bliss 0.0.7 → 0.0.9
Sign up to get free protection for your applications and to get access to all the features.
- data/CHANGELOG.rdoc +12 -0
- data/Gemfile +2 -2
- data/Gemfile.lock +11 -7
- data/Rakefile +7 -1
- data/VERSION +1 -1
- data/bliss.gemspec +18 -10
- data/complete_test.rb +74 -0
- data/gzip_support.rb +41 -0
- data/http-machine.rb +2 -3
- data/lib/bliss.rb +5 -1
- data/lib/bliss/constraint.rb +78 -0
- data/lib/bliss/encoding_error.rb +4 -0
- data/lib/bliss/format.rb +97 -0
- data/lib/bliss/parser.rb +208 -3
- data/lib/bliss/parser_machine.rb +93 -123
- data/lib/hash_extension.rb +16 -0
- data/spec.yml +23 -0
- data/spec/format_spec.rb +63 -0
- data/spec/spec_helper.rb +16 -0
- data/test.rb +44 -2
- metadata +31 -23
- data/lib/bliss/sax_parser.rb +0 -122
data/lib/hash_extension.rb
CHANGED
|
@@ -20,4 +20,20 @@ class Hash
|
|
|
20
20
|
chain.pop
|
|
21
21
|
return self.value_at_chain(chain)
|
|
22
22
|
end
|
|
23
|
+
|
|
24
|
+
def recurse(include_root=false, depth=[], &block)
|
|
25
|
+
self.each_pair { |k,v|
|
|
26
|
+
if v.is_a? Hash
|
|
27
|
+
if include_root
|
|
28
|
+
block.call(depth + [k], v)
|
|
29
|
+
end
|
|
30
|
+
depth.push k
|
|
31
|
+
v.recurse(include_root, depth, &block)
|
|
32
|
+
else
|
|
33
|
+
block.call(depth + [k], v)
|
|
34
|
+
#return "#{depth + [k]}: #{v.inspect}"
|
|
35
|
+
end
|
|
36
|
+
}
|
|
37
|
+
depth.pop
|
|
38
|
+
end
|
|
23
39
|
end
|
data/spec.yml
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
1
|
+
# TODO content_type = url
|
|
2
|
+
---
|
|
3
|
+
root:
|
|
4
|
+
ads:
|
|
5
|
+
tag_name_values: [ ads, jobs, job ]
|
|
6
|
+
ad:
|
|
7
|
+
id:
|
|
8
|
+
content_type: numeric
|
|
9
|
+
description:
|
|
10
|
+
tag_name_values: [ description, content ]
|
|
11
|
+
content_type: string
|
|
12
|
+
pictures:
|
|
13
|
+
tag_name_required: false
|
|
14
|
+
picture:
|
|
15
|
+
tag_name_required: false
|
|
16
|
+
url:
|
|
17
|
+
tag_name_required: true
|
|
18
|
+
content_type: string
|
|
19
|
+
content_format: /http:\/\/\w+/
|
|
20
|
+
url:
|
|
21
|
+
content_format: /http:\/\/\w+/
|
|
22
|
+
date:
|
|
23
|
+
content_type: date
|
data/spec/format_spec.rb
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
1
|
+
require 'spec_helper'
|
|
2
|
+
#require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
|
|
3
|
+
#require_dependency 'xmlrpc/client'
|
|
4
|
+
|
|
5
|
+
describe Bliss::Format do
|
|
6
|
+
before do
|
|
7
|
+
#@openx_banner = mock(OpenX::Services::Banner)
|
|
8
|
+
@format = Bliss::Format.new
|
|
9
|
+
end
|
|
10
|
+
|
|
11
|
+
describe '.constraints' do
|
|
12
|
+
#before do
|
|
13
|
+
#end
|
|
14
|
+
|
|
15
|
+
it 'should do it' do
|
|
16
|
+
@format.constraints.size.should == 8
|
|
17
|
+
end
|
|
18
|
+
end
|
|
19
|
+
|
|
20
|
+
#describe '.traffic' do
|
|
21
|
+
# before do
|
|
22
|
+
# @openx_banner.stub(:statistics) { YAML.load_file('spec/fixtures/openx_banner_statistics.yml') }
|
|
23
|
+
# OpenX::Services::Banner.should_receive(:find).with(1).and_return(@openx_banner)
|
|
24
|
+
# @banner = Banner.new(1)
|
|
25
|
+
# end
|
|
26
|
+
|
|
27
|
+
# it 'should return statistics' do
|
|
28
|
+
# @banner.traffic(Date.today, Date.today).should be_kind_of(Hash)
|
|
29
|
+
# end
|
|
30
|
+
#end
|
|
31
|
+
|
|
32
|
+
# describe '.created' do
|
|
33
|
+
# context 'when last creation is less than 2 days ago' do
|
|
34
|
+
# before do
|
|
35
|
+
# @site.stub(:last_creation_day_in_week) { Date.today - 1 }
|
|
36
|
+
# end
|
|
37
|
+
|
|
38
|
+
# it 'should be ok' do
|
|
39
|
+
# @site_evaluation.created[@site.id]['created'][0].should == 'ok'
|
|
40
|
+
# end
|
|
41
|
+
# end
|
|
42
|
+
|
|
43
|
+
# context 'when last creation is between 2 and 7 days ago' do
|
|
44
|
+
# before do
|
|
45
|
+
# @site.stub(:last_creation_day_in_week) { Date.today - 3 }
|
|
46
|
+
# end
|
|
47
|
+
|
|
48
|
+
# it 'should be a warning' do
|
|
49
|
+
# @site_evaluation.created[@site.id]['created'][0].should == 'warning'
|
|
50
|
+
# end
|
|
51
|
+
# end
|
|
52
|
+
|
|
53
|
+
# context 'when last creation is more than 7 days ago' do
|
|
54
|
+
# before do
|
|
55
|
+
# @site.stub(:last_creation_day_in_week) { Date.today - 8 }
|
|
56
|
+
# end
|
|
57
|
+
|
|
58
|
+
# it 'should be an alert' do
|
|
59
|
+
# @site_evaluation.created[@site.id]['created'][0].should == 'alert'
|
|
60
|
+
# end
|
|
61
|
+
# end
|
|
62
|
+
# end
|
|
63
|
+
end
|
data/spec/spec_helper.rb
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
|
|
2
|
+
$LOAD_PATH.unshift(File.dirname(__FILE__))
|
|
3
|
+
require 'rspec'
|
|
4
|
+
|
|
5
|
+
require 'bundler'
|
|
6
|
+
Bundler.require(:default, :development)
|
|
7
|
+
|
|
8
|
+
Dir["#{File.dirname(__FILE__)}/../lib/**/*.rb"].each {|f| require f}
|
|
9
|
+
|
|
10
|
+
# Requires supporting files with custom matchers and macros, etc,
|
|
11
|
+
# in ./support/ and its subdirectories.
|
|
12
|
+
Dir["#{File.dirname(__FILE__)}/support/**/*.rb"].each {|f| require f}
|
|
13
|
+
|
|
14
|
+
RSpec.configure do |config|
|
|
15
|
+
|
|
16
|
+
end
|
data/test.rb
CHANGED
|
@@ -1,5 +1,47 @@
|
|
|
1
1
|
require 'rubygems'
|
|
2
2
|
require 'bliss'
|
|
3
3
|
|
|
4
|
-
p = Bliss::
|
|
5
|
-
p.
|
|
4
|
+
p = Bliss::Parser.new('', 'output.xml')
|
|
5
|
+
p.wait_tag_close('ad')
|
|
6
|
+
#p.on_max_unhandled_bytes(20000) {
|
|
7
|
+
# puts 'Reached Max Unhandled Bytes'
|
|
8
|
+
# p.close
|
|
9
|
+
#}
|
|
10
|
+
|
|
11
|
+
@count = 0
|
|
12
|
+
@makes = 0
|
|
13
|
+
|
|
14
|
+
p.on_tag_close('ad') { |hash, depth|
|
|
15
|
+
if hash.has_key?('make')
|
|
16
|
+
@makes += 1
|
|
17
|
+
end
|
|
18
|
+
@count += 1
|
|
19
|
+
|
|
20
|
+
if @count == 600
|
|
21
|
+
p.close
|
|
22
|
+
end
|
|
23
|
+
}
|
|
24
|
+
|
|
25
|
+
=begin
|
|
26
|
+
p.on_tag_close('ad') { |hash|
|
|
27
|
+
count += 1
|
|
28
|
+
|
|
29
|
+
dict = {"make"=>"name"}
|
|
30
|
+
only_in_dict = false
|
|
31
|
+
hash = hash.inject({}) { |h,v| key = dict.invert[v[0]]; key ||= v[0] unless only_in_dict; h[key] = v[1] if key; h }
|
|
32
|
+
|
|
33
|
+
#puts hash.keys.inspect
|
|
34
|
+
if count == 100
|
|
35
|
+
p.close
|
|
36
|
+
end
|
|
37
|
+
}
|
|
38
|
+
=end
|
|
39
|
+
|
|
40
|
+
begin
|
|
41
|
+
p.parse
|
|
42
|
+
rescue Bliss::EncodingError
|
|
43
|
+
puts "Encoding Error!"
|
|
44
|
+
end
|
|
45
|
+
|
|
46
|
+
puts @count
|
|
47
|
+
puts @makes
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: bliss
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.9
|
|
5
5
|
prerelease:
|
|
6
6
|
platform: ruby
|
|
7
7
|
authors:
|
|
@@ -9,11 +9,11 @@ authors:
|
|
|
9
9
|
autorequire:
|
|
10
10
|
bindir: bin
|
|
11
11
|
cert_chain: []
|
|
12
|
-
date: 2012-
|
|
12
|
+
date: 2012-06-04 00:00:00.000000000 Z
|
|
13
13
|
dependencies:
|
|
14
14
|
- !ruby/object:Gem::Dependency
|
|
15
15
|
name: nokogiri
|
|
16
|
-
requirement: &
|
|
16
|
+
requirement: &16900020 !ruby/object:Gem::Requirement
|
|
17
17
|
none: false
|
|
18
18
|
requirements:
|
|
19
19
|
- - ! '>='
|
|
@@ -21,10 +21,10 @@ dependencies:
|
|
|
21
21
|
version: 1.5.2
|
|
22
22
|
type: :runtime
|
|
23
23
|
prerelease: false
|
|
24
|
-
version_requirements: *
|
|
24
|
+
version_requirements: *16900020
|
|
25
25
|
- !ruby/object:Gem::Dependency
|
|
26
26
|
name: eventmachine
|
|
27
|
-
requirement: &
|
|
27
|
+
requirement: &16899520 !ruby/object:Gem::Requirement
|
|
28
28
|
none: false
|
|
29
29
|
requirements:
|
|
30
30
|
- - ! '>='
|
|
@@ -32,10 +32,10 @@ dependencies:
|
|
|
32
32
|
version: 1.0.0.beta.4
|
|
33
33
|
type: :runtime
|
|
34
34
|
prerelease: false
|
|
35
|
-
version_requirements: *
|
|
35
|
+
version_requirements: *16899520
|
|
36
36
|
- !ruby/object:Gem::Dependency
|
|
37
37
|
name: em-http-request
|
|
38
|
-
requirement: &
|
|
38
|
+
requirement: &16898800 !ruby/object:Gem::Requirement
|
|
39
39
|
none: false
|
|
40
40
|
requirements:
|
|
41
41
|
- - ! '>='
|
|
@@ -43,32 +43,32 @@ dependencies:
|
|
|
43
43
|
version: 1.0.2
|
|
44
44
|
type: :runtime
|
|
45
45
|
prerelease: false
|
|
46
|
-
version_requirements: *
|
|
46
|
+
version_requirements: *16898800
|
|
47
47
|
- !ruby/object:Gem::Dependency
|
|
48
|
-
name:
|
|
49
|
-
requirement: &
|
|
48
|
+
name: rspec
|
|
49
|
+
requirement: &16898260 !ruby/object:Gem::Requirement
|
|
50
50
|
none: false
|
|
51
51
|
requirements:
|
|
52
|
-
- -
|
|
52
|
+
- - ~>
|
|
53
53
|
- !ruby/object:Gem::Version
|
|
54
|
-
version:
|
|
54
|
+
version: 2.8.0
|
|
55
55
|
type: :development
|
|
56
56
|
prerelease: false
|
|
57
|
-
version_requirements: *
|
|
57
|
+
version_requirements: *16898260
|
|
58
58
|
- !ruby/object:Gem::Dependency
|
|
59
59
|
name: bundler
|
|
60
|
-
requirement: &
|
|
60
|
+
requirement: &16897260 !ruby/object:Gem::Requirement
|
|
61
61
|
none: false
|
|
62
62
|
requirements:
|
|
63
63
|
- - ~>
|
|
64
64
|
- !ruby/object:Gem::Version
|
|
65
|
-
version: 1.
|
|
65
|
+
version: 1.1.3
|
|
66
66
|
type: :development
|
|
67
67
|
prerelease: false
|
|
68
|
-
version_requirements: *
|
|
68
|
+
version_requirements: *16897260
|
|
69
69
|
- !ruby/object:Gem::Dependency
|
|
70
70
|
name: jeweler
|
|
71
|
-
requirement: &
|
|
71
|
+
requirement: &16895760 !ruby/object:Gem::Requirement
|
|
72
72
|
none: false
|
|
73
73
|
requirements:
|
|
74
74
|
- - ~>
|
|
@@ -76,10 +76,10 @@ dependencies:
|
|
|
76
76
|
version: 1.6.4
|
|
77
77
|
type: :development
|
|
78
78
|
prerelease: false
|
|
79
|
-
version_requirements: *
|
|
79
|
+
version_requirements: *16895760
|
|
80
80
|
- !ruby/object:Gem::Dependency
|
|
81
81
|
name: simplecov
|
|
82
|
-
requirement: &
|
|
82
|
+
requirement: &16911540 !ruby/object:Gem::Requirement
|
|
83
83
|
none: false
|
|
84
84
|
requirements:
|
|
85
85
|
- - ! '>='
|
|
@@ -87,7 +87,7 @@ dependencies:
|
|
|
87
87
|
version: '0'
|
|
88
88
|
type: :development
|
|
89
89
|
prerelease: false
|
|
90
|
-
version_requirements: *
|
|
90
|
+
version_requirements: *16911540
|
|
91
91
|
description: streamed xml parsing tool
|
|
92
92
|
email: krakatoa1987@gmail.com
|
|
93
93
|
executables: []
|
|
@@ -97,6 +97,7 @@ extra_rdoc_files:
|
|
|
97
97
|
- README.rdoc
|
|
98
98
|
files:
|
|
99
99
|
- .document
|
|
100
|
+
- CHANGELOG.rdoc
|
|
100
101
|
- Gemfile
|
|
101
102
|
- Gemfile.lock
|
|
102
103
|
- LICENSE.txt
|
|
@@ -104,13 +105,20 @@ files:
|
|
|
104
105
|
- Rakefile
|
|
105
106
|
- VERSION
|
|
106
107
|
- bliss.gemspec
|
|
108
|
+
- complete_test.rb
|
|
109
|
+
- gzip_support.rb
|
|
107
110
|
- hash.rb
|
|
108
111
|
- http-machine.rb
|
|
109
112
|
- lib/bliss.rb
|
|
113
|
+
- lib/bliss/constraint.rb
|
|
114
|
+
- lib/bliss/encoding_error.rb
|
|
115
|
+
- lib/bliss/format.rb
|
|
110
116
|
- lib/bliss/parser.rb
|
|
111
117
|
- lib/bliss/parser_machine.rb
|
|
112
|
-
- lib/bliss/sax_parser.rb
|
|
113
118
|
- lib/hash_extension.rb
|
|
119
|
+
- spec.yml
|
|
120
|
+
- spec/format_spec.rb
|
|
121
|
+
- spec/spec_helper.rb
|
|
114
122
|
- test.rb
|
|
115
123
|
- test/helper.rb
|
|
116
124
|
- test/test_bliss.rb
|
|
@@ -129,7 +137,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
|
129
137
|
version: '0'
|
|
130
138
|
segments:
|
|
131
139
|
- 0
|
|
132
|
-
hash:
|
|
140
|
+
hash: 3727479071019105598
|
|
133
141
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
134
142
|
none: false
|
|
135
143
|
requirements:
|
|
@@ -138,7 +146,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
138
146
|
version: '0'
|
|
139
147
|
requirements: []
|
|
140
148
|
rubyforge_project:
|
|
141
|
-
rubygems_version: 1.8.
|
|
149
|
+
rubygems_version: 1.8.10
|
|
142
150
|
signing_key:
|
|
143
151
|
specification_version: 3
|
|
144
152
|
summary: streamed xml parsing tool
|
data/lib/bliss/sax_parser.rb
DELETED
|
@@ -1,122 +0,0 @@
|
|
|
1
|
-
module Bliss
|
|
2
|
-
class SaxParser < Nokogiri::XML::SAX::Document
|
|
3
|
-
def initialize
|
|
4
|
-
@depth = []
|
|
5
|
-
# @settings = {} # downcased
|
|
6
|
-
|
|
7
|
-
@root = nil
|
|
8
|
-
@nodes = {}
|
|
9
|
-
@current_node = {}
|
|
10
|
-
|
|
11
|
-
@on_root = nil
|
|
12
|
-
@on_tag_open = {}
|
|
13
|
-
@on_tag_close = {}
|
|
14
|
-
|
|
15
|
-
@closed = false
|
|
16
|
-
|
|
17
|
-
end
|
|
18
|
-
|
|
19
|
-
def on_root(&block)
|
|
20
|
-
@on_root = block
|
|
21
|
-
end
|
|
22
|
-
|
|
23
|
-
def on_tag_open(element, block)
|
|
24
|
-
@on_tag_open.merge!({element => block})
|
|
25
|
-
end
|
|
26
|
-
|
|
27
|
-
def on_tag_close(element, block)
|
|
28
|
-
@on_tag_close.merge!({element => block})
|
|
29
|
-
end
|
|
30
|
-
|
|
31
|
-
def close
|
|
32
|
-
@closed = true
|
|
33
|
-
end
|
|
34
|
-
|
|
35
|
-
def is_closed?
|
|
36
|
-
@closed
|
|
37
|
-
end
|
|
38
|
-
|
|
39
|
-
def start_element(element, attributes)
|
|
40
|
-
# element_transformation
|
|
41
|
-
|
|
42
|
-
if @root == nil
|
|
43
|
-
@root = element
|
|
44
|
-
if @on_root.is_a? Proc
|
|
45
|
-
@on_root.call(@root)
|
|
46
|
-
end
|
|
47
|
-
end
|
|
48
|
-
|
|
49
|
-
@depth.push(element) if @depth.last != element
|
|
50
|
-
|
|
51
|
-
if @on_tag_open.has_key? element
|
|
52
|
-
@on_tag_open[element].call(@depth)
|
|
53
|
-
end
|
|
54
|
-
|
|
55
|
-
current = @nodes.pair_at_chain(@depth)
|
|
56
|
-
|
|
57
|
-
value_at = @nodes.value_at_chain(@depth)
|
|
58
|
-
|
|
59
|
-
if current.is_a? Hash
|
|
60
|
-
if value_at.is_a? NilClass
|
|
61
|
-
current[element] = {}
|
|
62
|
-
elsif value_at.is_a? Hash
|
|
63
|
-
if current[element].is_a? Array
|
|
64
|
-
current[element].concat [{}]
|
|
65
|
-
else
|
|
66
|
-
current[element] = [current[element], {}]
|
|
67
|
-
#current = @nodes.pair_at_chain(@depth)
|
|
68
|
-
end
|
|
69
|
-
elsif value_at.is_a? Array
|
|
70
|
-
#puts @depth.inspect
|
|
71
|
-
#puts current[element].inspect
|
|
72
|
-
#puts current[element].inspect
|
|
73
|
-
end
|
|
74
|
-
elsif current.is_a? Array
|
|
75
|
-
end
|
|
76
|
-
|
|
77
|
-
@current_content = ''
|
|
78
|
-
end
|
|
79
|
-
|
|
80
|
-
def characters(string)
|
|
81
|
-
concat_content(string)
|
|
82
|
-
end
|
|
83
|
-
|
|
84
|
-
def cdata_block(string)
|
|
85
|
-
concat_content(string)
|
|
86
|
-
end
|
|
87
|
-
|
|
88
|
-
def end_element(element, attributes=[])
|
|
89
|
-
# element_transformation
|
|
90
|
-
|
|
91
|
-
current = @nodes.pair_at_chain(@depth)
|
|
92
|
-
value_at = @nodes.value_at_chain(@depth)
|
|
93
|
-
|
|
94
|
-
if value_at.is_a? Hash
|
|
95
|
-
current[element] = @current_content if @current_content.size > 0
|
|
96
|
-
elsif value_at.is_a? NilClass
|
|
97
|
-
if current.is_a? Array
|
|
98
|
-
current = current.last
|
|
99
|
-
current[element] = @current_content if @current_content.size > 0
|
|
100
|
-
end
|
|
101
|
-
end
|
|
102
|
-
@current_content = ''
|
|
103
|
-
|
|
104
|
-
if @on_tag_close.has_key? element
|
|
105
|
-
@on_tag_close[element].call(value_at)
|
|
106
|
-
end
|
|
107
|
-
|
|
108
|
-
@depth.pop if @depth.last == element
|
|
109
|
-
end
|
|
110
|
-
|
|
111
|
-
def concat_content(string)
|
|
112
|
-
string.strip!
|
|
113
|
-
if string
|
|
114
|
-
@current_content << string
|
|
115
|
-
end
|
|
116
|
-
end
|
|
117
|
-
|
|
118
|
-
def end_document
|
|
119
|
-
puts @nodes.inspect
|
|
120
|
-
end
|
|
121
|
-
end
|
|
122
|
-
end
|