Merge branch 'main' into typing

Author: tylerriccio33

.github/ISSUE_TEMPLATE/bug.md

@@ -7,7 +7,7 @@ labels: "Type: ☹︎ Bug"
 
 ## Prework
 
-- [ ] Read and agree to the [code of conduct](https://www.contributor-covenant.org/version/2/1/code_of_conduct/) and [contributing guidelines](https://github.com/posit-dev/pointblank/blob/main/.github/CONTRIBUTING.md).
+- [ ] Read and agree to the [code of conduct](https://www.contributor-covenant.org/version/2/1/code_of_conduct/) and [contributing guidelines](https://github.com/posit-dev/pointblank/blob/main/CONTRIBUTING.md).
 - [ ] If there is [already a relevant issue](https://github.com/posit-dev/pointblank/issues), whether open or closed, comment on the existing thread instead of posting a new issue.
 
 ## Description

.github/ISSUE_TEMPLATE/feature.md

@@ -7,7 +7,7 @@ labels: "Type: ★ Enhancement"
 
 ## Prework
 
-- [ ] Read and abide by the Pointblank [code of conduct](https://www.contributor-covenant.org/version/2/1/code_of_conduct/) and [contributing guidelines](https://github.com/posit-dev/pointblank/blob/main/.github/CONTRIBUTING.md).
+- [ ] Read and abide by the Pointblank [code of conduct](https://www.contributor-covenant.org/version/2/1/code_of_conduct/) and [contributing guidelines](https://github.com/posit-dev/pointblank/blob/main/CONTRIBUTING.md).
 - [ ] Search for duplicates among the [existing issues](https://github.com/posit-dev/pointblank/issues) (both open and closed).
 
 ## Proposal

.github/workflows/ci-tests.yaml

@@ -15,7 +15,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.10", "3.11", "3.12"]
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
       fail-fast: false
 
     steps:
@@ -24,11 +24,21 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+      - name: Set up Java for PySpark
+        uses: actions/setup-java@v4
+        with:
+          distribution: "temurin"
+          java-version: "11"
       - name: Install uv
         uses: astral-sh/setup-uv@v5
       - name: pytest unit tests
         run: |
           make test
+        env:
+          # Optimize PySpark for CI environment
+          PYSPARK_DRIVER_MEMORY: 1g
+          PYSPARK_EXECUTOR_MEMORY: 1g
+          SPARK_LOCAL_IP: 127.0.0.1
       - name: Upload coverage reports to Codecov
         uses: codecov/codecov-action@v5
         with:

.gitignore

@@ -119,6 +119,12 @@ docs/_site
 docs/.quarto
 docs/reference
 docs/objects.json
+docs/user-guide-pdf-clean.qmd
+docs/toc.html
+docs/toc.pdf
+docs/user-guilde-with-toc.pdf
+docs/basic_validation.yaml
+docs/validation_config.yaml
 
 datasets/
 /*.parquet
@@ -136,3 +142,5 @@ uv.lock
 
 # While typing is experimental, don't mark the entire package as typed
 pointblank/py.typed
+memory
+.vscode/mcp.json

.vscode/settings.json

@@ -15,6 +15,9 @@
       "source.organizeImports": "explicit"
     },
   },
+  "[markdown]": {
+    "editor.formatOnSave": false
+  },
   "python.testing.pytestArgs": ["tests"],
   "python.testing.unittestEnabled": false,
   "python.testing.pytestEnabled": true,

CITATION.cff

@@ -2,8 +2,8 @@ cff-version: 1.2.0
 message: 'If you wish to cite the "Pointblank" package use:'
 type: software
 license: MIT
-title: "Pointblank: Find out if your data is what you think it is"
-version: 0.7.3
+title: "Pointblank: data validation toolkit for assessing and monitoring data quality."
+version: 0.16.0
 abstract: Validate data in Polars and Pandas DataFrames and database tables.
   Validation pipelines can be made using easily-readable, consecutive validation
   steps. Upon execution of the validation plan, several reporting options are available.

Makefile

@@ -2,18 +2,37 @@
 
 .PHONY: test
 test:
-	@uv run pytest \
+	@uv run pytest tests \
 		--cov=pointblank \
 		--cov-report=term-missing \
 		--randomly-seed 123 \
 		-n auto \
 		--reruns 3 \
-		--reruns-delay 1
+		--reruns-delay 1 \
+		--doctest-modules pointblank \
+		--durations 10
+
+.PHONY: test-core
+test-core: ## Run core libraries only; useful for local CI
+	@SKIP_PYSPARK_TESTS=1 \
+		SKIP_SQLITE_TESTS=1 \
+		SKIP_PARQUET_TESTS=1 \
+		uv run pytest \
+		--cov=pointblank \
+		--cov-report=term-missing \
+		--randomly-seed 123 \
+		-n auto \
+		--durations=10
+
 
 test-update:
 	pytest --snapshot-update
 
+.PHONY: pre-commit
+pre-commit: ## Run pre-commit hooks
+	@uvx pre-commit run --all-files
 
+.PHONY: lint
 lint: ## Run ruff formatter and linter
 	@uv run ruff format
 	@uv run ruff check --fix
@@ -22,6 +41,13 @@ lint: ## Run ruff formatter and linter
 type: ## Run experimental(!) type checking
 	@uvx ty check pointblank
 
+.PHONY: install-pre-commit
+install-pre-commit: # Install pre-commit hooks
+	@uvx pre-commit install
+
+.PHONY: run-pre-commit
+run-pre-commit: # Run pre-commit hooks
+	@uvx pre-commit run --all-files
 
 check:
 	pyright --pythonversion 3.8 pointblank
@@ -60,5 +86,21 @@ docs-build:
 	  && quartodoc build --verbose \
 	  && quarto render
 
+docs-pdf: ## Build PDF version of User Guide (HTML to PDF preserving graphics)
+	@echo "Preparing PDF document (stripping YAML from includes)..."
+	uv run python scripts/create_pdf_doc.py
+	@echo "Rendering User Guide to self-contained HTML..."
+	cd docs && uv run quarto render user-guide-pdf-clean.qmd --to html --output user-guide-pdf.html
+	@echo "Converting HTML to PDF with Chrome (preserves validation reports)..."
+	uv run python scripts/html_to_pdf.py docs/_site/user-guide-pdf.html docs/user-guide.pdf
+	@echo "Creating Table of Contents page with actual page numbers..."
+	uv run python scripts/create_toc_pdf.py docs/user-guide.pdf
+	@echo "PDF available at docs/user-guide.pdf"
+
+docs-llms: ## Generate llms.txt and llms-full.txt files for LLM consumption
+	@uv run python scripts/generate_llms_txt.py
+
+docs-full: docs-build docs-llms ## Build docs and generate llms.txt files
+
 install: dist ## install the package to the active Python's site-packages
 	python3 -m pip install --force-reinstall dist/pointblank*.whl