utf8.h

   1 #ifndef UTF8_UTIL_H
   2 #define UTF8_UTIL_H
   3
   4 #ifdef __cplusplus
   5 extern "C" {
   6 #endif
   7
   8 /**
   9  * UTF-8 utility functions
  10  *
  11  * (c) 2010 Steve Bennett <steveb@workware.net.au>
  12  *
  13  * See LICENCE for licence details.
  14  */
  15 #include <jim-config.h>
  16
  17 /* Currently we support unicode points up to 2^22-1 */
  18 #define MAX_UTF8_LEN 4
  19
  20 /**
  21  * Converts the given unicode codepoint (0 - 0x1fffff) to utf-8
  22  * and stores the result at 'p'.
  23  *
  24  * Returns the number of utf-8 characters (up to MAX_UTF8_LEN).
  25  */
  26 int utf8_fromunicode(char *p, unsigned uc);
  27
  28 #ifndef JIM_UTF8
  29 #include <ctype.h>
  30
  31 /* No utf-8 support. 1 byte = 1 char */
  32 #define utf8_strlen(S, B) ((B) < 0 ? strlen(S) : (B))
  33 #define utf8_tounicode(S, CP) (*(CP) = (unsigned char)*(S), 1)
  34 #define utf8_getchars(CP, C) (*(CP) = (C), 1)
  35 #define utf8_upper(C) toupper(C)
  36 #define utf8_title(C) toupper(C)
  37 #define utf8_lower(C) tolower(C)
  38 #define utf8_index(C, I) (I)
  39 #define utf8_charlen(C) 1
  40 #define utf8_prev_len(S, L) 1
  41
  42 #else
  43 #if !defined(JIM_BOOTSTRAP)
  44
  45 #define utf8_getchars utf8_fromunicode
  46
  47 /**
  48  * Returns the length of the utf-8 sequence starting with 'c'.
  49  *
  50  * Returns 1-4, or -1 if this is not a valid start byte.
  51  *
  52  * Note that charlen=4 is not supported by the rest of the API.
  53  */
  54 int utf8_charlen(int c);
  55
  56 /**
  57  * Returns the number of characters in the utf-8
  58  * string of the given byte length.
  59  *
  60  * Any bytes which are not part of an valid utf-8
  61  * sequence are treated as individual characters.
  62  *
  63  * The string *must* be null terminated.
  64  *
  65  * Does not support unicode code points > \u1fffff
  66  */
  67 int utf8_strlen(const char *str, int bytelen);
  68
  69 /**
  70  * Returns the byte index of the given character in the utf-8 string.
  71  *
  72  * The string *must* be null terminated.
  73  *
  74  * This will return the byte length of a utf-8 string
  75  * if given the char length.
  76  */
  77 int utf8_index(const char *str, int charindex);
  78
  79 /**
  80  * Returns the unicode codepoint corresponding to the
  81  * utf-8 sequence 'str'.
  82  *
  83  * Stores the result in *uc and returns the number of bytes
  84  * consumed.
  85  *
  86  * If 'str' is null terminated, then an invalid utf-8 sequence
  87  * at the end of the string will be returned as individual bytes.
  88  *
  89  * If it is not null terminated, the length *must* be checked first.
  90  *
  91  * Does not support unicode code points > \u1fffff
  92  */
  93 int utf8_tounicode(const char *str, int *uc);
  94
  95 /**
  96  * Returns the number of bytes before 'str' that the previous
  97  * utf-8 character sequence starts (which may be the middle of a sequence).
  98  *
  99  * Looks back at most 'len' bytes backwards, which must be > 0.
 100  * If no start char is found, returns -len
 101  */
 102 int utf8_prev_len(const char *str, int len);
 103
 104 /**
 105  * Returns the upper-case variant of the given unicode codepoint.
 106  *
 107  * Unicode code points > \uffff are returned unchanged.
 108  */
 109 int utf8_upper(int uc);
 110
 111 /**
 112  * Returns the title-case variant of the given unicode codepoint.
 113  *
 114  * If none, returns utf8_upper().
 115  *
 116  * Unicode code points > \uffff are returned unchanged.
 117  */
 118 int utf8_title(int uc);
 119
 120 /**
 121  * Returns the lower-case variant of the given unicode codepoint.
 122  *
 123  * NOTE: Use utf8_upper() in preference for case-insensitive matching.
 124  *
 125  * Unicode code points > \uffff are returned unchanged.
 126  */
 127 int utf8_lower(int uc);
 128 #endif /* JIM_BOOTSTRAP */
 129
 130 #endif
 131
 132 #ifdef __cplusplus
 133 }
 134 #endif
 135
 136 #endif