dwc_agent 3.0.5.0 → 3.0.7.0
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 +9 -6
- 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: 309d97f743627171e1479527de5354f5f0f172b88e3cc24f40e0cbe8bc3d1ee1
|
4
|
+
data.tar.gz: 1d45999c8bf87e5ff68e3479ed24b7c9910e82f21295895fc3ab08e2f47cc301
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: ed8b465cf99cf1a63d03b4bb23ef972a840d33a2c107c66f5a2993d95071ec70a2d97e7dbbecdbc3bee16491908118684b9b35260853bc83c7825e86725b2e92
|
7
|
+
data.tar.gz: f02efd62c4917e326ab111c45598f82b2d1c462d525a12753a88cacb43d5e6054e005b25a16b2522151dc06d08651a12deae3499c4d51e4f5a7bbbb474f78539
|
data/lib/dwc_agent/constants.rb
CHANGED
@@ -127,7 +127,8 @@ module DwcAgent
|
|
127
127
|
\:?\s*(?i:exch)(\b|\z)|
|
128
128
|
\s+de\s*$|
|
129
129
|
\.{2,}$|
|
130
|
-
\[|\]
|
130
|
+
\[|\]|
|
131
|
+
[^[:alnum:][:blank:][:punct:][∣´|ǀ∣|│`~$^+|<>]] # Removes emojis from string
|
131
132
|
}x
|
132
133
|
|
133
134
|
SPLIT_BY = %r{
|
@@ -144,6 +145,7 @@ module DwcAgent
|
|
144
145
|
\b(?i:confirmada)(\s+por)?\s*\b|
|
145
146
|
\b(?i:checked?(\s+by)?)\s*\b|
|
146
147
|
\b(?i:det\.?(\s+by)?)\s*\b|
|
148
|
+
\b(?i:(donated)?\s*by)\s+|
|
147
149
|
\b(?i:dupl?\.?(\s+by)?|duplicate(\s+by)?)\s*\b|
|
148
150
|
\b(?i:ex\.?(\s+by)?|examined(\s+by)?)\s*\b|
|
149
151
|
\b(?i:in?dentified(\s+by)?)\s*\b|
|
@@ -156,8 +158,7 @@ module DwcAgent
|
|
156
158
|
\b(?i:stet)\s*\b|
|
157
159
|
\b(?i:then(\s+by)?)\s+|
|
158
160
|
\b(?i:veri?f?\.?\:?(\s+by)?|v(e|é)rifi(e|é)d?(\s+by)?)\s*\b|
|
159
|
-
\b(?i:via|from)\s*\b
|
160
|
-
\b(?i:(donated)?\s*by)\s+
|
161
|
+
\b(?i:via|from)\s*\b
|
161
162
|
}x
|
162
163
|
|
163
164
|
CHAR_SUBS = {
|
@@ -202,14 +203,16 @@ module DwcAgent
|
|
202
203
|
}
|
203
204
|
|
204
205
|
SEPARATORS = {
|
206
|
+
"^([A-Z]{1}\\.\\s*[[:alpha:]]{1,}),\\s*?([A-Z.]{1,})$" => "\\1 \\2",
|
205
207
|
"^(\\S{4,},\\s+(?:\\S\\.\\s*){1,})\\s+(\\S{4,},\\s+(?:\\S\.\\s*){1,})$" => "\\1 | \\2",
|
206
208
|
"(\\S{1}\\.)([[:alpha:]]{2,})" => "\\1 \\2",
|
209
|
+
"^([[:alpha:]]{2,})(?:\\s+)((?:\\S{1}\\.\\s?){1,})$" => "\\1, \\2",
|
207
210
|
"([[:alpha:]]*),?\\s+(.*)\\s+(van|von)$" => "\\3 \\1, \\2",
|
208
211
|
"^([A-Z.\\s]+)\\s+(?:and|&|et|e)\\s+([A-Z.\\s]+)\\s+([[:alpha:]]{2,})\\s+([[:alpha:]]{2,})$" => "\\1 \\4 | \\2 \\3 \\4",
|
209
212
|
"^([A-Z.\\s]+)\\s+(?:and|&|et|e)\\s+([A-Z.\\s]+)\\s+([[:alpha:]]{2,})(.*)$" => "\\1 \\3 | \\2 \\3 | \\4",
|
210
|
-
"^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?
|
211
|
-
"^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?
|
212
|
-
"^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?
|
213
|
+
"^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?(?i:and|&|et|e|,)\\s+([A-Z][[:alpha:]]{2,})$" => "\\1 | \\2 | \\3",
|
214
|
+
"^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?(?i:and|&|et|e|,)\\s+([A-Z][[:alpha:]]{3,})$" => "\\1 | \\2 | \\3 | \\4",
|
215
|
+
"^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?(?i:and|&|et|e|,)\\s+([A-Z][[:alpha:]]{3,})$" => "\\1 | \\2 | \\3 | \\4 | \\5"
|
213
216
|
}
|
214
217
|
|
215
218
|
BLACKLIST = %r{
|
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: 3.0.
|
4
|
+
version: 3.0.7.0
|
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: 2023-
|
11
|
+
date: 2023-08-02 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: namae
|