iudex-barc 1.4.0-java → 1.4.1-java
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/History.rdoc +4 -0
- data/Manifest.txt +1 -1
- data/README.rdoc +1 -1
- data/bin/iudex-barc +1 -1
- data/bin/iudex-http-record +6 -4
- data/lib/iudex-barc.rb +1 -1
- data/lib/iudex-barc/base.rb +2 -2
- data/lib/iudex-barc/iudex-barc-1.4.1.jar +0 -0
- data/pom.xml +1 -1
- metadata +29 -47
- data/lib/iudex-barc/iudex-barc-1.4.0.jar +0 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: a667bd887b89becb73ca9d1cec5012eddf2b1123
|
4
|
+
data.tar.gz: 97f9f5c63b6e4777ad932a6813bbc60ef8b450f5
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 7fd1122cdddd6d1dc7cf47e1ac9a7104b1990e04284542c3b96633cfa34db5c1b7bce387ae6f305089f349baf6a7866c82f8e139eb9b7bae9184c0ab2a55ffbe
|
7
|
+
data.tar.gz: 3a1f0350238b44003cb2fff584a5ce27ca0d397b07b27dd7fb91cbebcc4c7561fa6a7a0b703a9704c1fa67d89093e0be21d36489764338d8e1047e763648854c
|
data/History.rdoc
CHANGED
data/Manifest.txt
CHANGED
data/README.rdoc
CHANGED
data/bin/iudex-barc
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
#!/usr/bin/env jruby
|
2
2
|
# -*- ruby -*-
|
3
3
|
#--
|
4
|
-
# Copyright (c) 2008-
|
4
|
+
# Copyright (c) 2008-2015 David Kellum
|
5
5
|
#
|
6
6
|
# Licensed under the Apache License, Version 2.0 (the "License"); you
|
7
7
|
# may not use this file except in compliance with the License. You
|
data/bin/iudex-http-record
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
#!/usr/bin/env jruby
|
2
2
|
# -*- ruby -*-
|
3
3
|
#--
|
4
|
-
# Copyright (c) 2008-
|
4
|
+
# Copyright (c) 2008-2015 David Kellum
|
5
5
|
#
|
6
6
|
# Licensed under the Apache License, Version 2.0 (the "License"); you
|
7
7
|
# may not use this file except in compliance with the License. You
|
@@ -50,11 +50,12 @@ module IudexBinScript
|
|
50
50
|
|
51
51
|
mgr = Iudex::HTTPClient3.create_manager
|
52
52
|
mgr.client_params.set_int_parameter( "http.protocol.max-redirects", 8 )
|
53
|
-
mgr.client_params.connection_manager_timeout =
|
54
|
-
mgr.client_params.so_timeout =
|
53
|
+
mgr.client_params.connection_manager_timeout = 30_000 #ms
|
54
|
+
mgr.client_params.so_timeout = 90_000 #ms
|
55
55
|
mgr.start
|
56
56
|
|
57
57
|
hclient = HTTPClient3.new( mgr.client )
|
58
|
+
hclient.max_content_length = 200*1024*1024
|
58
59
|
|
59
60
|
barc_file = Iudex::BARC::BARCFile.new( java.io.File.new( @barc_name ) )
|
60
61
|
barc_file.truncate if @barc_name == './record.barc'
|
@@ -108,7 +109,8 @@ module IudexBinScript
|
|
108
109
|
end
|
109
110
|
|
110
111
|
def accept_types
|
111
|
-
"application/xhtml+xml,text/html,application/xml;q=0.9,
|
112
|
+
( "application/xhtml+xml,text/html,application/xml;q=0.9," +
|
113
|
+
"text/*;q=0.8,*/*;q=0.1" )
|
112
114
|
end
|
113
115
|
|
114
116
|
end
|
data/lib/iudex-barc.rb
CHANGED
data/lib/iudex-barc/base.rb
CHANGED
@@ -1,5 +1,5 @@
|
|
1
1
|
#--
|
2
|
-
# Copyright (c) 2008-
|
2
|
+
# Copyright (c) 2008-2015 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
|
@@ -16,7 +16,7 @@
|
|
16
16
|
|
17
17
|
module Iudex
|
18
18
|
module BARC
|
19
|
-
VERSION = '1.4.
|
19
|
+
VERSION = '1.4.1'
|
20
20
|
|
21
21
|
LIB_DIR = File.dirname( __FILE__ ) # :nodoc:
|
22
22
|
end
|
Binary file
|
data/pom.xml
CHANGED
metadata
CHANGED
@@ -1,96 +1,85 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: iudex-barc
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
|
5
|
-
version: 1.4.0
|
4
|
+
version: 1.4.1
|
6
5
|
platform: java
|
7
6
|
authors:
|
8
7
|
- David Kellum
|
9
8
|
autorequire:
|
10
9
|
bindir: bin
|
11
10
|
cert_chain: []
|
12
|
-
date:
|
11
|
+
date: 2015-01-25 00:00:00.000000000 Z
|
13
12
|
dependencies:
|
14
13
|
- !ruby/object:Gem::Dependency
|
15
|
-
name: rjack-slf4j
|
16
|
-
version_requirements: !ruby/object:Gem::Requirement
|
17
|
-
requirements:
|
18
|
-
- - ~>
|
19
|
-
- !ruby/object:Gem::Version
|
20
|
-
version: 1.7.0
|
21
|
-
none: false
|
22
14
|
requirement: !ruby/object:Gem::Requirement
|
23
15
|
requirements:
|
24
16
|
- - ~>
|
25
17
|
- !ruby/object:Gem::Version
|
26
18
|
version: 1.7.0
|
27
|
-
|
19
|
+
name: rjack-slf4j
|
28
20
|
prerelease: false
|
29
21
|
type: :runtime
|
30
|
-
- !ruby/object:Gem::Dependency
|
31
|
-
name: gravitext-util
|
32
22
|
version_requirements: !ruby/object:Gem::Requirement
|
33
23
|
requirements:
|
34
24
|
- - ~>
|
35
25
|
- !ruby/object:Gem::Version
|
36
26
|
version: 1.7.0
|
37
|
-
|
27
|
+
- !ruby/object:Gem::Dependency
|
38
28
|
requirement: !ruby/object:Gem::Requirement
|
39
29
|
requirements:
|
40
30
|
- - ~>
|
41
31
|
- !ruby/object:Gem::Version
|
42
32
|
version: 1.7.0
|
43
|
-
|
33
|
+
name: gravitext-util
|
44
34
|
prerelease: false
|
45
35
|
type: :runtime
|
46
|
-
- !ruby/object:Gem::Dependency
|
47
|
-
name: iudex-http
|
48
36
|
version_requirements: !ruby/object:Gem::Requirement
|
49
37
|
requirements:
|
50
38
|
- - ~>
|
51
39
|
- !ruby/object:Gem::Version
|
52
|
-
version: 1.
|
53
|
-
|
40
|
+
version: 1.7.0
|
41
|
+
- !ruby/object:Gem::Dependency
|
54
42
|
requirement: !ruby/object:Gem::Requirement
|
55
43
|
requirements:
|
56
44
|
- - ~>
|
57
45
|
- !ruby/object:Gem::Version
|
58
46
|
version: 1.4.0
|
59
|
-
|
47
|
+
name: iudex-http
|
60
48
|
prerelease: false
|
61
49
|
type: :runtime
|
62
|
-
- !ruby/object:Gem::Dependency
|
63
|
-
name: minitest
|
64
50
|
version_requirements: !ruby/object:Gem::Requirement
|
65
51
|
requirements:
|
66
52
|
- - ~>
|
67
53
|
- !ruby/object:Gem::Version
|
68
|
-
version: 4.
|
69
|
-
|
54
|
+
version: 1.4.0
|
55
|
+
- !ruby/object:Gem::Dependency
|
70
56
|
requirement: !ruby/object:Gem::Requirement
|
71
57
|
requirements:
|
72
58
|
- - ~>
|
73
59
|
- !ruby/object:Gem::Version
|
74
60
|
version: 4.7.4
|
75
|
-
|
61
|
+
name: minitest
|
76
62
|
prerelease: false
|
77
63
|
type: :development
|
78
|
-
- !ruby/object:Gem::Dependency
|
79
|
-
name: rjack-tarpit
|
80
64
|
version_requirements: !ruby/object:Gem::Requirement
|
81
65
|
requirements:
|
82
66
|
- - ~>
|
83
67
|
- !ruby/object:Gem::Version
|
84
|
-
version:
|
85
|
-
|
68
|
+
version: 4.7.4
|
69
|
+
- !ruby/object:Gem::Dependency
|
86
70
|
requirement: !ruby/object:Gem::Requirement
|
87
71
|
requirements:
|
88
72
|
- - ~>
|
89
73
|
- !ruby/object:Gem::Version
|
90
|
-
version: '2.
|
91
|
-
|
74
|
+
version: '2.1'
|
75
|
+
name: rjack-tarpit
|
92
76
|
prerelease: false
|
93
77
|
type: :development
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ~>
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '2.1'
|
94
83
|
description: Iudex is a general purpose web crawler and feed processor in ruby/java. The iudex-barc gem contains support for the BARC Basic ARChive format.
|
95
84
|
email:
|
96
85
|
- dek-oss@gravitext.com
|
@@ -111,9 +100,11 @@ files:
|
|
111
100
|
- bin/iudex-http-record
|
112
101
|
- lib/iudex-barc/base.rb
|
113
102
|
- lib/iudex-barc.rb
|
114
|
-
- lib/iudex-barc/iudex-barc-1.4.
|
103
|
+
- lib/iudex-barc/iudex-barc-1.4.1.jar
|
115
104
|
homepage: http://iudex.gravitext.com
|
116
|
-
licenses:
|
105
|
+
licenses:
|
106
|
+
- Apache-2.0
|
107
|
+
metadata: {}
|
117
108
|
post_install_message:
|
118
109
|
rdoc_options:
|
119
110
|
- --main
|
@@ -122,27 +113,18 @@ require_paths:
|
|
122
113
|
- lib
|
123
114
|
required_ruby_version: !ruby/object:Gem::Requirement
|
124
115
|
requirements:
|
125
|
-
- -
|
116
|
+
- - '>='
|
126
117
|
- !ruby/object:Gem::Version
|
127
|
-
version:
|
128
|
-
segments:
|
129
|
-
- 0
|
130
|
-
hash: 2
|
131
|
-
none: false
|
118
|
+
version: 1.8.7
|
132
119
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
133
120
|
requirements:
|
134
|
-
- -
|
121
|
+
- - '>='
|
135
122
|
- !ruby/object:Gem::Version
|
136
123
|
version: '0'
|
137
|
-
segments:
|
138
|
-
- 0
|
139
|
-
hash: 2
|
140
|
-
none: false
|
141
124
|
requirements: []
|
142
125
|
rubyforge_project:
|
143
|
-
rubygems_version: 1.
|
126
|
+
rubygems_version: 2.1.9
|
144
127
|
signing_key:
|
145
|
-
specification_version:
|
128
|
+
specification_version: 4
|
146
129
|
summary: Iudex is a general purpose web crawler and feed processor in ruby/java.
|
147
130
|
test_files: []
|
148
|
-
...
|
Binary file
|