2009-08-24 Corinna Vinschen <corinna@vinschen.de>

* libc/locale/locale.c: Update documentation. (loadlocale): Map "KOI8-R" and "KOI8-U" to CP20866 and CP21866. 2009-08-24 Andy Koppe <andy.koppe@gmail.com> * libc/stdlib/sb_charsets.c (__cp_conv): Add KOI8-R (Russian, CP20866) and KOI8-U (Ukrainian, CP21866) to Windows codepage conversion tables. * libc/ctype/ctype_cp.h (__ctype_cp): Likewise for ctype tables.
2009-08-24 22:11:11 +00:00
parent ce1831cb4e
commit 162a23c504
4 changed files with 143 additions and 14 deletions
--- a/newlib/ChangeLog
+++ b/newlib/ChangeLog
@@ -1,3 +1,14 @@
+2009-08-24  Corinna Vinschen  <corinna@vinschen.de>
+
+	* libc/locale/locale.c: Update documentation.
+	(loadlocale): Map "KOI8-R" and "KOI8-U" to CP20866 and CP21866.
+
+2009-08-24  Andy Koppe  <andy.koppe@gmail.com>
+
+	* libc/stdlib/sb_charsets.c (__cp_conv): Add KOI8-R (Russian, CP20866)
+	and KOI8-U (Ukrainian, CP21866) to Windows codepage conversion tables.
+	* libc/ctype/ctype_cp.h (__ctype_cp): Likewise for ctype tables.
+
 2009-08-24  Andy Koppe  <andy.koppe@gmail.com>

 	* libc/ctype/iswspace.c (iswspace): Include "non-breaking
--- a/newlib/libc/ctype/ctype_cp.h
+++ b/newlib/libc/ctype/ctype_cp.h
@@ -397,6 +397,43 @@
 	_L,	_L,	_P,	_L,	_L,	_L,	_L,	_P, \
 	_L,	_L,	_L,	_L,	_L,	_L,	_P
 #define _CTYPE_CP1258_255 _L
+#define _CTYPE_CP20866_128_254 \
+   	_P,	_P,	_P,	_P,	_P,	_P,	_P,	_P, \
+	_P,	_P,	_P,	_P,	_P,	_P,	_P,	_P, \
+	_P,	_P,	_P,	_P,	_P,	_P,	_P,	_P, \
+	_P,	_P,	_S|_B,	_P,	_P,	_P,	_P,	_P, \
+	_P,	_P,	_P,	_L,	_P,	_P,	_P,	_P, \
+	_P,	_P,	_P,	_P,	_P,	_P,	_P,	_P, \
+	_P,	_P,	_P,	_U,	_P,	_P,	_P,	_P, \
+	_P,	_P,	_P,	_P,	_P,	_P,	_P,	_P, \
+	_L,	_L,	_L,	_L,	_L,	_L,	_L,	_L, \
+	_L,	_L,	_L,	_L,	_L,	_L,	_L,	_L, \
+	_L,	_L,	_L,	_L,	_L,	_L,	_L,	_L, \
+	_L,	_L,	_L,	_L,	_L,	_L,	_L,	_L, \
+	_U,	_U,	_U,	_U,	_U,	_U,	_U,	_U, \
+	_U,	_U,	_U,	_U,	_U,	_U,	_U,	_U, \
+	_U,	_U,	_U,	_U,	_U,	_U,	_U,	_U, \
+	_U,	_U,	_U,	_U,	_U,	_U,	_U
+#define _CTYPE_CP20866_255 _U
+#define _CTYPE_CP21866_128_254 \
+   	_P,	_P,	_P,	_P,	_P,	_P,	_P,	_P, \
+	_P,	_P,	_P,	_P,	_P,	_P,	_P,	_P, \
+	_P,	_P,	_P,	_P,	_P,	_P,	_P,	_P, \
+	_P,	_P,	_S|_B,	_P,	_P,	_P,	_P,	_P, \
+	_P,	_P,	_P,	_L,	_L,	_P,	_L,	_L, \
+	_P,	_P,	_P,	_P,	_P,	_L,	_P,	_P, \
+	_P,	_P,	_P,	_U,	_U,	_P,	_U,	_U, \
+	_P,	_P,	_P,	_P,	_P,	_U,	_P,	_P, \
+	_L,	_L,	_L,	_L,	_L,	_L,	_L,	_L, \
+	_L,	_L,	_L,	_L,	_L,	_L,	_L,	_L, \
+	_L,	_L,	_L,	_L,	_L,	_L,	_L,	_L, \
+	_L,	_L,	_L,	_L,	_L,	_L,	_L,	_L, \
+	_U,	_U,	_U,	_U,	_U,	_U,	_U,	_U, \
+	_U,	_U,	_U,	_U,	_U,	_U,	_U,	_U, \
+	_U,	_U,	_U,	_U,	_U,	_U,	_U,	_U, \
+	_U,	_U,	_U,	_U,	_U,	_U,	_U
+#define _CTYPE_CP21866_255 _U
+

 extern int __cp_index (const char *charset_ext);

@@ -405,7 +442,7 @@ extern int __cp_index (const char *charset_ext);
 #ifndef __CYGWIN__
 static _CONST
 #endif
-char __ctype_cp[22][128 + 256] = {
+char __ctype_cp[24][128 + 256] = {
  { _CTYPE_CP437_128_254,
    0,
    _CTYPE_DATA_0_127,
@@ -538,6 +575,18 @@ char __ctype_cp[22][128 + 256] = {
    _CTYPE_CP1258_128_254,
    _CTYPE_CP1258_255
  },
+  { _CTYPE_CP20866_128_254,
+    0,
+    _CTYPE_DATA_0_127,
+    _CTYPE_CP20866_128_254,
+    _CTYPE_CP20866_255
+  },
+  { _CTYPE_CP21866_128_254,
+    0,
+    _CTYPE_DATA_0_127,
+    _CTYPE_CP21866_128_254,
+    _CTYPE_CP21866_255
+  },
 };

 #else /* !defined(ALLOW_NEGATIVE_CTYPE_INDEX) */
@@ -653,6 +702,16 @@ static _CONST char __ctype_cp[22][1 + 256] = {
    _CTYPE_CP1258_128_254,
    _CTYPE_CP1258_255
  },
+  { 0,
+    _CTYPE_DATA_0_127,
+    _CTYPE_CP20866_128_254,
+    _CTYPE_CP20866_255
+  },
+  { 0,
+    _CTYPE_DATA_0_127,
+    _CTYPE_CP21866_128_254,
+    _CTYPE_CP21866_255
+  },
 };

 #endif /* ALLOW_NEGATIVE_CTYPE_INDEX */
--- a/newlib/libc/locale/locale.c
+++ b/newlib/libc/locale/locale.c
@@ -54,20 +54,21 @@ the form
 <<"language">> is a two character string per ISO 639.  <<"TERRITORY">> is a
 country code per ISO 3166.  For <<"charset">> and <<"modifier">> see below.

-Additionally to the POSIX specifier, five extensions are supported for
+Additionally to the POSIX specifier, seven extensions are supported for
 backward compatibility with older implementations using newlib:
-<<"C-UTF-8">>, <<"C-JIS">>, <<"C-EUCJP">>/<<"C-eucJP">>, <<"C-SJIS">>,
-<<"C-ISO-8859-x">> with 1 <= x <= 15, or <<"C-CPxxx">> with xxx in [437,
-720, 737, 775, 850, 852, 855, 857, 858, 862, 866, 874, 1125, 1250, 1251,
-1252, 1253, 1254, 1255, 1256, 1257, 1258].
+<<"C-UTF-8">>, <<"C-JIS">>, <<"C-eucJP">>, <<"C-SJIS">>, <<C-KOI8-R>>,
+<<C-KOI8-U>>, <<"C-ISO-8859-x">> with 1 <= x <= 15, or <<"C-CPxxx">> with
+xxx in [437, 720, 737, 775, 850, 852, 855, 857, 858, 862, 866, 874, 1125,
+1250, 1251, 1252, 1253, 1254, 1255, 1256, 1257, 1258].

 Even when using POSIX locale strings, the only charsets allowed are
-<<"UTF-8">>, <<"JIS">>, <<"EUCJP">>/<<"eucJP">>, <<"SJIS">>, <<"ISO-8859-x">>
-with 1 <= x <= 15, or <<"CPxxx">> with xxx in [437, 720, 737, 775, 850,
-852, 855, 857, 858, 862, 866, 874, 1125, 1250, 1251, 1252, 1253, 1254,
-1255, 1256, 1257, 1258].  Charsets are case insensitive.  For instance,
-<<"UTF-8">> and <<"utf-8">> are equivalent.  <<"UTF-8">> can also be
-written without dash, as in <<"UTF8">> or <<"utf8">>.
+<<"UTF-8">>, <<"JIS">>, <<"EUCJP">>, <<"SJIS">>, <<KOI8-R>>, <<KOI8-U>>,
+<<"ISO-8859-x">> with 1 <= x <= 15, or <<"CPxxx">> with xxx in
+[437, 720, 737, 775, 850, 852, 855, 857, 858, 862, 866, 874, 1125, 1250,
+1251, 1252, 1253, 1254, 1255, 1256, 1257, 1258].
+Charsets are case insensitive.  For instance, <<"EUCJP">> and <<"eucJP">>
+are equivalent.  <<"UTF-8">> can also be written without dash, as in
+<<"UTF8">> or <<"utf8">>.

 (<<"">> is also accepted; if given, the settings are read from the
 corresponding LC_* environment variables and $LANG according to POSIX rules.
@@ -615,6 +616,24 @@ loadlocale(struct _reent *p, int category)
 	  return NULL;
 	}
    break;
+    case 'K':
+    case 'k':
+      if (!strcasecmp (charset, "KOI8-R"))
+	strcpy (charset, "CP20866");
+      else if (!strcasecmp (charset, "KOI8-U"))
+	strcpy (charset, "CP21866");
+      else
+	return NULL;
+#ifdef _MB_CAPABLE
+#ifdef _MB_EXTENDED_CHARSETS_WINDOWS
+      l_wctomb = __cp_wctomb;
+      l_mbtowc = __cp_mbtowc;
+#else /* !_MB_EXTENDED_CHARSETS_WINDOWS */
+      l_wctomb = __ascii_wctomb;
+      l_mbtowc = __ascii_mbtowc;
+#endif /* _MB_EXTENDED_CHARSETS_WINDOWS */
+#endif
+      break;
    case 'A':
    case 'a':
      if (strcasecmp (charset, "ASCII"))
--- a/newlib/libc/stdlib/sb_charsets.c
+++ b/newlib/libc/stdlib/sb_charsets.c
@@ -203,7 +203,7 @@ wchar_t __iso_8859_conv[14][0x60] = {
   value (function __cp_index), the second index is the value of the
   incoming character - 0x80.
   Values < 0x80 don't have to be converted anyway. */
-wchar_t __cp_conv[22][0x80] = {
+wchar_t __cp_conv[24][0x80] = {
  /* CP437 */
  { 0xc7, 0xfc, 0xe9, 0xe2, 0xe4, 0xe0, 0xe5, 0xe7,
    0xea, 0xeb, 0xe8, 0xef, 0xee, 0xec, 0xc4, 0xc5,
@@ -577,7 +577,41 @@ wchar_t __cp_conv[22][0x80] = {
    0xe0, 0xe1, 0xe2, 0x103, 0xe4, 0xe5, 0xe6, 0xe7,
    0xe8, 0xe9, 0xea, 0xeb, 0x301, 0xed, 0xee, 0xef,
    0x111, 0xf1, 0x323, 0xf3, 0xf4, 0x1a1, 0xf6, 0xf7,
-    0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0x1b0, 0x20ab, 0xff }
+    0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0x1b0, 0x20ab, 0xff },
+  /* CP20866 (KOI8-R) */
+  { 0x2500, 0x2502, 0x250c, 0x2510, 0x2514, 0x2518, 0x251c, 0x2524,
+    0x252c, 0x2534, 0x253c, 0x2580, 0x2584, 0x2588, 0x258c, 0x2590,
+    0x2591, 0x2592, 0x2593, 0x2320, 0x25a0, 0x2219, 0x221a, 0x2248,
+    0x2264, 0x2265, 0xa0, 0x2321, 0xb0, 0xb2, 0xb7, 0xf7,
+    0x2550, 0x2551, 0x2552, 0x451, 0x2553, 0x2554, 0x2555, 0x2556,
+    0x2557, 0x2558, 0x2559, 0x255a, 0x255b, 0x255c, 0x255d, 0x255e,
+    0x255f, 0x2560, 0x2561, 0x401, 0x2562, 0x2563, 0x2564, 0x2565,
+    0x2566, 0x2567, 0x2568, 0x2569, 0x256a, 0x256b, 0x256c, 0xa9,
+    0x44e, 0x430, 0x431, 0x446, 0x434, 0x435, 0x444, 0x433,
+    0x445, 0x438, 0x439, 0x43a, 0x43b, 0x43c, 0x43d, 0x43e,
+    0x43f, 0x44f, 0x440, 0x441, 0x442, 0x443, 0x436, 0x432,
+    0x44c, 0x44b, 0x437, 0x448, 0x44d, 0x449, 0x447, 0x44a,
+    0x42e, 0x410, 0x411, 0x426, 0x414, 0x415, 0x424, 0x413,
+    0x425, 0x418, 0x419, 0x41a, 0x41b, 0x41c, 0x41d, 0x41e,
+    0x41f, 0x42f, 0x420, 0x421, 0x422, 0x423, 0x416, 0x412,
+    0x42c, 0x42b, 0x417, 0x428, 0x42d, 0x429, 0x427, 0x42a },
+  /* CP21866 (KOI8-U) */
+  { 0x2500, 0x2502, 0x250c, 0x2510, 0x2514, 0x2518, 0x251c, 0x2524,
+    0x252c, 0x2534, 0x253c, 0x2580, 0x2584, 0x2588, 0x258c, 0x2590,
+    0x2591, 0x2592, 0x2593, 0x2320, 0x25a0, 0x2219, 0x221a, 0x2248,
+    0x2264, 0x2265, 0xa0, 0x2321, 0xb0, 0xb2, 0xb7, 0xf7,
+    0x2550, 0x2551, 0x2552, 0x451, 0x454, 0x2554, 0x456, 0x457,
+    0x2557, 0x2558, 0x2559, 0x255a, 0x255b, 0x491, 0x255d, 0x255e,
+    0x255f, 0x2560, 0x2561, 0x401, 0x404, 0x2563, 0x406, 0x407,
+    0x2566, 0x2567, 0x2568, 0x2569, 0x256a, 0x490, 0x256c, 0xa9,
+    0x44e, 0x430, 0x431, 0x446, 0x434, 0x435, 0x444, 0x433,
+    0x445, 0x438, 0x439, 0x43a, 0x43b, 0x43c, 0x43d, 0x43e,
+    0x43f, 0x44f, 0x440, 0x441, 0x442, 0x443, 0x436, 0x432,
+    0x44c, 0x44b, 0x437, 0x448, 0x44d, 0x449, 0x447, 0x44a,
+    0x42e, 0x410, 0x411, 0x426, 0x414, 0x415, 0x424, 0x413,
+    0x425, 0x418, 0x419, 0x41a, 0x41b, 0x41c, 0x41d, 0x41e,
+    0x41f, 0x42f, 0x420, 0x421, 0x422, 0x423, 0x416, 0x412,
+    0x42c, 0x42b, 0x417, 0x428, 0x42d, 0x429, 0x427, 0x42a }
 };
 #endif /* _MB_EXTENDED_CHARSETS_WINDOWS */

@@ -687,6 +721,12 @@ __cp_index (const char *charset_ext)
    case 1258:
      cp_idx = 21;
      break;
+    case 20866:
+      cp_idx = 22;
+      break;
+    case 21866:
+      cp_idx = 23;
+      break;
    default:
      cp_idx = -1;
      break;