galetahub-copyscape 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 7668fcb74ce8f1b89373abc290d5787823ab6200
+  data.tar.gz: 6990772cee3f7d5d70d5dc5c1698b5a701cf6043
+SHA512:
+  metadata.gz: ac1bbbb27fbd06c5feaad9bb34c4eb308d56c02dc1e0dfa95680ca703d9da2a9bb03cf2b886a2c18938c3a6684b9e25e67ceccad22e11d21e1b76bca97cb8e5c
+  data.tar.gz: fa8a45afffed617caff217e7c65b0d608a78a886a9bd000f124a74c30df7af06d5826b24718b7f916581129d3206587eedbac552bb0c7c69ba1d3ff5a0675569

data/MIT-LICENSE

@@ -0,0 +1,20 @@
+Copyright 2018 Fodojo LLC
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,51 @@
+copyscape
+=========
+
+Ruby wrapper for the Copyscape API.
+
+
+Usage
+-----
+
+First, you'll need to setup your [Copyscape](http://www.copyscape.com/) account and whatnot.  You can do
+that [here](http://www.copyscape.com/signup.php?pro=1&o=f).
+API documentation [here](http://www.copyscape.com/apiconfigure.php).
+
+Next, install the gem.
+
+    $ gem install copyscape
+
+And then you can do things like this...
+
+    Copyscape.username = 'yourname'
+    Copyscape.api_key = 'abc123'
+    
+    # URL search
+    search = Copyscape.url_search("http://www.copyscape.com/example.html")
+    search.duplicate? # => true
+    search.count # => 81
+    search.duplicates.each do |duplicate|
+      puts duplciate['title']
+      puts duplicate['url']
+      puts duplicate['textsnippet']
+      puts duplicate['htmlsnippet']
+      puts duplicate['minwordsmatched']
+    end
+    
+    # Text search
+    search = Copyscape.text_search('This is some text I want to check for plagurism')
+    search.duplicate? # => false
+
+    # Search with additional options
+    Copyscape.text_search('This is some text I want to check for plagurism', :x => 1, :c => 5)
+    
+    
+Currently, there is no support in the gem for "private index" searching, though
+it would be pretty easy to add.
+
+    
+More...
+-------
+
+I'm in no way associated with Copyscape.
+

data/Rakefile

@@ -0,0 +1,17 @@
+# encoding: utf-8
+
+require 'rake'
+require 'rake/testtask'
+
+require File.join(File.dirname(__FILE__), 'lib', 'copyscape', 'version')
+
+desc 'Default: run unit tests.'
+task :default => :test
+
+desc 'Test the enum_field plugin.'
+Rake::TestTask.new(:test) do |t|
+  t.libs << 'lib'
+  t.libs << 'test'
+  t.pattern = 'test/**/*_test.rb'
+  t.verbose = true
+end

data/lib/copyscape.rb

@@ -0,0 +1,23 @@
+require 'copyscape/response'
+require 'copyscape/url_search'
+require 'copyscape/text_search'
+require 'copyscape/balance'
+require 'copyscape/version'
+
+module Copyscape
+  class << self
+    attr_accessor :username, :api_key
+
+    def url_search(*args)
+      UrlSearch.new(*args)
+    end
+
+    def text_search(*args)
+      TextSearch.new(*args)
+    end
+
+    def balance(*args)
+      Balance.new(*args)
+    end
+  end
+end

data/lib/copyscape/balance.rb

@@ -0,0 +1,15 @@
+require 'copyscape/request_base'
+
+module Copyscape
+  class Balance < RequestBase
+    def initialize(format = :xml, options = {})
+      options = {
+        f: format.to_s,
+        o: 'balance'
+      }.merge(options)
+
+      http_response = get_response(options)
+      @response = Response.new(http_response)
+    end
+  end
+end

data/lib/copyscape/request_base.rb

@@ -0,0 +1,50 @@
+require 'forwardable'
+require 'httparty'
+
+module Copyscape
+  class RequestBase
+    include HTTParty
+    extend Forwardable
+
+    base_uri 'http://www.copyscape.com/api'
+
+    def_delegators :response, :duplicate_count, :duplicates, :duplicate?,
+                   :count, :error, :error?, :query, :query_words, :raw_response,
+                   :allwordsmatched, :allpercentmatched, :alltextmatched, :allviewurl
+
+    # API operation (o): Use csearch to search against the public Internet or psearch to search against your private index.
+    # You can also use cpsearch to search against both the Internet and your private index, for the cost of two search credits.
+    # Text encoding (e): Use an IANA name, such as UTF-8 (Unicode), ISO-8859-1 (Latin-1) or WINDOWS-1251 (Cyrillic).
+    # Text to be searched (t): If you are using the Raw POST method, as described above, the raw text should be supplied
+    # in the POST payload without a parameter name and without any urlencoding.
+    # Full comparisons (c): Set to a value between 1 and 10 to request a full text-on-text comparison
+    # (with an exact count of matching words) between the query text and the top (one to ten) results found.
+    # Note that full comparisons may add a delay of a few seconds.
+    # Response format (f): If omitted or set to xml, the API will respond in XML.
+    # If set to html, the API will respond in basic HTML.
+    # Example test (x): If set to 1, the API will search the Internet for copies of the text on this page and
+    # you will not be charged.
+    #
+    def base_params
+      raise 'You must set Copyscape.username' unless Copyscape.username
+      raise 'You must set Copyscape.api_key' unless Copyscape.api_key
+      {
+        u: Copyscape.username,
+        k: Copyscape.api_key
+      }
+    end
+
+    def response
+      raise '@response must be set' unless @response
+      @response
+    end
+
+    def get_response(params)
+      self.class.get('/', query: base_params.merge(params)).body
+    end
+
+    def post_response(params)
+      self.class.post('/', body: base_params.merge(params)).body
+    end
+  end
+end

data/lib/copyscape/response.rb

@@ -0,0 +1,103 @@
+# More info here http://www.copyscape.com/api-guide.php
+#
+require 'nokogiri'
+
+module Copyscape
+  class Response
+    attr_reader :raw_response
+
+    def initialize(buffer)
+      @raw_response = buffer
+      @document = Nokogiri(buffer)
+    end
+
+    # URL searched
+    # Presert: if a URL search
+    # The <query> value may differ from the original URL you supplied if there was a frameset or redirection.
+    #
+    def query
+      field('query')
+    end
+
+    # Number of words checked
+    def query_words
+      (field('querywords') || 0).to_i
+    end
+
+    # Returns the number of duplicates
+    def count
+      (field('count') || 0).to_i
+    end
+
+    # Returns true if the response was an error
+    def error?
+      !!error
+    end
+
+    # Reason for API request failure
+    # Present: if request failed
+    #
+    def error
+      field('error')
+    end
+
+    # Number of source words matched
+    # Present: if succeeded and c>=3 and o is not cpsearch
+    #
+    def allwordsmatched
+      (field('allwordsmatched') || 0).to_i
+    end
+
+    # Percentage of source words matched
+    # Present: if succeeded and c>=3 and o is not cpsearch
+    #
+    def allpercentmatched
+      (field('allpercentmatched') || 0).to_i
+    end
+
+    # Full extract of source text matched
+    # Present: if succeeded and c>=3 and o is not cpsearch
+    #
+    def alltextmatched
+      field('alltextmatched')
+    end
+
+    # URL for viewing found results
+    # Present: if succeeded and o is csearch
+    # The <allviewurl> value can be used to display the list of results in an iframe or window.
+    # If used, the contents of this page must be displayed in full, without modification.
+    #
+    def allviewurl
+      field('allviewurl')
+    end
+
+    # Returns true if there are one or more duplicates
+    def duplicate?
+      count > 0
+    end
+
+    # Returns an array of all the results in the form of a hash:
+    def duplicates
+      @duplicates ||= [].tap do |r|
+        @document.search('result').collect do |result|
+          r << result_to_hash(result)
+        end
+      end
+    end
+
+    private
+
+    # Given a result xml element, return a hash of the values we're interested in.
+    def result_to_hash(result)
+      result.children.inject({}) do |hash, node|
+        hash[node.name] = (node.text =~ /^\d+$/ ? node.text.to_i : node.text)
+        hash
+      end
+    end
+
+    def field(name)
+      node = @document.search(name).first
+      node.text if node
+    end
+  end
+end

data/lib/copyscape/text_search.rb

@@ -0,0 +1,29 @@
+require 'copyscape/request_base'
+
+module Copyscape
+  class TextSearch < RequestBase
+    # The parameters are as follows:
+    # Parameter Explanation         Value                    Required? Default
+    # u         Your username       [your username]          Yes       -
+    # k         Your API key        [your API key]           Yes       -
+    # o         API operation       csearch (or psearch or
+    #  cpsearch if you create a private index)               Yes       -
+    # e         Text encoding       [encoding name]          Yes       -
+    # t         Text to be searched [the text]               Yes       -
+    # c         Full comparisons    0 to 10                  No        0
+    # f         Response format     xml or html              No        xml
+    # x         Example test        1 or omitted             No        -
+    #
+    def initialize(text, encoding = 'UTF-8', options = {})
+      options = {
+        t: text,
+        e: encoding,
+        o: 'csearch',
+        f: 'xml'
+      }.merge(options)
+
+      http_response = post_response(options)
+      @response = Response.new(http_response)
+    end
+  end
+end

data/lib/copyscape/url_search.rb

@@ -0,0 +1,28 @@
+require 'copyscape/request_base'
+
+module Copyscape
+  class UrlSearch < RequestBase
+    # The parameters are as follows:
+    # Parameter Explanation         Value                    Required? Default
+    # u         Your username       [your username]          Yes       -
+    # k         Your API key        [your API key]           Yes       -
+    # o         API operation       csearch (or psearch or
+    #  cpsearch if you create a private index)               Yes       -
+    # e         Text encoding       [encoding name]          Yes       -
+    # t         Text to be searched [the text]               Yes       -
+    # c         Full comparisons    0 to 10                  No        0
+    # f         Response format     xml or html              No        xml
+    # x         Example test        1 or omitted             No        -
+    #
+    def initialize(url, options = {})
+      options = {
+        q: url,
+        o: 'csearch',
+        f: 'xml'
+      }.merge(options)
+
+      http_response = get_response(options)
+      @response = Response.new(http_response)
+    end
+  end
+end

data/lib/copyscape/version.rb

@@ -0,0 +1,3 @@
+module Copyscape
+  VERSION = '0.1.0'.freeze
+end

data/test/balance.html

@@ -0,0 +1 @@
+<html><head><title>Copyscape Premium balance for joe</title></head><body><B>$9.25</B> remaining, <B>185</B> searches remaining, <B>185</B> available today.</body></html>

data/test/balance.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="utf-8"?>
+<remaining>
+	<value>9.25</value>
+	<total>185</total>
+	<today>185</today>
+</remaining>

data/test/balance_test.rb

@@ -0,0 +1,37 @@
+require File.dirname(__FILE__) + '/test_helper'
+
+class BalanceTest < Test::Unit::TestCase
+  context "request balance in xml" do
+    setup do
+      Copyscape::Balance.expects(:get).once.returns(balance_response_duplicate(:xml))
+      @balance = Copyscape::Balance.new(:xml)
+    end
+
+    should "have the correct url" do
+      assert_match raw_response_duplicate(:xml), @balance.raw_response
+    end
+  end
+
+  context "request balance in html" do
+    setup do
+      Copyscape::Balance.expects(:get).once.returns(balance_response_duplicate(:html))
+      @balance = Copyscape::Balance.new(:html)
+    end
+
+    should "have the correct url" do
+      assert_match raw_response_duplicate(:html), @balance.raw_response
+    end
+  end
+
+  private
+
+  def balance_response_duplicate(format)
+    o = Object.new
+    o.stubs(:body).returns(File.read(File.expand_path("../balance.#{format.to_s}", __FILE__)))
+    o
+  end
+
+  def raw_response_duplicate(format)
+    balance_response_duplicate(format).body
+  end
+end

data/test/error_response.xml

@@ -0,0 +1,5 @@
+<?xml version="1.0" encoding="utf-8"?>
+<response>
+  <error>connection failed (2) - please ensure you entered the URL correctly</error>
+  <query>http://www.somethingthatdoesntexist.com/</query>
+</response>

data/test/response_test.rb

@@ -0,0 +1,98 @@
+require File.dirname(__FILE__) + '/test_helper'
+require 'copyscape/response'
+
+class ResponseTest < Test::Unit::TestCase
+  context "response" do
+    setup do
+      @response = Copyscape::Response.new(url_search_response_duplicate)
+    end
+
+    should "include query" do
+      assert_equal "http://www.copyscape.com/example.html", @response.query
+    end
+
+    should "include query words" do
+      assert_equal 1340, @response.query_words
+    end
+
+    should "not be an error" do
+      assert !@response.error?
+    end
+  end
+
+  context "duplicate" do
+    setup do
+      @response = Copyscape::Response.new(url_search_response_duplicate)
+    end
+
+    should "include count" do
+      assert_equal 81, @response.count
+    end
+
+    should "be a duplicate" do
+      assert @response.duplicate?
+    end
+
+    should "include duplicates" do
+      dup = @response.duplicates.first
+      assert_equal 'http://www.archives.gov/exhibits/charters/declaration_transcript.html', dup['url']
+      assert_equal "Declaration of Independence - Transcript", dup['title']
+      assert_equal "... We hold these truths to be self-evident, that all men are created equal, that   they are endowed by ... But when a long train of abuses and usurpations, pursuing invariably the same ... to pass Laws of immediate and pressing importance, unless suspended in their ... for opposing with manly firmness his invasions on the   rights of the people. ... English Laws in a neighbouring Province, establishing therein an Arbitrary   government, ... He has plundered our seas, ravaged our Coasts, burnt our towns, ... of Cruelty & perfidy scarcely paralleled in the most barbarous ages, ... He has constrained our fellow Citizens taken Captive on the high Seas to   bear ... the merciless Indian Savages, whose known rule of warfare, ... which, would inevitably interrupt our connections and correspondence. ... on   the protection of divine Providence, we mutually pledge to each other our ... ",
+        dup['textsnippet']
+      assert_equal "<font color=\"#777777\">... </font><font color=\"#000000\">We hold these truths to be self-evident, that all men are created equal, that   they are endowed by ... </font><font color=\"#777777\"></font><font color=\"#000000\">But when a long train of abuses and usurpations, pursuing invariably the same ... </font><font color=\"#777777\"></font><font color=\"#000000\">to pass Laws of immediate and pressing importance, unless suspended in their ... </font><font color=\"#777777\"></font><font color=\"#000000\">for opposing with manly firmness his invasions on the   rights of the people. ... </font><font color=\"#777777\"></font><font color=\"#000000\">English Laws in a neighbouring Province, establishing therein an Arbitrary   government, ... </font><font color=\"#777777\"></font><font color=\"#000000\">He has plundered our seas, ravaged our Coasts, burnt our towns, ... </font><font color=\"#777777\"></font><font color=\"#000000\">of Cruelty &amp; perfidy scarcely paralleled in the most barbarous ages, ... </font><font color=\"#777777\"></font><font color=\"#000000\">He has constrained our fellow Citizens taken Captive on the high Seas to   bear ... </font><font color=\"#777777\"></font><font color=\"#000000\">the merciless Indian Savages, whose known rule of warfare, ... </font><font color=\"#777777\"></font><font color=\"#000000\">which, would inevitably interrupt our connections and correspondence. ... </font><font color=\"#777777\"></font><font color=\"#000000\">on   the protection of divine Providence, we mutually pledge to each other our ... </font>",
+        dup['htmlsnippet']
+      assert_equal 134, dup['minwordsmatched']
+    end
+
+    should "have the right amount of duplicates" do
+      assert_equal @response.count, @response.duplicates.length
+    end
+
+  end
+
+  context "not duplicate" do
+    setup do
+      @response = Copyscape::Response.new(url_search_response_not_duplicate)
+    end
+
+    should "include count" do
+      assert_equal 0, @response.count
+    end
+
+    should "be a duplicate" do
+      assert !@response.duplicate?
+    end
+
+    should "include duplicates" do
+      assert @response.duplicates.empty?
+    end
+  end
+
+  context "error" do
+    setup do
+      @response = Copyscape::Response.new(error_response)
+    end
+
+    should "be an error" do
+      assert @response.error?
+    end
+
+    should "return error message" do
+      assert_equal "connection failed (2) - please ensure you entered the URL correctly", @response.error
+    end
+  end
+
+  private
+
+  def url_search_response_duplicate
+    File.read(File.expand_path('../url_search_response_duplicate.xml', __FILE__))
+  end
+
+  def url_search_response_not_duplicate
+    File.read(File.expand_path('../url_search_response_not_duplicate.xml', __FILE__))
+  end
+
+  def error_response
+    File.read(File.expand_path('../error_response.xml', __FILE__))
+  end
+end