base: Update Unicode data to 13.0.0wip/forward-ports

(cherry picked from commit d22e087f7bf74341c4468f11b4eb0273033ca931)

5 files changed, 101 insertions, 49 deletions

diff --git a/docs/users_guide/9.2.1-notes.rst b/docs/users_guide/9.2.1-notes.rst
index 63543f728b..db38a53df5 100644
--- a/docs/users_guide/9.2.1-notes.rst
+++ b/docs/users_guide/9.2.1-notes.rst
@@ -312,6 +312,8 @@ Eventlog
 ``base`` library
 ~~~~~~~~~~~~~~~~
 
+- Character set metadata bumped to Unicode 13.0.0.
+
 - It's possible now to promote the ``Natural`` type: ::
 
     data Coordinate = Mk2D Natural Natural
diff --git a/libraries/base/cbits/README.Unicode b/libraries/base/cbits/README.Unicode
index 1eef278c96..70e4e2ead9 100644
--- a/libraries/base/cbits/README.Unicode
+++ b/libraries/base/cbits/README.Unicode
@@ -3,10 +3,9 @@ Generating GHC's Unicode table
 
 WCsubst.c is generated with:
 
+    version=13.0.0
+    url=https://www.unicode.org/Public/$version/ucd/UnicodeData.txt
+    curl -L $url > UnicodeData.txt
     sh ubconfc 12.0.0 < UnicodeData.txt > WCsubst.c
 
-where UnicodeData.txt came from
-
-    https://www.unicode.org/Public/12.0.0/ucd/UnicodeData.txt
-
 Don't forget to mention the update in the User's Guide.
diff --git a/libraries/base/cbits/WCsubst.c b/libraries/base/cbits/WCsubst.c
index a3a8108cfa..3e9512b15c 100644
--- a/libraries/base/cbits/WCsubst.c
+++ b/libraries/base/cbits/WCsubst.c
@@ -1,6 +1,6 @@
 /*-------------------------------------------------------------------------
 This is an automatically generated file: do not edit
-Generated by ubconfc at Mon Feb 10 11:42:51 EST 2020
+Generated by ubconfc at Tue 23 Mar 2021 08:47:53 PM EDT
 @generated
 -------------------------------------------------------------------------*/
 
@@ -90,8 +90,8 @@ struct _charblock_
 #define GENCAT_MN 2097152
 #define GENCAT_LO 16384
 #define MAX_UNI_CHAR 1114109
-#define NUM_BLOCKS 3351
-#define NUM_CONVBLOCKS 1326
+#define NUM_BLOCKS 3396
+#define NUM_CONVBLOCKS 1332
 #define NUM_SPACEBLOCKS 7
 #define NUM_LAT1BLOCKS 63
 #define NUM_RULES 205
@@ -1123,7 +1123,7 @@ static const struct _charblock_ allchars[]={
 	{2142, 1, &rule2},
 	{2144, 11, &rule14},
 	{2208, 21, &rule14},
-	{2230, 8, &rule14},
+	{2230, 18, &rule14},
 	{2259, 15, &rule92},
 	{2274, 1, &rule16},
 	{2275, 32, &rule92},
@@ -1239,7 +1239,7 @@ static const struct _charblock_ allchars[]={
 	{2887, 2, &rule124},
 	{2891, 2, &rule124},
 	{2893, 1, &rule92},
-	{2902, 1, &rule92},
+	{2901, 2, &rule92},
 	{2903, 1, &rule124},
 	{2908, 2, &rule14},
 	{2911, 3, &rule14},
@@ -1318,7 +1318,7 @@ static const struct _charblock_ allchars[]={
 	{3313, 2, &rule14},
 	{3328, 2, &rule92},
 	{3330, 2, &rule124},
-	{3333, 8, &rule14},
+	{3332, 9, &rule14},
 	{3342, 3, &rule14},
 	{3346, 41, &rule14},
 	{3387, 2, &rule92},
@@ -1339,6 +1339,7 @@ static const struct _charblock_ allchars[]={
 	{3440, 9, &rule17},
 	{3449, 1, &rule13},
 	{3450, 6, &rule14},
+	{3457, 1, &rule92},
 	{3458, 2, &rule124},
 	{3461, 18, &rule14},
 	{3482, 24, &rule14},
@@ -1582,6 +1583,7 @@ static const struct _charblock_ allchars[]={
 	{6824, 6, &rule2},
 	{6832, 14, &rule92},
 	{6846, 1, &rule119},
+	{6847, 2, &rule92},
 	{6912, 4, &rule92},
 	{6916, 1, &rule124},
 	{6917, 47, &rule14},
@@ -2221,7 +2223,7 @@ static const struct _charblock_ allchars[]={
 	{11079, 6, &rule6},
 	{11085, 39, &rule13},
 	{11126, 32, &rule13},
-	{11160, 104, &rule13},
+	{11159, 105, &rule13},
 	{11264, 47, &rule122},
 	{11312, 47, &rule123},
 	{11360, 1, &rule22},
@@ -2417,6 +2419,8 @@ static const struct _charblock_ allchars[]={
 	{11841, 1, &rule2},
 	{11842, 1, &rule4},
 	{11843, 13, &rule2},
+	{11856, 2, &rule13},
+	{11858, 1, &rule2},
 	{11904, 26, &rule13},
 	{11931, 89, &rule13},
 	{12032, 214, &rule13},
@@ -2476,7 +2480,7 @@ static const struct _charblock_ allchars[]={
 	{12688, 2, &rule13},
 	{12690, 4, &rule17},
 	{12694, 10, &rule13},
-	{12704, 27, &rule14},
+	{12704, 32, &rule14},
 	{12736, 36, &rule13},
 	{12784, 16, &rule14},
 	{12800, 31, &rule13},
@@ -2490,9 +2494,9 @@ static const struct _charblock_ allchars[]={
 	{12938, 39, &rule13},
 	{12977, 15, &rule17},
 	{12992, 320, &rule13},
-	{13312, 6582, &rule14},
+	{13312, 6592, &rule14},
 	{19904, 64, &rule13},
-	{19968, 20976, &rule14},
+	{19968, 20989, &rule14},
 	{40960, 21, &rule14},
 	{40981, 1, &rule91},
 	{40982, 1143, &rule14},
@@ -2750,6 +2754,12 @@ static const struct _charblock_ allchars[]={
 	{42948, 1, &rule194},
 	{42949, 1, &rule195},
 	{42950, 1, &rule196},
+	{42951, 1, &rule22},
+	{42952, 1, &rule23},
+	{42953, 1, &rule22},
+	{42954, 1, &rule23},
+	{42997, 1, &rule22},
+	{42998, 1, &rule23},
 	{42999, 1, &rule14},
 	{43000, 2, &rule91},
 	{43002, 1, &rule20},
@@ -2764,6 +2774,7 @@ static const struct _charblock_ allchars[]={
 	{43045, 2, &rule92},
 	{43047, 1, &rule124},
 	{43048, 4, &rule13},
+	{43052, 1, &rule92},
 	{43056, 6, &rule17},
 	{43062, 2, &rule13},
 	{43064, 1, &rule3},
@@ -2865,7 +2876,9 @@ static const struct _charblock_ allchars[]={
 	{43860, 7, &rule20},
 	{43867, 1, &rule10},
 	{43868, 4, &rule91},
-	{43872, 8, &rule20},
+	{43872, 9, &rule20},
+	{43881, 1, &rule91},
+	{43882, 2, &rule10},
 	{43888, 80, &rule198},
 	{43968, 35, &rule14},
 	{44003, 2, &rule124},
@@ -3022,7 +3035,7 @@ static const struct _charblock_ allchars[]={
 	{65913, 17, &rule13},
 	{65930, 2, &rule17},
 	{65932, 3, &rule13},
-	{65936, 12, &rule13},
+	{65936, 13, &rule13},
 	{65952, 1, &rule13},
 	{66000, 45, &rule13},
 	{66045, 1, &rule92},
@@ -3121,6 +3134,10 @@ static const struct _charblock_ allchars[]={
 	{68900, 4, &rule92},
 	{68912, 10, &rule8},
 	{69216, 31, &rule17},
+	{69248, 42, &rule14},
+	{69291, 2, &rule92},
+	{69293, 1, &rule7},
+	{69296, 2, &rule14},
 	{69376, 29, &rule14},
 	{69405, 10, &rule17},
 	{69415, 1, &rule14},
@@ -3128,6 +3145,8 @@ static const struct _charblock_ allchars[]={
 	{69446, 11, &rule92},
 	{69457, 4, &rule17},
 	{69461, 5, &rule2},
+	{69552, 21, &rule14},
+	{69573, 7, &rule17},
 	{69600, 23, &rule14},
 	{69632, 1, &rule124},
 	{69633, 1, &rule92},
@@ -3159,6 +3178,7 @@ static const struct _charblock_ allchars[]={
 	{69952, 4, &rule2},
 	{69956, 1, &rule14},
 	{69957, 2, &rule124},
+	{69959, 1, &rule14},
 	{69968, 35, &rule14},
 	{70003, 1, &rule92},
 	{70004, 2, &rule2},
@@ -3173,6 +3193,8 @@ static const struct _charblock_ allchars[]={
 	{70085, 4, &rule2},
 	{70089, 4, &rule92},
 	{70093, 1, &rule2},
+	{70094, 1, &rule124},
+	{70095, 1, &rule92},
 	{70096, 10, &rule8},
 	{70106, 1, &rule14},
 	{70107, 1, &rule2},
@@ -3231,10 +3253,10 @@ static const struct _charblock_ allchars[]={
 	{70727, 4, &rule14},
 	{70731, 5, &rule2},
 	{70736, 10, &rule8},
-	{70747, 1, &rule2},
+	{70746, 2, &rule2},
 	{70749, 1, &rule2},
 	{70750, 1, &rule92},
-	{70751, 1, &rule14},
+	{70751, 3, &rule14},
 	{70784, 48, &rule14},
 	{70832, 3, &rule124},
 	{70835, 6, &rule92},
@@ -3299,7 +3321,23 @@ static const struct _charblock_ allchars[]={
 	{71872, 32, &rule12},
 	{71904, 10, &rule8},
 	{71914, 9, &rule17},
-	{71935, 1, &rule14},
+	{71935, 8, &rule14},
+	{71945, 1, &rule14},
+	{71948, 8, &rule14},
+	{71957, 2, &rule14},
+	{71960, 24, &rule14},
+	{71984, 6, &rule124},
+	{71991, 2, &rule124},
+	{71995, 2, &rule92},
+	{71997, 1, &rule124},
+	{71998, 1, &rule92},
+	{71999, 1, &rule14},
+	{72000, 1, &rule124},
+	{72001, 1, &rule14},
+	{72002, 1, &rule124},
+	{72003, 1, &rule92},
+	{72004, 3, &rule2},
+	{72016, 10, &rule8},
 	{72096, 8, &rule14},
 	{72106, 39, &rule14},
 	{72145, 3, &rule124},
@@ -3377,6 +3415,7 @@ static const struct _charblock_ allchars[]={
 	{73459, 2, &rule92},
 	{73461, 2, &rule124},
 	{73463, 2, &rule2},
+	{73648, 1, &rule14},
 	{73664, 21, &rule17},
 	{73685, 8, &rule13},
 	{73693, 4, &rule3},
@@ -3420,8 +3459,11 @@ static const struct _charblock_ allchars[]={
 	{94176, 2, &rule91},
 	{94178, 1, &rule2},
 	{94179, 1, &rule91},
+	{94180, 1, &rule92},
+	{94192, 2, &rule124},
 	{94208, 6136, &rule14},
-	{100352, 755, &rule14},
+	{100352, 1238, &rule14},
+	{101632, 9, &rule14},
 	{110592, 287, &rule14},
 	{110928, 3, &rule14},
 	{110948, 4, &rule14},
@@ -3609,8 +3651,7 @@ static const struct _charblock_ allchars[]={
 	{127169, 15, &rule13},
 	{127185, 37, &rule13},
 	{127232, 13, &rule17},
-	{127248, 93, &rule13},
-	{127344, 61, &rule13},
+	{127245, 161, &rule13},
 	{127462, 29, &rule13},
 	{127504, 44, &rule13},
 	{127552, 9, &rule13},
@@ -3618,9 +3659,9 @@ static const struct _charblock_ allchars[]={
 	{127584, 6, &rule13},
 	{127744, 251, &rule13},
 	{127995, 5, &rule10},
-	{128000, 726, &rule13},
+	{128000, 728, &rule13},
 	{128736, 13, &rule13},
-	{128752, 11, &rule13},
+	{128752, 13, &rule13},
 	{128768, 116, &rule13},
 	{128896, 89, &rule13},
 	{128992, 12, &rule13},
@@ -3629,24 +3670,28 @@ static const struct _charblock_ allchars[]={
 	{129104, 10, &rule13},
 	{129120, 40, &rule13},
 	{129168, 30, &rule13},
-	{129280, 12, &rule13},
-	{129293, 101, &rule13},
-	{129395, 4, &rule13},
-	{129402, 41, &rule13},
-	{129445, 6, &rule13},
-	{129454, 29, &rule13},
+	{129200, 2, &rule13},
+	{129280, 121, &rule13},
+	{129402, 82, &rule13},
 	{129485, 135, &rule13},
 	{129632, 14, &rule13},
-	{129648, 4, &rule13},
+	{129648, 5, &rule13},
 	{129656, 3, &rule13},
-	{129664, 3, &rule13},
-	{129680, 6, &rule13},
-	{131072, 42711, &rule14},
+	{129664, 7, &rule13},
+	{129680, 25, &rule13},
+	{129712, 7, &rule13},
+	{129728, 3, &rule13},
+	{129744, 7, &rule13},
+	{129792, 147, &rule13},
+	{129940, 55, &rule13},
+	{130032, 10, &rule8},
+	{131072, 42718, &rule14},
 	{173824, 4149, &rule14},
 	{177984, 222, &rule14},
 	{178208, 5762, &rule14},
 	{183984, 7473, &rule14},
 	{194560, 542, &rule14},
+	{196608, 4939, &rule14},
 	{917505, 1, &rule16},
 	{917536, 96, &rule16},
 	{917760, 240, &rule92},
@@ -4964,6 +5009,12 @@ static const struct _charblock_ convchars[]={
 	{42948, 1, &rule194},
 	{42949, 1, &rule195},
 	{42950, 1, &rule196},
+	{42951, 1, &rule22},
+	{42952, 1, &rule23},
+	{42953, 1, &rule22},
+	{42954, 1, &rule23},
+	{42997, 1, &rule22},
+	{42998, 1, &rule23},
 	{43859, 1, &rule197},
 	{43888, 80, &rule198},
 	{65313, 26, &rule9},
diff --git a/libraries/base/include/UnicodeVersion.h b/libraries/base/include/UnicodeVersion.h
index bfecd69c6c..5d1042aa8b 100644
--- a/libraries/base/include/UnicodeVersion.h
+++ b/libraries/base/include/UnicodeVersion.h
@@ -1,7 +1,7 @@
 #if 0
 This is an automatically generated file: do not edit
-Generated by ubconfc at Mon Feb 10 11:42:51 EST 2020
+Generated by ubconfc at Tue 23 Mar 2021 08:47:53 PM EDT
 @generated
 #endif
 
-#define UNICODE_VERSION_NUMS [12,1,0]
+#define UNICODE_VERSION_NUMS [12,0,0]
diff --git a/libraries/base/tests/unicode002.stdout b/libraries/base/tests/unicode002.stdout
index 8a5febbb0a..aa8dabe205 100644
--- a/libraries/base/tests/unicode002.stdout
+++ b/libraries/base/tests/unicode002.stdout
@@ -2237,16 +2237,16 @@ Code C P S U L A D
 2235 F T F F F T F 
 2236 F T F F F T F 
 2237 F T F F F T F 
-2238 F F F F F F F 
-2239 F F F F F F F 
-2240 F F F F F F F 
-2241 F F F F F F F 
-2242 F F F F F F F 
-2243 F F F F F F F 
-2244 F F F F F F F 
-2245 F F F F F F F 
-2246 F F F F F F F 
-2247 F F F F F F F 
+2238 F T F F F T F 
+2239 F T F F F T F 
+2240 F T F F F T F 
+2241 F T F F F T F 
+2242 F T F F F T F 
+2243 F T F F F T F 
+2244 F T F F F T F 
+2245 F T F F F T F 
+2246 F T F F F T F 
+2247 F T F F F T F 
 2248 F F F F F F F 
 2249 F F F F F F F 
 2250 F F F F F F F 
@@ -2900,7 +2900,7 @@ Code C P S U L A D
 2898 F F F F F F F 
 2899 F F F F F F F 
 2900 F F F F F F F 
-2901 F F F F F F F 
+2901 F T F F F F F 
 2902 F T F F F F F 
 2903 F T F F F F F 
 2904 F F F F F F F 
@@ -3331,7 +3331,7 @@ Code C P S U L A D
 3329 F T F F F F F 
 3330 F T F F F F F 
 3331 F T F F F F F 
-3332 F F F F F F F 
+3332 F T F F F T F 
 3333 F T F F F T F 
 3334 F T F F F T F 
 3335 F T F F F T F 
@@ -3456,7 +3456,7 @@ Code C P S U L A D
 3454 F T F F F T F 
 3455 F T F F F T F 
 3456 F F F F F F F 
-3457 F F F F F F F 
+3457 F T F F F F F 
 3458 F T F F F F F 
 3459 F T F F F F F 
 3460 F F F F F F F