feat(sync): Add EML to TXT conversion for improved document handling in RAGflow sync

src/steps/crm/akte/akte_sync_event_step.py

@@ -674,6 +674,63 @@ async def _run_ragflow_sync(
                     file_content = await espocrm.download_attachment(attachment_id)
                     ctx.logger.info(f"     Downloaded {len(file_content)} bytes")
 
+                    # ── EML → TXT Konvertierung ───────────────────────────────
+                    if filename.lower().endswith('.eml'):
+                        try:
+                            import email as _email
+                            from bs4 import BeautifulSoup
+                            msg = _email.message_from_bytes(file_content)
+                            subject = msg.get('Subject', '')
+                            from_   = msg.get('From', '')
+                            date    = msg.get('Date', '')
+                            plain_parts, html_parts = [], []
+                            if msg.is_multipart():
+                                for part in msg.walk():
+                                    ct = part.get_content_type()
+                                    if ct == 'text/plain':
+                                        plain_parts.append(part.get_payload(decode=True).decode(
+                                            part.get_content_charset() or 'utf-8', errors='replace'))
+                                    elif ct == 'text/html':
+                                        html_parts.append(part.get_payload(decode=True).decode(
+                                            part.get_content_charset() or 'utf-8', errors='replace'))
+                            else:
+                                ct = msg.get_content_type()
+                                payload = msg.get_payload(decode=True).decode(
+                                    msg.get_content_charset() or 'utf-8', errors='replace')
+                                if ct == 'text/html':
+                                    html_parts.append(payload)
+                                else:
+                                    plain_parts.append(payload)
+                            if plain_parts:
+                                body = '\n\n'.join(plain_parts)
+                            elif html_parts:
+                                soup = BeautifulSoup('\n'.join(html_parts), 'html.parser')
+                                for tag in soup(['script', 'style', 'header', 'footer', 'nav']):
+                                    tag.decompose()
+                                body = '\n'.join(
+                                    line.strip()
+                                    for line in soup.get_text(separator='\n').splitlines()
+                                    if line.strip()
+                                )
+                            else:
+                                body = ''
+                            header = (
+                                f"Betreff: {subject}\n"
+                                f"Von: {from_}\n"
+                                f"Datum: {date}\n"
+                                f"{'-' * 80}\n\n"
+                            )
+                            converted_text = (header + body).strip()
+                            file_content = converted_text.encode('utf-8')
+                            filename = filename[:-4] + '.txt'
+                            mime_type = 'text/plain'
+                            ctx.logger.info(
+                                f"     📧 EML→TXT konvertiert: {len(file_content)} bytes "
+                                f"(blake3 des Original-EML bleibt erhalten)"
+                            )
+                        except Exception as eml_err:
+                            ctx.logger.warn(f"     ⚠️  EML-Konvertierung fehlgeschlagen, lade roh hoch: {eml_err}")
+
                     ctx.logger.info(f"     📤 Uploading '{filename}' ({mime_type})…")
                     result = await ragflow.upload_document(
                         dataset_id=dataset_id,