コード例 #1
0
ファイル: sjis.c プロジェクト: openmobl/UniverseCore
int
sjis_mbtowc (conv_t conv, ucs4_t *pwc, const unsigned char *s, int n)
{
  unsigned char c = *s;
  if (c < 0x80 || (c >= 0xa1 && c <= 0xdf))
    return jisx0201_mbtowc(conv,pwc,s,n);
  else {
    unsigned char s1, s2;
    s1 = c;
    if ((s1 >= 0x81 && s1 <= 0x9f) || (s1 >= 0xe0 && s1 <= 0xea)) {
      if (n < 2)
        return RET_TOOFEW(0);
      s2 = s[1];
      if ((s2 >= 0x40 && s2 <= 0x7e) || (s2 >= 0x80 && s2 <= 0xfc)) {
        unsigned char t1 = (s1 < 0xe0 ? s1-0x81 : s1-0xc1);
        unsigned char t2 = (s2 < 0x80 ? s2-0x40 : s2-0x41);
        unsigned char buf[2];
        buf[0] = 2*t1 + (t2 < 0x5e ? 0 : 1) + 0x21;
        buf[1] = (t2 < 0x5e ? t2 : t2-0x5e) + 0x21;
        return jisx0208_mbtowc(conv,pwc,buf,2);
      }
    } else if (s1 >= 0xf0 && s1 <= 0xf9) {
      /* User-defined range. See
       * Ken Lunde's "CJKV Information Processing", table 4-66, p. 206. */
      if (n < 2)
        return RET_TOOFEW(0);
      s2 = s[1];
      if ((s2 >= 0x40 && s2 <= 0x7e) || (s2 >= 0x80 && s2 <= 0xfc)) {
        *pwc = 0xe000 + 188*(s1 - 0xf0) + (s2 < 0x80 ? s2-0x40 : s2-0x41);
        return 2;
      }
    }
    return RET_ILSEQ;
  }
}
コード例 #2
0
ファイル: charset-conversion.c プロジェクト: amba/pdfout
static int
utf16be_mbtowc (conv_t conv, ucs4_t *pwc, const unsigned char *s,
		int n)
{
  int count = 0;
  if (n >= 2)
    {
      ucs4_t wc = (s[0] << 8) + s[1];
      if (wc >= 0xd800 && wc < 0xdc00)
	{
	  if (n >= 4)
	    {
	      ucs4_t wc2 = (s[2] << 8) + s[3];
	      if (!(wc2 >= 0xdc00 && wc2 < 0xe000))
		goto ilseq;
	      *pwc = 0x10000 + ((wc - 0xd800) << 10) + (wc2 - 0xdc00);
	      return count+4;
	    }
	}
      else if (wc >= 0xdc00 && wc < 0xe000)
	  goto ilseq;
      else
	{
	  *pwc = wc;
	  return count+2;
	}
    }
  return RET_TOOFEW(count);

 ilseq:
  return RET_ILSEQ;
}
コード例 #3
0
ファイル: lcUTF8.c プロジェクト: dikerex/theqvd
static int
utf8tostr(
    XlcConv conv,
    XPointer *from,
    int *from_left,
    XPointer *to,
    int *to_left,
    XPointer *args,
    int num_args)
{
    unsigned char const *src;
    unsigned char const *srcend;
    unsigned char *dst;
    unsigned char *dstend;
    int unconv_num;

    if (from == NULL || *from == NULL)
	return 0;

    src = (unsigned char const *) *from;
    srcend = src + *from_left;
    dst = (unsigned char *) *to;
    dstend = dst + *to_left;
    unconv_num = 0;

    while (src < srcend) {
	unsigned char c;
	ucs4_t wc;
	int consumed;

	consumed = utf8_mbtowc(NULL, &wc, src, srcend-src);
	if (consumed == RET_TOOFEW(0))
	    break;
	if (dst == dstend)
	    break;
	if (consumed == RET_ILSEQ) {
	    consumed = 1;
	    c = BAD_CHAR;
	    unconv_num++;
	} else {
	    if ((wc & ~(ucs4_t)0xff) != 0) {
		c = BAD_CHAR;
		unconv_num++;
	    } else
		c = (unsigned char) wc;
	}
	*dst++ = c;
	src += consumed;
    }

    *from = (XPointer) src;
    *from_left = srcend - src;
    *to = (XPointer) dst;
    *to_left = dstend - dst;

    return unconv_num;
}
コード例 #4
0
ファイル: PokemonString.cpp プロジェクト: TuxSH/PkmGCTools
int pkmgba_mbtowc(conv_t conv, ucs4_t *pwc, const unsigned char* s, int n, bool jap) {
    if (n < 1) return RET_TOOFEW(0);

    if (*s == 0xff) *pwc = 0;
    else if (*s >= 0xf7 && *s <= 0xfe) return RET_ILSEQ; // commands
    else *pwc = GBAToUCS4(*s, jap);

    return 1;
}
コード例 #5
0
ファイル: lcUTF8.c プロジェクト: dikerex/theqvd
static int
utf8towcs(
    XlcConv conv,
    XPointer *from,
    int *from_left,
    XPointer *to,
    int *to_left,
    XPointer *args,
    int num_args)
{
    unsigned char const *src;
    unsigned char const *srcend;
    wchar_t *dst;
    wchar_t *dstend;
    int unconv_num;

    if (from == NULL || *from == NULL)
	return 0;

    src = (unsigned char const *) *from;
    srcend = src + *from_left;
    dst = (wchar_t *) *to;
    dstend = dst + *to_left;
    unconv_num = 0;

    while (src < srcend && dst < dstend) {
	ucs4_t wc;
	int consumed = utf8_mbtowc(NULL, &wc, src, srcend-src);
	if (consumed == RET_TOOFEW(0))
	    break;
	if (consumed == RET_ILSEQ) {
	    src++;
	    *dst = BAD_WCHAR;
	    unconv_num++;
	} else {
	    src += consumed;
	    *dst = wc;
	}
	dst++;
    }

    *from = (XPointer) src;
    *from_left = srcend - src;
    *to = (XPointer) dst;
    *to_left = dstend - dst;

    return unconv_num;
}
コード例 #6
0
ファイル: big5_2003.c プロジェクト: openmobl/UniverseCore
int
big5_2003_mbtowc (conv_t conv, ucs4_t *pwc, const unsigned char *s, int n)
{
  unsigned char c = *s;
  /* Code set 0 (ASCII) */
  if (c < 0x80)
    return ascii_mbtowc(conv,pwc,s,n);
  /* Code set 1 (BIG5 extended) */
  if (c >= 0x81 && c < 0xff) {
    if (n < 2)
      return RET_TOOFEW(0);
    {
      unsigned char c2 = s[1];
      if ((c2 >= 0x40 && c2 < 0x7f) || (c2 >= 0xa1 && c2 < 0xff)) {
        if (c >= 0xa1) {
          if (c < 0xa3) {
            unsigned int i = 157 * (c - 0xa1) + (c2 - (c2 >= 0xa1 ? 0x62 : 0x40));
            unsigned short wc = big5_2003_2uni_pagea1[i];
            if (wc != 0xfffd) {
              *pwc = (ucs4_t) wc;
              return 2;
            }
          }
          if (!((c == 0xc6 && c2 >= 0xa1) || c == 0xc7)) {
            if (!(c == 0xc2 && c2 == 0x55)) {
              int ret = big5_mbtowc(conv,pwc,s,2);
              if (ret != RET_ILSEQ)
                return ret;
              if (c == 0xa3) {
                if (c2 >= 0xc0 && c2 <= 0xe1) {
                  *pwc = (c2 == 0xe1 ? 0x20ac : c2 == 0xe0 ? 0x2421 : 0x2340 + c2);
                  return 2;
                }
              } else if (c == 0xf9) {
                if (c2 >= 0xd6) {
                  *pwc = big5_2003_2uni_pagef9[c2-0xd6];
                  return 2;
                }
              } else if (c >= 0xfa) {
                *pwc = 0xe000 + 157 * (c - 0xfa) + (c2 - (c2 >= 0xa1 ? 0x62 : 0x40));
                return 2;
              }
            } else {
              /* c == 0xc2 && c2 == 0x55. */
              *pwc = 0x5f5e;
              return 2;
            }
          } else {
            /* (c == 0xc6 && c2 >= 0xa1) || c == 0xc7. */
            unsigned int i = 157 * (c - 0xc6) + (c2 - (c2 >= 0xa1 ? 0x62 : 0x40));
            if (i < 133) {
              /* 63 <= i < 133. */
              unsigned short wc = big5_2003_2uni_pagec6[i-63];
              if (wc != 0xfffd) {
                *pwc = (ucs4_t) wc;
                return 2;
              }
            } else if (i < 216) {
              /* 133 <= i < 216. Hiragana. */
              *pwc = 0x3041 - 133 + i;
              return 2;
            } else if (i < 302) {
              /* 216 <= i < 302. Katakana. */
              *pwc = 0x30a1 - 216 + i;
              return 2;
            }
          }
        } else {
          /* 0x81 <= c < 0xa1. */
          *pwc = (c >= 0x8e ? 0xdb18 : 0xeeb8) + 157 * (c - 0x81)
                 + (c2 - (c2 >= 0xa1 ? 0x62 : 0x40));
          return 2;
        }
      }
    }
  }
  return RET_ILSEQ;
}
コード例 #7
0
ファイル: chinese.c プロジェクト: crayonzx/chs_rec
static int
utf8_mbtowc (ucs4_t *pwc, const unsigned char *s, int n)
{
  unsigned char c = s[0];

  if (c < 0x80) {
    *pwc = c;
    return 1;
  } else if (c < 0xc2) {
    return RET_ILSEQ;
  } else if (c < 0xe0) {
    if (n < 2)
      return RET_TOOFEW(0);
    if (!((s[1] ^ 0x80) < 0x40))
      return RET_ILSEQ;
    *pwc = ((ucs4_t) (c & 0x1f) << 6)
           | (ucs4_t) (s[1] ^ 0x80);
    return 2;
  } else if (c < 0xf0) {
    if (n < 3)
      return RET_TOOFEW(0);
    if (!((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
          && (c >= 0xe1 || s[1] >= 0xa0)))
      return RET_ILSEQ;
    *pwc = ((ucs4_t) (c & 0x0f) << 12)
           | ((ucs4_t) (s[1] ^ 0x80) << 6)
           | (ucs4_t) (s[2] ^ 0x80);
    return 3;
  } else if (c < 0xf8 && sizeof(ucs4_t)*8 >= 32) {
    if (n < 4)
      return RET_TOOFEW(0);
    if (!((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
          && (s[3] ^ 0x80) < 0x40
          && (c >= 0xf1 || s[1] >= 0x90)))
      return RET_ILSEQ;
    *pwc = ((ucs4_t) (c & 0x07) << 18)
           | ((ucs4_t) (s[1] ^ 0x80) << 12)
           | ((ucs4_t) (s[2] ^ 0x80) << 6)
           | (ucs4_t) (s[3] ^ 0x80);
    return 4;
  } else if (c < 0xfc && sizeof(ucs4_t)*8 >= 32) {
    if (n < 5)
      return RET_TOOFEW(0);
    if (!((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
          && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40
          && (c >= 0xf9 || s[1] >= 0x88)))
      return RET_ILSEQ;
    *pwc = ((ucs4_t) (c & 0x03) << 24)
           | ((ucs4_t) (s[1] ^ 0x80) << 18)
           | ((ucs4_t) (s[2] ^ 0x80) << 12)
           | ((ucs4_t) (s[3] ^ 0x80) << 6)
           | (ucs4_t) (s[4] ^ 0x80);
    return 5;
  } else if (c < 0xfe && sizeof(ucs4_t)*8 >= 32) {
    if (n < 6)
      return RET_TOOFEW(0);
    if (!((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
          && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40
          && (s[5] ^ 0x80) < 0x40
          && (c >= 0xfd || s[1] >= 0x84)))
      return RET_ILSEQ;
    *pwc = ((ucs4_t) (c & 0x01) << 30)
           | ((ucs4_t) (s[1] ^ 0x80) << 24)
           | ((ucs4_t) (s[2] ^ 0x80) << 18)
           | ((ucs4_t) (s[3] ^ 0x80) << 12)
           | ((ucs4_t) (s[4] ^ 0x80) << 6)
           | (ucs4_t) (s[5] ^ 0x80);
    return 6;
  } else
    return RET_ILSEQ;
}
コード例 #8
0
ファイル: tiniconv.c プロジェクト: chrisgrill/fldigi
int tiniconv_convert(struct tiniconv_ctx_s *ctx,
  unsigned char const *in_buf, int in_size, int *p_in_size_consumed,
  unsigned char *out_buf, int out_size, int *p_out_size_consumed)
{
  ucs4_t wc;
  int in_idx, out_idx;
  int result, last_result;
  conv_state_t last_istate;
  
  assert(ctx != NULL);
  assert(in_buf != NULL);
  assert(out_buf != NULL);
  
  for (in_idx = 0, out_idx = 0; in_idx < in_size && out_idx < out_size;)
  {
  	last_istate = ctx->istate;
    /* typedef int (*xxx_mb2wc_t) (conv_t conv, ucs4_t *pwc, unsigned char const *s, int n); */
    result = ctx->mb2wc(ctx, &wc, in_buf + in_idx, in_size - in_idx);
    assert(result <= in_size - in_idx);
    if (result < 0)
    {
      if (result == RET_ILSEQ)
      {
        if (ctx->options & TINICONV_OPTION_IGNORE_IN_ILSEQ)
        {
          ctx->istate = 0;
          in_idx ++;
          continue;
        }
        else
        {
          result = TINICONV_CONVERT_IN_ILSEQ;
          goto exit;
        }
      }
      else if (result == RET_TOOSMALL)
      {
        result = TINICONV_CONVERT_IN_TOO_SMALL;
        goto exit;
      }
      else
      {
      	in_idx += RET_TOOFEW(result);
      	continue;
      }
    }
    in_idx += last_result = result;
    
    /* typedef int (*xxx_wc2mb_t) (conv_t conv, unsigned char *r, ucs4_t wc, int n); */
    result = ctx->wc2mb(ctx, out_buf + out_idx, wc, out_size - out_idx);
    assert(result <= out_size - out_idx);
    if (result < 0)
    {
      if (result == RET_ILUNI)
      {
        if (ctx->options & TINICONV_OPTION_IGNORE_OUT_ILSEQ)
        {
          out_buf[out_idx ++] = TINICONV_OPTION_GET_OUT_ILSEQ_CHAR(ctx->options);
          ctx->ostate = 0;
          continue;
        }
        else
        {
          result = TINICONV_CONVERT_OUT_ILSEQ;
          in_idx -= last_result; /* discarding the last read sequence */
          ctx->istate = last_istate;
          goto exit;
        }
      }
      else if (result == RET_TOOSMALL)
      {
        result = TINICONV_CONVERT_OUT_TOO_SMALL;
        in_idx -= last_result; /* discarding the last read sequence */
        ctx->istate = last_istate;
        goto exit;
      }
    }
    out_idx += result;
  }
  result = TINICONV_CONVERT_OK;

exit:
  if (p_in_size_consumed)
    *p_in_size_consumed = in_idx;
  if (p_out_size_consumed)
    *p_out_size_consumed = out_idx;
  return result;
}
コード例 #9
0
ファイル: locale.cpp プロジェクト: m8a/uim
int
utf8_mbtowc(uchar *wc, const unsigned char *src, int src_len)
{
    if (!wc)
	return 0;

    unsigned char c = src[0];
    if (c < 0x80) {
	*wc = c;
	return 1;
    } else if (c < 0xc2) {
	return RET_ILSEQ;
    } else if (c < 0xe0) {
	if (src_len < 2)
	    return RET_TOOFEW(0);
	if (!((src[1] ^ 0x80) < 0x40))
	    return RET_ILSEQ;
	*wc = ((uchar)(c & 0x1f) << 6) | (uchar)(src[1] ^ 0x80);
	return 2;
    } else if (c < 0xf0) {
	if (src_len < 3)
	    return RET_TOOFEW(0);
	if (!((src[1] ^ 0x80) < 0x40 &&
	      (src[2] ^ 0x80) < 0x40 &&
	      (c >= 0xe1 || src[1] >= 0xa0)))
	    return RET_ILSEQ;
	*wc = ((uchar)(c & 0x0f) << 12) |
	      ((uchar)(src[1] ^ 0x80) << 6) |
	      (uchar)(src[2] ^ 0x80);
	return 3;
    } else if (c < 0xf8) {
	if (src_len < 4)
	    return RET_TOOFEW(0);
	if (!((src[1] ^ 0x80) < 0x40 &&
	      (src[2] ^ 0x80) < 0x40 &&
	      (src[3] ^ 0x80) < 0x40 &&
	      (c >= 0xf1 || src[1] >= 0x90)))
	    return RET_ILSEQ;
	*wc = ((uchar)(c & 0x07) << 18) |
	      ((uchar)(src[1] ^ 0x80) << 12) |
	      ((uchar)(src[2] ^ 0x80) << 6) |
	      (uchar)(src[3] ^ 0x80);
	return 4;
    } else if (c < 0xfc) {
	if (src_len < 5)
	    return RET_TOOFEW(0);
	if (!((src[1] ^ 0x80) < 0x40 &&
	      (src[2] ^ 0x80) < 0x40 &&
	      (src[3] ^ 0x80) < 0x40 &&
	      (src[4] ^ 0x80) < 0x40 &&
	      (c >= 0xf9 || src[1] >= 0x88)))
	    return RET_ILSEQ;
	*wc = ((uchar)(c & 0x03) << 24) |
	      ((uchar)(src[1] ^ 0x80) << 18) |
	      ((uchar)(src[2] ^ 0x80) << 12) |
	      ((uchar)(src[3] ^ 0x80) << 6) |
	      (uchar)(src[4] ^ 0x80);
	return 5;
    } else if (c < 0xfe) {
	if (src_len < 6)
	    return RET_TOOFEW(0);
	if (!((src[1] ^ 0x80) < 0x40 &&
	      (src[2] ^ 0x80) < 0x40 &&
	      (src[3] ^ 0x80) < 0x40 &&
	      (src[4] ^ 0x80) < 0x40 &&
	      (src[5] ^ 0x80) < 0x40 &&
	      (c >= 0xfd || src[1] >= 0x84)))
	    return RET_ILSEQ;
	*wc = ((uchar)(c & 0x01) << 30) |
	      ((uchar)(src[1] ^ 0x80) << 24) |
	      ((uchar)(src[2] ^ 0x80) << 18) |
	      ((uchar)(src[3] ^ 0x80) << 12) |
	      ((uchar)(src[4] ^ 0x80) << 6) |
	      (uchar)(src[5] ^ 0x80);
	return 6;
    } else
	return RET_ILSEQ;
}
コード例 #10
0
ファイル: lcUTF8.c プロジェクト: dikerex/theqvd
static int
utf8tocs1(
    XlcConv conv,
    XPointer *from,
    int *from_left,
    XPointer *to,
    int *to_left,
    XPointer *args,
    int num_args)
{
    Utf8Conv *preferred_charsets;
    XlcCharSet last_charset = NULL;
    unsigned char const *src;
    unsigned char const *srcend;
    unsigned char *dst;
    unsigned char *dstend;
    int unconv_num;

    if (from == NULL || *from == NULL)
	return 0;

    preferred_charsets = (Utf8Conv *) conv->state;
    src = (unsigned char const *) *from;
    srcend = src + *from_left;
    dst = (unsigned char *) *to;
    dstend = dst + *to_left;
    unconv_num = 0;

    while (src < srcend && dst < dstend) {
	Utf8Conv chosen_charset = NULL;
	XlcSide chosen_side = XlcNONE;
	ucs4_t wc;
	int consumed;
	int count;

	consumed = utf8_mbtowc(NULL, &wc, src, srcend-src);
	if (consumed == RET_TOOFEW(0))
	    break;
	if (consumed == RET_ILSEQ) {
	    src++;
	    unconv_num++;
	    continue;
	}

	count = charset_wctocs(preferred_charsets, &chosen_charset, &chosen_side, conv, dst, wc, dstend-dst);
	if (count == RET_TOOSMALL)
	    break;
	if (count == RET_ILSEQ) {
	    src += consumed;
	    unconv_num++;
	    continue;
	}

	if (last_charset == NULL) {
	    last_charset =
	        _XlcGetCharSetWithSide(chosen_charset->name, chosen_side);
	    if (last_charset == NULL) {
		src += consumed;
		unconv_num++;
		continue;
	    }
	} else {
	    if (!(last_charset->xrm_encoding_name == chosen_charset->xrm_name
	          && (last_charset->side == XlcGLGR
	              || last_charset->side == chosen_side)))
		break;
	}
	src += consumed;
	dst += count;
	break;
    }

    if (last_charset == NULL)
	return -1;

    *from = (XPointer) src;
    *from_left = srcend - src;
    *to = (XPointer) dst;
    *to_left = dstend - dst;

    if (num_args >= 1)
	*((XlcCharSet *)args[0]) = last_charset;

    return unconv_num;
}
コード例 #11
0
ファイル: lcUTF8.c プロジェクト: dikerex/theqvd
static int
cstoutf8(
    XlcConv conv,
    XPointer *from,
    int *from_left,
    XPointer *to,
    int *to_left,
    XPointer *args,
    int num_args)
{
    XlcCharSet charset;
    const char *name;
    Utf8Conv convptr;
    int i;
    unsigned char const *src;
    unsigned char const *srcend;
    unsigned char *dst;
    unsigned char *dstend;
    int unconv_num;

    if (from == NULL || *from == NULL)
	return 0;

    if (num_args < 1)
	return -1;

    charset = (XlcCharSet) args[0];
    name = charset->encoding_name;
    /* not charset->name because the latter has a ":GL"/":GR" suffix */

    for (convptr = all_charsets, i = all_charsets_count-1; i > 0; convptr++, i--)
	if (!strcmp(convptr->name, name))
	    break;
    if (i == 0)
	return -1;

    src = (unsigned char const *) *from;
    srcend = src + *from_left;
    dst = (unsigned char *) *to;
    dstend = dst + *to_left;
    unconv_num = 0;

    while (src < srcend) {
	ucs4_t wc;
	int consumed;
	int count;

	consumed = convptr->cstowc(conv, &wc, src, srcend-src);
	if (consumed == RET_ILSEQ)
	    return -1;
	if (consumed == RET_TOOFEW(0))
	    break;

	count = utf8_wctomb(NULL, dst, wc, dstend-dst);
	if (count == RET_TOOSMALL)
	    break;
	if (count == RET_ILSEQ) {
	    count = utf8_wctomb(NULL, dst, BAD_WCHAR, dstend-dst);
	    if (count == RET_TOOSMALL)
		break;
	    unconv_num++;
	}
	src += consumed;
	dst += count;
    }

    *from = (XPointer) src;
    *from_left = srcend - src;
    *to = (XPointer) dst;
    *to_left = dstend - dst;

    return unconv_num;
}
コード例 #12
0
ファイル: iso2022_kr.c プロジェクト: openmobl/UniverseCore
int
iso2022_kr_mbtowc (conv_t conv, ucs4_t *pwc, const unsigned char *s, int n)
{
  state_t state = conv->istate;
  SPLIT_STATE;
  int count = 0;
  unsigned char c;
  for (;;) {
    c = *s;
    if (c == ESC) {
      if (n < count+4)
        goto none;
      if (s[1] == '$') {
        if (s[2] == ')') {
          if (s[3] == 'C') {
            state2 = STATE2_DESIGNATED_KSC5601;
            s += 4; count += 4;
            if (n < count+1)
              goto none;
            continue;
          }
        }
      }
      return RET_ILSEQ;
    }
    if (c == SO) {
      if (state2 != STATE2_DESIGNATED_KSC5601)
        return RET_ILSEQ;
      state1 = STATE_TWOBYTE;
      s++; count++;
      if (n < count+1)
        goto none;
      continue;
    }
    if (c == SI) {
      state1 = STATE_ASCII;
      s++; count++;
      if (n < count+1)
        goto none;
      continue;
    }
    break;
  }
  switch (state1) {
    case STATE_ASCII:
      if (c < 0x80) {
        int ret = ascii_mbtowc(conv,pwc,s,1);
        if (ret == RET_ILSEQ)
          return RET_ILSEQ;
        if (ret != 1) return SIG_ABRT;
#if 0 /* Accept ISO-2022-KR according to CJK.INF. */
        if (*pwc == 0x000a || *pwc == 0x000d)
          state2 = STATE2_NONE;
#endif
        COMBINE_STATE;
        conv->istate = state;
        return count+1;
      } else
        return RET_ILSEQ;
    case STATE_TWOBYTE:
      if (n < count+2)
        goto none;
      if (state2 != STATE2_DESIGNATED_KSC5601) return SIG_ABRT;
      if (s[0] < 0x80 && s[1] < 0x80) {
        int ret = ksc5601_mbtowc(conv,pwc,s,2);
        if (ret == RET_ILSEQ)
          return RET_ILSEQ;
        if (ret != 2) return SIG_ABRT;
        COMBINE_STATE;
        conv->istate = state;
        return count+2;
      } else
        return RET_ILSEQ;
    default: return SIG_ABRT;
  }

none:
  COMBINE_STATE;
  conv->istate = state;
  return RET_TOOFEW(count);
}
コード例 #13
0
ファイル: iconv.c プロジェクト: Xeffyr/KolibriOS-Mod
size_t iconv(iconv_t cd, const char **inbuf, size_t *inbytesleft,
	char **outbuf, size_t *outbytesleft)
{
	int n, to, from, count1,count2;
	int pwc, converted,written;
	int (*mbtowc)(conv_t, ucs4_t *, const unsigned char *, int);
	int (*wctomb)(conv_t, ucs4_t *, const unsigned char *, int);

	char *str;
	str=*outbuf;

	from=cd>>16;
	to=cd&0xFFFF;

	switch (from)
	{
		case CP866: mbtowc=cp866_mbtowc; break;
		case CP1251: mbtowc=cp1251_mbtowc; break;
		case CP1252: mbtowc=cp1252_mbtowc; break;
		case ISO8859_5: mbtowc=iso8859_5_mbtowc; break;
		case KOI8_RU: mbtowc=koi8_ru_mbtowc; break;
		case UTF_8: mbtowc=utf8_mbtowc; break;
		default: return -2;
	}

	switch (to)
	{
		case CP866: wctomb=cp866_wctomb; break;
		case CP1251: wctomb=cp1251_wctomb; break;
		case CP1252: wctomb=cp1252_wctomb; break;
		case ISO8859_5: wctomb=iso8859_5_wctomb; break;
		case KOI8_RU: wctomb=koi8_ru_wctomb; break;
		case UTF_8: wctomb=utf8_wctomb; break;
		default: return -3;
	}

	count1=0;
	count2=0;

	while ( *inbytesleft>0 && *outbytesleft>1)
	{
		n=1;

		do {
		//converted= (utf8_mbtowc)(0,&pwc,((*inbuf)+count1),n);
		//	printf("%d\n",n);
		converted= (mbtowc)(0,&pwc,((*inbuf)+count1),n);

		n++;
		}	while (converted==RET_TOOFEW(0));

		if (converted<0) return -10;
		//written=  (cp866_wctomb)(0,str+count2,pwc,1);
		written=  (wctomb)(0,str+count2,pwc,1);
		if (written<0) written=0;//return -11;

		//printf("Conv:%d Wri:%d In:%d Out:%d UTF:%x UCS:%x 866:%s\n",converted, written, *inbytesleft,*outbytesleft,*((*inbuf)+count1),pwc, str);

		(*inbytesleft)-=converted;
		(*outbytesleft)-=written;
		count1+=converted;
		count2+=written;
	}
	*(str+count2)='\0';

	if (*inbytesleft>0 && *outbytesleft==0) return -12;
	return 0;
}