crawler_detect 1.1.2 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 673437c210276238f1622c6dee5d01546da01cfa84b24fb8cf2daab2b8de94cf
-  data.tar.gz: 8a3e9b62efee0be6030022bdd2bfa2d029d278e0423f8cd30f19a6cae0ae4446
+  metadata.gz: abc20006d901205f658b54f78a94acb2480f3efbbc80213540381a1f956ce9d8
+  data.tar.gz: 53a3959effd4a78f93afa1d438ea06b6db567a3f3227311f24bbc7a1ea0d89fc
 SHA512:
-  metadata.gz: 9cf065939aa5fd30f5b295f42a38095648abaaa17de39ec17eb483d0eef14e3be01d56e6ac334b567a0640b87f0a514be11922bdc612066d29610104d85a992b
-  data.tar.gz: f6cae54635ef3224ba6b0289a5c9f199bd5630ca06c6a0d0b7efce8ce7df65d53ac179c1a23dd309ebf3d32348365e3e835f2484780f2a9f148e4934f7ed43b4
+  metadata.gz: '018d27fba7246b394e3cb5444cd8c0862e4ea08bf1b9e1fa12adb46d887b8753820ecbc103030c89af0b0e8ab05fa2c1d42ee33466685eaadfbc61b3185ef32f'
+  data.tar.gz: 02536c1035099e35961fafc9877a3d29d72ff5ed20848f2f4eb183d4fbbc300d6d5d7d68d23282e49e2a19ad589c04bc6ffb8dd8200e14b81a602286af924261

data/CHANGELOG.md

@@ -3,6 +3,10 @@
 This changelog **does not contain** raw data updates 
 but only major changes.
 
+1.2.0
+---------
+- Speed up crawler detection by caching Regexp objects [#38]
+
 1.1.0
 ---------
 - Moves to Ruby's Stdlib JSON implementation to reduce dependencies

data/Gemfile.lock

@@ -1,13 +1,13 @@
 PATH
   remote: .
   specs:
-    crawler_detect (1.1.1)
+    crawler_detect (1.1.2)
       qonfig (~> 0.24)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    activesupport (6.0.3.1)
+    activesupport (6.0.4.1)
       concurrent-ruby (~> 1.0, >= 1.0.2)
       i18n (>= 0.7, < 2)
       minitest (~> 5.1)
@@ -19,31 +19,31 @@ GEM
       rubocop-rails (= 2.5.2)
       rubocop-rake (= 0.5.1)
       rubocop-rspec (= 1.38.1)
-    ast (2.4.0)
-    awesome_print (1.8.0)
-    byebug (11.1.2)
-    coderay (1.1.2)
-    concurrent-ruby (1.1.6)
-    diff-lcs (1.3)
-    fuubar (2.5.0)
+    ast (2.4.2)
+    awesome_print (1.9.2)
+    byebug (11.1.3)
+    coderay (1.1.3)
+    concurrent-ruby (1.1.9)
+    diff-lcs (1.4.4)
+    fuubar (2.5.1)
       rspec-core (~> 3.0)
       ruby-progressbar (~> 1.4)
-    i18n (1.8.2)
+    i18n (1.8.10)
       concurrent-ruby (~> 1.0)
     jaro_winkler (1.5.4)
     method_source (1.0.0)
-    minitest (5.14.1)
-    parallel (1.19.1)
+    minitest (5.14.4)
+    parallel (1.20.1)
     parallel_tests (2.32.0)
       parallel
-    parser (2.7.1.2)
-      ast (~> 2.4.0)
-    pry (0.13.1)
+    parser (3.0.2.0)
+      ast (~> 2.4.1)
+    pry (0.14.1)
       coderay (~> 1.1)
       method_source (~> 1.0)
-    pry-byebug (3.9.0)
+    pry-byebug (3.8.0)
       byebug (~> 11.0)
-      pry (~> 0.13.0)
+      pry (~> 0.10)
     pry-meta (0.0.10)
       awesome_print
       pry
@@ -52,26 +52,26 @@ GEM
     pry-remote (0.1.8)
       pry (~> 0.9)
       slop (~> 3.0)
-    qonfig (0.24.1)
+    qonfig (0.26.0)
     rack (2.2.3)
     rack-test (1.1.0)
       rack (>= 1.0, < 3)
     rainbow (3.0.0)
-    rake (13.0.1)
-    rexml (3.2.4)
-    rspec (3.9.0)
-      rspec-core (~> 3.9.0)
-      rspec-expectations (~> 3.9.0)
-      rspec-mocks (~> 3.9.0)
-    rspec-core (3.9.1)
-      rspec-support (~> 3.9.1)
-    rspec-expectations (3.9.1)
+    rake (13.0.6)
+    rexml (3.2.5)
+    rspec (3.10.0)
+      rspec-core (~> 3.10.0)
+      rspec-expectations (~> 3.10.0)
+      rspec-mocks (~> 3.10.0)
+    rspec-core (3.10.1)
+      rspec-support (~> 3.10.0)
+    rspec-expectations (3.10.1)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.9.0)
-    rspec-mocks (3.9.1)
+      rspec-support (~> 3.10.0)
+    rspec-mocks (3.10.2)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.9.0)
-    rspec-support (3.9.2)
+      rspec-support (~> 3.10.0)
+    rspec-support (3.10.2)
     rubocop (0.82.0)
       jaro_winkler (~> 1.5.1)
       parallel (~> 1.10)
@@ -90,13 +90,13 @@ GEM
       rubocop
     rubocop-rspec (1.38.1)
       rubocop (>= 0.68.1)
-    ruby-progressbar (1.10.1)
+    ruby-progressbar (1.11.0)
     slop (3.6.0)
     thread_safe (0.3.6)
-    tzinfo (1.2.7)
+    tzinfo (1.2.9)
       thread_safe (~> 0.1)
     unicode-display_width (1.7.0)
-    zeitwerk (2.3.0)
+    zeitwerk (2.4.2)
 
 PLATFORMS
   ruby

data/lib/crawler_detect/library.rb

@@ -5,12 +5,16 @@ module CrawlerDetect
   module Library
     DATA_CLASSES = [Library::Headers, Library::Exclusions, Library::Crawlers].freeze
 
+    @regexp_cache = {}
+
     class << self
       # @param param [String] Name of raw data
       # @return [Regexp]
       def get_regexp(param)
-        data = get_array(param)
-        %r{#{data.join('|')}}i
+        @regexp_cache[param] ||= begin
+          data = get_array(param)
+          %r{#{data.join('|')}}i
+        end
       end
 
       # @param param [String] Name of raw data
@@ -18,6 +22,12 @@ module CrawlerDetect
       def get_array(param)
         const_get("CrawlerDetect::Library::#{param.capitalize}").send(:data)
       end
+
+      # @return [void]
+      def reset_cache
+        DATA_CLASSES.each(&:reload_data)
+        @regexp_cache = {}
+      end
     end
   end
 end

data/lib/crawler_detect/version.rb

@@ -2,5 +2,5 @@
 
 # @since 0.1.0
 module CrawlerDetect
-  VERSION = "1.1.2"
+  VERSION = "1.2.0"
 end

data/lib/crawler_detect.rb

@@ -32,7 +32,7 @@ module CrawlerDetect
     # @param config [Proc]
     def setup!(&config)
       @config = CrawlerDetect::Config.new(&config)
-      Library::DATA_CLASSES.each(&:reload_data)
+      Library.reset_cache
     end
 
     # @since 1.0.0

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: crawler_detect
 version: !ruby/object:Gem::Version
-  version: 1.1.2
+  version: 1.2.0
 platform: ruby
 authors:
 - Pavel Kozlov
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2021-04-10 00:00:00.000000000 Z
+date: 2021-09-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: qonfig