first commit

backend/app/services/mime_parser.py

@@ -0,0 +1,90 @@
+import re
+from datetime import timezone
+from email import policy
+from email.parser import BytesParser
+from email.utils import getaddresses, parsedate_to_datetime
+from html import unescape
+
+
+def _addresses(values: list[str]) -> list[dict[str, str]]:
+    return [
+        {
+            "name": name.strip() or address.split("@", 1)[0],
+            "address": address.lower(),
+        }
+        for name, address in getaddresses(values)
+        if address
+    ]
+
+
+def _text(part) -> str:
+    try:
+        value = part.get_content()
+    except (LookupError, UnicodeError):
+        payload = part.get_payload(decode=True) or b""
+        value = payload.decode("utf-8", errors="replace")
+    return value if isinstance(value, str) else ""
+
+
+def _snippet(text: str, html: str | None, limit: int = 240) -> str:
+    source = text
+    if not source and html:
+        source = re.sub(r"<[^>]+>", " ", html)
+        source = unescape(source)
+    return re.sub(r"\s+", " ", source).strip()[:limit]
+
+
+def parse_mime(raw: bytes) -> dict:
+    message = BytesParser(policy=policy.default).parsebytes(raw)
+    sender = _addresses(message.get_all("from", []))
+    from_value = sender[0] if sender else {"name": "Unknown sender", "address": ""}
+    text_parts: list[str] = []
+    html_parts: list[str] = []
+    attachments: list[dict] = []
+
+    for part in message.walk():
+        if part.is_multipart():
+            continue
+        disposition = part.get_content_disposition()
+        filename = part.get_filename()
+        content_type = part.get_content_type()
+        payload = part.get_payload(decode=True) or b""
+        if disposition == "attachment" or filename:
+            attachments.append(
+                {
+                    "filename": filename or "attachment",
+                    "content_type": content_type,
+                    "size": len(payload),
+                    "content_id": (part.get("Content-ID") or "").strip("<>") or None,
+                    "disposition": disposition or "attachment",
+                }
+            )
+        elif content_type == "text/plain":
+            text_parts.append(_text(part))
+        elif content_type == "text/html":
+            html_parts.append(_text(part))
+
+    date = None
+    if message.get("Date"):
+        try:
+            date = parsedate_to_datetime(message["Date"])
+            if date.tzinfo is None:
+                date = date.replace(tzinfo=timezone.utc)
+            date = date.astimezone(timezone.utc)
+        except (TypeError, ValueError, OverflowError):
+            pass
+    body_text = "\n".join(text_parts).strip()
+    body_html = "\n".join(html_parts).strip() or None
+    return {
+        "message_id": (message.get("Message-ID") or "").strip() or None,
+        "sender": from_value,
+        "to": _addresses(message.get_all("to", [])),
+        "cc": _addresses(message.get_all("cc", [])),
+        "reply_to": _addresses(message.get_all("reply-to", [])),
+        "subject": str(message.get("Subject") or ""),
+        "sent_at": date,
+        "body_text": body_text,
+        "body_html": body_html,
+        "snippet": _snippet(body_text, body_html),
+        "attachments": attachments,
+    }