Sync to trunk

src/calibre/__init__.py

@@ -424,15 +424,19 @@ def entity_to_unicode(match, exceptions=[], encoding='cp1252'):
 
 if isosx:
     fdir = os.path.expanduser('~/.fonts')
-    if not os.path.exists(fdir):
+    try:
-        os.makedirs(fdir)
+        if not os.path.exists(fdir):
-    if not os.path.exists(os.path.join(fdir, 'LiberationSans_Regular.ttf')):
+            os.makedirs(fdir)
-        from calibre.ebooks.lrf.fonts.liberation import __all__ as fonts
+        if not os.path.exists(os.path.join(fdir, 'LiberationSans_Regular.ttf')):
-        for font in fonts:
+            from calibre.ebooks.lrf.fonts.liberation import __all__ as fonts
-            l = {}
+            for font in fonts:
-            exec 'from calibre.ebooks.lrf.fonts.liberation.'+font+' import font_data' in l
+                l = {}
-            open(os.path.join(fdir, font+'.ttf'), 'wb').write(l['font_data'])
+                exec 'from calibre.ebooks.lrf.fonts.liberation.'+font+' import font_data' in l
-            
+                open(os.path.join(fdir, font+'.ttf'), 'wb').write(l['font_data'])
+    except:
+        import traceback
+        traceback.print_exc()
+                
 # Migrate from QSettings based config system
 from calibre.utils.config import migrate
 migrate()

src/calibre/ebooks/html.py

@@ -898,7 +898,7 @@ def config(defaults=None, config_name='html',
     metadata('title', ['-t', '--title'], default=None,
              help=_('Set the title. Default is to autodetect.'))
     metadata('authors', ['-a', '--authors'], default=None,
-             help=_('The author(s) of the ebook, as a comma separated list.'))
+             help=_('The author(s) of the ebook, as a & separated list.'))
     metadata('tags', ['--subjects'], default=None,
              help=_('The subject(s) of this book, as a comma separated list.'))
     metadata('publisher', ['--publisher'], default=None,
@@ -994,7 +994,9 @@ def merge_metadata(htmlfile, opf, opts):
         val = getattr(opts, attr, None)
         if val is None or val == _('Unknown') or val == [_('Unknown')]:
             continue
-        if attr in ('authors', 'tags'):
+        if attr =='authors':
+            val = [i.strip() for i in val.split('&') if i.strip()]
+        elif attr == 'tags':
             val = [i.strip() for i in val.split(',') if i.strip()]
         setattr(mi, attr, val)
         

src/calibre/ebooks/lrf/rtf/convert_from.py

@@ -170,7 +170,7 @@ def generate_html(rtfpath, tdir):
         f.write(res)
         f.close()
         try:
-            mi = get_metadata(open(rtfpath, 'rb'))
+            mi = get_metadata(open(rtfpath, 'rb'), 'rtf')
         except:
             mi = MetaInformation(None, None)
         if not mi.title:

src/calibre/ebooks/metadata/opf.xml

@@ -16,9 +16,9 @@
         <dc:description py:if="mi.comments">${mi.comments}</dc:description>
         <dc:publisher py:if="mi.publisher">${mi.publisher}</dc:publisher>
         <dc:identifier opf:scheme="ISBN" py:if="mi.isbn">${mi.isbn}</dc:identifier>
-        <series py:if="mi.series">${mi.series}</series>
+        <meta py:if="mi.series is not None" name="series" content="${mi.series}"/>
-        <series_index py:if="mi.series_index is not None">${mi.series_index}</series_index>
+        <meta py:if="mi.series_index is not None" name="series_index" content="${mi.series_index}"/>
-        <rating py:if="mi.rating is not None">${mi.rating}</rating>
+        <meta py:if="mi.rating is not None" name="rating" content="${mi.rating}"/>
         <py:for each="tag in mi.tags">
         <dc:subject py:if="mi.tags is not None">${tag}</dc:subject>
         </py:for>

src/calibre/ebooks/metadata/opf2.py

@@ -392,8 +392,8 @@ class MetadataField(object):
     def __set__(self, obj, val):
         elem = obj.get_metadata_element(self.name)
         if elem is None:
-            elem = obj.create_metadata_element(self.name, ns='dc' if self.is_dc else 'opf')
+            elem = obj.create_metadata_element(self.name, is_dc=self.is_dc)
-        elem.text = unicode(val)
+        obj.set_text(elem, unicode(val))
 
 class OPF(object):
     MIMETYPE         = 'application/oebps-package+xml'
@@ -403,16 +403,18 @@ class OPF(object):
                         'dc'  : "http://purl.org/dc/elements/1.1/",
                         'opf' : "http://www.idpf.org/2007/opf",
                        }
+    META             = '{%s}meta' % NAMESPACES['opf']
     xpn = NAMESPACES.copy()
     xpn.pop(None)
     xpn['re'] = 'http://exslt.org/regular-expressions'
     XPath = functools.partial(etree.XPath, namespaces=xpn)
+    CONTENT          = XPath('self::*[re:match(name(), "meta$", "i")]/@content')
     TEXT             = XPath('string()')
     
     
     metadata_path   = XPath('descendant::*[re:match(name(), "metadata", "i")]')
-    metadata_elem_path = XPath('descendant::*[re:match(name(), $name, "i")]')
+    metadata_elem_path = XPath('descendant::*[re:match(name(), $name, "i") or (re:match(name(), "^meta$", "i") and re:match(@name, $name, "i"))]')
-    series_path     = XPath('descendant::*[re:match(name(), "series$", "i")]')
+    series_path     = XPath('descendant::*[re:match(name(), "series$", "i") or (re:match(name(), "^meta$", "i") and re:match(@name, "series$", "i"))]')
     authors_path    = XPath('descendant::*[re:match(name(), "creator", "i") and (@role="aut" or @opf:role="aut" or (not(@role) and not(@opf:role)))]')
     bkp_path        = XPath('descendant::*[re:match(name(), "contributor", "i") and (@role="bkp" or @opf:role="bkp")]')
     tags_path       = XPath('descendant::*[re:match(name(), "subject", "i")]')
@@ -497,7 +499,13 @@ class OPF(object):
     
         
     def get_text(self, elem):
-        return u''.join(self.TEXT(elem))
+        return u''.join(self.CONTENT(elem) or self.TEXT(elem))
+
+    def set_text(self, elem, content):
+        if elem.tag == self.META:
+            elem.attib['content'] = content
+        else:
+            elem.text = content
     
     def itermanifest(self):
         return self.manifest_path(self.root)
@@ -611,9 +619,9 @@ class OPF(object):
             for elem in remove:
                 self.metadata.remove(elem)
             for author in val:
-                elem = self.create_metadata_element('creator', ns='dc',
+                attrib = {'{%s}role'%self.NAMESPACES['opf']: 'aut'}
-                                                    attrib={'{%s}role'%self.NAMESPACES['opf']:'aut'})
+                elem = self.create_metadata_element('creator', attrib=attrib)
-                elem.text = author
+                self.set_text(elem, author)
         
         return property(fget=fget, fset=fset)
     
@@ -650,8 +658,8 @@ class OPF(object):
             for tag in list(self.tags_path(self.metadata)):
                 self.metadata.remove(tag)
             for tag in val:
-                elem = self.create_metadata_element('subject', ns='dc')
+                elem = self.create_metadata_element('subject')
-                elem.text = unicode(tag)
+                self.set_text(elem, unicode(tag))
         
         return property(fget=fget, fset=fset)
     
@@ -660,14 +668,15 @@ class OPF(object):
         
         def fget(self):
             for match in self.isbn_path(self.metadata):
-                return match.text if match.text else None
+                return self.get_text(match) or None
             
         def fset(self, val):
             matches = self.isbn_path(self.metadata)
             if not matches:
-                matches = [self.create_metadata_element('identifier', ns='dc',
+                attrib = {'{%s}scheme'%self.NAMESPACES['opf']: 'ISBN'}
-                                                attrib={'{%s}scheme'%self.NAMESPACES['opf']:'ISBN'})]
+                matches = [self.create_metadata_element('identifier',
-            matches[0].text = unicode(val)
+                                                        attrib=attrib)]
+            self.set_text(matches[0], unicode(val))
 
         return property(fget=fget, fset=fset)
 
@@ -676,14 +685,15 @@ class OPF(object):
         
         def fget(self):
             for match in self.application_id_path(self.metadata):
-                return match.text if match.text else None
+                return self.get_text(match) or None
             
         def fset(self, val):
             matches = self.application_id_path(self.metadata)
             if not matches:
-                matches = [self.create_metadata_element('identifier', ns='dc',
+                attrib = {'{%s}scheme'%self.NAMESPACES['opf']: 'calibre'}
-                                                attrib={'{%s}scheme'%self.NAMESPACES['opf']:'calibre'})]
+                matches = [self.create_metadata_element('identifier',
-            matches[0].text = unicode(val)
+                                                        attrib=attrib)]
+            self.set_text(matches[0], unicode(val))
 
         return property(fget=fget, fset=fset)
 
@@ -693,13 +703,13 @@ class OPF(object):
         
         def fget(self):
             for match in self.series_path(self.metadata):
-                return match.text if match.text else None
+                return self.get_text(match) or None
         
         def fset(self, val):
             matches = self.series_path(self.metadata)
             if not matches:
-                matches = [self.create_metadata_element('series')]
+                matches = [self.create_metadata_element('series', is_dc=False)]
-            matches[0].text = unicode(val)
+            self.set_text(matches[0], unicode(val))
         
         return property(fget=fget, fset=fset)
     
@@ -710,14 +720,15 @@ class OPF(object):
         
         def fget(self):
             for match in self.bkp_path(self.metadata):
-                return match.text if match.text else None
+                return self.get_text(match) or None
             
         def fset(self, val):
             matches = self.bkp_path(self.metadata)
             if not matches:
-                matches = [self.create_metadata_element('contributor', ns='dc',
+                attrib = {'{%s}role'%self.NAMESPACES['opf']: 'bkp'}
-                                                attrib={'{%s}role'%self.NAMESPACES['opf']:'bkp'})]
+                matches = [self.create_metadata_element('contributor',
-            matches[0].text = unicode(val)
+                                                        attrib=attrib)]
+            self.set_text(matches[0], unicode(val))
         return property(fget=fget, fset=fset)
     
     
@@ -783,9 +794,15 @@ class OPF(object):
         if matches:
             return matches[-1]
         
-    def create_metadata_element(self, name, attrib=None, ns='opf'):
+    def create_metadata_element(self, name, attrib=None, is_dc=True):
-        elem = etree.SubElement(self.metadata, '{%s}%s'%(self.NAMESPACES[ns], name), 
+        if is_dc:
-                                attrib=attrib, nsmap=self.NAMESPACES)
+            name = '{%s}%s' % (self.NAMESPACES['dc'], name)
+        else:
+            attrib = attrib or {}
+            attrib['name'] = name
+            name = '{%s}%s' % (self.NAMESPACES['opf'], 'meta')
+        elem = etree.SubElement(self.metadata, name, attrib=attrib,
+                                nsmap=self.NAMESPACES)
         elem.tail = '\n'
         return elem
         

src/calibre/ebooks/rtf2xml/copy.py

@@ -15,7 +15,8 @@
 #                                                                       #
 #                                                                       #
 #########################################################################
-import sys, os
+import sys, os, shutil
+
 class Copy:
     """Copy each changed file to a directory for debugging purposes"""
     __dir = ""
@@ -64,25 +65,7 @@ class Copy:
         of cp. Otherwise, use a safe python method.
         """
         write_file = os.path.join(Copy.__dir,new_file)
-        platform = sys.platform
+        shutil.copyfile(file, write_file)
-        if platform[:5] == 'linux':
+    
-            command = 'cp %(file)s %(write_file)s' % vars()
-            os.system(command)
-        else:
-            read_obj = open(file,'r')
-            write_obj = open(write_file, 'w')
-            line = "dummy"
-            while line:
-                    line = read_obj.read(1000)
-                    write_obj.write(line )
-            read_obj.close()
-            write_obj.close()
     def rename(self, source, dest):
-        read_obj = open(source, 'r')
+        shutil.copyfile(source, dest)
-        write_obj = open(dest, 'w')
-        line = 1
-        while line:
-            line = read_obj.readline()
-            write_obj.write(line)
-        read_obj.close()
-        write_obj.close()

src/odf/manifest.py

@@ -39,15 +39,3 @@ def Algorithm(**args):
 def KeyDerivation(**args):
     return Element(qname = (MANIFESTNS,'key-derivation'), **args)
 
-
-
-if __name__ == "__main__":
-    import cStringIO
-    xml=cStringIO.StringIO()
-    m = Manifest()
-    f = FileEntry(mediatype="text/xml", fullpath="content.xml")
-    m.addElement(f)
-
-    m.toXml(0,xml)
-    print xml.getvalue()
-

src/odf/namespaces.py

@@ -17,7 +17,7 @@
 #
 # Contributor(s):
 #
-TOOLSVERSION = u"ODFPY/0.8.1dev"
+TOOLSVERSION = u"ODFPY/0.8.2dev"
 
 ANIMNS         = u"urn:oasis:names:tc:opendocument:xmlns:animation:1.0"
 DBNS           = u"urn:oasis:names:tc:opendocument:xmlns:database:1.0"
@@ -49,7 +49,7 @@ TABLENS        = u"urn:oasis:names:tc:opendocument:xmlns:table:1.0"
 TEXTNS         = u"urn:oasis:names:tc:opendocument:xmlns:text:1.0"
 XFORMSNS       = u"http://www.w3.org/2002/xforms"
 XLINKNS        = u"http://www.w3.org/1999/xlink"
-XMLNS          = "http://www.w3.org/XML/1998/namespace"
+XMLNS          = u"http://www.w3.org/XML/1998/namespace"
 
 
 nsdict = {

src/odf/opendocument.py

@@ -64,6 +64,12 @@ odmimetypes = {
  'application/vnd.oasis.opendocument.text-web':              '.oth',
 }
 
+class OpaqueObject:
+    def __init__(self, filename, mediatype, content=None):
+       self.mediatype = mediatype
+       self.filename = filename
+       self.content = content
+
 class OpenDocument:
     """ A class to hold the content of an OpenDocument document
         Use the xml method to write the XML
@@ -76,6 +82,7 @@ class OpenDocument:
     def __init__(self, mimetype, add_generator=True):
         self.mimetype = mimetype
         self.childobjects = []
+        self._extra = []
         self.folder = "" # Always empty for toplevel documents
         self.topnode = Document(mimetype=self.mimetype)
         self.topnode.ownerDocument = self
@@ -303,12 +310,15 @@ class OpenDocument:
         else:
             self.thumbnail = filecontent
 
-    def addObject(self, document):
+    def addObject(self, document, objectname=None):
         """ Add an object. The object must be an OpenDocument class
             The return value will be the folder in the zipfile the object is stored in
         """
         self.childobjects.append(document)
-        document.folder = "%s/Object %d" % (self.folder, len(self.childobjects))
+        if objectname is None:
+            document.folder = "%s/Object %d" % (self.folder, len(self.childobjects))
+        else:
+            document.folder = objectname
         return ".%s" % document.folder
 
     def _savePictures(self, object, folder):
@@ -348,7 +358,7 @@ class OpenDocument:
         else:
             if addsuffix:
                 outputfile = outputfile + odmimetypes.get(self.mimetype,'.xxx')
-            outputfp = zipfile.ZipFile(outputfile,"w")
+            outputfp = zipfile.ZipFile(outputfile, "w")
         self._zipwrite(outputfp)
         outputfp.close()
 
@@ -382,6 +392,14 @@ class OpenDocument:
             zi.external_attr = UNIXPERMS
             self._z.writestr(zi, self.thumbnail)
 
+        # Write any extra files
+        for op in self._extra:
+            self.manifest.addElement(manifest.FileEntry(fullpath=op.filename, mediatype=op.mediatype))
+            zi = zipfile.ZipInfo(op.filename.encode('utf-8'), self._now)
+            zi.compress_type = zipfile.ZIP_DEFLATED
+            zi.external_attr = UNIXPERMS
+            if op.content is not None:
+                self._z.writestr(zi, op.content)
         # Write manifest
         zi = zipfile.ZipInfo("META-INF/manifest.xml", self._now)
         zi.compress_type = zipfile.ZIP_DEFLATED
@@ -528,15 +546,20 @@ def load(odffile):
             parser.parse(inpsrc)
             del doc._parsing
         except KeyError, v: pass
-    # Add the thumbnail here
+    # FIXME: Add subobjects correctly here
-    # Add the images here
     for mentry,mvalue in manifest.items():
         if mentry[:9] == "Pictures/" and len(mentry) > 9:
             doc.addPicture(mvalue['full-path'], mvalue['media-type'], z.read(mentry))
         elif mentry == "Thumbnails/thumbnail.png":
             doc.addThumbnail(z.read(mentry))
+        elif mentry in ('settings.xml', 'meta.xml', 'content.xml', 'styles.xml'):
+            pass
         else:
-            pass  # Add the SUN junk here to the struct somewhere
+            if mvalue['full-path'][-1] == '/':
+                doc._extra.append(OpaqueObject(mvalue['full-path'], mvalue['media-type'], None))
+            else:
+                doc._extra.append(OpaqueObject(mvalue['full-path'], mvalue['media-type'], z.read(mentry)))
+            # Add the SUN junk here to the struct somewhere
             # It is cached data, so it can be out-of-date
     z.close()
     b = doc.getElementsByType(Body)

src/odf/userfield.py

@@ -231,6 +231,19 @@ class ODFContentParser(xml.sax.saxutils.XMLGenerator):
         self._callback_func = callback_func
         xml.sax.saxutils.XMLGenerator.__init__(self, out, encoding)
 
+    def _qname(self, name):
+        """Builds a qualified name from a (ns_url, localname) pair"""
+        if name[0]:
+            if name[0] == u'http://www.w3.org/XML/1998/namespace':
+                return u'xml' + ":" + name[1]
+            # The name is in a non-empty namespace
+            prefix = self._current_context[name[0]]
+            if prefix:
+                # If it is not the default namespace, prepend the prefix
+                return prefix + ":" + name[1]
+        # Return the unqualified name
+        return name[1]
+
     def startElementNS(self, name, qname, attrs):
         if name == (TEXTNS, u'user-field-decl'):
             field_name = attrs.get((TEXTNS, u'name'))