@larsgw/formica 0.8.8 → 0.9.1

package/CHANGELOG.md

@@ -1,12 +1,35 @@
-## [0.8.8](https://github.com/identification-resources/formica/compare/v0.8.7...v0.8.8) (2025-12-25)
+## [0.9.1](https://github.com/identification-resources/formica/compare/v0.9.0...v0.9.1) (2026-04-21)
+
+
+### Bug Fixes
+
+* **resources:** fix RDF mapping of taxonomic status ([c65383e](https://github.com/identification-resources/formica/commit/c65383e4d64c674c6c3b9f69e8cae925fcdf6896))
 
 
 ### Features
 
-* **resources:** add 'subclass' rank ([4b10405](https://github.com/identification-resources/formica/commit/4b10405b32840c1675caf7ef24bf2bbfd821a236))
+* **catalog:** add more validation for taxa ([2bbc017](https://github.com/identification-resources/formica/commit/2bbc0177f8d4a6909339cfee812c33873770f725))
 
+# [0.9.0](https://github.com/identification-resources/formica/compare/v0.8.8...v0.9.0) (2026-02-04)
 
 
+### Bug Fixes
+
+* **resources:** improve taxonomic status ([0ea8fd2](https://github.com/identification-resources/formica/commit/0ea8fd220571f5f6ff05f517069aba10148c6888))
+
+
+### Features
+
+* **resources:** include cluster data in DwC files ([60a28ac](https://github.com/identification-resources/formica/commit/60a28ace18b0760696735ca416a2e8d014d1c928))
+* **resources:** include uncertainty of synonymy in DwC if specified ([03b6734](https://github.com/identification-resources/formica/commit/03b6734851dc9c331ec88fab21e90ad3f0303c3c))
+
+## [0.8.8](https://github.com/identification-resources/formica/compare/v0.8.7...v0.8.8) (2025-12-25)
+
+
+### Features
+
+* **resources:** add 'subclass' rank ([4b10405](https://github.com/identification-resources/formica/commit/4b10405b32840c1675caf7ef24bf2bbfd821a236))
+
 ## [0.8.7](https://github.com/identification-resources/formica/compare/v0.8.6...v0.8.7) (2025-11-01)
 
 
@@ -14,8 +37,6 @@
 
 * **resources:** fix handling of corrections ([49c05b4](https://github.com/identification-resources/formica/commit/49c05b499262e64514b832313360d1e6a4cc6378))
 
-
-
 ## [0.8.6](https://github.com/identification-resources/formica/compare/v0.8.5...v0.8.6) (2025-10-28)
 
 
@@ -29,8 +50,6 @@
 
 * **resources:** ignore errors in later-corrected names ([4c1f69e](https://github.com/identification-resources/formica/commit/4c1f69e81450664f122cdf00e68cb918248790e6)), closes [#5](https://github.com/identification-resources/formica/issues/5)
 
-
-
 ## [0.8.5](https://github.com/identification-resources/formica/compare/v0.8.4...v0.8.5) (2025-10-28)
 
 
@@ -48,8 +67,6 @@
 * **resources:** handle subgenus synonyms of genera ([4e61336](https://github.com/identification-resources/formica/commit/4e61336e36054ffd6df57ebad5479e7ceebcb235)), closes [#16](https://github.com/identification-resources/formica/issues/16)
 * **resources:** rework parsing of resources ([cff7730](https://github.com/identification-resources/formica/commit/cff773000c5b9e3f990c619cdd45a76a18ee39a9)), closes [#15](https://github.com/identification-resources/formica/issues/15) [#7](https://github.com/identification-resources/formica/issues/7)
 
-
-
 ## [0.8.4](https://github.com/identification-resources/formica/compare/v0.8.3...v0.8.4) (2025-09-19)
 
 
@@ -63,8 +80,6 @@
 
 * **catalog:** map additional scope value ([80c6d26](https://github.com/identification-resources/formica/commit/80c6d269a7d5b03600991fb353280e81afcefb0e))
 
-
-
 ## [0.8.3](https://github.com/identification-resources/formica/compare/v0.8.2...v0.8.3) (2025-07-15)
 
 
@@ -72,8 +87,6 @@
 
 * **catalog:** add catalog field key_characteristics ([6529cfa](https://github.com/identification-resources/formica/commit/6529cfab81f759f926b81bdd9d5a36e84b526284))
 
-
-
 ## [0.8.2](https://github.com/identification-resources/formica/compare/v0.8.1...v0.8.2) (2025-06-26)
 
 
@@ -82,8 +95,6 @@
 * **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)
 
 
@@ -97,8 +108,6 @@
 
 * **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)
 
 
@@ -111,8 +120,6 @@
 
 * **catalog:** implement generation of linked data ([334616e](https://github.com/identification-resources/formica/commit/334616e2e12c0d91e49f84f06bdd00ab7a238b8e))
 
-
-
 ## [0.7.3](https://github.com/identification-resources/formica/compare/v0.7.2...v0.7.3) (2025-04-17)
 
 
@@ -120,8 +127,6 @@
 
 * **catalog:** update validation for identifiers ([156a703](https://github.com/identification-resources/formica/commit/156a7036ab09c411d091bc9d0f628831a30ba3f5))
 
-
-
 ## [0.7.2](https://github.com/identification-resources/formica/compare/v0.7.1...v0.7.2) (2025-04-02)
 
 
@@ -129,8 +134,6 @@
 
 * **catalog:** add validation for taxa.csv ([59cfcf2](https://github.com/identification-resources/formica/commit/59cfcf28ebbef42e28e648e800c178a7d528f37a))
 
-
-
 ## [0.7.1](https://github.com/identification-resources/formica/compare/v0.7.0...v0.7.1) (2025-03-25)
 
 
@@ -138,8 +141,6 @@
 
 * **resources:** add 'subphylum' rank ([8b5243b](https://github.com/identification-resources/formica/commit/8b5243bfd79b6486c613ca1178f1e1c9ec3f43a4))
 
-
-
 # [0.7.0](https://github.com/identification-resources/formica/compare/v0.6.8...v0.7.0) (2025-03-14)
 
 
@@ -157,8 +158,6 @@
 
 * **resources:** "indet" lines now have to be prefixed with "[indet]"
 
-
-
 ## [0.6.8](https://github.com/identification-resources/formica/compare/v0.6.7...v0.6.8) (2025-03-13)
 
 
@@ -168,8 +167,6 @@
 * **resources:** create index of CoL identifiers ([3792903](https://github.com/identification-resources/formica/commit/37929035374bc0c67ed2403e775e06a904bdbd4d))
 * **resources:** support intergeneric hybrids ([0a6696c](https://github.com/identification-resources/formica/commit/0a6696c5fd0603a0366c80c2298b6544636ed0c6))
 
-
-
 ## [0.6.7](https://github.com/identification-resources/formica/compare/v0.6.6...v0.6.7) (2025-02-26)
 
 
@@ -184,8 +181,6 @@
 
 * **resources:** add support for completeness flags ([55b5427](https://github.com/identification-resources/formica/commit/55b5427125b4f1072191cadbc461ba31d37e6f2e))
 
-
-
 ## [0.6.6](https://github.com/identification-resources/formica/compare/v0.6.5...v0.6.6) (2025-02-16)
 
 
@@ -193,8 +188,6 @@
 
 * **resources:** allow other resources in version_of ([85947b0](https://github.com/identification-resources/formica/commit/85947b0dcfbdb4bfd6537c628b34087a6e6326f7))
 
-
-
 ## [0.6.5](https://github.com/identification-resources/formica/compare/v0.6.4...v0.6.5) (2024-12-20)
 
 
@@ -204,8 +197,6 @@
 * **resources:** improve (ICBN) author parsing ([d3e3faf](https://github.com/identification-resources/formica/commit/d3e3faf411d1a7dccd528a5ee78bd0823a5883b4)), closes [#13](https://github.com/identification-resources/formica/issues/13) [#14](https://github.com/identification-resources/formica/issues/14)
 * **resources:** support "et al." in author name ([82993bf](https://github.com/identification-resources/formica/commit/82993bffac5e7f3ed00d00c28c836f347b264a43))
 
-
-
 ## [0.6.4](https://github.com/identification-resources/formica/compare/v0.6.3...v0.6.4) (2024-12-16)
 
 
@@ -213,8 +204,6 @@
 
 * **resources:** fix matching of some ICBN names ([3c18458](https://github.com/identification-resources/formica/commit/3c184586b64e2a31f1eb7298bcd7c80c1d119069))
 
-
-
 ## [0.6.3](https://github.com/identification-resources/formica/compare/v0.6.2...v0.6.3) (2024-04-12)
 
 
@@ -222,8 +211,6 @@
 
 * **resources:** allow 'phylum' rank ([ff9be66](https://github.com/identification-resources/formica/commit/ff9be66abab79a86263764b54d6a2709833b14d4))
 
-
-
 ## [0.6.2](https://github.com/identification-resources/formica/compare/v0.6.1...v0.6.2) (2024-04-08)
 
 
@@ -236,8 +223,6 @@
 
 * **catalog:** add script to de-duplicate links ([b719348](https://github.com/identification-resources/formica/commit/b719348635e1b35ee80758c0cdd9938625d79ebf))
 
-
-
 ## [0.6.1](https://github.com/identification-resources/formica/compare/v0.6.0...v0.6.1) (2024-03-20)
 
 
@@ -245,8 +230,6 @@
 
 * **resources:** allow two-part hybrid names ([8e3b836](https://github.com/identification-resources/formica/commit/8e3b8368985d1db35b62d306d833121150e91865))
 
-
-
 # [0.6.0](https://github.com/identification-resources/formica/compare/v0.5.2...v0.6.0) (2024-01-05)
 
 
@@ -254,8 +237,6 @@
 
 * **catalog:** add entry type, key type values ([ed6e4fb](https://github.com/identification-resources/formica/commit/ed6e4fb545e09cddb5d466f602bffb8a8483f043))
 
-
-
 ## [0.5.2](https://github.com/identification-resources/formica/compare/v0.5.1...v0.5.2) (2023-11-27)
 
 
@@ -263,8 +244,6 @@
 
 * **resources:** fix GBIF index generation ([c88e2d2](https://github.com/identification-resources/formica/commit/c88e2d2b306b930ca0b00b978e3eb89b8adfb656))
 
-
-
 ## [0.5.1](https://github.com/identification-resources/formica/compare/v0.5.0...v0.5.1) (2023-11-03)
 
 
@@ -272,8 +251,6 @@
 
 * **resources:** fix file listing in processor ([009b980](https://github.com/identification-resources/formica/commit/009b98091b0f597e91213ace82252facbe3b5fed))
 
-
-
 # [0.5.0](https://github.com/identification-resources/formica/compare/v0.4.3...v0.5.0) (2023-10-24)
 
 
@@ -304,8 +281,6 @@
 does no longer pass validation. Use the "taxon_scope" and "scope" fields
 in "catalog" instead.
 
-
-
 ## [0.4.3](https://github.com/identification-resources/formica/compare/v0.4.2...v0.4.3) (2023-09-30)
 
 
@@ -313,8 +288,6 @@ in "catalog" instead.
 
 * **resource:** fix regression in taxon parsing ([098477b](https://github.com/identification-resources/formica/commit/098477b5914324a3c15ec885617d4cf30996f30d))
 
-
-
 ## [0.4.2](https://github.com/identification-resources/formica/compare/v0.4.1...v0.4.2) (2023-09-30)
 
 
@@ -324,8 +297,6 @@ in "catalog" instead.
 * **resources:** correct synonym rank determintation ([766ea2a](https://github.com/identification-resources/formica/commit/766ea2af14ff3aa64a7a2e19ed096836d38182cf))
 * **resources:** do not parse "indet." lines as taxa ([f4debf6](https://github.com/identification-resources/formica/commit/f4debf695b0cdb375bfb60ab5ce942fa2f7dee85)), closes [#8](https://github.com/identification-resources/formica/issues/8)
 
-
-
 ## [0.4.1](https://github.com/identification-resources/formica/compare/v0.4.0...v0.4.1) (2023-09-07)
 
 
@@ -333,8 +304,6 @@ in "catalog" instead.
 
 * **catalog:** fix typo in duplicate_of schema ([fbb6333](https://github.com/identification-resources/formica/commit/fbb6333d10dd6f5846856ea8de81d941ce539d21))
 
-
-
 # [0.4.0](https://github.com/identification-resources/formica/compare/v0.3.1...v0.4.0) (2023-09-07)
 
 
@@ -348,8 +317,6 @@ in "catalog" instead.
 
 * **catalog:** add duplicate_of field ([e4a8bbe](https://github.com/identification-resources/formica/commit/e4a8bbecef9c6a40d0f2cc5d4e8bb67685a453ff))
 
-
-
 ## [0.3.1](https://github.com/identification-resources/formica/compare/v0.3.0...v0.3.1) (2023-09-04)
 
 
@@ -359,8 +326,6 @@ in "catalog" instead.
 * **resources:** fix regression in c737d5b ([d4e52e9](https://github.com/identification-resources/formica/commit/d4e52e95ed1a35dabbd80b9f9aace1a824fdae98))
 * **resources:** handle corrections to synonyms ([21ed9b7](https://github.com/identification-resources/formica/commit/21ed9b79f77e1e6d0639d96ed9822d5212a85a2e)), closes [#4](https://github.com/identification-resources/formica/issues/4)
 
-
-
 # [0.3.0](https://github.com/identification-resources/formica/compare/v0.2.1...v0.3.0) (2023-08-20)
 
 
@@ -372,8 +337,6 @@ in "catalog" instead.
 * **resources:** improve taxon name matching ([78ff480](https://github.com/identification-resources/formica/commit/78ff480485ca42bd1d1f2893f230e61db6cb6be8)), closes [#2](https://github.com/identification-resources/formica/issues/2)
 * **resources:** test for rank mismatch ([0e69b7f](https://github.com/identification-resources/formica/commit/0e69b7f0a6654fa5255e797be7516cd06edb4df3)), closes [#2](https://github.com/identification-resources/formica/issues/2)
 
-
-
 ## [0.2.1](https://github.com/identification-resources/formica/compare/v0.2.0...v0.2.1) (2023-08-10)
 
 
@@ -382,8 +345,6 @@ in "catalog" instead.
 * **resources:** do not validate old versions ([1a8dd2e](https://github.com/identification-resources/formica/commit/1a8dd2e0e373489e287d1fd89dbb7443245c5214))
 * **resources:** fix check for missing leaf taxa ([035f1ad](https://github.com/identification-resources/formica/commit/035f1ad20efa80b388ec3828d4ace4518c7b344e))
 
-
-
 # [0.2.0](https://github.com/identification-resources/formica/compare/v0.1.1...v0.2.0) (2023-08-09)
 
 
@@ -392,8 +353,6 @@ in "catalog" instead.
 * **catalog:** add taxon_scope column ([6a06c37](https://github.com/identification-resources/formica/commit/6a06c37ec0640a8ffbc258ad6a4d81d84d35fee9))
 * **resources:** check for missing leaf taxa ([387c47d](https://github.com/identification-resources/formica/commit/387c47d10bb7f1fb09a68c10dfa869bb924b7633))
 
-
-
 ## [0.1.1](https://github.com/identification-resources/formica/compare/v0.1.0...v0.1.1) (2023-05-10)
 
 
@@ -401,8 +360,6 @@ in "catalog" instead.
 
 * **processor:** add Node hashbang ([51dee57](https://github.com/identification-resources/formica/commit/51dee57b8547afba449b2b846bd7d65e7927368f))
 
-
-
 # [0.1.0](https://github.com/identification-resources/formica/compare/fed91fd6f350c47bd067d221a4d0e2278a199dae...v0.1.0) (2023-03-01)
 
 
@@ -424,6 +381,3 @@ in "catalog" instead.
 * **resources:** add support for hybrids ([e49e96a](https://github.com/identification-resources/formica/commit/e49e96af9c3958bab2a3b0508b1fc8a018b80716))
 * **validate:** add catalog validation script ([4cdf785](https://github.com/identification-resources/formica/commit/4cdf785afb2c77320cd9b5b76483e3464c0f1cff))
 * **validate:** add script to validate resources ([246fb5d](https://github.com/identification-resources/formica/commit/246fb5dd8da03e736884850874cc51a11be9985c))
-
-
-

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

@@ -125,7 +125,8 @@ const GBIF_RANKS = ['kingdom', 'phylum', 'class', 'order', 'family', 'genus', 's
 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 = {
     'accepted': 'http://rs.gbif.org/vocabulary/gbif/taxonomicStatus/accepted',
-    'heterotypic synonym': 'http://rs.gbif.org/vocabulary/gbif/taxonomicStatus/heterotypicSynonym',
+    'misapplied': 'http://rs.gbif.org/vocabulary/gbif/taxonomicStatus/misapplied',
+    'proparte synonym': 'http://rs.gbif.org/vocabulary/gbif/taxonomicStatus/proParteSynonym',
     'synonym': 'http://rs.gbif.org/vocabulary/gbif/taxonomicStatus/synonym',
 };
 function getCoveringTaxon(taxa) {
@@ -284,9 +285,12 @@ function makeLinkedDataForScientificName(name) {
     if (GBIF_VOCAB_RANKS.includes(name.taxonRank)) {
         node[DWC_FIELDS.taxonRank] = makeTaxonRankUri(name.taxonRank);
     }
-    if (name.taxonomicStatus) {
+    if (name.taxonomicStatus in STATUSES) {
         node[DWC_FIELDS.taxonomicStatus] = makeTaxonomicStatusUri(name.taxonomicStatus);
     }
+    else {
+        console.error('Unmapped taxonomic status:', name.taxonomicStatus);
+    }
     if (name.acceptedNameUsageID) {
         node['dwc:acceptedNameUsageID'] = makeScientificNameUri(name.acceptedNameUsageID);
     }

package/lib/bin/process-resources.js

@@ -82,6 +82,7 @@ const DWC_FIELDS = [
     'subgenus',
     'higherClassification',
     'verbatimIdentification',
+    'dynamicProperties',
     'colTaxonID',
     'gbifTaxonID',
     'colAcceptedTaxonID',

package/lib/bin/validate-catalog.js

@@ -46,12 +46,66 @@ Object.defineProperty(exports, "__esModule", { value: true });
 const fs_1 = require("fs");
 const path = __importStar(require("path"));
 const index_1 = require("../index");
+class TaxaValidator {
+    constructor(taxa) {
+        this.taxa = Array.from(taxa).filter(taxon => taxon.has('ancestors_gbif'));
+        this.errors = [];
+        this.parentIndex = {};
+    }
+    validate() {
+        for (const taxon of this.taxa) {
+            const parents = taxon.get('ancestors_gbif');
+            if (parents.length > 1) {
+                const id = taxon.get('id');
+                for (let i = 1; i < parents.length; i++) {
+                    this.addToIndex(id, 'ancestors_gbif', parents[i], parents[i - 1]);
+                }
+            }
+        }
+        for (const taxon of this.taxa) {
+            if (taxon.has('gbif')) {
+                const id = taxon.get('id');
+                const parents = taxon.get('ancestors_gbif');
+                const parent = parents[parents.length - 1];
+                this.addToIndex(id, 'gbif', taxon.get('gbif'), parent);
+            }
+        }
+        for (const taxon of this.taxa) {
+            if (taxon.has('children_gbif')) {
+                const id = taxon.get('id');
+                const parents = taxon.get('ancestors_gbif');
+                const parent = parents[parents.length - 1];
+                const childIds = taxon.get('children_gbif');
+                for (const childId of childIds) {
+                    this.addToIndex(id, 'gbif', childId, parent);
+                }
+            }
+        }
+        return this.errors;
+    }
+    addToIndex(entity, field, childId, parentId) {
+        const actualParentId = this.parentIndex[childId];
+        if (!actualParentId) {
+            this.parentIndex[childId] = parentId;
+        }
+        else if (actualParentId !== parentId) {
+            const error = `Inconsistent ancestor of ${childId}, expected ${actualParentId} but got ${parentId}`;
+            this.errors.push({ entity, field, error });
+        }
+    }
+}
 function validateFile(arg) {
     return __awaiter(this, void 0, void 0, function* () {
         const filePath = path.resolve(arg);
         const file = yield fs_1.promises.readFile(filePath, 'utf8');
         const sheet = path.basename(filePath, '.csv');
-        return index_1.catalog.loadData(file, sheet).validate();
+        const entities = index_1.catalog.loadData(file, sheet);
+        const errors = entities.validate();
+        if (sheet === 'taxa') {
+            const validator = new TaxaValidator(entities);
+            errors.push(...validator.validate());
+        }
+        return errors;
     });
 }
 function main(args) {

package/lib/resources/parse-name.js

@@ -43,7 +43,7 @@ exports.RANKS = [
 ];
 const TAXONOMIC_STATUS = {
     '>': 'incorrect',
-    '+': 'heterotypic synonym',
+    '+': 'proparte synonym',
     '=': 'synonym'
 };
 const RANK_LABELS = {
@@ -113,6 +113,7 @@ const SUBGENUS_PATTERN = /^([A-Z]\S+) (?:\(([A-Z]\S+?)\))(?= |$)/;
  *     $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 CLUSTER_PATTERN = /^\[(_|\d+)\] /;
 function compareRanks(a, b) {
     return exports.RANKS.indexOf(a) - exports.RANKS.indexOf(b);
 }
@@ -158,15 +159,21 @@ function parseName(name, rank, parent) {
     const isSynonym = /^[+=>] /.test(name);
     if (isSynonym) {
         item.taxonomicStatus = TAXONOMIC_STATUS[name[0]];
-        name = name.replace(/^[+=>] (\? ?)?/, '');
+        name = name.slice(2);
+        if (/^\? ?/.test(name)) {
+            item.dynamicProperties = '{"synonymUncertain":true}';
+            name = name.replace(/^\? ?/, '');
+        }
         rank = getSynonymRank(name, parent.taxonRank);
     }
     else {
         item.taxonomicStatus = 'accepted';
     }
     // Clusters
-    if (/^\[(_|\d+)\] /.test(name)) {
-        name = name.replace(/^\[(_|\d+)\] /, '');
+    if (CLUSTER_PATTERN.test(name)) {
+        const [match, cluster] = name.match(CLUSTER_PATTERN);
+        item.cluster = cluster;
+        name = name.slice(match.length);
     }
     // Set verbatim identification after subsequent syntax is removed.
     item.verbatimIdentification = name.replace(/(?<=^| )x(?=$| )/g, HYBRID_SIGN).replace(/_/g, ' ');
@@ -351,5 +358,8 @@ function parseName(name, rank, parent) {
     if (item.scientificNameAuthorship) {
         item.scientificName += ` ${item.scientificNameAuthorship}`;
     }
+    if (isSynonym && /^auctt?\./.test(item.taxonRemarks)) {
+        item.taxonomicStatus = 'misapplied';
+    }
     return item;
 }

package/lib/resources/parse-text.js

@@ -153,6 +153,32 @@ function parseResource(resource) {
     const offsetLine = resource.offsetLine + (header + _).split('\n').length - 1;
     return [config, { content, offsetLine }];
 }
+function getTaxonChildren(parent, taxa) {
+    const children = [];
+    for (const id in taxa) {
+        if (taxa[id].parentNameUsageID === parent) {
+            children.push(taxa[id]);
+        }
+    }
+    return children;
+}
+function processClusters(taxa) {
+    for (const id in taxa) {
+        const taxon = taxa[id];
+        if (taxon.taxonomicStatus !== 'accepted' || !taxon.cluster) {
+            continue;
+        }
+        const dynamicProperties = taxon.dynamicProperties ? JSON.parse(taxon.dynamicProperties) : {};
+        if (taxon.cluster === '_') {
+            dynamicProperties.identifiable = false;
+        }
+        else {
+            const siblings = getTaxonChildren(taxon.parentNameUsageID, taxa).filter(sibling => sibling.scientificNameID !== id);
+            dynamicProperties.indistinguishableFrom = siblings.filter(sibling => sibling.cluster === taxon.cluster).map(sibling => sibling.scientificNameID);
+        }
+        taxon.dynamicProperties = JSON.stringify(dynamicProperties);
+    }
+}
 function parseResourceContent(content, resource, oldIds, offsetLine) {
     var _a, _b;
     const leafTaxonIndex = resource.metadata.levels.reduce((last, rank, i) => MAIN_RANKS.includes(rank) ? i : last, 0);
@@ -311,6 +337,7 @@ function parseResourceContent(content, resource, oldIds, offsetLine) {
     if (errors.length) {
         throw mergeParserErrors(errors);
     }
+    processClusters(data);
     return resource;
 }
 function splitResources(file) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@larsgw/formica",
-  "version": "0.8.8",
+  "version": "0.9.1",
   "description": "SDK and tools for data from the Library of Identification Resources",
   "main": "lib/index.js",
   "types": "lib/index.d.ts",
@@ -34,7 +34,7 @@
   "dependencies": {
     "ietf-language-tag-regex": "^0.0.5",
     "js-yaml": "^4.1.0",
-    "jsonld": "^8.3.3",
+    "jsonld": "^9.0.0",
     "n3": "^1.25.2",
     "spdx-license-list": "^6.6.0"
   },

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

@@ -106,7 +106,8 @@ const GBIF_RANKS = ['kingdom', 'phylum', 'class', 'order', 'family', 'genus', 's
 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',
+    'misapplied': 'http://rs.gbif.org/vocabulary/gbif/taxonomicStatus/misapplied',
+    'proparte synonym': 'http://rs.gbif.org/vocabulary/gbif/taxonomicStatus/proParteSynonym',
     'synonym': 'http://rs.gbif.org/vocabulary/gbif/taxonomicStatus/synonym',
 }
 
@@ -182,8 +183,8 @@ function makeTaxonRankUri (rank: string): NodeObject|string {
     }
 }
 
-function makeTaxonomicStatusUri (status: string): NodeObject {
-    return { '@id': STATUSES[status] as string }
+function makeTaxonomicStatusUri (status: keyof typeof STATUSES): NodeObject {
+    return { '@id': STATUSES[status] }
 }
 
 function makeLinkedDataForAuthor (author: catalog.Entity): NodeObject {
@@ -313,8 +314,10 @@ function makeLinkedDataForScientificName (name: AmendedTaxon): NodeObject {
         node[DWC_FIELDS.taxonRank] = makeTaxonRankUri(name.taxonRank)
     }
 
-    if (name.taxonomicStatus) {
+    if (name.taxonomicStatus in STATUSES) {
         node[DWC_FIELDS.taxonomicStatus] = makeTaxonomicStatusUri(name.taxonomicStatus)
+    } else {
+        console.error('Unmapped taxonomic status:', name.taxonomicStatus)
     }
 
     if (name.acceptedNameUsageID) {

package/src/bin/process-resources.ts

@@ -44,6 +44,8 @@ const DWC_FIELDS: (keyof AmendedTaxon)[] = [
     'higherClassification',
     'verbatimIdentification',
 
+    'dynamicProperties',
+
     'colTaxonID',
     'gbifTaxonID',
     'colAcceptedTaxonID',

package/src/bin/validate-catalog.ts

@@ -4,11 +4,81 @@ import { promises as fs } from 'fs'
 import * as path from 'path'
 import { catalog } from '../index'
 
+class TaxaValidator {
+    taxa: catalog.Entity[];
+    errors: WorkError[];
+    parentIndex: Record<string, string>;
+
+    constructor (taxa: catalog.Entities) {
+        this.taxa = Array.from(taxa).filter(taxon => taxon.has('ancestors_gbif'))
+        this.errors = []
+        this.parentIndex = {}
+    }
+
+    validate (): WorkError[] {
+        for (const taxon of this.taxa) {
+            const parents = taxon.get('ancestors_gbif') as string[]
+
+            if (parents.length > 1) {
+                const id = taxon.get('id') as string
+
+                for (let i = 1; i < parents.length; i++) {
+                    this.addToIndex(id, 'ancestors_gbif', parents[i], parents[i - 1])
+                }
+            }
+        }
+
+        for (const taxon of this.taxa) {
+            if (taxon.has('gbif')) {
+                const id = taxon.get('id') as string
+                const parents = taxon.get('ancestors_gbif') as string[]
+                const parent = parents[parents.length - 1] as string
+
+                this.addToIndex(id, 'gbif', taxon.get('gbif') as string, parent)
+            }
+        }
+
+        for (const taxon of this.taxa) {
+            if (taxon.has('children_gbif')) {
+                const id = taxon.get('id') as string
+                const parents = taxon.get('ancestors_gbif') as string[]
+                const parent = parents[parents.length - 1] as string
+
+                const childIds = taxon.get('children_gbif') as string[]
+                for (const childId of childIds) {
+                    this.addToIndex(id, 'gbif', childId, parent)
+                }
+            }
+        }
+
+        return this.errors
+    }
+
+    addToIndex (entity: string, field: string, childId: string, parentId: string) {
+        const actualParentId = this.parentIndex[childId]
+
+        if (!actualParentId) {
+            this.parentIndex[childId] = parentId
+        } else if (actualParentId !== parentId) {
+            const error = `Inconsistent ancestor of ${childId}, expected ${actualParentId} but got ${parentId}`
+            this.errors.push({ entity, field, error })
+        }
+    }
+}
+
 async function validateFile (arg: string): Promise<WorkError[]> {
     const filePath = path.resolve(arg)
     const file = await fs.readFile(filePath, 'utf8')
     const sheet = path.basename(filePath, '.csv')
-    return catalog.loadData(file, sheet).validate()
+    const entities = catalog.loadData(file, sheet)
+    const errors = entities.validate()
+
+    if (sheet === 'taxa') {
+        const validator = new TaxaValidator(entities)
+        errors.push(...validator.validate())
+    }
+
+    return errors
 }
 
 async function main (args: string[]): Promise<void> {

package/src/module.d.ts

@@ -56,12 +56,14 @@ interface TaxonBase {
     subgenus?: string,
     higherClassification?: string,
     verbatimIdentification?: string,
+    dynamicProperties?: string,
 }
 
 interface WorkingTaxon extends TaxonBase {
     // Non-standard
     scientificNameOnly?: string,
-    incorrect?: WorkingTaxon
+    incorrect?: WorkingTaxon,
+    cluster?: string
 }
 
 interface Taxon extends TaxonBase {

package/src/resources/parse-name.ts

@@ -42,7 +42,7 @@ export const RANKS: Rank[] = [
 
 const TAXONOMIC_STATUS: Record<string, TaxonStatus> = {
     '>': 'incorrect',
-    '+': 'heterotypic synonym',
+    '+': 'proparte synonym',
     '=': 'synonym'
 }
 
@@ -123,6 +123,8 @@ const SUBGENUS_PATTERN = /^([A-Z]\S+) (?:\(([A-Z]\S+?)\))(?= |$)/
  */
 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 CLUSTER_PATTERN = /^\[(_|\d+)\] /
+
 function compareRanks (a: Rank, b: Rank): number {
     return RANKS.indexOf(a) - RANKS.indexOf(b)
 }
@@ -173,15 +175,21 @@ export function parseName (name: string, rank: Rank, parent: WorkingTaxon): Work
     const isSynonym = /^[+=>] /.test(name)
     if (isSynonym) {
         item.taxonomicStatus = TAXONOMIC_STATUS[name[0]]
-        name = name.replace(/^[+=>] (\? ?)?/, '')
+        name = name.slice(2)
+        if (/^\? ?/.test(name)) {
+            item.dynamicProperties = '{"synonymUncertain":true}'
+            name = name.replace(/^\? ?/, '')
+        }
         rank = getSynonymRank(name, parent.taxonRank as Rank)
     } else {
         item.taxonomicStatus = 'accepted'
     }
 
     // Clusters
-    if (/^\[(_|\d+)\] /.test(name)) {
-        name = name.replace(/^\[(_|\d+)\] /, '')
+    if (CLUSTER_PATTERN.test(name)) {
+        const [match, cluster] = name.match(CLUSTER_PATTERN) as string[]
+        item.cluster = cluster
+        name = name.slice(match.length)
     }
 
     // Set verbatim identification after subsequent syntax is removed.
@@ -376,5 +384,9 @@ export function parseName (name: string, rank: Rank, parent: WorkingTaxon): Work
         item.scientificName += ` ${item.scientificNameAuthorship}`
     }
 
+    if (isSynonym && /^auctt?\./.test(item.taxonRemarks)) {
+        item.taxonomicStatus = 'misapplied'
+    }
+
     return item
 }

package/src/resources/parse-text.ts

@@ -134,6 +134,36 @@ function parseResource (resource: FilePart): [ResourceMetadata, FilePart] {
     return [config, { content, offsetLine }]
 }
 
+function getTaxonChildren (parent: TaxonId|undefined, taxa: Record<TaxonId, WorkingTaxon>): WorkingTaxon[] {
+    const children = []
+    for (const id in taxa) {
+        if (taxa[id].parentNameUsageID === parent) {
+            children.push(taxa[id])
+        }
+    }
+    return children
+}
+
+function processClusters (taxa: Record<TaxonId, WorkingTaxon>) {
+    for (const id in taxa) {
+        const taxon = taxa[id]
+        if (taxon.taxonomicStatus !== 'accepted' || !taxon.cluster) {
+            continue
+        }
+
+        const dynamicProperties = taxon.dynamicProperties ? JSON.parse(taxon.dynamicProperties) : {}
+
+        if (taxon.cluster === '_') {
+            dynamicProperties.identifiable = false
+        } else {
+            const siblings = getTaxonChildren(taxon.parentNameUsageID, taxa).filter(sibling => sibling.scientificNameID !== id)
+            dynamicProperties.indistinguishableFrom = siblings.filter(sibling => sibling.cluster === taxon.cluster).map(sibling => sibling.scientificNameID)
+        }
+
+        taxon.dynamicProperties = JSON.stringify(dynamicProperties)
+    }
+}
+
 function parseResourceContent (content: ResourceDiff, resource: Resource, oldIds: number[], offsetLine: number): Resource {
     const leafTaxonIndex = resource.metadata.levels.reduce((last, rank, i) => MAIN_RANKS.includes(rank) ? i : last, 0)
     const data = resource.taxa as Record<TaxonId, WorkingTaxon>
@@ -307,6 +337,8 @@ function parseResourceContent (content: ResourceDiff, resource: Resource, oldIds
         throw mergeParserErrors(errors)
     }
 
+    processClusters(data)
+
     return resource
 }
 

package/test/resources.js

@@ -166,6 +166,27 @@ Polistes Latreille, 1802
         assert.strictEqual(resource.taxa['T1:1:2'].genericName, 'Polistes')
     })
 
+    test('handles clusters', () => {
+        const [resource] = resources.parseTextFile(`---
+levels: [genus, species]
+---
+
+Eurydema Laporte, 1833
+  oleracea (Linnaeus, 1758)
+  [1] rotundicollis (Dohrn, 1860)
+  [1] fieberi Schummel, 1837
+  [2] ornata (Linnaeus, 1758)
+  [2] ventralis Kolenati, 1846
+  [_] eckerleini Josifov, 1961
+`, 'T1')
+        assert.strictEqual(resource.taxa['T1:1:2'].dynamicProperties, undefined)
+        assert.strictEqual(resource.taxa['T1:1:3'].dynamicProperties, '{"indistinguishableFrom":["T1:1:4"]}')
+        assert.strictEqual(resource.taxa['T1:1:4'].dynamicProperties, '{"indistinguishableFrom":["T1:1:3"]}')
+        assert.strictEqual(resource.taxa['T1:1:5'].dynamicProperties, '{"indistinguishableFrom":["T1:1:6"]}')
+        assert.strictEqual(resource.taxa['T1:1:6'].dynamicProperties, '{"indistinguishableFrom":["T1:1:5"]}')
+        assert.strictEqual(resource.taxa['T1:1:7'].dynamicProperties, '{"identifiable":false}')
+    })
+
     suite('leaf taxa checks', () => {
         test('errors for missing leaf taxa', () => {
             assert.throws(() => {