eea · mckeea · Sep 28, 2025 · Jun 18, 2025 · Jun 18, 2025 · Jun 18, 2025
@@ -0,0 +1,10 @@
+{
+  "_comment": "This file maps non-browsable QMD source files to their persistent random output names and URLs. Do not publish this file.",
+  "mappings": [
+    {
+      "source": "it-principles/IT_Architecture_Principles_and_Implementation_Guidelines.qmd",
+      "base": "smnkbw05zgz5l0llz5tefwxrowqqds6c36zi1i9ssswbslnleuj28yc5c7sui5pl",
+      "url": "/smnkbw05zgz5l0llz5tefwxrowqqds6c36zi1i9ssswbslnleuj28yc5c7sui5pl.html"
+    }
+  ]
+}
@@ -1,51 +1,89 @@
 #!/bin/bash
 set -e
 
-echo "🖼 Render all documents into to HTML/DOCX"
+echo "🔄 Copying DOCS to origin_DOCS..."
+mv DOCS origin_DOCS
+
+echo "🔄 Updating URL mappings..."
+python3 .github/scripts/update_url_mappings.py
+
+echo "🔄 Grouping documents by category..."
+python3 .github/scripts/group_docs_by_category.py
+
+# Change to DOCS directory as it'll be the root of rendered content
+cd DOCS
+# Link assets to origin_DOCS as these files need to be served from rendered content
+ln -s ../assets assets
+
+
+echo "🖼 Render all documents to HTML"
+if [[ -n "$SKIP_DOCX" ]]; then
+  echo "   (DOCX generation will be skipped)"
+else
+  echo "   (DOCX generation will follow)"
+fi
 sudo cp /usr/bin/chromium /usr/bin/chromium-browser
-QUARTO_CHROMIUM_HEADLESS_MODE=new quarto render --to docx 
-find _site -type f -name 'index.docx' -delete
+
+# Set up quarto configuration based on environment variables
+if [[ -n "$SKIP_DOCX" ]]; then
+  echo "📄 Using configuration for DOCX cleanup (HTML only)"
+  cp _quarto-no-headers.yml _quarto.yml
+else
+  echo "📄 Using default configuration (HTML + DOCX files kept)"
+  # _quarto.yml is already the default with headers - no copying needed
+fi
+
 QUARTO_CHROMIUM_HEADLESS_MODE=new quarto render --to html --no-clean
 
 # Backup the correct sitemap as it may be overwritten by next operations
 sleep 5
 mv _site/sitemap.xml _site/sitemap.xml.bkp
 
+# Generate DOCX files (always needed for PDF conversion)
+echo "📄 Generating DOCX files for PDF conversion..."
+QUARTO_CHROMIUM_HEADLESS_MODE=new quarto render --to docx --no-clean
+find _site -type f -name 'index.docx' -delete
+
 echo "🛠 Generate index.qmd files for all DOCS/* folders"e
-node .github/scripts/generate_index_all.mjs
+node ../.github/scripts/generate_index_all.mjs
 
 echo "📄 Render only index.qmd files using 'index' profile"
 mv _quarto.yml _quarto_not_used.yml
 mv _quarto-index.yml _quarto.yml
-find DOCS -type f -name index.qmd -print0 | while IFS= read -r -d '' src; do
+find ./ -type f -name index.qmd -print0 | while IFS= read -r -d '' src; do
   echo "🔧 Rendering $src using profile=index..."
-  QUARTO_CHROMIUM_HEADLESS_MODE=new quarto render "$src" --profile index --to html --no-clean
+  QUARTO_CHROMIUM_HEADLESS_MODE=new quarto render "$src" --profile index --to html --no-clean $QUARTO_FLAGS
 done
 mv _quarto.yml _quarto-index.yml
 cp _quarto_not_used.yml _quarto.yml && rm _quarto_not_used.yml
 
-echo "🔄 Additional processing of index.html file"
-echo '<!DOCTYPE html>
-<html>
-  <head>
-    <meta http-equiv="refresh" content="0; url=DOCS/index.html" />
-    <title>Redirecting...</title>
-  </head>
-  <body>
-    <p>If you are not redirected automatically, <a href="DOCS/index.html">click here</a>.</p>
-  </body>
-</html>' > _site/index.html
+
+echo "📄 Converting .docx files to .pdf..."
+timeout 3s ../.github/scripts/convert_docx_to_pdf.sh || true
+timeout 10m ../.github/scripts/convert_docx_to_pdf.sh
+
+# Clean up DOCX files if requested (they're only needed for PDF conversion)
+if [[ -n "$SKIP_DOCX" ]]; then
+  echo "🗑️  Cleaning up DOCX files (keeping only PDFs and HTML)..."
+  find _site -name "*.docx" -type f -delete
+  echo "   ✅ DOCX files removed to save space"
+else
+  echo "💾 Keeping DOCX files for download/access"
+fi
 
 # Revert the correct sitemap
 cp _site/sitemap.xml.bkp _site/sitemap.xml
 rm -f _site/sitemap.xml.bkp
 
-echo "📄 Converting .docx files to .pdf..."
-#chmod +x ./convert_docx_to_pdf.sh
-timeout 3s .github/scripts/convert_docx_to_pdf.sh || true
-timeout 10m .github/scripts/convert_docx_to_pdf.sh
+# Remove non-browsable links from sitemap.xml
+python3 ../.github/scripts/remove_non_browsable_from_sitemap.py _site/sitemap.xml
 
 echo "🧹 Cleaning up..."
-find _site -type f -name '*.docx' -delete
+find _site -type f -name '*.qmd' -delete
+
+cp ../404.html _site/404.html
+cp ../redirect_map.json _site/redirect_map.json
+cp ../url_mapping.json _site/url_mapping.json
+
 
-echo "✅ Docs built successfully"
+echo "✅ Docs built successfully"
@@ -2,7 +2,7 @@
 
 #set -euo pipefail
 
-RENDERED_DOCS_DIR="../../_site"
+RENDERED_DOCS_DIR="../../DOCS/_site"
 
 # Set the working directory to the script's location
 cd "$(dirname "${BASH_SOURCE[0]}")" || exit

@@ -18,5 +18,6 @@ run_git "Configuring Git user name" config --global user.name "ci_docker_builder
 run_git "Configuring Git user email" config --global user.email "[email protected]"
 
 run_git "Setting remote URL" remote set-url origin [email protected]:${GITHUB_REPOSITORY}.git
+#run_git "Fetching origin develop branch" fetch origin develop
 
 echo "✅ Environment ready."
@@ -3,85 +3,144 @@ set -euo pipefail
 
 source "$(dirname "$0")/helpers/git-utils.sh"
 
-
-echo "🚀 Starting validation..."
 PROJECT_NAME=$(echo "$PUBLISH_BRANCH" | sed -E 's/^publish-(.+)-[0-9]{8}-[0-9]{6}$/\1/')
-echo "Project: $PROJECT_NAME"
-
-echo "🔎 Checking files inside publish branch (fast tree scan)..."
-run_git "fetching develop branch" fetch origin develop
 PUBLISH_COMMIT=$(git rev-parse origin/${PUBLISH_BRANCH})
-echo "PUBLISH_COMMIT: $PUBLISH_COMMIT"
-
-git ls-tree -r --name-only "$PUBLISH_COMMIT" > changed-files.txt
-sed -i '/^\.gitignore$/d; /^\.github\/workflows\/trigger\.yml$/d' changed-files.txt
-cat changed-files.txt
-
-INVALID_FILES=$(grep -v "^DOCS/${PROJECT_NAME}/" changed-files.txt || true)
-if [ -n "$INVALID_FILES" ]; then
-  echo "❌ Changes outside DOCS/${PROJECT_NAME} detected:"
-  echo "$INVALID_FILES"
-  exit 1
-fi
-
-echo "✅ Folder validation passed."
-
-echo "🔀 Preparing secure diff-aware merge into develop..."
-git checkout develop
-git pull origin develop
-mkdir -p tmp_publish
-git archive "$PUBLISH_COMMIT" DOCS/"$PROJECT_NAME" | tar -x -C tmp_publish
-
-# ✅ Remove any GitHub workflows injected into the subtree
-rm -rf tmp_publish/DOCS/"${PROJECT_NAME}"/.github
-rm -rf tmp_publish/DOCS/"${PROJECT_NAME}"/.gitignore
-
-echo "🔍 Finding modified and deleted files only..."
-MODIFIED_FILES=()
-while IFS= read -r file; do
-  if [ ! -f "$file" ] || ! cmp -s "$file" "tmp_publish/$file"; then
-    MODIFIED_FILES+=("$file")
-  fi
-done < <(find tmp_publish/DOCS/"$PROJECT_NAME" -type f | sed 's|tmp_publish/||')
-
-DELETED_FILES=()
-while IFS= read -r file; do
-  if [ ! -f "tmp_publish/$file" ]; then
-    DELETED_FILES+=("$file")
-  fi
-done < <(find DOCS/"$PROJECT_NAME" -type f)
-
-if [ "${#MODIFIED_FILES[@]}" -eq 0 ] && [ "${#DELETED_FILES[@]}" -eq 0 ]; then
-  echo "🟡 No real changes to DOCS/$PROJECT_NAME — skipping commit."
-  exit 0
-fi
-
-echo "✅ Modified files:"
-printf '%s\n' "${MODIFIED_FILES[@]}"
-echo "🗑️ Deleted files:"
-printf '%s\n' "${DELETED_FILES[@]}"
-
-for file in "${MODIFIED_FILES[@]}"; do
-  mkdir -p "$(dirname "$file")"
-  cp "tmp_publish/$file" "$file"; 
-done
+TEMP_WORKSPACE="tmp_publish"
 
-if [ "${#DELETED_FILES[@]}" -gt 0 ]; then
-    run_git "removing deleted files" rm "${DELETED_FILES[@]}"
-fi
-for file in "${MODIFIED_FILES[@]}"; do
-   run_git "adding $file to staging" add "$file"
-done
+echo "Project: $PROJECT_NAME"
+echo "PUBLISH_COMMIT: $PUBLISH_COMMIT"
 
-COMMIT_MSG=$(cat <<EOF
+get_changed_files() {
+    git ls-tree -r --name-only "$PUBLISH_COMMIT" > changed-files.txt
+    # Remove specific files we want to ignore
+    sed -i '/^\.gitignore$/d; /^\.github\/workflows\/trigger\.yml$/d' changed-files.txt
+    cat changed-files.txt
+}
+
+check_files_within_project() {
+    local invalid_files
+
+    invalid_files=$(grep -v "^DOCS/${PROJECT_NAME}/" changed-files.txt || true)
+
+    if [ -n "$invalid_files" ]; then
+        echo "❌ Changes outside DOCS/${PROJECT_NAME} detected:"
+        echo "$invalid_files"
+        return 1
+    fi
+
+    echo "✅ All changes within project boundaries"
+    return 0
+}
+
+prepare_merge_environment() {
+    echo "🔀 Preparing secure diff-aware merge into develop..."
+    git checkout develop
+    git pull origin develop
+    mkdir -p "$TEMP_WORKSPACE"
+    git archive "$PUBLISH_COMMIT" DOCS/"$PROJECT_NAME" | tar -x -C $TEMP_WORKSPACE
+}
+
+# Remove any GitHub workflows injected into the subtree
+cleanup_extracted_files() {
+    echo "🧹 Cleaning up extracted files..."
+    rm -rf "$TEMP_WORKSPACE"/DOCS/"${PROJECT_NAME}"/.github
+    rm -rf "$TEMP_WORKSPACE"/DOCS/"${PROJECT_NAME}"/.gitignore
+}
+
+find_file_changes() {    
+    echo "🔍 Finding modified and deleted files..."
+
+    # Find modified files
+    MODIFIED_FILES=()
+    while IFS= read -r file; do
+        if [ ! -f "$file" ] || ! cmp -s "$file" "$TEMP_WORKSPACE/$file"; then
+            MODIFIED_FILES+=("$file")
+        fi
+    done < <(find "$TEMP_WORKSPACE"/DOCS/"$PROJECT_NAME" -type f | sed "s|$TEMP_WORKSPACE/||")
+
+    # Find deleted files
+    DELETED_FILES=()
+    while IFS= read -r file; do
+        if [ ! -f "$TEMP_WORKSPACE/$file" ]; then
+            DELETED_FILES+=("$file")
+        fi
+    done < <(find DOCS/"$PROJECT_NAME" -type f)
+}
+
+check_for_changes() {
+    if [ "${#MODIFIED_FILES[@]}" -eq 0 ] && [ "${#DELETED_FILES[@]}" -eq 0 ]; then
+        echo "🟡 No real changes to DOCS/$PROJECT_NAME — skipping commit."
+        return 1 
+    fi
+
+    echo "✅ Modified files:"
+    printf '%s\n' "${MODIFIED_FILES[@]}"
+    echo "🗑️ Deleted files:" 
+    printf '%s\n' "${DELETED_FILES[@]}"
+
+    return 0
+}
+
+apply_file_changes() {
+    echo "📝 Applying file changes..."
+
+    # Copy modified files
+    for file in "${MODIFIED_FILES[@]}"; do
+        mkdir -p "$(dirname "$file")"
+        cp "$TEMP_WORKSPACE/$file" "$file"
+    done
+
+    # Remove deleted files
+    if [ "${#DELETED_FILES[@]}" -gt 0 ]; then
+        run_git "removing deleted files" rm "${DELETED_FILES[@]}"
+    fi
+
+    # Stage modified files
+    for file in "${MODIFIED_FILES[@]}"; do
+        run_git "adding $file to staging" add "$file"
+    done
+}
+
+generate_commit_message() {    
+    cat <<EOF
 chore(ci): merge DOCS/$PROJECT_NAME from $PUBLISH_BRANCH
 
 Triggered by: CI Workflow
 Branch: $PUBLISH_BRANCH
 Commit: $PUBLISH_COMMIT
 Repo: https://github.com/$GITHUB_REPOSITORY/commit/$PUBLISH_COMMIT
 EOF
-)
+}
+
+commit_and_push_changes() {
+    local commit_msg
+    commit_msg=$(generate_commit_message)
+
+    echo "💾 Committing and pushing changes..."
+    run_git "committing changes to develop branch" commit -m "$commit_msg"
+    run_git "pushing changes to develop branch" push origin develop
+}
+
+########## Main logic ##########
+
+# 1. Get changed files in the publish branch
+echo "🔎 Checking files inside publish branch (fast tree scan)..."
+run_git "fetching develop branch" fetch origin develop
+
+get_changed_files
+
+# 2. Validate that the changes are correctly scoped to the project and are correct
+check_files_within_project || exit 1
+python .github/scripts/validate_qmd_files.py || exit 1
+
+# 3. Merge the changes into develop
+prepare_merge_environment
+cleanup_extracted_files
+find_file_changes
+
+if ! check_for_changes; then
+    exit 0
+fi
 
-run_git "committing changes to develop branch" commit -m "$COMMIT_MSG"
-run_git "pushing changes to develop branch" push origin develop
+apply_file_changes
+commit_and_push_changes