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

a couple fixes and more supported image files

Browse Source
This commit is contained in:
jonaswinkler
2020-12-02 17:39:49 +01:00
parent 5e1543bad5
commit e3ce573fbb
8 changed files with 41 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
src/paperless_tesseract/tests/test_parser.py
View File

@@ -247,3 +247,33 @@ class TestParser(DirectoriesMixin, TestCase):
parser.parse(os.path.join(self.SAMPLE_FILES, "multi-page-images.pdf"), "application/pdf")
self.assertTrue(os.path.join(parser.archive_path))
self.assertContainsStrings(parser.get_text().lower(), ["page 1", "page 2", "page 3"])
class TestParserFileTypes(DirectoriesMixin, TestCase):
SAMPLE_FILES = os.path.join(os.path.dirname(__file__), "samples")
def test_bmp(self):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "simple.bmp"), "image/bmp")
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertTrue("this is a test document" in parser.get_text().lower())
def test_jpg(self):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "simple.jpg"), "image/jpeg")
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertTrue("this is a test document" in parser.get_text().lower())
@override_settings(OCR_IMAGE_DPI=200)
def test_gif(self):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "simple.gif"), "image/gif")
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertTrue("this is a test document" in parser.get_text().lower())
def test_tiff(self):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "simple.tif"), "image/tiff")
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertTrue("this is a test document" in parser.get_text().lower())