[PATCH] tty utf8 mode

This sounds like a good moment to come with this patch.

This is essentially a five-year-old patch by Bruno Haible.  It
introduces utf8 mode, and the effect it has on erasing input characters.

(Side note - without stty support, this is not very useful, but now
the infrastructure is in place)

drivers/char/n_tty.c

@@ -172,6 +172,16 @@ ssize_t n_tty_chars_in_buffer(struct tty_struct *tty)
 	return n;
 }
 
+static inline int is_utf8_continuation(unsigned char c)
+{
+	return (c & 0xc0) == 0x80;
+}
+
+static inline int is_continuation(unsigned char c, struct tty_struct *tty)
+{
+	return I_IUTF8(tty) && is_utf8_continuation(c);
+}
+
 /*
  * Perform OPOST processing.  Returns -1 when the output device is
  * full and the character must be retried.
@@ -226,7 +236,7 @@ static int opost(unsigned char c, struct tty_struct *tty)
 		default:
 			if (O_OLCUC(tty))
 				c = toupper(c);
-			if (!iscntrl(c))
+			if (!iscntrl(c) && !is_continuation(c, tty))
 				tty->column++;
 			break;
 		}
@@ -330,7 +340,7 @@ static inline void finish_erasing(struct tty_struct *tty)
 static void eraser(unsigned char c, struct tty_struct *tty)
 {
 	enum { ERASE, WERASE, KILL } kill_type;
-	int head, seen_alnums;
+	int head, seen_alnums, cnt;
 	unsigned long flags;
 
 	if (tty->read_head == tty->canon_head) {
@@ -368,8 +378,18 @@ static void eraser(unsigned char c, struct tty_struct *tty)
 
 	seen_alnums = 0;
 	while (tty->read_head != tty->canon_head) {
-		head = (tty->read_head - 1) & (N_TTY_BUF_SIZE-1);
-		c = tty->read_buf[head];
+		head = tty->read_head;
+
+		/* erase a single possibly multibyte character */
+		do {
+			head = (head - 1) & (N_TTY_BUF_SIZE-1);
+			c = tty->read_buf[head];
+		} while (is_continuation(c, tty) && head != tty->canon_head);
+
+		/* do not partially erase */
+		if (is_continuation(c, tty))
+			break;
+
 		if (kill_type == WERASE) {
 			/* Equivalent to BSD's ALTWERASE. */
 			if (isalnum(c) || c == '_')
@@ -377,9 +397,10 @@ static void eraser(unsigned char c, struct tty_struct *tty)
 			else if (seen_alnums)
 				break;
 		}
+		cnt = (tty->read_head - head) & (N_TTY_BUF_SIZE-1);
 		spin_lock_irqsave(&tty->read_lock, flags);
 		tty->read_head = head;
-		tty->read_cnt--;
+		tty->read_cnt -= cnt;
 		spin_unlock_irqrestore(&tty->read_lock, flags);
 		if (L_ECHO(tty)) {
 			if (L_ECHOPRT(tty)) {
@@ -388,7 +409,12 @@ static void eraser(unsigned char c, struct tty_struct *tty)
 					tty->column++;
 					tty->erasing = 1;
 				}
+				/* if cnt > 1, output a multi-byte character */
 				echo_char(c, tty);
+				while (--cnt > 0) {
+					head = (head+1) & (N_TTY_BUF_SIZE-1);
+					put_char(tty->read_buf[head], tty);
+				}
 			} else if (kill_type == ERASE && !L_ECHOE(tty)) {
 				echo_char(ERASE_CHAR(tty), tty);
 			} else if (c == '\t') {
@@ -403,7 +429,7 @@ static void eraser(unsigned char c, struct tty_struct *tty)
 					else if (iscntrl(c)) {
 						if (L_ECHOCTL(tty))
 							col += 2;
-					} else
+					} else if (!is_continuation(c, tty))
 						col++;
 					tail = (tail+1) & (N_TTY_BUF_SIZE-1);
 				}

include/asm-alpha/termbits.h

@@ -56,12 +56,10 @@ struct termios {
 #define ICRNL	0000400
 #define IXON	0001000
 #define IXOFF	0002000
-#if !defined(KERNEL) || defined(__USE_BSD)
-  /* POSIX.1 doesn't want these... */
-# define IXANY		0004000
-# define IUCLC		0010000
-# define IMAXBEL	0020000
-#endif
+#define IXANY	0004000
+#define IUCLC	0010000
+#define IMAXBEL	0020000
+#define IUTF8	0040000
 
 /* c_oflag bits */
 #define OPOST	0000001

include/asm-arm/termbits.h

@@ -49,6 +49,7 @@ struct termios {
 #define IXANY	0004000
 #define IXOFF	0010000
 #define IMAXBEL	0020000
+#define IUTF8	0040000
 
 /* c_oflag bits */
 #define OPOST	0000001

include/asm-arm26/termbits.h

@@ -49,6 +49,7 @@ struct termios {
 #define IXANY	0004000
 #define IXOFF	0010000
 #define IMAXBEL	0020000
+#define IUTF8	0040000
 
 /* c_oflag bits */
 #define OPOST	0000001

include/asm-cris/termbits.h

@@ -53,6 +53,7 @@ struct termios {
 #define IXANY	0004000
 #define IXOFF	0010000
 #define IMAXBEL	0020000
+#define IUTF8	0040000
 
 /* c_oflag bits */
 #define OPOST	0000001

include/asm-h8300/termbits.h

@@ -52,6 +52,7 @@ struct termios {
 #define IXANY	0004000
 #define IXOFF	0010000
 #define IMAXBEL	0020000
+#define IUTF8	0040000
 
 /* c_oflag bits */
 #define OPOST	0000001

include/asm-i386/termbits.h

@@ -51,6 +51,7 @@ struct termios {
 #define IXANY	0004000
 #define IXOFF	0010000
 #define IMAXBEL	0020000
+#define IUTF8	0040000
 
 /* c_oflag bits */
 #define OPOST	0000001

include/asm-ia64/termbits.h

@@ -60,6 +60,7 @@ struct termios {
 #define IXANY	0004000
 #define IXOFF	0010000
 #define IMAXBEL	0020000
+#define IUTF8	0040000
 
 /* c_oflag bits */
 #define OPOST	0000001

include/asm-m68k/termbits.h

@@ -52,6 +52,7 @@ struct termios {
 #define IXANY	0004000
 #define IXOFF	0010000
 #define IMAXBEL	0020000
+#define IUTF8	0040000
 
 /* c_oflag bits */
 #define OPOST	0000001

include/asm-mips/termbits.h

@@ -77,6 +77,7 @@ struct termios {
 #define IXANY	0004000		/* Any character will restart after stop.  */
 #define IXOFF	0010000		/* Enable start/stop input control.  */
 #define IMAXBEL	0020000		/* Ring bell when input queue is full.  */
+#define IUTF8	0040000		/* Input is UTF8 */
 
 /* c_oflag bits */
 #define OPOST	0000001		/* Perform output processing.  */

include/asm-parisc/termbits.h

@@ -52,6 +52,7 @@ struct termios {
 #define IXANY	0004000
 #define IXOFF	0010000
 #define IMAXBEL	0040000
+#define IUTF8	0100000
 
 /* c_oflag bits */
 #define OPOST	0000001

include/asm-ppc/termbits.h

@@ -58,6 +58,7 @@ struct termios {
 #define IXANY		0004000
 #define IUCLC		0010000
 #define IMAXBEL	0020000
+#define IUTF8	0040000
 
 /* c_oflag bits */
 #define OPOST	0000001

include/asm-ppc64/termbits.h

@@ -66,6 +66,7 @@ struct termios {
 #define IXANY	0004000
 #define IUCLC	0010000
 #define IMAXBEL	0020000
+#define	IUTF8	0040000
 
 /* c_oflag bits */
 #define OPOST	0000001

include/asm-s390/termbits.h

@@ -59,6 +59,7 @@ struct termios {
 #define IXANY	0004000
 #define IXOFF	0010000
 #define IMAXBEL	0020000
+#define IUTF8	0040000
 
 /* c_oflag bits */
 #define OPOST	0000001

include/asm-sh/termbits.h

@@ -51,6 +51,7 @@ struct termios {
 #define IXANY	0004000
 #define IXOFF	0010000
 #define IMAXBEL	0020000
+#define IUTF8	0040000
 
 /* c_oflag bits */
 #define OPOST	0000001

include/asm-sparc/termbits.h

@@ -78,6 +78,7 @@ struct termios {
 #define IXANY	0x00000800
 #define IXOFF	0x00001000
 #define IMAXBEL	0x00002000
+#define IUTF8   0x00004000
 
 /* c_oflag bits */
 #define OPOST	0x00000001

include/asm-sparc64/termbits.h

@@ -80,6 +80,7 @@ struct termios {
 #define IXANY	0x00000800
 #define IXOFF	0x00001000
 #define IMAXBEL	0x00002000
+#define IUTF8	0x00004000
 
 /* c_oflag bits */
 #define OPOST	0x00000001

include/asm-v850/termbits.h

@@ -52,6 +52,7 @@ struct termios {
 #define IXANY	0004000
 #define IXOFF	0010000
 #define IMAXBEL	0020000
+#define IUTF8	0040000
 
 /* c_oflag bits */
 #define OPOST	0000001

include/asm-x86_64/termbits.h

@@ -51,6 +51,7 @@ struct termios {
 #define IXANY	0004000
 #define IXOFF	0010000
 #define IMAXBEL	0020000
+#define IUTF8	0040000
 
 /* c_oflag bits */
 #define OPOST	0000001

include/linux/tty.h

@@ -184,6 +184,7 @@ struct tty_flip_buffer {
 #define I_IXANY(tty)	_I_FLAG((tty),IXANY)
 #define I_IXOFF(tty)	_I_FLAG((tty),IXOFF)
 #define I_IMAXBEL(tty)	_I_FLAG((tty),IMAXBEL)
+#define I_IUTF8(tty)	_I_FLAG((tty),IUTF8)
 
 #define O_OPOST(tty)	_O_FLAG((tty),OPOST)
 #define O_OLCUC(tty)	_O_FLAG((tty),OLCUC)