locale.c: Add detection of Turkic UTF-8 locales

When switching into a new locale, after it is decided this is a UTF-8
locale, the code now also checks for if the locale is a specialized
Turkic one, which has a couple of slightly modified casing change rules.
If so, it sets a flag indicating this.

The code that has been added in previous commits in this series check if
that flag is set when they are actually paying attention to the
background locale, and if so behave according to Unicode Turkic rules.

diff --git a/locale.c b/locale.c
index 383b213..07e5525 100644 (file)
--- a/locale.c
+++ b/locale.c
@@ -1507,6 +1507,7 @@ S_new_ctype(pTHX_ const char *newctype)
 
     /* Don't check for problems if we are suppressing the warnings */
     bool check_for_problems = ckWARN_d(WARN_LOCALE) || UNLIKELY(DEBUG_L_TEST);
+    bool maybe_utf8_turkic = FALSE;
 
     PERL_ARGS_ASSERT_NEW_CTYPE;
 
@@ -1523,6 +1524,14 @@ S_new_ctype(pTHX_ const char *newctype)
      * handle this specially because of the three problematic code points */
     if (PL_in_utf8_CTYPE_locale) {
         Copy(PL_fold_latin1, PL_fold_locale, 256, U8);
+
+        /* UTF-8 locales can have special handling for 'I' and 'i' if they are
+         * Turkic.  Make sure these two are the only anomalies.  (We don't use
+         * towupper and towlower because they aren't in C89.) */
+        if (toupper('i') == 'i' && tolower('I') == 'I') {
+            check_for_problems = TRUE;
+            maybe_utf8_turkic = TRUE;
+        }
     }
 
     /* We don't populate the other lists if a UTF-8 locale, but do check that
@@ -1668,7 +1677,18 @@ S_new_ctype(pTHX_ const char *newctype)
             }
         }
 
+        if (bad_count == 2 && maybe_utf8_turkic) {
+            bad_count = 0;
+            *bad_chars_list = '\0';
+            PL_fold_locale['I'] = 'I';
+            PL_fold_locale['i'] = 'i';
+            PL_in_utf8_turkic_locale = TRUE;
+            DEBUG_L(PerlIO_printf(Perl_debug_log, "%s:%d: %s is turkic\n",
+                                                 __FILE__, __LINE__, newctype));
+        }
+        else {
             PL_in_utf8_turkic_locale = FALSE;
+        }
 
 #  ifdef MB_CUR_MAX
 
@@ -1695,7 +1715,10 @@ S_new_ctype(pTHX_ const char *newctype)
 
 #  endif
 
-        if (UNLIKELY(bad_count) || UNLIKELY(multi_byte_locale)) {
+        /* If we found problems and we want them output, do so */
+        if (   (UNLIKELY(bad_count) || UNLIKELY(multi_byte_locale))
+            && (LIKELY(ckWARN_d(WARN_LOCALE)) || UNLIKELY(DEBUG_L_TEST)))
+        {
             if (UNLIKELY(bad_count) && PL_in_utf8_CTYPE_locale) {
                 PL_warn_locale = Perl_newSVpvf(aTHX_
                      "Locale '%s' contains (at least) the following characters"