iudex-barc 1.2.b.0-java → 1.2.b.1-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/Manifest.txt +1 -1
- data/bin/iudex-http-record +84 -20
- data/lib/iudex-barc/base.rb +1 -1
- data/lib/iudex-barc/{iudex-barc-1.2.b.0.jar → iudex-barc-1.2.b.1.jar} +0 -0
- data/pom.xml +1 -1
- metadata +3 -3
data/History.rdoc
CHANGED
@@ -1,3 +1,8 @@
|
|
1
|
+
=== 1.2.b.1 (2012-5-31)
|
2
|
+
* Improve usability of iudex-http-record CLI
|
3
|
+
* Output (H) default type in BARCResponseHandler (as used by
|
4
|
+
iudex-http-record)
|
5
|
+
|
1
6
|
=== 1.2.b.0 (2012-3-4)
|
2
7
|
* Upgrade to gravitext-util ~> 1.6.b (beta)
|
3
8
|
* Upgrade to tarpit ~> 2.0, bundler Gemfile, gemspec (dev)
|
data/Manifest.txt
CHANGED
data/bin/iudex-http-record
CHANGED
@@ -19,33 +19,97 @@
|
|
19
19
|
$LOAD_PATH.unshift File.join( File.dirname(__FILE__), "..", "lib" )
|
20
20
|
|
21
21
|
require 'rubygems'
|
22
|
-
require '
|
23
|
-
RJack::Logback.config_console
|
22
|
+
require 'optparse'
|
24
23
|
|
25
|
-
|
26
|
-
#RJack::Logback[ "iudex" ].level = RJack::Logback::DEBUG
|
24
|
+
module IudexBinScript
|
27
25
|
|
28
|
-
require '
|
29
|
-
|
26
|
+
require 'rjack-logback'
|
27
|
+
include RJack
|
30
28
|
|
31
|
-
|
32
|
-
import 'iudex.barc.http.BARCResponseHandler'
|
33
|
-
import 'iudex.barc.BARCFile'
|
29
|
+
Logback.config_console( :stderr => true )
|
34
30
|
|
35
|
-
|
36
|
-
|
31
|
+
#FIXME: Add debug flags
|
32
|
+
#RJack::Logback[ "org.apache.commons.httpclient" ].level = RJack::Logback::INFO
|
33
|
+
#RJack::Logback[ "iudex" ].level = RJack::Logback::DEBUG
|
37
34
|
|
38
|
-
|
35
|
+
require 'iudex-barc'
|
39
36
|
|
40
|
-
|
41
|
-
barc_file.truncate #FIXME: Optional
|
37
|
+
require 'iudex-httpclient-3' #FIXME: Unspecified dependency
|
42
38
|
|
43
|
-
|
44
|
-
|
39
|
+
class BARCRecorder
|
40
|
+
import 'iudex.httpclient3.HTTPClient3'
|
41
|
+
import 'iudex.barc.http.BARCResponseHandler'
|
45
42
|
|
46
|
-
|
47
|
-
|
43
|
+
def initialize
|
44
|
+
@req_headers = { 'User-Agent' => http_user_agent,
|
45
|
+
'Accept' => accept_types }
|
46
|
+
end
|
48
47
|
|
49
|
-
|
48
|
+
def run( args = ARGV )
|
49
|
+
urls = parse_args( args )
|
50
50
|
|
51
|
-
|
51
|
+
mgr = Iudex::HTTPClient3.create_manager
|
52
|
+
mgr.client_params.set_int_parameter( "http.protocol.max-redirects", 8 )
|
53
|
+
mgr.start
|
54
|
+
|
55
|
+
hclient = HTTPClient3.new( mgr.client )
|
56
|
+
|
57
|
+
barc_file = Iudex::BARC::BARCFile.new( java.io.File.new( @barc_name ) )
|
58
|
+
barc_file.truncate if @barc_name == './record.barc'
|
59
|
+
|
60
|
+
handler = BARCResponseHandler.new( barc_file )
|
61
|
+
handler.do_compress = false
|
62
|
+
|
63
|
+
urls.each do |url|
|
64
|
+
hsession = hclient.createSession;
|
65
|
+
hsession.url = url
|
66
|
+
headers = @req_headers.map { |h,v| Iudex::HTTP::Header.new( h, v ) }
|
67
|
+
hsession.add_request_headers( headers )
|
68
|
+
hclient.request( hsession, handler )
|
69
|
+
end
|
70
|
+
|
71
|
+
ensure
|
72
|
+
mgr.shutdown if mgr
|
73
|
+
barc_file.close if barc_file
|
74
|
+
end
|
75
|
+
|
76
|
+
def parse_args( args = ARGV )
|
77
|
+
parser = OptionParser.new do |opts|
|
78
|
+
opts.banner = ( "Usage: iudex-http-record [options] URL... " +
|
79
|
+
"[BARCFile]\n" +
|
80
|
+
"Options:\n" )
|
81
|
+
|
82
|
+
opts.on( "-v", "--version", "Display version and exit" ) do
|
83
|
+
puts "iudex-barc: #{Iudex::BARC::VERSION}"
|
84
|
+
exit 1
|
85
|
+
end
|
86
|
+
|
87
|
+
opts.on( "-A", "--User-Agent UA", String, "Set alt User-Agent" ) do |s|
|
88
|
+
@req_headers[ 'User-Agent' ] = s
|
89
|
+
end
|
90
|
+
|
91
|
+
end
|
92
|
+
|
93
|
+
args = parser.parse( args )
|
94
|
+
@barc_name = './record.barc'
|
95
|
+
if args.last =~ /.barc$/
|
96
|
+
@barc_name = args.pop
|
97
|
+
end
|
98
|
+
|
99
|
+
args #urls
|
100
|
+
end
|
101
|
+
|
102
|
+
def http_user_agent
|
103
|
+
( "Mozilla/5.0 (compatible; " +
|
104
|
+
"Iudex #{Iudex::HTTPClient3::VERSION}; " +
|
105
|
+
"+http://gravitext.com/iudex)" )
|
106
|
+
end
|
107
|
+
|
108
|
+
def accept_types
|
109
|
+
"application/xhtml+xml,text/html,application/xml;q=0.9,text/*;q=0.8"
|
110
|
+
end
|
111
|
+
|
112
|
+
end
|
113
|
+
|
114
|
+
BARCRecorder.new.run
|
115
|
+
end
|
data/lib/iudex-barc/base.rb
CHANGED
Binary file
|
data/pom.xml
CHANGED
metadata
CHANGED
@@ -2,7 +2,7 @@
|
|
2
2
|
name: iudex-barc
|
3
3
|
version: !ruby/object:Gem::Version
|
4
4
|
prerelease: 4
|
5
|
-
version: 1.2.b.
|
5
|
+
version: 1.2.b.1
|
6
6
|
platform: java
|
7
7
|
authors:
|
8
8
|
- David Kellum
|
@@ -10,7 +10,7 @@ autorequire:
|
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
12
|
|
13
|
-
date: 2012-
|
13
|
+
date: 2012-06-01 00:00:00 Z
|
14
14
|
dependencies:
|
15
15
|
- !ruby/object:Gem::Dependency
|
16
16
|
name: rjack-slf4j
|
@@ -88,7 +88,7 @@ files:
|
|
88
88
|
- bin/iudex-http-record
|
89
89
|
- lib/iudex-barc/base.rb
|
90
90
|
- lib/iudex-barc.rb
|
91
|
-
- lib/iudex-barc/iudex-barc-1.2.b.
|
91
|
+
- lib/iudex-barc/iudex-barc-1.2.b.1.jar
|
92
92
|
homepage: http://github.com/dekellum/iudex
|
93
93
|
licenses: []
|
94
94
|
|