src/utils/lib/charset.mli

   1 (* Copyright 2005 b8_bavard, INRIA *)
   2 (*
   3     This file is part of mldonkey.
   4
   5     mldonkey is free software; you can redistribute it and/or modify
   6     it under the terms of the GNU General Public License as published by
   7     the Free Software Foundation; either version 2 of the License, or
   8     (at your option) any later version.
   9
  10     mldonkey is distributed in the hope that it will be useful,
  11     but WITHOUT ANY WARRANTY; without even the implied warranty of
  12     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  13     GNU General Public License for more details.
  14
  15     You should have received a copy of the GNU General Public License
  16     along with mldonkey; if not, write to the Free Software
  17     Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  18 *)
  19
  20 type uchar = int
  21
  22 type charset =
  23 | ANSI_X3_4_1968 | ANSI_X3_4_1986 | ASCII | CP367 | IBM367 | ISO_IR_6 | ISO646_US | ISO_646_IRV_1991 | US | US_ASCII | CSASCII
  24 | UTF_8
  25 | ISO_10646_UCS_2 | UCS_2 | CSUNICODE
  26 | UCS_2BE | UNICODE_1_1 | UNICODEBIG | CSUNICODE11
  27 | UCS_2LE | UNICODELITTLE
  28 | ISO_10646_UCS_4 | UCS_4 | CSUCS4
  29 | UCS_4BE
  30 | UCS_4LE
  31 | UTF_16
  32 | UTF_16BE
  33 | UTF_16LE
  34 | UTF_32
  35 | UTF_32BE
  36 | UTF_32LE
  37 | UNICODE_1_1_UTF_7 | UTF_7 | CSUNICODE11UTF7
  38 | UCS_2_INTERNAL
  39 | UCS_2_SWAPPED
  40 | UCS_4_INTERNAL
  41 | UCS_4_SWAPPED
  42 | C99
  43 | JAVA
  44 | CP819 | IBM819 | ISO_8859_1 | ISO_IR_100 | ISO8859_1 | ISO_8859_1_1987 | L1 | LATIN1 | CSISOLATIN1
  45 | ISO_8859_2 | ISO_IR_101 | ISO8859_2 | ISO_8859_2_1987 | L2 | LATIN2 | CSISOLATIN2
  46 | ISO_8859_3 | ISO_IR_109 | ISO8859_3 | ISO_8859_3_1988 | L3 | LATIN3 | CSISOLATIN3
  47 | ISO_8859_4 | ISO_IR_110 | ISO8859_4 | ISO_8859_4_1988 | L4 | LATIN4 | CSISOLATIN4
  48 | CYRILLIC | ISO_8859_5 | ISO_IR_144  | ISO8859_5 | ISO_8859_5_1988 | CSISOLATINCYRILLIC
  49 | ARABIC | ASMO_708 | ECMA_114 | ISO_8859_6 | ISO_IR_127 | ISO8859_6 | ISO_8859_6_1987 | CSISOLATINARABIC
  50 | ECMA_118 | ELOT_928 | GREEK | GREEK8 | ISO_8859_7 | ISO_IR_126 | ISO8859_7 | ISO_8859_7_1987 | CSISOLATINGREEK
  51 | HEBREW | ISO_8859_8 | ISO_IR_138 | ISO8859_8 | ISO_8859_8_1988 | CSISOLATINHEBREW
  52 | ISO_8859_9 | ISO_IR_148 | ISO8859_9 | ISO_8859_9_1989 | L5 | LATIN5 | CSISOLATIN5
  53 | ISO_8859_10 | ISO_IR_157 | ISO8859_10 | ISO_8859_10_1992 | L6 | LATIN6 | CSISOLATIN6
  54 | ISO_8859_13 | ISO_IR_179 | ISO8859_13 | L7 | LATIN7
  55 | ISO_8859_14 | ISO_CELTIC | ISO8859_14 | ISO_IR_199 | ISO_8859_14_1998 | L8 | LATIN8
  56 | ISO_8859_15 | ISO_IR_203 | ISO8859_15 | ISO_8859_15_1998
  57 | ISO_8859_16 | ISO_IR_226 | ISO8859_16 | ISO_8859_16_2000
  58 | KOI8_R | CSKOI8R
  59 | KOI8_U
  60 | KOI8_RU
  61 | CP1250 | MS_EE | WINDOWS_1250
  62 | CP1251 | MS_CYRL | WINDOWS_1251
  63 | CP1252 | MS_ANSI | WINDOWS_1252
  64 | CP1253 | MS_GREEK | WINDOWS_1253
  65 | CP1254 | MS_TURK | WINDOWS_1254
  66 | CP1255 | MS_HEBR | WINDOWS_1255
  67 | CP1256 | MS_ARAB | WINDOWS_1256
  68 | CP1257 | WINBALTRIM | WINDOWS_1257
  69 | CP1258 | WINDOWS_1258
  70 | I_850 | CP850 | IBM850 | CSPC850MULTILINGUAL
  71 | I_862 | CP862 | IBM862 | CSPC862LATINHEBREW
  72 | I_866 | CP866 | IBM866 | CSIBM866
  73 | MAC | MACINTOSH | MACROMAN | CSMACINTOSH
  74 | MACCENTRALEUROPE
  75 | MACICELAND
  76 | MACCROATIAN
  77 | MACROMANIA
  78 | MACCYRILLIC
  79 | MACUKRAINE
  80 | MACGREEK
  81 | MACTURKISH
  82 | MACHEBREW
  83 | MACARABIC
  84 | MACTHAI
  85 | HP_ROMAN8 | R8 | ROMAN8 | CSHPROMAN8
  86 | NEXTSTEP
  87 | ARMSCII_8
  88 | GEORGIAN_ACADEMY
  89 | GEORGIAN_PS
  90 | KOI8_T
  91 | MULELAO_1
  92 | CP1133 | IBM_CP1133
  93 | ISO_IR_166 | TIS_620 | TIS620 | TIS620_0 | TIS620_2529_1 | TIS620_2533_0 | TIS620_2533_1
  94 | CP874 | WINDOWS_874
  95 | VISCII | VISCII1_1_1 | CSVISCII
  96 | TCVN | TCVN_5712 | TCVN5712_1 | TCVN5712_1_1993
  97 | ISO_IR_14 | ISO646_JP | JIS_C6220_1969_RO | JP | CSISO14JISC6220RO
  98 | JISX0201_1976 | JIS_X0201 | X0201 | CSHALFWIDTHKATAKANA
  99 | ISO_IR_87 | JIS0208 | JIS_C6226_1983 | JIS_X0208 | JIS_X0208_1983 | JIS_X0208_1990 | X0208 | CSISO87JISX0208
 100 | ISO_IR_159 | JIS_X0212 | JIS_X0212_1990 | JIS_X0212_1990_0 | X0212 | CSISO159JISX02121990
 101 | CN | GB_1988_80 | ISO_IR_57 | ISO646_CN | CSISO57GB1988
 102 | CHINESE | GB_2312_80 | ISO_IR_58 | CSISO58GB231280
 103 | CN_GB_ISOIR165 | ISO_IR_165
 104 | ISO_IR_149 | KOREAN | KSC_5601 | KS_C_5601_1987 | KS_C_5601_1989 | CSKSC56011987
 105 | EUC_JP | EUCJP | EXTENDED_UNIX_CODE_PACKED_FORMAT_FOR_JAPANESE | CSEUCPKDFMTJAPANESE
 106 | MS_KANJI | SHIFT_JIS | SJIS | CSSHIFTJIS
 107 | CP932
 108 | ISO_2022_JP | CSISO2022JP
 109 | ISO_2022_JP_1
 110 | ISO_2022_JP_2 | CSISO2022JP2
 111 | CN_GB | EUC_CN | EUCCN | GB2312 | CSGB2312
 112 | CP936 | GBK
 113 | GB18030
 114 | ISO_2022_CN | CSISO2022CN
 115 | ISO_2022_CN_EXT
 116 | HZ | HZ_GB_2312
 117 | EUC_TW | EUCTW | CSEUCTW
 118 | BIG_5 | BIG_FIVE | BIG5 | BIGFIVE | CN_BIG5 | CSBIG5
 119 | CP950
 120 | BIG5_HKSCS | BIG5HKSCS
 121 | EUC_KR | EUCKR | CSEUCKR
 122 | CP949 | UHC
 123 | CP1361 | JOHAB
 124 | ISO_2022_KR | CSISO2022KR
 125 | I_437 | CP437 | IBM437 | CSPC8CODEPAGE437
 126 | CP737
 127 | CP775 | IBM775 | CSPC775BALTIC
 128 | I_852 | CP852 | IBM852 | CSPCP852
 129 | CP853
 130 | I_855 | CP855 | IBM855 | CSIBM855
 131 | I_857 | CP857 | IBM857 | CSIBM857
 132 | CP858
 133 | I_860 | CP860 | IBM860 | CSIBM860
 134 | I_861 | CP_IS | CP861 | IBM861 | CSIBM861
 135 | I_863 | CP863 | IBM863 | CSIBM863
 136 | CP864 | IBM864 | CSIBM864
 137 | I_865 | CP865 | IBM865 | CSIBM865
 138 | I_869 | CP_GR | CP869 | IBM869 | CSIBM869
 139 | CP1125
 140
 141 (** @return ASCII if nothing matches *)
 142 val charset_from_string : string -> charset
 143
 144 val charset_to_string : charset -> string
 145
 146 (** [convert ~from_charset ~to_charset s]
 147     @raise CharsetError if the string s is not entirely convertible. *)
 148 val convert : from_charset : charset -> to_charset : charset -> string -> string
 149
 150 (** [safe_convert enc s] convert [s] from encoding [enc] to UTF-8.
 151   Return unmodified string if conversion fails.
 152   *)
 153 val safe_convert: string -> string -> string
 154
 155 (** [is_utf8 s]
 156     returns TRUE if s is a valid UTF-8, otherwise returns FALSE.
 157     Other functions assume strings are valid UTF-8, so it is prudent
 158     to test their validity for strings from untrusted origins. *)
 159 val is_utf8 : string -> bool
 160
 161 (** [utf8_get s n]
 162     returns [n]-th Unicode character of [s].
 163     The call requires O(n)-time. *)
 164 val utf8_get : string -> int -> uchar
 165
 166 (** [utf8_length s]
 167     returns the number of Unicode characters contained in s *)
 168 val utf8_length : string -> int
 169
 170 (** [utf8_nth s n] @return index of [n]-th utf-8 character in [s] (must be valid utf-8 string). O(n) *)
 171 val utf8_nth : string -> int -> int
 172
 173 (** [add_uchar buf u]
 174     add one Unicode character to the buffer. *)
 175 val add_uchar : Buffer.t -> uchar -> unit
 176
 177 (** Locale dependent conversions *)
 178 module Locale : sig
 179
 180 (** [to_utf8 s]
 181     Converts the input string to UTF-8. *)
 182 val to_utf8 : string -> string
 183
 184 (** [to_locale s]
 185     Converts the input string to the encoding of the current locale. *)
 186 val to_locale : string -> string
 187
 188 val default_language : string
 189 val locale_string : string
 190 val conversion_enabled : bool ref
 191
 192 end
 193