ktrans: correct Korean input (thanks npmania!)

This patch implements two specific behaviors of Dubeolsik layout.

dubeollkup function makes Jongseong(final consonant) to be treated as
Choseong(initial consonant) when possible. For example, QWERTY input
"zhem" in Dubeolsik has to be "코드", not "콛ㅡ" where switched
Jongseong is "ㄷ".

dubeolbksp function emits out syllable remaining after single
backspace. So when user presses backspace on "코드", the expected output
is "코ㄷ", still allowing user to edit latter syllable, rather than
"코" without dubeolbksp. This should only apply to last syllable
considering it's de facto in Dubeolsik implementations.

sys/man/1/ktrans

@@ -51,7 +51,7 @@ Chinese.
 ctl-c and zh
 .TP
 Korean.
-ctl-k and ko
+ctl-s and ko
 .TP
 Vietnamese.
 ctl-v and vn
@@ -199,8 +199,8 @@ Implicit conversion is modeled after Telex, supporting
 standard diacritic suffixes.
 .SS KOREAN
 Mapping is done by emulating a Dubeolsik layout, with each Latin
-character mapping to a single Jamo. Sequences of up to three Jamo
-are automatically converted to Hangul syllables.
+character mapping to a single Jamo. Sequences of Jamo are automatically
+converted to Hangul syllables.
 .SH EXAMPLES
 To type the following Japanese text:
 

sys/src/cmd/ktrans/main.c

@@ -670,6 +670,59 @@ telexlkup(Str *line)
 	}
 }
 
+static void
+dubeolbksp(Str *line)
+{
+	Map lkup;
+
+	popstr(line);
+	/* lookup and emit remaining Jamo to output */
+	if(hmapget(hangul, line->b, &lkup) < 0)
+		return;
+	emitutf(output, lkup.kana, 0);
+}
+
+static void
+dubeollkup(Str *line)
+{
+	Map lkup;
+	char buf[UTFmax*2];
+	char *e2, *e1;
+
+	e1 = peekstr(line->p, line->b);
+	if(e1 != line->b){
+		e2 = peekstr(e1, line->b);
+		pushutf(buf, buf+sizeof buf, e2, utflen(e2));
+	}else
+		pushutf(buf, buf+sizeof buf, e1, utflen(e1));
+
+	if(hmapget(hangul, line->b, &lkup) < 0){
+		if(hmapget(hangul, buf, &lkup) < 0){
+			resetstr(line, nil);
+			line->p = pushutf(line->p, strend(line), e1, utflen(e1));
+			if(hmapget(hangul, line->b, &lkup) < 0)
+				return;
+		}else{
+			/* treat Jongseong as Choseong when it matches with new Jamo */
+			popstr(line);
+			popstr(line);
+			hmapget(hangul, line->b, &lkup);
+			emitutf(output, backspace, 2);
+			emitutf(output, lkup.kana, 0);
+
+			hmapget(hangul, buf, &lkup);
+			emitutf(output, lkup.kana, 0);
+			line->p = pushutf(line->b, strend(line), buf, utflen(buf));
+			return;
+		}
+	}
+	if(utflen(line->b) == 1)
+		emitutf(output, backspace, 1);
+	else
+		emitutf(output, backspace, 2);
+	emitutf(output, lkup.kana, 0);
+}
+
 static void
 keythread(void*)
 {
@@ -737,6 +790,10 @@ keythread(void*)
 				resetstr(&line, nil);
 				continue;
 			} else if(r == '\b'){
+				if(lang == LangKO){
+					dubeolbksp(&line);
+					continue;
+				}
 				popstr(&line);
 				continue;
 			}
@@ -745,6 +802,9 @@ keythread(void*)
 			if(lang == LangVN){
 				telexlkup(&line);
 				continue;
+			}else if(lang == LangKO){
+				dubeollkup(&line);
+				continue;
 			}
 			if(maplkup(lang, line.b, &lkup) < 0){
 				resetstr(&line, nil);

sys/src/cmd/ktrans/test.c

@@ -43,6 +43,10 @@ struct {
 	"ddaua", L"đâu",
 	"hoir", L"hỏi",
 	"giof", L"giò",
+
+	"gpffhdnjfemsms wlruqwksw\bgdk, wha tlstjsgks rj djqtdj?",
+	L"헬로월드는 지겹잖아, 좀 신선한 거 없어?",
+
 };
 
 char*