zacc806
/
pdfminer.six
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #133 from timb07/speedup 

Speed up handling of PDFs with large images
pull/173/head
Tata Ganesh 2018-07-15 11:27:35 +05:30 committed by GitHub
parent d437e5c637 083f11b165
commit 259b29299e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
pdfminer/pdfparser.py
View File

@ -102,7 +102,7 @@ class PDFParser(PSStackParser):
return return
pos += len(line) pos += len(line)
self.fp.seek(pos) self.fp.seek(pos)
data = self.fp.read(objlen) data = bytearray(self.fp.read(objlen))
self.seek(pos+objlen) self.seek(pos+objlen)
while 1: while 1:
try: try:
@ -120,6 +120,7 @@ class PDFParser(PSStackParser):
objlen += len(line) objlen += len(line)
if self.fallback: if self.fallback:
data += line data += line
data = bytes(data)
self.seek(pos+objlen) self.seek(pos+objlen)
# XXX limit objlen not to exceed object boundary # XXX limit objlen not to exceed object boundary
log.debug('Stream: pos=%d, objlen=%d, dic=%r, data=%r...', pos, objlen, dic, data[:10]) log.debug('Stream: pos=%d, objlen=%d, dic=%r, data=%r...', pos, objlen, dic, data[:10])