Add PDF-based document generation with LibreOffice; fix line numbering and margins

- Add LibreOffice Writer and DejaVu fonts to Dockerfile for PDF generation
- Add PyPDF2 and reportlab to requirements.txt
- Refactor email_sender.py:
  - Enforce 1-inch margins on all sides
  - Isolate line numbering to transcript section only
  - Add generate_pdf_documents() to build:
    - TRANSCRIPT.pdf (cover + transcript)
    - SUMMARY.pdf (cover + summary)
    - COMBINED.pdf (transcript cover + summary + TRANSCRIPT header + transcript)
  - Add page numbers (bottom-right) to all PDFs via reportlab
- Update tasks.py:
  - Use generate_pdf_documents() after creating DOCX files
  - Attach source JSON, MD files, and compiled PDFs in success email
- Add test_docx_generation.py for transcript/summary/combined DOCX testing

scraibe/tasks.py

@@ -14,7 +14,7 @@ from .summarizer import SummarizerClient, SummarizerError
 from .misc import setup_logging
 from .email_sender import send_email, EmailError, load_template
 from .email_sender import create_transcript_docx, create_summary_docx
-from .email_sender import create_combined_docx
+from .email_sender import create_combined_docx, generate_pdf_documents
 
 logger = logging.getLogger("scraibe.tasks")
 
@@ -545,6 +545,26 @@ def process_transcription_task(
             )
             temp_files.append(docx_combined_path)
 
+        # 4b) Generate PDF documents
+        pdf_files = {}
+        try:
+            pdf_output_dir = tempfile.mkdtemp(prefix="pdf_output_")
+            pdf_files = generate_pdf_documents(
+                transcript_text=transcript_text,
+                summary_text=summary_text if include_summary else "",
+                output_dir=pdf_output_dir,
+                transcript_cover_date=today_str,
+                transcript_cover_desc=transcript_cover_desc,
+                summary_cover_date=today_str,
+                summary_cover_desc=summary_cover_desc,
+            )
+            for pdf_path in pdf_files.values():
+                if pdf_path and os.path.exists(pdf_path):
+                    temp_files.append(pdf_path)
+        except Exception as e:
+            logger.warning("PDF generation failed (continuing with DOCX attachments): %s", e)
+
+        # 5) Build attachments list
         attachments = [
             md_transcript_path,
             docx_transcript_path,
@@ -555,7 +575,15 @@ def process_transcription_task(
             if docx_combined_path:
                 attachments.append(docx_combined_path)
 
-        # 5) Send success email
+        # Add PDFs to attachments
+        if pdf_files.get("transcript_pdf"):
+            attachments.append(pdf_files["transcript_pdf"])
+        if pdf_files.get("summary_pdf"):
+            attachments.append(pdf_files["summary_pdf"])
+        if pdf_files.get("combined_pdf"):
+            attachments.append(pdf_files["combined_pdf"])
+
+        # 6) Send success email
         send_success_email(
             to=email_to,
             transcript_text=transcript_text,
@@ -575,7 +603,7 @@ def process_transcription_task(
         )
         raise e
     finally:
-        # 6) Cleanup
+        # 7) Cleanup
         for path in temp_files:
             _remove_file(path)
         if audio_path: