yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-07-19 23:11:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Adjust PDF conversion subprocess for Python v3.6 (#194)

Browse Source
This commit is contained in:
Tanay Soni 2020-07-06 16:56:10 +02:00 committed by GitHub
parent 7ada5a91cd
commit 0eb8a29da9
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
haystack/indexing/file_converters/pdf.py
View File

@ -128,7 +128,7 @@ class PDFToTextConverter(BaseConverter):
command = ["pdftotext", "-layout", str(file_path), "-"] command = ["pdftotext", "-layout", str(file_path), "-"]
else: else:
command = ["pdftotext", str(file_path), "-"] command = ["pdftotext", str(file_path), "-"]
output = subprocess.run(command, capture_output=True, shell=False) output = subprocess.run(command, stdout=subprocess.PIPE, shell=False)
document = output.stdout.decode(errors="ignore") document = output.stdout.decode(errors="ignore")
pages = document.split("\f") pages = document.split("\f")
pages = pages[:-1] # the last page in the split is always empty. pages = pages[:-1] # the last page in the split is always empty.