[Emacs-diffs] Changes to emacs/lisp/international/encoded-kb.el,v

[Stefan Monnier]

CVSROOT:        /sources/emacs
Module name:    emacs
Changes by:     Stefan Monnier <monnier>        08/06/15 04:43:35

Index: international/encoded-kb.el
===================================================================
RCS file: /sources/emacs/emacs/lisp/international/encoded-kb.el,v
retrieving revision 1.45
retrieving revision 1.46
diff -u -b -r1.45 -r1.46
--- international/encoded-kb.el 6 May 2008 04:18:11 -0000       1.45
+++ international/encoded-kb.el 15 Jun 2008 04:43:35 -0000      1.46
@@ -219,8 +219,9 @@
 
 (defun encoded-kbd-self-insert-utf-8 (arg)
   (interactive "p")
-  (let ((char (encoded-kbd-last-key))
-       len)
+  (let* ((lead (encoded-kbd-last-key))
+         (char lead)
+         len event)
     (cond ((< char #xE0)
           (setq len 1 char (logand char #x1F)))
          ((< char #xF0)
@@ -230,8 +231,22 @@
          (t
           (setq len 4 char 0)))
     (while (> len 0)
-      (setq char (logior (lsh char 6) (logand (read-char-exclusive) #x3F))
-           len (1- len)))
+      (setq event (read-char-exclusive))
+      (if (and (>= event #x80) (< event #xc0))
+          ;; Valid utf-8 sequence.
+          (setq char (logior (lsh char 6) (- event #x80))
+                len (1- len))
+        ;; Invalid utf-8 sequence.  Might be because Quail got involved
+        ;; in-between and the bytes we thought we were reading were actually
+        ;; latin-1 chars.  Let's presume that `event' is the second "byte",
+        ;; i.e. there weren't any "apprently correct" between `lead' and
+        ;; `event': it's easy to recover in this case, and the more general
+        ;; case seems pretty unlikely.
+        ;; FIXME: We should really do encoded-kbd decoding before processing
+        ;; input-methods.
+        (push event unread-command-events)
+        (setq char lead)
+        (setq len 0)))
     (vector char)))
 
 (defun encoded-kbd-setup-keymap (keymap coding)