Reorganize perlapi

[perl5.git] / unicode_constants.h

diff --git a/unicode_constants.h b/unicode_constants.h
index 318b901..e434570 100644 (file)
--- a/unicode_constants.h
+++ b/unicode_constants.h
@@ -22,9 +22,9 @@
  *                with no additional suffix are both string constants */
 
 /*
-=head1 Unicode Support
+=for apidoc_section Unicode Support
 
-=for apidoc AmU|placeholder|BOM_UTF8
+=for apidoc AmnU|const char *|BOM_UTF8
 
 This is a macro that evaluates to a string constant of the  UTF-8 bytes that
 define the Unicode BYTE ORDER MARK (U+FEFF) for the platform that perl
@@ -33,7 +33,7 @@ works on both ASCII and EBCDIC platforms.
 S<C<sizeof(BOM_UTF8) - 1>> can be used to get its length in
 bytes.
 
-=for apidoc AmU|placeholder|REPLACEMENT_CHARACTER_UTF8
+=for apidoc AmnU|const char *|REPLACEMENT_CHARACTER_UTF8
 
 This is a macro that evaluates to a string constant of the  UTF-8 bytes that
 define the Unicode REPLACEMENT CHARACTER (U+FFFD) for the platform that perl
@@ -45,7 +45,7 @@ bytes.
 =cut
 */
 
-#define UNICODE_MAJOR_VERSION   9
+#define UNICODE_MAJOR_VERSION   13
 #define UNICODE_DOT_VERSION     0
 #define UNICODE_DOT_DOT_VERSION 0
 
@@ -54,9 +54,7 @@ bytes.
 #   define LATIN_SMALL_LETTER_LONG_S_UTF8  "\xC5\xBF"    /* U+017F */
 
 #   define COMBINING_GRAVE_ACCENT_UTF8  "\xCC\x80"    /* U+0300 */
-
-#   define GREEK_CAPITAL_LETTER_IOTA_UTF8  "\xCE\x99"    /* U+0399 */
-#   define GREEK_SMALL_LETTER_MU_UTF8  "\xCE\xBC"    /* U+03BC */
+#   define COMBINING_DOT_ABOVE_UTF8  "\xCC\x87"    /* U+0307 */
 
 #   define LATIN_CAPITAL_LETTER_SHARP_S_UTF8  "\xE1\xBA\x9E"    /* U+1E9E */
 
@@ -73,6 +71,8 @@ bytes.
 
 #   define REPLACEMENT_CHARACTER_UTF8  "\xEF\xBF\xBD"    /* U+FFFD */
 
+#   define MAX_UNICODE_UTF8  "\xF4\x8F\xBF\xBF"    /* U+10FFFF */
+
 #   define NBSP_NATIVE  0xA0    /* U+00A0 */
 #   define NBSP_UTF8  "\xC2\xA0"    /* U+00A0 */
 
@@ -93,13 +93,11 @@ bytes.
 #if 'A' == 193 /* EBCDIC 1047 */ \
      && '\\' == 224 && '[' == 173 && ']' == 189 && '{' == 192 && '}' == 208 \
      && '^' == 95 && '~' == 161 && '!' == 90 && '#' == 123 && '|' == 79 \
-     && '$' == 91 && '@' == 124 && '`' == 121
+     && '$' == 91 && '@' == 124 && '`' == 121 && '\n' == 21
 #   define LATIN_SMALL_LETTER_LONG_S_UTF8  "\x8F\x73"    /* U+017F */
 
 #   define COMBINING_GRAVE_ACCENT_UTF8  "\xAF\x41"    /* U+0300 */
-
-#   define GREEK_CAPITAL_LETTER_IOTA_UTF8  "\xB3\x68"    /* U+0399 */
-#   define GREEK_SMALL_LETTER_MU_UTF8  "\xB4\x70"    /* U+03BC */
+#   define COMBINING_DOT_ABOVE_UTF8  "\xAF\x48"    /* U+0307 */
 
 #   define LATIN_CAPITAL_LETTER_SHARP_S_UTF8  "\xBF\x63\x72"    /* U+1E9E */
 
@@ -116,6 +114,8 @@ bytes.
 
 #   define REPLACEMENT_CHARACTER_UTF8  "\xDD\x73\x73\x71"    /* U+FFFD */
 
+#   define MAX_UNICODE_UTF8  "\xEE\x42\x73\x73\x73"    /* U+10FFFF */
+
 #   define NBSP_NATIVE  0x41    /* U+00A0 */
 #   define NBSP_UTF8  "\x80\x41"    /* U+00A0 */
 
@@ -136,13 +136,11 @@ bytes.
 #if 'A' == 193 /* EBCDIC 037 */ \
      && '\\' == 224 && '[' == 186 && ']' == 187 && '{' == 192 && '}' == 208 \
      && '^' == 176 && '~' == 161 && '!' == 90 && '#' == 123 && '|' == 79 \
-     && '$' == 91 && '@' == 124 && '`' == 121
+     && '$' == 91 && '@' == 124 && '`' == 121 && '\n' == 37
 #   define LATIN_SMALL_LETTER_LONG_S_UTF8  "\x8E\x72"    /* U+017F */
 
 #   define COMBINING_GRAVE_ACCENT_UTF8  "\xAD\x41"    /* U+0300 */
-
-#   define GREEK_CAPITAL_LETTER_IOTA_UTF8  "\xB2\x67"    /* U+0399 */
-#   define GREEK_SMALL_LETTER_MU_UTF8  "\xB3\x6A"    /* U+03BC */
+#   define COMBINING_DOT_ABOVE_UTF8  "\xAD\x48"    /* U+0307 */
 
 #   define LATIN_CAPITAL_LETTER_SHARP_S_UTF8  "\xBF\x62\x71"    /* U+1E9E */
 
@@ -159,6 +157,8 @@ bytes.
 
 #   define REPLACEMENT_CHARACTER_UTF8  "\xDD\x72\x72\x70"    /* U+FFFD */
 
+#   define MAX_UNICODE_UTF8  "\xEE\x42\x72\x72\x72"    /* U+10FFFF */
+
 #   define NBSP_NATIVE  0x41    /* U+00A0 */
 #   define NBSP_UTF8  "\x78\x41"    /* U+00A0 */
 
@@ -177,7 +177,7 @@ bytes.
 #endif /* EBCDIC 037 */
 
 /* The number of code points not matching \pC */
-#define NON_OTHER_COUNT_FOR_USE_ONLY_BY_REGCOMP_DOT_C  128021
+#define NON_OTHER_COUNT_FOR_USE_ONLY_BY_REGCOMP_DOT_C  143698
 
 /* The highest code point that has any type of case change */
 #define HIGHEST_CASE_CHANGING_CP_FOR_USE_ONLY_BY_UTF8_DOT_C  0x1E943