add cmp_nocase_utf8()

This is like cmp_nocase(), only that it doesn't use toupper(), tolower()
and therefore is agnostic of the current locale, and attempts to compare
strings in a UTF8-aware way (or falls back to ASCII if one of the
strings isn't UTF8-encoded).
This commit is contained in:
Nils Philippsen
2013-12-10 21:29:24 +01:00
parent e5ae775b42
commit 96947e2f3a
2 changed files with 36 additions and 0 deletions

View File

@@ -57,6 +57,7 @@ static inline float f_max(float x, float a) {
std::string bump_name_once(const std::string& s, char delimiter);
int cmp_nocase (const std::string& s, const std::string& s2);
int cmp_nocase_utf8 (const std::string& s1, const std::string& s2);
int touch_file(std::string path);

View File

@@ -232,6 +232,41 @@ cmp_nocase (const string& s, const string& s2)
return (s2.size() == s.size()) ? 0 : (s.size() < s2.size()) ? -1 : 1;
}
int cmp_nocase_utf8 (const string& s1, const string& s2)
{
const char *cstr1 = s1.c_str();
const char *cstr2 = s2.c_str();
gchar *cstr1folded = NULL;
gchar *cstr2folded = NULL;
int retval;
if (!g_utf8_validate (cstr1, -1, NULL) ||
!g_utf8_validate (cstr2, -1, NULL)) {
// fall back to comparing ASCII
return g_ascii_strcasecmp (cstr1, cstr2);
}
cstr1folded = g_utf8_casefold (cstr1, -1);
cstr2folded = g_utf8_casefold (cstr2, -1);
if (cstr1folded && cstr2folded) {
retval = strcmp (cstr1folded, cstr2folded);
} else {
// this shouldn't happen, make the best of it
retval = g_ascii_strcasecmp (cstr1, cstr2);
}
if (cstr1folded) {
g_free (cstr1folded);
}
if (cstr2folded) {
g_free (cstr2folded);
}
return retval;
}
int
touch_file (string path)
{