Zeige den Bezug zwischen Schreiben und lies eine E-Mail vor dem Uebernehmen.
Die Liste behaelt die Schreiben dazwischen. Richtung, Absender, Empfaenger und Anhaenge bleiben an der Nachricht erkennbar. Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
1 parent
97bffc6175
commit
f27df3ff35
19 files changed
+1049
-49
No files matched your search
+167
-1
@@ -143,6 +143,21 @@ def imap_messages(
|
||||
_imap_logout(client)
|
||||
|
||||
|
||||
def imap_preview(conn, owner_id: UUID, connector_id: UUID, mailbox: str, uid: int) -> dict:
|
||||
row = _owned(conn, owner_id, connector_id)
|
||||
if row["kind"] != "imap":
|
||||
raise unprocessable("Das ist kein E-Mail-Konto.")
|
||||
_check_mailbox(mailbox)
|
||||
if uid < 1:
|
||||
raise unprocessable("Die Nachricht ist ungültig.")
|
||||
client = _imap_login(row["settings"], row["secret"])
|
||||
try:
|
||||
_select_mailbox(client, mailbox)
|
||||
return _fetch_message(client, uid, mailbox)
|
||||
finally:
|
||||
_imap_logout(client)
|
||||
|
||||
|
||||
def _owned(conn, owner_id: UUID, connector_id: UUID) -> dict:
|
||||
row = conn.execute(
|
||||
"SELECT id, kind, name, settings, secret FROM connectors WHERE id = %s AND owner_id = %s",
|
||||
@@ -432,13 +447,42 @@ def _uid_search(client: imaplib.IMAP4, query: str):
|
||||
raise unprocessable("Das Postfach kann diese Suche nicht ausführen. Blättere im Fach oder kürze den Suchtext.") from exc
|
||||
|
||||
|
||||
def _check_mailbox(mailbox: str) -> None:
|
||||
if any(char in mailbox for char in "\r\n\x00"):
|
||||
raise unprocessable("Der Fachname ist ungültig.")
|
||||
|
||||
|
||||
def _select_mailbox(client: imaplib.IMAP4, mailbox: str) -> None:
|
||||
folders = _imap_mailboxes(client)
|
||||
match = next((item for item in folders if item["name"] == mailbox), None)
|
||||
if match is None or not match["selectable"]:
|
||||
raise unprocessable("Dieses Fach gibt es in dem Konto nicht.")
|
||||
try:
|
||||
status, _ = client.select(mailbox, readonly=True)
|
||||
except imaplib.IMAP4.error as exc:
|
||||
raise unprocessable("Dieses Fach lässt sich nicht öffnen.") from exc
|
||||
if status != "OK":
|
||||
raise unprocessable("Dieses Fach lässt sich nicht öffnen.")
|
||||
|
||||
|
||||
def _fetch_header(client: imaplib.IMAP4, uid: int, mailbox: str) -> dict | None:
|
||||
try:
|
||||
status, fetched = client.uid("FETCH", str(uid), "(BODY.PEEK[HEADER.FIELDS (FROM SUBJECT DATE MESSAGE-ID)])")
|
||||
status, fetched = client.uid(
|
||||
"FETCH",
|
||||
str(uid),
|
||||
"(BODY.PEEK[HEADER.FIELDS (FROM TO CC SUBJECT DATE MESSAGE-ID)])",
|
||||
)
|
||||
except imaplib.IMAP4.error:
|
||||
return None
|
||||
if status != "OK" or not fetched or not isinstance(fetched[0], tuple):
|
||||
return None
|
||||
attachments = []
|
||||
try:
|
||||
struct_status, structure = client.uid("FETCH", str(uid), "(BODYSTRUCTURE)")
|
||||
if struct_status == "OK":
|
||||
attachments = _structure_attachments(structure)
|
||||
except imaplib.IMAP4.error:
|
||||
attachments = []
|
||||
header = BytesParser().parsebytes(fetched[0][1])
|
||||
subject = _decode(header.get("Subject")) or "(ohne Betreff)"
|
||||
sender = _decode(header.get("From"))
|
||||
@@ -448,10 +492,132 @@ def _fetch_header(client: imaplib.IMAP4, uid: int, mailbox: str) -> dict | None:
|
||||
"uid": uid,
|
||||
"title": subject[:200],
|
||||
"message_from": sender[:200],
|
||||
"message_to": _decode(header.get("To"))[:500],
|
||||
"message_cc": _decode(header.get("Cc"))[:500],
|
||||
"direction": _direction(mailbox),
|
||||
"attachments": attachments,
|
||||
"document_on": _mail_date(header.get("Date")),
|
||||
}
|
||||
|
||||
|
||||
def _fetch_message(client: imaplib.IMAP4, uid: int, mailbox: str) -> dict:
|
||||
try:
|
||||
status, fetched = client.uid("FETCH", str(uid), "(BODY.PEEK[])")
|
||||
except imaplib.IMAP4.error as exc:
|
||||
raise unprocessable("Die Nachricht lässt sich nicht lesen.") from exc
|
||||
raw = _literal(fetched)
|
||||
if status != "OK" or raw is None:
|
||||
raise unprocessable("Die Nachricht lässt sich nicht lesen.")
|
||||
if len(raw) > 1_500_000:
|
||||
raise unprocessable("Die Nachricht ist zu groß für die Vorschau.")
|
||||
message = BytesParser().parsebytes(raw)
|
||||
subject = _decode(message.get("Subject")) or "(ohne Betreff)"
|
||||
return {
|
||||
"uid": uid,
|
||||
"mailbox": mailbox,
|
||||
"title": subject[:200],
|
||||
"message_from": _decode(message.get("From"))[:200],
|
||||
"message_to": _decode(message.get("To"))[:500],
|
||||
"message_cc": _decode(message.get("Cc"))[:500],
|
||||
"direction": _direction(mailbox),
|
||||
"document_on": _mail_date(message.get("Date")),
|
||||
"attachments": _message_attachments(message),
|
||||
"text": _message_text(message),
|
||||
}
|
||||
|
||||
|
||||
_SENT_FOLDER = re.compile(
|
||||
r"(^|/)(sent|sent items|sent messages|gesendet|gesendete|gesendete elemente|outbox|postausgang)($|/)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
|
||||
def _direction(mailbox: str) -> str:
|
||||
folded = mailbox.casefold().replace("\\", "/")
|
||||
return "out" if _SENT_FOLDER.search(folded) else "in"
|
||||
|
||||
|
||||
def _literal(fetched) -> bytes | None:
|
||||
for part in fetched or []:
|
||||
if isinstance(part, tuple) and len(part) > 1 and isinstance(part[1], (bytes, bytearray)):
|
||||
return bytes(part[1])
|
||||
return None
|
||||
|
||||
|
||||
def _structure_attachments(fetched) -> list[dict]:
|
||||
chunks: list[bytes] = []
|
||||
for part in fetched or []:
|
||||
if isinstance(part, tuple):
|
||||
chunks.extend(bytes(item) for item in part if isinstance(item, (bytes, bytearray)))
|
||||
elif isinstance(part, (bytes, bytearray)):
|
||||
chunks.append(bytes(part))
|
||||
blob = b" ".join(chunks)
|
||||
names = re.findall(br'FILENAME"\s+"([^"\r\n]+)"', blob, flags=re.IGNORECASE)
|
||||
items = []
|
||||
seen: set[str] = set()
|
||||
for raw in names:
|
||||
name = raw.decode("utf-8", errors="replace").strip()[:200]
|
||||
if not name or name in seen:
|
||||
continue
|
||||
seen.add(name)
|
||||
items.append({"filename": name})
|
||||
if len(items) == 40:
|
||||
break
|
||||
return items
|
||||
|
||||
|
||||
def _message_attachments(message) -> list[dict]:
|
||||
items = []
|
||||
seen: set[str] = set()
|
||||
for part in message.walk():
|
||||
filename = part.get_filename()
|
||||
if not filename:
|
||||
continue
|
||||
name = _decode(filename)[:200]
|
||||
if not name or name in seen:
|
||||
continue
|
||||
seen.add(name)
|
||||
items.append({"filename": name, "content_type": part.get_content_type()[:120]})
|
||||
if len(items) == 40:
|
||||
break
|
||||
return items
|
||||
|
||||
|
||||
def _message_text(message) -> str:
|
||||
plain: list[str] = []
|
||||
html: list[str] = []
|
||||
parts = message.walk() if message.is_multipart() else [message]
|
||||
for part in parts:
|
||||
if part.is_multipart() or part.get_content_disposition() == "attachment" or part.get_filename():
|
||||
continue
|
||||
kind = part.get_content_type()
|
||||
if kind == "text/plain":
|
||||
plain.append(_part_text(part))
|
||||
elif kind == "text/html":
|
||||
html.append(_html_text(_part_text(part)))
|
||||
text = "\n".join(chunk for chunk in plain if chunk).strip()
|
||||
if not text:
|
||||
text = "\n".join(chunk for chunk in html if chunk).strip()
|
||||
return text[:8000]
|
||||
|
||||
|
||||
def _part_text(part) -> str:
|
||||
payload = part.get_payload(decode=True)
|
||||
if payload is None:
|
||||
raw = part.get_payload()
|
||||
return raw.strip() if isinstance(raw, str) else ""
|
||||
charset = part.get_content_charset() or "utf-8"
|
||||
return payload.decode(charset, errors="replace").strip()
|
||||
|
||||
|
||||
def _html_text(value: str) -> str:
|
||||
text = re.sub(r"(?is)<(script|style)\b.*?>.*?</\1>", " ", value)
|
||||
text = re.sub(r"(?i)<br\s*/?>", "\n", text)
|
||||
text = re.sub(r"(?i)</p>", "\n", text)
|
||||
text = re.sub(r"<[^>]+>", " ", text)
|
||||
return re.sub(r"[ \t]{2,}", " ", text).strip()
|
||||
|
||||
|
||||
def _parse_list_line(raw) -> dict | None:
|
||||
if not isinstance(raw, (bytes, str)) or not raw:
|
||||
return None
|
||||
|
||||
Reference in new issue
Block a user