Use the parsed unicode stuff to decide what is valid identifier characters, and symbol characters.unicode-props

FossilOrigin-Name: afa25da5a44e8cb032d74269a6d4b7ec1e8842f18cefbd54d5f84a0b6d780f70

1 files changed, 15 insertions, 5 deletions

diff --git a/src/lib/unicode.c b/src/lib/unicode.c
index b5c6471..48cb91e 100644
--- a/src/lib/unicode.c
+++ b/src/lib/unicode.c
@@ -18,18 +18,28 @@
  */
 
 #include "aplwc_internal.h"
-#include "unicode.h"
+#include "unicode_properties.c"
 
 static int
 is(uint32_t c, enum unicode_property p)
 {
-	int n;
+	int n, a, b, i;
 	struct unicode_range *r;
 
-	UNUSED_PARAMETER(c);
-
 	unicode_get(p, &n, &r);
-
+	a = 0;
+	b = n-1;
+	while(a <= b){
+		i = a + (b-a) / 2;
+		if(c >= r[i].from && c <= r[i].to)
+			return 1;
+		else if(c < r[i].from)
+			b = i-1;
+		else{
+			assert(c > r[i].to);
+			a = i+1;
+		}
+	}
 	return 0;
 }