iudex-html 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 +24 -0
- data/README.rdoc +25 -0
- data/Rakefile +53 -0
- data/build/HTML.java.erb +91 -0
- data/build/attributes +82 -0
- data/build/java_generate.rb +139 -0
- data/build/tags +130 -0
- data/lib/iudex-html.rb +56 -0
- data/lib/iudex-html/base.rb +21 -0
- data/lib/iudex-html/factory_helper.rb +95 -0
- data/lib/iudex-html/iudex-html-1.0.0.jar +0 -0
- data/pom.xml +51 -0
- data/test/html_test_helper.rb +100 -0
- data/test/setup.rb +38 -0
- data/test/test_characters_normalizer.rb +81 -0
- data/test/test_extract_filter.rb +165 -0
- data/test/test_factory_helper.rb +51 -0
- data/test/test_html_parser.rb +128 -0
- data/test/test_other_filters.rb +51 -0
- data/test/test_other_tree_filters.rb +124 -0
- data/test/test_parse_filter.rb +72 -0
- data/test/test_tree_walker.rb +94 -0
- data/test/test_word_counters.rb +96 -0
- metadata +162 -0
@@ -0,0 +1,72 @@
|
|
1
|
+
#!/usr/bin/env jruby
|
2
|
+
#.hashdot.profile += jruby-shortlived
|
3
|
+
|
4
|
+
#--
|
5
|
+
# Copyright (c) 2010-2011 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
|
+
|
22
|
+
class TestParseFilter < MiniTest::Unit::TestCase
|
23
|
+
include HTMLTestHelper
|
24
|
+
include Gravitext::HTMap
|
25
|
+
include Iudex::Core
|
26
|
+
include Iudex::HTML
|
27
|
+
include Iudex::HTML::Filters
|
28
|
+
|
29
|
+
def setup
|
30
|
+
@filter = html_parse_filter( :title )
|
31
|
+
@filter.min_parse = 0
|
32
|
+
end
|
33
|
+
|
34
|
+
def test_marked
|
35
|
+
assert( ! marked?( "" ) )
|
36
|
+
assert( ! marked?( "simple" ) )
|
37
|
+
assert( ! marked?( "<simple" ) )
|
38
|
+
assert( ! marked?( "x < y" ) )
|
39
|
+
assert( ! marked?( "AT&T" ) )
|
40
|
+
assert( ! marked?( "AT & T;" ) )
|
41
|
+
|
42
|
+
assert( marked?( "<a>" ) )
|
43
|
+
assert( marked?( "Words © 2010" ) )
|
44
|
+
assert( marked?( "" ) )
|
45
|
+
assert( marked?( "߬" ) )
|
46
|
+
assert( marked?( "<![CDATA[simple]]>" ) )
|
47
|
+
assert( marked?( "<![CDATA[simple" ) )
|
48
|
+
assert( marked?( "<!-- comment -->" ) )
|
49
|
+
end
|
50
|
+
|
51
|
+
def marked?( text )
|
52
|
+
@filter.text_marked( text )
|
53
|
+
end
|
54
|
+
|
55
|
+
def test_markup
|
56
|
+
tests = [ [ "simple", 0, "simple" ],
|
57
|
+
[ "<i>inner</i>", 1, nil ],
|
58
|
+
[ "<i>inner</i>", 2, nil ],
|
59
|
+
[ "<!--ignore-->text", 1, "text" ],
|
60
|
+
[ "<!--ignore-->text", 2, "text" ],
|
61
|
+
[ "<", 1, "<" ],
|
62
|
+
[ "&lt;", 2, "<" ] ]
|
63
|
+
|
64
|
+
tests.each do | input, count, out |
|
65
|
+
map = UniMap.new
|
66
|
+
map.title = input
|
67
|
+
assert_equal( count, @filter.parse_loop( map ), input )
|
68
|
+
assert_equal( out, map.title && map.title.to_s )
|
69
|
+
end
|
70
|
+
end
|
71
|
+
|
72
|
+
end
|
@@ -0,0 +1,94 @@
|
|
1
|
+
#!/usr/bin/env jruby
|
2
|
+
#.hashdot.profile += jruby-shortlived
|
3
|
+
|
4
|
+
#--
|
5
|
+
# Copyright (c) 2010-2011 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
|
+
|
22
|
+
class TestTreeWalker < MiniTest::Unit::TestCase
|
23
|
+
include HTMLTestHelper
|
24
|
+
|
25
|
+
import 'iudex.html.tree.TreeFilter'
|
26
|
+
Action = TreeFilter::Action
|
27
|
+
|
28
|
+
DROP_HTML = {
|
29
|
+
:in => "<div>one<p>foo</p><br/> two</div>",
|
30
|
+
:out => "<div>one~~~~~~~~~~<br/> two</div>" }
|
31
|
+
# Note: ~~~ is padding removed in compare
|
32
|
+
|
33
|
+
def test_drop
|
34
|
+
filter = TagFilter.new( HTML::P, Action::DROP )
|
35
|
+
[ :walk_depth_first, :walk_breadth_first ].each do |order|
|
36
|
+
assert_transform( DROP_HTML, filter, order )
|
37
|
+
end
|
38
|
+
end
|
39
|
+
|
40
|
+
SKIP_HTML = {
|
41
|
+
:in => "<div>first<b>drop</b><span><b>not dropped</b></span></div>",
|
42
|
+
:out => "<div>first~~~~~~~~~~~<span><b>not dropped</b></span></div>" }
|
43
|
+
|
44
|
+
def test_skip
|
45
|
+
chain = TreeFilterChain.new( [ TagFilter.new( HTML::SPAN, Action::SKIP ),
|
46
|
+
TagFilter.new( HTML::B, Action::DROP ) ] )
|
47
|
+
assert_transform( SKIP_HTML, chain, :walk_breadth_first )
|
48
|
+
end
|
49
|
+
|
50
|
+
TERM_HTML = {
|
51
|
+
:in => "<div><span>first</span><b>term</b><span><b>not</b></span></div>",
|
52
|
+
:out => "<div>~~~~~~~~~~~~~~~~~~<b>term</b><span><b>not</b></span></div>" }
|
53
|
+
|
54
|
+
def test_terminate
|
55
|
+
chain = TreeFilterChain.new( [ TagFilter.new( HTML::B, Action::TERMINATE ),
|
56
|
+
TagFilter.new( HTML::SPAN, Action::DROP ) ] )
|
57
|
+
[ :walk_depth_first, :walk_breadth_first ].each do |order|
|
58
|
+
assert_equal( Action::TERMINATE,
|
59
|
+
assert_transform( TERM_HTML, chain, order ) )
|
60
|
+
end
|
61
|
+
end
|
62
|
+
|
63
|
+
FOLD_HTML = {
|
64
|
+
:in => "<div>first <b>drop</b> <span> remain <b>drop</b> </span> </div>",
|
65
|
+
:out => "<div>first ~~~~~~~~~~~ ~~~~~~ remain ~~~~~~~~~~~ ~~~~~~~ </div>" }
|
66
|
+
|
67
|
+
def test_fold
|
68
|
+
chain = TreeFilterChain.new( [ TagFilter.new( HTML::SPAN, Action::FOLD ),
|
69
|
+
TagFilter.new( HTML::B, Action::DROP ) ] )
|
70
|
+
|
71
|
+
[ :walk_breadth_first, :walk_depth_first ].each do |order|
|
72
|
+
assert_transform( FOLD_HTML, chain, order )
|
73
|
+
end
|
74
|
+
end
|
75
|
+
|
76
|
+
class TagFilter
|
77
|
+
include TreeFilter
|
78
|
+
|
79
|
+
def initialize( tag, action )
|
80
|
+
@tag = tag
|
81
|
+
@action = action
|
82
|
+
end
|
83
|
+
|
84
|
+
def filter( node )
|
85
|
+
elm = node.as_element
|
86
|
+
if( elm && elm.tag == @tag )
|
87
|
+
@action
|
88
|
+
else
|
89
|
+
Action::CONTINUE
|
90
|
+
end
|
91
|
+
end
|
92
|
+
end
|
93
|
+
|
94
|
+
end
|
@@ -0,0 +1,96 @@
|
|
1
|
+
#!/usr/bin/env jruby
|
2
|
+
# -*- coding: utf-8 -*-
|
3
|
+
#.hashdot.profile += jruby-shortlived
|
4
|
+
|
5
|
+
#--
|
6
|
+
# Copyright (c) 2010-2011 David Kellum
|
7
|
+
#
|
8
|
+
# Licensed under the Apache License, Version 2.0 (the "License"); you
|
9
|
+
# may not use this file except in compliance with the License. You
|
10
|
+
# may obtain a copy of the License at
|
11
|
+
#
|
12
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
13
|
+
#
|
14
|
+
# Unless required by applicable law or agreed to in writing, software
|
15
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
16
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
17
|
+
# implied. See the License for the specific language governing
|
18
|
+
# permissions and limitations under the License.
|
19
|
+
#++
|
20
|
+
|
21
|
+
require File.join( File.dirname( __FILE__ ), "setup" )
|
22
|
+
|
23
|
+
class TestWordCounters < MiniTest::Unit::TestCase
|
24
|
+
include HTMLTestHelper
|
25
|
+
include Iudex::HTML::Tree
|
26
|
+
include Iudex::HTML::Tree::Filters
|
27
|
+
|
28
|
+
def test_counts
|
29
|
+
tset = [ [ "", 0, 0 ],
|
30
|
+
[ "<div><span> </span></div>", 0, 0 ],
|
31
|
+
|
32
|
+
[ "a b", 2, 2 ],
|
33
|
+
[ "<div>a b</div>", 2, 2 ],
|
34
|
+
[ "<div><span>a b</span></div>", 2, 2 ],
|
35
|
+
[ "<div><span>a b</span><span>c d</span></div>", 4, 4 ],
|
36
|
+
|
37
|
+
[ "<div>a b <span><a name='foo'>c</a> d</span> e f</div>", 6, 6 ],
|
38
|
+
|
39
|
+
[ "<div><a href='foo'>a b</a></div>",
|
40
|
+
2, 2 * 0.25 ],
|
41
|
+
|
42
|
+
[ "<div><div>a b</div><div>c d</div></div>",
|
43
|
+
4, ( 2*2 + 2*2 ) / 4.0 ],
|
44
|
+
|
45
|
+
[ "<div><div>a b</div><div>c d</div><div> </div></div>",
|
46
|
+
4, ( 2*2 + 2*2 + 0*0 ) / 4.0 ],
|
47
|
+
|
48
|
+
[ "<div>a <div>a b</div><div>c d</div></div>",
|
49
|
+
5, 1.0 + ( 2*2 + 2*2 ) / 5.0 ],
|
50
|
+
|
51
|
+
[ "<div>a <div>a b c</div><div>c d</div></div>",
|
52
|
+
6, 1.0 + ( 3*3 + 2*2 ) / 6.0 ],
|
53
|
+
|
54
|
+
[ "<div><p>a b</p><p>c d</p></div><div>e f g</div>",
|
55
|
+
7, ( 2*4 + 3*3 ) / 7.0 ] ]
|
56
|
+
|
57
|
+
chain = TreeFilterChain.new( [ WordCounter.new, WordyCounter.new ] )
|
58
|
+
|
59
|
+
tset.each do |html, word_count, wordiness|
|
60
|
+
tree = parse( html )
|
61
|
+
TreeWalker::walk_depth_first( chain, tree )
|
62
|
+
|
63
|
+
assert_equal( word_count,
|
64
|
+
tree.get( HTMLTreeKeys::WORD_COUNT ),
|
65
|
+
"word_count for: " + html )
|
66
|
+
|
67
|
+
assert_in_delta( wordiness,
|
68
|
+
tree.get( HTMLTreeKeys::WORDINESS ),
|
69
|
+
1e-4,
|
70
|
+
" wordiness for: " + html )
|
71
|
+
end
|
72
|
+
end
|
73
|
+
|
74
|
+
def test_doc
|
75
|
+
html = <<HTML
|
76
|
+
<html xmlns="http://www.w3.org/1999/xhtml">
|
77
|
+
<head>
|
78
|
+
<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
|
79
|
+
<title>Iūdex</title>
|
80
|
+
<style>style</style>
|
81
|
+
</head>
|
82
|
+
<body>
|
83
|
+
<p>Iūdex test.</p>
|
84
|
+
</body>
|
85
|
+
</html>
|
86
|
+
HTML
|
87
|
+
tree = parse( html, "UTF-8" )
|
88
|
+
chain = TreeFilterChain.new( [ MetaSkipFilter.new,
|
89
|
+
WordCounter.new,
|
90
|
+
WordyCounter.new ] )
|
91
|
+
TreeWalker::walk_depth_first( chain, tree )
|
92
|
+
assert_equal( 2, tree.get( HTMLTreeKeys::WORD_COUNT ) );
|
93
|
+
assert_equal( 2, tree.get( HTMLTreeKeys::WORDINESS ) );
|
94
|
+
end
|
95
|
+
|
96
|
+
end
|
metadata
ADDED
@@ -0,0 +1,162 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: iudex-html
|
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: iudex-core
|
18
|
+
prerelease: false
|
19
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
20
|
+
none: false
|
21
|
+
requirements:
|
22
|
+
- - ~>
|
23
|
+
- !ruby/object:Gem::Version
|
24
|
+
version: 1.0.0
|
25
|
+
type: :runtime
|
26
|
+
version_requirements: *id001
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rjack-nekohtml
|
29
|
+
prerelease: false
|
30
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
31
|
+
none: false
|
32
|
+
requirements:
|
33
|
+
- - ~>
|
34
|
+
- !ruby/object:Gem::Version
|
35
|
+
version: 1.9.14
|
36
|
+
type: :runtime
|
37
|
+
version_requirements: *id002
|
38
|
+
- !ruby/object:Gem::Dependency
|
39
|
+
name: gravitext-xmlprod
|
40
|
+
prerelease: false
|
41
|
+
requirement: &id003 !ruby/object:Gem::Requirement
|
42
|
+
none: false
|
43
|
+
requirements:
|
44
|
+
- - ~>
|
45
|
+
- !ruby/object:Gem::Version
|
46
|
+
version: 1.4.0
|
47
|
+
type: :runtime
|
48
|
+
version_requirements: *id003
|
49
|
+
- !ruby/object:Gem::Dependency
|
50
|
+
name: minitest
|
51
|
+
prerelease: false
|
52
|
+
requirement: &id004 !ruby/object:Gem::Requirement
|
53
|
+
none: false
|
54
|
+
requirements:
|
55
|
+
- - ">="
|
56
|
+
- !ruby/object:Gem::Version
|
57
|
+
version: 1.7.1
|
58
|
+
- - <
|
59
|
+
- !ruby/object:Gem::Version
|
60
|
+
version: "2.1"
|
61
|
+
type: :development
|
62
|
+
version_requirements: *id004
|
63
|
+
- !ruby/object:Gem::Dependency
|
64
|
+
name: rjack-logback
|
65
|
+
prerelease: false
|
66
|
+
requirement: &id005 !ruby/object:Gem::Requirement
|
67
|
+
none: false
|
68
|
+
requirements:
|
69
|
+
- - ~>
|
70
|
+
- !ruby/object:Gem::Version
|
71
|
+
version: "1.0"
|
72
|
+
type: :development
|
73
|
+
version_requirements: *id005
|
74
|
+
- !ruby/object:Gem::Dependency
|
75
|
+
name: rjack-tarpit
|
76
|
+
prerelease: false
|
77
|
+
requirement: &id006 !ruby/object:Gem::Requirement
|
78
|
+
none: false
|
79
|
+
requirements:
|
80
|
+
- - ~>
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: 1.3.0
|
83
|
+
type: :development
|
84
|
+
version_requirements: *id006
|
85
|
+
description: |-
|
86
|
+
Iudex is a general purpose web crawler and feed processor in
|
87
|
+
ruby/java. The iudex-html gem contains filters for HTML parsing,
|
88
|
+
filtering, exracting text and links.
|
89
|
+
email:
|
90
|
+
- dek-oss@gravitext.com
|
91
|
+
executables: []
|
92
|
+
|
93
|
+
extensions: []
|
94
|
+
|
95
|
+
extra_rdoc_files:
|
96
|
+
- Manifest.txt
|
97
|
+
- History.rdoc
|
98
|
+
- README.rdoc
|
99
|
+
files:
|
100
|
+
- History.rdoc
|
101
|
+
- Manifest.txt
|
102
|
+
- README.rdoc
|
103
|
+
- Rakefile
|
104
|
+
- pom.xml
|
105
|
+
- build/HTML.java.erb
|
106
|
+
- build/attributes
|
107
|
+
- build/java_generate.rb
|
108
|
+
- build/tags
|
109
|
+
- lib/iudex-html/base.rb
|
110
|
+
- lib/iudex-html.rb
|
111
|
+
- lib/iudex-html/factory_helper.rb
|
112
|
+
- test/html_test_helper.rb
|
113
|
+
- test/setup.rb
|
114
|
+
- test/test_characters_normalizer.rb
|
115
|
+
- test/test_extract_filter.rb
|
116
|
+
- test/test_factory_helper.rb
|
117
|
+
- test/test_html_parser.rb
|
118
|
+
- test/test_other_filters.rb
|
119
|
+
- test/test_other_tree_filters.rb
|
120
|
+
- test/test_parse_filter.rb
|
121
|
+
- test/test_tree_walker.rb
|
122
|
+
- test/test_word_counters.rb
|
123
|
+
- lib/iudex-html/iudex-html-1.0.0.jar
|
124
|
+
has_rdoc: true
|
125
|
+
homepage: http://github.com/dekellum/iudex
|
126
|
+
licenses: []
|
127
|
+
|
128
|
+
post_install_message:
|
129
|
+
rdoc_options:
|
130
|
+
- --main
|
131
|
+
- README.rdoc
|
132
|
+
require_paths:
|
133
|
+
- lib
|
134
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
135
|
+
none: false
|
136
|
+
requirements:
|
137
|
+
- - ">="
|
138
|
+
- !ruby/object:Gem::Version
|
139
|
+
version: "0"
|
140
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
141
|
+
none: false
|
142
|
+
requirements:
|
143
|
+
- - ">="
|
144
|
+
- !ruby/object:Gem::Version
|
145
|
+
version: "0"
|
146
|
+
requirements: []
|
147
|
+
|
148
|
+
rubyforge_project: iudex-html
|
149
|
+
rubygems_version: 1.5.1
|
150
|
+
signing_key:
|
151
|
+
specification_version: 3
|
152
|
+
summary: Iudex is a general purpose web crawler and feed processor in ruby/java
|
153
|
+
test_files:
|
154
|
+
- test/test_factory_helper.rb
|
155
|
+
- test/test_other_filters.rb
|
156
|
+
- test/test_characters_normalizer.rb
|
157
|
+
- test/test_word_counters.rb
|
158
|
+
- test/test_extract_filter.rb
|
159
|
+
- test/test_tree_walker.rb
|
160
|
+
- test/test_other_tree_filters.rb
|
161
|
+
- test/test_html_parser.rb
|
162
|
+
- test/test_parse_filter.rb
|