1 files changed, 57 insertions, 0 deletions
diff --git a/src/gen-os2-unicode-ranges.py b/src/gen-os2-unicode-ranges.py
new file mode 100644
index 0000000..8cf5985
--- /dev/null
+++ b/src/gen-os2-unicode-ranges.py
@@ -0,0 +1,57 @@
+# -*- coding: utf-8 -*-
+
+# Generates the code for a sorted unicode range array as used in hb-ot-os2-unicode-ranges.hh
+# Input is a tab seperated list of unicode ranges from the otspec
+# (https://docs.microsoft.com/en-us/typography/opentype/spec/os2#ulunicoderange1).
+
+from __future__ import print_function, division, absolute_import
+
+import io
+import re
+import sys
+
+try:
+  reload(sys)
+  sys.setdefaultencoding('utf-8')
+except NameError:
+  pass  # Python 3
+
+print ("""static OS2Range _hb_os2_unicode_ranges[] =
+{""")
+
+args = sys.argv[1:]
+input_file = args[0]
+
+with io.open(input_file, mode="r", encoding="utf-8") as f:
+
+  all_ranges = [];
+  current_bit = 0
+  while True:
+    line = f.readline().strip()
+    if not line:
+      break
+    fields = re.split(r'\t+', line)
+    if len(fields) == 3:
+      current_bit = fields[0]
+      fields = fields[1:]
+    elif len(fields) > 3:
+      raise Exception("bad input :(.")
+
+    name = fields[0]
+    ranges = re.split("-", fields[1])
+    if len(ranges) != 2:
+      raise Exception("bad input :(.")
+
+    v = tuple((int(ranges[0], 16), int(ranges[1], 16), int(current_bit), name))
+    all_ranges.append(v)
+
+all_ranges = sorted(all_ranges, key=lambda t: t[0])
+
+for ranges in all_ranges:
+  start = ("0x%X" % ranges[0]).rjust(8)
+  end = ("0x%X" % ranges[1]).rjust(8)
+  bit = ("%s" % ranges[2]).rjust(3)
+
+  print ("  {%s, %s, %s}, // %s" % (start, end, bit, ranges[3]))
+
+print ("""};""")