21709 plus tweaks: use $KEYTIMEOUT for multibyte chars.Reset input state on invalid characters or EOF

ChangeLog

@@ -1,3 +1,11 @@
+2005-09-09  Peter Stephenson  <pws@csr.com>
+
+	* 21709 plus tweaks: Doc/Zsh/zle.yo, Src/builtin.c, Src/init.c,
+	Src/Zle/zle_keymap.c, Src/Zle/zle_main.c, Src/Zle/zle_misc.c,
+	Src/Zle/zle_vi.c: Use $KEYTIMOUT for bytes after the first
+	in a multibyte character.  Reset input state on invalid
+	character or EOF.
+
 2005-09-07  Clint Adams  <clint@zsh.org>
 
 	* 21704, 21705: Completion/Unix/Command/_date: completion for

Doc/Zsh/zle.yo

@@ -87,6 +87,14 @@ execute the binding.  This timeout is defined by the tt(KEYTIMEOUT) parameter;
 its default is 0.4 sec.  There is no timeout if the prefix string is not
 itself bound to a command.
 
+The key timeout is also applied when ZLE is reading the bytes from a
+multibyte character string when it is in the appropriate mode.  (This
+requires that the shell was compiled with multibyte mode enabled; typically
+also the locale has characters with the UTF-8 encoding, although any
+multibyte encoding known to the operating system is supported.)  If the
+second or a subsequent byte is not read within the timeout period, the
+shell acts as if tt(?) were typed and resets the input state.
+
 As well as ZLE commands, key sequences can be bound to other strings, by using
 `tt(bindkey -s)'.
 When such a sequence is read, the replacement string is pushed back as input,

Src/Zle/zle_keymap.c

@@ -1341,7 +1341,7 @@ getkeymapcmd(Keymap km, Thingy *funcp, char **strp)
 static int
 getkeybuf(int w)
 {
-    int c = getbyte(w);
+    int c = getbyte(w, NULL);
 
     if(c < 0)
 	return EOF;

Src/Zle/zle_main.c

@@ -628,13 +628,16 @@ raw_getbyte(int keytmout, char *cptr)
 
 /**/
 mod_export int
-getbyte(int keytmout)
+getbyte(int keytmout, int *timeout)
 {
     char cc;
     unsigned int ret;
     int die = 0, r, icnt = 0;
     int old_errno = errno, obreaks = breaks;
 
+    if (timeout)
+	*timeout = 0;
+
 #ifdef ZLE_UNICODE_SUPPORT
     /*
      * Reading a single byte always invalidates the status
@@ -660,8 +663,12 @@ getbyte(int keytmout)
 	    dont_queue_signals();
 	    r = raw_getbyte(keytmout, &cc);
 	    restore_queue_signals(q);
-	    if (r == -2)	/* timeout */
+	    if (r == -2) {
+		/* timeout */
+		if (timeout)
+		    *timeout = 1;
 		return lastchar = EOF;
+	    }
 	    if (r == 1)
 		break;
 	    if (r == 0) {
@@ -733,7 +740,7 @@ getbyte(int keytmout)
 mod_export ZLE_INT_T
 getfullchar(int keytmout)
 {
-    int inchar = getbyte(keytmout);
+    int inchar = getbyte(keytmout, NULL);
 
 #ifdef ZLE_UNICODE_SUPPORT
     return getrestchar(inchar);
@@ -759,7 +766,7 @@ getrestchar(int inchar)
     /* char cnull = '\0'; */
     char c = inchar;
     wchar_t outchar;
-    int ret;
+    int ret, timeout;
     static mbstate_t ps;
 
     /*
@@ -769,8 +776,11 @@ getrestchar(int inchar)
      */
     lastchar_wide_valid = 1;
 
-    if (inchar == EOF)
+    if (inchar == EOF) {
+	/* End of input, so reset the shift state. */
+	memset(&ps, 0, sizeof(ps));
 	return lastchar_wide = WEOF;
+    }
 
     /*
      * Return may be zero if we have a NULL; handle this like
@@ -781,15 +791,34 @@ getrestchar(int inchar)
 	    /*
 	     * Invalid input.  Hmm, what's the right thing to do here?
 	     */
+	    memset(&ps, 0, sizeof(ps));
 	    return lastchar_wide = WEOF;
 	}
 
-	/* No timeout here as we really need the character. */
-	inchar = getbyte(0);
+	/*
+	 * Always apply KEYTIMEOUT to the remains of the input
+	 * character.  The parts of a multibyte character should
+	 * arrive together.  If we don't do this the input can
+	 * get stuck if an invalid byte sequence arrives.
+	 */
+	inchar = getbyte(1, &timeout);
 	/* getbyte deliberately resets lastchar_wide_valid */
 	lastchar_wide_valid = 1;
-	if (inchar == EOF)
-	    return lastchar_wide = WEOF;
+	if (inchar == EOF) {
+	    memset(&ps, 0, sizeof(ps));
+	    if (timeout)
+	    {
+		/*
+		 * This case means that we got a valid initial byte
+		 * (since we tested for EOF above), but the followup
+		 * timed out.  This probably indicates a duff character.
+		 * Return a '?'.
+		 */
+		lastchar_wide = L'?';
+	    }
+	    else
+		return lastchar_wide = WEOF;
+	}
 	c = inchar;
     }
     return lastchar_wide = (ZLE_INT_T)outchar;

Src/Zle/zle_misc.c

@@ -595,7 +595,7 @@ universalargument(char **args)
      *
      * Hence for now this remains byte-by-byte.
      */
-    while ((gotk = getbyte(0)) != EOF) {
+    while ((gotk = getbyte(0, NULL)) != EOF) {
 	if (gotk == '-' && !digcnt) {
 	    minus = -1;
 	    digcnt++;

Src/Zle/zle_vi.c

@@ -108,7 +108,7 @@ vigetkey(void)
     char m[3], *str;
     Thingy cmd;
 
-    if(getbyte(0) == EOF)
+    if (getbyte(0, NULL) == EOF)
 	return ZLEEOF;
 
     m[0] = lastchar;

Src/builtin.c

@@ -4539,7 +4539,7 @@ bin_read(char *name, char **args, Options ops, UNUSED(int func))
 
 	do {
 	    if (izle) {
-		if ((val = getkeyptr(0)) < 0)
+		if ((val = getkeyptr(0, NULL)) < 0)
 		    break;
 		*bptr++ = (char) val;
 		nchars--;
@@ -4595,7 +4595,7 @@ bin_read(char *name, char **args, Options ops, UNUSED(int func))
 
 	/* get, and store, reply */
 	if (izle) {
-	    int key = getkeyptr(0);
+	    int key = getkeyptr(0, NULL);
 
 	    readbuf[0] = (key == 'y' ? 'y' : 'n');
 	} else {
@@ -4818,7 +4818,7 @@ zread(int izle, int *readchar)
     int ret;
 
     if (izle) {
-	int c = getkeyptr(0);
+	int c = getkeyptr(0, NULL);
 
 	return (c < 0 ? EOF : c);
     }

Src/init.c

@@ -82,7 +82,7 @@ mod_export int hasam, hasxn;
 /* Pointer to read-key function from zle */
 
 /**/
-mod_export int (*getkeyptr) _((int));
+mod_export int (*getkeyptr) _((int, int *));
 
 /* SIGCHLD mask */