1 files changed, 47 insertions, 0 deletions
diff --git a/subscript.py b/subscript.py
new file mode 100755
index 0000000..1abd38f
--- /dev/null
+++ b/subscript.py
@@ -0,0 +1,47 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0-only
+
+from sys import stderr
+
+with open("UnicodeData.txt") as f:
+    data = f.read()
+data = data.split("\n")
+
+subscripts = {}
+
+
+def line_to_char(line):
+    return chr(int(line.split(";", 1)[0], 16))
+
+
+for line in data:
+    if "SUBSCRIPT" in line:
+        normal_name = ''.join(line.split(";", 2)[1].split("SUBSCRIPT ", 1))
+        if normal_name == "MINUS":
+            normal_name = "MINUS SIGN"
+        if normal_name == "ARABIC ALEF":
+            normal_name = "ARABIC LETTER ALEF"
+        normal_line = None
+        for line2 in data:
+            if (
+                (";" + normal_name + ";" in line2 or ";DIGIT " + normal_name + ";" in line2)
+                and line != line2
+                and "<control>" not in line2
+            ):
+                normal_line = line2
+                break
+        if not normal_line:
+            print("not found:", line, file=stderr)
+            continue
+        char = line_to_char(line)
+        normal = line_to_char(normal_line)
+        if normal not in subscripts:
+            subscripts[normal] = char
+
+subscripts["-"] = subscripts["−"]
+subscripts[" "] = " "
+
+import json
+
+print("window.unicodeMaps.toSubscript =", json.dumps(subscripts), ";")
+print(subscripts, file=stderr)