wikidata-diff-analyzer 0.1.1 → 2.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +8 -0
- data/Gemfile +0 -2
- data/README.md +268 -105
- data/lib/wikidata/diff/alias_analyzer.rb +69 -52
- data/lib/wikidata/diff/api.rb +31 -18
- data/lib/wikidata/diff/claim_analyzer.rb +94 -211
- data/lib/wikidata/diff/comment_analyzer.rb +49 -0
- data/lib/wikidata/diff/description_analyzer.rb +57 -35
- data/lib/wikidata/diff/form_analyzer.rb +67 -0
- data/lib/wikidata/diff/gloss_analyzer.rb +71 -0
- data/lib/wikidata/diff/inside_claim_analyzer.rb +84 -0
- data/lib/wikidata/diff/label_analyzer.rb +63 -41
- data/lib/wikidata/diff/large_batches_analyzer.rb +39 -24
- data/lib/wikidata/diff/lemma_analyzer.rb +70 -0
- data/lib/wikidata/diff/qualifier_analyzer.rb +83 -0
- data/lib/wikidata/diff/reference_analyzer.rb +49 -0
- data/lib/wikidata/diff/representation_analyzer.rb +71 -0
- data/lib/wikidata/diff/revision_analyzer.rb +153 -37
- data/lib/wikidata/diff/sense_analyzer.rb +106 -0
- data/lib/wikidata/diff/sitelink_analyzer.rb +3 -7
- data/lib/wikidata/diff/total.rb +31 -0
- data/lib/wikidata-diff-analyzer/version.rb +5 -0
- data/lib/{wikidata/diff/analyzer.rb → wikidata-diff-analyzer.rb} +36 -21
- data/wikidata-diff-analyzer.gemspec +14 -8
- metadata +71 -9
- data/CODE_OF_CONDUCT.md +0 -84
- data/Gemfile.lock +0 -81
- data/lib/wikidata/diff/analyzer/version.rb +0 -9
- data/lib/wikidata/diff/mediawiki_login.rb +0 -12
- data/sig/wikidata/diff/analyzer.rbs +0 -8
@@ -3,48 +3,164 @@ require_relative 'alias_analyzer'
|
|
3
3
|
require_relative 'label_analyzer'
|
4
4
|
require_relative 'description_analyzer'
|
5
5
|
require_relative 'sitelink_analyzer'
|
6
|
+
require_relative 'comment_analyzer'
|
7
|
+
require_relative 'form_analyzer'
|
8
|
+
require_relative 'sense_analyzer'
|
9
|
+
require_relative 'lemma_analyzer'
|
10
|
+
|
6
11
|
|
7
12
|
class RevisionAnalyzer
|
13
|
+
CLAIM_TYPES = [:added_claims, :removed_claims, :changed_claims,:added_references, :removed_references, :changed_references,:added_qualifiers, :removed_qualifiers, :changed_qualifiers].freeze
|
14
|
+
ALIAS_TYPES = [:added_aliases, :removed_aliases, :changed_aliases].freeze
|
15
|
+
LABEL_TYPES = [:added_labels, :removed_labels, :changed_labels].freeze
|
16
|
+
DESCRIPTION_TYPES = [:added_descriptions, :removed_descriptions, :changed_descriptions].freeze
|
17
|
+
SITELINK_TYPES = [:added_sitelinks, :removed_sitelinks, :changed_sitelinks].freeze
|
18
|
+
COMMENT_TYPES = [:merge_to, :merge_from, :redirect, :undo, :restore, :clear_item].freeze
|
19
|
+
LEMMA_TYPES = [:added_lemmas, :removed_lemmas, :changed_lemmas].freeze
|
20
|
+
FORM_TYPES = [:added_forms, :removed_forms, :changed_forms, :added_representations, :removed_representations, :changed_representations, :added_formclaims, :removed_formclaims, :changed_formclaims].freeze
|
21
|
+
SENSE_TYPES = [:added_senses, :removed_senses, :changed_senses, :added_glosses, :removed_glosses, :changed_glosses, :added_senseclaims, :removed_senseclaims, :changed_senseclaims].freeze
|
22
|
+
NOT_IN_ITEM = [:create_lexeme, :create_property, :added_lemmas, :removed_lemmas, :changed_lemmas, :added_forms, :removed_forms, :changed_forms, :added_senses, :removed_senses, :changed_senses, :added_representations, :removed_representations, :changed_representations, :added_glosses, :removed_glosses, :changed_glosses, :added_formclaims, :removed_formclaims, :changed_formclaims, :added_senseclaims, :removed_senseclaims, :changed_senseclaims].freeze
|
23
|
+
NOT_IN_PROPERTY = [:create_lexeme, :create_item, :added_sitelinks, :removed_sitelinks, :changed_sitelinks, :added_lemmas, :removed_lemmas, :changed_lemmas, :added_forms, :removed_forms, :changed_forms, :added_senses, :removed_senses, :changed_senses, :added_representations, :removed_representations, :changed_representations, :added_glosses, :removed_glosses, :changed_glosses, :added_formclaims, :removed_formclaims, :changed_formclaims, :added_senseclaims, :removed_senseclaims, :changed_senseclaims].freeze
|
24
|
+
NOT_IN_LEXEME = [:create_item, :create_property, :added_sitelinks, :changed_sitelinks, :removed_sitelinks, :added_aliases, :changed_aliases, :removed_aliases, :added_labels, :changed_labels, :removed_labels, :added_descriptions, :changed_descriptions, :removed_descriptions].freeze
|
25
|
+
|
8
26
|
# This method takes two revisions as input and returns the differences between them.
|
9
|
-
def self.analyze_diff(
|
27
|
+
def self.analyze_diff(revision_data)
|
28
|
+
model = revision_data[:model]
|
10
29
|
diff = {}
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
diff
|
19
|
-
|
20
|
-
|
21
|
-
|
30
|
+
if model == 'wikibase-item'
|
31
|
+
item(diff, revision_data)
|
32
|
+
elsif model == 'wikibase-property'
|
33
|
+
property(diff, revision_data)
|
34
|
+
elsif model == 'wikibase-lexeme'
|
35
|
+
lexeme(diff, revision_data)
|
36
|
+
end
|
37
|
+
diff
|
38
|
+
end
|
39
|
+
|
40
|
+
def self.item(diff, revision_data)
|
41
|
+
current_content = revision_data[:current_content]
|
42
|
+
parent_content = revision_data[:parent_content]
|
43
|
+
comment = revision_data[:comment]
|
44
|
+
|
45
|
+
|
46
|
+
claim_diff = ClaimAnalyzer.isolate_claims_differences(current_content, parent_content)
|
47
|
+
CLAIM_TYPES.each do |change_type|
|
48
|
+
diff[change_type] = claim_diff[change_type].length
|
49
|
+
end
|
50
|
+
|
51
|
+
alias_diff = AliasAnalyzer.isolate_aliases_differences(current_content, parent_content)
|
52
|
+
ALIAS_TYPES.each do |change_type|
|
53
|
+
diff[change_type] = alias_diff[change_type].length
|
54
|
+
end
|
55
|
+
|
56
|
+
# Calculate label differences
|
57
|
+
label_diff = LabelAnalyzer.isolate_labels_differences(current_content, parent_content)
|
58
|
+
LABEL_TYPES.each do |change_type|
|
59
|
+
diff[change_type] = label_diff[change_type].length
|
60
|
+
end
|
61
|
+
|
62
|
+
# Calculate description differences
|
63
|
+
description_diff = DescriptionAnalyzer.isolate_descriptions_differences(current_content, parent_content)
|
64
|
+
DESCRIPTION_TYPES.each do |change_type|
|
65
|
+
diff[change_type] = description_diff[change_type].length
|
66
|
+
end
|
67
|
+
|
68
|
+
# Calculate sitelink differences
|
69
|
+
sitelink_diff = SitelinkAnalyzer.isolate_sitelinks_differences(current_content, parent_content)
|
70
|
+
SITELINK_TYPES.each do |change_type|
|
71
|
+
diff[change_type] = sitelink_diff[change_type].length
|
72
|
+
end
|
73
|
+
|
74
|
+
phrases = CommentAnalyzer.isolate_comment_differences(comment)
|
75
|
+
COMMENT_TYPES.each do |change_type|
|
76
|
+
diff[change_type] = phrases[change_type]
|
77
|
+
end
|
78
|
+
|
79
|
+
NOT_IN_ITEM.each do |change_type|
|
80
|
+
diff[change_type] = 0
|
81
|
+
end
|
82
|
+
|
83
|
+
diff[:create_item] = phrases[:create_item]
|
84
|
+
|
85
|
+
diff
|
86
|
+
end
|
87
|
+
|
88
|
+
def self.property(diff, revision_data)
|
89
|
+
current_content = revision_data[:current_content]
|
90
|
+
parent_content = revision_data[:parent_content]
|
91
|
+
comment = revision_data[:comment]
|
92
|
+
|
93
|
+
claim_diff = ClaimAnalyzer.isolate_claims_differences(current_content, parent_content)
|
94
|
+
CLAIM_TYPES.each do |change_type|
|
95
|
+
diff[change_type] = claim_diff[change_type].length
|
96
|
+
end
|
97
|
+
|
98
|
+
alias_diff = AliasAnalyzer.isolate_aliases_differences(current_content, parent_content)
|
99
|
+
ALIAS_TYPES.each do |change_type|
|
100
|
+
diff[change_type] = alias_diff[change_type].length
|
101
|
+
end
|
102
|
+
|
103
|
+
# Calculate label differences
|
104
|
+
label_diff = LabelAnalyzer.isolate_labels_differences(current_content, parent_content)
|
105
|
+
|
106
|
+
LABEL_TYPES.each do |change_type|
|
107
|
+
diff[change_type] = label_diff[change_type].length
|
108
|
+
end
|
109
|
+
|
110
|
+
# Calculate description differences
|
111
|
+
description_diff = DescriptionAnalyzer.isolate_descriptions_differences(current_content, parent_content)
|
112
|
+
DESCRIPTION_TYPES.each do |change_type|
|
113
|
+
diff[change_type] = description_diff[change_type].length
|
114
|
+
end
|
115
|
+
|
116
|
+
|
117
|
+
phrases = CommentAnalyzer.isolate_comment_differences(comment)
|
118
|
+
COMMENT_TYPES.each do |change_type|
|
119
|
+
diff[change_type] = phrases[change_type]
|
120
|
+
end
|
121
|
+
|
122
|
+
diff[:create_property] = phrases[:create_item]
|
123
|
+
|
124
|
+
NOT_IN_PROPERTY.each do |change_type|
|
125
|
+
diff[change_type] = 0
|
126
|
+
end
|
127
|
+
end
|
128
|
+
|
129
|
+
def self.lexeme(diff, revision_data)
|
130
|
+
current_content = revision_data[:current_content]
|
131
|
+
parent_content = revision_data[:parent_content]
|
132
|
+
comment = revision_data[:comment]
|
22
133
|
|
23
|
-
|
24
|
-
|
25
|
-
diff[
|
26
|
-
|
27
|
-
diff[:changed_aliases] = alias_diff[:changed].length
|
28
|
-
|
29
|
-
|
30
|
-
# Calculate label differences
|
31
|
-
label_diff = LabelAnalyzer.isolate_labels_differences(current_content, parent_content)
|
32
|
-
diff[:added_labels] = label_diff[:added].length
|
33
|
-
diff[:removed_labels] = label_diff[:removed].length
|
34
|
-
diff[:changed_labels] = label_diff[:changed].length
|
35
|
-
|
36
|
-
# Calculate description differences
|
37
|
-
description_diff = DescriptionAnalyzer.isolate_descriptions_differences(current_content, parent_content)
|
38
|
-
diff[:added_descriptions] = description_diff[:added].length
|
39
|
-
diff[:removed_descriptions] = description_diff[:removed].length
|
40
|
-
diff[:changed_descriptions] = description_diff[:changed].length
|
41
|
-
|
42
|
-
# Calculate sitelink differences
|
43
|
-
sitelink_diff = SitelinkAnalyzer.isolate_sitelinks_differences(current_content, parent_content)
|
44
|
-
diff[:added_sitelinks] = sitelink_diff[:added].length
|
45
|
-
diff[:removed_sitelinks] = sitelink_diff[:removed].length
|
46
|
-
diff[:changed_sitelinks] = sitelink_diff[:changed].length
|
134
|
+
claim_diff = ClaimAnalyzer.isolate_claims_differences(current_content, parent_content)
|
135
|
+
CLAIM_TYPES.each do |change_type|
|
136
|
+
diff[change_type] = claim_diff[change_type].length
|
137
|
+
end
|
47
138
|
|
48
|
-
|
139
|
+
forms_diff = FormAnalyzer.isolate_forms_differences(current_content, parent_content)
|
140
|
+
FORM_TYPES.each do |change_type|
|
141
|
+
diff[change_type] = forms_diff[change_type].length
|
142
|
+
end
|
143
|
+
|
144
|
+
# Calculate label differences
|
145
|
+
lemmas_diff = LemmaAnalyzer.isolate_lemmas_differences(current_content, parent_content)
|
146
|
+
LEMMA_TYPES.each do |change_type|
|
147
|
+
diff[change_type] = lemmas_diff[change_type].length
|
148
|
+
end
|
149
|
+
|
150
|
+
# Calculate description differences
|
151
|
+
senses_diff = SenseAnalyzer.isolate_senses_differences(current_content, parent_content)
|
152
|
+
SENSE_TYPES.each do |change_type|
|
153
|
+
diff[change_type] = senses_diff[change_type].length
|
154
|
+
end
|
155
|
+
|
156
|
+
phrases = CommentAnalyzer.isolate_comment_differences(comment)
|
157
|
+
COMMENT_TYPES.each do |change_type|
|
158
|
+
diff[change_type] = phrases[change_type]
|
159
|
+
end
|
160
|
+
|
161
|
+
NOT_IN_LEXEME.each do |change_type|
|
162
|
+
diff[change_type] = 0
|
163
|
+
end
|
164
|
+
diff[:create_lexeme] = phrases[:create_item]
|
49
165
|
end
|
50
166
|
end
|
@@ -0,0 +1,106 @@
|
|
1
|
+
require_relative 'gloss_analyzer'
|
2
|
+
require_relative 'inside_claim_analyzer'
|
3
|
+
class SenseAnalyzer
|
4
|
+
def self.isolate_senses_differences(current_content, parent_content)
|
5
|
+
# Initialize empty arrays to store the added, removed, and changed claims
|
6
|
+
added_senses = []
|
7
|
+
removed_senses = []
|
8
|
+
changed_senses = []
|
9
|
+
added_glosses = []
|
10
|
+
removed_glosses = []
|
11
|
+
changed_glosses = []
|
12
|
+
added_senseclaims = []
|
13
|
+
removed_senseclaims = []
|
14
|
+
changed_senseclaims = []
|
15
|
+
|
16
|
+
current_content_senses = current_content["senses"] if current_content
|
17
|
+
parent_content_senses = parent_content["senses"] if parent_content
|
18
|
+
|
19
|
+
if !current_content_senses.is_a?(Array) || !parent_content_senses.is_a?(Array)
|
20
|
+
return {
|
21
|
+
added_senses: added_senses,
|
22
|
+
removed_senses: removed_senses,
|
23
|
+
changed_senses: changed_senses,
|
24
|
+
added_glosses: added_glosses,
|
25
|
+
removed_glosses: removed_glosses,
|
26
|
+
changed_glosses: changed_glosses,
|
27
|
+
added_senseclaims: added_senseclaims,
|
28
|
+
removed_senseclaims: removed_senseclaims,
|
29
|
+
changed_senseclaims: changed_senseclaims
|
30
|
+
}
|
31
|
+
end
|
32
|
+
|
33
|
+
current_content_senses = current_content["senses"] || []
|
34
|
+
parent_content_senses = parent_content["senses"] || []
|
35
|
+
|
36
|
+
# if parentid is 0, add all current claims as added claims and return it
|
37
|
+
if parent_content.nil?
|
38
|
+
current_content_senses.each_with_index do |current_claim, index|
|
39
|
+
added_senses << { index: index }
|
40
|
+
glosses = GlossAnalyzer.isolate_gloss_differences(current_claim, nil)
|
41
|
+
added_glosses += glosses[:added]
|
42
|
+
removed_glosses += glosses[:removed]
|
43
|
+
changed_glosses += glosses[:changed]
|
44
|
+
senseclaims = InsideClaimAnalyzer.isolate_inside_claim_differences(current_claim, nil)
|
45
|
+
added_senseclaims += senseclaims[:added]
|
46
|
+
removed_senseclaims += senseclaims[:removed]
|
47
|
+
changed_senseclaims += senseclaims[:changed]
|
48
|
+
end
|
49
|
+
else
|
50
|
+
current_content_senses.each_with_index do |current_claim, index|
|
51
|
+
parent_claim = parent_content_senses[index]
|
52
|
+
if parent_claim.nil?
|
53
|
+
# Claim was added
|
54
|
+
added_senses << { index: index }
|
55
|
+
glosses = GlossAnalyzer.isolate_gloss_differences(current_claim, parent_claim)
|
56
|
+
added_glosses += glosses[:added]
|
57
|
+
removed_glosses += glosses[:removed]
|
58
|
+
changed_glosses += glosses[:changed]
|
59
|
+
senseclaims = InsideClaimAnalyzer.isolate_inside_claim_differences(current_claim, nil)
|
60
|
+
added_senseclaims += senseclaims[:added]
|
61
|
+
removed_senseclaims += senseclaims[:removed]
|
62
|
+
changed_senseclaims += senseclaims[:changed]
|
63
|
+
elsif current_claim != parent_claim
|
64
|
+
# Claim was changed
|
65
|
+
changed_senses << { index: index }
|
66
|
+
glosses = GlossAnalyzer.isolate_gloss_differences(current_claim, parent_claim)
|
67
|
+
added_glosses += glosses[:added]
|
68
|
+
removed_glosses += glosses[:removed]
|
69
|
+
changed_glosses += glosses[:changed]
|
70
|
+
senseclaims = InsideClaimAnalyzer.isolate_inside_claim_differences(current_claim, nil)
|
71
|
+
added_senseclaims += senseclaims[:added]
|
72
|
+
removed_senseclaims += senseclaims[:removed]
|
73
|
+
changed_senseclaims += senseclaims[:changed]
|
74
|
+
end
|
75
|
+
end
|
76
|
+
end
|
77
|
+
|
78
|
+
# Iterate over each claim key in the parent content
|
79
|
+
parent_content_senses.each_with_index do |parent_claim, index|
|
80
|
+
current_claim = current_content_senses[index]
|
81
|
+
if current_claim.nil?
|
82
|
+
# Claim was removed
|
83
|
+
removed_senses << { index: index }
|
84
|
+
glosses = GlossAnalyzer.isolate_gloss_differences(current_claim, parent_claim)
|
85
|
+
added_glosses += glosses[:added]
|
86
|
+
removed_glosses += glosses[:removed]
|
87
|
+
changed_glosses += glosses[:changed]
|
88
|
+
senseclaims = InsideClaimAnalyzer.isolate_inside_claim_differences(current_claim, nil)
|
89
|
+
added_senseclaims += senseclaims[:added]
|
90
|
+
removed_senseclaims += senseclaims[:removed]
|
91
|
+
changed_senseclaims += senseclaims[:changed]
|
92
|
+
end
|
93
|
+
end
|
94
|
+
{
|
95
|
+
added_senses: added_senses,
|
96
|
+
removed_senses: removed_senses,
|
97
|
+
changed_senses: changed_senses,
|
98
|
+
added_glosses: added_glosses,
|
99
|
+
removed_glosses: removed_glosses,
|
100
|
+
changed_glosses: changed_glosses,
|
101
|
+
added_senseclaims: added_senseclaims,
|
102
|
+
removed_senseclaims: removed_senseclaims,
|
103
|
+
changed_senseclaims: changed_senseclaims
|
104
|
+
}
|
105
|
+
end
|
106
|
+
end
|
@@ -47,15 +47,11 @@ class SitelinkAnalyzer
|
|
47
47
|
# All sitelinks are removed if current content is nil
|
48
48
|
removed_sitelinks = parent_content['sitelinks']
|
49
49
|
end
|
50
|
-
|
51
|
-
# puts "Added sitelinks: #{added_sitelinks}"
|
52
|
-
# puts "Removed sitelinks: #{removed_sitelinks}"
|
53
|
-
# puts "Changed sitelinks: #{changed_sitelinks}"
|
54
50
|
|
55
51
|
{
|
56
|
-
|
57
|
-
|
58
|
-
|
52
|
+
added_sitelinks: added_sitelinks,
|
53
|
+
removed_sitelinks: removed_sitelinks,
|
54
|
+
changed_sitelinks: changed_sitelinks
|
59
55
|
}
|
60
56
|
end
|
61
57
|
end
|
data/lib/wikidata/diff/total.rb
CHANGED
@@ -21,5 +21,36 @@ class Total
|
|
21
21
|
total[:sitelinks_added] += diff_data[:added_sitelinks]
|
22
22
|
total[:sitelinks_removed] += diff_data[:removed_sitelinks]
|
23
23
|
total[:sitelinks_changed] += diff_data[:changed_sitelinks]
|
24
|
+
total[:lemmas_added] += diff_data[:added_lemmas]
|
25
|
+
total[:lemmas_removed] += diff_data[:removed_lemmas]
|
26
|
+
total[:lemmas_changed] += diff_data[:changed_lemmas]
|
27
|
+
total[:forms_added] += diff_data[:added_forms]
|
28
|
+
total[:forms_removed] += diff_data[:removed_forms]
|
29
|
+
total[:forms_changed] += diff_data[:changed_forms]
|
30
|
+
total[:representations_added] += diff_data[:added_representations]
|
31
|
+
total[:representations_removed] += diff_data[:removed_representations]
|
32
|
+
total[:representations_changed] += diff_data[:changed_representations]
|
33
|
+
total[:formclaims_added] += diff_data[:added_formclaims]
|
34
|
+
total[:formclaims_removed] += diff_data[:removed_formclaims]
|
35
|
+
total[:formclaims_changed] += diff_data[:changed_formclaims]
|
36
|
+
total[:senses_added] += diff_data[:added_senses]
|
37
|
+
total[:senses_removed] += diff_data[:removed_senses]
|
38
|
+
total[:senses_changed] += diff_data[:changed_senses]
|
39
|
+
total[:glosses_added] += diff_data[:added_glosses]
|
40
|
+
total[:glosses_removed] += diff_data[:removed_glosses]
|
41
|
+
total[:glosses_changed] += diff_data[:changed_glosses]
|
42
|
+
total[:senseclaims_added] += diff_data[:added_senseclaims]
|
43
|
+
total[:senseclaims_removed] += diff_data[:removed_senseclaims]
|
44
|
+
total[:senseclaims_changed] += diff_data[:changed_senseclaims]
|
45
|
+
total[:merge_from] += diff_data[:merge_from]
|
46
|
+
total[:merge_to] += diff_data[:merge_to]
|
47
|
+
total[:undo] += diff_data[:undo]
|
48
|
+
total[:restore] += diff_data[:restore]
|
49
|
+
total[:clear_item] += diff_data[:clear_item]
|
50
|
+
total[:create_item] += diff_data[:create_item]
|
51
|
+
total[:create_property] += diff_data[:create_property]
|
52
|
+
total[:create_lexeme] += diff_data[:create_lexeme]
|
53
|
+
total[:redirect] += diff_data[:redirect]
|
54
|
+
|
24
55
|
end
|
25
56
|
end
|
@@ -1,8 +1,7 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
|
-
require_relative 'large_batches_analyzer'
|
3
|
-
require_relative 'revision_analyzer'
|
4
|
-
require_relative 'total'
|
5
|
-
require_relative 'mediawiki_login'
|
2
|
+
require_relative 'wikidata/diff/large_batches_analyzer'
|
3
|
+
require_relative 'wikidata/diff/revision_analyzer'
|
4
|
+
require_relative 'wikidata/diff/total'
|
6
5
|
|
7
6
|
module WikidataDiffAnalyzer
|
8
7
|
class Error < StandardError; end
|
@@ -34,7 +33,37 @@ module WikidataDiffAnalyzer
|
|
34
33
|
descriptions_changed: 0,
|
35
34
|
sitelinks_added: 0,
|
36
35
|
sitelinks_removed: 0,
|
37
|
-
sitelinks_changed: 0
|
36
|
+
sitelinks_changed: 0,
|
37
|
+
lemmas_added: 0,
|
38
|
+
lemmas_removed: 0,
|
39
|
+
lemmas_changed: 0,
|
40
|
+
forms_added: 0,
|
41
|
+
forms_removed: 0,
|
42
|
+
forms_changed: 0,
|
43
|
+
representations_added: 0,
|
44
|
+
representations_removed: 0,
|
45
|
+
representations_changed: 0,
|
46
|
+
formclaims_added: 0,
|
47
|
+
formclaims_removed: 0,
|
48
|
+
formclaims_changed: 0,
|
49
|
+
senses_added: 0,
|
50
|
+
senses_removed: 0,
|
51
|
+
senses_changed: 0,
|
52
|
+
glosses_added: 0,
|
53
|
+
glosses_removed: 0,
|
54
|
+
glosses_changed: 0,
|
55
|
+
senseclaims_added: 0,
|
56
|
+
senseclaims_removed: 0,
|
57
|
+
senseclaims_changed: 0,
|
58
|
+
merge_to: 0,
|
59
|
+
merge_from: 0,
|
60
|
+
redirect: 0,
|
61
|
+
undo: 0,
|
62
|
+
restore: 0,
|
63
|
+
clear_item: 0,
|
64
|
+
create_item: 0,
|
65
|
+
create_property: 0,
|
66
|
+
create_lexeme: 0
|
38
67
|
}
|
39
68
|
|
40
69
|
# if revision_ids has 0, then 0 can never be analyzed, so remove it and add in not analyzed
|
@@ -42,24 +71,13 @@ module WikidataDiffAnalyzer
|
|
42
71
|
revision_ids.delete(0)
|
43
72
|
diffs_not_analyzed << 0
|
44
73
|
end
|
45
|
-
# # if mediawiki can be logged in call for 500, otherwise call for 50
|
46
|
-
# if MediawikiLogin.mediawiki_login
|
47
|
-
# puts 'Logged in to mediawiki'
|
48
|
-
# result = LargeBatchesAnalyzer.handle_large_batches(revision_ids, 500)
|
49
|
-
# else
|
50
|
-
# puts 'Not logged in to mediawiki'
|
51
|
-
# result = LargeBatchesAnalyzer.handle_large_batches(revision_ids, 50)
|
52
|
-
# end
|
53
74
|
|
54
75
|
result = LargeBatchesAnalyzer.handle_large_batches(revision_ids, 50)
|
55
|
-
# result is a hash which has contents like this:
|
56
|
-
# result[revid] = { current_content: data[:content], parent_content: parent_content }
|
57
76
|
|
58
77
|
result.each do |revision_id, revision_data|
|
59
78
|
current_content = revision_data[:current_content]
|
60
|
-
|
61
|
-
|
62
|
-
diff = RevisionAnalyzer.analyze_diff(current_content, parent_content)
|
79
|
+
if current_content
|
80
|
+
diff = RevisionAnalyzer.analyze_diff(revision_data)
|
63
81
|
diffs[revision_id] = diff
|
64
82
|
Total.accumulate_totals(diff, total)
|
65
83
|
diffs_analyzed << revision_id
|
@@ -78,6 +96,3 @@ module WikidataDiffAnalyzer
|
|
78
96
|
}
|
79
97
|
end
|
80
98
|
end
|
81
|
-
|
82
|
-
|
83
|
-
|
@@ -1,10 +1,10 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
|
-
|
3
|
+
require File.expand_path('lib/wikidata-diff-analyzer/version', __dir__)
|
4
4
|
|
5
5
|
Gem::Specification.new do |spec|
|
6
6
|
spec.name = "wikidata-diff-analyzer"
|
7
|
-
spec.version =
|
7
|
+
spec.version = WikidataDiffAnalyzer::VERSION
|
8
8
|
spec.authors = ["Sulagna Saha"]
|
9
9
|
spec.email = ["saha23s@mtholyoke.edu"]
|
10
10
|
|
@@ -22,16 +22,22 @@ Gem::Specification.new do |spec|
|
|
22
22
|
|
23
23
|
# Specify which files should be added to the gem when it is released.
|
24
24
|
# The `git ls-files -z` loads the files in the RubyGem that have been added into git.
|
25
|
-
spec.files = Dir.
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
25
|
+
spec.files = Dir['README.md', 'LICENSE',
|
26
|
+
'CHANGELOG.md', 'lib/**/*.rb',
|
27
|
+
'lib/**/*.rake',
|
28
|
+
'wikidata-diff-analyzer.gemspec', '.github/*.md',
|
29
|
+
'Gemfile', 'Rakefile']
|
30
|
+
spec.extra_rdoc_files = ['README.md']
|
31
|
+
spec.require_paths = ['lib']
|
32
|
+
|
30
33
|
spec.bindir = "exe"
|
31
34
|
spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
|
32
|
-
spec.require_paths = ["lib"]
|
33
35
|
spec.files.reject! { |f| File.extname(f) == '.gem' }
|
34
36
|
|
35
37
|
# Adding the dependencies
|
36
38
|
spec.add_dependency 'json', '~> 2.1'
|
39
|
+
spec.add_dependency 'mediawiki_api', '~> 0.7.0'
|
40
|
+
spec.add_dependency 'rspec', '~> 3.0'
|
41
|
+
spec.add_dependency 'rubocop', '~> 1.21'
|
42
|
+
spec.add_dependency 'rake', '~> 13.0'
|
37
43
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: wikidata-diff-analyzer
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1
|
4
|
+
version: 2.0.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Sulagna Saha
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2023-07-
|
11
|
+
date: 2023-07-31 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: json
|
@@ -24,34 +24,96 @@ dependencies:
|
|
24
24
|
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: '2.1'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: mediawiki_api
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 0.7.0
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 0.7.0
|
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: :runtime
|
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: '1.21'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '1.21'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: rake
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '13.0'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '13.0'
|
27
83
|
description: This gem provides tools for analyzing diffs between Wikidata items, including
|
28
84
|
retrieving the JSON representation of an item for a specific revision.
|
29
85
|
email:
|
30
86
|
- saha23s@mtholyoke.edu
|
31
87
|
executables: []
|
32
88
|
extensions: []
|
33
|
-
extra_rdoc_files:
|
89
|
+
extra_rdoc_files:
|
90
|
+
- README.md
|
34
91
|
files:
|
35
92
|
- CHANGELOG.md
|
36
|
-
- CODE_OF_CONDUCT.md
|
37
93
|
- Gemfile
|
38
|
-
- Gemfile.lock
|
39
94
|
- LICENSE
|
40
95
|
- README.md
|
41
96
|
- Rakefile
|
97
|
+
- lib/wikidata-diff-analyzer.rb
|
98
|
+
- lib/wikidata-diff-analyzer/version.rb
|
42
99
|
- lib/wikidata/diff/alias_analyzer.rb
|
43
|
-
- lib/wikidata/diff/analyzer.rb
|
44
|
-
- lib/wikidata/diff/analyzer/version.rb
|
45
100
|
- lib/wikidata/diff/api.rb
|
46
101
|
- lib/wikidata/diff/claim_analyzer.rb
|
102
|
+
- lib/wikidata/diff/comment_analyzer.rb
|
47
103
|
- lib/wikidata/diff/description_analyzer.rb
|
104
|
+
- lib/wikidata/diff/form_analyzer.rb
|
105
|
+
- lib/wikidata/diff/gloss_analyzer.rb
|
106
|
+
- lib/wikidata/diff/inside_claim_analyzer.rb
|
48
107
|
- lib/wikidata/diff/label_analyzer.rb
|
49
108
|
- lib/wikidata/diff/large_batches_analyzer.rb
|
50
|
-
- lib/wikidata/diff/
|
109
|
+
- lib/wikidata/diff/lemma_analyzer.rb
|
110
|
+
- lib/wikidata/diff/qualifier_analyzer.rb
|
111
|
+
- lib/wikidata/diff/reference_analyzer.rb
|
112
|
+
- lib/wikidata/diff/representation_analyzer.rb
|
51
113
|
- lib/wikidata/diff/revision_analyzer.rb
|
114
|
+
- lib/wikidata/diff/sense_analyzer.rb
|
52
115
|
- lib/wikidata/diff/sitelink_analyzer.rb
|
53
116
|
- lib/wikidata/diff/total.rb
|
54
|
-
- sig/wikidata/diff/analyzer.rbs
|
55
117
|
- wikidata-diff-analyzer.gemspec
|
56
118
|
homepage: https://github.com/WikiEducationFoundation/wikidata-diff-analyzer
|
57
119
|
licenses:
|