mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2025-04-02 13:45:10 -05:00
split handle_message function
This commit is contained in:
phail
parent
1fa735eb23
commit
df101f5e7a
@ -351,11 +351,15 @@ class MailAccountHandler(LoggingMixin):
|
||||
return total_processed_files
|
||||
|
||||
def handle_message(self, message, rule: MailRule) -> int:
|
||||
processed_elements = 0
|
||||
|
||||
# Skip Message handling when only attachments are to be processed but
|
||||
# message doesn't have any.
|
||||
if (
|
||||
not message.attachments
|
||||
and rule.consumption_scope == MailRule.ConsumptionScope.ATTACHMENTS_ONLY
|
||||
):
|
||||
return 0
|
||||
return processed_elements
|
||||
|
||||
self.log(
|
||||
"debug",
|
||||
@ -368,62 +372,41 @@ class MailAccountHandler(LoggingMixin):
|
||||
tag_ids = [tag.id for tag in rule.assign_tags.all()]
|
||||
doc_type = rule.assign_document_type
|
||||
|
||||
processed_attachments = 0
|
||||
|
||||
if (
|
||||
rule.consumption_scope == MailRule.ConsumptionScope.EML_ONLY
|
||||
or rule.consumption_scope == MailRule.ConsumptionScope.EVERYTHING
|
||||
):
|
||||
os.makedirs(settings.SCRATCH_DIR, exist_ok=True)
|
||||
_, temp_filename = tempfile.mkstemp(
|
||||
prefix="paperless-mail-",
|
||||
dir=settings.SCRATCH_DIR,
|
||||
suffix=".eml",
|
||||
processed_elements += self.process_eml(
|
||||
message,
|
||||
rule,
|
||||
correspondent,
|
||||
tag_ids,
|
||||
doc_type,
|
||||
)
|
||||
with open(temp_filename, "wb") as f:
|
||||
# Move "From"-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.
|
||||
from_element = None
|
||||
for i, header in enumerate(message.obj._headers):
|
||||
if header[0] == "From":
|
||||
from_element = i
|
||||
if from_element:
|
||||
new_headers = [message.obj._headers.pop(from_element)]
|
||||
new_headers += message.obj._headers
|
||||
message.obj._headers = new_headers
|
||||
|
||||
f.write(message.obj.as_bytes())
|
||||
|
||||
self.log(
|
||||
"info",
|
||||
f"Rule {rule}: "
|
||||
f"Consuming eml from mail "
|
||||
f"{message.subject} from {message.from_}",
|
||||
)
|
||||
|
||||
consume_file.delay(
|
||||
path=temp_filename,
|
||||
override_filename=pathvalidate.sanitize_filename(
|
||||
message.subject + ".eml",
|
||||
),
|
||||
override_title=message.subject,
|
||||
override_correspondent_id=correspondent.id if correspondent else None,
|
||||
override_document_type_id=doc_type.id if doc_type else None,
|
||||
override_tag_ids=tag_ids,
|
||||
)
|
||||
processed_attachments += 1
|
||||
|
||||
if (
|
||||
rule.consumption_scope == MailRule.ConsumptionScope.ATTACHMENTS_ONLY
|
||||
or rule.consumption_scope == MailRule.ConsumptionScope.EVERYTHING
|
||||
):
|
||||
processed_elements += self.process_attachments(
|
||||
message,
|
||||
rule,
|
||||
correspondent,
|
||||
tag_ids,
|
||||
doc_type,
|
||||
)
|
||||
|
||||
return processed_elements
|
||||
|
||||
def process_attachments(
|
||||
self,
|
||||
message: MailMessage,
|
||||
rule: MailRule,
|
||||
correspondent,
|
||||
tag_ids,
|
||||
doc_type,
|
||||
):
|
||||
processed_attachments = 0
|
||||
for att in message.attachments:
|
||||
|
||||
if (
|
||||
@ -494,4 +477,57 @@ class MailAccountHandler(LoggingMixin):
|
||||
f"by paperless",
|
||||
)
|
||||
|
||||
return processed_attachments
|
||||
def process_eml(
|
||||
self,
|
||||
message: MailMessage,
|
||||
rule: MailRule,
|
||||
correspondent,
|
||||
tag_ids,
|
||||
doc_type,
|
||||
):
|
||||
os.makedirs(settings.SCRATCH_DIR, exist_ok=True)
|
||||
_, temp_filename = tempfile.mkstemp(
|
||||
prefix="paperless-mail-",
|
||||
dir=settings.SCRATCH_DIR,
|
||||
suffix=".eml",
|
||||
)
|
||||
with open(temp_filename, "wb") as f:
|
||||
# Move "From"-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.
|
||||
from_element = None
|
||||
for i, header in enumerate(message.obj._headers):
|
||||
if header[0] == "From":
|
||||
from_element = i
|
||||
if from_element:
|
||||
new_headers = [message.obj._headers.pop(from_element)]
|
||||
new_headers += message.obj._headers
|
||||
message.obj._headers = new_headers
|
||||
|
||||
f.write(message.obj.as_bytes())
|
||||
|
||||
self.log(
|
||||
"info",
|
||||
f"Rule {rule}: "
|
||||
f"Consuming eml from mail "
|
||||
f"{message.subject} from {message.from_}",
|
||||
)
|
||||
|
||||
consume_file.delay(
|
||||
path=temp_filename,
|
||||
override_filename=pathvalidate.sanitize_filename(
|
||||
message.subject + ".eml",
|
||||
),
|
||||
override_title=message.subject,
|
||||
override_correspondent_id=correspondent.id if correspondent else None,
|
||||
override_document_type_id=doc_type.id if doc_type else None,
|
||||
override_tag_ids=tag_ids,
|
||||
)
|
||||
processed_elements = 1
|
||||
return processed_elements
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user