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