@larsgw/formica 0.8.0 → 0.8.2

package/CHANGELOG.md

@@ -1,3 +1,28 @@
+## [0.8.2](https://github.com/identification-resources/formica/compare/v0.8.1...v0.8.2) (2025-06-26)
+
+
+### Bug Fixes
+
+* **resources:** add support for documented flag ([6cb89e4](https://github.com/identification-resources/formica/commit/6cb89e428bde8665b7e8f03b5c7f47a44e15f58e))
+* **resources:** allow hyphens in biname pattern ([6a58a77](https://github.com/identification-resources/formica/commit/6a58a77757b8b6ae8c2d7d01440775776d183d05))
+
+
+
+## [0.8.1](https://github.com/identification-resources/formica/compare/v0.8.0...v0.8.1) (2025-05-30)
+
+
+### Bug Fixes
+
+* **catalog:** fix aspects of linked data ([1b2964f](https://github.com/identification-resources/formica/commit/1b2964f46b8409c6a67f0475faf067a80734288c))
+* **catalog:** set display_name to required, as documented ([3f36909](https://github.com/identification-resources/formica/commit/3f36909bbe6261cbee022139050875de37174611))
+
+
+### Features
+
+* **resources:** add support for "(sub)gen. nov" pattern ([d2598eb](https://github.com/identification-resources/formica/commit/d2598ebfd2f80d9c2bcc00ce145b9fc229316e5b))
+
+
+
 # [0.8.0](https://github.com/identification-resources/formica/compare/v0.7.3...v0.8.0) (2025-05-07)
 
 

package/lib/bin/generate-linked-data.js

@@ -129,7 +129,6 @@ var SCOPES = {
     'queens': ['dwc:caste', 'queen'],
     'workers': ['dwc:caste', 'worker'],
     'soldiers': ['dwc:caste', 'soldier'],
-    'alates': ['dwc:caste', 'alate'],
     'alatae': ['dwc:caste', 'alate'],
     'apterae': ['dwc:caste', 'aptera'],
     'viviparae': ['dwc:caste', 'vivipara'],
@@ -151,7 +150,9 @@ var PREFIXES = {
     'dwciri': 'http://rs.tdwg.org/dwc/iri/',
     'foaf': 'http://xmlns.com/foaf/0.1/',
     'owl': 'http://www.w3.org/2002/07/owl#',
+    'rdfs': 'http://www.w3.org/2000/01/rdf-schema#',
     'schema': 'https://schema.org/',
+    'xsd': 'http://www.w3.org/2001/XMLSchema#',
 };
 var DWC_FIELDS = {
     scientificName: 'dwc:scientificName',
@@ -166,6 +167,12 @@ var DWC_FIELDS = {
     verbatimIdentification: 'dwc:verbatimIdentification',
 };
 var GBIF_RANKS = ['kingdom', 'phylum', 'class', 'order', 'family', 'genus', 'species', 'subspecies'];
+var GBIF_VOCAB_RANKS = ['domain', 'kingdom', 'subkingdom', 'superphylum', 'phylum', 'subphylum', 'superclass', 'class', 'subclass', 'supercohort', 'cohort', 'subcohort', 'superorder', 'order', 'suborder', 'infraorder', 'superfamily', 'family', 'subfamily', 'tribe', 'subtribe', 'genus', 'subgenus', 'section', 'subsection', 'series', 'subseries', 'speciesAggregate', 'species', 'subspecificAggregate', 'subspecies', 'variety', 'subvariety', 'form', 'subform', 'cultivarGroup', 'cultivar', 'strain'];
+var STATUSES = {
+    'accepted': 'http://rs.gbif.org/vocabulary/gbif/taxonomicStatus/accepted',
+    'heterotypic synonym': 'http://rs.gbif.org/vocabulary/gbif/taxonomicStatus/heterotypicSynonym',
+    'synonym': 'http://rs.gbif.org/vocabulary/gbif/taxonomicStatus/synonym',
+};
 function getCoveringTaxon(taxa) {
     if (taxa.length === 1 && !taxa[0].has('gbif')) {
         return "".concat(PREFIX, "taxon/").concat(taxa[0].get('id'));
@@ -222,6 +229,17 @@ function makeScientificNameUri(id) {
     var resource = id.split(':').slice(0, -1).join(':');
     return { '@id': "".concat(PREFIX, "resource/").concat(resource, "#").concat(id) };
 }
+function makeTaxonRankUri(rank) {
+    if (GBIF_VOCAB_RANKS.includes(rank)) {
+        return { '@id': "http://rs.gbif.org/vocabulary/gbif/rank/".concat(rank) };
+    }
+    else {
+        return rank;
+    }
+}
+function makeTaxonomicStatusUri(status) {
+    return { '@id': STATUSES[status] };
+}
 function makeLinkedDataForAuthor(author) {
     var node = {
         '@id': "".concat(PREFIX, "author/").concat(author.get('id')),
@@ -246,7 +264,7 @@ function makeLinkedDataForPlace(place) {
 }
 function makeLinkedDataForPublisher(publisher) {
     var node = {
-        '@id': "".concat(PREFIX, "author/").concat(publisher.get('id')),
+        '@id': "".concat(PREFIX, "publisher/").concat(publisher.get('id')),
         '@type': 'foaf:Organization',
         'foaf:name': publisher.get('display_name')
     };
@@ -262,7 +280,7 @@ function makeLinkedDataForTaxon(taxon) {
         'dwc:scientificName': taxon.get('display_name'),
     };
     if (taxon.has('rank')) {
-        node['dwc:taxonRank'] = taxon.get('rank');
+        node['dwc:taxonRank'] = makeTaxonRankUri(taxon.get('rank'));
     }
     var ids = [];
     if (taxon.has('qid')) {
@@ -291,7 +309,7 @@ function makeLinkedDataForTaxa(files) {
             node['dwc:parentNameUsageID'] = { '@id': "".concat(PREFIX, "taxon/T141") };
         }
         for (var i = 0; i < ancestors.length; i++) {
-            gbifTaxa[ancestors[i]] = __assign(__assign({}, makeGbifUri(ancestors[i])), { 'dwc:taxonRank': GBIF_RANKS[i], 'dwc:parentNameUsageID': i ? makeGbifUri(ancestors[i - 1]) : { '@id': "".concat(PREFIX, "taxon/T141") } });
+            gbifTaxa[ancestors[i]] = __assign(__assign({}, makeGbifUri(ancestors[i])), { 'dwc:taxonRank': makeTaxonRankUri(GBIF_RANKS[i]), 'dwc:parentNameUsageID': i ? makeGbifUri(ancestors[i - 1]) : { '@id': "".concat(PREFIX, "taxon/T141") } });
         }
         if (taxon.has('children_gbif')) {
             var children = taxon.get('children_gbif');
@@ -299,7 +317,7 @@ function makeLinkedDataForTaxa(files) {
             var childRank = GBIF_RANKS[ancestors.length];
             for (var _c = 0, children_1 = children; _c < children_1.length; _c++) {
                 var child = children_1[_c];
-                gbifTaxa[child] = __assign(__assign({}, makeGbifUri(child)), { 'dwc:taxonRank': childRank });
+                gbifTaxa[child] = __assign(__assign({}, makeGbifUri(child)), { 'dwc:taxonRank': makeTaxonRankUri(childRank) });
             }
         }
         nodes.push(node);
@@ -315,6 +333,12 @@ function makeLinkedDataForScientificName(name) {
             node[DWC_FIELDS[field]] = value;
         }
     }
+    if (GBIF_VOCAB_RANKS.includes(name.taxonRank)) {
+        node[DWC_FIELDS.taxonRank] = makeTaxonRankUri(name.taxonRank);
+    }
+    if (name.taxonomicStatus) {
+        node[DWC_FIELDS.taxonomicStatus] = makeTaxonomicStatusUri(name.taxonomicStatus);
+    }
     if (name.acceptedNameUsageID) {
         node['dwc:acceptedNameUsageID'] = makeScientificNameUri(name.acceptedNameUsageID);
     }
@@ -436,7 +460,10 @@ function makeLinkedDataForWork(work, files) {
     node['dcterms:language'] = languages.map(function (language) { return ({ '@id': "http://id.loc.gov/vocabulary/iso639-1/".concat(language) }); });
     if (work.has('title')) {
         var title = work.get('title');
-        node['dcterms:title'] = title.map(function (value, i) { return ({ '@value': value, '@lang': languages[i] }); });
+        if (title.length > languages.length) {
+            title.splice(0, title.length, title.join('; '));
+        }
+        node['dcterms:title'] = title.map(function (value, i) { return ({ '@value': value, '@language': languages[i] }); });
     }
     if (work.has('pages') && work.get('pages').includes('-')) {
         var containers = work.has('part_of') ? work.get('part_of').map(function (id) { return files.catalog.get(id); }) : [];
@@ -462,7 +489,7 @@ function makeLinkedDataForWork(work, files) {
         var urls = work.get('url');
         var handle = urls.find(function (url) { return url.startsWith(HANDLE_PREFIX); });
         if (handle) {
-            node['bibo:handle'] = handle.slice(HANDLE_PREFIX.length);
+            node['bibo:handle'] = { '@id': handle.slice(HANDLE_PREFIX.length) };
         }
         node['schema:url'] = urls.map(function (url) { return ({ '@id': url }); });
     }
@@ -474,7 +501,18 @@ function makeLinkedDataForWork(work, files) {
         node['schema:archivedAt'] = work.get('archive_url').map(function (url) { return ({ '@id': url }); });
     }
     if (work.has('date')) {
-        node['dcterms:issued'] = work.get('date');
+        var date = work.get('date');
+        var dateType = 'rdfs:Literal';
+        if (date.match(/^\d{4}-\d{2}-\d{2}$/)) {
+            dateType = 'xsd:date';
+        }
+        else if (date.match(/^\d{4}-\d{2}$/)) {
+            dateType = 'xsd:gYearMonth';
+        }
+        else if (date.match(/^\d{4}$/)) {
+            dateType = 'xsd:gYear';
+        }
+        node['dcterms:issued'] = { '@value': work.get('date'), '@type': dateType };
     }
     if (work.has('publisher')) {
         var publishers = mapEntities(work.get('publisher'), files.publishers.entities).map(function (publisher) { return ({ '@id': "".concat(PREFIX, "publisher/").concat(publisher.get('id')) }); });
@@ -519,9 +557,15 @@ function makeLinkedDataForWork(work, files) {
         else if (range.length === 2) {
             node['bibo:pages'] = pages;
             var _a = range.map(function (part) { return parseInt(part); }), start = _a[0], end = _a[1];
-            node['bibo:pageStart'] = start;
-            node['bibo:pageEnd'] = end;
-            node['bibo:numPages'] = end - start + 1;
+            if (!isNaN(start)) {
+                node['bibo:pageStart'] = start;
+            }
+            if (!isNaN(end)) {
+                node['bibo:pageEnd'] = end;
+            }
+            if (!isNaN(start) && !isNaN(end)) {
+                node['bibo:numPages'] = end - start + 1;
+            }
         }
         else {
             node['bibo:pages'] = pages;
@@ -582,7 +626,7 @@ function makeLinkedDataForWorks(files) {
             var originals = work.get('version_of');
             var originalLanguages_1 = originals.map(function (id) { return works.get(id).get('language').join(); });
             node['bibo:translationOf'] = originals.filter(function (_, i) { return originalLanguages_1[i] !== language.join(); }).map(makeWorkUri);
-            node['dcterms:isVersionOf'] = originals.map(makeWorkUri);
+            node['dcterms:isVersionOf'] = originals.filter(function (id) { return work.get('id') !== id; }).map(makeWorkUri);
         }
         var resourceIndex = 1;
         var resourceId = void 0;

package/lib/catalog/tables/author.js

@@ -25,7 +25,7 @@ var Author = /** @class */ (function (_super) {
             name: { required: true, multiple: true },
             id: { required: true, multiple: false, format: value_1.FORMATS.AUTHOR_ID },
             qid: { required: false, multiple: false, format: value_1.FORMATS.QID },
-            display_name: { required: false, multiple: false },
+            display_name: { required: true, multiple: false },
             full_names: { required: false, multiple: true },
             duplicate_of: { required: false, multiple: false, format: value_1.FORMATS.AUTHOR_ID }
         }) || this;

package/lib/catalog/tables/place.js

@@ -25,7 +25,7 @@ var Place = /** @class */ (function (_super) {
             name: { required: true, multiple: false },
             id: { required: true, multiple: false, format: value_1.FORMATS.PLACE_ID },
             qid: { required: false, multiple: false, format: value_1.FORMATS.QID },
-            display_name: { required: false, multiple: false },
+            display_name: { required: true, multiple: false },
             duplicate_of: { required: false, multiple: false, format: value_1.FORMATS.PLACE_ID }
         }) || this;
     }

package/lib/catalog/tables/publisher.js

@@ -25,7 +25,7 @@ var Publisher = /** @class */ (function (_super) {
             name: { required: true, multiple: true },
             id: { required: true, multiple: false, format: value_1.FORMATS.PUBLISHER_ID },
             qid: { required: false, multiple: false, format: value_1.FORMATS.QID },
-            display_name: { required: false, multiple: false },
+            display_name: { required: true, multiple: false },
             full_names: { required: false, multiple: true },
             duplicate_of: { required: false, multiple: false, format: value_1.FORMATS.PUBLISHER_ID }
         }) || this;

package/lib/resources/parse-text.js

@@ -102,7 +102,8 @@ var DWC_RANKS = [
 var FLAGS = [
     'MISSING_TAXA',
     'MISSING_PARENT_TAXA',
-    'MISSING_SYNONYMS'
+    'MISSING_SYNONYMS',
+    'MISSING_AUTHORSHIP'
 ];
 var TAXONOMIC_STATUS = {
     '>': 'incorrect',
@@ -145,7 +146,7 @@ var NAME_PATTERN = new RegExp('^' +
     // $2 optional author citation
     '(?: ' +
     // but not auct(t)., etc.
-    '(?!auctt?\\.|(?:syn|comb|sp|spec|nom)\\. n(?:ov)?\\.|s(?:ens[.u]|\\.)|in part|partim)' +
+    '(?!auctt?\\.|(?:syn|comb|sp|spec|nom|gen|subgen)\\. n(?:ov)?\\.|s(?:ens[.u]|\\.)|in part|partim)' +
     '(' +
     // $2.1 anything in parentheses, followed by optional revising author(s)
     '\\(.+?\\)(?:\\s+' + SIMPLE_AUTHOR_PATTERN + ')?' +
@@ -164,12 +165,12 @@ var NAME_PATTERN = new RegExp('^' +
  *   $1 genus+subgenus (+ trailing space): (?:([A-Z]\S+) (?:\(([A-Z]\S+?)\) )?)?
  *     $1.1 genus: ((?:x )?[A-Z]\S+)
  *     $1.2 subgenus: (?:\(([A-Z]\S+?)\) )?
- *   $2 species: (x [a-z]+|[a-z][^\s.]+(?: x [a-z]+)?|[A-Z][a-z]+_[a-z]+ x [A-Z][a-z]+_[a-z]+)
- *     $2a: x [a-z]+
- *     $2b hybrid: [a-z][^\s.]+(?: x [a-z]+)?
- *     $2c intergeneric hybrid: [A-Z][a-z]+_[a-z]+ x [A-Z][a-z]+_[a-z]+
+ *   $2 species: (x [a-z-]+|[a-z-][^\s.]+(?: x [a-z-]+)?|[A-Z][a-z]+_[a-z-]+ x [A-Z][a-z]+_[a-z-]+)
+ *     $2a: x [a-z-]+
+ *     $2b hybrid: [a-z-][^\s.]+(?: x [a-z-]+)?
+ *     $2c intergeneric hybrid: [A-Z][a-z]+_[a-z-]+ x [A-Z][a-z]+_[a-z-]+
  */
-var BINAME_PATTERN = /^(?:((?:x )?[A-Z]\S+) (?:\(([A-Z]\S+?)\) )?)?(x [a-z]+|[a-z][^\s.]+(?: x [a-z]+)?|[A-Z][a-z]+_[a-z]+ x [A-Z][a-z]+_[a-z]+)(?= |$)/;
+var BINAME_PATTERN = /^(?:((?:x )?[A-Z]\S+) (?:\(([A-Z]\S+?)\) )?)?(x [a-z-]+|[a-z-][^\s.]+(?: x [a-z-]+)?|[A-Z][a-z]+_[a-z-]+ x [A-Z][a-z]+_[a-z-]+)(?= |$)/;
 function compareRanks(a, b) {
     return RANKS.indexOf(a) - RANKS.indexOf(b);
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@larsgw/formica",
-  "version": "0.8.0",
+  "version": "0.8.2",
   "description": "SDK and tools for data from the Library of Identification Resources",
   "main": "lib/index.js",
   "types": "lib/index.d.ts",

package/src/bin/generate-linked-data.ts

@@ -62,7 +62,6 @@ const SCOPES: Record<string, [string, string]> = {
     'queens': ['dwc:caste', 'queen'],
     'workers': ['dwc:caste', 'worker'],
     'soldiers': ['dwc:caste', 'soldier'],
-    'alates': ['dwc:caste', 'alate'],
     'alatae': ['dwc:caste', 'alate'],
     'apterae': ['dwc:caste', 'aptera'],
     'viviparae': ['dwc:caste', 'vivipara'],
@@ -85,7 +84,9 @@ const PREFIXES = {
     'dwciri': 'http://rs.tdwg.org/dwc/iri/',
     'foaf': 'http://xmlns.com/foaf/0.1/',
     'owl': 'http://www.w3.org/2002/07/owl#',
+    'rdfs': 'http://www.w3.org/2000/01/rdf-schema#',
     'schema': 'https://schema.org/',
+    'xsd': 'http://www.w3.org/2001/XMLSchema#',
 }
 const DWC_FIELDS: Record<string, string> = {
     scientificName: 'dwc:scientificName',
@@ -100,6 +101,12 @@ const DWC_FIELDS: Record<string, string> = {
     verbatimIdentification: 'dwc:verbatimIdentification',
 }
 const GBIF_RANKS = ['kingdom', 'phylum', 'class', 'order', 'family', 'genus', 'species', 'subspecies']
+const GBIF_VOCAB_RANKS = ['domain', 'kingdom', 'subkingdom', 'superphylum', 'phylum', 'subphylum', 'superclass', 'class', 'subclass', 'supercohort', 'cohort', 'subcohort', 'superorder', 'order', 'suborder', 'infraorder', 'superfamily', 'family', 'subfamily', 'tribe', 'subtribe', 'genus', 'subgenus', 'section', 'subsection', 'series', 'subseries', 'speciesAggregate', 'species', 'subspecificAggregate', 'subspecies', 'variety', 'subvariety', 'form', 'subform', 'cultivarGroup', 'cultivar', 'strain']
+const STATUSES: Record<string, string> = {
+    'accepted': 'http://rs.gbif.org/vocabulary/gbif/taxonomicStatus/accepted',
+    'heterotypic synonym': 'http://rs.gbif.org/vocabulary/gbif/taxonomicStatus/heterotypicSynonym',
+    'synonym': 'http://rs.gbif.org/vocabulary/gbif/taxonomicStatus/synonym',
+}
 
 function getCoveringTaxon (taxa: catalog.Entity[]): string|null {
     if (taxa.length === 1 && !taxa[0].has('gbif')) {
@@ -165,6 +172,18 @@ function makeScientificNameUri (id: string): NodeObject {
     return { '@id': `${PREFIX}resource/${resource}#${id}` }
 }
 
+function makeTaxonRankUri (rank: string): NodeObject|string {
+    if (GBIF_VOCAB_RANKS.includes(rank)) {
+        return { '@id': `http://rs.gbif.org/vocabulary/gbif/rank/${rank}` }
+    } else {
+        return rank
+    }
+}
+
+function makeTaxonomicStatusUri (status: string): NodeObject {
+    return { '@id': STATUSES[status] as string }
+}
+
 function makeLinkedDataForAuthor (author: catalog.Entity): NodeObject {
     const node: NodeObject = {
         '@id': `${PREFIX}author/${author.get('id')}`,
@@ -195,7 +214,7 @@ function makeLinkedDataForPlace (place: catalog.Entity): NodeObject {
 
 function makeLinkedDataForPublisher (publisher: catalog.Entity): NodeObject {
     const node: NodeObject = {
-        '@id': `${PREFIX}author/${publisher.get('id')}`,
+        '@id': `${PREFIX}publisher/${publisher.get('id')}`,
         '@type': 'foaf:Organization',
         'foaf:name': publisher.get('display_name')
     }
@@ -215,7 +234,7 @@ function makeLinkedDataForTaxon (taxon: catalog.Entity): NodeObject {
     }
 
     if (taxon.has('rank')) {
-        node['dwc:taxonRank'] = taxon.get('rank')
+        node['dwc:taxonRank'] = makeTaxonRankUri(taxon.get('rank') as string)
     }
 
     const ids = []
@@ -249,7 +268,7 @@ function makeLinkedDataForTaxa (files: Catalog): NodeObject[] {
         for (let i = 0; i < ancestors.length; i++) {
             gbifTaxa[ancestors[i]] = {
                 ...makeGbifUri(ancestors[i]),
-                'dwc:taxonRank': GBIF_RANKS[i],
+                'dwc:taxonRank': makeTaxonRankUri(GBIF_RANKS[i]),
                 'dwc:parentNameUsageID': i ? makeGbifUri(ancestors[i - 1]) : { '@id': `${PREFIX}taxon/T141` }
             }
         }
@@ -262,7 +281,7 @@ function makeLinkedDataForTaxa (files: Catalog): NodeObject[] {
             for (const child of children) {
                 gbifTaxa[child] = {
                     ...makeGbifUri(child),
-                    'dwc:taxonRank': childRank,
+                    'dwc:taxonRank': makeTaxonRankUri(childRank),
                 }
             }
         }
@@ -288,6 +307,14 @@ function makeLinkedDataForScientificName (name: AmendedTaxon): NodeObject {
         }
     }
 
+    if (GBIF_VOCAB_RANKS.includes(name.taxonRank)) {
+        node[DWC_FIELDS.taxonRank] = makeTaxonRankUri(name.taxonRank)
+    }
+
+    if (name.taxonomicStatus) {
+        node[DWC_FIELDS.taxonomicStatus] = makeTaxonomicStatusUri(name.taxonomicStatus)
+    }
+
     if (name.acceptedNameUsageID) {
         node['dwc:acceptedNameUsageID'] = makeScientificNameUri(name.acceptedNameUsageID)
     }
@@ -435,7 +462,10 @@ function makeLinkedDataForWork (work: catalog.Entity, files: Catalog): NodeObjec
 
     if (work.has('title')) {
         const title = work.get('title') as string[]
-        node['dcterms:title'] = title.map((value, i) => ({ '@value': value, '@lang': languages[i] }))
+        if (title.length > languages.length) {
+            title.splice(0, title.length, title.join('; '))
+        }
+        node['dcterms:title'] = title.map((value, i) => ({ '@value': value, '@language': languages[i] }))
     }
 
     if (work.has('pages') && (work.get('pages') as string).includes('-')) {
@@ -462,7 +492,7 @@ function makeLinkedDataForWork (work: catalog.Entity, files: Catalog): NodeObjec
 
         const handle = urls.find(url => url.startsWith(HANDLE_PREFIX))
         if (handle) {
-            node['bibo:handle'] = handle.slice(HANDLE_PREFIX.length)
+            node['bibo:handle'] = { '@id': handle.slice(HANDLE_PREFIX.length) }
         }
 
         node['schema:url'] = urls.map(url => ({ '@id': url }))
@@ -479,7 +509,17 @@ function makeLinkedDataForWork (work: catalog.Entity, files: Catalog): NodeObjec
     }
 
     if (work.has('date')) {
-        node['dcterms:issued'] = work.get('date')
+        const date = work.get('date') as string
+        let dateType = 'rdfs:Literal'
+        if (date.match(/^\d{4}-\d{2}-\d{2}$/)) {
+            dateType = 'xsd:date'
+        } else if (date.match(/^\d{4}-\d{2}$/)) {
+            dateType = 'xsd:gYearMonth'
+        } else if (date.match(/^\d{4}$/)) {
+            dateType = 'xsd:gYear'
+        }
+
+        node['dcterms:issued'] = { '@value': work.get('date'), '@type': dateType }
     }
 
     if (work.has('publisher')) {
@@ -531,9 +571,15 @@ function makeLinkedDataForWork (work: catalog.Entity, files: Catalog): NodeObjec
             node['bibo:pages'] = pages
 
             const [start, end] = range.map(part => parseInt(part))
-            node['bibo:pageStart'] = start
-            node['bibo:pageEnd'] = end
-            node['bibo:numPages'] = end - start + 1
+            if (!isNaN(start)) {
+                node['bibo:pageStart'] = start
+            }
+            if (!isNaN(end)) {
+                node['bibo:pageEnd'] = end
+            }
+            if (!isNaN(start) && !isNaN(end)) {
+                node['bibo:numPages'] = end - start + 1
+            }
         } else {
             node['bibo:pages'] = pages
         }
@@ -600,7 +646,7 @@ function makeLinkedDataForWorks (files: Catalog): NodeObject[] {
             const originals = work.get('version_of') as string[]
             const originalLanguages = originals.map(id => ((works.get(id) as catalog.Entity).get('language') as string[]).join())
             node['bibo:translationOf'] = originals.filter((_, i) => originalLanguages[i] !== language.join()).map(makeWorkUri)
-            node['dcterms:isVersionOf'] = originals.map(makeWorkUri)
+            node['dcterms:isVersionOf'] = originals.filter(id => work.get('id') !== id).map(makeWorkUri)
         }
 
         let resourceIndex = 1

package/src/catalog/tables/author.ts

@@ -7,7 +7,7 @@ export class Author extends Entity {
             name: { required: true, multiple: true },
             id: { required: true, multiple: false, format: FORMATS.AUTHOR_ID },
             qid: { required: false, multiple: false, format: FORMATS.QID },
-            display_name: { required: false, multiple: false },
+            display_name: { required: true, multiple: false },
             full_names: { required: false, multiple: true },
             duplicate_of: { required: false, multiple: false, format: FORMATS.AUTHOR_ID }
         })

package/src/catalog/tables/place.ts

@@ -7,7 +7,7 @@ export class Place extends Entity {
             name: { required: true, multiple: false },
             id: { required: true, multiple: false, format: FORMATS.PLACE_ID },
             qid: { required: false, multiple: false, format: FORMATS.QID },
-            display_name: { required: false, multiple: false },
+            display_name: { required: true, multiple: false },
             duplicate_of: { required: false, multiple: false, format: FORMATS.PLACE_ID }
         })
     }

package/src/catalog/tables/publisher.ts

@@ -7,7 +7,7 @@ export class Publisher extends Entity {
             name: { required: true, multiple: true },
             id: { required: true, multiple: false, format: FORMATS.PUBLISHER_ID },
             qid: { required: false, multiple: false, format: FORMATS.QID },
-            display_name: { required: false, multiple: false },
+            display_name: { required: true, multiple: false },
             full_names: { required: false, multiple: true },
             duplicate_of: { required: false, multiple: false, format: FORMATS.PUBLISHER_ID }
         })

package/src/resources/parse-text.ts

@@ -58,7 +58,8 @@ const DWC_RANKS: DwcRank[] = [
 const FLAGS: ResourceFlag[] = [
     'MISSING_TAXA',
     'MISSING_PARENT_TAXA',
-    'MISSING_SYNONYMS'
+    'MISSING_SYNONYMS',
+    'MISSING_AUTHORSHIP'
 ]
 
 const TAXONOMIC_STATUS: Record<string, TaxonStatus> = {
@@ -108,7 +109,7 @@ const NAME_PATTERN = new RegExp(
         // $2 optional author citation
         '(?: ' +
             // but not auct(t)., etc.
-            '(?!auctt?\\.|(?:syn|comb|sp|spec|nom)\\. n(?:ov)?\\.|s(?:ens[.u]|\\.)|in part|partim)' +
+            '(?!auctt?\\.|(?:syn|comb|sp|spec|nom|gen|subgen)\\. n(?:ov)?\\.|s(?:ens[.u]|\\.)|in part|partim)' +
         '(' +
             // $2.1 anything in parentheses, followed by optional revising author(s)
             '\\(.+?\\)(?:\\s+' + SIMPLE_AUTHOR_PATTERN + ')?' +
@@ -130,12 +131,12 @@ const NAME_PATTERN = new RegExp(
  *   $1 genus+subgenus (+ trailing space): (?:([A-Z]\S+) (?:\(([A-Z]\S+?)\) )?)?
  *     $1.1 genus: ((?:x )?[A-Z]\S+)
  *     $1.2 subgenus: (?:\(([A-Z]\S+?)\) )?
- *   $2 species: (x [a-z]+|[a-z][^\s.]+(?: x [a-z]+)?|[A-Z][a-z]+_[a-z]+ x [A-Z][a-z]+_[a-z]+)
- *     $2a: x [a-z]+
- *     $2b hybrid: [a-z][^\s.]+(?: x [a-z]+)?
- *     $2c intergeneric hybrid: [A-Z][a-z]+_[a-z]+ x [A-Z][a-z]+_[a-z]+
+ *   $2 species: (x [a-z-]+|[a-z-][^\s.]+(?: x [a-z-]+)?|[A-Z][a-z]+_[a-z-]+ x [A-Z][a-z]+_[a-z-]+)
+ *     $2a: x [a-z-]+
+ *     $2b hybrid: [a-z-][^\s.]+(?: x [a-z-]+)?
+ *     $2c intergeneric hybrid: [A-Z][a-z]+_[a-z-]+ x [A-Z][a-z]+_[a-z-]+
  */
-const BINAME_PATTERN = /^(?:((?:x )?[A-Z]\S+) (?:\(([A-Z]\S+?)\) )?)?(x [a-z]+|[a-z][^\s.]+(?: x [a-z]+)?|[A-Z][a-z]+_[a-z]+ x [A-Z][a-z]+_[a-z]+)(?= |$)/
+const BINAME_PATTERN = /^(?:((?:x )?[A-Z]\S+) (?:\(([A-Z]\S+?)\) )?)?(x [a-z-]+|[a-z-][^\s.]+(?: x [a-z-]+)?|[A-Z][a-z]+_[a-z-]+ x [A-Z][a-z]+_[a-z-]+)(?= |$)/
 
 function compareRanks (a: Rank, b: Rank): number {
     return RANKS.indexOf(a) - RANKS.indexOf(b)