utf-8.el

[Stefan Monnier]

Does anyone see a problem with the simple patch below?
Also, could anyone confirm that the docstring of mule-utf-8 is correct in
saying that invalid utf-8 sequences are not always correctly preserved?
Why is that?  Can't we fix it?

Also could anyone explain to me why `utf-8-compose' needs to lookup the
hashtable (get 'utf-subst-table-for-decode 'translation-hash-table), since
it looks to me like ccl-decode-mule-utf-8 already takes care of decoding
chars that are in this table.  I also don't understand the following part of
the code:

          (if (= l 2)
              (put-text-property (point) (min (point-max) (+ l (point)))
                                 'display (format "\\%03o" ch))
            (compose-region (point) (+ l (point)) ?�))

what does it mean for l (the number of bytes) to be equal to 2?


        Stefan


--- orig/lisp/international/utf-8.el
+++ mod/lisp/international/utf-8.el
@@ -2,7 +2,7 @@
 
 ;; Copyright (C) 2001, 2004 Electrotechnical Laboratory, JAPAN.
 ;; Licensed to the Free Software Foundation.
-;; Copyright (C) 2001, 2002 Free Software Foundation, Inc.
+;; Copyright (C) 2001, 2002, 2005  Free Software Foundation, Inc.
 
 ;; Author: TAKAHASHI Naoto  <address@hidden>
 ;; Maintainer: FSF
@@ -259,7 +259,7 @@
                                 (funcall decode-char-no-trans (car x))
                                 (funcall decode-char-no-trans (cdr x))))
                     ranges "")))
-  ;; These forces loading and settting tables for
+  ;; This forces loading and setting tables for
   ;; utf-translate-cjk-mode.
   (setq utf-translate-cjk-lang-env nil
        ucs-mule-cjk-to-unicode (make-hash-table :test 'eq)
@@ -951,10 +951,7 @@
   (save-excursion
     (save-restriction
       (narrow-to-region (point) (+ (point) length))
-      ;; Can't do eval-when-compile to insert a multibyte constant
-      ;; version of the string in the loop, since it's always loaded as
-      ;; unibyte from a byte-compiled file.
-      (let ((range (string-as-multibyte "^\xc0-\xc3\xe1-\xf7"))
+      (let ((range "^\xc0-\xc3\xe1-\xf7")
            (buffer-multibyte enable-multibyte-characters)
            hash-table ch)
        (set-buffer-multibyte t)
@@ -1036,8 +1033,7 @@
     mule-unicode-0100-24ff
     mule-unicode-2500-33ff
     mule-unicode-e000-ffff
-    ,@(if utf-translate-cjk-mode
-         utf-translate-cjk-charsets))
+    ,@utf-translate-cjk-charsets)
    (mime-charset . utf-8)
    (coding-category . coding-category-utf-8)
    (valid-codes (0 . 255))
@@ -1054,23 +1050,23 @@
 ;; I think this needs special private charsets defined for the
 ;; untranslated sequences, if it's going to work well.
 
-;;; (defun utf-8-compose-function (pos to pattern &optional string)
-;;;   (let* ((prop (get-char-property pos 'composition string))
-;;;     (l (and prop (- (cadr prop) (car prop)))))
-;;;     (cond ((and l (> l (- to pos)))
-;;;       (delete-region pos to))
-;;;      ((and (> (char-after pos) 224)
-;;;            (< (char-after pos) 256)
-;;;            (save-restriction
-;;;              (narrow-to-region pos to)
-;;;              (utf-8-compose)))
-;;;       t))))
-
-;;; (dotimes (i 96)
-;;;   (aset composition-function-table
-;;;    (+ 128 i)
-;;;    `((,(string-as-multibyte "[\200-\237\240-\377]")
-;;;       . utf-8-compose-function))))
+;; (defun utf-8-compose-function (pos to pattern &optional string)
+;;   (let* ((prop (get-char-property pos 'composition string))
+;;      (l (and prop (- (cadr prop) (car prop)))))
+;;     (cond ((and l (> l (- to pos)))
+;;        (delete-region pos to))
+;;       ((and (> (char-after pos) 224)
+;;             (< (char-after pos) 256)
+;;             (save-restriction
+;;               (narrow-to-region pos to)
+;;               (utf-8-compose)))
+;;        t))))
+
+;; (dotimes (i 96)
+;;   (aset composition-function-table
+;;     (+ 128 i)
+;;     `((,(string-as-multibyte "[\200-\237\240-\377]")
+;;        . utf-8-compose-function))))
 
 ;; arch-tag: b08735b7-753b-4ae6-b754-0f3efe4515c5
 ;;; utf-8.el ends here