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