The old _pcre_ucp_othercase() function was wrong in returning
NOTACHAR (0xffffffff) for characters that aren't changed by upper-
and lower-casing. This led to PCRE internally using incorrect (or
at least inefficient) character classes when using G_REGEX_CASELESS.
E.g. [Z-\x{100}] turned into:
[Z\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{39c}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{fffe}\x{178}z-\x{101}]
instead of the expected and efficient
[Z\x{39c}\x{178}z-\x{101}]
https://bugzilla.gnome.org/show_bug.cgi?id=678273
const int PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table);
-unsigned int
+unsigned int
_pcre_ucp_othercase(const unsigned int c)
{
- int other_case = NOTACHAR;
+ unsigned int oc;
- if (g_unichar_islower(c))
- other_case = g_unichar_toupper(c);
- else if (g_unichar_isupper(c))
- other_case = g_unichar_tolower(c);
+ if ((oc = g_unichar_tolower(c)) != c)
+ return oc;
+ if ((oc = g_unichar_toupper(c)) != c)
+ return oc;
- if (other_case == c)
- other_case = NOTACHAR;
-
- return other_case;
+ return c;
}
#endif /* SUPPORT_UTF */