iudex-core 1.0.0-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 +2 -0
- data/Manifest.txt +18 -0
- data/README.rdoc +25 -0
- data/Rakefile +61 -0
- data/bin/iudex-test-config +43 -0
- data/bin/iudex-url-norm +72 -0
- data/build/TLDSets.java.erb +50 -0
- data/build/effective_tld_name.dat +4786 -0
- data/build/tld_set_generator.rb +96 -0
- data/config/config.rb +12 -0
- data/lib/iudex-core.rb +49 -0
- data/lib/iudex-core/base.rb +23 -0
- data/lib/iudex-core/config.rb +51 -0
- data/lib/iudex-core/iudex-core-1.0.0.jar +0 -0
- data/pom.xml +74 -0
- data/test/setup.rb +40 -0
- data/test/test_content_fetcher.rb +200 -0
- data/test/test_log_writer.rb +39 -0
- metadata +183 -0
@@ -0,0 +1,39 @@
|
|
1
|
+
#!/usr/bin/env jruby
|
2
|
+
#.hashdot.profile += jruby-shortlived
|
3
|
+
|
4
|
+
#--
|
5
|
+
# Copyright (c) 2008-2011 David Kellum
|
6
|
+
#
|
7
|
+
# Licensed under the Apache License, Version 2.0 (the "License"); you
|
8
|
+
# may not use this file except in compliance with the License. You
|
9
|
+
# may obtain a copy of the License at
|
10
|
+
#
|
11
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
12
|
+
#
|
13
|
+
# Unless required by applicable law or agreed to in writing, software
|
14
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
15
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
16
|
+
# implied. See the License for the specific language governing
|
17
|
+
# permissions and limitations under the License.
|
18
|
+
#++
|
19
|
+
|
20
|
+
require File.join( File.dirname( __FILE__ ), "setup" )
|
21
|
+
require 'iudex-core'
|
22
|
+
|
23
|
+
class TestLogWriter < MiniTest::Unit::TestCase
|
24
|
+
import 'java.io.PrintWriter'
|
25
|
+
import 'iudex.util.LogWriter'
|
26
|
+
import 'java.util.regex.Pattern'
|
27
|
+
|
28
|
+
def test_log_writer
|
29
|
+
lw = LogWriter.new( 'TestLogWriter' )
|
30
|
+
lw.remove_pattern = Pattern.compile( '(^test)|(\s+$)' )
|
31
|
+
pw = PrintWriter.new( lw, true )
|
32
|
+
pw.print( "test 1 \n\r" )
|
33
|
+
pw.println( "test 2 \n\r" )
|
34
|
+
pw.print( "test 3" )
|
35
|
+
|
36
|
+
#FIXME: Assert?
|
37
|
+
end
|
38
|
+
|
39
|
+
end
|
metadata
ADDED
@@ -0,0 +1,183 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: iudex-core
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
prerelease:
|
5
|
+
version: 1.0.0
|
6
|
+
platform: java
|
7
|
+
authors:
|
8
|
+
- David Kellum
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
|
13
|
+
date: 2011-04-04 00:00:00 -07:00
|
14
|
+
default_executable:
|
15
|
+
dependencies:
|
16
|
+
- !ruby/object:Gem::Dependency
|
17
|
+
name: rjack-slf4j
|
18
|
+
prerelease: false
|
19
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
20
|
+
none: false
|
21
|
+
requirements:
|
22
|
+
- - ~>
|
23
|
+
- !ruby/object:Gem::Version
|
24
|
+
version: 1.6.1
|
25
|
+
type: :runtime
|
26
|
+
version_requirements: *id001
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: hooker
|
29
|
+
prerelease: false
|
30
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
31
|
+
none: false
|
32
|
+
requirements:
|
33
|
+
- - ~>
|
34
|
+
- !ruby/object:Gem::Version
|
35
|
+
version: 1.0.0
|
36
|
+
type: :runtime
|
37
|
+
version_requirements: *id002
|
38
|
+
- !ruby/object:Gem::Dependency
|
39
|
+
name: gravitext-util
|
40
|
+
prerelease: false
|
41
|
+
requirement: &id003 !ruby/object:Gem::Requirement
|
42
|
+
none: false
|
43
|
+
requirements:
|
44
|
+
- - ~>
|
45
|
+
- !ruby/object:Gem::Version
|
46
|
+
version: 1.5.0
|
47
|
+
type: :runtime
|
48
|
+
version_requirements: *id003
|
49
|
+
- !ruby/object:Gem::Dependency
|
50
|
+
name: iudex-filter
|
51
|
+
prerelease: false
|
52
|
+
requirement: &id004 !ruby/object:Gem::Requirement
|
53
|
+
none: false
|
54
|
+
requirements:
|
55
|
+
- - ~>
|
56
|
+
- !ruby/object:Gem::Version
|
57
|
+
version: 1.0.0
|
58
|
+
type: :runtime
|
59
|
+
version_requirements: *id004
|
60
|
+
- !ruby/object:Gem::Dependency
|
61
|
+
name: iudex-http
|
62
|
+
prerelease: false
|
63
|
+
requirement: &id005 !ruby/object:Gem::Requirement
|
64
|
+
none: false
|
65
|
+
requirements:
|
66
|
+
- - ~>
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: 1.0.0
|
69
|
+
type: :runtime
|
70
|
+
version_requirements: *id005
|
71
|
+
- !ruby/object:Gem::Dependency
|
72
|
+
name: iudex-barc
|
73
|
+
prerelease: false
|
74
|
+
requirement: &id006 !ruby/object:Gem::Requirement
|
75
|
+
none: false
|
76
|
+
requirements:
|
77
|
+
- - ~>
|
78
|
+
- !ruby/object:Gem::Version
|
79
|
+
version: 1.0.0
|
80
|
+
type: :runtime
|
81
|
+
version_requirements: *id006
|
82
|
+
- !ruby/object:Gem::Dependency
|
83
|
+
name: minitest
|
84
|
+
prerelease: false
|
85
|
+
requirement: &id007 !ruby/object:Gem::Requirement
|
86
|
+
none: false
|
87
|
+
requirements:
|
88
|
+
- - ">="
|
89
|
+
- !ruby/object:Gem::Version
|
90
|
+
version: 1.7.1
|
91
|
+
- - <
|
92
|
+
- !ruby/object:Gem::Version
|
93
|
+
version: "2.1"
|
94
|
+
type: :development
|
95
|
+
version_requirements: *id007
|
96
|
+
- !ruby/object:Gem::Dependency
|
97
|
+
name: rjack-logback
|
98
|
+
prerelease: false
|
99
|
+
requirement: &id008 !ruby/object:Gem::Requirement
|
100
|
+
none: false
|
101
|
+
requirements:
|
102
|
+
- - ~>
|
103
|
+
- !ruby/object:Gem::Version
|
104
|
+
version: "1.0"
|
105
|
+
type: :development
|
106
|
+
version_requirements: *id008
|
107
|
+
- !ruby/object:Gem::Dependency
|
108
|
+
name: rjack-tarpit
|
109
|
+
prerelease: false
|
110
|
+
requirement: &id009 !ruby/object:Gem::Requirement
|
111
|
+
none: false
|
112
|
+
requirements:
|
113
|
+
- - ~>
|
114
|
+
- !ruby/object:Gem::Version
|
115
|
+
version: 1.3.0
|
116
|
+
type: :development
|
117
|
+
version_requirements: *id009
|
118
|
+
description: |-
|
119
|
+
Iudex is a general purpose web crawler and feed processor in
|
120
|
+
ruby/java. The iudex-core gem contains core facilities and notably,
|
121
|
+
does not contain such facilities as database-backed state management.
|
122
|
+
email:
|
123
|
+
- dek-oss@gravitext.com
|
124
|
+
executables:
|
125
|
+
- iudex-test-config
|
126
|
+
- iudex-url-norm
|
127
|
+
extensions: []
|
128
|
+
|
129
|
+
extra_rdoc_files:
|
130
|
+
- Manifest.txt
|
131
|
+
- History.rdoc
|
132
|
+
- README.rdoc
|
133
|
+
files:
|
134
|
+
- History.rdoc
|
135
|
+
- Manifest.txt
|
136
|
+
- README.rdoc
|
137
|
+
- Rakefile
|
138
|
+
- pom.xml
|
139
|
+
- bin/iudex-test-config
|
140
|
+
- bin/iudex-url-norm
|
141
|
+
- build/TLDSets.java.erb
|
142
|
+
- build/effective_tld_name.dat
|
143
|
+
- build/tld_set_generator.rb
|
144
|
+
- config/config.rb
|
145
|
+
- lib/iudex-core/base.rb
|
146
|
+
- lib/iudex-core.rb
|
147
|
+
- lib/iudex-core/config.rb
|
148
|
+
- test/setup.rb
|
149
|
+
- test/test_content_fetcher.rb
|
150
|
+
- test/test_log_writer.rb
|
151
|
+
- lib/iudex-core/iudex-core-1.0.0.jar
|
152
|
+
has_rdoc: true
|
153
|
+
homepage: http://github.com/dekellum/iudex
|
154
|
+
licenses: []
|
155
|
+
|
156
|
+
post_install_message:
|
157
|
+
rdoc_options:
|
158
|
+
- --main
|
159
|
+
- README.rdoc
|
160
|
+
require_paths:
|
161
|
+
- lib
|
162
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
163
|
+
none: false
|
164
|
+
requirements:
|
165
|
+
- - ">="
|
166
|
+
- !ruby/object:Gem::Version
|
167
|
+
version: "0"
|
168
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
169
|
+
none: false
|
170
|
+
requirements:
|
171
|
+
- - ">="
|
172
|
+
- !ruby/object:Gem::Version
|
173
|
+
version: "0"
|
174
|
+
requirements: []
|
175
|
+
|
176
|
+
rubyforge_project: iudex-core
|
177
|
+
rubygems_version: 1.5.1
|
178
|
+
signing_key:
|
179
|
+
specification_version: 3
|
180
|
+
summary: Iudex is a general purpose web crawler and feed processor in ruby/java
|
181
|
+
test_files:
|
182
|
+
- test/test_content_fetcher.rb
|
183
|
+
- test/test_log_writer.rb
|