Add Kana Typing related tables.

2 files changed, 169 insertions, 31 deletions

diff --git a/engine/engine.py b/engine/engine.py
index 074acd8..db6f195 100644
--- a/engine/engine.py
+++ b/engine/engine.py
@@ -803,7 +803,7 @@ class JaSegment:
             self.__jachars = jachars
             return []
 
-        jachars, c = double_consonat_typing_rule.get(text, (None, None))
+        jachars, c = romaji_double_consonat_typing_rule.get(text, (None, None))
         if jachars:
             self.__enchars = text[0]
             self.__jachars = jachars
@@ -818,13 +818,13 @@ class JaSegment:
                 self.__enchars = text[:i]
                 return [jasegment]
 
-            jachars, c = double_consonat_typing_rule.get(enchars, (None, None))
+            jachars, c = romaji_double_consonat_typing_rule.get(enchars, (None, None))
             if jachars:
                 jasegment = JaSegment(enchars[:-len(c)], jachars)
                 self.__enchars = text[:i]
                 return [jasegment, JaSegment(c)]
 
-            jachars, c = correction_rule.get(enchars, (None, None))
+            jachars, c = romaji_correction_rule.get(enchars, (None, None))
             if jachars:
                 jasegment = JaSegment(enchars[:-len(c)], jachars)
                 self.__enchars = text[:i]
@@ -849,7 +849,7 @@ class JaSegment:
             self.__jachars = jachars
             return []
 
-        jachars, c = double_consonat_typing_rule.get(text, (None, None))
+        jachars, c = romaji_double_consonat_typing_rule.get(text, (None, None))
         if jachars:
             self.__enchars = c
             return [JaSegment(text[0], jachars)]
@@ -863,12 +863,12 @@ class JaSegment:
                 self.__enchars = text[i:]
                 return [jasegment]
 
-            jachars, c = double_consonat_typing_rule.get(enchars, (None, None))
+            jachars, c = romaji_double_consonat_typing_rule.get(enchars, (None, None))
             if jachars:
                 self.__enchars = c + text[i:]
                 return [JaSegment(enchars[:-len(c)], jachars)]
 
-            jachars, c = correction_rule.get(enchars, (None, None))
+            jachars, c = romaji_correction_rule.get(enchars, (None, None))
             if jachars:
                 self.__enchars = c + text[i:]
                 return [JaSegment(enchars[:-len(c)], jachars)]
diff --git a/engine/tables.py b/engine/tables.py
index 5bf44f9..9694ae0 100644
--- a/engine/tables.py
+++ b/engine/tables.py
@@ -260,7 +260,8 @@ romaji_typing_rule = {
     u"_"  : u"＿",
 }
 
-double_consonat_typing_rule = {
+# this is only used with romaji_typing_rule
+romaji_double_consonat_typing_rule = {
     # double consonant rule
     u"bb" : (u"っ", u"b"),
     u"cc" : (u"っ", u"c"),
@@ -282,7 +283,8 @@ double_consonat_typing_rule = {
     u"zz" : (u"っ", u"z"),
 }
 
-correction_rule = {
+# this is only used with romaji_typing_rule
+romaji_oorrection_rule = {
     u"nb" : (u"ん", u"b"),
     u"nc" : (u"ん", u"c"),
     u"nd" : (u"ん", u"d"),
@@ -303,6 +305,162 @@ correction_rule = {
     u"nz" : (u"ん", u"z"),
 }
 
+# a port of 101kana.sty from scim-anthy
+kana_typing_rule = {
+    # no modifiers keys
+    u"1" : u"ぬ",
+    u"2" : u"ふ",
+    u"3" : u"あ",
+    u"4" : u"う",
+    u"5" : u"え",
+    u"6" : u"お",
+    u"7" : u"や",
+    u"8" : u"ゆ",
+    u"9" : u"よ",
+    u"0" : u"わ",
+    u"-" : u"ほ",
+    u"^" : u"へ",
+
+    u"q" : u"た",
+    u"w" : u"て",
+    u"e" : u"い",
+    u"r" : u"す",
+    u"t" : u"か",
+    u"y" : u"ん",
+    u"u" : u"な",
+    u"i" : u"に",
+    u"o" : u"ら",
+    u"p" : u"せ",
+    u"@" : u"゛",
+    u"[" : u"゜",
+
+    u"a" : u"ち",
+    u"s" : u"と",
+    u"d" : u"し",
+    u"f" : u"は",
+    u"g" : u"き",
+    u"h" : u"く",
+    u"j" : u"ま",
+    u"k" : u"の",
+    u"l" : u"り",
+    u";" : u"れ",
+    u":" : u"け",
+    u"]" : u"む",
+
+    u"z" : u"つ",
+    u"x" : u"さ",
+    u"c" : u"そ",
+    u"v" : u"ひ",
+    u"b" : u"こ",
+    u"n" : u"み",
+    u"m" : u"も",
+    u"," : u"ね",
+    u"." : u"る",
+    u"/" : u"め",
+    u"\\" : u"ー",
+
+    # shift modifiered keys
+    u"!" : u"ぬ",
+    u"\"" : u"ふ",
+    u"#" : u"ぁ",
+    u"$" : u"ぅ",
+    u"%" : u"ぇ",
+    u"&" : u"ぉ",
+    u"'" : u"ゃ",
+    u"(" : u"ゅ",
+    u")" : u"ょ",
+    u"~" : u"を",
+    u"=" : u"ほ",
+    u"|" : u"ー",
+
+    u"Q" : u"た",
+    u"W" : u"て",
+    u"E" : u"ぃ",
+    u"R" : u"す",
+    u"T" : u"ヵ",
+    u"Y" : u"ん",
+    u"U" : u"な",
+    u"I" : u"に",
+    u"O" : u"ら",
+    u"P" : u"せ",
+    u"`" : u"゛",
+
+    u"{" : u"「",
+
+    u"A" : u"ち",
+    u"S" : u"と",
+    u"D" : u"し",
+    u"F" : u"ゎ",
+    u"G" : u"き",
+    u"H" : u"く",
+    u"J" : u"ま",
+    u"K" : u"の",
+    u"L" : u"り",
+    u"+" : u"れ",
+    u"*" : u"ヶ",
+
+    u"}" : u"」",
+
+    u"Z" : u"っ",
+    u"X" : u"さ",
+    u"C" : u"そ",
+    u"V" : u"ゐ",
+    u"B" : u"こ",
+    u"M" : u"も",
+    u"N" : u"み",
+
+    u"?" : u"・",
+    u"_" : u"ろ",
+}
+
+kana_voiced_consonant_rule = {
+    u"か@" : u"が",
+    u"き@" : u"ぎ",
+    u"く@" : u"ぐ",
+    u"け@" : u"げ",
+    u"こ@" : u"ご",
+    u"さ@" : u"ざ",
+    u"し@" : u"じ",
+    u"す@" : u"ず",
+    u"せ@" : u"ぜ",
+    u"そ@" : u"ぞ",
+    u"た@" : u"だ",
+    u"ち@" : u"ぢ",
+    u"つ@" : u"づ",
+    u"て@" : u"で",
+    u"と@" : u"ど",
+    u"は@" : u"ば",
+    u"ひ@" : u"び",
+    u"ふ@" : u"ぶ",
+    u"へ@" : u"べ",
+    u"ほ@" : u"ぼ",
+    u"か`" : u"が",
+    u"き`" : u"ぎ",
+    u"く`" : u"ぐ",
+    u"け`" : u"げ",
+    u"こ`" : u"ご",
+    u"さ`" : u"ざ",
+    u"し`" : u"じ",
+    u"す`" : u"ず",
+    u"せ`" : u"ぜ",
+    u"そ`" : u"ぞ",
+    u"た`" : u"だ",
+    u"ち`" : u"ぢ",
+    u"つ`" : u"づ",
+    u"て`" : u"で",
+    u"と`" : u"ど",
+    u"は`" : u"ば",
+    u"ひ`" : u"び",
+    u"ふ`" : u"ぶ",
+    u"へ`" : u"べ",
+    u"ほ`" : u"ぼ",
+    u"は[" : u"ぱ",
+    u"ひ[" : u"ぴ",
+    u"ふ[" : u"ぷ",
+    u"へ[" : u"ぺ",
+    u"ほ[" : u"ぽ",
+}
+
 symbols_set = set([
     u",",
     u".",
@@ -427,37 +585,17 @@ hiragana_katakana_table = {
     u"ゑ" : (u"ヱ", u"ｪ"),
     u"ヴ" : (u"ヴ", u"ｳﾞ"),
 
-    # double consonant rule
-    # u"っb" : (u"ッb", u"ｯb"),
-    # u"っc" : (u"ッc", u"ｯc"),
-    # u"っd" : (u"ッd", u"ｯd"),
-    # u"っf" : (u"ッf", u"ｯf"),
-    # u"っg" : (u"ッg", u"ｯg"),
-    # u"っh" : (u"ッh", u"ｯh"),
-    # u"っj" : (u"ッj", u"ｯj"),
-    # u"っk" : (u"ッk", u"ｯk"),
-    # u"っm" : (u"ッm", u"ｯm"),
-    # u"っp" : (u"ッp", u"ｯp"),
-    # u"っr" : (u"ッr", u"ｯr"),
-    # u"っs" : (u"ッs", u"ｯs"),
-    # u"っt" : (u"ッt", u"ｯt"),
-    # u"っv" : (u"ッv", u"ｯv"),
-    # u"っw" : (u"ッw", u"ｯw"),
-    # u"っx" : (u"ッx", u"ｯx"),
-    # u"っy" : (u"ッy", u"ｯy"),
-    # u"っz" : (u"ッz", u"ｯz"),
-
     # symbols
     u"ー" : (u"ー", u"ｰ"),
     u"、" : (u"、", u"､"),
     u"。" : (u"。", u"｡"),
     u"！" : (u"！", u"!"),
-    u"”" : (u"”", u"\""),
+    u"”"  : (u"”", u"\""),
     u"＃" : (u"＃", u"#"),
     u"＄" : (u"＄", u"$"),
     u"％" : (u"％", u"%"),
     u"＆" : (u"＆", u"&"),
-    u"’" : (u"’", u"'"),
+    u"’"  : (u"’", u"'"),
     u"（" : (u"（", u""),
     u"）" : (u"）", u")"),
     u"〜" : (u"〜", u"~"),
@@ -465,7 +603,7 @@ hiragana_katakana_table = {
     u"＾" : (u"＾", u"u"),
     u"＼" : (u"＼", u"\\"),
     u"｜" : (u"｜", u"|"),
-    u"‘" : (u"‘", u"`"),
+    u"‘"  : (u"‘", u"`"),
     u"＠" : (u"＠", u"@"),
     u"｛" : (u"｛", u""),
     u"「" : (u"「", u"｢"),