[DOC] Downloadable PDF Developer Guides-s

Signed-off-by: Arya Soni <[email protected]>

Author: aryasoni98

_pdf_generator/pdf_generator.rb

@@ -1,10 +1,18 @@
 # frozen_string_literal: true
 
 require "jekyll"
-require "grover"
 require "fileutils"
 require "uri"
 
+# Conditionally require grover - only needed when PDF generation is enabled
+begin
+  require "grover"
+  GROVER_AVAILABLE = true
+rescue LoadError
+  GROVER_AVAILABLE = false
+  # Don't log here as Jekyll logger may not be available yet
+end
+
 ##
 # Jekyll Generator Plugin for PDF Generation
 # Generates PDF versions of documentation collections during Jekyll build
@@ -18,6 +26,7 @@ class PdfGenerator < Generator
 
     def generate(site)
       return unless site.config["pdf_generator"] && site.config["pdf_generator"]["enabled"]
+      return unless GROVER_AVAILABLE
 
       @site = site
       @pdf_config = site.config["pdf_generator"]
@@ -226,8 +235,8 @@ def build_document_section(doc, section_number, total_sections)
       end
 
       # Clean up content - remove script tags and interactive elements
-      content = content.gsub(/<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>/mi, "")
-      content = content.gsub(/<style\b[^<]*(?:(?!<\/style>)<[^<]*)*<\/style>/mi, "")
+      content = content.gsub(/<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>/mis, "")
+      content = content.gsub(/<style\b[^<]*(?:(?!<\/style>)<[^<]*)*<\/style>/mis, "")
 
       # Extract main content from HTML - try to find the main content area
       # Remove common HTML structure elements
@@ -253,42 +262,42 @@ def extract_main_content(html)
       return "" if html.nil? || html.empty?
 
       # Remove entire head section
-      html = html.gsub(/<head[^>]*>.*?<\/head>/mi, "")
+      html = html.gsub(/<head[^>]*>.*?<\/head>/mis, "")
 
       # Remove header/nav elements (entire elements)
-      html = html.gsub(/<header[^>]*>.*?<\/header>/mi, "")
-      html = html.gsub(/<nav[^>]*>.*?<\/nav>/mi, "")
-      html = html.gsub(/<aside[^>]*>.*?<\/aside>/mi, "")
-      html = html.gsub(/<footer[^>]*>.*?<\/footer>/mi, "")
+      html = html.gsub(/<header[^>]*>.*?<\/header>/mis, "")
+      html = html.gsub(/<nav[^>]*>.*?<\/nav>/mis, "")
+      html = html.gsub(/<aside[^>]*>.*?<\/aside>/mis, "")
+      html = html.gsub(/<footer[^>]*>.*?<\/footer>/mis, "")
 
       # Remove side-bar and navigation divs (multiline match)
-      html = html.gsub(/<div[^>]*class=["'][^"']*side-bar[^"']*["'][^>]*>.*?<\/div>/mi, "")
-      html = html.gsub(/<div[^>]*class=["'][^"']*site-nav[^"']*["'][^>]*>.*?<\/div>/mi, "")
-      html = html.gsub(/<div[^>]*class=["'][^"']*site-header[^"']*["'][^>]*>.*?<\/div>/mi, "")
-      html = html.gsub(/<div[^>]*class=["'][^"']*toc-wrap[^"']*["'][^>]*>.*?<\/div>/mi, "")
+      html = html.gsub(/<div[^>]*class=["'][^"']*side-bar[^"']*["'][^>]*>.*?<\/div>/mis, "")
+      html = html.gsub(/<div[^>]*class=["'][^"']*site-nav[^"']*["'][^>]*>.*?<\/div>/mis, "")
+      html = html.gsub(/<div[^>]*class=["'][^"']*site-header[^"']*["'][^>]*>.*?<\/div>/mis, "")
+      html = html.gsub(/<div[^>]*class=["'][^"']*toc-wrap[^"']*["'][^>]*>.*?<\/div>/mis, "")
 
       # Try to extract main content area - look for main-content or main-content-wrap
       # Using multiline and dotall matching
-      if html =~ /<div[^>]*class=["'][^"']*main-content[^"']*["'][^>]*>(.*?)<\/div>/mi
+      if html =~ /<div[^>]*class=["'][^"']*main-content[^"']*["'][^>]*>(.*?)<\/div>/mis
         html = $1
-      elsif html =~ /<div[^>]*id=["'][^"']*main-content[^"']*["'][^>]*>(.*?)<\/div>/mi
+      elsif html =~ /<div[^>]*id=["'][^"']*main-content[^"']*["'][^>]*>(.*?)<\/div>/mis
         html = $1
-      elsif html =~ /<main[^>]*>(.*?)<\/main>/mi
+      elsif html =~ /<main[^>]*>(.*?)<\/main>/mis
         html = $1
-      elsif html =~ /<div[^>]*id=["'][^"']*main[^"']*["'][^>]*>(.*?)<\/div>/mi
+      elsif html =~ /<div[^>]*id=["'][^"']*main[^"']*["'][^>]*>(.*?)<\/div>/mis
         html = $1
       end
 
       # Remove breadcrumb navigation
-      html = html.gsub(/<nav[^>]*aria-label=["']Breadcrumb["'][^>]*>.*?<\/nav>/mi, "")
-      html = html.gsub(/<div[^>]*class=["'][^"']*breadcrumb[^"']*["'][^>]*>.*?<\/div>/mi, "")
+      html = html.gsub(/<nav[^>]*aria-label=["']Breadcrumb["'][^>]*>.*?<\/nav>/mis, "")
+      html = html.gsub(/<div[^>]*class=["'][^"']*breadcrumb[^"']*["'][^>]*>.*?<\/div>/mis, "")
 
       # Remove any remaining script/style tags
-      html = html.gsub(/<script[^>]*>.*?<\/script>/mi, "")
-      html = html.gsub(/<style[^>]*>.*?<\/style>/mi, "")
+      html = html.gsub(/<script[^>]*>.*?<\/script>/mis, "")
+      html = html.gsub(/<style[^>]*>.*?<\/style>/mis, "")
 
       # Remove SVG elements (icons, etc.)
-      html = html.gsub(/<svg[^>]*>.*?<\/svg>/mi, "")
+      html = html.gsub(/<svg[^>]*>.*?<\/svg>/mis, "")
 
       # Clean up extra whitespace
       html = html.gsub(/\s+/, " ")
@@ -560,6 +569,7 @@ def escape_html(text)
 # Hook to generate PDFs after all files are written
 Jekyll::Hooks.register :site, :post_write do |site|
   next unless site.config["pdf_generator"] && site.config["pdf_generator"]["enabled"]
+  next unless GROVER_AVAILABLE
 
   # Process all queued PDF generations
   Jekyll::PdfGenerator.pdf_jobs.each do |pdf_job|

_plugins/pdf_generator_loader.rb

@@ -2,5 +2,27 @@
 
 # Loader for PDF Generator plugin
 # This file ensures the PDF generator plugin is loaded from _pdf_generator directory
-require_relative "../_pdf_generator/pdf_generator"
+# The PDF generator handles missing grover gem gracefully, so this will not fail if grover is unavailable
+begin
+  require_relative "../_pdf_generator/pdf_generator"
+rescue LoadError => e
+  # If the PDF generator file itself can't be loaded, that's a real error
+  # But if grover is missing, the PDF generator will handle it gracefully
+  if e.message.include?("grover") || e.message.include?("cannot load such file -- grover")
+    # If it's just grover missing, we can continue - PDF generation will be disabled
+    # Define a dummy constant so the code doesn't break
+    module Jekyll
+      class PdfGenerator < Generator
+        def generate(site)
+          # No-op when grover is not available
+        end
+      end
+    end
+    # Set the constant that the PDF generator expects
+    GROVER_AVAILABLE = false unless defined?(GROVER_AVAILABLE)
+  else
+    # Re-raise if it's a different error
+    raise e
+  end
+end