[normalization] adding a normalize_string_latin method

This commit is contained in:
Al
2015-07-05 23:38:01 -04:00
parent acd5d07d17
commit 6ff91fef6b
2 changed files with 21 additions and 5 deletions

View File

@@ -34,7 +34,9 @@ extern "C" {
#define NORMALIZE_TOKEN_DROP_ENGLISH_POSSESSIVES 1 << 4
#define NORMALIZE_TOKEN_DELETE_OTHER_APOSTROPHE 1 << 5
char *utf8_normalize_string(char *str, uint64_t options);
char *normalize_string_utf8(char *str, uint64_t options);
char *normalize_string_latin(char *str, size_t len, uint64_t options);
// Takes NORMALIZE_TOKEN_* options
bool add_token_alternatives(cstring_array *array, char *str, token_t token, uint64_t options);