legitbot 1.0.0 → 1.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 34d1432c7c405d783b22a46851db88ccdea9f303defeccdd1cf98604bbb6ce09
-  data.tar.gz: a66b586f4b2dca67fb875ea37add6e7d89a7ce5d0705c3d1898d96ecf091036e
+  metadata.gz: 1596ed8c3809fc3c3068f14d8bbbcf84232286fd7157fe724ba9515d195259cd
+  data.tar.gz: f0078d0404d752550adeeaa9c64954cbcec57fef3d0b37c98bc50d765c29bc1f
 SHA512:
-  metadata.gz: cad1db2571e939020f74e871365c4748dd78ff18eb8ad9f005ea5bf5b0707835e296afa2601fc6309c994f69b7903d21da788fc219f5d712ee75e1ae9885fb7b
-  data.tar.gz: c72af598d60c55aff35a1b5e244dcde160a67589c588d68b9482d5e5c5f0590441c92505ec94beb462ff70a730ec9aabe80877a2d9db2f72c566c3a9c0b19059
+  metadata.gz: 5640ae1e351bbd697325cd0bed0bdac45c3726e7b31923b7b5c8f51859ed025d4eb368d937a2b3bf9ef6c150d83418f8e019304dec3bc1b010572a4e1598c661
+  data.tar.gz: bf326da52d3adf1b2cfa3693b51cc763daef54c9b175cfb91b437b213722a0f578565db553f1240b6d6ee47d159bb418fdcc1db1f95cb14696b2bfb52e50b75d

data/README.md

@@ -67,3 +67,8 @@ Apache 2.0
   detects bots by `User-Agent`
 * [crawler_detect](https://github.com/loadkpi/crawler_detect) is a Ruby gem and Rack
   middleware to detect crawlers by few different request headers, including `User-Agent`
+* Project Honeypot's
+  [http:BL](https://www.projecthoneypot.org/httpbl_api.php) can not only
+  classify IP as a search engine, but also label them as suspicious and
+  reports the number of days since the last activity. My implementation of
+  the protocol in Scala is [here](https://github.com/osinka/httpbl).

data/lib/legitbot/legitbot.rb

@@ -18,6 +18,7 @@ module Legitbot
   # otherwise.
   # :yields: a found bot
   #
+  # rubocop:disable Metrics/CyclomaticComplexity
   def self.bot(user_agent, ip)
     bots = @rules
            .select { |rule| rule[:fragments].any? { |f| user_agent.index f } }
@@ -32,6 +33,7 @@ module Legitbot
       selected
     end
   end
+  # rubocop:enable Metrics/CyclomaticComplexity
 
   def self.rule(clazz, fragments)
     @rules << { class: clazz, fragments: fragments }

data/lib/legitbot/validators/ip_ranges.rb

@@ -59,22 +59,26 @@ module Legitbot
           partition_ips(@ip_ranges_loader.call)
         end
 
-        # rubocop:disable Metrics/AbcSize, Metrics/MethodLength
         def partition_ips(ips)
-          return [] if ips.empty?
+          return [] unless ips&.any?
 
           ips
             .map { |cidr| IPAddr.new(cidr) }
             .partition(&:ipv4?)
             .each_with_index
             .map do |list, index|
-              ranges = list.map(&:to_range).map do |r|
-                (r.begin.to_i..r.end.to_i)
-              end
-              [FAMILIES[index], IntervalTree::Tree.new(ranges)]
+              [FAMILIES[index], build_interval_tree(list)]
             end.to_h
         end
-        # rubocop:enable Metrics/AbcSize, Metrics/MethodLength
+
+        private
+
+        def build_interval_tree(list)
+          ranges = list.map(&:to_range).map do |r|
+            (r.begin.to_i..r.end.to_i)
+          end
+          IntervalTree::Tree.new(ranges)
+        end
       end
     end
   end

data/lib/legitbot/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Legitbot
-  VERSION = '1.0.0'
+  VERSION = '1.0.1'
 end

data/test/legitbot/validators/ip_ranges_test.rb

@@ -46,6 +46,11 @@ module Legitbot
       end
     end
 
+    class NilRanges
+      include IpRanges
+      ip_ranges { nil }
+    end
+
     class IpRangesTest < Minitest::Test
       def test_partition_method
         empty = NoRanges.partition_ips([])
@@ -108,6 +113,10 @@ module Legitbot
         assert_equal 2, LoadRanges.counter
       end
       # rubocop:enable Metrics/AbcSize
+
+      def test_nil_ranges
+        assert NilRanges.valid_ip?('127.0.0.1')
+      end
     end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: legitbot
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.0.1
 platform: ruby
 authors:
 - Alexander Azarov
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-06-18 00:00:00.000000000 Z
+date: 2020-07-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: augmented_interval_tree