py3: more unicode porting

src/calibre/ebooks/pdf/pageoptions.py

@@ -1,4 +1,6 @@
 # -*- coding: utf-8 -*-
+from __future__ import absolute_import, division, print_function, unicode_literals
+
 __license__ = 'GPL 3'
 __copyright__ = '2009, John Schember <john@nachtimwald.com>'
 __docformat__ = 'restructuredtext en'
@@ -72,5 +74,5 @@ def orientation(orientation):
 def size(size):
     try:
         return int(size)
-    except:
+    except Exception:
         return 1

src/calibre/ebooks/textile/__init__.py

@@ -1,3 +1,4 @@
+from __future__ import absolute_import, division, print_function, unicode_literals
 from .functions import textile, textile_restricted, Textile
 
 if False:

src/calibre/ebooks/textile/functions.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python2
 # -*- coding: utf-8 -*-
+from __future__ import absolute_import, division, print_function, unicode_literals
 
 """
 PyTextile
@@ -64,6 +65,7 @@ import re
 import uuid
 
 from calibre.utils.smartypants import smartyPants
+from polyglot.builtins import unicode_type
 from polyglot.urllib import urlopen, urlparse
 
 
@@ -694,7 +696,7 @@ class Textile(object):
     def footnoteID(self, match):
         id, t = match.groups()
         if id not in self.fn:
-            self.fn[id] = str(uuid.uuid4())
+            self.fn[id] = unicode_type(uuid.uuid4())
         fnid = self.fn[id]
         if not t:
             t = ''
@@ -799,7 +801,7 @@ class Textile(object):
         return url
 
     def shelve(self, text):
-        id = str(uuid.uuid4()) + 'c'
+        id = unicode_type(uuid.uuid4()) + 'c'
         self.shelf[id] = text
         return id
 

src/calibre/ebooks/textile/unsmarten.py

@@ -1,4 +1,5 @@
 # -*- coding: utf-8 -*-
+from __future__ import absolute_import, division, print_function, unicode_literals
 
 __license__ = 'GPL 3'
 __copyright__ = '2011, Leigh Parry <leighparry@blueyonder.co.uk>'

src/calibre/translations/__init__.py

@@ -1,4 +1,4 @@
-from __future__ import print_function
+from __future__ import absolute_import, division, print_function, unicode_literals
 __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
 '''

src/calibre/translations/dynamic.py

@@ -1,3 +1,4 @@
+from __future__ import absolute_import, division, print_function, unicode_literals
 '''
 Dynamic language lookup of translations for user-visible strings.
 '''
@@ -26,7 +27,7 @@ def translate(lang, text):
                 allow_user_override=False), 'r') as zf:
                 try:
                     buf = io.BytesIO(zf.read(mpath + '/messages.mo'))
-                except:
+                except Exception:
                     pass
                 else:
                     trans = GNUTranslations(buf)

src/calibre/translations/msgfmt.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python2
 # Written by Martin v. Loewis <loewis@informatik.hu-berlin.de>
+from __future__ import absolute_import, division, print_function, unicode_literals
 
 """Generate binary message catalog from textual translation description.
 
@@ -44,11 +45,11 @@ def usage(code, msg=''):
     sys.exit(code)
 
 
-def add(id, str, fuzzy):
+def add(id, s, fuzzy):
     "Add a non-fuzzy translation to the dictionary."
     global MESSAGES
-    if not fuzzy and str:
+    if not fuzzy and s:
-        MESSAGES[id] = str
+        MESSAGES[id] = s
         if id:
             STATS['translated'] += 1
     else:
@@ -59,7 +60,7 @@ def add(id, str, fuzzy):
 def generate():
     "Return the generated output."
     global MESSAGES
-    keys = MESSAGES.keys()
+    keys = list(MESSAGES)
     # the keys are sorted in the .mo file
     keys.sort()
     offsets = []
@@ -93,8 +94,8 @@ def generate():
                          7*4+len(keys)*8,   # start of value index
                          0, 0)              # size and offset of hash table
     output += array.array("i", offsets).tostring()
-    output += ids
+    output += ids.encode('utf-8')
-    output += strs
+    output += strs.encode('utf-8')
     return output
 
 
@@ -123,6 +124,7 @@ def make(filename, outfile):
     lno = 0
     msgid = msgstr = ''
     for l in lines:
+        l = l.decode('utf-8')
         lno += 1
         # If we get a comment line after a msgstr, this is a new entry
         if l[0] == '#' and section == STR: