#include <stdlib.h>
#include <string.h>
#include "stringprep.h"
#include "gunidecomp.h"
#include "gunicomp.h"
Go to the source code of this file.
Defines |
| #define | gboolean int |
| #define | gchar char |
| #define | guchar unsigned char |
| #define | glong long |
| #define | gint int |
| #define | guint unsigned int |
| #define | gushort unsigned short |
| #define | gint16 int16_t |
| #define | guint16 uint16_t |
| #define | gunichar uint32_t |
| #define | gsize size_t |
| #define | gssize ssize_t |
| #define | g_malloc malloc |
| #define | g_free free |
| #define | g_return_val_if_fail(expr, val) |
| #define | FALSE (0) |
| #define | TRUE (!FALSE) |
| #define | G_N_ELEMENTS(arr) (sizeof (arr) / sizeof ((arr)[0])) |
| #define | G_UNLIKELY(expr) (expr) |
| #define | g_utf8_next_char(p) ((p) + g_utf8_skip[*(const guchar *)(p)]) |
| #define | UTF8_COMPUTE(Char, Mask, Len) |
| #define | UTF8_LENGTH(Char) |
| #define | UTF8_GET(Result, Chars, Count, Mask, Len) |
| #define | CC_PART1(Page, Char) |
| #define | CC_PART2(Page, Char) |
| #define | COMBINING_CLASS(Char) |
| #define | SBase 0xAC00 |
| #define | LBase 0x1100 |
| #define | VBase 0x1161 |
| #define | TBase 0x11A7 |
| #define | LCount 19 |
| #define | VCount 21 |
| #define | TCount 28 |
| #define | NCount (VCount * TCount) |
| #define | SCount (LCount * NCount) |
| #define | CI(Page, Char) |
| #define | COMPOSE_INDEX(Char) (((Char >> 8) > (COMPOSE_TABLE_LAST)) ? 0 : CI((Char) >> 8, (Char) & 0xff)) |
Enumerations |
| enum | GNormalizeMode {
G_NORMALIZE_DEFAULT,
G_NORMALIZE_NFD = G_NORMALIZE_DEFAULT,
G_NORMALIZE_DEFAULT_COMPOSE,
G_NORMALIZE_NFC = G_NORMALIZE_DEFAULT_COMPOSE,
G_NORMALIZE_ALL,
G_NORMALIZE_NFKD = G_NORMALIZE_ALL,
G_NORMALIZE_ALL_COMPOSE,
G_NORMALIZE_NFKC = G_NORMALIZE_ALL_COMPOSE
} |
Functions |
| uint32_t | stringprep_utf8_to_unichar (const char *p) |
| int | stringprep_unichar_to_utf8 (uint32_t c, char *outbuf) |
| uint32_t * | stringprep_utf8_to_ucs4 (const char *str, ssize_t len, size_t *items_written) |
| char * | stringprep_ucs4_to_utf8 (const uint32_t *str, ssize_t len, size_t *items_read, size_t *items_written) |
| char * | stringprep_utf8_nfkc_normalize (const char *str, ssize_t len) |
| uint32_t * | stringprep_ucs4_nfkc_normalize (const uint32_t *str, ssize_t len) |
Variables |
| const gchar *const | g_utf8_skip = utf8_skip_data |
Define Documentation
Value:
Definition at line 554 of file nfkc.c.
Value:
Definition at line 559 of file nfkc.c.
| #define CI |
( |
|
Page, |
|
|
|
Char |
|
) |
| |
Value:
Definition at line 723 of file nfkc.c.
Value:
Definition at line 564 of file nfkc.c.
| #define G_N_ELEMENTS |
( |
|
arr | ) |
(sizeof (arr) / sizeof ((arr)[0])) |
Value:{ \
if (!(expr)) \
return (val); \
}
Definition at line 54 of file nfkc.c.
| #define guint unsigned int |
| #define UTF8_GET |
( |
|
Result, |
|
|
|
Chars, |
|
|
|
Count, |
|
|
|
Mask, |
|
|
|
Len |
|
) |
| |
Value:(Result) = (Chars)[0] & (Mask); \
for ((Count) = 1; (Count) < (Len); ++(Count)) \
{ \
if (((Chars)[(Count)] & 0xc0) != 0x80) \
{ \
(Result) = -1; \
break; \
} \
(Result) <<= 6; \
(Result) |= ((Chars)[(Count)] & 0x3f); \
}
Definition at line 194 of file nfkc.c.
Value:((Char) < 0x80 ? 1 : \
((Char) < 0x800 ? 2 : \
((Char) < 0x10000 ? 3 : \
((Char) < 0x200000 ? 4 : \
((Char) < 0x4000000 ? 5 : 6)))))
Definition at line 187 of file nfkc.c.
Enumeration Type Documentation
- Enumerator:
| G_NORMALIZE_DEFAULT |
|
| G_NORMALIZE_NFD |
|
| G_NORMALIZE_DEFAULT_COMPOSE |
|
| G_NORMALIZE_NFC |
|
| G_NORMALIZE_ALL |
|
| G_NORMALIZE_NFKD |
|
| G_NORMALIZE_ALL_COMPOSE |
|
| G_NORMALIZE_NFKC |
|
Definition at line 115 of file nfkc.c.
Function Documentation
stringprep_ucs4_nfkc_normalize:
- Parameters:
-
| str | a Unicode string. |
| len | length of array, or -1 if is nul-terminated. |
Converts a UCS4 string into canonical form, see stringprep_utf8_nfkc_normalize() for more information.
Return value: a newly allocated Unicode string, that is the NFKC normalized form of .
Definition at line 1091 of file nfkc.c.
stringprep_ucs4_to_utf8:
- Parameters:
-
| str | a UCS-4 encoded string |
| len | the maximum length of to use. If < 0, then the string is terminated with a 0 character. |
| items_read | location to store number of characters read read, or NULL. |
| items_written | location to store number of bytes written or NULL. The value here stored does not include the trailing 0 byte. |
Convert a string from a 32-bit fixed width representation as UCS-4. to UTF-8. The result will be terminated with a 0 byte.
Return value: a pointer to a newly allocated UTF-8 string. This value must be deallocated by the caller. If an error occurs, NULL will be returned.
Definition at line 1044 of file nfkc.c.
stringprep_unichar_to_utf8:
- Parameters:
-
| c | a ISO10646 character code |
| outbuf | output buffer, must have at least 6 bytes of space. If NULL, the length will be computed and returned and nothing will be written to . |
Converts a single character to UTF-8.
Return value: number of bytes written.
Definition at line 1000 of file nfkc.c.
stringprep_utf8_nfkc_normalize:
- Parameters:
-
| str | a UTF-8 encoded string. |
| len | length of , in bytes, or -1 if is nul-terminated. |
Converts a string into canonical form, standardizing such issues as whether a character with an accent is represented as a base character and combining accent or as a single precomposed character.
The normalization mode is NFKC (ALL COMPOSE). It standardizes differences that do not affect the text content, such as the above-mentioned accent representation. It standardizes the "compatibility" characters in Unicode, such as SUPERSCRIPT THREE to the standard forms (in this case DIGIT THREE). Formatting information may be lost but for most text operations such characters should be considered the same. It returns a result with composed forms rather than a maximally decomposed form.
Return value: a newly allocated string, that is the NFKC normalized form of .
Definition at line 1074 of file nfkc.c.
stringprep_utf8_to_ucs4:
- Parameters:
-
| str | a UTF-8 encoded string |
| len | the maximum length of to use. If < 0, then the string is nul-terminated. |
| items_written | location to store the number of characters in the result, or NULL. |
Convert a string from UTF-8 to a 32-bit fixed width representation as UCS-4, assuming valid UTF-8 input. This function does no error checking on the input.
Return value: a pointer to a newly allocated UCS-4 string. This value must be deallocated by the caller.
Definition at line 1021 of file nfkc.c.
stringprep_utf8_to_unichar:
- Parameters:
-
| p | a pointer to Unicode character encoded as UTF-8 |
Converts a sequence of bytes encoded as UTF-8 to a Unicode character. If does not point to a valid UTF-8 encoded character, results are undefined.
Return value: the resulting character.
Definition at line 983 of file nfkc.c.
Variable Documentation
