Merge from trunk

resources/default_tweaks.py

@@ -39,7 +39,7 @@ completer_append_separator = False
 
 # The algorithm used to copy author to author_sort
 # Possible values are:
-#  invert: use "fn ln" -> "ln, fn" (the original algorithm)
+#  invert: use "fn ln" -> "ln, fn" (the default algorithm)
 #  copy  : copy author to author_sort without modification
 #  comma : use 'copy' if there is a ',' in the name, otherwise use 'invert'
 #  nocomma : "fn ln" -> "ln fn" (without the comma)

src/calibre/ebooks/conversion/preprocess.py

@@ -245,17 +245,17 @@ class Dehyphenator(object):
         self.html = html
         self.format = format
         if format == 'html':
-            intextmatch = re.compile(u'(?<=.{%i})(?P<firstpart>[^\[\]\\\^\$\.\|\?\*\+\(\)“"\s>]+)(-|‐)\s*(?=<)(?P<wraptags>(</span>)?\s*(</[iubp]>\s*){1,2}(?P<up2threeblanks><(p|div)[^>]*>\s*(<p[^>]*>\s*</p>\s*)?</(p|div)>\s+){0,3}\s*(<[iubp][^>]*>\s*){1,2}(<span[^>]*>)?)\s*(?P<secondpart>[\w\d]+)' % length)
+            intextmatch = re.compile(u'(?<=.{%i})(?P<firstpart>[^\W\-]+)(-|‐)\s*(?=<)(?P<wraptags>(</span>)?\s*(</[iubp]>\s*){1,2}(?P<up2threeblanks><(p|div)[^>]*>\s*(<p[^>]*>\s*</p>\s*)?</(p|div)>\s+){0,3}\s*(<[iubp][^>]*>\s*){1,2}(<span[^>]*>)?)\s*(?P<secondpart>[\w\d]+)' % length)
         elif format == 'pdf':
-            intextmatch = re.compile(u'(?<=.{%i})(?P<firstpart>[^\[\]\\\^\$\.\|\?\*\+\(\)“"\s>]+)(-|‐)\s*(?P<wraptags><p>|</[iub]>\s*<p>\s*<[iub]>)\s*(?P<secondpart>[\w\d]+)'% length)
+            intextmatch = re.compile(u'(?<=.{%i})(?P<firstpart>[^\W\-]+)(-|‐)\s*(?P<wraptags><p>|</[iub]>\s*<p>\s*<[iub]>)\s*(?P<secondpart>[\w\d]+)'% length)
         elif format == 'txt':
-            intextmatch = re.compile(u'(?<=.{%i})(?P<firstpart>[^\[\]\\\^\$\.\|\?\*\+\(\)“"\s>]+)(-|‐)(\u0020|\u0009)*(?P<wraptags>(\n(\u0020|\u0009)*)+)(?P<secondpart>[\w\d]+)'% length)
+            intextmatch = re.compile(u'(?<=.{%i})(?P<firstpart>[^\W\-]+)(-|‐)(\u0020|\u0009)*(?P<wraptags>(\n(\u0020|\u0009)*)+)(?P<secondpart>[\w\d]+)'% length)
         elif format == 'individual_words':
-            intextmatch = re.compile(u'(?!<)(?P<firstpart>\w+)(-|‐)\s*(?P<secondpart>\w+)(?![^<]*?>)')
+            intextmatch = re.compile(u'(?!<)(?P<firstpart>[^\W\-]+)(-|‐)\s*(?P<secondpart>\w+)(?![^<]*?>)')
         elif format == 'html_cleanup':
-            intextmatch = re.compile(u'(?P<firstpart>[^\[\]\\\^\$\.\|\?\*\+\(\)“"\s>]+)(-|‐)\s*(?=<)(?P<wraptags></span>\s*(</[iubp]>\s*<[iubp][^>]*>\s*)?<span[^>]*>|</[iubp]>\s*<[iubp][^>]*>)?\s*(?P<secondpart>[\w\d]+)')
+            intextmatch = re.compile(u'(?P<firstpart>[^\W\-]+)(-|‐)\s*(?=<)(?P<wraptags></span>\s*(</[iubp]>\s*<[iubp][^>]*>\s*)?<span[^>]*>|</[iubp]>\s*<[iubp][^>]*>)?\s*(?P<secondpart>[\w\d]+)')
         elif format == 'txt_cleanup':
-            intextmatch = re.compile(u'(?P<firstpart>\w+)(-|‐)(?P<wraptags>\s+)(?P<secondpart>[\w\d]+)')
+            intextmatch = re.compile(u'(?P<firstpart>[^\W\-]+)(-|‐)(?P<wraptags>\s+)(?P<secondpart>[\w\d]+)')
 
 
         html = intextmatch.sub(self.dehyphenate, html)

src/calibre/ebooks/conversion/utils.py

@@ -34,6 +34,8 @@ class HeuristicProcessor(object):
         self.line_close = "(</(?P=inner3)>)?\s*(</(?P=inner2)>)?\s*(</(?P=inner1)>)?\s*</(?P=outer)>"
         self.single_blank = re.compile(r'(\s*<p[^>]*>\s*</p>)', re.IGNORECASE)
         self.scene_break_open = '<p class="scenebreak" style="text-align:center; text-indent:0%; margin-top:1em; margin-bottom:1em; page-break-before:avoid">'
+        self.common_in_text_endings = u'[\"\'—’”,\.!\?\…\)„\w]'
+        self.common_in_text_beginnings = u'[\w\'\"“‘‛]'
 
     def is_pdftohtml(self, src):
         return '<!-- created by calibre\'s pdftohtml -->' in src[:1000]
@@ -638,7 +640,7 @@ class HeuristicProcessor(object):
             blanks_count = len(self.any_multi_blank.findall(html))
             if blanks_count >= 1:
                 html = self.merge_blanks(html, blanks_count)
-            scene_break_regex = self.line_open+'(?![\w\'\"])(?P<break>((?P<break_char>((?!\s)\W))\s*(?P=break_char)?)+)\s*'+self.line_close
+            scene_break_regex = self.line_open+'(?!('+self.common_in_text_beginnings+'|.*?'+self.common_in_text_endings+'<))(?P<break>((?P<break_char>((?!\s)\W))\s*(?P=break_char)?)+)\s*'+self.line_close
             scene_break = re.compile(r'%s' % scene_break_regex, re.IGNORECASE|re.UNICODE)
             # If the user has enabled scene break replacement, then either softbreaks
             # or 'hard' scene breaks are replaced, depending on which is in use

src/calibre/gui2/preferences/plugins.py

@@ -329,7 +329,7 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form):
                     return error_dialog(self, _('Must restart'),
                             _('You must restart calibre before you can'
                                 ' configure the <b>%s</b> plugin')%plugin.name, show=True)
-                if plugin.do_user_config():
+                if plugin.do_user_config(self.gui):
                     self._plugin_model.refresh_plugin(plugin)
             elif op == 'remove':
                 msg = _('Plugin <b>{0}</b> successfully removed').format(plugin.name)

src/calibre/library/server/content.py

@@ -125,7 +125,7 @@ class ContentServer(object):
             ua.startswith('Stanza')
 
         # A better search would be great
-        want_mobile = self.MOBILE_UA.search(ua) is not None
+        want_mobile = self.is_mobile_browser(ua)
         if self.opts.develop and not want_mobile:
             cherrypy.log('User agent: '+ua)
 

src/calibre/library/server/mobile.py

@@ -169,6 +169,10 @@ class MobileServer(object):
 
     MOBILE_UA = re.compile('(?i)(?:iPhone|Opera Mini|NetFront|webOS|Mobile|Android|imode|DoCoMo|Minimo|Blackberry|MIDP|Symbian|HD2|Kindle)')
 
+    def is_mobile_browser(self, ua):
+        match = self.MOBILE_UA.search(ua)
+        return match is not None and 'iPad' not in ua
+
     def add_routes(self, connect):
         connect('mobile', '/mobile', self.mobile)
         connect('mobile_css', '/mobile/style.css', self.mobile_css)

src/calibre/manual/faq.rst

@@ -316,6 +316,25 @@ When you first run |app|, it will ask you for a folder in which to store your bo
 
 Metadata about the books is stored in the file ``metadata.db`` at the top level of the library folder This file is is a sqlite database. When backing up your library make sure you copy the entire folder and all its sub-folders.
 
+How does |app| manage author names and sorting?
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Author names are complex, especially across cultures. |app| has a very flexible strategy for managing author names. The first thing to understand is that books and authors are separate entities in |app|. A book can have more than one author, and an author can have more than one book. You can manage the authors of a book by the edit metadata dialog. You can manage individual authors by right clicking on the author in the Tag Browser on the left of the main |app| screen and selecting :guilabel:`Manage authors`. Using this dialog you can change the name of an author and also how that name is sorted. This will automatically change the name of the author in all the books of that author. When a book has multiple authors, separate their names using the & character.
+
+Now coming to author name sorting:
+
+    * When a new author is added to |app| (this happens whenever a book by a new author is added), |app| automatically computes a sort string for both the book and the author.
+    * Authors in the Tag Browser are sorted by the sort value for the **authors**. Remember that this is different from the Author sort field for a book. 
+    * By default, this sort algorithm assumes that the author name is in ``First name Last name`` format and generates a ``Last name, First name`` sort value.
+    * You can change this algorithm by going to Preferences->Tweaks and setting the :guilabel:`author_sort_copy_method` tweak.
+    * You can force |app| to recalculate the author sort values for every author by right clicking on any author and selecting :guilabel:`Manage authors`
+    * You can force |app| to recalculate the author sort values for all books by using the bulk metadata edit dialog (select all books and click edit metadata)
+    * When recalculating the author sort values for books, |app| uses the author sort values for each individual author.
+    * You can control whether the Tag Browser display authors using their names or their sort values by setting the :guilabel:`categories_use_field_for_author_name` tweak in Preferences->Tweaks
+
+With all this flexibility, it is possible to have |app| manage your author names however you like. For example, one common request is to have |app| display author names LN, FN. To do this first set the ``author_sort_copy_method`` to ``copy``. Then change all author names to LN, FN via the Manage authors dialog. Then have |app| recalculate author sort values as described above.
+
+
 Why doesn't |app| let me store books in my own directory structure?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~