Merge from trunk

resources/recipes/dailytportal.recipe

@@ -0,0 +1,66 @@
+__license__   = 'GPL v3'
+__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
+'''
+daily.tportal.hr
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Pagina12(BasicNewsRecipe):
+    title                 = 'Daily tportal.h'
+    __author__            = 'Darko Miletic'
+    description           = 'News from Croatia'
+    publisher             = 'tportal.hr'
+    category              = 'news, politics, Croatia'
+    oldest_article        = 2
+    max_articles_per_feed = 200
+    no_stylesheets        = True
+    encoding              = 'utf-8'
+    use_embedded_content  = False
+    language              = 'en_HR'
+    remove_empty_feeds    = True
+    publication_type      = 'newsportal'
+    extra_css             = """
+                               body{font-family: Verdana,sans-serif }
+                               img{margin-bottom: 0.4em; display:block}
+                               h1,h2{color: #2D648A; font-family: Georgia,serif}
+                               .artAbstract{font-size: 1.2em; font-family: Georgia,serif}
+                            """
+
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    remove_tags = [
+                     dict(name=['meta','link','embed','object','iframe','base'])
+                    ,dict(name='div', attrs={'class':'artInfo'})
+                  ]
+    remove_attributes=['lang']
+
+    keep_only_tags=dict(attrs={'class':'articleDetails'})
+
+    feeds = [(u'News', u'http://daily.tportal.hr/rss/dailynaslovnicarss.xml')]
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        for item in soup.findAll('a'):
+            limg = item.find('img')
+            if item.string is not None:
+               str = item.string
+               item.replaceWith(str)
+            else:
+               if limg:
+                  item.name = 'div'
+                  item.attrs = []
+               else:
+                   str = self.tag_to_string(item)
+                   item.replaceWith(str)
+        for item in soup.findAll('img'):
+            if not item.has_key('alt'):
+               item['alt'] = 'image'
+        return soup
+

resources/recipes/heise.recipe

@@ -52,6 +52,7 @@ class heiseDe(BasicNewsRecipe):
 		   dict(id='navi_login'),
 		   dict(id='navigation'),
 		   dict(id='breadcrumb'),
+		   dict(id='adblockerwarnung'),
 		   dict(id=''),
 		   dict(id='sitemap'),
 		   dict(id='bannerzone'),
@@ -67,3 +68,4 @@ class heiseDe(BasicNewsRecipe):
 
 
 
+

resources/recipes/hna.recipe

@@ -21,7 +21,7 @@ class hnaDe(BasicNewsRecipe):
     max_articles_per_feed = 40
     no_stylesheets = True
     remove_javascript = True
-    encoding = 'iso-8859-1'
+    encoding = 'utf-8'
 
     remove_tags = [dict(id='topnav'),
 		   dict(id='nav_main'),
@@ -60,3 +60,4 @@ class hnaDe(BasicNewsRecipe):
     feeds =  [ ('hna_soehre', 'http://feeds2.feedburner.com/hna/soehre'),
 	       ('hna_kassel', 'http://feeds2.feedburner.com/hna/kassel') ]
 
+

resources/recipes/zdnet.recipe

@@ -27,12 +27,34 @@ class cdnet(BasicNewsRecipe):
 		   dict(id='header'),
 		   dict(id='search'),
 		   dict(id='nav'),
+		   dict(id='blog-author-info'),
+		   dict(id='post-tags'),
+		   dict(id='bio-naraine'),
+		   dict(id='bio-kennedy'),
+		   dict(id='author-short-disclosure-kennedy'),
 		   dict(id=''),
 		   dict(name='div', attrs={'class':'banner'}),
+		   dict(name='div', attrs={'class':'int'}),
+		   dict(name='div', attrs={'class':'talkback clear space-2'}),
+		   dict(name='div', attrs={'class':'content-1 clear'}),
+		   dict(name='div', attrs={'class':'space-2'}),
+		   dict(name='div', attrs={'class':'space-3'}),
+		   dict(name='div', attrs={'class':'thumb-2 left'}),
+		   dict(name='div', attrs={'class':'hotspot'}),
+		   dict(name='div', attrs={'class':'hed hed-1 space-1'}),
+		   dict(name='div', attrs={'class':'view-1 clear content-3 space-2'}),
+		   dict(name='div', attrs={'class':'hed hed-1 space-1'}),
+		   dict(name='div', attrs={'class':'hed hed-1'}),
+		   dict(name='div', attrs={'class':'post-header'}),
+		   dict(name='div', attrs={'class':'lvl-nav clear'}),
+		   dict(name='div', attrs={'class':'t-share-overlay overlay-pop contain-overlay-4'}),
 		   dict(name='p', attrs={'class':'tags'}),
+		   dict(name='span', attrs={'class':'follow'}),
+		   dict(name='span', attrs={'class':'int'}),
+		   dict(name='h4', attrs={'class':'h s-4'}),
 		   dict(name='a', attrs={'href':'http://www.twitter.com/ryanaraine'}),
 		   dict(name='div', attrs={'class':'special1'})]
-    remove_tags_after = [dict(name='div', attrs={'class':'bloggerDesc clear'})]
+    remove_tags_after = [dict(name='div', attrs={'class':'clear'})]
 
     feeds =  [ ('zdnet', 'http://feeds.feedburner.com/zdnet/security') ]
 
@@ -43,3 +65,4 @@ class cdnet(BasicNewsRecipe):
         return soup
 
 
+

src/calibre/devices/android/driver.py

@@ -54,7 +54,7 @@ class ANDROID(USBMS):
             0x1004 : { 0x61cc : [0x100] },
 
             # Archos
-            0x0e79 : { 0x1419: [0x0216], 0x1420 : [0x0216]},
+            0x0e79 : { 0x1419: [0x0216], 0x1420 : [0x0216], 0x1422 : [0x0216]},
 
             }
     EBOOK_DIR_MAIN = ['eBooks/import', 'wordplayer/calibretransfer', 'Books']
@@ -70,7 +70,7 @@ class ANDROID(USBMS):
             '__UMS_COMPOSITE', '_MB200', 'MASS_STORAGE', '_-_CARD', 'SGH-I897',
             'GT-I9000', 'FILE-STOR_GADGET', 'SGH-T959', 'SAMSUNG_ANDROID',
             'SCH-I500_CARD', 'SPH-D700_CARD', 'MB810', 'GT-P1000', 'DESIRE',
-            'SGH-T849', '_MB300', 'A70S', 'S_ANDROID', 'A101IT']
+            'SGH-T849', '_MB300', 'A70S', 'S_ANDROID', 'A101IT', 'A70H']
     WINDOWS_CARD_A_MEM = ['ANDROID_PHONE', 'GT-I9000_CARD', 'SGH-I897',
             'FILE-STOR_GADGET', 'SGH-T959', 'SAMSUNG_ANDROID', 'GT-P1000_CARD',
             'A70S', 'A101IT']

src/calibre/ebooks/conversion/utils.py

@@ -25,13 +25,15 @@ class HeuristicProcessor(object):
         self.chapters_with_title = 0
         self.blanks_deleted = False
         self.linereg = re.compile('(?<=<p).*?(?=</p>)', re.IGNORECASE|re.DOTALL)
-        self.blankreg = re.compile(r'\s*(?P<openline><p(?!\sid=\"softbreak\")[^>]*>)\s*(?P<closeline></p>)', re.IGNORECASE)
+        self.blankreg = re.compile(r'\s*(?P<openline><p(?!\sclass=\"softbreak\")[^>]*>)\s*(?P<closeline></p>)', re.IGNORECASE)
+        self.softbreak = re.compile(r'\s*(?P<openline><p(?=\sclass=\"softbreak\")[^>]*>)\s*(?P<closeline></p>)', re.IGNORECASE)
         self.multi_blank = re.compile(r'(\s*<p[^>]*>\s*</p>){2,}', re.IGNORECASE)
 
     def is_pdftohtml(self, src):
         return '<!-- created by calibre\'s pdftohtml -->' in src[:1000]
 
     def chapter_head(self, match):
+        from calibre.utils.html2text import html2text
         chap = match.group('chap')
         title = match.group('title')
         if not title:
@@ -40,10 +42,12 @@ class HeuristicProcessor(object):
                     " chapters. - " + unicode(chap))
             return '<h2>'+chap+'</h2>\n'
         else:
+            txt_chap = html2text(chap)
+            txt_title = html2text(title)
             self.html_preprocess_sections = self.html_preprocess_sections + 1
             self.log.debug("marked " + unicode(self.html_preprocess_sections) +
                     " chapters & titles. - " + unicode(chap) + ", " + unicode(title))
-            return '<h2>'+chap+'</h2>\n<h3>'+title+'</h3>\n'
+            return '<h2 title="'+txt_chap+', '+txt_title+'">'+chap+'</h2>\n<h3 class="sigilNotInTOC">'+title+'</h3>\n'
 
     def chapter_break(self, match):
         chap = match.group('section')
@@ -203,8 +207,8 @@ class HeuristicProcessor(object):
             blank_lines = ""
         opt_title_open = "("
         opt_title_close = ")?"
-        n_lookahead_open = "\s+(?!"
+        n_lookahead_open = "(?!\s*"
-        n_lookahead_close = ")"
+        n_lookahead_close = ")\s*"
 
         default_title = r"(<[ibu][^>]*>)?\s{0,3}(?!Chapter)([\w\:\'’\"-]+\s{0,3}){1,5}?(</[ibu][^>]*>)?(?=<)"
         simple_title = r"(<[ibu][^>]*>)?\s{0,3}(?!(Chapter|\s+<)).{0,65}?(</[ibu][^>]*>)?(?=<)"
@@ -215,7 +219,7 @@ class HeuristicProcessor(object):
             [r"[^'\"]?(Introduction|Synopsis|Acknowledgements|Epilogue|CHAPTER|Kapitel|Volume\b|Prologue|Book\b|Part\b|Dedication|Preface)\s*([\d\w-]+\:?\'?\s*){0,5}", True, True, True, False, "Searching for common section headings", 'common'],
             [r"[^'\"]?(CHAPTER|Kapitel)\s*([\dA-Z\-\'\"\?!#,]+\s*){0,7}\s*", True, True, True, False, "Searching for most common chapter headings", 'chapter'],  # Highest frequency headings which include titles
             [r"<b[^>]*>\s*(<span[^>]*>)?\s*(?!([*#•=]+\s*)+)(\s*(?=[\d.\w#\-*\s]+<)([\d.\w#-*]+\s*){1,5}\s*)(?!\.)(</span>)?\s*</b>", True, True, True, False, "Searching for emphasized lines", 'emphasized'], # Emphasized lines
-            [r"[^'\"]?(\d+(\.|:))\s*([\dA-Z\-\'\"#,]+\s*){0,7}\s*", True, True, True, False, "Searching for numeric chapter headings", 'numeric'],  # Numeric Chapters
+            [r"[^'\"]?(\d+(\.|:))\s*([\w\-\'\"#,]+\s*){0,7}\s*", True, True, True, False, "Searching for numeric chapter headings", 'numeric'],  # Numeric Chapters
             [r"([A-Z]\s+){3,}\s*([\d\w-]+\s*){0,3}\s*", True, True, True, False, "Searching for letter spaced headings", 'letter_spaced'],  # Spaced Lettering
             [r"[^'\"]?(\d+\.?\s+([\d\w-]+\:?\'?-?\s?){0,5})\s*", True, True, True, False, "Searching for numeric chapters with titles", 'numeric_title'], # Numeric Titles
             [r"[^'\"]?(\d+)\s*([\dA-Z\-\'\"\?!#,]+\s*){0,7}\s*", True, True, True, False, "Searching for simple numeric headings", 'plain_number'],  # Numeric Chapters, no dot or colon
@@ -275,7 +279,7 @@ class HeuristicProcessor(object):
                         self.log.debug(unicode(type_name)+" had "+unicode(hits)+" hits - "+unicode(self.chapters_no_title)+" chapters with no title, "+unicode(self.chapters_with_title)+" chapters with titles, "+unicode(float(self.chapters_with_title) / float(hits))+" percent. ")
                         if type_name == 'common':
                             analysis_result.append([chapter_type, n_lookahead_req, strict_title, ignorecase, title_req, log_message, type_name])
-                        elif self.min_chapters <= hits < max_chapters:
+                        elif self.min_chapters <= hits < max_chapters or self.min_chapters < 3 > hits:
                             analysis_result.append([chapter_type, n_lookahead_req, strict_title, ignorecase, title_req, log_message, type_name])
                             break
                 else:
@@ -367,6 +371,8 @@ class HeuristicProcessor(object):
         html = re.sub(ur'\s*<o:p>\s*</o:p>', ' ', html)
         # Delete microsoft 'smart' tags
         html = re.sub('(?i)</?st1:\w+>', '', html)
+        # Delete self closing paragraph tags
+        html = re.sub('<p\s?/>', '', html)
         # Get rid of empty span, bold, font, em, & italics tags
         html = re.sub(r"\s*<span[^>]*>\s*(<span[^>]*>\s*</span>){0,2}\s*</span>\s*", " ", html)
         html = re.sub(r"\s*<(font|[ibu]|em)[^>]*>\s*(<(font|[ibu]|em)[^>]*>\s*</(font|[ibu]|em)>\s*){0,2}\s*</(font|[ibu]|em)>", " ", html)
@@ -467,7 +473,7 @@ class HeuristicProcessor(object):
         if blanks_between_paragraphs and getattr(self.extra_opts, 'delete_blank_paragraphs', False):
             self.log.debug("deleting blank lines")
             self.blanks_deleted = True
-            html = self.multi_blank.sub('\n<p id="softbreak" style="margin-top:1.5em; margin-bottom:1.5em"> </p>', html)
+            html = self.multi_blank.sub('\n<p class="softbreak" style="margin-top:1.5em; margin-bottom:1.5em"> </p>', html)
             html = self.blankreg.sub('', html)
 
         # Determine line ending type
@@ -522,11 +528,11 @@ class HeuristicProcessor(object):
             # Center separator lines
             html = re.sub(u'<(?P<outer>p|div)[^>]*>\s*(<(?P<inner1>font|span|[ibu])[^>]*>)?\s*(<(?P<inner2>font|span|[ibu])[^>]*>)?\s*(<(?P<inner3>font|span|[ibu])[^>]*>)?\s*(?P<break>([*#•=✦]+\s*)+)\s*(</(?P=inner3)>)?\s*(</(?P=inner2)>)?\s*(</(?P=inner1)>)?\s*</(?P=outer)>', '<p style="text-align:center; margin-top:1.25em; margin-bottom:1.25em">' + '\g<break>' + '</p>', html)
             if not self.blanks_deleted:
-                html = self.multi_blank.sub('\n<p id="softbreak" style="margin-top:1.5em; margin-bottom:1.5em"> </p>', html)
+                html = self.multi_blank.sub('\n<p class="softbreak" style="margin-top:1.5em; margin-bottom:1.5em"> </p>', html)
-            html = re.sub('<p\s+id="softbreak"[^>]*>\s*</p>', '<div id="softbreak" style="margin-left: 45%; margin-right: 45%; margin-top:1.5em; margin-bottom:1.5em"><hr style="height: 3px; background:#505050" /></div>', html)
+            html = re.sub('<p\s+class="softbreak"[^>]*>\s*</p>', '<div id="softbreak" style="margin-left: 45%; margin-right: 45%; margin-top:1.5em; margin-bottom:1.5em"><hr style="height: 3px; background:#505050" /></div>', html)
 
         if self.deleted_nbsps:
             # put back non-breaking spaces in empty paragraphs to preserve original formatting
             html = self.blankreg.sub('\n'+r'\g<openline>'+u'\u00a0'+r'\g<closeline>', html)
-
+            html = self.softbreak.sub('\n'+r'\g<openline>'+u'\u00a0'+r'\g<closeline>', html)
         return html

src/calibre/ebooks/metadata/fetch.py

@@ -411,7 +411,7 @@ def search(title=None, author=None, publisher=None, isbn=None, isbndb_key=None,
                     r.pubdate = pubdate
 
     def fix_case(x):
-        if x and x.isupper():
+        if x:
             x = titlecase(x)
         return x
 

src/calibre/gui2/convert/regex_builder.py

@@ -6,7 +6,7 @@ __docformat__ = 'restructuredtext en'
 
 import re
 
-from PyQt4.QtCore import SIGNAL, Qt
+from PyQt4.QtCore import SIGNAL, Qt, pyqtSignal
 from PyQt4.QtGui import QDialog, QWidget, QDialogButtonBox, \
                         QBrush, QTextCursor, QTextEdit
 
@@ -19,8 +19,8 @@ from calibre.gui2.dialogs.choose_format import ChooseFormatDialog
 
 class RegexBuilder(QDialog, Ui_RegexBuilder):
 
-    def __init__(self, db, book_id, regex, *args):
+    def __init__(self, db, book_id, regex, doc=None, parent=None):
-        QDialog.__init__(self, *args)
+        QDialog.__init__(self, parent)
         self.setupUi(self)
 
         self.regex.setText(regex)
@@ -28,9 +28,13 @@ class RegexBuilder(QDialog, Ui_RegexBuilder):
 
         if not db or not book_id:
             self.button_box.addButton(QDialogButtonBox.Open)
-        elif not self.select_format(db, book_id):
+        elif not doc and not self.select_format(db, book_id):
             self.cancelled = True
             return
+
+        if doc:
+            self.preview.setPlainText(doc)
+
         self.cancelled = False
         self.connect(self.button_box, SIGNAL('clicked(QAbstractButton*)'), self.button_clicked)
         self.connect(self.regex, SIGNAL('textChanged(QString)'), self.regex_valid)
@@ -153,24 +157,36 @@ class RegexBuilder(QDialog, Ui_RegexBuilder):
         if button == self.button_box.button(QDialogButtonBox.Ok):
             self.accept()
 
+    def doc(self):
+        return unicode(self.preview.toPlainText())
+
 class RegexEdit(QWidget, Ui_Edit):
 
+    doc_update = pyqtSignal(unicode)
+
     def __init__(self, parent=None):
         QWidget.__init__(self, parent)
         self.setupUi(self)
 
         self.book_id = None
         self.db = None
+        self.doc_cache = None
 
         self.connect(self.button, SIGNAL('clicked()'), self.builder)
 
     def builder(self):
-        bld = RegexBuilder(self.db, self.book_id, self.edit.text(), self)
+        bld = RegexBuilder(self.db, self.book_id, self.edit.text(), self.doc_cache, self)
         if bld.cancelled:
             return
+        if not self.doc_cache:
+            self.doc_cache = bld.doc()
+            self.doc_update.emit(self.doc_cache)
         if bld.exec_() == bld.Accepted:
             self.edit.setText(bld.regex.text())
 
+    def doc(self):
+        return self.doc_cache
+
     def setObjectName(self, *args):
         QWidget.setObjectName(self, *args)
         if hasattr(self, 'edit'):
@@ -185,8 +201,11 @@ class RegexEdit(QWidget, Ui_Edit):
     def set_db(self, db):
         self.db = db
 
+    def set_doc(self, doc):
+        self.doc_cache = doc
+
     def break_cycles(self):
-        self.db = None
+        self.db = self.doc_cache = None
 
     @property
     def text(self):

src/calibre/gui2/convert/search_and_replace.py

@@ -35,13 +35,26 @@ class SearchAndReplaceWidget(Widget, Ui_Form):
         self.opt_sr3_search.set_book_id(book_id)
         self.opt_sr3_search.set_db(db)
 
+        self.opt_sr1_search.doc_update.connect(self.update_doc)
+        self.opt_sr2_search.doc_update.connect(self.update_doc)
+        self.opt_sr3_search.doc_update.connect(self.update_doc)
+
     def break_cycles(self):
         Widget.break_cycles(self)
 
+        self.opt_sr1_search.doc_update.disconnect()
+        self.opt_sr2_search.doc_update.disconnect()
+        self.opt_sr3_search.doc_update.disconnect()
+
         self.opt_sr1_search.break_cycles()
         self.opt_sr2_search.break_cycles()
         self.opt_sr3_search.break_cycles()
 
+    def update_doc(self, doc):
+        self.opt_sr1_search.set_doc(doc)
+        self.opt_sr2_search.set_doc(doc)
+        self.opt_sr3_search.set_doc(doc)
+
     def pre_commit_check(self):
         for x in ('sr1_search', 'sr2_search', 'sr3_search'):
             x = getattr(self, 'opt_'+x)

src/calibre/gui2/dialogs/metadata_bulk.py

@@ -7,7 +7,7 @@ import re, os
 
 from PyQt4.Qt import Qt, QDialog, QGridLayout, QVBoxLayout, QFont, QLabel, \
                      pyqtSignal, QDialogButtonBox, QInputDialog, QLineEdit, \
-                     QMessageBox, QDate, QLineEdit
+                     QMessageBox, QDate
 
 from calibre.gui2.dialogs.metadata_bulk_ui import Ui_MetadataBulkDialog
 from calibre.gui2.dialogs.tag_editor import TagEditor
@@ -15,7 +15,7 @@ from calibre.ebooks.metadata import string_to_authors, authors_to_string
 from calibre.ebooks.metadata.book.base import composite_formatter
 from calibre.ebooks.metadata.meta import get_metadata
 from calibre.gui2.custom_column_widgets import populate_metadata_page
-from calibre.gui2 import error_dialog, ResizableDialog, UNDEFINED_QDATE
+from calibre.gui2 import error_dialog, ResizableDialog, UNDEFINED_QDATE, gprefs
 from calibre.gui2.progress_indicator import ProgressIndicator
 from calibre.utils.config import dynamic, JSONConfig
 from calibre.utils.titlecase import titlecase
@@ -321,8 +321,15 @@ class MetadataBulkDialog(ResizableDialog, Ui_MetadataBulkDialog):
             'This operation cannot be canceled or undone'))
         self.do_again = False
         self.central_widget.setCurrentIndex(tab)
+        geom = gprefs.get('bulk_metadata_window_geometry', None)
+        if geom is not None:
+            self.restoreGeometry(bytes(geom))
         self.exec_()
 
+    def save_state(self, *args):
+        gprefs['bulk_metadata_window_geometry'] = \
+            bytearray(self.saveGeometry())
+
     def do_apply_pubdate(self, *args):
         self.apply_pubdate.setChecked(True)
 
@@ -790,7 +797,12 @@ class MetadataBulkDialog(ResizableDialog, Ui_MetadataBulkDialog):
             self.series_start_number.setEnabled(False)
             self.series_start_number.setValue(1)
 
+    def reject(self):
+        self.save_state()
+        ResizableDialog.reject(self)
+
     def accept(self):
+        self.save_state()
         if len(self.ids) < 1:
             return QDialog.accept(self)
 

src/calibre/gui2/dialogs/metadata_bulk.ui

@@ -6,8 +6,8 @@
    <rect>
     <x>0</x>
     <y>0</y>
-    <width>850</width>
+    <width>962</width>
-    <height>650</height>
+    <height>727</height>
    </rect>
   </property>
   <property name="windowTitle">
@@ -44,8 +44,8 @@
        <rect>
         <x>0</x>
         <y>0</y>
-        <width>832</width>
+        <width>954</width>
-        <height>574</height>
+        <height>666</height>
        </rect>
       </property>
       <layout class="QVBoxLayout" name="verticalLayout_2">
@@ -55,7 +55,7 @@
        <item>
         <widget class="QTabWidget" name="central_widget">
          <property name="currentIndex">
-          <number>2</number>
+          <number>0</number>
          </property>
          <widget class="QWidget" name="tabWidgetPage1">
           <attribute name="title">
@@ -996,8 +996,8 @@ not multiple and the destination field is multiple</string>
                <rect>
                 <x>0</x>
                 <y>0</y>
-                <width>810</width>
+                <width>197</width>
-                <height>264</height>
+                <height>60</height>
                </rect>
               </property>
               <layout class="QGridLayout" name="testgrid">

src/calibre/gui2/dialogs/tag_editor.py

@@ -16,7 +16,7 @@ class TagEditor(QDialog, Ui_TagEditor):
         self.setupUi(self)
 
         self.db = db
-        self.index = db.row(id_)
+        self.index = db.row(id_) if id_ is not None else None
         if self.index is not None:
             tags = self.db.tags(self.index)
         else:

src/calibre/gui2/filename_pattern.ui

@@ -43,7 +43,17 @@ p, li { white-space: pre-wrap; }
      </property>
      <layout class="QVBoxLayout">
       <item>
-       <widget class="QLineEdit" name="re"/>
+       <widget class="QComboBox" name="re">
+        <property name="editable">
+         <bool>true</bool>
+        </property>
+        <property name="maxCount">
+         <number>10</number>
+        </property>
+        <property name="insertPolicy">
+         <enum>QComboBox::InsertAtTop</enum>
+        </property>
+       </widget>
       </item>
      </layout>
     </widget>
@@ -94,8 +104,8 @@ p, li { white-space: pre-wrap; }
             <rect>
              <x>0</x>
              <y>0</y>
-             <width>301</width>
+             <width>277</width>
-             <height>234</height>
+             <height>276</height>
             </rect>
            </property>
            <layout class="QGridLayout" name="gridLayout_2">

src/calibre/gui2/widgets.py

@@ -16,7 +16,6 @@ from PyQt4.Qt import QIcon, QFont, QLabel, QListWidget, QAction, \
                         QTimer, QRect
 
 from calibre.gui2 import NONE, error_dialog, pixmap_to_data, gprefs
-from calibre.constants import isosx
 from calibre.gui2.filename_pattern_ui import Ui_Form
 from calibre import fit_image
 from calibre.ebooks import BOOK_EXTENSIONS
@@ -67,17 +66,31 @@ class FilenamePattern(QWidget, Ui_Form):
         self.setupUi(self)
 
         self.connect(self.test_button, SIGNAL('clicked()'), self.do_test)
-        self.connect(self.re, SIGNAL('returnPressed()'), self.do_test)
+        self.connect(self.re.lineEdit(), SIGNAL('returnPressed()'), self.do_test)
-        self.initialize()
+        self.re.lineEdit().textChanged.connect(lambda x: self.changed_signal.emit())
-        self.re.textChanged.connect(lambda x: self.changed_signal.emit())
 
     def initialize(self, defaults=False):
+        # Get all itmes in the combobox. If we are resting
+        # to defaults we don't want to lose what the user
+        # has added.
+        val_hist = [unicode(self.re.lineEdit().text())] + [unicode(self.re.itemText(i)) for i in xrange(self.re.count())]
+        self.re.clear()
+        
         if defaults:
             val = prefs.defaults['filename_pattern']
         else:
             val = prefs['filename_pattern']
-        self.re.setText(val)
+        self.re.lineEdit().setText(val)
         
+        val_hist += gprefs.get('filename_pattern_history', ['(?P<title>.+)', '(?P<author>[^_-]+) -?\s*(?P<series>[^_0-9-]*)(?P<series_index>[0-9]*)\s*-\s*(?P<title>[^_].+) ?'])
+        if val in val_hist:
+            del val_hist[val_hist.index(val)]
+        val_hist.insert(0, val)
+        for v in val_hist:
+            # Ensure we don't have duplicate items.
+            if v and self.re.findText(v) == -1:
+                self.re.addItem(v)
+        self.re.setCurrentIndex(0)
 
     def do_test(self):
         try:
@@ -110,12 +123,21 @@ class FilenamePattern(QWidget, Ui_Form):
 
 
     def pattern(self):
-        pat = unicode(self.re.text())
+        pat = unicode(self.re.lineEdit().text())
         return re.compile(pat)
 
     def commit(self):
         pat = self.pattern().pattern
         prefs['filename_pattern'] = pat
+        
+        history = []
+        history_pats = [unicode(self.re.lineEdit().text())] + [unicode(self.re.itemText(i)) for i in xrange(self.re.count())]
+        for p in history_pats[:14]:
+            # Ensure we don't have duplicate items.
+            if p and p not in history:
+                history.append(p)
+        gprefs['filename_pattern_history'] = history 
+        
         return pat
 
 
@@ -304,8 +326,9 @@ class FontFamilyModel(QAbstractListModel):
             return NONE
         if role == Qt.DisplayRole:
             return QVariant(family)
-        if not isosx and role == Qt.FontRole:
+        if False and role == Qt.FontRole:
-            # Causes a Qt crash with some fonts on OS X
+            # Causes a Qt crash with some fonts
+            # so disabled.
             return QVariant(QFont(family))
         return NONE
 

src/calibre/library/caches.py

@@ -135,7 +135,7 @@ def _match(query, value, matchkind):
             pass
     return False
 
-class CacheRow(list):
+class CacheRow(list): # {{{
 
     def __init__(self, db, composites, val):
         self.db = db
@@ -166,6 +166,7 @@ class CacheRow(list):
     def __getslice__(self, i, j):
         return self.__getitem__(slice(i, j))
 
+# }}}
 
 class ResultCache(SearchQueryParser): # {{{
 
@@ -192,7 +193,7 @@ class ResultCache(SearchQueryParser): # {{{
     def break_cycles(self):
         self._data = self.field_metadata = self.FIELD_MAP = \
             self.numeric_search_relops = self.date_search_relops = \
-            self.all_search_locations = None
+            self.all_search_locations = self.db_prefs = None
 
 
     def __getitem__(self, row):
@@ -410,7 +411,7 @@ class ResultCache(SearchQueryParser): # {{{
         res = set([])
         if self.db_prefs is None:
             return  res
-        user_cats = self.db_prefs['user_categories']
+        user_cats = self.db_prefs.get('user_categories', [])
         if location not in user_cats:
             return res
         c = set(candidates)

src/calibre/manual/conversion.rst

@@ -603,7 +603,7 @@ TXT input supports a number of options to differentiate how paragraphs are detec
         formatting will be applied.
 
     :guilabel:`Formatting Style: Heuristic`
-        Analyses the document for common chapter headings, scene breaks, and italicized words and applies the
+        Analyzes the document for common chapter headings, scene breaks, and italicized words and applies the
         appropriate html markup during conversion.
 
     :guilabel:`Formatting Style: Markdown`

src/calibre/utils/localization.py

@@ -105,6 +105,7 @@ _extra_lang_codes = {
         'en_TH' : _('English (Thailand)'),
         'en_CY' : _('English (Cyprus)'),
         'en_PK' : _('English (Pakistan)'),
+        'en_HR' : _('English (Croatia)'),
         'en_IL' : _('English (Israel)'),
         'en_SG' : _('English (Singapore)'),
         'en_YE' : _('English (Yemen)'),