74df76c8-4768-48d5-bb7f-5ee50aa05217

Committed 06 Nov 2023 01:38PM UTC coverage: 67.523% (-0.3%) from 67.801%

Build # 74df76c8-4768-48d5-bb7f-5ee50aa05217

Build Type

Pull #2177

circleci

Committed by

VirginiaDooley

Commit Message

Create TextractResults model

Pull Request Pull Request #2177: Spike: AWS Textract

Run Details

1640 of 2760 branches covered (0.0%)

Branch coverage included in aggregate %.

12 of 62 new or added lines in 3 files covered. (19.35%)

110 existing lines in 10 files now uncovered.

6662 of 9535 relevant lines covered (69.87%)

0.7 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

50.0

/ynr/apps/sopn_parsing/helpers/extract_pages.py

from pdfminer.pdftypes import PDFException
from sopn_parsing.helpers.pdf_helpers import SOPNDocument
from sopn_parsing.helpers.text_helpers import NoTextInDocumentError


def extract_pages_for_ballot(ballot):
    """
    Try to extract the page numbers for the latest SOPN document related to this
    ballot.

    Because documents can apply to more than one ballot, we also perform
    "drive by" parsing of other ballots contained in a given document.

    :type ballot: candidates.models.Ballot

    """
    try:
        sopn = SOPNDocument(
            file=ballot.sopn.uploaded_file,
            source_url=ballot.sopn.source_url,
            election_date=ballot.election.election_date,
        )
        return sopn.match_all_pages()
    except NoTextInDocumentError:
        raise NoTextInDocumentError(
            f"Failed to extract pages for {ballot.sopn.uploaded_file.path} as a NoTextInDocumentError was raised"
        )
    except PDFException:
        print(
            f"{ballot.ballot_paper_id} failed to parse as a PDFSyntaxError was raised"
        )
        raise PDFException(
            f"Failed to extract pages for {ballot.sopn.uploaded_file.path} as a PDFSyntaxError was raised"
        )

1	from pdfminer.pdftypes import PDFException	1✔
2	from sopn_parsing.helpers.pdf_helpers import SOPNDocument	1✔
3	from sopn_parsing.helpers.text_helpers import NoTextInDocumentError	1✔
4
5
6	def extract_pages_for_ballot(ballot):	1✔
7	"""
8	Try to extract the page numbers for the latest SOPN document related to this
9	ballot.
10
11	Because documents can apply to more than one ballot, we also perform
12	"drive by" parsing of other ballots contained in a given document.
13
14	:type ballot: candidates.models.Ballot
15
16	"""
17	try:	1✔
18	sopn = SOPNDocument(	1✔
19	file=ballot.sopn.uploaded_file,
20	source_url=ballot.sopn.source_url,
21	election_date=ballot.election.election_date,
22	)
23	return sopn.match_all_pages()	1✔
UNCOV 24	except NoTextInDocumentError:	×
UNCOV 25	raise NoTextInDocumentError(	×
26	f"Failed to extract pages for {ballot.sopn.uploaded_file.path} as a NoTextInDocumentError was raised"
27	)
UNCOV 28	except PDFException:	×
UNCOV 29	print(	×
30	f"{ballot.ballot_paper_id} failed to parse as a PDFSyntaxError was raised"
31	)
UNCOV 32	raise PDFException(	×
33	f"Failed to extract pages for {ballot.sopn.uploaded_file.path} as a PDFSyntaxError was raised"
34	)

DemocracyClub / yournextrepresentative / 74df76c8-4768-48d5-bb7f-5ee50aa05217

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous