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 /**
  13  * Converts the given unicode codepoint (0 - 0xffff) to utf-8
  14  * and stores the result at 'p'.
  15  *
  16  * Returns the number of utf-8 characters (1-3).
  17  */
  18 int utf8_fromunicode(char *p, unsigned short uc);
  19
  20 #ifndef JIM_UTF8
  21 #include <ctype.h>
  22
  23 /* No utf-8 support. 1 byte = 1 char */
  24 #define utf8_strlen(S, B) (B) < 0 ? strlen(S) : (B)
  25 #define utf8_tounicode(S, CP) (*(CP) = *(S), 1)
  26 #define utf8_upper(C) toupper(C)
  27 #define utf8_lower(C) tolower(C)
  28 #define utf8_index(C, I) (I)
  29 #define utf8_charlen(C) 1
  30 #define utf8_prev_len(S, L) 1
  31
  32 #else
  33 /**
  34  * Returns the length of the utf-8 sequence starting with 'c'.
  35  *
  36  * Returns 1-4, or -1 if this is not a valid start byte.
  37  *
  38  * Note that charlen=4 is not supported by the rest of the API.
  39  */
  40 int utf8_charlen(int c);
  41
  42 /**
  43  * Returns the number of characters in the utf-8
  44  * string of the given byte length.
  45  *
  46  * Any bytes which are not part of an valid utf-8
  47  * sequence are treated as individual characters.
  48  *
  49  * The string *must* be null terminated.
  50  *
  51  * Does not support unicode code points > \uffff
  52  */
  53 int utf8_strlen(const char *str, int bytelen);
  54
  55 /**
  56  * Returns the byte index of the given character in the utf-8 string.
  57  *
  58  * The string *must* be null terminated.
  59  *
  60  * This will return the byte length of a utf-8 string
  61  * if given the char length.
  62  */
  63 int utf8_index(const char *str, int charindex);
  64
  65 /**
  66  * Returns the unicode codepoint corresponding to the
  67  * utf-8 sequence 'str'.
  68  *
  69  * Stores the result in *uc and returns the number of bytes
  70  * consumed.
  71  *
  72  * If 'str' is null terminated, then an invalid utf-8 sequence
  73  * at the end of the string will be returned as individual bytes.
  74  *
  75  * If it is not null terminated, the length *must* be checked first.
  76  *
  77  * Does not support unicode code points > \uffff
  78  */
  79 int utf8_tounicode(const char *str, int *uc);
  80
  81 /**
  82  * Returns the number of bytes before 'str' that the previous
  83  * utf-8 character sequence starts (which may be the middle of a sequence).
  84  *
  85  * Looks back at most 'len' bytes backwards, which must be > 0.
  86  * If no start char is found, returns -len
  87  */
  88 int utf8_prev_len(const char *str, int len);
  89
  90 /**
  91  * Returns the upper-case variant of the given unicode codepoint.
  92  *
  93  * Does not support unicode code points > \uffff
  94  */
  95 int utf8_upper(int uc);
  96
  97 /**
  98  * Returns the lower-case variant of the given unicode codepoint.
  99  *
 100  * NOTE: Use utf8_upper() in preference for case-insensitive matching.
 101  *
 102  * Does not support unicode code points > \uffff
 103  */
 104 int utf8_lower(int uc);
 105
 106 #endif
 107
 108 #endif