matthias/mayan-edms
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Detech empty PDF parsing by detecting unicode /u000c and not ASCII /x0c

Browse Source
This commit is contained in:
Roberto Rosario
2015-01-24 04:27:57 -04:00
parent c23d71424f
commit 9a01a23e4c
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
mayan/apps/ocr/parsers/__init__.py
View File

@@ -88,7 +88,7 @@ class SlateParser(Parser):
pdf_pages = slate.PDF(descriptor)
descriptor.close()
if pdf_pages[document_page.page_number - 1] == '\x0c':
if unicode(pdf_pages[document_page.page_number - 1]) == '\u000c':
raise ParserError
document_page.content = pdf_pages[document_page.page_number - 1]
@@ -164,7 +164,7 @@ class PopplerParser(Parser):
raise ParserError
output = proc.stdout.read()
if output == '\x0c':
if unicode(output) == '\u000c':
logger.debug('Parser didn\'t any output')
raise ParserError('No output')