dwc_agent 3.0.8.0 → 3.0.10.0
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 +11 -4
- data/lib/dwc_agent/parser.rb +2 -0
- data/lib/dwc_agent/version.rb +2 -2
- 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: bf7946475612999b141445b40ee1b93c1252d3f987b65eab8523238716ab162e
|
4
|
+
data.tar.gz: '09d2c2353fc63d86bdb327cfc8cd29e33be945d2eb4a6d147c55e31e30c80c14'
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: ce194f8823af1f1a594a43a0f37eb2e08ea51dbec107fb3c7d19dceb04e6579efe30d7a5bbaafbf964f1110debd8b4a8bb2abe53a55c9f99965da0a6cc32f8d3
|
7
|
+
data.tar.gz: 7f6b7b0fe8c23cd1e0bbef6eefa1488300867f7acbb8b039bef65f0c597011a85aad7f926652ce99993a0fa6bbebbc4eef99f73769031714e4f5e0002d5c6737
|
data/lib/dwc_agent/constants.rb
CHANGED
@@ -22,8 +22,9 @@ module DwcAgent
|
|
22
22
|
\b[,;]?\s*(?i:importer|gift)\:?\b|
|
23
23
|
\b[,;]?\s*(?i:string)\b|
|
24
24
|
\b[,;]?\s*(?i:person\s*string)\b|
|
25
|
+
^(?i:colln?)\.?\s+|\s*(?i:colln?)\.?\s*$|
|
26
|
+
^(?i:collection)\:?\s+|\s*(?i:collection)\s*$|
|
25
27
|
\b[,;]?\s*(?i:colls)\.(\b|\z)|
|
26
|
-
\b[,;]?\s*(?i:colln?)[:.]?(\b|\z)|
|
27
28
|
\b[,;]?\s*(?i:stet)[,!]?\s*\d*\z|
|
28
29
|
[,;]?\s*\d+[-/\s+](?i:\d+|Jan|Feb|Mar|Apr|
|
29
30
|
May|Jun|Jul|Aug|Sept?|
|
@@ -53,7 +54,7 @@ module DwcAgent
|
|
53
54
|
\d+\s+(?i:Nov|Novemb(er|re))\.?\b|
|
54
55
|
\d+\s+(?i:Dec|D(e|é)cemb(er|re))\.?\b|
|
55
56
|
\b[.-–,;:/]?\s*(?i:Alabama|Alaska|Arizona|Arkansas|California|Colorado|Connecticut|Delaware|Evergreen|Florida|Hawaii|Idaho|Illinois|Indiana|Iowa|Kansas|Kentucky|Louisiana|Maine|Maryland|Massachusetts|Michigan|Minnesota|Mississippi|Missouri|Montana|Nebraska|Nevada|New\s+Hampshire|New\s+Jersey|New\s+Mexico|New\s+York|North\s+Carolina|North\s+Dakota|Ohio|Oklahoma|Oregon|Pennsylvania|Portland|Rhode\s+Island|South\s+Carolina|South\s+Dakota|St\s+Petersburg|Tennessee|Texas|Utah|Vermont|Washington|West\s+Virginia|Wisconsin|Wyoming)\s+(?i:State)\s*\b|
|
56
|
-
\b[.,;:/]?\s*?(?i:Afghanistan|Åland Islands|Albania|Algeria|American Samoa|Andorra|Angola|Anguilla|Antarctica|Antigua and Barbuda|Argentina|Armenia|Aruba|Australia|Azerbaijan|Bahamas|Bahrain|Bangladesh|Barbados|Belarus|Belize|Benin|Bermuda|Bhutan|Bolivia \(Plurinational State of\)|Bonaire, Sint Eustatius and Saba|Bosnia and Herzegovina|Botswana|Bouvet Island|Brazil|British Indian Ocean Territory|Brunei Darussalam|Bulgaria|Burkina Faso|Burundi|Cabo Verde|Cambodia|Cameroon|Canada|Cayman Islands|Central African Republic|Chad|Chile|Christmas Island|Cocos \(Keeling\) Islands|Colombia|Comoros|Congo|Congo \(Democratic Republic of the\)|Cook Islands|Costa Rica|Côte d'Ivoire|Croatia|Cuba|Curaçao|Cyprus|Czechia|Djibouti|Dominica|Dominican Republic|Ecuador|Egypt|El Salvador|Equatorial Guinea|Eritrea|Estonia|Ethiopia|Falkland Islands \(Malvinas\)|Faroe Islands|Fiji|Finland|French Guiana|French Polynesia|French Southern Territories|Gabon|Gambia|Germany|Ghana|Gibraltar|Greece|Greenland|Grenada|Guadeloupe|Guam|Guatemala|Guernsey|Guinea-Bissau|Guyana|Haiti|Heard Island and McDonald Islands|Holy See|Honduras|Hong Kong|Hungary|Iceland|India|Indonesia|Iran \(Islamic Republic of\)|Iraq|
|
57
|
+
\b[.,;:/]?\s*?(?i:Afghanistan|Åland Islands|Albania|Algeria|American Samoa|Andorra|Angola|Anguilla|Antarctica|Antigua and Barbuda|Argentina|Armenia|Aruba|Australia|Azerbaijan|Bahamas|Bahrain|Bangladesh|Barbados|Belarus|Belize|Benin|Bermuda|Bhutan|Bolivia \(Plurinational State of\)|Bonaire, Sint Eustatius and Saba|Bosnia and Herzegovina|Botswana|Bouvet Island|Brazil|British Indian Ocean Territory|Brunei Darussalam|Bulgaria|Burkina Faso|Burundi|Cabo Verde|Cambodia|Cameroon|Canada|Cayman Islands|Central African Republic|Chad|Chile|Christmas Island|Cocos \(Keeling\) Islands|Colombia|Comoros|Congo|Congo \(Democratic Republic of the\)|Cook Islands|Costa Rica|Côte d'Ivoire|Croatia|Cuba|Curaçao|Cyprus|Czechia|Djibouti|Dominica|Dominican Republic|Ecuador|Egypt|El Salvador|Equatorial Guinea|Eritrea|Estonia|Ethiopia|Falkland Islands \(Malvinas\)|Faroe Islands|Fiji|Finland|French Guiana|French Polynesia|French Southern Territories|Gabon|Gambia|Germany|Ghana|Gibraltar|Greece|Greenland|Grenada|Guadeloupe|Guam|Guatemala|Guernsey|Guinea-Bissau|Guyana|Haiti|Heard Island and McDonald Islands|Holy See|Honduras|Hong Kong|Hungary|Iceland|India|Indonesia|Iran \(Islamic Republic of\)|Iraq|Isle of Man|Italy|Jamaica|Japan|Jersey|Kazakhstan|Kenya|Kiribati|Korea \(Democratic People\'s Republic of\)|Korea \(Republic of\)|Kuwait|Kyrgyzstan|Lao People\'s Democratic Republic|Latvia|Lebanon|Lesotho|Liberia|Libya|Liechtenstein|Lithuania|Luxembourg|Macao|Macedonia (the former Yugoslav Republic of)|Madagascar|Malawi|Malaysia|Maldives|Malta|Marshall Islands|Martinique|Mauritania|Mauritius|Mayotte|Mexico|Micronesia \(Federated States of\)|Moldova \(Republic of\)|Monaco|Mongolia|Montenegro|Morocco|Mozambique|Myanmar|Namibia|Nauru|Nepal|Netherlands|New Caledonia|New Zealand|Nicaragua|Niger|Nigeria|Niue|Norfolk Island|Northern Mariana Islands|Norway|Oman|Pakistan|Palau|Palestine, State of|Panama|Papua New Guinea|Paraguay|Peru|Philippines|Pitcairn|Poland|Puerto Rico|Qatar|Réunion|Romania|Russian Federation|Russia|Rwanda|Saint Barthélemy|Saint Helena, Ascension and Tristan da Cunha|Saint Kitts and Nevis|Saint Lucia|Saint Martin \(French part\)|Saint Pierre and Miquelon|Saint Vincent and the Grenadines|Samoa|San Marino|Sao Tome and Principe|Saudi Arabia|Senegal|Serbia|Seychelles|Sierra Leone|Singapore|Sint Maarten \(Dutch part\)|Slovakia|Slovenia|Solomon Islands|Somalia|South Africa|South Georgia and the South Sandwich Islands|South Sudan|Sri Lanka|Sudan|Suriname|Svalbard and Jan Mayen|Swaziland|Sweden|Switzerland|Syrian Arab Republic|Taiwan|Tajikistan|Tanzania, United Republic of|Thailand|Timor-Leste|Togo|Tokelau|Tonga|Trinidad and Tobago|Tunisia|Turkey|Turkmenistan|Turks and Caicos Islands|Tuvalu|Uganda|Ukraine|United Arab Emirates|United Kingdom of Great Britain and Northern Ireland|United States of America|United States Minor Outlying Islands|Uruguay|Uzbekistan|Vanuatu|Venezuela \(Bolivarian Republic of\)|Viet Nam|Virgin Islands \(British\)|Virgin Islands \(U\.S\.\)|Wallis and Futuna|Western Sahara|Yemen|Zambia|Zimbabwe)\b|
|
57
58
|
(?i:autres?\s+de|probab|likely|possibl(e|y)|doubtful)|
|
58
59
|
\b\s*(?i:maybe)\s*\b|
|
59
60
|
\b\s*(?i:prob)\.\s*\b|
|
@@ -149,6 +150,7 @@ module DwcAgent
|
|
149
150
|
\b(?i:dupl?\.?(\s+by)?|duplicate(\s+by)?)\s*\b|
|
150
151
|
\b(?i:ex\.?(\s+by)?|examined(\s+by)?)\s*\b|
|
151
152
|
\b(?i:in?dentified(\s+by)?)\s*\b|
|
153
|
+
\b(?i:in\s+coll\.?\s*\b)|
|
152
154
|
\b(?i:in\s+part(\s+by)?)\s*\b|
|
153
155
|
\b(?i:och)\s*\b|
|
154
156
|
\b(?i:prep\.?\s+(?i:by)?)\s*\b|
|
@@ -161,6 +163,10 @@ module DwcAgent
|
|
161
163
|
\b(?i:via|from)\s*\b
|
162
164
|
}x
|
163
165
|
|
166
|
+
POST_STRIP_TIDY = %r{
|
167
|
+
^\s*[&,;.]\s*
|
168
|
+
}x
|
169
|
+
|
164
170
|
CHAR_SUBS = {
|
165
171
|
'"' => '\'',
|
166
172
|
'|' => ' | ',
|
@@ -206,11 +212,12 @@ module DwcAgent
|
|
206
212
|
|
207
213
|
SEPARATORS = {
|
208
214
|
"^(\\S{4,}),\\s+(Mrs?\\.|MRS?\\.)\\s+([A-Za-z\\.\\s]{1,})$" => "\\2 \\3 \\1",
|
215
|
+
"^(Mrs?\\.?)\\s+&\\s+(Mrs?\\.?)\\s+(.*)$" => "\\1 \\3 | \\2 \\3",
|
209
216
|
"^([A-Z]{1}\\.\\s*[[:alpha:]]{1,}),\\s*?([A-Z.]{1,})$" => "\\1 \\2",
|
210
217
|
"^(\\S{4,},\\s+(?:\\S\\.\\s*){1,})\\s+(\\S{4,},\\s+(?:\\S\.\\s*){1,})$" => "\\1 | \\2",
|
211
218
|
"(\\S{1}\\.)([[:alpha:]]{2,})" => "\\1 \\2",
|
212
219
|
"^([[:alpha:]]{2,})(?:\\s+)((?:\\S{1}\\.\\s?){1,})$" => "\\1, \\2",
|
213
|
-
"([[:alpha:]]*),?\\s
|
220
|
+
"([[:alpha:]]*),?\\s*(.*)\\s+(van|von)$" => "\\3 \\1, \\2",
|
214
221
|
"^([A-Z.\\s]+)\\s+(?:and|&|et|e)\\s+([A-Z.\\s]+)\\s+([[:alpha:]]{2,})\\s+([[:alpha:]]{2,})$" => "\\1 \\4 | \\2 \\3 \\4",
|
215
222
|
"^([A-Z.\\s]+)\\s+(?:and|&|et|e)\\s+([A-Z.\\s]+)\\s+([[:alpha:]]{2,})(.*)$" => "\\1 \\3 | \\2 \\3 | \\4",
|
216
223
|
"^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?(?i:and|&|et|e|,)\\s+([A-Z][[:alpha:]]{2,})$" => "\\1 | \\2 | \\3",
|
@@ -222,7 +229,7 @@ module DwcAgent
|
|
222
229
|
(?i:abundant)|
|
223
230
|
(?i:adult|juvenile)|
|
224
231
|
(?i:administra(d|t)or)|
|
225
|
-
(?i:anon)
|
232
|
+
^(?i:anon)$|
|
226
233
|
(?i:australian?)|
|
227
234
|
(?i:average)|
|
228
235
|
(?i:believe|unclear|ill?egible|none|suggested|(dis)?agrees?)|approach|
|
data/lib/dwc_agent/parser.rb
CHANGED
@@ -18,6 +18,7 @@ module DwcAgent
|
|
18
18
|
}
|
19
19
|
@namae = Namae::Parser.new(options)
|
20
20
|
@strip_out_regex = Regexp.new STRIP_OUT.to_s
|
21
|
+
@tidy_remains_regex = Regexp.new POST_STRIP_TIDY.to_s
|
21
22
|
@char_subs_regex = Regexp.new [CHAR_SUBS.keys.join].to_s
|
22
23
|
@phrase_subs_regex = Regexp.new PHRASE_SUBS.keys.map{|a| Regexp.escape a }.join('|').to_s
|
23
24
|
@residual_terminators_regex = Regexp.new SPLIT_BY.to_s + %r{\s*\z}.to_s
|
@@ -31,6 +32,7 @@ module DwcAgent
|
|
31
32
|
def parse(name)
|
32
33
|
return [] if name.nil? || name == ""
|
33
34
|
name.gsub!(@strip_out_regex, ' ')
|
35
|
+
name.gsub!(@tidy_remains_regex, '')
|
34
36
|
name.gsub!(Regexp.union(@char_subs_regex, @phrase_subs_regex), CHAR_SUBS.merge(PHRASE_SUBS))
|
35
37
|
@separators.each{|k| name.gsub!(k[0], k[1])}
|
36
38
|
name.gsub!(@residual_terminators_regex, '')
|
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: 3.0.10.0
|
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: 2023-09-11 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: namae
|