jpmschweitzer/odysseus
1
0
Fork 0
mirror of https://github.com/pewdiepie-archdaemon/odysseus.git synced 2026-11-03 19:52:20 +01:00
Code Issues Packages Projects Releases Wiki Activity

fix(email): decode MIME alternatives without duplicating bodies (#6953)

Browse Source
This commit is contained in:
red person
2026-11-03 00:39:55 +00:00
committed by GitHub
parent b7ab0a37c1
commit 682662d36f
4 changed files with 123 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files
routes/email/email_helpers.py
+18 -23
View File
@@ -36,6 +36,7 @@ from fastapi import Query, HTTPException, Request
from pydantic import BaseModel
from typing import Optional, List
from src.email_mime import decode_text_part as _decode_text_part
from src.auth_helpers import _auth_disabled, get_current_user
from src.secret_storage import decrypt as _decrypt
from src.url_safety import OutboundAddressBlocked, connect_outbound_tcp
@@ -1776,44 +1777,38 @@ def _extract_html(msg):
ct = part.get_content_type()
cd = str(part.get("Content-Disposition", ""))
if ct == "text/html" and "attachment" not in cd:
payload = part.get_payload(decode=True)
if payload:
charset = part.get_content_charset() or "utf-8"
return payload.decode(charset, errors="replace")
text = _decode_text_part(part)
if text:
return text
elif msg.get_content_type() == "text/html":
payload = msg.get_payload(decode=True)
if payload:
charset = msg.get_content_charset() or "utf-8"
return payload.decode(charset, errors="replace")
text = _decode_text_part(msg)
if text:
return text
return None
def _extract_text(msg):
if msg.is_multipart():
text_parts = []
html_parts = []
for part in msg.walk():
ct = part.get_content_type()
cd = str(part.get("Content-Disposition", ""))
if ct == "text/plain" and "attachment" not in cd:
payload = part.get_payload(decode=True)
if payload:
charset = part.get_content_charset() or "utf-8"
text_parts.append(payload.decode(charset, errors="replace"))
elif ct == "text/html" and not text_parts and "attachment" not in cd:
payload = part.get_payload(decode=True)
if payload:
charset = part.get_content_charset() or "utf-8"
raw_html = payload.decode(charset, errors="replace")
text = _decode_text_part(part)
if text:
text_parts.append(text)
elif ct == "text/html" and not html_parts and "attachment" not in cd:
raw_html = _decode_text_part(part)
if raw_html:
text = re.sub(r"<br\s*/?>", "\n", raw_html, flags=re.I)
text = re.sub(r"<[^>]+>", "", text)
text = html.unescape(text)
text_parts.append(text.strip())
return "\n".join(text_parts)
html_parts.append(text.strip())
return "\n".join(text_parts or html_parts)
else:
payload = msg.get_payload(decode=True)
if payload:
charset = msg.get_content_charset() or "utf-8"
text = payload.decode(charset, errors="replace")
text = _decode_text_part(msg)
if text:
if msg.get_content_type() == "text/html":
text = re.sub(r"<br\s*/?>", "\n", text, flags=re.I)
text = re.sub(r"</(?:p|div|li|tr|h[1-6])\s*>", "\n", text, flags=re.I)