libcpp: Update to Unicode 15

The following pseudo-patch regenerates the libcpp tables with Unicode 15.0.0
which added 4489 new characters.

As mentioned previously, this isn't just a matter of running the
two libcpp/make*.cc programs on the new Unicode files, but one needs
to manually update a table inside of makeuname2c.cc according to
a table in Unicode text (which is partially reflected in the text
files, but e.g. in Unicode 14.0.0 not 100% accurately, in 15.0.0
actually accurately).
I've also added some randomly chosen subset of those 4489 new
characters to a testcase.

2022-11-04  Jakub Jelinek  <jakub@redhat.com>

gcc/testsuite/
	* c-c++-common/cpp/named-universal-char-escape-1.c: Add tests for some
	characters newly added in Unicode 15.0.0.
libcpp/
	* makeuname2c.cc (struct generated): Update from Unicode 15.0.0
	table 4-8.
	* ucnid.h: Regenerated for Unicode 15.0.0.
	* uname2c.h: Likewise.

1 files changed, 24 insertions, 0 deletions

diff --git a/gcc/testsuite/c-c++-common/cpp/named-universal-char-escape-1.c b/gcc/testsuite/c-c++-common/cpp/named-universal-char-escape-1.c
index 3c692f45..054eb50 100644
--- a/gcc/testsuite/c-c++-common/cpp/named-universal-char-escape-1.c
+++ b/gcc/testsuite/c-c++-common/cpp/named-universal-char-escape-1.c
@@ -117,6 +117,27 @@ typedef __CHAR32_TYPE__ char32_t;
     || U'\u0FD0' != U'\N{TIBETAN MARK BSKA- SHOG GI MGO RGYAN}' \
     || U'\uFE18' != U'\N{PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET}' \
     || U'\uFE18' != U'\N{PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRACKET}' \
+    || U'\u0CF3' != U'\N{KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT}' \
+    || U'\u0ECE' != U'\N{LAO YAMAKKAN}' \
+    || U'\U00010EFE' != U'\N{ARABIC SMALL LOW WORD QASR}' \
+    || U'\U00011241' != U'\N{KHOJKI VOWEL SIGN VOCALIC R}' \
+    || U'\U00011B06' != U'\N{DEVANAGARI SIGN WESTERN FIVE-LIKE BHALE}' \
+    || U'\U00011F0B' != U'\N{KAWI LETTER VOCALIC RR}' \
+    || U'\U0001342F' != U'\N{EGYPTIAN HIEROGLYPH V011D}' \
+    || U'\U00013451' != U'\N{EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT START AND BOTTOM}' \
+    || U'\U0001B132' != U'\N{HIRAGANA LETTER SMALL KO}' \
+    || U'\U0001B155' != U'\N{KATAKANA LETTER SMALL KO}' \
+    || U'\U0001D2C4' != U'\N{KAKTOVIK NUMERAL FOUR}' \
+    || U'\U0001DF27' != U'\N{LATIN SMALL LETTER N WITH MID-HEIGHT LEFT HOOK}' \
+    || U'\U0001E036' != U'\N{MODIFIER LETTER CYRILLIC SMALL ZHE}' \
+    || U'\U0001E05B' != U'\N{CYRILLIC SUBSCRIPT SMALL LETTER EL}' \
+    || U'\U0001E4E5' != U'\N{NAG MUNDARI LETTER ENN}' \
+    || U'\U0001F6DC' != U'\N{WIRELESS}' \
+    || U'\U0001F77E' != U'\N{QUAOAR}' \
+    || U'\U0001F7D9' != U'\N{NINE POINTED WHITE STAR}' \
+    || U'\U0001FA76' != U'\N{GREY HEART}' \
+    || U'\U0001FA88' != U'\N{FLUTE}' \
+    || U'\U0001FABC' != U'\N{JELLYFISH}' \
     || U'\uAC00' != U'\N{HANGUL SYLLABLE GA}' \
     || U'\uAC02' != U'\N{HANGUL SYLLABLE GAGG}' \
     || U'\uAD8D' != U'\N{HANGUL SYLLABLE GWEONJ}' \
@@ -134,6 +155,7 @@ typedef __CHAR32_TYPE__ char32_t;
     || U'\U0002A6DD' != U'\N{CJK UNIFIED IDEOGRAPH-2A6DD}' \
     || U'\U00020700' != U'\N{CJK UNIFIED IDEOGRAPH-20700}' \
     || U'\U0002B734' != U'\N{CJK UNIFIED IDEOGRAPH-2B734}' \
+    || U'\U0002B739' != U'\N{CJK UNIFIED IDEOGRAPH-2B739}' \
     || U'\U0002B740' != U'\N{CJK UNIFIED IDEOGRAPH-2B740}' \
     || U'\U0002B81D' != U'\N{CJK UNIFIED IDEOGRAPH-2B81D}' \
     || U'\U0002B820' != U'\N{CJK UNIFIED IDEOGRAPH-2B820}' \
@@ -142,6 +164,8 @@ typedef __CHAR32_TYPE__ char32_t;
     || U'\U0002EBE0' != U'\N{CJK UNIFIED IDEOGRAPH-2EBE0}' \
     || U'\U00030000' != U'\N{CJK UNIFIED IDEOGRAPH-30000}' \
     || U'\U0003134A' != U'\N{CJK UNIFIED IDEOGRAPH-3134A}' \
+    || U'\U00031350' != U'\N{CJK UNIFIED IDEOGRAPH-31350}' \
+    || U'\U000323AF' != U'\N{CJK UNIFIED IDEOGRAPH-323AF}' \
     || U'\U00017000' != U'\N{TANGUT IDEOGRAPH-17000}' \
     || U'\U000187F7' != U'\N{TANGUT IDEOGRAPH-187F7}' \
     || U'\U00018D00' != U'\N{TANGUT IDEOGRAPH-18D00}' \