paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-15 10:13:15 -05:00
Code Issues Packages Projects Releases Wiki Activity

workaround for wrong mime detection of .eml files

Browse Source
This commit is contained in:
phail 2022-05-14 16:47:12 +02:00
parent c317eca1ca
commit 6809b15ce1
1 changed files with 19 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
src/paperless_mail/mail.py
View File

@ -339,8 +339,27 @@ class MailAccountHandler(LoggingMixin):
_, temp_filename = tempfile.mkstemp( _, temp_filename = tempfile.mkstemp(
prefix="paperless-mail-", prefix="paperless-mail-",
dir=settings.SCRATCH_DIR, dir=settings.SCRATCH_DIR,
suffix=".eml",
) )
with open(temp_filename, "wb") as f: with open(temp_filename, "wb") as f:
# Move "Date"-header to beginning of file
# TODO: This ugly workaround is needed because the parser is
# chosen only by the mime_type detected via magic
# (see documents/consumer.py "mime_type = magic.from_file")
# Unfortunately magic sometimes fails to detect the mime
# type of .eml files correctly as message/rfc822 and instead
# detects text/plain.
# This also effects direct file consumption of .eml files
# which are not treated with this workaround.
date_element = None
for i, header in enumerate(message.obj._headers):
if header[0] == "Date":
date_element = i
if date_element:
new_headers = [message.obj._headers.pop(date_element)]
new_headers += message.obj._headers
message.obj._headers = new_headers
f.write(message.obj.as_bytes()) f.write(message.obj.as_bytes())
self.log( self.log(