paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-28 18:24:38 -05:00
Code Issues Packages Projects Releases Wiki Activity

added file type checks to the parsers to prevent temporary files from being consumed. Also: parsers announce file types they wish to use as default for each mime type.

Browse Source
This commit is contained in:
jonaswinkler
2020-11-30 00:40:04 +01:00
parent ed5c3b550d
commit 7658c07b4d
7 changed files with 83 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/documents/tests/test_consumer.py
View File

@@ -423,7 +423,7 @@ class TestConsumer(DirectoriesMixin, TestCase):
m = patcher.start()
m.return_value = [(None, {
"parser": self.make_dummy_parser,
"mime_types": ["application/pdf"],
"mime_types": {"application/pdf": ".pdf"},
"weight": 0
})]
@@ -519,7 +519,7 @@ class TestConsumer(DirectoriesMixin, TestCase):
try:
self.consumer.try_consume_file(self.get_test_file())
except ConsumerError as e:
self.assertTrue(str(e).startswith("No parsers abvailable"))
self.assertTrue("File extension .pdf does not map to any" in str(e))
return
self.fail("Should throw exception")
@@ -528,7 +528,7 @@ class TestConsumer(DirectoriesMixin, TestCase):
def testFaultyParser(self, m):
m.return_value = [(None, {
"parser": self.make_faulty_parser,
"mime_types": ["application/pdf"],
"mime_types": {"application/pdf": ".pdf"},
"weight": 0
})]

29
src/documents/tests/test_parsers.py
View File

@@ -4,7 +4,10 @@ from unittest import mock
from django.test import TestCase
from documents.parsers import get_parser_class
from documents.parsers import get_parser_class, get_supported_file_extensions, get_default_file_extension, \
get_parser_class_for_mime_type
from paperless_tesseract.parsers import RasterisedDocumentParser
from paperless_text.parsers import TextDocumentParser
def fake_magic_from_file(file, mime=False):
@@ -27,7 +30,7 @@ class TestParserDiscovery(TestCase):
pass
m.return_value = (
(None, {"weight": 0, "parser": DummyParser, "mime_types": ["application/pdf"]}),
(None, {"weight": 0, "parser": DummyParser, "mime_types": {"application/pdf": ".pdf"}}),
)
self.assertEqual(
@@ -45,8 +48,8 @@ class TestParserDiscovery(TestCase):
pass
m.return_value = (
(None, {"weight": 0, "parser": DummyParser1, "mime_types": ["application/pdf"]}),
(None, {"weight": 1, "parser": DummyParser2, "mime_types": ["application/pdf"]}),
(None, {"weight": 0, "parser": DummyParser1, "mime_types": {"application/pdf": ".pdf"}}),
(None, {"weight": 1, "parser": DummyParser2, "mime_types": {"application/pdf": ".pdf"}}),
)
self.assertEqual(
@@ -61,3 +64,21 @@ class TestParserDiscovery(TestCase):
self.assertIsNone(
get_parser_class("doc.pdf")
)
class TestParserAvailability(TestCase):
def test_file_extensions(self):
for ext in [".pdf", ".jpe", ".jpg", ".jpeg", ".txt", ".csv"]:
self.assertIn(ext, get_supported_file_extensions())
self.assertEqual(get_default_file_extension('application/pdf'), ".pdf")
self.assertEqual(get_default_file_extension('image/png'), ".png")
self.assertEqual(get_default_file_extension('image/jpeg'), ".jpg")
self.assertEqual(get_default_file_extension('text/plain'), ".txt")
self.assertEqual(get_default_file_extension('text/csv'), ".csv")
self.assertEqual(get_default_file_extension('aasdasd/dgfgf'), None)
self.assertEqual(get_parser_class_for_mime_type('application/pdf'), RasterisedDocumentParser)
self.assertEqual(get_parser_class_for_mime_type('text/plain'), TextDocumentParser)
self.assertEqual(get_parser_class_for_mime_type('text/sdgsdf'), None)