fix(unicode): renamed functions to be easier to understand their functions

1 files changed, 40 insertions, 0 deletions

diff --git a/sys/libunicode/decode.c b/sys/libunicode/decode.c
new file mode 100644
index 0000000..79271f2
--- /dev/null
+++ b/sys/libunicode/decode.c
@@ -0,0 +1,40 @@
+#include "internal.h"
+
+int
+utf8·decode(byte *s, rune* r)
+{
+    int c[UTFmax], i;
+    rune l;
+
+    c[0] = *(ubyte*)(s);
+    if(c[0] < Tx) {
+        *r = c[0];
+        return 1;
+    }
+
+    l = c[0];
+    for(i = 1; i < UTFmax; i++) {
+        c[i]  = *(ubyte*)(s+i);
+        c[i] ^= Tx;
+        if (c[i] & Testx) goto bad;
+
+        l = (l << Bitx) | c[i];
+        if(c[0] < Tbyte(i + 2)) {
+            l &= RuneX(i + 1);
+            if (i == 1) {
+                if (c[0] < Tbyte(2) || l <= Rune1)
+                    goto bad;
+            } else if (l <= RuneX(i) || l > RuneMax)
+                goto bad;
+            if (i == 2 && SurrogateMin <= l && l <= SurrogateMax)
+                goto bad;
+
+            *r = l;
+            return i + 1;
+        }
+    }
+bad:
+    *r = RuneErr;
+    return 1;
+}
+