dwc_agent 1.5.0.7 → 1.5.1.2
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/cleaner.rb +1 -1
- data/lib/dwc_agent/constants.rb +12 -6
- data/lib/dwc_agent/version.rb +2 -2
- metadata +3 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 46975c588975ffd636e3c07506e27c0121e9af9acbc1e7b36275bedb5bc67f29
|
4
|
+
data.tar.gz: c39f8a7f561fa69abc0ba5cb0f8a67d545f63356dc28c7eb27c465ac20824c3c
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: d974871f6ce3c31424d2802bff332190b702cacb1008e82c2827f63da30643506b71b484be05c436a4d6cf2f8ab841979bd626ee721a8a4230e07fe2b96b97c4
|
7
|
+
data.tar.gz: 8ade64986b8f7774cfdc8bb9170a1ad3134b0ec6dc84d81aab1909175f1ec48af1df260c10bb7c113b73ae1da16f6f0163fcf8fd57b3579c718666f31fe8aac7
|
data/lib/dwc_agent/cleaner.rb
CHANGED
data/lib/dwc_agent/constants.rb
CHANGED
@@ -12,6 +12,7 @@ module DwcAgent
|
|
12
12
|
\bu\.\s*a\.|
|
13
13
|
\b[,;]?\s*(?i:and|&)?\s*(?i:others|party)\s*\b|
|
14
14
|
\b[,;]?\s*(?i:etc)\.?|
|
15
|
+
\b[,;]?\s*(?i:exp)\.?\s*(\b|\z)|
|
15
16
|
\b[,;]?\s*(?i:on)\b|
|
16
17
|
\b[,;]?\s*(?i:unkn?own)\b|
|
17
18
|
\b[,;]?\s*(?i:n/a)\b|
|
@@ -50,8 +51,8 @@ module DwcAgent
|
|
50
51
|
\d+\s+(?i:Oct|Octob(er|re))\.?\b|
|
51
52
|
\d+\s+(?i:Nov|Novemb(er|re))\.?\b|
|
52
53
|
\d+\s+(?i:Dec|D(e|é)cemb(er|re))\.?\b|
|
53
|
-
\b[.-–,;:/]?\s*(?i:Alabama|Alaska|Arizona|Arkansas|California|Colorado|Connecticut|Delaware|Evergreen|Florida|
|
54
|
-
\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|
|
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|Montserrat|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|
|
55
56
|
(?i:autres?\s+de|probab|likely|possibl(e|y)|doubtful)|
|
56
57
|
\b\s*(?i:maybe)\s*\b|
|
57
58
|
\b\s*(?i:prob)\.\s*\b|
|
@@ -66,6 +67,7 @@ module DwcAgent
|
|
66
67
|
(?i:(by)?\s+correspondance)|
|
67
68
|
(?i:pers\.?\s*comm\.?)|
|
68
69
|
(?i:crossed\s+out)|
|
70
|
+
(?i:(ohne|keine)\s+angaben)|
|
69
71
|
\(?(?i:source)\(?|
|
70
72
|
(?i:according\s+to)|
|
71
73
|
(?i:lanuv)\d+|
|
@@ -88,7 +90,7 @@ module DwcAgent
|
|
88
90
|
\b(?i:to\s+(sub)?spp?)\.?|
|
89
91
|
(?i:nom\.?\s+rev\.?)|
|
90
92
|
FNA|DAO|HUH|FDNMB|MNHN|PNI|USNM|ZMUC|CSIRO|ACAD|USGS|NAWQA|
|
91
|
-
|
93
|
+
(?i:para|topo|syn|holo|allo|choro|eco|iso|isoepi|isopara|karyo|morpho|neo|mero|pala|paralecto|paraneo|photo|schizo)?(?i:types?\:?)|
|
92
94
|
AFSC\/POLISH\s+SORTING\s+CTR\.?|
|
93
95
|
(?i:university|museum|exhibits?)|
|
94
96
|
(?i:uqam)|
|
@@ -110,11 +112,14 @@ module DwcAgent
|
|
110
112
|
(\(|\[|\{).{1,}\z|
|
111
113
|
\b(?i:leg)[\.:]?\s*\b|
|
112
114
|
(?i:ded)\:|
|
115
|
+
\d*[A-Za-z]*\d*-\d*\z|
|
116
|
+
\s+[A-Z]*\d+\z|
|
117
|
+
\s+\d+[A-Za-z]+\z|
|
113
118
|
^[-,.\s;*\d]+\s?|
|
114
|
-
-\d?\z|
|
115
119
|
\s*?-{2,}\s*?|
|
116
120
|
^(?i:exc?p?)[:.]\s*|
|
117
|
-
\s+de\s
|
121
|
+
\s+de\s*$|
|
122
|
+
\.{2,}$
|
118
123
|
}x
|
119
124
|
|
120
125
|
SPLIT_BY = %r{
|
@@ -212,6 +217,7 @@ module DwcAgent
|
|
212
217
|
(?i:exc?s?icc?at(a|i))|
|
213
218
|
(?i:evidence)|
|
214
219
|
(?i:exporter)|
|
220
|
+
(?i:foundation)|
|
215
221
|
(?i:ichthyology)|
|
216
222
|
(?i:inconn?u)|
|
217
223
|
(?i:internation|gou?vern|ministry|extension|unit|district|provincial|na(c|t)ional|military|region|environ|natur(e|al)|naturelles|division|program|direction|national)|
|
@@ -240,7 +246,7 @@ module DwcAgent
|
|
240
246
|
(?i:skeleton)|
|
241
247
|
(?i:survey|assessment|station|monitor|stn\.|index|project|bureau|engine|(e|é)x?chang(e|é)s?|ex(c|k)ursi(e|o|ó)n?|exped\.?|exp(e|i)di(c|t)i(e|o|ó)n?|experiment|explora(d|t)|festival|generation|inventory|marine|service)|
|
242
248
|
(?i:submersible)|
|
243
|
-
(?i:synonymy?)|
|
249
|
+
(?i:synonymy?)|
|
244
250
|
(?i:systematic|perspective)|
|
245
251
|
\s+(?i:off)\s+|
|
246
252
|
\s*(?i:too)\s+|\s*(?i:the)\s+|
|
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.
|
4
|
+
version: 1.5.1.2
|
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-
|
11
|
+
date: 2020-11-26 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: namae
|
@@ -112,7 +112,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
112
112
|
requirements:
|
113
113
|
- - "~>"
|
114
114
|
- !ruby/object:Gem::Version
|
115
|
-
version: '2.
|
115
|
+
version: '2.7'
|
116
116
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
117
117
|
requirements:
|
118
118
|
- - ">="
|