common-crawl-index 0.0.1.alpha

data/.gitignore

@@ -0,0 +1,18 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+.rvmrc

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--format progress

data/Gemfile

@@ -0,0 +1,7 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in cc-url-index.gemspec
+gemspec
+
+gem 'aws-sdk'
+#gem 'open3'

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 Amit Ambardekar
+
+MIT License
+
+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 +1,29 @@
+# CommonCrawlIndex
+
+TODO: Write a gem description
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'common-crawl-index'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install common-crawl-index
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/common-crawl-index.gemspec

@@ -0,0 +1,21 @@
+# -*- encoding: utf-8 -*-
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'common-crawl-index/version'
+
+Gem::Specification.new do |gem|
+  gem.name          = "common-crawl-index"
+  gem.version       = CommonCrawlIndex::VERSION
+  gem.authors       = ["Amit Ambardekar"]
+  gem.email         = ["amitamb@gmail.com"]
+  gem.description   = %q{Access coomon crawl URL index}
+  gem.summary       = %q{Access coomon crawl URL index}
+  gem.homepage      = ""
+
+  gem.add_development_dependency "rspec"
+
+  gem.files         = `git ls-files`.split($/)
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.require_paths = ["lib"]
+end

data/lib/common-crawl-index.rb

@@ -0,0 +1,171 @@
+require "common-crawl-index/version"
+require 'aws-sdk'
+require 'open3'
+
+
+module CommonCrawlIndex
+  class Client
+    @@settings = {
+      :access_key_id => nil,
+      :secret_access_key => nil,
+      :cc_index_path => "s3://aws-publicdatasets/common-crawl/projects/url-index/url-index.1356128792"
+    }
+
+    def self.config(settings = {})
+      @@settings = @@settings.merge(settings)
+    end
+
+    HEADER_OFFSET = 8
+
+    def initialize(access_key_id=nil, secret_access_key=nil, cc_index_path = nil)
+      @s3=AWS::S3.new(
+        :access_key_id => access_key_id || @@settings[:access_key_id],
+        :secret_access_key => secret_access_key || @@settings[:secret_access_key]
+      )
+
+      @cc_index_path = cc_index_path || @@settings[:cc_index_path]
+
+      proto,unused,@bucket_name,*rest=@cc_index_path.chomp.split File::SEPARATOR
+      raise ArgumentError, "#{__FILE__}: Unknown S3 Protocol #{proto}" unless proto=~/^s3/
+      @object_name=File.join rest
+
+      @block_size, @index_block_count = read( (0..7) ).unpack("LL")
+    end
+
+    def find_by_prefix(url, exact_match = false, &proc_block)
+      next_block = 0
+      while next_block < @index_block_count
+        next_block = get_next_block_id(url, next_block)
+      end
+      get_matching_urls_from_data_blocks(next_block, url, exact_match, &proc_block)
+    end
+
+    def self.normalize_url(url, append_scheme = true)
+      url_to_find = url
+      norm_url_to_find = URI(url_to_find)
+      norm_url_to_find.host = norm_url_to_find.host.split(".").reverse.join(".")
+      norm_url = norm_url_to_find.to_s
+      norm_url = norm_url[norm_url.index("\/\/")+2..-1]
+      norm_url += ":" + norm_url_to_find.scheme if append_scheme
+      norm_url
+    end
+
+    def self.denormalize_url(normalized_url, has_scheme = true)
+      scheme = "http"
+      colon_index = 0
+      if has_scheme
+        colon_index = normalized_url.rindex(":")
+        scheme = normalized_url[colon_index+1..-1] if colon_index
+      end
+      url_with_scheme = scheme + "://" + normalized_url[0..colon_index-1]
+      uri = URI(url_with_scheme)
+      uri.host = uri.host.split(".").reverse.join(".")
+      uri.to_s
+    end
+
+    private
+
+    def s3_object
+      @s3_object ||= @s3.buckets[@bucket_name].objects[@object_name]
+    end
+
+    def get_matching_urls_from_data_blocks(start_block, url_to_find, exact_match, &proc_block)
+
+      norm_url = Client.normalize_url(url_to_find, false)
+      norm_url_length = norm_url.length
+
+      first_match_found = false
+
+      cur_block_index = start_block
+      cur_block = read_block(start_block)
+      cur_loc = 0
+
+      end_found = false
+      while(!end_found)
+        if cur_block[cur_loc..cur_loc] == "\x00" || cur_loc >= @block_size
+          # to next block
+          if !first_match_found || exact_match # don't search next block for exact match
+            return false
+          end
+          cur_block_index += 1
+          cur_block = read_block(cur_block_index)
+          cur_loc = 0
+        end
+        nil_loc = cur_block.index("\x00", cur_loc)
+        url = cur_block[cur_loc..nil_loc-1]
+        if url[0..norm_url_length-1] == norm_url
+          url_data = {}
+          url_data[:normalized_url] = url
+          url_data[:url] = Client.denormalize_url(url)
+          a,b,c,d,e = cur_block[nil_loc+1..nil_loc+32].unpack("QQLQL")
+          url_data[:arcSourceSegmentId] = a
+          url_data[:arcFileDate] = b
+          url_data[:arcFilePartition] = c
+          url_data[:arcFileOffset] = d
+          url_data[:compressedSize] = e
+          if exact_match
+            if url == Client.normalize_url(url_to_find, true)
+              proc_block.call(url_data)
+              break
+            end
+          else
+            first_match_found = true
+            break if proc_block.call(url_data) == false
+          end
+        else
+          if first_match_found
+            break
+          end
+        end
+        cur_loc = nil_loc + 32 + 1
+      end
+    end
+
+    def read(target_range)
+      s3_object.read( :range => target_range )
+    end
+
+    def read_block(block_id)
+      #puts "Reading block No: #{block_id}"
+      start = HEADER_OFFSET + @block_size * block_id
+      target_range = (start..start+@block_size-1)
+      cur_block = read(target_range)
+    end
+
+    # search within
+    def get_next_block_id(url_to_find, block_id)
+      norm_url = Client.normalize_url(url_to_find, false)
+      cur_block = read_block(block_id)
+
+      not_found = true
+      cur_loc = 4
+      last_block_num = nil
+
+      counter = 0
+
+      while not_found
+
+        counter += 1
+
+        # read from cur_loc
+        next_nil_loc = cur_block.index("\x00", cur_loc)
+
+        break if next_nil_loc == cur_loc + 1
+
+        cur_prefix = cur_block[cur_loc..next_nil_loc-1]
+        cur_block_num = cur_block[next_nil_loc+1..next_nil_loc+1+4].unpack("L")[0]
+
+        if cur_prefix >= norm_url
+          next_block = last_block_num || cur_block_num
+          return next_block
+        end
+
+        break if cur_loc >= @block_size
+
+        last_block_num = cur_block_num
+        cur_loc = next_nil_loc + 1 + 4
+      end
+
+    end
+  end
+end

data/lib/common-crawl-index/version.rb

@@ -0,0 +1,3 @@
+module CommonCrawlIndex
+  VERSION = "0.0.1.alpha"
+end

data/spec/basic_spec.rb

@@ -0,0 +1,71 @@
+require 'spec_helper'
+describe CommonCrawlIndex do
+
+  AMAZON_ACCESS_KEY_ID = ENV['AMAZON_ACCESS_KEY_ID']
+  AMAZON_SECRET_ACCESS_KEY = ENV['AMAZON_SECRET_ACCESS_KEY']
+
+  it "should config successfully" do
+    settings = {
+      :access_key_id => "access_key",
+      :secret_access_key => "secret_key",
+      :cc_index_path => "s3://aws-publicdatasets/common-crawl/projects/url-index/url-index.1356128792" # optional
+    }
+
+    CommonCrawlIndex::Client.config(settings)
+
+    final_settings = CommonCrawlIndex::Client.class_variable_get(:@@settings)
+
+    final_settings.should == settings
+  end
+
+  it "should initialize client" do
+    client = CommonCrawlIndex::Client.new(AMAZON_ACCESS_KEY_ID, AMAZON_SECRET_ACCESS_KEY)
+    client.should_not == nil
+  end
+
+  it "should find by prefix" do
+    client = CommonCrawlIndex::Client.new(AMAZON_ACCESS_KEY_ID, AMAZON_SECRET_ACCESS_KEY)
+
+    total_urls_to_test = 100
+
+    url = "http://www.amazon.com/"
+    normalized_url = CommonCrawlIndex::Client.normalize_url(url, false)
+    normalized_url_length = normalized_url.length
+
+    client.find_by_prefix(url) do |url_data|
+      total_urls_to_test -= 1
+      prefix = url_data[:normalized_url][0..normalized_url_length-1]
+      normalized_url.should eql prefix
+      false if total_urls_to_test == 0
+    end
+  end
+
+  it "should match an exact url" do
+    client = CommonCrawlIndex::Client.new(AMAZON_ACCESS_KEY_ID, AMAZON_SECRET_ACCESS_KEY)
+
+    client.find_by_prefix("http://www.google.com/", true) do |url_data|
+      expected_url_data = {:normalized_url=>"com.google.www/:http", :url=>"http://www.google.com/", :arcSourceSegmentId=>1346823846039, :arcFileDate=>1346870285062, :arcFilePartition=>14, :arcFileOffset=>38347629, :compressedSize=>6198}
+      url_data.should eql expected_url_data
+    end
+  end
+
+  it "should normalize the urls correctly" do
+    normalized_url =  CommonCrawlIndex::Client.normalize_url("http://www.google.com/test/path")
+    normalized_url.should == "com.google.www/test/path:http"
+  end
+
+  it "should normalize the urls correctly without scheme" do
+    normalized_url =  CommonCrawlIndex::Client.normalize_url("http://www.google.com/test/path", false)
+    normalized_url.should == "com.google.www/test/path"
+  end
+
+  it "should denormalize the urls correctly" do
+    url =  CommonCrawlIndex::Client.denormalize_url("com.google.www/test/path:http")
+    url.should == "http://www.google.com/test/path"
+  end
+
+  it "should denormalize the urls correctly without scheme" do
+    url =  CommonCrawlIndex::Client.denormalize_url("com.google.www/test/path", false)
+    url.should == "http://www.google.com/test/path"
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,22 @@
+require 'rubygems'
+require 'bundler/setup'
+
+require 'common-crawl-index' # and any other gems you need
+
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# Require this file using `require "spec_helper"` to ensure that it is only
+# loaded once.
+#
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+RSpec.configure do |config|
+  config.treat_symbols_as_metadata_keys_with_true_values = true
+  config.run_all_when_everything_filtered = true
+  config.filter_run :focus
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = 'random'
+end

metadata

@@ -0,0 +1,74 @@
+--- !ruby/object:Gem::Specification
+name: common-crawl-index
+version: !ruby/object:Gem::Version
+  version: 0.0.1.alpha
+  prerelease: 6
+platform: ruby
+authors:
+- Amit Ambardekar
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-01-23 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Access coomon crawl URL index
+email:
+- amitamb@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .rspec
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- common-crawl-index.gemspec
+- lib/common-crawl-index.rb
+- lib/common-crawl-index/version.rb
+- spec/basic_spec.rb
+- spec/spec_helper.rb
+homepage: ''
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>'
+    - !ruby/object:Gem::Version
+      version: 1.3.1
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.24
+signing_key: 
+specification_version: 3
+summary: Access coomon crawl URL index
+test_files:
+- spec/basic_spec.rb
+- spec/spec_helper.rb