Fix minor inconsistencies in 'char-script-table'

* admin/unidata/blocks.awk (name2alias): Map some obscure blocks
to their native scripts, to follow Scripts.txt.

* lisp/international/characters.el (char-script-table): Add
few exceptions.
* lisp/international/fontset.el (script-representative-chars):
Remove scripts no longer used.

diff --git a/admin/unidata/blocks.awk b/admin/unidata/blocks.awk
index 48d8c873c7a7f4a55fd991b75e7308a7a3b95026..5f392b5ad3540f932e3e2cb818deb104b32f5b6a 100755 (executable)
--- a/admin/unidata/blocks.awk
+++ b/admin/unidata/blocks.awk
@@ -98,7 +98,7 @@ function name2alias(name   , w, w2) {
     else if (name ~ /arabic/) return "arabic"
     else if (name ~ /^greek/) return "greek"
     else if (name ~ /^coptic/) return "coptic"
-    else if (name ~ /cuneiform number/) return "cuneiform-numbers-and-punctuation"
+    else if (name ~ /cuneiform number/) return "cuneiform"
     else if (name ~ /cuneiform/) return "cuneiform"
     else if (name ~ /mathematical alphanumeric symbol/) return "mathematical"
     else if (name ~ /punctuation|mathematical|arrows|currency|superscript|small form variants|geometric|dingbats|enclosed|alchemical|pictograph|emoticon|transport/) return "symbol"
@@ -113,9 +113,11 @@ function name2alias(name   , w, w2) {
     else if (name ~/^(specials|tags)$/) return 0
     else if (name ~ /linear b/) return "linear-b"
     else if (name ~ /aramaic/) return "aramaic"
-    else if (name ~ /rumi num/) return "rumi-number"
+    else if (name ~ /rumi num/) return "arabic"
     else if (name ~ /duployan|shorthand/) return "duployan-shorthand"
     else if (name ~ /sutton signwriting/) return "sutton-sign-writing"
+    else if (name ~ /sinhala archaic number/) return "sinhala"
+    else if (name ~ /tangut components/) return "tangut"
 
     sub(/^small /, "", name)
     sub(/ (extended|extensions*|supplement).*/, "", name)

diff --git a/lisp/international/characters.el b/lisp/international/characters.el
index 080e7898c47f5990d8a280b3f95e4dda2e629067..3ff280f480235374d9529401faf7a90986b52386 100644 (file)
--- a/lisp/international/characters.el
+++ b/lisp/international/characters.el
@@ -1440,6 +1440,10 @@ Setup `char-width-table' appropriate for non-CJK language environment."
    (set-char-table-range char-script-table range 'tibetan))
  'tibetan)
 
+;; Fix some exceptions that blocks.awk/Blocks.txt couldn't get right.
+(set-char-table-range char-script-table '(#x2ea . #x2eb) 'bopomofo)
+(set-char-table-range char-script-table #xab65 'greek)
+
 \f
 ;;; Setting unicode-category-table.
 

diff --git a/lisp/international/fontset.el b/lisp/international/fontset.el
index a2e0838a427ea71cf01140154ff57d33ec190d6c..cf82514095596cc62c41a11557c37c4b7b05f35c 100644 (file)
--- a/lisp/international/fontset.el
+++ b/lisp/international/fontset.el
@@ -231,7 +231,6 @@
        (elymaic #x10FE0)
        (old-uyghur #x10F70)
        (mahajani #x11150)
-       (sinhala-archaic-number #x111E1)
        (khojki #x11200)
        (khudawadi #x112B0)
        (grantha #x11305)
@@ -253,7 +252,6 @@
        (gunjala-gondi #x11D60)
        (makasar #x11EE0)
        (cuneiform #x12000)
-       (cuneiform-numbers-and-punctuation #x12400)
        (cypro-minoan #x12F90)
        (egyptian #x13000)
        (mro #x16A40)
@@ -262,7 +260,6 @@
        (pahawh-hmong #x16B11)
        (medefaidrin #x16E40)
        (tangut #x17000)
-       (tangut-components #x18800)
        (khitan-small-script #x18B00)
        (nushu #x1B170)
        (duployan-shorthand #x1BC20)