1 | /**********************************************************************
|
---|
2 | *
|
---|
3 | * unitool.h -- Unicode support.
|
---|
4 | * Copyright (C) 1999 The New Zealand Digital Library Project
|
---|
5 | *
|
---|
6 | * A component of the Greenstone digital library software
|
---|
7 | * from the New Zealand Digital Library Project at the
|
---|
8 | * University of Waikato, New Zealand.
|
---|
9 | *
|
---|
10 | * This program is free software; you can redistribute it and/or modify
|
---|
11 | * it under the terms of the GNU General Public License as published by
|
---|
12 | * the Free Software Foundation; either version 2 of the License, or
|
---|
13 | * (at your option) any later version.
|
---|
14 | *
|
---|
15 | * This program is distributed in the hope that it will be useful,
|
---|
16 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
17 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
18 | * GNU General Public License for more details.
|
---|
19 | *
|
---|
20 | * You should have received a copy of the GNU General Public License
|
---|
21 | * along with this program; if not, write to the Free Software
|
---|
22 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
23 | *
|
---|
24 | *********************************************************************/
|
---|
25 |
|
---|
26 | #ifndef UNITOOL_H
|
---|
27 | #define UNITOOL_H
|
---|
28 |
|
---|
29 | /* This module is based on Unicode 2.1 */
|
---|
30 |
|
---|
31 |
|
---|
32 | /* parse_utf8_char parses the next utf-8 character, placing its
|
---|
33 | * unicode equivalent in *value. The length of the utf-8 character
|
---|
34 | * is returned. end is the address of the last character. */
|
---|
35 | int parse_utf8_char (const unsigned char *here,
|
---|
36 | const unsigned char *end,
|
---|
37 | unsigned short *value);
|
---|
38 |
|
---|
39 | /* output_utf8_char encodes a unicode character as a UTF-8 character.
|
---|
40 | * The length of the encoding is returned. If the string was not
|
---|
41 | * long enough to encode the character 0 is returned. end is the
|
---|
42 | * address of the last character */
|
---|
43 | int output_utf8_char (unsigned short value,
|
---|
44 | unsigned char *here,
|
---|
45 | unsigned char *end);
|
---|
46 |
|
---|
47 | /* decompose_str will decompose a unicode string into its canonical
|
---|
48 | * equivalents. NULL is returned if the input array was not
|
---|
49 | * large enough to contain the fully decomposed string (the array
|
---|
50 | * will be in a correct, but partially decomposed state). The input
|
---|
51 | * must be null-terminated. */
|
---|
52 | unsigned short *decompose_str (unsigned short *input,
|
---|
53 | int max_output_len);
|
---|
54 |
|
---|
55 | /* tests to see whether 'value' is a valid Unicode letter */
|
---|
56 | int is_unicode_letter (unsigned short value);
|
---|
57 |
|
---|
58 | /* tests to see whether 'value' is a valid Unicode digit */
|
---|
59 | int is_unicode_digit (unsigned short value);
|
---|
60 |
|
---|
61 | /* tests to see whether 'value' is a valid Unicode letter or
|
---|
62 | * digit */
|
---|
63 | int is_unicode_letdig (unsigned short value);
|
---|
64 |
|
---|
65 | /* tests to see whether 'value' is a valid space
|
---|
66 | * The test includes both "C" spaces and "Unicode" spaces, i.e.
|
---|
67 | * form-feed, newline, carriage return, horizontal tab,
|
---|
68 | * vertical tab, and the Zs, Zl, and Zp Unicode categorizations */
|
---|
69 | int is_unicode_space (unsigned short value);
|
---|
70 |
|
---|
71 | /* returns the length of the unicode string */
|
---|
72 | int unicode_strlen (const unsigned short *str);
|
---|
73 |
|
---|
74 | /* returns the length of the unicode string, up to a maximum */
|
---|
75 | int unicode_strnlen (const unsigned short *str, int max_length);
|
---|
76 |
|
---|
77 | /* returns the upper-case equivalent of value */
|
---|
78 | unsigned short unicode_toupper (unsigned short value);
|
---|
79 |
|
---|
80 | /* returns the lower-case equivalent of value */
|
---|
81 | unsigned short unicode_tolower (unsigned short value);
|
---|
82 |
|
---|
83 | /* returns the simplified Chinese character equivalent of
|
---|
84 | * another Chinese character */
|
---|
85 | unsigned short unicode_tosimplified (unsigned short value);
|
---|
86 |
|
---|
87 |
|
---|
88 | /* converts a utf-8 word (string with length stored in the first byte
|
---|
89 | * to a Unicode array. To handle all situations the output buffer should
|
---|
90 | * be 256 unsigned shorts long. The output will also have the length as
|
---|
91 | * the first entry. */
|
---|
92 | unsigned short *utf8_word_to_unicode (const unsigned char *input,
|
---|
93 | unsigned short *output,
|
---|
94 | int max_output_length);
|
---|
95 |
|
---|
96 | /* converts a unicode word buffer (with the length stored in the
|
---|
97 | * entry) to a utf8 encoded word output (with the length stored in
|
---|
98 | * the first byte. Only 255 bytes (not characters) can be stored
|
---|
99 | * in the output. */
|
---|
100 | unsigned char *unicode_to_utf8_word (const unsigned short *input,
|
---|
101 | unsigned char *output,
|
---|
102 | int max_output_length);
|
---|
103 |
|
---|
104 |
|
---|
105 | #endif
|
---|