amorfo77/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2026-03-28 03:42:45 +00:00
Code Issues Projects Releases Wiki Activity

Fix: update remaining imports and move live Tika tests after parser migration

Browse Source 
- src/documents/tests/test_parsers.py: import TikaDocumentParser from
  paperless.parsers.tika (old paperless_tika.parsers no longer exists)
- git mv paperless_tika/tests/test_live_tika.py →
  paperless/tests/parsers/test_live_tika.py to co-locate all Tika tests
  with the parser; update import and replace old attribute API
  (tika_parser.text/.archive_path) with accessor methods
  (get_text/get_archive_path)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Trenton H
2026-03-12 15:38:25 -07:00
parent 2b33617262
commit d0b95f2cda
2 changed files with 21 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/documents/tests/test_parsers.py
View File

@@ -10,8 +10,8 @@ from documents.parsers import get_parser_class_for_mime_type
from documents.parsers import get_supported_file_extensions
from documents.parsers import is_file_ext_supported
from paperless.parsers.text import TextDocumentParser
from paperless.parsers.tika import TikaDocumentParser
from paperless_tesseract.parsers import RasterisedDocumentParser
from paperless_tika.parsers import TikaDocumentParser
class TestParserDiscovery(TestCase):

38
src/paperless_tika/tests/test_live_tika.py → src/paperless/tests/parsers/test_live_tika.py
View File

@@ -4,7 +4,7 @@ from pathlib import Path
import pytest
from documents.tests.utils import util_call_with_backoff
from paperless_tika.parsers import TikaDocumentParser
from paperless.parsers.tika import TikaDocumentParser
@pytest.mark.skipif(
@@ -42,14 +42,15 @@ class TestTikaParserAgainstServer:
)
assert (
tika_parser.text
tika_parser.get_text()
== "This is an ODT test document, created September 14, 2022"
)
assert tika_parser.archive_path is not None
assert b"PDF-" in tika_parser.archive_path.read_bytes()[:10]
archive = tika_parser.get_archive_path()
assert archive is not None
assert b"PDF-" in archive.read_bytes()[:10]
# TODO: Unsure what can set the Creation-Date field in a document, enable when possible
# self.assertEqual(tika_parser.date, datetime.datetime(2022, 9, 14))
# self.assertEqual(tika_parser.get_date(), datetime.datetime(2022, 9, 14))
def test_basic_parse_docx(
self,
@@ -74,14 +75,15 @@ class TestTikaParserAgainstServer:
)
assert (
tika_parser.text
tika_parser.get_text()
== "This is an DOCX test document, also made September 14, 2022"
)
assert tika_parser.archive_path is not None
with Path(tika_parser.archive_path).open("rb") as f:
archive = tika_parser.get_archive_path()
assert archive is not None
with archive.open("rb") as f:
assert b"PDF-" in f.read()[:10]
# self.assertEqual(tika_parser.date, datetime.datetime(2022, 9, 14))
# self.assertEqual(tika_parser.get_date(), datetime.datetime(2022, 9, 14))
def test_basic_parse_doc(
self,
@@ -102,13 +104,12 @@ class TestTikaParserAgainstServer:
[sample_doc_file, "application/msword"],
)
assert tika_parser.text is not None
assert (
"This is a test document, saved in the older .doc format"
in tika_parser.text
)
assert tika_parser.archive_path is not None
with Path(tika_parser.archive_path).open("rb") as f:
text = tika_parser.get_text()
assert text is not None
assert "This is a test document, saved in the older .doc format" in text
archive = tika_parser.get_archive_path()
assert archive is not None
with archive.open("rb") as f:
assert b"PDF-" in f.read()[:10]
def test_tika_fails_multi_part(
@@ -133,6 +134,7 @@ class TestTikaParserAgainstServer:
[sample_broken_odt, "application/vnd.oasis.opendocument.text"],
)
assert tika_parser.archive_path is not None
with Path(tika_parser.archive_path).open("rb") as f:
archive = tika_parser.get_archive_path()
assert archive is not None
with archive.open("rb") as f:
assert b"PDF-" in f.read()[:10]