new_from_meta constructor (#19596)
add e8196f462f Remove coalesce batches rule and deprecate
CoalesceBatchesExec (#19622)
add 166ef81121 Perf: Optimize `substring_index` via single-byte fast path
and direct indexing (#19590)
add 1f654bbe62 feat: implement metrics for AsyncFuncExec (#19626)
add ce08307a4c refactor: Use `Signature::coercible` for isnan/iszero
(#19604)
add 680ddcc6cb feat: split BatchPartitioner::try_new into hash and
round-robin constructors (#19668)
add 566bcde9e1 Parquet: Push down supported list predicates
(array_has/any/all) during decoding (#19545)
add 3a0ca4ef79 Remove dependency on `rust_decimal`, remove ignore of
`RUSTSEC-2026-0001` (#19666)
add 142f5972d5 Store example data directly inside the datafusion-examples
(#19141) (#19319)
add 35ff4ab0a0 Allow logical optimizer to be run without evaluating now()
& refactor SimplifyInfo (#19505)
add 646213ec7c feat: add Time type support to date_trunc function (#19640)
add 102caeb226 minor: More comments to `ParquetOpener::open()` (#19677)
add d18e670e78 feat: Allow log with non-integer base on decimals (#19372)
add 1d5d63c413 Feat: Allow pow with negative & non-integer exponent on
decimals (#19369)
add e6049de5a7 Make default ListingFilesCache table scoped (#19616)
add 5194fd5eb0 chore(deps): bump taiki-e/install-action from 2.65.13 to
2.65.15 (#19676)
add 0cf45cae9c Refactor cache APIs to support ordering information (#19597)
add b9a3b9f94f Record sort order when writing Parquet with WITH ORDER
(#19595)
add a55b77e7de fix: DynamicFilterPhysicalExpr violates Hash/Eq contract
(#19659)
add 62658cd624 implement var distinct (#19706)
add c98fa5616e perfect hash join (#19411)
add b7091c0d2f Optimize `Nullstate` / accumulators (#19625)
add 07e63edfa0 Fix TopK aggregation for UTF-8/Utf8View group keys and add
safe fallback for unsupported string aggregates (#19285)
add 8ba46466d3 docs: Fix two small issues in introduction.md (#19712)
add 209a0a2e86 fix: unnest struct field with an alias failed with internal
error (#19698)
add 20870da20d infer parquet file order from metadata and use it to
optimize scans (#19433)
add 5c2b1236b5 feat(spark): implement array_repeat function (#19702)
add 821d410fc0 feat(spark): Implement collect_list/collect_set aggregate
functions (#19699)
add 3087ca8a92 perf: optimize `NthValue` when `ignore_nulls` is true
(#19496)
add afc912106b Optimize `concat/concat_ws` scalar path by pre-allocating
memory (#19547)
add 45fb0b4b98 fix(accumulators): preserve state in evaluate() for window
frame queries (#19618)
add 458b49109a perf: optimize left function by eliminating double chars()
iteration (#19571)
add 4e0161d99c fix: Don't treat quoted column names as placeholder
variables in SQL (#19339)
add 013efb4fe1 docs: Refine Communication documentation to highlight
Discord (#19714)
add 41a0b85afa Add support for additional numeric types in to_timestamp
functions (#19663)
add 9fa7500bbc Fix internal error "Physical input schema should be the
same as the one converted from logical input schema." (#18412)
add 0c5c97b22a fix(functions-aggregate): drain CORR state vectors for
streaming aggregation (#19669)
add 30c6ff1982 chore: bump dependabot PR limit for cargo from 5 to 15
(#19730)
add 84ea07029f chore(deps): bump maturin from 1.10.2 to 1.11.5 in /docs
(#19740)
add 2067324f17 chore(deps): bump taiki-e/install-action from 2.65.15 to
2.66.1 (#19741)
add c03606547d chore(deps): bump sqllogictest from 0.28.4 to 0.29.0
(#19744)
add 4ca82cfdbf chore(deps): bump blake3 from 1.8.2 to 1.8.3 (#19746)
add 1ddc639fae chore(deps): bump libc from 0.2.179 to 0.2.180 (#19748)
add 1c37638113 chore(deps): bump async-compression from 0.4.36 to 0.4.37
(#19742)
add f9697c14e2 chore(deps): bump indexmap from 2.12.1 to 2.13.0 (#19747)
add d103d8886f chore: remove LZO Parquet compression (#19726)
add bd2f348059 Improve comment for predicate_cache_inner_records (#19762)
add 383e673ac3 Update 52.0.0 release version number and changelog (#19767)
add 2fb9fb3fb9 Update the upgrading.md (#19769)
add 278950a764 Fix dynamic filter is_used function (#19734)
add 7716cae504 chore: update copyright notice year (#19758)
add cb9ec127e6 slt: Add test for REE arrays in group by (#19763)
add d484c09baf perf: Optimize floor and ceil scalar performance (#19752)
add e8efd59203 chore(deps): Update sqlparser to 0.60 (#19672)
add 803cce881b feat: implement Spark size function for arrays and maps
(#19592)
add 36880d89f7 Fix run_tpcds data dir (#19771)
add ec974ee5f1 chore(deps): bump taiki-e/install-action from 2.66.1 to
2.66.2 (#19778)
add f60b68a28c Include .proto files in datafusion-proto distribution
(#19490)
add e076e59b2b Simplify `expr = L1 AND expr != L2` to `expr = L1` when `L1
!= L2` (#19731)
add 4e1bc79e00 fix: enhance CTE resolution with identifier normalization
(#19519)
add 4c67d02089 feat: Add null-aware anti join support (#19635)
add 6267feef81 chore(deps): bump flate2 from 1.1.5 to 1.1.8 (#19780)
add 617700d1b3 Upgrade DataFusion to arrow-rs/parquet 57.2.0 (#19355)
add 2f10d453f3 Expose Spilling Progress Interface in DataFusion (#19708)
add 1d19c52852 perf: improve performance of `spark hex` function (#19738)
add 6bf5e98b59 dev: Add a script to auto fix all lint violations (#19560)
add 567ba75840 doc: Add an auto-generated dependency graph for internal
crates (#19280)
add 429f5a792f refactor: Optimize `required_columns` from `BTreeSet` to
`Vec` in struct `PushdownChecker` (#19678)
add 472a729afc Revert Workround for Empty FixedSizeBinary Values Buffer
After arrow-rs Upgrade (#19801)
add 79869a7537 feat: support Set Comparison Subquery (#19109)
add c4f039f53b chore(deps): bump taiki-e/install-action from 2.66.2 to
2.66.3 (#19802)
add f73da4da38 Add Reproducer for Issues with LEFT joins on Fixed Size
Binary Columns (#19800)
add 154ab70040 feat(spark): implement array slice function (#19811)
add 0808f3a8d2 Improvements to `list_files_cache` table function (#19703)
add eadbed51b5 perf: Optimize initcap scalar performance (#19776)
add a414ea078d Issue 19781 : Internal error: Assertion failed:
!self.finished: LimitedBatchCoalescer (#19785)
add c173de1fc4 fix: expose `ListFilesEntry` (#19804)
add 094e7ee90a physical plan: add `reset_plan_states `, plan re-use
benchmark (#19806)
add 6f92ea6005 chore(deps): bump actions/setup-node from 6.1.0 to 6.2.0
(#19825)
add de40f0c9f5 Docs: Fix some links in docs (#19834)
add 54b848c077 feat(spark): implement substring function (#19805)
add 7c9a76acf1 Use correct setting for click bench queries in sql_planner
benchmark (#19835)
add 5d68b751c0 fix: trunc function with precision uses round instead of
trunc semantics (#19794)
add 14d919ddaa chore(deps): bump taiki-e/install-action from 2.66.3 to
2.66.5 (#19824)
add 1441269429 chore: refactor scalarvalue/encoding using available
upstream arrow-rs methods (#19797)
add 7b0ed2d616 Refactor Spark `date_add`/`date_sub`/`bitwise_not` to
remove unnecessary scalar arg check (#19473)
add 444ddf2e1c Add BatchAdapter to simplify using PhysicalExprAdapter /
Projector to map RecordBatch between schemas (#19716)
add 5edda9b309 fix: calculate total seconds from interval fields for
`extract(epoch)` (#19807)
add ca904b3086 Row group limit pruning for row groups that entirely match
predicates (#18868)
add 9208f12873 [Minor] Reuse indices buffer in RepartitionExec (#19775)
add 5e893ab921 fix: predicate cache stats calculation (#19561)
add f3f6dec7c9 feat: Add support for 'isoyear' in date_part function
(#19821)
add c91dcfdb6a Docs: add additional links to blog posts (#19833)
add ab81d3bd2b Fix(optimizer): Make `EnsureCooperative` optimizer
idempotent under multiple runs (#19757)
add ac67ae4af5 Ensure null inputs to array setop functions return null
output (#19683)
add 8afccc9510 Allow dropping qualified columns (#19549)
add 0c959d6d91 Doc: Add more blog links to doc comments (#19837)
add 3d90d4b601 datafusion/common: Add support for hashing ListView arrays
(#19814)
add e353eb08fb Project sort expressions in StreamingTable (#19719)
add 1ab7e4184e Fix grouping set subset satisfaction (#19853)
add 3ea21aa332 perf: Optimize trunc scalar performance (#19788)
add 67fbf2d437 chore(deps): bump sphinx from 8.2.3 to 9.1.0 in /docs
This update added new revisions after undoing existing revisions.
That is to say, some revisions that were in the old version of the
branch are not in the new version. This situation occurs
when a user --force pushes a change and generates a repository
containing something like this:
* -- * -- B -- O -- O -- O (0b393243d4)
\
N -- N -- N refs/heads/dependabot/pip/docs/sphinx-9.1.0
(67fbf2d437)
You should already have received notification emails for all of the O
revisions, and so the following emails describe only the N revisions
from the common base, B.
Any revisions marked "omit" are not gone; other references still
refer to them. Any revisions marked "discard" are gone forever.
No new revisions were added by this update.
Summary of changes:
.asf.yaml | 3 +
.github/dependabot.yml | 1 +
.github/workflows/audit.yml | 4 +-
.github/workflows/dependencies.yml | 2 +-
.github/workflows/dev.yml | 2 +-
.github/workflows/docs.yaml | 6 +
.github/workflows/docs_pr.yaml | 7 +-
.github/workflows/rust.yml | 6 +-
Cargo.lock | 1378 ++++++++------------
Cargo.toml | 98 +-
NOTICE.txt | 2 +-
benchmarks/bench.sh | 8 +-
benchmarks/compare.py | 20 +-
benchmarks/src/hj.rs | 410 ++++--
ci/scripts/doc_prettier_check.sh | 85 +-
ci/scripts/license_header.sh | 62 +-
ci/scripts/rust_clippy.sh | 59 +-
ci/scripts/rust_docs.sh | 1 +
ci/scripts/rust_fmt.sh | 51 +-
ci/scripts/rust_toml_fmt.sh | 55 +-
ci/scripts/typos_check.sh | 55 +-
ci/scripts/{rust_fmt.sh => utils/git.sh} | 10 +-
datafusion-cli/src/functions.rs | 190 ++-
datafusion-cli/src/main.rs | 113 +-
datafusion-examples/Cargo.toml | 15 +-
datafusion-examples/README.md | 9 +-
datafusion-examples/data/README.md | 25 +
.../data => datafusion-examples/data/csv}/cars.csv | 0
.../data/csv}/regex.csv | 0
.../examples/builtin_functions/function_factory.rs | 4 +-
.../examples/builtin_functions/regexp.rs | 31 +-
.../examples/custom_data_source/csv_json_opener.rs | 32 +-
.../custom_data_source/csv_sql_streaming.rs | 19 +-
.../examples/data_io/parquet_encrypted.rs | 32 +-
.../examples/data_io/parquet_exec_visitor.rs | 24 +-
.../examples/dataframe/cache_factory.rs | 42 +-
.../examples/dataframe/dataframe.rs | 84 +-
.../examples/dataframe/deserialize_to_struct.rs | 321 ++++-
datafusion-examples/examples/dataframe/main.rs | 2 +-
.../examples/execution_monitoring/tracing.rs | 34 +-
datafusion-examples/examples/flight/client.rs | 17 +-
datafusion-examples/examples/flight/server.rs | 38 +-
datafusion-examples/examples/flight/sql_server.rs | 25 +-
.../examples/query_planning/expr_api.rs | 13 +-
.../examples/query_planning/parse_sql_expr.rs | 70 +-
.../examples/query_planning/plan_to_sql.rs | 80 +-
.../examples/query_planning/planner_api.rs | 23 +-
.../examples/query_planning/thread_pools.rs | 14 +-
.../examples/relation_planner/match_recognize.rs | 6 +-
.../examples/relation_planner/pivot_unpivot.rs | 10 +-
.../examples/relation_planner/table_sample.rs | 18 +-
datafusion-examples/examples/sql_ops/query.rs | 64 +-
datafusion-examples/examples/udf/advanced_udaf.rs | 15 +-
datafusion-examples/examples/udf/advanced_udwf.rs | 49 +-
datafusion-examples/examples/udf/async_udf.rs | 3 +-
datafusion-examples/examples/udf/simple_udtf.rs | 27 +-
.../mod.rs => datafusion-examples/src/lib.rs | 4 +-
datafusion-examples/src/utils/csv_to_parquet.rs | 245 ++++
.../src/utils/datasets/cars.rs | 16 +-
datafusion-examples/src/utils/datasets/mod.rs | 139 ++
.../src/utils/datasets/regex.rs | 22 +-
.../src/utils}/mod.rs | 5 +-
datafusion/catalog-listing/src/helpers.rs | 1 +
datafusion/catalog-listing/src/table.rs | 336 ++++-
datafusion/catalog/src/streaming.rs | 26 +-
datafusion/common/Cargo.toml | 2 +-
datafusion/common/src/config.rs | 23 +-
datafusion/common/src/dfschema.rs | 6 +
.../common/src/file_options/parquet_writer.rs | 6 +-
datafusion/common/src/hash_utils.rs | 152 ++-
datafusion/common/src/metadata.rs | 4 +
datafusion/common/src/scalar/mod.rs | 51 +-
datafusion/core/Cargo.toml | 5 +
datafusion/core/benches/reset_plan_states.rs | 198 +++
datafusion/core/benches/sql_planner.rs | 5 +
datafusion/core/benches/topk_aggregate.rs | 87 +-
datafusion/core/src/dataframe/mod.rs | 70 +-
datafusion/core/src/datasource/file_format/mod.rs | 12 +-
datafusion/core/src/datasource/listing/table.rs | 2 +-
.../core/src/datasource/listing_table_factory.rs | 3 +-
datafusion/core/src/datasource/mod.rs | 9 +-
.../core/src/datasource/physical_plan/parquet.rs | 84 +-
datafusion/core/src/execution/context/mod.rs | 35 +-
datafusion/core/src/execution/session_state.rs | 57 +-
datafusion/core/src/physical_planner.rs | 5 +
datafusion/core/src/test_util/parquet.rs | 15 +-
datafusion/core/tests/dataframe/mod.rs | 106 +-
datafusion/core/tests/execution/coop.rs | 46 +-
datafusion/core/tests/expr_api/mod.rs | 5 +-
datafusion/core/tests/expr_api/simplification.rs | 156 ++-
datafusion/core/tests/fuzz_cases/join_fuzz.rs | 1 +
datafusion/core/tests/parquet/custom_reader.rs | 10 +-
datafusion/core/tests/parquet/filter_pushdown.rs | 16 +
datafusion/core/tests/parquet/mod.rs | 106 +-
datafusion/core/tests/parquet/ordering.rs | 103 ++
datafusion/core/tests/parquet/page_pruning.rs | 9 +-
datafusion/core/tests/parquet/row_group_pruning.rs | 339 ++++-
.../physical_optimizer/aggregate_statistics.rs | 86 ++
.../physical_optimizer/enforce_distribution.rs | 11 +-
.../tests/physical_optimizer/enforce_sorting.rs | 79 +-
.../physical_optimizer/filter_pushdown/mod.rs | 321 ++---
.../tests/physical_optimizer/join_selection.rs | 10 +
.../tests/physical_optimizer/limit_pushdown.rs | 84 +-
.../physical_optimizer/partition_statistics.rs | 38 -
.../physical_optimizer/projection_pushdown.rs | 57 +-
.../core/tests/physical_optimizer/pushdown_sort.rs | 76 +-
.../replace_with_order_preserving_variants.rs | 229 ++--
.../core/tests/physical_optimizer/test_utils.rs | 9 +-
datafusion/core/tests/set_comparison.rs | 193 +++
datafusion/core/tests/sql/explain_analyze.rs | 1 -
datafusion/core/tests/sql/unparser.rs | 4 +
.../core/tests/user_defined/relation_planner.rs | 16 +-
.../user_defined_async_scalar_functions.rs | 40 +-
.../user_defined/user_defined_scalar_functions.rs | 19 +-
datafusion/datasource-arrow/NOTICE.txt | 2 +-
.../datasource-avro/src/avro_to_arrow/schema.rs | 4 +-
datafusion/datasource-parquet/Cargo.toml | 7 +
.../benches/parquet_nested_filter_pushdown.rs | 238 ++++
datafusion/datasource-parquet/src/access_plan.rs | 4 +
datafusion/datasource-parquet/src/file_format.rs | 92 +-
datafusion/datasource-parquet/src/metadata.rs | 142 +-
datafusion/datasource-parquet/src/metrics.rs | 37 +-
datafusion/datasource-parquet/src/mod.rs | 1 +
datafusion/datasource-parquet/src/opener.rs | 70 +-
datafusion/datasource-parquet/src/row_filter.rs | 508 +++++++-
.../datasource-parquet/src/row_group_filter.rs | 228 +++-
datafusion/datasource-parquet/src/source.rs | 1 +
.../datasource-parquet/src/supported_predicates.rs | 144 ++
datafusion/datasource/Cargo.toml | 2 +-
datafusion/datasource/src/display.rs | 9 +-
datafusion/datasource/src/file_format.rs | 76 ++
datafusion/datasource/src/file_scan_config.rs | 105 +-
datafusion/datasource/src/mod.rs | 44 +
datafusion/datasource/src/schema_adapter.rs | 24 +-
datafusion/datasource/src/source.rs | 17 +
datafusion/datasource/src/url.rs | 94 +-
datafusion/execution/Cargo.toml | 1 +
datafusion/execution/src/cache/cache_manager.rs | 185 ++-
datafusion/execution/src/cache/cache_unit.rs | 454 +++++--
.../execution/src/cache/file_metadata_cache.rs | 429 +++---
datafusion/execution/src/cache/list_files_cache.rs | 922 +++++++------
datafusion/execution/src/cache/mod.rs | 49 +-
datafusion/execution/src/disk_manager.rs | 31 +-
datafusion/execution/src/runtime_env.rs | 7 +-
datafusion/expr-common/src/accumulator.rs | 23 +-
datafusion/expr-common/src/groups_accumulator.rs | 3 +
datafusion/expr-common/src/type_coercion/binary.rs | 18 +
datafusion/expr/src/execution_props.rs | 16 +-
datafusion/expr/src/expr.rs | 100 +-
datafusion/expr/src/expr_schema.rs | 38 +-
datafusion/expr/src/function.rs | 8 +-
datafusion/expr/src/logical_plan/builder.rs | 23 +
datafusion/expr/src/logical_plan/invariants.rs | 20 +-
datafusion/expr/src/logical_plan/plan.rs | 24 +
datafusion/expr/src/logical_plan/tree_node.rs | 23 +-
datafusion/expr/src/partition_evaluator.rs | 4 +
datafusion/expr/src/planner.rs | 21 +-
datafusion/expr/src/simplify.rs | 120 +-
datafusion/expr/src/tree_node.rs | 20 +-
datafusion/expr/src/udaf.rs | 2 +-
datafusion/expr/src/udf.rs | 8 +-
datafusion/expr/src/udwf.rs | 2 +-
datafusion/expr/src/utils.rs | 1 +
.../src/aggregate/groups_accumulator/accumulate.rs | 214 ++-
.../src/aggregate/groups_accumulator/bool_op.rs | 2 +-
.../src/aggregate/groups_accumulator/prim_op.rs | 5 +-
datafusion/functions-aggregate/src/array_agg.rs | 2 +-
datafusion/functions-aggregate/src/average.rs | 21 +-
datafusion/functions-aggregate/src/correlation.rs | 62 +-
datafusion/functions-aggregate/src/count.rs | 4 +-
.../functions-aggregate/src/percentile_cont.rs | 505 ++++---
datafusion/functions-aggregate/src/string_agg.rs | 13 +-
datafusion/functions-aggregate/src/variance.rs | 144 +-
datafusion/functions-nested/src/array_has.rs | 21 +-
datafusion/functions-nested/src/except.rs | 51 +-
datafusion/functions-nested/src/planner.rs | 16 +-
datafusion/functions-nested/src/set_ops.rs | 109 +-
datafusion/functions-window/Cargo.toml | 8 +
datafusion/functions-window/benches/nth_value.rs | 263 ++++
datafusion/functions-window/src/nth_value.rs | 182 +--
datafusion/functions/Cargo.toml | 18 +-
datafusion/functions/benches/concat.rs | 100 +-
.../functions/benches/{concat.rs => concat_ws.rs} | 64 +-
datafusion/functions/benches/floor_ceil.rs | 135 ++
datafusion/functions/benches/initcap.rs | 125 +-
datafusion/functions/benches/split_part.rs | 382 ++++++
datafusion/functions/benches/substr_index.rs | 124 +-
datafusion/functions/benches/to_timestamp.rs | 24 +-
datafusion/functions/benches/trunc.rs | 48 +-
datafusion/functions/src/core/arrow_cast.rs | 4 +-
datafusion/functions/src/core/coalesce.rs | 4 +-
datafusion/functions/src/core/getfield.rs | 2 +-
datafusion/functions/src/core/nvl.rs | 4 +-
datafusion/functions/src/core/nvl2.rs | 4 +-
datafusion/functions/src/core/union_extract.rs | 5 +-
datafusion/functions/src/datetime/common.rs | 153 ++-
datafusion/functions/src/datetime/current_date.rs | 23 +-
datafusion/functions/src/datetime/current_time.rs | 65 +-
datafusion/functions/src/datetime/date_part.rs | 32 +-
datafusion/functions/src/datetime/date_trunc.rs | 284 ++--
datafusion/functions/src/datetime/mod.rs | 46 +-
datafusion/functions/src/datetime/now.rs | 18 +-
datafusion/functions/src/datetime/to_date.rs | 6 +-
datafusion/functions/src/datetime/to_timestamp.rs | 1007 +++++++++++---
datafusion/functions/src/datetime/to_unixtime.rs | 2 +-
datafusion/functions/src/encoding/inner.rs | 93 +-
datafusion/functions/src/macros.rs | 29 +
datafusion/functions/src/math/ceil.rs | 46 +-
datafusion/functions/src/math/floor.rs | 46 +-
datafusion/functions/src/math/iszero.rs | 32 +-
datafusion/functions/src/math/log.rs | 249 ++--
datafusion/functions/src/math/nans.rs | 32 +-
datafusion/functions/src/math/nanvl.rs | 27 +-
datafusion/functions/src/math/power.rs | 325 ++++-
datafusion/functions/src/math/trunc.rs | 59 +-
datafusion/functions/src/regex/regexplike.rs | 4 +-
datafusion/functions/src/string/concat.rs | 11 +-
datafusion/functions/src/string/concat_ws.rs | 35 +-
datafusion/functions/src/string/split_part.rs | 38 +-
datafusion/functions/src/string/starts_with.rs | 9 +-
datafusion/functions/src/unicode/initcap.rs | 35 +-
datafusion/functions/src/unicode/left.rs | 15 +-
datafusion/functions/src/unicode/substr.rs | 4 +-
datafusion/functions/src/unicode/substrindex.rs | 70 +-
datafusion/functions/src/unicode/translate.rs | 15 +-
datafusion/macros/Cargo.toml | 2 +-
datafusion/optimizer/src/analyzer/type_coercion.rs | 41 +-
datafusion/optimizer/src/decorrelate.rs | 10 +-
.../src/decorrelate_predicate_subquery.rs | 72 +-
datafusion/optimizer/src/eliminate_cross_join.rs | 3 +
datafusion/optimizer/src/eliminate_outer_join.rs | 1 +
.../optimizer/src/extract_equijoin_predicate.rs | 4 +
datafusion/optimizer/src/lib.rs | 1 +
.../optimizer/src/optimize_projections/mod.rs | 13 +-
datafusion/optimizer/src/optimizer.rs | 30 +-
datafusion/optimizer/src/push_down_filter.rs | 1 +
datafusion/optimizer/src/rewrite_set_comparison.rs | 171 +++
.../src/simplify_expressions/expr_simplifier.rs | 214 +--
.../optimizer/src/simplify_expressions/mod.rs | 2 +-
.../src/simplify_expressions/simplify_exprs.rs | 13 +-
.../src/simplify_expressions/simplify_literal.rs | 7 +-
.../src/simplify_expressions/unwrap_cast.rs | 22 +-
.../optimizer/src/simplify_expressions/utils.rs | 48 +
datafusion/physical-expr-adapter/src/lib.rs | 5 +-
.../physical-expr-adapter/src/schema_rewriter.rs | 348 +++++
.../physical-expr-common/src/metrics/value.rs | 40 +-
datafusion/physical-expr/src/expressions/binary.rs | 94 ++
.../src/expressions/dynamic_filters.rs | 139 +-
.../physical-optimizer/src/coalesce_batches.rs | 87 --
.../physical-optimizer/src/enforce_distribution.rs | 23 +-
.../physical-optimizer/src/enforce_sorting/mod.rs | 10 +-
datafusion/physical-optimizer/src/ensure_coop.rs | 328 ++++-
.../physical-optimizer/src/join_selection.rs | 28 +-
datafusion/physical-optimizer/src/lib.rs | 1 -
.../physical-optimizer/src/limit_pushdown.rs | 27 +-
datafusion/physical-optimizer/src/optimizer.rs | 4 -
.../physical-optimizer/src/topk_aggregation.rs | 21 +-
datafusion/physical-plan/Cargo.toml | 1 +
datafusion/physical-plan/src/aggregates/mod.rs | 70 +-
.../src/aggregates/topk/hash_table.rs | 178 +--
.../physical-plan/src/aggregates/topk/heap.rs | 192 ++-
.../src/aggregates/topk/priority_map.rs | 103 ++
.../physical-plan/src/aggregates/topk_stream.rs | 14 +
datafusion/physical-plan/src/async_func.rs | 10 +-
datafusion/physical-plan/src/coalesce/mod.rs | 4 +
datafusion/physical-plan/src/coalesce_batches.rs | 7 +
.../physical-plan/src/coalesce_partitions.rs | 13 +
datafusion/physical-plan/src/coop.rs | 5 +
datafusion/physical-plan/src/execution_plan.rs | 38 +
datafusion/physical-plan/src/filter.rs | 91 +-
datafusion/physical-plan/src/joins/array_map.rs | 547 ++++++++
datafusion/physical-plan/src/joins/chain.rs | 69 +
.../physical-plan/src/joins/hash_join/exec.rs | 1293 +++++++++++++++---
.../src/joins/hash_join/partitioned_hash_eval.rs | 227 ++--
.../src/joins/hash_join/shared_bounds.rs | 29 +-
.../physical-plan/src/joins/hash_join/stream.rs | 163 ++-
.../physical-plan/src/joins/join_hash_map.rs | 111 +-
datafusion/physical-plan/src/joins/mod.rs | 27 +
.../physical-plan/src/joins/stream_join_utils.rs | 14 +-
datafusion/physical-plan/src/joins/test_utils.rs | 1 +
datafusion/physical-plan/src/limit.rs | 29 +
datafusion/physical-plan/src/projection.rs | 13 +
datafusion/physical-plan/src/recursive_query.rs | 16 +-
datafusion/physical-plan/src/repartition/mod.rs | 170 ++-
.../src/sorts/sort_preserving_merge.rs | 31 +-
.../src/spill/in_progress_spill_file.rs | 29 +-
datafusion/physical-plan/src/spill/mod.rs | 74 +-
datafusion/physical-plan/src/spill/spill_pool.rs | 10 +-
datafusion/physical-plan/src/test.rs | 2 +-
datafusion/physical-plan/src/topk/mod.rs | 3 +
datafusion/proto-common/src/from_proto/mod.rs | 21 +-
datafusion/proto/Cargo.toml | 3 -
datafusion/proto/proto/datafusion.proto | 1 +
datafusion/proto/src/generated/pbjson.rs | 18 +
datafusion/proto/src/generated/prost.rs | 2 +
datafusion/proto/src/logical_plan/to_proto.rs | 1 +
datafusion/proto/src/physical_plan/from_proto.rs | 61 +-
datafusion/proto/src/physical_plan/mod.rs | 6 +
.../proto/tests/cases/roundtrip_logical_plan.rs | 12 +-
.../proto/tests/cases/roundtrip_physical_plan.rs | 20 +-
datafusion/pruning/src/pruning_predicate.rs | 1 -
datafusion/spark/Cargo.toml | 14 +
datafusion/spark/benches/hex.rs | 152 +++
.../array_slice.rs => spark/benches/slice.rs} | 59 +-
.../substr.rs => spark/benches/substring.rs} | 4 +-
datafusion/spark/src/function/aggregate/collect.rs | 200 +++
datafusion/spark/src/function/aggregate/mod.rs | 19 +-
datafusion/spark/src/function/array/mod.rs | 16 +-
datafusion/spark/src/function/array/repeat.rs | 128 ++
datafusion/spark/src/function/array/slice.rs | 172 +++
.../spark/src/function/bitwise/bitwise_not.rs | 52 +-
datafusion/spark/src/function/collection/mod.rs | 13 +-
datafusion/spark/src/function/collection/size.rs | 162 +++
datafusion/spark/src/function/conditional/if.rs | 2 +-
datafusion/spark/src/function/datetime/date_add.rs | 54 +-
datafusion/spark/src/function/datetime/date_sub.rs | 51 +-
datafusion/spark/src/function/math/hex.rs | 231 ++--
datafusion/spark/src/function/mod.rs | 1 +
datafusion/spark/src/function/null_utils.rs | 122 ++
datafusion/spark/src/function/string/concat.rs | 110 +-
datafusion/spark/src/function/string/mod.rs | 8 +
datafusion/spark/src/function/string/substring.rs | 258 ++++
datafusion/spark/src/lib.rs | 1 +
.../src/datetime => spark/src}/planner.rs | 9 +-
datafusion/sql/Cargo.toml | 1 +
datafusion/sql/src/expr/identifier.rs | 4 +-
datafusion/sql/src/expr/mod.rs | 62 +-
datafusion/sql/src/expr/subquery.rs | 51 +-
datafusion/sql/src/planner.rs | 2 +-
datafusion/sql/src/query.rs | 1 +
datafusion/sql/src/relation/mod.rs | 8 +-
datafusion/sql/src/resolve.rs | 162 ++-
datafusion/sql/src/statement.rs | 192 +--
datafusion/sql/src/unparser/expr.rs | 29 +-
datafusion/sql/src/unparser/plan.rs | 1 +
datafusion/sql/src/utils.rs | 25 +-
datafusion/sql/src/values.rs | 8 +-
datafusion/sql/tests/common/mod.rs | 12 +-
datafusion/sql/tests/sql_integration.rs | 37 +
datafusion/sqllogictest/Cargo.toml | 5 +-
datafusion/sqllogictest/src/engines/conversion.rs | 6 +-
.../src/engines/postgres_engine/mod.rs | 131 +-
.../src/engines/postgres_engine/types.rs | 45 -
datafusion/sqllogictest/src/test_context.rs | 125 +-
datafusion/sqllogictest/test_files/aggregate.slt | 431 +++++-
.../sqllogictest/test_files/aggregates_topk.slt | 88 ++
datafusion/sqllogictest/test_files/array.slt | 68 +-
datafusion/sqllogictest/test_files/async_udf.slt | 12 +-
datafusion/sqllogictest/test_files/case.slt | 5 +-
.../test_files/cte_quoted_reference.slt | 70 +
.../test_files/datetime/arith_date_date.slt | 11 +-
.../sqllogictest/test_files/datetime/date_part.slt | 102 ++
.../sqllogictest/test_files/datetime/dates.slt | 14 +-
.../test_files/datetime/timestamps.slt | 897 ++++++++++++-
datafusion/sqllogictest/test_files/decimal.slt | 40 +-
datafusion/sqllogictest/test_files/explain.slt | 8 +-
.../test_files/grouping_set_repartition.slt | 246 ++++
.../sqllogictest/test_files/information_schema.slt | 61 +-
datafusion/sqllogictest/test_files/join.slt.part | 8 +-
datafusion/sqllogictest/test_files/joins.slt | 71 +-
datafusion/sqllogictest/test_files/limit.slt | 2 +-
.../sqllogictest/test_files/limit_pruning.slt | 81 ++
.../test_files/limit_single_row_batches.slt | 22 +
datafusion/sqllogictest/test_files/metadata.slt | 38 +
.../test_files/null_aware_anti_join.slt | 453 +++++++
.../test_files/parquet_filter_pushdown.slt | 111 ++
.../sqllogictest/test_files/run_end_encoded.slt | 57 +
datafusion/sqllogictest/test_files/scalar.slt | 2 +-
.../sqllogictest/test_files/simplify_expr.slt | 18 +
.../test_files/spark/aggregate/collect.slt | 93 ++
.../test_files/spark/array/array_repeat.slt | 77 +-
.../sqllogictest/test_files/spark/array/slice.slt | 101 ++
.../test_files/spark/collection/size.slt | 132 ++
.../test_files/spark/datetime/date_add.slt | 12 +-
.../sqllogictest/test_files/spark/hash/crc32.slt | 6 +-
.../test_files/spark/string/substr.slt | 37 -
.../test_files/spark/string/substring.slt | 206 ++-
.../test_files/string/string_query.slt.part | 10 +-
datafusion/sqllogictest/test_files/struct.slt | 39 +-
datafusion/sqllogictest/test_files/subquery.slt | 61 +-
.../test_files/to_timestamp_timezone.slt | 204 +++
.../test_files/tpch/plans/q16.slt.part | 29 +-
datafusion/sqllogictest/test_files/unnest.slt | 30 +-
.../src/logical_plan/consumer/expr/subquery.rs | 56 +-
.../src/logical_plan/producer/expr/mod.rs | 1 +
.../src/logical_plan/producer/expr/subquery.rs | 56 +-
.../logical_plan/producer/substrait_producer.rs | 19 +-
datafusion/substrait/src/physical_plan/consumer.rs | 12 +-
.../tests/cases/roundtrip_logical_plan.rs | 80 +-
datafusion/wasmtest/src/lib.rs | 11 +-
dev/changelog/52.0.0.md | 745 +++++++++++
dev/rust_lint.sh | 127 +-
docs/.gitignore | 4 +
docs/README.md | 5 +
docs/build.sh | 9 +-
docs/requirements.txt | 2 +-
docs/scripts/generate_dependency_graph.sh | 97 ++
.../architecture/dependency-graph.md | 180 +++
docs/source/contributor-guide/communication.md | 68 +-
docs/source/index.rst | 4 +-
docs/source/library-user-guide/extending-sql.md | 5 +
.../library-user-guide/functions/adding-udfs.md | 4 +
docs/source/library-user-guide/query-optimizer.md | 16 +-
docs/source/library-user-guide/upgrading.md | 271 ++--
docs/source/user-guide/cli/functions.md | 50 +
docs/source/user-guide/concepts-readings-events.md | 28 +
docs/source/user-guide/configs.md | 6 +-
docs/source/user-guide/explain-usage.md | 1 +
docs/source/user-guide/introduction.md | 5 +-
docs/source/user-guide/sql/data_types.md | 5 +
docs/source/user-guide/sql/format_options.md | 64 +-
docs/source/user-guide/sql/scalar_functions.md | 98 +-
412 files changed, 24451 insertions(+), 7261 deletions(-)
copy ci/scripts/{rust_fmt.sh => utils/git.sh} (73%)
mode change 100755 => 100644
create mode 100644 datafusion-examples/data/README.md
copy {datafusion/core/tests/data => datafusion-examples/data/csv}/cars.csv
(100%)
copy {datafusion/physical-expr/tests/data =>
datafusion-examples/data/csv}/regex.csv (100%)
copy datafusion/physical-expr/src/statistics/mod.rs =>
datafusion-examples/src/lib.rs (91%)
create mode 100644 datafusion-examples/src/utils/csv_to_parquet.rs
copy datafusion/spark/src/function/collection/mod.rs =>
datafusion-examples/src/utils/datasets/cars.rs (66%)
create mode 100644 datafusion-examples/src/utils/datasets/mod.rs
copy datafusion/spark/src/function/conditional/mod.rs =>
datafusion-examples/src/utils/datasets/regex.rs (67%)
copy {datafusion/physical-expr/src/statistics =>
datafusion-examples/src/utils}/mod.rs (90%)
create mode 100644 datafusion/core/benches/reset_plan_states.rs
create mode 100644 datafusion/core/tests/parquet/ordering.rs
create mode 100644 datafusion/core/tests/set_comparison.rs
create mode 100644
datafusion/datasource-parquet/benches/parquet_nested_filter_pushdown.rs
create mode 100644 datafusion/datasource-parquet/src/supported_predicates.rs
create mode 100644 datafusion/functions-window/benches/nth_value.rs
copy datafusion/functions/benches/{concat.rs => concat_ws.rs} (56%)
create mode 100644 datafusion/functions/benches/floor_ceil.rs
create mode 100644 datafusion/functions/benches/split_part.rs
create mode 100644 datafusion/optimizer/src/rewrite_set_comparison.rs
delete mode 100644 datafusion/physical-optimizer/src/coalesce_batches.rs
create mode 100644 datafusion/physical-plan/src/joins/array_map.rs
create mode 100644 datafusion/physical-plan/src/joins/chain.rs
create mode 100644 datafusion/spark/benches/hex.rs
copy datafusion/{functions-nested/benches/array_slice.rs =>
spark/benches/slice.rs} (73%)
copy datafusion/{functions/benches/substr.rs => spark/benches/substring.rs}
(98%)
create mode 100644 datafusion/spark/src/function/aggregate/collect.rs
create mode 100644 datafusion/spark/src/function/array/repeat.rs
create mode 100644 datafusion/spark/src/function/array/slice.rs
create mode 100644 datafusion/spark/src/function/collection/size.rs
create mode 100644 datafusion/spark/src/function/null_utils.rs
create mode 100644 datafusion/spark/src/function/string/substring.rs
copy datafusion/{functions/src/datetime => spark/src}/planner.rs (82%)
delete mode 100644 datafusion/sqllogictest/src/engines/postgres_engine/types.rs
create mode 100644 datafusion/sqllogictest/test_files/cte_quoted_reference.slt
create mode 100644
datafusion/sqllogictest/test_files/grouping_set_repartition.slt
create mode 100644 datafusion/sqllogictest/test_files/limit_pruning.slt
create mode 100644
datafusion/sqllogictest/test_files/limit_single_row_batches.slt
create mode 100644 datafusion/sqllogictest/test_files/null_aware_anti_join.slt
create mode 100644 datafusion/sqllogictest/test_files/run_end_encoded.slt
create mode 100644
datafusion/sqllogictest/test_files/spark/aggregate/collect.slt
create mode 100644 datafusion/sqllogictest/test_files/spark/array/slice.slt
create mode 100644 datafusion/sqllogictest/test_files/spark/collection/size.slt
delete mode 100644 datafusion/sqllogictest/test_files/spark/string/substr.slt
create mode 100644 datafusion/sqllogictest/test_files/to_timestamp_timezone.slt
create mode 100644 dev/changelog/52.0.0.md
create mode 100755 docs/scripts/generate_dependency_graph.sh
create mode 100644
docs/source/contributor-guide/architecture/dependency-graph.md
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
