mirror/OCRmyPDF
1
0
Fork 0
mirror of https://github.com/ocrmypdf/OCRmyPDF.git synced 2026-05-04 12:48:02 -04:00
Code Issues Packages Projects Releases Wiki Activity

graft: use faster unparse_content_stream if available

Browse Source
This commit is contained in:
James R. Barlow
2021-08-31 02:16:25 -07:00
parent b91096c615
commit 4e4f0bfa1f
1 changed files with 16 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
src/ocrmypdf/_graft.py
View File

@@ -73,17 +73,24 @@ def strip_invisible_text(pdf, page):
except AttributeError:
return str(op).encode('ascii')
lines = []
if hasattr(pikepdf, 'unparse_content_stream'):
content_stream = pikepdf.unparse_content_stream(stream)
else:
lines = []
for operands, operator in stream:
if operator == pikepdf.Operator('INLINE IMAGE'):
iim = operands[0]
line = iim.unparse()
else:
line = b' '.join(convert(op) for op in operands) + b' ' + operator.unparse()
lines.append(line)
for operands, operator in stream:
if operator == pikepdf.Operator('INLINE IMAGE'):
iim = operands[0]
line = iim.unparse()
else:
line = (
b' '.join(convert(op) for op in operands)
+ b' '
+ operator.unparse()
)
lines.append(line)
content_stream = b'\n'.join(lines)
content_stream = b'\n'.join(lines)
page.Contents = pikepdf.Stream(pdf, content_stream)