utf8.h

   1 #ifndef UTF8_UTIL_H
   2 #define UTF8_UTIL_H
   3 /**
   4  * UTF-8 utility functions
   5  *
   6  * (c) 2010 Steve Bennett <steveb@workware.net.au>
   7  *
   8  * See LICENCE for licence details.
   9  */
  10 #include <jim-config.h>
  11
  12 /* Currently we support unicode points up to 2^22-1 */
  13 #define MAX_UTF8_LEN 4
  14
  15 /**
  16  * Converts the given unicode codepoint (0 - 0x1fffff) to utf-8
  17  * and stores the result at 'p'.
  18  *
  19  * Returns the number of utf-8 characters (up to MAX_UTF8_LEN).
  20  */
  21 int utf8_fromunicode(char *p, unsigned uc);
  22
  23 #ifndef JIM_UTF8
  24 #include <ctype.h>
  25
  26 /* No utf-8 support. 1 byte = 1 char */
  27 #define utf8_strlen(S, B) ((B) < 0 ? strlen(S) : (B))
  28 #define utf8_tounicode(S, CP) (*(CP) = (unsigned char)*(S), 1)
  29 #define utf8_getchars(CP, C) (*(CP) = (C), 1)
  30 #define utf8_upper(C) toupper(C)
  31 #define utf8_title(C) toupper(C)
  32 #define utf8_lower(C) tolower(C)
  33 #define utf8_index(C, I) (I)
  34 #define utf8_charlen(C) 1
  35 #define utf8_prev_len(S, L) 1
  36
  37 #else
  38 #if !defined(JIM_BOOTSTRAP)
  39
  40 #define utf8_getchars utf8_fromunicode
  41
  42 /**
  43  * Returns the length of the utf-8 sequence starting with 'c'.
  44  *
  45  * Returns 1-4, or -1 if this is not a valid start byte.
  46  *
  47  * Note that charlen=4 is not supported by the rest of the API.
  48  */
  49 int utf8_charlen(int c);
  50
  51 /**
  52  * Returns the number of characters in the utf-8
  53  * string of the given byte length.
  54  *
  55  * Any bytes which are not part of an valid utf-8
  56  * sequence are treated as individual characters.
  57  *
  58  * The string *must* be null terminated.
  59  *
  60  * Does not support unicode code points > \u1fffff
  61  */
  62 int utf8_strlen(const char *str, int bytelen);
  63
  64 /**
  65  * Returns the byte index of the given character in the utf-8 string.
  66  *
  67  * The string *must* be null terminated.
  68  *
  69  * This will return the byte length of a utf-8 string
  70  * if given the char length.
  71  */
  72 int utf8_index(const char *str, int charindex);
  73
  74 /**
  75  * Returns the unicode codepoint corresponding to the
  76  * utf-8 sequence 'str'.
  77  *
  78  * Stores the result in *uc and returns the number of bytes
  79  * consumed.
  80  *
  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.
  83  *
  84  * If it is not null terminated, the length *must* be checked first.
  85  *
  86  * Does not support unicode code points > \u1fffff
  87  */
  88 int utf8_tounicode(const char *str, int *uc);
  89
  90 /**
  91  * Returns the number of bytes before 'str' that the previous
  92  * utf-8 character sequence starts (which may be the middle of a sequence).
  93  *
  94  * Looks back at most 'len' bytes backwards, which must be > 0.
  95  * If no start char is found, returns -len
  96  */
  97 int utf8_prev_len(const char *str, int len);
  98
  99 /**
 100  * Returns the upper-case variant of the given unicode codepoint.
 101  *
 102  * Unicode code points > \uffff are returned unchanged.
 103  */
 104 int utf8_upper(int uc);
 105
 106 /**
 107  * Returns the title-case variant of the given unicode codepoint.
 108  *
 109  * If none, returns utf8_upper().
 110  *
 111  * Unicode code points > \uffff are returned unchanged.
 112  */
 113 int utf8_title(int uc);
 114
 115 /**
 116  * Returns the lower-case variant of the given unicode codepoint.
 117  *
 118  * NOTE: Use utf8_upper() in preference for case-insensitive matching.
 119  *
 120  * Unicode code points > \uffff are returned unchanged.
 121  */
 122 int utf8_lower(int uc);
 123 #endif /* JIM_BOOTSTRAP */
 124
 125 #endif
 126
 127 #endif