From 19b4a0a20efc6b9df98b6a43536ecdd628ba4643 Mon Sep 17 00:00:00 2001 From: Rich Felker Date: Wed, 7 Aug 2013 13:16:14 -0400 Subject: add Big5 charset support to iconv at this point, it is just the common base charset equivalent to Windows CP 950, with no further extensions. HKSCS and possibly other supersets will be added later. other aliases may need to be added too. --- src/locale/iconv.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'src/locale/iconv.c') diff --git a/src/locale/iconv.c b/src/locale/iconv.c index d3caafa7..30ea8da6 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 BIG5 0340 #define EUC_KR 0350 /* FIXME: these are not implemented yet @@ -48,6 +49,7 @@ static const unsigned char charmaps[] = "gb18030\0\0\330" "gbk\0\0\331" "gb2312\0\0\332" +"big5\0bigfive\0cp950\0\0\340" "euckr\0ksc5601\0ksx1001\0cp949\0\0\350" #include "codepages.h" ; @@ -64,6 +66,10 @@ static const unsigned short gb18030[126][190] = { #include "gb18030.h" }; +static const unsigned short big5[89][157] = { +#include "big5.h" +}; + static const unsigned short ksc[93][94] = { #include "ksc.h" }; @@ -284,6 +290,18 @@ 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 BIG5: + l = 2; + if (*inb < 2) goto starved; + d = *((unsigned char *)*in + 1); + if (c-0xa1>=0xfa-0xa1) goto ilseq; + c -= 0xa1; + if (d-0x40>=0xff-0x40 || d-0x7f<0xa1-0x7f) goto ilseq; + d -= 0x40; + if (d > 0x3e) d -= 0x22; + c = big5[c][d]; + if (!c) goto ilseq; + break; case EUC_KR: l = 2; if (*inb < 2) goto starved; -- cgit v1.2.1