Main Page | Class Hierarchy | Alphabetical List | Data Structures | Directories | File List | Data Fields | Globals | Related Pages

utf.h

Go to the documentation of this file.
00001 /*
00002 *******************************************************************************
00003 *
00004 *   Copyright (C) 1999-2001, International Business Machines
00005 *   Corporation and others.  All Rights Reserved.
00006 *
00007 *******************************************************************************
00008 *   file name:  utf.h
00009 *   encoding:   US-ASCII
00010 *   tab size:   8 (not used)
00011 *   indentation:4
00012 *
00013 *   created on: 1999sep09
00014 *   created by: Markus W. Scherer
00015 */
00016 
00087 #ifndef __UTF_H__
00088 #define __UTF_H__
00089 
00090 /*
00091  * ANSI C headers:
00092  * stddef.h defines wchar_t
00093  */
00094 #include <stddef.h>
00095 #include "unicode/umachine.h"
00096 /* include the utfXX.h after the following definitions */
00097 
00098 /* If there is no compiler option for the preferred UTF size, then default to UTF-16. */
00099 #ifndef UTF_SIZE
00100 
00101 #   define UTF_SIZE 16
00102 #endif
00103 
00105 #define U_SIZEOF_UCHAR (UTF_SIZE>>3)
00106 
00111 #ifndef U_HAVE_WCHAR_H
00112 #   define U_HAVE_WCHAR_H 1
00113 #endif
00114 
00115 /* U_SIZEOF_WCHAR_T==sizeof(wchar_t) (0 means it is not defined or autoconf could not set it) */
00116 #if U_SIZEOF_WCHAR_T==0
00117 #   undef U_SIZEOF_WCHAR_T
00118 #   define U_SIZEOF_WCHAR_T 4
00119 #endif
00120 
00129 #if !defined(U_WCHAR_IS_UTF16) && !defined(U_WCHAR_IS_UTF32)
00130 #   ifdef __STDC_ISO_10646__ 
00131 #       if (U_SIZEOF_WCHAR_T==2)
00132 #           define U_WCHAR_IS_UTF16
00133 #       elif (U_SIZEOF_WCHAR_T==4)
00134 #           define  U_WCHAR_IS_UTF32
00135 #       endif
00136 #   elif defined __UCS2__
00137 #       if (__OS390__ || __OS400__) && (U_SIZEOF_WCHAR_T==2)
00138 #           define U_WCHAR_IS_UTF16
00139 #       endif
00140 #   elif defined __UCS4__
00141 #       if (U_SIZEOF_WCHAR_T==4)
00142 #           define U_WCHAR_IS_UTF32
00143 #       endif
00144 #   elif defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
00145 #       define U_WCHAR_IS_UTF16    
00146 #   endif
00147 #endif
00148 
00154 #if U_SIZEOF_WCHAR_T==4
00155     typedef wchar_t UChar32;
00156 #else
00157     typedef uint32_t UChar32;
00158 #endif
00159 
00167 typedef int32_t UTextOffset;
00168 
00169 /* Specify which macro versions are the default ones - safe or fast. */
00170 #if !defined(UTF_SAFE) && !defined(UTF_STRICT) && !defined(UTF_UNSAFE)
00171 
00175 #   define UTF_SAFE
00176 #endif
00177 
00178 /* internal definitions ----------------------------------------------------- */
00179 
00192 #define UTF8_ERROR_VALUE_1 0x15
00193 #define UTF8_ERROR_VALUE_2 0x9f
00194 
00199 #define UTF_ERROR_VALUE 0xffff
00200 
00201 /* single-code point definitions -------------------------------------------- */
00202 
00204 #define UTF_IS_SURROGATE(uchar) (((uchar)&0xfffff800)==0xd800)
00205 
00209 #define UTF_IS_UNICODE_NONCHAR(c) \
00210     (((((c) & 0xfffe) == 0xfffe) || ((c) >= 0xfdd0 && (c) <= 0xfdef)) && \
00211     ((c) <= 0x10ffff))
00212 
00226 #define UTF_IS_UNICODE_CHAR(c) \
00227     ((uint32_t)(c)<0xd800 || \
00228         ((uint32_t)(c)>0xdfff && \
00229          (uint32_t)(c)<=0x10ffff && \
00230          !UTF_IS_UNICODE_NONCHAR(c)))
00231 
00236 #define UTF_IS_ERROR(c) \
00237     (((c)&0xfffe)==0xfffe || (c)==UTF8_ERROR_VALUE_1 || (c)==UTF8_ERROR_VALUE_2)
00238 
00240 #define UTF_IS_VALID(c) \
00241     (UTF_IS_UNICODE_CHAR(c) && \
00242      (c)!=UTF8_ERROR_VALUE_1 && (c)!=UTF8_ERROR_VALUE_2)
00243 
00244 /* include the utfXX.h ------------------------------------------------------ */
00245 
00246 #include "unicode/utf8.h"
00247 #include "unicode/utf16.h"
00248 #include "unicode/utf32.h"
00249 
00250 /* Define types and macros according to the selected UTF size. -------------- */
00251 
00258 #if UTF_SIZE==8
00259 
00260 #   error UTF-8 is not implemented, undefine UTF_SIZE or define it to 16
00261 
00262 /*
00263  * ANSI C header:
00264  * limits.h defines CHAR_MAX
00265  */
00266 #   include <limits.h>
00267 
00268     /* Define UChar to be compatible with char if possible. */
00269 #   if CHAR_MAX>=255
00270         typedef char UChar;
00271 #   else
00272         typedef uint8_t UChar;
00273 #   endif
00274 
00275 #elif UTF_SIZE==16
00276 
00277     /* Define UChar to be compatible with wchar_t if possible. */
00278 #   if U_SIZEOF_WCHAR_T==2
00279         typedef wchar_t UChar;
00280 #   else
00281         typedef uint16_t UChar;
00282 #   endif
00283 
00285 #   define UTF_IS_SINGLE(uchar)                         UTF16_IS_SINGLE(uchar)
00286 
00287 #   define UTF_IS_LEAD(uchar)                           UTF16_IS_LEAD(uchar)
00288 
00289 #   define UTF_IS_TRAIL(uchar)                          UTF16_IS_TRAIL(uchar)
00290 
00292 #   define UTF_NEED_MULTIPLE_UCHAR(c)                   UTF16_NEED_MULTIPLE_UCHAR(c)
00293 
00294 #   define UTF_CHAR_LENGTH(c)                           UTF16_CHAR_LENGTH(c)
00295 
00296 #   define UTF_MAX_CHAR_LENGTH                          UTF16_MAX_CHAR_LENGTH
00297 
00298 #   define UTF_ARRAY_SIZE(size)                         UTF16_ARRAY_SIZE(size)
00299 
00301 #   define UTF_GET_CHAR_UNSAFE(s, i, c)                 UTF16_GET_CHAR_UNSAFE(s, i, c)
00302 
00303 #   define UTF_GET_CHAR_SAFE(s, start, i, length, c, strict) UTF16_GET_CHAR_SAFE(s, start, i, length, c, strict)
00304 
00306 #   define UTF_NEXT_CHAR_UNSAFE(s, i, c)                UTF16_NEXT_CHAR_UNSAFE(s, i, c)
00307 
00308 #   define UTF_NEXT_CHAR_SAFE(s, i, length, c, strict)  UTF16_NEXT_CHAR_SAFE(s, i, length, c, strict)
00309 
00311 #   define UTF_APPEND_CHAR_UNSAFE(s, i, c)              UTF16_APPEND_CHAR_UNSAFE(s, i, c)
00312 
00313 #   define UTF_APPEND_CHAR_SAFE(s, i, length, c)        UTF16_APPEND_CHAR_SAFE(s, i, length, c)
00314 
00316 #   define UTF_FWD_1_UNSAFE(s, i)                       UTF16_FWD_1_UNSAFE(s, i)
00317 
00318 #   define UTF_FWD_1_SAFE(s, i, length)                 UTF16_FWD_1_SAFE(s, i, length)
00319 
00321 #   define UTF_FWD_N_UNSAFE(s, i, n)                    UTF16_FWD_N_UNSAFE(s, i, n)
00322 
00323 #   define UTF_FWD_N_SAFE(s, i, length, n)              UTF16_FWD_N_SAFE(s, i, length, n)
00324 
00326 #   define UTF_SET_CHAR_START_UNSAFE(s, i)              UTF16_SET_CHAR_START_UNSAFE(s, i)
00327 
00328 #   define UTF_SET_CHAR_START_SAFE(s, start, i)         UTF16_SET_CHAR_START_SAFE(s, start, i)
00329 
00331 #   define UTF_PREV_CHAR_UNSAFE(s, i, c)                UTF16_PREV_CHAR_UNSAFE(s, i, c)
00332 
00333 #   define UTF_PREV_CHAR_SAFE(s, start, i, c, strict)   UTF16_PREV_CHAR_SAFE(s, start, i, c, strict)
00334 
00336 #   define UTF_BACK_1_UNSAFE(s, i)                      UTF16_BACK_1_UNSAFE(s, i)
00337 
00338 #   define UTF_BACK_1_SAFE(s, start, i)                 UTF16_BACK_1_SAFE(s, start, i)
00339 
00341 #   define UTF_BACK_N_UNSAFE(s, i, n)                   UTF16_BACK_N_UNSAFE(s, i, n)
00342 
00343 #   define UTF_BACK_N_SAFE(s, start, i, n)              UTF16_BACK_N_SAFE(s, start, i, n)
00344 
00346 #   define UTF_SET_CHAR_LIMIT_UNSAFE(s, i)              UTF16_SET_CHAR_LIMIT_UNSAFE(s, i)
00347 
00348 #   define UTF_SET_CHAR_LIMIT_SAFE(s, start, i, length) UTF16_SET_CHAR_LIMIT_SAFE(s, start, i, length)
00349 
00350 #elif UTF_SIZE==32
00351 
00352 #   error UTF-32 is not implemented, undefine UTF_SIZE or define it to 16
00353 
00354     typedef UChar32 UChar;
00355 
00356 #else
00357 #   error UTF_SIZE must be undefined or one of { 8, 16, 32 } - only 16 is implemented
00358 #endif
00359 
00360 /* Define the default macros for handling UTF characters. ------------------- */
00361 
00469 #ifdef UTF_SAFE
00470 
00471 #   define UTF_GET_CHAR(s, start, i, length, c) UTF_GET_CHAR_SAFE(s, start, i, length, c, FALSE)
00472 
00473 #   define UTF_NEXT_CHAR(s, i, length, c)       UTF_NEXT_CHAR_SAFE(s, i, length, c, FALSE)
00474 #   define UTF_APPEND_CHAR(s, i, length, c)     UTF_APPEND_CHAR_SAFE(s, i, length, c)
00475 #   define UTF_FWD_1(s, i, length)              UTF_FWD_1_SAFE(s, i, length)
00476 #   define UTF_FWD_N(s, i, length, n)           UTF_FWD_N_SAFE(s, i, length, n)
00477 #   define UTF_SET_CHAR_START(s, start, i)      UTF_SET_CHAR_START_SAFE(s, start, i)
00478 
00479 #   define UTF_PREV_CHAR(s, start, i, c)        UTF_PREV_CHAR_SAFE(s, start, i, c, FALSE)
00480 #   define UTF_BACK_1(s, start, i)              UTF_BACK_1_SAFE(s, start, i)
00481 #   define UTF_BACK_N(s, start, i, n)           UTF_BACK_N_SAFE(s, start, i, n)
00482 #   define UTF_SET_CHAR_LIMIT(s, start, i, length) UTF_SET_CHAR_LIMIT_SAFE(s, start, i, length)
00483 
00484 #elif defined(UTF_STRICT)
00485 
00486 #   define UTF_GET_CHAR(s, start, i, length, c) UTF_GET_CHAR_SAFE(s, start, i, length, c, TRUE)
00487 
00488 #   define UTF_NEXT_CHAR(s, i, length, c)       UTF_NEXT_CHAR_SAFE(s, i, length, c, TRUE)
00489 #   define UTF_APPEND_CHAR(s, i, length, c)     UTF_APPEND_CHAR_SAFE(s, i, length, c)
00490 #   define UTF_FWD_1(s, i, length)              UTF_FWD_1_SAFE(s, i, length)
00491 #   define UTF_FWD_N(s, i, length, n)           UTF_FWD_N_SAFE(s, i, length, n)
00492 #   define UTF_SET_CHAR_START(s, start, i)      UTF_SET_CHAR_START_SAFE(s, start, i)
00493 
00494 #   define UTF_PREV_CHAR(s, start, i, c)        UTF_PREV_CHAR_SAFE(s, start, i, c, TRUE)
00495 #   define UTF_BACK_1(s, start, i)              UTF_BACK_1_SAFE(s, start, i)
00496 #   define UTF_BACK_N(s, start, i, n)           UTF_BACK_N_SAFE(s, start, i, n)
00497 #   define UTF_SET_CHAR_LIMIT(s, start, i, length) UTF_SET_CHAR_LIMIT_SAFE(s, start, i, length)
00498 
00499 #else /* UTF_UNSAFE */
00500 
00501 #   define UTF_GET_CHAR(s, start, i, length, c) UTF_GET_CHAR_UNSAFE(s, i, c)
00502 
00503 #   define UTF_NEXT_CHAR(s, i, length, c)       UTF_NEXT_CHAR_UNSAFE(s, i, c)
00504 #   define UTF_APPEND_CHAR(s, i, length, c)     UTF_APPEND_CHAR_UNSAFE(s, i, c)
00505 #   define UTF_FWD_1(s, i, length)              UTF_FWD_1_UNSAFE(s, i)
00506 #   define UTF_FWD_N(s, i, length, n)           UTF_FWD_N_UNSAFE(s, i, n)
00507 #   define UTF_SET_CHAR_START(s, start, i)      UTF_SET_CHAR_START_UNSAFE(s, i)
00508 
00509 #   define UTF_PREV_CHAR(s, start, i, c)        UTF_PREV_CHAR_UNSAFE(s, i, c)
00510 #   define UTF_BACK_1(s, start, i)              UTF_BACK_1_UNSAFE(s, i)
00511 #   define UTF_BACK_N(s, start, i, n)           UTF_BACK_N_UNSAFE(s, i, n)
00512 #   define UTF_SET_CHAR_LIMIT(s, start, i, length) UTF_SET_CHAR_LIMIT_UNSAFE(s, i)
00513 
00514 #endif
00515 
00516 #endif

Generated on Tue Jul 26 18:11:49 2005 for ICU 2.1 by  doxygen 1.4.3-20050530