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

Fixed dumppdf.py issues.

pull/1/head
Yusuke Shinyama 2014-03-24 20:55:00 +09:00
parent 607be269ab
commit f9079e4c0a
2 changed files with 4 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
pdfminer/pdfdocument.py
View File

@ -219,7 +219,7 @@ class PDFXRefStream(PDFBaseXRef):
if not isinstance(stream, PDFStream) or stream['Type'] is not LITERAL_XREF: if not isinstance(stream, PDFStream) or stream['Type'] is not LITERAL_XREF:
raise PDFNoValidXRef('Invalid PDF stream spec.') raise PDFNoValidXRef('Invalid PDF stream spec.')
size = stream['Size'] size = stream['Size']
index_array = stream.get('Index', (0, size)) index_array = stream.get('Index', (1, size))
if len(index_array) % 2 != 0: if len(index_array) % 2 != 0:
raise PDFSyntaxError('Invalid index number') raise PDFSyntaxError('Invalid index number')
self.ranges.extend(choplist(2, index_array)) self.ranges.extend(choplist(2, index_array))

10
tools/dumppdf.py
View File

@ -114,8 +114,7 @@ def dumpoutline(outfp, fname, objids, pagenos, password='',
dumpall=False, codec=None, extractdir=None): dumpall=False, codec=None, extractdir=None):
fp = file(fname, 'rb') fp = file(fname, 'rb')
parser = PDFParser(fp) parser = PDFParser(fp)
doc = PDFDocument(parser) doc = PDFDocument(parser, password)
doc.initialize(password)
pages = dict( (page.pageid, pageno) for (pageno,page) pages = dict( (page.pageid, pageno) for (pageno,page)
in enumerate(PDFPage.create_pages(doc)) ) in enumerate(PDFPage.create_pages(doc)) )
def resolve_dest(dest): def resolve_dest(dest):
@ -185,9 +184,7 @@ def extractembedded(outfp, fname, objids, pagenos, password='',
fp = file(fname, 'rb') fp = file(fname, 'rb')
parser = PDFParser(fp) parser = PDFParser(fp)
doc = PDFDocument(parser) doc = PDFDocument(parser, password)
doc.initialize(password)
for xref in doc.xrefs: for xref in doc.xrefs:
for objid in xref.get_objids(): for objid in xref.get_objids():
obj = doc.getobj(objid) obj = doc.getobj(objid)
@ -200,8 +197,7 @@ def dumppdf(outfp, fname, objids, pagenos, password='',
dumpall=False, codec=None, extractdir=None): dumpall=False, codec=None, extractdir=None):
fp = file(fname, 'rb') fp = file(fname, 'rb')
parser = PDFParser(fp) parser = PDFParser(fp)
doc = PDFDocument(parser) doc = PDFDocument(parser, password)
doc.initialize(password)
if objids: if objids:
for objid in objids: for objid in objids:
obj = doc.getobj(objid) obj = doc.getobj(objid)