RubyGems - snapsearch-client-ruby - Versions diffs - 0.1.0 - Mend

snapsearch-client-ruby 0.1.0

Files changed (34) hide show

checksums.yaml +7 -0
data/Gemfile +9 -0
data/Gemfile.lock +83 -0
data/LICENSE +20 -0
data/README.md +109 -0
data/Rakefile +20 -0
data/VERSION +1 -0
data/examples/rack/Gemfile +5 -0
data/examples/rack/config.ru +88 -0
data/examples/rack/public/index.html +15 -0
data/examples/sinatra/Gemfile +5 -0
data/examples/sinatra/Gemfile.lock +90 -0
data/examples/sinatra/config.ru +15 -0
data/examples/sinatra/lib/sinatra_snap_search.rb +19 -0
data/examples/sinatra/public/index.html +15 -0
data/lib/rack/snap_search.rb +143 -0
data/lib/rack/snap_search/config.rb +85 -0
data/lib/snap_search.rb +14 -0
data/lib/snap_search/client.rb +147 -0
data/lib/snap_search/connection_exception.rb +15 -0
data/lib/snap_search/detector.rb +248 -0
data/lib/snap_search/exception.rb +8 -0
data/lib/snap_search/interceptor.rb +66 -0
data/lib/snap_search/validation_exception.rb +17 -0
data/resources/cacert.pem +3785 -0
data/resources/extensions.json +26 -0
data/resources/robots.json +208 -0
data/snapsearch.gemspec +31 -0
data/spec/lib/rack/qs_spec.rb +34 -0
data/spec/lib/rack/snap_search/config_spec.rb +56 -0
data/spec/lib/snap_search/detector_spec.rb +362 -0
data/spec/lib/snap_search/interceptor_spec.rb +116 -0
data/spec/spec_helper.rb +6 -0
metadata +216 -0

data/examples/sinatra/config.ru ADDED Viewed

@@ -0,0 +1,15 @@
+# Notes to run:
+#     gem install bundler
+#     bundle install
+#     rackup
+#
+# Testing:
+#    Visit http://localhost:9292/
+#    Visit http://localhost:9292/?_escaped_fragment_
+require 'bundler/setup'
+require 'pathname'
+$:.unshift( Pathname.new(__FILE__).join('..', 'lib').expand_path.to_s )
+require 'sinatra_snap_search'
+run SinatraSnapSearch

data/examples/sinatra/lib/sinatra_snap_search.rb ADDED Viewed

@@ -0,0 +1,19 @@
+require 'bundler/setup'
+require 'sinatra/base'
+require 'pathname'
+require 'snap_search'
+class SinatraSnapSearch < Sinatra::Base
+  configure do
+    set :root, SnapSearch.root.join('examples', 'sinatra')
+    enable :sessions, :logging, :method_override, :static
+    use Rack::SnapSearch, email: 'email', key: 'key'
+  end
+  get '/' do
+    redirect to('/index.html')
+  end
+end

data/examples/sinatra/public/index.html ADDED Viewed

@@ -0,0 +1,15 @@
+<!DOCTYPE html>
+<html lang='en'>
+  <head>
+    <meta charset='utf-8'>
+    <title>SnapSearch Example</title>
+    <link href="/css/blah.css" media="all" rel="stylesheet" />
+    <!--[if lt IE 9]>
+      <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
+    <![endif]-->
+    <!-- <script src="/js/blah.js"></script> -->
+  </head>
+  <body>
+    <h1>SnapSearch Example</h1>
+  </body>
+</html>

data/lib/rack/snap_search.rb ADDED Viewed

@@ -0,0 +1,143 @@
+require 'snap_search'
+require 'rack/snap_search/config'
+module Rack
+    # Use to enable SnapSearch detection within your web application.
+    class SnapSearch
+        # Initialize the middleware.
+        #
+        # @param [#call] app The Rack application.
+        # @param [Hash, #to_h] options Options to configure this middleware with.
+        # @yield [Rack::SnapSearch::Config, SnapSearch::Detector] A block to further modify the middleware.
+        # @yieldparam [Rack::SnapSearch::Config] config Options to configure this middleware with, optionally preset with the `options` param.
+        # @yieldparam [SnapSearch::Detector] detector The instance of the Detector class which will be used for detecting whether requests are coming from a robot.
+        def initialize(app, options={}, &block)
+            raise TypeError, 'app must respond to #call' unless app.respond_to?(:call)
+            raise TypeError, 'options must be a Hash or respond to #to_h or #to_hash' unless options.is_a?(Hash) || options.respond_to?(:to_h)    || options.respond_to?(:to_hash)
+            options = options.to_h rescue options.to_hash
+            @app = app
+            setup_config(options)
+            block.call(@config) if block_given?
+            setup_client
+            setup_detector
+            setup_interceptor
+        end
+        # Run the middleware.
+        #
+        # @param [Hash, to_h] app The Rack environment
+        def call(environment)
+            raise TypeError, 'environment must be a Hash or respond to #to_h or #to_hash' unless environment.is_a?(Hash) || environment.respond_to?(:to_h)    || environment.respond_to?(:to_hash)
+            environment = environment.to_h rescue environment.to_hash
+            setup_x_forwarded_proto(environment) if @config.x_forwarded_proto
+            setup_api_response_from_environment(environment) # Will set @api_response if one is given from the API
+            if @api_response
+              setup_attributes_from_api_response
+            else
+              setup_attributes_from_app(environment)
+            end
+            @config.response_callback.nil? ? rack_response : @config.response_callback.call(*rack_response)
+        end
+        protected
+        # == Initialization Helpers
+        # Setup the Config instance from the given options.
+        def setup_config(options)
+            @config = Rack::SnapSearch::Config.new(options)
+            @config.x_forwarded_proto ||= true
+        end
+        # Setup the Client instance from the @config.
+        def setup_client
+            @client = ::SnapSearch::Client.new(
+                email:          @config.email,
+                key:            @config.key,
+                parameters:     @config.parameters,
+                api_url:        @config.api_url,
+                ca_cert_file:   @config.ca_cert_file
+            )
+        end
+        # Setup the Detector instance from the @config.
+        def setup_detector
+            @detector = ::SnapSearch::Detector.new(
+                matched_routes:     @config.matched_routes,
+                ignored_routes:     @config.ignored_routes,
+                robots_json:        @config.robots_json,
+                extensions_json:    @config.extensions_json,
+                check_static_files: @config.check_static_files
+            )
+        end
+        # Setup the Interceptor instance using the @client and @detector, then setup callbacks if needed.
+        def setup_interceptor
+            @interceptor = ::SnapSearch::Interceptor.new(@client, @detector)
+            @interceptor.before_intercept(&@config.before_intercept) unless @config.before_intercept.nil?
+            @interceptor.after_intercept(&@config.after_intercept) unless @config.before_intercept.nil?
+        end
+        # == Running Helpers
+        # Alter the environment if the X-FORWARDED-PROTO header is given.
+        def setup_x_forwarded_proto(environment)
+            # Check X-Forwarded-Proto because Heroku SSL Support terminates at the load balancer
+            if environment['X-FORWARDED-PROTO']
+                environment['HTTPS'] = true && environment['rack.url_scheme'] = 'https' && environment['SERVER_PORT'] = 443 if environment['X-FORWARDED-PROTO'] == 'https'
+                environment['HTTPS'] = false && environment['rack.url_scheme'] = 'http' && environment['SERVER_PORT'] = 80 if env['X-FORWARDED-PROTO'] == 'http'
+            end
+        end
+        # Intercept and return the response.
+        def setup_api_response_from_environment(environment)
+            begin
+                request = Rack::Request.new(environment.to_h)
+                @api_response = @interceptor.intercept(request: request)
+            rescue SnapSearch::Exception => exception
+                @config.on_exception.nil? ? raise(exception) : @config.on_exception.call(exception)
+            end
+        end
+        # Setup the Location header in the response.
+        def setup_location_header
+            response_location_header = @api_response['headers'].find { |header| header['name'] == 'Location' }
+            @headers['Location'] = response_location_header['value'] unless response_location_header.nil?
+        end
+        # Setup the Status header and body in the response.
+        def setup_status_and_body
+            @status, @body = @api_response['status'], [ @api_response['html'] ] # Note that the body in the Rack response must be an interable containing Strings, we it's wrapped within an Array.
+        end
+        # Setup Location and Status headers, as well as teh body, if we got a response from SnapSearch.
+        def setup_attributes_from_api_response
+            setup_location_header
+            # TODO: Should setup_content_length_header?
+            setup_status_and_body
+        end
+        def setup_attributes_from_app(environment)
+          @status, @headers, @body = @app.call(environment)
+        end
+        def rack_response
+          [ @status, @headers, @body ]
+        end
+    end
+end

data/lib/rack/snap_search/config.rb ADDED Viewed

@@ -0,0 +1,85 @@
+module Rack
+    class SnapSearch
+        # The configuration class for the Rack middleware.
+        # Holds the attributes to initialize the Client, Interceptor, and Detector with.
+        class Config
+            ATTRIBUTES = [
+                :email, :key, :api_url, :ca_cert_file, :x_forwarded_proto, :parameters,               # Client options
+                :matched_routes, :ignored_routes, :robots_json, :extensions_json, :check_static_files # Detector options
+            ]
+            attr_accessor *ATTRIBUTES # Setup reader & writer instance methods for each attribute
+            # Create a new instance.
+            #
+            # @param [Hash] options The options to initialize this instance with.
+            # @option options [String] :email The email to authenticate with.
+            # @option options [String] :key The key to authenticate with.
+            # @option options [String] :api_url The API URL to send requests to.
+            # @option options [String] :ca_cert_file The CA Cert file to use when sending HTTPS requests to the API.
+            # @option options [String] :x_forwarded_proto Check X-Forwarded-Proto because Heroku SSL Support terminates at the load balancer
+            # @option options [String] :parameters Extra parameters to send to the API.
+            # @option options [String] :matched_routes Whitelisted routes. Should be an Array of Regexp instances.
+            # @option options [String] :ignored_routes Blacklisted routes. Should be an Array of Regexp instances.
+            # @option options [String] :robots_json A path of the JSON file containing the user agent whitelist & blacklist.
+            # @option options [String] :extensions_json A path to the JSON file containing a single Hash with the keys `ignore` and `match`. These keys contain Arrays of Strings (user agents)
+            # @option options [String] :check_static_files Set to `true` to ignore direct requests to files.
+            # @option options [Proc, #call] :on_exception The block to run when an exception within SnapSearch occurs.
+            # @option options [Proc, #call] :before_intercept A block to run before the interception of a bot.
+            # @option options [Proc, #call] :after_intercept A block to run after the interception of a bot.
+            # @option options [Proc, #call] :response_callback A block to manipulate the response from the SnapSearch API.
+            def initialize(options={})
+                raise TypeError, 'options must be a Hash or respond to #to_h' unless options.is_a?(Hash) || options.respond_to?(:to_h) || options.respond_to?(:to_hash)
+                options = options.to_h rescue options.to_hash
+                ATTRIBUTES.each do |attribute|
+                    send( "#{attribute}=", options[attribute] ) if options.has_key?(attribute)
+                end
+            end
+            # Getter/Setter for the `on_exception` attribute.
+            #
+            # @yield If given, the Proc or callable to set the attribute as.
+            # @return [Proc] The value of the attribute.
+            def on_exception(&block)
+                @on_exception = block if block_given?
+                @on_exception
+            end
+            # Getter/Setter for the `before_intercept` attribute on the Interceptor.
+            #
+            # @yield If given, the Proc or callable to set the attribute as.
+            # @return [Proc] The value of the attribute.
+            def before_intercept(&block)
+                @before_intercept = block if block_given?
+                @before_intercept
+            end
+            # Getter/Setter for the `after_intercept` attribute on the Interceptor.
+            #
+            # @yield If given, the Proc or callable to set the attribute as.
+            # @return [Proc] The value of the attribute.
+            def after_intercept(&block)
+                @after_intercept = block if block_given?
+                @after_intercept
+            end
+            # Getter/Setter for the `response_callback` attribute on the Interceptor.
+            #
+            # @yield If given, the Proc or callable to set the attribute as.
+            # @return [Proc] The value of the attribute.
+            def response_callback(&block)
+                @response_callback = block if block_given?
+                @response_callback
+            end
+        end
+    end
+end

data/lib/snap_search.rb ADDED Viewed

@@ -0,0 +1,14 @@
+require 'pathname'
+module SnapSearch
+    def self.root
+        @root ||= Pathname.new(__FILE__).join('..', '..').expand_path
+    end
+end
+require 'snap_search/client'
+require 'snap_search/detector'
+require 'snap_search/interceptor'
+require 'rack/snap_search'

data/lib/snap_search/client.rb ADDED Viewed

@@ -0,0 +1,147 @@
+require 'json'
+require 'httpi'
+require 'snap_search/connection_exception'
+require 'snap_search/validation_exception'
+module SnapSearch
+    # The Client sends an authenticated HTTP request to the SnapChat API and returns the `content`
+    # field from the JSON response body.
+    class Client
+        attr_reader :email, :key, :parameters, :api_url, :ca_cert_file
+        # Create a new Client instance.
+        #
+        # @param [Hash, #to_h] options The options to create the Client with.
+        # @option options [String, #to_s] :email The email to authenticate with.
+        # @option options [String, #to_s] :key The secret authentication key.
+        # @option options [Hash, #to_h] :parameters ({}) The parameters to send with the HTTP request.
+        # @option options [String, #to_s] :api_url (https://snapsearch.io/api/v1/robot) The URL to send the HTTP request to.
+        # @option options [String, #to_s] :ca_cert_file (ROOT/resources/cacert.pem) The CA cert file to use with request.
+        def initialize(options={})
+            initialize_attributes(options)
+        end
+        # Validate and set the value of the `email` attribute.
+        #
+        # @param [String, #to_s] value The value to set the attribute to.
+        # @return [String] The new value of the attribute.
+        def email=(value)
+            raise TypeError, 'email must be a String or respond to #to_s' unless value.is_a?(String) || respond_to?(:to_s)
+            value = value.to_s
+            raise ArgumentError, 'email must be an email address' unless value.include?(?@)
+            @email = value
+        end
+        # Validate and set the value of the `key` attribute.
+        #
+        # @param [String, #to_s] value The value to set the attribute to.
+        # @return [String] The new value of the attribute.
+        def key=(value)
+            @key = value.nil? ? nil : value.to_s
+        end
+        # Validate and set the value of the `parameters` attribute.
+        #
+        # @param [Hash, #to_h] value The value to set the attribute to.
+        # @return [Hash] The new value of the attribute.
+        def parameters=(value)
+            raise TypeError, 'parameters must be a Hash or respond to #to_h or #to_hash' unless value.is_a?(Hash) || value.respond_to?(:to_h) || value.respond_to?(:to_hash)
+            value = value.to_h rescue value.to_hash
+            @parameters = value.to_h
+        end
+        # Validate and set the value of the `api_url` attribute.
+        #
+        # @param [String, #to_s] value The value to set the attribute to.
+        # @return [String] The new value of the attribute.
+        def api_url=(value)
+            raise TypeError, 'api_url must be a String or respond_to #to_s' unless value.is_a?(String) || value.respond_to?(:to_s)
+            @api_url = value.to_s
+        end
+        # Validate and set the value of the `ca_cert_file` attribute.
+        #
+        # @param [String, #to_s] value The value to set the attribute to.
+        # @return [String] The new value of the attribute.
+        def ca_cert_file=(value)
+            raise TypeError, 'ca_cert_file must be a String or respond_to #to_s' unless value.is_a?(String) || value.respond_to?(:to_s)
+            @ca_cert_file = value.to_s
+        end
+        # Send an authenticated HTTP request to the `api_url` and return the `content` field from the JSON response body.
+        #
+        # @param [String, #to_s] url The url to send in the parameters to the `api_url`.
+        # @return [String] The `content` field from the JSON response body.
+        def request(url)
+            raise TypeError, 'url must be a String or respond_to #to_s' unless url.is_a?(String) || url.respond_to?(:to_s)
+            @parameters['url'] = url.to_s # The URL must contain the entire URL with the _escaped_fragment_ parsed out
+            content_from_response(send_request)
+        end
+        protected
+        # Initialize this instance based on options passed.
+        #
+        # @param [Hash, #to_h] options The options to create the Client with.
+        # @option options [String, #to_s] :email The email to authenticate with.
+        # @option options [String, #to_s] :key The secret authentication key.
+        # @option options [Hash, #to_h] :parameters ({}) The parameters to send with the HTTP request.
+        # @option options [String, #to_s] :api_url (https://snapsearch.io/api/v1/robot) The URL to send the HTTP request to.
+        # @option options [String, #to_s] :ca_cert_file (ROOT/resources/cacert.pem) The CA cert file to use with request.
+        def initialize_attributes(options)
+            raise TypeError, 'options must be a Hash or respond to #to_h' unless options.is_a?(Hash) || options.respond_to?(:to_h) || options.respond_to?(:to_hash)
+            options = options.to_h rescue options.to_hash
+            options = {
+                parameters: {},
+                api_url: 'https://snapsearch.io/api/v1/robot',
+                ca_cert_file: SnapSearch.root.join('resources', 'cacert.pem')
+            }.merge(options.to_h)
+            self.email, self.key, self.parameters, self.api_url, self.ca_cert_file = options.values_at(:email, :key, :parameters, :api_url, :ca_cert_file)
+        end
+        # Send an authenticated HTTP POST request encoded in JSON to the API URL
+        # using the HTTP client adapter of the developer's choice.
+        #
+        # @return [HTTPI::Response] The HTTP response object.
+        def send_request
+            request = HTTPI::Request.new
+            request.url = api_url
+            request.auth.basic(email, key)
+            request.auth.ssl.ca_cert_file = ca_cert_file
+            request.auth.ssl.verify_mode = :peer
+            request.open_timeout = 30
+            request.headers['Content-Type'] = 'application/json'
+            request.headers['Accept-Encoding'] = 'gzip, deflate, identity'
+            request.body = @parameters.to_json
+            HTTPI.post(request)
+        rescue
+            raise ConnectionException
+        end
+        # Retrieve the `content` or raise an error based on the `code` field in the JSON response.
+        #
+        # @return [HTTPI::Response] The HTTP response object.
+        def content_from_response(response)
+            body = JSON.parse(response.body)
+            case body['code']
+            when 'success' then body['content']
+            when 'validation_error' then raise( ValidationException, body['content'] )
+            else; false # System error on SnapSearch; Nothing we can do # TODO: Raise exception?
+            end
+        end
+    end
+end