Use structured filenames and formal DOCX transcript styling

scraibe/tasks.py

@@ -17,6 +17,32 @@ from .email_sender import create_transcript_docx, create_summary_docx
 logger = logging.getLogger("scraibe.tasks")
 
 
+def _local_part(email: str) -> str:
+    """
+    Extract the part before '@' from an email, sanitized for filenames.
+    """
+    local = (email or "").split("@")[0].strip()
+    local = "".join(ch if ch.isalnum() or ch in ("-", "_", ".") else "_" for ch in local)
+    return local or "user"
+
+
+def _date_tag() -> str:
+    """
+    Date tag in DD-MON-YYYY format (e.g. 01-JAN-2025).
+    """
+    return datetime.utcnow().strftime("%d-%b-%Y").upper()
+
+
+def _safe_filename(base: str, local: str, date_tag: str, ext: str) -> str:
+    """
+    Create a temp file with the requested logical name.
+    Uses mktemp for uniqueness but keeps the desired name pattern.
+    """
+    name = f"{base}-{local}-{date_tag}{ext}"
+    # Ensure uniqueness while preserving the logical name pattern
+    return tempfile.mktemp(prefix=name.replace(".", ""), suffix=ext)
+
+
 def _remove_file(path: str):
     """
     Remove a file if it exists. Best-effort; logs but never raises.
@@ -224,6 +250,10 @@ def process_transcription_task(
     # Track all temporary files to clean up later
     temp_files = []
 
+    # Derive naming components
+    local = _local_part(email_to)
+    date_tag = _date_tag()
+
     try:
         # 1) Determine queue position and send initial email
         queue_pos = get_queue_position(task_id)
@@ -266,24 +296,21 @@ def process_transcription_task(
             segments = result.get("segments", [])
             raw_result = result.get("raw_result")
 
-        # 4) Prepare files for email
-        attachments = []
+        # 4) Prepare files for email with required naming
 
         # Transcript as .md
-        md_transcript_path = tempfile.mktemp(suffix=".md")
+        md_transcript_path = _safe_filename("TRANSCRIPT", local, date_tag, ".md")
         with open(md_transcript_path, "w", encoding="utf-8") as f:
             f.write("# Transcript\n\n")
             f.write(transcript_text)
-        attachments.append(md_transcript_path)
         temp_files.append(md_transcript_path)
 
-        # Transcript as .docx
-        docx_transcript_path = tempfile.mktemp(suffix=".docx")
+        # Transcript as .docx (with required style)
+        docx_transcript_path = _safe_filename("TRANSCRIPT", local, date_tag, ".docx")
         create_transcript_docx(transcript_text, docx_transcript_path)
-        attachments.append(docx_transcript_path)
         temp_files.append(docx_transcript_path)
 
-        # JSON with diarization
+        # JSON with diarization as SOURCE
         json_data = {
             "task": task_type,
             "transcript": transcript_text,
@@ -300,27 +327,36 @@ def process_transcription_task(
         if raw_result is not None:
             json_data["raw_result"] = raw_result
 
-        json_path = tempfile.mktemp(suffix=".json")
+        json_path = _safe_filename("SOURCE", local, date_tag, ".json")
         with open(json_path, "w", encoding="utf-8") as f:
             json.dump(json_data, f, indent=2, ensure_ascii=False)
-        attachments.append(json_path)
         temp_files.append(json_path)
 
         # Summary as .md (only when summary is available)
         if summary_text:
-            md_summary_path = tempfile.mktemp(suffix=".md")
+            md_summary_path = _safe_filename("SUMMARY", local, date_tag, ".md")
             with open(md_summary_path, "w", encoding="utf-8") as f:
                 f.write("# Summary\n\n")
                 f.write(summary_text)
-            attachments.append(md_summary_path)
             temp_files.append(md_summary_path)
 
             # Summary as .docx
-            docx_summary_path = tempfile.mktemp(suffix=".docx")
+            docx_summary_path = _safe_filename("SUMMARY", local, date_tag, ".docx")
             create_summary_docx(summary_text, docx_summary_path)
-            attachments.append(docx_summary_path)
             temp_files.append(docx_summary_path)
 
+        # All attachments
+        attachments = [
+            md_transcript_path,
+            docx_transcript_path,
+            json_path,
+        ]
+        if summary_text:
+            attachments += [
+                md_summary_path,
+                docx_summary_path,
+            ]
+
         # 5) Send success email
         send_success_email(
             to=email_to,