Sync to trunk

installer/windows/calibre/calibre.mpi

@@ -299,7 +299,6 @@ File ::2BCD9281-2CBC-CF0D-0E12-2CE11F6ED758 -name comic2epub.exe.local -parent 8
 File ::EDE6F457-C83F-C5FA-9AF4-38FDFF17D929 -name PIL._imagingtk.pyd -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
 File ::09D0906E-3611-3DB7-32CF-A140585694A7 -name win32pdh.pyd -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
 File ::4C84F0DC-7157-0C90-2062-180139B03E25 -name IM_MOD_RL_rgb_.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
-File ::F402F507-87C5-BDB1-80AE-AD3FF4A4BCE7 -name bzrlib._patiencediff_c.pyd -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
 File ::A732EDE7-4796-241F-BECA-68E59F88F8AF -name lrs2lrf.exe -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
 File ::69072379-7D16-B9F7-9F39-3E6403C48267 -name IM_MOD_RL_xbm_.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
 File ::FBD11D98-D1E7-5DD9-BF02-01CE92518859 -name IM_MOD_RL_otb_.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
@@ -365,7 +364,6 @@ File ::26741B21-C241-E100-8BB1-8B679BC3E662 -name configure.xml -parent 8E5D85A4
 File ::7D491E89-C6D3-1E6E-F4BD-8E55260FE33E -name libexpat.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
 File ::A4910EB3-0F1C-F6F0-CD2D-16A64BBAA92B -name calibre-fontconfig.exe.local -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
 File ::8711327A-716D-B162-6AC6-2FB4AD071266 -name fb22lrf.exe -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
-File ::0FDD3A7A-31F3-8089-CE32-D80EAA6F62B2 -name bzrlib._btree_serializer_c.pyd -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
 File ::476CB977-5155-D56F-26CA-EB243AEBBA99 -name unrar.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
 File ::2DA1CC8D-AF5C-3B03-2060-301DFE0356CC -name mobi2oeb.exe.local -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
 File ::2E2A9EDA-5386-444E-8479-557386794552 -name IM_MOD_RL_uil_.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
@@ -487,7 +485,6 @@ File ::AA761ACD-B728-2324-AA75-B20A2A79F125 -name lrf2lrs.exe -parent 8E5D85A4-7
 File ::95434C76-22F5-B9CE-6194-6E1B1EE3232D -name IM_MOD_RL_info_.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
 File ::AAF45D03-322F-5553-63A7-312DB754A20B -name _ctypes.pyd -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
 File ::C3D351CA-A8D8-AB35-55D9-5AACF8DB37D1 -name python26.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
-File ::2F90B52F-A728-2CA4-5688-0283674695B7 -name _elementtree.pyd -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
 File ::B50B66A1-FB65-FAD5-1DD7-E894ACC07464 -name QtSvg4.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
 File ::906FF13D-D993-7192-7EA5-6D15A5A24BFB -name CORE_RL_png_.dll -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
 File ::5D368661-6BF0-D6AF-7C1A-87646864EB4B -name delegates.xml -parent 8E5D85A4-7608-47A1-CF7C-309060D5FF40
@@ -552,7 +549,7 @@ SetupType ::D9ADE41C-B744-690C-2CED-CF826BF03D2E -setup Install -active Yes -pla
 
 InstallComponent 3EA07B17-04D8-6508-B535-96CC7173B49A -setup Install -type pane -conditions D7F585DB-0DEC-A94E-DAB0-94D558D82764 -title {Welcome Screen} -component Welcome -command insert -active Yes -parent StandardInstall
 Condition D7F585DB-0DEC-A94E-DAB0-94D558D82764 -active Yes -parent 3EA07B17-04D8-6508-B535-96CC7173B49A -title {Execute Script Condition} -component ExecuteScriptCondition -TreeObject::id D7F585DB-0DEC-A94E-DAB0-94D558D82764
-InstallComponent 7CCDA4BB-861C-C21E-3011-E93DB58F07D6 -setup Install -type action -conditions ADBCD53E-C9A6-A3CA-1AAC-0DB0CE84F71E -title {Check for Previous Install} -component CheckForPreviousInstall -command reorder -active Yes -parent 3EA07B17-04D8-6508-B535-96CC7173B49A
+InstallComponent 7CCDA4BB-861C-C21E-3011-E93DB58F07D6 -setup Install -type action -conditions ADBCD53E-C9A6-A3CA-1AAC-0DB0CE84F71E -title {Check for Previous Install} -component CheckForPreviousInstall -command insert -active Yes -parent 3EA07B17-04D8-6508-B535-96CC7173B49A
 Condition ADBCD53E-C9A6-A3CA-1AAC-0DB0CE84F71E -active Yes -parent 7CCDA4BB-861C-C21E-3011-E93DB58F07D6 -title {Execute Script Condition} -component ExecuteScriptCondition -TreeObject::id ADBCD53E-C9A6-A3CA-1AAC-0DB0CE84F71E
 InstallComponent 580ACF2C-517F-5E48-9DEF-7DAEFBA59FDD -setup Install -type action -conditions 6DE3B369-9D6B-6BC1-4EA0-2C54ECE159EB -title {Set Virtual Text} -component SetVirtualText -command insert -active Yes -parent 3EA07B17-04D8-6508-B535-96CC7173B49A
 Condition 6DE3B369-9D6B-6BC1-4EA0-2C54ECE159EB -active Yes -parent 580ACF2C-517F-5E48-9DEF-7DAEFBA59FDD -title {String Is Condition} -component StringIsCondition -TreeObject::id 6DE3B369-9D6B-6BC1-4EA0-2C54ECE159EB

installer/windows/freeze.py

@@ -12,7 +12,7 @@ LIBUNRAR         = 'C:\\Program Files\\UnrarDLL\\unrar.dll'
 PDFTOHTML        = 'C:\\pdftohtml\\pdftohtml.exe'
 IMAGEMAGICK_DIR  = 'C:\\ImageMagick'
 FONTCONFIG_DIR   = 'C:\\fontconfig'
-VC90             = r'C:\Program Files\Microsoft Visual Studio 9.0\VC\redist\x86\Microsoft.VC90.CRT'
+VC90             = r'C:\VC90.CRT'
 
 import sys, os, py2exe, shutil, zipfile, glob, subprocess, re
 from distutils.core import setup

src/calibre/__init__.py

@@ -17,10 +17,17 @@ from calibre.constants import iswindows, isosx, islinux, isfrozen, \
                               filesystem_encoding
 import mechanize
 
-mimetypes.add_type('application/epub+zip', '.epub')
+mimetypes.add_type('application/epub+zip',                '.epub')
-mimetypes.add_type('text/x-sony-bbeb+xml', '.lrs')
+mimetypes.add_type('text/x-sony-bbeb+xml',                '.lrs')
-mimetypes.add_type('application/x-sony-bbeb', '.lrf')
+mimetypes.add_type('http://www.w3.org/1999/xhtml',        '.xhtml')
-mimetypes.add_type('application/x-dtbncx+xml', '.ncx')
+mimetypes.add_type('image/svg+xml',                       '.svg')
+mimetypes.add_type('application/x-sony-bbeb',             '.lrf')
+mimetypes.add_type('application/x-dtbncx+xml',            '.ncx')
+mimetypes.add_type('application/adobe-page-template+xml', '.xpgt')
+mimetypes.add_type('application/x-font-opentype',         '.otf')
+mimetypes.add_type('application/x-font-truetype',         '.ttf')
+mimetypes.add_type('application/oebps-package+xml',       '.opf')
+
 
 def to_unicode(raw, encoding='utf-8', errors='strict'):
     if isinstance(raw, unicode):

src/calibre/constants.py

@@ -2,7 +2,7 @@ __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
 __docformat__ = 'restructuredtext en'
 __appname__   = 'calibre'
-__version__   = '0.4.132'
+__version__   = '0.4.134'
 __author__    = "Kovid Goyal <kovid@kovidgoyal.net>"
 '''
 Various run time constants.

src/calibre/devices/prs500/driver.py

@@ -96,7 +96,7 @@ class PRS500(Device):
     # Location of cache.xml on storage card in device
     CACHE_XML = "/Sony Reader/database/cache.xml" 
     # Ordered list of supported formats
-    FORMATS     = ["lrf", "rtf", "pdf", "txt"]             
+    FORMATS     = ["lrf", "lrx", "rtf", "pdf", "txt"]             
     # Height for thumbnails of books/images on the device
     THUMBNAIL_HEIGHT = 68
     # Directory on card to which books are copied

src/calibre/devices/prs505/driver.py

@@ -27,12 +27,12 @@ class File(object):
         
 
 class PRS505(Device):
-    VENDOR_ID    = 0x054c #: SONY Vendor Id
+    VENDOR_ID    = 0x054c   #: SONY Vendor Id
-    PRODUCT_ID   = 0x031e #: Product Id for the PRS-505
+    PRODUCT_ID   = 0x031e   #: Product Id for the PRS-505
     BCD          = [0x229]  #: Needed to disambiguate 505 and 700 on linux
     PRODUCT_NAME = 'PRS-505'
     VENDOR_NAME  = 'SONY'
-    FORMATS      = ['lrf', 'epub', "rtf", "pdf", "txt"]
+    FORMATS      = ['lrf', 'epub', 'lrx', 'rtf', 'pdf', 'txt']
     
     MEDIA_XML    = 'database/cache/media.xml'
     CACHE_XML    = 'Sony Reader/database/cache.xml'
@@ -147,6 +147,7 @@ class PRS505(Device):
             
     
     def open_windows(self):
+        time.sleep(6)
         drives = []
         wmi = __import__('wmi', globals(), locals(), [], -1) 
         c = wmi.WMI()

src/calibre/devices/usbms/device.py

@@ -172,6 +172,7 @@ class Device(_Device):
         return prefix
 
     def open_windows(self):
+        time.sleep(6)
         drives = {}
         wmi = __import__('wmi', globals(), locals(), [], -1)
         c = wmi.WMI()

src/calibre/ebooks/epub/__init__.py

@@ -102,13 +102,23 @@ def config(defaults=None, name='epub'):
     c.remove_opt('zip')
     
     c.add_opt('output', ['-o', '--output'], default=None,
-             help=_('The output EPUB file. If not specified, it is derived from the input file name.'))
+             help=_('The output EPUB file. If not specified, it is '
+                    'derived from the input file name.'))
     c.add_opt('profile', ['--profile'], default='PRS505', choices=list(PROFILES.keys()),
-              help=_('Profile of the target device this EPUB is meant for. Set to None to create a device independent EPUB. The profile is used for device specific restrictions on the EPUB. Choices are: ')+str(list(PROFILES.keys())))
+              help=_('Profile of the target device this EPUB is meant for. '
+                     'Set to None to create a device independent EPUB. '
+                     'The profile is used for device specific restrictions '
+                     'on the EPUB. Choices are: ')+str(list(PROFILES.keys())))
     c.add_opt('override_css', ['--override-css'], default=None,
-              help=_('Either the path to a CSS stylesheet or raw CSS. This CSS will override any existing CSS declarations in the source files.'))
+              help=_('Either the path to a CSS stylesheet or raw CSS. '
-    structure = c.add_group('structure detection', _('Control auto-detection of document structure.'))
+                     'This CSS will override any existing CSS '
-    structure('chapter', ['--chapter'], default="//*[re:match(name(), 'h[1-2]') and re:test(., 'chapter|book|section|part', 'i')] | //*[@class = 'chapter']",
+                     'declarations in the source files.'))
+    structure = c.add_group('structure detection', 
+                            _('Control auto-detection of document structure.'))
+    structure('chapter', ['--chapter'], 
+              default="//*[re:match(name(), 'h[1-2]') and "
+              "re:test(., 'chapter|book|section|part', 'i')] | "
+              "//*[@class = 'chapter']",
             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 
@@ -118,14 +128,39 @@ use the expression "/". See the XPath Tutorial in the calibre User Manual for fu
 help on using this feature.
 ''').replace('\n', ' '))
     structure('chapter_mark', ['--chapter-mark'], choices=['pagebreak', 'rule', 'both', 'none'],
-              default='pagebreak', 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.'))
+              default='pagebreak', 
+              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.'))
     structure('cover', ['--cover'], default=None,
               help=_('Path to the cover to be used for this book'))
     structure('prefer_metadata_cover', ['--prefer-metadata-cover'], default=False,
               action='store_true',
-              help=_('Use the cover detected from the source file in preference to the specified cover.'))
+              help=_('Use the cover detected from the source file in preference '
+                     'to the specified cover.'))
+    structure('remove_first_image', ['--remove-first-image'], default=False,
+              help=_('Remove the first image from the input ebook. Useful if '
+                     'the first image in the source file is a cover and you '
+                     'are specifying an external cover.'))
     structure('dont_split_on_page_breaks', ['--dont-split-on-page-breaks'], default=False,
-              help=_('Turn off splitting at page breaks. Normally, input files are automatically split at every page break into two files. This gives an output ebook that can be parsed faster and with less resources. However, splitting is slow and if your source file contains a very large number of page breaks, you should turn off splitting on page breaks.'))
+              help=_('Turn off splitting at page breaks. Normally, input files '
+                     'are automatically split at every page break into '
+                     'two files. This gives an output ebook that can be parsed '
+                     'faster and with less resources. However, splitting is '
+                     'slow and if your source file contains a very large '
+                     'number of page breaks, you should turn off splitting '
+                     'on page breaks.'))
+    structure('page', ['--page'], default=None,
+              help=_('XPath expression to detect page boundaries for building '
+                     'a custom pagination map, as used by AdobeDE. Default is '
+                     'not to build an explicit pagination map.'))
+    structure('page_names', ['--page-names'], default=None,
+              help=_('XPath expression to find the name of each page in the '
+                     'pagination map relative to its boundary element. '
+                     'Default is to number all pages staring with 1.'))
     toc = c.add_group('toc', 
         _('''\
 Control the automatic generation of a Table of Contents. If an OPF file is detected
@@ -133,21 +168,36 @@ and it specifies a Table of Contents, then that will be used rather than trying
 to auto-generate a Table of Contents.
 ''').replace('\n', ' '))
     toc('max_toc_links', ['--max-toc-links'], default=50, 
-        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 --toc-threshold number of chapters were detected.'))
+        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 --toc-threshold number of chapters were detected.'))
     toc('no_chapters_in_toc', ['--no-chapters-in-toc'], default=False,
         help=_("Don't add auto-detected chapters to the Table of Contents."))
     toc('toc_threshold', ['--toc-threshold'], default=6,
-        help=_('If fewer than this number of chapters is detected, then links are added to the Table of Contents. Default: %default'))
+        help=_('If fewer than this number of chapters is detected, then links '
+               'are added to the Table of Contents. Default: %default'))
     toc('level1_toc', ['--level1-toc'], default=None,
-        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.'))
+        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.'))
     toc('level2_toc', ['--level2-toc'], default=None,
-        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.'))
+        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.'))
     toc('level3_toc', ['--level3-toc'], default=None,
-        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.'))
+        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.'))
     toc('from_ncx', ['--from-ncx'], default=None,
-        help=_('Path to a .ncx file that contains the table of contents to use for this ebook. The NCX file should contain links relative to the directory it is placed in. See http://www.niso.org/workrooms/daisy/Z39-86-2005.html#NCX for an overview of the NCX format.'))
+        help=_('Path to a .ncx file that contains the table of contents to use '
+               'for this ebook. The NCX file should contain links relative to '
+               'the directory it is placed in. See '
+               'http://www.niso.org/workrooms/daisy/Z39-86-2005.html#NCX for '
+               'an overview of the NCX format.'))
     toc('use_auto_toc', ['--use-auto-toc'], default=False,
-        help=_('Normally, if the source file already has a Table of Contents, it is used in preference to the autodetected one. With this option, the autodetected one is always used.'))
+        help=_('Normally, if the source file already has a Table of Contents, '
+               'it is used in preference to the autodetected one. '
+               'With this option, the autodetected one is always used.'))
     
     layout = c.add_group('page layout', _('Control page layout'))
     layout('margin_top', ['--margin-top'], default=5.0, 
@@ -159,18 +209,33 @@ to auto-generate a Table of Contents.
     layout('margin_right', ['--margin-right'], default=5.0, 
            help=_('Set the right margin in pts. Default is %default'))
     layout('base_font_size2', ['--base-font-size'], default=12.0,
-           help=_('The base font size in pts. Default is %defaultpt. Set to 0 to disable rescaling of fonts.'))
+           help=_('The base font size in pts. Default is %defaultpt. '
+                  'Set to 0 to disable rescaling of fonts.'))
     layout('remove_paragraph_spacing', ['--remove-paragraph-spacing'], default=False,
-           help=_('Remove spacing between paragraphs. Will not work if the source file forces inter-paragraph spacing.'))
+           help=_('Remove spacing between paragraphs. '
+                  'Also sets a indent on paragraphs of 1.5em. '
+                  'You can override this by adding p {text-indent: 0cm} to '
+                  '--override-css. Spacing removal will not work if the source '
+                  'file forces inter-paragraph spacing.'))
+    layout('no_justification', ['--no-justification'], default=False,
+           help=_('Do not force text to be justified in output.'))
+    layout('linearize_tables', ['--linearize-tables'], default=False,
+           help=_('Remove table markup, converting it into paragraphs. '
+                  'This is useful if your source file uses a table to manage layout.'))
     layout('preserve_tag_structure', ['--preserve-tag-structure'], default=False,
-           help=_('Preserve the HTML tag structure while splitting large HTML files. This is only neccessary if the HTML files contain CSS that uses sibling selectors. Enabling this greatly slows down processing of large HTML files.'))
+           help=_('Preserve the HTML tag structure while splitting large HTML files. '
+                  'This is only neccessary if the HTML files contain CSS that '
+                  'uses sibling selectors. Enabling this greatly slows down '
+                  'processing of large HTML files.'))
     
     c.add_opt('show_opf', ['--show-opf'], default=False, group='debug',
               help=_('Print generated OPF file to stdout'))
     c.add_opt('show_ncx', ['--show-ncx'], default=False, group='debug',
               help=_('Print generated NCX file to stdout'))
-    c.add_opt('keep_intermediate', ['--keep-intermediate-files'], group='debug', default=False,
+    c.add_opt('keep_intermediate', ['--keep-intermediate-files'], group='debug', 
+              default=False,
               help=_('Keep intermediate files during processing by html2epub'))
     c.add_opt('extract_to', ['--extract-to'], group='debug', default=None,
-              help=_('Extract the contents of the produced EPUB file to the specified directory.'))
+              help=_('Extract the contents of the produced EPUB file to the '
-    return c
+                     'specified directory.'))
+    return c

src/calibre/ebooks/epub/from_html.py

@@ -46,6 +46,7 @@ from calibre.ebooks.metadata.toc import TOC
 from calibre.ebooks.metadata.opf2 import OPF
 from calibre.ebooks.epub import initialize_container, PROFILES
 from calibre.ebooks.epub.split import split
+from calibre.ebooks.epub.pages import add_page_map
 from calibre.ebooks.epub.fonts import Rationalizer
 from calibre.constants import preferred_encoding
 from calibre.customize.ui import run_plugins_on_postprocess
@@ -141,7 +142,7 @@ class HTMLProcessor(Processor, Rationalizer):
             p = QPixmap()
             p.load(path)
             if not p.isNull():
-                p.save(path+'_calibre_converted.jpg')
+                p.save(path + '_calibre_converted.jpg')
                 os.remove(path)
                 for key, val in self.resource_map.items():
                     if val == rpath:
@@ -194,7 +195,10 @@ class HTMLProcessor(Processor, Rationalizer):
             if not tag.text and not tag.get('src', False):
                 tag.getparent().remove(tag)
                 
-        
+        if self.opts.linearize_tables:
+            for tag in self.root.xpath('//table | //tr | //th | //td'):
+                tag.tag = 'div'
+            
     
     def save(self):
         for meta in list(self.root.xpath('//meta')):
@@ -203,6 +207,13 @@ class HTMLProcessor(Processor, Rationalizer):
         #    self.convert_image(img)
         Processor.save(self)
         
+    def remove_first_image(self):
+        images = self.root.xpath('//img')
+        if images:
+            images[0].getparent().remove(images[0])
+            return True
+        return False
+        
     
             
 
@@ -224,10 +235,13 @@ def parse_content(filelist, opts, tdir):
     resource_map, stylesheets = {}, {}
     toc = TOC(base_path=tdir, type='root')
     stylesheet_map = {}
+    first_image_removed = False
     for htmlfile in filelist:
         logging.getLogger('html2epub').debug('Processing %s...'%htmlfile)
         hp = HTMLProcessor(htmlfile, opts, os.path.join(tdir, 'content'), 
                            resource_map, filelist, stylesheets)
+        if not first_image_removed and opts.remove_first_image:
+            first_image_removed = hp.remove_first_image()
         hp.populate_toc(toc)
         hp.save()
         stylesheet_map[os.path.basename(hp.save_path())] = \
@@ -425,6 +439,9 @@ def convert(htmlfile, opts, notification=None, create_epub=True,
             if opts.show_ncx:
                 print toc
         split(opf_path, opts, stylesheet_map)
+        if opts.page:
+            logger.info('\tBuilding page map...')
+            add_page_map(opf_path, opts)
         check_links(opf_path, opts.pretty_print)
         
         opf = OPF(opf_path, tdir)
@@ -441,12 +458,9 @@ def convert(htmlfile, opts, notification=None, create_epub=True,
         
         cpath = os.path.join(tdir, 'content', 'resources', '_cover_.jpg')
         if os.path.exists(cpath):
-            opf.add_path_to_manifest(cpath, 'image/jpeg')    
+            opf.add_path_to_manifest(cpath, 'image/jpeg')
         with open(opf_path, 'wb') as f:
-            raw = opf.render()
+            f.write(opf.render())
-            if not raw.startswith('<?xml '):
-                raw = '<?xml version="1.0"  encoding="UTF-8"?>\n'+raw
-            f.write(raw)
         ncx_path = os.path.join(os.path.dirname(opf_path), 'toc.ncx')
         if os.path.exists(ncx_path) and os.stat(ncx_path).st_size > opts.profile.flow_size:
             logger.info('Condensing NCX from %d bytes...'%os.stat(ncx_path).st_size)
@@ -462,7 +476,7 @@ def convert(htmlfile, opts, notification=None, create_epub=True,
             logger.info(_('Output written to ')+opts.output)
         
         if opts.show_opf:
-            print open(os.path.join(tdir, 'metadata.opf')).read()
+            print open(opf_path, 'rb').read()
         
         if opts.extract_to is not None:
             if os.path.exists(opts.extract_to):

src/calibre/ebooks/epub/pages.py

@@ -0,0 +1,59 @@
+'''
+Add page mapping information to an EPUB book.
+'''
+
+from __future__ import with_statement
+
+__license__   = 'GPL v3'
+__copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'
+__docformat__ = 'restructuredtext en'
+
+import os, re
+from itertools import count, chain
+from calibre.ebooks.oeb.base import XHTML, XHTML_NS
+from calibre.ebooks.oeb.base import OEBBook, DirWriter
+from lxml import etree, html
+from lxml.etree import XPath
+
+NSMAP = {'h': XHTML_NS, 'html': XHTML_NS, 'xhtml': XHTML_NS}
+PAGE_RE = re.compile(r'page', re.IGNORECASE)
+ROMAN_RE = re.compile(r'^[ivxlcdm]+$', re.IGNORECASE)
+
+def filter_name(name):
+    name = name.strip()
+    name = PAGE_RE.sub('', name)
+    for word in name.split():
+        if word.isdigit() or ROMAN_RE.match(word):
+            name = word
+            break
+    return name
+
+def build_name_for(expr):
+    if not expr:
+        counter = count(1)
+        return lambda elem: str(counter.next())
+    selector = XPath(expr, namespaces=NSMAP)
+    def name_for(elem):
+        results = selector(elem)
+        if not results:
+            return ''
+        name = ' '.join(results)
+        return filter_name(name)
+    return name_for
+
+def add_page_map(opfpath, opts):
+    oeb = OEBBook(opfpath)
+    selector = XPath(opts.page, namespaces=NSMAP)
+    name_for = build_name_for(opts.page_names)
+    idgen = ("calibre-page-%d" % n for n in count(1))
+    for item in oeb.spine:
+        data = item.data
+        for elem in selector(data):
+            name = name_for(elem)
+            id = elem.get('id', None)
+            if id is None:
+                id = elem.attrib['id'] = idgen.next()
+            href = '#'.join((item.href, id))
+            oeb.pages.add(name, href)
+    writer = DirWriter(version='2.0', page_map=True)
+    writer.dump(oeb, opfpath)

src/calibre/ebooks/html.py

@@ -9,7 +9,7 @@ directory or zip file. All the action starts in :function:`create_dir`.
 '''
 
 import sys, re, os, shutil, logging, tempfile, cStringIO, operator, functools
-from urlparse import urlparse
+from urlparse import urlparse, urlunparse
 from urllib import unquote
 
 from lxml import etree
@@ -98,7 +98,8 @@ class Link(object):
     
     @classmethod
     def url_to_local_path(cls, url, base):
-        path = url.path
+        path = urlunparse(('', '', url.path, url.params, url.query, ''))
+        path = unquote(path)
         if os.path.isabs(path):
             return path
         return os.path.abspath(os.path.join(base, path))
@@ -111,11 +112,11 @@ class Link(object):
         '''
         assert isinstance(url, unicode) and isinstance(base, unicode)
         self.url         = url
-        self.parsed_url  = urlparse(unquote(self.url))
+        self.parsed_url  = urlparse(self.url)
         self.is_local    = self.parsed_url.scheme in ('', 'file')
         self.is_internal = self.is_local and not bool(self.parsed_url.path)
         self.path        = None
-        self.fragment    = self.parsed_url.fragment 
+        self.fragment    = unquote(self.parsed_url.fragment)
         if self.is_local and not self.is_internal:
             self.path = self.url_to_local_path(self.parsed_url, base)
 
@@ -594,15 +595,21 @@ class Processor(Parser):
         '''
         Populate the Table of Contents from detected chapters and links.
         '''
-        
+        class Adder(object):
-        def add_item(href, fragment, text, target, type='link'):
+            
-            for entry in toc.flat():
+            def __init__(self, toc):
-                if entry.href == href and entry.fragment == fragment:
+                self.next_play_order = max([x.play_order for x in toc.flat()])
-                    return entry
+                
-            if len(text) > 50:
+            def __call__(self, href, fragment, text, target, type='link'):
-                text = text[:50] + u'\u2026'
+                for entry in toc.flat():
-            return target.add_item(href, fragment, text, type=type)
+                    if entry.href == href and entry.fragment == fragment:
-        
+                        return entry
+                if len(text) > 50:
+                    text = text[:50] + u'\u2026'
+                self.next_play_order += 1
+                return target.add_item(href, fragment, text, type=type, 
+                                       play_order=self.next_play_order)
+        add_item = Adder(toc)
         name = self.htmlfile_map[self.htmlfile.path]
         href = 'content/'+name
         
@@ -629,13 +636,15 @@ class Processor(Parser):
         
         if self.opts.level1_toc is not None:
             level1 = self.opts.level1_toc(self.root)
+            level1_order = []
             if level1:
                 added = {}
                 for elem in level1:
                     text, _href, frag = elem_to_link(elem, href, counter)
                     counter += 1
                     if text:
-                        added[elem] = add_item(_href, frag, text, toc, type='chapter')
+                        level1_order.append(add_item(_href, frag, text, toc, type='chapter'))
+                        added[elem] = level1_order[-1]
                         add_item(_href, frag, 'Top', added[elem], type='chapter')
                 if self.opts.level2_toc is not None:
                     added2 = {}
@@ -664,6 +673,15 @@ class Processor(Parser):
                                     if text:
                                         add_item(_href, frag, text, level2, type='chapter')
                 
+            
+            if level1_order: # Fix play order
+                next_play_order = level1_order[0].play_order
+                for x in level1_order:
+                    for y in x.flat():
+                        y.play_order = next_play_order
+                        next_play_order += 1
+                    
+                        
                     
             if len(toc) > 0:
                 return
@@ -867,6 +885,8 @@ class Processor(Parser):
         css += '\n\na { color: inherit; text-decoration: inherit; cursor: default; }\na[href] { color: blue; text-decoration: underline; cursor:pointer; }'
         if self.opts.remove_paragraph_spacing:
             css += '\n\np {text-indent: 1.5em; margin-top:0pt; margin-bottom:0pt; padding:0pt; border:0pt;}'
+        if not self.opts.no_justification:
+            css += '\n\nbody {text-align: justify}'
         if self.opts.override_css:
             css += '\n\n' + self.opts.override_css
         self.override_css = self.css_parser.parseString(self.preprocess_css(css))
@@ -987,7 +1007,6 @@ def merge_metadata(htmlfile, opf, opts):
             mi =  get_metadata(open(htmlfile, 'rb'), 'html')
         except:
             mi = MetaInformation(None, None)
-    
     if opts.from_opf is not None and os.access(opts.from_opf, os.R_OK):
         mi.smart_update(OPF(open(opts.from_opf, 'rb'), os.path.abspath(os.path.dirname(opts.from_opf))))
     for attr in ('title', 'authors', 'publisher', 'tags', 'comments'):

src/calibre/ebooks/lit/writer.py

@@ -23,7 +23,7 @@ from urllib import unquote as urlunquote
 from lxml import etree
 from calibre.ebooks.lit.reader import DirectoryEntry
 import calibre.ebooks.lit.maps as maps
-from calibre.ebooks.oeb.base import OEB_DOCS, OEB_STYLES, OEB_CSS_MIME, \
+from calibre.ebooks.oeb.base import OEB_DOCS, XHTML_MIME, OEB_STYLES, \
     CSS_MIME, OPF_MIME, XML_NS, XML
 from calibre.ebooks.oeb.base import namespace, barename, prefixname, \
     urlnormalize, xpath
@@ -474,7 +474,7 @@ class LitWriter(object):
             name = '/data/' + item.id
             data = item.data
             secnum = 0
-            if not isinstance(data, basestring):
+            if isinstance(data, etree._Element):
                 self._add_folder(name)
                 rebin = ReBinary(data, item, self._oeb, map=HTML_MAP)
                 self._add_file(name + '/ahc', rebin.ahc, 0)
@@ -483,6 +483,8 @@ class LitWriter(object):
                 data = rebin.content
                 name = name + '/content'
                 secnum = 1
+            elif isinstance(data, unicode):
+                data = data.encode('utf-8')
             self._add_file(name, data, secnum)
             item.size = len(data)
 
@@ -493,7 +495,7 @@ class LitWriter(object):
             if item.spine_position is not None:
                 key = 'linear' if item.linear else 'nonlinear'
                 manifest[key].append(item)
-            elif item.media_type == CSS_MIME:
+            elif item.media_type in OEB_STYLES:
                 manifest['css'].append(item)
             elif item.media_type in LIT_IMAGES:
                 manifest['images'].append(item)
@@ -506,6 +508,11 @@ class LitWriter(object):
             data.write(pack('<I', len(items)))
             for item in items:
                 id, media_type = item.id, item.media_type
+                if media_type in OEB_DOCS:
+                    # Needs to have 'html' in media-type
+                    media_type = XHTML_MIME
+                elif media_type in OEB_STYLES:
+                    media_type = CSS_MIME
                 href = urlunquote(item.href)
                 item.offset = offset \
                     if state in ('linear', 'nonlinear') else 0
@@ -525,7 +532,12 @@ class LitWriter(object):
         pb3 = StringIO()
         pb3cur = 0
         bits = 0
+        linear = []
+        nonlinear = []
         for item in self._oeb.spine:
+            dest = linear if item.linear else nonlinear
+            dest.append(item)
+        for item in chain(linear, nonlinear):
             page_breaks = copy.copy(item.page_breaks)
             if not item.linear:
                 page_breaks.insert(0, (0, []))

src/calibre/ebooks/metadata/__init__.py

@@ -214,7 +214,7 @@ class MetaInformation(object):
         #: mi.cover_data = (ext, data)
         self.cover_data   = getattr(mi, 'cover_data', (None, None))
         
-        for x in ('author_sort', 'title_sort', 'comments', 'category', 'publisher', 
+        for x in ('author_sort', 'title_sort', 'comments', 'category', 'publisher',
                   'series', 'series_index', 'rating', 'isbn', 'language',
                   'application_id', 'manifest', 'toc', 'spine', 'guide', 'cover',
                   'book_producer',
@@ -247,6 +247,12 @@ class MetaInformation(object):
         if getattr(mi, 'cover_data', None) and mi.cover_data[0] is not None:
             self.cover_data = mi.cover_data
             
+    def format_series_index(self):
+        try:
+            x = float(self.series_index)
+        except ValueError:
+            x = 1.0
+        return '%d'%x if int(x) == x else '%.2f'%x
             
     def __unicode__(self):
         ans = u''
@@ -267,7 +273,7 @@ class MetaInformation(object):
         if self.tags:
             ans += u'Tags     : ' + u', '.join([unicode(t) for t in self.tags]) + '\n'
         if self.series:
-            ans += u'Series   : '+unicode(self.series) + ' #%d\n'%self.series_index  
+            ans += u'Series   : '+unicode(self.series) + ' #%s\n'%self.format_series_index()  
         if self.language:
             ans += u'Language : '     + unicode(self.language) + u'\n'
         return ans.strip()
@@ -277,11 +283,11 @@ class MetaInformation(object):
         ans += [(_('Author(s)'), (authors_to_string(self.authors) if self.authors else _('Unknown')))]
         ans += [(_('Publisher'), unicode(self.publisher))]
         ans += [(_('Producer'), unicode(self.book_producer))]
-        ans += [(_('Category'), unicode(self.category))]
         ans += [(_('Comments'), unicode(self.comments))]
         ans += [('ISBN', unicode(self.isbn))]
         ans += [(_('Tags'), u', '.join([unicode(t) for t in self.tags]))]
-        ans += [(_('Series'), unicode(self.series))]
+        if self.series:
+            ans += [(_('Series'), unicode(self.series))+ ' #%s'%self.format_series_index()]
         ans += [(_('Language'), unicode(self.language))]
         for i, x in enumerate(ans):
             ans[i] = u'<tr><td><b>%s</b></td><td>%s</td></tr>'%x

src/calibre/ebooks/metadata/opf.xml

@@ -6,9 +6,9 @@
          
 >
     <metadata xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:opf="http://www.idpf.org/2007/opf" xmlns:calibre="http://calibre.kovidgoyal.net/2009/metadata">
-        <dc:title py:with="attrs={'opf:files-as':mi.title_sort}" py:attrs="attrs">${mi.title}</dc:title>
+        <dc:title py:with="attrs={'opf:file-as':mi.title_sort}" py:attrs="attrs">${mi.title}</dc:title>
         <dc:creator opf:role="aut" py:for="i, author in enumerate(mi.authors)" py:attrs="{'opf:file-as':mi.author_sort} if mi.author_sort and i == 0 else {}">${author}</dc:creator>
-        <dc:contributor opf:role="bkp" py:with="attrs={'opf:files-as':__appname__}" py:attrs="attrs">${'%s (%s)'%(__appname__, __version__)} [http://${__appname__}.kovidgoyal.net]</dc:contributor> 
+        <dc:contributor opf:role="bkp" py:with="attrs={'opf:file-as':__appname__}" py:attrs="attrs">${'%s (%s)'%(__appname__, __version__)} [http://${__appname__}.kovidgoyal.net]</dc:contributor> 
         <dc:identifier opf:scheme="${__appname__}" id="${__appname__}_id">${mi.application_id}</dc:identifier>
     
         <dc:language>${mi.language if mi.language else 'UND'}</dc:language>

src/calibre/ebooks/metadata/opf2.py

@@ -17,21 +17,21 @@ from calibre.ebooks.chardet import xml_to_unicode
 from calibre import relpath
 from calibre.constants import __appname__, __version__
 from calibre.ebooks.metadata.toc import TOC
-from calibre.ebooks.metadata import MetaInformation, get_parser
+from calibre.ebooks.metadata import MetaInformation
 
 
 class Resource(object):
     '''
-    Represents a resource (usually a file on the filesystem or a URL pointing 
+    Represents a resource (usually a file on the filesystem or a URL pointing
     to the web. Such resources are commonly referred to in OPF files.
-    
+
     They have the interface:
-    
+
     :member:`path`
     :member:`mime_type`
     :method:`href`
     '''
-    
+
     def __init__(self, href_or_path, basedir=os.getcwd(), is_path=True):
         self.orig = href_or_path
         self._href = None
@@ -63,13 +63,13 @@ class Resource(object):
                 pc = pc.decode('utf-8')
                 self.path = os.path.abspath(os.path.join(basedir, pc.replace('/', os.sep)))
                 self.fragment = url[-1]
-        
+
-    
+
     def href(self, basedir=None):
         '''
         Return a URL pointing to this resource. If it is a file on the filesystem
         the URL is relative to `basedir`.
-        
+
         `basedir`: If None, the basedir of this resource is used (see :method:`set_basedir`).
         If this resource has no basedir, then the current working directory is used as the basedir.
         '''
@@ -91,54 +91,54 @@ class Resource(object):
         if isinstance(rpath, unicode):
             rpath = rpath.encode('utf-8')
         return rpath.replace(os.sep, '/')+frag
-    
+
     def set_basedir(self, path):
         self._basedir = path
-        
+
     def basedir(self):
         return self._basedir
-    
+
     def __repr__(self):
         return 'Resource(%s, %s)'%(repr(self.path), repr(self.href()))
-        
+
-        
+
 class ResourceCollection(object):
-    
+
     def __init__(self):
         self._resources = []
-        
+
     def __iter__(self):
         for r in self._resources:
             yield r
-            
+
     def __len__(self):
         return len(self._resources)
-    
+
     def __getitem__(self, index):
         return self._resources[index]
-    
+
     def __bool__(self):
         return len(self._resources) > 0
-    
+
     def __str__(self):
         resources = map(repr, self)
         return '[%s]'%', '.join(resources)
-    
+
     def __repr__(self):
         return str(self)
-    
+
     def append(self, resource):
         if not isinstance(resource, Resource):
             raise ValueError('Can only append objects of type Resource')
         self._resources.append(resource)
-        
+
     def remove(self, resource):
         self._resources.remove(resource)
-    
+
     def replace(self, start, end, items):
         'Same as list[start:end] = items'
         self._resources[start:end] = items
-        
+
     @staticmethod
     def from_directory_contents(top, topdown=True):
         collection = ResourceCollection()
@@ -148,16 +148,16 @@ class ResourceCollection(object):
             res.set_basedir(top)
             collection.append(res)
         return collection
-    
+
     def set_basedir(self, path):
         for res in self:
             res.set_basedir(path)
-        
+
 
 
 
 class ManifestItem(Resource):
-    
+
     @staticmethod
     def from_opf_manifest_item(item, basedir):
         href = item.get('href', None)
@@ -167,7 +167,7 @@ class ManifestItem(Resource):
             if mt:
                 res.mime_type = mt
             return res
-    
+
     @apply
     def media_type():
         def fget(self):
@@ -175,18 +175,18 @@ class ManifestItem(Resource):
         def fset(self, val):
             self.mime_type = val
         return property(fget=fget, fset=fset)
-    
+
-        
+
     def __unicode__(self):
         return u'<item id="%s" href="%s" media-type="%s" />'%(self.id, self.href(), self.media_type)
-    
+
     def __str__(self):
         return unicode(self).encode('utf-8')
-    
+
     def __repr__(self):
         return unicode(self)
-        
+
-    
+
     def __getitem__(self, index):
         if index == 0:
             return self.href()
@@ -196,7 +196,7 @@ class ManifestItem(Resource):
 
 
 class Manifest(ResourceCollection):
-    
+
     @staticmethod
     def from_opf_manifest_element(items, dir):
         m = Manifest()
@@ -211,7 +211,7 @@ class Manifest(ResourceCollection):
             except ValueError:
                 continue
         return m
-    
+
     @staticmethod
     def from_paths(entries):
         '''
@@ -226,7 +226,7 @@ class Manifest(ResourceCollection):
             m.next_id += 1
             m.append(mi)
         return m
-    
+
     def add_item(self, path, mime_type=None):
         mi = ManifestItem(path, is_path=True)
         if mime_type:
@@ -235,37 +235,37 @@ class Manifest(ResourceCollection):
         self.next_id += 1
         self.append(mi)
         return mi.id
-    
+
     def __init__(self):
         ResourceCollection.__init__(self)
         self.next_id = 1
-            
+
-                
+
     def item(self, id):
         for i in self:
             if i.id == id:
                 return i
-            
+
     def id_for_path(self, path):
         path = os.path.normpath(os.path.abspath(path))
         for i in self:
             if i.path and os.path.normpath(i.path) == path:
-                return i.id    
+                return i.id
-            
+
     def path_for_id(self, id):
         for i in self:
             if i.id == id:
                 return i.path
 
 class Spine(ResourceCollection):
-    
+
     class Item(Resource):
-        
+
         def __init__(self, idfunc, *args, **kwargs):
             Resource.__init__(self, *args, **kwargs)
             self.is_linear = True
             self.id = idfunc(self.path)
-        
+
     @staticmethod
     def from_opf_spine_element(itemrefs, manifest):
         s = Spine(manifest)
@@ -278,7 +278,7 @@ class Spine(ResourceCollection):
                     r.is_linear = itemref.get('linear', 'yes') == 'yes'
                     s.append(r)
         return s
-                
+
     @staticmethod
     def from_paths(paths, manifest):
         s = Spine(manifest)
@@ -288,14 +288,14 @@ class Spine(ResourceCollection):
             except:
                 continue
         return s
-            
+
-            
+
-    
+
     def __init__(self, manifest):
         ResourceCollection.__init__(self)
         self.manifest = manifest
-            
+
-            
+
     def replace(self, start, end, ids):
         '''
         Replace the items between start (inclusive) and end (not inclusive) with
@@ -308,7 +308,7 @@ class Spine(ResourceCollection):
                 raise ValueError('id %s not in manifest')
             items.append(Spine.Item(lambda x: id, path, is_path=True))
         ResourceCollection.replace(start, end, items)
-                    
+
     def linear_items(self):
         for r in self:
             if r.is_linear:
@@ -318,15 +318,15 @@ class Spine(ResourceCollection):
         for r in self:
             if not r.is_linear:
                 yield r.path
-        
+
     def items(self):
         for i in self:
             yield i.path
-    
+
 class Guide(ResourceCollection):
-    
+
     class Reference(Resource):
-        
+
         @staticmethod
         def from_opf_resource_item(ref, basedir):
             title, href, type = ref.get('title', ''), ref.get('href'), ref.get('type')
@@ -334,14 +334,14 @@ class Guide(ResourceCollection):
             res.title = title
             res.type = type
             return res
-        
+
         def __repr__(self):
             ans = '<reference type="%s" href="%s" '%(self.type, self.href())
             if self.title:
                 ans += 'title="%s" '%self.title
             return ans + '/>'
-        
+
-        
+
     @staticmethod
     def from_opf_guide(references, base_dir=os.getcwdu()):
         coll = Guide()
@@ -352,7 +352,7 @@ class Guide(ResourceCollection):
             except:
                 continue
         return coll
-        
+
     def set_cover(self, path):
         map(self.remove, [i for i in self if 'cover' in i.type.lower()])
         for type in ('cover', 'other.ms-coverimage-standard', 'other.ms-coverimage'):
@@ -362,13 +362,13 @@ class Guide(ResourceCollection):
 
 
 class MetadataField(object):
-    
+
     def __init__(self, name, is_dc=True, formatter=None, none_is=None):
         self.name      = name
         self.is_dc     = is_dc
         self.formatter = formatter
         self.none_is   = none_is
-        
+
     def __real_get__(self, obj, type=None):
         ans = obj.get_metadata_element(self.name)
         if ans is None:
@@ -382,13 +382,13 @@ class MetadataField(object):
             except:
                 return None
         return ans
-    
+
     def __get__(self, obj, type=None):
         ans = self.__real_get__(obj, type)
         if ans is None:
             ans = self.none_is
         return ans
-    
+
     def __set__(self, obj, val):
         elem = obj.get_metadata_element(self.name)
         if elem is None:
@@ -410,10 +410,11 @@ class OPF(object):
     XPath = functools.partial(etree.XPath, namespaces=xpn)
     CONTENT          = XPath('self::*[re:match(name(), "meta$", "i")]/@content')
     TEXT             = XPath('string()')
-    
+
-    
+
     metadata_path   = XPath('descendant::*[re:match(name(), "metadata", "i")]')
     metadata_elem_path = XPath('descendant::*[re:match(name(), concat($name, "$"), "i") or (re:match(name(), "meta$", "i") and re:match(@name, concat("^calibre:", $name, "$"), "i"))]')
+    title_path      = XPath('descendant::*[re:match(name(), "title", "i")]')
     authors_path    = XPath('descendant::*[re:match(name(), "creator", "i") and (@role="aut" or @opf:role="aut" or (not(@role) and not(@opf:role)))]')
     bkp_path        = XPath('descendant::*[re:match(name(), "contributor", "i") and (@role="bkp" or @opf:role="bkp")]')
     tags_path       = XPath('descendant::*[re:match(name(), "subject", "i")]')
@@ -423,10 +424,10 @@ class OPF(object):
     application_id_path = XPath('descendant::*[re:match(name(), "identifier", "i") and '+
                             '(re:match(@opf:scheme, "calibre|libprs500", "i") or re:match(@scheme, "calibre|libprs500", "i"))]')
     manifest_path   = XPath('descendant::*[re:match(name(), "manifest", "i")]/*[re:match(name(), "item", "i")]')
-    manifest_ppath  = XPath('descendant::*[re:match(name(), "manifest", "i")]') 
+    manifest_ppath  = XPath('descendant::*[re:match(name(), "manifest", "i")]')
     spine_path      = XPath('descendant::*[re:match(name(), "spine", "i")]/*[re:match(name(), "itemref", "i")]')
     guide_path      = XPath('descendant::*[re:match(name(), "guide", "i")]/*[re:match(name(), "reference", "i")]')
-    
+
     title           = MetadataField('title')
     publisher       = MetadataField('publisher')
     language        = MetadataField('language')
@@ -435,8 +436,8 @@ class OPF(object):
     series          = MetadataField('series', is_dc=False)
     series_index    = MetadataField('series_index', is_dc=False, formatter=int, none_is=1)
     rating          = MetadataField('rating', is_dc=False, formatter=int)
-    
+
-    
+
     def __init__(self, stream, basedir=os.getcwdu(), unquote_urls=True):
         if not hasattr(stream, 'read'):
             stream = open(stream, 'rb')
@@ -463,7 +464,7 @@ class OPF(object):
         self.guide = Guide.from_opf_guide(guide, basedir) if guide else None
         self.cover_data = (None, None)
         self.find_toc()
-        
+
     def find_toc(self):
         self.toc = None
         try:
@@ -480,7 +481,7 @@ class OPF(object):
                 for item in self.manifest:
                     if 'toc' in item.href().lower():
                         toc = item.path
-            
+
             if toc is None: return
             self.toc = TOC(base_path=self.base_dir)
             if toc.lower() in ('ncx', 'ncxtoc'):
@@ -494,22 +495,22 @@ class OPF(object):
             else:
                 self.toc.read_html_toc(toc)
         except:
-            pass        
+            pass
-            
+
-    
+
-        
+
     def get_text(self, elem):
         return u''.join(self.CONTENT(elem) or self.TEXT(elem))
 
     def set_text(self, elem, content):
         if elem.tag == self.META:
-            elem.attib['content'] = content
+            elem.attrib['content'] = content
         else:
             elem.text = content
-    
+
     def itermanifest(self):
         return self.manifest_path(self.root)
-    
+
     def create_manifest_item(self, href, media_type):
         ids = [i.get('id', None) for i in self.itermanifest()]
         id = None
@@ -519,11 +520,11 @@ class OPF(object):
                 break
         if not media_type:
             media_type = 'application/xhtml+xml'
-        ans = etree.Element('{%s}item'%self.NAMESPACES['opf'], 
+        ans = etree.Element('{%s}item'%self.NAMESPACES['opf'],
                              attrib={'id':id, 'href':href, 'media-type':media_type})
         ans.tail = '\n\t\t'
         return ans
-    
+
     def replace_manifest_item(self, item, items):
         items = [self.create_manifest_item(*i) for i in items]
         for i, item2 in enumerate(items):
@@ -532,7 +533,7 @@ class OPF(object):
         index = manifest.index(item)
         manifest[index:index+1] = items
         return [i.get('id') for i in items]
-    
+
     def add_path_to_manifest(self, path, media_type):
         has_path = False
         path = os.path.abspath(path)
@@ -546,22 +547,22 @@ class OPF(object):
             item = self.create_manifest_item(href, media_type)
             manifest = self.manifest_ppath(self.root)[0]
             manifest.append(item)
-    
+
     def iterspine(self):
         return self.spine_path(self.root)
-    
+
     def spine_items(self):
         for item in self.iterspine():
             idref = item.get('idref', '')
             for x in self.itermanifest():
                 if x.get('id', None) == idref:
                     yield x.get('href', '')
-    
+
     def create_spine_item(self, idref):
         ans = etree.Element('{%s}itemref'%self.NAMESPACES['opf'], idref=idref)
         ans.tail = '\n\t\t'
         return ans
-    
+
     def replace_spine_items_by_idref(self, idref, new_idrefs):
         items = list(map(self.create_spine_item, new_idrefs))
         spine = self.XPath('/opf:package/*[re:match(name(), "spine", "i")]')(self.root)[0]
@@ -569,31 +570,31 @@ class OPF(object):
         for x in old:
             i = spine.index(x)
             spine[i:i+1] = items
-    
+
     def create_guide_element(self):
         e = etree.SubElement(self.root, '{%s}guide'%self.NAMESPACES['opf'])
         e.text = '\n        '
         e.tail =  '\n'
         return e
-    
+
     def remove_guide(self):
         self.guide = None
         for g in self.root.xpath('./*[re:match(name(), "guide", "i")]', namespaces={'re':'http://exslt.org/regular-expressions'}):
             self.root.remove(g)
-    
+
     def create_guide_item(self, type, title, href):
-        e = etree.Element('{%s}reference'%self.NAMESPACES['opf'], 
+        e = etree.Element('{%s}reference'%self.NAMESPACES['opf'],
                              type=type, title=title, href=href)
         e.tail='\n'
         return e
-        
+
     def add_guide_item(self, type, title, href):
         g = self.root.xpath('./*[re:match(name(), "guide", "i")]', namespaces={'re':'http://exslt.org/regular-expressions'})[0]
         g.append(self.create_guide_item(type, title, href))
-        
+
     def iterguide(self):
         return self.guide_path(self.root)
-    
+
     def unquote_urls(self):
         def get_href(item):
             raw = unquote(item.get('href', ''))
@@ -604,16 +605,16 @@ class OPF(object):
             item.set('href', get_href(item))
         for item in self.iterguide():
             item.set('href', get_href(item))
-    
+
     @apply
     def authors():
-        
+
         def fget(self):
             ans = []
             for elem in self.authors_path(self.metadata):
                 ans.extend([x.strip() for x in self.get_text(elem).split(',')])
             return ans
-        
+
         def fset(self, val):
             remove = list(self.authors_path(self.metadata))
             for elem in remove:
@@ -622,12 +623,12 @@ class OPF(object):
                 attrib = {'{%s}role'%self.NAMESPACES['opf']: 'aut'}
                 elem = self.create_metadata_element('creator', attrib=attrib)
                 self.set_text(elem, author)
-        
+
         return property(fget=fget, fset=fset)
-    
+
     @apply
     def author_sort():
-        
+
         def fget(self):
             matches = self.authors_path(self.metadata)
             if matches:
@@ -637,39 +638,65 @@ class OPF(object):
                         ans = match.get('file-as', None)
                     if ans:
                         return ans
-            
+
         def fset(self, val):
             matches = self.authors_path(self.metadata)
             if matches:
+                for key in matches[0].attrib:
+                    if key.endswith('file-as'):
+                        matches[0].attrib.pop(key)
                 matches[0].set('file-as', unicode(val))
-            
+
         return property(fget=fget, fset=fset)
-    
+
+    @apply
+    def title_sort():
+
+        def fget(self):
+            matches = self.title_path(self.metadata)
+            if matches:
+                for match in matches:
+                    ans = match.get('{%s}file-as'%self.NAMESPACES['opf'], None)
+                    if not ans:
+                        ans = match.get('file-as', None)
+                    if ans:
+                        return ans
+
+        def fset(self, val):
+            matches = self.title_path(self.metadata)
+            if matches:
+                for key in matches[0].attrib:
+                    if key.endswith('file-as'):
+                        matches[0].attrib.pop(key)
+                matches[0].set('file-as', unicode(val))
+
+        return property(fget=fget, fset=fset)
+
     @apply
     def tags():
-        
+
         def fget(self):
             ans = []
             for tag in self.tags_path(self.metadata):
                 ans.append(self.get_text(tag))
             return ans
-        
+
         def fset(self, val):
             for tag in list(self.tags_path(self.metadata)):
                 self.metadata.remove(tag)
             for tag in val:
                 elem = self.create_metadata_element('subject')
                 self.set_text(elem, unicode(tag))
-        
+
         return property(fget=fget, fset=fset)
-    
+
     @apply
     def isbn():
-        
+
         def fget(self):
             for match in self.isbn_path(self.metadata):
                 return self.get_text(match) or None
-            
+
         def fset(self, val):
             matches = self.isbn_path(self.metadata)
             if not matches:
@@ -682,11 +709,11 @@ class OPF(object):
 
     @apply
     def application_id():
-        
+
         def fget(self):
             for match in self.application_id_path(self.metadata):
                 return self.get_text(match) or None
-            
+
         def fset(self, val):
             matches = self.application_id_path(self.metadata)
             if not matches:
@@ -696,14 +723,14 @@ class OPF(object):
             self.set_text(matches[0], unicode(val))
 
         return property(fget=fget, fset=fset)
-    
+
     @apply
     def book_producer():
-        
+
         def fget(self):
             for match in self.bkp_path(self.metadata):
                 return self.get_text(match) or None
-            
+
         def fset(self, val):
             matches = self.bkp_path(self.metadata)
             if not matches:
@@ -712,8 +739,8 @@ class OPF(object):
                                                         attrib=attrib)]
             self.set_text(matches[0], unicode(val))
         return property(fget=fget, fset=fset)
-    
+
-    
+
     def guess_cover(self):
         '''
         Try to guess a cover. Needed for some old/badly formed OPF files.
@@ -733,11 +760,11 @@ class OPF(object):
                         cpath = os.access(os.path.join(self.base_dir, prefix+suffix), os.R_OK)
                         if os.access(os.path.join(self.base_dir, prefix+suffix), os.R_OK):
                             return cpath
-            
+
-    
+
     @apply
     def cover():
-        
+
         def fget(self):
             if self.guide is not None:
                 for t in ('cover', 'other.ms-coverimage-standard', 'other.ms-coverimage'):
@@ -748,19 +775,19 @@ class OPF(object):
                 return self.guess_cover()
             except:
                 pass
-                        
+
         def fset(self, path):
             if self.guide is not None:
                 self.guide.set_cover(path)
                 for item in list(self.iterguide()):
                     if 'cover' in item.get('type', ''):
                         item.getparent().remove(item)
-                        
+
             else:
                 g = self.create_guide_element()
                 self.guide = Guide()
                 self.guide.set_cover(path)
-                etree.SubElement(g, 'opf:reference', nsmap=self.NAMESPACES, 
+                etree.SubElement(g, 'opf:reference', nsmap=self.NAMESPACES,
                                  attrib={'type':'cover', 'href':self.guide[-1].href()})
             id = self.manifest.id_for_path(self.cover)
             if id is None:
@@ -768,14 +795,14 @@ class OPF(object):
                     for item in self.guide:
                         if item.type.lower() == t:
                             self.create_manifest_item(item.href(), mimetypes.guess_type(path)[0])
-                 
+
-        return property(fget=fget, fset=fset)                    
+        return property(fget=fget, fset=fset)
-            
+
     def get_metadata_element(self, name):
         matches = self.metadata_elem_path(self.metadata, name=name)
         if matches:
             return matches[-1]
-        
+
     def create_metadata_element(self, name, attrib=None, is_dc=True):
         if is_dc:
             name = '{%s}%s' % (self.NAMESPACES['dc'], name)
@@ -787,21 +814,24 @@ class OPF(object):
                                 nsmap=self.NAMESPACES)
         elem.tail = '\n'
         return elem
-        
+
     def render(self, encoding='utf-8'):
-        return etree.tostring(self.root, encoding='utf-8', pretty_print=True)
+        raw = etree.tostring(self.root, encoding=encoding, pretty_print=True)
-    
+        if not raw.lstrip().startswith('<?xml '):
+            raw = '<?xml version="1.0"  encoding="%s"?>\n'%encoding.upper()+raw
+        return raw
+
     def smart_update(self, mi):
-        for attr in ('author_sort', 'title_sort', 'comments', 'category',
+        for attr in ('title', 'authors', 'author_sort', 'title_sort',
                      'publisher', 'series', 'series_index', 'rating',
-                     'isbn', 'language', 'tags', 'title', 'authors'):
+                     'isbn', 'language', 'tags', 'category', 'comments'):
             val = getattr(mi, attr, None)
             if val is not None and val != [] and val != (None, None):
                 setattr(self, attr, val)
-    
+
-    
+
 class OPFCreator(MetaInformation):
-    
+
     def __init__(self, base_path, *args, **kwargs):
         '''
         Initialize.
@@ -821,63 +851,64 @@ class OPFCreator(MetaInformation):
             self.guide = Guide()
         if self.cover:
             self.guide.set_cover(self.cover)
-        
+
-        
+
     def create_manifest(self, entries):
         '''
         Create <manifest>
-        
+
         `entries`: List of (path, mime-type) If mime-type is None it is autodetected
         '''
-        entries = map(lambda x: x if os.path.isabs(x[0]) else 
+        entries = map(lambda x: x if os.path.isabs(x[0]) else
                       (os.path.abspath(os.path.join(self.base_path, x[0])), x[1]),
                       entries)
         self.manifest = Manifest.from_paths(entries)
         self.manifest.set_basedir(self.base_path)
-        
+
     def create_manifest_from_files_in(self, files_and_dirs):
         entries = []
-        
+
         def dodir(dir):
             for spec in os.walk(dir):
                 root, files = spec[0], spec[-1]
                 for name in files:
                     path = os.path.join(root, name)
                     if os.path.isfile(path):
-                        entries.append((path, None)) 
+                        entries.append((path, None))
-        
+
         for i in files_and_dirs:
             if os.path.isdir(i):
                 dodir(i)
             else:
                 entries.append((i, None))
-                
+
-        self.create_manifest(entries)    
+        self.create_manifest(entries)
-            
+
     def create_spine(self, entries):
         '''
         Create the <spine> element. Must first call :method:`create_manifest`.
-        
+
         `entries`: List of paths
         '''
-        entries = map(lambda x: x if os.path.isabs(x) else 
+        entries = map(lambda x: x if os.path.isabs(x) else
                       os.path.abspath(os.path.join(self.base_path, x)), entries)
         self.spine = Spine.from_paths(entries, self.manifest)
-        
+
     def set_toc(self, toc):
         '''
         Set the toc. You must call :method:`create_spine` before calling this
         method.
-        
+
         :param toc: A :class:`TOC` object
         '''
         self.toc = toc
-        
+
     def create_guide(self, guide_element):
         self.guide = Guide.from_opf_guide(guide_element, self.base_path)
         self.guide.set_basedir(self.base_path)
-            
+
-    def render(self, opf_stream, ncx_stream=None, ncx_manifest_entry=None):
+    def render(self, opf_stream=sys.stdout, ncx_stream=None,
+               ncx_manifest_entry=None):
         from calibre.resources import opf_template
         from calibre.utils.genshi.template import MarkupTemplate
         template = MarkupTemplate(opf_template)
@@ -910,14 +941,14 @@ class OPFCreator(MetaInformation):
 
 
 class OPFTest(unittest.TestCase):
-    
+
     def setUp(self):
         self.stream = cStringIO.StringIO(
 '''\
 <?xml version="1.0"  encoding="UTF-8"?>
 <package version="2.0" xmlns="http://www.idpf.org/2007/opf" >
 <metadata xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:opf="http://www.idpf.org/2007/opf">
-    <dc:title>A Cool &amp; &copy; &#223; Title</dc:title>
+    <dc:title opf:file-as="Wow">A Cool &amp; &copy; &#223; Title</dc:title>
     <creator opf:role="aut" file-as="Monkey">Monkey Kitchen, Next</creator>
     <dc:subject>One</dc:subject><dc:subject>Two</dc:subject>
     <dc:identifier scheme="ISBN">123456789</dc:identifier>
@@ -932,34 +963,51 @@ class OPFTest(unittest.TestCase):
 '''
         )
         self.opf = OPF(self.stream, os.getcwd())
-        
+
-    def testReading(self):
+    def testReading(self, opf=None):
-        opf = self.opf
+        if opf is None:
+            opf = self.opf
         self.assertEqual(opf.title, u'A Cool & \xa9 \xdf Title')
         self.assertEqual(opf.authors, u'Monkey Kitchen,Next'.split(','))
         self.assertEqual(opf.author_sort, 'Monkey')
+        self.assertEqual(opf.title_sort, 'Wow')
         self.assertEqual(opf.tags, ['One', 'Two'])
         self.assertEqual(opf.isbn, '123456789')
         self.assertEqual(opf.series, 'A one book series')
-        self.assertEqual(opf.series_index, None)
+        self.assertEqual(opf.series_index, 1)
         self.assertEqual(list(opf.itermanifest())[0].get('href'), 'a ~ b')
-        
+
     def testWriting(self):
         for test in [('title', 'New & Title'), ('authors', ['One', 'Two']),
                      ('author_sort', "Kitchen"), ('tags', ['Three']),
-                     ('isbn', 'a'), ('rating', 3), ('series_index', 1)]:
+                     ('isbn', 'a'), ('rating', 3), ('series_index', 1),
+                     ('title_sort', 'ts')]:
             setattr(self.opf, *test)
-            self.assertEqual(getattr(self.opf, test[0]), test[1])
+            attr, val = test
-        
+            self.assertEqual(getattr(self.opf, attr), val)
+
         self.opf.render()
 
+    def testCreator(self):
+        opf = OPFCreator(os.getcwd(), self.opf)
+        buf = cStringIO.StringIO()
+        opf.render(buf)
+        raw = buf.getvalue()
+        self.testReading(opf=OPF(cStringIO.StringIO(raw), os.getcwd()))
+
+    def testSmartUpdate(self):
+        self.opf.smart_update(MetaInformation(self.opf))
+        self.testReading()
+
 def suite():
     return unittest.TestLoader().loadTestsFromTestCase(OPFTest)
-    
+
 def test():
     unittest.TextTestRunner(verbosity=2).run(suite())
 
+
 def option_parser():
+    from calibre.ebooks.metadata import get_parser
     parser = get_parser('opf')
     parser.add_option('--language', default=None, help=_('Set the dc:language field'))
     return parser
@@ -1006,7 +1054,7 @@ def main(args=sys.argv):
     print MetaInformation(OPF(open(opfpath, 'rb'), basedir))
     return 0
 
-    
+
 
 if __name__ == '__main__':
     sys.exit(main())

src/calibre/ebooks/mobi/mobiml.py

@@ -138,7 +138,8 @@ class MobiMLizer(object):
         return result
     
     def mobimlize_content(self, tag, text, bstate, istates):
-        bstate.content = True
+        if text or tag != 'br':
+            bstate.content = True
         istate = istates[-1]
         para = bstate.para
         if tag in SPECIAL_TAGS and not text:
@@ -188,11 +189,6 @@ class MobiMLizer(object):
                     vspace -= 1
             if istate.halign != 'auto':
                 para.attrib['align'] = istate.halign
-        if istate.ids:
-            last = bstate.body[-1]
-            for id in istate.ids:
-                last.addprevious(etree.Element(XHTML('a'), attrib={'id': id}))
-            istate.ids.clear()
         pstate = bstate.istate
         if tag in CONTENT_TAGS:
             bstate.inline = para
@@ -200,6 +196,11 @@ class MobiMLizer(object):
             etree.SubElement(para, XHTML(tag), attrib=istate.attrib)
         elif tag in TABLE_TAGS:
             para.attrib['valign'] = 'top'
+        if istate.ids:
+            last = bstate.body[-1]
+            for id in istate.ids:
+                last.addprevious(etree.Element(XHTML('a'), attrib={'id': id}))
+            istate.ids.clear()
         if not text:
             return
         if not pstate or istate != pstate:

src/calibre/ebooks/mobi/reader.py

@@ -121,6 +121,7 @@ class BookHeader(object):
             sublangid = (langcode >> 10) & 0xFF
             self.language = main_language.get(langid, 'ENGLISH')
             self.sublanguage = sub_language.get(sublangid, 'NEUTRAL')
+            self.mobi_version = struct.unpack('>I', raw[0x68:0x6c])[0]
             self.first_image_index = struct.unpack('>L', raw[0x6c:0x6c+4])[0]
             
             self.exth_flag, = struct.unpack('>L', raw[0x80:0x84])
@@ -132,11 +133,8 @@ class BookHeader(object):
             
 
 class MobiReader(object):
-    
     PAGE_BREAK_PAT = re.compile(r'(<[/]{0,1}mbp:pagebreak\s*[/]{0,1}>)+', re.IGNORECASE)
-    IMAGE_PATS     = map(re.compile, (r'\shirecindex=[\'"]{0,1}(\d+)[\'"]{0,1}', 
+    IMAGE_ATTRS = ('lowrecindex', 'recindex', 'hirecindex')
-                        r'\srecindex=[\'"]{0,1}(\d+)[\'"]{0,1}', 
-                        r'\slorecindex=[\'"]{0,1}(\d+)[\'"]{0,1}'))
     
     def __init__(self, filename_or_stream, verbose=False):
         self.verbose = verbose
@@ -247,6 +245,7 @@ class MobiReader(object):
         self.processed_html = re.sub(r'<div height="0(pt|px|ex|em|%){0,1}"></div>', '', self.processed_html)
         if self.book_header.ancient and '<html' not in self.mobi_html[:300].lower():
             self.processed_html = '<html><p>'+self.processed_html.replace('\n\n', '<p>')+'</html>'
+        self.processed_html = self.processed_html.replace('\r\n', '\n')
         self.processed_html = self.processed_html.replace('> <', '>\n<')
         for t, c in [('b', 'bold'), ('i', 'italic')]:
             self.processed_html = re.sub(r'(?i)<%s>'%t, r'<span class="%s">'%c, self.processed_html)
@@ -264,6 +263,7 @@ class MobiReader(object):
                     'x-large'  : '5',
                     'xx-large' : '6',
                     }
+        mobi_version = self.book_header.mobi_version
         for tag in root.iter(etree.Element):
             if tag.tag in ('country-region', 'place', 'placetype', 'placename',
                            'state', 'city'):
@@ -290,6 +290,11 @@ class MobiReader(object):
                 align = attrib.pop('align').strip()
                 if align:
                     styles.append('text-align: %s' % align)
+            if mobi_version == 1 and tag.tag == 'hr':
+                tag.tag = 'div'
+                styles.append('page-break-before: always')
+                styles.append('display: block')
+                styles.append('margin: 0')
             if styles:
                 attrib['style'] = '; '.join(styles)
                 
@@ -300,6 +305,17 @@ class MobiReader(object):
                 except ValueError:
                     if sz in size_map.keys():
                         attrib['size'] = size_map[sz]
+            if 'filepos-id' in attrib:
+                attrib['id'] = attrib.pop('filepos-id')
+            if 'filepos' in attrib:
+                filepos = int(attrib.pop('filepos'))
+                attrib['href'] = "#filepos%d" % filepos
+            if tag.tag == 'img':
+                recindex = None
+                for attr in self.IMAGE_ATTRS:
+                    recindex = attrib.pop(attr, None) or recindex
+                if recindex is not None:
+                    attrib['src'] = 'images/%s.jpg' % recindex
     
     def create_opf(self, htmlfile, guide=None):
         mi = self.book_header.exth.mi
@@ -399,38 +415,40 @@ class MobiReader(object):
             
     
     def replace_page_breaks(self):
-        self.processed_html = self.PAGE_BREAK_PAT.sub('<br style="page-break-after:always" />',
+        self.processed_html = self.PAGE_BREAK_PAT.sub(
-                                                      self.processed_html)
+            '<div style="page-break-after: always; margin: 0; display: block" />',
+            self.processed_html)
     
     def add_anchors(self):
         if self.verbose:
             print 'Adding anchors...'
         positions = set([])
-        link_pattern = re.compile(r'<[^<>]+filepos=[\'"]{0,1}(\d+)[^<>]*>', re.IGNORECASE)
+        link_pattern = re.compile(r'''<[^<>]+filepos=['"]{0,1}(\d+)[^<>]*>''',
+                                  re.IGNORECASE)
         for match in link_pattern.finditer(self.mobi_html):
             positions.add(int(match.group(1)))
-        positions = list(positions)
-        positions.sort()
         pos = 0
         self.processed_html = ''
-        for end in positions:
+        end_tag_re = re.compile(r'<\s*/')
+        for end in sorted(positions):
             if end == 0:
                 continue
             oend = end
             l = self.mobi_html.find('<', end)
             r = self.mobi_html.find('>', end)
-            if r > -1 and r < l: # Move out of tag
+            anchor = '<a id="filepos%d"></a>'
-                end = r+1
+            if r > -1 and (r < l or l == end or l == -1):
-            self.processed_html += self.mobi_html[pos:end] + '<a id="filepos%d" name="filepos%d"></a>'%(oend, oend) 
+                p = self.mobi_html.rfind('<', 0, end + 1)
+                if pos < end and p > -1 and \
+                   not end_tag_re.match(self.mobi_html[p:r]):
+                    anchor = ' filepos-id="filepos%d"'
+                    end = r
+                else:
+                    end = r + 1
+            self.processed_html += self.mobi_html[pos:end] + (anchor % oend)
             pos = end
-            
         self.processed_html += self.mobi_html[pos:]
-        fpat = re.compile(r'filepos=[\'"]{0,1}(\d+)[\'"]{0,1}', re.IGNORECASE)
+    
-        def fpos_to_href(match):
-            return fpat.sub('href="#filepos%d"'%int(match.group(1)), match.group())
-        self.processed_html = link_pattern.sub(fpos_to_href, 
-                                               self.processed_html)
-        
     def extract_images(self, processed_records, output_dir):
         if self.verbose:
             print 'Extracting images...'
@@ -454,19 +472,6 @@ class MobiReader(object):
             path = os.path.join(output_dir, '%05d.jpg'%image_index)
             self.image_names.append(os.path.basename(path))
             im.convert('RGB').save(open(path, 'wb'), format='JPEG')
-            
-        def fix_images(match):
-            tag = match.group()
-            for pat in self.IMAGE_PATS:
-                m = pat.search(tag)
-                if m:
-                    return pat.sub(' src="images/%s.jpg"'%m.group(1), tag)
-                    
-        
-        if hasattr(self, 'processed_html'):
-            self.processed_html = \
-            re.compile(r'<img (.*?)>', re.IGNORECASE|re.DOTALL)\
-                .sub(fix_images, self.processed_html)
 
 def get_metadata(stream):
     mr = MobiReader(stream)

src/calibre/ebooks/oeb/stylizer.py

@@ -109,6 +109,7 @@ class Stylizer(object):
     STYLESHEETS = {}
     
     def __init__(self, tree, path, oeb, profile=PROFILES['PRS505']):
+        self.oeb = oeb
         self.profile = profile
         self.logger = oeb.logger
         item = oeb.manifest.hrefs[path]
@@ -117,7 +118,7 @@ class Stylizer(object):
         stylesheets = [HTML_CSS_STYLESHEET]
         head = xpath(tree, '/h:html/h:head')[0]
         parser = cssutils.CSSParser()
-        parser.setFetcher(lambda path: ('utf-8', oeb.container.read(path)))
+        parser.setFetcher(self._fetch_css_file)
         for elem in head:
             if elem.tag == XHTML('style') and elem.text \
                and elem.get('type', CSS_MIME) in OEB_STYLES:
@@ -138,8 +139,7 @@ class Stylizer(object):
                 if path in self.STYLESHEETS:
                     stylesheet = self.STYLESHEETS[path]
                 else:
-                    data = XHTML_CSS_NAMESPACE
+                    data = self._fetch_css_file(path)[1]
-                    data += oeb.manifest.hrefs[path].data
                     stylesheet = parser.parseString(data, href=path)
                     stylesheet.namespaces['h'] = XHTML_NS
                     self.STYLESHEETS[path] = stylesheet
@@ -167,6 +167,14 @@ class Stylizer(object):
         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:
+            return (None, None)
+        data = hrefs[path].data
+        data = XHTML_CSS_NAMESPACE + data
+        return ('utf-8', data)
+    
     def flatten_rule(self, rule, href, index):
         results = []
         if isinstance(rule, CSSStyleRule):

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

@@ -13,13 +13,9 @@ from urlparse import urldefrag
 from lxml import etree
 import cssutils
 from calibre.ebooks.oeb.base import XPNSMAP, CSS_MIME, OEB_DOCS
+from calibre.ebooks.oeb.base import LINK_SELECTORS, CSSURL_RE
 from calibre.ebooks.oeb.base import urlnormalize
 
-LINK_SELECTORS = []
-for expr in ('//h:link/@href', '//h:img/@src', '//h:object/@data',
-             '//*/@xl:href'):
-    LINK_SELECTORS.append(etree.XPath(expr, namespaces=XPNSMAP))
-
 class ManifestTrimmer(object):
     def transform(self, oeb, context):
         oeb.logger.info('Trimming unused files from manifest...')
@@ -53,15 +49,13 @@ class ManifestTrimmer(object):
                             if found not in used:
                                 new.add(found)
                 elif item.media_type == CSS_MIME:
-                    def replacer(uri):
+                    for match in CSSURL_RE.finditer(item.data):
-                        absuri = item.abshref(urlnormalize(uri))
+                        href = match.group('url')
-                        if absuri in oeb.manifest.hrefs:
+                        href = item.abshref(urlnormalize(href))
+                        if href in oeb.manifest.hrefs:
                             found = oeb.manifest.hrefs[href]
                             if found not in used:
                                 new.add(found)
-                        return uri
-                    sheet = cssutils.parseString(item.data, href=item.href)
-                    cssutils.replaceUrls(sheet, replacer)
             used.update(new)
             unchecked = new
         for item in oeb.manifest.values():

src/calibre/gui2/dialogs/epub.py

@@ -18,7 +18,7 @@ from calibre.gui2 import error_dialog, choose_images, pixmap_to_data, ResizableD
 from calibre.ebooks.epub.from_any import SOURCE_FORMATS, config as epubconfig
 from calibre.ebooks.metadata import MetaInformation
 from calibre.ptempfile import PersistentTemporaryFile
-from calibre.ebooks.metadata.opf import OPFCreator
+from calibre.ebooks.metadata.opf2 import OPFCreator
 from calibre.ebooks.metadata import authors_to_string, string_to_authors
 
 
@@ -224,6 +224,7 @@ class Config(ResizableDialog, Ui_Dialog):
                     g.setValue(val)
                 elif isinstance(g, (QLineEdit, QTextEdit)):
                     getattr(g, 'setPlainText', g.setText)(val)
+                    getattr(g, 'setCursorPosition', lambda x: x)(0)
                 elif isinstance(g, QComboBox):
                     for value in pref.choices:
                         g.addItem(value)
@@ -253,7 +254,8 @@ class Config(ResizableDialog, Ui_Dialog):
                     self.source_format = d.format()
                 
     def accept(self):
-        for opt in ('chapter', 'level1_toc', 'level2_toc', 'level3_toc'):
+        for opt in ('chapter', 'level1_toc', 'level2_toc', 'level3_toc', 'page',
+                    'page_names'):
             text = unicode(getattr(self, 'opt_'+opt).text())
             if text:
                 try:

src/calibre/gui2/dialogs/epub.ui

@@ -493,6 +493,20 @@
                </property>
               </widget>
              </item>
+             <item row="7" column="0" >
+              <widget class="QCheckBox" name="opt_no_justification" >
+               <property name="text" >
+                <string>No text &amp;justification</string>
+               </property>
+              </widget>
+             </item>
+             <item row="8" column="0" >
+              <widget class="QCheckBox" name="opt_linearize_tables" >
+               <property name="text" >
+                <string>&amp;Linearize tables</string>
+               </property>
+              </widget>
+             </item>
             </layout>
            </item>
            <item>
@@ -510,7 +524,7 @@
           </layout>
          </widget>
          <widget class="QWidget" name="pagesetup_page" >
-          <layout class="QGridLayout" name="_13" >
+          <layout class="QGridLayout" name="gridLayout_7" >
            <item row="0" column="0" >
             <widget class="QLabel" name="profile_label" >
              <property name="text" >
@@ -531,6 +545,32 @@
              </property>
             </widget>
            </item>
+           <item row="1" column="0" >
+            <widget class="QLabel" name="source_profile_label" >
+             <property name="text" >
+              <string>&amp;Source profile:</string>
+             </property>
+             <property name="buddy" >
+              <cstring>opt_source_profile</cstring>
+             </property>
+            </widget>
+           </item>
+           <item row="1" column="1" >
+            <widget class="QComboBox" name="opt_source_profile" />
+           </item>
+           <item row="2" column="0" >
+            <widget class="QLabel" name="dest_profile_label" >
+             <property name="text" >
+              <string>&amp;Destination profile:</string>
+             </property>
+             <property name="buddy" >
+              <cstring>opt_dest_profile</cstring>
+             </property>
+            </widget>
+           </item>
+           <item row="2" column="1" >
+            <widget class="QComboBox" name="opt_dest_profile" />
+           </item>
            <item row="3" column="0" >
             <widget class="QLabel" name="label_12" >
              <property name="text" >
@@ -630,31 +670,72 @@
              </property>
             </widget>
            </item>
-           <item row="1" column="0" >
+           <item row="8" column="0" colspan="2" >
-            <widget class="QLabel" name="source_profile_label" >
+            <widget class="QGroupBox" name="page_map_box" >
-             <property name="text" >
+             <property name="title" >
-              <string>&amp;Source profile:</string>
+              <string>&amp;Page map</string>
-             </property>
-             <property name="buddy" >
-              <cstring>opt_source_profile</cstring>
              </property>
+             <layout class="QGridLayout" name="gridLayout" >
+              <item rowspan="2" row="0" column="0" colspan="4" >
+               <widget class="QLabel" name="label_23" >
+                <property name="sizePolicy" >
+                 <sizepolicy vsizetype="Minimum" hsizetype="Preferred" >
+                  <horstretch>0</horstretch>
+                  <verstretch>0</verstretch>
+                 </sizepolicy>
+                </property>
+                <property name="text" >
+                 <string>&lt;p>You can control how calibre detects page boundaries using a XPath expression. To learn how to use XPath expressions see the &lt;a href="http://calibre.kovidgoyal.net/user_manual/xpath.html">XPath tutorial&lt;/a>. The page boundaries are useful only if you want a mapping from pages in a paper book, to locations in the e-book. This controls where Adobe Digital Editions displays the page numbers in the right margin.&lt;/p></string>
+                </property>
+                <property name="wordWrap" >
+                 <bool>true</bool>
+                </property>
+                <property name="openExternalLinks" >
+                 <bool>true</bool>
+                </property>
+               </widget>
+              </item>
+              <item row="1" column="0" >
+               <widget class="QLabel" name="label_21" >
+                <property name="text" >
+                 <string>&amp;Boundary XPath:</string>
+                </property>
+                <property name="buddy" >
+                 <cstring>opt_page</cstring>
+                </property>
+               </widget>
+              </item>
+              <item row="1" column="1" >
+               <widget class="QLineEdit" name="opt_page" />
+              </item>
+              <item row="1" column="2" >
+               <widget class="QLabel" name="label_22" >
+                <property name="text" >
+                 <string>&amp;Name XPath:</string>
+                </property>
+                <property name="buddy" >
+                 <cstring>opt_page_names</cstring>
+                </property>
+               </widget>
+              </item>
+              <item row="1" column="3" >
+               <widget class="QLineEdit" name="opt_page_names" />
+              </item>
+             </layout>
             </widget>
            </item>
-           <item row="1" column="1" >
+           <item row="9" column="0" >
-            <widget class="QComboBox" name="opt_source_profile" />
+            <spacer name="verticalSpacer" >
-           </item>
+             <property name="orientation" >
-           <item row="2" column="0" >
+              <enum>Qt::Vertical</enum>
-            <widget class="QLabel" name="dest_profile_label" >
-             <property name="text" >
-              <string>&amp;Destination profile:</string>
              </property>
-             <property name="buddy" >
+             <property name="sizeHint" stdset="0" >
-              <cstring>opt_dest_profile</cstring>
+              <size>
+               <width>20</width>
+               <height>40</height>
+              </size>
              </property>
-            </widget>
+            </spacer>
-           </item>
-           <item row="2" column="1" >
-            <widget class="QComboBox" name="opt_dest_profile" />
            </item>
           </layout>
          </widget>
@@ -665,28 +746,11 @@
              <property name="title" >
               <string>Automatic &amp;chapter detection</string>
              </property>
-             <layout class="QGridLayout" name="gridLayout" >
+             <layout class="QVBoxLayout" name="verticalLayout_4" >
-              <item row="1" column="0" >
+              <item>
-               <widget class="QLabel" name="label_17" >
-                <property name="text" >
-                 <string>&amp;XPath:</string>
-                </property>
-                <property name="buddy" >
-                 <cstring>opt_chapter</cstring>
-                </property>
-               </widget>
-              </item>
-              <item row="1" column="1" >
-               <widget class="QLineEdit" name="opt_chapter" />
-              </item>
-              <item row="0" column="0" colspan="2" >
                <widget class="QLabel" name="label_8" >
                 <property name="text" >
-                 <string>&lt;!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0//EN" "http://www.w3.org/TR/REC-html40/strict.dtd">
+                 <string>&lt;p>You can control how calibre detects chapters using a XPath expression. To learn how to use XPath expressions see the &lt;a href="http://calibre.kovidgoyal.net/user_manual/xpath.html">XPath tutorial&lt;/a>&lt;/p></string>
-&lt;html>&lt;head>&lt;meta name="qrichtext" content="1" />&lt;style type="text/css">
-p, li { white-space: pre-wrap; }
-&lt;/style>&lt;/head>&lt;body style=" font-family:'DejaVu Sans'; font-size:10pt; font-weight:400; font-style:normal;">
-&lt;p style=" margin-top:12px; margin-bottom:12px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;">You can control how calibre detects chapters using a XPath expression. To learn how to use XPath expressions see the &lt;a href="https://calibre.kovidgoyal.net/user_manual/xpath.html">&lt;span style=" text-decoration: underline; color:#0000ff;">XPath tutorial&lt;/span>&lt;/a>&lt;/p>&lt;/body>&lt;/html></string>
                 </property>
                 <property name="textFormat" >
                  <enum>Qt::RichText</enum>
@@ -694,21 +758,41 @@ p, li { white-space: pre-wrap; }
                 <property name="wordWrap" >
                  <bool>true</bool>
                 </property>
-               </widget>
+                <property name="openExternalLinks" >
-              </item>
+                 <bool>true</bool>
-              <item row="2" column="1" >
-               <widget class="QComboBox" name="opt_chapter_mark" />
-              </item>
-              <item row="2" column="0" >
-               <widget class="QLabel" name="label_9" >
-                <property name="text" >
-                 <string>Chapter &amp;mark:</string>
-                </property>
-                <property name="buddy" >
-                 <cstring>opt_chapter_mark</cstring>
                 </property>
                </widget>
               </item>
+              <item>
+               <layout class="QHBoxLayout" name="horizontalLayout_3" >
+                <item>
+                 <widget class="QLabel" name="label_17" >
+                  <property name="text" >
+                   <string>&amp;XPath:</string>
+                  </property>
+                  <property name="buddy" >
+                   <cstring>opt_chapter</cstring>
+                  </property>
+                 </widget>
+                </item>
+                <item>
+                 <widget class="QLineEdit" name="opt_chapter" />
+                </item>
+                <item>
+                 <widget class="QLabel" name="label_9" >
+                  <property name="text" >
+                   <string>Chapter &amp;mark:</string>
+                  </property>
+                  <property name="buddy" >
+                   <cstring>opt_chapter_mark</cstring>
+                  </property>
+                 </widget>
+                </item>
+                <item>
+                 <widget class="QComboBox" name="opt_chapter_mark" />
+                </item>
+               </layout>
+              </item>
              </layout>
             </widget>
            </item>
@@ -834,7 +918,7 @@ p, li { white-space: pre-wrap; }
      </property>
     </widget>
    </item>
-   <item row="2" column="0" colspan="2" >
+   <item row="3" column="0" colspan="2" >
     <widget class="QDialogButtonBox" name="buttonBox" >
      <property name="orientation" >
       <enum>Qt::Horizontal</enum>

src/calibre/gui2/dialogs/mobi.py

@@ -17,4 +17,7 @@ class Config(_Config):
         self.profile_label.setVisible(False)
         self.opt_profile.setVisible(False)
         self.opt_dont_split_on_page_breaks.setVisible(False)
-        self.opt_preserve_tag_structure.setVisible(False)
+        self.opt_preserve_tag_structure.setVisible(False)
+        self.opt_linearize_tables.setVisible(False)
+        self.opt_no_justification.setVisible(False)
+        self.page_map_box.setVisible(False)

src/calibre/gui2/dialogs/recipelistview.py

@@ -1,16 +0,0 @@
-__license__   = 'GPL v3'
-__copyright__ = '2009, John Schember john@nachtimwald.com'
-'''
-List View for showing recipies. Allows for keyboad events when selecting new
-items.
-'''
-
-from PyQt4.Qt import QListView, SIGNAL
-            
-class RecipeListView(QListView):
-    def __init__(self, *args):
-        QListView.__init__(self, *args)
-        
-    def selectionChanged(self, selected, deselected):
-        self.emit(SIGNAL('itemChanged(QModelIndex)'), selected.indexes()[0])
-

src/calibre/gui2/dialogs/scheduler.py

@@ -10,8 +10,8 @@ Scheduler for automated recipe downloads
 import sys, copy, time
 from datetime import datetime, timedelta, date
 from PyQt4.Qt import QDialog, QApplication, QLineEdit, QPalette, SIGNAL, QBrush, \
-                     QColor, QAbstractListModel, Qt, QVariant, QFont, QIcon, \
+                     QColor, QAbstractItemModel, Qt, QVariant, QFont, QIcon, \
-                     QFile, QObject, QTimer, QMutex, QMenu, QAction, QTime
+                     QFile, QObject, QTimer, QMutex, QMenu, QAction, QTime, QModelIndex
 
 from calibre import english_sort
 from calibre.gui2.dialogs.scheduler_ui import Ui_Dialog
@@ -30,6 +30,7 @@ class Recipe(object):
         self.id                 = id
         self.title              = getattr(recipe_class, 'title', None)
         self.description        = getattr(recipe_class, 'description', None)
+        self.language           = getattr(recipe_class, 'language', _('Unknown'))
         self.last_downloaded    = datetime.fromordinal(1)
         self.downloading        = False
         self.builtin            = builtin
@@ -86,12 +87,12 @@ def load_recipes():
         recipes.append(r)
     return recipes
 
-class RecipeModel(QAbstractListModel, SearchQueryParser):
+class RecipeModel(QAbstractItemModel, SearchQueryParser):
     
     LOCATIONS = ['all']
     
     def __init__(self, db, *args):
-        QAbstractListModel.__init__(self, *args)
+        QAbstractItemModel.__init__(self, *args)
         SearchQueryParser.__init__(self)
         self.default_icon = QIcon(':/images/news.svg')
         self.custom_icon = QIcon(':/images/user_profile.svg')
@@ -99,8 +100,11 @@ class RecipeModel(QAbstractListModel, SearchQueryParser):
         for x in db.get_recipes():
             recipe = compile_recipe(x[1])
             self.recipes.append(Recipe(x[0], recipe, False))
-        self.refresh()    
+        self.refresh()
-        self._map = list(range(len(self.recipes)))
+        self.bold_font = QFont()
+        self.bold_font.setBold(True)
+        self.bold_font = QVariant(self.bold_font)
+        
     
     def refresh(self):
         sr = load_recipes()
@@ -110,7 +114,35 @@ class RecipeModel(QAbstractListModel, SearchQueryParser):
                 recipe.last_downloaded = sr[sr.index(recipe)].last_downloaded
         
         self.recipes.sort()
+        self.num_of_recipes = len(self.recipes)
         
+        self.category_map = {}
+        for r in self.recipes:
+            category = getattr(r, 'language', _('Unknown'))
+            if not r.builtin:
+                category = _('Custom')
+            if r.schedule is not None:
+                category = _('Scheduled')
+            if category not in self.category_map.keys():
+                self.category_map[category] = []
+            self.category_map[category].append(r)
+            
+        self.categories = sorted(self.category_map.keys(), cmp=self.sort_categories)
+        self._map = dict(self.category_map)
+        
+    def sort_categories(self, x, y):
+        
+        def decorate(x):
+            if x == _('Scheduled'):
+                x = '0' + x
+            elif x == _('Custom'):
+                x = '1' + x
+            else:
+                x = '2' + x
+            return x
+        
+        return cmp(decorate(x), decorate(y))
+                
     
     def universal_set(self):
         return set(self.recipes)
@@ -129,48 +161,64 @@ class RecipeModel(QAbstractListModel, SearchQueryParser):
         try:
             results = self.parse(unicode(query))
         except ParseException:
-            self._map = list(range(len(self.recipes)))
+            self._map = dict(self.category_map)
         else:
-            self._map = []
+            self._map = {}
-            for i, recipe in enumerate(self.recipes):
+            for category in self.categories:
-                if recipe in results:
+                self._map[category] = []
-                    self._map.append(i)
+                for recipe in self.category_map[category]:
+                    if recipe in results:
+                        self._map[category].append(recipe)
         self.reset()
     
     def resort(self):
         self.recipes.sort()
         self.reset()
+    
+    def index(self, row, column, parent):
+        return self.createIndex(row, column, parent.row() if parent.isValid() else -1)
+    
+    def parent(self, index):
+        if index.internalId() == -1:
+            return QModelIndex()
+        return self.createIndex(index.internalId(), 0, -1)
+    
+    def columnCount(self, parent):
+        if not parent.isValid() or not parent.parent().isValid():
+            return 1
+        return 0
+    
+    def rowCount(self, parent):
+        if not parent.isValid():
+            return len(self.categories)
+        if not parent.parent().isValid():
+            category = self.categories[parent.row()]
+            return len(self._map[category])
+        return 0
         
-    def columnCount(self, *args):
-        return 1
-    
-    def rowCount(self, *args):
-        return len(self._map)
-    
     def data(self, index, role):
-        recipe = self.recipes[self._map[index.row()]]
+        if index.parent().isValid():
-        if role == Qt.FontRole:
+            category = self.categories[index.parent().row()]
-            if recipe.schedule is not None:
+            recipe   = self._map[category][index.row()]
-                font = QFont()
+            if role == Qt.DisplayRole:
-                font.setBold(True)
+                return QVariant(recipe.title)
-                return QVariant(font)
+            elif role == Qt.UserRole:
-            if not recipe.builtin:
+                return recipe
-                font = QFont()
+            elif role == Qt.DecorationRole:
-                font.setItalic(True)
+                icon = self.default_icon
-                return QVariant(font)
+                icon_path = (':/images/news/%s.png'%recipe.id).replace('recipe_', '') 
-        elif role == Qt.DisplayRole:
+                if not recipe.builtin:
-            return QVariant(recipe.title)
+                    icon = self.custom_icon
-        elif role == Qt.UserRole:
+                elif QFile().exists(icon_path):
-            return recipe
+                    icon = QIcon(icon_path)
-        elif role == Qt.DecorationRole:
+                return QVariant(icon)
-            icon = self.default_icon
+        else:
-            icon_path = (':/images/news/%s.png'%recipe.id).replace('recipe_', '') 
+            category = self.categories[index.row()]
-            if not recipe.builtin:
+            if role == Qt.DisplayRole:
-                icon = self.custom_icon
+                num = len(self._map[category])
-            elif QFile().exists(icon_path):
+                return QVariant(category + ' [%d]'%num)
-                icon = QIcon(icon_path)
+            elif role == Qt.FontRole:
-            return QVariant(icon)
+                return self.bold_font
-        
         return NONE
     
     def update_recipe_schedule(self, recipe):
@@ -241,7 +289,7 @@ class SchedulerDialog(QDialog, Ui_Dialog):
         self._model = RecipeModel(db)
         self.current_recipe = None
         self.recipes.setModel(self._model)
-        self.connect(self.recipes, SIGNAL('itemChanged(QModelIndex)'), self.show_recipe)
+        self.recipes.currentChanged = self.currentChanged
         self.connect(self.username, SIGNAL('textEdited(QString)'), self.set_account_info)
         self.connect(self.password, SIGNAL('textEdited(QString)'), self.set_account_info)
         self.connect(self.schedule, SIGNAL('stateChanged(int)'), self.do_schedule)
@@ -257,10 +305,14 @@ class SchedulerDialog(QDialog, Ui_Dialog):
         self.connect(self.download, SIGNAL('clicked()'), self.download_now)
         self.search.setFocus(Qt.OtherFocusReason)
         self.old_news.setValue(gconf['oldest_news'])
-        self.rnumber.setText(_('%d recipes')%self._model.rowCount(None))
+        self.rnumber.setText(_('%d recipes')%self._model.num_of_recipes)
         for day in (_('day'), _('Monday'), _('Tuesday'), _('Wednesday'), 
                     _('Thursday'), _('Friday'), _('Saturday'), _('Sunday')):
             self.day.addItem(day)
+    
+    def currentChanged(self, current, previous):
+        if current.parent().isValid():
+            self.show_recipe(current)
         
     def download_now(self):
         recipe = self._model.data(self.recipes.currentIndex(), Qt.UserRole)
@@ -304,6 +356,7 @@ class SchedulerDialog(QDialog, Ui_Dialog):
                 hour, minute = t.hour(), t.minute()
                 recipe.schedule = encode_schedule(day_of_week, hour, minute)
         else:
+            recipe.schedule = None
             if recipe in recipes:
                 recipes.remove(recipe)
         save_recipes(recipes)
@@ -432,7 +485,7 @@ class Scheduler(QObject):
                     day_matches = day > 6 or day == now.tm_wday
                     tnow = now.tm_hour*60 + now.tm_min
                     matches = day_matches and (hour*60+minute) < tnow
-                    if matches and nowt.toordinal() < date.today().toordinal():
+                    if matches and recipe.last_downloaded.toordinal() < date.today().toordinal():
                         needs_downloading.add(recipe)
                 
             self.debug('Needs downloading:', needs_downloading)
@@ -464,7 +517,7 @@ class Scheduler(QObject):
                 recipe = self.recipes[self.recipes.index(recipe)]
             now = datetime.utcnow()
             d = now - recipe.last_downloaded
-            if recipe.schedule is not None:
+            if recipe.schedule is not None and recipe.schedule < 1e4:
                 interval = timedelta(days=recipe.schedule)
                 if abs(d - interval) < timedelta(hours=1):
                     recipe.last_downloaded += interval
@@ -487,7 +540,7 @@ class Scheduler(QObject):
             if recipe not in self.queue:
                 self.do_download(recipe)
         finally:
-            self.lock.unlock()    
+            self.lock.unlock()
     
     def refresh_schedule(self, recipes):
         self.recipes = recipes

src/calibre/gui2/dialogs/scheduler.ui

@@ -24,8 +24,20 @@
      </property>
      <layout class="QVBoxLayout" name="verticalLayout" >
       <item>
-       <widget class="RecipeListView" name="recipes" >
+       <widget class="QTreeView" name="recipes" >
-        <property name="alternatingRowColors" >
+        <property name="showDropIndicator" stdset="0" >
+         <bool>false</bool>
+        </property>
+        <property name="iconSize" >
+         <size>
+          <width>16</width>
+          <height>16</height>
+         </size>
+        </property>
+        <property name="animated" >
+         <bool>true</bool>
+        </property>
+        <property name="headerHidden" >
          <bool>true</bool>
         </property>
        </widget>
@@ -321,13 +333,6 @@
    </item>
   </layout>
  </widget>
- <customwidgets>
-  <customwidget>
-   <class>RecipeListView</class>
-   <extends>QListView</extends>
-   <header>recipelistview.h</header>
-  </customwidget>
- </customwidgets>
  <resources>
   <include location="../images.qrc" />
  </resources>

src/calibre/gui2/dialogs/search.ui

@@ -114,6 +114,9 @@
      <property name="text" >
       <string>See the &lt;a href="http://calibre.kovidgoyal.net/user_manual/gui.html#the-search-interface">User Manual&lt;/a> for more help</string>
      </property>
+     <property name="openExternalLinks" >
+      <bool>true</bool>
+     </property>
     </widget>
    </item>
    <item>

src/calibre/gui2/main.py

@@ -115,16 +115,11 @@ class Main(MainWindow, Ui_MainWindow):
         self.connect(self.donate_action, SIGNAL('triggered(bool)'), self.donate)
         self.connect(self.restore_action, SIGNAL('triggered(bool)'), lambda c : self.show())
         self.connect(self.action_show_book_details, SIGNAL('triggered(bool)'), self.show_book_info)
-        def restart_app(c):
+        self.connect(self.action_restart, SIGNAL('triggered(bool)'), 
-            self.quit(None, restart=True)
+                     lambda c : self.quit(None, restart=True))
-        self.connect(self.action_restart, SIGNAL('triggered(bool)'), restart_app)
+        self.connect(self.system_tray_icon, SIGNAL('activated(QSystemTrayIcon::ActivationReason)'), 
-        def sta(r):
+                     self.system_tray_icon_activated)
-            if r == QSystemTrayIcon.Trigger:
+        self.tool_bar.contextMenuEvent = self.no_op
-                self.hide() if self.isVisible() else self.show()
-        self.connect(self.system_tray_icon, SIGNAL('activated(QSystemTrayIcon::ActivationReason)'), sta)
-        def tcme(self, *args):
-            pass
-        self.tool_bar.contextMenuEvent = tcme
         ####################### Location View ########################
         QObject.connect(self.location_view, SIGNAL('location_selected(PyQt_PyObject)'),
                         self.location_selected)
@@ -165,15 +160,11 @@ class Main(MainWindow, Ui_MainWindow):
         sm.addSeparator()
         sm.addAction(_('Send to storage card by default'))
         sm.actions()[-1].setCheckable(True)
-        def default_sync(checked):
+        QObject.connect(sm.actions()[-1], SIGNAL('toggled(bool)'), 
-            config.set('send_to_storage_card_by_default', bool(checked))
+                        self.do_default_sync)
-            QObject.disconnect(self.action_sync, SIGNAL("triggered(bool)"), self.sync_to_main_memory)
-            QObject.disconnect(self.action_sync, SIGNAL("triggered(bool)"), self.sync_to_card)
-            QObject.connect(self.action_sync, SIGNAL("triggered(bool)"), self.sync_to_card if checked else self.sync_to_main_memory)
-        QObject.connect(sm.actions()[-1], SIGNAL('toggled(bool)'), default_sync)
 
         sm.actions()[-1].setChecked(config.get('send_to_storage_card_by_default'))
-        default_sync(sm.actions()[-1].isChecked())
+        self.do_default_sync(sm.actions()[-1].isChecked())
         self.sync_menu = sm # Needed
         md = QMenu()
         md.addAction(_('Edit metadata individually'))
@@ -294,7 +285,7 @@ class Main(MainWindow, Ui_MainWindow):
         self.stack.setCurrentIndex(0)
         try:
             db = LibraryDatabase2(self.library_path)
-        except OSError, err:
+        except Exception, err:
             error_dialog(self, _('Bad database location'), unicode(err)).exec_()
             dir = unicode(QFileDialog.getExistingDirectory(self,
                             _('Choose a location for your ebook library.'), os.path.expanduser('~')))
@@ -371,6 +362,32 @@ class Main(MainWindow, Ui_MainWindow):
         self.connect(self.action_news, SIGNAL('triggered(bool)'), self.scheduler.show_dialog)
         self.location_view.setCurrentIndex(self.location_view.model().index(0))
     
+    def no_op(self, *args):
+        pass
+    
+    def system_tray_icon_activated(self, r):
+        if r == QSystemTrayIcon.Trigger:
+            if self.isVisible():
+                for window in QApplication.topLevelWidgets():
+                    if isinstance(window, (MainWindow, QDialog)) and window.isVisible():
+                        window.hide()
+                        setattr(window, '__systray_minimized', True)
+            else:
+                for window in QApplication.topLevelWidgets():
+                    if getattr(window, '__systray_minimized', False):
+                        window.show()
+                        setattr(window, '__systray_minimized', False)
+                         
+    
+    def do_default_sync(self, checked):
+        config.set('send_to_storage_card_by_default', bool(checked))
+        QObject.disconnect(self.action_sync, SIGNAL("triggered(bool)"), 
+                           self.sync_to_main_memory)
+        QObject.disconnect(self.action_sync, SIGNAL("triggered(bool)"), 
+                           self.sync_to_card)
+        QObject.connect(self.action_sync, SIGNAL("triggered(bool)"), 
+                        self.sync_to_card if checked else self.sync_to_main_memory)
+    
     def change_output_format(self, x):
         of = unicode(x).strip()
         if of != prefs['output_format']:
@@ -1426,10 +1443,10 @@ class Main(MainWindow, Ui_MainWindow):
     def donate(self, *args):
         BUTTON = '''
         <form action="https://www.paypal.com/cgi-bin/webscr" method="post">
-            <input type="hidden" name="cmd" value="_s-xclick">
+            <input type="hidden" name="cmd" value="_s-xclick" />
-            <input type="hidden" name="hosted_button_id" value="1335186">
+            <input type="hidden" name="hosted_button_id" value="3029467" />
-            <input type="image" src="https://www.paypal.com/en_US/i/btn/btn_donateCC_LG.gif" border="0" name="submit" alt="">
+            <input type="image" src="https://www.paypal.com/en_US/i/btn/btn_donateCC_LG.gif" border="0" name="submit" alt="Donate to support calibre development" />
-            <img alt="" border="0" src="https://www.paypal.com/en_US/i/scr/pixel.gif" width="1" height="1">
+            <img alt="" border="0" src="https://www.paypal.com/en_US/i/scr/pixel.gif" width="1" height="1" />
         </form>
         '''
         MSG = _('is the result of the efforts of many volunteers from all over the world. If you find it useful, please consider donating to support its development.')

src/calibre/library/database2.py

@@ -27,15 +27,6 @@ from calibre.customize.ui import run_plugins_on_import
 from calibre import sanitize_file_name
 
 copyfile = os.link if hasattr(os, 'link') else shutil.copyfile
-iscaseinsensitive = iswindows or isosx
-
-def normpath(x):
-    # The builtin os.path.normcase doesn't work on OS X
-    x = os.path.abspath(x)
-    if iscaseinsensitive:
-        x = x.lower()
-    return x
-
 
 FIELD_MAP = {'id':0, 'title':1, 'authors':2, 'publisher':3, 'rating':4, 'timestamp':5, 
              'size':6, 'tags':7, 'comments':8, 'series':9, 'series_index':10,
@@ -355,6 +346,8 @@ class LibraryDatabase2(LibraryDatabase):
         if isinstance(self.dbpath, unicode):
             self.dbpath = self.dbpath.encode(filesystem_encoding)
         self.connect()
+        self.is_case_sensitive = not iswindows and not isosx and \
+            not os.path.exists(self.dbpath.replace('metadata.db', 'MeTAdAtA.dB'))
         # Upgrade database 
         while True:
             meth = getattr(self, 'upgrade_version_%d'%self.user_version, None)
@@ -488,6 +481,16 @@ class LibraryDatabase2(LibraryDatabase):
         name   = title + ' - ' + author
         return name
     
+    def rmtree(self, path):
+        if not self.normpath(self.library_path).startswith(self.normpath(path)):
+            shutil.rmtree(path)
+    
+    def normpath(self, path):
+        path = os.path.abspath(os.path.realpath(path))
+        if not self.is_case_sensitive:
+            path = path.lower()
+        return path
+    
     def set_path(self, index, index_is_id=False):
         '''
         Set the path to the directory containing this books files based on its
@@ -531,11 +534,11 @@ class LibraryDatabase2(LibraryDatabase):
         self.data.set(id, FIELD_MAP['path'], path, row_is_id=True)
         # Delete not needed directories
         if current_path and os.path.exists(spath):
-            if normpath(spath) != normpath(tpath):
+            if self.normpath(spath) != self.normpath(tpath):
-                shutil.rmtree(spath)
+                self.rmtree(spath)
                 parent  = os.path.dirname(spath)
                 if len(os.listdir(parent)) == 0:
-                    shutil.rmtree(parent)
+                    self.rmtree(parent)
             
     def add_listener(self, listener):
         '''
@@ -698,10 +701,10 @@ class LibraryDatabase2(LibraryDatabase):
         path = os.path.join(self.library_path, self.path(id, index_is_id=True))
         self.data.remove(id)
         if os.path.exists(path):
-            shutil.rmtree(path)
+            self.rmtree(path)
             parent = os.path.dirname(path)
             if len(os.listdir(parent)) == 0:
-                shutil.rmtree(parent)
+                self.rmtree(parent)
         self.conn.execute('DELETE FROM books WHERE id=?', (id,))
         self.conn.commit()
         self.clean()

src/calibre/manual/faq.rst

@@ -102,7 +102,7 @@ Device Integration
 
 What devices does |app| support?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-At the moment |app| has full support for the SONY PRS 500/505/700, Cybook Gen 3 as well as the iPhone. In addition, using the :guilabel:`Save to disk` function you can use it with any ebook reader that exports itself as a USB disk.
+At the moment |app| has full support for the SONY PRS 500/505/700, Cybook Gen 3, Amazon Kindle as well as the iPhone. In addition, using the :guilabel:`Save to disk` function you can use it with any ebook reader that exports itself as a USB disk.
 
 I used |app| to transfer some books to my reader, and now the SONY software hangs every time I connect the reader?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

src/calibre/parallel.py

@@ -161,7 +161,7 @@ class WorkerMother(object):
             self.executable = self.gui_executable = sys.executable
             self.prefix = ''
             if isfrozen:
-                fd = getattr(sys, 'frameworks_dir')
+                fd = os.path.realpath(getattr(sys, 'frameworks_dir'))
                 contents = os.path.dirname(fd)
                 self.gui_executable = os.path.join(contents, 'MacOS',
                                                os.path.basename(sys.executable))

src/calibre/trac/donations/server.py

@@ -196,7 +196,7 @@ class Server(object):
     
     def calculate_month_trend(self, days=31):
         stats = self.get_slice(date.today()-timedelta(days=days-1), date.today())
-        fig = plt.figure(2, (8, 3), 96)#, facecolor, edgecolor, frameon, FigureClass)
+        fig = plt.figure(2, (12, 4), 96)#, facecolor, edgecolor, frameon, FigureClass)
         ax = fig.add_subplot(111)
         x = list(range(days-1, -1, -1))
         y = stats.daily_totals
@@ -205,6 +205,17 @@ class Server(object):
         ax.set_ylabel('Income ($)')
         ax.hlines([stats.daily_average], 0, days-1)
         ax.set_xlim([0, days-1])
+        text = u'''\
+Total: $%(total).2f
+Daily average: $%(da).2f \u00b1 %(dd).2f
+Average contribution: $%(ac).2f \u00b1 %(ad).2f
+Donors per day: %(dpd).2f
+        '''%dict(total=stats.total, da=stats.daily_average, 
+                 dd=stats.daily_deviation, ac=stats.average,
+                 ad=stats.average_deviation,
+                 dpd=len(stats.totals)/float(stats.period.days),
+             )
+        text = ax.annotate(text, (0.6, 0.65), textcoords='axes fraction')
         fig.savefig(self.MONTH_TRENDS)
     
     def calculate_trend(self):
@@ -223,7 +234,7 @@ class Server(object):
         x = [m.min for m in _months]
         y = [m.total for m in _months]
         ml   = mdates.MonthLocator() # every month
-        fig = plt.figure(1, (8, 3), 96)#, facecolor, edgecolor, frameon, FigureClass)
+        fig = plt.figure(1, (8, 4), 96)#, facecolor, edgecolor, frameon, FigureClass)
         ax = fig.add_subplot(111)
         ax.bar(x, y, align='center', width=20, color='g')
         ax.xaxis.set_major_locator(ml)

src/calibre/trac/plugins/templates/binary.html

@@ -23,15 +23,14 @@
       While you wait for the download to complete, please consider donating to support the development
       of ${app}.
       <div>
-        <form action="https://www.paypal.com/cgi-bin/webscr" method="post">
+          <form action="https://www.paypal.com/cgi-bin/webscr" method="post">
             <input type="hidden" name="cmd" value="_s-xclick" />
-            <input type="image" src="https://www.paypal.com/en_US/i/btn/btn_donateCC_LG.gif" border="0" name="submit" alt="PayPal - The safer, easier way to pay online!" />
+            <input type="hidden" name="hosted_button_id" value="3029289" />
+            <input type="image" src="https://www.paypal.com/en_US/i/btn/btn_donateCC_LG.gif" border="0" name="submit" alt="Donate to support calibre development" />
             <img alt="" border="0" src="https://www.paypal.com/en_US/i/scr/pixel.gif" width="1" height="1" />
-            <input type="hidden" name="encrypted" value="-----BEGIN PKCS7-----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-----END PKCS7-----" />
+          </form>
-        </form>
+          <br />
-        
+      </div>
-      </div>        
-      <br />
       
       <h2>Note</h2>
       <div class="note">$note</div>

src/calibre/trac/plugins/templates/distro.html

@@ -57,11 +57,11 @@ python setup.py build && sudo python setup.py install
       While you wait for the installation to complete, please consider donating to support the development of ${distro.app}.
         <div>
             <form action="https://www.paypal.com/cgi-bin/webscr" method="post">
-            <input type="hidden" name="cmd" value="_s-xclick" />
+                <input type="hidden" name="cmd" value="_s-xclick" />
-            <input type="image" src="https://www.paypal.com/en_US/i/btn/btn_donateCC_LG.gif" border="0" name="submit" alt="PayPal - The safer, easier way to pay online!" />
+                <input type="hidden" name="hosted_button_id" value="3029289" />
-            <img alt="" border="0" src="https://www.paypal.com/en_US/i/scr/pixel.gif" width="1" height="1" />
+                <input type="image" src="https://www.paypal.com/en_US/i/btn/btn_donateCC_LG.gif" border="0" name="submit" alt="Donate to support calibre development" />
-            <input type="hidden" name="encrypted" value="-----BEGIN PKCS7-----MIIHbwYJKoZIhvcNAQcEoIIHYDCCB1wCAQExggEwMIIBLAIBADCBlDCBjjELMAkGA1UEBhMCVVMxCzAJBgNVBAgTAkNBMRYwFAYDVQQHEw1Nb3VudGFpbiBWaWV3MRQwEgYDVQQKEwtQYXlQYWwgSW5jLjETMBEGA1UECxQKbGl2ZV9jZXJ0czERMA8GA1UEAxQIbGl2ZV9hcGkxHDAaBgkqhkiG9w0BCQEWDXJlQHBheXBhbC5jb20CAQAwDQYJKoZIhvcNAQEBBQAEgYBn7jneGiSLVO8rcDrBtOUXL+HftY+CiC47hTntwICio6qqpLKezIryyG8tKcjY58Rcocur/kDwljEutIafVG7XRA7BJL9eZdHAZsZdX04f4dApzkWwR9w6GQhj0kwmO2ZNE878UcgGZBve4qQKWM8bf2pMY7vJwCNoo6ozpIi3VTELMAkGBSsOAwIaBQAwgewGCSqGSIb3DQEHATAUBggqhkiG9w0DBwQIBTALt7s1gJmAgcjEAwUMRYeIdIOE/yi0Y5vrVKBFxOUCbqTx/lu3Rk4EHsODZXLHT+BDA5WSWYO3AXfv2Lmlv1kJ7jWrjUVirYoQ5M4qdIhY9DtvPioIMMRoTJmYM9JKH8n2TWcjJ1XIzIuDP4zn8/Ya9hap3RHOrj2RBj89g7iSuFRsjoA0PYZgtWAKwR7g3LLpjRachn041JO55BEd3YWUgorNQeo3WEHgowLFfTWgFFePkm8OoWA1klWkYp4S07IhX5NaRc8OegkdshpkiIHGAKCCA4cwggODMIIC7KADAgECAgEAMA0GCSqGSIb3DQEBBQUAMIGOMQswCQYDVQQGEwJVUzELMAkGA1UECBMCQ0ExFjAUBgNVBAcTDU1vdW50YWluIFZpZXcxFDASBgNVBAoTC1BheVBhbCBJbmMuMRMwEQYDVQQLFApsaXZlX2NlcnRzMREwDwYDVQQDFAhsaXZlX2FwaTEcMBoGCSqGSIb3DQEJARYNcmVAcGF5cGFsLmNvbTAeFw0wNDAyMTMxMDEzMTVaFw0zNTAyMTMxMDEzMTVaMIGOMQswCQYDVQQGEwJVUzELMAkGA1UECBMCQ0ExFjAUBgNVBAcTDU1vdW50YWluIFZpZXcxFDASBgNVBAoTC1BheVBhbCBJbmMuMRMwEQYDVQQLFApsaXZlX2NlcnRzMREwDwYDVQQDFAhsaXZlX2FwaTEcMBoGCSqGSIb3DQEJARYNcmVAcGF5cGFsLmNvbTCBnzANBgkqhkiG9w0BAQEFAAOBjQAwgYkCgYEAwUdO3fxEzEtcnI7ZKZL412XvZPugoni7i7D7prCe0AtaHTc97CYgm7NsAtJyxNLixmhLV8pyIEaiHXWAh8fPKW+R017+EmXrr9EaquPmsVvTywAAE1PMNOKqo2kl4Gxiz9zZqIajOm1fZGWcGS0f5JQ2kBqNbvbg2/Za+GJ/qwUCAwEAAaOB7jCB6zAdBgNVHQ4EFgQUlp98u8ZvF71ZP1LXChvsENZklGswgbsGA1UdIwSBszCBsIAUlp98u8ZvF71ZP1LXChvsENZklGuhgZSkgZEwgY4xCzAJBgNVBAYTAlVTMQswCQYDVQQIEwJDQTEWMBQGA1UEBxMNTW91bnRhaW4gVmlldzEUMBIGA1UEChMLUGF5UGFsIEluYy4xEzARBgNVBAsUCmxpdmVfY2VydHMxETAPBgNVBAMUCGxpdmVfYXBpMRwwGgYJKoZIhvcNAQkBFg1yZUBwYXlwYWwuY29tggEAMAwGA1UdEwQFMAMBAf8wDQYJKoZIhvcNAQEFBQADgYEAgV86VpqAWuXvX6Oro4qJ1tYVIT5DgWpE692Ag422H7yRIr/9j/iKG4Thia/Oflx4TdL+IFJBAyPK9v6zZNZtBgPBynXb048hsP16l2vi0k5Q2JKiPDsEfBhGI+HnxLXEaUWAcVfCsQFvd2A1sxRr67ip5y2wwBelUecP3AjJ+YcxggGaMIIBlgIBATCBlDCBjjELMAkGA1UEBhMCVVMxCzAJBgNVBAgTAkNBMRYwFAYDVQQHEw1Nb3VudGFpbiBWaWV3MRQwEgYDVQQKEwtQYXlQYWwgSW5jLjETMBEGA1UECxQKbGl2ZV9jZXJ0czERMA8GA1UEAxQIbGl2ZV9hcGkxHDAaBgkqhkiG9w0BCQEWDXJlQHBheXBhbC5jb20CAQAwCQYFKw4DAhoFAKBdMBgGCSqGSIb3DQEJAzELBgkqhkiG9w0BBwEwHAYJKoZIhvcNAQkFMQ8XDTA4MDQzMDE1MzkyMlowIwYJKoZIhvcNAQkEMRYEFJSI9/zWx7TUlKPY7kLjnvzB1h6sMA0GCSqGSIb3DQEBAQUABIGAikZNCmQdkWPdfmYnGqOb1f65ViaK0zjHf50azvsigWQLlhHqJ3PgB+jEJH3JU9Pm9M4wgiK23Bg2oIGuIsAfQkYO9mw/HjtDtOQHqXyZZbrM32YGtNWUD4ynakLYnaz7OnPl40aTPD4iDApgsGcj1oMdmw7KA2E9J0l2J9iJXF4=-----END PKCS7-----" />
+                <img alt="" border="0" src="https://www.paypal.com/en_US/i/scr/pixel.gif" width="1" height="1" />
-            </form>
+          </form>
         </div>
     </div>
   </body>

src/calibre/translations/bg.po

@@ -13,7 +13,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 "Generated-By: pygettext.py 1.5\n"
 

src/calibre/translations/ca.po

@@ -17,7 +17,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 
 #: /home/kovid/work/calibre/src/calibre/customize/__init__.py:41

src/calibre/translations/cs.po

@@ -14,7 +14,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 
 #: /home/kovid/work/calibre/src/calibre/customize/__init__.py:41

src/calibre/translations/de.po

@@ -14,7 +14,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 "Generated-By: pygettext.py 1.5\n"
 

src/calibre/translations/el.po

@@ -14,7 +14,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 
 #: /home/kovid/work/calibre/src/calibre/customize/__init__.py:41

src/calibre/translations/es.po

@@ -17,7 +17,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 
 #: /home/kovid/work/calibre/src/calibre/customize/__init__.py:41

src/calibre/translations/fr.po

@@ -13,7 +13,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 "Generated-By: pygettext.py 1.5\n"
 

src/calibre/translations/gl.po

@@ -14,7 +14,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 
 #: /home/kovid/work/calibre/src/calibre/customize/__init__.py:41

src/calibre/translations/hu.po

@@ -8,13 +8,13 @@ msgstr ""
 "Project-Id-Version: calibre\n"
 "Report-Msgid-Bugs-To: FULL NAME <EMAIL@ADDRESS>\n"
 "POT-Creation-Date: 2009-01-27 01:54+0000\n"
-"PO-Revision-Date: 2009-01-23 21:22+0000\n"
+"PO-Revision-Date: 2009-02-04 20:39+0000\n"
-"Last-Translator: Molnár Gábor <csirkus@gmail.com>\n"
+"Last-Translator: Kovid Goyal <Unknown>\n"
 "Language-Team: Hungarian <hu@li.org>\n"
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 
 #: /home/kovid/work/calibre/src/calibre/customize/__init__.py:41
@@ -142,7 +142,7 @@ msgstr "Tömörített könyvek metaadatait is olvassa be"
 
 #: /home/kovid/work/calibre/src/calibre/customize/builtins.py:196
 msgid "Read metadata from ebooks in RAR archives"
-msgstr ""
+msgstr "Metaadatok olvasása a RAR-ral tömörített könyvekből is"
 
 #: /home/kovid/work/calibre/src/calibre/customize/builtins.py:207
 #: /home/kovid/work/calibre/src/calibre/customize/builtins.py:217
@@ -274,7 +274,7 @@ msgstr ""
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/epub/__init__.py:110
 msgid "Control auto-detection of document structure."
-msgstr ""
+msgstr "Dokumentum-struktúra automatikus felismerése."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/epub/__init__.py:112
 msgid ""
@@ -832,6 +832,9 @@ msgid ""
 "FONT_DELTA pts. FONT_DELTA can be a fraction.If FONT_DELTA is negative, the "
 "font size is decreased."
 msgstr ""
+"A betűméret nővelése 2*FONT_DELTA ponttal, és a sortávolság növelése "
+"FONT_DELTA ponttal. A FONT_DELTA érték törtszám is lehet, valamint ha "
+"negatív az értéke, a betűméret csökkenni fog."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/__init__.py:125
 msgid ""
@@ -1086,6 +1089,8 @@ msgstr "Szerző a fájl metaadataiban. Alapértelmezés: %default"
 msgid ""
 "Path to output file. By default a file is created in the current directory."
 msgstr ""
+"A kimeneti fájl útvonala. Alapértelmezés szerint az aktuális könyvtárba "
+"kerül a fájl."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/comic/convert_from.py:299
 msgid "Number of colors for grayscale image conversion. Default: %default"
@@ -1134,6 +1139,8 @@ msgid ""
 "Don't sort the files found in the comic alphabetically by name. Instead use "
 "the order they were added to the comic."
 msgstr ""
+"A képregény csomagban talált fájlokat a képregényhez való hozzáadás "
+"sorrendje alapján rendezze a névsorrend helyett."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/comic/convert_from.py:317
 msgid ""
@@ -1185,6 +1192,10 @@ msgid ""
 "        \n"
 "%prog converts mybook.epub to mybook.lrf"
 msgstr ""
+"Használat: %prog [beállítások] konyv.epub\n"
+"        \n"
+"        \n"
+"A %prog a konyv.epub fájlt lrf formátumba konvertálja."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/fb2/convert_from.py:23
 msgid ""
@@ -1205,7 +1216,7 @@ msgstr "A létrehozott HTML kiírása a kimenetre, majd kilépés."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/fb2/convert_from.py:30
 msgid "Keep generated HTML files after completing conversion to LRF."
-msgstr ""
+msgstr "Ne törölje a konvertálásnál keletkező átmeneti HTML fájlokat."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/feeds/convert_from.py:20
 msgid "Options to control the behavior of feeds2disk"
@@ -1225,7 +1236,7 @@ msgstr ""
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:319
 msgid "\tParsing HTML..."
-msgstr ""
+msgstr "\tHTML beolvasása..."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:342
 msgid "\tBaen file detected. Re-parsing..."
@@ -1241,71 +1252,79 @@ msgstr "Feldolgozás: %s"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:390
 msgid "\tConverting to BBeB..."
-msgstr ""
+msgstr "\tKonvertálás BBeB formátumba..."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:536
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:549
 msgid "Could not parse file: %s"
-msgstr ""
+msgstr "Nem tudtam feldolgozni a fájlt: %s"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:541
 msgid "%s is an empty file"
-msgstr ""
+msgstr "A %s fájl üres!"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:561
 msgid "Failed to parse link %s %s"
-msgstr ""
+msgstr "A link feldolgozása nem sikerült: %s %s"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:605
 msgid "Cannot add link %s to TOC"
-msgstr ""
+msgstr "Nem tudtam a linket hozzáadni a tartalomjegyzékhez: %s"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:957
 msgid "Unable to process image %s. Error: %s"
-msgstr ""
+msgstr "Hiba a \"%s\" kép feldolgozása közben: %s"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:995
 msgid "Unable to process interlaced PNG %s"
-msgstr ""
+msgstr "Nem tudtam feldolgozni a PNG képet: %s"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:1010
 msgid ""
 "Could not process image: %s\n"
 "%s"
 msgstr ""
+"Nem tudtam feldolgozni a képet: %s\n"
+"%s"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:1763
 msgid ""
 "An error occurred while processing a table: %s. Ignoring table markup."
 msgstr ""
+"Hiba történt a táblázat feldolgozása közben: %s. A táblázat formázást "
+"figyelmen kívül hagyom."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:1765
 msgid ""
 "Bad table:\n"
 "%s"
 msgstr ""
+"Hibás táblázat:\n"
+"%s"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:1787
 msgid "Table has cell that is too large"
-msgstr ""
+msgstr "A táblázatban olyan cellák vannak, amelyek túl nagyok."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:1817
 msgid ""
 "You have to save the website %s as an html file first and then run html2lrf "
 "on it."
 msgstr ""
+"Mentsd le a %s weboldalt egy mappába, majd a html fájlon futtasd a html2lrf "
+"konvertáló programot."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:1860
 msgid "Could not read cover image: %s"
-msgstr ""
+msgstr "Nem tudtam a borító képet olvasni: %s"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:1863
 msgid "Cannot read from: %s"
-msgstr ""
+msgstr "Hiba olvasás közben: %s"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:1988
 msgid "Failed to process opf file"
-msgstr ""
+msgstr "Hiba az opf fájl feldolgozása közben"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/html/convert_from.py:1994
 msgid ""
@@ -1317,6 +1336,13 @@ msgid ""
 "to local files recursively. Thus, you can use it to \n"
 "convert a whole tree of HTML files."
 msgstr ""
+"Használat: %prog [beállítások] konyv.html\n"
+"\n"
+"\n"
+"A %prog a konyv.html fájlt LRF formátumba konvertálja. \n"
+"A %prog minden linket rekurzívan követ ami helyi \n"
+"html fájlokra hivatkozik, tehát lehetséges sok összefüggő \n"
+"html fájl konvertálása is."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/lit/convert_from.py:15
 msgid ""
@@ -1325,16 +1351,22 @@ msgid ""
 "\n"
 "%prog converts mybook.lit to mybook.lrf"
 msgstr ""
+"Használat: %prog [beállítások] konyv.lit\n"
+"\n"
+"\n"
+"A %prog a konyv.lit fájlt LRF formátumba konvertálja"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/lrfparser.py:136
 msgid ""
 "%prog book.lrf\n"
 "Convert an LRF file into an LRS (XML UTF-8 encoded) file"
 msgstr ""
+"%prog konyv.lrf\n"
+"A prog a konyv.lrf fájlt LRS formátumba (UTF-8 kódolású XML) konvertálja."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/lrfparser.py:137
 msgid "Output LRS file"
-msgstr ""
+msgstr "Kimeneti LRS fájl"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/lrfparser.py:139
 msgid "Do not save embedded image and font files to disk"
@@ -1342,42 +1374,44 @@ msgstr ""
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/lrfparser.py:158
 msgid "Parsing LRF..."
-msgstr ""
+msgstr "LRF fájl beolvasása..."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/lrfparser.py:161
 msgid "Creating XML..."
-msgstr ""
+msgstr "XML létrehozása..."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/lrfparser.py:163
 msgid "LRS written to "
-msgstr ""
+msgstr "Az LRS fájl helye: "
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/lrs/convert_from.py:249
 msgid "Could not read from thumbnail file:"
-msgstr ""
+msgstr "Nem tudtam az ikon fájlt olvasni:"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/lrs/convert_from.py:269
 msgid ""
 "%prog [options] file.lrs\n"
 "Compile an LRS file into an LRF file."
 msgstr ""
+"%prog [beállítások] konyv.lrf\n"
+"LRS fájlt lefordítása LRF formátumba."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/lrs/convert_from.py:270
 msgid "Path to output file"
-msgstr ""
+msgstr "A célfájl elérési útja"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/lrs/convert_from.py:272
 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/isbndb.py:115
 msgid "Verbose processing"
-msgstr ""
+msgstr "Informatívabb üzenetek feldolgozásnál"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/lrs/convert_from.py:274
 msgid "Convert LRS to LRS, useful for debugging."
-msgstr ""
+msgstr "LRS fájl konvertálása LRS formátumba (hibakeresésnél hasznos)."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/meta.py:455
 msgid "Invalid LRF file. Could not set metadata."
-msgstr ""
+msgstr "Érvénytelen LRF fájl. Nem tudtam a metadatokat beállítani."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/meta.py:580
 msgid ""
@@ -1391,42 +1425,44 @@ msgstr ""
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/meta.py:587
 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/__init__.py:43
 msgid "Set the book title"
-msgstr ""
+msgstr "A könyv címe"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/meta.py:589
 msgid "Set sort key for the title"
-msgstr ""
+msgstr "Rendezési kulcs a címhez"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/meta.py:591
 msgid "Set the author"
-msgstr ""
+msgstr "Szerző"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/meta.py:593
 msgid "Set sort key for the author"
-msgstr ""
+msgstr "Rendezési kulcs a szerzőhöz"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/meta.py:595
 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/__init__.py:47
 msgid "The category this book belongs to. E.g.: History"
-msgstr ""
+msgstr "A kategória, amibe a könyv tartozik. Pl.: történelem"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/meta.py:598
 msgid "Path to a graphic that will be set as this files' thumbnail"
-msgstr ""
+msgstr "A fájlhoz használandó ikon elérési útja"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/meta.py:601
 msgid ""
 "Path to a txt file containing the comment to be stored in the lrf file."
 msgstr ""
+"A txt fájl útvonala, amelynek tartalma az lrf fájlhoz lesz csatolva "
+"megjegyzésként."
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/meta.py:605
 msgid "Extract thumbnail from LRF file"
-msgstr ""
+msgstr "Ikon kinyerése az LRF fájlból"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/meta.py:606
 #: /home/kovid/work/calibre/src/calibre/ebooks/metadata/mobi.py:182
 msgid "Set the publisher"
-msgstr ""
+msgstr "Kiadó"
 
 #: /home/kovid/work/calibre/src/calibre/ebooks/lrf/meta.py:607
 msgid "Set the book classification"

src/calibre/translations/it.po

@@ -15,7 +15,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 "Generated-By: pygettext.py 1.5\n"
 

src/calibre/translations/nb.po

@@ -14,7 +14,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 
 #: /home/kovid/work/calibre/src/calibre/customize/__init__.py:41

src/calibre/translations/nds.po

@@ -14,7 +14,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 "Generated-By: pygettext.py 1.5\n"
 

src/calibre/translations/nl.po

@@ -14,7 +14,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 
 #: /home/kovid/work/calibre/src/calibre/customize/__init__.py:41

src/calibre/translations/pl.po

@@ -14,7 +14,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 
 #: /home/kovid/work/calibre/src/calibre/customize/__init__.py:41

src/calibre/translations/pt.po

@@ -14,7 +14,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 
 #: /home/kovid/work/calibre/src/calibre/customize/__init__.py:41

src/calibre/translations/ro.po

@@ -14,7 +14,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 
 #: /home/kovid/work/calibre/src/calibre/customize/__init__.py:41

src/calibre/translations/ru.po

@@ -13,7 +13,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 "X-Poedit-Country: RUSSIAN FEDERATION\n"
 "X-Poedit-Language: Russian\n"

src/calibre/translations/sk.po

@@ -14,7 +14,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 
 #: /home/kovid/work/calibre/src/calibre/customize/__init__.py:41

src/calibre/translations/sl.po

@@ -13,7 +13,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 "Generated-By: pygettext.py 1.5\n"
 

src/calibre/translations/sv.po

@@ -14,7 +14,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 
 #: /home/kovid/work/calibre/src/calibre/customize/__init__.py:41

src/calibre/translations/te.po

@@ -14,7 +14,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2009-01-30 19:20+0000\n"
+"X-Launchpad-Export-Date: 2009-02-04 21:04+0000\n"
 "X-Generator: Launchpad (build Unknown)\n"
 
 #: /home/kovid/work/calibre/src/calibre/customize/__init__.py:41

src/calibre/web/feeds/news.py

@@ -47,6 +47,9 @@ class BasicNewsRecipe(object, LoggingInterface):
     #: The author of this recipe
     __author__             = __appname__    
     
+    #: The language that the news is in
+    language               = _('Unknown')
+    
     #: Maximum number of articles to download from each feed. This is primarily
     #: useful for feeds that don't have article dates. For most feeds, you should
     #: use :attr:`BasicNewsRecipe.oldest_article`

src/calibre/web/feeds/recipes/__init__.py

@@ -24,7 +24,9 @@ recipe_modules = ['recipe_' + r for r in (
            'joelonsoftware', 'telepolis', 'common_dreams', 'nin', 'tomshardware_de',
            'pagina12', 'infobae', 'ambito', 'elargentino', 'sueddeutsche', 'the_age',
            'laprensa', 'amspec', 'freakonomics', 'criticadigital', 'elcronista',
-           'shacknews', 'teleread',
+           'shacknews', 'teleread', 'granma', 'juventudrebelde', 'juventudrebelde_english',
+           'la_tercera', 'el_mercurio_chile', 'la_cuarta', 'lanacion_chile', 'la_segunda',
+           'jb_online', 'estadao', 'o_globo', 'vijesti', 'elmundo', 'the_oz', 'exiled',
           )]
 
 import re, imp, inspect, time, os

src/calibre/web/feeds/recipes/recipe_ambito.py

@@ -18,6 +18,7 @@ class Ambito(BasicNewsRecipe):
     no_stylesheets        = True
     use_embedded_content  = False
     encoding              = 'iso--8859-1'
+    language              = _('Spanish')
     cover_url             = 'http://www.ambito.com/img/logo_.jpg'
 
     html2lrf_options = [

src/calibre/web/feeds/recipes/recipe_amspec.py

@@ -9,27 +9,28 @@ spectator.org
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class TheAmericanSpectator(BasicNewsRecipe):
-      title                 = 'The American Spectator'
+    title                 = 'The American Spectator'
-      __author__            = 'Darko Miletic'
+    __author__            = 'Darko Miletic'
-      description           = 'news from USA'
+    language              = _('English')
-      oldest_article        = 7
+    description           = 'News from USA'
-      max_articles_per_feed = 100
+    oldest_article        = 7
-      no_stylesheets        = True
+    max_articles_per_feed = 100
-      use_embedded_content  = False
+    no_stylesheets        = True
-      INDEX                 = 'http://spectator.org'
+    use_embedded_content  = False
+    INDEX                 = 'http://spectator.org'
       
-      html2lrf_options = [
+    html2lrf_options = [
                              '--comment'       , description
                            , '--category'      , 'news, politics, USA'
                            , '--publisher'     , title
                          ]
 
-      keep_only_tags   = [
+    keep_only_tags   = [
                              dict(name='div', attrs={'class':'post inner'})
                             ,dict(name='div', attrs={'class':'author-bio'})
                          ]
 
-      remove_tags     = [
+    remove_tags     = [
                              dict(name='object')
                             ,dict(name='div', attrs={'class':'col3'         })
                             ,dict(name='div', attrs={'class':'post-options' })
@@ -37,17 +38,17 @@ class TheAmericanSpectator(BasicNewsRecipe):
                             ,dict(name='div', attrs={'class':'social'       })
                         ]
                          
-      feeds = [ (u'Articles', u'http://feedproxy.google.com/amspecarticles')]
+    feeds = [ (u'Articles', u'http://feedproxy.google.com/amspecarticles')]
 
-      def get_cover_url(self):
+    def get_cover_url(self):
-          cover_url = None
+        cover_url = None
-          soup = self.index_to_soup(self.INDEX)
+        soup = self.index_to_soup(self.INDEX)
-          link_item = soup.find('a',attrs={'class':'cover'})
+        link_item = soup.find('a',attrs={'class':'cover'})
-          if link_item:
+        if link_item:
-             soup2 = self.index_to_soup(link_item['href'])
+            soup2 = self.index_to_soup(link_item['href'])
-             link_item2 = soup2.find('div',attrs={'class':'post inner issues'})
+            link_item2 = soup2.find('div',attrs={'class':'post inner issues'})
-             cover_url = self.INDEX + link_item2.img['src']
+            cover_url = self.INDEX + link_item2.img['src']
-          return cover_url
+        return cover_url
           
-      def print_version(self, url):
+    def print_version(self, url):
-          return url + '/print'
+        return url + '/print'

src/calibre/web/feeds/recipes/recipe_ap.py

@@ -8,6 +8,7 @@ class AssociatedPress(BasicNewsRecipe):
     description = 'Global news'
     __author__ = 'Kovid Goyal'
     use_embedded_content   = False
+    language = _('English')
     max_articles_per_feed = 15
     html2lrf_options = ['--force-page-break-before-tag="chapter"']
     

src/calibre/web/feeds/recipes/recipe_ars_technica.py

@@ -13,6 +13,7 @@ class ArsTechnica(BasicNewsRecipe):
     title          = 'Ars Technica'
     description    = 'The art of technology'
     oldest_article = 7
+    language = _('English')
     no_stylesheets = True
     __author__     = 'Michael Warner'
     max_articles_per_feed = 100

src/calibre/web/feeds/recipes/recipe_atlantic.py

@@ -14,7 +14,7 @@ class TheAtlantic(BasicNewsRecipe):
     __author__ = 'Kovid Goyal'
     description = 'Current affairs and politics focussed on the US'
     INDEX = 'http://www.theatlantic.com/doc/current'
-    
+    language = _('English')
     remove_tags_before = dict(name='div', id='storytop')
     remove_tags        = [dict(name='div', id=['seealso', 'storybottom', 'footer', 'ad_banner_top', 'sidebar'])]
     no_stylesheets     = True

src/calibre/web/feeds/recipes/recipe_b92.py

@@ -6,12 +6,13 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
 b92.net
 '''
 
-import string,re
+import re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class B92(BasicNewsRecipe):
     title                 = u'B92'
     __author__            = 'Darko Miletic'
+    language = _('Serbian')
     description           = 'Dnevne vesti iz Srbije i sveta'    
     oldest_article        = 7
     max_articles_per_feed = 100

src/calibre/web/feeds/recipes/recipe_barrons.py

@@ -15,6 +15,7 @@ class Barrons(BasicNewsRecipe):
         title = 'Barron\'s' 
         max_articles_per_feed = 50
         needs_subscription    = True
+        language = _('English')
         __author__ = 'Kovid Goyal'
         description = 'Weekly publication for investors from the publisher of the Wall Street Journal'
         timefmt  = ' [%a, %b %d, %Y]' 

src/calibre/web/feeds/recipes/recipe_bbc.py

@@ -13,6 +13,7 @@ class BBC(BasicNewsRecipe):
     __author__     = 'Kovid Goyal'
     description    = 'Global news and current affairs from the British Broadcasting Corporation'
     no_stylesheets = True
+    language = _('English')
 
     remove_tags    = [dict(name='div', attrs={'class':'footer'})]
     extra_css      = '.headline {font-size: x-large;} \n .fact { padding-top: 10pt  }' 

src/calibre/web/feeds/recipes/recipe_business_week.py

@@ -13,6 +13,7 @@ class BusinessWeek(BasicNewsRecipe):
     title          = 'Business Week'
     description    = 'Business News, Stock Market and Financial Advice'
     __author__     = 'ChuckEggDotCom'
+    language = _('English')
     oldest_article = 7
     max_articles_per_feed = 10
 

src/calibre/web/feeds/recipes/recipe_chr_mon.py

@@ -8,6 +8,7 @@ class ChristianScienceMonitor(BasicNewsRecipe):
     description = 'Providing context and clarity on national and international news, peoples and cultures'
     max_articles_per_feed = 20
     __author__ = 'Kovid Goyal'
+    language = _('English')
     no_stylesheets = True
     use_embedded_content   = False
   

src/calibre/web/feeds/recipes/recipe_clarin.py

@@ -15,6 +15,7 @@ class Clarin(BasicNewsRecipe):
     description           = 'Noticias de Argentina y mundo'
     oldest_article        = 2
     max_articles_per_feed = 100
+    language = _('Spanish')
     use_embedded_content  = False
     no_stylesheets        = True
     cover_url             = strftime('http://www.clarin.com/diario/%Y/%m/%d/portada.jpg')

src/calibre/web/feeds/recipes/recipe_cnn.py

@@ -12,6 +12,7 @@ class CNN(BasicNewsRecipe):
     description = 'Global news'
     timefmt  = ' [%d %b %Y]'
     __author__ = 'Kovid Goyal'
+    language = _('English')
     no_stylesheets = True
     use_embedded_content   = False
     oldest_article        = 15

src/calibre/web/feeds/recipes/recipe_common_dreams.py

@@ -5,6 +5,7 @@ class CommonDreams(BasicNewsRecipe):
     title          = u'Common Dreams'
     description    = u'Progressive news and views'
     __author__     = u'XanthanGum'
+    language = _('English')
     oldest_article = 7
     max_articles_per_feed = 100
     

src/calibre/web/feeds/recipes/recipe_criticadigital.py

@@ -14,6 +14,7 @@ class CriticaDigital(BasicNewsRecipe):
     description           = 'Noticias de Argentina'
     oldest_article        = 2
     max_articles_per_feed = 100
+    language = _('Spanish')
     no_stylesheets        = True
     use_embedded_content  = False
     encoding              = 'cp1252'

src/calibre/web/feeds/recipes/recipe_cyberpresse.py

@@ -6,6 +6,7 @@ class Cyberpresse(BasicNewsRecipe):
     title          = u'Cyberpresse'
     __author__     = 'balok'
     description    = 'Canadian news in French'
+    language = _('French')
     oldest_article = 7
     max_articles_per_feed = 100
     no_stylesheets = True

src/calibre/web/feeds/recipes/recipe_daily_telegraph.py

@@ -12,6 +12,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
 class DailyTelegraph(BasicNewsRecipe):
     title          = u'Daily Telegraph'
     __author__     = u'AprilHare'
+    language = _('English')
     description    = u'News from down under'
     oldest_article = 2
     max_articles_per_feed = 10

src/calibre/web/feeds/recipes/recipe_de_standaard.py

@@ -9,6 +9,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
 class DeStandaard(BasicNewsRecipe):
     title                 = u'De Standaard'
     __author__            = u'Darko Miletic'
+    language = _('French')
     description           = u'News from Belgium'    
     oldest_article        = 7
     max_articles_per_feed = 100

src/calibre/web/feeds/recipes/recipe_discover_magazine.py

@@ -13,7 +13,8 @@ class DiscoverMagazine(BasicNewsRecipe):
     title = u'Discover Magazine'
     description = u'Science, Technology and the Future' 
     __author__ = 'Mike Diaz' 
-    oldest_article = 33 
+    oldest_article = 33
+    language = _('English') 
     max_articles_per_feed = 20 
     feeds = [
              (u'Technology', u'http://discovermagazine.com/topics/technology/rss.xml'), 

src/calibre/web/feeds/recipes/recipe_economist.py

@@ -14,6 +14,7 @@ from urllib2 import quote
 class Economist(BasicNewsRecipe):
     
     title = 'The Economist'
+    language = _('English')
     __author__ = "Kovid Goyal"
     description = 'Global news and current affairs from a European perspective'
     oldest_article = 7.0

src/calibre/web/feeds/recipes/recipe_el_mercurio_chile.py

@@ -0,0 +1,48 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+emol.com
+'''
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class ElMercurio(BasicNewsRecipe):
+    title                 = 'El Mercurio online'
+    language = _('Spanish')
+    __author__            = 'Darko Miletic'
+    description           = 'El sitio de noticias online de Chile'    
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'cp1252'
+    cover_url             = 'http://www.emol.com/especiales/logo_emol/logo_emol.gif'
+
+    html2lrf_options = [
+                          '--comment'       , description
+                        , '--category'      , 'news, Chile'
+                        , '--publisher'     , title
+                        ]
+                        
+    keep_only_tags = [  
+                        dict(name='div', attrs={'class':'despliegue-txt_750px'})
+                       ,dict(name='div', attrs={'id':'div_cuerpo_participa'})
+                     ]
+                        
+
+    remove_tags = [  
+                     dict(name='div', attrs={'class':'contenedor_despliegue-col-left300'})
+                    ,dict(name='div', attrs={'id':['div_centro_dn_opc','div_cabezera','div_secciones','div_contenidos','div_pie','nav']})
+                    ]
+                        
+    feeds = [  
+               (u'Noticias de ultima hora', u'http://www.emol.com/rss20/rss.asp?canal=0')
+              ,(u'Nacional', u'http://www.emol.com/rss20/rss.asp?canal=1')
+              ,(u'Mundo', u'http://www.emol.com/rss20/rss.asp?canal=2')
+              ,(u'Deportes', u'http://www.emol.com/rss20/rss.asp?canal=4')
+              ,(u'Magazine', u'http://www.emol.com/rss20/rss.asp?canal=6')
+              ,(u'Tecnologia', u'http://www.emol.com/rss20/rss.asp?canal=5')
+              ,(u'La Musica', u'http://www.emol.com/rss20/rss.asp?canal=7')
+            ]
+        

src/calibre/web/feeds/recipes/recipe_el_pais.py

@@ -11,6 +11,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
 
 class ElPais(BasicNewsRecipe):
     title          = u'EL PAIS'
+    language = _('Spanish')
     oldest_article = 7
     max_articles_per_feed = 100
 

src/calibre/web/feeds/recipes/recipe_elargentino.py

@@ -12,6 +12,7 @@ class ElArgentino(BasicNewsRecipe):
     title                 = 'ElArgentino.com'
     __author__            = 'Darko Miletic'
     description           = 'Informacion Libre las 24 horas'    
+    language = _('Spanish')
     oldest_article        = 2
     max_articles_per_feed = 100
     no_stylesheets        = True

src/calibre/web/feeds/recipes/recipe_elcronista.py

@@ -13,6 +13,7 @@ class ElCronista(BasicNewsRecipe):
     __author__            = 'Darko Miletic'
     description           = 'Noticias de Argentina'
     oldest_article        = 2
+    language = _('Spanish')
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False

src/calibre/web/feeds/recipes/recipe_elmundo.py

@@ -0,0 +1,46 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+elmundo.es
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class ElMundo(BasicNewsRecipe):
+    title                 = 'El Mundo'
+    __author__            = 'Darko Miletic'
+    description           = 'News from Spain'
+    language = _('Spanish')
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'iso8859_15'
+    cover_url             = 'http://estaticos02.cache.el-mundo.net/papel/imagenes/v2.0/logoverde.gif'
+
+    html2lrf_options = [
+                          '--comment'       , description
+                        , '--category'      , 'news, Spain'
+                        , '--publisher'     , title
+                        ]
+
+    keep_only_tags = [dict(name='div', attrs={'class':'noticia'})]
+                     
+    remove_tags = [
+                     dict(name='div', attrs={'class':['herramientas','publicidad_google','video','herramientasarriba','contenido_noticia_02']})
+                    ,dict(name='div', attrs={'id':'modulo_multimedia' })
+                    ,dict(name=['object','script','link', 'a'])
+                    ,dict(name='ul', attrs={'class':'herramientas'})
+                  ]
+                            
+    feeds = [ 
+              (u'Portada'         , u'http://rss.elmundo.es/rss/descarga.htm?data2=4' )
+             ,(u'Television'      , u'http://rss.elmundo.es/rss/descarga.htm?data2=76')
+             ,(u'Espana'          , u'http://rss.elmundo.es/rss/descarga.htm?data2=8' )
+             ,(u'Internacional'   , u'http://rss.elmundo.es/rss/descarga.htm?data2=9' )
+             ,(u'Cultura'         , u'http://rss.elmundo.es/rss/descarga.htm?data2=6' )
+             ,(u'Ciencia/Ecologia', u'http://rss.elmundo.es/rss/descarga.htm?data2=5' )
+             ,(u'Comunicacion'    , u'http://rss.elmundo.es/rss/descarga.htm?data2=26')
+            ]

src/calibre/web/feeds/recipes/recipe_endgadget.py

@@ -12,7 +12,8 @@ from calibre.web.feeds.news import BasicNewsRecipe
 class Engadget(BasicNewsRecipe):
     title                 = u'Engadget'
     __author__            = 'Darko Miletic'
-    description           = 'Tech news'    
+    description           = 'Tech news'
+    language = _('English')    
     oldest_article        = 7
     max_articles_per_feed = 100
     no_stylesheets        = True

src/calibre/web/feeds/recipes/recipe_espn.py

@@ -14,6 +14,7 @@ class ESPN(BasicNewsRecipe):
     title       = 'ESPN'
     description = 'Sports news'
     __author__  = 'Kovid Goyal'
+    language = _('English')
     
     needs_subscription = True
     remove_tags = [dict(name='font', attrs={'class':'footer'}), dict(name='hr', noshade='noshade')]

src/calibre/web/feeds/recipes/recipe_estadao.py

@@ -0,0 +1,55 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+estadao.com.br
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+
+class Estadao(BasicNewsRecipe):
+    title                 = 'O Estado de S. Paulo'
+    __author__            = 'Darko Miletic'
+    description           = 'News from Brasil'
+    language = _('Spanish')    
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'utf8'
+    cover_url             = 'http://www.estadao.com.br/img/logo_estadao.png'
+
+    html2lrf_options = [
+                          '--comment'       , description
+                        , '--category'      , 'news, Brasil'
+                        , '--publisher'     , title
+                        ]
+                        
+    keep_only_tags = [dict(name='div', attrs={'id':'c1'})]
+
+    remove_tags = [
+                     dict(name=['script','object','form','ul'])
+                    ,dict(name='div', attrs={'id':['votacao','estadaohoje']})
+                    ,dict(name='p', attrs={'id':'ctrl_texto'})
+                    ,dict(name='p', attrs={'class':'texto'})
+                  ]
+    
+    feeds = [
+               (u'Manchetes Estadao', u'http://www.estadao.com.br/rss/manchetes.xml')
+              ,(u'Ultimas noticias', u'http://www.estadao.com.br/rss/ultimas.xml')
+              ,(u'Nacional', u'http://www.estadao.com.br/rss/nacional.xml')
+              ,(u'Internacional', u'http://www.estadao.com.br/rss/internacional.xml')
+              ,(u'Cidades', u'http://www.estadao.com.br/rss/cidades.xml')
+              ,(u'Esportes', u'http://www.estadao.com.br/rss/esportes.xml')
+              ,(u'Arte & Lazer', u'http://www.estadao.com.br/rss/arteelazer.xml')
+              ,(u'Economia', u'http://www.estadao.com.br/rss/economia.xml')
+              ,(u'Vida &', u'http://www.estadao.com.br/rss/vidae.xml')
+            ]
+
+    def preprocess_html(self, soup):
+        ifr = soup.find('iframe')
+        if ifr:
+           ifr.extract()
+        return soup

src/calibre/web/feeds/recipes/recipe_exiled.py

@@ -0,0 +1,51 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+exiledonline.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Exiled(BasicNewsRecipe):
+    title                 = 'Exiled Online'
+    __author__            = 'Darko Miletic'
+    description           = "Mankind's only alternative since 1997 - Formerly known as The eXile"
+    publisher             = 'Exiled Online'
+    language              = _('English')
+    category              = 'news, politics, international'
+    oldest_article        = 15
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'utf8'
+    remove_javascript     = True
+    cover_url             = 'http://exiledonline.com/wp-content/themes/exiledonline_theme/images/header-sm.gif'
+
+    html2lrf_options = [
+                          '--comment'       , description
+                        , '--category'      , category
+                        , '--publisher'     , publisher
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
+    
+    keep_only_tags = [dict(name='div', attrs={'id':'main'})]
+
+    remove_tags = [
+                     dict(name=['object','link'])
+                    ,dict(name='div', attrs={'class':'info'})
+                    ,dict(name='div', attrs={'id':['comments','navig']})
+                  ]
+
+                        
+    feeds = [(u'Articles', u'http://exiledonline.com/feed/' )]
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        mtag = '\n<meta http-equiv="Content-Language" content="en"/>\n<meta http-equiv="Content-Type" content="text/html; charset=utf-8">\n'
+        soup.head.insert(0,mtag)
+        return soup
+    

src/calibre/web/feeds/recipes/recipe_faznet.py

@@ -11,8 +11,9 @@ class FazNet(BasicNewsRecipe):
 
     title = 'FAZ NET'
     __author__ = 'Kovid Goyal'
-    description = '"Frankfurter Allgemeine Zeitung'
+    description = 'Frankfurter Allgemeine Zeitung'
-    use_embedded_content   = False 
+    use_embedded_content   = False
+    language = _('German') 
     max_articles_per_feed = 30 
 
     preprocess_regexps = [

src/calibre/web/feeds/recipes/recipe_financial_times.py

@@ -13,6 +13,7 @@ class FinancialTimes(BasicNewsRecipe):
     __author__            = 'Darko Miletic'
     description           = 'Financial world news'
     oldest_article        = 2
+    language = _('English')
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False