HTMLZ: Fix handling of covers. Fixes #775669 (HTMLZ missing cover when added to Calibre)

src/calibre/ebooks/htmlz/input.py

@@ -7,10 +7,12 @@ __copyright__ = '2011, John Schember <john@nachtimwald.com>'
 __docformat__ = 'restructuredtext en'
 
 import os
+import posixpath
 
-from calibre import walk
+from calibre import guess_type, walk
 from calibre.customize.conversion import InputFormatPlugin
 from calibre.ebooks.chardet import xml_to_unicode
+from calibre.ebooks.metadata.opf2 import OPF
 from calibre.utils.zipfile import ZipFile
 
 class HTMLZInput(InputFormatPlugin):
@@ -27,7 +29,7 @@ class HTMLZInput(InputFormatPlugin):
 
         # Extract content from zip archive.
         zf = ZipFile(stream)
-        zf.extractall('.')
+        zf.extractall()
 
         for x in walk('.'):
             if os.path.splitext(x)[1].lower() in ('.html', '.xhtml', '.htm'):
@@ -71,4 +73,23 @@ class HTMLZInput(InputFormatPlugin):
         mi = get_file_type_metadata(stream, file_ext)
         meta_info_to_oeb_metadata(mi, oeb.metadata, log)
         
+        # Get the cover path from the OPF.
+        cover_href = None
+        opf = None
+        for x in walk('.'):
+            if os.path.splitext(x)[1].lower() in ('.opf'):
+                opf = x
+                break
+        if opf:
+            opf = OPF(opf)
+            cover_href = posixpath.relpath(opf.cover, os.path.dirname(stream.name))
+        # Set the cover.
+        if cover_href:
+            cdata = None
+            with open(cover_href, 'rb') as cf:
+                cdata = cf.read()
+            id, href = oeb.manifest.generate('cover', cover_href)
+            oeb.manifest.add(id, href, guess_type(cover_href)[0], data=cdata)
+            oeb.guide.add('cover', 'Cover', href)
+
         return oeb

src/calibre/ebooks/htmlz/output.py

@@ -7,11 +7,13 @@ __copyright__ = '2011, John Schember <john@nachtimwald.com>'
 __docformat__ = 'restructuredtext en'
 
 import os
+from cStringIO import StringIO
 
 from lxml import etree
 
 from calibre.customize.conversion import OutputFormatPlugin, \
     OptionRecommendation
+from calibre.ebooks.metadata.opf2 import OPF, metadata_to_opf
 from calibre.ptempfile import TemporaryDirectory
 from calibre.utils.zipfile import ZipFile
 
@@ -80,9 +82,30 @@ class HTMLZOutput(OutputFormatPlugin):
                         with open(fname, 'wb') as img:
                             img.write(data)
             
+            # Cover
+            cover_path = None
+            try:
+                cover_data = None
+                if oeb_book.metadata.cover:
+                    term = oeb_book.metadata.cover[0].term
+                    cover_data = oeb_book.guide[term].item.data
+                if cover_data:
+                    from calibre.utils.magick.draw import save_cover_data_to
+                    cover_path = os.path.join(tdir, 'cover.jpg')
+                    with open(cover_path, 'w') as cf:
+                        cf.write('')
+                    save_cover_data_to(cover_data, cover_path)
+            except:
+                import traceback
+                traceback.print_exc()
+
             # Metadata
             with open(os.path.join(tdir, 'metadata.opf'), 'wb') as mdataf:
-                mdataf.write(etree.tostring(oeb_book.metadata.to_opf1()))
+                opf = OPF(StringIO(etree.tostring(oeb_book.metadata.to_opf1())))
+                mi = opf.to_book_metadata()
+                if cover_path:
+                    mi.cover = 'cover.jpg'
+                mdataf.write(metadata_to_opf(mi))
 
             htmlz = ZipFile(output_path, 'w')
             htmlz.add_dir(tdir)

src/calibre/ebooks/metadata/extz.py

@@ -13,7 +13,7 @@ import posixpath
 from cStringIO import StringIO
 
 from calibre.ebooks.metadata import MetaInformation
-from calibre.ebooks.metadata.opf2 import OPF
+from calibre.ebooks.metadata.opf2 import OPF, metadata_to_opf
 from calibre.ptempfile import PersistentTemporaryFile
 from calibre.utils.zipfile import ZipFile, safe_replace
 
@@ -31,9 +31,9 @@ def get_metadata(stream, extract_cover=True):
             opf = OPF(opf_stream)
             mi = opf.to_book_metadata()
             if extract_cover:
-                cover_name = opf.raster_cover
-                if cover_name:
-                    mi.cover_data = ('jpg', zf.read(cover_name))
+                cover_href = posixpath.relpath(opf.cover, os.path.dirname(stream.name))
+                if cover_href:
+                    mi.cover_data = ('jpg', zf.read(cover_href))
     except:
         return mi
     return mi
@@ -59,17 +59,20 @@ def set_metadata(stream, mi):
         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)
+        cover = opf.cover
+        if not cover:
+            cover = 'cover.jpg'
+        cpath = posixpath.join(posixpath.dirname(opf_path), cover)
         new_cover = _write_new_cover(new_cdata, cpath)
         replacements[cpath] = open(new_cover.name, 'rb')
+        mi.cover = cover
 
     # Update the metadata.
-    opf.smart_update(mi, replace_metadata=True)
+    old_mi = opf.to_book_metadata()
+    old_mi.smart_update(mi)
+    opf.smart_update(metadata_to_opf(old_mi))
     newopf = StringIO(opf.render())
-    safe_replace(stream, opf_path, newopf, extra_replacements=replacements)
+    safe_replace(stream, opf_path, newopf, extra_replacements=replacements, add_missing=True)
 
     # Cleanup temporary files.
     try:

src/calibre/ebooks/rtf/rtfml.py

@@ -15,7 +15,6 @@ import cStringIO
 from lxml import etree
 
 from calibre.ebooks.metadata import authors_to_string
-from calibre.utils.filenames import ascii_text
 from calibre.utils.magick.draw import save_cover_data_to, identify_data
 
 TAGS = {