Kernel utf-8 handling

This patch fixes dead keys and copy/paste of non-ASCII characters in UTF-8
mode on Linux console.  See more details about the original patch at:
http://chris.heathens.co.nz/linux/utf8.html

Already posted on
	(Oldest) http://lkml.org/lkml/2003/5/31/148
	         http://lkml.org/lkml/2005/12/24/69
	(Recent) http://lkml.org/lkml/2006/8/7/75

[bunk@stusta.de: make drivers/char/selection.c:store_utf8() static]
Signed-off-by: Jan Engelhardt <jengelh@gmx.de>
Cc: Alexander E. Patrakov <patrakov@ums.usu.ru>
Cc: Dmitry Torokhov <dtor@mail.ru>
Cc: "Antonino A. Daplas" <adaplas@pol.net>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Cc: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 40 insertions, 8 deletions

diff --git a/drivers/char/selection.c b/drivers/char/selection.c
index a69f094d1ed..d63f5ccc29e 100644
--- a/drivers/char/selection.c
+++ b/drivers/char/selection.c
@@ -20,6 +20,7 @@
 
 #include <asm/uaccess.h>
 
+#include <linux/kbd_kern.h>
 #include <linux/vt_kern.h>
 #include <linux/consolemap.h>
 #include <linux/selection.h>
@@ -34,6 +35,7 @@ extern void poke_blanked_console(void);
 /* Variables for selection control. */
 /* Use a dynamic buffer, instead of static (Dec 1994) */
 struct vc_data *sel_cons;		/* must not be deallocated */
+static int use_unicode;
 static volatile int sel_start = -1; 	/* cleared by clear_selection */
 static int sel_end;
 static int sel_buffer_lth;
@@ -54,10 +56,11 @@ static inline void highlight_pointer(const int where)
 	complement_pos(sel_cons, where);
 }
 
-static unsigned char
+static u16
 sel_pos(int n)
 {
-	return inverse_translate(sel_cons, screen_glyph(sel_cons, n));
+	return inverse_translate(sel_cons, screen_glyph(sel_cons, n),
+				use_unicode);
 }
 
 /* remove the current selection highlight, if any,
@@ -86,8 +89,8 @@ static u32 inwordLut[8]={
   0xFF7FFFFF  /* latin-1 accented letters, not division sign */
 };
 
-static inline int inword(const unsigned char c) {
-	return ( inwordLut[c>>5] >> (c & 0x1F) ) & 1;
+static inline int inword(const u16 c) {
+	return c > 0xff || (( inwordLut[c>>5] >> (c & 0x1F) ) & 1);
 }
 
 /* set inwordLut contents. Invoked by ioctl(). */
@@ -108,13 +111,36 @@ static inline unsigned short limit(const unsigned short v, const unsigned short
 	return (v > u) ? u : v;
 }
 
+/* stores the char in UTF8 and returns the number of bytes used (1-3) */
+static int store_utf8(u16 c, char *p)
+{
+	if (c < 0x80) {
+		/*  0******* */
+		p[0] = c;
+		return 1;
+	} else if (c < 0x800) {
+		/* 110***** 10****** */
+		p[0] = 0xc0 | (c >> 6);
+		p[1] = 0x80 | (c & 0x3f);
+		return 2;
+    	} else {
+		/* 1110**** 10****** 10****** */
+		p[0] = 0xe0 | (c >> 12);
+		p[1] = 0x80 | ((c >> 6) & 0x3f);
+		p[2] = 0x80 | (c & 0x3f);
+		return 3;
+    	}
+}
+
 /* set the current selection. Invoked by ioctl() or by kernel code. */
 int set_selection(const struct tiocl_selection __user *sel, struct tty_struct *tty)
 {
 	struct vc_data *vc = vc_cons[fg_console].d;
 	int sel_mode, new_sel_start, new_sel_end, spc;
 	char *bp, *obp;
-	int i, ps, pe;
+	int i, ps, pe, multiplier;
+	u16 c;
+	struct kbd_struct *kbd = kbd_table + fg_console;
 
 	poke_blanked_console();
 
@@ -158,6 +184,7 @@ int set_selection(const struct tiocl_selection __user *sel, struct tty_struct *t
 		clear_selection();
 		sel_cons = vc_cons[fg_console].d;
 	}
+	use_unicode = kbd && kbd->kbdmode == VC_UNICODE;
 
 	switch (sel_mode)
 	{
@@ -240,7 +267,8 @@ int set_selection(const struct tiocl_selection __user *sel, struct tty_struct *t
 	sel_end = new_sel_end;
 
 	/* Allocate a new buffer before freeing the old one ... */
-	bp = kmalloc((sel_end-sel_start)/2+1, GFP_KERNEL);
+	multiplier = use_unicode ? 3 : 1;  /* chars can take up to 3 bytes */
+	bp = kmalloc((sel_end-sel_start)/2*multiplier+1, GFP_KERNEL);
 	if (!bp) {
 		printk(KERN_WARNING "selection: kmalloc() failed\n");
 		clear_selection();
@@ -251,8 +279,12 @@ int set_selection(const struct tiocl_selection __user *sel, struct tty_struct *t
 
 	obp = bp;
 	for (i = sel_start; i <= sel_end; i += 2) {
-		*bp = sel_pos(i);
-		if (!isspace(*bp++))
+		c = sel_pos(i);
+		if (use_unicode)
+			bp += store_utf8(c, bp);
+		else
+			*bp++ = c;
+		if (!isspace(c))
 			obp = bp;
 		if (! ((i + 2) % vc->vc_size_row)) {
 			/* strip trailing blanks from line and add newline,