Sync ctype definitions for the UTF-8 locale to FreeBSD, fixing width of

various zero-width characters (e.g. diacritical marks). Also fix runetype
mask definitions so that mklocale interprets zero width properly.
Diff from Alexander Polakov.
Character definition changes checked against Unicode 5.2 by me.
ok matthew nicm

1 files changed, 35 insertions, 16 deletions

diff --git a/share/locale/ctype/en_US.UTF-8.src b/share/locale/ctype/en_US.UTF-8.src
index e576c2b2ce9..b091a5ff6ad 100644
--- a/share/locale/ctype/en_US.UTF-8.src
+++ b/share/locale/ctype/en_US.UTF-8.src
@@ -491,9 +491,9 @@ SWIDTH1   0x02b0 - 0x02ee
  * U+0300 - U+036F : Combining Diacritical Marks
  */
 
-GRAPH     0x0300 - 0x034f  0x0360 - 0x036f
-PRINT     0x0300 - 0x034f  0x0360 - 0x036f
-SWIDTH1   0x0300 - 0x034f  0x0360 - 0x036f
+GRAPH     0x0300 - 0x034e  0x0350 - 0x036f
+PRINT     0x0300 - 0x034e  0x0350 - 0x036f
+SWIDTH0   0x0300 - 0x034e  0x0350 - 0x036f
 
 MAPUPPER  < 0x0345 0x0399 >
 
@@ -583,7 +583,7 @@ LOWER     0x04b9  0x04bb  0x04bd  0x04bf  0x04c2  0x04c4  0x04c6
 LOWER     0x04c8  0x04ca  0x04cc  0x04ce  0x04d1  0x04d3  0x04d5
 LOWER     0x04d7  0x04d9  0x04db  0x04dd  0x04df  0x04e1  0x04e3
 LOWER     0x04e5  0x04e7  0x04e9  0x04eb  0x04ed  0x04ef  0x04f1
-LOWER     0x04f3  0x04f5  0x04f9
+LOWER     0x04f3  0x04f5  0x04f7  0x04f9
 PUNCT     0x0482
 UPPER     0x0400 - 0x042f  0x0460  0x0462  0x0464  0x0466  0x0468
 UPPER     0x046a  0x046c  0x046e  0x0470  0x0472  0x0474  0x0476
@@ -595,9 +595,10 @@ UPPER     0x04b8  0x04ba  0x04bc  0x04be  0x04c0  0x04c1  0x04c3
 UPPER     0x04c5  0x04c7  0x04c9  0x04cb  0x04cd  0x04d0  0x04d2
 UPPER     0x04d4  0x04d6  0x04d8  0x04da  0x04dc  0x04de  0x04e0
 UPPER     0x04e2  0x04e4  0x04e6  0x04e8  0x04ea  0x04ec  0x04ee
-UPPER     0x04f0  0x04f2  0x04f4  0x04f8
-PRINT     0x0400 - 0x0486  0x0488 - 0x04ce  0x04d0 - 0x04f5  0x04f8  0x04f9
-SWIDTH1   0x0400 - 0x0486  0x0488 - 0x04ce  0x04d0 - 0x04f5  0x04f8  0x04f9
+UPPER     0x04f0  0x04f2  0x04f4  0x04f6  0x04f8
+PRINT     0x0400 - 0x0486  0x0488 - 0x04ce  0x04d0 - 0x04f9
+SWIDTH0   0x0483 - 0x0486  0x0488 - 0x0489
+SWIDTH1   0x0400 - 0x0482  0x048a - 0x04ce  0x04d0 - 0x04f9
 
 MAPUPPER  < 0x0430 - 0x044f : 0x0410 >
 MAPUPPER  < 0x0450 - 0x045f : 0x0400 >
@@ -671,6 +672,7 @@ MAPUPPER  < 0x04ef 0x04ee >
 MAPUPPER  < 0x04f1 0x04f0 >
 MAPUPPER  < 0x04f3 0x04f2 >
 MAPUPPER  < 0x04f5 0x04f4 >
+MAPUPPER  < 0x04f7 0x04f6 >
 MAPUPPER  < 0x04f9 0x04f8 >
 MAPLOWER  < 0x0400 - 0x040f : 0x0450 >
 MAPLOWER  < 0x0410 - 0x042f : 0x0430 >
@@ -744,6 +746,7 @@ MAPLOWER  < 0x04ee 0x04ef >
 MAPLOWER  < 0x04f0 0x04f1 >
 MAPLOWER  < 0x04f2 0x04f3 >
 MAPLOWER  < 0x04f4 0x04f5 >
+MAPLOWER  < 0x04f6 0x04f7 >
 MAPLOWER  < 0x04f8 0x04f9 >
 
 
@@ -1052,7 +1055,8 @@ DIGIT     0x0e50 - 0x0e59
 GRAPH     0x0e01 - 0x0e3a  0x0e3f - 0x0e5b
 PUNCT     0x0e3f  0x0e4f  0x0e5a  0x0e5b
 PRINT     0x0e01 - 0x0e3a  0x0e3f - 0x0e5b
-SWIDTH1   0x0e01 - 0x0e3a  0x0e3f - 0x0e5b
+SWIDTH0   0x0e31   0x0e34 - 0x0e3a  0x0e47 - 0x0e4e
+SWIDTH1   0x0e01 - 0x0e30  0x0e32 - 0x0e33  0x0e3f - 0x0e46  0x0e4f - 0x0e5b
 
 TODIGIT   < 0x0e50 - 0x0e59 : 0x0000 >
 
@@ -1283,6 +1287,14 @@ SWIDTH1   0x1800 - 0x180d  0x1810 - 0x1819  0x1820 - 0x1877  0x1880 - 0x18a9
 
 TODIGIT   < 0x1810 - 0x1819 : 0x0000 >
 
+/*
+ * U+1DC0 - U+1DFF : Combining Diacritical Marks Supplement
+ */
+
+GRAPH     0x1DC0 - 0x1DC3
+PRINT     0x1DC0 - 0x1DC3
+SWIDTH0   0x1DC0 - 0x1DC3
+
 
 /*
  * U+1E00 - U+1EFF : Latin Extended Additional
@@ -1672,7 +1684,8 @@ SPACE     0x2000 - 0x200b  0x2028  0x2029  0x202f  0x205f
 BLANK     0x2000 - 0x200b  0x202f  0x205f
 PRINT     0x2000 - 0x200b  0x2010 - 0x2029  0x202f - 0x2052  0x2057
 PRINT     0x205f
-SWIDTH1   0x2000 - 0x200b  0x2010 - 0x2029  0x202f - 0x2052  0x2057
+SWIDTH1   0x2000 - 0x200a  0x2010 - 0x2029  0x202f - 0x2052  0x2057
+SWIDTH0   0x200b - 0x200d
 SWIDTH1   0x205f
 
 
@@ -1707,9 +1720,9 @@ SWIDTH1   0x20a0 - 0x20b1
  * U+20D0 - U+20FF : Combining Diacritical Marks for Symbols
  */
 
-GRAPH     0x20d0 - 0x20ea
-PRINT     0x20d0 - 0x20ea
-SWIDTH1   0x20d0 - 0x20ea
+GRAPH     0x20d0 - 0x20eb
+PRINT     0x20d0 - 0x20eb
+SWIDTH0   0x20d0 - 0x20eb
 
 
 /*
@@ -1987,7 +2000,8 @@ GRAPH     0x3041 - 0x3096  0x3099 - 0x309f
 PUNCT     0x309b  0x309c
 PRINT     0x3041 - 0x3096  0x3099 - 0x309f
 PHONOGRAM 0x3041 - 0x3096  0x309f
-SWIDTH2   0x3041 - 0x3096  0x3099 - 0x309f
+SWIDTH0   0x3099 - 0x309a
+SWIDTH2   0x3041 - 0x3096  0x309b - 0x309f
 
 
 /*
@@ -2211,7 +2225,7 @@ SWIDTH1   0xfe00 - 0xfe0f
 
 GRAPH     0xfe20 - 0xfe23
 PRINT     0xfe20 - 0xfe23
-SWIDTH1   0xfe20 - 0xfe23
+SWIDTH0   0xfe20 - 0xfe23
 
 
 /*
@@ -2333,8 +2347,13 @@ CONTROL   0x1d173 - 0x1d17a
 GRAPH     0x1d100 - 0x1d126  0x1d12a - 0x1d172  0x1d17b - 0x1d1dd
 PUNCT     0x1d100 - 0x1d126  0x1d12a - 0x1d164  0x1d16a - 0x1d16c
 PUNCT     0x1d183  0x1d184  0x1d18c - 0x1d1a9  0x1d1ae - 0x1d1dd
-PRINT     0x1d100 - 0x1d126  0x1d12a - 0x1d172  0x1d17b - 0x1d1dd
-SWIDTH1   0x1d100 - 0x1d126  0x1d12a - 0x1d172  0x1d17b - 0x1d1dd
+PRINT     0x1d100 - 0x1d126  0x1d12a - 0x1d158  0x1d15a - 0x1d172
+PRINT     0x1d17b - 0x1d1dd
+SWIDTH0   0x1d165 - 0x1d169  0x1d16d - 0x1d172  0x1d17b - 0x1d182
+SWIDTH0   0x1d185 - 0x1d18b  0x1d1aa - 0x1d1ad
+SWIDTH1   0x1d100 - 0x1d126  0x1d12a - 0x1d158  0x1d15a - 0x1d164
+SWIDTH1   0x1d16a - 0x1d16c  0x1d183   0x1d184  0x1d18c - 0x1d1a9
+SWIDTH1   0x1d1ae - 0x1d1dd
 
 
 /*