1 files changed, 28 insertions, 0 deletions
diff --git a/lowercasing_test/src/tests/lowercasing/fetchletters.py b/lowercasing_test/src/tests/lowercasing/fetchletters.py
new file mode 100644
index 00000000000..350dfa050da
--- /dev/null
+++ b/lowercasing_test/src/tests/lowercasing/fetchletters.py
@@ -0,0 +1,28 @@
+#! /usr/bin/env python
+# Copyright 2016 Yahoo Inc. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.
+
+# This program reads a Unicode database and emits all letters in lower
+# and upper case.
+
+# Refer to http://www.unicode.org/ucd/ to download new files.
+
+import sys
+
+def add_character(unicodespec, characterstore):
+    characterstora
+
+def main(raw, out):
+    # Fetch upper and lower case characters in Unicode
+    characters = filter(lambda x: x[2] == 'Lu' or x[2] == 'Ll', raw)
+    image = [unichr(int(c[0], 16)) for c in characters]
+    output = u"\n".join(image)
+    out.write(output.encode("UTF-8"))
+    out.write(u"\n".encode("UTF-8"))
+
+if __name__ == '__main__':
+    try:
+        raw = [x.split(";") for x in open("./UnicodeData.txt", "r").readlines()]
+    except:
+        sys.stderr.write("Problems reading ./UnicodeData.txt.\n")
+        sys.exit(1)
+    main(raw, sys.stdout)