+ # These regular expressions assume traditional Unix unibyte behavior.
+ # They are needed for old or broken versions of awk, e.g.,
+ # mawk 1.3.3 (1996), or gawk on MSYS (2015), and/or for systems that
+ # cannot use UTF-8 as the codeset for the locale.
+ space = "[ \f\n\r\t\v]"
+ non_space = "[^ \f\n\r\t\v]"
+ # The non_print below rejects control characters and surrogates
+ # UTF-8 for: 0x01-0x1f 0x7f 0x80-0x9f 0xd800-0xdbff 0xdc00-0xdfff
+ non_print = "[\1-\37\177]|\302[\200-\237]|\355[\240-\277][\200-\277]"
+
+ # Prefer POSIX regular expressions if available, as they do a
+ # better job of checking. Similarly, prefer POSIX negated
+ # expressions if UTF-8 also works.