update unicode version

lib/std/text/unicode.kk

@@ -125,11 +125,11 @@ pub fun string/width( s : string ) : int {
 //--------------------------------------------------------------
 
 // These characters are considered wide, i.e. 2 columns wide.
-// https://www.unicode.org/Public/15.0.0/ucd/EastAsianWidth.txt 
+// https://www.unicode.org/Public/16.0.0/ucd/EastAsianWidth.txt 
 // See ranges with postfix ;W
 // 
 // Update with `python3 util/update-unicode.py -a`
-// TODO: Handle 'unassigned' ranges: (Following is an excerpt from https://www.unicode.org/Public/15.0.0/ucd/EastAsianWidth.txt )
+// TODO: Handle 'unassigned' ranges: (Following is an excerpt from https://www.unicode.org/Public/16.0.0/ucd/EastAsianWidth.txt )
 // - All code points, assigned or unassigned, that are not listed
 //      explicitly are given the value "N".
 // - The unassigned code points in the following blocks default to "W":
@@ -181,7 +181,7 @@ val asian-wide : delayed<total,rtree> = delay{
     single(0x2E80,0x2E99),
     single(0x2E9B,0x2EF3),
     single(0x2F00,0x2FD5),
-    single(0x2FF0,0x2FFB),
+    single(0x2FF0,0x2FFF),
     single(0x3001,0x3003),
     single(0x3004,0x3004),
     single(0x3005,0x3005),
@@ -237,7 +237,8 @@ val asian-wide : delayed<total,rtree> = delay{
     single(0x3192,0x3195),
     single(0x3196,0x319F),
     single(0x31A0,0x31BF),
-    single(0x31C0,0x31E3),
+    single(0x31C0,0x31E5),
+    single(0x31EF,0x31EF),
     single(0x31F0,0x31FF),
     single(0x3200,0x321E),
     single(0x3220,0x3229),
@@ -314,6 +315,7 @@ val asian-wide : delayed<total,rtree> = delay{
     single(0x17000,0x187F7),
     single(0x18800,0x18AFF),
     single(0x18B00,0x18CD5),
+    single(0x18CFF,0x18CFF),
     single(0x18D00,0x18D08),
     single(0x1AFF0,0x1AFF3),
     single(0x1AFF5,0x1AFFB),
@@ -368,11 +370,10 @@ val asian-wide : delayed<total,rtree> = delay{
     single(0x1F93C,0x1F945),
     single(0x1F947,0x1F9FF),
     single(0x1FA70,0x1FA7C),
-    single(0x1FA80,0x1FA88),
-    single(0x1FA90,0x1FABD),
-    single(0x1FABF,0x1FAC5),
-    single(0x1FACE,0x1FADB),
-    single(0x1FAE0,0x1FAE8),
+    single(0x1FA80,0x1FA89),
+    single(0x1FA8F,0x1FAC6),
+    single(0x1FACE,0x1FADC),
+    single(0x1FADF,0x1FAE9),
     single(0x1FAF0,0x1FAF8),
     single(0x20000,0x2A6DF),
     single(0x2A6E0,0x2A6FF),
@@ -383,7 +384,9 @@ val asian-wide : delayed<total,rtree> = delay{
     single(0x2B820,0x2CEA1),
     single(0x2CEA2,0x2CEAF),
     single(0x2CEB0,0x2EBE0),
-    single(0x2EBE1,0x2F7FF),
+    single(0x2EBE1,0x2EBEF),
+    single(0x2EBF0,0x2EE5D),
+    single(0x2EE5E,0x2F7FF),
     single(0x2F800,0x2FA1D),
     single(0x2FA1E,0x2FA1F),
     single(0x2FA20,0x2FFFD),

package.yaml

@@ -8,6 +8,9 @@
 # - support/vscode/koka.language-koka/package.json
 # - whatsnew.md, readme.md
 
+# Also update unicode asian-width list in `std/text/unicode`
+#  using the output of `python3 util/update-unicode.py -a` 
+#  after checking for a newer version of the unicode link it fetches from
 
 name:       koka
 version:    3.0.5

util/update-unicode.py

@@ -6,13 +6,14 @@
   parser.add_argument("-a", "--asian_wide", default=False, action='store_true')
   args = parser.parse_args()
   if args.asian_wide:
-    result = requests.get("https://www.unicode.org/Public/15.0.0/ucd/EastAsianWidth.txt")
+    # TODO: Check for latest version (right now it is 16.0.0), also two links in documentation in std/text/unicode
+    result = requests.get("https://www.unicode.org/Public/16.0.0/ucd/EastAsianWidth.txt")
     for line in result.text.split("\n"):
       values = line.split(";")
       if len(values) >= 2:
         width = values[1].split("#")[0].strip()
         if width == "W":
-          charrange = values[0].split("..")
+          charrange = values[0].strip().split("..")
           if len(charrange) == 2:
             print(f"    single(0x{charrange[0]},0x{charrange[1]}),")
           elif len(charrange) == 1: