diff --git a/scripts/imap_sync.py b/scripts/imap_sync.py
index 220a54f..e900aed 100644
--- a/scripts/imap_sync.py
+++ b/scripts/imap_sync.py
@@ -698,21 +698,43 @@ def _parse_message(conn: imaplib.IMAP4, uid: bytes) -> Optional[dict]:
return None
msg = email.message_from_bytes(data[0][1])
- body = ""
+ # Prefer text/html (preserves href attributes for digest link extraction);
+ # fall back to text/plain if no HTML part exists.
+ html_body = ""
+ plain_body = ""
if msg.is_multipart():
for part in msg.walk():
- if part.get_content_type() == "text/plain":
+ ct = part.get_content_type()
+ if ct == "text/html" and not html_body:
try:
- body = part.get_payload(decode=True).decode("utf-8", errors="replace")
+ html_body = part.get_payload(decode=True).decode("utf-8", errors="replace")
+ except Exception:
+ pass
+ elif ct == "text/plain" and not plain_body:
+ try:
+ plain_body = part.get_payload(decode=True).decode("utf-8", errors="replace")
except Exception:
pass
- break
else:
+ ct = msg.get_content_type()
try:
- body = msg.get_payload(decode=True).decode("utf-8", errors="replace")
+ raw = msg.get_payload(decode=True).decode("utf-8", errors="replace")
+ if ct == "text/html":
+ html_body = raw
+ else:
+ plain_body = raw
except Exception:
pass
+ if html_body:
+ # Strip … (CSS, meta, title) and any stray ", "", body, flags=re.I)
+ body = re.sub(r"", "", body, flags=re.I)
+ else:
+ body = plain_body
+
mid = msg.get("Message-ID", "").strip()
if not mid:
return None # No Message-ID → can't dedup; skip to avoid repeat inserts
@@ -723,7 +745,7 @@ def _parse_message(conn: imaplib.IMAP4, uid: bytes) -> Optional[dict]:
"from_addr": _decode_str(msg.get("From")),
"to_addr": _decode_str(msg.get("To")),
"date": _decode_str(msg.get("Date")),
- "body": body[:4000],
+ "body": body, # no truncation — digest emails need full content
}
except Exception:
return None
diff --git a/tests/test_imap_sync.py b/tests/test_imap_sync.py
index f9cc4e5..5bdc687 100644
--- a/tests/test_imap_sync.py
+++ b/tests/test_imap_sync.py
@@ -1024,8 +1024,8 @@ def test_sync_all_per_job_exception_continues(tmp_path):
# ── Performance / edge cases ──────────────────────────────────────────────────
-def test_parse_message_large_body_truncated():
- """Body longer than 4000 chars is silently truncated to 4000."""
+def test_parse_message_large_body_not_truncated():
+ """Body longer than 4000 chars is stored in full (no truncation)."""
from scripts.imap_sync import _parse_message
big_body = ("x" * 10_000).encode()
@@ -1037,7 +1037,7 @@ def test_parse_message_large_body_truncated():
conn.fetch.return_value = ("OK", [(b"1 (RFC822)", raw)])
result = _parse_message(conn, b"1")
assert result is not None
- assert len(result["body"]) <= 4000
+ assert len(result["body"]) == 10_000
def test_parse_message_binary_attachment_no_crash():