paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-09-01 01:46:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

checking file types against parsers in the consumer.

Browse Source
This commit is contained in:
jonaswinkler
2020-12-01 15:26:05 +01:00
parent b0c8ade241
commit 834352130c
5 changed files with 127 additions and 113 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
src/documents/consumer.py
View File

@@ -41,21 +41,6 @@ class Consumer(LoggingMixin):
raise ConsumerError("Cannot consume {}: It is not a file".format(
self.path))
def pre_check_file_extension(self):
extensions = get_supported_file_extensions()
_, ext = os.path.splitext(self.filename)
if not ext:
raise ConsumerError(
f"Not consuming {self.filename}: File type unknown."
)
if ext not in extensions:
raise ConsumerError(
f"Not consuming {self.filename}: File extension {ext} does "
f"not map to any known file type ({str(extensions)})"
)
def pre_check_duplicate(self):
with open(self.path, "rb") as f:
checksum = hashlib.md5(f.read()).hexdigest()
@@ -98,7 +83,6 @@ class Consumer(LoggingMixin):
# Make sure that preconditions for consuming the file are met.
self.pre_check_file_exists()
self.pre_check_file_extension()
self.pre_check_directories()
self.pre_check_duplicate()