From 8dcf2a7d1ed72cf0628477f0ee26ffa497b82513 Mon Sep 17 00:00:00 2001 From: Matthew Van Schellebeeck Date: Mon, 7 Nov 2022 07:22:30 -0500 Subject: [PATCH 1/3] Update existing docs --- docs/source/user-guide/configs.md | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/docs/source/user-guide/configs.md b/docs/source/user-guide/configs.md index 0e2810ef2868..1b82037d0335 100644 --- a/docs/source/user-guide/configs.md +++ b/docs/source/user-guide/configs.md @@ -37,15 +37,16 @@ Environment variables are read during `SessionConfig` initialisation so they mus | key | type | default | description | | ----------------------------------------------- | ------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| datafusion.catalog.location | Utf8 | NULL | Location scanned to load tables for `default` schema | -| datafusion.catalog.type | Utf8 | NULL | Type of `TableProvider` to use when loading `default` schema | +| datafusion.catalog.location | Utf8 | NULL | Location scanned to load tables for `default` schema, defaults to None | +| datafusion.catalog.type | Utf8 | NULL | Type of `TableProvider` to use when loading `default` schema. Defaults to None | | datafusion.execution.batch_size | UInt64 | 8192 | Default batch size while creating new batches, it's especially useful for buffer-in-memory batches since creating tiny batches would results in too much metadata memory consumption. | | datafusion.execution.coalesce_batches | Boolean | true | When set to true, record batches will be examined between each operator and small batches will be coalesced into larger batches. This is helpful when there are highly selective filters or joins that could produce tiny output batches. The target batch size is determined by the configuration setting 'datafusion.execution.coalesce_target_batch_size'. | | datafusion.execution.coalesce_target_batch_size | UInt64 | 4096 | Target batch size when coalescing batches. Uses in conjunction with the configuration setting 'datafusion.execution.coalesce_batches'. | | datafusion.execution.parquet.enable_page_index | Boolean | false | If true, uses parquet data page level metadata (Page Index) statistics to reduce the number of rows decoded. | | datafusion.execution.parquet.pushdown_filters | Boolean | false | If true, filter expressions are be applied during the parquet decoding operation to reduce the number of rows decoded. | | datafusion.execution.parquet.reorder_filters | Boolean | false | If true, filter expressions evaluated during the parquet decoding opearation will be reordered heuristically to minimize the cost of evaluation. If false, the filters are applied in the same order as written in the query. | -| datafusion.execution.time_zone | Utf8 | UTC | The session time zone which some function require e.g. EXTRACT(HOUR from SOME_TIME) shift the underline datetime according to the time zone, then extract the hour. | +| datafusion.execution.time_zone | Utf8 | +00:00 | The session time zone which some function require e.g. EXTRACT(HOUR from SOME_TIME) shift the underline datetime according to the time zone, | +| then extract the hour. | | datafusion.explain.logical_plan_only | Boolean | false | When set to true, the explain statement will only print logical plans. | | datafusion.explain.physical_plan_only | Boolean | false | When set to true, the explain statement will only print physical plans. | | datafusion.optimizer.filter_null_join_keys | Boolean | false | When set to true, the optimizer will insert filters before a join between a nullable and non-nullable column to filter out nulls on the nullable side. This filter can add additional overhead when the file format does not fully support predicate push down. | From 4469669c075799b38e32ddf8f0b8aa38abd2b1bf Mon Sep 17 00:00:00 2001 From: Matthew Van Schellebeeck Date: Mon, 7 Nov 2022 07:23:06 -0500 Subject: [PATCH 2/3] Add workflow to test for updated docs --- .github/workflows/rust.yml | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/.github/workflows/rust.yml b/.github/workflows/rust.yml index c3cc2df6ec6b..e74429e0e546 100644 --- a/.github/workflows/rust.yml +++ b/.github/workflows/rust.yml @@ -477,3 +477,33 @@ jobs: # ignore ./Cargo.toml because putting workspaces in multi-line lists make it easy to read ci/scripts/rust_toml_fmt.sh git diff --exit-code + + config-docs-check: + name: check configs.md is up-to-date + needs: [linux-build-lib] + runs-on: ubuntu-latest + container: + image: amd64/rust + env: + # Disable full debug symbol generation to speed up CI build and keep memory down + # "1" means line tables only, which is useful for panic tracebacks. + RUSTFLAGS: "-C debuginfo=1" + steps: + - uses: actions/checkout@v3 + with: + submodules: true + - name: Cache Cargo + uses: actions/cache@v3 + with: + path: /github/home/.cargo + # this key equals the ones on `linux-build-lib` for re-use + key: cargo-cache- + - name: Setup Rust toolchain + uses: ./.github/actions/setup-builder + with: + rust-version: stable + - name: Check if configs.md has been modified + run: | + # If you encounter an error, run './dev/update_config_docs.sh' and commit + ./dev/update_config_docs.sh + git diff --exit-code From efb072da1a3afadbf263ca0902bc23c87aa0c06a Mon Sep 17 00:00:00 2001 From: Matthew Van Schellebeeck Date: Mon, 7 Nov 2022 07:33:38 -0500 Subject: [PATCH 3/3] Set up node --- .github/workflows/rust.yml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/.github/workflows/rust.yml b/.github/workflows/rust.yml index e74429e0e546..61229d8254f7 100644 --- a/.github/workflows/rust.yml +++ b/.github/workflows/rust.yml @@ -502,6 +502,9 @@ jobs: uses: ./.github/actions/setup-builder with: rust-version: stable + - uses: actions/setup-node@v3 + with: + node-version: "14" - name: Check if configs.md has been modified run: | # If you encounter an error, run './dev/update_config_docs.sh' and commit