dwc_agent 1.5.0.1 → 1.5.0.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8c68777377378c1b85c2a86e4dbd72c8115233a9b86fd3d9233fa273b395b6bf
-  data.tar.gz: b1cef19d499caab6280b2084d3b4ce9f8fdabc7d2b34bce5334c3e40471e6f08
+  metadata.gz: 4b3360ae9a26c61f08d3a687e8c4e1af9e19334714746a976cb4c90e93d72a63
+  data.tar.gz: 4ada728f04c124ec1fbd6a9b45c1ecba80f45319f051a087c2074b2417110478
 SHA512:
-  metadata.gz: 561146115cc194b0e4a03e25d9bebc99f266dfc5b2b294f576b3cd0e4be21f2566b5a1453f3aac29f9a759bea918ba6e967885f99f19cb041231948c88ff3627
-  data.tar.gz: 83362e1759206a8cca73e27563c456cb3ad521b9fa719868bdb8bda8f9a8a69548e5b43ac5736ba7bace4ec46f30adb3992e933bfe9f0b7768eab46561479435
+  metadata.gz: ced6e4cd9352b267ee8662993d4a39c9aa6e35965c550fef33993bd3c7c40feb07e7ad1ac8e6c60531f843b5e3d18a5bc0caafb38de41b55f0ad706be898d81a
+  data.tar.gz: 4c3c76a1f3cf17114d9e23a2ec19f40772fe38b5bd1b6dd49264cf82081dac797b182ae0a2cd5d90732a0f3cd947251ea28830f7769a82d4bfe8a10ca166213e

data/lib/dwc_agent/cleaner.rb

@@ -18,10 +18,6 @@ module DwcAgent
     def clean(parsed_namae)
       blank_name = { title: nil, appellation: nil, given: nil, particle: nil, family: nil, suffix: nil }
 
-      if parsed_namae.family && FAMILY_BLACKLIST.any?{ |s| s.casecmp(parsed_namae.family) == 0 }
-        return blank_name
-      end
-
       if parsed_namae.given && GIVEN_BLACKLIST.any?{ |s| s.casecmp(parsed_namae.given) == 0 }
         return blank_name
       end
@@ -30,7 +26,7 @@ module DwcAgent
         return blank_name
       end
 
-      if parsed_namae.given && parsed_namae.given.length > 25
+      if parsed_namae.given && parsed_namae.given.length > 35
         return blank_name
       end
 
@@ -79,6 +75,10 @@ module DwcAgent
         parsed_namae.given = NameCase(parsed_namae.given)
       end
 
+      if parsed_namae.family && FAMILY_BLACKLIST.any?{ |s| s.casecmp(parsed_namae.family) == 0 }
+        return blank_name
+      end
+
       parsed_namae.normalize_initials
 
       family = parsed_namae.family.gsub(/\.\z/, '').strip rescue nil

data/lib/dwc_agent/constants.rb

@@ -6,15 +6,16 @@ module DwcAgent
     \s*?\d+\.\d+|
     \b\d+\(?(?i:[[:alpha:]])\)?\b|
     \b[,;]?\s*(?i:et\.?\s+al|&\s+al)\.?|
+    \b[,;]?\s*(?i:etal)\.?|
     \b\s+(bis|ter)(\b|\z)|
     \bu\.\s*a\.|
-    \b[,;]?\s*(?i:and|&)?\s*(?i:others)\s*\b|
+    \b[,;]?\s*(?i:and|&)?\s*(?i:others|party)\s*\b|
     \b[,;]?\s*(?i:etc)\.?|
     \b[,;]?\s*(?i:on)\b|
     \b[,;]?\s*(?i:unkn?own)\b|
     \b[,;]?\s*(?i:n/a)\b|
     \b[,;]?\s*(?i:ann?onymous)\b|
-    \b[,;]?\s*\(?(?i:undetermined|indeterminable|dummy|interim|accession|ill(eg|is)ible|scripsit|presumed?)\)?\b|
+    \b[,;]?\s*\(?(?i:undetermined|indeterminable|dummy|interim|accession|ill(eg|is)ible|scripsit|presumed?|presumably)\)?\b|
     \b[,;]?\s*(?i:importer|gift)\:?\b|
     \b[,;]?\s*(?i:string)\b|
     \b[,;]?\s*(?i:person\s*string)\b|
@@ -49,33 +50,36 @@ module DwcAgent
     \d+\s+(?i:Nov|Novemb(er|re))\.?\b|
     \d+\s+(?i:Dec|D(e|é)cemb(er|re))\.?\b|
     \b[.-–,;:/]?\s*(?i:Alabama|Alaska|Arizona|Arkansas|California|Colorado|Connecticut|Delaware|Evergreen|Florida|Georgia|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|Virginia|Washington|West\s+Virginia|Wisconsin|Wyoming)\s+(?i:State)\s*\b|
-    \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|Georgia|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|Jordan|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[.,;:/]?\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|Georgia|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|Jordan|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|
     (?i:autres?\s+de|probab|likely|possibl(e|y)|doubtful)|
     \b\s*(?i:maybe)\s*\b|
     \b\s*(?i:prob)\.\s*\b|
-    \(?[,]?\s*?(?i:(local)?\s?collector|data\s*recorder|netter|(oper|prepar)ator)\(?s?\)?\.?\:?|
+    \(?[,]?\s*?(?i:(local)?\s?collectors?|data\s*recorder|netter|(oper|prepar)ator)\(?s?\)?\.?\:?|
     \b[.-–,;:]?\s*(?i:department|faculty)\s*?(?i:of)?\s*?(?i:entomology|biology|zoology)|
     (?i:Engº|Agrº|Fcº|Drº|Mº|Profº|Dº|Fº)|
     (?i:fide)\:?\s*\b|
+    (?i:first\s+name\s+unknown)|
     (?i:game\s+dept)\.?\s*\b|
     (?i:see\s+notes?\s*(inside)?)|
     (?i:see\s+letter\s+enclosed)|
     (?i:(by)?\s+correspondance)|
-    (?i:pers\.?\s+comm\.?)|
+    (?i:pers\.?\s*comm\.?)|
     (?i:crossed\s+out)|
     \(?(?i:source)\(?|
     (?i:according\s+to)|
     (?i:lanuv)\d+|
+    \b\s*name\b|
+    \b\s*lost\b|
     (?i:nswobs)|
     ORCID|
     MRI(\s|-)PAS|
     urn\:qm\.qld\.gov\.au\:collector|
     (?i:University\s+of\s+(Southern\s+)?California(,\s+Berkeley)?)|
-    (?i:Field\s+Museum\s+of\s+Natural\s+History)|
-    (?i:American\s+Museum\s+of\s+Natural\s+History)|
+    (?i:field\s+museum\s+of\s+natural\s+history)|
+    (?i:american\s+museum\s+of\s+natural\s+history)|
     (?i:The\s+Paleontological\s+Research\s+Institution)|
     (?i:museums?\s+victoria)|
-    \b\s*(?i:United\s+States|Russia)\s*\b|
+    \b\s*(?i:united\s+states|russia)\s*\b|
     (?i:revised|photograph|fruits\s+only)|
     -?\s*(?i:sight\s+(id|identifi?cation))\.?\s*\b|
     -?\s*(?i:synonym(y|ie))|
@@ -83,11 +87,14 @@ module DwcAgent
     \b(?i:to\s+(sub)?spp?)\.?|
     (?i:nom\.?\s+rev\.?)|
     FNA|DAO|HUH|FDNMB|MNHN|PNI|USNM|ZMUC|CSIRO|ACAD|USGS|NAWQA|
+    \b,?\s*(?i:para|topo|syn)?(?i:type)|
     AFSC\/POLISH\s+SORTING\s+CTR\.?|
     (?i:university|museum|exhibits?)|
     (?i:uqam)|
     (?i:sem\s+(colec?tor|data))|
     (?i:no\s+coll\.?(ector)?)|
+    (?i:not?)\s+(?i:name|date|details?|specific)?\s*?(?i:given|name|date|noted)|
+    (?i:non?)\s+(?i:specificato)|
     \b[,;]\s+\d+\z|
     ["!@?]|
     [,]?\d+|
@@ -113,19 +120,22 @@ module DwcAgent
     [–|ǀ∣｜│&+\/;:]|
     \s+-\s+|
     \s+a\.\s+|
-    \b(e|y|i|en|et|or|per|for)\s*\b|
+    \b(con|e|y|i|en|et|or|per|for)\s*\b|
     \b(?i:and|with)\s*\b|
     \b(?i:annotated(\s+by)?)\s*\b|
     \b(?i:coll\.)\s*\b|
     \b(?i:communicate?d(\s+to)?)\s*\b|
     \b(?i:conf\.?(\s+by)?|confirmed(\s+by)?)\s*\b|
+    \b(?i:confirmada)(\s+por)?\s*\b|
     \b(?i:checked?(\s+by)?)\s*\b|
     \b(?i:det\.?(\s+by)?)\s*\b|
     \b(?i:dupl?\.?(\s+by)?|duplicate(\s+by)?)\s*\b|
     \b(?i:ex\.?(\s+by)?|examined(\s+by)?)\s*\b|
     \b(?i:in?dentified(\s+by)?)\s*\b|
     \b(?i:in\s+part(\s+by)?)\s*\b|
+    \b(?i:och)\s*\b|
     \b(?i:prep\.?\s+(?i:by)?)\s*\b|
+    \b(?i:purchased?)(\s+by)?\s*\b|
     \b(?i:redet\.?(\s+by?)?)\s*\b|
     \b(?i:reidentified(\s+by)?)\s*\b|
     \b(?i:stet)\s*\b|
@@ -155,16 +165,24 @@ module DwcAgent
     '}' => '',
     '@' => '',
     '%' => '',
-    '\\' => ''
+    '\\' => '',
+    '´' => '\'',
+    '+' => ' | '
   }
 
   PHRASE_SUBS = {
-    'prof\.' => 'Prof. ',
-    '\, ph\.d\.' => ' Ph.D.',
-    '\, bro\.' => ' Bro.',
-    ' jr\.\,' => ' Jr.;',
-    ' jr\,' => ' Jr.;',
-    '\-jr' => ' Jr.'
+    ', ph.d.' => ' Ph.D.',
+    ', Ph.D.' => ' Ph.D.',
+    ', bro.' => ' Bro.',
+    ', Jr.,' => ' Jr.;',
+    ', Jr.' => ' Jr.',
+    ',Jr.' => ' Jr.',
+    ', Sr.' => ' Sr.',
+    ',Sr.' => ' Sr.',
+    ' jr.,' => ' Jr.;',
+    ' jr,' => ' Jr.;',
+    '-jr' => ' Jr.',
+    '-Jr' => ' Jr.'
   }
 
   COMPLEX_SEPARATORS = %r{
@@ -229,7 +247,7 @@ module DwcAgent
     (?i:though)|
     (?i:texas\s+instruments?)\s*?(for)?|
     (?:tropical)|
-    (?i:toward|seen at)|
+    (?i:toward|seen\s+at)|
     (?i:unidentified|unspecified|unk?nown?|unnamed|unread|unmistak|no agent)|
     (?i:urn\:)|
     (?i:usda|ucla)|
@@ -238,29 +256,47 @@ module DwcAgent
   }x
 
   FAMILY_BLACKLIST = [
+    "ap",
     "da",
+    "de",
     "de'",
     "del",
     "der",
+    "di",
+    "do",
+    "dos",
     "du",
     "el",
+    "le",
+    "la",
     "van",
     "von",
     "the",
     "of",
     "adjustment",
+    "annotator",
     "available",
     "arachnology",
     "catalogue",
     "curators",
     "data",
+    "details",
+    "determiner",
     "determination",
     "dissection",
     "entered",
+    "erased",
+    "indecipherable",
     "nomenclatural",
     "orig",
     "registration",
-    "science"
+    "science",
+    "wg",
+    "wm",
+    "wn",
+    "zw",
+    "zz",
+    "z-"
   ]
 
   GIVEN_BLACKLIST = [
@@ -268,7 +304,7 @@ module DwcAgent
     "has not"
   ]
 
-  TITLE = /\s*\b(sir|count(ess)?|colonel|(gen|adm|col|maj|capt|cmdr|lt|sgt|cpl|pvt|prof|dr|md|ph\.?d|rev|mme|abbé|ptre|bro|esq)\.?|docteur|father|cantor|vicar|père|pastor|rabbi|reverend|pere|soeur|sister|professor)(\s+|$)/i
+  TITLE = /\s*\b(sir|count(ess)?|colonel|(gen|adm|col|maj|major|capt|cmdr|lt|sgt|cpl|pvt|proff?|dr|md|ph\.?d|rev|mme|abbé|ptre|bro|esq)\.?|docteur|father|cantor|vicar|père|pastor|rabbi|reverend|pere|soeur|sister|professor)(\s+|$)/i
 
   APPELLATION = /\s*\b((mrs?|ms|fr|hr)\.?|miss|herr|frau)(\s+|$)/i
 

data/lib/dwc_agent/parser.rb

@@ -20,7 +20,7 @@ module DwcAgent
       @strip_out_regex = Regexp.new STRIP_OUT.to_s
       @residual_terminators_regex = Regexp.new SPLIT_BY.to_s + %r{\s*\z}.to_s
       @char_subs_regex = Regexp.new [CHAR_SUBS.keys.join].to_s
-      @phrase_subs_regex = Regexp.new PHRASE_SUBS.keys.join('|').to_s, Regexp::IGNORECASE
+      @phrase_subs_regex = Regexp.new PHRASE_SUBS.keys.map{|a| Regexp.escape a }.join('|').to_s
       @complex_separators_regex = Regexp.new COMPLEX_SEPARATORS.to_s
       @add_separators_regex = Regexp.new %r{(\S{1}\.)([[:alpha:]]{2,})}.to_s
     end

data/lib/dwc_agent/version.rb

@@ -4,7 +4,7 @@ module DwcAgent
     MAJOR = 1
     MINOR = 5
     PATCH = 0
-    BUILD = 1
+    BUILD = 6
 
     def self.version
       [MAJOR, MINOR, PATCH, BUILD].compact.join('.').freeze

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: dwc_agent
 version: !ruby/object:Gem::Version
-  version: 1.5.0.1
+  version: 1.5.0.6
 platform: ruby
 authors:
 - David P. Shorthouse
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-08-07 00:00:00.000000000 Z
+date: 2020-09-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: namae
@@ -102,7 +102,7 @@ homepage: https://github.com/bionomia/dwc_agent
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options:
 - "--encoding"
 - UTF-8
@@ -119,8 +119,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.6
-signing_key: 
+rubygems_version: 3.1.2
+signing_key:
 specification_version: 4
 summary: Parse Darwin Core agent terms such as recordedBy and identifiedBy
 test_files: []