dwc_agent 1.5.1.4 → 1.5.1.9
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 -4
- 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: bb6ce105789bd5ef9568c5e7264d61de63def444aa00dbe9e1f593fa3cf3b7a0
|
4
|
+
data.tar.gz: 89838b01e9c3780d21bf2a233296f7cb5a91d0d73250157d0b582fa8f4289e8b
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: d756b5915bd8fbd4d5e167f49d7ad28f379e50c84c9d2acc23926f8ac71de2e2b180f8e7d22140962d9ecd82aacc99be5663869a930e1c5137c402c571ba79e8
|
7
|
+
data.tar.gz: bdb4802ff417c65fa2fad958eddbda1cf0f8a7447f483a5cd42724ba22d220cb1132be6b9b3b58c23d8e74f3ecb1abe2ea4c7450db74562e108527720e97b5e4
|
data/lib/dwc_agent/constants.rb
CHANGED
@@ -52,7 +52,7 @@ module DwcAgent
|
|
52
52
|
\d+\s+(?i:Nov|Novemb(er|re))\.?\b|
|
53
53
|
\d+\s+(?i:Dec|D(e|é)cemb(er|re))\.?\b|
|
54
54
|
\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|
|
55
|
-
\b[.,;:/]?\s*?(?i:Afghanistan|Åland Islands|Albania|Algeria|American Samoa|Andorra|Angola|Anguilla|Antarctica|Antigua and Barbuda|Argentina|Armenia|Aruba|Australia|Austria|Azerbaijan|Bahamas|Bahrain|Bangladesh|Barbados|Belarus|Belgium|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|China|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|Denmark|Djibouti|Dominica|Dominican Republic|Ecuador|Egypt|El Salvador|Equatorial Guinea|Eritrea|Estonia|Ethiopia|Falkland Islands \(Malvinas\)|Faroe Islands|Fiji|Finland|France|French Guiana|French Polynesia|French Southern Territories|Gabon|Gambia|Germany|Ghana|Gibraltar|Greece|Greenland|Grenada|Guadeloupe|Guam|Guatemala|Guernsey|Guinea|Guinea-Bissau|Guyana|Haiti|Heard Island and McDonald Islands|Holy See|Honduras|Hong Kong|Hungary|Iceland|India|Indonesia|Iran \(Islamic Republic of\)|Iraq|Ireland|Isle of Man|Israel|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|
|
55
|
+
\b[.,;:/]?\s*?(?i:Afghanistan|Åland Islands|Albania|Algeria|American Samoa|Andorra|Angola|Anguilla|Antarctica|Antigua and Barbuda|Argentina|Armenia|Aruba|Australia|Austria|Azerbaijan|Bahamas|Bahrain|Bangladesh|Barbados|Belarus|Belgium|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|China|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|Denmark|Djibouti|Dominica|Dominican Republic|Ecuador|Egypt|El Salvador|Equatorial Guinea|Eritrea|Estonia|Ethiopia|Falkland Islands \(Malvinas\)|Faroe Islands|Fiji|Finland|France|French Guiana|French Polynesia|French Southern Territories|Gabon|Gambia|Germany|Ghana|Gibraltar|Greece|Greenland|Grenada|Guadeloupe|Guam|Guatemala|Guernsey|Guinea|Guinea-Bissau|Guyana|Haiti|Heard Island and McDonald Islands|Holy See|Honduras|Hong Kong|Hungary|Iceland|India|Indonesia|Iran \(Islamic Republic of\)|Iraq|Ireland|Isle of Man|Israel|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|Portugal|Puerto Rico|Qatar|Réunion|Romania|Russian Federation|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|Spain|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|
|
56
56
|
(?i:autres?\s+de|probab|likely|possibl(e|y)|doubtful)|
|
57
57
|
\b\s*(?i:maybe)\s*\b|
|
58
58
|
\b\s*(?i:prob)\.\s*\b|
|
@@ -92,7 +92,7 @@ module DwcAgent
|
|
92
92
|
FNA|DAO|HUH|FDNMB|MNHN|PNI|USNM|ZMUC|CSIRO|ACAD|USGS|NAWQA|
|
93
93
|
(?i:para|topo|syn|holo|allo|choro|eco|iso|isoepi|isopara|karyo|morpho|neo|mero|pala|paralecto|paraneo|photo|schizo)?(?i:types?\:?)|
|
94
94
|
AFSC\/POLISH\s+SORTING\s+CTR\.?|
|
95
|
-
(?i:university|
|
95
|
+
(?i:university|mus(e|é)um|exhibits?)|
|
96
96
|
(?i:uqam)|
|
97
97
|
(?i:sem\s+(colec?tor|data))|
|
98
98
|
(?i:no\s+coll\.?(ector)?)|
|
@@ -111,13 +111,14 @@ module DwcAgent
|
|
111
111
|
(\(|\{|\[).{1,}(\)|\]|\})|
|
112
112
|
(\(|\[|\{).{1,}\z|
|
113
113
|
\b(?i:leg)[\.:]?\s*\b|
|
114
|
-
(
|
114
|
+
(?:[Dd](ed|on))[\.:]|
|
115
115
|
\d*[A-Za-z]*\d*-\d*\z|
|
116
116
|
\s+[A-Z]*\d+\z|
|
117
117
|
\s+\d+[A-Za-z]+\z|
|
118
118
|
^[-,.\s;*\d]+\s?|
|
119
119
|
\s*?-{2,}\s*?|
|
120
120
|
^(?i:exc?p?)[:.]\s*|
|
121
|
+
\:?\s*(?i:exch)(\b|\z)|
|
121
122
|
\s+de\s*$|
|
122
123
|
\.{2,}$
|
123
124
|
}x
|
@@ -194,7 +195,10 @@ module DwcAgent
|
|
194
195
|
SEPARATORS = {
|
195
196
|
"^(\\S{4,},\\s+(?:\\S\\.\\s*){1,})\\s+(\\S{4,},\\s+(?:\\S\.\\s*){1,})$" => "\\1 | \\2",
|
196
197
|
"(\\S{1}\\.)([[:alpha:]]{2,})" => "\\1 \\2",
|
197
|
-
"(\\w*),?\\s+(.*)\\s+(van|von)$" => "\\3 \\1, \\2"
|
198
|
+
"(\\w*),?\\s+(.*)\\s+(van|von)$" => "\\3 \\1, \\2",
|
199
|
+
"^([A-Z.\\s]+)\\s+(?:and|&|et|e)\\s+([A-Z.\\s]+)\\s+(\\w{2,})(.*)" => "\\1 \\3 | \\2 \\3 | \\4",
|
200
|
+
"^([A-Z]\\w{2,}),\\s*?([A-Z]\\w{2,})\\s*?[,&]\\s*?([A-Z]\\w{2,})$" => "\\1 | \\2 | \\3",
|
201
|
+
"^([A-Z]\\w{2,}),\\s*?([A-Z]\\w{2,}),\\s*?([A-Z]\\w{2,})\\s*?[,&]\\s*?([A-Z]\\w{3,})$" => "\\1 | \\2 | \\3 | \\4"
|
198
202
|
}
|
199
203
|
|
200
204
|
BLACKLIST = %r{
|
@@ -227,6 +231,7 @@ module DwcAgent
|
|
227
231
|
(?i:o?\.?m\.?n\.?r\.?)|
|
228
232
|
(?i:measurement)|
|
229
233
|
(?i:ent(o|y)mology)|
|
234
|
+
(?i:malacology)|
|
230
235
|
(?i:geographic)|
|
231
236
|
(?i:mus(eum|ée)|universit(y|é|e|at)|college|institute?|acad(e|é)m|school|écol(e|iers?)|laboratoi?r|projec?t|polytech|dep(t|art?ment)|research|clinic|hospital|cientifica|sanctuary|safari)|
|
232
237
|
(?i:univ\.)|
|
@@ -295,11 +300,19 @@ module DwcAgent
|
|
295
300
|
"dissection",
|
296
301
|
"entered",
|
297
302
|
"erased",
|
303
|
+
"expd",
|
304
|
+
"expdn",
|
305
|
+
"hist",
|
306
|
+
"historical",
|
307
|
+
"historie",
|
298
308
|
"indecipherable",
|
309
|
+
"inst",
|
299
310
|
"nomenclatural",
|
300
311
|
"orig",
|
312
|
+
"qld",
|
301
313
|
"registration",
|
302
314
|
"science",
|
315
|
+
"study",
|
303
316
|
"wg",
|
304
317
|
"wm",
|
305
318
|
"wn",
|
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: 1.5.1.
|
4
|
+
version: 1.5.1.9
|
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: 2021-
|
11
|
+
date: 2021-03-23 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: namae
|