Update to Unicode 14.0.0.

* lib/gen-uni-tables.c (UC_JOINING_GROUP_THIN_YEH,
UC_JOINING_GROUP_VERTICAL_TAIL): New enum values.
(fill_arabicshaping, joining_group_as_c_identifier): Recognize these
joining groups.
* lib/unictype.in.h (UC_JOINING_GROUP_THIN_YEH,
UC_JOINING_GROUP_VERTICAL_TAIL): New enum values.
* lib/unictype/joininggroup_name.h: Add the THIN_YEH, VERTICAL_TAIL
joining groups.
* lib/unictype/joininggroup_byname.gperf: Likewise.

* lib/gen-uni-tables.c (LBP_ID1, LBP_ID2): New enum values.
(LBP_ID): Assign artificial value.
(get_lbp): Use the extended_pictographic property to assign LBP_ID1,
LBP_ID2 instead of LBP_ID. Update such that unilbrk/lbrkprop.txt comes
out as expected.
(debug_output_lbp): Print either LBP_ID1 or LBP_ID2 as LBP_ID.
(lbp_value_to_string): Handle LBP_ID1, LBP_ID2 instead of LBP_ID.
(output_lbrk_rules_as_tables): Treat LBP_ID as macro that maps to two
table rows/columns. In rule LB30b, use LBP_ID2 in addition to LBP_EB.
Remove redundant part of rule LB27.
* lib/unilbrk/lbrktables.h (LBP_ID1, LBP_ID2): New enum values.
(LBP_ID): Remove enum value.
(unilbrk_table): Update declaration.
* lib/unilbrk/u8-possible-linebreaks.c (u8_possible_linebreaks_loop):
Use LBP_ID1 instead of LBP_ID.
* lib/unilbrk/u16-possible-linebreaks.c (u16_possible_linebreaks_loop):
Likewise.
* lib/unilbrk/u32-possible-linebreaks.c (u32_possible_linebreaks_loop):
Likewise.
* tests/unilbrk/test-u8-possible-linebreaks.c (test_function): Add a
test of potential future emoji.
* tests/unilbrk/test-u16-possible-linebreaks.c (test_function):
Likewise.
* tests/unilbrk/test-u32-possible-linebreaks.c (test_function):
Likewise.

* lib/uniwidth/width.c (nonspacing_table_data, nonspacing_table_ind):
Update.
(uc_width): Assign width 2 to the characters 0x1AFF0..0x1AFF3,
0x1AFF5..0x1AFFB, 0x1AFFD..0x1AFFE, 0x1B120..0x1B122, 0x1F6DD..0x1F6DF,
0x1F7F0, 0x1FA7B..0x1FA7C, 0x1FAA9..0x1FAAC, 0x1FAB7..0x1FABA,
0x1FAC3..0x1FAC5, 0x1FAD7..0x1FAD9, 0x1FAE0..0x1FAE7, 0x1FAF0..0x1FAF6.
* tests/uniwidth/test-uc_width2.sh: Expect width 0 for the characters
0x0890..0x0891, 0x0898..0x089F, 0x08CA..0x0902, 0x0C3C, 0x180F,
0x1AC1..0x1ACE, 0x1DFA, 0x10F82..0x10F85, 0x11070, 0x11073..0x11074,
0x110C2, 0x1CF00..0x1CF2D, 0x1CF30..0x1CF46, 0x1E2AE. Expect ambiguous
width for the character 0x1734. Expect width 2 for the characters
0x1AFF0..0x1AFF3, 0x1AFF5..0x1AFFB, 0x1AFFD..0x1AFFE, 0x1B120..0x1B122,
0x1F6DD..0x1F6DF, 0x1F7F0, 0x1FA7B..0x1FA7C, 0x1FAA9..0x1FAAC,
0x1FAB7..0x1FABA, 0x1FAC3..0x1FAC5, 0x1FAD7..0x1FAD9, 0x1FAE0..0x1FAE7,
0x1FAF0..0x1FAF6.

* All generated files under lib/uni* and tests/uni*: Regenerate.
* tests/uniname/NameAliases.txt: Update.
* tests/uniname/UnicodeData.txt: Update.
* tests/uninorm/NormalizationTest.txt: Update.
* tests/unigbrk/GraphemeBreakTest.txt: Update.
* tests/uniwbrk/WordBreakTest.txt: Update.

* All the affected modules: Bump required libunistring version.

1 files changed, 37 insertions, 22 deletions

diff --git a/lib/uniwidth/width.c b/lib/uniwidth/width.c
index da818f8f38..9c8d7fb68a 100644
--- a/lib/uniwidth/width.c
+++ b/lib/uniwidth/width.c
@@ -45,7 +45,7 @@
      <https://sourceware.org/bugzilla/show_bug.cgi?id=21750>
      <https://sourceware.org/bugzilla/show_bug.cgi?id=26120>
  */
-static const unsigned char nonspacing_table_data[46*64] = {
+static const unsigned char nonspacing_table_data[47*64] = {
   /* 0x0000-0x01ff */
   0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, /* 0x0000-0x003f */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80, /* 0x0040-0x007f */
@@ -85,8 +85,8 @@ static const unsigned char nonspacing_table_data[46*64] = {
   /* 0x0800-0x09ff */
   0x00, 0x00, 0xc0, 0xfb, 0xef, 0x3e, 0x00, 0x00, /* 0x0800-0x083f */
   0x00, 0x00, 0x00, 0x0e, 0x00, 0x00, 0x00, 0x00, /* 0x0840-0x087f */
-  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x0880-0x08bf */
-  0x00, 0x00, 0xf8, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08c0-0x08ff */
+  0x00, 0x00, 0x03, 0xff, 0x00, 0x00, 0x00, 0x00, /* 0x0880-0x08bf */
+  0x00, 0xfc, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08c0-0x08ff */
   0x07, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x14, /* 0x0900-0x093f */
   0xfe, 0x21, 0xfe, 0x00, 0x0c, 0x00, 0x00, 0x00, /* 0x0940-0x097f */
   0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, /* 0x0980-0x09bf */
@@ -101,7 +101,7 @@ static const unsigned char nonspacing_table_data[46*64] = {
   0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x0b80-0x0bbf */
   0x01, 0x20, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x0bc0-0x0bff */
   /* 0x0c00-0x0dff */
-  0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc0, /* 0x0c00-0x0c3f */
+  0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xd0, /* 0x0c00-0x0c3f */
   0xc1, 0x3d, 0x60, 0x00, 0x0c, 0x00, 0x00, 0x00, /* 0x0c40-0x0c7f */
   0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, /* 0x0c80-0x0cbf */
   0x00, 0x30, 0x00, 0x00, 0x0c, 0x00, 0x00, 0x00, /* 0x0cc0-0x0cff */
@@ -141,12 +141,12 @@ static const unsigned char nonspacing_table_data[46*64] = {
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1640-0x167f */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1680-0x16bf */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x16c0-0x16ff */
-  0x00, 0x00, 0x1c, 0x00, 0x00, 0x00, 0x1c, 0x00, /* 0x1700-0x173f */
+  0x00, 0x00, 0x1c, 0x00, 0x00, 0x00, 0x0c, 0x00, /* 0x1700-0x173f */
   0x00, 0x00, 0x0c, 0x00, 0x00, 0x00, 0x0c, 0x00, /* 0x1740-0x177f */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xb0, 0x3f, /* 0x1780-0x17bf */
   0x40, 0xfe, 0x0f, 0x20, 0x00, 0x00, 0x00, 0x00, /* 0x17c0-0x17ff */
   /* 0x1800-0x19ff */
-  0x00, 0x78, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1800-0x183f */
+  0x00, 0xf8, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1800-0x183f */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1840-0x187f */
   0x60, 0x00, 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, /* 0x1880-0x18bf */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18c0-0x18ff */
@@ -158,7 +158,7 @@ static const unsigned char nonspacing_table_data[46*64] = {
   0x00, 0x00, 0x80, 0x09, 0x00, 0x00, 0x00, 0x00, /* 0x1a00-0x1a3f */
   0x00, 0x00, 0x40, 0x7f, 0xe5, 0x1f, 0xf8, 0x9f, /* 0x1a40-0x1a7f */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, /* 0x1a80-0x1abf */
-  0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1ac0-0x1aff */
+  0xff, 0x7f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1ac0-0x1aff */
   0x0f, 0x00, 0x00, 0x00, 0x00, 0x00, 0xd0, 0x17, /* 0x1b00-0x1b3f */
   0x04, 0x00, 0x00, 0x00, 0x00, 0xf8, 0x0f, 0x00, /* 0x1b40-0x1b7f */
   0x03, 0x00, 0x00, 0x00, 0x3c, 0x3b, 0x00, 0x00, /* 0x1b80-0x1bbf */
@@ -171,7 +171,7 @@ static const unsigned char nonspacing_table_data[46*64] = {
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1d00-0x1d3f */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1d40-0x1d7f */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1d80-0x1dbf */
-  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xfb, /* 0x1dc0-0x1dff */
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x1dc0-0x1dff */
   /* 0x2000-0x21ff */
   0x00, 0xf8, 0x00, 0x00, 0x00, 0x7c, 0x00, 0x00, /* 0x2000-0x203f */
   0x00, 0x00, 0x00, 0x00, 0xdf, 0xff, 0x00, 0x00, /* 0x2040-0x207f */
@@ -296,13 +296,13 @@ static const unsigned char nonspacing_table_data[46*64] = {
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10ec0-0x10eff */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10f00-0x10f3f */
   0xc0, 0xff, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10f40-0x10f7f */
-  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10f80-0x10fbf */
+  0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10f80-0x10fbf */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10fc0-0x10fff */
   /* 0x11000-0x111ff */
   0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, /* 0x11000-0x1103f */
-  0x7f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80, /* 0x11040-0x1107f */
+  0x7f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x19, 0x80, /* 0x11040-0x1107f */
   0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x78, 0x26, /* 0x11080-0x110bf */
-  0x00, 0x20, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x110c0-0x110ff */
+  0x04, 0x20, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x110c0-0x110ff */
   0x07, 0x00, 0x00, 0x00, 0x80, 0xef, 0x1f, 0x00, /* 0x11100-0x1113f */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x08, 0x00, /* 0x11140-0x1117f */
   0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc0, 0x7f, /* 0x11180-0x111bf */
@@ -406,6 +406,15 @@ static const unsigned char nonspacing_table_data[46*64] = {
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1bd40-0x1bd7f */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1bd80-0x1bdbf */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1bdc0-0x1bdff */
+  /* 0x1ce00-0x1cfff */
+  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1ce00-0x1ce3f */
+  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1ce40-0x1ce7f */
+  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1ce80-0x1cebf */
+  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1cec0-0x1ceff */
+  0xff, 0xff, 0xff, 0xff, 0xff, 0x3f, 0xff, 0xff, /* 0x1cf00-0x1cf3f */
+  0x7f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1cf40-0x1cf7f */
+  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1cf80-0x1cfbf */
+  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1cfc0-0x1cfff */
   /* 0x1d000-0x1d1ff */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1d000-0x1d03f */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1d040-0x1d07f */
@@ -445,7 +454,7 @@ static const unsigned char nonspacing_table_data[46*64] = {
   /* 0x1e200-0x1e3ff */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1e200-0x1e23f */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1e240-0x1e27f */
-  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1e280-0x1e2bf */
+  0x00, 0x00, 0x00, 0x00, 0x00, 0x40, 0x00, 0x00, /* 0x1e280-0x1e2bf */
   0x00, 0x00, 0x00, 0x00, 0x00, 0xf0, 0x00, 0x00, /* 0x1e2c0-0x1e2ff */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1e300-0x1e33f */
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x1e340-0x1e37f */
@@ -490,9 +499,9 @@ static const signed char nonspacing_table_ind[248] = {
   -1, -1, -1, -1, -1, -1, -1, -1, /* 0x19000-0x19fff */
   -1, -1, -1, -1, -1, -1, -1, -1, /* 0x1a000-0x1afff */
   -1, -1, -1, -1, -1, -1, 39, -1, /* 0x1b000-0x1bfff */
-  -1, -1, -1, -1, -1, -1, -1, -1, /* 0x1c000-0x1cfff */
-  40, 41, -1, -1, -1, 42, -1, -1, /* 0x1d000-0x1dfff */
-  43, 44, -1, -1, 45, -1, -1, -1  /* 0x1e000-0x1efff */
+  -1, -1, -1, -1, -1, -1, -1, 40, /* 0x1c000-0x1cfff */
+  41, 42, -1, -1, -1, 43, -1, -1, /* 0x1d000-0x1dfff */
+  44, 45, -1, -1, 46, -1, -1, -1  /* 0x1e000-0x1efff */
 };
 
 /* Determine number of column positions required for UC.  */
@@ -585,7 +594,9 @@ uc_width (ucs4_t uc, const char *encoding)
           || (uc >= 0x17000 && uc < 0x187f8) /* Tangut */
           || (uc >= 0x18800 && uc < 0x18cd6) /* Tangut components */
           || (uc >= 0x18d00 && uc < 0x18d09) /* Tangul Ideograph Supplement */
-          || (uc >= 0x1b000 && uc < 0x1b120) /* Kana supplement, Kana Extended-A */
+          || ((uc >= 0x1aff0 && uc < 0x1afff) /* Katakana letter Minnan */
+              && uc != 0x1aff4 && uc != 0x1affc)
+          || (uc >= 0x1b000 && uc < 0x1b123) /* Kana supplement, Kana Extended-A */
           || (uc >= 0x1b150 && uc < 0x1b153) /* Small Hiragana */
           || (uc >= 0x1b164 && uc < 0x1b168) /* Small Katakana */
           || (uc >= 0x1b170 && uc < 0x1b2fc) /* Nushu */
@@ -621,19 +632,23 @@ uc_width (ucs4_t uc, const char *encoding)
                   || uc == 0x1f6cc
                   || (uc >= 0x1f6d0 && uc < 0x1f6d3)
                   || (uc >= 0x1f6d5 && uc < 0x1f6d8)
+                  || (uc >= 0x1f6dd && uc < 0x1f6e0)
                   || (uc >= 0x1f6eb && uc < 0x1f6ed)
                   || (uc >= 0x1f6f4 && uc < 0x1f6fd)
-                  || (uc >= 0x1f7e0 && uc < 0x1f7ec)))
+                  || (uc >= 0x1f7e0 && uc < 0x1f7ec)
+                  || uc == 0x1f7f0))
           || ((uc >= 0x1f90c && uc < 0x1fa00)
               && uc != 0x1f93b && uc != 0x1f946)
           || ((uc >> 9) == 0xfd
               && ((uc >= 0x1fa70 && uc < 0x1fa75)
-                  || (uc >= 0x1fa78 && uc < 0x1fa7b)
+                  || (uc >= 0x1fa78 && uc < 0x1fa7d)
                   || (uc >= 0x1fa80 && uc < 0x1fa87)
-                  || (uc >= 0x1fa90 && uc < 0x1faa9)
-                  || (uc >= 0x1fab0 && uc < 0x1fab7)
-                  || (uc >= 0x1fac0 && uc < 0x1fac3)
-                  || (uc >= 0x1fad0 && uc < 0x1fad7)))
+                  || (uc >= 0x1fa90 && uc < 0x1faad)
+                  || (uc >= 0x1fab0 && uc < 0x1fabb)
+                  || (uc >= 0x1fac0 && uc < 0x1fac6)
+                  || (uc >= 0x1fad0 && uc < 0x1fada)
+                  || (uc >= 0x1fae0 && uc < 0x1fae8)
+                  || (uc >= 0x1faf0 && uc < 0x1faf7)))
           || (uc >= 0x20000 && uc <= 0x2ffff) /* Supplementary Ideographic Plane */
           || (uc >= 0x30000 && uc <= 0x3ffff) /* Tertiary Ideographic Plane */
      )   )