win32 bug fixed

git-svn-id: https://pdfminerr.googlecode.com/svn/trunk/pdfminer@27 1aa58f4a-7d42-0410-adbc-911cccaed67c

Makefile

@@ -1,7 +1,7 @@
 # Makefile for pdfminer
 
 PACKAGE=pdfminer
-VERSION=20080427
+VERSION=20080429
 GNUTAR=tar
 SVN=svn
 PYTHON=python

README.html

@@ -11,7 +11,7 @@ blockquote { background: #eeeeee; }
 <h1>PDFMiner</h1>
 <div align=right class=lastmod>
 <!-- hhmts start -->
-Last Modified: Sun Apr 27 20:54:51 JST 2008
+Last Modified: Tue Apr 29 20:16:22 JST 2008
 <!-- hhmts end -->
 </div>
 
@@ -44,8 +44,8 @@ http://www.unixuser.org/~euske/python/pdfminer/index.html
 
 <p>
 <strong>Download (source):</strong><br>
-<a href="http://www.unixuser.org/~euske/python/pdfminer/pdfminer-dist-20080427.tar.gz">
-http://www.unixuser.org/~euske/python/pdfminer/pdfminer-dist-20080427.tar.gz
+<a href="http://www.unixuser.org/~euske/python/pdfminer/pdfminer-dist-20080429.tar.gz">
+http://www.unixuser.org/~euske/python/pdfminer/pdfminer-dist-20080429.tar.gz
 </a>
 (1.8Mbytes)
 
@@ -216,6 +216,7 @@ no stream header is displayed for the ease of saving it to a file.
 <hr noshade>
 <h2>Changes</h2>
 <ul>
+<li> 2007/04/29: Bugfix for Win32. Thanks to Chris Clark.
 <li> 2007/04/27: Basic encryption and LZW decoding support added.
 <li> 2007/01/07: Several bugfixes. Thanks to Nick Fabry for his contribution.
 <li> 2007/12/31: Initial release.

cmap.py

@@ -199,7 +199,7 @@ class CMapDB:
         if 1 <= klass.debug:
           print >>stderr, 'Reading: CMap %r...' % fname
         cmap = CMap()
-        fp = file(fname)
+        fp = file(fname, 'rb')
         CMapParser(cmap, fp, debug=klass.debug).run()
         fp.close()
       elif not strict:

dumppdf.py

@@ -99,7 +99,7 @@ def dumpallobjs(out, doc):
 def dumppdf(outfp, fname, objids, pageids, password='',
             dumpall=False, codec=None, debug=0):
   doc = PDFDocument(debug=debug)
-  fp = file(fname)
+  fp = file(fname, 'rb')
   parser = PDFParser(doc, fp, debug=debug)
   doc.initialize(password)
   if objids:
@@ -151,7 +151,7 @@ def main(argv):
     elif k == '-r': codec = 'raw'
     elif k == '-b': codec = 'binary'
     elif k == '-t': codec = 'text'
-    elif k == '-o': outfp = file(v, 'w')
+    elif k == '-o': outfp = file(v, 'wb')
   #
   for fname in args:
     dumppdf(outfp, fname, objids, pageids, password=password,

pdf2txt.py

@@ -171,7 +171,7 @@ class TextExtractionNotAllowed(RuntimeError): pass
 def pdf2txt(outfp, rsrc, fname, pages, codec, password='', debug=0):
   device = TextConverter(rsrc, debug=debug)
   doc = PDFDocument(debug=debug)
-  fp = file(fname)
+  fp = file(fname, 'rb')
   parser = PDFParser(doc, fp, debug=debug)
   try:
     doc.initialize(password)