[5503] | 1 | #ifndef UNITOOL_H
|
---|
| 2 | #define UNITOOL_H
|
---|
| 3 |
|
---|
| 4 | #ifdef __cplusplus
|
---|
| 5 | extern "C" {
|
---|
| 6 | #endif
|
---|
| 7 |
|
---|
| 8 |
|
---|
| 9 | /* This module is based on Unicode 2.1 */
|
---|
| 10 |
|
---|
| 11 |
|
---|
| 12 | /* parse_utf8_char parses the next utf-8 character, placing its
|
---|
| 13 | * unicode equivalent in *value. The length of the utf-8 character
|
---|
| 14 | * is returned. end is the address of the last character. */
|
---|
| 15 | int parse_utf8_char (const unsigned char *here,
|
---|
| 16 | const unsigned char *end,
|
---|
| 17 | unsigned short *value);
|
---|
| 18 |
|
---|
| 19 | /* output_utf8_char encodes a unicode character as a UTF-8 character.
|
---|
| 20 | * The length of the encoding is returned. If the string was not
|
---|
| 21 | * long enough to encode the character 0 is returned. end is the
|
---|
| 22 | * address of the last character */
|
---|
| 23 | int output_utf8_char (unsigned short value,
|
---|
| 24 | unsigned char *here,
|
---|
| 25 | unsigned char *end);
|
---|
| 26 |
|
---|
| 27 | /* decompose_str will decompose a unicode string into its canonical
|
---|
| 28 | * equivalents. NULL is returned if the input array was not
|
---|
| 29 | * large enough to contain the fully decomposed string (the array
|
---|
| 30 | * will be in a correct, but partially decomposed state). The input
|
---|
| 31 | * must be null-terminated. */
|
---|
| 32 | unsigned short *decompose_str (unsigned short *input,
|
---|
| 33 | int max_output_len);
|
---|
| 34 |
|
---|
| 35 | /* tests to see whether 'value' is a valid Unicode letter */
|
---|
| 36 | int is_unicode_letter (unsigned short value);
|
---|
| 37 |
|
---|
| 38 | /* tests to see whether 'value' is a valid Unicode digit */
|
---|
| 39 | int is_unicode_digit (unsigned short value);
|
---|
| 40 |
|
---|
| 41 | /* tests to see whether 'value' is a valid Unicode letter or
|
---|
| 42 | * digit */
|
---|
| 43 | int is_unicode_letdig (unsigned short value);
|
---|
| 44 |
|
---|
| 45 | /* tests to see whether 'value' is a valid space
|
---|
| 46 | * The test includes both "C" spaces and "Unicode" spaces, i.e.
|
---|
| 47 | * form-feed, newline, carriage return, horizontal tab,
|
---|
| 48 | * vertical tab, and the Zs, Zl, and Zp Unicode categorizations */
|
---|
| 49 | int is_unicode_space (unsigned short value);
|
---|
| 50 |
|
---|
| 51 | /* returns the length of the unicode string */
|
---|
| 52 | int unicode_strlen (const unsigned short *str);
|
---|
| 53 |
|
---|
| 54 | /* returns the length of the unicode string, up to a maximum */
|
---|
| 55 | int unicode_strnlen (const unsigned short *str, int max_length);
|
---|
| 56 |
|
---|
| 57 | /* returns the upper-case equivalent of value */
|
---|
| 58 | unsigned short unicode_toupper (unsigned short value);
|
---|
| 59 |
|
---|
| 60 | /* returns the lower-case equivalent of value */
|
---|
| 61 | unsigned short unicode_tolower (unsigned short value);
|
---|
| 62 |
|
---|
| 63 | /* returns the simplified Chinese character equivalent of
|
---|
| 64 | * another Chinese character */
|
---|
| 65 | unsigned short unicode_tosimplified (unsigned short value);
|
---|
| 66 |
|
---|
| 67 |
|
---|
| 68 | /* converts a utf-8 word (string with length stored in the first byte
|
---|
| 69 | * to a Unicode array. To handle all situations the output buffer should
|
---|
| 70 | * be 256 unsigned shorts long. The output will also have the length as
|
---|
| 71 | * the first entry. */
|
---|
| 72 | unsigned short *utf8_word_to_unicode (const unsigned char *input,
|
---|
| 73 | unsigned short *output,
|
---|
| 74 | int max_output_length);
|
---|
| 75 |
|
---|
| 76 | /* converts a unicode word buffer (with the length stored in the
|
---|
| 77 | * entry) to a utf8 encoded word output (with the length stored in
|
---|
| 78 | * the first byte. Only 255 bytes (not characters) can be stored
|
---|
| 79 | * in the output. */
|
---|
| 80 | unsigned char *unicode_to_utf8_word (const unsigned short *input,
|
---|
| 81 | unsigned char *output,
|
---|
| 82 | int max_output_length);
|
---|
| 83 |
|
---|
| 84 | #ifdef __cplusplus
|
---|
| 85 | }
|
---|
| 86 | #endif
|
---|
| 87 |
|
---|
| 88 | #endif
|
---|