Sync to trunk.

Changelog.yaml

@@ -11,7 +11,7 @@
     - title: "Page turn animations in the e-book viewer"
       type: major
       description: >
-        "Now when you use the Page Down/Page Up keys or the next/previous page buttons in the viewer, page turning will be animated. The duration of the animation can be controlled in the viewer preferences. Setting it to o disables the animation completely."
+        "Now when you use the Page Down/Page Up keys or the next/previous page buttons in the viewer, page turning will be animated. The duration of the animation can be controlled in the viewer preferences. Setting it to 0 disables the animation completely."
 
     - title: "Conversion pipeline: Add an option to set the minimum line height of all elemnts as a percentage of the computed font size. By default, calibre now sets the line height to 120% of the computed font size."
 

resources/default_tweaks.py

@@ -41,6 +41,20 @@ series_index_auto_increment = 'next'
 # selecting 'manage authors', and pressing 'Recalculate all author sort values'.
 author_sort_copy_method = 'invert'
 
+# Set which author field to display in the tags pane (the list of authors,
+# series, publishers etc on the left hand side). The choices are author and
+# author_sort. This tweak affects only the tags pane, and only what is displayed
+# under the authors category. Please note that if you set this to author_sort,
+# it is very possible to see duplicate names in the list becasue although it is
+# guaranteed that author names are unique, there is no such guarantee for
+# author_sort values. Showing duplicates won't break anything, but it could
+# lead to some confusion. When using 'author_sort', the tooltip will show the
+# author's name.
+# Examples:
+#   tags_pane_use_field_for_author_name = 'author'
+#   tags_pane_use_field_for_author_name = 'author_sort'
+tags_pane_use_field_for_author_name = 'author'
+
 
 # Set whether boolean custom columns are two- or three-valued.
 #  Two-values for true booleans

resources/recipes/johm.recipe

@@ -1,78 +1,72 @@
-# -*- coding: utf-8 -*-
+import re
-
 from calibre.web.feeds.recipes import BasicNewsRecipe
 
 class JournalofHospitalMedicine(BasicNewsRecipe):
 
     title       = 'Journal of Hospital Medicine'
-    __author__  = 'Krittika Goyal'
+    __author__  = 'Kovid Goyal'
     description = 'Medical news'
     timefmt = ' [%d %b, %Y]'
     needs_subscription = True
     language = 'en'
 
     no_stylesheets = True
+    keep_only_tags = [dict(id=['articleTitle', 'articleMeta', 'fulltext'])]
+    remove_tags = [dict(attrs={'class':'licensedContent'})]
 
 
    # TO LOGIN
     def get_browser(self):
         br = BasicNewsRecipe.get_browser()
         br.open('http://www3.interscience.wiley.com/cgi-bin/home')
-        br.select_form(name='siteLogin')
+        br.select_form(nr=0)
-        br['LoginName'] = self.username
+        br['j_username'] = self.username
-        br['Password'] = self.password
+        br['j_password'] = self.password
         response = br.submit()
         raw = response.read()
-        if 'userName = ""' in raw:
+        if '<h2>LOGGED IN</h2>' not in raw:
             raise Exception('Login failed. Check your username and password')
         return br
 
     #TO GET ARTICLE TOC
     def johm_get_index(self):
-        return self.index_to_soup('http://www3.interscience.wiley.com/journal/111081937/home')
+        return self.index_to_soup('http://onlinelibrary.wiley.com/journal/10.1002/(ISSN)1553-5606/currentissue')
 
     # To parse artice toc
     def parse_index(self):
-        parse_soup = self.johm_get_index()
+        soup = self.johm_get_index()
-
+        toc = soup.find(id='issueTocGroups')
-        div = parse_soup.find(id='contentCell')
-
-        current_section = None
-        current_articles = []
         feeds = []
-        for x in div.findAll(True):
+        for group in toc.findAll('li', id=re.compile(r'group\d+')):
-            if x.name == 'h4':
+            gtitle = group.find(attrs={'class':'subSectionHeading'})
-                # Section heading found
+            if gtitle is None:
-                if current_articles and current_section:
-                    feeds.append((current_section, current_articles))
-                current_section = self.tag_to_string(x)
-                current_articles = []
-                self.log('\tFound section:', current_section)
-            if current_section is not None and x.name == 'strong':
-                title = self.tag_to_string(x)
-                p = x.parent.parent.find('a', href=lambda x: x and '/HTMLSTART' in x)
-                if p is None:
                 continue
-                url = p.get('href', False)
+            gtitle = self.tag_to_string(gtitle)
-                if not url or not title:
+            arts = group.find(attrs={'class':'articles'})
+            if arts is None:
                 continue
+            self.log('Found section:', gtitle)
+            articles = []
+            for art in arts.findAll(attrs={'class':lambda x: x and 'tocArticle'
+                in x}):
+                a = art.find('a', href=True)
+                if a is None:
+                    continue
+                url = a.get('href')
                 if url.startswith('/'):
-                        url = 'http://www3.interscience.wiley.com'+url
+                    url = 'http://onlinelibrary.wiley.com' + url
-                url = url.replace('/HTMLSTART', '/main.html,ftx_abs')
+                url = url.replace('/abstract', '/full')
-                self.log('\t\tFound article:', title)
+                title = self.tag_to_string(a)
-                self.log('\t\t\t', url)
+                a.extract()
-                #if url.startswith('/'):
+                pm = art.find(attrs={'class':'productMenu'})
-                    #url = 'http://online.wsj.com'+url
+                if pm is not None:
-                current_articles.append({'title': title, 'url':url,
+                    pm.extract()
-                    'description':'', 'date':''})
+                desc = self.tag_to_string(art)
-
+                self.log('\tFound article:', title, 'at', url)
-        if current_articles and current_section:
+                articles.append({'title':title, 'url':url, 'description':desc,
-            feeds.append((current_section, current_articles))
+                    'date':''})
+            if articles:
+                feeds.append((gtitle, articles))
 
         return feeds
 
-    def preprocess_html(self, soup):
-        for img in soup.findAll('img', src=True):
-            img['src'] = img['src'].replace('tfig', 'nfig')
-        return soup
-

resources/recipes/nejm.recipe

@@ -4,7 +4,7 @@ from calibre.web.feeds.recipes import BasicNewsRecipe
 class NYTimes(BasicNewsRecipe):
 
     title       = 'New England Journal of Medicine'
-    __author__  = 'Krittika Goyal'
+    __author__  = 'Kovid Goyal'
     description = 'Medical news'
     timefmt = ' [%d %b, %Y]'
     needs_subscription = True

setup/installer/windows/notes.rst

@@ -36,6 +36,16 @@ Install BeautifulSoup 3.0.x manually into site-packages (3.1.x parses broken HTM
 
 Install pywin32 and edit win32com\__init__.py setting _frozen = True and
 __gen_path__ to a temp dir (otherwise it tries to set it to a dir in the install tree which leads to permission errors)
+Note that you should use::
+
+    import tempfile
+    __gen_path__ = os.path.join(
+                            tempfile.gettempdir(), "gen_py",
+                            "%d.%d" % (sys.version_info[0], sys.version_info[1]))
+
+Use gettempdir instead of the win32 api method as gettempdir returns a temp dir that is guaranteed to actually work.
+
+
 Also edit win32com\client\gencache.py and change the except IOError on line 57 to catch all exceptions.
 
 SQLite

src/calibre/devices/android/driver.py

@@ -28,7 +28,7 @@ class ANDROID(USBMS):
 
             # Motorola
             0x22b8 : { 0x41d9 : [0x216], 0x2d67 : [0x100], 0x41db : [0x216],
-                0x4285 : [0x216]},
+                0x4285 : [0x216], 0x42a3 : [0x216] },
 
             # Sony Ericsson
             0xfce : { 0xd12e : [0x0100]},

src/calibre/devices/misc.py

@@ -62,9 +62,9 @@ class SWEEX(USBMS):
     # Ordered list of supported formats
     FORMATS     = ['epub', 'prc', 'fb2', 'html', 'rtf', 'chm', 'pdf', 'txt']
 
-    VENDOR_ID   = [0x0525]
+    VENDOR_ID   = [0x0525, 0x177f]
-    PRODUCT_ID  = [0xa4a5]
+    PRODUCT_ID  = [0xa4a5, 0x300]
-    BCD         = [0x0319]
+    BCD         = [0x0319, 0x110]
 
     VENDOR_NAME = 'SWEEX'
     WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = 'EBOOKREADER'

src/calibre/ebooks/rtf/input.py

@@ -245,7 +245,7 @@ class RTFInput(InputFormatPlugin):
         from calibre.ebooks.metadata.meta import get_metadata
         from calibre.ebooks.metadata.opf2 import OPFCreator
         from calibre.ebooks.rtf2xml.ParseRtf import RtfInvalidCodeException
-        self.options = options
+        self.opts = options
         self.log = log
         self.log('Converting RTF to XML...')
         #Name of the preprocesssed RTF file
@@ -290,12 +290,12 @@ class RTFInput(InputFormatPlugin):
             res = transform.tostring(result)
             res = res[:100].replace('xmlns:html', 'xmlns') + res[100:]
             # Replace newlines inserted by the 'empty_paragraphs' option in rtf2xml with html blank lines
-            if not getattr(self.options, 'remove_paragraph_spacing', False):
+            if not getattr(self.opts, 'remove_paragraph_spacing', False):
                 res = re.sub('\s*<body>', '<body>', res)
                 res = re.sub('(?<=\n)\n{2}',
                         u'<p>\u00a0</p>\n'.encode('utf-8'), res)
-            if self.options.preprocess_html:
+            if self.opts.preprocess_html:
-                preprocessor = PreProcessor(self.options, log=getattr(self, 'log', None))
+                preprocessor = PreProcessor(self.opts, log=getattr(self, 'log', None))
                 res = preprocessor(res)
             f.write(res)
         self.write_inline_css(inline_class, border_styles)

src/calibre/gui2/tag_view.py

@@ -18,6 +18,7 @@ from PyQt4.Qt import Qt, QTreeView, QApplication, pyqtSignal, \
 from calibre.ebooks.metadata import title_sort
 from calibre.gui2 import config, NONE
 from calibre.library.field_metadata import TagsIcons, category_icon_map
+from calibre.utils.config import tweaks
 from calibre.utils.icu import sort_key
 from calibre.utils.search_query_parser import saved_searches
 from calibre.gui2 import error_dialog
@@ -409,17 +410,31 @@ class TagTreeItem(object): # {{{
         return NONE
 
     def tag_data(self, role):
-        if role == Qt.DisplayRole:
+        tag = self.tag
-            if self.tag.count == 0:
+        if tag.category == 'authors' and \
-                return QVariant('%s'%(self.tag.name))
+                tweaks['tags_pane_use_field_for_author_name'] == 'author_sort':
+            name = tag.sort
+            tt_author = True
         else:
-                return QVariant('[%d] %s'%(self.tag.count, self.tag.name))
+            name = tag.name
+            tt_author = False
+        if role == Qt.DisplayRole:
+            if tag.count == 0:
+                return QVariant('%s'%(name))
+            else:
+                return QVariant('[%d] %s'%(tag.count, name))
         if role == Qt.EditRole:
-            return QVariant(self.tag.name)
+            return QVariant(tag.name)
         if role == Qt.DecorationRole:
-            return self.icon_state_map[self.tag.state]
+            return self.icon_state_map[tag.state]
-        if role == Qt.ToolTipRole and self.tag.tooltip is not None:
+        if role == Qt.ToolTipRole:
-            return QVariant(self.tag.tooltip)
+            if tt_author:
+                if tag.tooltip is not None:
+                    return QVariant('(%s) %s'%(tag.name, tag.tooltip))
+                else:
+                    return QVariant(tag.name)
+            if tag.tooltip is not None:
+                return QVariant(tag.tooltip)
         return NONE
 
     def toggle(self):

src/calibre/library/database2.py

@@ -1128,6 +1128,10 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
                 for l in list:
                     (id, val, sort_val) = (l[0], l[1], l[2])
                     tids[category][val] = (id, sort_val)
+            elif cat['datatype'] == 'rating':
+                for l in list:
+                    (id, val) = (l[0], l[1])
+                    tids[category][val] = (id, '{0:05.2f}'.format(val))
             else:
                 for l in list:
                     (id, val) = (l[0], l[1])
@@ -1256,12 +1260,7 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
 
             # sort the list
             if sort == 'name':
-                def get_sort_key(x):
+                kf = lambda x :sort_key(x.s)
-                    sk = x.s
-                    if isinstance(sk, unicode):
-                        sk = sort_key(sk)
-                    return sk
-                kf = get_sort_key
                 reverse=False
             elif sort == 'popularity':
                 kf = lambda x: x.c

src/calibre/manual/conversion.rst

@@ -541,7 +541,9 @@ Use the options to remove headers and footers to mitigate this issue. If the hea
 removed from the text it can throw off the paragraph unwrapping.
 
 Some limitations of PDF input is complex, multi-column, and image based documents are not supported.
-Extraction of vector images and tables from within the document is also not supported.
+Extraction of vector images and tables from within the document is also not supported. Some PDFs use special glyphs to
+represent double ll or doubfle ff or fi,etc. Conversion of these may or may not work depending on jusy how they are 
+represented internally in the PDF.
 
 Comic Book Collections
 ~~~~~~~~~~~~~~~~~~~~~~~~~