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

Removed PDFDocument.read_xref().

pull/1/head
Yusuke Shinyama 2013-10-10 18:57:08 +09:00
parent 658be970b8
commit cfd60eafbf
1 changed files with 7 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
pdfminer/pdfdocument.py
View File

@ -312,11 +312,15 @@ class PDFDocument(object):
# Retrieve the information of each header that was appended # Retrieve the information of each header that was appended
# (maybe multiple times) at the end of the document. # (maybe multiple times) at the end of the document.
try: try:
self.xrefs = self.read_xref(parser) pos = self.find_xref(parser)
self.read_xref_from(parser, pos, self.xrefs)
except PDFNoValidXRef: except PDFNoValidXRef:
fallback = True fallback = True
if fallback: if fallback:
self.xrefs.extend(self.read_xref(parser, fallback=True)) parser.fallback = True
xref = PDFXRefFallback()
xref.load(parser)
self.xrefs.append(xref)
for xref in self.xrefs: for xref in self.xrefs:
trailer = xref.get_trailer() trailer = xref.get_trailer()
if not trailer: continue if not trailer: continue
@ -639,17 +643,3 @@ class PDFDocument(object):
pos = int_value(trailer['Prev']) pos = int_value(trailer['Prev'])
self.read_xref_from(parser, pos, xrefs) self.read_xref_from(parser, pos, xrefs)
return return
# read xref tables and trailers
def read_xref(self, parser, fallback=False):
"""Reads all the XRefs in the PDF file and returns them."""
xrefs = []
parser.fallback = fallback
if parser.fallback:
xref = PDFXRefFallback()
xref.load(parser)
xrefs.append(xref)
else:
pos = self.find_xref(parser)
self.read_xref_from(parser, pos, xrefs)
return xrefs