Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix: Initialize docling PDF parser on module level #80

Closed
wants to merge 5 commits into from
Closed

fix: Initialize docling PDF parser on module level #80

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
1b1af3d
Initialize docling PDF parser on module level
cau-git Sep 16, 2024
cf8cb7d
updated the output of error messages
PeterStaar-IBM Sep 18, 2024
7684ba9
Merge branch 'main' of github.com:DS4SD/docling into cau/docling-pars…
cau-git Sep 18, 2024
1b4c80a
Merge branch 'cau/docling-parse-init' of github.com:DS4SD/docling int…
cau-git Sep 18, 2024
d3eb6c5
Fix tests to have unique document_hashes per test
cau-git Sep 18, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion docling/backend/docling_parse_backend.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,8 @@

_log = logging.getLogger(__name__)

pdf_parser = pdf_parser()


class DoclingParsePageBackend(PdfPageBackend):
def __init__(
Expand Down Expand Up @@ -190,7 +192,7 @@ def __init__(self, path_or_stream: Union[BytesIO, Path], document_hash: str):
super().__init__(path_or_stream, document_hash)

self._pdoc = pdfium.PdfDocument(path_or_stream)
self.parser = pdf_parser()
self.parser = pdf_parser

success = False
if isinstance(path_or_stream, BytesIO):
Expand Down
11 changes: 7 additions & 4 deletions tests/test_backend_docling_parse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ def test_doc_path():
def test_text_cell_counts():
pdf_doc = Path("./tests/data/redp5695.pdf")

doc_backend = DoclingParseDocumentBackend(pdf_doc, "123456xyz")
doc_backend = DoclingParseDocumentBackend(pdf_doc, "123456xyz5")

for page_index in range(0, doc_backend.page_count()):
last_cell_count = None
Expand All @@ -36,7 +36,7 @@ def test_text_cell_counts():


def test_get_text_from_rect(test_doc_path):
doc_backend = DoclingParseDocumentBackend(test_doc_path, "123456xyz")
doc_backend = DoclingParseDocumentBackend(test_doc_path, "123456xyz4")
page_backend: DoclingParsePageBackend = doc_backend.load_page(0)

# Get the title text of the DocLayNet paper
Expand All @@ -46,19 +46,22 @@ def test_get_text_from_rect(test_doc_path):
ref = "DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis"

assert textpiece.strip() == ref
doc_backend.unload()


def test_crop_page_image(test_doc_path):
doc_backend = DoclingParseDocumentBackend(test_doc_path, "123456xyz")
doc_backend = DoclingParseDocumentBackend(test_doc_path, "123456xyz3")
page_backend: DoclingParsePageBackend = doc_backend.load_page(0)

# Crop out "Figure 1" from the DocLayNet paper
im = page_backend.get_page_image(
scale=2, cropbox=BoundingBox(l=317, t=246, r=574, b=527)
)
# im.show()
doc_backend.unload()


def test_num_pages(test_doc_path):
doc_backend = DoclingParseDocumentBackend(test_doc_path, "123456xyz")
doc_backend = DoclingParseDocumentBackend(test_doc_path, "123456xyz2")
doc_backend.page_count() == 9
doc_backend.unload()
Loading