Merge unicode-props into trunk

FossilOrigin-Name: 95c406d482112373a41982bf36f3a9159fceff5ff95162cab34e97fd0cfaa73c

1 files changed, 62 insertions, 0 deletions

diff --git a/src/lib/unicode.c b/src/lib/unicode.c
new file mode 100644
index 0000000..48cb91e
--- /dev/null
+++ b/src/lib/unicode.c
@@ -0,0 +1,62 @@
+/* 
+ * Copyright (C) 2026 Peter Mikkelsen <petermikkelsen10@gmail.com>
+ *
+ * This file is part of aplwc.
+ *
+ * Aplwc is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Aplwc is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with aplwc.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+#include "aplwc_internal.h"
+#include "unicode_properties.c"
+
+static int
+is(uint32_t c, enum unicode_property p)
+{
+	int n, a, b, i;
+	struct unicode_range *r;
+
+	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;
+}
+
+int
+is_id_start(uint32_t c)
+{
+	return is(c, ID_Start);
+}
+
+int
+is_id_continue(uint32_t c)
+{
+	return is(c, ID_Continue);
+}
+
+int
+is_pattern_syntax(uint32_t c)
+{
+	return is(c, Pattern_Syntax);
+}