Merge remote-tracking branch 'origin/master'

Conflicts:
	MANIFEST.in
	README.md
	pdfminer/latin_enc.py
	pdfminer/pdfdocument.py
	pdfminer/pdfinterp.py
	pdfminer/pdfpage.py
	pdfminer/pdftypes.py
	pdfminer/psparser.py
	pdfminer/utils.py
	samples/Makefile
	setup.py

MANIFEST.in

@@ -1,7 +1,9 @@
 include Makefile
 include LICENSE
+include *.txt
 include *.md
 include *.py
+graft cmaprsrc
 graft docs
 graft pdfminer
 graft samples

Makefile

@@ -1,4 +1,4 @@
-##  Makefile (for maintainance purpose)
+##  Makefile (for maintenance purpose)
 ##
 
 PACKAGE=pdfminer

cmaprsrc/README.txt

@@ -5,7 +5,7 @@ to decode text data written in CJK (Chinese, Japanese, Korean) language.
 CMap resources are now available freely from Adobe web site:
 http://opensource.adobe.com/wiki/display/cmap/CMap+Resources
 
-The follwing files were extracted from the downloadable tarballs:
+The following files were extracted from the downloadable tarballs:
 
 cid2code_Adobe_CNS1.txt:
 	http://download.macromedia.com/pub/opensource/cmap/cmapresources_cns1-6.tar.z

pdfminer/converter.py

@@ -214,7 +214,7 @@ class TextConverter(PDFConverter):
         return
 
     # Some dummy functions to save memory/CPU when all that is wanted
-    # is text.  This stops all the image and drawing ouput from being
+    # is text.  This stops all the image and drawing output from being
     # recorded and taking up RAM.
     def render_image(self, name, stream):
         if self.imagewriter is None:
@@ -349,7 +349,7 @@ class HTMLConverter(PDFConverter):
             if self._font is not None:
                 self.write('</span>')
             self.write('<span style="font-family: %s; font-size:%dpx">' %
-                       (fontname, fontsize * self.scale * self.fontscale))
+                       (enc(fontname), fontsize * self.scale * self.fontscale))
             self._font = font
         self.write_text(text)
         return

pdfminer/layout.py

@@ -682,13 +682,20 @@ class LTLayoutContainer(LTContainer):
         for obj in empties:
             obj.analyze(laparams)
         textboxes = list(self.group_textlines(laparams, textlines))
-        if textboxes:
+        if -1 <= laparams.boxes_flow and laparams.boxes_flow <= +1 and textboxes:
             self.groups = self.group_textboxes(laparams, textboxes)
             assigner = IndexAssigner()
             for group in self.groups:
                 group.analyze(laparams)
                 assigner.run(group)
             textboxes.sort(key=lambda box: box.index)
+        else:
+            def getkey(box):
+                if isinstance(box, LTTextBoxVertical):
+                    return (0, -box.x1, box.y0)
+                else:
+                    return (1, box.y0, box.x0)
+            textboxes.sort(key=getkey)
         self._objs = textboxes + otherobjs + empties
         return
 

tools/pdf2html.cgi

@@ -197,7 +197,7 @@ class WebApp(object):
                 convert(item.file, self.outfp, tmppath, pagenos=pagenos, codec=self.codec,
                         maxpages=self.MAXPAGES, maxfilesize=self.MAXFILESIZE, html=html)
             except Exception, e:
-                self.put('<p>Sorry, an error has occured: %s' % q(repr(e)))
+                self.put('<p>Sorry, an error has occurred: %s' % q(repr(e)))
                 self.logger.error('convert: %r: path=%r: %s' % (e, traceback.format_exc()))
         finally:
             try: