(eight-bit): Add :docstring,

:short-name properties.
(cp851): Doc fix.
(unicode-bmp): New.

diff --git a/lisp/ChangeLog b/lisp/ChangeLog
index b3b512a12280529ee5712b881df964b395f49e13..1252a054f01199355fe997eefaf0944c0ae8d625 100644 (file)
--- a/lisp/ChangeLog
+++ b/lisp/ChangeLog
@@ -1,3 +1,16 @@
+2002-09-08  Dave Love  <fx@gnu.org>
+
+       * international/mule-conf.el (eight-bit): Add :docstring,
+       :short-name properties.
+       (cp851): Doc fix.
+       (unicode-bmp): New.
+
+       * case-table.el (set-case-syntax-pair): Remove check on byte
+       lengths.
+
+       * language/european.el (cp858): New.
+       ("Turkish"): Add special case rules.
+
 2002-09-05  Dave Love  <fx@gnu.org>
 
        * international/characters.el: Make \e,_/\e(B and \e,A\7f\e(B a case pair.

diff --git a/lisp/international/mule-conf.el b/lisp/international/mule-conf.el
index f1dbd6b100ae1741a0ba756e273f14712eee3cce..f999ba8529d26c9f95809f80dc1953f5e5f24e9a 100644 (file)
--- a/lisp/international/mule-conf.el
+++ b/lisp/international/mule-conf.el
@@ -49,14 +49,14 @@
 
 ;;; Definitions of character sets.
 
-;; The charsets `ascii' and `unicode' are already defined in charset.c
-;; as below:
+;; The charsets `ascii', `unicode' and `eight-bit' are already defined
+;; in charset.c as below:
 ;;
 ;; (define-charset 'ascii
 ;;   ""
 ;;   :dimension 1
 ;;   :code-space [0 127]
-;;   :iso-final-char ?A
+;;   :iso-final-char ?B
 ;;   :ascii-compatible-p t
 ;;   :emacs-mule-id 0
 ;;   :code-offset 0)
@@ -68,6 +68,12 @@
 ;;   :ascii-compatible-p t
 ;;   :code-offset 0)
 ;;
+;; (define-charset 'eight-bit
+;;   ""
+;;   :dimension 1
+;;   :code-space [128 255]
+;;   :code-offset #x3FFF80)
+;;
 ;; We now set :docstring, :short-name, and :long-name properties.
 
 (put-charset-property
@@ -88,6 +94,8 @@
  'unicode :short-name "Unicode")
 (put-charset-property
  'unicode :long-name "Unicode (ISO10646)")
+(put-charset-property 'eight-bit :docstring "Raw bytes 0-255")
+(put-charset-property 'eight-bit :short-name "Raw bytes")
 
 (define-charset-alias 'ucs 'unicode)
 
@@ -201,6 +209,7 @@
 (fmakunbound 'define-iso-single-byte-charset)
 
 ;; Can this be shared with 8859-11?
+;; N.b. not all of these are defined unicodes.
 (define-charset 'thai-tis620
   "TIS620.2533"
   :short-name "TIS620.2533"
@@ -639,7 +648,7 @@
   :map "cp775")
 
 (define-charset 'cp851
-  "CP851"
+  "CP851 (Greek)"
   :short-name "CP851"
   :code-space [0 255]
   :ascii-compatible-p t
@@ -762,6 +771,7 @@
 
 ;; Lao script.
 ;; Codes 0x21..0x7E are mapped to Unicode U+0E81..U+0EDF.
+;; Not all of them are defined unicodes.
 (define-charset 'lao
   "Lao characters (ISO10646 0E81..0EDF)"
   :short-name "Lao"
@@ -875,6 +885,12 @@
   :code-space [#x20 #x7F #x20 #x7F]
   :code-offset #x100)
 
+(define-charset 'unicode-bmp
+  "Unicode Basic Multilingual Plane"
+  :short-name "Unicode BMP"
+  :code-space [0 255 0 255]
+  :subset '(unicode 0 #xFFFF 0))
+
 (define-charset 'ethiopic
   "Ethiopic characters for Amharic and Tigrigna."
   :short-name "Ethiopic"