From 4fcbaa8919921d426bc4ad9f02eafb1a35835b6c Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Sat, 26 Nov 2011 20:13:13 +0530
Subject: [PATCH] Fix #896585 (extra articles for dutch language)

---
 resources/default_tweaks.py      |  4 +++-
 src/calibre/gui2/duplicates.py   | 11 +++++++++++
 src/calibre/library/database2.py | 17 +++++++++++++++--
 3 files changed, 29 insertions(+), 3 deletions(-)
 create mode 100644 src/calibre/gui2/duplicates.py

diff --git a/resources/default_tweaks.py b/resources/default_tweaks.py
index ecd3888bf7..224038b0f9 100644
--- a/resources/default_tweaks.py
+++ b/resources/default_tweaks.py
@@ -232,7 +232,9 @@ per_language_title_sort_articles = {
         'deu'  : (r'Der\s+', r'Die\s+', r'Das\s+', r'Den\s+', r'Ein\s+',
                   r'Eine\s+', r'Einen\s+', ),
         # Dutch
-        'nld'  : (r'De\s+', r'Het\s+', r'Een\s+', ),
+        'nld'  : (r'De\s+', r'Het\s+', r'Een\s+', r"'n\s+", r"'s\s+", r'Ene\s+',
+                  r'Ener\s+', r'Enes\s+', r'Den\s+', r'Der\s+', r'Des\s+',
+                  r"'t\s+"),
         # Swedish
         'swe'  : (r'En\s+', r'Ett\s+', r'Det\s+', r'Den\s+', r'De\s+', ),
         # Turkish
diff --git a/src/calibre/gui2/duplicates.py b/src/calibre/gui2/duplicates.py
new file mode 100644
index 0000000000..cc6da1e995
--- /dev/null
+++ b/src/calibre/gui2/duplicates.py
@@ -0,0 +1,11 @@
+#!/usr/bin/env python
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import (unicode_literals, division, absolute_import,
+                        print_function)
+
+__license__   = 'GPL v3'
+__copyright__ = '2011, Kovid Goyal <kovid@kovidgoyal.net>'
+__docformat__ = 'restructuredtext en'
+
+
+
diff --git a/src/calibre/library/database2.py b/src/calibre/library/database2.py
index a917aa09b2..3782149512 100644
--- a/src/calibre/library/database2.py
+++ b/src/calibre/library/database2.py
@@ -13,7 +13,7 @@ import threading, random
 from itertools import repeat
 from math import ceil
 
-from calibre import prints
+from calibre import prints, force_unicode
 from calibre.ebooks.metadata import (title_sort, author_to_author_sort,
         string_to_authors, authors_to_string, get_title_sort_pat)
 from calibre.ebooks.metadata.opf2 import metadata_to_opf
@@ -33,7 +33,7 @@ from calibre import isbytestring
 from calibre.utils.filenames import ascii_filename
 from calibre.utils.date import utcnow, now as nowf, utcfromtimestamp
 from calibre.utils.config import prefs, tweaks, from_json, to_json
-from calibre.utils.icu import sort_key, strcmp
+from calibre.utils.icu import sort_key, strcmp, lower
 from calibre.utils.search_query_parser import saved_searches, set_saved_searches
 from calibre.ebooks import BOOK_EXTENSIONS, check_ebook_format
 from calibre.utils.magick.draw import save_cover_data_to
@@ -1003,6 +1003,19 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
             return bool(self.conn.get('SELECT id FROM books where title=?', (title,), all=False))
         return False
 
+    def books_with_same_title(self, mi, all_matches=True):
+        title = mi.title
+        ans = set()
+        if title:
+            title = lower(force_unicode(title))
+            for book_id in self.all_ids():
+                x = self.title(book_id, index_is_id=True)
+                if lower(x) == title:
+                    ans.add(book_id)
+                    if not all_matches:
+                        break
+        return ans
+
     def find_identical_books(self, mi):
         fuzzy_title_patterns = [(re.compile(pat, re.IGNORECASE) if
             isinstance(pat, basestring) else pat, repl) for pat, repl in