release/src/router/usbmodeswitch/jim/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) = (unsigned char)*(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 #if !defined(JIM_BOOTSTRAP)
  34 /**
  35  * Returns the length of the utf-8 sequence starting with 'c'.
  36  *
  37  * Returns 1-4, or -1 if this is not a valid start byte.
  38  *
  39  * Note that charlen=4 is not supported by the rest of the API.
  40  */
  41 int utf8_charlen(int c);
  42
  43 /**
  44  * Returns the number of characters in the utf-8
  45  * string of the given byte length.
  46  *
  47  * Any bytes which are not part of an valid utf-8
  48  * sequence are treated as individual characters.
  49  *
  50  * The string *must* be null terminated.
  51  *
  52  * Does not support unicode code points > \uffff
  53  */
  54 int utf8_strlen(const char *str, int bytelen);
  55
  56 /**
  57  * Returns the byte index of the given character in the utf-8 string.
  58  *
  59  * The string *must* be null terminated.
  60  *
  61  * This will return the byte length of a utf-8 string
  62  * if given the char length.
  63  */
  64 int utf8_index(const char *str, int charindex);
  65
  66 /**
  67  * Returns the unicode codepoint corresponding to the
  68  * utf-8 sequence 'str'.
  69  *
  70  * Stores the result in *uc and returns the number of bytes
  71  * consumed.
  72  *
  73  * If 'str' is null terminated, then an invalid utf-8 sequence
  74  * at the end of the string will be returned as individual bytes.
  75  *
  76  * If it is not null terminated, the length *must* be checked first.
  77  *
  78  * Does not support unicode code points > \uffff
  79  */
  80 int utf8_tounicode(const char *str, int *uc);
  81
  82 /**
  83  * Returns the number of bytes before 'str' that the previous
  84  * utf-8 character sequence starts (which may be the middle of a sequence).
  85  *
  86  * Looks back at most 'len' bytes backwards, which must be > 0.
  87  * If no start char is found, returns -len
  88  */
  89 int utf8_prev_len(const char *str, int len);
  90
  91 /**
  92  * Returns the upper-case variant of the given unicode codepoint.
  93  *
  94  * Does not support unicode code points > \uffff
  95  */
  96 int utf8_upper(int uc);
  97
  98 /**
  99  * Returns the lower-case variant of the given unicode codepoint.
 100  *
 101  * NOTE: Use utf8_upper() in preference for case-insensitive matching.
 102  *
 103  * Does not support unicode code points > \uffff
 104  */
 105 int utf8_lower(int uc);
 106 #endif /* JIM_BOOTSTRAP */
 107
 108 #endif
 109
 110 #endif