Add pytest configuration and new GitHub Action for detecting changed files

.github/actions/detect-changed-files/README.md

@@ -0,0 +1,101 @@
+# Detect Changed Files Action
+
+A GitHub Action that detects changed files using native Git commands with support for pull requests and push events.
+
+## Features
+
+- 🔍 **Smart Detection**: Automatically detects changed files based on Git history
+- 📋 **Event Support**: Works with pull requests, push events, and manual triggers
+- 🎯 **Pattern Matching**: Supports glob patterns for file filtering
+- 📊 **Rich Outputs**: Provides file lists, change counts, and boolean flags
+
+## Usage
+
+### Basic Usage
+
+```yaml
+- name: Get changed files
+  id: changed-files
+  uses: ./.github/actions/detect-changed-files
+  with:
+    files: 'notebooks/**/*.ipynb'
+```
+
+### Advanced Usage
+
+```yaml
+- name: Get changed files
+  id: changed-files
+  uses: ./.github/actions/detect-changed-files
+  with:
+    files: 'src/**/*.py'
+    base-sha: ${{ github.event.pull_request.base.sha }}
+    head-sha: ${{ github.event.pull_request.head.sha }}
+```
+
+## Inputs
+
+| Input | Description | Required | Default |
+|-------|-------------|----------|---------|
+| `files` | File pattern to match (e.g., `notebooks/**/*.ipynb`) | ✅ | - |
+| `token` | GitHub token for API access | ❌ | `${{ github.token }}` |
+| `base-sha` | Base SHA for comparison | ❌ | Auto-detected |
+| `head-sha` | Head SHA for comparison | ❌ | Auto-detected |
+
+## Outputs
+
+| Output | Description |
+|--------|-------------|
+| `all_changed_files` | JSON array of all changed files matching the pattern |
+| `has_changes` | Boolean indicating if any files changed |
+| `files_count` | Number of changed files |
+
+## Examples
+
+### Check for notebook changes
+
+```yaml
+- name: Check for notebook changes
+  id: notebooks
+  uses: ./.github/actions/detect-changed-files
+  with:
+    files: 'notebooks/**/*.ipynb'
+
+- name: Run tests if notebooks changed
+  if: steps.notebooks.outputs.has_changes == 'true'
+  run: |
+    echo "Found changed notebooks:"
+    echo "${{ steps.notebooks.outputs.all_changed_files }}"
+```
+
+### Conditional workflow steps
+
+```yaml
+- name: Get changed Python files
+  id: python-files
+  uses: ./.github/actions/detect-changed-files
+  with:
+    files: 'src/**/*.py'
+
+- name: Run linting
+  if: steps.python-files.outputs.has_changes == 'true'
+  run: |
+    echo "Linting ${{ steps.python-files.outputs.files_count }} Python files"
+```
+
+## Supported Events
+
+- **Pull Requests**: Compares PR head with base branch
+- **Push Events**: Compares current commit with previous commit
+- **Manual Triggers**: Finds all files matching the pattern
+
+## Pattern Examples
+
+- `notebooks/**/*.ipynb` - All Jupyter notebooks in notebooks directory
+- `src/**/*.py` - All Python files in src directory
+- `*.md` - All Markdown files in root directory
+- `docs/**/*` - All files in docs directory
+
+## Author
+
+ODH Data Processing Team

.github/actions/detect-changed-files/action.yml

@@ -0,0 +1,118 @@
+name: 'Detect Changed Files'
+description: 'Detect changed files using native Git commands with support for PRs and push events'
+author: 'ODH Data Processing Team'
+
+inputs:
+  files:
+    description: 'File pattern to match (e.g., notebooks/**/*.ipynb)'
+    required: true
+  token:
+    description: 'GitHub token for API access'
+    required: false
+    default: ${{ github.token }}
+  base-sha:
+    description: 'Base SHA for comparison (auto-detected if not provided)'
+    required: false
+  head-sha:
+    description: 'Head SHA for comparison (auto-detected if not provided)'
+    required: false
+
+outputs:
+  all_changed_files:
+    description: 'JSON array of all changed files matching the pattern'
+    value: ${{ steps.detect.outputs.all_changed_files }}
+  has_changes:
+    description: 'Boolean indicating if any files changed'
+    value: ${{ steps.detect.outputs.has_changes }}
+  files_count:
+    description: 'Number of changed files'
+    value: ${{ steps.detect.outputs.files_count }}
+
+runs:
+  using: 'composite'
+  steps:
+    - name: Detect changed files
+      id: detect
+      shell: bash
+      run: |
+        set -euo pipefail
+
+        echo "🔍 Detecting changed files for pattern: ${{ inputs.files }}"
+        echo "📋 Event: ${{ github.event_name }}"
+
+        # Determine comparison SHAs based on event type
+        if [ "${{ github.event_name }}" == "pull_request" ]; then
+          # For PRs, use provided SHAs or extract from event
+          if [ -n "${{ inputs.base-sha }}" ] && [ -n "${{ inputs.head-sha }}" ]; then
+            BASE_SHA="${{ inputs.base-sha }}"
+            HEAD_SHA="${{ inputs.head-sha }}"
+          else
+            BASE_SHA="${{ github.event.pull_request.base.sha }}"
+            HEAD_SHA="${{ github.event.pull_request.head.sha }}"
+          fi
+
+          echo "📊 Comparing PR: $BASE_SHA..$HEAD_SHA"
+
+          # Get changed files for PR
+          CHANGED_FILES=$(git diff --name-only --diff-filter=ACMRT $BASE_SHA..$HEAD_SHA -- '${{ inputs.files }}' | jq -R -s -c 'split("\n") | map(select(length > 0))')
+
+        elif [ "${{ github.event_name }}" == "push" ]; then
+          # For push events, compare with previous commit
+          if [ -n "${{ inputs.base-sha }}" ]; then
+            BASE_SHA="${{ inputs.base-sha }}"
+            HEAD_SHA="${{ github.sha }}"
+          else
+            # Compare with previous commit
+            BASE_SHA="HEAD~1"
+            HEAD_SHA="HEAD"
+          fi
+
+          echo "📊 Comparing push: $BASE_SHA..$HEAD_SHA"
+
+          # Get changed files for push
+          CHANGED_FILES=$(git diff --name-only --diff-filter=ACMRT $BASE_SHA $HEAD_SHA -- '${{ inputs.files }}' | jq -R -s -c 'split("\n") | map(select(length > 0))')
+
+        else
+          # For other events (workflow_dispatch, schedule), assume no file-based filtering needed
+          echo "📊 Event type '${{ github.event_name }}' - returning all matching files"
+
+          # Find all files matching pattern
+          if command -v find >/dev/null 2>&1; then
+            # Use find for better pattern matching
+            PATTERN="${{ inputs.files }}"
+            # Extract directory prefix and file pattern
+            if [[ "$PATTERN" == *"**"* ]]; then
+             # Pattern has **: extract base directory and filename pattern
+             BASE_DIR=$(echo "$PATTERN" | cut -d'/' -f1)
+             FILE_PATTERN=$(echo "$PATTERN" | cut -d'/' -f2-)
+             CHANGED_FILES=$(find "$BASE_DIR" -type f -name "$FILE_PATTERN" 2>/dev/null | sed 's|^\./||' | jq -R -s -c 'split("\n") | map(select(length > 0))')
+            else
+              # Simple pattern without **: use -path directly
+              CHANGED_FILES=$(find . -path "./$PATTERN" -type f | sed 's|^\./||' | jq -R -s -c 'split("\n") | map(select(length > 0))')
+            fi
+          else
+            # Fallback: assume all files changed (conservative approach)
+            CHANGED_FILES='[]'
+          fi
+        fi
+
+        # Calculate if there are changes and file count
+        FILES_COUNT=$(echo "$CHANGED_FILES" | jq length)
+        HAS_CHANGES=$([ "$FILES_COUNT" -gt 0 ] && echo "true" || echo "false")
+
+        # Output results
+        echo "📁 Found $FILES_COUNT changed files"
+        echo "$CHANGED_FILES" | jq -r '.[]' | while read -r file; do
+          [ -n "$file" ] && echo "  - $file"
+        done || true
+
+        # Set outputs
+        echo "all_changed_files=$CHANGED_FILES" >> $GITHUB_OUTPUT
+        echo "has_changes=$HAS_CHANGES" >> $GITHUB_OUTPUT  
+        echo "files_count=$FILES_COUNT" >> $GITHUB_OUTPUT
+
+        echo "✅ Detection complete: has_changes=$HAS_CHANGES, files_count=$FILES_COUNT"
+
+branding:
+  icon: 'search'
+  color: 'blue'

.github/workflows/execute-notebooks.yml

@@ -0,0 +1,53 @@
+name: Execute Notebooks Tests for Notebooks
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened]
+    paths:
+      - "notebooks/**/*.ipynb"
+      - ".github/workflows/execute-notebooks.yml"
+  push:
+    branches: [ main ]
+    paths:
+      - "notebooks/**/*.ipynb"
+      - ".github/workflows/execute-notebooks.yml"
+
+permissions:
+  contents: read
+
+jobs:
+  execute_tests:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        # Set the notebooks to execute
+        notebook_to_execute: ["notebooks/use-cases/document-conversion-standard.ipynb"]
+
+        # Set the files use in each notebook execution
+        file_to_use: ["https://raw.githubusercontent.com/py-pdf/sample-files/refs/heads/main/001-trivial/minimal-document.pdf"]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+          cache: pip
+
+      - name: Install Testing Tools
+        run: |
+          pip install papermill ipykernel
+          ipython kernel install --name "python3" --user
+
+      - name: Execute Notebooks
+        run: |
+          set -ux
+
+          NOTEBOOK="${{ matrix.notebook_to_execute }}"
+          FILE="${{ matrix.file_to_use }}"
+
+          echo "Executing notebook '$NOTEBOOK' with file '$FILE'..."
+
+          papermill $NOTEBOOK $NOTEBOOK.tmp.ipynb -b $(echo -n "files: [\"$FILE\"]" | base64 -w 0)
+
+          echo "✓ Notebook $NOTEBOOK executed successfully"