mirror of
https://github.com/unicode-org/icu.git
synced 2025-04-18 11:14:22 +00:00
ICU-2329 use a single ASCII-EBCDIC table and add functions to check if a string contains only invariant characters
X-SVN-Rev: 12579
This commit is contained in:
Markus Scherer
parent
a66ecb7536
commit
7c3cd6b0a5
1 changed files with 180 additions and 86 deletions
|
|
@ -65,6 +65,7 @@
|
|||
/* include ICU headers */
|
||||
#include "unicode/utypes.h"
|
||||
#include "unicode/putil.h"
|
||||
#include "uassert.h"
|
||||
#include "umutex.h"
|
||||
#include "cmemory.h"
|
||||
#include "cstring.h"
|
||||
|
|
@ -1898,97 +1899,55 @@ uprv_getDefaultCodepage()
|
|||
#endif
|
||||
}
|
||||
|
||||
#if U_CHARSET_FAMILY==U_EBCDIC_FAMILY
|
||||
#ifdef OS390
|
||||
/*
|
||||
* These maps for ASCII to/from EBCDIC are from
|
||||
* "UTF-EBCDIC - EBCDIC-Friendly Unicode (or UCS) Transformation Format"
|
||||
* at http://www.unicode.org/unicode/reports/tr16/
|
||||
* (which should reflect codepage 1047)
|
||||
* but modified to explicitly exclude the variant
|
||||
* control and graphical characters that are in ASCII-based
|
||||
* codepages at 0x80 and above.
|
||||
* Also, unlike in Version 6.0 of the UTR on UTF-EBCDIC,
|
||||
* the Line Feed mapping varies according to the environment.
|
||||
* These maps for ASCII to/from EBCDIC map invariant characters (see utypes.h)
|
||||
* appropriately for most EBCDIC codepages.
|
||||
*
|
||||
* These tables do not establish a converter or a codepage.
|
||||
*/
|
||||
|
||||
/* on S/390 Open Edition, ASCII 0xa (LF) maps to 0x15 and ISO-8 0x85 maps to 0x25 */
|
||||
# define E_LF 0x15
|
||||
# define A_15 0x0a
|
||||
# define A_25 0x00
|
||||
|
||||
# if 0
|
||||
/* the CDRA variation of 1047 is not currently used - see tables in #else below */
|
||||
/* in standard EBCDIC (CDRA), ASCII 0xa (LF) maps to 0x25 and ISO-8 0x85 maps to 0x15 */
|
||||
# define E_LF 0x25
|
||||
# define A_15 0x00
|
||||
# define A_25 0x0a
|
||||
# endif
|
||||
|
||||
static const uint8_t asciiFromEbcdic[256]={
|
||||
0x00, 0x01, 0x02, 0x03, 0x00, 0x09, 0x00, 0x7F, 0x00, 0x00, 0x00, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
|
||||
0x10, 0x11, 0x12, 0x13, 0x00, A_15, 0x08, 0x00, 0x18, 0x19, 0x00, 0x00, 0x1C, 0x1D, 0x1E, 0x1F,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, A_25, 0x17, 0x1B, 0x00, 0x00, 0x00, 0x00, 0x00, 0x05, 0x06, 0x07,
|
||||
0x00, 0x00, 0x16, 0x00, 0x00, 0x00, 0x00, 0x04, 0x00, 0x00, 0x00, 0x00, 0x14, 0x15, 0x00, 0x1A,
|
||||
0x20, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
|
||||
0x26, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0x5E,
|
||||
0x2D, 0x2F, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
|
||||
0x00, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0x00, 0x00, 0x00, 0x5B, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x5D, 0x00, 0x00,
|
||||
0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x5C, 0x00, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
|
||||
};
|
||||
|
||||
static const uint8_t ebcdicFromAscii[256]={
|
||||
0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, E_LF, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
|
||||
0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
|
||||
0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
|
||||
0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
|
||||
0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
|
||||
0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xAD, 0xE0, 0xBD, 0x5F, 0x6D,
|
||||
0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
|
||||
0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xC0, 0x4F, 0xD0, 0xA1, 0x07,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
|
||||
};
|
||||
|
||||
#else
|
||||
/*
|
||||
* These maps for ASCII to/from EBCDIC were generated
|
||||
* using the ICU converter for codepage 37 on 2000-may-22.
|
||||
* They explicitly exclude the variant
|
||||
* They currently also map most other ASCII graphic characters,
|
||||
* appropriately for codepages 37 and 1047.
|
||||
* Exceptions: The characters for []^ have different codes in 37 & 1047.
|
||||
* Both versions are mapped to ASCII.
|
||||
*
|
||||
* ASCII 37 1047
|
||||
* [ 5B BA AD
|
||||
* ] 5D BB BD
|
||||
* ^ 5E B0 5F
|
||||
*
|
||||
* There are no mappings for variant characters from Unicode to EBCDIC.
|
||||
*
|
||||
* Currently, C0 control codes are also included in these maps.
|
||||
* Exceptions: S/390 Open Edition swaps LF and NEL codes compared with other
|
||||
* EBCDIC platforms; both codes (15 and 25) are mapped to ASCII LF (0A),
|
||||
* but there is no mapping for ASCII LF back to EBCDIC.
|
||||
*
|
||||
* ASCII EBCDIC S/390-OE
|
||||
* LF 0A 25 15
|
||||
* NEL 85 15 25
|
||||
*
|
||||
* The maps below explicitly exclude the variant
|
||||
* control and graphical characters that are in ASCII-based
|
||||
* codepages at 0x80 and above.
|
||||
* "No mapping" is expressed by mapping to a 00 byte.
|
||||
*
|
||||
* These tables do not establish a converter or a codepage.
|
||||
*/
|
||||
|
||||
static const uint8_t asciiFromEbcdic[256]={
|
||||
0x00, 0x01, 0x02, 0x03, 0x00, 0x09, 0x00, 0x7f, 0x00, 0x00, 0x00, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
|
||||
0x10, 0x11, 0x12, 0x13, 0x00, 0x00, 0x08, 0x00, 0x18, 0x19, 0x00, 0x00, 0x1c, 0x1d, 0x1e, 0x1f,
|
||||
0x10, 0x11, 0x12, 0x13, 0x00, 0x0a, 0x08, 0x00, 0x18, 0x19, 0x00, 0x00, 0x1c, 0x1d, 0x1e, 0x1f,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x0a, 0x17, 0x1b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x05, 0x06, 0x07,
|
||||
0x00, 0x00, 0x16, 0x00, 0x00, 0x00, 0x00, 0x04, 0x00, 0x00, 0x00, 0x00, 0x14, 0x15, 0x00, 0x1a,
|
||||
|
||||
0x20, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x2e, 0x3c, 0x28, 0x2b, 0x7c,
|
||||
0x26, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x21, 0x24, 0x2a, 0x29, 0x3b, 0x00,
|
||||
0x26, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x21, 0x24, 0x2a, 0x29, 0x3b, 0x5e,
|
||||
0x2d, 0x2f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x2c, 0x25, 0x5f, 0x3e, 0x3f,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x3a, 0x23, 0x40, 0x27, 0x3d, 0x22,
|
||||
|
||||
0x00, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, 0x70, 0x71, 0x72, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x7e, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x5e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x5b, 0x5d, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x7e, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x00, 0x00, 0x00, 0x5b, 0x00, 0x00,
|
||||
0x5e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x5b, 0x5d, 0x00, 0x5d, 0x00, 0x00,
|
||||
|
||||
0x7b, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x7d, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, 0x50, 0x51, 0x52, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x5c, 0x00, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5a, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
|
|
@ -1996,54 +1955,189 @@ static const uint8_t asciiFromEbcdic[256]={
|
|||
};
|
||||
|
||||
static const uint8_t ebcdicFromAscii[256]={
|
||||
0x00, 0x01, 0x02, 0x03, 0x37, 0x2d, 0x2e, 0x2f, 0x16, 0x05, 0x25, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
|
||||
0x00, 0x01, 0x02, 0x03, 0x37, 0x2d, 0x2e, 0x2f, 0x16, 0x05, 0x00, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
|
||||
0x10, 0x11, 0x12, 0x13, 0x3c, 0x3d, 0x32, 0x26, 0x18, 0x19, 0x3f, 0x27, 0x1c, 0x1d, 0x1e, 0x1f,
|
||||
0x40, 0x5a, 0x7f, 0x7b, 0x5b, 0x6c, 0x50, 0x7d, 0x4d, 0x5d, 0x5c, 0x4e, 0x6b, 0x60, 0x4b, 0x61,
|
||||
0x40, 0x00, 0x7f, 0x00, 0x00, 0x6c, 0x50, 0x7d, 0x4d, 0x5d, 0x5c, 0x4e, 0x6b, 0x60, 0x4b, 0x61,
|
||||
0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0x7a, 0x5e, 0x4c, 0x7e, 0x6e, 0x6f,
|
||||
0x7c, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, 0xc8, 0xc9, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6,
|
||||
0xd7, 0xd8, 0xd9, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0xba, 0xe0, 0xbb, 0xb0, 0x6d,
|
||||
0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
|
||||
0x97, 0x98, 0x99, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, 0xa8, 0xa9, 0xc0, 0x4f, 0xd0, 0xa1, 0x07,
|
||||
|
||||
0x00, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, 0xc8, 0xc9, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6,
|
||||
0xd7, 0xd8, 0xd9, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0x00, 0x00, 0x00, 0x00, 0x6d,
|
||||
0x00, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
|
||||
0x97, 0x98, 0x99, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, 0xa8, 0xa9, 0x00, 0x00, 0x00, 0x00, 0x07,
|
||||
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
|
||||
};
|
||||
|
||||
#endif
|
||||
/*
|
||||
* Bit sets indicating which characters of the ASCII repertoire
|
||||
* (by ASCII/Unicode code) are "invariant".
|
||||
* See utypes.h for more details.
|
||||
*
|
||||
* As invariant are considered the characters of the ASCII repertoire except
|
||||
* for the following:
|
||||
* 21 '!' <exclamation mark>
|
||||
* 23 '#' <number sign>
|
||||
* 24 '$' <dollar sign>
|
||||
*
|
||||
* 40 '@' <commercial at>
|
||||
*
|
||||
* 5b '[' <left bracket>
|
||||
* 5c '\' <backslash>
|
||||
* 5d ']' <right bracket>
|
||||
* 5e '^' <circumflex>
|
||||
*
|
||||
* 60 '`' <grave accent>
|
||||
*
|
||||
* 7b '{' <left brace>
|
||||
* 7c '|' <vertical line>
|
||||
* 7d '}' <right brace>
|
||||
* 7e '~' <tilde>
|
||||
*/
|
||||
static const uint32_t invariantChars[4]={
|
||||
0xfffffbff, /* 00..1f but not 0a */
|
||||
0xffffffe5, /* 20..3f but not 21 23 24 */
|
||||
0x87fffffe, /* 40..5f but not 40 5b..5e */
|
||||
0x87fffffe /* 60..7f but not 60 7b..7e */
|
||||
};
|
||||
|
||||
#define CHAR_IS_INVARIANT(c) ((0<=(c)) && ((c)<=0x7f) && (invariantChars[(c)>>5]&((uint32_t)1<<((c)&0x1f)))!=0)
|
||||
|
||||
#endif
|
||||
|
||||
U_CAPI void U_EXPORT2
|
||||
u_charsToUChars(const char *cs, UChar *us, int32_t length) {
|
||||
UChar u;
|
||||
uint8_t c;
|
||||
UBool onlyInvariantChars;
|
||||
|
||||
/*
|
||||
* Allow the entire ASCII repertoire to be mapped _to_ Unicode.
|
||||
* For EBCDIC systems, this works for characters with codes from
|
||||
* codepages 37 and 1047 or compatible.
|
||||
*/
|
||||
onlyInvariantChars=TRUE;
|
||||
while(length>0) {
|
||||
c=(uint8_t)(*cs++);
|
||||
#if U_CHARSET_FAMILY==U_ASCII_FAMILY
|
||||
*us++=(UChar)(uint8_t)(*cs++);
|
||||
u=(UChar)c;
|
||||
#elif U_CHARSET_FAMILY==U_EBCDIC_FAMILY
|
||||
*us++=(UChar)asciiFromEbcdic[(uint8_t)(*cs++)];
|
||||
u=(UChar)asciiFromEbcdic[c];
|
||||
#else
|
||||
# error U_CHARSET_FAMILY is not valid
|
||||
#endif
|
||||
if(u==0 && c!=0) {
|
||||
onlyInvariantChars=FALSE;
|
||||
}
|
||||
*us++=u;
|
||||
--length;
|
||||
}
|
||||
U_ASSERT(onlyInvariantChars); /* only invariant chars? */
|
||||
}
|
||||
|
||||
U_CAPI void U_EXPORT2
|
||||
u_UCharsToChars(const UChar *us, char *cs, int32_t length) {
|
||||
UChar u;
|
||||
UBool onlyInvariantChars;
|
||||
|
||||
onlyInvariantChars=TRUE;
|
||||
while(length>0) {
|
||||
u=*us++;
|
||||
if(!CHAR_IS_INVARIANT(u)) {
|
||||
onlyInvariantChars=FALSE;
|
||||
u=0;
|
||||
}
|
||||
#if U_CHARSET_FAMILY==U_ASCII_FAMILY
|
||||
*cs++=(char)(*us++);
|
||||
*cs++=(char)u;
|
||||
#elif U_CHARSET_FAMILY==U_EBCDIC_FAMILY
|
||||
*cs++=(char)ebcdicFromAscii[(uint8_t)(*us++)];
|
||||
*cs++=(char)ebcdicFromAscii[u];
|
||||
#else
|
||||
# error U_CHARSET_FAMILY is not valid
|
||||
#endif
|
||||
--length;
|
||||
}
|
||||
U_ASSERT(onlyInvariantChars); /* only invariant chars? */
|
||||
}
|
||||
|
||||
U_CAPI UBool U_EXPORT2
|
||||
uprv_isInvariantString(const char *s, int32_t length) {
|
||||
char c;
|
||||
|
||||
for(;;) {
|
||||
if(length<0) {
|
||||
/* NUL-terminated */
|
||||
c=*s++;
|
||||
if(c==0) {
|
||||
break;
|
||||
}
|
||||
} else {
|
||||
/* count length */
|
||||
if(length==0) {
|
||||
break;
|
||||
}
|
||||
--length;
|
||||
c=*s++;
|
||||
if(c==0) {
|
||||
continue; /* NUL is invariant */
|
||||
}
|
||||
}
|
||||
/* c!=0 now, one branch below checks c==0 for variant characters */
|
||||
|
||||
/*
|
||||
* no assertions here because these functions are legitimately called
|
||||
* for strings with variant characters
|
||||
*/
|
||||
#if U_CHARSET_FAMILY==U_ASCII_FAMILY
|
||||
if(!CHAR_IS_INVARIANT(c)) {
|
||||
return FALSE; /* found a variant char */
|
||||
}
|
||||
#elif U_CHARSET_FAMILY==U_EBCDIC_FAMILY
|
||||
c=(char)asciiFromEbcdic[(uint8_t)c];
|
||||
if(c==0 || !CHAR_IS_INVARIANT(c)) {
|
||||
return FALSE; /* found a variant char */
|
||||
}
|
||||
#else
|
||||
# error U_CHARSET_FAMILY is not valid
|
||||
#endif
|
||||
}
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
U_CAPI UBool U_EXPORT2
|
||||
uprv_isInvariantUString(const UChar *s, int32_t length) {
|
||||
UChar c;
|
||||
|
||||
for(;;) {
|
||||
if(length<0) {
|
||||
/* NUL-terminated */
|
||||
c=*s++;
|
||||
if(c==0) {
|
||||
break;
|
||||
}
|
||||
} else {
|
||||
/* count length */
|
||||
if(length==0) {
|
||||
break;
|
||||
}
|
||||
--length;
|
||||
c=*s++;
|
||||
}
|
||||
|
||||
/*
|
||||
* no assertions here because these functions are legitimately called
|
||||
* for strings with variant characters
|
||||
*/
|
||||
if(!CHAR_IS_INVARIANT(c)) {
|
||||
return FALSE; /* found a variant char */
|
||||
}
|
||||
}
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
/* end of platform-specific implementation */
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue