paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-30 18:27:45 -05:00
Code Issues Packages Projects Releases Wiki Activity

supply file_name for tika parser

Browse Source
This commit is contained in:
jonaswinkler
2021-01-01 22:19:43 +01:00
parent f800fdf66a
commit 755f950cd2
6 changed files with 10 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/documents/consumer.py
View File

@@ -1,6 +1,5 @@
import datetime
import hashlib
import logging
import os
import magic
@@ -130,7 +129,7 @@ class Consumer(LoggingMixin):
try:
self.log("debug", "Parsing {}...".format(self.filename))
document_parser.parse(self.path, mime_type)
document_parser.parse(self.path, mime_type, self.filename)
self.log("debug", f"Generating thumbnail for {self.filename}...")
thumbnail = document_parser.get_optimised_thumbnail(

2
src/documents/parsers.py
View File

@@ -267,7 +267,7 @@ class DocumentParser(LoggingMixin):
def extract_metadata(self, document_path, mime_type):
return []
def parse(self, document_path, mime_type):
def parse(self, document_path, mime_type, file_name=None):
raise NotImplementedError()
def get_archive_path(self):

4
src/documents/tests/test_consumer.py
View File

@@ -177,7 +177,7 @@ class DummyParser(DocumentParser):
def get_optimised_thumbnail(self, document_path, mime_type):
return self.fake_thumb
def parse(self, document_path, mime_type):
def parse(self, document_path, mime_type, file_name=None):
self.text = "The Text"
@@ -194,7 +194,7 @@ class FaultyParser(DocumentParser):
def get_optimised_thumbnail(self, document_path, mime_type):
return self.fake_thumb
def parse(self, document_path, mime_type):
def parse(self, document_path, mime_type, file_name=None):
raise ParseError("Does not compute.")