fix: remove unused parquet dep from proto-common, regenerate configs.md

kszucs · kszucs · commit db1bf5d8e7ca · 2026-03-28T13:32:17.000+01:00
diff --git a/Cargo.lock b/Cargo.lock
diff --git a/datafusion/proto-common/Cargo.toml b/datafusion/proto-common/Cargo.toml
@@ -37,12 +37,11 @@ name = "datafusion_proto_common"
 [features]
 default = []
 json = ["serde", "pbjson"]
-parquet = ["datafusion-common/parquet", "dep:parquet"]
+parquet = ["datafusion-common/parquet"]
 
 [dependencies]
 arrow = { workspace = true }
 datafusion-common = { workspace = true }
-parquet = { workspace = true, optional = true }
 pbjson = { workspace = true, optional = true }
 prost = { workspace = true }
 serde = { version = "1.0", optional = true }
diff --git a/docs/source/user-guide/configs.md b/docs/source/user-guide/configs.md
@@ -112,6 +112,7 @@ The following configuration settings are available:
 | datafusion.execution.parquet.allow_single_file_parallelism              | true                      | (writing) Controls whether DataFusion will attempt to speed up writing parquet files by serializing them in parallel. Each column in each row group in each output file are serialized in parallel leveraging a maximum possible core count of n_files*n_row_groups*n_columns.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
 | datafusion.execution.parquet.maximum_parallel_row_group_writers         | 1                         | (writing) By default parallel parquet writer is tuned for minimum memory usage in a streaming execution plan. You may see a performance benefit when writing large parquet files by increasing maximum_parallel_row_group_writers and maximum_buffered_record_batches_per_stream if your system has idle cores and can tolerate additional memory usage. Boosting these values is likely worthwhile when writing out already in-memory data, such as from a cached data frame.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
 | datafusion.execution.parquet.maximum_buffered_record_batches_per_stream | 2                         | (writing) By default parallel parquet writer is tuned for minimum memory usage in a streaming execution plan. You may see a performance benefit when writing large parquet files by increasing maximum_parallel_row_group_writers and maximum_buffered_record_batches_per_stream if your system has idle cores and can tolerate additional memory usage. Boosting these values is likely worthwhile when writing out already in-memory data, such as from a cached data frame.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| datafusion.execution.parquet.use_content_defined_chunking               | NULL                      | (writing) EXPERIMENTAL: Enable content-defined chunking (CDC) when writing parquet files. When `Some`, CDC is enabled with the given options; when `None` (the default), CDC is disabled. When CDC is enabled, parallel writing is automatically disabled since the chunker state must persist across row groups.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
 | datafusion.execution.planning_concurrency                               | 0                         | Fan-out during initial physical planning. This is mostly use to plan `UNION` children in parallel. Defaults to the number of CPU cores on the system                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
 | datafusion.execution.skip_physical_aggregate_schema_check               | false                     | When set to true, skips verifying that the schema produced by planning the input of `LogicalPlan::Aggregate` exactly matches the schema of the input plan. When set to false, if the schema does not match exactly (including nullability and metadata), a planning error will be raised. This is used to workaround bugs in the planner that are now caught by the new schema verification step.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
 | datafusion.execution.spill_compression                                  | uncompressed              | Sets the compression codec used when spilling data to disk. Since datafusion writes spill files using the Arrow IPC Stream format, only codecs supported by the Arrow IPC Stream Writer are allowed. Valid values are: uncompressed, lz4_frame, zstd. Note: lz4_frame offers faster (de)compression, but typically results in larger spill files. In contrast, zstd achieves higher compression ratios at the cost of slower (de)compression speed.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
