cp949.h 3.4 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127
  1. /*
  2. * Copyright (C) 1999-2001, 2005, 2007, 2016 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 Lesser General Public
  7. * License as published by the Free Software Foundation; either version 2.1
  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. * Lesser General Public License for more details.
  14. *
  15. * You should have received a copy of the GNU Lesser General Public
  16. * License along with the GNU LIBICONV Library; see the file COPYING.LIB.
  17. * If not, see <https://www.gnu.org/licenses/>.
  18. */
  19. /*
  20. * CP949 is EUC-KR, extended with UHC (Unified Hangul Code).
  21. *
  22. * Some variants of CP949 (in JDK, Windows-2000, ICU) also add:
  23. *
  24. * 2. Private area mappings:
  25. *
  26. * code Unicode
  27. * 0xC9{A1..FE} U+E000..U+E05D
  28. * 0xFE{A1..FE} U+E05E..U+E0BB
  29. *
  30. * We add them too because, although there are backward compatibility problems
  31. * when a character from a private area is moved to an official Unicode code
  32. * point, they are useful for some people in practice.
  33. */
  34. #include "uhc_1.h"
  35. #include "uhc_2.h"
  36. static int
  37. cp949_mbtowc (conv_t conv, ucs4_t *pwc, const unsigned char *s, size_t n)
  38. {
  39. unsigned char c = *s;
  40. /* Code set 0 (ASCII) */
  41. if (c < 0x80)
  42. return ascii_mbtowc(conv,pwc,s,n);
  43. /* UHC part 1 */
  44. if (c >= 0x81 && c <= 0xa0)
  45. return uhc_1_mbtowc(conv,pwc,s,n);
  46. if (c >= 0xa1 && c < 0xff) {
  47. if (n < 2)
  48. return RET_TOOFEW(0);
  49. {
  50. unsigned char c2 = s[1];
  51. if (c2 < 0xa1)
  52. /* UHC part 2 */
  53. return uhc_2_mbtowc(conv,pwc,s,n);
  54. else if (c2 < 0xff && !(c == 0xa2 && c2 == 0xe8)) {
  55. /* Code set 1 (KS C 5601-1992, now KS X 1001:1998) */
  56. unsigned char buf[2];
  57. int ret;
  58. buf[0] = c-0x80; buf[1] = c2-0x80;
  59. ret = ksc5601_mbtowc(conv,pwc,buf,2);
  60. if (ret != RET_ILSEQ)
  61. return ret;
  62. /* User-defined characters */
  63. if (c == 0xc9) {
  64. *pwc = 0xe000 + (c2 - 0xa1);
  65. return 2;
  66. }
  67. if (c == 0xfe) {
  68. *pwc = 0xe05e + (c2 - 0xa1);
  69. return 2;
  70. }
  71. }
  72. }
  73. }
  74. return RET_ILSEQ;
  75. }
  76. static int
  77. cp949_wctomb (conv_t conv, unsigned char *r, ucs4_t wc, size_t n)
  78. {
  79. unsigned char buf[2];
  80. int ret;
  81. /* Code set 0 (ASCII) */
  82. ret = ascii_wctomb(conv,r,wc,n);
  83. if (ret != RET_ILUNI)
  84. return ret;
  85. /* Code set 1 (KS C 5601-1992, now KS X 1001:1998) */
  86. if (wc != 0x327e) {
  87. ret = ksc5601_wctomb(conv,buf,wc,2);
  88. if (ret != RET_ILUNI) {
  89. if (ret != 2) abort();
  90. if (n < 2)
  91. return RET_TOOSMALL;
  92. r[0] = buf[0]+0x80;
  93. r[1] = buf[1]+0x80;
  94. return 2;
  95. }
  96. }
  97. /* UHC */
  98. if (wc >= 0xac00 && wc < 0xd7a4) {
  99. if (wc < 0xc8a5)
  100. return uhc_1_wctomb(conv,r,wc,n);
  101. else
  102. return uhc_2_wctomb(conv,r,wc,n);
  103. }
  104. /* User-defined characters */
  105. if (wc >= 0xe000 && wc < 0xe0bc) {
  106. if (n < 2)
  107. return RET_TOOSMALL;
  108. if (wc < 0xe05e) {
  109. r[0] = 0xc9;
  110. r[1] = wc - 0xe000 + 0xa1;
  111. } else {
  112. r[0] = 0xfe;
  113. r[1] = wc - 0xe05e + 0xa1;
  114. }
  115. return 2;
  116. }
  117. return RET_ILUNI;
  118. }