iconv support for legacy Korean encodings

like for other character sets, stateful iso-2022 form is not supported
yet but everything else should work. all charset aliases are treated
the same, as Windows codepage 949, because reportedly the EUC-KR
charset name is in widespread (mis?)usage in email and on the web for
data which actually uses the extended characters outside the standard
93x94 grid. this could easily be changed if desired.

the principle of this converter for handling the giant bulk of rare
Hangul syllables outside of the standard KS X 1001 93x94 grid is the
same as the GB18030 converter's treatment of non-explicitly-coded
Unicode codepoints: sequences in the extension range are mapped to an
integer index N, and the converter explicitly computes the Nth Hangul
syllable not explicitly encoded in the character map. empirically,
this requires at most 7 passes over the grid. this approach reduces
the table size required for Korean legacy encodings from roughly 44k
to 17k and should have minimal performance impact on real-world text
conversions since the "slow" characters are rare. where it does have
impact, the cost is merely a large constant time factor.

1 files changed, 38 insertions, 0 deletions

diff --git a/src/locale/iconv.c b/src/locale/iconv.c
index a2332ce0..d3caafa7 100644
--- a/src/locale/iconv.c
+++ b/src/locale/iconv.c
@@ -20,6 +20,7 @@
 #define GB18030     0330
 #define GBK         0331
 #define GB2312      0332
+#define EUC_KR      0350
 
 /* FIXME: these are not implemented yet
  * EUC:   A1-FE A1-FE
@@ -47,6 +48,7 @@ static const unsigned char charmaps[] =
 "gb18030\0\0\330"
 "gbk\0\0\331"
 "gb2312\0\0\332"
+"euckr\0ksc5601\0ksx1001\0cp949\0\0\350"
 #include "codepages.h"
 ;
 
@@ -62,6 +64,10 @@ static const unsigned short gb18030[126][190] = {
 #include "gb18030.h"
 };
 
+static const unsigned short ksc[93][94] = {
+#include "ksc.h"
+};
+
 static int fuzzycmp(const unsigned char *a, const unsigned char *b)
 {
 	for (; *a && *b; a++, b++) {
@@ -278,6 +284,38 @@ size_t iconv(iconv_t cd0, char **restrict in, size_t *restrict inb, char **restr
 			if (d>63) d--;
 			c = gb18030[c][d];
 			break;
+		case EUC_KR:
+			l = 2;
+			if (*inb < 2) goto starved;
+			d = *((unsigned char *)*in + 1);
+			c -= 0xa1;
+			d -= 0xa1;
+			if (c >= 93 || d >= 94) {
+				c += (0xa1-0x81);
+				d += 0xa1;
+				if (c >= 93 || c>=0xc6-0x81 && d>0x52)
+					goto ilseq;
+				if (d-'A'<26) d = d-'A';
+				else if (d-'a'<26) d = d-'a'+26;
+				else if (d-0x81<0xff-0x81) d = d-0x81+52;
+				else goto ilseq;
+				if (c < 0x20) c = 178*c + d;
+				else c = 178*0x20 + 84*(c-0x20) + d;
+				c += 0xac00;
+				for (d=0xac00; d<=c; ) {
+					k = 0;
+					for (int i=0; i<93; i++)
+						for (int j=0; j<94; j++)
+							if (ksc[i][j]-d <= c-d)
+								k++;
+					d = c+1;
+					c += k;
+				}
+				break;
+			}
+			c = ksc[c][d];
+			if (!c) goto ilseq;
+			break;
 		default:
 			if (c < 128+type) break;
 			c -= 128+type;