feat: Handle missing article GUIDs by generating and embedding one in source file

swap_guids.py

@@ -1,5 +1,6 @@
 import logging
 import pprint
+import uuid
 
 from pelican import signals
 
@@ -20,7 +21,64 @@ def modify_feed(context, feed):
             raise Exception(f"Article not found for title: {item_title}")
 
         if not hasattr(article, 'guid') or not article.guid:
-            raise Exception(f"Article '{article.title}' is missing a guid.")
+            log.info(f"Article '{article.title}' ({article.source_path}) is missing a guid. Generating and embedding one.")
+            new_guid_str = uuid.uuid4().hex
+            # The string to embed in the paragraph. Note the leading space.
+            guid_text_to_embed = f" Guid: {new_guid_str}"
+
+            source_path = article.source_path
+            
+            # Reconstruct metadata header from article.metadata
+            # article.metadata keys are typically lowercase. Capitalize them for convention.
+            metadata_header_lines = []
+            for key, value in article.metadata.items():
+                if isinstance(value, list):
+                    # Convert list items to string and join with comma (e.g., for tags)
+                    metadata_header_lines.append(f"{key.capitalize()}: {', '.join(map(str, value))}")
+                else:
+                    # Ensure value is string for concatenation
+                    metadata_header_lines.append(f"{key.capitalize()}: {str(value)}")
+            
+            # article._content holds the raw Markdown content string (after metadata parsing)
+            if not hasattr(article, '_content'):
+                log.error(f"Article '{article.title}' does not have '_content' attribute. Cannot embed Guid into source file.")
+                # This is a critical issue for the requested operation.
+                raise Exception(f"Cannot find raw content for article '{article.title}' to embed Guid.")
+
+            markdown_body = article._content
+
+            # Split the markdown body into the first paragraph and the rest
+            # Paragraphs in Markdown are separated by one or more blank lines (\n\n)
+            parts = markdown_body.split('\n\n', 1)
+            first_paragraph_text = parts[0]
+            rest_of_body = parts[1] if len(parts) > 1 else ""
+
+            # Append the Guid text to the end of the first paragraph
+            # .rstrip() removes any trailing whitespace/newlines from the paragraph itself before appending.
+            modified_first_paragraph = first_paragraph_text.rstrip() + guid_text_to_embed
+            
+            # Reconstruct the new markdown body
+            new_markdown_body = modified_first_paragraph
+            if rest_of_body: # Add back the rest of the body with the double newline separator
+                new_markdown_body += '\n\n' + rest_of_body
+            
+            # Combine metadata and new body to form the complete new file content
+            if metadata_header_lines:
+                full_new_content = "\n".join(metadata_header_lines) + "\n\n" + new_markdown_body
+            else: # No metadata, just the body
+                full_new_content = new_markdown_body
+
+            try:
+                with open(source_path, 'w', encoding='utf-8') as f:
+                    f.write(full_new_content)
+                log.info(f"Successfully wrote updated content with embedded Guid to '{source_path}'.")
+            except Exception as e:
+                log.error(f"Failed to write updated content to '{source_path}': {e}")
+                raise # Re-raise the exception to halt processing if file write fails
+
+            # Set article.guid for the current Pelican run, so it's used for the feed item
+            article.guid = new_guid_str
+            log.debug(f"Set in-memory article.guid = '{new_guid_str}' for '{article.title}'.")
 
         item['unique_id'] = article.guid