[fix] NFD normalization should be the default in normalize.c, not NFKD, as NFKD does some unwanted things like converting superscripts and the Latin-ASCII transliterator does a better, more thorough job while staying faithful to the original string
This commit is contained in:
@@ -13,7 +13,7 @@ char *utf8_normalize_string(char *str, uint64_t options) {
|
|||||||
|
|
||||||
if (options & NORMALIZE_STRING_DECOMPOSE) {
|
if (options & NORMALIZE_STRING_DECOMPOSE) {
|
||||||
have_utf8proc_options = true;
|
have_utf8proc_options = true;
|
||||||
utf8proc_options |= UTF8PROC_OPTIONS_NFKD;
|
utf8proc_options |= UTF8PROC_OPTIONS_NFD;
|
||||||
}
|
}
|
||||||
|
|
||||||
if (options & NORMALIZE_STRING_STRIP_ACCENTS) {
|
if (options & NORMALIZE_STRING_STRIP_ACCENTS) {
|
||||||
|
|||||||
Reference in New Issue
Block a user