arx 0.3.2 → 1.2.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +124 -0
- data/LICENSE +1 -1
- data/README.md +107 -27
- data/Rakefile +1 -1
- data/arx.gemspec +7 -5
- data/lib/arx.rb +19 -7
- data/lib/arx/categories.rb +30 -0
- data/lib/arx/cleaner.rb +46 -5
- data/lib/arx/entities/author.rb +40 -1
- data/lib/arx/entities/category.rb +38 -1
- data/lib/arx/entities/link.rb +1 -0
- data/lib/arx/entities/paper.rb +108 -20
- data/lib/arx/inspector.rb +2 -0
- data/lib/arx/query/query.rb +46 -36
- data/lib/arx/query/validate.rb +4 -1
- data/lib/arx/version.rb +3 -3
- metadata +51 -17
data/lib/arx/inspector.rb
CHANGED
@@ -2,6 +2,7 @@ module Arx
|
|
2
2
|
|
3
3
|
# Restricts +inspect+ to dump a whitelist of methods on an object.
|
4
4
|
# It will always provide `object_id` at a minimum.
|
5
|
+
#
|
5
6
|
# @private
|
6
7
|
module Inspector
|
7
8
|
|
@@ -24,6 +25,7 @@ module Arx
|
|
24
25
|
end
|
25
26
|
|
26
27
|
# Defines helper +inspector_fields+ instance variable & method, and +inspector+ instance method on the target object.
|
28
|
+
#
|
27
29
|
# @param [Object] source An arbitrary object (the object that +includes+ the +Inspector+ module).
|
28
30
|
def included(source)
|
29
31
|
inspected << source
|
data/lib/arx/query/query.rb
CHANGED
@@ -22,14 +22,8 @@ module Arx
|
|
22
22
|
and_not: 'ANDNOT'
|
23
23
|
}
|
24
24
|
|
25
|
-
# Logical connective method names.
|
26
|
-
CONNECTIVE_METHODS = {
|
27
|
-
'&': :and,
|
28
|
-
'!': :and_not,
|
29
|
-
'|': :or
|
30
|
-
}
|
31
|
-
|
32
25
|
# Supported fields for the search queries made to the arXiv search API.
|
26
|
+
#
|
33
27
|
# @see https://arxiv.org/help/prep arXiv metadata fields
|
34
28
|
# @see https://arxiv.org/help/api/user-manual#query_details arXiv user manual (query details)
|
35
29
|
FIELDS = {
|
@@ -73,35 +67,38 @@ module Arx
|
|
73
67
|
|
74
68
|
ids.flatten!
|
75
69
|
unless ids.empty?
|
76
|
-
ids.map! {|id| extract_id
|
77
|
-
Validate.ids ids
|
70
|
+
ids.map! {|id| Cleaner.extract_id(id, version: true)}
|
78
71
|
@query << "&#{PARAMS[:id_list]}=#{ids * ','}"
|
79
72
|
end
|
80
73
|
|
81
74
|
yield self if block_given?
|
82
75
|
end
|
83
76
|
|
84
|
-
# @!method
|
77
|
+
# @!method and
|
85
78
|
# Logical conjunction (+AND+) of subqueries.
|
79
|
+
#
|
86
80
|
# @see https://arxiv.org/help/api/user-manual#query_details arXiv user manual
|
87
81
|
# @return [self]
|
88
82
|
|
89
|
-
# @!method
|
83
|
+
# @!method and_not
|
90
84
|
# Logical negated conjunction (+ANDNOT+) of subqueries.
|
85
|
+
#
|
91
86
|
# @see https://arxiv.org/help/api/user-manual#query_details arXiv user manual
|
92
87
|
# @return [self]
|
93
88
|
|
94
|
-
# @!method
|
89
|
+
# @!method or
|
95
90
|
# Logical disjunction (+OR+) of subqueries.
|
91
|
+
#
|
96
92
|
# @see https://arxiv.org/help/api/user-manual#query_details arXiv user manual
|
97
93
|
# @return [self]
|
98
94
|
|
99
|
-
|
100
|
-
define_method(
|
95
|
+
CONNECTIVES.keys.each do |connective|
|
96
|
+
define_method(connective) { add_connective connective }
|
101
97
|
end
|
102
98
|
|
103
99
|
# @!method title(*values, exact: true, connective: :and)
|
104
100
|
# Search for papers by {https://arxiv.org/help/prep#title title}.
|
101
|
+
#
|
105
102
|
# @param values [Array<String>] Title(s) of papers to search for.
|
106
103
|
# @param exact [Boolean] Whether to search for an exact match of the title(s).
|
107
104
|
# @param connective [Symbol] The logical connective to use (see {CONNECTIVES}). Only applies if there are multiple values.
|
@@ -109,6 +106,7 @@ module Arx
|
|
109
106
|
|
110
107
|
# @!method author(*values, exact: true, connective: :and)
|
111
108
|
# Search for papers by {https://arxiv.org/help/prep#author author}.
|
109
|
+
#
|
112
110
|
# @param values [Array<String>] Author(s) of papers to search for.
|
113
111
|
# @param exact [Boolean] Whether to search for an exact match of the author's name(s).
|
114
112
|
# @param connective [Symbol] The logical connective to use (see {CONNECTIVES}). Only applies if there are multiple values.
|
@@ -116,6 +114,7 @@ module Arx
|
|
116
114
|
|
117
115
|
# @!method abstract(*values, exact: true, connective: :and)
|
118
116
|
# Search for papers by {https://arxiv.org/help/prep#abstract abstract}.
|
117
|
+
#
|
119
118
|
# @param values [Array<String>] Abstract(s) of papers to search for.
|
120
119
|
# @param exact [Boolean] Whether to search for an exact match of the abstract(s).
|
121
120
|
# @param connective [Symbol] The logical connective to use (see {CONNECTIVES}). Only applies if there are multiple values.
|
@@ -123,6 +122,7 @@ module Arx
|
|
123
122
|
|
124
123
|
# @!method comment(*values, exact: true, connective: :and)
|
125
124
|
# Search for papers by {https://arxiv.org/help/prep#comments comment}.
|
125
|
+
#
|
126
126
|
# @param values [Array<String>] Comment(s) of papers to search for.
|
127
127
|
# @param exact [Boolean] Whether to search for an exact match of the comment(s).
|
128
128
|
# @param connective [Symbol] The logical connective to use (see {CONNECTIVES}). Only applies if there are multiple values.
|
@@ -130,6 +130,7 @@ module Arx
|
|
130
130
|
|
131
131
|
# @!method journal(*values, exact: true, connective: :and)
|
132
132
|
# Search for papers by {https://arxiv.org/help/prep#journal journal reference}.
|
133
|
+
#
|
133
134
|
# @param values [Array<String>] Journal reference(s) of papers to search for.
|
134
135
|
# @param exact [Boolean] Whether to search for an exact match of the journal refernece(s).
|
135
136
|
# @param connective [Symbol] The logical connective to use (see {CONNECTIVES}). Only applies if there are multiple values.
|
@@ -137,18 +138,21 @@ module Arx
|
|
137
138
|
|
138
139
|
# @!method category(*values, connective: :and)
|
139
140
|
# Search for papers by {https://arxiv.org/help/prep#category category}.
|
141
|
+
#
|
140
142
|
# @param values [Array<String>] Category(s) of papers to search for.
|
141
143
|
# @param connective [Symbol] The logical connective to use (see {CONNECTIVES}). Only applies if there are multiple values.
|
142
144
|
# @return [self]
|
143
145
|
|
144
146
|
# @!method report(*values, connective: :and)
|
145
147
|
# Search for papers by {https://arxiv.org/help/prep#report report number}.
|
148
|
+
#
|
146
149
|
# @param values [Array<String>] Report number(s) of papers to search for.
|
147
150
|
# @param connective [Symbol] The logical connective to use (see {CONNECTIVES}). Only applies if there are multiple values.
|
148
151
|
# @return [self]
|
149
152
|
|
150
153
|
# @!method all(*values, exact: true, connective: :and)
|
151
154
|
# Search for papers by all fields (see {FIELDS}).
|
155
|
+
#
|
152
156
|
# @param values [Array<String>] Field value(s) of papers to search for.
|
153
157
|
# @param exact [Boolean] Whether to search for an exact match of the comment(s).
|
154
158
|
# @param connective [Symbol] The logical connective to use (see {CONNECTIVES}). Only applies if there are multiple values.
|
@@ -181,6 +185,20 @@ module Arx
|
|
181
185
|
end
|
182
186
|
end
|
183
187
|
|
188
|
+
# Creates a nested subquery (grouped statements with parentheses).
|
189
|
+
#
|
190
|
+
# @return [self]
|
191
|
+
def group
|
192
|
+
add_connective :and unless end_with_connective?
|
193
|
+
@query << (search_query? ? '+' : "&#{PARAMS[:search_query]}=")
|
194
|
+
|
195
|
+
@query << CGI.escape('(')
|
196
|
+
yield
|
197
|
+
@query << CGI.escape(')')
|
198
|
+
|
199
|
+
self
|
200
|
+
end
|
201
|
+
|
184
202
|
# Returns the query string.
|
185
203
|
#
|
186
204
|
# @return [String]
|
@@ -196,8 +214,9 @@ module Arx
|
|
196
214
|
# @param connective [Symbol] The symbol of the logical connective to add.
|
197
215
|
# @return [self]
|
198
216
|
def add_connective(connective)
|
199
|
-
|
200
|
-
|
217
|
+
if search_query?
|
218
|
+
@query << "+#{CONNECTIVES[connective]}" unless end_with_connective? || start_of_group?
|
219
|
+
end
|
201
220
|
self
|
202
221
|
end
|
203
222
|
|
@@ -205,13 +224,10 @@ module Arx
|
|
205
224
|
#
|
206
225
|
# @param subquery [String] The subquery to add.
|
207
226
|
def add_subquery(subquery)
|
227
|
+
add_connective :and unless end_with_connective?
|
228
|
+
|
208
229
|
if search_query?
|
209
|
-
|
210
|
-
@query << "+#{subquery}"
|
211
|
-
else
|
212
|
-
add_connective :and
|
213
|
-
@query << "+#{subquery}"
|
214
|
-
end
|
230
|
+
@query << (start_of_group? ? "#{subquery}" : "+#{subquery}")
|
215
231
|
else
|
216
232
|
@query << "&#{PARAMS[:search_query]}=#{subquery}"
|
217
233
|
end
|
@@ -229,10 +245,17 @@ module Arx
|
|
229
245
|
#
|
230
246
|
# @see CONNECTIVES
|
231
247
|
# @return [Boolean]
|
232
|
-
def
|
248
|
+
def end_with_connective?
|
233
249
|
CONNECTIVES.values.any? &@query.method(:end_with?)
|
234
250
|
end
|
235
251
|
|
252
|
+
# Whether the query string ends in a start-of-group character '('.
|
253
|
+
#
|
254
|
+
# @return [Boolean]
|
255
|
+
def start_of_group?
|
256
|
+
@query.end_with? CGI.escape('(')
|
257
|
+
end
|
258
|
+
|
236
259
|
# Parenthesizes a string with CGI-escaped parentheses.
|
237
260
|
#
|
238
261
|
# @param string [String] The string to parenthesize.
|
@@ -248,18 +271,5 @@ module Arx
|
|
248
271
|
def enquote(string)
|
249
272
|
CGI.escape("\"") + string + CGI.escape("\"")
|
250
273
|
end
|
251
|
-
|
252
|
-
# Attempt to extract an ID from an arXiv URL.
|
253
|
-
#
|
254
|
-
# @param url [String] The URL to extract the ID from.
|
255
|
-
# @return [String] The extracted ID if successful, otherwise the original string.
|
256
|
-
def extract_id(url)
|
257
|
-
prefix = %r"^(https?\:\/\/)?(www.)?arxiv\.org\/abs\/"
|
258
|
-
if %r"#{prefix}.*$".match? url
|
259
|
-
url.sub(prefix, '').sub(%r"\/$", '')
|
260
|
-
else
|
261
|
-
url
|
262
|
-
end
|
263
|
-
end
|
264
274
|
end
|
265
275
|
end
|
data/lib/arx/query/validate.rb
CHANGED
@@ -1,6 +1,7 @@
|
|
1
1
|
module Arx
|
2
2
|
|
3
3
|
# Validations for arXiv search query fields and identifier schemes.
|
4
|
+
#
|
4
5
|
# @private
|
5
6
|
module Validate
|
6
7
|
class << self
|
@@ -94,7 +95,9 @@ module Arx
|
|
94
95
|
# @see NEW_IDENTIFIER_FORMAT
|
95
96
|
# @see OLD_IDENTIFIER_FORMAT
|
96
97
|
def id?(id)
|
97
|
-
NEW_IDENTIFIER_FORMAT.match?
|
98
|
+
return true if NEW_IDENTIFIER_FORMAT.match? id
|
99
|
+
return true if OLD_IDENTIFIER_FORMAT.match?(id) && Arx::CATEGORIES.keys.include?(id.split('/').first)
|
100
|
+
false
|
98
101
|
end
|
99
102
|
end
|
100
103
|
end
|
data/lib/arx/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: arx
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version:
|
4
|
+
version: 1.2.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Edwin Onuonga
|
8
|
-
autorequire:
|
8
|
+
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2021-01-26 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: nokogiri
|
@@ -42,44 +42,44 @@ dependencies:
|
|
42
42
|
name: bundler
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
|
-
- - "
|
45
|
+
- - ">="
|
46
46
|
- !ruby/object:Gem::Version
|
47
|
-
version: '
|
47
|
+
version: '0'
|
48
48
|
type: :development
|
49
49
|
prerelease: false
|
50
50
|
version_requirements: !ruby/object:Gem::Requirement
|
51
51
|
requirements:
|
52
|
-
- - "
|
52
|
+
- - ">="
|
53
53
|
- !ruby/object:Gem::Version
|
54
|
-
version: '
|
54
|
+
version: '0'
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
56
|
name: rake
|
57
57
|
requirement: !ruby/object:Gem::Requirement
|
58
58
|
requirements:
|
59
59
|
- - "~>"
|
60
60
|
- !ruby/object:Gem::Version
|
61
|
-
version: '
|
61
|
+
version: '13.0'
|
62
62
|
type: :development
|
63
63
|
prerelease: false
|
64
64
|
version_requirements: !ruby/object:Gem::Requirement
|
65
65
|
requirements:
|
66
66
|
- - "~>"
|
67
67
|
- !ruby/object:Gem::Version
|
68
|
-
version: '
|
68
|
+
version: '13.0'
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: thor
|
71
71
|
requirement: !ruby/object:Gem::Requirement
|
72
72
|
requirements:
|
73
73
|
- - "~>"
|
74
74
|
- !ruby/object:Gem::Version
|
75
|
-
version:
|
75
|
+
version: 0.20.3
|
76
76
|
type: :development
|
77
77
|
prerelease: false
|
78
78
|
version_requirements: !ruby/object:Gem::Requirement
|
79
79
|
requirements:
|
80
80
|
- - "~>"
|
81
81
|
- !ruby/object:Gem::Version
|
82
|
-
version:
|
82
|
+
version: 0.20.3
|
83
83
|
- !ruby/object:Gem::Dependency
|
84
84
|
name: rspec
|
85
85
|
requirement: !ruby/object:Gem::Requirement
|
@@ -94,9 +94,43 @@ dependencies:
|
|
94
94
|
- - "~>"
|
95
95
|
- !ruby/object:Gem::Version
|
96
96
|
version: '3.7'
|
97
|
-
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: coveralls
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - '='
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: 0.8.23
|
104
|
+
type: :development
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - '='
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: 0.8.23
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: yard
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - "~>"
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '0.9'
|
118
|
+
- - ">="
|
119
|
+
- !ruby/object:Gem::Version
|
120
|
+
version: 0.9.10
|
121
|
+
type: :development
|
122
|
+
prerelease: false
|
123
|
+
version_requirements: !ruby/object:Gem::Requirement
|
124
|
+
requirements:
|
125
|
+
- - "~>"
|
126
|
+
- !ruby/object:Gem::Version
|
127
|
+
version: '0.9'
|
128
|
+
- - ">="
|
129
|
+
- !ruby/object:Gem::Version
|
130
|
+
version: 0.9.10
|
131
|
+
description:
|
98
132
|
email:
|
99
|
-
- ed@
|
133
|
+
- ed@eonu.net
|
100
134
|
executables: []
|
101
135
|
extensions: []
|
102
136
|
extra_rdoc_files: []
|
@@ -128,13 +162,13 @@ metadata:
|
|
128
162
|
documentation_uri: https://www.rubydoc.info/github/eonu/arx/master/toplevel
|
129
163
|
bug_tracker_uri: https://github.com/eonu/arx/issues
|
130
164
|
changelog_uri: https://github.com/eonu/arx/blob/master/CHANGELOG.md
|
131
|
-
post_install_message:
|
165
|
+
post_install_message:
|
132
166
|
rdoc_options: []
|
133
167
|
require_paths:
|
134
168
|
- lib
|
135
169
|
required_ruby_version: !ruby/object:Gem::Requirement
|
136
170
|
requirements:
|
137
|
-
- - "
|
171
|
+
- - ">="
|
138
172
|
- !ruby/object:Gem::Version
|
139
173
|
version: '2.5'
|
140
174
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
@@ -143,8 +177,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
143
177
|
- !ruby/object:Gem::Version
|
144
178
|
version: '0'
|
145
179
|
requirements: []
|
146
|
-
rubygems_version: 3.
|
147
|
-
signing_key:
|
180
|
+
rubygems_version: 3.1.2
|
181
|
+
signing_key:
|
148
182
|
specification_version: 4
|
149
183
|
summary: A Ruby interface for querying academic papers on the arXiv search API.
|
150
184
|
test_files: []
|