Sync to pluginize

src/calibre/constants.py

@@ -2,7 +2,7 @@ __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
 __docformat__ = 'restructuredtext en'
 __appname__   = 'calibre'
-__version__   = '0.5.7'
+__version__   = '0.5.8'
 __author__    = "Kovid Goyal <kovid@kovidgoyal.net>"
 '''
 Various run time constants.

src/calibre/customize/builtins.py

@@ -282,6 +282,9 @@ from calibre.ebooks.pdb.input import PDBInput
 from calibre.ebooks.pdf.input import PDFInput
 from calibre.ebooks.txt.input import TXTInput
 from calibre.ebooks.lit.input import LITInput
+from calibre.ebooks.fb2.input import FB2Input
+from calibre.ebooks.odt.input import ODTInput
+from calibre.ebooks.rtf.input import RTFInput
 from calibre.ebooks.html.input import HTMLInput
 from calibre.ebooks.oeb.output import OEBOutput
 from calibre.ebooks.txt.output import TXTOutput
@@ -289,7 +292,8 @@ from calibre.ebooks.pdf.output import PDFOutput
 from calibre.customize.profiles import input_profiles, output_profiles
 
 plugins = [HTML2ZIP, EPUBInput, MOBIInput, PDBInput, PDFInput, HTMLInput,
-        TXTInput, OEBOutput, TXTOutput, PDFOutput, LITInput]
+        TXTInput, OEBOutput, TXTOutput, PDFOutput, LITInput,
+        FB2Input, ODTInput, RTFInput]
 plugins += [x for x in list(locals().values()) if isinstance(x, type) and \
                                         x.__name__.endswith('MetadataReader')]
 plugins += [x for x in list(locals().values()) if isinstance(x, type) and \

src/calibre/ebooks/__init__.py

@@ -59,7 +59,10 @@ class HTMLRenderer(object):
 
 def render_html(path_to_html, width=590, height=750):
     from PyQt4.QtWebKit import QWebPage
-    from PyQt4.Qt import QEventLoop, QPalette, Qt, SIGNAL, QUrl, QSize
+    from PyQt4.Qt import QEventLoop, QPalette, Qt, SIGNAL, QUrl, QSize, \
+                         QApplication
+    if QApplication.instance() is None:
+        QApplication([])
     path_to_html = os.path.abspath(path_to_html)
     with CurrentDir(os.path.dirname(path_to_html)):
         page = QWebPage()

src/calibre/ebooks/conversion/cli.py

@@ -116,6 +116,25 @@ def add_pipeline_options(parser, plumber):
                       'font_size_mapping',
                       'line_height',
                       'linearize_tables',
+                      'extra_css',
+                  ]
+                  ),
+
+              'STRUCTURE DETECTION' : (
+                  _('Control auto-detection of document structure.'),
+                  [
+                      'dont_split_on_page_breaks', 'chapter', 'chapter_mark',
+                  ]
+                  ),
+
+              'TABLE OF CONTENTS' : (
+                  _('Control the automatic generation of a Table of Contents. By '
+                  'default, if the source file has a Table of Contents, it will '
+                  'be used in preference to the automatically generated one.'),
+                  [
+                    'level1_toc', 'level2_toc', 'level3_toc',
+                    'toc_threshold', 'max_toc_links', 'no_chapters_in_toc',
+                    'use_auto_toc', 'toc_filter',
                   ]
                   ),
 
@@ -130,7 +149,8 @@ def add_pipeline_options(parser, plumber):
 
               }
 
-    group_order = ['', 'LOOK AND FEEL', 'METADATA', 'DEBUG']
+    group_order = ['', 'LOOK AND FEEL', 'STRUCTURE DETECTION',
+            'TABLE OF CONTENTS', 'METADATA', 'DEBUG']
 
     for group in group_order:
         desc, options = groups[group]
@@ -163,6 +183,10 @@ def main(args=sys.argv):
     add_pipeline_options(parser, plumber)
 
     opts = parser.parse_args(args)[0]
+    y = lambda q : os.path.abspath(os.path.expanduser(q))
+    for x in ('read_metadata_from_opf', 'cover'):
+        if getattr(opts, x, None) is not None:
+            setattr(opts, x, y(getattr(opts, x)))
     recommendations = [(n.dest, getattr(opts, n.dest),
                         OptionRecommendation.HIGH) \
                                         for n in parser.options_iter()

src/calibre/ebooks/conversion/plumber.py

@@ -3,13 +3,21 @@ __license__ = 'GPL 3'
 __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 
-import os
+import os, re
 
 from calibre.customize.conversion import OptionRecommendation
 from calibre.customize.ui import input_profiles, output_profiles, \
         plugin_for_input_format, plugin_for_output_format
 from calibre.ebooks.conversion.preprocess import HTMLPreProcessor
 from calibre.ptempfile import PersistentTemporaryDirectory
+from calibre import extract, walk
+
+def supported_input_formats():
+    from calibre.customize.ui import available_input_formats
+    fmts = available_input_formats()
+    for x in ('zip', 'rar', 'oebzip'):
+        fmts.add(x)
+    return fmts
 
 class OptionValues(object):
     pass
@@ -121,6 +129,105 @@ OptionRecommendation(name='dont_split_on_page_breaks',
                 )
         ),
 
+OptionRecommendation(name='level1_toc',
+            recommended_value=None, level=OptionRecommendation.LOW,
+            help=_('XPath expression that specifies all tags that '
+            'should be added to the Table of Contents at level one. If '
+            'this is specified, it takes precedence over other forms '
+            'of auto-detection.'
+                )
+        ),
+
+OptionRecommendation(name='level2_toc',
+            recommended_value=None, level=OptionRecommendation.LOW,
+            help=_('XPath expression that specifies all tags that should be '
+            'added to the Table of Contents at level two. Each entry is added '
+            'under the previous level one entry.'
+                )
+        ),
+
+OptionRecommendation(name='level3_toc',
+            recommended_value=None, level=OptionRecommendation.LOW,
+            help=_('XPath expression that specifies all tags that should be '
+                'added to the Table of Contents at level three. Each entry '
+                'is added under the previous level two entry.'
+                )
+        ),
+
+OptionRecommendation(name='use_auto_toc',
+            recommended_value=False, level=OptionRecommendation.LOW,
+            help=_('Normally, if the source file already has a Table of '
+            'Contents, it is used in preference to the auto-generated one. '
+            'With this option, the auto-generated one is always used.'
+                )
+        ),
+
+OptionRecommendation(name='no_chapters_in_toc',
+            recommended_value=False, level=OptionRecommendation.LOW,
+            help=_("Don't add auto-detected chapters to the Table of "
+            'Contents.'
+                )
+        ),
+
+OptionRecommendation(name='toc_threshold',
+            recommended_value=6, level=OptionRecommendation.LOW,
+            help=_(
+        'If fewer than this number of chapters is detected, then links '
+        'are added to the Table of Contents. Default: %default')
+        ),
+
+OptionRecommendation(name='max_toc_links',
+            recommended_value=50, level=OptionRecommendation.LOW,
+            help=_('Maximum number of links to insert into the TOC. Set to 0 '
+               'to disable. Default is: %default. Links are only added to the '
+            'TOC if less than the threshold number of chapters were detected.'
+                )
+        ),
+
+OptionRecommendation(name='toc_filter',
+            recommended_value=None, level=OptionRecommendation.LOW,
+            help=_('Remove entries from the Table of Contents whose titles '
+            'match the specified regular expression. Matching entries and all '
+            'their children are removed.'
+                )
+        ),
+
+
+OptionRecommendation(name='chapter',
+        recommended_value="//*[((name()='h1' or name()='h2') and "
+              "re:test(., 'chapter|book|section|part', 'i')) or @class "
+              "= 'chapter']", level=OptionRecommendation.LOW,
+            help=_('An XPath expression to detect chapter titles. The default '
+                'is to consider <h1> or <h2> tags that contain the words '
+                '"chapter","book","section" or "part" as chapter titles as '
+                'well as any tags that have class="chapter". The expression '
+                'used must evaluate to a list of elements. To disable chapter '
+                'detection, use the expression "/". See the XPath Tutorial '
+                'in the calibre User Manual for further help on using this '
+                'feature.'
+                )
+        ),
+
+OptionRecommendation(name='chapter_mark',
+            recommended_value='pagebreak', level=OptionRecommendation.LOW,
+            choices=['pagebreak', 'rule', 'both', 'none'],
+            help=_('Specify how to mark detected chapters. A value of '
+                    '"pagebreak" will insert page breaks before chapters. '
+                    'A value of "rule" will insert a line before chapters. '
+                    'A value of "none" will disable chapter marking and a '
+                    'value of "both" will use both page breaks and lines '
+                    'to mark chapters.')
+        ),
+
+OptionRecommendation(name='extra_css',
+            recommended_value=None, level=OptionRecommendation.LOW,
+            help=_('Either the path to a CSS stylesheet or raw CSS. '
+                'This CSS will be appended to the style rules from '
+                'the source file, so it can be used to override those '
+                'rules.')
+        ),
+
+
 
 OptionRecommendation(name='read_metadata_from_opf',
             recommended_value=None, level=OptionRecommendation.LOW,
@@ -130,6 +237,7 @@ OptionRecommendation(name='read_metadata_from_opf',
                    'file.')
         ),
 
+
 OptionRecommendation(name='title',
     recommended_value=None, level=OptionRecommendation.LOW,
     help=_('Set the title.')),
@@ -187,11 +295,14 @@ OptionRecommendation(name='language',
     help=_('Set the language.')),
 ]
 
-
         input_fmt = os.path.splitext(self.input)[1]
         if not input_fmt:
             raise ValueError('Input file must have an extension')
         input_fmt = input_fmt[1:].lower()
+        if input_fmt in ('zip', 'rar', 'oebzip'):
+            self.log('Processing archive...')
+            tdir = PersistentTemporaryDirectory('_plumber')
+            self.input, input_fmt = self.unarchive(self.input, tdir)
 
         if os.path.exists(self.output) and os.path.isdir(self.output):
             output_fmt = 'oeb'
@@ -201,7 +312,7 @@ OptionRecommendation(name='language',
                 output_fmt = '.oeb'
             output_fmt = output_fmt[1:].lower()
 
-        self.input_plugin = plugin_for_input_format(input_fmt)
+        self.input_plugin  = plugin_for_input_format(input_fmt)
         self.output_plugin = plugin_for_output_format(output_fmt)
 
         if self.input_plugin is None:
@@ -224,6 +335,43 @@ OptionRecommendation(name='language',
         # plugins.
         self.merge_plugin_recommendations()
 
+    @classmethod
+    def unarchive(self, path, tdir):
+        extract(path, tdir)
+        files = list(walk(tdir))
+        from calibre.customize.ui import available_input_formats
+        fmts = available_input_formats()
+        for x in ('htm', 'html', 'xhtm', 'xhtml'): fmts.remove(x)
+
+        for ext in fmts:
+            for f in files:
+                if f.lower().endswith('.'+ext):
+                    if ext in ['txt', 'rtf'] and os.stat(f).st_size < 2048:
+                        continue
+                    return f, ext
+        return self.find_html_index(files)
+
+    @classmethod
+    def find_html_index(self, files):
+        '''
+        Given a list of files, find the most likely root HTML file in the
+        list.
+        '''
+        html_pat = re.compile(r'\.(x){0,1}htm(l){0,1}$', re.IGNORECASE)
+        html_files = [f for f in files if html_pat.search(f) is not None]
+        if not html_files:
+            raise ValueError(_('Could not find an ebook inside the archive'))
+        html_files = [(f, os.stat(f).st_size) for f in html_files]
+        html_files.sort(cmp = lambda x, y: cmp(x[1], y[1]))
+        html_files = [f[0] for f in html_files]
+        for q in ('toc', 'index'):
+            for f in html_files:
+                if os.path.splitext(os.path.basename(f))[0].lower() == q:
+                    return f, os.path.splitext(f)[1].lower()[1:]
+        return html_files[-1], os.path.splitext(html_files[-1])[1].lower()[1:]
+
+
+
     def get_option_by_name(self, name):
         for group in (self.input_options, self.pipeline_options,
                       self.output_options):
@@ -237,6 +385,7 @@ OptionRecommendation(name='language',
                 rec = self.get_option_by_name(name)
                 if rec is not None and rec.level <= level:
                     rec.recommended_value = val
+                    rec.level = level
 
     def merge_ui_recommendations(self, recommendations):
         '''
@@ -248,6 +397,7 @@ OptionRecommendation(name='language',
             rec = self.get_option_by_name(name)
             if rec is not None and rec.level <= level and rec.level < rec.HIGH:
                 rec.recommended_value = val
+                rec.level = level
 
     def read_user_metadata(self):
         '''
@@ -332,6 +482,9 @@ OptionRecommendation(name='language',
         self.opts.source = self.opts.input_profile
         self.opts.dest = self.opts.output_profile
 
+        from calibre.ebooks.oeb.transforms.structure import DetectStructure
+        DetectStructure()(self.oeb, self.opts)
+
         from calibre.ebooks.oeb.transforms.flatcss import CSSFlattener
         fbase = self.opts.base_font_size
         if fbase == 0:
@@ -342,6 +495,9 @@ OptionRecommendation(name='language',
         else:
             fkey = map(float, fkey.split(','))
 
+        if self.opts.extra_css and os.path.exists(self.opts.extra_css):
+            self.opts.extra_css = open(self.opts.extra_css, 'rb').read()
+
         flattener = CSSFlattener(fbase=fbase, fkey=fkey,
                 lineh=self.opts.line_height,
                 untable=self.opts.linearize_tables)
@@ -364,6 +520,8 @@ OptionRecommendation(name='language',
         trimmer = ManifestTrimmer()
         trimmer(self.oeb, self.opts)
 
+        self.oeb.toc.rationalize_play_orders()
+
         self.log.info('Creating %s...'%self.output_plugin.name)
         self.output_plugin.convert(self.oeb, self.output, self.input_plugin,
                 self.opts, self.log)
@@ -384,4 +542,3 @@ def create_oebbook(log, path_or_stream, opts, reader=None):
 
     reader()(oeb, path_or_stream)
     return oeb
-

src/calibre/ebooks/epub/from_any.py

@@ -15,130 +15,17 @@ from calibre.ebooks import DRMError
 from calibre.ebooks.epub import config as common_config
 from calibre.ebooks.epub.from_html import convert as html2epub, find_html_index
 from calibre.ptempfile import TemporaryDirectory
-from calibre.ebooks.metadata import MetaInformation
-from calibre.ebooks.metadata.opf2 import OPFCreator, OPF
 from calibre.utils.zipfile import ZipFile
 from calibre.customize.ui import run_plugins_on_preprocess
 
-def lit2opf(path, tdir, opts):
-    from calibre.ebooks.lit.reader import LitReader
-    print 'Exploding LIT file:', path
-    reader = LitReader(path)
-    reader.extract_content(tdir, False)
-    opf = None
-    for opf in walk(tdir):
-        if opf.lower().endswith('.opf'):
-            break
-    if not opf.endswith('.opf'):
-        opf = None
-    if opf is not None: # Check for url-quoted filenames
-        _opf = OPF(opf, os.path.dirname(opf))
-        replacements = []
-        for item in _opf.itermanifest():
-            href = item.get('href', '')
-            path = os.path.join(os.path.dirname(opf), *(href.split('/')))
-            if not os.path.exists(path) and os.path.exists(path.replace('&', '%26')):
-                npath = path
-                path = path.replace('&', '%26')
-                replacements.append((path, npath))
-        if replacements:
-            print 'Fixing quoted filenames...'
-            for path, npath in replacements:
-                if os.path.exists(path):
-                    os.rename(path, npath)
-            for f in walk(tdir):
-                with open(f, 'r+b') as f:
-                    raw = f.read()
-                    for path, npath in replacements:
-                        raw = raw.replace(os.path.basename(path), os.path.basename(npath))
-                        f.seek(0)
-                        f.truncate()
-                        f.write(raw)
-    return opf
 
-def mobi2opf(path, tdir, opts):
+SOURCE_FORMATS = ['lit', 'mobi', 'prc', 'azw', 'fb2', 'odt', 'rtf',
-    from calibre.ebooks.mobi.reader import MobiReader
-    print 'Exploding MOBI file:', path.encode('utf-8') if isinstance(path, unicode) else path
-    reader = MobiReader(path)
-    reader.extract_content(tdir)
-    files = list(walk(tdir))
-    opts.encoding = 'utf-8'
-    for f in files:
-        if f.lower().endswith('.opf'):
-            return f
-    html_pat = re.compile(r'\.(x){0,1}htm(l){0,1}', re.IGNORECASE)
-    hf = [f for f in files if html_pat.match(os.path.splitext(f)[1]) is not None]
-    mi = MetaInformation(os.path.splitext(os.path.basename(path))[0], [_('Unknown')])
-    opf = OPFCreator(tdir, mi)
-    opf.create_manifest([(hf[0], None)])
-    opf.create_spine([hf[0]])
-    ans = os.path.join(tdir, 'metadata.opf')
-    opf.render(open(ans, 'wb'))
-    return ans
-
-def fb22opf(path, tdir, opts):
-    from calibre.ebooks.lrf.fb2.convert_from import to_html
-    print 'Converting FB2 to HTML...'
-    return to_html(path, tdir)
-    
-def rtf2opf(path, tdir, opts):
-    from calibre.ebooks.lrf.rtf.convert_from import generate_html
-    generate_html(path, tdir)
-    return os.path.join(tdir, 'metadata.opf')
-
-def txt2opf(path, tdir, opts):
-    from calibre.ebooks.lrf.txt.convert_from import generate_html
-    generate_html(path, opts.encoding, tdir)
-    return os.path.join(tdir, 'metadata.opf')
-
-def pdf2opf(path, tdir, opts):
-    from calibre.ebooks.lrf.pdf.convert_from import generate_html
-    generate_html(path, tdir)
-    opts.dont_split_on_page_breaks = True
-    return os.path.join(tdir, 'metadata.opf')
-
-def epub2opf(path, tdir, opts):
-    zf = ZipFile(path)
-    zf.extractall(tdir)
-    opts.chapter_mark = 'none'
-    encfile = os.path.join(tdir, 'META-INF', 'encryption.xml')
-    opf = None
-    for f in walk(tdir):
-        if f.lower().endswith('.opf'):
-            opf = f
-            break
-    if opf and os.path.exists(encfile):
-        if not process_encryption(encfile, opf):
-            raise DRMError(os.path.basename(path))
-        
-    if opf is None:
-        raise ValueError('%s is not a valid EPUB file'%path)
-    return opf
-    
-def odt2epub(path, tdir, opts):
-    from calibre.ebooks.odt.to_oeb import Extract
-    opts.encoding = 'utf-8'
-    return Extract()(path, tdir)
-
-MAP = {
-       'lit'  : lit2opf,
-       'mobi' : mobi2opf,
-       'prc'  : mobi2opf,
-       'azw'  : mobi2opf,
-       'fb2'  : fb22opf,
-       'rtf'  : rtf2opf,
-       'txt'  : txt2opf,
-       'pdf'  : pdf2opf,
-       'epub' : epub2opf,
-       'odt'  : odt2epub,
-       }
-SOURCE_FORMATS = ['lit', 'mobi', 'prc', 'azw', 'fb2', 'odt', 'rtf', 
                   'txt', 'pdf', 'rar', 'zip', 'oebzip', 'htm', 'html', 'epub']
 
 def unarchive(path, tdir):
     extract(path, tdir)
     files = list(walk(tdir))
-    
+
     for ext in ['opf'] + list(MAP.keys()):
         for f in files:
             if f.lower().endswith('.'+ext):
@@ -147,32 +34,32 @@ def unarchive(path, tdir):
                 return f, ext
     return find_html_index(files)
 
-def any2epub(opts, path, notification=None, create_epub=True, 
+def any2epub(opts, path, notification=None, create_epub=True,
              oeb_cover=False, extract_to=None):
     path = run_plugins_on_preprocess(path)
     ext = os.path.splitext(path)[1]
     if not ext:
         raise ValueError('Unknown file type: '+path)
     ext = ext.lower()[1:]
-    
+
     if opts.output is None:
         opts.output = os.path.splitext(os.path.basename(path))[0]+'.epub'
-    
+
     with nested(TemporaryDirectory('_any2epub1'), TemporaryDirectory('_any2epub2')) as (tdir1, tdir2):
         if ext in ['rar', 'zip', 'oebzip']:
             path, ext = unarchive(path, tdir1)
             print 'Found %s file in archive'%(ext.upper())
-    
+
         if ext in MAP.keys():
             path = MAP[ext](path, tdir2, opts)
             ext = 'opf'
-            
+
-    
+
         if re.match(r'((x){0,1}htm(l){0,1})|opf', ext) is None:
             raise ValueError('Conversion from %s is not supported'%ext.upper())
-        
+
         print 'Creating EPUB file...'
-        html2epub(path, opts, notification=notification, 
+        html2epub(path, opts, notification=notification,
                   create_epub=create_epub, oeb_cover=oeb_cover,
                   extract_to=extract_to)
 

src/calibre/ebooks/epub/input.py

@@ -11,12 +11,12 @@ from lxml import etree
 from calibre.customize.conversion import InputFormatPlugin
 
 class EPUBInput(InputFormatPlugin):
-    
+
     name        = 'EPUB Input'
     author      = 'Kovid Goyal'
     description = 'Convert EPUB files (.epub) to HTML'
     file_types  = set(['epub'])
-    
+
     @classmethod
     def decrypt_font(cls, key, path):
         raw = open(path, 'rb').read()
@@ -26,7 +26,7 @@ class EPUBInput(InputFormatPlugin):
         with open(path, 'wb') as f:
             f.write(decrypt)
             f.write(raw[1024:])
-    
+
     @classmethod
     def process_ecryption(cls, encfile, opf, log):
         key = None
@@ -51,25 +51,75 @@ class EPUBInput(InputFormatPlugin):
             traceback.print_exc()
         return False
 
+    @classmethod
+    def rationalize_cover(self, opf):
+        guide_cover, guide_elem = None, None
+        for guide_elem in opf.iterguide():
+            if guide_elem.get('type', '').lower() == 'cover':
+                guide_cover = guide_elem.get('href', '')
+                break
+        if not guide_cover:
+            return
+        spine = list(opf.iterspine())
+        if not spine:
+            return
+        idref = spine[0].get('idref', '')
+        manifest = list(opf.itermanifest())
+        if not manifest:
+            return
+        if manifest[0].get('id', False) != idref:
+            return
+        spine[0].getparent().remove(spine[0])
+        guide_elem.set('href', 'calibre_raster_cover.jpg')
+        for elem in list(opf.iterguide()):
+            if elem.get('type', '').lower() == 'titlepage':
+                elem.getparent().remove(elem)
+        from calibre.ebooks.oeb.base import OPF
+        t = etree.SubElement(guide_elem.getparent(), OPF('reference'))
+        t.set('type', 'titlepage')
+        t.set('href', guide_cover)
+        t.set('title', 'Title Page')
+        from calibre.ebooks import render_html
+        open('calibre_raster_cover.jpg', 'wb').write(
+                render_html(guide_cover).data)
+
+
     def convert(self, stream, options, file_ext, log, accelerators):
         from calibre.utils.zipfile import ZipFile
         from calibre import walk
         from calibre.ebooks import DRMError
+        from calibre.ebooks.metadata.opf2 import OPF
         zf = ZipFile(stream)
         zf.extractall(os.getcwd())
         encfile = os.path.abspath(os.path.join('META-INF', 'encryption.xml'))
         opf = None
-        for f in walk('.'):
+        for f in walk(u'.'):
             if f.lower().endswith('.opf'):
-                opf = f
+                opf = os.path.abspath(f)
                 break
         path = getattr(stream, 'name', 'stream')
-        
+
         if opf is None:
             raise ValueError('%s is not a valid EPUB file'%path)
-        
+
         if os.path.exists(encfile):
             if not self.process_encryption(encfile, opf, log):
                 raise DRMError(os.path.basename(path))
 
-        return os.path.join(os.getcwd(), opf)
+        opf = os.path.relpath(opf, os.getcwdu())
+        parts = os.path.split(opf)
+        opf = OPF(opf, os.path.dirname(os.path.abspath(opf)))
+
+        if len(parts) > 1:
+            delta = '/'.join(parts[:-1])+'/'
+            for elem in opf.itermanifest():
+                elem.set('href', delta+elem.get('href'))
+            for elem in opf.iterguide():
+                elem.set('href', delta+elem.get('href'))
+
+        self.rationalize_cover(opf)
+
+        with open('content.opf', 'wb') as nopf:
+            nopf.write(opf.render())
+
+        return os.path.abspath('content.opf')

src/calibre/ebooks/fb2/input.py

@@ -0,0 +1,74 @@
+from __future__ import with_statement
+__license__   = 'GPL v3'
+__copyright__ = '2008, Anatoly Shipitsin <norguhtar at gmail.com>'
+"""
+Convert .fb2 files to .lrf
+"""
+import os
+from base64 import b64decode
+from lxml import etree
+
+from calibre.customize.conversion import InputFormatPlugin, OptionRecommendation
+from calibre import guess_type
+
+FB2NS = 'http://www.gribuser.ru/xml/fictionbook/2.0'
+
+class FB2Input(InputFormatPlugin):
+
+    name        = 'FB2 Input'
+    author      = 'Anatoly Shipitsin'
+    description = 'Convert FB2 files to HTML'
+    file_types  = set(['fb2'])
+
+    recommendations = set([
+        ('level1_toc', '//h:h1', OptionRecommendation.MED),
+        ('level2_toc', '//h:h2', OptionRecommendation.MED),
+        ('level3_toc', '//h:h3', OptionRecommendation.MED),
+        ])
+
+    def convert(self, stream, options, file_ext, log,
+                accelerators):
+        from calibre.resources import fb2_xsl
+        from calibre.ebooks.metadata.opf2 import OPFCreator
+        from calibre.ebooks.metadata.meta import get_metadata
+        from calibre.ebooks.oeb.base import XLINK_NS
+        NAMESPACES = {'f':FB2NS, 'l':XLINK_NS}
+
+        log.debug('Parsing XML...')
+        parser = etree.XMLParser(recover=True, no_network=True)
+        doc = etree.parse(stream, parser)
+        self.extract_embedded_content(doc)
+        log.debug('Converting XML to HTML...')
+        styledoc = etree.fromstring(fb2_xsl)
+
+        transform = etree.XSLT(styledoc)
+        result = transform(doc)
+        open('index.xhtml', 'wb').write(transform.tostring(result))
+        stream.seek(0)
+        mi = get_metadata(stream, 'fb2')
+        if not mi.title:
+            mi.title = _('Unknown')
+        if not mi.authors:
+            mi.authors = [_('Unknown')]
+        opf = OPFCreator(os.getcwdu(), mi)
+        entries = [(f, guess_type(f)[0]) for f in os.listdir('.')]
+        opf.create_manifest(entries)
+        opf.create_spine(['index.xhtml'])
+
+        for img in doc.xpath('//f:coverpage/f:image', namespaces=NAMESPACES):
+            href = img.get('{%s}href'%XLINK_NS, img.get('href', None))
+            if href is not None:
+                if href.startswith('#'):
+                    href = href[1:]
+                opf.guide.set_cover(os.path.abspath(href))
+
+        opf.render(open('metadata.opf', 'wb'))
+        return os.path.join(os.getcwd(), 'metadata.opf')
+
+    def extract_embedded_content(self, doc):
+        for elem in doc.xpath('./*'):
+            if 'binary' in elem.tag and elem.attrib.has_key('id'):
+                fname = elem.attrib['id']
+                data = b64decode(elem.text.strip())
+                open(fname, 'wb').write(data)
+

src/calibre/ebooks/lrf/fb2/convert_from.py

@@ -1,125 +0,0 @@
-from __future__ import with_statement
-__license__   = 'GPL v3'
-__copyright__ = '2008, Anatoly Shipitsin <norguhtar at gmail.com>'
-"""
-Convert .fb2 files to .lrf
-"""
-import os, sys, shutil, logging
-from base64 import b64decode
-from lxml import etree
-    
-from calibre.ebooks.lrf import option_parser as lrf_option_parser
-from calibre.ebooks.metadata.meta import get_metadata
-from calibre.ebooks.lrf.html.convert_from import process_file as html_process_file
-from calibre import setup_cli_handlers
-from calibre.resources import fb2_xsl
-from calibre.ptempfile import PersistentTemporaryDirectory
-from calibre.ebooks.metadata.opf import OPFCreator
-from calibre.ebooks.metadata import MetaInformation
-
-
-def option_parser():
-    parser = lrf_option_parser(
-_('''%prog [options] mybook.fb2
-
-
-%prog converts mybook.fb2 to mybook.lrf'''))
-    parser.add_option('--debug-html-generation', action='store_true', default=False,
-                      dest='debug_html_generation', help=_('Print generated HTML to stdout and quit.'))
-    parser.add_option('--keep-intermediate-files', action='store_true', default=False,
-                      help=_('Keep generated HTML files after completing conversion to LRF.'))
-    return parser
-    
-def extract_embedded_content(doc):
-    for elem in doc.xpath('./*'):
-        if 'binary' in elem.tag and elem.attrib.has_key('id'):
-            fname = elem.attrib['id']
-            data = b64decode(elem.text.strip())
-            open(fname, 'wb').write(data)
-
-def to_html(fb2file, tdir):
-    fb2file = os.path.abspath(fb2file)
-    cwd = os.getcwd()
-    try:
-        os.chdir(tdir)
-        print 'Parsing XML...'
-        parser = etree.XMLParser(recover=True, no_network=True)
-        doc = etree.parse(fb2file, parser)
-        extract_embedded_content(doc)
-        print 'Converting XML to HTML...'
-        styledoc = etree.fromstring(fb2_xsl)
-    
-        transform = etree.XSLT(styledoc)
-        result = transform(doc)
-        open('index.html', 'wb').write(transform.tostring(result))
-        try:
-            mi = get_metadata(open(fb2file, 'rb'), 'fb2')
-        except:
-            mi = MetaInformation(None, None)
-        if not mi.title:
-            mi.title = os.path.splitext(os.path.basename(fb2file))[0]
-        if not mi.authors:
-            mi.authors = [_('Unknown')]
-        opf = OPFCreator(tdir, mi)
-        opf.create_manifest([('index.html', None)])
-        opf.create_spine(['index.html'])
-        opf.render(open('metadata.opf', 'wb'))
-        return os.path.join(tdir, 'metadata.opf')
-    finally:
-        os.chdir(cwd)
-
-    
-def generate_html(fb2file, encoding, logger):
-    tdir = PersistentTemporaryDirectory('_fb22lrf')
-    to_html(fb2file, tdir)
-    return os.path.join(tdir, 'index.html')
-    
-def process_file(path, options, logger=None):
-    if logger is None:
-        level = logging.DEBUG if options.verbose else logging.INFO
-        logger = logging.getLogger('fb22lrf')
-        setup_cli_handlers(logger, level)
-    fb2 = os.path.abspath(os.path.expanduser(path))
-    f = open(fb2, 'rb')
-    mi = get_metadata(f, 'fb2')
-    f.close()
-    htmlfile = generate_html(fb2, options.encoding, logger)
-    tdir = os.path.dirname(htmlfile)
-    cwd = os.getcwdu()
-    try:
-        if not options.output:
-            ext = '.lrs' if options.lrs else '.lrf'
-            options.output = os.path.abspath(os.path.basename(os.path.splitext(path)[0]) + ext)
-        options.output = os.path.abspath(os.path.expanduser(options.output))
-        if not mi.title:
-            mi.title = os.path.splitext(os.path.basename(fb2))[0]
-        if (not options.title or options.title == _('Unknown')):
-            options.title = mi.title
-        if (not options.author or options.author == _('Unknown')) and mi.authors:
-            options.author = mi.authors.pop()
-        if (not options.category or options.category == _('Unknown')) and mi.category:
-            options.category = mi.category
-        if (not options.freetext or options.freetext == _('Unknown')) and mi.comments:
-            options.freetext = mi.comments
-        os.chdir(tdir)
-        html_process_file(htmlfile, options, logger)
-    finally:
-        os.chdir(cwd)
-        if getattr(options, 'keep_intermediate_files', False):
-            logger.debug('Intermediate files in '+ tdir)
-        else:
-            shutil.rmtree(tdir)
-
-def main(args=sys.argv, logger=None):
-    parser = option_parser()    
-    options, args = parser.parse_args(args)
-    if len(args) != 2:
-        parser.print_help()
-        print
-        print 'No fb2 file specified'
-        return 1
-    process_file(args[1], options, logger)
-    return 0
-
-if __name__ == '__main__':
-    sys.exit(main())

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

@@ -1,190 +0,0 @@
-__license__   = 'GPL v3'
-__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
-import os, sys, shutil, logging, glob
-
-from lxml import etree
-
-from calibre.ebooks.lrf import option_parser as lrf_option_parser
-from calibre.ebooks.metadata.meta import get_metadata
-from calibre.ebooks.lrf.html.convert_from import process_file as html_process_file
-from calibre import setup_cli_handlers
-from calibre.libwand import convert, WandException
-from calibre.ebooks.BeautifulSoup import BeautifulStoneSoup
-from calibre.ebooks.lrf.rtf.xsl import xhtml
-from calibre.ebooks.rtf2xml.ParseRtf import RtfInvalidCodeException
-from calibre.ptempfile import PersistentTemporaryDirectory
-from calibre.ebooks.metadata import MetaInformation
-from calibre.ebooks.metadata.opf import OPFCreator 
-
-def option_parser():
-    parser = lrf_option_parser(
-_('''%prog [options] mybook.rtf
-
-
-%prog converts mybook.rtf to mybook.lrf''')
-        )
-    parser.add_option('--keep-intermediate-files', action='store_true', default=False)
-    return parser
-
-def convert_images(html, logger):
-    wmfs = glob.glob('*.wmf') + glob.glob('*.WMF')
-    for wmf in wmfs:
-        target = os.path.join(os.path.dirname(wmf), os.path.splitext(os.path.basename(wmf))[0]+'.jpg')
-        try:
-            convert(wmf, target)
-            html = html.replace(os.path.basename(wmf), os.path.basename(target))
-        except WandException, err:
-            logger.warning(u'Unable to convert image %s with error: %s'%(wmf, unicode(err)))
-            continue
-    return html
-
-def process_file(path, options, logger=None):
-    if logger is None:
-        level = logging.DEBUG if options.verbose else logging.INFO
-        logger = logging.getLogger('rtf2lrf')
-        setup_cli_handlers(logger, level)
-    rtf = os.path.abspath(os.path.expanduser(path))
-    f = open(rtf, 'rb')
-    mi = get_metadata(f, 'rtf')
-    f.close()
-    tdir = PersistentTemporaryDirectory('_rtf2lrf')
-    html = generate_html(rtf, tdir)
-    cwd = os.getcwdu()
-    try:
-        if not options.output:
-            ext = '.lrs' if options.lrs else '.lrf'
-            options.output = os.path.abspath(os.path.basename(os.path.splitext(path)[0]) + ext)
-        options.output = os.path.abspath(os.path.expanduser(options.output))
-        if not mi.title:
-            mi.title = os.path.splitext(os.path.basename(rtf))[0]
-        if (not options.title or options.title == 'Unknown'):
-            options.title = mi.title
-        if (not options.author or options.author == 'Unknown') and mi.author:
-            options.author = mi.author
-        if (not options.category or options.category == 'Unknown') and mi.category:
-            options.category = mi.category
-        if (not options.freetext or options.freetext == 'Unknown') and mi.comments:
-            options.freetext = mi.comments
-        os.chdir(tdir)
-        html_process_file(html, options, logger)
-    finally:
-        os.chdir(cwd)
-        if hasattr(options, 'keep_intermediate_files') and options.keep_intermediate_files:
-            logger.debug('Intermediate files in '+ tdir)
-        else:
-            shutil.rmtree(tdir)
-
-def main(args=sys.argv, logger=None):
-    parser = option_parser()
-    options, args = parser.parse_args(args)
-    if len(args) != 2:
-        parser.print_help()
-        print
-        print 'No rtf file specified'
-        return 1
-    process_file(args[1], options, logger)
-    return 0
-    
-
-def generate_xml(rtfpath, tdir):
-    from calibre.ebooks.rtf2xml.ParseRtf import ParseRtf
-    ofile = os.path.join(tdir, 'index.xml')
-    cwd = os.getcwdu()
-    os.chdir(tdir)
-    rtfpath = os.path.abspath(rtfpath)
-    try:
-        parser = ParseRtf(
-            in_file    = rtfpath,
-            out_file   = ofile,
-            # Convert symbol fonts to unicode equivelents. Default
-            # is 1
-            convert_symbol = 1,
-    
-            # Convert Zapf fonts to unicode equivelents. Default
-            # is 1.
-            convert_zapf = 1,
-    
-            # Convert Wingding fonts to unicode equivelents.
-            # Default is 1.
-            convert_wingdings = 1,
-    
-            # Convert RTF caps to real caps.
-            # Default is 1.
-            convert_caps = 1,
-    
-            # Indent resulting XML.
-            # Default is 0 (no indent).
-            indent = 1,
-    
-            # Form lists from RTF. Default is 1.
-            form_lists = 1,
-    
-            # Convert headings to sections. Default is 0.
-            headings_to_sections = 1,
-    
-            # Group paragraphs with the same style name. Default is 1.
-            group_styles = 1,
-    
-            # Group borders. Default is 1.
-            group_borders = 1,
-    
-            # Write or do not write paragraphs. Default is 0.
-            empty_paragraphs = 0,
-        )
-        parser.parse_rtf()
-    finally:
-        os.chdir(cwd)
-    return ofile
-
-
-def generate_html(rtfpath, tdir):
-    print 'Converting RTF to XML...'
-    rtfpath = os.path.abspath(rtfpath)
-    try:
-        xml = generate_xml(rtfpath, tdir)
-    except RtfInvalidCodeException:
-        raise Exception(_('This RTF file has a feature calibre does not support. Convert it to HTML and then convert it.'))
-    tdir = os.path.dirname(xml)
-    cwd = os.getcwdu()
-    os.chdir(tdir)
-    try:
-        print 'Parsing XML...'
-        parser = etree.XMLParser(recover=True, no_network=True)
-        try:
-            doc = etree.parse(xml, parser)
-        except:
-            raise
-            print 'Parsing failed. Trying to clean up XML...'
-            soup = BeautifulStoneSoup(open(xml, 'rb').read())
-            doc = etree.fromstring(str(soup))
-        print 'Converting XML to HTML...'
-        styledoc = etree.fromstring(xhtml)
-        
-        transform = etree.XSLT(styledoc)
-        result = transform(doc)
-        tdir = os.path.dirname(xml)
-        html = os.path.join(tdir, 'index.html')
-        f = open(html, 'wb')
-        res = transform.tostring(result)
-        res = res[:100].replace('xmlns:html', 'xmlns') + res[100:]
-        f.write(res)
-        f.close()
-        try:
-            mi = get_metadata(open(rtfpath, 'rb'), 'rtf')
-        except:
-            mi = MetaInformation(None, None)
-        if not mi.title:
-            mi.title = os.path.splitext(os.path.basename(rtfpath))[0]
-        if not mi.authors:
-            mi.authors = [_('Unknown')]
-        opf = OPFCreator(tdir, mi)
-        opf.create_manifest([('index.html', None)])
-        opf.create_spine(['index.html'])
-        opf.render(open('metadata.opf', 'wb'))
-    finally:
-        os.chdir(cwd)
-    return html
-            
-if __name__ == '__main__':
-    sys.exit(main())    
-        

src/calibre/ebooks/metadata/library_thing.py

@@ -4,13 +4,15 @@ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
 Fetch cover from LibraryThing.com based on ISBN number.
 '''
 
-import sys, socket, os, re, mechanize
+import sys, socket, os, re
 
 from calibre import browser as _browser
 from calibre.utils.config import OptionParser
-from calibre.ebooks.BeautifulSoup import BeautifulSoup 
+from calibre.ebooks.BeautifulSoup import BeautifulSoup
 browser = None
 
+OPENLIBRARY = 'http://covers.openlibrary.org/b/isbn/%s-L.jpg?default=false'
+
 class LibraryThingError(Exception):
     pass
 
@@ -30,15 +32,21 @@ def login(username, password, force=True):
     browser['formusername'] = username
     browser['formpassword'] = password
     browser.submit()
-    
 
-def cover_from_isbn(isbn, timeout=5.):
+
+def cover_from_isbn(isbn, timeout=5., username=None, password=None):
     global browser
     if browser is None:
         browser = _browser()
     _timeout = socket.getdefaulttimeout()
     socket.setdefaulttimeout(timeout)
-    src = None                
+    src = None
+    try:
+        return browser.open(OPENLIBRARY%isbn).read(), 'jpg'
+    except:
+        pass # Cover not found
+    if username and password:
+        login(username, password, force=False)
     try:
         src = browser.open('http://www.librarything.com/isbn/'+isbn).read().decode('utf-8', 'replace')
     except Exception, err:
@@ -55,7 +63,7 @@ def cover_from_isbn(isbn, timeout=5.):
         url = url.find('img')
         if url is None:
             raise LibraryThingError(_('LibraryThing.com server error. Try again later.'))
-        url = re.sub(r'_SX\d+', '', url['src'])
+        url = re.sub(r'_S[XY]\d+', '', url['src'])
         cover_data = browser.open(url).read()
         return cover_data, url.rpartition('.')[-1]
     finally:
@@ -68,9 +76,9 @@ _('''
 
 Fetch a cover image for the book identified by ISBN from LibraryThing.com
 '''))
-    parser.add_option('-u', '--username', default=None, 
+    parser.add_option('-u', '--username', default=None,
                       help='Username for LibraryThing.com')
-    parser.add_option('-p', '--password', default=None, 
+    parser.add_option('-p', '--password', default=None,
                       help='Password for LibraryThing.com')
     return parser
 
@@ -81,13 +89,8 @@ def main(args=sys.argv):
         parser.print_help()
         return 1
     isbn = args[1]
-    if opts.username and opts.password:
+    cover_data, ext = cover_from_isbn(isbn, username=opts.username,
-        try:
+            password=opts.password)
-            login(opts.username, opts.password)
-        except mechanize.FormNotFoundError:
-            raise LibraryThingError(_('LibraryThing.com server error. Try again later.'))
-        
-    cover_data, ext = cover_from_isbn(isbn)
     if not ext:
         ext = 'jpg'
     oname = os.path.abspath(isbn+'.'+ext)
@@ -96,4 +99,4 @@ def main(args=sys.argv):
     return 0
 
 if __name__ == '__main__':
-    sys.exit(main())
+    sys.exit(main())

src/calibre/ebooks/odt/input.py

@@ -0,0 +1,67 @@
+from __future__ import with_statement
+__license__   = 'GPL v3'
+__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
+__docformat__ = 'restructuredtext en'
+
+'''
+Convert an ODT file into a Open Ebook
+'''
+import os
+from odf.odf2xhtml import ODF2XHTML
+
+from calibre import CurrentDir, walk
+from calibre.customize.conversion import InputFormatPlugin
+
+class Extract(ODF2XHTML):
+
+    def extract_pictures(self, zf):
+        if not os.path.exists('Pictures'):
+            os.makedirs('Pictures')
+        for name in zf.namelist():
+            if name.startswith('Pictures'):
+                data = zf.read(name)
+                with open(name, 'wb') as f:
+                    f.write(data)
+
+    def __call__(self, stream, odir):
+        from calibre.utils.zipfile import ZipFile
+        from calibre.ebooks.metadata.meta import get_metadata
+        from calibre.ebooks.metadata.opf2 import OPFCreator
+
+
+        if not os.path.exists(odir):
+            os.makedirs(odir)
+        with CurrentDir(odir):
+            print 'Extracting ODT file...'
+            html = self.odf2xhtml(stream)
+            with open('index.xhtml', 'wb') as f:
+                f.write(html.encode('utf-8'))
+            zf = ZipFile(stream, 'r')
+            self.extract_pictures(zf)
+            stream.seek(0)
+            mi = get_metadata(stream, 'odt')
+            if not mi.title:
+                mi.title = _('Unknown')
+            if not mi.authors:
+                mi.authors = [_('Unknown')]
+            opf = OPFCreator(os.path.abspath(os.getcwdu()), mi)
+            opf.create_manifest([(os.path.abspath(f), None) for f in walk(os.getcwd())])
+            opf.create_spine([os.path.abspath('index.xhtml')])
+            with open('metadata.opf', 'wb') as f:
+                opf.render(f)
+            return os.path.abspath('metadata.opf')
+
+
+class ODTInput(InputFormatPlugin):
+
+    name        = 'ODT Input'
+    author      = 'Kovid Goyal'
+    description = 'Convert ODT (OpenOffice) files to HTML'
+    file_types  = set(['odt'])
+
+
+    def convert(self, stream, options, file_ext, log,
+                accelerators):
+        return Extract()(stream, '.')
+
+

src/calibre/ebooks/odt/to_oeb.py

@@ -1,72 +0,0 @@
-from __future__ import with_statement
-__license__   = 'GPL v3'
-__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
-__docformat__ = 'restructuredtext en'
-
-'''
-Convert an ODT file into a Open Ebook
-'''
-import os, sys
-from odf.odf2xhtml import ODF2XHTML
-
-from calibre import CurrentDir, walk
-from calibre.utils.zipfile import ZipFile
-from calibre.utils.config import OptionParser
-from calibre.ebooks.metadata.odt import get_metadata
-from calibre.ebooks.metadata.opf2 import OPFCreator
-
-class Extract(ODF2XHTML):
-    
-    def extract_pictures(self, zf):
-        if not os.path.exists('Pictures'):
-            os.makedirs('Pictures')
-        for name in zf.namelist():
-            if name.startswith('Pictures'):
-                data = zf.read(name)
-                with open(name, 'wb') as f:
-                    f.write(data)
-                
-    def __call__(self, path, odir):
-        if not os.path.exists(odir):
-            os.makedirs(odir)
-        path = os.path.abspath(path)
-        with CurrentDir(odir):
-            print 'Extracting ODT file...'
-            html = self.odf2xhtml(path)
-            with open('index.html', 'wb') as f:
-                f.write(html.encode('utf-8'))
-            with open(path, 'rb') as f:
-                zf = ZipFile(f, 'r')
-                self.extract_pictures(zf)
-                f.seek(0)
-                mi = get_metadata(f)
-                if not mi.title:
-                    mi.title = os.path.splitext(os.path.basename(path))
-                if not mi.authors:
-                    mi.authors = [_('Unknown')]
-            opf = OPFCreator(os.path.abspath(os.getcwdu()), mi)
-            opf.create_manifest([(os.path.abspath(f), None) for f in walk(os.getcwd())])
-            opf.create_spine([os.path.abspath('index.html')])
-            with open('metadata.opf', 'wb') as f:
-                opf.render(f)
-            return os.path.abspath('metadata.opf')
-            
-def option_parser():
-    parser = OptionParser('%prog [options] file.odt')
-    parser.add_option('-o', '--output-dir', default='.', 
-                      help=_('The output directory. Defaults to the current directory.'))
-    return parser
-
-def main(args=sys.argv):
-    parser = option_parser()
-    opts, args = parser.parse_args(args)
-    if len(args) < 2:
-        parser.print_help()
-        print 'No ODT file specified'
-        return 1
-    Extract()(args[1], os.path.abspath(opts.output_dir))
-    print 'Extracted to', os.path.abspath(opts.output_dir)
-    return 0
-
-if __name__ == '__main__':
-    sys.exit(main())

src/calibre/ebooks/oeb/base.py

@@ -41,10 +41,12 @@ NCX_NS       = 'http://www.daisy.org/z3986/2005/ncx/'
 SVG_NS       = 'http://www.w3.org/2000/svg'
 XLINK_NS     = 'http://www.w3.org/1999/xlink'
 CALIBRE_NS   = 'http://calibre.kovidgoyal.net/2009/metadata'
+RE_NS        = 'http://exslt.org/regular-expressions'
+
 XPNSMAP      = {'h'  : XHTML_NS, 'o1' : OPF1_NS,    'o2' : OPF2_NS,
                 'd09': DC09_NS,  'd10': DC10_NS,    'd11': DC11_NS,
                 'xsi': XSI_NS,   'dt' : DCTERMS_NS, 'ncx': NCX_NS,
-                'svg': SVG_NS,   'xl' : XLINK_NS}
+                'svg': SVG_NS,   'xl' : XLINK_NS,   're': RE_NS}
 OPF1_NSMAP   = {'dc': DC11_NS, 'oebpackage': OPF1_NS}
 OPF2_NSMAP   = {'opf': OPF2_NS, 'dc': DC11_NS, 'dcterms': DCTERMS_NS,
                 'xsi': XSI_NS, 'calibre': CALIBRE_NS}
@@ -1024,7 +1026,7 @@ class Manifest(object):
                 media_type = XHTML_MIME
             elif media_type in OEB_STYLES:
                 media_type = CSS_MIME
-            attrib = {'id': item.id, 'href': item.href,
+            attrib = {'id': item.id, 'href': urlunquote(item.href),
                       'media-type': media_type}
             if item.fallback:
                 attrib['fallback'] = item.fallback
@@ -1236,7 +1238,7 @@ class Guide(object):
     def to_opf2(self, parent=None):
         elem = element(parent, OPF('guide'))
         for ref in self.refs.values():
-            attrib = {'type': ref.type, 'href': ref.href}
+            attrib = {'type': ref.type, 'href': urlunquote(ref.href)}
             if ref.title:
                 attrib['title'] = ref.title
             element(elem, OPF('reference'), attrib=attrib)
@@ -1256,19 +1258,34 @@ class TOC(object):
     :attr:`klass`: Optional semantic class referenced by this node.
     :attr:`id`: Option unique identifier for this node.
     """
-    def __init__(self, title=None, href=None, klass=None, id=None):
+    def __init__(self, title=None, href=None, klass=None, id=None,
+            play_order=None):
         self.title = title
         self.href = urlnormalize(href) if href else href
         self.klass = klass
         self.id = id
         self.nodes = []
+        self.play_order = 0
+        if play_order is None:
+            play_order = self.next_play_order()
+        self.play_order = play_order
 
-    def add(self, title, href, klass=None, id=None):
+    def add(self, title, href, klass=None, id=None, play_order=0):
         """Create and return a new sub-node of this node."""
-        node = TOC(title, href, klass, id)
+        node = TOC(title, href, klass, id, play_order)
         self.nodes.append(node)
         return node
 
+    def remove(self, node):
+        for child in self.nodes:
+            if child is node:
+                self.nodes.remove(child)
+                return True
+            else:
+                if child.remove(node):
+                    return True
+        return False
+
     def iter(self):
         """Iterate over this node and all descendants in depth-first order."""
         yield self
@@ -1276,6 +1293,18 @@ class TOC(object):
             for node in child.iter():
                 yield node
 
+    def count(self):
+        return len(list(self.iter())) - 1
+
+    def next_play_order(self):
+        return max([x.play_order for x in self.iter()])+1
+
+    def has_href(self, href):
+        for x in self.iter():
+            if x.href == href:
+                return True
+        return False
+
     def iterdescendants(self):
         """Iterate over all descendant nodes in depth-first order."""
         for child in self.nodes:
@@ -1309,6 +1338,10 @@ class TOC(object):
         except ValueError:
             return 1
 
+    def __str__(self):
+        return 'TOC: %s --> %s'%(self.title, self.href)
+
+
     def to_opf1(self, tour):
         for node in self.nodes:
             element(tour, 'site', attrib={
@@ -1319,7 +1352,7 @@ class TOC(object):
     def to_ncx(self, parent):
         for node in self.nodes:
             id = node.id or unicode(uuid.uuid4())
-            attrib = {'id': id, 'playOrder': '0'}
+            attrib = {'id': id, 'playOrder': str(node.play_order)}
             if node.klass:
                 attrib['class'] = node.klass
             point = element(parent, NCX('navPoint'), attrib=attrib)
@@ -1329,6 +1362,34 @@ class TOC(object):
             node.to_ncx(point)
         return parent
 
+    def rationalize_play_orders(self):
+        '''
+        Ensure that all nodes with the same play_order have the same href and
+        with different play_orders have different hrefs.
+        '''
+        def po_node(n):
+            for x in self.iter():
+                if x is n:
+                    return
+                if x.play_order == n.play_order:
+                    return x
+
+        def href_node(n):
+            for x in self.iter():
+                if x is n:
+                    return
+                if x.href == n.href:
+                    return x
+
+        for x in self.iter():
+            y = po_node(x)
+            if y is not None:
+                if x.href != y.href:
+                    x.play_order = getattr(href_node(x), 'play_order',
+                            self.next_play_order())
+            y = href_node(x)
+            if y is not None:
+                x.play_order = y.play_order
 
 class PageList(object):
     """Collection of named "pages" to mapped positions within an OEB data model

src/calibre/ebooks/oeb/iterator.py

@@ -118,6 +118,7 @@ class EbookIterator(object):
                                     print 'Loaded embedded font:', repr(family)
 
     def __enter__(self):
+        self.delete_on_exit = []
         self._tdir = TemporaryDirectory('_ebook_iter')
         self.base  = self._tdir.__enter__()
         from calibre.ebooks.conversion.plumber import Plumber
@@ -137,9 +138,11 @@ class EbookIterator(object):
 
         cover = self.opf.cover
         if self.ebook_ext in ('lit', 'mobi', 'prc', 'opf') and cover:
-            cfile = os.path.join(os.path.dirname(self.spine[0]), 'calibre_ei_cover.html')
+            cfile = os.path.join(os.path.dirname(self.spine[0]),
+                    'calibre_iterator_cover.html')
             open(cfile, 'wb').write(TITLEPAGE%cover)
             self.spine[0:0] = [SpineItem(cfile)]
+            self.delete_on_exit.append(cfile)
 
         if self.opf.path_to_html_toc is not None and \
            self.opf.path_to_html_toc not in self.spine:
@@ -221,3 +224,6 @@ class EbookIterator(object):
 
     def __exit__(self, *args):
         self._tdir.__exit__(*args)
+        for x in self.delete_on_exit:
+            if os.path.exists(x):
+                os.remove(x)

src/calibre/ebooks/oeb/reader.py

@@ -343,7 +343,8 @@ class OEBReader(object):
                 continue
             id = child.get('id')
             klass = child.get('class')
-            node = toc.add(title, href, id=id, klass=klass)
+            po = int(child.get('playOrder', self.oeb.toc.next_play_order()))
+            node = toc.add(title, href, id=id, klass=klass, play_order=po)
             self._toc_from_navpoint(item, node, child)
 
     def _toc_from_ncx(self, item):

src/calibre/ebooks/oeb/stylizer.py

@@ -88,7 +88,7 @@ FONT_SIZE_NAMES = set(['xx-small', 'x-small', 'small', 'medium', 'large',
 class CSSSelector(etree.XPath):
     MIN_SPACE_RE = re.compile(r' *([>~+]) *')
     LOCAL_NAME_RE = re.compile(r"(?<!local-)name[(][)] *= *'[^:]+:")
-    
+
     def __init__(self, css, namespaces=XPNSMAP):
         css = self.MIN_SPACE_RE.sub(r'\1', css)
         path = css_to_xpath(css)
@@ -103,10 +103,10 @@ class CSSSelector(etree.XPath):
             self.css)
 
 
-class Stylizer(object):    
+class Stylizer(object):
     STYLESHEETS = WeakKeyDictionary()
-    
+
-    def __init__(self, tree, path, oeb, profile=PROFILES['PRS505']):
+    def __init__(self, tree, path, oeb, profile=PROFILES['PRS505'], extra_css=''):
         self.oeb = oeb
         self.profile = profile
         self.logger = oeb.logger
@@ -135,6 +135,11 @@ class Stylizer(object):
                         (path, item.href))
                     continue
                 stylesheets.append(sitem.data)
+        if extra_css:
+            text = XHTML_CSS_NAMESPACE + extra_css
+            stylesheet = parser.parseString(text, href=cssname)
+            stylesheet.namespaces['h'] = XHTML_NS
+            stylesheets.append(stylesheet)
         rules = []
         index = 0
         self.stylesheets = set()
@@ -159,7 +164,7 @@ class Stylizer(object):
                 self.style(elem)._update_cssdict(cssdict)
         for elem in xpath(tree, '//h:*[@style]'):
             self.style(elem)._apply_style_attr()
-    
+
     def _fetch_css_file(self, path):
         hrefs = self.oeb.manifest.hrefs
         if path not in hrefs:
@@ -171,7 +176,7 @@ class Stylizer(object):
             return (None, None)
         data = item.data.cssText
         return ('utf-8', data)
-    
+
     def flatten_rule(self, rule, href, index):
         results = []
         if isinstance(rule, CSSStyleRule):
@@ -185,7 +190,7 @@ class Stylizer(object):
             style = self.flatten_style(rule.style)
             self.page_rule.update(style)
         return results
-    
+
     def flatten_style(self, cssstyle):
         style = {}
         for prop in cssstyle:
@@ -202,7 +207,7 @@ class Stylizer(object):
             if size in FONT_SIZE_NAMES:
                 style['font-size'] = "%dpt" % self.profile.fnames[size]
         return style
-    
+
     def _normalize_edge(self, cssvalue, name):
         style = {}
         if isinstance(cssvalue, CSSValueList):
@@ -224,7 +229,7 @@ class Stylizer(object):
         for edge, value in itertools.izip(edges, values):
             style["%s-%s" % (name, edge)] = value
         return style
-        
+
     def _normalize_font(self, cssvalue):
         composition = ('font-style', 'font-variant', 'font-weight',
                        'font-size', 'line-height', 'font-family')
@@ -271,7 +276,7 @@ class Stylizer(object):
 
 class Style(object):
     UNIT_RE = re.compile(r'^(-*[0-9]*[.]?[0-9]*)\s*(%|em|px|mm|cm|in|pt|pc)$')
-    
+
     def __init__(self, element, stylizer):
         self._element = element
         self._profile = stylizer.profile
@@ -285,7 +290,7 @@ class Style(object):
 
     def _update_cssdict(self, cssdict):
         self._style.update(cssdict)
-    
+
     def _apply_style_attr(self):
         attrib = self._element.attrib
         if 'style' not in attrib:
@@ -297,7 +302,7 @@ class Style(object):
         except CSSSyntaxError:
             return
         self._style.update(self._stylizer.flatten_style(style))
-    
+
     def _has_parent(self):
         return (self._element.getparent() is not None)
 
@@ -346,7 +351,7 @@ class Style(object):
             elif unit == 'in':
                 result = value * 72.0
             elif unit == 'pt':
-                result = value 
+                result = value
             elif unit == 'em':
                 font = font or self.fontSize
                 result = value * font
@@ -421,7 +426,7 @@ class Style(object):
                 result = self._unit_convert(width, base=base)
             self._width = result
         return self._width
-    
+
     @property
     def height(self):
         if self._height is None:
@@ -463,27 +468,27 @@ class Style(object):
                 result = 1.2 * self.fontSize
             self._lineHeight = result
         return self._lineHeight
-    
+
     @property
     def marginTop(self):
         return self._unit_convert(
             self._get('margin-top'), base=self.height)
-    
+
     @property
     def marginBottom(self):
         return self._unit_convert(
             self._get('margin-bottom'), base=self.height)
-    
+
     @property
     def paddingTop(self):
         return self._unit_convert(
             self._get('padding-top'), base=self.height)
-    
+
     @property
     def paddingBottom(self):
         return self._unit_convert(
             self._get('padding-bottom'), base=self.height)
-    
+
     def __str__(self):
         items = self._style.items()
         items.sort()

src/calibre/ebooks/oeb/transforms/flatcss.py

@@ -116,7 +116,8 @@ class CSSFlattener(object):
         profile = self.context.source
         for item in self.oeb.spine:
             html = item.data
-            stylizer = Stylizer(html, item.href, self.oeb, profile)
+            stylizer = Stylizer(html, item.href, self.oeb, profile,
+                    extra_css=self.context.extra_css)
             self.stylizers[item] = stylizer
 
     def baseline_node(self, node, stylizer, sizes, csize):

src/calibre/ebooks/oeb/transforms/split.py

@@ -15,12 +15,10 @@ from lxml.etree import XPath as _XPath
 from lxml import etree
 from lxml.cssselect import CSSSelector
 
-from calibre.ebooks.oeb.base import OEB_STYLES, XPNSMAP, urldefrag, \
+from calibre.ebooks.oeb.base import OEB_STYLES, XPNSMAP as NAMESPACES, \
-                rewrite_links
+        urldefrag, rewrite_links
 from calibre.ebooks.epub import tostring, rules
 
-NAMESPACES = dict(XPNSMAP)
-NAMESPACES['re'] = 'http://exslt.org/regular-expressions'
 
 XPath = functools.partial(_XPath, namespaces=NAMESPACES)
 
@@ -104,7 +102,10 @@ class Split(object):
                     page_breaks.add(elem)
 
         for i, elem in enumerate(item.data.iter()):
-            elem.set('pb_order', str(i))
+            try:
+                elem.set('pb_order', str(i))
+            except TypeError: # Cant set attributes on comment nodes etc.
+                continue
 
         page_breaks = list(page_breaks)
         page_breaks.sort(cmp=
@@ -118,7 +119,7 @@ class Split(object):
             page_break_ids.append(id)
 
         for elem in item.data.iter():
-            elem.attrib.pop('pb_order')
+            elem.attrib.pop('pb_order', False)
             if elem.get('pb_before', False):
                 elem.attrib.pop('pb_before')
 

src/calibre/ebooks/oeb/transforms/structure.py

@@ -0,0 +1,159 @@
+#!/usr/bin/env python
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import with_statement
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
+__docformat__ = 'restructuredtext en'
+
+import re
+
+from lxml import etree
+from urlparse import urlparse
+
+from calibre.ebooks.oeb.base import XPNSMAP, TOC
+XPath = lambda x: etree.XPath(x, namespaces=XPNSMAP)
+
+class DetectStructure(object):
+
+    def __call__(self, oeb, opts):
+        self.log = oeb.log
+        self.oeb = oeb
+        self.opts = opts
+        self.log('Detecting structure...')
+
+        self.detect_chapters()
+        if self.oeb.auto_generated_toc or opts.use_auto_toc:
+            orig_toc = self.oeb.toc
+            self.oeb.toc = TOC()
+            self.create_level_based_toc()
+            if self.oeb.toc.count() < 1:
+                if not opts.no_chapters_in_toc and self.detected_chapters:
+                    self.create_toc_from_chapters()
+                    if self.oeb.toc.count() < opts.toc_threshold:
+                        self.create_toc_from_links()
+            if self.oeb.toc.count() < 2 and orig_toc.count() > 2:
+                self.oeb.toc = orig_toc
+            else:
+                self.oeb.auto_generated_toc = True
+                self.log('Auto generated TOC with %d entries.' %
+                        self.oeb.toc.count())
+
+        if opts.toc_filter is not None:
+            regexp = re.compile(opts.toc_filter)
+            for node in self.oeb.toc.iter():
+                if not node.title or regexp.search(node.title) is not None:
+                    self.oeb.toc.remove(node)
+
+
+    def detect_chapters(self):
+        self.detected_chapters = []
+        if self.opts.chapter:
+            chapter_xpath = XPath(self.opts.chapter)
+            for item in self.oeb.spine:
+                for x in chapter_xpath(item.data):
+                    self.detected_chapters.append((item, x))
+
+            chapter_mark = self.opts.chapter_mark
+            page_break_before = 'display: block; page-break-before: always'
+            page_break_after = 'display: block; page-break-after: always'
+            for item, elem in self.detected_chapters:
+                text = u' '.join([t.strip() for t in elem.xpath('descendant::text()')])
+                self.log('\tDetected chapter:', text[:50])
+                if chapter_mark == 'none':
+                    continue
+                elif chapter_mark == 'rule':
+                    mark = etree.Element('hr')
+                elif chapter_mark == 'pagebreak':
+                    mark = etree.Element('div', style=page_break_after)
+                else: # chapter_mark == 'both':
+                    mark = etree.Element('hr', style=page_break_before)
+                elem.addprevious(mark)
+
+    def create_level_based_toc(self):
+        if self.opts.level1_toc is None:
+            return
+        for item in self.oeb.spine:
+            self.add_leveled_toc_items(item)
+
+    def create_toc_from_chapters(self):
+        counter = self.oeb.toc.next_play_order()
+        for item, elem in self.detected_chapters:
+            text, href = self.elem_to_link(item, elem, counter)
+            self.oeb.toc.add(text, href, play_order=counter)
+            counter += 1
+
+    def create_toc_from_links(self):
+        for item in self.oeb.spine:
+            for a in item.data.xpath('//h:a[@href]'):
+                href = a.get('href')
+                purl = urlparse(href)
+                if not purl[0] or purl[0] == 'file':
+                    href, frag = purl.path, purl.fragment
+                    href = item.abshref(href)
+                    if frag:
+                        href = '#'.join((href, frag))
+                    if not self.oeb.toc.has_href(href):
+                        text = u' '.join([t.strip() for t in \
+                                a.xpath('descendant::text()')])
+                        text = text[:100].strip()
+                        if not self.oeb.toc.has_text(text):
+                            self.oeb.toc.add(text, href,
+                                play_order=self.oeb.toc.next_play_order())
+
+
+    def elem_to_link(self, item, elem, counter):
+        text = u' '.join([t.strip() for t in elem.xpath('descendant::text()')])
+        text = text[:100].strip()
+        id = elem.get('id', 'calibre_toc_%d'%counter)
+        elem.set('id', id)
+        href = '#'.join((item.href, id))
+        return text, href
+
+
+    def add_leveled_toc_items(self, item):
+        level1 = XPath(self.opts.level1_toc)(item.data)
+        level1_order = []
+
+        counter = 1
+        if level1:
+            added = {}
+            for elem in level1:
+                text, _href = self.elem_to_link(item, elem, counter)
+                counter += 1
+                if text:
+                    node = self.oeb.toc.add(text, _href,
+                            play_order=self.oeb.toc.next_play_order())
+                    level1_order.append(node)
+                    added[elem] = node
+                    #node.add(_('Top'), _href)
+            if self.opts.level2_toc is not None:
+                added2 = {}
+                level2 = list(XPath(self.opts.level2_toc)(item.data))
+                for elem in level2:
+                    level1 = None
+                    for item in item.data.iterdescendants():
+                        if item in added.keys():
+                            level1 = added[item]
+                        elif item == elem and level1 is not None:
+                            text, _href = self.elem_to_link(item, elem, counter)
+                            counter += 1
+                            if text:
+                                added2[elem] = level1.add(text, _href,
+                                    play_order=self.oeb.toc.next_play_order())
+                if self.opts.level3_toc is not None:
+                    level3 = list(XPath(self.opts.level3_toc)(item.data))
+                    for elem in level3:
+                        level2 = None
+                        for item in item.data.iterdescendants():
+                            if item in added2.keys():
+                                level2 = added2[item]
+                            elif item == elem and level2 is not None:
+                                text, _href = \
+                                        self.elem_to_link(item, elem, counter)
+                                counter += 1
+                                if text:
+                                    level2.add(text, _href,
+                                    play_order=self.oeb.toc.next_play_order())
+
+

src/calibre/ebooks/rtf/input.py

@@ -0,0 +1,101 @@
+from __future__ import with_statement
+__license__   = 'GPL v3'
+__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
+
+import os
+
+from lxml import etree
+
+from calibre.customize.conversion import InputFormatPlugin
+
+class RTFInput(InputFormatPlugin):
+
+    name        = 'RTF Input'
+    author      = 'Kovid Goyal'
+    description = 'Convert RTF files to HTML'
+    file_types  = set(['rtf'])
+
+    def generate_xml(self, stream):
+        from calibre.ebooks.rtf2xml.ParseRtf import ParseRtf
+        ofile = 'out.xml'
+        parser = ParseRtf(
+            in_file    = stream,
+            out_file   = ofile,
+            # Convert symbol fonts to unicode equivelents. Default
+            # is 1
+            convert_symbol = 1,
+
+            # Convert Zapf fonts to unicode equivelents. Default
+            # is 1.
+            convert_zapf = 1,
+
+            # Convert Wingding fonts to unicode equivelents.
+            # Default is 1.
+            convert_wingdings = 1,
+
+            # Convert RTF caps to real caps.
+            # Default is 1.
+            convert_caps = 1,
+
+            # Indent resulting XML.
+            # Default is 0 (no indent).
+            indent = 1,
+
+            # Form lists from RTF. Default is 1.
+            form_lists = 1,
+
+            # Convert headings to sections. Default is 0.
+            headings_to_sections = 1,
+
+            # Group paragraphs with the same style name. Default is 1.
+            group_styles = 1,
+
+            # Group borders. Default is 1.
+            group_borders = 1,
+
+            # Write or do not write paragraphs. Default is 0.
+            empty_paragraphs = 0,
+        )
+        parser.parse_rtf()
+        ans = open('out.xml').read()
+        os.remove('out.xml')
+        return ans
+
+    def convert(self, stream, options, file_ext, log,
+                accelerators):
+        from calibre.ebooks.rtf.xsl import xhtml
+        from calibre.ebooks.metadata.meta import get_metadata
+        from calibre.ebooks.metadata.opf import OPFCreator
+        from calibre.ebooks.rtf2xml.ParseRtf import RtfInvalidCodeException
+        self.log = log
+        self.log('Converting RTF to XML...')
+        try:
+            xml = self.generate_xml(stream)
+        except RtfInvalidCodeException:
+            raise ValueError(_('This RTF file has a feature calibre does not '
+            'support. Convert it to HTML first and then try it.'))
+        self.log('Parsing XML...')
+        parser = etree.XMLParser(recover=True, no_network=True)
+        doc = etree.fromstring(xml, parser=parser)
+        self.log('Converting XML to HTML...')
+        styledoc = etree.fromstring(xhtml)
+
+        transform = etree.XSLT(styledoc)
+        result = transform(doc)
+        html = 'index.xhtml'
+        with open(html, 'wb') as f:
+            res = transform.tostring(result)
+            res = res[:100].replace('xmlns:html', 'xmlns') + res[100:]
+            f.write(res)
+        stream.seek(0)
+        mi = get_metadata(stream, 'rtf')
+        if not mi.title:
+            mi.title = _('Unknown')
+        if not mi.authors:
+            mi.authors = [_('Unknown')]
+        opf = OPFCreator(os.getcwd(), mi)
+        opf.create_manifest([('index.xhtml', None)])
+        opf.create_spine(['index.xhtml'])
+        opf.render(open('metadata.opf', 'wb'))
+        return os.path.abspath('metadata.opf')
+

src/calibre/ebooks/rtf2xml/ParseRtf.py

@@ -149,9 +149,10 @@ class ParseRtf:
         self.__group_borders = group_borders
         self.__empty_paragraphs = empty_paragraphs
         self.__no_dtd = no_dtd
-        
+
     def __check_file(self, the_file, type):
         """Check to see if files exist"""
+        if hasattr(the_file, 'read'): return
         if the_file == None:
             if type == "file_to_parse":
                 message = "You must provide a file for the script to work"
@@ -545,13 +546,12 @@ class ParseRtf:
     def __make_temp_file(self,file):
         """Make a temporary file to parse"""
         write_file="rtf_write_file"
-        read_obj = open(file,'r')
+        read_obj = file if hasattr(file, 'read') else 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()
         return write_file
     """

src/calibre/ebooks/rtf2xml/pict.py

@@ -58,10 +58,12 @@ class Pict:
         return line[18:]
     def __make_dir(self):
         """ Make a dirctory to put the image data in"""
-        base_name = os.path.basename(self.__orig_file)
+        base_name = os.path.basename(getattr(self.__orig_file, 'name',
+            self.__orig_file))
         base_name = os.path.splitext(base_name)[0]
         if self.__out_file:
-            dir_name = os.path.dirname(self.__out_file)
+            dir_name = os.path.dirname(getattr(self.__out_file, 'name',
+                self.__out_file))
         else:
             dir_name = os.path.dirname(self.__orig_file)
         # self.__output_to_file_func()

src/calibre/gui2/dialogs/metadata_single.py

@@ -16,16 +16,14 @@ from calibre.gui2 import qstring_to_unicode, error_dialog, file_icon_provider, \
 from calibre.gui2.dialogs.metadata_single_ui import Ui_MetadataSingleDialog
 from calibre.gui2.dialogs.fetch_metadata import FetchMetadata
 from calibre.gui2.dialogs.tag_editor import TagEditor
-from calibre.gui2.dialogs.password import PasswordDialog
 from calibre.gui2.widgets import ProgressIndicator
 from calibre.ebooks import BOOK_EXTENSIONS
 from calibre.ebooks.metadata import authors_to_sort_string, string_to_authors, authors_to_string
-from calibre.ebooks.metadata.library_thing import login, cover_from_isbn
+from calibre.ebooks.metadata.library_thing import cover_from_isbn
 from calibre import islinux
 from calibre.ebooks.metadata.meta import get_metadata
 from calibre.utils.config import prefs
 from calibre.customize.ui import run_plugins_on_import
-from calibre.gui2 import config as gui_conf
 
 class CoverFetcher(QThread):
 
@@ -60,9 +58,8 @@ class CoverFetcher(QThread):
                     return
                 self.isbn = results[0]
 
-            if self.username and self.password:
+            self.cover_data = cover_from_isbn(self.isbn, timeout=self.timeout,
-                login(self.username, self.password, force=False)
+                    username=self.username, password=self.password)[0]
-            self.cover_data = cover_from_isbn(self.isbn, timeout=self.timeout)[0]
         except Exception, e:
             self.exception = e
             self.traceback = traceback.format_exc()
@@ -290,7 +287,6 @@ class MetadataSingleDialog(ResizableDialog, Ui_MetadataSingleDialog):
         self.series_index.setValue(self.db.series_index(row))
         QObject.connect(self.series, SIGNAL('currentIndexChanged(int)'), self.enable_series_index)
         QObject.connect(self.series, SIGNAL('editTextChanged(QString)'), self.enable_series_index)
-        QObject.connect(self.password_button, SIGNAL('clicked()'), self.change_password)
 
         self.show()
         height_of_rest = self.frameGeometry().height() - self.cover.height()
@@ -363,30 +359,12 @@ class MetadataSingleDialog(ResizableDialog, Ui_MetadataSingleDialog):
             tag_string = ', '.join(d.tags)
             self.tags.setText(tag_string)
 
-    def lt_password_dialog(self):
-        return PasswordDialog(self, 'LibraryThing account',
-                 _('<p>Enter your username and password for '
-                   '<b>LibraryThing.com</b>. This is <b>optional</b>. It will '
-                   'make fetching of covers faster and more reliable.<br/>If '
-                   'you do not have an account, you can '
-                   '<a href=\'http://www.librarything.com\'>register</a> for '
-                   'free.</p>'))
-
-    def change_password(self):
-        d = self.lt_password_dialog()
-        d.exec_()
-
     def fetch_cover(self):
         isbn   = unicode(self.isbn.text()).strip()
-        d = self.lt_password_dialog()
-        if not gui_conf['asked_library_thing_password'] and \
-                (not d.username() or not d.password()):
-            d.exec_()
-            gui_conf['asked_library_thing_password'] = True
         self.fetch_cover_button.setEnabled(False)
         self.setCursor(Qt.WaitCursor)
         title, author = map(unicode, (self.title.text(), self.authors.text()))
-        self.cover_fetcher = CoverFetcher(d.username(), d.password(), isbn,
+        self.cover_fetcher = CoverFetcher(None, None, isbn,
                                             self.timeout, title, author)
         self.cover_fetcher.start()
         self._hangcheck = QTimer(self)

src/calibre/gui2/dialogs/metadata_single.ui

@@ -589,17 +589,7 @@
                    <item>
                     <widget class="QPushButton" name="fetch_cover_button">
                      <property name="text">
-                      <string>Fetch &amp;cover image from server</string>
+                      <string>Download &amp;cover</string>
-                     </property>
-                    </widget>
-                   </item>
-                   <item>
-                    <widget class="QPushButton" name="password_button">
-                     <property name="toolTip">
-                      <string>Change the username and/or password for your account at LibraryThing.com</string>
-                     </property>
-                     <property name="text">
-                      <string>Change &amp;password</string>
                      </property>
                     </widget>
                    </item>
@@ -655,7 +645,6 @@
   <tabstop>comments</tabstop>
   <tabstop>fetch_metadata_button</tabstop>
   <tabstop>fetch_cover_button</tabstop>
-  <tabstop>password_button</tabstop>
   <tabstop>formats</tabstop>
   <tabstop>add_format_button</tabstop>
   <tabstop>remove_format_button</tabstop>

src/calibre/linux.py

@@ -27,10 +27,6 @@ entry_points = {
              'lrs2lrf            = calibre.ebooks.lrf.lrs.convert_from:main',
              'isbndb             = calibre.ebooks.metadata.isbndb:main',
              'librarything       = calibre.ebooks.metadata.library_thing:main',
-             'comic2lrf          = calibre.ebooks.lrf.comic.convert_from:main',
-             'comic2epub         = calibre.ebooks.epub.from_comic:main',
-             'comic2mobi         = calibre.ebooks.mobi.from_comic:main',
-             'comic2pdf          = calibre.ebooks.pdf.from_comic:main',
              'calibre-debug      = calibre.debug:main',
              'calibredb          = calibre.library.cli:main',
              'calibre-fontconfig = calibre.utils.fontconfig:main',
@@ -151,8 +147,6 @@ def setup_completion(fatal_errors):
         from calibre.ebooks.lrf.pdf.reflow import option_parser as pdfhtmlop
         from calibre.web.feeds.main import option_parser as feeds2disk
         from calibre.web.feeds.recipes import titles as feed_titles
-        from calibre.ebooks.lrf.comic.convert_from import option_parser as comicop
-        from calibre.ebooks.epub.from_comic import option_parser as comic2epub
         from calibre.ebooks.metadata.fetch import option_parser as fem_op
         from calibre.gui2.main import option_parser as guiop
         from calibre.utils.smtp import option_parser as smtp_op
@@ -181,10 +175,6 @@ def setup_completion(fatal_errors):
         f.write(opts_and_exts('ebook-meta', metaop, list(meta_filetypes())))
         f.write(opts_and_exts('lrfviewer', lrfviewerop, ['lrf']))
         f.write(opts_and_exts('pdfrelow', pdfhtmlop, ['pdf']))
-        f.write(opts_and_exts('comic2lrf', comicop, ['cbz', 'cbr']))
-        f.write(opts_and_exts('comic2epub', comic2epub, ['cbz', 'cbr']))
-        f.write(opts_and_exts('comic2mobi', comic2epub, ['cbz', 'cbr']))
-        f.write(opts_and_exts('comic2pdf', comic2epub, ['cbz', 'cbr']))
         f.write(opts_and_words('feeds2disk', feeds2disk, feed_titles))
         f.write(opts_and_words('fetch-ebook-metadata', fem_op, []))
         f.write(opts_and_words('calibre-smtp', smtp_op, []))

src/calibre/web/feeds/news.py

@@ -266,7 +266,7 @@ class BasicNewsRecipe(object):
 
     def get_feeds(self):
         '''
-        Return a list of :term:RSS feeds to fetch for this profile. Each element of the list
+        Return a list of :term:`RSS` feeds to fetch for this profile. Each element of the list
         must be a 2-element tuple of the form (title, url). If title is None or an
         empty string, the title from the feed is used. This method is useful if your recipe
         needs to do some processing to figure out the list of feeds to download. If

src/odf/attrconverters.py

@@ -182,11 +182,6 @@ def cnv_points(attribute, arg, element):
             raise ValueError, "Points must be string or [(0,0),(1,1)] - not %s" % arg
         return strarg
 
-def cnv_position(attribute, arg, element):
-    if element == (STYLENS,u'tab-stop'):
-       return cnv_length(attribute, arg, element)
-    return cnv_string(attribute, arg, element)
-
 def cnv_positiveInteger(attribute, arg, element):
     return str(arg)
 
@@ -253,7 +248,7 @@ attrconverters = {
 	((CHARTNS,u'gap-width'), None): cnv_string,
 	((CHARTNS,u'interpolation'), None): cnv_string,
 	((CHARTNS,u'interval-major'), None): cnv_string,
-	((CHARTNS,u'interval-minor'), None): cnv_string,
+	((CHARTNS,u'interval-minor-divisor'), None): cnv_string,
 	((CHARTNS,u'japanese-candle-stick'), None): cnv_boolean,
 	((CHARTNS,u'label-arrangement'), None): cnv_string,
 	((CHARTNS,u'label-cell-address'), None): cnv_string,
@@ -352,6 +347,7 @@ attrconverters = {
 	((DRAWNS,u'caption-line-length'), None): cnv_length,
 	((DRAWNS,u'caption-point-x'), None): cnv_string,
 	((DRAWNS,u'caption-point-y'), None): cnv_string,
+	((DRAWNS,u'caption-id'), None): cnv_IDREF,
 	((DRAWNS,u'caption-type'), None): cnv_string,
 	((DRAWNS,u'chain-next-name'), None): cnv_string,
 	((DRAWNS,u'class-id'), None): cnv_string,
@@ -476,6 +472,7 @@ attrconverters = {
 	((DRAWNS,u'modifiers'), None): cnv_string,
 	((DRAWNS,u'name'), None): cnv_NCName,
 #	((DRAWNS,u'name'), None): cnv_string,
+	((DRAWNS,u'nav-order'), None): cnv_IDREF,
 	((DRAWNS,u'nohref'), None): cnv_string,
 	((DRAWNS,u'notify-on-update-of-ranges'), None): cnv_string,
 	((DRAWNS,u'object'), None): cnv_string,
@@ -683,7 +680,7 @@ attrconverters = {
 	((MANIFESTNS,'initialisation-vector'), None): cnv_string,
 	((MANIFESTNS,'iteration-count'), None): cnv_nonNegativeInteger,
 	((MANIFESTNS,'key-derivation-name'), None): cnv_string,
-	((MANIFESTNS,'manifest:media-type'), None): cnv_string,
+	((MANIFESTNS,'media-type'), None): cnv_string,
 	((MANIFESTNS,'salt'), None): cnv_string,
 	((MANIFESTNS,'size'), None): cnv_nonNegativeInteger,
 	((METANS,u'cell-count'), None): cnv_nonNegativeInteger,
@@ -746,6 +743,7 @@ attrconverters = {
 	((OFFICENS,u'target-frame'), None): cnv_string,
 	((OFFICENS,u'target-frame-name'), None): cnv_string,
 	((OFFICENS,u'time-value'), None): cnv_duration,
+	((OFFICENS,u'title'), None): cnv_string,
 	((OFFICENS,u'value'), None): cnv_double,
 	((OFFICENS,u'value-type'), None): cnv_string,
 	((OFFICENS,u'version'), None): cnv_string,
@@ -783,6 +781,7 @@ attrconverters = {
 	((PRESENTATIONNS,u'preset-id'), None): cnv_string,
 	((PRESENTATIONNS,u'preset-sub-type'), None): cnv_string,
 	((PRESENTATIONNS,u'show'), None): cnv_string,
+	((PRESENTATIONNS,u'show-end-of-presentation-slide'), None): cnv_boolean,
 	((PRESENTATIONNS,u'show-logo'), None): cnv_boolean,
 	((PRESENTATIONNS,u'source'), None): cnv_string,
 	((PRESENTATIONNS,u'speed'), None): cnv_string,
@@ -873,6 +872,8 @@ attrconverters = {
 	((STYLENS,u'flow-with-text'), None): cnv_boolean,
 	((STYLENS,u'font-adornments'), None): cnv_string,
 	((STYLENS,u'font-charset'), None): cnv_string,
+	((STYLENS,u'font-charset-asian'), None): cnv_string,
+	((STYLENS,u'font-charset-complex'), None): cnv_string,
 	((STYLENS,u'font-family-asian'), None): cnv_string,
 	((STYLENS,u'font-family-complex'), None): cnv_string,
 	((STYLENS,u'font-family-generic-asian'), None): cnv_string,
@@ -949,7 +950,8 @@ attrconverters = {
 	((STYLENS,u'page-usage'), None): cnv_string,
 	((STYLENS,u'paper-tray-name'), None): cnv_string,
 	((STYLENS,u'parent-style-name'), None): cnv_StyleNameRef,
-	((STYLENS,u'position'), None): cnv_position,
+	((STYLENS,u'position'), (STYLENS,u'tab-stop')): cnv_length,
+	((STYLENS,u'position'), None): cnv_string,
 	((STYLENS,u'print'), None): cnv_string,
 	((STYLENS,u'print-content'), None): cnv_boolean,
 	((STYLENS,u'print-orientation'), None): cnv_string,
@@ -1015,7 +1017,7 @@ attrconverters = {
 	((STYLENS,u'wrap'), None): cnv_string,
 	((STYLENS,u'wrap-contour'), None): cnv_boolean,
 	((STYLENS,u'wrap-contour-mode'), None): cnv_string,
-	((STYLENS,u'wrap-dynamic-treshold'), None): cnv_string,
+	((STYLENS,u'wrap-dynamic-threshold'), None): cnv_length,
 	((STYLENS,u'writing-mode-automatic'), None): cnv_boolean,
 	((STYLENS,u'writing-mode'), None): cnv_string,
 	((SVGNS,u'accent-height'), None): cnv_integer,
@@ -1122,7 +1124,7 @@ attrconverters = {
 	((TABLENS,u'database-table-name'), None): cnv_string,
 	((TABLENS,u'date-end'), None): cnv_string,
 	((TABLENS,u'date-start'), None): cnv_string,
-	((TABLENS,u'date-value-type'), None): cnv_date,
+	((TABLENS,u'date-value'), None): cnv_date,
 	((TABLENS,u'default-cell-style-name'), None): cnv_StyleNameRef,
 	((TABLENS,u'direction'), None): cnv_string,
 	((TABLENS,u'display-border'), None): cnv_boolean,
@@ -1304,7 +1306,7 @@ attrconverters = {
 	((TEXTNS,u'database-name'), None): cnv_string,
 	((TEXTNS,u'date-adjust'), None): cnv_duration,
 	((TEXTNS,u'date-value'), None): cnv_date,
-	((TEXTNS,u'date-value'), None): cnv_dateTime,
+#	((TEXTNS,u'date-value'), None): cnv_dateTime,
 	((TEXTNS,u'default-style-name'), None): cnv_StyleNameRef,
 	((TEXTNS,u'description'), None): cnv_string,
 	((TEXTNS,u'display'), None): cnv_string,
@@ -1366,6 +1368,7 @@ attrconverters = {
 	((TEXTNS,u'outline-level'), None): cnv_string,
 	((TEXTNS,u'page-adjust'), None): cnv_integer,
 	((TEXTNS,u'pages'), None): cnv_string,
+	((TEXTNS,u'paragraph-style-name'), None): cnv_StyleNameRef,
 	((TEXTNS,u'placeholder-type'), None): cnv_string,
 	((TEXTNS,u'prefix'), None): cnv_string,
 	((TEXTNS,u'protected'), None): cnv_boolean,
@@ -1417,6 +1420,7 @@ attrconverters = {
 	((TEXTNS,u'use-objects'), None): cnv_boolean,
 	((TEXTNS,u'use-other-objects'), None): cnv_boolean,
 	((TEXTNS,u'use-outline-level'), None): cnv_boolean,
+	((TEXTNS,u'use-soft-page-breaks'), None): cnv_boolean,
 	((TEXTNS,u'use-spreadsheet-objects'), None): cnv_boolean,
 	((TEXTNS,u'use-tables'), None): cnv_boolean,
 	((TEXTNS,u'value'), None): cnv_nonNegativeInteger,

src/odf/element.py

@@ -258,10 +258,7 @@ class Element(Node):
         self.ownerDocument = None
         self.childNodes=[]
         self.allowed_children = grammar.allowed_children.get(self.qname)
-        namespace = self.qname[0]
+        prefix = self.get_nsprefix(self.qname[0])
-        prefix = _nsassign(namespace)
-        if not self.namespaces.has_key(namespace):
-            self.namespaces[namespace] = prefix
         self.tagName = prefix + ":" + self.qname[1]
         if text is not None:
             self.addText(text)
@@ -296,6 +293,13 @@ class Element(Node):
                 if self.getAttrNS(r[0],r[1]) is None:
                     raise AttributeError, "Required attribute missing: %s in <%s>" % (r[1].lower().replace('-',''), self.tagName)
 
+    def get_nsprefix(self, namespace):
+        if namespace is None: namespace = ""
+        prefix = _nsassign(namespace)
+        if not self.namespaces.has_key(namespace):
+            self.namespaces[namespace] = prefix
+        return prefix
+
     def allowed_attributes(self):
         return grammar.allowed_attributes.get(self.qname)
 
@@ -378,24 +382,18 @@ class Element(Node):
             Must overwrite, If attribute already exists.
         """
         allowed_attrs = self.allowed_attributes()
-        prefix = _nsassign(namespace)
+        prefix = self.get_nsprefix(namespace)
-        if not self.namespaces.has_key(namespace):
-            self.namespaces[namespace] = prefix
 #       if allowed_attrs and (namespace, localpart) not in allowed_attrs:
 #           raise AttributeError, "Attribute %s:%s is not allowed in element <%s>" % ( prefix, localpart, self.tagName)
         c = AttrConverters()
         self.attributes[prefix + ":" + localpart] = c.convert((namespace, localpart), value, self.qname)
 
     def getAttrNS(self, namespace, localpart):
-        prefix = _nsassign(namespace)
+        prefix = self.get_nsprefix(namespace)
-        if not self.namespaces.has_key(namespace):
-            self.namespaces[namespace] = prefix
         return self.attributes.get(prefix + ":" + localpart)
 
     def removeAttrNS(self, namespace, localpart):
-        prefix = _nsassign(namespace)
+        prefix = self.get_nsprefix(namespace)
-        if not self.namespaces.has_key(namespace):
-            self.namespaces[namespace] = prefix
         del self.attributes[prefix + ":" + localpart]
 
     def getAttribute(self, attr):

src/odf/elementtypes.py

@@ -109,11 +109,6 @@ inline_elements = (
 )
 
 
-struct_elements = (
-	(CONFIGNS,'config-item-set'),
-	(TABLENS,u'table-cell'),
-)
-
 # It is almost impossible to determine what elements are block elements.
 # There are so many that don't fit the form
 block_elements = (

src/odf/load.py

@@ -29,12 +29,7 @@ from xml.sax.xmlreader import InputSource
 import xml.sax.saxutils
 from element import Element
 from namespaces import OFFICENS
-
+from cStringIO import StringIO
-try:
-    from cStringIO import StringIO
-except ImportError:
-    from StringIO import StringIO
-
 
 #
 # Parse the XML files
@@ -70,7 +65,7 @@ class LoadParser(handler.ContentHandler):
         # Add any accumulated text content
         content = ''.join(self.data).strip()
         if len(content) > 0:
-            self.parent.addText(content)
+            self.parent.addText(content, check_grammar=False)
             self.data = []
         # Create the element
         attrdict = {}
@@ -109,7 +104,7 @@ class LoadParser(handler.ContentHandler):
         self.level = self.level - 1
         str = ''.join(self.data)
         if len(str.strip()) > 0:
-            self.curr.addText(str)
+            self.curr.addText(str, check_grammar=False)
         self.data = []
         self.curr = self.curr.parentNode
         self.parent = self.curr

src/odf/namespaces.py

@@ -1,5 +1,5 @@
 # -*- coding: utf-8 -*-
-# Copyright (C) 2006-2007 Søren Roug, European Environment Agency
+# Copyright (C) 2006-2009 Søren Roug, European Environment Agency
 #
 # This library is free software; you can redistribute it and/or
 # modify it under the terms of the GNU Lesser General Public
@@ -17,7 +17,7 @@
 #
 # Contributor(s):
 #
-TOOLSVERSION = u"ODFPY/0.8.2dev"
+TOOLSVERSION = u"ODFPY/0.9.1dev"
 
 ANIMNS         = u"urn:oasis:names:tc:opendocument:xmlns:animation:1.0"
 DBNS           = u"urn:oasis:names:tc:opendocument:xmlns:database:1.0"
@@ -71,7 +71,7 @@ nsdict = {
    OFFICENS: u'office',
    OOONS: u'ooo',
    OOOWNS: u'ooow',
-   OOOCNS: u'ooc',
+   OOOCNS: u'oooc',
    PRESENTATIONNS: u'presentation',
    RDFANS: u'rdfa',
    SCRIPTNS: u'script',

src/odf/odf2xhtml.py

@@ -25,11 +25,7 @@ import xml.sax
 from xml.sax import handler, expatreader
 from xml.sax.xmlreader import InputSource
 from xml.sax.saxutils import escape, quoteattr
-
+from cStringIO import StringIO
-try:
-    from cStringIO import StringIO
-except ImportError:
-    from StringIO import StringIO
 
 from namespaces import ANIMNS, CHARTNS, CONFIGNS, DCNS, DR3DNS, DRAWNS, FONS, \
   FORMNS, MATHNS, METANS, NUMBERNS, OFFICENS, PRESENTATIONNS, SCRIPTNS, \

src/odf/odfmanifest.py

@@ -24,12 +24,7 @@ import zipfile
 from xml.sax import make_parser,handler
 from xml.sax.xmlreader import InputSource
 import xml.sax.saxutils
-
+from cStringIO import StringIO
-try:
-    from cStringIO import StringIO
-except ImportError:
-    from StringIO import StringIO
-
 
 MANIFESTNS="urn:oasis:names:tc:opendocument:xmlns:manifest:1.0"
 

src/odf/office.py

@@ -44,19 +44,19 @@ def Chart(**args):
 def DdeSource(**args):
     return Element(qname = (OFFICENS,'dde-source'), **args)
 
-def Document(version="1.0", **args):
+def Document(version="1.1", **args):
     return Element(qname = (OFFICENS,'document'), version=version, **args)
 
-def DocumentContent(version="1.0", **args):
+def DocumentContent(version="1.1", **args):
     return Element(qname = (OFFICENS, 'document-content'), version=version, **args)
 
-def DocumentMeta(version="1.0", **args):
+def DocumentMeta(version="1.1", **args):
     return Element(qname = (OFFICENS, 'document-meta'), version=version, **args)
 
-def DocumentSettings(version="1.0", **args):
+def DocumentSettings(version="1.1", **args):
     return Element(qname = (OFFICENS, 'document-settings'), version=version, **args)
 
-def DocumentStyles(version="1.0", **args):
+def DocumentStyles(version="1.1", **args):
     return Element(qname = (OFFICENS, 'document-styles'), version=version, **args)
 
 def Drawing(**args):

src/odf/ooostyles.py

@@ -1,71 +0,0 @@
-from style import Style, ParagraphProperties, TextProperties
-
-def addOOoStandardStyles(styles):
-    style = Style(name="Standard", family="paragraph", attributes={'class':"text"})
-    styles.addElement(style)
-
-    style = Style(name="Text_20_body", displayname="Text body", family="paragraph", parentstylename="Standard", attributes={'class':"text"})
-    p = ParagraphProperties(margintop="0cm", marginbottom="0.212cm")
-    style.addElement(p)
-    styles.addElement(style)
-
-    style = Style(name="Text_20_body_20_indent", displayname="Text body indent", family="paragraph", parentstylename="Text_20_body", attributes={'class':"text"})
-    p = ParagraphProperties(marginleft="0.499cm", marginright="0cm", textindent="0cm", autotextindent="false")
-    style.addElement(p)
-    styles.addElement(style)
-
-    style = Style(name="Salutation", family="paragraph", parentstylename="Standard", attributes={'class':"text"})
-    p = ParagraphProperties(numberlines="false", linenumber=0)
-    style.addElement(p)
-    styles.addElement(style)
-
-    style = Style(name="Signature", family="paragraph", parentstylename="Standard", attributes={'class':"text"})
-    p = ParagraphProperties(numberlines="false", linenumber=0)
-    style.addElement(p)
-    styles.addElement(style)
-
-    style = Style(name="Heading", family="paragraph", parentstylename="Standard", nextstylename="Text_20_body", attributes={'class':"text"})
-    p = ParagraphProperties(margintop="0.423cm", marginbottom="0.212cm", keepwithnext="always")
-    style.addElement(p)
-    p = TextProperties(fontname="Nimbus Sans L", fontsize="14pt", fontnameasian="DejaVu LGC Sans", fontsizeasian="14pt", fontnamecomplex="DejaVu LGC Sans", fontsizecomplex="14pt")
-    style.addElement(p)
-    styles.addElement(style)
-
-    style = Style(name="Heading_20_1", displayname="Heading 1", family="paragraph", parentstylename="Heading", nextstylename="Text_20_body", attributes={'class':"text"}, defaultoutlinelevel=1)
-    p = TextProperties(fontsize="115%", fontweight="bold", fontsizeasian="115%", fontweightasian="bold", fontsizecomplex="115%", fontweightcomplex="bold")
-    style.addElement(p)
-    styles.addElement(style)
-
-    style = Style(name="Heading_20_2", displayname="Heading 2", family="paragraph", parentstylename="Heading", nextstylename="Text_20_body", attributes={'class':"text"}, defaultoutlinelevel=2)
-    p = TextProperties(fontsize="14pt", fontstyle="italic", fontweight="bold", fontsizeasian="14pt", fontstyleasian="italic", fontweightasian="bold", fontsizecomplex="14pt", fontstylecomplex="italic", fontweightcomplex="bold")
-    style.addElement(p)
-    styles.addElement(style)
-
-    style = Style(name="Heading_20_3", displayname="Heading 3", family="paragraph", parentstylename="Heading", nextstylename="Text_20_body", attributes={'class':"text"}, defaultoutlinelevel=3)
-    p = TextProperties(fontsize="14pt", fontweight="bold", fontsizeasian="14pt", fontweightasian="bold", fontsizecomplex="14pt", fontweightcomplex="bold")
-    style.addElement(p)
-    styles.addElement(style)
-
-    style = Style(name="List", family="paragraph", parentstylename="Text_20_body", attributes={'class':"list"})
-    styles.addElement(style)
-
-    style = Style(name="Caption", family="paragraph", parentstylename="Standard", attributes={'class':"extra"})
-    p = ParagraphProperties(margintop="0.212cm", marginbottom="0.212cm", numberlines="false", linenumber="0")
-    style.addElement(p)
-    p = TextProperties(fontsize="12pt", fontstyle="italic", fontsizeasian="12pt", fontstyleasian="italic", fontsizecomplex="12pt", fontstylecomplex="italic")
-    style.addElement(p)
-    styles.addElement(style)
-
-    style = Style(name="Index", family="paragraph", parentstylename="Standard", attributes={'class':"index"})
-    p = ParagraphProperties(numberlines="false", linenumber=0)
-    styles.addElement(style)
-
-    style = Style(name="Source_20_Text", displayname="Source Text", family="text")
-    p = TextProperties(fontname="Courier", fontnameasian="Courier", fontnamecomplex="Courier")
-    style.addElement(p)
-    styles.addElement(style)
-
-    style = Style(name="Variable", family="text")
-    p = TextProperties(fontstyle="italic", fontstyleasian="italic", fontstylecomplex="italic")
-    style.addElement(p)
-    styles.addElement(style)

src/odf/opendocument.py

@@ -1,5 +1,5 @@
 # -*- coding: utf-8 -*-
-# Copyright (C) 2006-2008 Søren Roug, European Environment Agency
+# Copyright (C) 2006-2009 Søren Roug, European Environment Agency
 #
 # This library is free software; you can redistribute it and/or
 # modify it under the terms of the GNU Lesser General Public
@@ -300,6 +300,37 @@ class OpenDocument:
             self.Pictures[manifestfn] = (IS_IMAGE, content, mediatype)
         return manifestfn
 
+    def addPictureFromFile(self, filename, mediatype=None):
+        """ Add a picture
+            It uses the same convention as OOo, in that it saves the picture in
+            the zipfile in the subdirectory 'Pictures'.
+            If mediatype is not given, it will be guessed from the filename
+            extension.
+        """
+        if mediatype is None:
+            mediatype, encoding = mimetypes.guess_type(filename)
+        if mediatype is None:
+            mediatype = ''
+            try: ext = filename[filename.rindex('.'):]
+            except ValueError: ext=''
+        else:
+            ext = mimetypes.guess_extension(mediatype)
+        manifestfn = "Pictures/%0.0f%s" % ((time.time()*10000000000), ext)
+        self.Pictures[manifestfn] = (IS_FILENAME, filename, mediatype)
+        return manifestfn
+
+    def addPictureFromString(self, content, mediatype):
+        """ Add a picture
+            It uses the same convention as OOo, in that it saves the picture in
+            the zipfile in the subdirectory 'Pictures'. The content variable
+            is a string that contains the binary image data. The mediatype
+            indicates the image format.
+        """
+        ext = mimetypes.guess_extension(mediatype)
+        manifestfn = "Pictures/%0.0f%s" % ((time.time()*10000000000), ext)
+        self.Pictures[manifestfn] = (IS_IMAGE, content, mediatype)
+        return manifestfn
+
     def addThumbnail(self, filecontent=None):
         """ Add a fixed thumbnail
             The thumbnail in the library is big, so this is pretty useless.
@@ -394,6 +425,7 @@ class OpenDocument:
 
         # Write any extra files
         for op in self._extra:
+            if op.filename == "META-INF/documentsignatures.xml": continue # Don't save signatures
             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

src/odf/userfield.py

@@ -31,11 +31,7 @@ import xml.sax.saxutils
 
 from odf.namespaces import OFFICENS, TEXTNS
 
-try:
+from cStringIO import StringIO
-    from cStringIO import StringIO
-except ImportError:
-    from StringIO import StringIO
-
 
 OUTENCODING = "utf-8"
 

src/odf/xforms.py

@@ -27,3 +27,8 @@ from element import Element
 def Model(**args):
     return Element(qname = (XFORMSNS,'model'), **args)
 
+def Instance(**args):
+    return Element(qname = (XFORMSNS,'instance'), **args)
+
+def Bind(**args):
+    return Element(qname = (XFORMSNS,'bind'), **args)

upload.py

@@ -139,7 +139,7 @@ class resources(OptionlessCommand):
     RESOURCES = dict(
         opf_template    = 'ebooks/metadata/opf.xml',
         ncx_template    = 'ebooks/metadata/ncx.xml',
-        fb2_xsl         = 'ebooks/lrf/fb2/fb2.xsl',
+        fb2_xsl         = 'ebooks/fb2/fb2.xsl',
         metadata_sqlite = 'library/metadata_sqlite.sql',
         jquery          = 'gui2/viewer/jquery.js',
         jquery_scrollTo = 'gui2/viewer/jquery_scrollTo.js',