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) 2010-2016 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 ? (int)strlen(S) : (B))
  33 #define utf8_strwidth(S, B) utf8_strlen((S), (B))
  34 #define utf8_tounicode(S, CP) (*(CP) = (unsigned char)*(S), 1)
  35 #define utf8_getchars(CP, C) (*(CP) = (C), 1)
  36 #define utf8_upper(C) toupper(C)
  37 #define utf8_title(C) toupper(C)
  38 #define utf8_lower(C) tolower(C)
  39 #define utf8_index(C, I) (I)
  40 #define utf8_charlen(C) 1
  41 #define utf8_prev_len(S, L) 1
  42 #define utf8_width(C) 1
  43
  44 #else
  45 #if !defined(JIM_BOOTSTRAP)
  46
  47 #define utf8_getchars utf8_fromunicode
  48
  49 /**
  50  * Returns the length of the utf-8 sequence starting with 'c'.
  51  *
  52  * Returns 1-4.
  53  * If 'c' is not a valid start byte, returns 1.
  54  */
  55 int utf8_charlen(int c);
  56
  57 /**
  58  * Returns the number of characters in the utf-8
  59  * string of the given byte length.
  60  *
  61  * Any bytes which are not part of an valid utf-8
  62  * sequence are treated as individual characters.
  63  *
  64  * The string *must* be null terminated.
  65  *
  66  * Does not support unicode code points > \u1fffff
  67  */
  68 int utf8_strlen(const char *str, int bytelen);
  69
  70 /**
  71  * Calculates the display width of the first 'charlen' characters in 'str'.
  72  * See utf8_width()
  73  */
  74 int utf8_strwidth(const char *str, int charlen);
  75
  76 /**
  77  * Returns the byte index of the given character in the utf-8 string.
  78  *
  79  * The string *must* be null terminated.
  80  *
  81  * This will return the byte length of a utf-8 string
  82  * if given the char length.
  83  */
  84 int utf8_index(const char *str, int charindex);
  85
  86 /**
  87  * Returns the unicode codepoint corresponding to the
  88  * utf-8 sequence 'str'.
  89  *
  90  * Stores the result in *uc and returns the number of bytes
  91  * consumed.
  92  *
  93  * If 'str' is null terminated, then an invalid utf-8 sequence
  94  * at the end of the string will be returned as individual bytes.
  95  *
  96  * If it is not null terminated, the length *must* be checked first.
  97  *
  98  * Does not support unicode code points > \u1fffff
  99  */
 100 int utf8_tounicode(const char *str, int *uc);
 101
 102 /**
 103  * Returns the number of bytes before 'str' that the previous
 104  * utf-8 character sequence starts (which may be the middle of a sequence).
 105  *
 106  * Looks back at most 'len' bytes backwards, which must be > 0.
 107  * If no start char is found, returns -len
 108  */
 109 int utf8_prev_len(const char *str, int len);
 110
 111 /**
 112  * Returns the upper-case variant of the given unicode codepoint.
 113  *
 114  * Unicode code points > \uffff are returned unchanged.
 115  */
 116 int utf8_upper(int uc);
 117
 118 /**
 119  * Returns the title-case variant of the given unicode codepoint.
 120  *
 121  * If none, returns utf8_upper().
 122  *
 123  * Unicode code points > \uffff are returned unchanged.
 124  */
 125 int utf8_title(int uc);
 126
 127 /**
 128  * Returns the lower-case variant of the given unicode codepoint.
 129  *
 130  * NOTE: Use utf8_upper() in preference for case-insensitive matching.
 131  *
 132  * Unicode code points > \uffff are returned unchanged.
 133  */
 134 int utf8_lower(int uc);
 135
 136 /**
 137  * Returns the width (in characters) of the given unicode codepoint.
 138  * This is 1 for normal letters and 0 for combining characters and 2 for wide characters.
 139  */
 140 int utf8_width(int ch);
 141
 142 #endif /* JIM_BOOTSTRAP */
 143
 144 #endif
 145
 146 #ifdef __cplusplus
 147 }
 148 #endif
 149
 150 #endif