Merge from trunk

Changelog.yaml

@@ -4,6 +4,74 @@
 # for important features/bug fixes.
 # Also, each release can have new and improved recipes.
 
+- version: 0.7.8
+  date: 2010-07-09
+
+  new features:
+    - title: "New tool to help prepare EPUBs for publication"
+      type: major
+      description: >
+        "calibre now contains a new command line tool called epub-fix that can automatically fix
+        common problems in EPUB files that cause them to be rejected by poorly designed publishing services.
+        The tool is plugin based for extensible functionality in the future. Currently, it can fix unmanifested files
+        and workaround the date and svg preserveaspectratio bugs of epubcheck."
+
+    - title: "New icons for the toolbar buttons by Kamil Tatara"
+
+    - title: "Display rating (when available) in cover browser"
+
+    - title: "Clicking on the central cover int the cover browser now opens that book in the viewer"
+
+    - title: "Use the status bar instead of the area to the right of the location view to display status information"
+
+    - title: "Driver for the Pandigital Novel e-book reader"
+
+  bug fixes:
+    - title: "News download: Don not specify a font family for article descriptions"
+
+    - title: "News download: Fix regression introduced in 0.7.0 that broke download of some embedded content feeds"
+
+    - title: "MOBI Output: Partial support for nested superscript and subscripts."
+      tickets: [6132]
+
+    - title: "CHM Input: Fix handling of buggy CHM files with no .hhc"
+      tickets: [6087]
+
+    - title: "EPUB Input: Fix bug in unzipping EPUB files that have been zipped in depth first order."
+      tickets: [6127]
+
+    - title: "TXT Input: Convert HTML entities to characters."
+      tickets: [6114]
+
+    - title: "LRF Input: Handle LRF files with random null bytes in the text"
+      tickets: [6097]
+
+    - title: "Kobo driver: Fix detection of txt/html files on the device"
+
+    - title: "Fix opening of books when calibre library is on an unmapped network share in windows"
+
+    - title: "SONY driver: Only update the timestamp in the XML db for newly added books"
+
+    - title: "Cover browser: Fix rendering of center cover when width of cover browser is less than the width of a single cover"
+
+    - title: "Cover browser: Correct fix for setPixel out of bounds warning causing UI slowdown in calibre"
+
+  new recipes:
+    - title: "evz.ro"
+      author: Darko Miletic
+
+    - title: "Anchorage Daily News, China Economic Net, BBC Chinese and Singtao Daily"
+      author: rty
+
+    - title: Big Oven
+      author: Starson17
+
+  improved recipes:
+    - Haaretz
+    - Editor and Publisher
+    - Estadao
+
+
 - version: 0.7.7
   date: 2010-07-02
 

src/calibre/constants.py

@@ -2,7 +2,7 @@ __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
 __docformat__ = 'restructuredtext en'
 __appname__   = 'calibre'
-__version__   = '0.7.7'
+__version__   = '0.7.8'
 __author__    = "Kovid Goyal <kovid@kovidgoyal.net>"
 
 import re

src/calibre/customize/builtins.py

@@ -460,7 +460,7 @@ from calibre.devices.hanvon.driver import N516, EB511, ALEX, AZBOOKA, THEBOOK
 from calibre.devices.edge.driver import EDGE
 from calibre.devices.teclast.driver import TECLAST_K3, NEWSMY, IPAPYRUS
 from calibre.devices.sne.driver import SNE
-from calibre.devices.misc import PALMPRE, AVANT, SWEEX
+from calibre.devices.misc import PALMPRE, AVANT, SWEEX, PDNOVEL
 from calibre.devices.folder_device.driver import FOLDER_DEVICE_FOR_CONFIG
 from calibre.devices.kobo.driver import KOBO
 
@@ -562,6 +562,7 @@ plugins += [
     AVANT,
     MENTOR,
     SWEEX,
+    PDNOVEL,
     ITUNES,
 ]
 plugins += [x for x in list(locals().values()) if isinstance(x, type) and \

src/calibre/devices/kindle/driver.py

@@ -213,7 +213,7 @@ class KINDLE_DX(KINDLE2):
     PRODUCT_ID = [0x0003]
     BCD        = [0x0100]
 
-class Bookmark():
+class Bookmark(): # {{{
     '''
     A simple class fetching bookmark data
     Kindle-specific
@@ -517,3 +517,6 @@ class Bookmark():
 
         else:
             print "unsupported bookmark_extension: %s" % self.bookmark_extension
+
+# }}}
+

src/calibre/devices/kobo/driver.py

@@ -176,23 +176,22 @@ class KOBO(USBMS):
             ImageID = row[0]
         cursor.close()
 
+        cursor = connection.cursor()
+        if ContentType == 6:
+            # Delete the shortcover_pages first
+            cursor.execute('delete from shortcover_page where shortcoverid in (select ContentID from content where BookID = ?)', t)
+
+        #Delete the volume_shortcovers second
+        cursor.execute('delete from volume_shortcovers where volumeid = ?', t)
+
+        # Delete the chapters associated with the book next
+        t = (ContentID,ContentID,)
+        cursor.execute('delete from content where BookID  = ? or ContentID = ?', t)
+
+        connection.commit()
+
+        cursor.close()
         if ImageID != None:
-            cursor = connection.cursor()
-            if ContentType == 6:
-                # Delete the shortcover_pages first
-                cursor.execute('delete from shortcover_page where shortcoverid in (select ContentID from content where BookID = ?)', t)
-
-            #Delete the volume_shortcovers second
-            cursor.execute('delete from volume_shortcovers where volumeid = ?', t)
-
-            # Delete the chapters associated with the book next
-            t = (ContentID,ContentID,)
-            cursor.execute('delete from content where BookID  = ? or ContentID = ?', t)
-
-            connection.commit()
-
-            cursor.close()
-        else:
             print "Error condition ImageID was not found"
             print "You likely tried to delete a book that the kobo has not yet added to the database"
 
@@ -227,12 +226,16 @@ class KOBO(USBMS):
                 #print "kobo book"
                 ContentType = 6
                 ContentID = self.contentid_from_path(path, ContentType)
-            if extension == '.pdf' or extension == '.epub':
+            elif extension == '.pdf' or extension == '.epub':
                 # print "ePub or pdf"
                 ContentType = 16
                 #print "Path: " + path
                 ContentID = self.contentid_from_path(path, ContentType)
                 # print "ContentID: " + ContentID
+            else: # if extension == '.html' or extension == '.txt':
+                ContentType = 999 # Yet another hack: to get around Kobo changing how ContentID is stored
+                ContentID = self.contentid_from_path(path, ContentType)
+                 
             ImageID = self.delete_via_sql(ContentID, ContentType)
             #print " We would now delete the Images for" + ImageID
             self.delete_images(ImageID)
@@ -316,6 +319,11 @@ class KOBO(USBMS):
             ContentID = ContentID.replace(self._main_prefix, '')
             if self._card_a_prefix is not None:
                 ContentID = ContentID.replace(self._card_a_prefix, '')
+        elif ContentType == 999: # HTML Files
+            ContentID = path
+            ContentID = ContentID.replace(self._main_prefix, "/mnt/onboard/")
+            if self._card_a_prefix is not None:
+                ContentID = ContentID.replace(self._card_a_prefix, "/mnt/sd/")
         else: # ContentType = 16
             ContentID = path
             ContentID = ContentID.replace(self._main_prefix, "file:///mnt/onboard/")

src/calibre/devices/misc.py

@@ -69,3 +69,21 @@ class SWEEX(USBMS):
     EBOOK_DIR_MAIN = ''
     SUPPORTS_SUB_DIRS = True
 
+class PDNOVEL(USBMS):
+    name = 'Pandigital Novel device interface'
+    gui_name = 'PD Novel'
+    description = _('Communicate with the Pandigital Novel')
+    author = 'Kovid Goyal'
+    supported_platforms = ['windows', 'linux', 'osx']
+    FORMATS = ['epub', 'pdf']
+
+    VENDOR_ID   = [0x18d1]
+    PRODUCT_ID  = [0xb004]
+    BCD         = [0x224]
+
+    VENDOR_NAME = 'ANDROID'
+    WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = '__UMS_COMPOSITE'
+
+    EBOOK_DIR_MAIN = 'eBooks'
+    SUPPORTS_SUB_DIRS = False
+

src/calibre/ebooks/chm/input.py

@@ -49,7 +49,6 @@ class CHMInput(InputFormatPlugin):
             log.debug('stream.name=%s' % stream.name)
             mainname = self._chmtohtml(tdir, chm_name, no_images, log)
             mainpath = os.path.join(tdir, mainname)
-            #raw_input()
 
             metadata = get_metadata_from_reader(self._chm_reader)
 
@@ -141,10 +140,9 @@ class CHMInput(InputFormatPlugin):
         log.debug('Found %d section nodes' % len(chapters))
         htmlpath = os.path.splitext(hhcpath)[0] + ".html"
         f = open(htmlpath, 'wb')
-        f.write('<html><head><meta http-equiv="Content-type"'
-                ' content="text/html;charset=UTF-8" /></head><body>\n')
-
         if chapters:
+            f.write('<html><head><meta http-equiv="Content-type"'
+                ' content="text/html;charset=UTF-8" /></head><body>\n')
             path0 = chapters[0][1]
             subpath = os.path.dirname(path0)
 
@@ -158,7 +156,9 @@ class CHMInput(InputFormatPlugin):
                     url = url.encode('utf-8')
                 f.write(url)
 
-        f.write("</body></html>")
+            f.write("</body></html>")
+        else:
+            f.write(hhcdata)
         f.close()
         return htmlpath
 

src/calibre/ebooks/chm/reader.py

@@ -8,7 +8,7 @@ import os, re
 from mimetypes import guess_type as guess_mimetype
 
 from calibre.ebooks.BeautifulSoup import BeautifulSoup, NavigableString
-from calibre.constants import iswindows
+from calibre.constants import iswindows, filesystem_encoding
 from calibre.utils.chm.chm import CHMFile
 from calibre.utils.chm.chmlib import (
   CHM_RESOLVE_SUCCESS, CHM_ENUMERATE_NORMAL,
@@ -78,6 +78,8 @@ class CHMError(Exception):
 class CHMReader(CHMFile):
     def __init__(self, input, log):
         CHMFile.__init__(self)
+        if isinstance(input, unicode):
+            input = input.encode(filesystem_encoding)
         if not self.LoadCHM(input):
             raise CHMError("Unable to open CHM file '%s'"%(input,))
         self.log = log
@@ -91,7 +93,6 @@ class CHMReader(CHMFile):
         self.root, ext = os.path.splitext(self.topics.lstrip('/'))
         self.hhc_path = self.root + ".hhc"
 
-
     def _parse_toc(self, ul, basedir=os.getcwdu()):
         toc = TOC(play_order=self._playorder, base_path=basedir, text='')
         self._playorder += 1
@@ -152,6 +153,8 @@ class CHMReader(CHMFile):
                 if f.lower() == self.hhc_path.lower():
                     self.hhc_path = f
                     break
+        if self.hhc_path not in files and files:
+            self.hhc_path = files[0]
 
     def _reformat(self, data):
         try:
@@ -159,7 +162,7 @@ class CHMReader(CHMFile):
             soup = BeautifulSoup(data)
         except ValueError:
             # hit some strange encoding problems...
-            print "Unable to parse html for cleaning, leaving it :("
+            self.log.exception("Unable to parse html for cleaning, leaving it")
             return data
         # nuke javascript...
         [s.extract() for s in soup('script')]

src/calibre/ebooks/mobi/mobiml.py

@@ -58,6 +58,7 @@ class FormatState(object):
         self.fsize = 3
         self.ids = set()
         self.valign = 'baseline'
+        self.nest = False
         self.italic = False
         self.bold = False
         self.strikethrough = False
@@ -233,9 +234,17 @@ class MobiMLizer(object):
                 inline = etree.SubElement(inline, XHTML('a'), href=href)
                 bstate.anchor = inline
             if valign == 'super':
-                inline = etree.SubElement(inline, XHTML('sup'))
+                parent = inline
+                if istate.nest and bstate.inline is not None:
+                    parent = bstate.inline
+                    istate.nest = False
+                inline = etree.SubElement(parent, XHTML('sup'))
             elif valign == 'sub':
-                inline = etree.SubElement(inline, XHTML('sub'))
+                parent = inline
+                if istate.nest and bstate.inline is not None:
+                    parent = bstate.inline
+                    istate.nest = False
+                inline = etree.SubElement(parent, XHTML('sub'))
             elif fsize != 3:
                 inline = etree.SubElement(inline, XHTML('font'),
                                           size=str(fsize))
@@ -343,8 +352,10 @@ class MobiMLizer(object):
             istate.family = 'serif'
         valign = style['vertical-align']
         if valign in ('super', 'text-top') or asfloat(valign) > 0:
+            istate.nest = istate.valign in ('sub', 'super')
             istate.valign = 'super'
         elif valign == 'sub'  or asfloat(valign) < 0:
+            istate.nest = istate.valign in ('sub', 'super')
             istate.valign = 'sub'
         else:
             istate.valign = 'baseline'

src/calibre/gui2/dialogs/delete_matching_from_device.py

@@ -66,7 +66,7 @@ class DeleteMatchingFromDeviceDialog(QDialog, Ui_DeleteMatchingFromDeviceDialog)
 
         self.explanation.setText('<p>'+_('All checked books will be '
                                    '<b>permanently deleted</b> from your '
-                                   'device. Please verify the list.'+'</p>'))
+                                   'device. Please verify the list.')+'</p>')
         self.buttonBox.accepted.connect(self.accepted)
         self.table.cellClicked.connect(self.cell_clicked)
         self.table.setSelectionMode(QAbstractItemView.NoSelection)

src/calibre/gui2/dialogs/tag_list_editor.py

@@ -17,7 +17,7 @@ class ListWidgetItem(QListWidgetItem):
     def data(self, role):
         if role == Qt.DisplayRole:
             if self.old_value != self.cur_value:
-                return _('%s (was %s)'%(self.cur_value, self.old_value))
+                return _('%s (was %s)')%(self.cur_value, self.old_value)
             else:
                 return self.cur_value
         elif role == Qt.EditRole:

src/calibre/utils/zipfile.py

@@ -1071,8 +1071,13 @@ class ZipFile:
 
         # Create all upper directories if necessary.
         upperdirs = os.path.dirname(targetpath)
-        if upperdirs and os.path.exists(upperdirs) and not os.path.isdir(upperdirs):
-            os.unlink(upperdirs)
+        while upperdirs:
+            if os.path.exists(upperdirs):
+                if os.path.isdir(upperdirs):
+                    break
+                os.remove(upperdirs)
+            upperdirs = os.path.dirname(upperdirs)
+        upperdirs = os.path.dirname(targetpath)
         if upperdirs and not os.path.exists(upperdirs):
             os.makedirs(upperdirs)
 

src/calibre/web/feeds/news.py

@@ -264,7 +264,7 @@ class BasicNewsRecipe(Recipe):
             }
 
             .article_description {
-                font-family: sans; text-indent: 0pt;
+                text-indent: 0pt;
             }
 
             a.article {

src/calibre/web/feeds/templates.py

@@ -70,7 +70,10 @@ class EmbeddedContent(Template):
             div.text = elements[0]
             elements = list(elements)[1:]
         for elem in elements:
-            elem.getparent().remove(elem)
+            if hasattr(elem, 'getparent'):
+                elem.getparent().remove(elem)
+            else:
+                elem = SPAN(elem)
             div.append(elem)
 
 class IndexTemplate(Template):