FreeChainXenon/gcc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

libcpp: Update to Unicode 15

Browse source 
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.
This commit is contained in:
Jakub Jelinek 2022-11-04 18:18:42 +01:00
parent 26d2db895b
commit 2662d537b0
4 changed files with 17225 additions and 16992 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
gcc/testsuite/c-c++-common/cpp/named-universal-char-escape-1.c
View file

@ -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}' \

9
libcpp/makeuname2c.cc
View file

@ -69,7 +69,7 @@ struct entry { const char *name; unsigned long codepoint; };
static struct entry *entries;
static unsigned long num_allocated, num_entries;
/* Unicode 14 Table 4-8. */
/* Unicode 15 Table 4-8. */
struct generated {
const char *prefix;
/* max_high is a workaround for UnicodeData.txt inconsistencies
@ -81,13 +81,14 @@ struct generated {
static struct generated generated_ranges[] =
{ { "HANGUL SYLLABLE ", 0xac00, 0xd7a3, 0, 0, 0 }, /* NR1 rule */
{ "CJK UNIFIED IDEOGRAPH-", 0x3400, 0x4dbf, 0, 1, 0 }, /* NR2 rules */
{ "CJK UNIFIED IDEOGRAPH-", 0x4e00, 0x9ffc, 0x9fff, 1, 0 },
{ "CJK UNIFIED IDEOGRAPH-", 0x20000, 0x2a6dd, 0x2a6df, 1, 0 },
{ "CJK UNIFIED IDEOGRAPH-", 0x2a700, 0x2b734, 0x2b738, 1, 0 },
{ "CJK UNIFIED IDEOGRAPH-", 0x4e00, 0x9fff, 0, 1, 0 },
{ "CJK UNIFIED IDEOGRAPH-", 0x20000, 0x2a6df, 0, 1, 0 },
{ "CJK UNIFIED IDEOGRAPH-", 0x2a700, 0x2b739, 0, 1, 0 },
{ "CJK UNIFIED IDEOGRAPH-", 0x2b740, 0x2b81d, 0, 1, 0 },
{ "CJK UNIFIED IDEOGRAPH-", 0x2b820, 0x2cea1, 0, 1, 0 },
{ "CJK UNIFIED IDEOGRAPH-", 0x2ceb0, 0x2ebe0, 0, 1, 0 },
{ "CJK UNIFIED IDEOGRAPH-", 0x30000, 0x3134a, 0, 1, 0 },
{ "CJK UNIFIED IDEOGRAPH-", 0x31350, 0x323af, 0, 1, 0 },
{ "TANGUT IDEOGRAPH-", 0x17000, 0x187f7, 0, 2, 0 },
{ "TANGUT IDEOGRAPH-", 0x18d00, 0x18d08, 0, 2, 0 },
{ "KHITAN SMALL SCRIPT CHARACTER-", 0x18b00, 0x18cd5, 0, 3, 0 },

46
libcpp/ucnid.h
View file

@ -766,6 +766,7 @@ static const struct ucnrange ucnranges[] = {
{ C99|N99| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x0cef },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x0cf0 },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x0cf2 },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x0cf3 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x0cff },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x0d01 },
{ C99| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x0d03 },
@ -889,6 +890,7 @@ static const struct ucnrange ucnranges[] = {
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x0ec7 },
{ C99| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 122, 0x0ecb },
{ C99| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x0ecd },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x0ece },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x0ecf },
{ C99|N99| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x0ed9 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x0edb },
@ -2085,7 +2087,8 @@ static const struct ucnrange ucnranges[] = {
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 230, 0x10eac },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x10eaf },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x10eb1 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x10eff },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x10efc },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 220, 0x10eff },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x10f1c },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x10f26 },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x10f27 },
@ -2180,6 +2183,8 @@ static const struct ucnrange ucnranges[] = {
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x11237 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1123d },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x1123e },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x11240 },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x11241 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1127f },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x11286 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x11287 },
@ -2420,6 +2425,19 @@ static const struct ucnrange ucnranges[] = {
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x11edf },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x11ef2 },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x11ef6 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x11eff },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x11f01 },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x11f02 },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x11f03 },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x11f10 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x11f11 },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x11f33 },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x11f3a },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x11f3d },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x11f40 },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 9, 0x11f42 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x11f4f },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x11f59 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x11faf },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x11fb0 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x11fff },
@ -2431,7 +2449,11 @@ static const struct ucnrange ucnranges[] = {
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x12f8f },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x12ff0 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x12fff },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x1342e },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x1342f },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1343f },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x13440 },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x13446 },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x13455 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x143ff },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x14646 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x167ff },
@ -2491,8 +2513,12 @@ static const struct ucnrange ucnranges[] = {
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x1affe },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1afff },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x1b122 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1b131 },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x1b132 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1b14f },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x1b152 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1b154 },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x1b155 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1b163 },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x1b167 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1b16f },
@ -2606,6 +2632,8 @@ static const struct ucnrange ucnranges[] = {
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x1daaf },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1deff },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x1df1e },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1df24 },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x1df2a },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1dfff },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 230, 0x1e006 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1e007 },
@ -2616,6 +2644,10 @@ static const struct ucnrange ucnranges[] = {
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 230, 0x1e024 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1e025 },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 230, 0x1e02a },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1e02f },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC| 0| 0, 0, 0x1e06d },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1e08e },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 230, 0x1e08f },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1e0ff },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x1e12c },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1e12f },
@ -2632,6 +2664,12 @@ static const struct ucnrange ucnranges[] = {
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x1e2eb },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 230, 0x1e2ef },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x1e2f9 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1e4cf },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x1e4eb },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 232, 0x1e4ed },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 220, 0x1e4ee },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 230, 0x1e4ef },
{ 0| 0| 0|C11| 0|CXX23|NXX23|CID|NFC|NKC| 0, 0, 0x1e4f9 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1e7df },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x1e7e6 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1e7e7 },
@ -2741,7 +2779,7 @@ static const struct ucnrange ucnranges[] = {
{ 0| 0| 0| 0| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x1ffff },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x2a6df },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x2a6ff },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x2b738 },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x2b739 },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x2b73f },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x2b81d },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x2b81f },
@ -2753,6 +2791,8 @@ static const struct ucnrange ucnranges[] = {
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x2fffd },
{ 0| 0| 0| 0| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x2ffff },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x3134a },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x3134f },
{ 0| 0| 0|C11| 0|CXX23| 0|CID|NFC|NKC| 0, 0, 0x323af },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x3fffd },
{ 0| 0| 0| 0| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x3ffff },
{ 0| 0| 0|C11| 0| 0| 0|CID|NFC|NKC| 0, 0, 0x4fffd },

34138
libcpp/uname2c.h
View file

File diff suppressed because it is too large Load diff