paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-28 18:24:38 -05:00
Code Issues Packages Projects Releases Wiki Activity

Chore: switch from os.path to pathlib.Path (#9060)

Browse Source
This commit is contained in:
Sebastian Steinbeißer
2025-03-05 22:06:01 +01:00
committed by GitHub
parent aaaa6c1393
commit 76d363f22d
17 changed files with 89 additions and 150 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
src/paperless_tesseract/parsers.py
View File

@@ -159,7 +159,7 @@ class RasterisedDocumentParser(DocumentParser):
# the whole text, so do not utilize it in that case
if (
sidecar_file is not None
and os.path.isfile(sidecar_file)
and sidecar_file.is_file()
and self.settings.mode != "redo"
):
text = self.read_file_handle_unicode_errors(sidecar_file)
@@ -174,7 +174,7 @@ class RasterisedDocumentParser(DocumentParser):
# no success with the sidecar file, try PDF
if not os.path.isfile(pdf_file):
if not Path(pdf_file).is_file():
return None
try:
@@ -368,8 +368,8 @@ class RasterisedDocumentParser(DocumentParser):
from ocrmypdf import SubprocessOutputError
from ocrmypdf.exceptions import DigitalSignatureError
archive_path = Path(os.path.join(self.tempdir, "archive.pdf"))
sidecar_file = Path(os.path.join(self.tempdir, "sidecar.txt"))
archive_path = Path(self.tempdir) / "archive.pdf"
sidecar_file = Path(self.tempdir) / "sidecar.txt"
args = self.construct_ocrmypdf_parameters(
document_path,
@@ -412,12 +412,8 @@ class RasterisedDocumentParser(DocumentParser):
f"Attempting force OCR to get the text.",
)
archive_path_fallback = Path(
os.path.join(self.tempdir, "archive-fallback.pdf"),
)
sidecar_file_fallback = Path(
os.path.join(self.tempdir, "sidecar-fallback.txt"),
)
archive_path_fallback = Path(self.tempdir) / "archive-fallback.pdf"
sidecar_file_fallback = Path(self.tempdir) / "sidecar-fallback.txt"
# Attempt to run OCR with safe settings.