Class: Wmap::HostTracker

Inherits:
Object
  • Object
show all
Includes:
Singleton, Utils
Defined in:
lib/wmap/host_tracker.rb,
lib/wmap/host_tracker/primary_host.rb

Overview

Class to handle the local host data repository file where lists of known hosts from discovery and past assessment efforts are stored

Direct Known Subclasses

PrimaryHost

Defined Under Namespace

Classes: PrimaryHost

Constant Summary

Constants included from Utils::UrlMagic

Utils::UrlMagic::Max_http_timeout, Utils::UrlMagic::User_agent

Constants included from Utils::DomainRoot

Utils::DomainRoot::File_ccsld, Utils::DomainRoot::File_cctld, Utils::DomainRoot::File_gtld, Utils::DomainRoot::File_tld

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods included from Utils

#cidr_2_ips, #file_2_hash, #file_2_list, #get_nameserver, #get_nameservers, #host_2_ip, #host_2_ips, #is_cidr?, #is_fqdn?, #is_ip?, #list_2_file, #reverse_dns_lookup, #sort_ips, #valid_dns_record?, #zone_transferable?

Methods included from Utils::Logger

#wlog

Methods included from Utils::UrlMagic

#create_absolute_url_from_base, #create_absolute_url_from_context, #host_2_url, #is_site?, #is_ssl?, #is_url?, #landing_location, #make_absolute, #normalize_url, #open_page, #redirect_location, #response_code, #response_headers, #url_2_host, #url_2_path, #url_2_port, #url_2_site, #urls_on_same_domain?

Methods included from Utils::DomainRoot

#get_domain_root, #get_domain_root_by_ccsld, #get_domain_root_by_cctld, #get_domain_root_by_tlds, #get_sub_domain, #is_domain_root?, #print_ccsld, #print_cctld, #print_gtld

Constructor Details

#initialize(params = {}) ⇒ HostTracker

Instance default variables



21
22
23
24
25
26
27
28
29
30
31
 
# File 'lib/wmap/host_tracker.rb', line 21

def initialize (params = {})
	@verbose=params.fetch(:verbose, false)
	@data_dir=params.fetch(:data_dir, File.dirname(__FILE__)+'/../../data/')
	Dir.mkdir(@data_dir) unless Dir.exist?(@data_dir)
	# Set default instance variables
	@hosts_file=params.fetch(:hosts_file, @data_dir + 'hosts')
	@max_parallel=params.fetch(:max_parallel, 40)
	# Initialize the instance variables
	File.write(@hosts_file, "") unless File.exist?(@hosts_file)
	load_known_hosts_from_file(@hosts_file)
end

Instance Attribute Details

#alias ⇒ Object (readonly)

Returns the value of attribute alias.



18
19
20
 
# File 'lib/wmap/host_tracker.rb', line 18

def alias
  @alias
end

#data_dir ⇒ Object

Returns the value of attribute data_dir.



17
18
19
 
# File 'lib/wmap/host_tracker.rb', line 17

def data_dir
  @data_dir
end

#hosts_file ⇒ Object

Returns the value of attribute hosts_file.



17
18
19
 
# File 'lib/wmap/host_tracker.rb', line 17

def hosts_file
  @hosts_file
end

#known_hosts ⇒ Object

Returns the value of attribute known_hosts.



17
18
19
 
# File 'lib/wmap/host_tracker.rb', line 17

def known_hosts
  @known_hosts
end

#max_parallel ⇒ Object

Returns the value of attribute max_parallel.



17
18
19
 
# File 'lib/wmap/host_tracker.rb', line 17

def max_parallel
  @max_parallel
end

#verbose ⇒ Object

Returns the value of attribute verbose.



17
18
19
 
# File 'lib/wmap/host_tracker.rb', line 17

def verbose
  @verbose
end

Instance Method Details

#add(host) ⇒ Object

Setter to add host entry to the cache once at a time



100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
 
# File 'lib/wmap/host_tracker.rb', line 100

def add(host)
	puts "Add entry to the local host repository: #{host}"
	host=host.strip.downcase unless host.nil?
	unless @known_hosts.key?(host)
		ip=host_2_ip(host)
		record=Hash.new
		if is_ip?(ip)
			# filter host to known domains only
			root=get_domain_root(host)
			puts "Domain root: #{root}" if @verbose
			domain_tracker=Wmap::DomainTracker.instance
			domain_tracker.data_dir=@data_dir
			domain_tracker.domains_file = domain_tracker.data_dir + "domains"
			domain_tracker.load_domains_from_file
			if domain_tracker.domain_known?(root)
				domain_tracker=nil
				record[host]=ip
				record[ip]=host
				puts "Host data repository entry loaded: #{host} <=> #{ip}"
				# Replace instance with the class variable to avoid potential race condition under parallel engine
				# add additional logic to update the sub-domain table as well, 02/10/2014
				sub=get_sub_domain(host)
				if sub!=root
					tracker=Wmap::DomainTracker::SubDomain.instance
					tracker.data_dir=@data_dir
					tracker.sub_domains_file = tracker.data_dir + "sub_domains"
					tracker.known_internet_sub_domains=tracker.load_domains_from_file(tracker.sub_domains_file)
					unless tracker.domain_known?(sub)
						tracker.add(sub)
						tracker.save!
					end
					tracker=nil
				end
				@known_hosts.merge!(record)
				return record
			else
				domain_tracker=nil
				puts "Error - host #{host} has an untrusted internet root domain: #{root}\nPlease update the trusted domain seeds file first if necessary."
			end
		else
			puts "Problem resolve host #{host} - unknown IP: #{ip}"
		end
	else
		puts "Host is already exist. Skip: #{host}"
	end
rescue => ee
	puts "Exception on method #{__method__}: #{ee}" if @verbose
end

#bulk_add(list, num = @max_parallel) ⇒ Object Also known as: adds

Setter to add host entry to the local hosts in batch (from an array)



150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
 
# File 'lib/wmap/host_tracker.rb', line 150

def bulk_add(list, num=@max_parallel)
	puts "Add entries to the local host repository: #{list}"
	results=Hash.new
	if list.size > 0
		puts "Start parallel host update processing on:\n #{list}" if @verbose
		Parallel.map(list, :in_processes => num) { |target|
			add(target)
		}.each do |process|
			if process.nil?
				next
			elsif process.empty?
				#do nothing
			else
				results.merge!(process)
			end
		end
		@known_hosts.merge!(results)
		puts "Done loading entries."
		return results
	else
		puts "Error: empty list - no entry is loaded. Please check your input list and try again."
	end
	return results
rescue => ee
	puts "Exception on method #{__method__}: #{ee}"
end

#bulk_delete(list) ⇒ Object Also known as: dels

‘setter’ to delete host entry to the cache in batch (from an array)



205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
 
# File 'lib/wmap/host_tracker.rb', line 205

def bulk_delete(list)
	puts "Delete entries to the local host repository from:\n #{list}"
	hosts=list
	changes=Array.new
	if hosts.size > 0
		hosts.map do |x|
			host=delete(x)
			changes.push(host) unless host.nil?
		end
		puts "Done deleting hosts."
		return changes
	else
		puts "Error: empty list - no entry is loaded. Please check your list and try again."
	end
rescue => ee
	puts "Exception on method #{__method__}: #{ee}"
end

#count ⇒ Object

Count numbers of entries in the local host repository



85
86
87
88
89
90
91
92
93
94
95
96
97
 
# File 'lib/wmap/host_tracker.rb', line 85

def count
	puts "Counting number of entries in the local host repository ..."
	cnt=0
	@known_hosts.keys.map do |key|
		unless is_ip?(key)
			cnt=cnt+1
		end
	end
	puts "Current number of entries: #{cnt}"
	return cnt
rescue => ee
	puts "Exception on method #{__method__}: #{ee}"
end

#delete(host) ⇒ Object

‘setter’ to remove entry from the local hosts one at a time



190
191
192
193
194
195
196
197
198
199
200
201
202
 
# File 'lib/wmap/host_tracker.rb', line 190

def delete(host)
	puts "Remove entry from the local host repository: #{host} "
	host=host.strip.downcase
	if @known_hosts.key?(host)
		@known_hosts.delete(host)
		puts "Entry cleared."
		return host
	else
		puts "Entry not fund. Skip: #{host}"
	end
rescue => ee
	puts "Exception on method #{__method__}: #{ee}"
end

#dump_sub_domains ⇒ Object Also known as: get_sub_domains

Extract a list of sub-domains from the local host repository @known_hosts



404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
 
# File 'lib/wmap/host_tracker.rb', line 404

def dump_sub_domains
	puts "Dump out all active sub domains from the local hosts." if @verbose
	subs=Array.new
	@known_hosts.keys.each do |hostname|
		next if is_ip?(hostname)
		hostname = hostname.strip
		sub = get_subdomain(hostname)
		subs.push(sub) unless sub.nil?
	end
	subs.uniq!.sort! unless subs.empty?
	puts "Found sub domains: #{subs}" if @verbose
	return subs
rescue Exception => ee
	puts "Exception on method #{__method__}: #{ee}"
	return subs
end

#file_add(file) ⇒ Object

‘setter’ to add host entry to the local hosts in batch (from a file)



179
180
181
182
183
184
185
186
187
 
# File 'lib/wmap/host_tracker.rb', line 179

def file_add(file)
	puts "Add entries to the local host repository from file: #{file}"
	raise "File non-exist. Please check your file path and name again: #{file}" unless File.exist?(file)
	hosts=file_2_list(file)
	changes=bulk_add(hosts)
	return changes
rescue => ee
	puts "Exception on method #{__method__}: #{ee}"
end

#file_delete(file) ⇒ Object

Setter to delete host entries in the local hosts in batch (from a file)



225
226
227
228
229
230
231
232
233
234
 
# File 'lib/wmap/host_tracker.rb', line 225

def file_delete(file)
	puts "Delete the local host repository entries from file: #{file}"
	raise "File non-exist. Please check your file path and name again: #{file}" unless File.exist?(file)
	hosts=file_2_list(file)
	changes=bulk_delete(hosts)
	puts "Delete done."
	return changes
rescue => ee
	puts "Exception on method #{__method__}: #{ee}"
end

#get_a_records ⇒ Object Also known as: dump_a_records

Extract hostname without the root domain part from the @known_hosts. Data can be used for statistics study.



305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
 
# File 'lib/wmap/host_tracker.rb', line 305

def get_a_records
	puts "Dump out all known A records from the local hosts."
	records=Array.new
	(@known_hosts.keys-["",nil]).map do |hostname|
		next if is_ip?(hostname)
		hostname = hostname.strip
		root = get_domain_root(hostname)
		record = hostname.sub('.'+root,'')
		records.push(record) unless record.nil?
	end
	records.sort!
	return records
rescue => ee
	puts "Exception on method #{__method__}: #{ee}"
end

#get_root_domains ⇒ Object Also known as: dump_root_domains

Extract known root domains from the local host repository @known_hosts



288
289
290
291
292
293
294
295
296
297
298
299
300
301
 
# File 'lib/wmap/host_tracker.rb', line 288

def get_root_domains
	puts "Dump out all active root domains from the cache."
	zones=Array.new
	(@known_hosts.keys-["",nil]).map do |hostname|
		next if is_ip?(hostname)
		hostname = hostname.strip
		zone = get_domain_root(hostname)
		zones.push(zone) unless zone.nil?
	end
	zones.uniq!.sort!
	return zones
rescue => ee
	puts "Exception on method #{__method__}: #{ee}"
end

#host_aliases(host) ⇒ Object Also known as: aliases

Search local host repository and return a list of aliases for the host



450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
 
# File 'lib/wmap/host_tracker.rb', line 450

def host_aliases (host)
	puts "Search aliases in the local hosts data repository for host: #{host}" if @verbose
	host.strip!
	raise "Unknown method input: #{host} We expect a FQDN host-name string from you. " unless is_fqdn?(host)
	aliases=Array.new
	if @known_hosts.key?(host)
		ip=local_host_2_ip(host)
		@known_hosts.keys.map do |key|
			my_ip=local_host_2_ip(key)
			if ip == my_ip
				aliases.push(key)
			end
		end
	else
		raise "Unknown host-name in the local hosts data repository: #{host}"
	end
	return aliases-[host]
rescue Exception => ee
	puts "Exception on method #{__method__}: #{ee}"
	return nil
end

#host_known?(host) ⇒ Boolean Also known as: is_known?

Check if the specific host within @known_hosts table

Returns:

  • (Boolean) 


363
364
365
366
367
368
369
370
371
372
 
# File 'lib/wmap/host_tracker.rb', line 363

def host_known? (host)
	host=host.strip.downcase unless host.nil?
	return false if @known_hosts==nil
	return @known_hosts.key?(host.strip)
rescue => ee
	if @verbose
		puts "Host Lookup Error: #{ee}"
	end
	return false
end

#ip_known?(ip) ⇒ Boolean Also known as: has_a_record?

Check if the specific IP within @known_hosts table

Returns:

  • (Boolean) 


351
352
353
354
355
356
357
358
359
 
# File 'lib/wmap/host_tracker.rb', line 351

def ip_known? (ip)
	known = false
	ip=ip.strip unless ip.nil?
	return false if @known_hosts==nil
	return @known_hosts.key?(ip.strip)
rescue => ee
	puts "IP Lookup Error: #{ee}" if @verbose
	return false
end

#load_known_hosts_from_file(f_hosts = @hosts_file) ⇒ Object

Setter to load the known hosts from the local hosts file into a class instance



34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
 
# File 'lib/wmap/host_tracker.rb', line 34

def load_known_hosts_from_file (f_hosts=@hosts_file)
	puts "Loading local hosts from file: #{f_hosts} ..." if @verbose
	@known_hosts=Hash.new
	@alias = Hash.new
	File.write(f_hosts, "") unless File.exist?(f_hosts)
	f=File.open(f_hosts, 'r')
	f.each do |line|
		next unless line =~ /\d+\.\d+\.\d+\.\d+/
		entry=line.chomp.split(%r{\t+|\s+|\,})
		key=entry[0].downcase
		value=entry[1]
		puts "Loading key value pair: #{key} - #{value}" if @verbose
		@known_hosts[key] = Hash.new unless @known_hosts.key?(key)
		@known_hosts[key]= value
		# For reverse host lookup
		@known_hosts[value] = Hash.new unless @known_hosts.key?(value)
		@known_hosts[value] = key
		# Count the number of alias for the recorded IP
		if @alias.key?(value)
			@alias[value]+=1
		else
			@alias[value]=1
		end
	end
	f.close
	return @known_hosts
rescue => ee
	puts "Exception on method #{__method__}: #{ee}"
	return known_hosts
end

#local_host_2_ip(host) ⇒ Object

Perform DNS lookup on the local host repository. Not to confuse with the DNS lookup from the Internet



390
391
392
393
394
395
396
397
398
399
400
401
 
# File 'lib/wmap/host_tracker.rb', line 390

def local_host_2_ip (host)
	puts "DNS lookup from the local host repository" if @verbose
	host=host.strip unless host.nil?
	if @known_hosts.key?(host)
		return @known_hosts[host]
	else
		return nil
	end
rescue => ee
	puts "Exception on method #{__method__}: #{ee}"
	return nil
end

#local_ip_2_host(ip) ⇒ Object

Perform reverse DNS lookup on the local host repository. Not to confuse with the reverse DNS lookup from the Internet



376
377
378
379
380
381
382
383
384
385
386
387
 
# File 'lib/wmap/host_tracker.rb', line 376

def local_ip_2_host (ip)
	puts "Reverse DNS lookup from the local host repository" if @verbose
	ip=ip.strip unless ip.nil?
	if @known_hosts.key?(ip)
		return @known_hosts[ip]
	else
		return nil
	end
rescue => ee
	puts "Exception on method #{__method__}: #{ee}"
	return nil
end

#print_host(host) ⇒ Object Also known as: print

Print summary report on the cache



335
336
337
338
339
340
341
342
343
344
345
346
347
 
# File 'lib/wmap/host_tracker.rb', line 335

def print_host(host)
	puts "Local host store entry for #{host}"
	host.strip!
	raise "Invalid input: #{host}" unless is_fqdn?(host)
	if @known_hosts.key?(host)
		value=@known_hosts[host]
		puts "#{host}\t#{value}"
	else
		puts "Unknown host in the local store: #{host}"
	end
rescue => ee
	puts "Exception on method #{__method__}: #{ee}"
end

#print_known_hosts ⇒ Object Also known as: print_all

Print summary report on the cache



323
324
325
326
327
328
329
330
331
 
# File 'lib/wmap/host_tracker.rb', line 323

def print_known_hosts
	puts "\nSummary of local hosts Table:"
	puts "Total entries: #{@known_hosts.size}"
	(@known_hosts.keys.sort-["",nil]).each do |key|
		value=@known_hosts[key]
		puts "#{key}\t#{value}" if is_fqdn?(key)
	end
	puts "End of the summary"
end

#refresh(host) ⇒ Object

Setter to refresh the entry from the cache one at a time



237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
 
# File 'lib/wmap/host_tracker.rb', line 237

def refresh(host)
	puts "Refresh the local host repository for host: #{host} "
	host=host.strip.downcase
	if @known_hosts.key?(host)
		old_ip=@known_hosts[host]
		new_ip=host_2_ip(host)
		if is_ip?(new_ip)
			if old_ip==new_ip
				puts "No change for the host entry: #{host}\t#{old_ip}"
				return nil
			else
				@known_hosts[host]=new_ip
				@known_hosts[new_ip]=host
				puts "Entry refreshed: #{host}\t#{@known_hosts[host]}"
				return host
			end
		else
			puts "Host can no longer be resolved in the Internet. Entry removed: #{host}\t#{@known_hosts[host]}"
			@known_hosts.delete(host)
			return host
		end
	else
		puts "Error entry non exist: #{host}"
	end
rescue => ee
	puts "Exception on method #{__method__}: #{ee}"
end

#refresh_all ⇒ Object

Refresh all the entries in the local hosts by querying the Internet



266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
 
# File 'lib/wmap/host_tracker.rb', line 266

def refresh_all
	puts "Refresh all the entries in the local host repository in one shot."
	changes=Hash.new
	hosts=@known_hosts.keys
	@known_hosts=Hash.new
	changes=bulk_add(hosts)
	@known_hosts.merge!(changes)
	#@known_hosts.keys.map do |key|
	#	unless is_ip?(key)
	#		host=refresh(key)
	#		changes.push(host) unless host.nil?
	#	end
	#end
	puts "\n#{changes.size} Entries Refreshed:" if changes.size>0
	#changes.map { |x| puts x }
	puts "Done refreshing the local hosts."
	return changes
rescue => ee
	puts "Exception on method #{__method__}: #{ee}"
end

#save_known_hosts_to_file!(f_hosts = @hosts_file) ⇒ Object Also known as: save!

Save the current local hosts hash table into a (random) data repository file



66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
 
# File 'lib/wmap/host_tracker.rb', line 66

def save_known_hosts_to_file!(f_hosts=@hosts_file)
	puts "Saving the local host repository from memory to file: #{f_hosts} ..."
	timestamp=Time.now
	f=File.open(f_hosts, 'w')
	f.write "# local hosts file created by the #{self.class} class #{__method__} method at: #{timestamp}"
	@known_hosts.keys.sort.map do |key|
		unless key =~ /\d+\.\d+\.\d+\.\d+/
			f.write "\n#{key}\t#{@known_hosts[key]}"
		end
	end
	f.write "\n"
	f.close
	puts "local host repository is successfully saved to: #{f_hosts}"
#rescue => ee
#	puts "Exception on method #{__method__}: #{ee}"
end

#search(pattern) ⇒ Object Also known as: find

Search potential matching sites from the host store by using simple regular expression. Note that any upper-case char in the search string will be automatically converted into lower case



433
434
435
436
437
438
439
440
441
442
443
444
445
446
 
# File 'lib/wmap/host_tracker.rb', line 433

def search (pattern)
	puts "Search host store based on the regular expression: #{pattern}" if @verbose
	pattern=pattern.strip.downcase
	results=Array.new
	@known_hosts.keys.map do |key|
		if key =~ /#{pattern}/i
			results.push(key)
		end
	end
	return results
rescue Exception => ee
	puts "Exception on method #{__method__}: #{ee}"
	return nil
end

#sub_domain_known?(domain) ⇒ Boolean

Based on the current host store, to determine if an entry is a known sub-domain

Returns:

  • (Boolean) 


423
424
425
426
427
428
429
430
 
# File 'lib/wmap/host_tracker.rb', line 423

def sub_domain_known?(domain)
	puts "Validate sub-domain: #{domain}" if @verbose
	domain=domain.strip.downcase
	subs=dump_sub_domains
	return subs.include?(domain)
rescue Exception => ee
	puts "Exception on method #{__method__}: #{ee}"
end

#top_hostname(num) ⇒ Object

Top hostname - sort out most common host-name in the host store in descendant order



474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
 
# File 'lib/wmap/host_tracker.rb', line 474

def top_hostname (num)
	puts "Sort the host store for the most common hostname. " if @verbose
	h=Hash.new
	host_store=Hash.new
	top=Array.new
	# Build a host table from the host file
	f=File.open(@hosts_file, 'r')
	f.each do |line|
		next unless line =~ /\d+\.\d+\.\d+\.\d+/
		# skip the domain roots in the host list
		next if is_domain_root?(line.chomp)
		entry=line.chomp.split(%r{\t+|\s+|\,})
		key=entry[0].downcase
		value=entry[1]
		puts "Loading key value pair: #{key} - #{value}" if @verbose
		host_store[key] = Hash.new unless known_hosts.key?(key)
		host_store[key]= value
	end
	f.close
	host_store.keys.map do |key|
		host=key.split('.')
		if h.key?(host[0])
			h[host[0]]+=1
		else
			h[host[0]]=1
		end
	end
	result = h.keys.sort { |a,b| h[b] <=> h[a] } # Sort by value descendantly
	num = result.size if result.size < num
	for i in 0...num
		top.push(result[i])
	end
	return top
rescue Exception => ee
	puts "Exception on method #{__method__}: #{ee}"
	return nil
end