Marmelator/image-classification-service
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 29 Wiki Activity

error handling for bad xrefs

Browse Source
This commit is contained in:
Matthias Bisping 2022-04-25 16:17:19 +02:00
parent e7d229c0d7
commit 956706378b
1 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
image_prediction/image_extractor/extractors/parsable.py
View File

@ -13,8 +13,11 @@ from image_prediction.image_extractor.extractor import ImageExtractor, ImageMeta
from image_prediction.info import Info
from image_prediction.stitching.stitching import stitch_pairs
from image_prediction.stitching.utils import validate_box_coords, validate_box_size
from image_prediction.utils import get_logger
from image_prediction.utils.generic import lift
logger = get_logger()
class ParsablePDFImageExtractor(ImageExtractor):
def __init__(self, verbose=False, tolerance=0):
@ -162,7 +165,11 @@ def has_alpha_channel(doc, xref):
if maybe_smask:
return any([doc.extract_image(maybe_smask) is not None, bool(fitz.Pixmap(doc, maybe_smask).alpha)])
else:
return bool(fitz.Pixmap(doc, xref).alpha)
try:
return bool(fitz.Pixmap(doc, xref).alpha)
except ValueError:
logger.debug(f"Encountered invalid xref `{xref}` in {doc.metadata.get('title', '<no title>')}.")
return False
def tiny(metadata):