script to remove private use area chars

1 files changed, 10 insertions, 0 deletions

diff --git a/fix-utf-8-pua b/fix-utf-8-pua
new file mode 100755
index 0000000..674d424
--- /dev/null
+++ b/fix-utf-8-pua
@@ -0,0 +1,10 @@
+#!/usr/bin/env ruby
+
+# remove private use area chars
+
+while line = STDIN.gets
+  line.strip!
+  line.gsub! /[\u{e000}-\u{f8ff}]/, " "
+  puts line
+end
+