Added an old character dict.

6 files changed, 70 insertions, 2 deletions

diff --git a/data/Makefile.am b/data/Makefile.am
index fcd3375..25f4f23 100644
--- a/data/Makefile.am
+++ b/data/Makefile.am
@@ -20,11 +20,13 @@
 # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 
 dicts_DATA = \
+	oldchar.t \
 	symbol.t \
 	$(NULL)
 
 dictsdir = $(pkgdatadir)/dicts
 
 EXTRA_DIST = \
+        oldchar.t \
         symbol.t \
         $(NULL)
diff --git a/data/oldchar.t b/data/oldchar.t
new file mode 100644
index 0000000..25bbf70
--- /dev/null
+++ b/data/oldchar.t
@@ -0,0 +1,30 @@
+# vim:set noet ts=4:
+#
+# ibus-anthy - The Anthy engine for IBus
+#
+# Copyright (c) 2010-2011 Takao Fujiwara <takao.fujiwara1@gmail.com>
+# Copyright (c) 2010-2011 Red Hat, Inc.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2, or (at your option)
+# any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+#
+# This file was imported from im-dict-ja
+# im-dict-ja - Japanese word dictionary set for input method
+# http://github.com/fujiwarat/im-dict-ja
+#
+# Typing 'va' can convert 'ヷ' with this dictionary.
+う゛ぁ #T35*500 ヷ
+う゛ぃ #T35*500 ヸ
+う゛ぇ #T35*500 ヹ
+う゛ぉ #T35*500 ヺ
diff --git a/engine/engine.py b/engine/engine.py
index c32b261..ae78d0f 100644
--- a/engine/engine.py
+++ b/engine/engine.py
@@ -721,7 +721,8 @@ class Engine(ibus.EngineBase):
         files = self.__prefs.get_value('dict', 'files')
         if id == 'embedded':
             pass
-        elif id == 'anthy_zipcode' or id == 'ibus_symbol':
+        elif id == 'anthy_zipcode' or id == 'ibus_symbol' or \
+             id == 'ibus_oldchar':
             file = self.__prefs.get_value('dict', id)[0]
         else:
             found = False
@@ -792,6 +793,15 @@ class Engine(ibus.EngineBase):
             else:
                 break
 
+    def __normalize_preedit(self, preedit):
+        if not self.__is_utf8:
+            return preedit
+        for key in romaji_normalize_rule.keys():
+            if preedit.find(key) >= 0:
+                for value in romaji_normalize_rule[key]:
+                    preedit = preedit.replace(key, value)
+        return preedit
+
     # begine convert
     def __begin_anthy_convert(self):
         if self.__segment_mode & SEGMENT_IMMEDIATE:
@@ -803,6 +813,7 @@ class Engine(ibus.EngineBase):
 #        text, cursor = self.__preedit_ja_string.get_hiragana()
         text, cursor = self.__preedit_ja_string.get_hiragana(True)
 
+        text = self.__normalize_preedit(text)
         self.__context.set_string(text.encode("utf8"))
         if self.__segment_mode & SEGMENT_SINGLE:
             self.__join_all_segments()
@@ -835,6 +846,7 @@ class Engine(ibus.EngineBase):
     def __end_convert(self):
         self.__end_anthy_convert()
 
+    # test case 'verudhi' can show U+3046 + U+309B and U+3094
     def __candidate_cb(self, candidate):
         if not self.__is_utf8:
             return
@@ -1442,6 +1454,8 @@ class Engine(ibus.EngineBase):
             id = 'anthy_zipcode'
         elif file in cls.__prefs.get_value('dict', 'ibus_symbol'):
             id = 'ibus_symbol'
+        elif file in cls.__prefs.get_value('dict', 'ibus_oldchar'):
+            id = 'ibus_oldchar'
         else:
             id = cls._get_quoted_id(file)
         return id
diff --git a/engine/tables.py b/engine/tables.py
index af99be1..e312d72 100644
--- a/engine/tables.py
+++ b/engine/tables.py
@@ -359,7 +359,12 @@ romaji_correction_rule = {
 
 # EUC-JP and SJIS do not have the chars
 romaji_utf8_rule = {
-    u"ヴ" : (u"ゔ"),
+    u"う゛" : [u"ゔ"],
+}
+
+# Hiragana normalization is needed for the personal dict.
+romaji_normalize_rule = {
+    u"ヴ" : [u"う゛"],
 }
 
 # a port of 101kana.sty from scim-anthy
diff --git a/setup/anthyprefs.py.in b/setup/anthyprefs.py.in
index e0910b5..fe238a5 100644
--- a/setup/anthyprefs.py.in
+++ b/setup/anthyprefs.py.in
@@ -817,9 +817,11 @@ _config = {
     'dict': {
         'anthy_zipcode': ['@ANTHY_ZIPCODE_FILE@'],
         'ibus_symbol': ['@pkgdatadir@/dicts/symbol.t'],
+        'ibus_oldchar': ['@pkgdatadir@/dicts/oldchar.t'],
         'files': [
             '@ANTHY_ZIPCODE_FILE@',
             '@pkgdatadir@/dicts/symbol.t',
+            '@pkgdatadir@/dicts/oldchar.t',
         ],
     },
 
@@ -868,6 +870,17 @@ _config = {
         'reverse': False,
         'is_system': True,
     },
+
+    'dict/file/ibus_oldchar': {
+        'embed': False,
+        'single': True,
+        'icon': None,
+        'short_label': '旧',
+        'long_label': N_("Old Character Style"),
+        'preview_lines': -1,
+        'reverse': False,
+        'is_system': True,
+    },
 }
 
 _shortcut_default = {
diff --git a/setup/main.py b/setup/main.py
index fb7ff88..8d5cfe5 100644
--- a/setup/main.py
+++ b/setup/main.py
@@ -528,6 +528,8 @@ class AnthySetup(object):
             return self.prefs.get_value('dict', 'anthy_zipcode')[0]
         elif selected_id == 'ibus_symbol':
             return self.prefs.get_value('dict', 'ibus_symbol')[0]
+        elif selected_id == 'ibus_oldchar':
+            return self.prefs.get_value('dict', 'ibus_oldchar')[0]
         for file in files:
             id = self.__get_quoted_id(file)
             if selected_id == id:
@@ -573,6 +575,8 @@ class AnthySetup(object):
                 id = 'anthy_zipcode'
             elif file in prefs.get_value('dict', 'ibus_symbol'):
                 id = 'ibus_symbol'
+            elif file in prefs.get_value('dict', 'ibus_oldchar'):
+                id = 'ibus_oldchar'
             else:
                 id = self.__get_quoted_id(file)
                 section = 'dict/file/' + id