bugfixes
git-svn-id: https://pdfminerr.googlecode.com/svn/trunk/pdfminer@44 1aa58f4a-7d42-0410-adbc-911cccaed67cpull/1/head
parent
2647867239
commit
bb07f28199
|
@ -11,7 +11,7 @@ blockquote { background: #eeeeee; }
|
||||||
<h1>PDFMiner</h1>
|
<h1>PDFMiner</h1>
|
||||||
<div align=right class=lastmod>
|
<div align=right class=lastmod>
|
||||||
<!-- hhmts start -->
|
<!-- hhmts start -->
|
||||||
Last Modified: Thu Jul 10 00:16:52 JST 2008
|
Last Modified: Thu Jul 10 00:18:46 JST 2008
|
||||||
<!-- hhmts end -->
|
<!-- hhmts end -->
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
|
@ -228,7 +228,8 @@ no stream header is displayed for the ease of saving it to a file.
|
||||||
<hr noshade>
|
<hr noshade>
|
||||||
<h2>Changes</h2>
|
<h2>Changes</h2>
|
||||||
<ul>
|
<ul>
|
||||||
<li> 2008/06/29: Added HTML output. Reorganized the directory structure.
|
<li> 2008/07/10: Outline (TOC) extraction support.
|
||||||
|
<li> 2008/06/29: HTML output added. Reorganized the directory structure.
|
||||||
<li> 2008/04/29: Bugfix for Win32. Thanks to Chris Clark.
|
<li> 2008/04/29: Bugfix for Win32. Thanks to Chris Clark.
|
||||||
<li> 2008/04/27: Basic encryption and LZW decoding support added.
|
<li> 2008/04/27: Basic encryption and LZW decoding support added.
|
||||||
<li> 2008/01/07: Several bugfixes. Thanks to Nick Fabry for his contribution.
|
<li> 2008/01/07: Several bugfixes. Thanks to Nick Fabry for his contribution.
|
||||||
|
|
4
TODO
4
TODO
|
@ -1,8 +1,8 @@
|
||||||
TODOs:
|
TODOs:
|
||||||
- Documentation.
|
- Documentation.
|
||||||
- Error handling for invalid type.
|
- Error handling for invalid type.
|
||||||
|
- Tagged PDF.
|
||||||
|
- Infer text stream by clustering.
|
||||||
|
|
||||||
- Outlines.
|
|
||||||
- Named Objects. (pages)
|
|
||||||
- Support writing/creating PDFs.
|
- Support writing/creating PDFs.
|
||||||
- Any special treatments for linearized PDFs?
|
- Any special treatments for linearized PDFs?
|
||||||
|
|
|
@ -726,6 +726,7 @@ class PDFParser(PSStackParser):
|
||||||
break
|
break
|
||||||
objlen += len(line)
|
objlen += len(line)
|
||||||
data += line
|
data += line
|
||||||
|
self.seek(pos+objlen)
|
||||||
if 1 <= self.debug:
|
if 1 <= self.debug:
|
||||||
print >>stderr, 'Stream: pos=%d, objlen=%d, dic=%r, data=%r...' % \
|
print >>stderr, 'Stream: pos=%d, objlen=%d, dic=%r, data=%r...' % \
|
||||||
(pos, objlen, dic, data[:10])
|
(pos, objlen, dic, data[:10])
|
||||||
|
|
|
@ -139,7 +139,7 @@ class PSBaseParser(object):
|
||||||
return
|
return
|
||||||
|
|
||||||
def tell(self):
|
def tell(self):
|
||||||
return self.fp.tell()
|
return self.bufpos+self.charpos
|
||||||
|
|
||||||
def poll(self, pos=None, n=80):
|
def poll(self, pos=None, n=80):
|
||||||
pos0 = self.fp.tell()
|
pos0 = self.fp.tell()
|
||||||
|
|
Loading…
Reference in New Issue