Test if the website works correctly with these exclusions + check sizes

.gitlab-ci.yml

@@ -24,7 +24,7 @@ before_script:
 build-book:
   stage: build
   script:
-    # Build logic remains same
+    # Previous build steps...
     - |
       if [ "$CI_COMMIT_BRANCH" == "release" ]; then
         echo "Building production version"
@@ -34,48 +34,74 @@ build-book:
         teachbooks build book/ > >(tee stdout.log) 2> >(tee stderr.log >&2)
       fi
 
-    # Size debugging
-    - echo "Initial directory sizes:"
-    - du -sh book/_build/* | tee build_debug.log
-    - echo "Files larger than 5MB:"
-    - find book/_build -type f -size +5M -exec ls -lh {} \; >> build_debug.log
+    # Size analysis
+    - echo "=== Size Analysis ===" | tee size_analysis.log
+    - echo "Directory Sizes:" | tee -a size_analysis.log
+    - du -sh book/_build/* | tee -a size_analysis.log
+
+    - echo -e "\nSize by File Type:" | tee -a size_analysis.log
+    - echo "HTML files:" | tee -a size_analysis.log
+    - find book/_build/html -name "*.html" -type f -exec du -ch {} + | grep total$ | tee -a size_analysis.log
+
+    - echo "JavaScript files:" | tee -a size_analysis.log
+    - find book/_build/html -name "*.js" -type f -exec du -ch {} + | grep total$ | tee -a size_analysis.log
+
+    - echo "CSS files:" | tee -a size_analysis.log
+    - find book/_build/html -name "*.css" -type f -exec du -ch {} + | grep total$ | tee -a size_analysis.log
+
+    - echo "Map files:" | tee -a size_analysis.log
+    - find book/_build/html -name "*.map" -type f -exec du -ch {} + | grep total$ | tee -a size_analysis.log
+
+    - echo -e "\nLargest Files (>1MB):" | tee -a size_analysis.log
+    - find book/_build -type f -size +1M -exec ls -lh {} \; | sort -k5 -hr | tee -a size_analysis.log
+
+    - echo -e "\nFile counts by type:" | tee -a size_analysis.log
+    - echo "HTML: $(find book/_build/html -name '*.html' | wc -l)" | tee -a size_analysis.log
+    - echo "JS: $(find book/_build/html -name '*.js' | wc -l)" | tee -a size_analysis.log
+    - echo "CSS: $(find book/_build/html -name '*.css' | wc -l)" | tee -a size_analysis.log
+    - echo "Images: $(find book/_build/html/_images -type f | wc -l)" | tee -a size_analysis.log
+    - echo "IPython Notebooks: $(find book/_build -name '*.ipynb' | wc -l)" | tee -a size_analysis.log
+
     - echo $CI_JOB_ID > build_job_id.txt
 
   artifacts:
     paths:
-      # HTML and static content
-      - book/_build/html/**/*.html
-      - book/_build/html/**/*.css
-      - book/_build/html/**/*.js
+      # Essential web content
+      - book/_build/html/**/*.{html,css,js}
       - book/_build/html/_images/**
       - book/_build/html/_static/**
       - book/_build/html/_custom_downloads/**
+      - book/_build/html/genindex.html
+      - book/_build/html/search.html
 
-      # Keep core JavaScript functionality
-      - book/_build/html/_static/index.js
-      - book/_build/html/_static/jquery.js
-      - book/_build/html/_static/underscore.js
+      # Required for interactive features
+      - book/_build/jupyter_execute/**/*.html
+      - book/_build/html/_static/scripts/**
 
-      # Build logs and ID
-      - book/_build/*.log
+      # Logs and build info
       - build_job_id.txt
       - build_debug.log
       - stdout.log
       - stderr.log
 
     exclude:
-      # Large unnecessary files
+      # Development/build files
       - "**/*.js.map"
-      - "**/*.doctree"
-      - "**/*.ipynb"
       - "**/_sources/**"
-
-      # Build artifacts
       - "**/__pycache__/**"
       - "**/*.pyc"
+      - "**/*.pickle"
       - book/_build/.doctrees/**
       - book/_build/jupyter_cache/**
-      - "**/*.pickle"
+      # Keep notebooks for interactive features
+      # - "**/*.ipynb"
+
+      # # Build artifacts
+      # - "**/__pycache__/**"
+      # - "**/*.pyc"
+      # - book/_build/.doctrees/**
+      # - book/_build/jupyter_cache/**
+      # - "**/*.pickle"
 
     expire_in: 1 week