Transform UTF-16 escape sequences generated by WGET into HTML entities

parse-wget-unicode.awk

#!/bin/local/gawk -f

# parse utf-16 escape sequences generated by WGET
# transform them all into HTML entities: `�`

function parse_unicode() {
	while (match($0, /\\u[0-9a-f][0-9a-f][0-9a-f][0-9a-f]/)) {
		hex = substr($0, RSTART+2, RLENGTH-2);
		gsub( "\\\\u" hex, "\\&#x" hex ";", $0);
	}
}

/\\u[0-9a-f][0-9a-f][0-9a-f][0-9a-f]/ {
	parse_unicode();
	print;
}