dwc_agent 1.5.0.3 → 1.5.0.4
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.
- checksums.yaml +4 -4
- data/lib/dwc_agent/constants.rb +17 -8
- data/lib/dwc_agent/parser.rb +1 -1
- data/lib/dwc_agent/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: cef90f0884c7b59a1c3aae50198ef043a282127ef4b883b326a0a4b1bfdcd337
|
|
4
|
+
data.tar.gz: a19a07304fdd82ddd1259080a503fea4d13d5d44b60b6edb651e799a5c473525
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: bcbebc3c10b85a5a86d9d67b8dbcee31164b64c46e8626f26378b36df7a2493d0f96a527423910a8748bc45fee7a9fd6ac8633392d78882bf43ff55902e2781d
|
|
7
|
+
data.tar.gz: 2f7e75e44b207fc72f6c90e413ac047337362494122cfe9ce976f993fe48bd9a0407c47ff56c5991c591c1e3562e999a88cfedcb869bb2712bed787b4cd17799
|
data/lib/dwc_agent/constants.rb
CHANGED
|
@@ -61,7 +61,7 @@ module DwcAgent
|
|
|
61
61
|
(?i:see\s+notes?\s*(inside)?)|
|
|
62
62
|
(?i:see\s+letter\s+enclosed)|
|
|
63
63
|
(?i:(by)?\s+correspondance)|
|
|
64
|
-
(?i:pers\.?\s
|
|
64
|
+
(?i:pers\.?\s*comm\.?)|
|
|
65
65
|
(?i:crossed\s+out)|
|
|
66
66
|
\(?(?i:source)\(?|
|
|
67
67
|
(?i:according\s+to)|
|
|
@@ -113,19 +113,22 @@ module DwcAgent
|
|
|
113
113
|
[–|ǀ∣|│&+\/;:]|
|
|
114
114
|
\s+-\s+|
|
|
115
115
|
\s+a\.\s+|
|
|
116
|
-
\b(e|y|i|en|et|or|per|for)\s*\b|
|
|
116
|
+
\b(con|e|y|i|en|et|or|per|for)\s*\b|
|
|
117
117
|
\b(?i:and|with)\s*\b|
|
|
118
118
|
\b(?i:annotated(\s+by)?)\s*\b|
|
|
119
119
|
\b(?i:coll\.)\s*\b|
|
|
120
120
|
\b(?i:communicate?d(\s+to)?)\s*\b|
|
|
121
121
|
\b(?i:conf\.?(\s+by)?|confirmed(\s+by)?)\s*\b|
|
|
122
|
+
\b(?i:confirmada)(\s+por)?\s*\b|
|
|
122
123
|
\b(?i:checked?(\s+by)?)\s*\b|
|
|
123
124
|
\b(?i:det\.?(\s+by)?)\s*\b|
|
|
124
125
|
\b(?i:dupl?\.?(\s+by)?|duplicate(\s+by)?)\s*\b|
|
|
125
126
|
\b(?i:ex\.?(\s+by)?|examined(\s+by)?)\s*\b|
|
|
126
127
|
\b(?i:in?dentified(\s+by)?)\s*\b|
|
|
127
128
|
\b(?i:in\s+part(\s+by)?)\s*\b|
|
|
129
|
+
\b(?i:och)\s*\b|
|
|
128
130
|
\b(?i:prep\.?\s+(?i:by)?)\s*\b|
|
|
131
|
+
\b(?i:purchased?)(\s+by)?\s*\b|
|
|
129
132
|
\b(?i:redet\.?(\s+by?)?)\s*\b|
|
|
130
133
|
\b(?i:reidentified(\s+by)?)\s*\b|
|
|
131
134
|
\b(?i:stet)\s*\b|
|
|
@@ -159,12 +162,18 @@ module DwcAgent
|
|
|
159
162
|
}
|
|
160
163
|
|
|
161
164
|
PHRASE_SUBS = {
|
|
162
|
-
'
|
|
163
|
-
'
|
|
164
|
-
'
|
|
165
|
-
' jr
|
|
166
|
-
' jr
|
|
167
|
-
'
|
|
165
|
+
', ph.d.' => ' Ph.D.',
|
|
166
|
+
', Ph.D.' => ' Ph.D.',
|
|
167
|
+
', bro.' => ' Bro.',
|
|
168
|
+
' jr.,' => ' Jr.;',
|
|
169
|
+
' jr,' => ' Jr.;',
|
|
170
|
+
'-jr' => ' Jr.',
|
|
171
|
+
'-Jr' => ' Jr.',
|
|
172
|
+
', Jr.' => ' Jr.',
|
|
173
|
+
',Jr.' => ' Jr.',
|
|
174
|
+
', Sr.' => ' Sr.',
|
|
175
|
+
',Sr.' => ' Sr.'
|
|
176
|
+
|
|
168
177
|
}
|
|
169
178
|
|
|
170
179
|
COMPLEX_SEPARATORS = %r{
|
data/lib/dwc_agent/parser.rb
CHANGED
|
@@ -20,7 +20,7 @@ module DwcAgent
|
|
|
20
20
|
@strip_out_regex = Regexp.new STRIP_OUT.to_s
|
|
21
21
|
@residual_terminators_regex = Regexp.new SPLIT_BY.to_s + %r{\s*\z}.to_s
|
|
22
22
|
@char_subs_regex = Regexp.new [CHAR_SUBS.keys.join].to_s
|
|
23
|
-
@phrase_subs_regex = Regexp.new PHRASE_SUBS.keys.join('|').to_s
|
|
23
|
+
@phrase_subs_regex = Regexp.new PHRASE_SUBS.keys.map{|a| Regexp.escape a }.join('|').to_s
|
|
24
24
|
@complex_separators_regex = Regexp.new COMPLEX_SEPARATORS.to_s
|
|
25
25
|
@add_separators_regex = Regexp.new %r{(\S{1}\.)([[:alpha:]]{2,})}.to_s
|
|
26
26
|
end
|
data/lib/dwc_agent/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: dwc_agent
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 1.5.0.
|
|
4
|
+
version: 1.5.0.4
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- David P. Shorthouse
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2020-08-
|
|
11
|
+
date: 2020-08-16 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: namae
|