dwc_agent 3.0.4.0 → 3.0.6.0

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 CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: f820b38b91a9baaa489c2f2b595636f17c1435633ddb06571a03ea4fbe469ba5
4
- data.tar.gz: '03600881a34efd76a6ca09c2be97a75a3e234316783bdb02f13a806279e61481'
3
+ metadata.gz: 69985a64afbcf03bbb14df6e00f85cfbd1470846a289aa490e1b62a41986285d
4
+ data.tar.gz: b2158f59c97be96d2217a9c8dbf86fce3d256a649485d6d29dc510069c144f04
5
5
  SHA512:
6
- metadata.gz: 3ad5fdb3bee1be9337a944be8a67d3248e33ca857df39ee68d6b4d826dee3575f40345842b698f5efc78d754b14a0b91992f04412a4031f58f1717e472cf8d08
7
- data.tar.gz: 2b41332a7e512c5dc38b1879111739d0753a3f07de95e41707fd1bafa542491a51863ba059123770b4e835b36fe9d40c7fef77b66ea46a4b0da4e8aca351ef18
6
+ metadata.gz: 2fd0d7089120d60ac306758a5a8b2efbd3a31d5174fe1e16cb4a627df73cbcb364e622c0cc0de05dcbadaaa775895aa2d89e57739b447679b2ac1fcce63acd60
7
+ data.tar.gz: 84398f5548ef552f4e86b05b3f1bc11e2a67355b283ef74986fc5061fa7e77bce894401ff88cd9dae72103bd01520c2e53896ed0d5d34aae0f38d48bbee8ae0e
@@ -6,7 +6,7 @@ module DwcAgent
6
6
  [,;]?\s*(?i:1st|2nd|3rd|[4-9]th)|
7
7
  \s*?\d+\.\d+|
8
8
  \b\d+\(?(?i:[[:alpha:]])\)?\b|
9
- \b[,;]?\s*(?i:et\.?\s+al|&\s+al)\.?|
9
+ \b[,;]?\s*(?:et\.?\s+al|&\s+al)\.?|
10
10
  \b[,;]?\s*(?i:etal)\.?|
11
11
  \b\s+(bis|ter)(\b|\z)|
12
12
  \bu\.\s*a\.|
@@ -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 +203,15 @@ 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",
207
209
  "([[:alpha:]]*),?\\s+(.*)\\s+(van|von)$" => "\\3 \\1, \\2",
208
210
  "^([A-Z.\\s]+)\\s+(?:and|&|et|e)\\s+([A-Z.\\s]+)\\s+([[:alpha:]]{2,})\\s+([[:alpha:]]{2,})$" => "\\1 \\4 | \\2 \\3 \\4",
209
211
  "^([A-Z.\\s]+)\\s+(?:and|&|et|e)\\s+([A-Z.\\s]+)\\s+([[:alpha:]]{2,})(.*)$" => "\\1 \\3 | \\2 \\3 | \\4",
210
- "^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?[,&]\\s*?([A-Z][[:alpha:]]{2,})$" => "\\1 | \\2 | \\3",
211
- "^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?[,&]\\s*?([A-Z][[:alpha:]]{3,})$" => "\\1 | \\2 | \\3 | \\4",
212
- "^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?[,&]\\s*?([A-Z][[:alpha:]]{3,})$" => "\\1 | \\2 | \\3 | \\4 | \\5"
212
+ "^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?(?i:and|&|et|e|,)\\s+([A-Z][[:alpha:]]{2,})$" => "\\1 | \\2 | \\3",
213
+ "^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?(?i:and|&|et|e|,)\\s+([A-Z][[:alpha:]]{3,})$" => "\\1 | \\2 | \\3 | \\4",
214
+ "^([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
215
  }
214
216
 
215
217
  BLACKLIST = %r{
@@ -4,7 +4,7 @@ module DwcAgent
4
4
 
5
5
  MAJOR = 3
6
6
  MINOR = 0
7
- PATCH = 4
7
+ PATCH = 6
8
8
  BUILD = 0
9
9
 
10
10
  def self.version
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: 3.0.4.0
4
+ version: 3.0.6.0
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: 2023-06-07 00:00:00.000000000 Z
11
+ date: 2023-06-30 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: namae