tommy/libpostal
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[utils] utf8 comparison can handle a non-valid UTF-8 sequence e.g. for trie suffix comparison where we may be in the middle of a multi-byte character. Adding a standard utf8_common_prefix method

Browse Source
This commit is contained in:
Al
2015-06-12 16:11:37 -04:00
parent 5c2839e534
commit 8520df96c8
2 changed files with 49 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/string_utils.h
View File

@@ -34,7 +34,8 @@ extern "C" {
// NOTE: this particular implementation works only for ASCII strings
int string_compare_case_insensitive(const char *str1, const char *str2);
int string_compare_len_case_insensitive(const char *str1, const char *str2, size_t len);
int string_common_prefix(const char *str1, const char *str2);
size_t string_common_prefix(const char *str1, const char *str2);
size_t string_common_suffix(const char *str1, const char *str2);
void string_lower(char *str);
void string_upper(char *str);
@@ -50,6 +51,7 @@ ssize_t utf8proc_iterate_reversed(const uint8_t *str, ssize_t start, int32_t *ds
char *utf8_lower(const char *s); // returns a copy, caller frees
int utf8_compare(const char *str1, const char *str2);
int utf8_compare_len(const char *str1, const char *str2, size_t len);
size_t utf8_common_prefix(const char *str1, const char *str2);
size_t utf8_common_prefix_ignore_separators(const char *str1, const char *str2);
size_t utf8_common_prefix_len_ignore_separators(const char *str1, const char *str2, size_t len);