Skip to content

Commit 4f9e6e4

Browse files
author
Gerit Wagner
committed
pdf-prep: needs_prep upon pymupdf.FileDataError
1 parent 93a7eee commit 4f9e6e4

1 file changed

Lines changed: 7 additions & 2 deletions

File tree

colrev/ops/pdf_prep.py

Lines changed: 7 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -21,7 +21,7 @@
2121
from colrev.constants import OperationsType
2222
from colrev.constants import RecordState
2323
from colrev.package_manager.package_manager import PackageManager
24-
24+
import pymupdf
2525

2626
class PDFPrep(colrev.process.operation.Operation):
2727
"""Prepare PDFs"""
@@ -139,7 +139,12 @@ def prepare_pdf(self, item: dict) -> dict:
139139
record_dict, path=self.review_manager.path
140140
)
141141
if record_dict[Fields.FILE].endswith(".pdf"):
142-
record.set_text_from_pdf(first_pages=True)
142+
try:
143+
record.set_text_from_pdf(first_pages=True)
144+
except pymupdf.FileDataError:
145+
record_dict[Fields.STATUS] = RecordState.pdf_needs_manual_preparation
146+
return record_dict
147+
143148
original_filename = record_dict[Fields.FILE]
144149

145150
self.review_manager.logger.debug(f"Start PDF prep of {record_dict[Fields.ID]}")

0 commit comments

Comments
 (0)