@larsgw/formica 0.4.0 → 0.4.2

package/CHANGELOG.md

@@ -1,3 +1,23 @@
+## [0.4.2](https://github.com/identification-resources/formica/compare/v0.4.1...v0.4.2) (2023-09-30)
+
+
+### Bug Fixes
+
+* **resources:** allow simpler intraspecific synonyms ([978186c](https://github.com/identification-resources/formica/commit/978186cbaf469f3085c24c2e8bc8ffb1f83f2799)), closes [#9](https://github.com/identification-resources/formica/issues/9)
+* **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)
+
+
+### Bug Fixes
+
+* **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)
 
 

package/lib/catalog/tables/work.js

@@ -52,7 +52,7 @@ var Work = /** @class */ (function (_super) {
             listed_in: { required: false, multiple: true, format: value_1.FORMATS.ID },
             part_of: { required: false, multiple: true, format: value_1.FORMATS.ID },
             version_of: { required: false, multiple: true, format: value_1.FORMATS.ID },
-            // duplicate_of: { required: false, multiple: false, format: FORMATS.ID }
+            duplicate_of: { required: false, multiple: false, format: value_1.FORMATS.ID }
         }) || this;
     }
     Work.prototype.deriveFields = function () {

package/lib/resources/parse-text.js

@@ -122,9 +122,9 @@ var NAME_PATTERN = new RegExp('^' +
  *   $1 genus+subgenus (+ trailing space): (?:([A-Z]\S+) (?:\(([A-Z]\S+?)\) )?)?
  *     $1.1 genus: ([A-Z]\S+)
  *     $1.2 subgenus: (?:\(([A-Z]\S+?)\) )?
- *   $2 species: ([a-z]\S+)
+ *   $2 species: ((?:x )?[a-z0-9-]+)
  */
-var BINAME_PATTERN = /^(?:([A-Z]\S+) (?:\(([A-Z]\S+?)\) )?)?([a-z]\S+) ?/;
+var BINAME_PATTERN = /^(?:([A-Z]\S+) (?:\(([A-Z]\S+?)\) )?)?((?:x )?[a-z0-9-]+)(?= |$)/;
 function compareRanks(a, b) {
     return RANKS.indexOf(a) - RANKS.indexOf(b);
 }
@@ -136,14 +136,14 @@ function isUpperCase(name) {
 }
 function getSynonymRank(name, rank) {
     var BINAME_PATTERN = /^([A-Z]\S+ (\([A-Z]\S+\) )?)?(x )?[a-z0-9-]+(?= |$)/;
-    if (!BINAME_PATTERN.test(name)) {
-        return rank;
-    }
     var rest = name.replace(BINAME_PATTERN, '');
-    var rankPrefix = rest.match(/^ (st|r|ab|f|var|ssp|subsp)\. /);
+    var rankPrefix = rest.match(/^(?: |^)(st|r|ab|f|var|ssp|subsp)\. /);
     if (rankPrefix) {
         return RANK_LABELS_REVERSE[rankPrefix[1]];
     }
+    else if (!BINAME_PATTERN.test(name)) {
+        return rank;
+    }
     else if (/^ (?!sensu)[a-z0-9-]+($| )/.test(rest)) {
         return 'subspecies';
     }
@@ -221,8 +221,9 @@ function parseName(name, rank, parent) {
         if (compareRanks('species', rank) < 0) {
             var speciesPrefix = parseContext.specificEpithet + ' ';
             if (name.startsWith(speciesPrefix)) {
-                name = name.slice(speciesPrefix.length).replace(/^(st|r|ab|f|var|ssp|subsp)\. /, '');
+                name = name.slice(speciesPrefix.length);
             }
+            name = name.replace(/^(st|r|ab|f|var|ssp|subsp)\. /, '');
         }
     }
     // Hybrids
@@ -400,6 +401,11 @@ function parseResourceContent(content, resource, oldIds) {
             id++;
             return "continue";
         }
+        // Do not process "indet" lines further, as they only serve to indicate
+        // that subtaxa are explicitely omitted
+        if (Array.from(INDET_SUFFIXES).some(function (suffix) { return line.endsWith(' ' + suffix); })) {
+            return "continue";
+        }
         var lineIndent = line.match(/^ */)[0].length;
         if (lineIndent > groupIndent) {
             // Do not count synonyms as parents (unless this is correcting a typo in the synonym)
@@ -431,8 +437,7 @@ function parseResourceContent(content, resource, oldIds) {
         var rank = resource.metadata.levels[groupIndent / 2];
         var item = parseName(name_1, rank, parent_1);
         var isSynonym = item.taxonomicStatus !== 'accepted';
-        var isIndet = Array.from(INDET_SUFFIXES).some(function (suffix) { return name_1.endsWith(' ' + suffix); });
-        if (item.taxonomicStatus === 'incorrect' || isIndet) {
+        if (item.taxonomicStatus === 'incorrect') {
             return "continue";
         }
         if (type === diff_resource_1.ResourceDiffType.Added) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@larsgw/formica",
-  "version": "0.4.0",
+  "version": "0.4.2",
   "description": "SDK and tools for data from the Library of Identification Resources",
   "main": "lib/index.js",
   "types": "lib/index.d.ts",

package/src/catalog/tables/work.ts

@@ -34,7 +34,7 @@ export class Work extends Entity {
             listed_in: { required: false, multiple: true, format: FORMATS.ID },
             part_of: { required: false, multiple: true, format: FORMATS.ID },
             version_of: { required: false, multiple: true, format: FORMATS.ID },
-            // duplicate_of: { required: false, multiple: false, format: FORMATS.ID }
+            duplicate_of: { required: false, multiple: false, format: FORMATS.ID }
         })
     }
 

package/src/resources/parse-text.ts

@@ -120,9 +120,9 @@ const NAME_PATTERN = new RegExp(
  *   $1 genus+subgenus (+ trailing space): (?:([A-Z]\S+) (?:\(([A-Z]\S+?)\) )?)?
  *     $1.1 genus: ([A-Z]\S+)
  *     $1.2 subgenus: (?:\(([A-Z]\S+?)\) )?
- *   $2 species: ([a-z]\S+)
+ *   $2 species: ((?:x )?[a-z0-9-]+)
  */
-const BINAME_PATTERN = /^(?:([A-Z]\S+) (?:\(([A-Z]\S+?)\) )?)?([a-z]\S+) ?/
+const BINAME_PATTERN = /^(?:([A-Z]\S+) (?:\(([A-Z]\S+?)\) )?)?((?:x )?[a-z0-9-]+)(?= |$)/
 
 function compareRanks (a: Rank, b: Rank): number {
     return RANKS.indexOf(a) - RANKS.indexOf(b)
@@ -138,13 +138,12 @@ function isUpperCase (name: string): boolean {
 
 function getSynonymRank (name: string, rank: Rank): Rank {
     const BINAME_PATTERN = /^([A-Z]\S+ (\([A-Z]\S+\) )?)?(x )?[a-z0-9-]+(?= |$)/
-    if (!BINAME_PATTERN.test(name)) {
-        return rank
-    }
     const rest = name.replace(BINAME_PATTERN, '')
-    const rankPrefix = rest.match(/^ (st|r|ab|f|var|ssp|subsp)\. /)
+    const rankPrefix = rest.match(/^(?: |^)(st|r|ab|f|var|ssp|subsp)\. /)
     if (rankPrefix) {
         return RANK_LABELS_REVERSE[rankPrefix[1]] as string
+    } else if (!BINAME_PATTERN.test(name)) {
+        return rank
     } else if (/^ (?!sensu)[a-z0-9-]+($| )/.test(rest)) {
         return 'subspecies'
     } else {
@@ -220,8 +219,9 @@ function parseName (name: string, rank: Rank, parent: WorkingTaxon): WorkingTaxo
         if (compareRanks('species', rank) < 0) {
             const speciesPrefix = parseContext.specificEpithet + ' '
             if (name.startsWith(speciesPrefix)) {
-                name = name.slice(speciesPrefix.length).replace(/^(st|r|ab|f|var|ssp|subsp)\. /, '')
+                name = name.slice(speciesPrefix.length)
             }
+            name = name.replace(/^(st|r|ab|f|var|ssp|subsp)\. /, '')
         }
     }
 
@@ -422,6 +422,12 @@ function parseResourceContent (content: ResourceDiff, resource: Resource, oldIds
             continue
         }
 
+        // Do not process "indet" lines further, as they only serve to indicate
+        // that subtaxa are explicitely omitted
+        if (Array.from(INDET_SUFFIXES).some(suffix => line.endsWith(' ' + suffix))) {
+            continue
+        }
+
         const lineIndent = (line.match(/^ */) as string[])[0].length
 
         if (lineIndent > groupIndent) {
@@ -452,9 +458,8 @@ function parseResourceContent (content: ResourceDiff, resource: Resource, oldIds
         const rank = resource.metadata.levels[groupIndent / 2]
         const item = parseName(name, rank, parent)
         const isSynonym = item.taxonomicStatus !== 'accepted'
-        const isIndet = Array.from(INDET_SUFFIXES).some(suffix => name.endsWith(' ' + suffix))
 
-        if (item.taxonomicStatus === 'incorrect' || isIndet) {
+        if (item.taxonomicStatus === 'incorrect') {
             continue
         }
 

package/test/resources.js

@@ -57,4 +57,37 @@ Cydnidae
     limbosus`, 'T1')
         })
     })
+
+    await t.test('parses synonyms starting with intraspecific ranks', (t) => {
+        const [resource] = resources.parseTextFile(`---
+levels: [species]
+---
+
+Lygaeus equestris (Linnaeus, 1758)
+  = f. lactans Horváth, 1899
+`, 'T1')
+        assert.strictEqual(resource.taxa['T1:1:2'].scientificName, 'Lygaeus equestris f. lactans Horváth, 1899')
+    })
+
+    await t.test('parses accepted taxa starting with intraspecific ranks', (t) => {
+        const [resource] = resources.parseTextFile(`---
+levels: [species, form]
+---
+
+Lygaeus equestris (Linnaeus, 1758)
+  f. lactans Horváth, 1899
+`, 'T1')
+        assert.strictEqual(resource.taxa['T1:1:2'].scientificName, 'Lygaeus equestris f. lactans Horváth, 1899')
+    })
+
+    await t.test('does not validate "indet." lines', (t) => {
+        const [resource] = resources.parseTextFile(`---
+levels: [genus, species]
+---
+
+Drymus
+  Unknown sp.
+`, 'T1')
+        assert.strictEqual(resource.taxa['T1:1:1'].scientificName, 'Drymus')
+    })
 })