Support reading/writing cover metadata to txtz/htmlz files

src/calibre/ebooks/__init__.py

@@ -26,7 +26,7 @@ class ParserError(ValueError):
     pass
 
 BOOK_EXTENSIONS = ['lrf', 'rar', 'zip', 'rtf', 'lit', 'txt', 'txtz', 'text', 'htm', 'xhtm',
-                   'html', 'xhtml', 'pdf', 'pdb', 'pdr', 'prc', 'mobi', 'azw', 'doc',
+                   'html', 'htmlz', 'xhtml', 'pdf', 'pdb', 'pdr', 'prc', 'mobi', 'azw', 'doc',
                    'epub', 'fb2', 'djvu', 'lrx', 'cbr', 'cbz', 'cbc', 'oebzip',
                    'rb', 'imp', 'odt', 'chm', 'tpz', 'azw1', 'pml', 'pmlz', 'mbp', 'tan', 'snb']
 

src/calibre/ebooks/htmlz/output.py

@@ -12,7 +12,7 @@ from lxml import etree
 
 from calibre.customize.conversion import OutputFormatPlugin, \
     OptionRecommendation
-from calibre.ebooks.oeb.base import OEB_IMAGES
+from calibre.ebooks.oeb.base import OEB_IMAGES, SVG_MIME
 from calibre.ptempfile import TemporaryDirectory
 from calibre.utils.zipfile import ZipFile
 
@@ -71,9 +71,13 @@ class HTMLZOutput(OutputFormatPlugin):
                     os.makedirs(os.path.join(tdir, 'images'))
                 for item in oeb_book.manifest:
                     if item.media_type in OEB_IMAGES and item.href in images:
+                        if item.media_type == SVG_MIME:
+                            data = unicode(etree.tostring(item.data, encoding=unicode)) 
+                        else:
+                            data = item.data
                         fname = os.path.join(tdir, 'images', images[item.href])
                         with open(fname, 'wb') as img:
-                            img.write(item.data)
+                            img.write(data)
 
             # Metadata
             with open(os.path.join(tdir, 'metadata.opf'), 'wb') as mdataf:

src/calibre/ebooks/metadata/extz.py

@@ -8,12 +8,13 @@ Read meta information from extZ (TXTZ, HTMLZ...) files.
 '''
 
 import os
+import posixpath
 
 from cStringIO import StringIO
 
 from calibre.ebooks.metadata import MetaInformation
-from calibre.ebooks.metadata.opf2 import OPF, metadata_to_opf
+from calibre.ebooks.metadata.opf2 import OPF
-from calibre.ptempfile import TemporaryDirectory
+from calibre.ptempfile import PersistentTemporaryFile
 from calibre.utils.zipfile import ZipFile, safe_replace
 
 def get_metadata(stream, extract_cover=True):
@@ -23,16 +24,75 @@ def get_metadata(stream, extract_cover=True):
     mi = MetaInformation(_('Unknown'), [_('Unknown')])
     stream.seek(0)
 
-    with TemporaryDirectory('_untxtz_mdata') as tdir:
+    try:
-        try:
+        with ZipFile(stream) as zf:
-            zf = ZipFile(stream)
+            opf_name = get_first_opf_name(zf)
-            zf.extract('metadata.opf', tdir)
+            opf_stream = StringIO(zf.read(opf_name))
-            with open(os.path.join(tdir, 'metadata.opf'), 'rb') as opff:
+            opf = OPF(opf_stream)
-                mi = OPF(opff).to_book_metadata()
+            mi = opf.to_book_metadata()
-        except:
+            if extract_cover:
-            return mi
+                cover_name = opf.raster_cover
+                if cover_name:
+                    mi.cover_data = ('jpg', zf.read(cover_name))
+    except:
+        return mi
     return mi
 
 def set_metadata(stream, mi):
-    opf = StringIO(metadata_to_opf(mi))
+    replacements = {}
-    safe_replace(stream, 'metadata.opf', opf)
+
+    # Get the OPF in the archive.
+    with ZipFile(stream) as zf:
+        opf_path = get_first_opf_name(zf)
+        opf_stream = StringIO(zf.read(opf_path))
+    opf = OPF(opf_stream)
+
+    # Cover.
+    new_cdata = None
+    try:
+        new_cdata = mi.cover_data[1]
+        if not new_cdata:
+            raise Exception('no cover')
+    except:
+        try:
+            new_cdata = open(mi.cover, 'rb').read()
+        except:
+            pass
+    if new_cdata:
+        raster_cover = opf.raster_cover
+        if not raster_cover:
+            raster_cover = 'cover.jpg'
+        cpath = posixpath.join(posixpath.dirname(opf_path), raster_cover)
+        new_cover = _write_new_cover(new_cdata, cpath)
+        replacements[cpath] = open(new_cover.name, 'rb')
+
+    # Update the metadata.
+    opf.smart_update(mi, replace_metadata=True)
+    newopf = StringIO(opf.render())
+    safe_replace(stream, opf_path, newopf, extra_replacements=replacements)
+
+    # Cleanup temporary files.
+    try:
+        if cpath is not None:
+            replacements[cpath].close()
+            os.remove(replacements[cpath].name)
+    except:
+        pass
+
+def get_first_opf_name(zf):
+    names = zf.namelist()
+    opfs = []
+    for n in names:
+        if n.endswith('.opf') and '/' not in n:
+            opfs.append(n)
+    if not opfs:
+        raise Exception('No OPF found')
+    opfs.sort()
+    return opfs[0]
+
+def _write_new_cover(new_cdata, cpath):
+    from calibre.utils.magick.draw import save_cover_data_to
+    new_cover = PersistentTemporaryFile(suffix=os.path.splitext(cpath)[1])
+    new_cover.close()
+    save_cover_data_to(new_cdata, new_cover.name)
+    return new_cover

src/calibre/gui2/__init__.py

@@ -357,6 +357,7 @@ class FileIconProvider(QFileIconProvider):
              'bmp'     : 'bmp',
              'svg'     : 'svg',
              'html'    : 'html',
+             'htmlz'   : 'html',
              'htm'     : 'html',
              'xhtml'   : 'html',
              'xhtm'    : 'html',