A libxml-ruby script to download XSD recursively

require 'uri'
require 'net/http'
require 'rubygems'
require 'xml'

class App

def initialize argv
@argv = argv
@cache = {}
@htconn = {}
end

def help
puts <<EOF
XSD downloader following includes and imports
usage: ruby #$0 [-pNUM] uri ...
-pNUM number of directory structure (including hostname) to be stripped
EOF
end

def outfnam uri
File.join(*[uri.host, uri.path].compact)
end

def close
@htconn[:conn].finish if @htconn[:conn]
end

def getconn uri
shp = [uri.scheme, uri.host, uri.port]
if @htconn[:shp] == shp then
puts 'reusing connection'
yield @htconn[:conn]
else
@htconn[:conn].finish if @htconn[:conn]
puts "connecting #{shp.join(' ')}"
@htconn[:shp] = shp
@htconn[:conn] = Net::HTTP.new(uri.host, uri.port)
@htconn[:conn].start
yield @htconn[:conn]
end
end

def assert_equal test, right
raise "#{test} != #{right}" unless test == right
end

XSD_NS = 'http://www.w3.org/2001/XMLSchema'

def mkdir_p dirname
return nil if File.directory?(dirname)
raise Errno::ENOTDIR, "not a directory: (#{dirname})" if
File.exist?(dirname)
puts "mkdir #{dirname}"
mkdir_p(File.dirname(dirname))
Dir.mkdir(dirname)
end

def savefile filename, content
puts "saving #{filename}"
mkdir_p File.dirname(filename)
File.open(filename, 'wb') { |fp| fp.write(content) }
end

def get1 uri, disp = nil
if @cache[uri.to_s] then
puts "skipping #{disp or uri}"
return
end
ofn = outfnam(uri)
buf = nil
getconn(uri) {|conn|
resp = conn.get(uri.path)
raise "#{resp.code} #{resp.message}" unless /^200/ === resp.code
buf = resp.body
}
savefile(ofn, buf)
@cache[uri.to_s] = true
doc = XML::Document.string(buf)
assert_equal(doc.root.namespaces.namespace.href, XSD_NS)
nodes = doc.find('/xs:schema/xs:import|/xs:schema/xs:include', 'xs'=>XSD_NS)
nodes.each { |node|
child = node['schemaLocation'].to_s
get1(uri + child, child)
}
nodes = nil
end

def run1 arg
uri = URI(arg)
get1(uri)
end

def run
for arg in @argv
run1 arg
end
self
end

end

App.new(ARGV).run.close