yujunjun/olmocr
1
0
Fork 0
mirror of https://github.com/allenai/olmocr.git synced 2025-11-02 02:54:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

More tests

Browse Source
This commit is contained in:
Jake Poznanski 2024-11-20 19:37:00 +00:00
parent 3153aea260
commit c9e1a4c540
2 changed files with 11 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
tests/gnarly_pdfs/load_v_error.pdf Normal file
View File

Binary file not shown.

11
tests/test_anchor.py
View File

@ -143,6 +143,17 @@ class AnchorTest(unittest.TestCase):
self.assertEqual(anchor_text.strip(), "Page dimensions: 612.0x792.0")
def testCannotLoad(self):
local_pdf_path = os.path.join(os.path.dirname(__file__), "gnarly_pdfs", "load_v_error.pdf")
reader = PdfReader(local_pdf_path)
page = 5
anchor_text = get_anchor_text(local_pdf_path, page, pdf_engine="pdfreport", target_length=6000)
print(anchor_text)
print(len(anchor_text))
self.assertLess(len(anchor_text), 6000)
# TODO This one still fails
def testExcessiveMapAnchor(self):
local_pdf_path = os.path.join(os.path.dirname(__file__), "gnarly_pdfs", "map1.pdf")