A gawk script to process a text file of Armenian Church Lectionary dates

passages.gawk

BEGIN { print "days:" }
/ ([a-zA-Z]*)/ { 
	monthtext = $2; 
	m["January"] = 1;
	m["February"] = 2;
	m["March"] = 3;
	m["April"] = 4;
	m["May"] = 5;
	m["June"] = 6;
	m["July"] = 7;
	m["August"] = 8;
	m["September"] = 9;
	m["October"] = 10;
	m["November"] = 11;
	m["December"] = 12;
	month = m[$2];
	}

/^([0-9]*)[ \t\n]+([[:alnum:] ]+)\.[ ]+([[:alnum:][:space:]\-\.\,\"\'\)\(]+)\.[ ]+(.*)/ {
	date = gensub(/([0-9]*)[ \t\n]+([[:alnum:] ]+)\.[ ]+([[:alnum:][:space:]\-\.\,\"\'\)\(]+)\.[ ]+(.*)/,"\\1","g");
	day = gensub(/([0-9]*)[ \t\n]+([[:alnum:] ]+)\.[ ]+([[:alnum:][:space:]\-\.\,\"\'\)\(]+)\.[ ]+(.*)/,"\\2","g");
	name = gensub(/([0-9]*)[ \t\n]+([[:alnum:] ]+)\.[ ]+([[:alnum:][:space:]\-\.\,\"\'\)\(]+)\.[ ]+(.*)/,"\\3","g");
	passages = gensub(/([0-9]*)[ \t\n]+([[:alnum:] ]+)\.[ ]+([[:alnum:][:space:]\-\.\,\"\'\)\(]+)\.[ ]+(.*)\./,"\\4","g");
	
	# Set year
	year = 2011;
	
	# Split passages into Array
	split(passages,a,", ");
	reading = "";
	for (item in a) {
		reading = reading "\n      - passage: "a[item];
	}
	
	#output
	printf "  - title: %s\n    date: %s-%d-%s\n    readings:%s\n", name, month, date, year, reading;

	null }