polipus 0.3.2 → 0.3.3

Sign up to get free protection for your applications and to get access to all the features.
Files changed (47) hide show
  1. checksums.yaml +8 -8
  2. data/.rubocop_todo.yml +0 -4
  3. data/CHANGELOG.md +6 -0
  4. data/Rakefile +1 -0
  5. data/examples/basic.rb +1 -0
  6. data/examples/error_handling.rb +1 -0
  7. data/examples/incremental.rb +1 -0
  8. data/examples/robots_txt_handling.rb +1 -0
  9. data/examples/survival.rb +1 -0
  10. data/lib/polipus/http.rb +1 -0
  11. data/lib/polipus/page.rb +1 -0
  12. data/lib/polipus/plugin.rb +1 -0
  13. data/lib/polipus/plugins/cleaner.rb +2 -1
  14. data/lib/polipus/plugins/sample.rb +1 -0
  15. data/lib/polipus/plugins/sleeper.rb +1 -0
  16. data/lib/polipus/queue_overflow.rb +1 -0
  17. data/lib/polipus/queue_overflow/base.rb +1 -0
  18. data/lib/polipus/queue_overflow/dev_null_queue.rb +1 -0
  19. data/lib/polipus/queue_overflow/manager.rb +1 -0
  20. data/lib/polipus/queue_overflow/mongo_queue.rb +1 -0
  21. data/lib/polipus/queue_overflow/mongo_queue_capped.rb +1 -0
  22. data/lib/polipus/robotex.rb +1 -0
  23. data/lib/polipus/signal_handler.rb +1 -0
  24. data/lib/polipus/storage.rb +1 -0
  25. data/lib/polipus/storage/base.rb +1 -0
  26. data/lib/polipus/storage/dev_null.rb +1 -0
  27. data/lib/polipus/storage/memory_store.rb +1 -0
  28. data/lib/polipus/storage/mongo_store.rb +2 -1
  29. data/lib/polipus/storage/s3_store.rb +1 -0
  30. data/lib/polipus/url_tracker.rb +1 -0
  31. data/lib/polipus/url_tracker/bloomfilter.rb +1 -0
  32. data/lib/polipus/url_tracker/redis_set.rb +1 -0
  33. data/lib/polipus/version.rb +2 -1
  34. data/spec/clear.rb +1 -0
  35. data/spec/http_spec.rb +1 -0
  36. data/spec/page_spec.rb +1 -0
  37. data/spec/polipus_spec.rb +1 -0
  38. data/spec/queue_overflow_manager_spec.rb +1 -0
  39. data/spec/queue_overflow_spec.rb +1 -0
  40. data/spec/robotex_spec.rb +1 -0
  41. data/spec/signal_handler_spec.rb +1 -0
  42. data/spec/spec_helper.rb +1 -0
  43. data/spec/storage_memory_spec.rb +1 -0
  44. data/spec/storage_mongo_spec.rb +1 -0
  45. data/spec/storage_s3_spec.rb +1 -0
  46. data/spec/url_tracker_spec.rb +1 -0
  47. metadata +2 -2
checksums.yaml CHANGED
@@ -1,15 +1,15 @@
1
1
  ---
2
2
  !binary "U0hBMQ==":
3
3
  metadata.gz: !binary |-
4
- NmQ5ZTBhZThlMDNlZGEzNzQ4ZDU0MGQ3NzBkODY0YjZlOGZmZTFmOA==
4
+ MGZhM2Q1OWE5ZTkxZWE3Y2JhMDJkNzZkMWRjMWZjYjI4YmRhODJmYw==
5
5
  data.tar.gz: !binary |-
6
- NTc3NTI5YmMyYzk4MzNkNDFjZTY4N2JiNGE2MzI4ZTRiZDZmZjY4Yw==
6
+ ODg4NTk5ZjhjNDM0ZjBhN2M2OWJlOWQyOTE4OWFiZmY1ZmQxMTZiYQ==
7
7
  SHA512:
8
8
  metadata.gz: !binary |-
9
- ZjczYmUzNjdhOWY0NjYzMzNhZDE4NmMwMWI5YTVhZTg1NGY5ZGJjNWJkN2I5
10
- NDYwZjRiNDM1ZGZlYjFmZTAxNWNiNmQ0MGM5MzJmNDAzZTAxYWUyNTc3OTlh
11
- ZWFhMWZkZGI4MTlhZmQ3NmM3NmQwZTk0YmM1YWU4NDJkYzk4NGQ=
9
+ NTdmYWZhMmMzYTQxOWY5OTBlNGE1ZWQzNWYwMThjMjAwNzQ4NmU4MDY4OWRi
10
+ OWVkNzEwNmYwNTY3OGI4NmFkZGJiNzNhN2I3M2ZjMDUxNjAzMDAyZjEyYmZj
11
+ ZGFkODliNDc5ZTYzYWE2ODNiMzdkMWFjZGExYjgzNTQyNmM4MDc=
12
12
  data.tar.gz: !binary |-
13
- ZmI4YzFjMzNiNTYwNWFkZmNiY2VmZTcyY2I1YTI3ZWQ2NWI2MjYwYTJiNDY3
14
- YjhmZjE3MGJkNWUwNmZkMWNhMTExZTJhYmE4YTI4OThlNmRkYWZhODkxZTY1
15
- MWZiZjA0M2E2MjcwOGZiNDViZmUyNTg4YmFkNmVjM2Y4ZjIzZDU=
13
+ NGYzNDc2ODQ3OTBiMzE5N2M5YmM3ZDliN2IyYWRmNjBiZDI3ZTYyYjkxNjBk
14
+ MDFhZjA0NDE5YjFkYzdiZTQxMjg0ZGEwODA3Nzk0YWZiNDRmY2I1MmE2ZWI4
15
+ MjQxNTU4NjgwOTM1ZDdlYjM4Mjg0NjhjY2M2OGU5MDA1YjNjMjY=
data/.rubocop_todo.yml CHANGED
@@ -17,10 +17,6 @@ Style/CyclomaticComplexity:
17
17
  Style/Documentation:
18
18
  Enabled: false
19
19
 
20
- # Offense count: 38
21
- # Configuration parameters: EnforcedStyle, SupportedStyles.
22
- Style/Encoding:
23
- Enabled: false
24
20
 
25
21
  # Offense count: 2
26
22
  # Configuration parameters: EnforcedStyle, SupportedStyles.
data/CHANGELOG.md CHANGED
@@ -1,5 +1,11 @@
1
1
  # Changelog
2
2
 
3
+ ## 0.3.3 (2015-06-26)
4
+
5
+ [Compare changes in gem](https://github.com/taganaka/polipus/compare/0.3.2...0.3.3)
6
+
7
+ * BugFix: Better compatibility for mongo 2.6.x on index creation
8
+
3
9
  ## 0.3.2 (2015-06-17)
4
10
 
5
11
  [Compare changes in gem](https://github.com/taganaka/polipus/compare/0.3.1...0.3.2)
data/Rakefile CHANGED
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'bundler/gem_tasks'
2
3
  require 'rspec/core/rake_task'
3
4
 
data/examples/basic.rb CHANGED
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'polipus'
2
3
  require 'mongo'
3
4
  require 'polipus/plugins/cleaner'
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'polipus'
2
3
 
3
4
  Polipus.crawler('rubygems', 'http://rubygems.org/') do |crawler|
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'polipus'
2
3
  require 'mongo'
3
4
 
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'polipus'
2
3
 
3
4
  options = {
data/examples/survival.rb CHANGED
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'polipus'
2
3
 
3
4
  Polipus.crawler('rubygems', 'http://rubygems.org/') do |crawler|
data/lib/polipus/http.rb CHANGED
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'net/https'
2
3
  require 'polipus/page'
3
4
  require 'zlib'
data/lib/polipus/page.rb CHANGED
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'nokogiri'
2
3
  require 'json'
3
4
  require 'ostruct'
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  module Polipus
2
3
  module Plugin
3
4
  @@plugins = {}
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  module Polipus
2
3
  module Plugin
3
4
  class Cleaner
@@ -8,7 +9,7 @@ module Polipus
8
9
  def on_initialize(crawler)
9
10
  crawler.logger.info { 'Cleaner plugin loaded' }
10
11
  unless @reset
11
- crawler.logger.info { 'Cleaner plugin is disable, add :reset => true to the plugin if you really know what you are doing' }
12
+ crawler.logger.info { 'Cleaner plugin is disabled, add :reset => true to the plugin if you really know what you are doing' }
12
13
  return nil
13
14
  end
14
15
  crawler.logger.info { 'Cleaning all: url_tracker, storage, queue' }
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  module Polipus
2
3
  module Plugin
3
4
  class Sample
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  module Polipus
2
3
  module Plugin
3
4
  class Sleeper
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'polipus/queue_overflow/manager'
2
3
  module Polipus
3
4
  module QueueOverflow
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  module Polipus
2
3
  module QueueOverflow
3
4
  class Base
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'thread'
2
3
  module Polipus
3
4
  module QueueOverflow
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  module Polipus
2
3
  module QueueOverflow
3
4
  class Manager
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'thread'
2
3
  require 'mongo'
3
4
  module Polipus
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'polipus/queue_overflow/mongo_queue'
2
3
  module Polipus
3
4
  module QueueOverflow
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'open-uri'
2
3
  require 'uri'
3
4
  require 'timeout'
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'singleton'
2
3
  module Polipus
3
4
  class SignalHandler
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'polipus/storage/base'
2
3
  module Polipus
3
4
  module Storage
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'uri'
2
3
 
3
4
  module Polipus
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  module Polipus
2
3
  module Storage
3
4
  class DevNull < Base
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'thread'
2
3
  module Polipus
3
4
  module Storage
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'mongo'
2
3
  require 'zlib'
3
4
  require 'thread'
@@ -9,7 +10,7 @@ module Polipus
9
10
  @mongo = options[:mongo]
10
11
  @collection = options[:collection]
11
12
  @mongo.create_collection(@collection)
12
- @mongo[@collection].ensure_index(:uuid, unique: true, drop_dups: true, background: true)
13
+ @mongo[@collection].ensure_index(:uuid, unique: true, dropDups: true, background: true)
13
14
  @compress_body = options[:compress_body] ||= true
14
15
  @except = options[:except] ||= []
15
16
  @semaphore = Mutex.new
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'aws/s3'
2
3
  require 'zlib'
3
4
  require 'thread'
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  module Polipus
2
3
  module UrlTracker
3
4
  def self.bloomfilter(options = {})
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'redis-bloomfilter'
2
3
  module Polipus
3
4
  module UrlTracker
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  module Polipus
2
3
  module UrlTracker
3
4
  class RedisSet
@@ -1,4 +1,5 @@
1
+ # encoding: UTF-8
1
2
  module Polipus
2
- VERSION = '0.3.2'
3
+ VERSION = '0.3.3'
3
4
  HOMEPAGE = 'https://github.com/taganaka/polipus'
4
5
  end
data/spec/clear.rb CHANGED
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'yaml'
2
3
  Dir.glob('./cassettes/*.yml').each do|f|
3
4
  next unless f =~ /[a-f0-9]{32}/
data/spec/http_spec.rb CHANGED
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'spec_helper'
2
3
  require 'mongo'
3
4
  require 'polipus/http'
data/spec/page_spec.rb CHANGED
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'spec_helper'
2
3
  require 'polipus/page'
3
4
 
data/spec/polipus_spec.rb CHANGED
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'spec_helper'
2
3
 
3
4
  describe Polipus::PolipusCrawler do
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'spec_helper'
2
3
  require 'mongo'
3
4
  require 'polipus/queue_overflow'
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'spec_helper'
2
3
  require 'polipus/queue_overflow'
3
4
 
data/spec/robotex_spec.rb CHANGED
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'spec_helper'
2
3
  require 'polipus/robotex'
3
4
  describe Polipus::Robotex do
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'spec_helper'
2
3
 
3
4
  describe Polipus::SignalHandler do
data/spec/spec_helper.rb CHANGED
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  # This file was generated by the `rspec --init` command. Conventionally, all
2
3
  # specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
3
4
  # Require this file using `require "spec_helper"` to ensure that it is only
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'spec_helper'
2
3
  require 'mongo'
3
4
  require 'polipus/storage/memory_store'
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'spec_helper'
2
3
  require 'mongo'
3
4
  require 'polipus/storage/mongo_store'
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'spec_helper'
2
3
  require 'aws/s3'
3
4
  require 'polipus/storage/s3_store'
@@ -1,3 +1,4 @@
1
+ # encoding: UTF-8
1
2
  require 'spec_helper'
2
3
  require 'polipus/url_tracker'
3
4
 
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: polipus
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.3.2
4
+ version: 0.3.3
5
5
  platform: ruby
6
6
  authors:
7
7
  - Francesco Laurita
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2014-06-18 00:00:00.000000000 Z
11
+ date: 2014-06-27 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: redis-bloomfilter