KG updates plus GwR epub description tweak

src/calibre/__init__.py

@@ -378,10 +378,11 @@ def strftime(fmt, t=None):
         t = time.localtime()
     early_year = t[0] < 1900
     if early_year:
+        replacement = 1900 if t[0]%4 == 0 else 1901
         fmt = fmt.replace('%Y', '_early year hack##')
         t = list(t)
         orig_year = t[0]
-        t[0] = 1900
+        t[0] = replacement
     ans = None
     if iswindows:
         if isinstance(fmt, unicode):

src/calibre/library/catalog.py

@@ -2235,7 +2235,7 @@ class EPUB_MOBI(CatalogPlugin):
                     cmTag['name'] = "author"
                     navStr = '%s | %s' % (self.formatNCXText(book['author'], dest='author'),
                           book['date'].split()[1])
-                    if 'tags' in book:
+                    if 'tags' in book and len(book['tags']):
                         navStr = self.formatNCXText(navStr + ' | ' + ' · '.join(sorted(book['tags'])), dest='author')
                     cmTag.insert(0, NavigableString(navStr))
                     navPointVolumeTag.insert(2, cmTag)
@@ -3298,10 +3298,10 @@ class EPUB_MOBI(CatalogPlugin):
             Deprecated HTML returns as HTML via BeautifulSoup()
 
             '''
-
-            # Explode lost CRs to \n\n
             # Hackish - ignoring sentences ending or beginning in numbers to avoid
             # confusion with decimal points.
+
+            # Explode lost CRs to \n\n
             for lost_cr in re.finditer('([a-z])([\.\?!])([A-Z])',comments):
                 comments = comments.replace(lost_cr.group(),
                                             '%s%s\n\n%s' % (lost_cr.group(1),
@@ -3323,6 +3323,8 @@ class EPUB_MOBI(CatalogPlugin):
             # Convert solo returns to <br />
             comments = re.sub('[\r\n]','<br />', comments)
 
+            # Convert two hypens to emdash
+            comments = re.sub('--','&mdash;',comments)
             soup = BeautifulSoup(comments)
 
             result = BeautifulSoup()

src/calibre/utils/date.py

@@ -11,8 +11,21 @@ from datetime import datetime
 from dateutil.parser import parse
 from dateutil.tz import tzlocal, tzutc
 
+class SafeLocalTimeZone(tzlocal):
+    '''
+    Assume DST was not in effect for historical dates, if DST
+    data for the local timezone is not present in the operating system.
+    '''
+
+    def _isdst(self, dt):
+        try:
+            return tzlocal._isdst(self, dt)
+        except ValueError:
+            pass
+        return False
+
 utc_tz = _utc_tz = tzutc()
-local_tz = _local_tz = tzlocal()
+local_tz = _local_tz = SafeLocalTimeZone()
 
 def parse_date(date_string, assume_utc=False, as_utc=True, default=None):
     '''

src/odf/element.py

@@ -165,6 +165,18 @@ class Node(xml.dom.Node):
         oldChild.parentNode = None
         return oldChild
 
+    def __str__(self):
+        val = []
+        for c in self.childNodes:
+            val.append(str(c))
+        return ''.join(val)
+
+    def __unicode__(self):
+        val = []
+        for c in self.childNodes:
+            val.append(unicode(c))
+        return u''.join(val)
+
 defproperty(Node, "firstChild", doc="First child node, or None.")
 defproperty(Node, "lastChild",  doc="Last child node, or None.")
 
@@ -221,6 +233,9 @@ class Text(Childless, Node):
         self.data = data
 
     def __str__(self):
+        return self.data.encode()
+
+    def __unicode__(self):
         return self.data
 
     def toXml(self,level,f):
@@ -452,3 +467,9 @@ class Element(Node):
         obj = element(check_grammar=False)
         return self._getElementsByObj(obj,[])
 
+    def isInstanceOf(self, element):
+        """ This is a check to see if the object is an instance of a type """
+        obj = element(check_grammar=False)
+        return self.qname == obj.qname
+
+

src/odf/grammar.py

@@ -4670,6 +4670,7 @@ allowed_attributes = {
 	(NUMBERNS,u'boolean-style'):(
 		(NUMBERNS,u'transliteration-language'),
 		(STYLENS,u'name'),
+		(STYLENS,u'display-name'),
 		(NUMBERNS,u'language'),
 		(NUMBERNS,u'title'),
 		(NUMBERNS,u'country'),
@@ -4681,6 +4682,7 @@ allowed_attributes = {
 	(NUMBERNS,u'currency-style'):(
 		(NUMBERNS,u'transliteration-language'),
 		(STYLENS,u'name'),
+		(STYLENS,u'display-name'),
 		(NUMBERNS,u'language'),
 		(NUMBERNS,u'title'),
 		(NUMBERNS,u'country'),
@@ -4698,6 +4700,7 @@ allowed_attributes = {
 	(NUMBERNS,u'date-style'):(
 		(NUMBERNS,u'transliteration-language'),
 		(STYLENS,u'name'),
+		(STYLENS,u'display-name'),
 		(NUMBERNS,u'language'),
 		(NUMBERNS,u'title'),
 		(NUMBERNS,u'country'),
@@ -4753,6 +4756,7 @@ allowed_attributes = {
 	(NUMBERNS,u'number-style'):(
 		(NUMBERNS,u'transliteration-language'),
 		(STYLENS,u'name'),
+		(STYLENS,u'display-name'),
 		(NUMBERNS,u'language'),
 		(NUMBERNS,u'title'),
 		(NUMBERNS,u'country'),
@@ -4765,6 +4769,7 @@ allowed_attributes = {
 	(NUMBERNS,u'percentage-style'):(
 		(NUMBERNS,u'transliteration-language'),
 		(STYLENS,u'name'),
+		(STYLENS,u'display-name'),
 		(NUMBERNS,u'language'),
 		(NUMBERNS,u'title'),
 		(NUMBERNS,u'country'),
@@ -4794,6 +4799,7 @@ allowed_attributes = {
 	(NUMBERNS,u'text-style'):(
 		(NUMBERNS,u'transliteration-language'),
 		(STYLENS,u'name'),
+		(STYLENS,u'display-name'),
 		(NUMBERNS,u'language'),
 		(NUMBERNS,u'title'),
 		(NUMBERNS,u'country'),
@@ -4806,6 +4812,7 @@ allowed_attributes = {
 		(NUMBERNS,u'transliteration-language'),
 		(NUMBERNS,u'transliteration-format'),
 		(STYLENS,u'name'),
+		(STYLENS,u'display-name'),
 		(NUMBERNS,u'language'),
 		(NUMBERNS,u'title'),
 		(NUMBERNS,u'country'),

src/odf/odf2xhtml.py

@@ -376,6 +376,8 @@ class ODF2XHTML(handler.ContentHandler):
         (OFFICENS, "text"):(self.s_office_text, self.e_office_text),
         (OFFICENS, "scripts"):(self.s_ignorexml, None),
         (PRESENTATIONNS, "notes"):(self.s_ignorexml, None),
+#       (STYLENS, "default-page-layout"):(self.s_style_default_page_layout, self.e_style_page_layout),
+        (STYLENS, "default-page-layout"):(self.s_ignorexml, None),
         (STYLENS, "default-style"):(self.s_style_default_style, self.e_style_default_style),
         (STYLENS, "drawing-page-properties"):(self.s_style_handle_properties, None),
         (STYLENS, "font-face"):(self.s_style_font_face, None),
@@ -834,8 +836,17 @@ class ODF2XHTML(handler.ContentHandler):
         self.stylestack.append(self.currentstyle)
         self.styledict[self.currentstyle] = {}
 
+    def s_style_default_page_layout(self, tag, attrs):
+        """ Collect the formatting for the default page layout style.
+        """
+        self.currentstyle = "@page"
+        self.stylestack.append(self.currentstyle)
+        self.styledict[self.currentstyle] = {}
+
     def s_style_page_layout(self, tag, attrs):
         """ Collect the formatting for the page layout style.
+            This won't work in CSS 2.1, as page identifiers are not allowed.
+            It is legal in CSS3, but the rest of the application doesn't specify when to use what page layout
         """
         name = attrs[(STYLENS,'name')]
         name = name.replace(".","_")