diff --git a/README.md b/README.md index 7c6e28c..9774d35 100644 --- a/README.md +++ b/README.md @@ -86,3 +86,50 @@ the [utf8proc issues page on Github](https://github.com/JuliaLang/utf8proc/issue ## See also An independent Lua translation of this library, [lua-mojibake](https://github.com/differentprogramming/lua-mojibake), is also available. + +## Examples + +### Convert codepoint to string +```c +// Convert codepoint `a` to utf8 string `str` +utf8proc_int32_t a = 223; +utf8proc_uint8_t str[16] = { 0 }; +utf8proc_encode_char(a, str); +printf("%s\n", str); +// ß +``` + +### Convert string to codepoint +```c +// Convert string `str` to pointer to codepoint `a` +utf8proc_uint8_t str[] = "ß"; +utf8proc_int32_t a; +utf8proc_iterate(str, -1, &a); +printf("%d\n", a); +// 223 +``` + +### Casefold + +```c +// Convert "ß" (U+00DF) to its casefold variant "ss" +utf8proc_uint8_t str[] = "ß"; +utf8proc_uint8_t *fold_str; +utf8proc_map(str, 0, &fold_str, UTF8PROC_NULLTERM | UTF8PROC_CASEFOLD); +printf("%s\n", fold_str); +// ss +free(fold_str); +``` + +### Normalization Form C/D (NFC/NFD) +```c +// Decompose "\u00e4\u00f6\u00fc" = "äöü" into "a\u0308o\u0308u\u0308" (= "äöü" via combining char U+0308) +utf8proc_uint8_t input[] = {0xc3, 0xa4, 0xc3, 0xb6, 0xc3, 0xbc}; // "\u00e4\u00f6\u00fc" = "äöü" in UTF-8 +utf8proc_uint8_t *nfd= utf8proc_NFD(input); // = {0x61, 0xcc, 0x88, 0x6f, 0xcc, 0x88, 0x75, 0xcc, 0x88} + +// Compose "a\u0308o\u0308u\u0308" into "\u00e4\u00f6\u00fc" (= "äöü" via precomposed characters) +utf8proc_uint8_t *nfc= utf8proc_NFC(nfd); + +free(nfd); +free(nfc); +```