cp949.h 3.4 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128
  1. /*
  2. * Copyright (C) 1999-2001, 2005, 2007 Free Software Foundation, Inc.
  3. * This file is part of the GNU LIBICONV Library.
  4. *
  5. * The GNU LIBICONV Library is free software; you can redistribute it
  6. * and/or modify it under the terms of the GNU Library General Public
  7. * License as published by the Free Software Foundation; either version 2
  8. * of the License, or (at your option) any later version.
  9. *
  10. * The GNU LIBICONV Library is distributed in the hope that it will be
  11. * useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
  12. * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
  13. * Library General Public License for more details.
  14. *
  15. * You should have received a copy of the GNU Library General Public
  16. * License along with the GNU LIBICONV Library; see the file COPYING.LIB.
  17. * If not, write to the Free Software Foundation, Inc., 51 Franklin Street,
  18. * Fifth Floor, Boston, MA 02110-1301, USA.
  19. */
  20. /*
  21. * CP949 is EUC-KR, extended with UHC (Unified Hangul Code).
  22. *
  23. * Some variants of CP949 (in JDK, Windows-2000, ICU) also add:
  24. *
  25. * 2. Private area mappings:
  26. *
  27. * code Unicode
  28. * 0xC9{A1..FE} U+E000..U+E05D
  29. * 0xFE{A1..FE} U+E05E..U+E0BB
  30. *
  31. * We add them too because, although there are backward compatibility problems
  32. * when a character from a private area is moved to an official Unicode code
  33. * point, they are useful for some people in practice.
  34. */
  35. #include "uhc_1.h"
  36. #include "uhc_2.h"
  37. static int
  38. cp949_mbtowc (conv_t conv, ucs4_t *pwc, const unsigned char *s, int n)
  39. {
  40. unsigned char c = *s;
  41. /* Code set 0 (ASCII) */
  42. if (c < 0x80)
  43. return ascii_mbtowc(conv,pwc,s,n);
  44. /* UHC part 1 */
  45. if (c >= 0x81 && c <= 0xa0)
  46. return uhc_1_mbtowc(conv,pwc,s,n);
  47. if (c >= 0xa1 && c < 0xff) {
  48. if (n < 2)
  49. return RET_TOOFEW(0);
  50. {
  51. unsigned char c2 = s[1];
  52. if (c2 < 0xa1)
  53. /* UHC part 2 */
  54. return uhc_2_mbtowc(conv,pwc,s,n);
  55. else if (c2 < 0xff && !(c == 0xa2 && c2 == 0xe8)) {
  56. /* Code set 1 (KS C 5601-1992, now KS X 1001:1998) */
  57. unsigned char buf[2];
  58. int ret;
  59. buf[0] = c-0x80; buf[1] = c2-0x80;
  60. ret = ksc5601_mbtowc(conv,pwc,buf,2);
  61. if (ret != RET_ILSEQ)
  62. return ret;
  63. /* User-defined characters */
  64. if (c == 0xc9) {
  65. *pwc = 0xe000 + (c2 - 0xa1);
  66. return 2;
  67. }
  68. if (c == 0xfe) {
  69. *pwc = 0xe05e + (c2 - 0xa1);
  70. return 2;
  71. }
  72. }
  73. }
  74. }
  75. return RET_ILSEQ;
  76. }
  77. static int
  78. cp949_wctomb (conv_t conv, unsigned char *r, ucs4_t wc, int n)
  79. {
  80. unsigned char buf[2];
  81. int ret;
  82. /* Code set 0 (ASCII) */
  83. ret = ascii_wctomb(conv,r,wc,n);
  84. if (ret != RET_ILUNI)
  85. return ret;
  86. /* Code set 1 (KS C 5601-1992, now KS X 1001:1998) */
  87. if (wc != 0x327e) {
  88. ret = ksc5601_wctomb(conv,buf,wc,2);
  89. if (ret != RET_ILUNI) {
  90. if (ret != 2) abort();
  91. if (n < 2)
  92. return RET_TOOSMALL;
  93. r[0] = buf[0]+0x80;
  94. r[1] = buf[1]+0x80;
  95. return 2;
  96. }
  97. }
  98. /* UHC */
  99. if (wc >= 0xac00 && wc < 0xd7a4) {
  100. if (wc < 0xc8a5)
  101. return uhc_1_wctomb(conv,r,wc,n);
  102. else
  103. return uhc_2_wctomb(conv,r,wc,n);
  104. }
  105. /* User-defined characters */
  106. if (wc >= 0xe000 && wc < 0xe0bc) {
  107. if (n < 2)
  108. return RET_TOOSMALL;
  109. if (wc < 0xe05e) {
  110. r[0] = 0xc9;
  111. r[1] = wc - 0xe000 + 0xa1;
  112. } else {
  113. r[0] = 0xfe;
  114. r[1] = wc - 0xe05e + 0xa1;
  115. }
  116. return 2;
  117. }
  118. return RET_ILUNI;
  119. }