Class: WCC::Prog

Inherits:

Object

• Object
• WCC::Prog

Defined in:

lib/wcc.rb

Class Method Summary

• .checkForUpdate(site) ⇒ Object
• .run! ⇒ Object

  main.

Class Method Details

.checkForUpdate(site) ⇒ Object

# File 'lib/wcc.rb', line 267

def self.checkForUpdate(site)
	WCC.logger.info "Requesting '#{site.uri.to_s}'"
	begin
		res = site.fetch
	rescue Timeout::Error => ex
		# don't claim on this
		return false
	rescue => ex
		WCC.logger.error "Cannot connect to #{site.uri.to_s} : #{ex.to_s}"
		return false
	end
	if not res.kind_of?(Net::HTTPOK)
		WCC.logger.error "Site #{site.uri.to_s} returned #{res.code} code, skipping it."
		return false
	end
	
	new_content = res.body
	
	# detect encoding from http header, meta element, default utf-8
	# do not use utf-8 regex because it will fail on non utf-8 pages
	encoding = (res['content-type'].to_s.match(/;\s*charset=([A-Za-z0-9-]*)/i).to_a[1] || 
				new_content.match(/<meta.*charset=([a-zA-Z0-9-]*).*/i).to_a[1]).to_s.downcase || 'utf-8'
	
	WCC.logger.info "Encoding is '#{encoding}'"
	
	# convert to utf-8
	begin
		new_content = Iconv.conv('utf-8', encoding, new_content)
	rescue => ex
		WCC.logger.error "Cannot convert site from '#{encoding}': #{ex.to_s}"
		return false
	end
	
	# strip html
	new_content = new_content.strip_html if site.strip_html?
	new_hash = Digest::MD5.hexdigest(new_content)
	
	WCC.logger.debug "Compare hashes\n  old: #{site.hash.to_s}\n  new: #{new_hash.to_s}"
	return false if new_hash == site.hash
	
	# do not try diff or anything if site was never checked before
	if site.new?
		site.hash, site.content = new_hash, new_content
		
		# set custom diff message
		diff = "Site was first checked so no diff was possible."
	else
		# save old site to tmp file
		old_site_file = Tempfile.new("wcc-#{site.id}-")
		old_site_file.write(site.content)
		old_site_file.close
		
		# calculate labels before updating
		old_label = "OLD (%s)" % File.mtime(Conf.file(site.id + ".md5")).strftime(DIFF_TIME_FMT)
		new_label = "NEW (%s)" % Time.now.strftime(DIFF_TIME_FMT)
	
		site.hash, site.content = new_hash, new_content
		
		# diff between OLD and NEW
		diff = %x[diff -U 1 --label "#{old_label}" --label "#{new_label}" #{old_site_file.path} #{Conf.file(site.id + '.site')}]
	end
	
	# HACK: there *was* an update but no notification is required
	return false if not Filter.accept(diff, site.filters)
	
	data = OpenStruct.new
	data.title = "[#{Conf[:tag]}] #{site.uri.host} changed"
	data.message = "Change at #{site.uri.to_s} - diff follows:\n\n#{diff}"
	
	Conf.mailer.send(data, @@mail_plain, MailAddress.new(Conf[:from_mail]), site.emails)
	
	system("logger -t '#{Conf[:tag]}' 'Change at #{site.uri.to_s} (tag #{site.id}) detected'") if Conf[:syslog]
	
	true
end

.run! ⇒ Object

main

# File 'lib/wcc.rb', line 344

def self.run!
	# first use of Conf initializes it
	WCC.logger = Logger.new(STDOUT)
	
	mp_path = File.join(Conf[:template_dir], 'mail-plain.erb')
	mp = File.open(mp_path, 'r') { |f| f.read }
	@@mail_plain = ERB.new(mp)
	
	Conf.sites.each do |site|
		if checkForUpdate(site)
			WCC.logger.warn "#{site.uri.host.to_s} has an update!"
		else
			WCC.logger.info "#{site.uri.host.to_s} is unchanged"
		end
	end
end