all: update to Unicode 17

Process:
- Disable unicode TestProperties.
- Run UNICODE_VERSION=17.0.0 go -C ../src/golang.org/x/text generate
- Run go generate strconv
- Update unicode TestProperties by hand to add missing test cases.

This will break x/text using the main repo until the corresponding
x/text CL is submitted. It should not break anything else.

For #77266.

Change-Id: Ia3ffb5a81e212b991714eef70eebfca98a0c8aab
Reviewed-on: https://go-review.googlesource.com/c/go/+/737420
Reviewed-by: Rob Pike <r@golang.org>
Reviewed-by: Roland Shoemaker <roland@golang.org>
TryBot-Bypass: Russ Cox <rsc@golang.org>

api/except.txt

@@ -503,6 +503,7 @@ pkg unicode, const Version = "10.0.0"
 pkg unicode, const Version = "11.0.0"
 pkg unicode, const Version = "12.0.0"
 pkg unicode, const Version = "13.0.0"
+pkg unicode, const Version = "15.0.0"
 pkg unicode, const Version = "6.2.0"
 pkg unicode, const Version = "6.3.0"
 pkg unicode, const Version = "7.0.0"

api/next/77266.txt

@@ -0,0 +1,16 @@
+pkg unicode, const Version = "17.0.0" #77266
+pkg unicode, var Beria_Erfe *RangeTable #77266
+pkg unicode, var Garay *RangeTable #77266
+pkg unicode, var Gurung_Khema *RangeTable #77266
+pkg unicode, var IDS_Unary_Operator *RangeTable #77266
+pkg unicode, var ID_Compat_Math_Continue *RangeTable #77266
+pkg unicode, var ID_Compat_Math_Start *RangeTable #77266
+pkg unicode, var Kirat_Rai *RangeTable #77266
+pkg unicode, var Modifier_Combining_Mark *RangeTable #77266
+pkg unicode, var Ol_Onal *RangeTable #77266
+pkg unicode, var Sidetic *RangeTable #77266
+pkg unicode, var Sunuwar *RangeTable #77266
+pkg unicode, var Tai_Yo *RangeTable #77266
+pkg unicode, var Todhri *RangeTable #77266
+pkg unicode, var Tolong_Siki *RangeTable #77266
+pkg unicode, var Tulu_Tigalari *RangeTable #77266

doc/next/6-stdlib/99-minor/unicode/77266.md

@@ -0,0 +1,4 @@
+The unicode package and associated support throughout the system has been upgraded from Unicode 15 to Unicode 17.
+See the [Unicode 16.0.0](https://www.unicode.org/versions/Unicode16.0.0/) and
+[Unicode 17.0.0](https://www.unicode.org/versions/Unicode17.0.0/)
+release notes for information about the changes.

src/strconv/isprint.go

@@ -6,7 +6,7 @@
 
 package strconv
 
-// (424+133+112)*2 + (508)*4 = 3370 bytes
+// (412+132+120)*2 + (566)*4 = 3592 bytes
 
 var isPrint16 = []uint16{
 	0x0020, 0x007e,
@@ -24,8 +24,8 @@ var isPrint16 = []uint16{
 	0x07fd, 0x082d,
 	0x0830, 0x085b,
 	0x085e, 0x086a,
-	0x0870, 0x088e,
-	0x0898, 0x098c,
+	0x0870, 0x088f,
+	0x0897, 0x098c,
 	0x098f, 0x0990,
 	0x0993, 0x09b2,
 	0x09b6, 0x09b9,
@@ -71,14 +71,13 @@ var isPrint16 = []uint16{
 	0x0be6, 0x0bfa,
 	0x0c00, 0x0c39,
 	0x0c3c, 0x0c4d,
-	0x0c55, 0x0c5a,
-	0x0c5d, 0x0c5d,
+	0x0c55, 0x0c5d,
 	0x0c60, 0x0c63,
 	0x0c66, 0x0c6f,
 	0x0c77, 0x0cb9,
 	0x0cbc, 0x0ccd,
 	0x0cd5, 0x0cd6,
-	0x0cdd, 0x0ce3,
+	0x0cdc, 0x0ce3,
 	0x0ce6, 0x0cf3,
 	0x0d00, 0x0d4f,
 	0x0d54, 0x0d63,
@@ -135,12 +134,12 @@ var isPrint16 = []uint16{
 	0x1a7f, 0x1a89,
 	0x1a90, 0x1a99,
 	0x1aa0, 0x1aad,
-	0x1ab0, 0x1ace,
-	0x1b00, 0x1b4c,
-	0x1b50, 0x1bf3,
+	0x1ab0, 0x1add,
+	0x1ae0, 0x1aeb,
+	0x1b00, 0x1bf3,
 	0x1bfc, 0x1c37,
 	0x1c3b, 0x1c49,
-	0x1c4d, 0x1c88,
+	0x1c4d, 0x1c8a,
 	0x1c90, 0x1cba,
 	0x1cbd, 0x1cc7,
 	0x1cd0, 0x1cfa,
@@ -156,10 +155,10 @@ var isPrint16 = []uint16{
 	0x2030, 0x205e,
 	0x2070, 0x2071,
 	0x2074, 0x209c,
-	0x20a0, 0x20c0,
+	0x20a0, 0x20c1,
 	0x20d0, 0x20f0,
 	0x2100, 0x218b,
-	0x2190, 0x2426,
+	0x2190, 0x2429,
 	0x2440, 0x244a,
 	0x2460, 0x2b73,
 	0x2b76, 0x2cf3,
@@ -171,17 +170,15 @@ var isPrint16 = []uint16{
 	0x2da0, 0x2e5d,
 	0x2e80, 0x2ef3,
 	0x2f00, 0x2fd5,
-	0x2ff0, 0x2ffb,
-	0x3001, 0x3096,
+	0x2ff0, 0x3096,
 	0x3099, 0x30ff,
-	0x3105, 0x31e3,
-	0x31f0, 0xa48c,
+	0x3105, 0x31e5,
+	0x31ef, 0xa48c,
 	0xa490, 0xa4c6,
 	0xa4d0, 0xa62b,
 	0xa640, 0xa6f7,
-	0xa700, 0xa7ca,
-	0xa7d0, 0xa7d9,
-	0xa7f2, 0xa82c,
+	0xa700, 0xa7dc,
+	0xa7f1, 0xa82c,
 	0xa830, 0xa839,
 	0xa840, 0xa877,
 	0xa880, 0xa8c5,
@@ -207,10 +204,7 @@ var isPrint16 = []uint16{
 	0xfa70, 0xfad9,
 	0xfb00, 0xfb06,
 	0xfb13, 0xfb17,
-	0xfb1d, 0xfbc2,
-	0xfbd3, 0xfd8f,
-	0xfd92, 0xfdc7,
-	0xfdcf, 0xfdcf,
+	0xfb1d, 0xfdcf,
 	0xfdf0, 0xfe19,
 	0xfe20, 0xfe6b,
 	0xfe70, 0xfefc,
@@ -271,6 +265,7 @@ var isNotPrint16 = []uint16{
 	0x0c45,
 	0x0c49,
 	0x0c57,
+	0x0c5b,
 	0x0c8d,
 	0x0c91,
 	0x0ca9,
@@ -317,7 +312,7 @@ var isNotPrint16 = []uint16{
 	0x180e,
 	0x191f,
 	0x1a5f,
-	0x1b7f,
+	0x1b4d,
 	0x1f58,
 	0x1f5a,
 	0x1f5c,
@@ -327,7 +322,6 @@ var isNotPrint16 = []uint16{
 	0x1fdc,
 	0x1ff5,
 	0x208f,
-	0x2b96,
 	0x2d26,
 	0x2da7,
 	0x2daf,
@@ -338,12 +332,11 @@ var isNotPrint16 = []uint16{
 	0x2dd7,
 	0x2ddf,
 	0x2e9a,
+	0x3000,
 	0x3040,
 	0x3130,
 	0x318f,
 	0x321f,
-	0xa7d2,
-	0xa7d4,
 	0xa9ce,
 	0xa9ff,
 	0xab27,
@@ -383,6 +376,7 @@ var isPrint32 = []uint32{
 	0x010500, 0x010527,
 	0x010530, 0x010563,
 	0x01056f, 0x0105bc,
+	0x0105c0, 0x0105f3,
 	0x010600, 0x010736,
 	0x010740, 0x010755,
 	0x010760, 0x010767,
@@ -395,7 +389,7 @@ var isPrint32 = []uint32{
 	0x0108e0, 0x0108f5,
 	0x0108fb, 0x01091b,
 	0x01091f, 0x010939,
-	0x01093f, 0x01093f,
+	0x01093f, 0x010959,
 	0x010980, 0x0109b7,
 	0x0109bc, 0x0109cf,
 	0x0109d2, 0x010a06,
@@ -417,9 +411,14 @@ var isPrint32 = []uint32{
 	0x010cc0, 0x010cf2,
 	0x010cfa, 0x010d27,
 	0x010d30, 0x010d39,
+	0x010d40, 0x010d65,
+	0x010d69, 0x010d85,
+	0x010d8e, 0x010d8f,
 	0x010e60, 0x010ead,
 	0x010eb0, 0x010eb1,
-	0x010efd, 0x010f27,
+	0x010ec2, 0x010ec7,
+	0x010ed0, 0x010ed8,
+	0x010efa, 0x010f27,
 	0x010f30, 0x010f59,
 	0x010f70, 0x010f89,
 	0x010fb0, 0x010fcb,
@@ -446,6 +445,10 @@ var isPrint32 = []uint32{
 	0x01135d, 0x011363,
 	0x011366, 0x01136c,
 	0x011370, 0x011374,
+	0x011380, 0x01138b,
+	0x01138e, 0x0113c2,
+	0x0113c5, 0x0113d8,
+	0x0113e1, 0x0113e2,
 	0x011400, 0x011461,
 	0x011480, 0x0114c7,
 	0x0114d0, 0x0114d9,
@@ -456,6 +459,7 @@ var isPrint32 = []uint32{
 	0x011660, 0x01166c,
 	0x011680, 0x0116b9,
 	0x0116c0, 0x0116c9,
+	0x0116d0, 0x0116e3,
 	0x011700, 0x01171a,
 	0x01171d, 0x01172b,
 	0x011730, 0x011746,
@@ -473,6 +477,9 @@ var isPrint32 = []uint32{
 	0x011a50, 0x011aa2,
 	0x011ab0, 0x011af8,
 	0x011b00, 0x011b09,
+	0x011b60, 0x011b67,
+	0x011bc0, 0x011be1,
+	0x011bf0, 0x011bf9,
 	0x011c00, 0x011c45,
 	0x011c50, 0x011c6c,
 	0x011c70, 0x011c8f,
@@ -482,9 +489,11 @@ var isPrint32 = []uint32{
 	0x011d50, 0x011d59,
 	0x011d60, 0x011d98,
 	0x011da0, 0x011da9,
+	0x011db0, 0x011ddb,
+	0x011de0, 0x011de9,
 	0x011ee0, 0x011ef8,
 	0x011f00, 0x011f3a,
-	0x011f3e, 0x011f59,
+	0x011f3e, 0x011f5a,
 	0x011fb0, 0x011fb0,
 	0x011fc0, 0x011ff1,
 	0x011fff, 0x012399,
@@ -493,7 +502,9 @@ var isPrint32 = []uint32{
 	0x012f90, 0x012ff2,
 	0x013000, 0x01342f,
 	0x013440, 0x013455,
+	0x013460, 0x0143fa,
 	0x014400, 0x014646,
+	0x016100, 0x016139,
 	0x016800, 0x016a38,
 	0x016a40, 0x016a69,
 	0x016a6e, 0x016ac9,
@@ -502,15 +513,18 @@ var isPrint32 = []uint32{
 	0x016b00, 0x016b45,
 	0x016b50, 0x016b77,
 	0x016b7d, 0x016b8f,
+	0x016d40, 0x016d79,
 	0x016e40, 0x016e9a,
+	0x016ea0, 0x016eb8,
+	0x016ebb, 0x016ed3,
 	0x016f00, 0x016f4a,
 	0x016f4f, 0x016f87,
 	0x016f8f, 0x016f9f,
 	0x016fe0, 0x016fe4,
-	0x016ff0, 0x016ff1,
-	0x017000, 0x0187f7,
-	0x018800, 0x018cd5,
-	0x018d00, 0x018d08,
+	0x016ff0, 0x016ff6,
+	0x017000, 0x018cd5,
+	0x018cff, 0x018d1e,
+	0x018d80, 0x018df2,
 	0x01aff0, 0x01b122,
 	0x01b132, 0x01b132,
 	0x01b150, 0x01b152,
@@ -522,6 +536,10 @@ var isPrint32 = []uint32{
 	0x01bc80, 0x01bc88,
 	0x01bc90, 0x01bc99,
 	0x01bc9c, 0x01bc9f,
+	0x01cc00, 0x01ccfc,
+	0x01cd00, 0x01ceb3,
+	0x01ceba, 0x01ced0,
+	0x01cee0, 0x01cef0,
 	0x01cf00, 0x01cf2d,
 	0x01cf30, 0x01cf46,
 	0x01cf50, 0x01cfc3,
@@ -557,6 +575,10 @@ var isPrint32 = []uint32{
 	0x01e2c0, 0x01e2f9,
 	0x01e2ff, 0x01e2ff,
 	0x01e4d0, 0x01e4f9,
+	0x01e5d0, 0x01e5fa,
+	0x01e5ff, 0x01e5ff,
+	0x01e6c0, 0x01e6f5,
+	0x01e6fe, 0x01e6ff,
 	0x01e7e0, 0x01e8c4,
 	0x01e8c7, 0x01e8d6,
 	0x01e900, 0x01e94b,
@@ -582,11 +604,10 @@ var isPrint32 = []uint32{
 	0x01f240, 0x01f248,
 	0x01f250, 0x01f251,
 	0x01f260, 0x01f265,
-	0x01f300, 0x01f6d7,
+	0x01f300, 0x01f6d8,
 	0x01f6dc, 0x01f6ec,
 	0x01f6f0, 0x01f6fc,
-	0x01f700, 0x01f776,
-	0x01f77b, 0x01f7d9,
+	0x01f700, 0x01f7d9,
 	0x01f7e0, 0x01f7eb,
 	0x01f7f0, 0x01f7f0,
 	0x01f800, 0x01f80b,
@@ -594,25 +615,26 @@ var isPrint32 = []uint32{
 	0x01f850, 0x01f859,
 	0x01f860, 0x01f887,
 	0x01f890, 0x01f8ad,
-	0x01f8b0, 0x01f8b1,
-	0x01f900, 0x01fa53,
+	0x01f8b0, 0x01f8bb,
+	0x01f8c0, 0x01f8c1,
+	0x01f8d0, 0x01f8d8,
+	0x01f900, 0x01fa57,
 	0x01fa60, 0x01fa6d,
 	0x01fa70, 0x01fa7c,
-	0x01fa80, 0x01fa88,
-	0x01fa90, 0x01fac5,
-	0x01face, 0x01fadb,
-	0x01fae0, 0x01fae8,
-	0x01faf0, 0x01faf8,
-	0x01fb00, 0x01fbca,
-	0x01fbf0, 0x01fbf9,
+	0x01fa80, 0x01fa8a,
+	0x01fa8e, 0x01fac8,
+	0x01facd, 0x01fadc,
+	0x01fadf, 0x01faea,
+	0x01faef, 0x01faf8,
+	0x01fb00, 0x01fbfa,
 	0x020000, 0x02a6df,
-	0x02a700, 0x02b739,
-	0x02b740, 0x02b81d,
-	0x02b820, 0x02cea1,
+	0x02a700, 0x02b81d,
+	0x02b820, 0x02cead,
 	0x02ceb0, 0x02ebe0,
+	0x02ebf0, 0x02ee5d,
 	0x02f800, 0x02fa1d,
 	0x030000, 0x03134a,
-	0x031350, 0x0323af,
+	0x031350, 0x033479,
 	0x0e0100, 0x0e01ef,
 }
 
@@ -654,6 +676,13 @@ var isNotPrint32 = []uint16{ // add 0x10000 to each entry
 	0x1331,
 	0x1334,
 	0x133a,
+	0x138a,
+	0x138f,
+	0x13b6,
+	0x13c1,
+	0x13c6,
+	0x13cb,
+	0x13d6,
 	0x145c,
 	0x1914,
 	0x1917,
@@ -695,6 +724,7 @@ var isNotPrint32 = []uint16{ // add 0x10000 to each entry
 	0xe007,
 	0xe022,
 	0xe025,
+	0xe6df,
 	0xe7e7,
 	0xe7ec,
 	0xe7ef,
@@ -727,7 +757,7 @@ var isNotPrint32 = []uint16{ // add 0x10000 to each entry
 	0xeeaa,
 	0xf0c0,
 	0xf0d0,
-	0xfabe,
+	0xfac7,
 	0xfb93,
 }
 

src/unicode/script_test.go

@@ -94,6 +94,10 @@ var inPropTest = []T{
 	{0x9FC3, "Unified_Ideograph"},
 	{0xFE0F, "Variation_Selector"},
 	{0x0020, "White_Space"},
+	{0x221e, "ID_Compat_Math_Start"},
+	{0x06e3, "Modifier_Combining_Mark"},
+	{0x2080, "ID_Compat_Math_Continue"},
+	{0x2ffe, "IDS_Unary_Operator"},
 }
 
 func TestCategories(t *testing.T) {