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_upper(C) toupper(C)
  30 #define utf8_title(C) toupper(C)
  31 #define utf8_lower(C) tolower(C)
  32 #define utf8_index(C, I) (I)
  33 #define utf8_charlen(C) 1
  34 #define utf8_prev_len(S, L) 1
  35
  36 #else
  37 #if !defined(JIM_BOOTSTRAP)
  38 /**
  39  * Returns the length of the utf-8 sequence starting with 'c'.
  40  *
  41  * Returns 1-4, or -1 if this is not a valid start byte.
  42  *
  43  * Note that charlen=4 is not supported by the rest of the API.
  44  */
  45 int utf8_charlen(int c);
  46
  47 /**
  48  * Returns the number of characters in the utf-8
  49  * string of the given byte length.
  50  *
  51  * Any bytes which are not part of an valid utf-8
  52  * sequence are treated as individual characters.
  53  *
  54  * The string *must* be null terminated.
  55  *
  56  * Does not support unicode code points > \u1fffff
  57  */
  58 int utf8_strlen(const char *str, int bytelen);
  59
  60 /**
  61  * Returns the byte index of the given character in the utf-8 string.
  62  *
  63  * The string *must* be null terminated.
  64  *
  65  * This will return the byte length of a utf-8 string
  66  * if given the char length.
  67  */
  68 int utf8_index(const char *str, int charindex);
  69
  70 /**
  71  * Returns the unicode codepoint corresponding to the
  72  * utf-8 sequence 'str'.
  73  *
  74  * Stores the result in *uc and returns the number of bytes
  75  * consumed.
  76  *
  77  * If 'str' is null terminated, then an invalid utf-8 sequence
  78  * at the end of the string will be returned as individual bytes.
  79  *
  80  * If it is not null terminated, the length *must* be checked first.
  81  *
  82  * Does not support unicode code points > \u1fffff
  83  */
  84 int utf8_tounicode(const char *str, int *uc);
  85
  86 /**
  87  * Returns the number of bytes before 'str' that the previous
  88  * utf-8 character sequence starts (which may be the middle of a sequence).
  89  *
  90  * Looks back at most 'len' bytes backwards, which must be > 0.
  91  * If no start char is found, returns -len
  92  */
  93 int utf8_prev_len(const char *str, int len);
  94
  95 /**
  96  * Returns the upper-case variant of the given unicode codepoint.
  97  *
  98  * Unicode code points > \uffff are returned unchanged.
  99  */
 100 int utf8_upper(int uc);
 101
 102 /**
 103  * Returns the title-case variant of the given unicode codepoint.
 104  *
 105  * If none, returns utf8_upper().
 106  *
 107  * Unicode code points > \uffff are returned unchanged.
 108  */
 109 int utf8_title(int uc);
 110
 111 /**
 112  * Returns the lower-case variant of the given unicode codepoint.
 113  *
 114  * NOTE: Use utf8_upper() in preference for case-insensitive matching.
 115  *
 116  * Unicode code points > \uffff are returned unchanged.
 117  */
 118 int utf8_lower(int uc);
 119 #endif /* JIM_BOOTSTRAP */
 120
 121 #endif
 122
 123 #endif