dwc_agent 1.5.1.0 → 1.5.1.5

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: 3b4adb16325e2c9ac0cd8ed23eb0c9455632d447b942c765af5fb1876b821ab1
4
- data.tar.gz: f9890ec976e2626700939134fc7f5ba3b5a5dea6eae94cea3f39579b208e2ee8
3
+ metadata.gz: 60fb91c31b1d74e63657e5c8ba4e7993d521524303689b74110d17e61e3cadf9
4
+ data.tar.gz: 8e38c2448aa5c059a0437fd14a47c0c6d9fa77e4a00b5a4a3269b0a10b2d0e18
5
5
  SHA512:
6
- metadata.gz: 1b9f1998b5edb9d6c5931e2fc1b87c46078875ac9715979f6ae0a7924f08c78731b05ead538c832d32f3e6025c102f18fa575a875186fdd9207f9bbc78f1c16c
7
- data.tar.gz: 451672cdf4a81718096534247d46e73c3bf56770b646e0b67ea401d8e194c7acf21edfd7f2223acd0d75def6fe9848734f891be3d67a93fe277af94d69fbc192
6
+ metadata.gz: a1a7fe93b0dbffd440cd68f4e1ffd330bf5cc66deae97e4414bf17d25784662b94e545c24203a7c184b122f96e30dc022bdeb906456c3a17ad3830739acab16d
7
+ data.tar.gz: 15d764c70cc733f1534ce552322f994d224d5e702b8e0cdccb085fd53a5f12320d4dacb862b7a9413b3144980f4856d5e32451516c0f22beff51935295a3c581
@@ -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|Mali|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
+ \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
- \b,?\s*(?i:para|topo|syn)?(?i:type)|
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)|
@@ -190,9 +191,12 @@ module DwcAgent
190
191
  '-Jr' => ' Jr.'
191
192
  }
192
193
 
193
- COMPLEX_SEPARATORS = %r{
194
- ^(\S{4,},\s+(?:\S\.\s*){1,})\s+(\S{4,},\s+(?:\S\.\s*){1,})$
195
- }x
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
+ "^([A-Z.]+)\\s+(?:and|&)\\s+([A-Z.]+)\\s+(.*)$" => "\\1 \\3 | \\2 \\3"
199
+ }
196
200
 
197
201
  BLACKLIST = %r{
198
202
  (?i:abundant)|
@@ -216,6 +220,7 @@ module DwcAgent
216
220
  (?i:exc?s?icc?at(a|i))|
217
221
  (?i:evidence)|
218
222
  (?i:exporter)|
223
+ (?i:foundation)|
219
224
  (?i:ichthyology)|
220
225
  (?i:inconn?u)|
221
226
  (?i:internation|gou?vern|ministry|extension|unit|district|provincial|na(c|t)ional|military|region|environ|natur(e|al)|naturelles|division|program|direction|national)|
@@ -244,7 +249,7 @@ module DwcAgent
244
249
  (?i:skeleton)|
245
250
  (?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)|
246
251
  (?i:submersible)|
247
- (?i:synonymy?)|(topo|syn|holo)type|
252
+ (?i:synonymy?)|
248
253
  (?i:systematic|perspective)|
249
254
  \s+(?i:off)\s+|
250
255
  \s*(?i:too)\s+|\s*(?i:the)\s+|
@@ -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
- @complex_separators_regex = Regexp.new COMPLEX_SEPARATORS.to_s
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!(@add_separators_regex, '\1 \2')
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!
@@ -4,7 +4,7 @@ module DwcAgent
4
4
  MAJOR = 1
5
5
  MINOR = 5
6
6
  PATCH = 1
7
- BUILD = 0
7
+ BUILD = 5
8
8
 
9
9
  def self.version
10
10
  [MAJOR, MINOR, PATCH, BUILD].compact.join('.').freeze
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: 1.5.1.0
4
+ version: 1.5.1.5
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: 2020-10-07 00:00:00.000000000 Z
11
+ date: 2021-01-10 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: 3.1.2
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