iudex-worker 1.1.0-java → 1.2.b.0-java
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/History.rdoc +5 -0
- data/README.rdoc +1 -1
- data/Rakefile +2 -39
- data/bin/iudex-worker-fg +1 -1
- data/init/iudex-worker +2 -2
- data/lib/iudex-worker/agent.rb +4 -4
- data/lib/iudex-worker/base.rb +2 -2
- data/lib/iudex-worker/fetch_helper.rb +1 -1
- data/lib/iudex-worker/filter_chain_factory.rb +1 -1
- data/lib/iudex-worker/prioritizer.rb +1 -1
- data/lib/iudex-worker.rb +1 -1
- data/test/setup.rb +22 -12
- data/test/test_agent.rb +1 -1
- data/test/test_filter_chain_factory.rb +1 -1
- data/test/test_prioritizer.rb +1 -1
- metadata +66 -70
- data/.gemtest +0 -0
data/History.rdoc
CHANGED
@@ -1,3 +1,8 @@
|
|
1
|
+
=== 1.2.b.0 (2012-3-4)
|
2
|
+
* Upgrade to tarpit ~> 2.0, bundler Gemfile, gemspec (dev)
|
3
|
+
* Fix agent http tests by checking deeper than package name loaded via
|
4
|
+
bundler/gemspecs
|
5
|
+
|
1
6
|
=== 1.1.0 (2011-11-13)
|
2
7
|
* Update to iudex-core, -da, -rome, -html, -simhash ~> 1.1.0
|
3
8
|
* Changes for VisitManager, VisitCounter, RedirectHandler, Revisitor
|
data/README.rdoc
CHANGED
data/Rakefile
CHANGED
@@ -1,44 +1,7 @@
|
|
1
1
|
# -*- ruby -*-
|
2
2
|
|
3
|
-
$LOAD_PATH << './lib'
|
4
|
-
require 'iudex-worker/base'
|
5
|
-
|
6
3
|
require 'rubygems'
|
7
|
-
|
4
|
+
require 'bundler/setup'
|
8
5
|
require 'rjack-tarpit'
|
9
6
|
|
10
|
-
|
11
|
-
|
12
|
-
t.specify do |h|
|
13
|
-
h.developer( "David Kellum", "dek-oss@gravitext.com" )
|
14
|
-
|
15
|
-
h.extra_deps += [ [ 'iudex-core', '~> 1.1.0' ],
|
16
|
-
[ 'rjack-logback', '~> 1.0' ],
|
17
|
-
[ 'iudex-da', '~> 1.1.0' ],
|
18
|
-
[ 'iudex-rome', '~> 1.1.0' ],
|
19
|
-
[ 'iudex-html', '~> 1.1.0' ],
|
20
|
-
[ 'iudex-simhash', '~> 1.1.0' ],
|
21
|
-
[ 'iudex-char-detector', '~> 1.1.0' ] ]
|
22
|
-
|
23
|
-
h.testlib = :minitest
|
24
|
-
h.extra_dev_deps += [ [ 'minitest', '~> 2.3' ],
|
25
|
-
[ 'iudex-httpclient-3', '~> 1.1.0' ],
|
26
|
-
[ 'iudex-jetty-httpclient', '~> 1.1.0' ],
|
27
|
-
[ 'iudex-async-httpclient', '~> 1.1.0' ] ]
|
28
|
-
end
|
29
|
-
|
30
|
-
task :chk_hist_vers do
|
31
|
-
t.test_line_match( 'History.rdoc', /^==/, / #{t.version} / )
|
32
|
-
end
|
33
|
-
task :chk_init_v do
|
34
|
-
t.test_line_match( 'init/iudex-worker', /^gem.+#{t.name}/, /= #{t.version}/ )
|
35
|
-
end
|
36
|
-
task :chk_hist_date do
|
37
|
-
t.test_line_match( 'History.rdoc', /^==/, /\([0-9\-]+\)$/ )
|
38
|
-
end
|
39
|
-
|
40
|
-
task :gem => [ :chk_hist_vers, :chk_init_v ]
|
41
|
-
task :tag => [ :chk_hist_vers, :chk_init_v, :chk_hist_date ]
|
42
|
-
task :push => [ :chk_hist_date ]
|
43
|
-
|
44
|
-
t.define_tasks
|
7
|
+
RJack::TarPit.new( 'iudex-worker' ).define_tasks
|
data/bin/iudex-worker-fg
CHANGED
data/init/iudex-worker
CHANGED
@@ -7,7 +7,7 @@
|
|
7
7
|
#. hashdot.vm.options += -XX:+UseConcMarkSweepGC -XX:+CMSClassUnloadingEnabled
|
8
8
|
|
9
9
|
#--
|
10
|
-
# Copyright (c) 2008-
|
10
|
+
# Copyright (c) 2008-2012 David Kellum
|
11
11
|
#
|
12
12
|
# Licensed under the Apache License, Version 2.0 (the "License"); you
|
13
13
|
# may not use this file except in compliance with the License. You
|
@@ -24,7 +24,7 @@
|
|
24
24
|
|
25
25
|
require 'rubygems'
|
26
26
|
|
27
|
-
gem( "iudex-worker", "= 1.
|
27
|
+
gem( "iudex-worker", "= 1.2.b.0" )
|
28
28
|
|
29
29
|
module IudexInitScript
|
30
30
|
|
data/lib/iudex-worker/agent.rb
CHANGED
@@ -1,5 +1,5 @@
|
|
1
1
|
#--
|
2
|
-
# Copyright (c) 2008-
|
2
|
+
# Copyright (c) 2008-2012 David Kellum
|
3
3
|
#
|
4
4
|
# Licensed under the Apache License, Version 2.0 (the "License"); you
|
5
5
|
# may not use this file except in compliance with the License. You
|
@@ -49,17 +49,17 @@ module Iudex
|
|
49
49
|
end
|
50
50
|
|
51
51
|
def http_client( executor )
|
52
|
-
if defined?( JettyHTTPClient )
|
52
|
+
if defined?( JettyHTTPClient.create_client )
|
53
53
|
@log.info "Setting up JettyHTTPClient"
|
54
54
|
JettyHTTPClient.create_client.tap do |c|
|
55
55
|
c.executor = executor
|
56
56
|
c.start
|
57
57
|
end
|
58
|
-
elsif defined?( AsyncHTTPClient )
|
58
|
+
elsif defined?( AsyncHTTPClient.create_client )
|
59
59
|
@log.info "Setting up AsyncHTTPClient"
|
60
60
|
AsyncHTTPClient.create_client( :executor_service => executor )
|
61
61
|
else
|
62
|
-
gem 'iudex-httpclient-3', '~> 1.
|
62
|
+
gem 'iudex-httpclient-3', '~> 1.2.b'
|
63
63
|
require 'iudex-httpclient-3'
|
64
64
|
@log.info "Setting up HTTPClient3"
|
65
65
|
@http_manager = HTTPClient3.create_manager
|
data/lib/iudex-worker/base.rb
CHANGED
@@ -1,5 +1,5 @@
|
|
1
1
|
#--
|
2
|
-
# Copyright (c) 2008-
|
2
|
+
# Copyright (c) 2008-2012 David Kellum
|
3
3
|
#
|
4
4
|
# Licensed under the Apache License, Version 2.0 (the "License"); you
|
5
5
|
# may not use this file except in compliance with the License. You
|
@@ -16,6 +16,6 @@
|
|
16
16
|
|
17
17
|
module Iudex
|
18
18
|
module Worker
|
19
|
-
VERSION = '1.
|
19
|
+
VERSION = '1.2.b.0'
|
20
20
|
end
|
21
21
|
end
|
data/lib/iudex-worker.rb
CHANGED
data/test/setup.rb
CHANGED
@@ -1,5 +1,5 @@
|
|
1
1
|
#--
|
2
|
-
# Copyright (c) 2008-
|
2
|
+
# Copyright (c) 2008-2012 David Kellum
|
3
3
|
#
|
4
4
|
# Licensed under the Apache License, Version 2.0 (the "License"); you
|
5
5
|
# may not use this file except in compliance with the License. You
|
@@ -14,21 +14,31 @@
|
|
14
14
|
# permissions and limitations under the License.
|
15
15
|
#++
|
16
16
|
|
17
|
-
#### General test setup
|
18
|
-
|
19
|
-
ldir = File.join( File.dirname( __FILE__ ), "..", "lib" )
|
20
|
-
$LOAD_PATH.unshift( ldir ) unless $LOAD_PATH.include?( ldir )
|
17
|
+
#### General test setup, logging, console output ####
|
21
18
|
|
22
19
|
require 'rubygems'
|
23
|
-
require '
|
24
|
-
RJack::Logback.config_console( :stderr => true, :mdc => "uhash" )
|
20
|
+
require 'bundler/setup'
|
25
21
|
|
26
22
|
require 'minitest/unit'
|
27
23
|
require 'minitest/autorun'
|
28
24
|
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
|
25
|
+
require 'rjack-logback'
|
26
|
+
|
27
|
+
module TestSetup
|
28
|
+
include RJack
|
29
|
+
Logback.config_console( :stderr => true, :thread => true )
|
30
|
+
|
31
|
+
if ( ARGV & %w[ -v --verbose --debug ] ).empty?
|
32
|
+
# Make test output logging compatible: no partial lines.
|
33
|
+
class TestOut
|
34
|
+
def print( *a ); $stdout.puts( *a ); end
|
35
|
+
def puts( *a ); $stdout.puts( *a ); end
|
36
|
+
end
|
37
|
+
MiniTest::Unit.output = TestOut.new
|
38
|
+
else
|
39
|
+
Logback.root.level = Logback::DEBUG
|
40
|
+
end
|
41
|
+
|
42
|
+
ARGV.delete( '--debug' )
|
43
|
+
|
33
44
|
end
|
34
|
-
MiniTest::Unit.output = TestOut.new
|
data/test/test_agent.rb
CHANGED
@@ -2,7 +2,7 @@
|
|
2
2
|
#.hashdot.profile += jruby-shortlived
|
3
3
|
|
4
4
|
#--
|
5
|
-
# Copyright (c) 2008-
|
5
|
+
# Copyright (c) 2008-2012 David Kellum
|
6
6
|
#
|
7
7
|
# Licensed under the Apache License, Version 2.0 (the "License"); you
|
8
8
|
# may not use this file except in compliance with the License. You
|
@@ -2,7 +2,7 @@
|
|
2
2
|
#.hashdot.profile += jruby-shortlived
|
3
3
|
|
4
4
|
#--
|
5
|
-
# Copyright (c) 2008-
|
5
|
+
# Copyright (c) 2008-2012 David Kellum
|
6
6
|
#
|
7
7
|
# Licensed under the Apache License, Version 2.0 (the "License"); you
|
8
8
|
# may not use this file except in compliance with the License. You
|
data/test/test_prioritizer.rb
CHANGED
@@ -2,7 +2,7 @@
|
|
2
2
|
#.hashdot.profile += jruby-shortlived
|
3
3
|
|
4
4
|
#--
|
5
|
-
# Copyright (c) 2008-
|
5
|
+
# Copyright (c) 2008-2012 David Kellum
|
6
6
|
#
|
7
7
|
# Licensed under the Apache License, Version 2.0 (the "License"); you
|
8
8
|
# may not use this file except in compliance with the License. You
|
metadata
CHANGED
@@ -1,8 +1,8 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: iudex-worker
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
prerelease:
|
5
|
-
version: 1.
|
4
|
+
prerelease: 4
|
5
|
+
version: 1.2.b.0
|
6
6
|
platform: java
|
7
7
|
authors:
|
8
8
|
- David Kellum
|
@@ -10,144 +10,141 @@ autorequire:
|
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
12
|
|
13
|
-
date:
|
13
|
+
date: 2012-03-05 00:00:00 Z
|
14
14
|
dependencies:
|
15
15
|
- !ruby/object:Gem::Dependency
|
16
16
|
name: iudex-core
|
17
|
-
|
18
|
-
requirement: &id001 !ruby/object:Gem::Requirement
|
17
|
+
version_requirements: &id001 !ruby/object:Gem::Requirement
|
19
18
|
none: false
|
20
19
|
requirements:
|
21
20
|
- - ~>
|
22
21
|
- !ruby/object:Gem::Version
|
23
|
-
version: 1.
|
24
|
-
|
25
|
-
version_requirements: *id001
|
26
|
-
- !ruby/object:Gem::Dependency
|
27
|
-
name: rjack-logback
|
22
|
+
version: 1.2.b
|
23
|
+
requirement: *id001
|
28
24
|
prerelease: false
|
29
|
-
requirement: &id002 !ruby/object:Gem::Requirement
|
30
|
-
none: false
|
31
|
-
requirements:
|
32
|
-
- - ~>
|
33
|
-
- !ruby/object:Gem::Version
|
34
|
-
version: "1.0"
|
35
25
|
type: :runtime
|
36
|
-
version_requirements: *id002
|
37
26
|
- !ruby/object:Gem::Dependency
|
38
27
|
name: iudex-da
|
39
|
-
|
40
|
-
requirement: &id003 !ruby/object:Gem::Requirement
|
28
|
+
version_requirements: &id002 !ruby/object:Gem::Requirement
|
41
29
|
none: false
|
42
30
|
requirements:
|
43
31
|
- - ~>
|
44
32
|
- !ruby/object:Gem::Version
|
45
|
-
version: 1.
|
33
|
+
version: 1.2.b
|
34
|
+
requirement: *id002
|
35
|
+
prerelease: false
|
46
36
|
type: :runtime
|
47
|
-
version_requirements: *id003
|
48
37
|
- !ruby/object:Gem::Dependency
|
49
38
|
name: iudex-rome
|
50
|
-
|
51
|
-
requirement: &id004 !ruby/object:Gem::Requirement
|
39
|
+
version_requirements: &id003 !ruby/object:Gem::Requirement
|
52
40
|
none: false
|
53
41
|
requirements:
|
54
42
|
- - ~>
|
55
43
|
- !ruby/object:Gem::Version
|
56
|
-
version: 1.
|
44
|
+
version: 1.2.b
|
45
|
+
requirement: *id003
|
46
|
+
prerelease: false
|
57
47
|
type: :runtime
|
58
|
-
version_requirements: *id004
|
59
48
|
- !ruby/object:Gem::Dependency
|
60
49
|
name: iudex-html
|
61
|
-
|
62
|
-
requirement: &id005 !ruby/object:Gem::Requirement
|
50
|
+
version_requirements: &id004 !ruby/object:Gem::Requirement
|
63
51
|
none: false
|
64
52
|
requirements:
|
65
53
|
- - ~>
|
66
54
|
- !ruby/object:Gem::Version
|
67
|
-
version: 1.
|
55
|
+
version: 1.2.b
|
56
|
+
requirement: *id004
|
57
|
+
prerelease: false
|
68
58
|
type: :runtime
|
69
|
-
version_requirements: *id005
|
70
59
|
- !ruby/object:Gem::Dependency
|
71
60
|
name: iudex-simhash
|
72
|
-
|
73
|
-
requirement: &id006 !ruby/object:Gem::Requirement
|
61
|
+
version_requirements: &id005 !ruby/object:Gem::Requirement
|
74
62
|
none: false
|
75
63
|
requirements:
|
76
64
|
- - ~>
|
77
65
|
- !ruby/object:Gem::Version
|
78
|
-
version: 1.
|
66
|
+
version: 1.2.b
|
67
|
+
requirement: *id005
|
68
|
+
prerelease: false
|
79
69
|
type: :runtime
|
80
|
-
version_requirements: *id006
|
81
70
|
- !ruby/object:Gem::Dependency
|
82
71
|
name: iudex-char-detector
|
72
|
+
version_requirements: &id006 !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ~>
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: 1.2.b
|
78
|
+
requirement: *id006
|
83
79
|
prerelease: false
|
84
|
-
|
80
|
+
type: :runtime
|
81
|
+
- !ruby/object:Gem::Dependency
|
82
|
+
name: rjack-logback
|
83
|
+
version_requirements: &id007 !ruby/object:Gem::Requirement
|
85
84
|
none: false
|
86
85
|
requirements:
|
87
86
|
- - ~>
|
88
87
|
- !ruby/object:Gem::Version
|
89
|
-
version: 1.
|
88
|
+
version: "1.0"
|
89
|
+
requirement: *id007
|
90
|
+
prerelease: false
|
90
91
|
type: :runtime
|
91
|
-
version_requirements: *id007
|
92
92
|
- !ruby/object:Gem::Dependency
|
93
93
|
name: minitest
|
94
|
-
|
95
|
-
requirement: &id008 !ruby/object:Gem::Requirement
|
94
|
+
version_requirements: &id008 !ruby/object:Gem::Requirement
|
96
95
|
none: false
|
97
96
|
requirements:
|
98
97
|
- - ~>
|
99
98
|
- !ruby/object:Gem::Version
|
100
99
|
version: "2.3"
|
100
|
+
requirement: *id008
|
101
|
+
prerelease: false
|
101
102
|
type: :development
|
102
|
-
version_requirements: *id008
|
103
103
|
- !ruby/object:Gem::Dependency
|
104
104
|
name: iudex-httpclient-3
|
105
|
-
|
106
|
-
requirement: &id009 !ruby/object:Gem::Requirement
|
105
|
+
version_requirements: &id009 !ruby/object:Gem::Requirement
|
107
106
|
none: false
|
108
107
|
requirements:
|
109
108
|
- - ~>
|
110
109
|
- !ruby/object:Gem::Version
|
111
|
-
version: 1.
|
110
|
+
version: 1.2.b
|
111
|
+
requirement: *id009
|
112
|
+
prerelease: false
|
112
113
|
type: :development
|
113
|
-
version_requirements: *id009
|
114
114
|
- !ruby/object:Gem::Dependency
|
115
115
|
name: iudex-jetty-httpclient
|
116
|
-
|
117
|
-
requirement: &id010 !ruby/object:Gem::Requirement
|
116
|
+
version_requirements: &id010 !ruby/object:Gem::Requirement
|
118
117
|
none: false
|
119
118
|
requirements:
|
120
119
|
- - ~>
|
121
120
|
- !ruby/object:Gem::Version
|
122
|
-
version: 1.
|
121
|
+
version: 1.2.b
|
122
|
+
requirement: *id010
|
123
|
+
prerelease: false
|
123
124
|
type: :development
|
124
|
-
version_requirements: *id010
|
125
125
|
- !ruby/object:Gem::Dependency
|
126
126
|
name: iudex-async-httpclient
|
127
|
-
|
128
|
-
requirement: &id011 !ruby/object:Gem::Requirement
|
127
|
+
version_requirements: &id011 !ruby/object:Gem::Requirement
|
129
128
|
none: false
|
130
129
|
requirements:
|
131
130
|
- - ~>
|
132
131
|
- !ruby/object:Gem::Version
|
133
|
-
version: 1.
|
132
|
+
version: 1.2.b
|
133
|
+
requirement: *id011
|
134
|
+
prerelease: false
|
134
135
|
type: :development
|
135
|
-
version_requirements: *id011
|
136
136
|
- !ruby/object:Gem::Dependency
|
137
137
|
name: rjack-tarpit
|
138
|
-
|
139
|
-
requirement: &id012 !ruby/object:Gem::Requirement
|
138
|
+
version_requirements: &id012 !ruby/object:Gem::Requirement
|
140
139
|
none: false
|
141
140
|
requirements:
|
142
141
|
- - ~>
|
143
142
|
- !ruby/object:Gem::Version
|
144
|
-
version:
|
143
|
+
version: "2.0"
|
144
|
+
requirement: *id012
|
145
|
+
prerelease: false
|
145
146
|
type: :development
|
146
|
-
|
147
|
-
description: |-
|
148
|
-
Iudex is a general purpose web crawler and feed processor in
|
149
|
-
ruby/java. The iudex-worker gem provides a worker deamon for feed/page
|
150
|
-
processing.
|
147
|
+
description: Iudex is a general purpose web crawler and feed processor in ruby/java. The iudex-worker gem provides a worker deamon for feed/page processing.
|
151
148
|
email:
|
152
149
|
- dek-oss@gravitext.com
|
153
150
|
executables:
|
@@ -155,7 +152,6 @@ executables:
|
|
155
152
|
extensions: []
|
156
153
|
|
157
154
|
extra_rdoc_files:
|
158
|
-
- Manifest.txt
|
159
155
|
- History.rdoc
|
160
156
|
- README.rdoc
|
161
157
|
files:
|
@@ -178,7 +174,6 @@ files:
|
|
178
174
|
- test/test_agent.rb
|
179
175
|
- test/test_filter_chain_factory.rb
|
180
176
|
- test/test_prioritizer.rb
|
181
|
-
- .gemtest
|
182
177
|
homepage: http://github.com/dekellum/iudex
|
183
178
|
licenses: []
|
184
179
|
|
@@ -193,21 +188,22 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
193
188
|
requirements:
|
194
189
|
- - ">="
|
195
190
|
- !ruby/object:Gem::Version
|
191
|
+
hash: 2
|
192
|
+
segments:
|
193
|
+
- 0
|
196
194
|
version: "0"
|
197
195
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
198
196
|
none: false
|
199
197
|
requirements:
|
200
|
-
- - "
|
198
|
+
- - ">"
|
201
199
|
- !ruby/object:Gem::Version
|
202
|
-
version:
|
200
|
+
version: 1.3.1
|
203
201
|
requirements: []
|
204
202
|
|
205
|
-
rubyforge_project:
|
206
|
-
rubygems_version: 1.8.
|
203
|
+
rubyforge_project:
|
204
|
+
rubygems_version: 1.8.15
|
207
205
|
signing_key:
|
208
206
|
specification_version: 3
|
209
|
-
summary: Iudex is a general purpose web crawler and feed processor in ruby/java
|
210
|
-
test_files:
|
211
|
-
|
212
|
-
- test/test_filter_chain_factory.rb
|
213
|
-
- test/test_prioritizer.rb
|
207
|
+
summary: Iudex is a general purpose web crawler and feed processor in ruby/java.
|
208
|
+
test_files: []
|
209
|
+
|
data/.gemtest
DELETED
File without changes
|