Start actually inserting full utf8 sequences

This makes it possible to cut-and-paste the UTF8 testfile into a new
buffer, and the end result looks correct.

NOTE! We still do various things wrong while editing.  For example,
while the cursor movements were fixed, simple things like deleting a
character still work on single bytes, rather than utf8 characters.

So while this is getting much closer to actually editing UTF-8 data,
it's not there yet.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 21 insertions, 2 deletions

diff --git a/line.c b/line.c
index f1aa084..6e46ffc 100644
--- a/line.c
+++ b/line.c
@@ -20,6 +20,7 @@
 #include "estruct.h"
 #include "edef.h"
 #include "efunc.h"
+#include "utf8.h"
 
 #define	BLOCK_SIZE 16 /* Line block chunk size. */
 
@@ -161,7 +162,7 @@ int linstr(char *instr)
  * well, and FALSE on errors.
  */
 
-int linsert(int n, int c)
+static int linsert_byte(int n, int c)
 {
 	char *cp1;
 	char *cp2;
@@ -239,6 +240,24 @@ int linsert(int n, int c)
 	return TRUE;
 }
 
+int linsert(int n, int c)
+{
+	char utf8[6];
+	int bytes = unicode_to_utf8(c, utf8), i;
+
+	if (bytes == 1)
+		return linsert_byte(n, (unsigned char) utf8[0]);
+	for (i = 0; i < n; i++) {
+		int j;
+		for (j = 0; j < bytes; j++) {
+			unsigned char c = utf8[j];
+			if (!linsert_byte(1, c))
+				return FALSE;
+		}
+	}
+	return TRUE;
+}
+
 /*
  * Overwrite a character into the current line at the current position
  *
diff --git a/main.c b/main.c
index 9331b38..a6dabf6 100644
--- a/main.c
+++ b/main.c
@@ -500,7 +500,7 @@ int execute(int c, int f, int n)
 	    || (c >= 0x80 && c <= 0xFE)) {
 #else
 #if	VMS || BSD || USG	/* 8BIT P.K. */
-	    || (c >= 0xA0 && c <= 0xFE)) {
+	    || (c >= 0xA0 && c <= 0xFFFF)) {
 #else
 	    ) {
 #endif