unicode: new toy.

Based loosely on the Plan9/Inferno utility, and a convenient way to go back
and forth between code points and utf8 sequences.

This patch also fixes a couple of bugs in wctoutf8 (and the tests for this
toy effectively serve as unit tests for wctoutf8/utf8towc).

1 files changed, 6 insertions, 5 deletions

diff --git a/lib/lib.c b/lib/lib.c
index 7786fcc1..3129e3e3 100644
--- a/lib/lib.c
+++ b/lib/lib.c
@@ -349,17 +349,18 @@ int stridx(char *haystack, char needle)
 // Convert wc to utf8, returning bytes written. Does not null terminate.
 int wctoutf8(char *s, unsigned wc)
 {
-  int len = (wc>0x7ff)+(wc>0xffff), mask = 12+len+!!len;
+  int len = (wc>0x7ff)+(wc>0xffff), i;
 
   if (wc<128) {
     *s = wc;
     return 1;
   } else {
+    i = len;
     do {
-      s[1+len] = 0x80+(wc&0x3f);
-      wc >>= 7;
-    } while (len--);
-    *s = wc|mask;
+      s[1+i] = 0x80+(wc&0x3f);
+      wc >>= 6;
+    } while (i--);
+    *s = (((signed char) 0x80) >> (len+1)) | wc;
   }
 
   return 2+len;