google_safe_browsing 0.3.9 → 0.4.0

data/lib/google_safe_browsing/canonicalize.rb

@@ -33,6 +33,7 @@ module GoogleSafeBrowsing
 
       #split into host and path components
       splits = split_host_path(cann)
+
       cann = fix_host( splits[:host] ) + '/' + fix_path( splits[:path] )
 
       # add leading protocol
@@ -48,6 +49,8 @@ module GoogleSafeBrowsing
     # @return (Array) array of cannonicalized url permutation strings
     def self.urls_for_lookup(lookup_url)
       lookup_url = url(lookup_url)
+      #return empty array if url returns nil; for invalid url
+      return [] if lookup_url.blank?
 
       lookup_url = remove_protocol(lookup_url)
 
@@ -71,219 +74,262 @@ module GoogleSafeBrowsing
       cart_prod(host_strings, path_strings)
     end
 
-   # private
+    # private
 
-      # Generates the path permutations from the raw path string
-      #
-      # @param (String) raw_path path split from the full url string
-      # @return (Array) array of path permutation strings
-      def self.generate_path_strings(raw_path)
-        return [ '/', '' ] if raw_path == ''
+    # Generates the path permutations from the raw path string
+    #
+    # @param (String) raw_path path split from the full url string
+    # @return (Array) array of path permutation strings
+    def self.generate_path_strings(raw_path)
+      return [ '/', '' ] if raw_path == ''
 
-        path_split = raw_path.split('?')
-        path = path_split[0] || ''
-        params = path_split[1] || ''
+      path_split = raw_path.split('?')
+      path = path_split[0] || ''
+      params = path_split[1] || ''
 
 
-        path_components = path.split('/').first(3)
-        path_strings = [ '/' ]
-        path_components.length.times do
-          path_strings << '/' + path_components.join('/')
-          path_components.pop
-        end
+      path_components = path.split('/').first(3)
+      path_strings = [ '/' ]
+      path_components.length.times do
+        path_strings << '/' + path_components.join('/')
+        path_components.pop
+      end
 
-        path_strings.map! do |p|
-          unless p.index('.')
-            p + '/'
-          else
-            p
-          end
-        end
-        path_strings.map!{ |p| p.to_s.gsub!(/\/+/, '/') }
-        path_strings.compact!
-        path_strings.uniq!
-
-        unless params.blank?
-          path_strings | path_strings.map do |p|
-            if p[-1] == '/'
-              p
-            else
-              "#{p}?#{params}"
-            end
-          end
+      path_strings.map! do |p|
+        unless p.index('.')
+          p + '/'
         else
-          return path_strings
+          p
         end
       end
+      path_strings.map!{ |p| p.to_s.gsub!(/\/+/, '/') }
+      path_strings.compact!
+      path_strings.uniq!
 
-      # Returns the cartesian product of two arrays by concatination of the string representation of the elements
-      #
-      # @param (Array) a_one array of strings
-      # @param (Array) a_two array of strings
-      # @return (Array) cartesian product of arrays with elements concatinated
-      def self.cart_prod(a_one, a_two)
-        result = []
-        a_one.each do |i|
-          a_two.each do |j|
-            result << "#{i}#{j}"
+      unless params.blank?
+        path_strings | path_strings.map do |p|
+          if p[-1] == '/'
+            p
+          else
+            "#{p}?#{params}"
           end
         end
-        result
+      else
+        return path_strings
       end
+    end
 
-      # Takes the canonicalized url and splits the host and the path apart
-      #
-      # @param (String) cann canonicalized url string
-      # @return (Hash) !{ :host => host_part, :path => path_part }
-      def self.split_host_path(cann)
-        ret= { :host => cann, :path => '' }
-        split_point = cann.index('/')
-        if split_point
-          ret[:host] = cann[0..split_point-1]
-          ret[:path] = cann[split_point+1..-1]
+    # Returns the cartesian product of two arrays by concatination of the string representation of the elements
+    #
+    # @param (Array) a_one array of strings
+    # @param (Array) a_two array of strings
+    # @return (Array) cartesian product of arrays with elements concatinated
+    def self.cart_prod(a_one, a_two)
+      result = []
+      a_one.each do |i|
+        a_two.each do |j|
+          result << "#{i}#{j}"
         end
-
-        ret
       end
+      result
+    end
 
-      # Strips the fragment portion of the url string (the last '#' and everything after)
-      #
-      # @param (String) string url
-      # @return (String) parameter with the fragment removed
-      def self.remove_fragment(string)
-        string = string[0..string.index('#')-1] if string.index('#')
-        string
+    # Takes the canonicalized url and splits the host and the path apart
+    #
+    # @param (String) cann canonicalized url string
+    # @return (Hash) !{ :host => host_part, :path => path_part }
+    def self.split_host_path(cann)
+      ret= { :host => cann, :path => '' }
+      split_point = cann.index('/')
+      if split_point
+        ret[:host] = cann[0..split_point-1]
+        ret[:path] = cann[split_point+1..-1]
       end
 
-      # Continues to unescape the url until unescaping has no effect
-      #
-      # @param (String) url url string
-      # @return (String) fully unescaped url string
-      def self.recursively_unescape(url)
-        compare_url = url.clone 
+      ret
+    end
+
+    # Strips the fragment portion of the url string (the last '#' and everything after)
+    #
+    # @param (String) string url
+    # @return (String) parameter with the fragment removed
+    def self.remove_fragment(string)
+      string = string[0..string.index('#')-1] if string.index('#')
+      string
+    end
+
+    # Continues to unescape the url until unescaping has no effect
+    #
+    # @param (String) url url string
+    # @return (String) fully unescaped url string
+    def self.recursively_unescape(url)
+      compare_url = url.clone 
+      url = URI.unescape(url)
+      while(compare_url != url)
+        compare_url = url.clone
         url = URI.unescape(url)
-        while(compare_url != url)
-          compare_url = url.clone
-          url = URI.unescape(url)
-        end
-        url
       end
+      url
+    end
 
-      # Apply initial fixes to host string
-      #
-      # @param (String) host host string
-      # @return (String) standardized host string
-      def self.fix_host(host)
-        #puts "In Host: #{host}"
-        # remove leading and trailing dots, multiple dots to one
-        host.gsub!(/\A\.+|\.+\Z/, '')
-        host.gsub!(/\.+/, '.')
-
-        host.downcase!
-
-        if host =~ /^\d+$/
-          host = IP::V4.new(host.to_i).to_addr
-        elsif host =~ /\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}/
-          host = IP.new(host).to_addr 
+    # Apply initial fixes to host string
+    #
+    # @param (String) host host string
+    # @return (String) standardized host string
+    def self.fix_host(host)
+      #puts "In Host: #{host}"
+      # remove leading and trailing dots, multiple dots to one
+      host.gsub!(/\A\.+|\.+\Z/, '')
+      host.gsub!(/\.+/, '.')
+
+      host.downcase!
+
+      host_splits = self.split_username_password_and_port(host)
+
+      if host_splits[:host] =~ /^\d+$/
+        host_splits[:host] = IP::V4.new(host.to_i).to_addr
+      elsif host_splits[:host] =~ /\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}/
+        begin
+          host_splits[:host] = IP.new(host).to_addr 
+        rescue ArgumentError
         end
-
-        host
       end
 
-      # Apply initial fixes to path string
-      #
-      # @param (String) path path string
-      # @return (String) standardized path string
-      def self.fix_path(path)
-        #puts "In Path: #{path}"
-
-        #remove leading slash
-        path = path[1..-1] if path[0..0] == '/'
+      result = host_splits[:host]
+      result = "#{host_splits[:creds]}@#{result}" unless host_splits[:creds].blank?
+      result = "#{result}:#{host_splits[:port]}" unless host_splits[:port].blank?
+      result
+    end
 
-        preserve_trailing_slash = ( path[-1..-1] == '/' )
+    # Apply initial fixes to path string
+    #
+    # @param (String) path path string
+    # @return (String) standardized path string
+    def self.fix_path(path)
+      #puts "In Path: #{path}"
 
-        if path.index('?')
-          first_ques = path.index('?')
-          params = path[first_ques..-1]
-          path = path[0..first_ques-1]
-        end
+      #remove leading slash
+      path = path[1..-1] if path[0..0] == '/'
 
-        # remove multiple '/'
-        path.gsub!(/\/+/, '/')
+      preserve_trailing_slash = ( path[-1..-1] == '/' )
 
-        new_path_array = []
-        path.split('/').each do |p|
-          new_path_array << p unless p == '.' || p == '..'
-          new_path_array.pop if p == '..'
-        end
+      if path.index('?')
+        first_ques = path.index('?')
+        params = path[first_ques..-1]
+        path = path[0..first_ques-1]
+      end
 
-        path = new_path_array.join('/')
-        path += '/' if preserve_trailing_slash
-        path += params if params
+      # remove multiple '/'
+      path.gsub!(/\/+/, '/')
 
-        path
+      new_path_array = []
+      path.split('/').each do |p|
+        new_path_array << p unless p == '.' || p == '..'
+        new_path_array.pop if p == '..'
       end
 
-      # Escape the url, but do not escape certain characters; such as the carat
-      #
-      # @param (String) url url string
-      # @return (String) escaped url string
-      def self.strict_escape(url)
-        url = URI.escape url
+      path = new_path_array.join('/')
+      path += '/' if preserve_trailing_slash
+      path += params if params
 
-        # unescape carat, may need other optionally escapeable chars
-        url.gsub!('%5E','^')
+      path
+    end
 
-        url
-      end
+    # Escape the url, but do not escape certain characters; such as the carat
+    #
+    # @param (String) url url string
+    # @return (String) escaped url string
+    def self.strict_escape(url)
+      url = URI.escape url
 
-      # Strip the leading protocol from the url string
-      #
-      # @param (String) cann url string
-      # @return (String) url string without the protocol
-      def self.remove_protocol(cann)
-        if cann.index(PROTOCOL_DELIMITER)
-          delimiting_index = cann.index(PROTOCOL_DELIMITER)
-          @protocol = cann[0..delimiting_index-1]
-          protocol_end_index = delimiting_index + PROTOCOL_DELIMITER.length
-          cann = cann[protocol_end_index..-1]
-        end
-        cann
-      end
+      # unescape carat, may need other optionally escapeable chars
+      url.gsub!('%5E','^')
+
+      url
+    end
 
-      # Strip the user name, password and port number from the url
-      #
-      # @param (String) host_string host portion of the url
-      # @return (String) host portion of the url without the username, password and port
-      def self.strip_username_password_and_port_from_host(host_string)
-        host_string = remove_port(host_string)
-        remove_username_and_password(host_string)
+    # Strip the leading protocol from the url string
+    #
+    # @param (String) cann url string
+    # @return (String) url string without the protocol
+    def self.remove_protocol(cann)
+      if cann.index(PROTOCOL_DELIMITER)
+        delimiting_index = cann.index(PROTOCOL_DELIMITER)
+        @protocol = cann[0..delimiting_index-1]
+        protocol_end_index = delimiting_index + PROTOCOL_DELIMITER.length
+        cann = cann[protocol_end_index..-1]
       end
+      cann
+    end
 
-      # Strip port number from host string
-      #
-      # @param (see strip_username_password_and_port_from_host)
-      # @return (String) host part without the port number
-      def self.remove_port(host_string)
-        port_sep = host_string.rindex(':')
-        if port_sep
-          host_string[0..port_sep-1]
-        else
-          host_string
-        end
+    # Strip the user name, password and port number from the url
+    #
+    # @param (String) host_string host portion of the url
+    # @return (String) host portion of the url without the username, password and port
+    def self.strip_username_password_and_port_from_host(host_string)
+      host_string = remove_port(host_string)
+      remove_username_and_password(host_string)
+    end
+
+    # Strip port number from host string
+    #
+    # @param (see strip_username_password_and_port_from_host)
+    # @return (String) host part without the port number
+    def self.remove_port(host_string)
+      self.split_port(host_string)[:host]
+    end
+
+    # Strip user name and password from host part of url
+    #
+    # @param (see remove_port)
+    # @return (String) host part of url without user name or password
+    def self.remove_username_and_password(host_string)
+      self.split_username_and_password(host_string)[:host]
+    end
+
+    # Split user name, passowrd from the host
+    #
+    # @param (see remove_port)_
+    # @return (Hash) :host has the host string, :creds holds the username and password string
+    def self.split_username_and_password(host_string)
+      un_sep = host_string.index('@')
+      result = {}
+      if un_sep
+        splits = host_string.split('@')
+        result[:host] = splits[1]
+        result[:creds] = splits[0]
+      else
+        result[:host] = host_string
+        result[:creds] = nil
       end
+      result
+    end
 
-      # Strip user name and password from host part of url
-      #
-      # @param (see remove_port)
-      # @return (String) host part of url without user name or password
-      def self.remove_username_and_password(host_string)
-        un_sep = host_string.index('@')
-        if un_sep
-          host_string[un_sep+1..-1]
-        else
-          host_string
-        end
+    # Split post number and host string into a hash
+    #
+    # @param (See remove_port)
+    # @return (Hash) :host has the host string, :port holds the port number
+    def self.split_port(host_string)
+      port_sep = host_string.rindex(':')
+      result = {}
+      if port_sep
+        splits = host_string.split(':')
+        result[:host] = splits[0]
+        result[:port] = splits[1]
+      else
+        result[:host] = host_string
+        result[:port] = nil
       end
+      result
+    end
+
+    # Split the user name, password and port from the host string
+    #
+    # @param (see remove_port)
+    # @return (Hash) :host as the host string; :creds has the username and password; :port holds the port number
+    def self.split_username_password_and_port(host_string)
+      result = self.split_username_and_password(host_string)
+      result.merge(self.split_port(result[:host]))
+    end
   end
 end

data/lib/google_safe_browsing/version.rb

@@ -1,3 +1,3 @@
 module GoogleSafeBrowsing
-  VERSION = "0.3.9"
+  VERSION = "0.4.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: google_safe_browsing
 version: !ruby/object:Gem::Version
-  version: 0.3.9
+  version: 0.4.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-06-06 00:00:00.000000000 Z
+date: 2012-07-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rails
@@ -151,7 +151,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -2592586138011771612
+      hash: -4373468862577111822
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -160,10 +160,10 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -2592586138011771612
+      hash: -4373468862577111822
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.23
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
 summary: Rails 3 plugin for Google's Safe Browsing API v2