[api] adding libpostal_expand_address_root to the public API. This will attempt to delete tokens that can be safely ignored. It's deterministic and rule-based, but is informed by libpostal's fairly comprehensive dictionaries, and should work relatively well across languages for deduping purposes.

This commit is contained in:
Al
2017-12-17 17:46:26 -05:00
parent 9eef46adee
commit 8b2a4d1ecf
2 changed files with 5 additions and 0 deletions

View File

@@ -48,6 +48,10 @@ char **libpostal_expand_address(char *input, libpostal_normalize_options_t optio
return expand_address(input, options, n); return expand_address(input, options, n);
} }
char **libpostal_expand_address_root(char *input, libpostal_normalize_options_t options, size_t *n) {
return expand_address_root(input, options, n);
}
void libpostal_expansion_array_destroy(char **expansions, size_t n) { void libpostal_expansion_array_destroy(char **expansions, size_t n) {
expansion_array_destroy(expansions, n); expansion_array_destroy(expansions, n);
} }

View File

@@ -138,6 +138,7 @@ typedef struct libpostal_normalize_options {
LIBPOSTAL_EXPORT libpostal_normalize_options_t libpostal_get_default_options(void); LIBPOSTAL_EXPORT libpostal_normalize_options_t libpostal_get_default_options(void);
LIBPOSTAL_EXPORT char **libpostal_expand_address(char *input, libpostal_normalize_options_t options, size_t *n); LIBPOSTAL_EXPORT char **libpostal_expand_address(char *input, libpostal_normalize_options_t options, size_t *n);
LIBPOSTAL_EXPORT char **libpostal_expand_address_root(char *input, libpostal_normalize_options_t options, size_t *n);
LIBPOSTAL_EXPORT void libpostal_expansion_array_destroy(char **expansions, size_t n); LIBPOSTAL_EXPORT void libpostal_expansion_array_destroy(char **expansions, size_t n);