decentral1se/pandora
1
0
Fork 0
forked from 0x2620/pandora
Code Issues Pull requests Projects Releases Wiki Activity

close filedescriptor after use

Browse source
This commit is contained in:
j 2022-01-03 12:33:15 +01:00
parent e4133ffa1d
commit 79c5d948b5
1 changed files with 2 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
pandora/document/fulltext.py
View file

@ -19,10 +19,11 @@ def extract_text(pdf, page=None):
# split page from pdf and ocr # split page from pdf and ocr
fd, page_pdf = tempfile.mkstemp('.pdf') fd, page_pdf = tempfile.mkstemp('.pdf')
cmd = ['pdfseparate', '-f', page, '-l', page, pdf, page_pdf] cmd = ['pdfseparate', '-f', page, '-l', page, pdf, page_pdf]
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=True)
stdout, stderr = p.communicate() stdout, stderr = p.communicate()
text = ocr_image(page_pdf) text = ocr_image(page_pdf)
os.unlink(page_pdf) os.unlink(page_pdf)
os.close(fd)
return text return text
else: else:
return ocr_image(pdf) return ocr_image(pdf)