9 * UTF-8 utility functions
11 * (c) 2010-2016 Steve Bennett <steveb@workware.net.au>
13 * See LICENCE for licence details.
19 /* No utf-8 support. 1 byte = 1 char */
20 #define utf8_strlen(S, B) ((B) < 0 ? (int)strlen(S) : (B))
21 #define utf8_strwidth(S, B) utf8_strlen((S), (B))
22 #define utf8_tounicode(S, CP) (*(CP) = (unsigned char)*(S), 1)
23 #define utf8_index(C, I) (I)
24 #define utf8_charlen(C) 1
25 #define utf8_width(C) 1
29 * Converts the given unicode codepoint (0 - 0x1fffff) to utf-8
30 * and stores the result at 'p'.
32 * Returns the number of utf-8 characters
34 int utf8_fromunicode(char *p, unsigned uc);
37 * Returns the length of the utf-8 sequence starting with 'c'.
39 * Returns 1-4, or -1 if this is not a valid start byte.
41 * Note that charlen=4 is not supported by the rest of the API.
43 int utf8_charlen(int c);
46 * Returns the number of characters in the utf-8
47 * string of the given byte length.
49 * Any bytes which are not part of an valid utf-8
50 * sequence are treated as individual characters.
52 * The string *must* be null terminated.
54 * Does not support unicode code points > \u1fffff
56 int utf8_strlen(const char *str, int bytelen);
59 * Calculates the display width of the first 'charlen' characters in 'str'.
62 int utf8_strwidth(const char *str, int charlen);
65 * Returns the byte index of the given character in the utf-8 string.
67 * The string *must* be null terminated.
69 * This will return the byte length of a utf-8 string
70 * if given the char length.
72 int utf8_index(const char *str, int charindex);
75 * Returns the unicode codepoint corresponding to the
76 * utf-8 sequence 'str'.
78 * Stores the result in *uc and returns the number of bytes
81 * If 'str' is null terminated, then an invalid utf-8 sequence
82 * at the end of the string will be returned as individual bytes.
84 * If it is not null terminated, the length *must* be checked first.
86 * Does not support unicode code points > \u1fffff
88 int utf8_tounicode(const char *str, int *uc);
91 * Returns the width (in characters) of the given unicode codepoint.
92 * This is 1 for normal letters and 0 for combining characters and 2 for wide characters.
94 int utf8_width(int ch);