docs: add CI for docs

.github/workflows/docs.yml

@@ -0,0 +1,64 @@
+name: Build documentation
+
+on:
+  pull_request:
+    paths:
+      - python/**
+      - docs/**
+      - mkdocs.yml
+      - .github/workflows/docs.yml
+jobs:
+  markdown-link-check:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - uses: gaurav-nelson/github-action-markdown-link-check@v1
+      with:
+        config-file: docs/mlc-config.json
+        folder-path: docs
+
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: psf/black@stable
+        with:
+          src: docs/src/python
+
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Install Rust
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          override: true
+          components: rustfmt, clippy
+
+      - uses: Swatinem/rust-cache@v2
+
+      - name: Set up Python
+        uses: actions/setup-python@v3
+        with:
+          python-version: '3.10'
+
+      - name: Build and install deltalake
+        run: |
+          cd python
+          pip install virtualenv
+          virtualenv venv
+          source venv/bin/activate
+          make develop
+          cd ..
+
+      - name: Install dependencies
+        run: |
+          source python/venv/bin/activate
+          pip install -r docs/requirements.txt
+
+      - name: Build documentation
+        run: |
+          source python/venv/bin/activate
+          mkdocs build

.gitignore

@@ -28,4 +28,5 @@ Cargo.lock
 !/proofs/Cargo.lock
 
 justfile
-site
+site
+__pycache__

docs/mlc_config.json

@@ -0,0 +1,7 @@
+{
+    "ignorePatterns": [
+        {
+            "pattern": "^https://crates.io/"
+        }
+    ]
+}

docs/requirements.txt

@@ -1,3 +1,7 @@
-mkdocs
-mkdocstrings[python]
-mkdocs-autorefs
+mkdocs==1.5.3
+mkdocstrings[python]==0.23.0
+mkdocs-autorefs==0.5.0
+mkdocs-material==9.4.5
+mkdocs-macros-plugin==1.0.4
+markdown-exec[ansi]==1.7.0
+mkdocs-simple-hooks==0.1.5

docs/src/python/delta_table.py

@@ -5,4 +5,4 @@ def get_table_info():
     dt = DeltaTable("../rust/tests/data/delta-0.2.0")
     print(f"Version: {dt.version()}")
     print(f"Files: {dt.files()}")
-    # --8<-- [end:get_table_info]
+    # --8<-- [end:get_table_info]

docs/usage/querying-delta-tables.md

@@ -61,7 +61,7 @@ scanning operation.
 ```
 
 PyArrow datasets may also be passed to compatible query engines, such as
-[DuckDB](https://duckdb.org/docs/api/python).
+[DuckDB](https://duckdb.org/docs/api/python/overview.html)
 
 ``` python
 >>> import duckdb

mkdocs.yml

@@ -30,6 +30,14 @@ nav:
     - api/storage.md
 not_in_nav: |
   /_build/
+
+exclude_docs: |
+  /_build/
+  /mlc_config.json
+  /src
+  /requirements.txt
+  *.py
+
 plugins:
   - autorefs
   - mkdocstrings:

python/deltalake/table.py

@@ -835,18 +835,24 @@ def repair(self, dry_run: bool = False) -> Dict[str, Any]:
         or corrupted files.
 
         Args:
-            dry_run(bool): when activated, list only the files, otherwise add remove actions to transaction log. Defaults to False.
+            dry_run: when activated, list only the files, otherwise add remove actions to transaction log. Defaults to False.
         Returns:
             The metrics from repair (FSCK) action.
 
         Examples:
 
-        >>> from deltalake import DeltaTable
-        >>> dt = DeltaTable('TEST')
-        >>> dt.repair(dry_run=False)
+        ```
+        from deltalake import DeltaTable
+
+        dt = DeltaTable('TEST')
+        dt.repair(dry_run=False)
+        ```
+        Results in
+        ```
         {'dry_run': False,
         'files_removed': ['6-0d084325-6885-4847-b008-82c1cf30674c-0.parquet',
         '5-4fba1d3e-3e20-4de1-933d-a8e13ac59f53-0.parquet']}
+        ```
         """
         metrics = self._table.repair(dry_run)
         return json.loads(metrics)

python/pyproject.toml

@@ -47,7 +47,7 @@ pyspark = [
 ]
 
 [project.urls]
-documentation = "https://delta-io.github.io/delta-rs/python/"
+documentation = "https://delta-io.github.io/delta-rs/"
 repository = "https://github.com/delta-io/delta-rs/tree/main/python/"
 
 [tool.mypy]