mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-09-23 09:50:32 +00:00
Trenton HandClaude Sonnet 4.6
f86ddcf221
All callers now call get_parser_registry().get_parser_for_file() with the actual filename and path, enabling score() to use file extension hints. The MIME-only helper is removed. - consumer.py: passes self.filename + self.working_copy - tasks.py: passes document.original_filename + document.source_path - document_thumbnails.py: same pattern - views.py: passes Path(file).name + Path(file) - parsers.py: internal helpers inline the registry call with filename="" - test_parsers.py: drop TestParserDiscovery (was testing mock behavior); TestParserAvailability uses registry directly - test_consumer.py: mocks switch to documents.consumer.get_parser_registry Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
114 lines
4.0 KiB
Python
114 lines
4.0 KiB
Python
from django.test import TestCase
|
|
from django.test import override_settings
|
|
|
|
from documents.parsers import get_default_file_extension
|
|
from documents.parsers import get_supported_file_extensions
|
|
from documents.parsers import is_file_ext_supported
|
|
from paperless.parsers.registry import get_parser_registry
|
|
from paperless.parsers.registry import reset_parser_registry
|
|
from paperless.parsers.tesseract import RasterisedDocumentParser
|
|
from paperless.parsers.text import TextDocumentParser
|
|
from paperless.parsers.tika import TikaDocumentParser
|
|
|
|
|
|
class TestParserAvailability(TestCase):
|
|
def test_tesseract_parser(self) -> None:
|
|
"""
|
|
GIVEN:
|
|
- Various mime types
|
|
WHEN:
|
|
- The parser class is instantiated
|
|
THEN:
|
|
- The Tesseract based parser is return
|
|
"""
|
|
supported_mimes_and_exts = [
|
|
("application/pdf", ".pdf"),
|
|
("image/png", ".png"),
|
|
("image/jpeg", ".jpg"),
|
|
("image/tiff", ".tif"),
|
|
("image/webp", ".webp"),
|
|
]
|
|
|
|
supported_exts = get_supported_file_extensions()
|
|
|
|
for mime_type, ext in supported_mimes_and_exts:
|
|
self.assertIn(ext, supported_exts)
|
|
self.assertEqual(get_default_file_extension(mime_type), ext)
|
|
self.assertIsInstance(
|
|
get_parser_registry().get_parser_for_file(mime_type, "")(),
|
|
RasterisedDocumentParser,
|
|
)
|
|
|
|
def test_text_parser(self) -> None:
|
|
"""
|
|
GIVEN:
|
|
- Various mime types of a text form
|
|
WHEN:
|
|
- The parser class is instantiated
|
|
THEN:
|
|
- The text based parser is return
|
|
"""
|
|
supported_mimes_and_exts = [
|
|
("text/plain", ".txt"),
|
|
("text/csv", ".csv"),
|
|
]
|
|
|
|
supported_exts = get_supported_file_extensions()
|
|
|
|
for mime_type, ext in supported_mimes_and_exts:
|
|
self.assertIn(ext, supported_exts)
|
|
self.assertEqual(get_default_file_extension(mime_type), ext)
|
|
self.assertIsInstance(
|
|
get_parser_registry().get_parser_for_file(mime_type, "")(),
|
|
TextDocumentParser,
|
|
)
|
|
|
|
def test_tika_parser(self) -> None:
|
|
"""
|
|
GIVEN:
|
|
- Various mime types of a office document form
|
|
WHEN:
|
|
- The parser class is instantiated
|
|
THEN:
|
|
- The Tika/Gotenberg based parser is return
|
|
"""
|
|
supported_mimes_and_exts = [
|
|
("application/vnd.oasis.opendocument.text", ".odt"),
|
|
("text/rtf", ".rtf"),
|
|
("application/msword", ".doc"),
|
|
(
|
|
"application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
|
".docx",
|
|
),
|
|
]
|
|
|
|
self.addCleanup(reset_parser_registry)
|
|
|
|
# Reset and rebuild the registry with Tika enabled.
|
|
with override_settings(TIKA_ENABLED=True):
|
|
reset_parser_registry()
|
|
supported_exts = get_supported_file_extensions()
|
|
|
|
for mime_type, ext in supported_mimes_and_exts:
|
|
self.assertIn(ext, supported_exts)
|
|
self.assertEqual(get_default_file_extension(mime_type), ext)
|
|
self.assertIsInstance(
|
|
get_parser_registry().get_parser_for_file(mime_type, "")(),
|
|
TikaDocumentParser,
|
|
)
|
|
|
|
def test_no_parser_for_mime(self) -> None:
|
|
self.assertIsNone(get_parser_registry().get_parser_for_file("text/sdgsdf", ""))
|
|
|
|
def test_default_extension(self) -> None:
|
|
# Test no parser declared still returns a an extension
|
|
self.assertEqual(get_default_file_extension("application/zip"), ".zip")
|
|
|
|
# Test invalid mimetype returns no extension
|
|
self.assertEqual(get_default_file_extension("aasdasd/dgfgf"), "")
|
|
|
|
def test_file_extension_support(self) -> None:
|
|
self.assertTrue(is_file_ext_supported(".pdf"))
|
|
self.assertFalse(is_file_ext_supported(".hsdfh"))
|
|
self.assertFalse(is_file_ext_supported(""))
|