dwc_agent 1.5.0.9 → 1.5.1.4
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 +15 -8
- data/lib/dwc_agent/parser.rb +2 -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: ae783fe8734f3f5bccf180ced2e9e3a88e9ef1769545c61a6184d18c4d9c27d7
|
4
|
+
data.tar.gz: 7dfd1c084d067f25f9392961892c3157cee6dd54fee33130a8ef5f6d9ba0c3b6
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 18fe383434e7e6fe9544db0a17110c8b2e88ecb816687e69eb95b19accc67d1c5fb3fda1cab503938932a66a9960240486a12968d10fbd04c3a2bcc60f91c719
|
7
|
+
data.tar.gz: 7aa8a268dd56f2f4aa64f743523a389178afb6e609ee950e0e2473809a51971201869f7281f87b01e4a50e80b6193171b5c8e5c75747a2bc6d037b6368b7f9a6
|
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|
|
@@ -51,7 +52,7 @@ module DwcAgent
|
|
51
52
|
\d+\s+(?i:Nov|Novemb(er|re))\.?\b|
|
52
53
|
\d+\s+(?i:Dec|D(e|é)cemb(er|re))\.?\b|
|
53
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|
|
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|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|
|
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|
|
@@ -89,7 +90,7 @@ module DwcAgent
|
|
89
90
|
\b(?i:to\s+(sub)?spp?)\.?|
|
90
91
|
(?i:nom\.?\s+rev\.?)|
|
91
92
|
FNA|DAO|HUH|FDNMB|MNHN|PNI|USNM|ZMUC|CSIRO|ACAD|USGS|NAWQA|
|
92
|
-
|
93
|
+
(?i:para|topo|syn|holo|allo|choro|eco|iso|isoepi|isopara|karyo|morpho|neo|mero|pala|paralecto|paraneo|photo|schizo)?(?i:types?\:?)|
|
93
94
|
AFSC\/POLISH\s+SORTING\s+CTR\.?|
|
94
95
|
(?i:university|museum|exhibits?)|
|
95
96
|
(?i:uqam)|
|
@@ -111,11 +112,14 @@ module DwcAgent
|
|
111
112
|
(\(|\[|\{).{1,}\z|
|
112
113
|
\b(?i:leg)[\.:]?\s*\b|
|
113
114
|
(?i:ded)\:|
|
115
|
+
\d*[A-Za-z]*\d*-\d*\z|
|
116
|
+
\s+[A-Z]*\d+\z|
|
117
|
+
\s+\d+[A-Za-z]+\z|
|
114
118
|
^[-,.\s;*\d]+\s?|
|
115
|
-
-\d?\z|
|
116
119
|
\s*?-{2,}\s*?|
|
117
120
|
^(?i:exc?p?)[:.]\s*|
|
118
|
-
\s+de\s
|
121
|
+
\s+de\s*$|
|
122
|
+
\.{2,}$
|
119
123
|
}x
|
120
124
|
|
121
125
|
SPLIT_BY = %r{
|
@@ -187,9 +191,11 @@ module DwcAgent
|
|
187
191
|
'-Jr' => ' Jr.'
|
188
192
|
}
|
189
193
|
|
190
|
-
|
191
|
-
^(
|
192
|
-
|
194
|
+
SEPARATORS = {
|
195
|
+
"^(\\S{4,},\\s+(?:\\S\\.\\s*){1,})\\s+(\\S{4,},\\s+(?:\\S\.\\s*){1,})$" => "\\1 | \\2",
|
196
|
+
"(\\S{1}\\.)([[:alpha:]]{2,})" => "\\1 \\2",
|
197
|
+
"(\\w*),?\\s+(.*)\\s+(van|von)$" => "\\3 \\1, \\2"
|
198
|
+
}
|
193
199
|
|
194
200
|
BLACKLIST = %r{
|
195
201
|
(?i:abundant)|
|
@@ -213,6 +219,7 @@ module DwcAgent
|
|
213
219
|
(?i:exc?s?icc?at(a|i))|
|
214
220
|
(?i:evidence)|
|
215
221
|
(?i:exporter)|
|
222
|
+
(?i:foundation)|
|
216
223
|
(?i:ichthyology)|
|
217
224
|
(?i:inconn?u)|
|
218
225
|
(?i:internation|gou?vern|ministry|extension|unit|district|provincial|na(c|t)ional|military|region|environ|natur(e|al)|naturelles|division|program|direction|national)|
|
@@ -241,7 +248,7 @@ module DwcAgent
|
|
241
248
|
(?i:skeleton)|
|
242
249
|
(?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)|
|
243
250
|
(?i:submersible)|
|
244
|
-
(?i:synonymy?)|
|
251
|
+
(?i:synonymy?)|
|
245
252
|
(?i:systematic|perspective)|
|
246
253
|
\s+(?i:off)\s+|
|
247
254
|
\s*(?i:too)\s+|\s*(?i:the)\s+|
|
data/lib/dwc_agent/parser.rb
CHANGED
@@ -16,13 +16,10 @@ module DwcAgent
|
|
16
16
|
suffix: SUFFIX
|
17
17
|
}
|
18
18
|
@namae = Namae::Parser.new(options)
|
19
|
-
|
20
19
|
@strip_out_regex = Regexp.new STRIP_OUT.to_s
|
21
|
-
@residual_terminators_regex = Regexp.new SPLIT_BY.to_s + %r{\s*\z}.to_s
|
22
20
|
@char_subs_regex = Regexp.new [CHAR_SUBS.keys.join].to_s
|
23
21
|
@phrase_subs_regex = Regexp.new PHRASE_SUBS.keys.map{|a| Regexp.escape a }.join('|').to_s
|
24
|
-
@
|
25
|
-
@add_separators_regex = Regexp.new %r{(\S{1}\.)([[:alpha:]]{2,})}.to_s
|
22
|
+
@residual_terminators_regex = Regexp.new SPLIT_BY.to_s + %r{\s*\z}.to_s
|
26
23
|
end
|
27
24
|
|
28
25
|
# Parses the passed-in string and returns a list of names.
|
@@ -35,8 +32,7 @@ module DwcAgent
|
|
35
32
|
name.gsub!(/\[|\]/, '')
|
36
33
|
name.gsub!(@char_subs_regex, CHAR_SUBS)
|
37
34
|
name.gsub!(@phrase_subs_regex, PHRASE_SUBS)
|
38
|
-
name.gsub!(
|
39
|
-
name.gsub!(@complex_separators_regex, '\1 | \2')
|
35
|
+
SEPARATORS.each{|key, value| name.gsub!(Regexp.new(key), value)}
|
40
36
|
name.gsub!(@residual_terminators_regex, '')
|
41
37
|
name.squeeze!(' ')
|
42
38
|
name.strip!
|
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: 1.5.1.4
|
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:
|
11
|
+
date: 2021-01-08 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: namae
|
@@ -119,7 +119,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
119
119
|
- !ruby/object:Gem::Version
|
120
120
|
version: '0'
|
121
121
|
requirements: []
|
122
|
-
rubygems_version: 3.
|
122
|
+
rubygems_version: 3.2.4
|
123
123
|
signing_key:
|
124
124
|
specification_version: 4
|
125
125
|
summary: Parse Darwin Core agent terms such as recordedBy and identifiedBy
|