utf8.h, regcomp.c: Use mnemonics for Unicode chars

Add a mnemonic definition for these three code points.  They are
currently used in only one place, but future commits will use them
elsewhere.

diff --git a/regcomp.c b/regcomp.c
index a05b853..e3e85c6 100644 (file)
--- a/regcomp.c
+++ b/regcomp.c
@@ -11995,15 +11995,13 @@ parseit:
                         switch (j) {
                             case 'k':
                             case 'K':
-                                /* KELVIN SIGN */
                                 cp_list =
-                                    add_cp_to_invlist(cp_list, 0x212A);
+                                    add_cp_to_invlist(cp_list, KELVIN_SIGN);
                                 break;
                             case 's':
                             case 'S':
-                                /* LATIN SMALL LETTER LONG S */
-                                cp_list =
-                                    add_cp_to_invlist(cp_list, 0x017F);
+                                cp_list = add_cp_to_invlist(cp_list,
+                                                    LATIN_SMALL_LETTER_LONG_S);
                                 break;
                             case MICRO_SIGN:
                                 cp_list = add_cp_to_invlist(cp_list,
@@ -12013,9 +12011,8 @@ parseit:
                                 break;
                             case LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE:
                             case LATIN_SMALL_LETTER_A_WITH_RING_ABOVE:
-                                /* ANGSTROM SIGN */
                                 cp_list =
-                                        add_cp_to_invlist(cp_list, 0x212B);
+                                    add_cp_to_invlist(cp_list, ANGSTROM_SIGN);
                                 break;
                             case LATIN_SMALL_LETTER_Y_WITH_DIAERESIS:
                                 cp_list = add_cp_to_invlist(cp_list,

diff --git a/utf8.h b/utf8.h
index 82d90f0..7a1e095 100644 (file)
--- a/utf8.h
+++ b/utf8.h
@@ -482,6 +482,9 @@ Perl's extended UTF-8 means we can have start bytes up to FF.
 #define GREEK_CAPITAL_LETTER_MU 0x039C /* Upper and title case of MICRON */
 #define LATIN_CAPITAL_LETTER_Y_WITH_DIAERESIS 0x0178   /* Also is title case */
 #define LATIN_CAPITAL_LETTER_SHARP_S   0x1E9E
+#define LATIN_SMALL_LETTER_LONG_S   0x017F
+#define KELVIN_SIGN                 0x212A
+#define ANGSTROM_SIGN               0x212B
 
 #define UNI_DISPLAY_ISPRINT    0x0001
 #define UNI_DISPLAY_BACKSLASH  0x0002