blacklight_internet_archive 0.1.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +11 -0
- data/.rspec +3 -0
- data/.rubocop.yml +25 -0
- data/.travis.yml +7 -0
- data/Gemfile +6 -0
- data/LICENSE.txt +21 -0
- data/README.md +43 -0
- data/Rakefile +6 -0
- data/blacklight_internet_archive.gemspec +30 -0
- data/lib/blacklight_internet_archive.rb +23 -0
- data/lib/blacklight_internet_archive/blacklight_response.rb +6 -0
- data/lib/blacklight_internet_archive/client.rb +92 -0
- data/lib/blacklight_internet_archive/entity_processor.rb +135 -0
- data/lib/blacklight_internet_archive/hash_with_response.rb +9 -0
- data/lib/blacklight_internet_archive/internet_archive.rb +11 -0
- data/lib/blacklight_internet_archive/repository.rb +32 -0
- data/lib/blacklight_internet_archive/request.rb +44 -0
- data/lib/blacklight_internet_archive/response.rb +84 -0
- data/lib/blacklight_internet_archive/response_adapter.rb +59 -0
- data/lib/blacklight_internet_archive/version.rb +3 -0
- metadata +154 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 6a5310c53053a495a98c09dab7cf64d56a1c8e48
|
4
|
+
data.tar.gz: 16a8bd98a70c27fb9c0ec65777c40487c521b1df
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 11759e993dfa3dccceb7a20272313c1550a82f798b5636271fa872fabe9397ae4a45f28504b243ce621be395b6814b008829a131dd3bec0c73dbfb21e4a6c430
|
7
|
+
data.tar.gz: a18c00ed489997bdfbdb4853bb2c57a8b3a28535f0b108d8ccd2aa03b39d457a049bd283b59bdc46b745dd30e9ba34d0a66437b66818899b7db57bb05575c810
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.rubocop.yml
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
require: rubocop-rspec
|
2
|
+
|
3
|
+
AllCops:
|
4
|
+
DisplayCopNames: true
|
5
|
+
Exclude:
|
6
|
+
- "blacklight_internet_archive.gemspec"
|
7
|
+
|
8
|
+
Metrics/BlockLength:
|
9
|
+
Exclude:
|
10
|
+
- 'spec/**/*'
|
11
|
+
|
12
|
+
Metrics/LineLength:
|
13
|
+
Max: 200
|
14
|
+
|
15
|
+
Style/StringLiterals:
|
16
|
+
Enabled: false
|
17
|
+
|
18
|
+
Layout/IndentationConsistency:
|
19
|
+
EnforcedStyle: normal
|
20
|
+
|
21
|
+
Rails/OutputSafety:
|
22
|
+
Enabled: false
|
23
|
+
|
24
|
+
Style/Documentation:
|
25
|
+
Enabled: false
|
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2018 JackBlackLight
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,43 @@
|
|
1
|
+
# BlacklightInternetArchive
|
2
|
+
|
3
|
+
Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/blacklight_internet_archive`. To experiment with that code, run `bin/console` for an interactive prompt.
|
4
|
+
|
5
|
+
TODO: Delete this and the text above, and describe your gem
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'blacklight_internet_archive'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install blacklight_internet_archive
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
TODO: Write usage instructions here
|
26
|
+
|
27
|
+
## Development
|
28
|
+
|
29
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
30
|
+
|
31
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
32
|
+
|
33
|
+
## Contributing
|
34
|
+
|
35
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/blacklight_internet_archive. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
|
36
|
+
|
37
|
+
## License
|
38
|
+
|
39
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
40
|
+
|
41
|
+
## Code of Conduct
|
42
|
+
|
43
|
+
Everyone interacting in the BlacklightInternetArchive project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/blacklight_internet_archive/blob/master/CODE_OF_CONDUCT.md).
|
data/Rakefile
ADDED
@@ -0,0 +1,30 @@
|
|
1
|
+
|
2
|
+
lib = File.expand_path("../lib", __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require "blacklight_internet_archive/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "blacklight_internet_archive"
|
8
|
+
spec.version = BlacklightInternetArchive::VERSION
|
9
|
+
spec.authors = ["jd2148"]
|
10
|
+
spec.email = ["jd2148@columbia.edu"]
|
11
|
+
spec.summary = %q{Blacklight discovery interface for an Internet Archive collection.}
|
12
|
+
spec.license = "MIT"
|
13
|
+
|
14
|
+
|
15
|
+
# Specify which files should be added to the gem when it is released.
|
16
|
+
# The `git ls-files -z` loads the files in the RubyGem that have been added into git.
|
17
|
+
spec.files = Dir.chdir(File.expand_path('..', __FILE__)) do
|
18
|
+
`git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
19
|
+
end
|
20
|
+
spec.bindir = "exe"
|
21
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
22
|
+
spec.require_paths = ["lib"]
|
23
|
+
|
24
|
+
spec.add_development_dependency "bundler", "~> 1.16"
|
25
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
26
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
27
|
+
spec.add_development_dependency 'rubocop', '~> 0.50.0'
|
28
|
+
spec.add_development_dependency 'rubocop-rspec', '~> 1.18', '>= 1.18.0'
|
29
|
+
spec.add_development_dependency "blacklight", '~> 6.0'
|
30
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
require "blacklight_internet_archive/version"
|
2
|
+
|
3
|
+
module BlacklightInternetArchive
|
4
|
+
|
5
|
+
autoload :InternetArchive, 'blacklight_internet_archive/internet_archive'
|
6
|
+
autoload :Client, 'blacklight_internet_archive/client'
|
7
|
+
autoload :Repository, 'blacklight_internet_archive/repository'
|
8
|
+
autoload :Request, 'blacklight_internet_archive/request'
|
9
|
+
autoload :Response, 'blacklight_internet_archive/response'
|
10
|
+
autoload :ResponseAdapter, 'blacklight_internet_archive/response_adapter'
|
11
|
+
autoload :EntityProcessor, 'blacklight_internet_archive/entity_processor'
|
12
|
+
autoload :BlacklightResponse, 'blacklight_internet_archive/blacklight_response'
|
13
|
+
autoload :HashWithResponse, 'blacklight_internet_archive/hash_with_response'
|
14
|
+
|
15
|
+
def self.connect(args)
|
16
|
+
connection = args[:url]
|
17
|
+
opts = args[:opts]
|
18
|
+
|
19
|
+
Client.new connection, opts
|
20
|
+
end
|
21
|
+
|
22
|
+
|
23
|
+
end
|
@@ -0,0 +1,92 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'net/http'
|
4
|
+
|
5
|
+
module BlacklightInternetArchive
|
6
|
+
class Client
|
7
|
+
def initialize(connection_url, options = {})
|
8
|
+
@connection_url = connection_url
|
9
|
+
@options = options
|
10
|
+
end
|
11
|
+
|
12
|
+
# +execute_query+ is the main request method responsible for sending requests to the +connection+ object.
|
13
|
+
#
|
14
|
+
# "path" : A string value that represents the repository request handler (set url value in blacklight.yml)
|
15
|
+
# "opts" : A hash containing searh parameters
|
16
|
+
|
17
|
+
def execute_query(path, opts)
|
18
|
+
request_context = build_request path, opts
|
19
|
+
execute request_context
|
20
|
+
end
|
21
|
+
|
22
|
+
def execute(request_context)
|
23
|
+
uri_string = request_context[:params][:uri]
|
24
|
+
uri = URI.parse(uri_string)
|
25
|
+
|
26
|
+
res = Net::HTTP.get_response(uri)
|
27
|
+
if res.is_a?(Net::HTTPSuccess)
|
28
|
+
res_data = res.read_body
|
29
|
+
return if res_data.nil? || res_data.empty?
|
30
|
+
res_data_mod = BlacklightInternetArchive::ResponseAdapter.adapt_response(res_data, @connection_url)
|
31
|
+
BlacklightInternetArchive::HashWithResponse.new(request_context, res, res_data_mod)
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
# +build_request+ accepts a path and options hash
|
36
|
+
# +build_request+ sets up the uri/query string
|
37
|
+
# returns a hash with the following keys:
|
38
|
+
# :uri
|
39
|
+
# :path
|
40
|
+
# :query
|
41
|
+
|
42
|
+
def build_request(path, opts)
|
43
|
+
raise "path must be a string or symbol, not #{path.inspect}" unless [String, Symbol].include?(path.class)
|
44
|
+
path = "#{path}.json"
|
45
|
+
|
46
|
+
opts[:path] = path
|
47
|
+
query_opts = {}
|
48
|
+
query_opts['pageSize'] = '10'
|
49
|
+
if opts['rows']
|
50
|
+
query_opts['pageSize'] = opts['rows']
|
51
|
+
else
|
52
|
+
query_opts['pageSize'] = '10'
|
53
|
+
end
|
54
|
+
if opts['page']
|
55
|
+
query_opts['page'] = opts['page']
|
56
|
+
else
|
57
|
+
query_opts['page'] = '1'
|
58
|
+
end
|
59
|
+
if query_opts['page'].to_i < 2
|
60
|
+
opts[:start] = 0
|
61
|
+
else
|
62
|
+
opts[:start] = ((query_opts['page'].to_i - 1) * query_opts['pageSize'].to_i)
|
63
|
+
end
|
64
|
+
|
65
|
+
query_opts['q'] = ''
|
66
|
+
query_opts['q'] = CGI.escape(opts['q']) if opts['q']
|
67
|
+
|
68
|
+
facet_string = ''
|
69
|
+
if opts['f']
|
70
|
+
opts['f'].each do |k, v|
|
71
|
+
v.each do |fv|
|
72
|
+
fval = CGI.escape(fv)
|
73
|
+
facet_string = "#{facet_string}fc=#{k}%3A#{fval}&"
|
74
|
+
end
|
75
|
+
end
|
76
|
+
end
|
77
|
+
|
78
|
+
facet_string = facet_string.tr(' ', '+').chomp('&')
|
79
|
+
query = query_opts.to_query
|
80
|
+
query = "#{query}&#{facet_string}" if facet_string
|
81
|
+
|
82
|
+
opts[:query] = query
|
83
|
+
opts[:uri] = path.to_s + (query ? "?#{query}" : '')
|
84
|
+
|
85
|
+
opts[:rows] = 10 if opts[:rows].nil?
|
86
|
+
|
87
|
+
opts[:start] = 0 if opts[:start].nil?
|
88
|
+
|
89
|
+
{ :params => opts }
|
90
|
+
end
|
91
|
+
end
|
92
|
+
end
|
@@ -0,0 +1,135 @@
|
|
1
|
+
require 'active_support/core_ext/string/output_safety'
|
2
|
+
require 'cgi'
|
3
|
+
|
4
|
+
module BlacklightInternetArchive
|
5
|
+
# extract and convert individual results from response
|
6
|
+
class EntityProcessor
|
7
|
+
@metadata_fields = %w[meta_Creator meta_Coverage meta_Subject meta_Language meta_Collector meta_Title]
|
8
|
+
@date_fields = %w[firstCapture lastCapture]
|
9
|
+
@linkable_fields = { 'meta_Title' => 'allURL', 'url' => 'allURL', 'numCaptures' => 'allURL',
|
10
|
+
'numVideos' => 'seedVideosUrl' }
|
11
|
+
|
12
|
+
def self.run(response_json, base_url)
|
13
|
+
raise ArgumentError 'No entities in response.' unless response_json['results']['entities']
|
14
|
+
raise ArgumentError 'Base url required.' unless base_url
|
15
|
+
entities = response_json['results']['entities']
|
16
|
+
entities_clone = entities.clone
|
17
|
+
entities.each do |entity|
|
18
|
+
next unless entity['isSeed']
|
19
|
+
entities_clone[entities.index(entity)] = reformat_entity(entity, response_json['results']['searchedFacets'], base_url)
|
20
|
+
end
|
21
|
+
puts entities_clone.class
|
22
|
+
entities_clone
|
23
|
+
end
|
24
|
+
|
25
|
+
def self.reformat_entity(entity, searched_facets, base_url)
|
26
|
+
entity_clone = entity.clone
|
27
|
+
entity.each do |entity_key, entity_val|
|
28
|
+
if entity_key == 'metadata'
|
29
|
+
entity_clone = facet_link_metadata(entity_val, entity_clone, searched_facets)
|
30
|
+
end
|
31
|
+
entity_clone = set_date_fields(entity_clone, entity_key, entity_val)
|
32
|
+
entity_clone = set_linked_fields(entity_clone, base_url)
|
33
|
+
end
|
34
|
+
# this field is not under the metadata node and not handled by process_entities
|
35
|
+
entity_clone['linked_websiteGroup'] = link_faceted_results_data('websiteGroup', [entity['websiteGroup']], searched_facets)
|
36
|
+
entity_clone
|
37
|
+
end
|
38
|
+
|
39
|
+
def self.facet_link_metadata(entval, ent_clone, facet_info)
|
40
|
+
@metadata_fields.each do |k|
|
41
|
+
if entval[k]
|
42
|
+
ent_clone[k] = entval[k].map(&:html_safe)
|
43
|
+
ent_clone["linked_#{k}"] = link_faceted_results_data(k, entval[k], facet_info)
|
44
|
+
end
|
45
|
+
end
|
46
|
+
ent_clone
|
47
|
+
end
|
48
|
+
|
49
|
+
def self.set_date_fields(e_clone, ent, entval)
|
50
|
+
@date_fields.each do |d|
|
51
|
+
next unless ent == d
|
52
|
+
new_key = "#{d}_date"
|
53
|
+
next unless entval['formattedDate']
|
54
|
+
formatted_date = entval['formattedDate']
|
55
|
+
date_url = entval['waybackUrl']
|
56
|
+
date_link = make_link(formatted_date, date_url)
|
57
|
+
e_clone[new_key] = formatted_date
|
58
|
+
e_clone["linked_#{new_key}"] = date_link.html_safe
|
59
|
+
end
|
60
|
+
e_clone
|
61
|
+
end
|
62
|
+
|
63
|
+
def self.set_linked_fields(e_clone, base_url)
|
64
|
+
@linkable_fields.each do |l, l_url|
|
65
|
+
val = e_clone[l]
|
66
|
+
val_url = e_clone[l_url]
|
67
|
+
if val_url.start_with?('?')
|
68
|
+
val_url = "#{base_url}#{val_url}"
|
69
|
+
end
|
70
|
+
linked_val = make_link(val, val_url)
|
71
|
+
e_clone["linked_#{l}"] = linked_val
|
72
|
+
end
|
73
|
+
e_clone
|
74
|
+
end
|
75
|
+
|
76
|
+
def self.link_faceted_results_data(meta_field, meta_val, searched_facets)
|
77
|
+
link_facets = []
|
78
|
+
meta_val.each do |mv|
|
79
|
+
searched_facets.each do |sf|
|
80
|
+
next unless sf['id'] == meta_field
|
81
|
+
sf['results'].each do |ra|
|
82
|
+
if ra['name'] == mv
|
83
|
+
link_facets << make_link(ra['name'], convert_ia_facet_url(ra['addFacetURL']))
|
84
|
+
end
|
85
|
+
end
|
86
|
+
end
|
87
|
+
end
|
88
|
+
link_facets.map(&:html_safe)
|
89
|
+
end
|
90
|
+
|
91
|
+
# translate ia facet url into blacklight facet syntax
|
92
|
+
def self.convert_ia_facet_url(ia_facet_url)
|
93
|
+
ifu_hash = CGI.parse(ia_facet_url.tr('?', ''))
|
94
|
+
url_arrays = prepare_url_params(ifu_hash, [], [])
|
95
|
+
compose_url(url_arrays)
|
96
|
+
end
|
97
|
+
|
98
|
+
def self.prepare_url_params(facet_hash, facet_url_arr, new_url_arr)
|
99
|
+
facet_hash.each do |k, v|
|
100
|
+
if k == 'fc'
|
101
|
+
v.each do |v_fc|
|
102
|
+
facet_url_arr << convert_ia_facet_url_param(v_fc)
|
103
|
+
end
|
104
|
+
else
|
105
|
+
new_url_arr << "#{k}=#{v[0]}"
|
106
|
+
end
|
107
|
+
end
|
108
|
+
[new_url_arr, facet_url_arr]
|
109
|
+
end
|
110
|
+
|
111
|
+
def self.compose_url(url_arrays)
|
112
|
+
new_url = ''
|
113
|
+
url_arrays[0].each do |param_string|
|
114
|
+
new_url = if new_url == ''
|
115
|
+
"#{param_string}&"
|
116
|
+
else
|
117
|
+
"#{new_url}&#{param_string}&"
|
118
|
+
end
|
119
|
+
end
|
120
|
+
url_arrays[1].each do |fps|
|
121
|
+
new_url = "#{new_url}#{fps}&"
|
122
|
+
end
|
123
|
+
"?#{new_url.chomp('&')}"
|
124
|
+
end
|
125
|
+
|
126
|
+
def self.convert_ia_facet_url_param(value)
|
127
|
+
ifu_arr = value.split(':')
|
128
|
+
"f[#{ifu_arr[0]}][]=#{ifu_arr[1]}"
|
129
|
+
end
|
130
|
+
|
131
|
+
def self.make_link(value, url)
|
132
|
+
"<a href=\"#{url}\">#{value}</a>".html_safe
|
133
|
+
end
|
134
|
+
end
|
135
|
+
end
|
@@ -0,0 +1,32 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
require 'blacklight'
|
3
|
+
|
4
|
+
module BlacklightInternetArchive
|
5
|
+
class Repository < Blacklight::AbstractRepository
|
6
|
+
##
|
7
|
+
# Find a single document result by a known id
|
8
|
+
# @param [String] id document's unique key value
|
9
|
+
# @param [Hash] params additional query parameters
|
10
|
+
def find(id, params = {})
|
11
|
+
# response = send_and_receive id, params
|
12
|
+
# raise Blacklight::Exceptions::RecordNotFound if response.documents.empty?
|
13
|
+
# response
|
14
|
+
end
|
15
|
+
|
16
|
+
##
|
17
|
+
# Execute a search query against a search index
|
18
|
+
# @param [Hash] params query parameters
|
19
|
+
def search(builder)
|
20
|
+
send_and_receive connection_config[:url], builder.blacklight_params
|
21
|
+
end
|
22
|
+
|
23
|
+
def send_and_receive(path, search_params = {})
|
24
|
+
res = connection.execute_query(path, search_params)
|
25
|
+
blacklight_config.response_model.new(res, search_params)
|
26
|
+
end
|
27
|
+
|
28
|
+
def build_connection
|
29
|
+
BlacklightInternetArchive.connect(connection_config)
|
30
|
+
end
|
31
|
+
end
|
32
|
+
end
|
@@ -0,0 +1,44 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module BlacklightInternetArchive
|
4
|
+
class Request < ActiveSupport::HashWithIndifferentAccess
|
5
|
+
SINGULAR_KEYS = %w(facet fl q qt rows start spellcheck spellcheck.q sort per_page wt hl group defType)
|
6
|
+
ARRAY_KEYS = %w(facet.field facet.query facet.pivot fq hl.fl)
|
7
|
+
|
8
|
+
def initialize(constructor = {})
|
9
|
+
if constructor.is_a?(Hash)
|
10
|
+
super()
|
11
|
+
update(constructor)
|
12
|
+
else
|
13
|
+
super(constructor)
|
14
|
+
end
|
15
|
+
ARRAY_KEYS.each do |key|
|
16
|
+
self[key] ||= []
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
def append_filter_query(query)
|
21
|
+
self['fq'] << query
|
22
|
+
end
|
23
|
+
|
24
|
+
def append_facet_fields(values)
|
25
|
+
self['facet.field'] += Array(values)
|
26
|
+
end
|
27
|
+
|
28
|
+
def append_facet_query(values)
|
29
|
+
self['facet.query'] += Array(values)
|
30
|
+
end
|
31
|
+
|
32
|
+
def append_facet_pivot(query)
|
33
|
+
self['facet.pivot'] << query
|
34
|
+
end
|
35
|
+
|
36
|
+
def append_highlight_field(query)
|
37
|
+
self['hl.fl'] << query
|
38
|
+
end
|
39
|
+
|
40
|
+
def to_hash
|
41
|
+
reject { |key, value| ARRAY_KEYS.include?(key) && value.blank? }
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
@@ -0,0 +1,84 @@
|
|
1
|
+
module BlacklightInternetArchive::Response
|
2
|
+
|
3
|
+
def self.included(base)
|
4
|
+
unless base < Hash
|
5
|
+
raise ArgumentError, "InternetArchive::Response expects to included only in (sub)classes of Hash; got included in '#{base}' instead."
|
6
|
+
end
|
7
|
+
base.send(:attr_reader, :request, :response)
|
8
|
+
end
|
9
|
+
|
10
|
+
def initialize_response(request, response, result)
|
11
|
+
@request = request
|
12
|
+
@response = response
|
13
|
+
self.merge!(result)
|
14
|
+
if self['response'] && self['response']['docs'].is_a?(::Array)
|
15
|
+
docs = PaginatedDocSet.new(self['response']['docs'])
|
16
|
+
docs.per_page = request[:params]['rows']
|
17
|
+
docs.page_start = request[:params]['start']
|
18
|
+
docs.total = self['response']['numFound'].to_s.to_i
|
19
|
+
self['response']['docs'] = docs
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
def with_indifferent_access
|
24
|
+
if defined?(::BlacklightInternetArchive::HashWithIndifferentAccessWithResponse)
|
25
|
+
::BlacklightInternetArchive::HashWithIndifferentAccessWithResponse.new(request, response, self)
|
26
|
+
else
|
27
|
+
if defined?(ActiveSupport::HashWithIndifferentAccess)
|
28
|
+
BlacklightInternetArchive.const_set('HashWithIndifferentAccessWithResponse', Class.new(ActiveSupport::HashWithIndifferentAccess))
|
29
|
+
BlacklightInternetArchive::HashWithIndifferentAccessWithResponse.class_eval <<-eos
|
30
|
+
include BlacklightInternetArchive::Response
|
31
|
+
|
32
|
+
def initialize(request, response, result)
|
33
|
+
super()
|
34
|
+
initialize_response(request, response, result)
|
35
|
+
end
|
36
|
+
eos
|
37
|
+
::BlacklightInternetArchive::HashWithIndifferentAccessWithResponse.new(request, response, self)
|
38
|
+
else
|
39
|
+
raise RuntimeError, 'HashWithIndifferentAccess is not currently defined'
|
40
|
+
end
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
# A response module which gets mixed into the ['response']['docs'] array.
|
45
|
+
class PaginatedDocSet < ::Array
|
46
|
+
attr_accessor :page_start, :per_page, :page_total
|
47
|
+
if !(Object.const_defined?('RUBY_ENGINE') && Object::RUBY_ENGINE == 'rbx')
|
48
|
+
alias_method(:start, :page_start)
|
49
|
+
alias_method(:start=, :page_start=)
|
50
|
+
alias_method(:total, :page_total)
|
51
|
+
alias_method(:total=, :page_total=)
|
52
|
+
end
|
53
|
+
|
54
|
+
# Returns the current page calculated from 'rows' and 'start'
|
55
|
+
def current_page
|
56
|
+
return 1 if start < 1
|
57
|
+
per_page_normalized = per_page < 1 ? 1 : per_page
|
58
|
+
@current_page ||= (start / per_page_normalized).ceil + 1
|
59
|
+
end
|
60
|
+
|
61
|
+
# Calcuates the total pages from 'numFound' and 'rows'
|
62
|
+
def total_pages
|
63
|
+
@total_pages ||= per_page > 0 ? (total / per_page.to_f).ceil : 1
|
64
|
+
end
|
65
|
+
|
66
|
+
# returns the previous page number or 1
|
67
|
+
def previous_page
|
68
|
+
@previous_page ||= current_page > 1 ? current_page - 1 : 1
|
69
|
+
end
|
70
|
+
|
71
|
+
# returns the next page number or the last
|
72
|
+
def next_page
|
73
|
+
@next_page ||= current_page == total_pages ? total_pages : current_page + 1
|
74
|
+
end
|
75
|
+
|
76
|
+
def has_next?
|
77
|
+
current_page < total_pages
|
78
|
+
end
|
79
|
+
|
80
|
+
def has_previous?
|
81
|
+
current_page > 1
|
82
|
+
end
|
83
|
+
end
|
84
|
+
end
|
@@ -0,0 +1,59 @@
|
|
1
|
+
require 'json'
|
2
|
+
|
3
|
+
module BlacklightInternetArchive
|
4
|
+
class ResponseAdapter
|
5
|
+
def self.adapt_response(response_body, base_url)
|
6
|
+
response_body_string = convert_highlighting(response_body.to_s)
|
7
|
+
res_data_json = JSON.parse(response_body_string)
|
8
|
+
|
9
|
+
entities = res_data_json['results']['entities']
|
10
|
+
# processed_entities = process_entities(entities, res_data_json['results']['searchedFacets'], base_url)
|
11
|
+
# response_docs = { 'response' => { 'docs' => processed_entities } }
|
12
|
+
|
13
|
+
# response_docs = EntityProcessor.run(res_data_json, base_url)
|
14
|
+
response_docs = { 'response' => { 'docs' => EntityProcessor.run(res_data_json, base_url) } }
|
15
|
+
|
16
|
+
|
17
|
+
|
18
|
+
response_docs.merge!('facet_counts' => { 'facet_queries' => {},
|
19
|
+
'facet_fields' => reformat_facets(res_data_json), 'facet_dates' => {} })
|
20
|
+
set_paging_stats(response_docs, res_data_json)
|
21
|
+
response_docs
|
22
|
+
end
|
23
|
+
|
24
|
+
def self.convert_highlighting(response_string)
|
25
|
+
response_string.gsub!('$high%', "<span class='highlight'>")
|
26
|
+
response_string.gsub!('/$light%', '</span>')
|
27
|
+
response_string
|
28
|
+
end
|
29
|
+
|
30
|
+
|
31
|
+
def self.set_paging_stats(response_docs, res_data_json)
|
32
|
+
response_docs['response']['numFound'] = res_data_json['results']['totalResultCount']
|
33
|
+
response_docs['response']['page'] = res_data_json['pageParams']['page']
|
34
|
+
response_docs['response']['rows'] = res_data_json['pageParams']['pageSize']
|
35
|
+
response_docs
|
36
|
+
end
|
37
|
+
|
38
|
+
|
39
|
+
def self.reformat_facets(response_json)
|
40
|
+
facets_hash = {}
|
41
|
+
facets = response_json['results']['searchedFacets']
|
42
|
+
facets.each do |f|
|
43
|
+
key_name = f['id']
|
44
|
+
facets_hash[key_name] = reformat_item(f['results'])
|
45
|
+
end
|
46
|
+
facets_hash
|
47
|
+
end
|
48
|
+
|
49
|
+
def self.reformat_item(item_arr)
|
50
|
+
new_item_arr = []
|
51
|
+
item_arr.each do |item_hash|
|
52
|
+
new_item_arr << item_hash['name']
|
53
|
+
new_item_arr << item_hash['count']
|
54
|
+
end
|
55
|
+
new_item_arr
|
56
|
+
end
|
57
|
+
|
58
|
+
end
|
59
|
+
end
|
metadata
ADDED
@@ -0,0 +1,154 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: blacklight_internet_archive
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.2
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- jd2148
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2018-08-22 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.16'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.16'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '3.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '3.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rubocop
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 0.50.0
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: 0.50.0
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: rubocop-rspec
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '1.18'
|
76
|
+
- - ">="
|
77
|
+
- !ruby/object:Gem::Version
|
78
|
+
version: 1.18.0
|
79
|
+
type: :development
|
80
|
+
prerelease: false
|
81
|
+
version_requirements: !ruby/object:Gem::Requirement
|
82
|
+
requirements:
|
83
|
+
- - "~>"
|
84
|
+
- !ruby/object:Gem::Version
|
85
|
+
version: '1.18'
|
86
|
+
- - ">="
|
87
|
+
- !ruby/object:Gem::Version
|
88
|
+
version: 1.18.0
|
89
|
+
- !ruby/object:Gem::Dependency
|
90
|
+
name: blacklight
|
91
|
+
requirement: !ruby/object:Gem::Requirement
|
92
|
+
requirements:
|
93
|
+
- - "~>"
|
94
|
+
- !ruby/object:Gem::Version
|
95
|
+
version: '6.0'
|
96
|
+
type: :development
|
97
|
+
prerelease: false
|
98
|
+
version_requirements: !ruby/object:Gem::Requirement
|
99
|
+
requirements:
|
100
|
+
- - "~>"
|
101
|
+
- !ruby/object:Gem::Version
|
102
|
+
version: '6.0'
|
103
|
+
description:
|
104
|
+
email:
|
105
|
+
- jd2148@columbia.edu
|
106
|
+
executables: []
|
107
|
+
extensions: []
|
108
|
+
extra_rdoc_files: []
|
109
|
+
files:
|
110
|
+
- ".gitignore"
|
111
|
+
- ".rspec"
|
112
|
+
- ".rubocop.yml"
|
113
|
+
- ".travis.yml"
|
114
|
+
- Gemfile
|
115
|
+
- LICENSE.txt
|
116
|
+
- README.md
|
117
|
+
- Rakefile
|
118
|
+
- blacklight_internet_archive.gemspec
|
119
|
+
- lib/blacklight_internet_archive.rb
|
120
|
+
- lib/blacklight_internet_archive/blacklight_response.rb
|
121
|
+
- lib/blacklight_internet_archive/client.rb
|
122
|
+
- lib/blacklight_internet_archive/entity_processor.rb
|
123
|
+
- lib/blacklight_internet_archive/hash_with_response.rb
|
124
|
+
- lib/blacklight_internet_archive/internet_archive.rb
|
125
|
+
- lib/blacklight_internet_archive/repository.rb
|
126
|
+
- lib/blacklight_internet_archive/request.rb
|
127
|
+
- lib/blacklight_internet_archive/response.rb
|
128
|
+
- lib/blacklight_internet_archive/response_adapter.rb
|
129
|
+
- lib/blacklight_internet_archive/version.rb
|
130
|
+
homepage:
|
131
|
+
licenses:
|
132
|
+
- MIT
|
133
|
+
metadata: {}
|
134
|
+
post_install_message:
|
135
|
+
rdoc_options: []
|
136
|
+
require_paths:
|
137
|
+
- lib
|
138
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
139
|
+
requirements:
|
140
|
+
- - ">="
|
141
|
+
- !ruby/object:Gem::Version
|
142
|
+
version: '0'
|
143
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
144
|
+
requirements:
|
145
|
+
- - ">="
|
146
|
+
- !ruby/object:Gem::Version
|
147
|
+
version: '0'
|
148
|
+
requirements: []
|
149
|
+
rubyforge_project:
|
150
|
+
rubygems_version: 2.6.10
|
151
|
+
signing_key:
|
152
|
+
specification_version: 4
|
153
|
+
summary: Blacklight discovery interface for an Internet Archive collection.
|
154
|
+
test_files: []
|