Fix for missing xml declaration of content.opf and toc.ncx

[librarian.git] / librarian / __init__.py

diff --git a/librarian/__init__.py b/librarian/__init__.py
index dd09ce4..bf15d13 100644 (file)
--- a/librarian/__init__.py
+++ b/librarian/__init__.py
@@ -8,24 +8,34 @@ from __future__ import with_statement
 import os
 import re
 import shutil
 import os
 import re
 import shutil

+import urllib

 
 

-class ParseError(Exception):
+
+class UnicodeException(Exception):

     def __str__(self):
         """ Dirty workaround for Python Unicode handling problems. """
     def __str__(self):
         """ Dirty workaround for Python Unicode handling problems. """

-        return self.message
+        return unicode(self).encode('utf-8')

 
     def __unicode__(self):
         """ Dirty workaround for Python Unicode handling problems. """
 
     def __unicode__(self):
         """ Dirty workaround for Python Unicode handling problems. """

-        return self.message
+        args = self.args[0] if len(self.args) == 1 else self.args
+        try:
+            message = unicode(args)
+        except UnicodeDecodeError:
+            message = unicode(args, encoding='utf-8', errors='ignore')
+        return message
+
+class ParseError(UnicodeException):
+    pass

 
 

-class ValidationError(Exception):
+class ValidationError(UnicodeException):

     pass
 
 class NoDublinCore(ValidationError):
     """There's no DublinCore section, and it's required."""
     pass
 
     pass
 
 class NoDublinCore(ValidationError):
     """There's no DublinCore section, and it's required."""
     pass
 

-class NoProvider(Exception):
+class NoProvider(UnicodeException):

     """There's no DocProvider specified, and it's needed."""
     pass
 
     """There's no DocProvider specified, and it's needed."""
     pass
 


@@ -55,6 +65,7 @@ class EmptyNamespace(XMLNamespace):
         return tag
 
 # some common namespaces we use
         return tag
 
 # some common namespaces we use

+XMLNS = XMLNamespace('http://www.w3.org/XML/1998/namespace')

 RDFNS = XMLNamespace('http://www.w3.org/1999/02/22-rdf-syntax-ns#')
 DCNS = XMLNamespace('http://purl.org/dc/elements/1.1/')
 XINS = XMLNamespace("http://www.w3.org/2001/XInclude")
 RDFNS = XMLNamespace('http://www.w3.org/1999/02/22-rdf-syntax-ns#')
 DCNS = XMLNamespace('http://purl.org/dc/elements/1.1/')
 XINS = XMLNamespace("http://www.w3.org/2001/XInclude")


@@ -70,7 +81,7 @@ class WLURI(object):
     slug = None
 
     example = 'http://wolnelektury.pl/katalog/lektura/template/'
     slug = None
 
     example = 'http://wolnelektury.pl/katalog/lektura/template/'

-    _re_wl_uri = re.compile('http://wolnelektury.pl/katalog/lektura/'
+    _re_wl_uri = re.compile(r'http://(www\.)?wolnelektury.pl/katalog/lektura/'

             '(?P<slug>[-a-z0-9]+)/?$')
 
     def __init__(self, uri):
             '(?P<slug>[-a-z0-9]+)/?$')
 
     def __init__(self, uri):


@@ -82,8 +93,8 @@ class WLURI(object):
     def strict(cls, uri):
         match = cls._re_wl_uri.match(uri)
         if not match:
     def strict(cls, uri):
         match = cls._re_wl_uri.match(uri)
         if not match:

-            raise ValueError('Supplied URI (%s) does not match '
-                'the template: %s.' % (uri, cls._re_wl_uri))
+            raise ValidationError(u'Invalid URI (%s). Should match: %s' % (
+                        uri, cls._re_wl_uri.pattern))

         return cls(uri)
 
     @classmethod
         return cls(uri)
 
     @classmethod


@@ -264,3 +275,8 @@ class OutputFile(object):
         if not os.path.isdir(dirname):
             os.makedirs(dirname)
         shutil.copy(self.get_filename(), path)
         if not os.path.isdir(dirname):
             os.makedirs(dirname)
         shutil.copy(self.get_filename(), path)

+
+
+class URLOpener(urllib.FancyURLopener):
+    version = 'FNP Librarian (http://github.com/fnp/librarian)'
+urllib._urlopener = URLOpener()