paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-10-30 03:56:23 -05:00
Code Issues Packages Projects Releases Wiki Activity

When PDF/A rendering fails, add a warning the user may want to allow it to continue

Browse Source
This commit is contained in:
Trenton H
2023-08-28 17:43:59 -07:00
parent 938f388a0b
commit 7e768bfe23
1 changed files with 8 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/paperless_tesseract/parsers.py
View File

@@ -304,6 +304,7 @@ class RasterisedDocumentParser(DocumentParser):
import ocrmypdf import ocrmypdf
from ocrmypdf import EncryptedPdfError from ocrmypdf import EncryptedPdfError
from ocrmypdf import InputFileError from ocrmypdf import InputFileError
from ocrmypdf import SubprocessOutputError
archive_path = Path(os.path.join(self.tempdir, "archive.pdf")) archive_path = Path(os.path.join(self.tempdir, "archive.pdf"))
sidecar_file = Path(os.path.join(self.tempdir, "sidecar.txt")) sidecar_file = Path(os.path.join(self.tempdir, "sidecar.txt"))
@@ -333,6 +334,13 @@ class RasterisedDocumentParser(DocumentParser):
) )
if original_has_text: if original_has_text:
self.text = text_original self.text = text_original
except SubprocessOutputError as e:
if "Ghostscript PDF/A rendering" in str(e):
self.log.warning(
"Ghostscript PDF/A rendering failed, consider setting "
"PAPERLESS_OCR_USER_ARGS: '{\"continue_on_soft_render_error\": true}'", # noqa: E501
)
raise e
except (NoTextFoundException, InputFileError) as e: except (NoTextFoundException, InputFileError) as e:
self.log.warning( self.log.warning(
f"Encountered an error while running OCR: {e!s}. " f"Encountered an error while running OCR: {e!s}. "