#!/usr/bin/env ruby
#
# Author: Martin Matusiak <numerodix@gmail.com>
# Licensed under the GNU Public License, version 3.
#
# revision 3 - allow spaces in urls
# revision 2 - introduce buffering to handle large files out of memory
# revision 1 - performance hacking: output entries immediately, only sort on
# emailcsv


require "optparse"


email = /([a-zA-Z0-9_\.-])+@(([a-zA-Z0-9-])+\.)+([a-zA-Z0-9]{2,4})+/m
url_orig = /([A-Za-z][A-Za-z0-9+.-]{1,120}:[A-Za-z0-9\/](([A-Za-z0-9$_.+!*,;\/?:@&~=-])|%[A-Fa-f0-9]{2}){1,333}(#([a-zA-Z0-9][a-zA-Z0-9$_.+!*,;\/?:@&~=%-]{0,1000}))?)/m
url = /([A-Za-z][A-Za-z0-9+.-]{1,120}:\/\/(([A-Za-z0-9$_.+!*,;\/?:@&~(){}\[\]=-])|%[A-Fa-f0-9]{2}){1,333}(#([a-zA-Z0-9][a-zA-Z0-9 $_.+!*,;\/?:@&~(){}\[\]=%-]{0,1000}))?)/m

pattern=url
joinlines=false
emailcsv=false
buffer_size=10*1024
hardlimit=100


## parse options
OptionParser.new do |opts|
	opts.on("--url", "url format") do |v|
		pattern = url
	end
	opts.on("--dat", "firefox history.dat format = \\\\n in urls") do |v|
		joinlines = true
	end
	opts.on("--email", "email format") do |v|
		pattern = email
	end
	opts.on("--emailcsv", "csv output (facebook contact import)") do |v|
		pattern = email
		emailcsv = true
	end
end.parse!


entries = []
previous = ""
while string = previous + STDIN.read(buffer_size).to_s and string.length > previous.length do
	partial = ""
	joinlines and string.gsub!(/\\\n/, "")
	while string and m = pattern.match(string) and m.size > 0 do
		m.end(0) == string.length and partial = m.to_s
		if partial.empty?
			if emailcsv
				entries << m.to_s
			else
				puts m.to_s
			end
		end
		pos = m.end(0)
		string = string[pos..-1]
	end
	if !partial.empty?
		previous = partial
	else
		if hardlimit < string.length
			previous = string[string.length-hardlimit..-1]
		else
			previous = string
		end
	end
end

# special stuff for csv email output
if !entries.empty?
	entries = entries.sort{ |a, b| a.downcase <=> b.downcase }.uniq
	puts '"Email Address","Formatted Name"'
	entries.each { |i| puts '"' + i + '",""' }
end