@natlibfi/melinda-record-matching 5.0.0-alpha.1 → 5.0.0-alpha.3

package/dist/match-detection/features/bib/authors.js

@@ -0,0 +1,57 @@
+import naturalPkg from "natural";
+const { LevenshteinDistance: leven } = naturalPkg;
+import { testStringOrNumber } from "../../../matching-utils.js";
+export default ({ nameTreshold = 10 } = {}) => ({
+  name: "Authors",
+  extract: ({ record }) => {
+    const authors = record.get(/^(?<def>100|700)$/u).map(({ subfields }) => {
+      return subfields.filter(({ code, value }) => code && value).filter(({ code }) => ["a", "0"].includes(code)).map(toObj).reduce((acc, v) => ({ ...acc, ...v }), {});
+      function toObj({ code, value }) {
+        if (code === "a") {
+          return { name: testStringOrNumber(value) ? String(value).replace(/[^\p{Letter}\p{Number}]/gu, "").toLowerCase() : "" };
+        }
+        return { id: value };
+      }
+    });
+    return authors;
+  },
+  compare: (a, b) => {
+    const maxAuthors = a.length > b.length ? a.length : b.length;
+    const matchingIds = findMatchingIds();
+    if (maxAuthors >= 3 && matchingIds >= 3) {
+      return 0.3;
+    }
+    const matchingNames = findMatchingNames();
+    const idPoints = matchingIds / maxAuthors * 0.3;
+    const namePoints = matchingNames / maxAuthors * 0.2;
+    const totalPoints = idPoints + namePoints;
+    return totalPoints <= 0.2 ? totalPoints : 0.2;
+    function findMatchingIds() {
+      return findMatches("id", (a2, b2) => a2 === b2);
+    }
+    function findMatchingNames() {
+      return findMatches("name", (a2, b2) => {
+        const distance = leven(a2, b2);
+        if (distance === 0) {
+          return true;
+        }
+        const maxLength = getMaxLength();
+        const percentage = distance / maxLength * 100;
+        return percentage <= nameTreshold;
+        function getMaxLength() {
+          return a2.length > b2.length ? a2.length : b2.length;
+        }
+      });
+    }
+    function findMatches(key, cb) {
+      const valuesA = a.filter((o) => o[key]).map((o) => o[key]);
+      const valuesB = b.filter((o) => o[key]).map((o) => o[key]);
+      const allValues = valuesA.concat(valuesB);
+      return allValues.reduce((acc, value) => {
+        const occurrance = allValues.filter((otherValue) => cb(value, otherValue)).length;
+        return occurrance >= 2 ? acc + 1 : acc;
+      }, 0);
+    }
+  }
+});
+//# sourceMappingURL=authors.js.map

package/dist/match-detection/features/bib/authors.js.map

@@ -0,0 +1,7 @@
+{
+  "version": 3,
+  "sources": ["../../../../src/match-detection/features/bib/authors.js"],
+  "sourcesContent": ["\n\nimport naturalPkg from 'natural';\nconst {LevenshteinDistance: leven} = naturalPkg;\nimport {testStringOrNumber} from '../../../matching-utils.js';\n\n// We should extract also organisational authors (110/710)\n\nexport default ({nameTreshold = 10} = {}) => ({\n  name: 'Authors',\n  extract: ({record}) => {\n    //const label = recordExternal && recordExternal.label ? recordExternal.label : 'record';\n    const authors = record.get(/^(?<def>100|700)$/u)\n      .map(({subfields}) => {\n        return subfields\n          .filter(({code, value}) => code && value)\n          .filter(({code}) => ['a', '0'].includes(code))\n          .map(toObj)\n          .reduce((acc, v) => ({...acc, ...v}), {});\n\n        function toObj({code, value}) {\n          if (code === 'a') {\n            return {name: testStringOrNumber(value) ? String(value).replace(/[^\\p{Letter}\\p{Number}]/gu, '').toLowerCase() : ''};\n          }\n\n          return {id: value};\n        }\n      });\n    return authors;\n  },\n  compare: (a, b) => {\n    const maxAuthors = a.length > b.length ? a.length : b.length;\n    const matchingIds = findMatchingIds();\n\n    if (maxAuthors >= 3 && matchingIds >= 3) {\n      return 0.3;\n    }\n\n    const matchingNames = findMatchingNames();\n    const idPoints = matchingIds / maxAuthors * 0.3;\n    const namePoints = matchingNames / maxAuthors * 0.2;\n    const totalPoints = idPoints + namePoints;\n\n    return totalPoints <= 0.2 ? totalPoints : 0.2;\n\n    function findMatchingIds() {\n      return findMatches('id', (a, b) => a === b);\n    }\n\n    function findMatchingNames() {\n      return findMatches('name', (a, b) => {\n        const distance = leven(a, b);\n\n        if (distance === 0) {\n          return true;\n        }\n\n        const maxLength = getMaxLength();\n        const percentage = distance / maxLength * 100;\n\n        return percentage <= nameTreshold;\n\n        function getMaxLength() {\n          return a.length > b.length ? a.length : b.length;\n        }\n      });\n    }\n\n    function findMatches(key, cb) {\n      const valuesA = a.filter(o => o[key]).map(o => o[key]);\n      const valuesB = b.filter(o => o[key]).map(o => o[key]);\n      const allValues = valuesA.concat(valuesB);\n\n      return allValues.reduce((acc, value) => {\n        const occurrance = allValues.filter(otherValue => cb(value, otherValue)).length;\n        return occurrance >= 2 ? acc + 1 : acc;\n      }, 0);\n    }\n  }\n});\n"],
+  "mappings": "AAEA,OAAO,gBAAgB;AACvB,MAAM,EAAC,qBAAqB,MAAK,IAAI;AACrC,SAAQ,0BAAyB;AAIjC,eAAe,CAAC,EAAC,eAAe,GAAE,IAAI,CAAC,OAAO;AAAA,EAC5C,MAAM;AAAA,EACN,SAAS,CAAC,EAAC,OAAM,MAAM;AAErB,UAAM,UAAU,OAAO,IAAI,oBAAoB,EAC5C,IAAI,CAAC,EAAC,UAAS,MAAM;AACpB,aAAO,UACJ,OAAO,CAAC,EAAC,MAAM,MAAK,MAAM,QAAQ,KAAK,EACvC,OAAO,CAAC,EAAC,KAAI,MAAM,CAAC,KAAK,GAAG,EAAE,SAAS,IAAI,CAAC,EAC5C,IAAI,KAAK,EACT,OAAO,CAAC,KAAK,OAAO,EAAC,GAAG,KAAK,GAAG,EAAC,IAAI,CAAC,CAAC;AAE1C,eAAS,MAAM,EAAC,MAAM,MAAK,GAAG;AAC5B,YAAI,SAAS,KAAK;AAChB,iBAAO,EAAC,MAAM,mBAAmB,KAAK,IAAI,OAAO,KAAK,EAAE,QAAQ,6BAA6B,EAAE,EAAE,YAAY,IAAI,GAAE;AAAA,QACrH;AAEA,eAAO,EAAC,IAAI,MAAK;AAAA,MACnB;AAAA,IACF,CAAC;AACH,WAAO;AAAA,EACT;AAAA,EACA,SAAS,CAAC,GAAG,MAAM;AACjB,UAAM,aAAa,EAAE,SAAS,EAAE,SAAS,EAAE,SAAS,EAAE;AACtD,UAAM,cAAc,gBAAgB;AAEpC,QAAI,cAAc,KAAK,eAAe,GAAG;AACvC,aAAO;AAAA,IACT;AAEA,UAAM,gBAAgB,kBAAkB;AACxC,UAAM,WAAW,cAAc,aAAa;AAC5C,UAAM,aAAa,gBAAgB,aAAa;AAChD,UAAM,cAAc,WAAW;AAE/B,WAAO,eAAe,MAAM,cAAc;AAE1C,aAAS,kBAAkB;AACzB,aAAO,YAAY,MAAM,CAACA,IAAGC,OAAMD,OAAMC,EAAC;AAAA,IAC5C;AAEA,aAAS,oBAAoB;AAC3B,aAAO,YAAY,QAAQ,CAACD,IAAGC,OAAM;AACnC,cAAM,WAAW,MAAMD,IAAGC,EAAC;AAE3B,YAAI,aAAa,GAAG;AAClB,iBAAO;AAAA,QACT;AAEA,cAAM,YAAY,aAAa;AAC/B,cAAM,aAAa,WAAW,YAAY;AAE1C,eAAO,cAAc;AAErB,iBAAS,eAAe;AACtB,iBAAOD,GAAE,SAASC,GAAE,SAASD,GAAE,SAASC,GAAE;AAAA,QAC5C;AAAA,MACF,CAAC;AAAA,IACH;AAEA,aAAS,YAAY,KAAK,IAAI;AAC5B,YAAM,UAAU,EAAE,OAAO,OAAK,EAAE,GAAG,CAAC,EAAE,IAAI,OAAK,EAAE,GAAG,CAAC;AACrD,YAAM,UAAU,EAAE,OAAO,OAAK,EAAE,GAAG,CAAC,EAAE,IAAI,OAAK,EAAE,GAAG,CAAC;AACrD,YAAM,YAAY,QAAQ,OAAO,OAAO;AAExC,aAAO,UAAU,OAAO,CAAC,KAAK,UAAU;AACtC,cAAM,aAAa,UAAU,OAAO,gBAAc,GAAG,OAAO,UAAU,CAAC,EAAE;AACzE,eAAO,cAAc,IAAI,MAAM,IAAI;AAAA,MACrC,GAAG,CAAC;AAAA,IACN;AAAA,EACF;AACF;",
+  "names": ["a", "b"]
+}

package/dist/match-detection/features/bib/bibliographic-level.js

@@ -0,0 +1,6 @@
+export default () => ({
+  name: "Bibliographic level",
+  extract: ({ record }) => record.leader[7] ? [record.leader[7]] : [],
+  compare: (a, b) => a[0] === b[0] ? 0.1 : -0.2
+});
+//# sourceMappingURL=bibliographic-level.js.map

package/dist/match-detection/features/bib/bibliographic-level.js.map

@@ -0,0 +1,7 @@
+{
+  "version": 3,
+  "sources": ["../../../../src/match-detection/features/bib/bibliographic-level.js"],
+  "sourcesContent": ["\nexport default () => ({\n  name: 'Bibliographic level',\n  extract: ({record}) => record.leader[7] ? [record.leader[7]] : [],\n  compare: (a, b) => a[0] === b[0] ? 0.1 : -0.2\n});\n"],
+  "mappings": "AACA,eAAe,OAAO;AAAA,EACpB,MAAM;AAAA,EACN,SAAS,CAAC,EAAC,OAAM,MAAM,OAAO,OAAO,CAAC,IAAI,CAAC,OAAO,OAAO,CAAC,CAAC,IAAI,CAAC;AAAA,EAChE,SAAS,CAAC,GAAG,MAAM,EAAE,CAAC,MAAM,EAAE,CAAC,IAAI,MAAM;AAC3C;",
+  "names": []
+}

package/dist/match-detection/features/bib/host-component.js

@@ -0,0 +1,6 @@
+export default () => ({
+  name: "Host/Component record",
+  extract: ({ record }) => record.get(/^773$/u).length > 0 ? ["component"] : ["host"],
+  compare: (a, b) => a[0] === b[0] ? 0 : -1
+});
+//# sourceMappingURL=host-component.js.map

package/dist/match-detection/features/bib/host-component.js.map

@@ -0,0 +1,7 @@
+{
+  "version": 3,
+  "sources": ["../../../../src/match-detection/features/bib/host-component.js"],
+  "sourcesContent": ["\nexport default () => ({\n  name: 'Host/Component record',\n  extract: ({record}) => record.get(/^773$/u).length > 0 ? ['component'] : ['host'],\n  compare: (a, b) => a[0] === b[0] ? 0.0 : -1.0\n});\n"],
+  "mappings": "AACA,eAAe,OAAO;AAAA,EACpB,MAAM;AAAA,EACN,SAAS,CAAC,EAAC,OAAM,MAAM,OAAO,IAAI,QAAQ,EAAE,SAAS,IAAI,CAAC,WAAW,IAAI,CAAC,MAAM;AAAA,EAChF,SAAS,CAAC,GAAG,MAAM,EAAE,CAAC,MAAM,EAAE,CAAC,IAAI,IAAM;AAC3C;",
+  "names": []
+}

package/dist/match-detection/features/bib/index.js

@@ -0,0 +1,17 @@
+export { default as hostComponent } from "./host-component.js";
+export { default as isbn } from "./isbn.js";
+export { default as issn } from "./issn.js";
+export { default as otherStandardIdentifier } from "./other-standard-identifier.js";
+export { default as title } from "./title.js";
+export { default as titleVersionOriginal } from "./title-version-original.js";
+export { default as authors } from "./authors.js";
+export { default as recordType } from "./record-type.js";
+export { default as publicationTime } from "./publication-time.js";
+export { default as publicationTimeAllowConsYears } from "./publication-time-allow-cons-years.js";
+export { default as publicationTimeAllowConsYearsMulti } from "./publication-time-allow-cons-years-multi.js";
+export { default as language } from "./language.js";
+export { default as bibliographicLevel } from "./bibliographic-level.js";
+export { default as melindaId } from "./melinda-id.js";
+export { default as allSourceIds } from "./all-source-ids.js";
+export { default as mediaType } from "./media-type.js";
+//# sourceMappingURL=index.js.map

package/dist/match-detection/features/bib/index.js.map

@@ -0,0 +1,7 @@
+{
+  "version": 3,
+  "sources": ["../../../../src/match-detection/features/bib/index.js"],
+  "sourcesContent": ["\nexport {default as hostComponent} from './host-component.js';\nexport {default as isbn} from './isbn.js';\nexport {default as issn} from './issn.js';\nexport {default as otherStandardIdentifier} from './other-standard-identifier.js';\nexport {default as title} from './title.js';\nexport {default as titleVersionOriginal} from './title-version-original.js';\nexport {default as authors} from './authors.js';\nexport {default as recordType} from './record-type.js';\nexport {default as publicationTime} from './publication-time.js';\nexport {default as publicationTimeAllowConsYears} from './publication-time-allow-cons-years.js';\nexport {default as publicationTimeAllowConsYearsMulti} from './publication-time-allow-cons-years-multi.js';\nexport {default as language} from './language.js';\nexport {default as bibliographicLevel} from './bibliographic-level.js';\nexport {default as melindaId} from './melinda-id.js';\nexport {default as allSourceIds} from './all-source-ids.js';\nexport {default as mediaType} from './media-type.js';\n"],
+  "mappings": "AACA,SAAQ,WAAW,qBAAoB;AACvC,SAAQ,WAAW,YAAW;AAC9B,SAAQ,WAAW,YAAW;AAC9B,SAAQ,WAAW,+BAA8B;AACjD,SAAQ,WAAW,aAAY;AAC/B,SAAQ,WAAW,4BAA2B;AAC9C,SAAQ,WAAW,eAAc;AACjC,SAAQ,WAAW,kBAAiB;AACpC,SAAQ,WAAW,uBAAsB;AACzC,SAAQ,WAAW,qCAAoC;AACvD,SAAQ,WAAW,0CAAyC;AAC5D,SAAQ,WAAW,gBAAe;AAClC,SAAQ,WAAW,0BAAyB;AAC5C,SAAQ,WAAW,iBAAgB;AACnC,SAAQ,WAAW,oBAAmB;AACtC,SAAQ,WAAW,iBAAgB;",
+  "names": []
+}

package/dist/match-detection/features/bib/index.test.js

@@ -0,0 +1,40 @@
+import assert from "node:assert";
+import { describe } from "node:test";
+import createDebugLogger from "debug";
+import generateTests from "@natlibfi/fixugen";
+import { READERS } from "@natlibfi/fixura";
+import { MarcRecord } from "@natlibfi/marc-record";
+import * as features from "./index.js";
+const debug = createDebugLogger("@natlibfi/melinda-record-matching:match-detection:features/bib:test");
+const debugData = debug.extend("data");
+describe("match-detection/features/bib/", () => {
+  generateTests({
+    path: [import.meta.dirname, "..", "..", "..", "..", "test-fixtures", "match-detection", "features", "bib"],
+    useMetadataFile: true,
+    fixura: {
+      reader: READERS.JSON
+    },
+    callback: ({ enabled = true, feature, options, type, ...expectations }) => {
+      if (!enabled) {
+        return;
+      }
+      debug(`Testing: ${feature} ${type}`);
+      if (type === "extract") {
+        const { expectedFeatures, inputRecord } = expectations;
+        const record = new MarcRecord(inputRecord, { subfieldValues: false });
+        debugData(`Record: ${record}`);
+        const { extract } = features[feature](options);
+        assert.deepStrictEqual(extract({ record }), expectedFeatures);
+        return;
+      }
+      if (type === "compare") {
+        const { featuresA, featuresB, expectedPoints } = expectations;
+        const { compare } = features[feature](options);
+        assert.equal(compare(featuresA, featuresB), expectedPoints);
+        return;
+      }
+      throw new Error(`Invalid type ${type}`);
+    }
+  });
+});
+//# sourceMappingURL=index.test.js.map

package/dist/match-detection/features/bib/index.test.js.map

@@ -0,0 +1,7 @@
+{
+  "version": 3,
+  "sources": ["../../../../src/match-detection/features/bib/index.test.js"],
+  "sourcesContent": ["\nimport assert from 'node:assert';\nimport {describe} from 'node:test';\nimport createDebugLogger from 'debug';\nimport generateTests from '@natlibfi/fixugen';\nimport {READERS} from '@natlibfi/fixura';\nimport {MarcRecord} from '@natlibfi/marc-record';\nimport * as features from './index.js';\n\n\nconst debug = createDebugLogger('@natlibfi/melinda-record-matching:match-detection:features/bib:test');\nconst debugData = debug.extend('data');\n\n\ndescribe('match-detection/features/bib/', () => {\n  generateTests({\n    path: [import.meta.dirname, '..', '..', '..', '..', 'test-fixtures', 'match-detection', 'features', 'bib'],\n    useMetadataFile: true,\n    fixura: {\n      reader: READERS.JSON\n    },\n\n    callback: ({enabled = true, feature, options, type, ...expectations}) => {\n\n      if (!enabled) {\n        return;\n      }\n\n      debug(`Testing: ${feature} ${type}`);\n\n      if (type === 'extract') {\n        const {expectedFeatures, inputRecord} = expectations;\n        const record = new MarcRecord(inputRecord, {subfieldValues: false});\n        debugData(`Record: ${record}`);\n        const {extract} = features[feature](options);\n\n        assert.deepStrictEqual(extract({record}), expectedFeatures);\n        return;\n      }\n\n      if (type === 'compare') {\n        const {featuresA, featuresB, expectedPoints} = expectations;\n        const {compare} = features[feature](options);\n\n        assert.equal(compare(featuresA, featuresB), expectedPoints);\n        return;\n      }\n\n      throw new Error(`Invalid type ${type}`);\n    }\n  });\n});\n"],
+  "mappings": "AACA,OAAO,YAAY;AACnB,SAAQ,gBAAe;AACvB,OAAO,uBAAuB;AAC9B,OAAO,mBAAmB;AAC1B,SAAQ,eAAc;AACtB,SAAQ,kBAAiB;AACzB,YAAY,cAAc;AAG1B,MAAM,QAAQ,kBAAkB,qEAAqE;AACrG,MAAM,YAAY,MAAM,OAAO,MAAM;AAGrC,SAAS,iCAAiC,MAAM;AAC9C,gBAAc;AAAA,IACZ,MAAM,CAAC,YAAY,SAAS,MAAM,MAAM,MAAM,MAAM,iBAAiB,mBAAmB,YAAY,KAAK;AAAA,IACzG,iBAAiB;AAAA,IACjB,QAAQ;AAAA,MACN,QAAQ,QAAQ;AAAA,IAClB;AAAA,IAEA,UAAU,CAAC,EAAC,UAAU,MAAM,SAAS,SAAS,MAAM,GAAG,aAAY,MAAM;AAEvE,UAAI,CAAC,SAAS;AACZ;AAAA,MACF;AAEA,YAAM,YAAY,OAAO,IAAI,IAAI,EAAE;AAEnC,UAAI,SAAS,WAAW;AACtB,cAAM,EAAC,kBAAkB,YAAW,IAAI;AACxC,cAAM,SAAS,IAAI,WAAW,aAAa,EAAC,gBAAgB,MAAK,CAAC;AAClE,kBAAU,WAAW,MAAM,EAAE;AAC7B,cAAM,EAAC,QAAO,IAAI,SAAS,OAAO,EAAE,OAAO;AAE3C,eAAO,gBAAgB,QAAQ,EAAC,OAAM,CAAC,GAAG,gBAAgB;AAC1D;AAAA,MACF;AAEA,UAAI,SAAS,WAAW;AACtB,cAAM,EAAC,WAAW,WAAW,eAAc,IAAI;AAC/C,cAAM,EAAC,QAAO,IAAI,SAAS,OAAO,EAAE,OAAO;AAE3C,eAAO,MAAM,QAAQ,WAAW,SAAS,GAAG,cAAc;AAC1D;AAAA,MACF;AAEA,YAAM,IAAI,MAAM,gBAAgB,IAAI,EAAE;AAAA,IACxC;AAAA,EACF,CAAC;AACH,CAAC;",
+  "names": []
+}

package/dist/match-detection/features/bib/isbn.js

@@ -0,0 +1,21 @@
+import createDebugLogger from "debug";
+import { parse as isbnParse } from "isbn3";
+import createInterface from "./standard-identifier-factory.js";
+const debug = createDebugLogger(`@natlibfi/melinda-record-matching:match-detection:features:standard-identifiers:ISBN`);
+const debugData = debug.extend("data");
+export default () => {
+  const IDENTIFIER_NAME = "ISBN";
+  function validatorAndNormalizer(string) {
+    const isbnParseResult = isbnParse(string);
+    debugData(`isbnParseResult: ${JSON.stringify(isbnParseResult)}`);
+    if (isbnParseResult === null) {
+      debug(`Not parseable ISBN, just removing hyphens`);
+      return { valid: false, value: string.replace(/-/ug, "") };
+    }
+    debug(`Parseable ISBN, normalizing to ISBN-13`);
+    return { valid: true, value: isbnParseResult.isbn13 };
+  }
+  const { extract, compare } = createInterface({ identifier: IDENTIFIER_NAME, pattern: /^020$/u, subfieldCodes: ["a", "z"], validIdentifierSubfieldCodes: ["a"], invalidIdentifierSubfieldCodes: ["z"], validatorAndNormalizer });
+  return { extract, compare, name: IDENTIFIER_NAME };
+};
+//# sourceMappingURL=isbn.js.map

package/dist/match-detection/features/bib/isbn.js.map

@@ -0,0 +1,7 @@
+{
+  "version": 3,
+  "sources": ["../../../../src/match-detection/features/bib/isbn.js"],
+  "sourcesContent": ["\nimport createDebugLogger from 'debug';\nimport {parse as isbnParse} from 'isbn3';\nimport createInterface from './standard-identifier-factory.js';\n\nconst debug = createDebugLogger(`@natlibfi/melinda-record-matching:match-detection:features:standard-identifiers:ISBN`);\nconst debugData = debug.extend('data');\n\nexport default () => {\n  const IDENTIFIER_NAME = 'ISBN';\n\n  function validatorAndNormalizer(string) {\n    const isbnParseResult = isbnParse(string);\n    debugData(`isbnParseResult: ${JSON.stringify(isbnParseResult)}`);\n    if (isbnParseResult === null) {\n      debug(`Not parseable ISBN, just removing hyphens`);\n      return {valid: false, value: string.replace(/-/ug, '')};\n    }\n    debug(`Parseable ISBN, normalizing to ISBN-13`);\n    return {valid: true, value: isbnParseResult.isbn13};\n  }\n\n  const {extract, compare} = createInterface({identifier: IDENTIFIER_NAME, pattern: /^020$/u, subfieldCodes: ['a', 'z'], validIdentifierSubfieldCodes: ['a'], invalidIdentifierSubfieldCodes: ['z'], validatorAndNormalizer});\n  return {extract, compare, name: IDENTIFIER_NAME};\n};\n\n"],
+  "mappings": "AACA,OAAO,uBAAuB;AAC9B,SAAQ,SAAS,iBAAgB;AACjC,OAAO,qBAAqB;AAE5B,MAAM,QAAQ,kBAAkB,sFAAsF;AACtH,MAAM,YAAY,MAAM,OAAO,MAAM;AAErC,eAAe,MAAM;AACnB,QAAM,kBAAkB;AAExB,WAAS,uBAAuB,QAAQ;AACtC,UAAM,kBAAkB,UAAU,MAAM;AACxC,cAAU,oBAAoB,KAAK,UAAU,eAAe,CAAC,EAAE;AAC/D,QAAI,oBAAoB,MAAM;AAC5B,YAAM,2CAA2C;AACjD,aAAO,EAAC,OAAO,OAAO,OAAO,OAAO,QAAQ,OAAO,EAAE,EAAC;AAAA,IACxD;AACA,UAAM,wCAAwC;AAC9C,WAAO,EAAC,OAAO,MAAM,OAAO,gBAAgB,OAAM;AAAA,EACpD;AAEA,QAAM,EAAC,SAAS,QAAO,IAAI,gBAAgB,EAAC,YAAY,iBAAiB,SAAS,UAAU,eAAe,CAAC,KAAK,GAAG,GAAG,8BAA8B,CAAC,GAAG,GAAG,gCAAgC,CAAC,GAAG,GAAG,uBAAsB,CAAC;AAC1N,SAAO,EAAC,SAAS,SAAS,MAAM,gBAAe;AACjD;",
+  "names": []
+}

package/dist/match-detection/features/bib/issn.js

@@ -0,0 +1,6 @@
+import createInterface from "./standard-identifier-factory.js";
+export default () => {
+  const { extract, compare } = createInterface({ pattern: /^022$/u, subfieldCodes: ["a", "z", "y"] });
+  return { extract, compare, name: "ISSN" };
+};
+//# sourceMappingURL=issn.js.map

package/dist/match-detection/features/bib/issn.js.map

@@ -0,0 +1,7 @@
+{
+  "version": 3,
+  "sources": ["../../../../src/match-detection/features/bib/issn.js"],
+  "sourcesContent": ["\nimport createInterface from './standard-identifier-factory.js';\n\nexport default () => {\n  const {extract, compare} = createInterface({pattern: /^022$/u, subfieldCodes: ['a', 'z', 'y']});\n  return {extract, compare, name: 'ISSN'};\n};\n"],
+  "mappings": "AACA,OAAO,qBAAqB;AAE5B,eAAe,MAAM;AACnB,QAAM,EAAC,SAAS,QAAO,IAAI,gBAAgB,EAAC,SAAS,UAAU,eAAe,CAAC,KAAK,KAAK,GAAG,EAAC,CAAC;AAC9F,SAAO,EAAC,SAAS,SAAS,MAAM,OAAM;AACxC;",
+  "names": []
+}

package/dist/match-detection/features/bib/language.js

@@ -0,0 +1,80 @@
+import createDebugLogger from "debug";
+import { getMatchCounts } from "../../../matching-utils.js";
+const debug = createDebugLogger("@natlibfi/melinda-record-matching:match-detection:features:language");
+const debugData = debug.extend("data");
+export default () => ({
+  name: "Language",
+  extract: ({ record, recordExternal }) => {
+    const label = recordExternal && recordExternal.label ? recordExternal.label : "record";
+    const value008 = get008Value();
+    const values041 = get041Values();
+    debugData(`${label}: 008: ${JSON.stringify(value008)}, 041: ${JSON.stringify(values041)}`);
+    if (!value008 && values041.length < 1) {
+      debugData(`${label}: No actual values found`);
+      return [];
+    }
+    const allValues = value008 === void 0 ? values041 : values041.concat(value008);
+    const uniqueSortedValues = [...new Set(allValues)].sort();
+    return uniqueSortedValues;
+    function get008Value() {
+      const value = record.get(/^008$/u)?.[0]?.value || void 0;
+      debugData(`${label}: 008 value: ${value}`);
+      if (!value) {
+        return void 0;
+      }
+      const code = value.slice(35, 38);
+      debugData(`${label}: 008 code: ${code}`);
+      return isLangCodeForALanguage(code) ? code : void 0;
+    }
+    function get041Values() {
+      return record.get(/^041$/u).filter(({ ind2 }) => ind2 === " ").map(({ subfields }) => subfields).flat().filter(({ code }) => code === "a" || code === "d").filter(({ value }) => value && isLangCodeForALanguage(value)).map(({ value }) => value);
+    }
+    function isLangCodeForALanguage(code) {
+      if (code.length !== 3) {
+        debugData(`Code ${code} is not correct length (3) for a language code.`);
+        return false;
+      }
+      if (code === "|||" || code === "   " || code === "^^^" || code === "mul" || code === "zxx") {
+        debugData(`Code ${code} is not code for a spesific language.`);
+        return false;
+      }
+      const langCodePattern = /^[a-z][a-z][a-z]$/ui;
+      if (!langCodePattern.test(code)) {
+        debugData(`Code ${code} is not valid as a language code`);
+        return false;
+      }
+      return true;
+    }
+  },
+  // eslint-disable-next-line max-statements
+  compare: (a, b) => {
+    debugData(`Comparing ${JSON.stringify(a)} and ${JSON.stringify(b)}`);
+    if (a.length === 0 || b.length === 0) {
+      debugData(`No language to compare`);
+      return 0;
+    }
+    if (a.length === b.length && a.every((element, index) => element === b[index])) {
+      debugData(`All languages match`);
+      return 0.1;
+    }
+    const { matchingValues, possibleMatchValues, maxValues } = getMatchCounts(a, b);
+    if (matchingValues < 1) {
+      debug(`Both have languages, but none of these match.`);
+      return -1;
+    }
+    debug(`Both have languages, ${matchingValues}/${possibleMatchValues} valid languages match.`);
+    debug(`Possible matches: ${possibleMatchValues}/${maxValues}`);
+    const missingCount = maxValues - possibleMatchValues;
+    const misMatchCount = possibleMatchValues - matchingValues;
+    debug(`	 missing: ${missingCount}`);
+    debug(`	 mismatches: ${misMatchCount}`);
+    const penaltyForMissing = 0.02 * (maxValues - possibleMatchValues);
+    const penaltyForMisMatch = 0.05 * (possibleMatchValues - matchingValues);
+    debug(`	 points: penaltyForMissing: ${penaltyForMissing}`);
+    debug(`	 points: penaltyForMisMatch: ${penaltyForMisMatch}`);
+    const points = Number(Number(0.1 - penaltyForMisMatch - penaltyForMissing).toFixed(2));
+    debug(`Total points: ${points}`);
+    return points;
+  }
+});
+//# sourceMappingURL=language.js.map

package/dist/match-detection/features/bib/language.js.map

@@ -0,0 +1,7 @@
+{
+  "version": 3,
+  "sources": ["../../../../src/match-detection/features/bib/language.js"],
+  "sourcesContent": ["\nimport createDebugLogger from 'debug';\nimport {getMatchCounts} from '../../../matching-utils.js';\n\nconst debug = createDebugLogger('@natlibfi/melinda-record-matching:match-detection:features:language');\nconst debugData = debug.extend('data');\n\nexport default () => ({\n  name: 'Language',\n  extract: ({record, recordExternal}) => {\n    const label = recordExternal && recordExternal.label ? recordExternal.label : 'record';\n\n    const value008 = get008Value();\n    const values041 = get041Values();\n    debugData(`${label}: 008: ${JSON.stringify(value008)}, 041: ${JSON.stringify(values041)}`);\n\n    if (!value008 && values041.length < 1) {\n      debugData(`${label}: No actual values found`);\n      return [];\n    }\n\n    const allValues = value008 === undefined ? values041 : values041.concat(value008);\n    const uniqueSortedValues = [...new Set(allValues)].sort();\n\n    return uniqueSortedValues;\n\n    function get008Value() {\n      const value = record.get(/^008$/u)?.[0]?.value || undefined;\n      debugData(`${label}: 008 value: ${value}`);\n\n      if (!value) {\n        return undefined;\n      }\n\n      const code = value.slice(35, 38);\n      debugData(`${label}: 008 code: ${code}`);\n      return isLangCodeForALanguage(code) ? code : undefined;\n    }\n\n    // Uses only f041s that have 2nd ind ' ', which means that the codes used are MARC 21 language codes\n\n    function get041Values() {\n      return record.get(/^041$/u)\n        .filter(({ind2}) => ind2 === ' ')\n        .map(({subfields}) => subfields)\n        .flat()\n        .filter(({code}) => code === 'a' || code === 'd')\n        .filter(({value}) => value && isLangCodeForALanguage(value))\n        .map(({value}) => value);\n    }\n\n    // Check if a string is a possible, validly formed language code for a single language\n    // Currently accept also codes in capitals\n    function isLangCodeForALanguage(code) {\n      if (code.length !== 3) {\n        debugData(`Code ${code} is not correct length (3) for a language code.`);\n        return false;\n      }\n      if (code === '|||' || code === '   ' || code === '^^^' || code === 'mul' || code === 'zxx') {\n        debugData(`Code ${code} is not code for a spesific language.`);\n        return false;\n      }\n      const langCodePattern = /^[a-z][a-z][a-z]$/ui;\n      if (!langCodePattern.test(code)) {\n        debugData(`Code ${code} is not valid as a language code`);\n        return false;\n      }\n      return true;\n    }\n\n  },\n  // eslint-disable-next-line max-statements\n  compare: (a, b) => {\n    debugData(`Comparing ${JSON.stringify(a)} and ${JSON.stringify(b)}`);\n\n    if (a.length === 0 || b.length === 0) {\n      debugData(`No language to compare`);\n      return 0;\n    }\n\n    if (a.length === b.length && a.every((element, index) => element === b[index])) {\n      debugData(`All languages match`);\n      return 0.1;\n    }\n\n    const {matchingValues, possibleMatchValues, maxValues} = getMatchCounts(a, b);\n\n    if (matchingValues < 1) {\n      debug(`Both have languages, but none of these match.`);\n      return -1.0;\n    }\n    debug(`Both have languages, ${matchingValues}/${possibleMatchValues} valid languages match.`);\n    // ignore non-matches if there is mismatching amount of values\n    debug(`Possible matches: ${possibleMatchValues}/${maxValues}`);\n    //we give some kind of penalty for mismatching amount of values instead of simple divide?\n    const missingCount = maxValues - possibleMatchValues;\n    const misMatchCount = possibleMatchValues - matchingValues;\n    debug(`\\t missing: ${missingCount}`);\n    debug(`\\t mismatches: ${misMatchCount}`);\n\n    const penaltyForMissing = 0.02 * (maxValues - possibleMatchValues);\n    const penaltyForMisMatch = 0.05 * (possibleMatchValues - matchingValues);\n    debug(`\\t points: penaltyForMissing: ${penaltyForMissing}`);\n    debug(`\\t points: penaltyForMisMatch: ${penaltyForMisMatch}`);\n\n    const points = Number(Number(0.1 - penaltyForMisMatch - penaltyForMissing).toFixed(2));\n    debug(`Total points: ${points}`);\n\n    return points;\n  }\n});\n"],
+  "mappings": "AACA,OAAO,uBAAuB;AAC9B,SAAQ,sBAAqB;AAE7B,MAAM,QAAQ,kBAAkB,qEAAqE;AACrG,MAAM,YAAY,MAAM,OAAO,MAAM;AAErC,eAAe,OAAO;AAAA,EACpB,MAAM;AAAA,EACN,SAAS,CAAC,EAAC,QAAQ,eAAc,MAAM;AACrC,UAAM,QAAQ,kBAAkB,eAAe,QAAQ,eAAe,QAAQ;AAE9E,UAAM,WAAW,YAAY;AAC7B,UAAM,YAAY,aAAa;AAC/B,cAAU,GAAG,KAAK,UAAU,KAAK,UAAU,QAAQ,CAAC,UAAU,KAAK,UAAU,SAAS,CAAC,EAAE;AAEzF,QAAI,CAAC,YAAY,UAAU,SAAS,GAAG;AACrC,gBAAU,GAAG,KAAK,0BAA0B;AAC5C,aAAO,CAAC;AAAA,IACV;AAEA,UAAM,YAAY,aAAa,SAAY,YAAY,UAAU,OAAO,QAAQ;AAChF,UAAM,qBAAqB,CAAC,GAAG,IAAI,IAAI,SAAS,CAAC,EAAE,KAAK;AAExD,WAAO;AAEP,aAAS,cAAc;AACrB,YAAM,QAAQ,OAAO,IAAI,QAAQ,IAAI,CAAC,GAAG,SAAS;AAClD,gBAAU,GAAG,KAAK,gBAAgB,KAAK,EAAE;AAEzC,UAAI,CAAC,OAAO;AACV,eAAO;AAAA,MACT;AAEA,YAAM,OAAO,MAAM,MAAM,IAAI,EAAE;AAC/B,gBAAU,GAAG,KAAK,eAAe,IAAI,EAAE;AACvC,aAAO,uBAAuB,IAAI,IAAI,OAAO;AAAA,IAC/C;AAIA,aAAS,eAAe;AACtB,aAAO,OAAO,IAAI,QAAQ,EACvB,OAAO,CAAC,EAAC,KAAI,MAAM,SAAS,GAAG,EAC/B,IAAI,CAAC,EAAC,UAAS,MAAM,SAAS,EAC9B,KAAK,EACL,OAAO,CAAC,EAAC,KAAI,MAAM,SAAS,OAAO,SAAS,GAAG,EAC/C,OAAO,CAAC,EAAC,MAAK,MAAM,SAAS,uBAAuB,KAAK,CAAC,EAC1D,IAAI,CAAC,EAAC,MAAK,MAAM,KAAK;AAAA,IAC3B;AAIA,aAAS,uBAAuB,MAAM;AACpC,UAAI,KAAK,WAAW,GAAG;AACrB,kBAAU,QAAQ,IAAI,iDAAiD;AACvE,eAAO;AAAA,MACT;AACA,UAAI,SAAS,SAAS,SAAS,SAAS,SAAS,SAAS,SAAS,SAAS,SAAS,OAAO;AAC1F,kBAAU,QAAQ,IAAI,uCAAuC;AAC7D,eAAO;AAAA,MACT;AACA,YAAM,kBAAkB;AACxB,UAAI,CAAC,gBAAgB,KAAK,IAAI,GAAG;AAC/B,kBAAU,QAAQ,IAAI,kCAAkC;AACxD,eAAO;AAAA,MACT;AACA,aAAO;AAAA,IACT;AAAA,EAEF;AAAA;AAAA,EAEA,SAAS,CAAC,GAAG,MAAM;AACjB,cAAU,aAAa,KAAK,UAAU,CAAC,CAAC,QAAQ,KAAK,UAAU,CAAC,CAAC,EAAE;AAEnE,QAAI,EAAE,WAAW,KAAK,EAAE,WAAW,GAAG;AACpC,gBAAU,wBAAwB;AAClC,aAAO;AAAA,IACT;AAEA,QAAI,EAAE,WAAW,EAAE,UAAU,EAAE,MAAM,CAAC,SAAS,UAAU,YAAY,EAAE,KAAK,CAAC,GAAG;AAC9E,gBAAU,qBAAqB;AAC/B,aAAO;AAAA,IACT;AAEA,UAAM,EAAC,gBAAgB,qBAAqB,UAAS,IAAI,eAAe,GAAG,CAAC;AAE5E,QAAI,iBAAiB,GAAG;AACtB,YAAM,+CAA+C;AACrD,aAAO;AAAA,IACT;AACA,UAAM,wBAAwB,cAAc,IAAI,mBAAmB,yBAAyB;AAE5F,UAAM,qBAAqB,mBAAmB,IAAI,SAAS,EAAE;AAE7D,UAAM,eAAe,YAAY;AACjC,UAAM,gBAAgB,sBAAsB;AAC5C,UAAM,cAAe,YAAY,EAAE;AACnC,UAAM,iBAAkB,aAAa,EAAE;AAEvC,UAAM,oBAAoB,QAAQ,YAAY;AAC9C,UAAM,qBAAqB,QAAQ,sBAAsB;AACzD,UAAM,gCAAiC,iBAAiB,EAAE;AAC1D,UAAM,iCAAkC,kBAAkB,EAAE;AAE5D,UAAM,SAAS,OAAO,OAAO,MAAM,qBAAqB,iBAAiB,EAAE,QAAQ,CAAC,CAAC;AACrF,UAAM,iBAAiB,MAAM,EAAE;AAE/B,WAAO;AAAA,EACT;AACF;",
+  "names": []
+}

package/dist/match-detection/features/bib/media-type.js

@@ -0,0 +1,31 @@
+import createDebugLogger from "debug";
+const debug = createDebugLogger("@natlibfi/melinda-record-matching:match-detection:features:media-type");
+const debugData = debug.extend("data");
+export default () => ({
+  name: "Media type",
+  extract: ({ record, recordExternal }) => {
+    const label = recordExternal && recordExternal.label ? recordExternal.label : "record";
+    debugData(`Record (${label}): ${JSON.stringify(record)}`);
+    debugData(`RecordExternal: ${JSON.stringify(recordExternal)}`);
+    const values337 = get337Values();
+    debug(`${label}: 337 $b values: ${JSON.stringify(values337)}`);
+    return values337;
+    function get337Values() {
+      return record.get(/^337$/u).filter((f) => f.subfields.some((subfield) => subfield.code === "2" && subfield.value === "rdamedia")).map(({ subfields }) => subfields).flat().filter(({ code }) => code === "b").map(({ value }) => value);
+    }
+  },
+  compare: (a, b) => {
+    debugData(`Comparing ${JSON.stringify(a)} and ${JSON.stringify(b)}`);
+    if (a.every((elem) => b.includes(elem))) {
+      debug(`All mediaTypes from A are in B`);
+      return 1;
+    }
+    if (b.every((elem) => a.includes(elem))) {
+      debug(`All mediaTypes from B are in A`);
+      return 1;
+    }
+    debug(`Mismatch in mediaTypes between A and B`);
+    return -1;
+  }
+});
+//# sourceMappingURL=media-type.js.map

package/dist/match-detection/features/bib/media-type.js.map

@@ -0,0 +1,7 @@
+{
+  "version": 3,
+  "sources": ["../../../../src/match-detection/features/bib/media-type.js"],
+  "sourcesContent": ["/* eslint-disable max-statements */\n\n\nimport createDebugLogger from 'debug';\n\nconst debug = createDebugLogger('@natlibfi/melinda-record-matching:match-detection:features:media-type');\nconst debugData = debug.extend('data');\n\nexport default () => ({\n  name: 'Media type',\n  extract: ({record, recordExternal}) => {\n    const label = recordExternal && recordExternal.label ? recordExternal.label : 'record';\n    debugData(`Record (${label}): ${JSON.stringify(record)}`);\n    debugData(`RecordExternal: ${JSON.stringify(recordExternal)}`);\n    const values337 = get337Values();\n    debug(`${label}: 337 $b values: ${JSON.stringify(values337)}`);\n\n    return values337;\n\n    function get337Values() {\n      return record.get(/^337$/u)\n        .filter(f => f.subfields.some((subfield) => subfield.code === '2' && subfield.value === 'rdamedia'))\n        .map(({subfields}) => subfields)\n        .flat()\n        .filter(({code}) => code === 'b')\n        .map(({value}) => value);\n    }\n  },\n  compare: (a, b) => {\n    debugData(`Comparing ${JSON.stringify(a)} and ${JSON.stringify(b)}`);\n\n    // Should we give extra good points if all mediaTypes match?\n    // Should we give partial points for partially matching mediaTypes?\n    // Should we check whether recordType is 'mixedMaterials'\n    // Should we okay typical cases of not totally matching mediaTypes? What would these be?\n\n    if (a.every(elem => b.includes(elem))) {\n      debug(`All mediaTypes from A are in B`);\n      return 1;\n    }\n\n    if (b.every(elem => a.includes(elem))) {\n      debug(`All mediaTypes from B are in A`);\n      return 1;\n    }\n\n    debug(`Mismatch in mediaTypes between A and B`);\n    return -1;\n\n  }\n});\n"],
+  "mappings": "AAGA,OAAO,uBAAuB;AAE9B,MAAM,QAAQ,kBAAkB,uEAAuE;AACvG,MAAM,YAAY,MAAM,OAAO,MAAM;AAErC,eAAe,OAAO;AAAA,EACpB,MAAM;AAAA,EACN,SAAS,CAAC,EAAC,QAAQ,eAAc,MAAM;AACrC,UAAM,QAAQ,kBAAkB,eAAe,QAAQ,eAAe,QAAQ;AAC9E,cAAU,WAAW,KAAK,MAAM,KAAK,UAAU,MAAM,CAAC,EAAE;AACxD,cAAU,mBAAmB,KAAK,UAAU,cAAc,CAAC,EAAE;AAC7D,UAAM,YAAY,aAAa;AAC/B,UAAM,GAAG,KAAK,oBAAoB,KAAK,UAAU,SAAS,CAAC,EAAE;AAE7D,WAAO;AAEP,aAAS,eAAe;AACtB,aAAO,OAAO,IAAI,QAAQ,EACvB,OAAO,OAAK,EAAE,UAAU,KAAK,CAAC,aAAa,SAAS,SAAS,OAAO,SAAS,UAAU,UAAU,CAAC,EAClG,IAAI,CAAC,EAAC,UAAS,MAAM,SAAS,EAC9B,KAAK,EACL,OAAO,CAAC,EAAC,KAAI,MAAM,SAAS,GAAG,EAC/B,IAAI,CAAC,EAAC,MAAK,MAAM,KAAK;AAAA,IAC3B;AAAA,EACF;AAAA,EACA,SAAS,CAAC,GAAG,MAAM;AACjB,cAAU,aAAa,KAAK,UAAU,CAAC,CAAC,QAAQ,KAAK,UAAU,CAAC,CAAC,EAAE;AAOnE,QAAI,EAAE,MAAM,UAAQ,EAAE,SAAS,IAAI,CAAC,GAAG;AACrC,YAAM,gCAAgC;AACtC,aAAO;AAAA,IACT;AAEA,QAAI,EAAE,MAAM,UAAQ,EAAE,SAAS,IAAI,CAAC,GAAG;AACrC,YAAM,gCAAgC;AACtC,aAAO;AAAA,IACT;AAEA,UAAM,wCAAwC;AAC9C,WAAO;AAAA,EAET;AACF;",
+  "names": []
+}

package/dist/match-detection/features/bib/melinda-id.js

@@ -0,0 +1,6 @@
+import createInterface from "./melinda-identifier-factory.js";
+export default () => {
+  const { extract, compare } = createInterface();
+  return { extract, compare, name: "melinda-id" };
+};
+//# sourceMappingURL=melinda-id.js.map

package/dist/match-detection/features/bib/melinda-id.js.map

@@ -0,0 +1,7 @@
+{
+  "version": 3,
+  "sources": ["../../../../src/match-detection/features/bib/melinda-id.js"],
+  "sourcesContent": ["\nimport createInterface from './melinda-identifier-factory.js';\n\nexport default () => {\n  const {extract, compare} = createInterface();\n  return {extract, compare, name: 'melinda-id'};\n};\n"],
+  "mappings": "AACA,OAAO,qBAAqB;AAE5B,eAAe,MAAM;AACnB,QAAM,EAAC,SAAS,QAAO,IAAI,gBAAgB;AAC3C,SAAO,EAAC,SAAS,SAAS,MAAM,aAAY;AAC9C;",
+  "names": []
+}

package/dist/match-detection/features/bib/melinda-identifier-factory.js

@@ -0,0 +1,38 @@
+import createDebugLogger from "debug";
+import { getMelindaIdsF035 } from "../../../matching-utils.js";
+export default () => {
+  const debug = createDebugLogger("@natlibfi/melinda-record-matching:match-detection:features/bib/melinda-id");
+  const debugData = debug.extend("data");
+  return { extract, compare };
+  function extract({ record, recordExternal }) {
+    const isMelindaRecord = record.get("003").some((f003) => f003.value === "FI-MELINDA");
+    const [f001] = record.get("001").map((field) => field.value);
+    const f035MelindaIds = getMelindaIdsF035(record);
+    if (isMelindaRecord === void 0 && f001 === void 0 && f035MelindaIds.length < 1) {
+      debug(`${recordExternal.label} No Melinda-IDs found`);
+      return {};
+    }
+    return { isMelindaRecord, f001, f035MelindaIds };
+  }
+  function compare(a, b) {
+    if (a.isMelindaRecord && b.isMelindaRecord && a.f001 === b.f001) {
+      debugData(`Melinda record's A f001 ${a.f001} matches Melinda record's B f001 ${a.f001}`);
+      return 1;
+    }
+    if (a.isMelindaRecord && typeof b.f035MelindaIds !== "undefined" && b.f035MelindaIds.some((id) => id === a.f001)) {
+      debugData(`Melinda record's A f001 ${a.f001} matches record B f035 ${JSON.stringify(b.f035MelindaIds)}`);
+      return 1;
+    }
+    if (b.isMelindaRecord && typeof a.f035MelindaIds !== "undefined" && a.f035MelindaIds.some((id) => id === b.f001)) {
+      debugData(`Melinda record's B f001 ${b.f001} matches record A f035 ${JSON.stringify(a.f035MelindaIds)}`);
+      return 1;
+    }
+    if (typeof a.f035MelindaIds !== "undefined" && typeof b.f035MelindaIds !== "undefined" && a.f035MelindaIds.some((idA) => b.f035MelindaIds.some((idB) => idB === idA))) {
+      debugData(`Record A f035 ${JSON.stringify(a.f035MelindaIds)} matches record B f035 ${JSON.stringify(b.f035MelindaIds)}`);
+      return 1;
+    }
+    debug(`No matching Melinda-IDs.`);
+    return 0;
+  }
+};
+//# sourceMappingURL=melinda-identifier-factory.js.map

package/dist/match-detection/features/bib/melinda-identifier-factory.js.map

@@ -0,0 +1,7 @@
+{
+  "version": 3,
+  "sources": ["../../../../src/match-detection/features/bib/melinda-identifier-factory.js"],
+  "sourcesContent": ["\nimport createDebugLogger from 'debug';\nimport {getMelindaIdsF035} from '../../../matching-utils.js';\n\n// 003+001 FI-MELINDA <melinda-id>\n// 035 $a (FI-MELINDA)<melinda-id>\n// 035 $z (FI-MELINDA)<melinda-id>\n// 035 $a FCC<melinda-id>\n// 035 $z FCC<melinda-id>\n// melinda-id = 001234567\n\nexport default () => {\n\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:match-detection:features/bib/melinda-id');\n  const debugData = debug.extend('data');\n\n  return {extract, compare};\n\n  function extract({record, recordExternal}) {\n\n    const isMelindaRecord = record.get('003').some(f003 => f003.value === 'FI-MELINDA');\n    const [f001] = record.get('001').map(field => field.value);\n    const f035MelindaIds = getMelindaIdsF035(record);\n\n    if (\n      isMelindaRecord === undefined &&\n      f001 === undefined &&\n      f035MelindaIds.length < 1) {\n\n      debug(`${recordExternal.label} No Melinda-IDs found`);\n      return {};\n    }\n\n    return {isMelindaRecord, f001, f035MelindaIds};\n\n  }\n\n  function compare(a, b) {\n\n    if (a.isMelindaRecord && b.isMelindaRecord &&\n      a.f001 === b.f001) {\n      debugData(`Melinda record's A f001 ${a.f001} matches Melinda record's B f001 ${a.f001}`);\n      return 1;\n    }\n\n    if (a.isMelindaRecord && typeof b.f035MelindaIds !== 'undefined' &&\n      b.f035MelindaIds.some(id => id === a.f001)) {\n      debugData(`Melinda record's A f001 ${a.f001} matches record B f035 ${JSON.stringify(b.f035MelindaIds)}`);\n      return 1;\n    }\n\n    if (b.isMelindaRecord && typeof a.f035MelindaIds !== 'undefined' &&\n      a.f035MelindaIds.some(id => id === b.f001)) {\n      debugData(`Melinda record's B f001 ${b.f001} matches record A f035 ${JSON.stringify(a.f035MelindaIds)}`);\n      return 1;\n    }\n\n    if (typeof a.f035MelindaIds !== 'undefined' && typeof b.f035MelindaIds !== 'undefined' &&\n      a.f035MelindaIds.some(idA => b.f035MelindaIds.some(idB => idB === idA))) {\n      debugData(`Record A f035 ${JSON.stringify(a.f035MelindaIds)} matches record B f035 ${JSON.stringify(b.f035MelindaIds)}`);\n      return 1;\n    }\n    debug(`No matching Melinda-IDs.`);\n    return 0;\n  }\n};\n"],
+  "mappings": "AACA,OAAO,uBAAuB;AAC9B,SAAQ,yBAAwB;AAShC,eAAe,MAAM;AAEnB,QAAM,QAAQ,kBAAkB,2EAA2E;AAC3G,QAAM,YAAY,MAAM,OAAO,MAAM;AAErC,SAAO,EAAC,SAAS,QAAO;AAExB,WAAS,QAAQ,EAAC,QAAQ,eAAc,GAAG;AAEzC,UAAM,kBAAkB,OAAO,IAAI,KAAK,EAAE,KAAK,UAAQ,KAAK,UAAU,YAAY;AAClF,UAAM,CAAC,IAAI,IAAI,OAAO,IAAI,KAAK,EAAE,IAAI,WAAS,MAAM,KAAK;AACzD,UAAM,iBAAiB,kBAAkB,MAAM;AAE/C,QACE,oBAAoB,UACpB,SAAS,UACT,eAAe,SAAS,GAAG;AAE3B,YAAM,GAAG,eAAe,KAAK,uBAAuB;AACpD,aAAO,CAAC;AAAA,IACV;AAEA,WAAO,EAAC,iBAAiB,MAAM,eAAc;AAAA,EAE/C;AAEA,WAAS,QAAQ,GAAG,GAAG;AAErB,QAAI,EAAE,mBAAmB,EAAE,mBACzB,EAAE,SAAS,EAAE,MAAM;AACnB,gBAAU,2BAA2B,EAAE,IAAI,oCAAoC,EAAE,IAAI,EAAE;AACvF,aAAO;AAAA,IACT;AAEA,QAAI,EAAE,mBAAmB,OAAO,EAAE,mBAAmB,eACnD,EAAE,eAAe,KAAK,QAAM,OAAO,EAAE,IAAI,GAAG;AAC5C,gBAAU,2BAA2B,EAAE,IAAI,0BAA0B,KAAK,UAAU,EAAE,cAAc,CAAC,EAAE;AACvG,aAAO;AAAA,IACT;AAEA,QAAI,EAAE,mBAAmB,OAAO,EAAE,mBAAmB,eACnD,EAAE,eAAe,KAAK,QAAM,OAAO,EAAE,IAAI,GAAG;AAC5C,gBAAU,2BAA2B,EAAE,IAAI,0BAA0B,KAAK,UAAU,EAAE,cAAc,CAAC,EAAE;AACvG,aAAO;AAAA,IACT;AAEA,QAAI,OAAO,EAAE,mBAAmB,eAAe,OAAO,EAAE,mBAAmB,eACzE,EAAE,eAAe,KAAK,SAAO,EAAE,eAAe,KAAK,SAAO,QAAQ,GAAG,CAAC,GAAG;AACzE,gBAAU,iBAAiB,KAAK,UAAU,EAAE,cAAc,CAAC,0BAA0B,KAAK,UAAU,EAAE,cAAc,CAAC,EAAE;AACvH,aAAO;AAAA,IACT;AACA,UAAM,0BAA0B;AAChC,WAAO;AAAA,EACT;AACF;",
+  "names": []
+}

package/dist/match-detection/features/bib/other-standard-identifier.js

@@ -0,0 +1,6 @@
+import createInterface from "./standard-identifier-factory.js";
+export default () => {
+  const { extract, compare } = createInterface({ pattern: /^024$/u, subfieldCodes: ["a", "z"] });
+  return { extract, compare, name: "Other standard identifier" };
+};
+//# sourceMappingURL=other-standard-identifier.js.map

package/dist/match-detection/features/bib/other-standard-identifier.js.map

@@ -0,0 +1,7 @@
+{
+  "version": 3,
+  "sources": ["../../../../src/match-detection/features/bib/other-standard-identifier.js"],
+  "sourcesContent": ["\nimport createInterface from './standard-identifier-factory.js';\n\n// DEVELOP: we should compare indicators and sf2 for f024\n\nexport default () => {\n  const {extract, compare} = createInterface({pattern: /^024$/u, subfieldCodes: ['a', 'z']});\n  return {extract, compare, name: 'Other standard identifier'};\n};\n"],
+  "mappings": "AACA,OAAO,qBAAqB;AAI5B,eAAe,MAAM;AACnB,QAAM,EAAC,SAAS,QAAO,IAAI,gBAAgB,EAAC,SAAS,UAAU,eAAe,CAAC,KAAK,GAAG,EAAC,CAAC;AACzF,SAAO,EAAC,SAAS,SAAS,MAAM,4BAA2B;AAC7D;",
+  "names": []
+}

package/dist/match-detection/features/bib/publication-time-allow-cons-years-multi.js

@@ -0,0 +1,116 @@
+import createDebugLogger from "debug";
+import { testStringOrNumber } from "../../../matching-utils.js";
+export default () => ({
+  name: "Publication time, allow consequent years, years from multiple sources",
+  extract: ({ record, recordExternal }) => {
+    const debug = createDebugLogger("@natlibfi/melinda-record-matching:match-detection:features/bib/publication-time-allow-cons-years-multi");
+    const label = recordExternal && recordExternal.label ? recordExternal.label : "record";
+    const f008Values = extractF008Values(record);
+    debug(`${label}: f008: ${JSON.stringify(f008Values)}`);
+    const f26xValues = extractF26xValues(record);
+    debug(`${label}: f26x: ${JSON.stringify(f26xValues)}`);
+    const f500Values = extractF500Years(record);
+    debug(`${label}: f500: ${JSON.stringify(f500Values)}`);
+    const normalYears = [...new Set(f26xValues.normalYears.concat(f008Values.f008Date1).filter((value) => value && value !== "    " && value !== "||||"))].sort();
+    const copyrightYears = [...new Set(f26xValues.copyrightYears)].sort();
+    const reprintYears = [...new Set(f500Values)].sort();
+    const combined = { normalYears, copyrightYears, reprintYears };
+    debug(`Combined: ${JSON.stringify(combined)}`);
+    return combined;
+    function extractF008Values(record2) {
+      const value = record2.get(/^008$/u)?.[0]?.value || void 0;
+      if (value && testStringOrNumber(value)) {
+        const f008Date1 = extractF008Date1(value);
+        const f008Date2 = extractF008Date2(value);
+        const f008YearType = extractF008YearType(value);
+        return { f008Date1, f008Date2, f008YearType };
+      }
+      return { f008Date1: void 0, f008Date2: void 0, f008YearType: void 0 };
+      function extractF008Date1(value2) {
+        return String(value2).slice(7, 11);
+      }
+      function extractF008Date2(value2) {
+        return String(value2).slice(11, 15);
+      }
+      function extractF008YearType(value2) {
+        return String(value2).slice(6, 7);
+      }
+    }
+    function extractF26xValues(record2) {
+      const copyrightRegex = /^(?<copyrightPrefix>cop|cop.|c|©|p|℗)/u;
+      const pubNormalSubFieldValues = extractPubNormalSubfieldValues(record2, copyrightRegex);
+      debug(`Normal years: ${JSON.stringify(pubNormalSubFieldValues)}`);
+      const pubF264CopySubFieldValues = extractPubF264CopySubfieldValues(record2);
+      debug(`F264 copyright years: ${JSON.stringify(pubF264CopySubFieldValues)}`);
+      const pubF260CopySubFieldValues = extractPubF260CopySubfieldValues(record2, copyrightRegex);
+      debug(`F260 copyright years: ${JSON.stringify(pubF260CopySubFieldValues)}`);
+      return { normalYears: pubNormalSubFieldValues, copyrightYears: [...pubF260CopySubFieldValues, ...pubF264CopySubFieldValues] };
+      function extractPubNormalSubfieldValues(record3, copyrightRegex2) {
+        return record3.get(/^26[04]$/u).filter((field) => !(field.tag === "264" && field.ind2 === "4")).map(({ subfields }) => subfields).flat().filter(({ code }) => code && code === "c").filter(({ value }) => value && !copyrightRegex2.test(value)).map(({ value }) => value).map((value) => removeNonAlphaNumeric(value));
+      }
+      function extractPubF264CopySubfieldValues(record3, copyrightRegex2) {
+        return record3.get(/^264$/u).filter((field) => field.ind2 === "4").map(({ subfields }) => subfields).flat().filter(({ code }) => code && code === "c").filter(({ value }) => value).map(({ value }) => value).map((value) => value.replace(copyrightRegex2, "")).map((value) => removeNonAlphaNumeric(value));
+      }
+      function extractPubF260CopySubfieldValues(record3, copyrightRegex2) {
+        return record3.get(/^260$/u).map(({ subfields }) => subfields).flat().filter(({ code }) => code && code === "c").filter(({ value }) => value && copyrightRegex2.test(value)).map(({ value }) => value).map((value) => value.replace(copyrightRegex2, "")).map((value) => removeNonAlphaNumeric(value));
+      }
+      function removeNonAlphaNumeric(value) {
+        debug(`Cleaning: ${JSON.stringify(value)}`);
+        const nonAlphaNumericRegex = /[^A-Za-z0-9]/ug;
+        return value ? value.replace(nonAlphaNumericRegex, "") : value;
+      }
+    }
+    function extractF500Years(record2) {
+      const reprintRegex = /(?<reprint>Lisäpainokset:|Lisäpainos:)/u;
+      const reprintFieldContents = record2.get(/^500$/u).map(({ subfields }) => subfields).flat().filter(({ code }) => code === "a").map(({ value }) => value);
+      debug(`f500 reprint field contents: ${JSON.stringify(reprintFieldContents)}`);
+      const filteredF500 = reprintFieldContents.filter((content) => content && content.match(reprintRegex));
+      debug(`f500 reprint field contents (filtered): ${JSON.stringify(filteredF500)}`);
+      const reprintYears2 = extractReprintYears(filteredF500);
+      return reprintYears2;
+    }
+    function extractReprintYears(contents) {
+      const yearRegex = /[0-9][0-9][0-9][0-9]/gu;
+      const years = contents.map((content) => content.match(yearRegex)).flat();
+      debug(`${JSON.stringify(years)}`);
+      const uniqYears = [...new Set(years)].sort();
+      debug(`${JSON.stringify(uniqYears)}`);
+      return uniqYears;
+    }
+  },
+  // eslint-disable-next-line max-statements
+  compare: (a, b) => {
+    const debug = createDebugLogger("@natlibfi/melinda-record-matching:match-detection:features/bib/publication-time-allow-cons-years-multi");
+    debug(`Comparing ${JSON.stringify(a)} to ${JSON.stringify(b)}`);
+    const [firstA] = a.normalYears ? a.normalYears : a;
+    const [firstB] = b.normalYears ? b.normalYears : b;
+    debug(`Comparing ${JSON.stringify(firstA)} to ${JSON.stringify(firstB)}`);
+    if (firstA === firstB) {
+      return 0.1;
+    }
+    if (!testStringOrNumber(firstA) || !testStringOrNumber(firstB)) {
+      return 0;
+    }
+    const firstANumber = parseInt(firstA, 10);
+    const firstBNumber = parseInt(firstB, 10);
+    if (!(isNaN(firstANumber) || isNaN(firstBNumber)) && (firstANumber + 1 === firstBNumber || firstANumber - 1 === firstBNumber)) {
+      return 0.1;
+    }
+    const bNormalInANormal = a.normalYears.filter((aValue) => b.normalYears.some((bValue) => aValue === bValue));
+    const aNormalInBNormal = b.normalYears.filter((bValue) => a.normalYears.some((aValue) => bValue === aValue));
+    debug(`BNorm in ANorm: ${JSON.stringify(bNormalInANormal)}`);
+    debug(`ANorm in BNorm: ${JSON.stringify(aNormalInBNormal)}`);
+    if (bNormalInANormal > 0 || aNormalInBNormal > 0) {
+      return 0;
+    }
+    const bNormalInAReprint = a.reprintYears.filter((aValue) => b.normalYears.some((bValue) => aValue === bValue));
+    const aNormalInBReprint = b.reprintYears.filter((bValue) => a.normalYears.some((aValue) => bValue === aValue));
+    debug(`BNorm in AReprint: ${JSON.stringify(bNormalInAReprint)}`);
+    debug(`ANorm in BReprint: ${JSON.stringify(aNormalInBReprint)}`);
+    if (bNormalInAReprint > 0 || aNormalInBReprint > 0) {
+      return 0;
+    }
+    return -1;
+  }
+});
+//# sourceMappingURL=publication-time-allow-cons-years-multi.js.map