@natlibfi/melinda-record-matching 5.1.6 → 5.1.7-alpha.1

package/dist/candidate-search/candidate-search-utils.js

@@ -2,10 +2,12 @@ import createDebugLogger from "debug";
 export function toQueries(identifiers, queryString) {
   const debug = createDebugLogger("@natlibfi/melinda-record-matching:toQueries");
   const debugData = debug.extend("data");
-  const quotedIdentifiers = identifiers.map((identifier) => identifier.match(/\//u) ? `"${identifier}"` : `${identifier}`);
-  const pairs = toPairs(quotedIdentifiers);
-  const queries = pairs.map(([a, b]) => b ? `${queryString}=${a} or ${queryString}=${b}` : `${queryString}=${a}`);
+  const quotedIdentifiers = identifiers.map((identifier) => identifier.match(/\//u) || identifier.match(/\^/u) ? `"${identifier}"` : `${identifier}`);
+  const caretPairs = toPairs(quotedIdentifiers.filter((identifier) => identifier.match(/\^/u)));
+  const nonCaretPairs = toPairs(quotedIdentifiers.filter((identifier) => !identifier.match(/\^/u)));
+  const pairs = nonCaretPairs.concat(caretPairs);
   debugData(`Pairs (${pairs.length}): ${JSON.stringify(pairs)}`);
+  const queries = pairs.map(([a, b]) => b ? `${queryString}=${a} or ${queryString}=${b}` : `${queryString}=${a}`);
   debugData(`Queries (${queries.length}): ${JSON.stringify(queries)}`);
   return queries;
 }

package/dist/candidate-search/candidate-search-utils.js.map

@@ -1,7 +1,7 @@
 {
   "version": 3,
   "sources": ["../../src/candidate-search/candidate-search-utils.js"],
-  "sourcesContent": ["import createDebugLogger from 'debug';\n\nexport function toQueries(identifiers, queryString) {\n\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:toQueries');\n  const debugData = debug.extend('data');\n\n  // We quote the identifier, if it contains a slash! (Slash in non-quoted SRU-search breaks search.)\n  const quotedIdentifiers = identifiers.map(identifier => identifier.match(/\\//u) ? `\"${identifier}\"` : `${identifier}`);\n\n  // Aleph supports only two queries with or -operator (This is not actually true)\n  const pairs = toPairs(quotedIdentifiers);\n  const queries = pairs.map(([a, b]) => b ? `${queryString}=${a} or ${queryString}=${b}` : `${queryString}=${a}`);\n\n  debugData(`Pairs (${pairs.length}): ${JSON.stringify(pairs)}`);\n  debugData(`Queries (${queries.length}): ${JSON.stringify(queries)}`);\n\n  return queries;\n}\n\nfunction toPairs(array) {\n  if (array.length === 0) {\n    return [];\n  }\n  return [array.slice(0, 2)].concat(toPairs(array.slice(2), 2));\n}\n"],
-  "mappings": "AAAA,OAAO,uBAAuB;AAEvB,gBAAS,UAAU,aAAa,aAAa;AAElD,QAAM,QAAQ,kBAAkB,6CAA6C;AAC7E,QAAM,YAAY,MAAM,OAAO,MAAM;AAGrC,QAAM,oBAAoB,YAAY,IAAI,gBAAc,WAAW,MAAM,KAAK,IAAI,IAAI,UAAU,MAAM,GAAG,UAAU,EAAE;AAGrH,QAAM,QAAQ,QAAQ,iBAAiB;AACvC,QAAM,UAAU,MAAM,IAAI,CAAC,CAAC,GAAG,CAAC,MAAM,IAAI,GAAG,WAAW,IAAI,CAAC,OAAO,WAAW,IAAI,CAAC,KAAK,GAAG,WAAW,IAAI,CAAC,EAAE;AAE9G,YAAU,UAAU,MAAM,MAAM,MAAM,KAAK,UAAU,KAAK,CAAC,EAAE;AAC7D,YAAU,YAAY,QAAQ,MAAM,MAAM,KAAK,UAAU,OAAO,CAAC,EAAE;AAEnE,SAAO;AACT;AAEA,SAAS,QAAQ,OAAO;AACtB,MAAI,MAAM,WAAW,GAAG;AACtB,WAAO,CAAC;AAAA,EACV;AACA,SAAO,CAAC,MAAM,MAAM,GAAG,CAAC,CAAC,EAAE,OAAO,QAAQ,MAAM,MAAM,CAAC,GAAG,CAAC,CAAC;AAC9D;",
+  "sourcesContent": ["import createDebugLogger from 'debug';\n\nexport function toQueries(identifiers, queryString) {\n\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:toQueries');\n  const debugData = debug.extend('data');\n\n  // We quote the identifier, if it contains a slash! (Slash in non-quoted SRU-search breaks search.)\n  // We also quote the identifier, if it starts with caret (f028 searches fail without caret and quotes...)\n  const quotedIdentifiers = identifiers.map(identifier => identifier.match(/\\//u) || identifier.match(/\\^/u) ? `\"${identifier}\"` : `${identifier}`);\n\n  // We can't pair queries with starting caret and without (ie. left anchored queries with non-left anchored queries)\n  const caretPairs = toPairs(quotedIdentifiers.filter(identifier => identifier.match(/\\^/u)));\n  const nonCaretPairs = toPairs(quotedIdentifiers.filter(identifier => !identifier.match(/\\^/u)));\n\n  const pairs = nonCaretPairs.concat(caretPairs);\n  debugData(`Pairs (${pairs.length}): ${JSON.stringify(pairs)}`);\n\n  // Aleph supports only two queries with or -operator (This is not actually true)\n  const queries = pairs.map(([a, b]) => b ? `${queryString}=${a} or ${queryString}=${b}` : `${queryString}=${a}`);\n  debugData(`Queries (${queries.length}): ${JSON.stringify(queries)}`);\n\n  return queries;\n}\n\nfunction toPairs(array) {\n  if (array.length === 0) {\n    return [];\n  }\n  return [array.slice(0, 2)].concat(toPairs(array.slice(2), 2));\n}\n"],
+  "mappings": "AAAA,OAAO,uBAAuB;AAEvB,gBAAS,UAAU,aAAa,aAAa;AAElD,QAAM,QAAQ,kBAAkB,6CAA6C;AAC7E,QAAM,YAAY,MAAM,OAAO,MAAM;AAIrC,QAAM,oBAAoB,YAAY,IAAI,gBAAc,WAAW,MAAM,KAAK,KAAK,WAAW,MAAM,KAAK,IAAI,IAAI,UAAU,MAAM,GAAG,UAAU,EAAE;AAGhJ,QAAM,aAAa,QAAQ,kBAAkB,OAAO,gBAAc,WAAW,MAAM,KAAK,CAAC,CAAC;AAC1F,QAAM,gBAAgB,QAAQ,kBAAkB,OAAO,gBAAc,CAAC,WAAW,MAAM,KAAK,CAAC,CAAC;AAE9F,QAAM,QAAQ,cAAc,OAAO,UAAU;AAC7C,YAAU,UAAU,MAAM,MAAM,MAAM,KAAK,UAAU,KAAK,CAAC,EAAE;AAG7D,QAAM,UAAU,MAAM,IAAI,CAAC,CAAC,GAAG,CAAC,MAAM,IAAI,GAAG,WAAW,IAAI,CAAC,OAAO,WAAW,IAAI,CAAC,KAAK,GAAG,WAAW,IAAI,CAAC,EAAE;AAC9G,YAAU,YAAY,QAAQ,MAAM,MAAM,KAAK,UAAU,OAAO,CAAC,EAAE;AAEnE,SAAO;AACT;AAEA,SAAS,QAAQ,OAAO;AACtB,MAAI,MAAM,WAAW,GAAG;AACtB,WAAO,CAAC;AAAA,EACV;AACA,SAAO,CAAC,MAAM,MAAM,GAAG,CAAC,CAAC,EAAE,OAAO,QAAQ,MAAM,MAAM,CAAC,GAAG,CAAC,CAAC;AAC9D;",
   "names": []
 }

package/dist/candidate-search/query-list/bib.js

@@ -287,9 +287,9 @@ export function bibStandardIdentifiers(record) {
       if (a) {
         const b = subfields.find((sf) => sf.code === "b");
         if (b) {
-          return [a.value, `${b.value} ${a.value}`];
+          return [`^${a.value}`, `^${b.value} ${a.value}`];
         }
-        return [a.value];
+        return [`^${a.value}`];
       }
     }
     return subfields.filter((sub) => ["a", "z"].includes(sub.code) && testStringOrNumber(sub.value) && otherIdReqExp.test(String(sub.value))).map(({ value }) => String(value));

package/dist/candidate-search/query-list/bib.js.map

@@ -1,7 +1,7 @@
 {
   "version": 3,
   "sources": ["../../../src/candidate-search/query-list/bib.js"],
-  "sourcesContent": ["import createDebugLogger from 'debug';\nimport {toQueries} from '../candidate-search-utils.js';\nimport {getMelindaIdsF035, validateSidFieldSubfieldCounts, getSubfieldValues, testStringOrNumber} from '../../matching-utils.js';\nimport {extractHostMelindaIdsFromField, extractPublicationYearFrom773, getHostMelindaFields} from './component.js';\nimport {fieldToString} from '@natlibfi/marc-record-validators-melinda';\nimport {getTitle} from '../../match-detection/features/bib/title.js';\n\nconst debug = createDebugLogger('@natlibfi/melinda-record-matching:candidate-search:query');\n\nconst IS_OK_ALONE_THRESHOLD = 5;\n\nexport function bibSourceIds(record) {\n\n  /* Melinda's SRU-index melinda.sourceid includes source IDs from SID fields in Melinda records\n     SID-fields in Melinda have sf $c with local id and sf $b with a code for the local db:\n\n     SID__ $c 123457 $b helka\n     SID__ $c (ANDL100020)1077305 $b sata\n     SID__ $c VER999999 $ FI-KV\n     SID__ $c /10024/508126 $ REPO_THESEUS\n\n    In melinda.sourceid -index case is kept, sourceprefixes in brackets and hyphens are normalized away:\n    Note: slashes are not normalized away, but a SRU-search-string including slashes needs to be quoted\n\n    1234567helka\n    1077305sata\n    VER999999FIKV\n    /10024/508126REPO_THESEUS\n\n    Note: All Melinda records that have a matching records in a local db do NOT have SID for that local records,\n          existence of a SID field depends on how the record has been added to Melinda and how it has been handled\n          afterwards. SIDs are also not reliably maintained. A record might or might not have a SID for a local db\n          after the matching record is removed from the local db.\n\n   */\n\n\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:candidate-search:query:source-ids');\n  const debugData = debug.extend('data');\n  //const debugInfo = debug.extend('info');\n\n  debug(`Creating queries for sourceid's`);\n\n  const fSids = record.get('SID');\n  debugData(`SID-fields (${fSids.length}): ${JSON.stringify(fSids)}`);\n\n  return fSids.length > 0 ? toSidQueries(fSids) : [];\n\n  function toSidQueries(fSids) {\n    debug(`Creating actual queries for sourceid's`);\n\n    const sidStrings = getSidStrings(fSids);\n\n    if (sidStrings.length < 1) {\n      debug(`No identifiers found, no queries created.`);\n      return [];\n    }\n\n    const sidQueries = toQueries(sidStrings, 'melinda.sourceid');\n\n    return sidQueries;\n\n    function getSidStrings(fSids) {\n      debug(`Getting Sid strings from SID fields`);\n\n      // Map SID fields to valid sidStrings, filter out empty strings\n      const sidStrings = fSids.map(toSidString).filter(nonEmptySid => nonEmptySid);\n      return sidStrings;\n\n      function toSidString(field) {\n        debug(`Getting string from a field`);\n\n        return validateSidFieldSubfieldCounts(field) ? createSidString(field) : '';\n\n        function createSidString(field) {\n          debug(`Creating string from a field`);\n          const [sfC] = getSubfieldValues(field, 'c');\n          const [sfB] = getSubfieldValues(field, 'b');\n\n          const cleanedSfC = removeSourcePrefix(normalizeSidSubfieldValue(sfC));\n          const cleanedSfB = normalizeSidSubfieldValue(sfB);\n\n          debugData(`${JSON.stringify(sfC)} + ${JSON.stringify(sfB)}`);\n          return cleanedSfC.concat(cleanedSfB);\n        }\n\n        function removeSourcePrefix(subfieldValue) {\n          const sourcePrefixRegex = (/^(?<sourcePrefix>\\([A-Za-z0-9-]+\\))(?<id>.+)$/u);\n          const normalizedValue = testStringOrNumber(subfieldValue) ? String(subfieldValue).replace(sourcePrefixRegex, '$<id>') : '';\n          debugData(`Normalized ${subfieldValue} to ${normalizedValue}`);\n          return normalizedValue;\n        }\n\n        function normalizeSidSubfieldValue(subfieldValue) {\n          debugData(`Normalizing ${subfieldValue}`);\n          const normalizeAwayRegex = (/[- ]/u);\n          return testStringOrNumber(subfieldValue) ? String(subfieldValue).replace(normalizeAwayRegex, '') : '';\n        }\n\n      }\n    }\n  }\n}\n\nexport function bibMelindaIds(record) {\n  // Melinda's SRU-index melinda.melindaid includes f001 controlnumbers and old Melinda-IDs from f035z's for all non-deleted Melinda-records\n\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:candidate-search:query:bibMelindaIds');\n  const debugData = debug.extend('data');\n  debug(`Creating queries for MelindaIds`);\n\n  // Note: Melinda-ID's for search queries are created just from records f035a's and f035z's\n  // Both (FI-MELINDA)- and FCC-prefixed forms are found\n  // f001 controlnumber is not currently included, even if record's f003 is FI-MELINDA\n  const melindaIds = getMelindaIdsF035(record);\n\n  debugData(`Unique identifiers (${melindaIds.length}): ${JSON.stringify(melindaIds)}`);\n\n  if (melindaIds.length < 1) {\n    debug(`No identifiers found, no queries created.`);\n    return [];\n  }\n\n  return toQueries(melindaIds, 'melinda.melindaid');\n}\n\n\n// bibHostComponents returns host id from the first subfield $w of first field f773, see test-fixtures 04 and 05\n// bibHostComponents should search all 773 $ws for possible host id, but what should it do in case of multiple host ids?\nexport function bibHostComponents(record) {\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:candidate-search:query:bibHostComponents');\n  const debugData = debug.extend('data');\n  debug(`Creating queries for hostIds`);\n  const f773s = getHostMelindaFields(record);\n  if (f773s.length !== 1) { // This needs some thinking...\n    return [];\n  }\n\n  const [id] = extractHostMelindaIdsFromField(f773s[0]);\n  debug(`Found id: ${JSON.stringify(id)}`);\n\n  // NB! record.isCR() does not work if LDR/07=a, so we get year from 773$g!\n  const year = extractPublicationYearFrom773(f773s[0]);\n  debug(`${fieldToString(f773s[0])} => ${year ? year : 'N/A'}`);\n  if (year) {\n    return [`dc.date=${year} AND melinda.partsofhost=${id}`];\n  }\n\n  return [`melinda.partsofhost=${id}`];\n\n}\n\n\n\n\n// SRU search dc.title with a search phrase starting with ^ maps currently in Melinda to (probably) to *headings* index TIT\n// - Aleph cannot currently handle headings searches starting with a boolean - in these cases use word search\n\nexport function bibTitle(record) {\n  // We get author/publisher only when formatted title is shorter than 5 chars\n  return bibTitleAuthorPublisher({record, onlyTitleLength: 5});\n}\n\nexport function bibTitleAuthor(record) {\n  debug('bibTitleAuthor');\n  // We use onlyTitleLength that is longer than our formatted length to\n  // get an author or an publisher always\n  return bibTitleAuthorPublisher({record, onlyTitleLength: 100});\n}\n\nexport function bibTitleAuthorYear(record) {\n  debug('bibTitleAuthorYearAlternates');\n  // We use onlyTitleLength that is longer than our formatted length to\n  // get an author or an publisher always\n\n  return bibTitleAuthorPublisher({record, onlyTitleLength: 100, addYear: true});\n}\n\nexport function bibTitleAuthorYearAlternates(record) {\n  debug('bibTitleAuthorYearAlternates');\n  // We use onlyTitleLength that is longer than our formatted length to\n  // get an author or an publisher always\n  const origQueryList = bibTitleAuthorPublisher({record, onlyTitleLength: 100, addYear: true, alternates: true, alternateQueries: []});\n  debug(`${JSON.stringify(origQueryList)}`);\n  return {queryList: Array.from(origQueryList).reverse(), queryListType: 'alternates'};\n}\n\nfunction getTitleForQuery(record) {\n  const title = getTitle(record, ['a']);\n  if (title) {\n    const nWords = title.split(' ');\n    // If lone $a is deemed too short, fetch $b as well:\n    // (NV: I've seen pairs with 245$a-only vs 245$a$b, so I'd like to use $a only if it is long enough)\n\n    if (nWords < 3 || title.length < 12) {\n      const [f245] = record.get('245');\n      // If punctuation is ' =' I think that f245$a is good enough despite shortness. Trying to balance between two bad situations...\n      // \"Suo (= short title) siell\u00E4, vetel\u00E4 (= missing $b name in another language) t\u00E4\u00E4ll\u00E4...\"\n      if (f245 && f245.subfields.find(sf => sf.code === 'a' && sf.value.match(/ =$/u)) && title.length >= IS_OK_ALONE_THRESHOLD) {\n        return title;\n      }\n      return getTitle(record, ['a', 'b']); // Try to get a longer title\n    }\n  }\n  return title;\n}\n\nfunction dcTitle(record, onlyTitleLength, alternates = false) {\n  const title = getTitleForQuery(record);\n  if (!testStringOrNumber(title)) {\n    return [];\n  }\n\n  const formatted = getFormattedTitle(title);\n\n  // use word search for titles starting with a boolean\n  const useWordSearch = checkUseWordSearch(formatted);\n  // Prevent too many matches / SRU crashing by having a minimum length\n  // Note that currently this fails matching if there are no matches from previous matchers\n  if (formatted.length >= onlyTitleLength && !alternates) {\n    return [`dc.title=\"${useWordSearch ? '' : '^'}${formatted}*\"`, formatted, true];\n  }\n\n  const queryIsOkAlone = !useWordSearch && formatted.length >= IS_OK_ALONE_THRESHOLD;\n\n  // use word search without ending * also in combination searches to avoid SRU-server crashes [MRA-189]\n  return [`dc.title=\"${useWordSearch || !queryIsOkAlone ? '' : '^'}${formatted}${queryIsOkAlone ? '*' : ''}\"`, formatted, queryIsOkAlone];\n\n  function getFormattedTitle(title) {\n    const formatted = String(title)\n      .replace(/[\\-+ !\"(){}\\[\\]<>;:.?/@*%=^_`~]/gu, ' ')\n      .replace(/[^\\w\\s\\p{Alphabetic}]/gu, '') // Apparently matches to/works with non-aplhabetic scripts such as Chinese as well\n      .replace(/  +/gu, ' ') // Clean up concurrent spaces from eg. subfield changes\n      .trim()\n      .replace(/^(.{30}\\S*) .*$/, \"$1\")\n      .trim();\n\n    return formatted;\n  }\n}\n\nexport function bibTitleAuthorPublisher({record, onlyTitleLength, addYear = false, alternates = false, alternateQueries = []}) {\n  debug(`bibTitleAuthorPublisher, onlyTitleLength: ${onlyTitleLength}, addYear: ${addYear}, alternates: ${alternates}`);\n  const [query, formatted, queryIsOkAlone] = dcTitle(record, onlyTitleLength, alternates);\n  if (query === undefined) {\n    return [];\n  }\n\n  debug(`query: ${query}`);\n\n  // Prevent too many matches / SRU crashing by having a minimum length\n  // Note that currently this fails matching if there are no matches from previous matchers\n  if (formatted.length >= onlyTitleLength && !alternates) {\n    return [query];\n  }\n\n  const newAlternateQueries = alternates ? [...alternateQueries, query] : alternateQueries;\n\n  return addAuthorsToSearch({query, queryIsOkAlone, addYear, alternates, alternateQueries: newAlternateQueries});\n\n  function addAuthorsToSearch({query, queryIsOkAlone = false, addYear = false, alternates = false, alternateQueries = []}) {\n    debug('addAuthorsToSearch');\n    const [authorQuery] = bibAuthors(record);\n    if (authorQuery !== undefined) {\n      if (addYear) {\n        const newAlternateQueries = alternates ? [...alternateQueries, `${authorQuery} AND ${query}`] : alternateQueries;\n        return addYearToSearch({query: `${authorQuery} AND ${query}`, queryIsOkAlone: true, alternates, alternateQueries: newAlternateQueries});\n      }\n      return alternates ? alternateQueries : [`${authorQuery} AND ${query}`];\n    }\n    return addPublisherToSearch({query, queryIsOkAlone, addYear, alternates, alternateQueries});\n    //return [];\n  }\n\n  function addPublisherToSearch({query, queryIsOkAlone = false, addYear = false, alternates = false, alternateQueries = []}) {\n    const [publisherQuery] = bibPublishers(record);\n    if (publisherQuery !== undefined) {\n      if (addYear) {\n        const newAlternateQueries = alternates ? [...alternateQueries, `${publisherQuery} AND ${query}`] : alternateQueries;\n        return addYearToSearch({query: `${publisherQuery} AND ${query}`, queryIsOkAlone: true, alternates, alternateQueries: newAlternateQueries});\n      }\n      return alternates ? alternateQueries : [`${publisherQuery} AND ${query}`];\n    }\n    if (queryIsOkAlone && !addYear) {\n      return alternates ? alternateQueries : [`${query}`];\n    }\n    return addYearToSearch({query, queryIsOkAlone, alternates, alternateQueries});\n  }\n\n  function addYearToSearch({query, queryIsOkAlone = false, alternates = false, alternateQueries = []}) {\n    const [yearQuery] = bibYear(record);\n    if (yearQuery !== undefined) {\n      const yearAndOtherQueries = `${yearQuery} AND ${query}`;\n      return alternates ? [...alternateQueries, yearAndOtherQueries] : [yearAndOtherQueries];\n    }\n    if (queryIsOkAlone) {\n      return alternates ? alternateQueries : [`${query}`];\n    }\n    return [];\n  }\n\n}\n\nexport function bibAuthors(record) {\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:candidate-search:query:bibAuthors');\n  const debugData = debug.extend('data');\n  debug(`Creating query for the first author`);\n  //debugData(record);\n\n  const author = getAuthor(record);\n\n  if (testStringOrNumber(author)) {\n    const formatted = String(author)\n      .replace(/[^\\w\\s\\p{Alphabetic}]/gu, '')\n      // Clean up concurrent spaces from fe. subfield changes\n      .replace(/ +/gu, ' ')\n      .trim()\n      .slice(0, 30)\n      .trim();\n\n    // use word search for authors starting with a boolean\n    const useWordSearch = checkUseWordSearch(formatted);\n    // Prevent too many matches by having a minimum length\n    debugData(`Author string: ${formatted}`);\n    if (formatted.length >= 5) {\n      return [`dc.author=\"${useWordSearch ? '' : '^'}${formatted}*\"`];\n    }\n    return [];\n  }\n\n  return [];\n\n  function getAuthor(record) {\n    //debugData(record);\n    const [field] = record.get(/^(?:100|110|111|700|710|711)$/u);\n    //debugData(field);\n\n    if (field) {\n      const authorString = field.subfields\n        .filter(({code}) => ['a'].includes(code)) // We might use different subfield code sets for X00, X10 and X11?\n        .map(({value}) => testStringOrNumber(value) ? String(value) : '')\n        .filter(value => value)\n        // In Melinda's index subfield separators are indexed as ' '\n        .join(' ');\n      return authorString;\n    }\n    return false;\n  }\n}\n\nexport function bibPublishers(record) {\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:candidate-search:query:bibPublishers');\n  const debugData = debug.extend('data');\n  debug(`Creating query for the first publisher`);\n  //debugData(record);\n\n  const publisher = getPublisher(record);\n  if (testStringOrNumber(publisher)) {\n    const formatted = String(publisher)\n      .replace(/[^\\w\\s\\p{Alphabetic}]/gu, '')\n      // Clean up concurrent spaces from fe. subfield changes\n      .replace(/ +/gu, ' ')\n      .trim()\n      .slice(0, 30)\n      .trim();\n\n    debugData(`Publisher string: '${formatted}'`);\n    if (formatted.length === 0) {\n      return [];\n    }\n    // use non-wildcard word search from dc.publisher\n    return [`dc.publisher=\"${formatted}\"`];\n  }\n\n  return [];\n\n  function getPublisher(record) {\n    //debugData(record);\n    const [field] = record.get(/^26[04]$/u).filter(f => f.subfields.some(sf => sf.code === 'b')); // Filter removes copyright-only fields\n    //debugData(field);\n\n    if (field) {\n      const publisherString = field.subfields\n        .filter(({code}) => ['b'].includes(code))\n        .map(({value}) => testStringOrNumber(value) ? String(value) : '')\n        .filter(value => value)\n        // In Melinda's index subfield separators are indexed as ' '\n        .join(' ')\n        .trim();\n      return publisherString;\n    }\n    return false;\n  }\n}\n\nexport function bibYear(record) {\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:candidate-search:query:bibYear');\n  const debugData = debug.extend('data');\n  debug(`Creating query for the publishing year`);\n\n  const year = getYear(record);\n  if (year) {\n    return [`dc.date=\"${year}\"`];\n  }\n  return [];\n\n  function getYear(record) {\n    const [f008] = record.get(/^008$/u);\n    if (!f008 || !f008.value || f008.value.length < 11) {\n      debug('f008 missing/crappy');\n      return false;\n    }\n\n    debugData(`f008: ${JSON.stringify(f008)}`);\n    const {value} = f008;\n    if (value === '||||' || value === '    ') { // Meaningless values\n      return false;\n    }\n    return value.slice(7, 11);\n  }\n}\n\nexport function checkUseWordSearch(formatted) {\n  const lowercased = formatted.toLowerCase();\n  // Note: add a space to startWords to catch just actual boolean words\n  const booleanStartWords = ['and ', 'or ', 'nor ', 'not '];\n  return booleanStartWords.some(word => lowercased.startsWith(word));\n}\n\nexport function bibStandardIdentifiers(record) {\n\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:candidate-search:query:bibStandardIdentifiers');\n  const debugData = debug.extend('data');\n  debug(`Creating queries for standard identifiers`);\n\n  // DEVELOP: should we query also f015 and f028?\n\n  // const fields = record.get(/^(?<def>020|022|024)$/u);\n  const fields = record.get(/^(?<def>015|020|022|024|028)$/u);\n  const identifiers = [].concat(...fields.map(toIdentifiers));\n  const uniqueIdentifiers = [...new Set(identifiers)];\n\n  debugData(`Standard identifier fields: ${JSON.stringify(fields)}`);\n  debugData(`Identifiers (${identifiers.length}): ${JSON.stringify(identifiers)}`);\n  debugData(`Unique identifiers (${uniqueIdentifiers.length}): ${JSON.stringify(uniqueIdentifiers)}`);\n\n  if (uniqueIdentifiers.length < 1) {\n    debug(`No identifiers found, no queries created.`);\n    return [];\n  }\n\n  return toQueries(uniqueIdentifiers, 'dc.identifier');\n\n  function toIdentifiers({tag, subfields}) {\n    const issnIsbnReqExp = (/^[A-Za-z0-9-]+$/u);\n    const otherIdReqExp = (/^[A-Za-z0-9-:]+$/u);\n\n    if (tag === '015') { // TODO: test (does this use the right index etc.)\n      return subfields\n        .filter(sf => sf.code === 'a' && sf.value.match(/^[A-Z0-9\\-]+$/ui))\n        .map(sf => sf.value)\n    }\n\n    if (tag === '020') {\n      return subfields\n        .filter(sub => ['a', 'z'].includes(sub.code) && testStringOrNumber(sub.value) && issnIsbnReqExp.test(String(sub.value)))\n        .map(({value}) => String(value));\n    }\n\n    if (tag === '022') {\n      return subfields\n        .filter(sub => ['a', 'z', 'y'].includes(sub.code) && testStringOrNumber(sub.value) && issnIsbnReqExp.test(String(sub.value)))\n        .map(({value}) => String(value));\n    }\n\n    if (tag === '028') { // TODO: test\n      const a = subfields.find(sf => sf.code === 'a');\n      if (a) {\n        const b = subfields.find(sf => sf.code === 'b');\n        // TODO: normalize?\n        if (b) {\n          return [a.value, `${b.value} ${a.value}`];\n        }\n        return [a.value];\n      }\n    }\n\n    // Default seems to be 024:\n    return subfields\n      .filter(sub => ['a', 'z'].includes(sub.code) && testStringOrNumber(sub.value) && otherIdReqExp.test(String(sub.value)))\n      .map(({value}) => String(value));\n  }\n}\n"],
-  "mappings": "AAAA,OAAO,uBAAuB;AAC9B,SAAQ,iBAAgB;AACxB,SAAQ,mBAAmB,gCAAgC,mBAAmB,0BAAyB;AACvG,SAAQ,gCAAgC,+BAA+B,4BAA2B;AAClG,SAAQ,qBAAoB;AAC5B,SAAQ,gBAAe;AAEvB,MAAM,QAAQ,kBAAkB,0DAA0D;AAE1F,MAAM,wBAAwB;AAEvB,gBAAS,aAAa,QAAQ;AA0BnC,QAAMA,SAAQ,kBAAkB,qEAAqE;AACrG,QAAM,YAAYA,OAAM,OAAO,MAAM;AAGrC,EAAAA,OAAM,iCAAiC;AAEvC,QAAM,QAAQ,OAAO,IAAI,KAAK;AAC9B,YAAU,eAAe,MAAM,MAAM,MAAM,KAAK,UAAU,KAAK,CAAC,EAAE;AAElE,SAAO,MAAM,SAAS,IAAI,aAAa,KAAK,IAAI,CAAC;AAEjD,WAAS,aAAaC,QAAO;AAC3B,IAAAD,OAAM,wCAAwC;AAE9C,UAAM,aAAa,cAAcC,MAAK;AAEtC,QAAI,WAAW,SAAS,GAAG;AACzB,MAAAD,OAAM,2CAA2C;AACjD,aAAO,CAAC;AAAA,IACV;AAEA,UAAM,aAAa,UAAU,YAAY,kBAAkB;AAE3D,WAAO;AAEP,aAAS,cAAcC,QAAO;AAC5B,MAAAD,OAAM,qCAAqC;AAG3C,YAAME,cAAaD,OAAM,IAAI,WAAW,EAAE,OAAO,iBAAe,WAAW;AAC3E,aAAOC;AAEP,eAAS,YAAY,OAAO;AAC1B,QAAAF,OAAM,6BAA6B;AAEnC,eAAO,+BAA+B,KAAK,IAAI,gBAAgB,KAAK,IAAI;AAExE,iBAAS,gBAAgBG,QAAO;AAC9B,UAAAH,OAAM,8BAA8B;AACpC,gBAAM,CAAC,GAAG,IAAI,kBAAkBG,QAAO,GAAG;AAC1C,gBAAM,CAAC,GAAG,IAAI,kBAAkBA,QAAO,GAAG;AAE1C,gBAAM,aAAa,mBAAmB,0BAA0B,GAAG,CAAC;AACpE,gBAAM,aAAa,0BAA0B,GAAG;AAEhD,oBAAU,GAAG,KAAK,UAAU,GAAG,CAAC,MAAM,KAAK,UAAU,GAAG,CAAC,EAAE;AAC3D,iBAAO,WAAW,OAAO,UAAU;AAAA,QACrC;AAEA,iBAAS,mBAAmB,eAAe;AACzC,gBAAM,oBAAqB;AAC3B,gBAAM,kBAAkB,mBAAmB,aAAa,IAAI,OAAO,aAAa,EAAE,QAAQ,mBAAmB,OAAO,IAAI;AACxH,oBAAU,cAAc,aAAa,OAAO,eAAe,EAAE;AAC7D,iBAAO;AAAA,QACT;AAEA,iBAAS,0BAA0B,eAAe;AAChD,oBAAU,eAAe,aAAa,EAAE;AACxC,gBAAM,qBAAsB;AAC5B,iBAAO,mBAAmB,aAAa,IAAI,OAAO,aAAa,EAAE,QAAQ,oBAAoB,EAAE,IAAI;AAAA,QACrG;AAAA,MAEF;AAAA,IACF;AAAA,EACF;AACF;AAEO,gBAAS,cAAc,QAAQ;AAGpC,QAAMH,SAAQ,kBAAkB,wEAAwE;AACxG,QAAM,YAAYA,OAAM,OAAO,MAAM;AACrC,EAAAA,OAAM,iCAAiC;AAKvC,QAAM,aAAa,kBAAkB,MAAM;AAE3C,YAAU,uBAAuB,WAAW,MAAM,MAAM,KAAK,UAAU,UAAU,CAAC,EAAE;AAEpF,MAAI,WAAW,SAAS,GAAG;AACzB,IAAAA,OAAM,2CAA2C;AACjD,WAAO,CAAC;AAAA,EACV;AAEA,SAAO,UAAU,YAAY,mBAAmB;AAClD;AAKO,gBAAS,kBAAkB,QAAQ;AACxC,QAAMA,SAAQ,kBAAkB,4EAA4E;AAC5G,QAAM,YAAYA,OAAM,OAAO,MAAM;AACrC,EAAAA,OAAM,8BAA8B;AACpC,QAAM,QAAQ,qBAAqB,MAAM;AACzC,MAAI,MAAM,WAAW,GAAG;AACtB,WAAO,CAAC;AAAA,EACV;AAEA,QAAM,CAAC,EAAE,IAAI,+BAA+B,MAAM,CAAC,CAAC;AACpD,EAAAA,OAAM,aAAa,KAAK,UAAU,EAAE,CAAC,EAAE;AAGvC,QAAM,OAAO,8BAA8B,MAAM,CAAC,CAAC;AACnD,EAAAA,OAAM,GAAG,cAAc,MAAM,CAAC,CAAC,CAAC,OAAO,OAAO,OAAO,KAAK,EAAE;AAC5D,MAAI,MAAM;AACR,WAAO,CAAC,WAAW,IAAI,4BAA4B,EAAE,EAAE;AAAA,EACzD;AAEA,SAAO,CAAC,uBAAuB,EAAE,EAAE;AAErC;AAQO,gBAAS,SAAS,QAAQ;AAE/B,SAAO,wBAAwB,EAAC,QAAQ,iBAAiB,EAAC,CAAC;AAC7D;AAEO,gBAAS,eAAe,QAAQ;AACrC,QAAM,gBAAgB;AAGtB,SAAO,wBAAwB,EAAC,QAAQ,iBAAiB,IAAG,CAAC;AAC/D;AAEO,gBAAS,mBAAmB,QAAQ;AACzC,QAAM,8BAA8B;AAIpC,SAAO,wBAAwB,EAAC,QAAQ,iBAAiB,KAAK,SAAS,KAAI,CAAC;AAC9E;AAEO,gBAAS,6BAA6B,QAAQ;AACnD,QAAM,8BAA8B;AAGpC,QAAM,gBAAgB,wBAAwB,EAAC,QAAQ,iBAAiB,KAAK,SAAS,MAAM,YAAY,MAAM,kBAAkB,CAAC,EAAC,CAAC;AACnI,QAAM,GAAG,KAAK,UAAU,aAAa,CAAC,EAAE;AACxC,SAAO,EAAC,WAAW,MAAM,KAAK,aAAa,EAAE,QAAQ,GAAG,eAAe,aAAY;AACrF;AAEA,SAAS,iBAAiB,QAAQ;AAChC,QAAM,QAAQ,SAAS,QAAQ,CAAC,GAAG,CAAC;AACpC,MAAI,OAAO;AACT,UAAM,SAAS,MAAM,MAAM,GAAG;AAI9B,QAAI,SAAS,KAAK,MAAM,SAAS,IAAI;AACnC,YAAM,CAAC,IAAI,IAAI,OAAO,IAAI,KAAK;AAG/B,UAAI,QAAQ,KAAK,UAAU,KAAK,QAAM,GAAG,SAAS,OAAO,GAAG,MAAM,MAAM,MAAM,CAAC,KAAK,MAAM,UAAU,uBAAuB;AACzH,eAAO;AAAA,MACT;AACA,aAAO,SAAS,QAAQ,CAAC,KAAK,GAAG,CAAC;AAAA,IACpC;AAAA,EACF;AACA,SAAO;AACT;AAEA,SAAS,QAAQ,QAAQ,iBAAiB,aAAa,OAAO;AAC5D,QAAM,QAAQ,iBAAiB,MAAM;AACrC,MAAI,CAAC,mBAAmB,KAAK,GAAG;AAC9B,WAAO,CAAC;AAAA,EACV;AAEA,QAAM,YAAY,kBAAkB,KAAK;AAGzC,QAAM,gBAAgB,mBAAmB,SAAS;AAGlD,MAAI,UAAU,UAAU,mBAAmB,CAAC,YAAY;AACtD,WAAO,CAAC,aAAa,gBAAgB,KAAK,GAAG,GAAG,SAAS,MAAM,WAAW,IAAI;AAAA,EAChF;AAEA,QAAM,iBAAiB,CAAC,iBAAiB,UAAU,UAAU;AAG7D,SAAO,CAAC,aAAa,iBAAiB,CAAC,iBAAiB,KAAK,GAAG,GAAG,SAAS,GAAG,iBAAiB,MAAM,EAAE,KAAK,WAAW,cAAc;AAEtI,WAAS,kBAAkBI,QAAO;AAChC,UAAMC,aAAY,OAAOD,MAAK,EAC3B,QAAQ,qCAAqC,GAAG,EAChD,QAAQ,2BAA2B,EAAE,EACrC,QAAQ,SAAS,GAAG,EACpB,KAAK,EACL,QAAQ,mBAAmB,IAAI,EAC/B,KAAK;AAER,WAAOC;AAAA,EACT;AACF;AAEO,gBAAS,wBAAwB,EAAC,QAAQ,iBAAiB,UAAU,OAAO,aAAa,OAAO,mBAAmB,CAAC,EAAC,GAAG;AAC7H,QAAM,6CAA6C,eAAe,cAAc,OAAO,iBAAiB,UAAU,EAAE;AACpH,QAAM,CAAC,OAAO,WAAW,cAAc,IAAI,QAAQ,QAAQ,iBAAiB,UAAU;AACtF,MAAI,UAAU,QAAW;AACvB,WAAO,CAAC;AAAA,EACV;AAEA,QAAM,UAAU,KAAK,EAAE;AAIvB,MAAI,UAAU,UAAU,mBAAmB,CAAC,YAAY;AACtD,WAAO,CAAC,KAAK;AAAA,EACf;AAEA,QAAM,sBAAsB,aAAa,CAAC,GAAG,kBAAkB,KAAK,IAAI;AAExE,SAAO,mBAAmB,EAAC,OAAO,gBAAgB,SAAS,YAAY,kBAAkB,oBAAmB,CAAC;AAE7G,WAAS,mBAAmB,EAAC,OAAAC,QAAO,gBAAAC,kBAAiB,OAAO,SAAAC,WAAU,OAAO,YAAAC,cAAa,OAAO,kBAAAC,oBAAmB,CAAC,EAAC,GAAG;AACvH,UAAM,oBAAoB;AAC1B,UAAM,CAAC,WAAW,IAAI,WAAW,MAAM;AACvC,QAAI,gBAAgB,QAAW;AAC7B,UAAIF,UAAS;AACX,cAAMG,uBAAsBF,cAAa,CAAC,GAAGC,mBAAkB,GAAG,WAAW,QAAQJ,MAAK,EAAE,IAAII;AAChG,eAAO,gBAAgB,EAAC,OAAO,GAAG,WAAW,QAAQJ,MAAK,IAAI,gBAAgB,MAAM,YAAAG,aAAY,kBAAkBE,qBAAmB,CAAC;AAAA,MACxI;AACA,aAAOF,cAAaC,oBAAmB,CAAC,GAAG,WAAW,QAAQJ,MAAK,EAAE;AAAA,IACvE;AACA,WAAO,qBAAqB,EAAC,OAAAA,QAAO,gBAAAC,iBAAgB,SAAAC,UAAS,YAAAC,aAAY,kBAAAC,kBAAgB,CAAC;AAAA,EAE5F;AAEA,WAAS,qBAAqB,EAAC,OAAAJ,QAAO,gBAAAC,kBAAiB,OAAO,SAAAC,WAAU,OAAO,YAAAC,cAAa,OAAO,kBAAAC,oBAAmB,CAAC,EAAC,GAAG;AACzH,UAAM,CAAC,cAAc,IAAI,cAAc,MAAM;AAC7C,QAAI,mBAAmB,QAAW;AAChC,UAAIF,UAAS;AACX,cAAMG,uBAAsBF,cAAa,CAAC,GAAGC,mBAAkB,GAAG,cAAc,QAAQJ,MAAK,EAAE,IAAII;AACnG,eAAO,gBAAgB,EAAC,OAAO,GAAG,cAAc,QAAQJ,MAAK,IAAI,gBAAgB,MAAM,YAAAG,aAAY,kBAAkBE,qBAAmB,CAAC;AAAA,MAC3I;AACA,aAAOF,cAAaC,oBAAmB,CAAC,GAAG,cAAc,QAAQJ,MAAK,EAAE;AAAA,IAC1E;AACA,QAAIC,mBAAkB,CAACC,UAAS;AAC9B,aAAOC,cAAaC,oBAAmB,CAAC,GAAGJ,MAAK,EAAE;AAAA,IACpD;AACA,WAAO,gBAAgB,EAAC,OAAAA,QAAO,gBAAAC,iBAAgB,YAAAE,aAAY,kBAAAC,kBAAgB,CAAC;AAAA,EAC9E;AAEA,WAAS,gBAAgB,EAAC,OAAAJ,QAAO,gBAAAC,kBAAiB,OAAO,YAAAE,cAAa,OAAO,kBAAAC,oBAAmB,CAAC,EAAC,GAAG;AACnG,UAAM,CAAC,SAAS,IAAI,QAAQ,MAAM;AAClC,QAAI,cAAc,QAAW;AAC3B,YAAM,sBAAsB,GAAG,SAAS,QAAQJ,MAAK;AACrD,aAAOG,cAAa,CAAC,GAAGC,mBAAkB,mBAAmB,IAAI,CAAC,mBAAmB;AAAA,IACvF;AACA,QAAIH,iBAAgB;AAClB,aAAOE,cAAaC,oBAAmB,CAAC,GAAGJ,MAAK,EAAE;AAAA,IACpD;AACA,WAAO,CAAC;AAAA,EACV;AAEF;AAEO,gBAAS,WAAW,QAAQ;AACjC,QAAMN,SAAQ,kBAAkB,qEAAqE;AACrG,QAAM,YAAYA,OAAM,OAAO,MAAM;AACrC,EAAAA,OAAM,qCAAqC;AAG3C,QAAM,SAAS,UAAU,MAAM;AAE/B,MAAI,mBAAmB,MAAM,GAAG;AAC9B,UAAM,YAAY,OAAO,MAAM,EAC5B,QAAQ,2BAA2B,EAAE,EAErC,QAAQ,QAAQ,GAAG,EACnB,KAAK,EACL,MAAM,GAAG,EAAE,EACX,KAAK;AAGR,UAAM,gBAAgB,mBAAmB,SAAS;AAElD,cAAU,kBAAkB,SAAS,EAAE;AACvC,QAAI,UAAU,UAAU,GAAG;AACzB,aAAO,CAAC,cAAc,gBAAgB,KAAK,GAAG,GAAG,SAAS,IAAI;AAAA,IAChE;AACA,WAAO,CAAC;AAAA,EACV;AAEA,SAAO,CAAC;AAER,WAAS,UAAUY,SAAQ;AAEzB,UAAM,CAAC,KAAK,IAAIA,QAAO,IAAI,gCAAgC;AAG3D,QAAI,OAAO;AACT,YAAM,eAAe,MAAM,UACxB,OAAO,CAAC,EAAC,KAAI,MAAM,CAAC,GAAG,EAAE,SAAS,IAAI,CAAC,EACvC,IAAI,CAAC,EAAC,MAAK,MAAM,mBAAmB,KAAK,IAAI,OAAO,KAAK,IAAI,EAAE,EAC/D,OAAO,WAAS,KAAK,EAErB,KAAK,GAAG;AACX,aAAO;AAAA,IACT;AACA,WAAO;AAAA,EACT;AACF;AAEO,gBAAS,cAAc,QAAQ;AACpC,QAAMZ,SAAQ,kBAAkB,wEAAwE;AACxG,QAAM,YAAYA,OAAM,OAAO,MAAM;AACrC,EAAAA,OAAM,wCAAwC;AAG9C,QAAM,YAAY,aAAa,MAAM;AACrC,MAAI,mBAAmB,SAAS,GAAG;AACjC,UAAM,YAAY,OAAO,SAAS,EAC/B,QAAQ,2BAA2B,EAAE,EAErC,QAAQ,QAAQ,GAAG,EACnB,KAAK,EACL,MAAM,GAAG,EAAE,EACX,KAAK;AAER,cAAU,sBAAsB,SAAS,GAAG;AAC5C,QAAI,UAAU,WAAW,GAAG;AAC1B,aAAO,CAAC;AAAA,IACV;AAEA,WAAO,CAAC,iBAAiB,SAAS,GAAG;AAAA,EACvC;AAEA,SAAO,CAAC;AAER,WAAS,aAAaY,SAAQ;AAE5B,UAAM,CAAC,KAAK,IAAIA,QAAO,IAAI,WAAW,EAAE,OAAO,OAAK,EAAE,UAAU,KAAK,QAAM,GAAG,SAAS,GAAG,CAAC;AAG3F,QAAI,OAAO;AACT,YAAM,kBAAkB,MAAM,UAC3B,OAAO,CAAC,EAAC,KAAI,MAAM,CAAC,GAAG,EAAE,SAAS,IAAI,CAAC,EACvC,IAAI,CAAC,EAAC,MAAK,MAAM,mBAAmB,KAAK,IAAI,OAAO,KAAK,IAAI,EAAE,EAC/D,OAAO,WAAS,KAAK,EAErB,KAAK,GAAG,EACR,KAAK;AACR,aAAO;AAAA,IACT;AACA,WAAO;AAAA,EACT;AACF;AAEO,gBAAS,QAAQ,QAAQ;AAC9B,QAAMZ,SAAQ,kBAAkB,kEAAkE;AAClG,QAAM,YAAYA,OAAM,OAAO,MAAM;AACrC,EAAAA,OAAM,wCAAwC;AAE9C,QAAM,OAAO,QAAQ,MAAM;AAC3B,MAAI,MAAM;AACR,WAAO,CAAC,YAAY,IAAI,GAAG;AAAA,EAC7B;AACA,SAAO,CAAC;AAER,WAAS,QAAQY,SAAQ;AACvB,UAAM,CAAC,IAAI,IAAIA,QAAO,IAAI,QAAQ;AAClC,QAAI,CAAC,QAAQ,CAAC,KAAK,SAAS,KAAK,MAAM,SAAS,IAAI;AAClD,MAAAZ,OAAM,qBAAqB;AAC3B,aAAO;AAAA,IACT;AAEA,cAAU,SAAS,KAAK,UAAU,IAAI,CAAC,EAAE;AACzC,UAAM,EAAC,MAAK,IAAI;AAChB,QAAI,UAAU,UAAU,UAAU,QAAQ;AACxC,aAAO;AAAA,IACT;AACA,WAAO,MAAM,MAAM,GAAG,EAAE;AAAA,EAC1B;AACF;AAEO,gBAAS,mBAAmB,WAAW;AAC5C,QAAM,aAAa,UAAU,YAAY;AAEzC,QAAM,oBAAoB,CAAC,QAAQ,OAAO,QAAQ,MAAM;AACxD,SAAO,kBAAkB,KAAK,UAAQ,WAAW,WAAW,IAAI,CAAC;AACnE;AAEO,gBAAS,uBAAuB,QAAQ;AAE7C,QAAMA,SAAQ,kBAAkB,iFAAiF;AACjH,QAAM,YAAYA,OAAM,OAAO,MAAM;AACrC,EAAAA,OAAM,2CAA2C;AAKjD,QAAM,SAAS,OAAO,IAAI,gCAAgC;AAC1D,QAAM,cAAc,CAAC,EAAE,OAAO,GAAG,OAAO,IAAI,aAAa,CAAC;AAC1D,QAAM,oBAAoB,CAAC,GAAG,IAAI,IAAI,WAAW,CAAC;AAElD,YAAU,+BAA+B,KAAK,UAAU,MAAM,CAAC,EAAE;AACjE,YAAU,gBAAgB,YAAY,MAAM,MAAM,KAAK,UAAU,WAAW,CAAC,EAAE;AAC/E,YAAU,uBAAuB,kBAAkB,MAAM,MAAM,KAAK,UAAU,iBAAiB,CAAC,EAAE;AAElG,MAAI,kBAAkB,SAAS,GAAG;AAChC,IAAAA,OAAM,2CAA2C;AACjD,WAAO,CAAC;AAAA,EACV;AAEA,SAAO,UAAU,mBAAmB,eAAe;AAEnD,WAAS,cAAc,EAAC,KAAK,UAAS,GAAG;AACvC,UAAM,iBAAkB;AACxB,UAAM,gBAAiB;AAEvB,QAAI,QAAQ,OAAO;AACjB,aAAO,UACJ,OAAO,QAAM,GAAG,SAAS,OAAO,GAAG,MAAM,MAAM,iBAAiB,CAAC,EACjE,IAAI,QAAM,GAAG,KAAK;AAAA,IACvB;AAEA,QAAI,QAAQ,OAAO;AACjB,aAAO,UACJ,OAAO,SAAO,CAAC,KAAK,GAAG,EAAE,SAAS,IAAI,IAAI,KAAK,mBAAmB,IAAI,KAAK,KAAK,eAAe,KAAK,OAAO,IAAI,KAAK,CAAC,CAAC,EACtH,IAAI,CAAC,EAAC,MAAK,MAAM,OAAO,KAAK,CAAC;AAAA,IACnC;AAEA,QAAI,QAAQ,OAAO;AACjB,aAAO,UACJ,OAAO,SAAO,CAAC,KAAK,KAAK,GAAG,EAAE,SAAS,IAAI,IAAI,KAAK,mBAAmB,IAAI,KAAK,KAAK,eAAe,KAAK,OAAO,IAAI,KAAK,CAAC,CAAC,EAC3H,IAAI,CAAC,EAAC,MAAK,MAAM,OAAO,KAAK,CAAC;AAAA,IACnC;AAEA,QAAI,QAAQ,OAAO;AACjB,YAAM,IAAI,UAAU,KAAK,QAAM,GAAG,SAAS,GAAG;AAC9C,UAAI,GAAG;AACL,cAAM,IAAI,UAAU,KAAK,QAAM,GAAG,SAAS,GAAG;AAE9C,YAAI,GAAG;AACL,iBAAO,CAAC,EAAE,OAAO,GAAG,EAAE,KAAK,IAAI,EAAE,KAAK,EAAE;AAAA,QAC1C;AACA,eAAO,CAAC,EAAE,KAAK;AAAA,MACjB;AAAA,IACF;AAGA,WAAO,UACJ,OAAO,SAAO,CAAC,KAAK,GAAG,EAAE,SAAS,IAAI,IAAI,KAAK,mBAAmB,IAAI,KAAK,KAAK,cAAc,KAAK,OAAO,IAAI,KAAK,CAAC,CAAC,EACrH,IAAI,CAAC,EAAC,MAAK,MAAM,OAAO,KAAK,CAAC;AAAA,EACnC;AACF;",
+  "sourcesContent": ["import createDebugLogger from 'debug';\nimport {toQueries} from '../candidate-search-utils.js';\nimport {getMelindaIdsF035, validateSidFieldSubfieldCounts, getSubfieldValues, testStringOrNumber} from '../../matching-utils.js';\nimport {extractHostMelindaIdsFromField, extractPublicationYearFrom773, getHostMelindaFields} from './component.js';\nimport {fieldToString} from '@natlibfi/marc-record-validators-melinda';\nimport {getTitle} from '../../match-detection/features/bib/title.js';\n\nconst debug = createDebugLogger('@natlibfi/melinda-record-matching:candidate-search:query');\n\nconst IS_OK_ALONE_THRESHOLD = 5;\n\nexport function bibSourceIds(record) {\n\n  /* Melinda's SRU-index melinda.sourceid includes source IDs from SID fields in Melinda records\n     SID-fields in Melinda have sf $c with local id and sf $b with a code for the local db:\n\n     SID__ $c 123457 $b helka\n     SID__ $c (ANDL100020)1077305 $b sata\n     SID__ $c VER999999 $ FI-KV\n     SID__ $c /10024/508126 $ REPO_THESEUS\n\n    In melinda.sourceid -index case is kept, sourceprefixes in brackets and hyphens are normalized away:\n    Note: slashes are not normalized away, but a SRU-search-string including slashes needs to be quoted\n\n    1234567helka\n    1077305sata\n    VER999999FIKV\n    /10024/508126REPO_THESEUS\n\n    Note: All Melinda records that have a matching records in a local db do NOT have SID for that local records,\n          existence of a SID field depends on how the record has been added to Melinda and how it has been handled\n          afterwards. SIDs are also not reliably maintained. A record might or might not have a SID for a local db\n          after the matching record is removed from the local db.\n\n   */\n\n\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:candidate-search:query:source-ids');\n  const debugData = debug.extend('data');\n  //const debugInfo = debug.extend('info');\n\n  debug(`Creating queries for sourceid's`);\n\n  const fSids = record.get('SID');\n  debugData(`SID-fields (${fSids.length}): ${JSON.stringify(fSids)}`);\n\n  return fSids.length > 0 ? toSidQueries(fSids) : [];\n\n  function toSidQueries(fSids) {\n    debug(`Creating actual queries for sourceid's`);\n\n    const sidStrings = getSidStrings(fSids);\n\n    if (sidStrings.length < 1) {\n      debug(`No identifiers found, no queries created.`);\n      return [];\n    }\n\n    const sidQueries = toQueries(sidStrings, 'melinda.sourceid');\n\n    return sidQueries;\n\n    function getSidStrings(fSids) {\n      debug(`Getting Sid strings from SID fields`);\n\n      // Map SID fields to valid sidStrings, filter out empty strings\n      const sidStrings = fSids.map(toSidString).filter(nonEmptySid => nonEmptySid);\n      return sidStrings;\n\n      function toSidString(field) {\n        debug(`Getting string from a field`);\n\n        return validateSidFieldSubfieldCounts(field) ? createSidString(field) : '';\n\n        function createSidString(field) {\n          debug(`Creating string from a field`);\n          const [sfC] = getSubfieldValues(field, 'c');\n          const [sfB] = getSubfieldValues(field, 'b');\n\n          const cleanedSfC = removeSourcePrefix(normalizeSidSubfieldValue(sfC));\n          const cleanedSfB = normalizeSidSubfieldValue(sfB);\n\n          debugData(`${JSON.stringify(sfC)} + ${JSON.stringify(sfB)}`);\n          return cleanedSfC.concat(cleanedSfB);\n        }\n\n        function removeSourcePrefix(subfieldValue) {\n          const sourcePrefixRegex = (/^(?<sourcePrefix>\\([A-Za-z0-9-]+\\))(?<id>.+)$/u);\n          const normalizedValue = testStringOrNumber(subfieldValue) ? String(subfieldValue).replace(sourcePrefixRegex, '$<id>') : '';\n          debugData(`Normalized ${subfieldValue} to ${normalizedValue}`);\n          return normalizedValue;\n        }\n\n        function normalizeSidSubfieldValue(subfieldValue) {\n          debugData(`Normalizing ${subfieldValue}`);\n          const normalizeAwayRegex = (/[- ]/u);\n          return testStringOrNumber(subfieldValue) ? String(subfieldValue).replace(normalizeAwayRegex, '') : '';\n        }\n\n      }\n    }\n  }\n}\n\nexport function bibMelindaIds(record) {\n  // Melinda's SRU-index melinda.melindaid includes f001 controlnumbers and old Melinda-IDs from f035z's for all non-deleted Melinda-records\n\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:candidate-search:query:bibMelindaIds');\n  const debugData = debug.extend('data');\n  debug(`Creating queries for MelindaIds`);\n\n  // Note: Melinda-ID's for search queries are created just from records f035a's and f035z's\n  // Both (FI-MELINDA)- and FCC-prefixed forms are found\n  // f001 controlnumber is not currently included, even if record's f003 is FI-MELINDA\n  const melindaIds = getMelindaIdsF035(record);\n\n  debugData(`Unique identifiers (${melindaIds.length}): ${JSON.stringify(melindaIds)}`);\n\n  if (melindaIds.length < 1) {\n    debug(`No identifiers found, no queries created.`);\n    return [];\n  }\n\n  return toQueries(melindaIds, 'melinda.melindaid');\n}\n\n\n// bibHostComponents returns host id from the first subfield $w of first field f773, see test-fixtures 04 and 05\n// bibHostComponents should search all 773 $ws for possible host id, but what should it do in case of multiple host ids?\nexport function bibHostComponents(record) {\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:candidate-search:query:bibHostComponents');\n  const debugData = debug.extend('data');\n  debug(`Creating queries for hostIds`);\n  const f773s = getHostMelindaFields(record);\n  if (f773s.length !== 1) { // This needs some thinking...\n    return [];\n  }\n\n  const [id] = extractHostMelindaIdsFromField(f773s[0]);\n  debug(`Found id: ${JSON.stringify(id)}`);\n\n  // NB! record.isCR() does not work if LDR/07=a, so we get year from 773$g!\n  const year = extractPublicationYearFrom773(f773s[0]);\n  debug(`${fieldToString(f773s[0])} => ${year ? year : 'N/A'}`);\n  if (year) {\n    return [`dc.date=${year} AND melinda.partsofhost=${id}`];\n  }\n\n  return [`melinda.partsofhost=${id}`];\n\n}\n\n\n\n\n// SRU search dc.title with a search phrase starting with ^ maps currently in Melinda to (probably) to *headings* index TIT\n// - Aleph cannot currently handle headings searches starting with a boolean - in these cases use word search\n\nexport function bibTitle(record) {\n  // We get author/publisher only when formatted title is shorter than 5 chars\n  return bibTitleAuthorPublisher({record, onlyTitleLength: 5});\n}\n\nexport function bibTitleAuthor(record) {\n  debug('bibTitleAuthor');\n  // We use onlyTitleLength that is longer than our formatted length to\n  // get an author or an publisher always\n  return bibTitleAuthorPublisher({record, onlyTitleLength: 100});\n}\n\nexport function bibTitleAuthorYear(record) {\n  debug('bibTitleAuthorYearAlternates');\n  // We use onlyTitleLength that is longer than our formatted length to\n  // get an author or an publisher always\n\n  return bibTitleAuthorPublisher({record, onlyTitleLength: 100, addYear: true});\n}\n\nexport function bibTitleAuthorYearAlternates(record) {\n  debug('bibTitleAuthorYearAlternates');\n  // We use onlyTitleLength that is longer than our formatted length to\n  // get an author or an publisher always\n  const origQueryList = bibTitleAuthorPublisher({record, onlyTitleLength: 100, addYear: true, alternates: true, alternateQueries: []});\n  debug(`${JSON.stringify(origQueryList)}`);\n  return {queryList: Array.from(origQueryList).reverse(), queryListType: 'alternates'};\n}\n\nfunction getTitleForQuery(record) {\n  const title = getTitle(record, ['a']);\n  if (title) {\n    const nWords = title.split(' ');\n    // If lone $a is deemed too short, fetch $b as well:\n    // (NV: I've seen pairs with 245$a-only vs 245$a$b, so I'd like to use $a only if it is long enough)\n\n    if (nWords < 3 || title.length < 12) {\n      const [f245] = record.get('245');\n      // If punctuation is ' =' I think that f245$a is good enough despite shortness. Trying to balance between two bad situations...\n      // \"Suo (= short title) siell\u00E4, vetel\u00E4 (= missing $b name in another language) t\u00E4\u00E4ll\u00E4...\"\n      if (f245 && f245.subfields.find(sf => sf.code === 'a' && sf.value.match(/ =$/u)) && title.length >= IS_OK_ALONE_THRESHOLD) {\n        return title;\n      }\n      return getTitle(record, ['a', 'b']); // Try to get a longer title\n    }\n  }\n  return title;\n}\n\nfunction dcTitle(record, onlyTitleLength, alternates = false) {\n  const title = getTitleForQuery(record);\n  if (!testStringOrNumber(title)) {\n    return [];\n  }\n\n  const formatted = getFormattedTitle(title);\n\n  // use word search for titles starting with a boolean\n  const useWordSearch = checkUseWordSearch(formatted);\n  // Prevent too many matches / SRU crashing by having a minimum length\n  // Note that currently this fails matching if there are no matches from previous matchers\n  if (formatted.length >= onlyTitleLength && !alternates) {\n    return [`dc.title=\"${useWordSearch ? '' : '^'}${formatted}*\"`, formatted, true];\n  }\n\n  const queryIsOkAlone = !useWordSearch && formatted.length >= IS_OK_ALONE_THRESHOLD;\n\n  // use word search without ending * also in combination searches to avoid SRU-server crashes [MRA-189]\n  return [`dc.title=\"${useWordSearch || !queryIsOkAlone ? '' : '^'}${formatted}${queryIsOkAlone ? '*' : ''}\"`, formatted, queryIsOkAlone];\n\n  function getFormattedTitle(title) {\n    const formatted = String(title)\n      .replace(/[\\-+ !\"(){}\\[\\]<>;:.?/@*%=^_`~]/gu, ' ')\n      .replace(/[^\\w\\s\\p{Alphabetic}]/gu, '') // Apparently matches to/works with non-aplhabetic scripts such as Chinese as well\n      .replace(/  +/gu, ' ') // Clean up concurrent spaces from eg. subfield changes\n      .trim()\n      .replace(/^(.{30}\\S*) .*$/, \"$1\")\n      .trim();\n\n    return formatted;\n  }\n}\n\nexport function bibTitleAuthorPublisher({record, onlyTitleLength, addYear = false, alternates = false, alternateQueries = []}) {\n  debug(`bibTitleAuthorPublisher, onlyTitleLength: ${onlyTitleLength}, addYear: ${addYear}, alternates: ${alternates}`);\n  const [query, formatted, queryIsOkAlone] = dcTitle(record, onlyTitleLength, alternates);\n  if (query === undefined) {\n    return [];\n  }\n\n  debug(`query: ${query}`);\n\n  // Prevent too many matches / SRU crashing by having a minimum length\n  // Note that currently this fails matching if there are no matches from previous matchers\n  if (formatted.length >= onlyTitleLength && !alternates) {\n    return [query];\n  }\n\n  const newAlternateQueries = alternates ? [...alternateQueries, query] : alternateQueries;\n\n  return addAuthorsToSearch({query, queryIsOkAlone, addYear, alternates, alternateQueries: newAlternateQueries});\n\n  function addAuthorsToSearch({query, queryIsOkAlone = false, addYear = false, alternates = false, alternateQueries = []}) {\n    debug('addAuthorsToSearch');\n    const [authorQuery] = bibAuthors(record);\n    if (authorQuery !== undefined) {\n      if (addYear) {\n        const newAlternateQueries = alternates ? [...alternateQueries, `${authorQuery} AND ${query}`] : alternateQueries;\n        return addYearToSearch({query: `${authorQuery} AND ${query}`, queryIsOkAlone: true, alternates, alternateQueries: newAlternateQueries});\n      }\n      return alternates ? alternateQueries : [`${authorQuery} AND ${query}`];\n    }\n    return addPublisherToSearch({query, queryIsOkAlone, addYear, alternates, alternateQueries});\n    //return [];\n  }\n\n  function addPublisherToSearch({query, queryIsOkAlone = false, addYear = false, alternates = false, alternateQueries = []}) {\n    const [publisherQuery] = bibPublishers(record);\n    if (publisherQuery !== undefined) {\n      if (addYear) {\n        const newAlternateQueries = alternates ? [...alternateQueries, `${publisherQuery} AND ${query}`] : alternateQueries;\n        return addYearToSearch({query: `${publisherQuery} AND ${query}`, queryIsOkAlone: true, alternates, alternateQueries: newAlternateQueries});\n      }\n      return alternates ? alternateQueries : [`${publisherQuery} AND ${query}`];\n    }\n    if (queryIsOkAlone && !addYear) {\n      return alternates ? alternateQueries : [`${query}`];\n    }\n    return addYearToSearch({query, queryIsOkAlone, alternates, alternateQueries});\n  }\n\n  function addYearToSearch({query, queryIsOkAlone = false, alternates = false, alternateQueries = []}) {\n    const [yearQuery] = bibYear(record);\n    if (yearQuery !== undefined) {\n      const yearAndOtherQueries = `${yearQuery} AND ${query}`;\n      return alternates ? [...alternateQueries, yearAndOtherQueries] : [yearAndOtherQueries];\n    }\n    if (queryIsOkAlone) {\n      return alternates ? alternateQueries : [`${query}`];\n    }\n    return [];\n  }\n\n}\n\nexport function bibAuthors(record) {\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:candidate-search:query:bibAuthors');\n  const debugData = debug.extend('data');\n  debug(`Creating query for the first author`);\n  //debugData(record);\n\n  const author = getAuthor(record);\n\n  if (testStringOrNumber(author)) {\n    const formatted = String(author)\n      .replace(/[^\\w\\s\\p{Alphabetic}]/gu, '')\n      // Clean up concurrent spaces from fe. subfield changes\n      .replace(/ +/gu, ' ')\n      .trim()\n      .slice(0, 30)\n      .trim();\n\n    // use word search for authors starting with a boolean\n    const useWordSearch = checkUseWordSearch(formatted);\n    // Prevent too many matches by having a minimum length\n    debugData(`Author string: ${formatted}`);\n    if (formatted.length >= 5) {\n      return [`dc.author=\"${useWordSearch ? '' : '^'}${formatted}*\"`];\n    }\n    return [];\n  }\n\n  return [];\n\n  function getAuthor(record) {\n    //debugData(record);\n    const [field] = record.get(/^(?:100|110|111|700|710|711)$/u);\n    //debugData(field);\n\n    if (field) {\n      const authorString = field.subfields\n        .filter(({code}) => ['a'].includes(code)) // We might use different subfield code sets for X00, X10 and X11?\n        .map(({value}) => testStringOrNumber(value) ? String(value) : '')\n        .filter(value => value)\n        // In Melinda's index subfield separators are indexed as ' '\n        .join(' ');\n      return authorString;\n    }\n    return false;\n  }\n}\n\nexport function bibPublishers(record) {\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:candidate-search:query:bibPublishers');\n  const debugData = debug.extend('data');\n  debug(`Creating query for the first publisher`);\n  //debugData(record);\n\n  const publisher = getPublisher(record);\n  if (testStringOrNumber(publisher)) {\n    const formatted = String(publisher)\n      .replace(/[^\\w\\s\\p{Alphabetic}]/gu, '')\n      // Clean up concurrent spaces from fe. subfield changes\n      .replace(/ +/gu, ' ')\n      .trim()\n      .slice(0, 30)\n      .trim();\n\n    debugData(`Publisher string: '${formatted}'`);\n    if (formatted.length === 0) {\n      return [];\n    }\n    // use non-wildcard word search from dc.publisher\n    return [`dc.publisher=\"${formatted}\"`];\n  }\n\n  return [];\n\n  function getPublisher(record) {\n    //debugData(record);\n    const [field] = record.get(/^26[04]$/u).filter(f => f.subfields.some(sf => sf.code === 'b')); // Filter removes copyright-only fields\n    //debugData(field);\n\n    if (field) {\n      const publisherString = field.subfields\n        .filter(({code}) => ['b'].includes(code))\n        .map(({value}) => testStringOrNumber(value) ? String(value) : '')\n        .filter(value => value)\n        // In Melinda's index subfield separators are indexed as ' '\n        .join(' ')\n        .trim();\n      return publisherString;\n    }\n    return false;\n  }\n}\n\nexport function bibYear(record) {\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:candidate-search:query:bibYear');\n  const debugData = debug.extend('data');\n  debug(`Creating query for the publishing year`);\n\n  const year = getYear(record);\n  if (year) {\n    return [`dc.date=\"${year}\"`];\n  }\n  return [];\n\n  function getYear(record) {\n    const [f008] = record.get(/^008$/u);\n    if (!f008 || !f008.value || f008.value.length < 11) {\n      debug('f008 missing/crappy');\n      return false;\n    }\n\n    debugData(`f008: ${JSON.stringify(f008)}`);\n    const {value} = f008;\n    if (value === '||||' || value === '    ') { // Meaningless values\n      return false;\n    }\n    return value.slice(7, 11);\n  }\n}\n\nexport function checkUseWordSearch(formatted) {\n  const lowercased = formatted.toLowerCase();\n  // Note: add a space to startWords to catch just actual boolean words\n  const booleanStartWords = ['and ', 'or ', 'nor ', 'not '];\n  return booleanStartWords.some(word => lowercased.startsWith(word));\n}\n\nexport function bibStandardIdentifiers(record) {\n\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:candidate-search:query:bibStandardIdentifiers');\n  const debugData = debug.extend('data');\n  debug(`Creating queries for standard identifiers`);\n\n  // DEVELOP: should we query also f015 and f028?\n\n  // const fields = record.get(/^(?<def>020|022|024)$/u);\n  const fields = record.get(/^(?<def>015|020|022|024|028)$/u);\n  const identifiers = [].concat(...fields.map(toIdentifiers));\n  const uniqueIdentifiers = [...new Set(identifiers)];\n\n  debugData(`Standard identifier fields: ${JSON.stringify(fields)}`);\n  debugData(`Identifiers (${identifiers.length}): ${JSON.stringify(identifiers)}`);\n  debugData(`Unique identifiers (${uniqueIdentifiers.length}): ${JSON.stringify(uniqueIdentifiers)}`);\n\n  if (uniqueIdentifiers.length < 1) {\n    debug(`No identifiers found, no queries created.`);\n    return [];\n  }\n\n  return toQueries(uniqueIdentifiers, 'dc.identifier');\n\n  function toIdentifiers({tag, subfields}) {\n    const issnIsbnReqExp = (/^[A-Za-z0-9-]+$/u);\n    const otherIdReqExp = (/^[A-Za-z0-9-:]+$/u);\n\n    if (tag === '015') { // TODO: test (does this use the right index etc.)\n      return subfields\n        .filter(sf => sf.code === 'a' && sf.value.match(/^[A-Z0-9\\-]+$/ui))\n        .map(sf => sf.value)\n    }\n\n    if (tag === '020') {\n      return subfields\n        .filter(sub => ['a', 'z'].includes(sub.code) && testStringOrNumber(sub.value) && issnIsbnReqExp.test(String(sub.value)))\n        .map(({value}) => String(value));\n    }\n\n    if (tag === '022') {\n      return subfields\n        .filter(sub => ['a', 'z', 'y'].includes(sub.code) && testStringOrNumber(sub.value) && issnIsbnReqExp.test(String(sub.value)))\n        .map(({value}) => String(value));\n    }\n\n    if (tag === '028') { // TODO: test\n      const a = subfields.find(sf => sf.code === 'a');\n      if (a) {\n        const b = subfields.find(sf => sf.code === 'b');\n        // TODO: normalize?\n        if (b) {\n          return [`^${a.value}`, `^${b.value} ${a.value}`];\n        }\n        return [`^${a.value}`];\n      }\n    }\n\n    // Default seems to be 024:\n    return subfields\n      .filter(sub => ['a', 'z'].includes(sub.code) && testStringOrNumber(sub.value) && otherIdReqExp.test(String(sub.value)))\n      .map(({value}) => String(value));\n  }\n}\n"],
+  "mappings": "AAAA,OAAO,uBAAuB;AAC9B,SAAQ,iBAAgB;AACxB,SAAQ,mBAAmB,gCAAgC,mBAAmB,0BAAyB;AACvG,SAAQ,gCAAgC,+BAA+B,4BAA2B;AAClG,SAAQ,qBAAoB;AAC5B,SAAQ,gBAAe;AAEvB,MAAM,QAAQ,kBAAkB,0DAA0D;AAE1F,MAAM,wBAAwB;AAEvB,gBAAS,aAAa,QAAQ;AA0BnC,QAAMA,SAAQ,kBAAkB,qEAAqE;AACrG,QAAM,YAAYA,OAAM,OAAO,MAAM;AAGrC,EAAAA,OAAM,iCAAiC;AAEvC,QAAM,QAAQ,OAAO,IAAI,KAAK;AAC9B,YAAU,eAAe,MAAM,MAAM,MAAM,KAAK,UAAU,KAAK,CAAC,EAAE;AAElE,SAAO,MAAM,SAAS,IAAI,aAAa,KAAK,IAAI,CAAC;AAEjD,WAAS,aAAaC,QAAO;AAC3B,IAAAD,OAAM,wCAAwC;AAE9C,UAAM,aAAa,cAAcC,MAAK;AAEtC,QAAI,WAAW,SAAS,GAAG;AACzB,MAAAD,OAAM,2CAA2C;AACjD,aAAO,CAAC;AAAA,IACV;AAEA,UAAM,aAAa,UAAU,YAAY,kBAAkB;AAE3D,WAAO;AAEP,aAAS,cAAcC,QAAO;AAC5B,MAAAD,OAAM,qCAAqC;AAG3C,YAAME,cAAaD,OAAM,IAAI,WAAW,EAAE,OAAO,iBAAe,WAAW;AAC3E,aAAOC;AAEP,eAAS,YAAY,OAAO;AAC1B,QAAAF,OAAM,6BAA6B;AAEnC,eAAO,+BAA+B,KAAK,IAAI,gBAAgB,KAAK,IAAI;AAExE,iBAAS,gBAAgBG,QAAO;AAC9B,UAAAH,OAAM,8BAA8B;AACpC,gBAAM,CAAC,GAAG,IAAI,kBAAkBG,QAAO,GAAG;AAC1C,gBAAM,CAAC,GAAG,IAAI,kBAAkBA,QAAO,GAAG;AAE1C,gBAAM,aAAa,mBAAmB,0BAA0B,GAAG,CAAC;AACpE,gBAAM,aAAa,0BAA0B,GAAG;AAEhD,oBAAU,GAAG,KAAK,UAAU,GAAG,CAAC,MAAM,KAAK,UAAU,GAAG,CAAC,EAAE;AAC3D,iBAAO,WAAW,OAAO,UAAU;AAAA,QACrC;AAEA,iBAAS,mBAAmB,eAAe;AACzC,gBAAM,oBAAqB;AAC3B,gBAAM,kBAAkB,mBAAmB,aAAa,IAAI,OAAO,aAAa,EAAE,QAAQ,mBAAmB,OAAO,IAAI;AACxH,oBAAU,cAAc,aAAa,OAAO,eAAe,EAAE;AAC7D,iBAAO;AAAA,QACT;AAEA,iBAAS,0BAA0B,eAAe;AAChD,oBAAU,eAAe,aAAa,EAAE;AACxC,gBAAM,qBAAsB;AAC5B,iBAAO,mBAAmB,aAAa,IAAI,OAAO,aAAa,EAAE,QAAQ,oBAAoB,EAAE,IAAI;AAAA,QACrG;AAAA,MAEF;AAAA,IACF;AAAA,EACF;AACF;AAEO,gBAAS,cAAc,QAAQ;AAGpC,QAAMH,SAAQ,kBAAkB,wEAAwE;AACxG,QAAM,YAAYA,OAAM,OAAO,MAAM;AACrC,EAAAA,OAAM,iCAAiC;AAKvC,QAAM,aAAa,kBAAkB,MAAM;AAE3C,YAAU,uBAAuB,WAAW,MAAM,MAAM,KAAK,UAAU,UAAU,CAAC,EAAE;AAEpF,MAAI,WAAW,SAAS,GAAG;AACzB,IAAAA,OAAM,2CAA2C;AACjD,WAAO,CAAC;AAAA,EACV;AAEA,SAAO,UAAU,YAAY,mBAAmB;AAClD;AAKO,gBAAS,kBAAkB,QAAQ;AACxC,QAAMA,SAAQ,kBAAkB,4EAA4E;AAC5G,QAAM,YAAYA,OAAM,OAAO,MAAM;AACrC,EAAAA,OAAM,8BAA8B;AACpC,QAAM,QAAQ,qBAAqB,MAAM;AACzC,MAAI,MAAM,WAAW,GAAG;AACtB,WAAO,CAAC;AAAA,EACV;AAEA,QAAM,CAAC,EAAE,IAAI,+BAA+B,MAAM,CAAC,CAAC;AACpD,EAAAA,OAAM,aAAa,KAAK,UAAU,EAAE,CAAC,EAAE;AAGvC,QAAM,OAAO,8BAA8B,MAAM,CAAC,CAAC;AACnD,EAAAA,OAAM,GAAG,cAAc,MAAM,CAAC,CAAC,CAAC,OAAO,OAAO,OAAO,KAAK,EAAE;AAC5D,MAAI,MAAM;AACR,WAAO,CAAC,WAAW,IAAI,4BAA4B,EAAE,EAAE;AAAA,EACzD;AAEA,SAAO,CAAC,uBAAuB,EAAE,EAAE;AAErC;AAQO,gBAAS,SAAS,QAAQ;AAE/B,SAAO,wBAAwB,EAAC,QAAQ,iBAAiB,EAAC,CAAC;AAC7D;AAEO,gBAAS,eAAe,QAAQ;AACrC,QAAM,gBAAgB;AAGtB,SAAO,wBAAwB,EAAC,QAAQ,iBAAiB,IAAG,CAAC;AAC/D;AAEO,gBAAS,mBAAmB,QAAQ;AACzC,QAAM,8BAA8B;AAIpC,SAAO,wBAAwB,EAAC,QAAQ,iBAAiB,KAAK,SAAS,KAAI,CAAC;AAC9E;AAEO,gBAAS,6BAA6B,QAAQ;AACnD,QAAM,8BAA8B;AAGpC,QAAM,gBAAgB,wBAAwB,EAAC,QAAQ,iBAAiB,KAAK,SAAS,MAAM,YAAY,MAAM,kBAAkB,CAAC,EAAC,CAAC;AACnI,QAAM,GAAG,KAAK,UAAU,aAAa,CAAC,EAAE;AACxC,SAAO,EAAC,WAAW,MAAM,KAAK,aAAa,EAAE,QAAQ,GAAG,eAAe,aAAY;AACrF;AAEA,SAAS,iBAAiB,QAAQ;AAChC,QAAM,QAAQ,SAAS,QAAQ,CAAC,GAAG,CAAC;AACpC,MAAI,OAAO;AACT,UAAM,SAAS,MAAM,MAAM,GAAG;AAI9B,QAAI,SAAS,KAAK,MAAM,SAAS,IAAI;AACnC,YAAM,CAAC,IAAI,IAAI,OAAO,IAAI,KAAK;AAG/B,UAAI,QAAQ,KAAK,UAAU,KAAK,QAAM,GAAG,SAAS,OAAO,GAAG,MAAM,MAAM,MAAM,CAAC,KAAK,MAAM,UAAU,uBAAuB;AACzH,eAAO;AAAA,MACT;AACA,aAAO,SAAS,QAAQ,CAAC,KAAK,GAAG,CAAC;AAAA,IACpC;AAAA,EACF;AACA,SAAO;AACT;AAEA,SAAS,QAAQ,QAAQ,iBAAiB,aAAa,OAAO;AAC5D,QAAM,QAAQ,iBAAiB,MAAM;AACrC,MAAI,CAAC,mBAAmB,KAAK,GAAG;AAC9B,WAAO,CAAC;AAAA,EACV;AAEA,QAAM,YAAY,kBAAkB,KAAK;AAGzC,QAAM,gBAAgB,mBAAmB,SAAS;AAGlD,MAAI,UAAU,UAAU,mBAAmB,CAAC,YAAY;AACtD,WAAO,CAAC,aAAa,gBAAgB,KAAK,GAAG,GAAG,SAAS,MAAM,WAAW,IAAI;AAAA,EAChF;AAEA,QAAM,iBAAiB,CAAC,iBAAiB,UAAU,UAAU;AAG7D,SAAO,CAAC,aAAa,iBAAiB,CAAC,iBAAiB,KAAK,GAAG,GAAG,SAAS,GAAG,iBAAiB,MAAM,EAAE,KAAK,WAAW,cAAc;AAEtI,WAAS,kBAAkBI,QAAO;AAChC,UAAMC,aAAY,OAAOD,MAAK,EAC3B,QAAQ,qCAAqC,GAAG,EAChD,QAAQ,2BAA2B,EAAE,EACrC,QAAQ,SAAS,GAAG,EACpB,KAAK,EACL,QAAQ,mBAAmB,IAAI,EAC/B,KAAK;AAER,WAAOC;AAAA,EACT;AACF;AAEO,gBAAS,wBAAwB,EAAC,QAAQ,iBAAiB,UAAU,OAAO,aAAa,OAAO,mBAAmB,CAAC,EAAC,GAAG;AAC7H,QAAM,6CAA6C,eAAe,cAAc,OAAO,iBAAiB,UAAU,EAAE;AACpH,QAAM,CAAC,OAAO,WAAW,cAAc,IAAI,QAAQ,QAAQ,iBAAiB,UAAU;AACtF,MAAI,UAAU,QAAW;AACvB,WAAO,CAAC;AAAA,EACV;AAEA,QAAM,UAAU,KAAK,EAAE;AAIvB,MAAI,UAAU,UAAU,mBAAmB,CAAC,YAAY;AACtD,WAAO,CAAC,KAAK;AAAA,EACf;AAEA,QAAM,sBAAsB,aAAa,CAAC,GAAG,kBAAkB,KAAK,IAAI;AAExE,SAAO,mBAAmB,EAAC,OAAO,gBAAgB,SAAS,YAAY,kBAAkB,oBAAmB,CAAC;AAE7G,WAAS,mBAAmB,EAAC,OAAAC,QAAO,gBAAAC,kBAAiB,OAAO,SAAAC,WAAU,OAAO,YAAAC,cAAa,OAAO,kBAAAC,oBAAmB,CAAC,EAAC,GAAG;AACvH,UAAM,oBAAoB;AAC1B,UAAM,CAAC,WAAW,IAAI,WAAW,MAAM;AACvC,QAAI,gBAAgB,QAAW;AAC7B,UAAIF,UAAS;AACX,cAAMG,uBAAsBF,cAAa,CAAC,GAAGC,mBAAkB,GAAG,WAAW,QAAQJ,MAAK,EAAE,IAAII;AAChG,eAAO,gBAAgB,EAAC,OAAO,GAAG,WAAW,QAAQJ,MAAK,IAAI,gBAAgB,MAAM,YAAAG,aAAY,kBAAkBE,qBAAmB,CAAC;AAAA,MACxI;AACA,aAAOF,cAAaC,oBAAmB,CAAC,GAAG,WAAW,QAAQJ,MAAK,EAAE;AAAA,IACvE;AACA,WAAO,qBAAqB,EAAC,OAAAA,QAAO,gBAAAC,iBAAgB,SAAAC,UAAS,YAAAC,aAAY,kBAAAC,kBAAgB,CAAC;AAAA,EAE5F;AAEA,WAAS,qBAAqB,EAAC,OAAAJ,QAAO,gBAAAC,kBAAiB,OAAO,SAAAC,WAAU,OAAO,YAAAC,cAAa,OAAO,kBAAAC,oBAAmB,CAAC,EAAC,GAAG;AACzH,UAAM,CAAC,cAAc,IAAI,cAAc,MAAM;AAC7C,QAAI,mBAAmB,QAAW;AAChC,UAAIF,UAAS;AACX,cAAMG,uBAAsBF,cAAa,CAAC,GAAGC,mBAAkB,GAAG,cAAc,QAAQJ,MAAK,EAAE,IAAII;AACnG,eAAO,gBAAgB,EAAC,OAAO,GAAG,cAAc,QAAQJ,MAAK,IAAI,gBAAgB,MAAM,YAAAG,aAAY,kBAAkBE,qBAAmB,CAAC;AAAA,MAC3I;AACA,aAAOF,cAAaC,oBAAmB,CAAC,GAAG,cAAc,QAAQJ,MAAK,EAAE;AAAA,IAC1E;AACA,QAAIC,mBAAkB,CAACC,UAAS;AAC9B,aAAOC,cAAaC,oBAAmB,CAAC,GAAGJ,MAAK,EAAE;AAAA,IACpD;AACA,WAAO,gBAAgB,EAAC,OAAAA,QAAO,gBAAAC,iBAAgB,YAAAE,aAAY,kBAAAC,kBAAgB,CAAC;AAAA,EAC9E;AAEA,WAAS,gBAAgB,EAAC,OAAAJ,QAAO,gBAAAC,kBAAiB,OAAO,YAAAE,cAAa,OAAO,kBAAAC,oBAAmB,CAAC,EAAC,GAAG;AACnG,UAAM,CAAC,SAAS,IAAI,QAAQ,MAAM;AAClC,QAAI,cAAc,QAAW;AAC3B,YAAM,sBAAsB,GAAG,SAAS,QAAQJ,MAAK;AACrD,aAAOG,cAAa,CAAC,GAAGC,mBAAkB,mBAAmB,IAAI,CAAC,mBAAmB;AAAA,IACvF;AACA,QAAIH,iBAAgB;AAClB,aAAOE,cAAaC,oBAAmB,CAAC,GAAGJ,MAAK,EAAE;AAAA,IACpD;AACA,WAAO,CAAC;AAAA,EACV;AAEF;AAEO,gBAAS,WAAW,QAAQ;AACjC,QAAMN,SAAQ,kBAAkB,qEAAqE;AACrG,QAAM,YAAYA,OAAM,OAAO,MAAM;AACrC,EAAAA,OAAM,qCAAqC;AAG3C,QAAM,SAAS,UAAU,MAAM;AAE/B,MAAI,mBAAmB,MAAM,GAAG;AAC9B,UAAM,YAAY,OAAO,MAAM,EAC5B,QAAQ,2BAA2B,EAAE,EAErC,QAAQ,QAAQ,GAAG,EACnB,KAAK,EACL,MAAM,GAAG,EAAE,EACX,KAAK;AAGR,UAAM,gBAAgB,mBAAmB,SAAS;AAElD,cAAU,kBAAkB,SAAS,EAAE;AACvC,QAAI,UAAU,UAAU,GAAG;AACzB,aAAO,CAAC,cAAc,gBAAgB,KAAK,GAAG,GAAG,SAAS,IAAI;AAAA,IAChE;AACA,WAAO,CAAC;AAAA,EACV;AAEA,SAAO,CAAC;AAER,WAAS,UAAUY,SAAQ;AAEzB,UAAM,CAAC,KAAK,IAAIA,QAAO,IAAI,gCAAgC;AAG3D,QAAI,OAAO;AACT,YAAM,eAAe,MAAM,UACxB,OAAO,CAAC,EAAC,KAAI,MAAM,CAAC,GAAG,EAAE,SAAS,IAAI,CAAC,EACvC,IAAI,CAAC,EAAC,MAAK,MAAM,mBAAmB,KAAK,IAAI,OAAO,KAAK,IAAI,EAAE,EAC/D,OAAO,WAAS,KAAK,EAErB,KAAK,GAAG;AACX,aAAO;AAAA,IACT;AACA,WAAO;AAAA,EACT;AACF;AAEO,gBAAS,cAAc,QAAQ;AACpC,QAAMZ,SAAQ,kBAAkB,wEAAwE;AACxG,QAAM,YAAYA,OAAM,OAAO,MAAM;AACrC,EAAAA,OAAM,wCAAwC;AAG9C,QAAM,YAAY,aAAa,MAAM;AACrC,MAAI,mBAAmB,SAAS,GAAG;AACjC,UAAM,YAAY,OAAO,SAAS,EAC/B,QAAQ,2BAA2B,EAAE,EAErC,QAAQ,QAAQ,GAAG,EACnB,KAAK,EACL,MAAM,GAAG,EAAE,EACX,KAAK;AAER,cAAU,sBAAsB,SAAS,GAAG;AAC5C,QAAI,UAAU,WAAW,GAAG;AAC1B,aAAO,CAAC;AAAA,IACV;AAEA,WAAO,CAAC,iBAAiB,SAAS,GAAG;AAAA,EACvC;AAEA,SAAO,CAAC;AAER,WAAS,aAAaY,SAAQ;AAE5B,UAAM,CAAC,KAAK,IAAIA,QAAO,IAAI,WAAW,EAAE,OAAO,OAAK,EAAE,UAAU,KAAK,QAAM,GAAG,SAAS,GAAG,CAAC;AAG3F,QAAI,OAAO;AACT,YAAM,kBAAkB,MAAM,UAC3B,OAAO,CAAC,EAAC,KAAI,MAAM,CAAC,GAAG,EAAE,SAAS,IAAI,CAAC,EACvC,IAAI,CAAC,EAAC,MAAK,MAAM,mBAAmB,KAAK,IAAI,OAAO,KAAK,IAAI,EAAE,EAC/D,OAAO,WAAS,KAAK,EAErB,KAAK,GAAG,EACR,KAAK;AACR,aAAO;AAAA,IACT;AACA,WAAO;AAAA,EACT;AACF;AAEO,gBAAS,QAAQ,QAAQ;AAC9B,QAAMZ,SAAQ,kBAAkB,kEAAkE;AAClG,QAAM,YAAYA,OAAM,OAAO,MAAM;AACrC,EAAAA,OAAM,wCAAwC;AAE9C,QAAM,OAAO,QAAQ,MAAM;AAC3B,MAAI,MAAM;AACR,WAAO,CAAC,YAAY,IAAI,GAAG;AAAA,EAC7B;AACA,SAAO,CAAC;AAER,WAAS,QAAQY,SAAQ;AACvB,UAAM,CAAC,IAAI,IAAIA,QAAO,IAAI,QAAQ;AAClC,QAAI,CAAC,QAAQ,CAAC,KAAK,SAAS,KAAK,MAAM,SAAS,IAAI;AAClD,MAAAZ,OAAM,qBAAqB;AAC3B,aAAO;AAAA,IACT;AAEA,cAAU,SAAS,KAAK,UAAU,IAAI,CAAC,EAAE;AACzC,UAAM,EAAC,MAAK,IAAI;AAChB,QAAI,UAAU,UAAU,UAAU,QAAQ;AACxC,aAAO;AAAA,IACT;AACA,WAAO,MAAM,MAAM,GAAG,EAAE;AAAA,EAC1B;AACF;AAEO,gBAAS,mBAAmB,WAAW;AAC5C,QAAM,aAAa,UAAU,YAAY;AAEzC,QAAM,oBAAoB,CAAC,QAAQ,OAAO,QAAQ,MAAM;AACxD,SAAO,kBAAkB,KAAK,UAAQ,WAAW,WAAW,IAAI,CAAC;AACnE;AAEO,gBAAS,uBAAuB,QAAQ;AAE7C,QAAMA,SAAQ,kBAAkB,iFAAiF;AACjH,QAAM,YAAYA,OAAM,OAAO,MAAM;AACrC,EAAAA,OAAM,2CAA2C;AAKjD,QAAM,SAAS,OAAO,IAAI,gCAAgC;AAC1D,QAAM,cAAc,CAAC,EAAE,OAAO,GAAG,OAAO,IAAI,aAAa,CAAC;AAC1D,QAAM,oBAAoB,CAAC,GAAG,IAAI,IAAI,WAAW,CAAC;AAElD,YAAU,+BAA+B,KAAK,UAAU,MAAM,CAAC,EAAE;AACjE,YAAU,gBAAgB,YAAY,MAAM,MAAM,KAAK,UAAU,WAAW,CAAC,EAAE;AAC/E,YAAU,uBAAuB,kBAAkB,MAAM,MAAM,KAAK,UAAU,iBAAiB,CAAC,EAAE;AAElG,MAAI,kBAAkB,SAAS,GAAG;AAChC,IAAAA,OAAM,2CAA2C;AACjD,WAAO,CAAC;AAAA,EACV;AAEA,SAAO,UAAU,mBAAmB,eAAe;AAEnD,WAAS,cAAc,EAAC,KAAK,UAAS,GAAG;AACvC,UAAM,iBAAkB;AACxB,UAAM,gBAAiB;AAEvB,QAAI,QAAQ,OAAO;AACjB,aAAO,UACJ,OAAO,QAAM,GAAG,SAAS,OAAO,GAAG,MAAM,MAAM,iBAAiB,CAAC,EACjE,IAAI,QAAM,GAAG,KAAK;AAAA,IACvB;AAEA,QAAI,QAAQ,OAAO;AACjB,aAAO,UACJ,OAAO,SAAO,CAAC,KAAK,GAAG,EAAE,SAAS,IAAI,IAAI,KAAK,mBAAmB,IAAI,KAAK,KAAK,eAAe,KAAK,OAAO,IAAI,KAAK,CAAC,CAAC,EACtH,IAAI,CAAC,EAAC,MAAK,MAAM,OAAO,KAAK,CAAC;AAAA,IACnC;AAEA,QAAI,QAAQ,OAAO;AACjB,aAAO,UACJ,OAAO,SAAO,CAAC,KAAK,KAAK,GAAG,EAAE,SAAS,IAAI,IAAI,KAAK,mBAAmB,IAAI,KAAK,KAAK,eAAe,KAAK,OAAO,IAAI,KAAK,CAAC,CAAC,EAC3H,IAAI,CAAC,EAAC,MAAK,MAAM,OAAO,KAAK,CAAC;AAAA,IACnC;AAEA,QAAI,QAAQ,OAAO;AACjB,YAAM,IAAI,UAAU,KAAK,QAAM,GAAG,SAAS,GAAG;AAC9C,UAAI,GAAG;AACL,cAAM,IAAI,UAAU,KAAK,QAAM,GAAG,SAAS,GAAG;AAE9C,YAAI,GAAG;AACL,iBAAO,CAAC,IAAI,EAAE,KAAK,IAAI,IAAI,EAAE,KAAK,IAAI,EAAE,KAAK,EAAE;AAAA,QACjD;AACA,eAAO,CAAC,IAAI,EAAE,KAAK,EAAE;AAAA,MACvB;AAAA,IACF;AAGA,WAAO,UACJ,OAAO,SAAO,CAAC,KAAK,GAAG,EAAE,SAAS,IAAI,IAAI,KAAK,mBAAmB,IAAI,KAAK,KAAK,cAAc,KAAK,OAAO,IAAI,KAAK,CAAC,CAAC,EACrH,IAAI,CAAC,EAAC,MAAK,MAAM,OAAO,KAAK,CAAC;AAAA,EACnC;AACF;",
   "names": ["debug", "fSids", "sidStrings", "field", "title", "formatted", "query", "queryIsOkAlone", "addYear", "alternates", "alternateQueries", "newAlternateQueries", "record"]
 }

package/dist/cli.js

@@ -3,6 +3,7 @@ import yargs from "yargs";
 import createMatchOperator, { candidateSearch, matchDetection } from "./index.js";
 import createDebugLogger from "debug";
 import { MarcRecord } from "@natlibfi/marc-record";
+import { uniqArray } from "@natlibfi/marc-record-validators-melinda/dist/utils.js";
 cli();
 async function cli() {
   const debug = createDebugLogger("@natlibfi/melinda-record-matching:cli");
@@ -44,6 +45,17 @@ async function cli() {
   const fileRaw = fs.readFileSync(file, "utf8");
   const record = new MarcRecord(JSON.parse(fileRaw), { subfieldValues: false });
   const result = await matchOperator({ record });
+  const matchCount = result.matches.length;
+  const matchIds = result.matches.map((matchA) => matchA.candidate.id);
+  const nonMatchCount = result.nonMatches?.length || result.nonMatchCount;
+  const nonMatchIds = result.nonMatches?.map((matchA) => matchA.candidate.id) || [];
+  const uniqueNonMatchIds = uniqArray(nonMatchIds);
+  const uniqueNonMatchCount = uniqueNonMatchIds.length;
+  const candidateCount = result.candidateCount;
+  debug(`Matches (${matchCount}) ${JSON.stringify(matchIds)}`);
+  debug(`NonMatches (${nonMatchCount}) ${JSON.stringify(nonMatchIds)}`);
+  debug(`Unique nonMatches (${uniqueNonMatchCount}) ${JSON.stringify(uniqueNonMatchIds)}`);
+  debug(`Candidates (${candidateCount})`);
   debug(JSON.stringify(result));
   function generateStrategy(searchType2) {
     if (["IDS"].includes(searchType2)) {
@@ -71,7 +83,9 @@ async function cli() {
         //  - ignore one year differences in publicationTime
         //  - extract publicationTimes from f008, f26x and reprint notes in f500
         //  - do not substract points for mismatching (normal) publicationTime, if there's a match between
-        //       normal publicationTime and a reprintPublication time
+        //       normal publicationTime and a reprintPublicationTime
+        //  - do not subract points for mismatchin (normal) publiscationTime if there's a match between 
+        //       normal publicationTime and a copyrightPublicationTime
         matchDetection.features.bib.publicationTimeAllowConsYearsMulti(),
         matchDetection.features.bib.language(),
         matchDetection.features.bib.bibliographicLevel(),

package/dist/cli.js.map

@@ -1,7 +1,7 @@
 {
   "version": 3,
   "sources": ["../src/cli.js"],
-  "sourcesContent": ["import fs from 'fs';\nimport yargs from 'yargs';\nimport createMatchOperator, {candidateSearch, matchDetection} from './index.js';\nimport createDebugLogger from 'debug';\nimport {MarcRecord} from '@natlibfi/marc-record';\n\ncli();\n\n// eslint-disable-next-line max-lines-per-function\nasync function cli() {\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:cli');\n  const args = yargs(process.argv.slice(2))\n    .scriptName('melinda-record-matching-js')\n    .epilog('Copyright (C) 2022-2023 University Of Helsinki (The National Library Of Finland)')\n    .usage('$0 <file> [options] and env variable info in README')\n    .usage('Installed globally: $0 <file> [options] and env variable info in README')\n    .usage('Not installed: npx $0 <file> [options] and env variable info in README')\n    .usage('Build from source: node dist/index.js <file> [options] and env variable info in README')\n    .showHelpOnFail(true)\n    .example([['$ node /dist/cli.js record.json']])\n    .env('MELINDA_RECORD_MATCH')\n    .version()\n    .positional('file', {type: 'string', describe: 'Json file of records to match'})\n    .options({\n      t: {type: 'string', default: 'IDS', alias: 'searchType', describe: 'IDS, STANDARD_IDS, COMPONENT, CONTENT or CONTENTALT'},\n      m: {type: 'number', default: 1, alias: 'maxMatches', describe: ''},\n      c: {type: 'number', default: 1000, alias: 'maxCandidates', describe: ''},\n      s: {type: 'boolean', default: false, alias: 'returnStrategy', describe: ''},\n      q: {type: 'boolean', default: false, alias: 'returnQuery', describe: ''},\n      n: {type: 'boolean', default: false, alias: 'returnNonMatches', describe: ''}\n    })\n    .check((args) => {\n      const [file] = args._;\n      if (file === undefined) {\n        throw new Error('No file argument given');\n      }\n\n      if (!fs.existsSync(file)) {\n        throw new Error(`File ${file} does not exist`);\n      }\n\n      if (args.sruUrl === undefined) {\n        throw new Error('Setup sru url');\n      }\n\n      if (!['IDS', 'STANDARD_IDS', 'COMPONENT', 'CONTENT', 'CONTENTALT', 'YSO'].includes(args.searchType)) {\n        throw new Error('Invalid search type');\n      }\n\n      return true;\n    })\n    .parseSync();\n\n  const [file] = args._;\n  const {searchType} = args;\n  debug(JSON.stringify(args));\n\n  const detection = {\n    threshold: 0.8999,\n    strategy: generateStrategy(searchType)\n  };\n\n  const search = {\n    url: args.sruUrl, searchSpec: generateSearchSpec(searchType)\n  };\n\n  const matchOperator = await createMatchOperator({detection, search, ...args});\n\n  const fileRaw = fs.readFileSync(file, 'utf8');\n  const record = new MarcRecord(JSON.parse(fileRaw), {subfieldValues: false});\n\n  const result = await matchOperator({record});\n  debug(JSON.stringify(result));\n\n\n  function generateStrategy(searchType) {\n    if (['IDS'].includes(searchType)) {\n      return [\n        matchDetection.features.bib.melindaId(),\n        matchDetection.features.bib.allSourceIds(),\n        matchDetection.features.bib.f773() // Host data\n      ];\n    }\n\n    // We could have differing strategy for STANDARD_IDS\n    // Let's not run title in strategy when we found the candidates through standard_ids search\n\n    if (['STANDARD_IDS'].includes(searchType)) {\n      return [\n        matchDetection.features.bib.hostComponent(),\n        matchDetection.features.bib.isbn(),\n        matchDetection.features.bib.issn(),\n        matchDetection.features.bib.publisherNumber(),\n        // matchDetection.features.bib.sid(),\n        matchDetection.features.bib.otherStandardIdentifier(),\n        // Let's not use the same title matchDetection here\n        //matchDetection.features.bib.title(),\n        matchDetection.features.bib.authors(),\n        // We probably should have some leeway here for notated music as BK etc.\n        matchDetection.features.bib.recordType(),\n        // Use publicationTimeAllowConsYearsMulti to\n        //  - ignore one year differences in publicationTime\n        //  - extract publicationTimes from f008, f26x and reprint notes in f500\n        //  - do not substract points for mismatching (normal) publicationTime, if there's a match between\n        //       normal publicationTime and a reprintPublication time\n        matchDetection.features.bib.publicationTimeAllowConsYearsMulti(),\n        matchDetection.features.bib.language(),\n        matchDetection.features.bib.bibliographicLevel(),\n        matchDetection.features.bib.f773() // Host data\n      ];\n    }\n\n    if (['COMPONENT'].includes(searchType)) {\n      return [\n        matchDetection.features.bib.hostComponent(),\n        matchDetection.features.bib.otherStandardIdentifier(),\n        matchDetection.features.bib.recordType(),\n        matchDetection.features.bib.title(),\n        matchDetection.features.bib.language(),\n        matchDetection.features.bib.authors(),\n        matchDetection.features.bib.bibliographicLevel(),\n        matchDetection.features.bib.f773() // Host data\n      ];\n    }\n\n    if (['CONTENT', 'CONTENTALT'].includes(searchType)) {\n      return [\n        matchDetection.features.bib.hostComponent(),\n        matchDetection.features.bib.isbn(),\n        matchDetection.features.bib.issn(),\n        matchDetection.features.bib.publisherNumber(),\n        // matchDetection.features.bib.sid(),\n        matchDetection.features.bib.otherStandardIdentifier(),\n        matchDetection.features.bib.title(),\n        matchDetection.features.bib.authors(),\n        matchDetection.features.bib.recordType(),\n        matchDetection.features.bib.publicationTime(),\n        matchDetection.features.bib.language(),\n        matchDetection.features.bib.bibliographicLevel(),\n        matchDetection.features.bib.f773() // Host data\n      ];\n    }\n\n    if (['YSO']) {\n      return [\n        // matchDetection.features.bib.sid(), // SIDs might be relevant on the auth side as well?\n        matchDetection.features.auth.yso()\n      ];\n    }\n\n    throw new Error('Unsupported match validation package');\n  }\n\n\n  function generateSearchSpec(searchType) {\n    if (['IDS'].includes(searchType)) {\n      return [\n        candidateSearch.searchTypes.bib.melindaId,\n        candidateSearch.searchTypes.bib.sourceIds\n      ];\n    }\n\n    if (['STANDARD_IDS'].includes(searchType)) {\n      return [candidateSearch.searchTypes.bib.standardIdentifiers];\n    }\n\n    if (['COMPONENT'].includes(searchType)) {\n      return [\n        //candidateSearch.searchTypes.bib.sourceIds,\n        candidateSearch.searchTypes.component.hostIdMelinda,\n        candidateSearch.searchTypes.component.hostIdOtherSource\n      ];\n    }\n\n    if (['CONTENT'].includes(searchType)) {\n      return [\n        candidateSearch.searchTypes.bib.hostComponents,\n        //candidateSearch.searchTypes.bib.titleAuthor,\n        candidateSearch.searchTypes.bib.title\n      ];\n    }\n    if (['CONTENTALT'].includes(searchType)) {\n      return [\n        candidateSearch.searchTypes.bib.hostComponents,\n        // titleAuthorYearAlternates searches for matchCandidates\n        // with alternate queries, starting from more tight searches\n        candidateSearch.searchTypes.bib.titleAuthorYearAlternates\n      ];\n    }\n\n    if (searchType === 'YSO') {\n      return [\n        candidateSearch.searchTypes.auth.authURX\n      ];\n    }\n\n    throw new Error('Unsupported match validation package');\n  }\n}\n"],
-  "mappings": "AAAA,OAAO,QAAQ;AACf,OAAO,WAAW;AAClB,OAAO,uBAAsB,iBAAiB,sBAAqB;AACnE,OAAO,uBAAuB;AAC9B,SAAQ,kBAAiB;AAEzB,IAAI;AAGJ,eAAe,MAAM;AACnB,QAAM,QAAQ,kBAAkB,uCAAuC;AACvE,QAAM,OAAO,MAAM,QAAQ,KAAK,MAAM,CAAC,CAAC,EACrC,WAAW,4BAA4B,EACvC,OAAO,kFAAkF,EACzF,MAAM,qDAAqD,EAC3D,MAAM,yEAAyE,EAC/E,MAAM,wEAAwE,EAC9E,MAAM,wFAAwF,EAC9F,eAAe,IAAI,EACnB,QAAQ,CAAC,CAAC,iCAAiC,CAAC,CAAC,EAC7C,IAAI,sBAAsB,EAC1B,QAAQ,EACR,WAAW,QAAQ,EAAC,MAAM,UAAU,UAAU,gCAA+B,CAAC,EAC9E,QAAQ;AAAA,IACP,GAAG,EAAC,MAAM,UAAU,SAAS,OAAO,OAAO,cAAc,UAAU,sDAAqD;AAAA,IACxH,GAAG,EAAC,MAAM,UAAU,SAAS,GAAG,OAAO,cAAc,UAAU,GAAE;AAAA,IACjE,GAAG,EAAC,MAAM,UAAU,SAAS,KAAM,OAAO,iBAAiB,UAAU,GAAE;AAAA,IACvE,GAAG,EAAC,MAAM,WAAW,SAAS,OAAO,OAAO,kBAAkB,UAAU,GAAE;AAAA,IAC1E,GAAG,EAAC,MAAM,WAAW,SAAS,OAAO,OAAO,eAAe,UAAU,GAAE;AAAA,IACvE,GAAG,EAAC,MAAM,WAAW,SAAS,OAAO,OAAO,oBAAoB,UAAU,GAAE;AAAA,EAC9E,CAAC,EACA,MAAM,CAACA,UAAS;AACf,UAAM,CAACC,KAAI,IAAID,MAAK;AACpB,QAAIC,UAAS,QAAW;AACtB,YAAM,IAAI,MAAM,wBAAwB;AAAA,IAC1C;AAEA,QAAI,CAAC,GAAG,WAAWA,KAAI,GAAG;AACxB,YAAM,IAAI,MAAM,QAAQA,KAAI,iBAAiB;AAAA,IAC/C;AAEA,QAAID,MAAK,WAAW,QAAW;AAC7B,YAAM,IAAI,MAAM,eAAe;AAAA,IACjC;AAEA,QAAI,CAAC,CAAC,OAAO,gBAAgB,aAAa,WAAW,cAAc,KAAK,EAAE,SAASA,MAAK,UAAU,GAAG;AACnG,YAAM,IAAI,MAAM,qBAAqB;AAAA,IACvC;AAEA,WAAO;AAAA,EACT,CAAC,EACA,UAAU;AAEb,QAAM,CAAC,IAAI,IAAI,KAAK;AACpB,QAAM,EAAC,WAAU,IAAI;AACrB,QAAM,KAAK,UAAU,IAAI,CAAC;AAE1B,QAAM,YAAY;AAAA,IAChB,WAAW;AAAA,IACX,UAAU,iBAAiB,UAAU;AAAA,EACvC;AAEA,QAAM,SAAS;AAAA,IACb,KAAK,KAAK;AAAA,IAAQ,YAAY,mBAAmB,UAAU;AAAA,EAC7D;AAEA,QAAM,gBAAgB,MAAM,oBAAoB,EAAC,WAAW,QAAQ,GAAG,KAAI,CAAC;AAE5E,QAAM,UAAU,GAAG,aAAa,MAAM,MAAM;AAC5C,QAAM,SAAS,IAAI,WAAW,KAAK,MAAM,OAAO,GAAG,EAAC,gBAAgB,MAAK,CAAC;AAE1E,QAAM,SAAS,MAAM,cAAc,EAAC,OAAM,CAAC;AAC3C,QAAM,KAAK,UAAU,MAAM,CAAC;AAG5B,WAAS,iBAAiBE,aAAY;AACpC,QAAI,CAAC,KAAK,EAAE,SAASA,WAAU,GAAG;AAChC,aAAO;AAAA,QACL,eAAe,SAAS,IAAI,UAAU;AAAA,QACtC,eAAe,SAAS,IAAI,aAAa;AAAA,QACzC,eAAe,SAAS,IAAI,KAAK;AAAA;AAAA,MACnC;AAAA,IACF;AAKA,QAAI,CAAC,cAAc,EAAE,SAASA,WAAU,GAAG;AACzC,aAAO;AAAA,QACL,eAAe,SAAS,IAAI,cAAc;AAAA,QAC1C,eAAe,SAAS,IAAI,KAAK;AAAA,QACjC,eAAe,SAAS,IAAI,KAAK;AAAA,QACjC,eAAe,SAAS,IAAI,gBAAgB;AAAA;AAAA,QAE5C,eAAe,SAAS,IAAI,wBAAwB;AAAA;AAAA;AAAA,QAGpD,eAAe,SAAS,IAAI,QAAQ;AAAA;AAAA,QAEpC,eAAe,SAAS,IAAI,WAAW;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,QAMvC,eAAe,SAAS,IAAI,mCAAmC;AAAA,QAC/D,eAAe,SAAS,IAAI,SAAS;AAAA,QACrC,eAAe,SAAS,IAAI,mBAAmB;AAAA,QAC/C,eAAe,SAAS,IAAI,KAAK;AAAA;AAAA,MACnC;AAAA,IACF;AAEA,QAAI,CAAC,WAAW,EAAE,SAASA,WAAU,GAAG;AACtC,aAAO;AAAA,QACL,eAAe,SAAS,IAAI,cAAc;AAAA,QAC1C,eAAe,SAAS,IAAI,wBAAwB;AAAA,QACpD,eAAe,SAAS,IAAI,WAAW;AAAA,QACvC,eAAe,SAAS,IAAI,MAAM;AAAA,QAClC,eAAe,SAAS,IAAI,SAAS;AAAA,QACrC,eAAe,SAAS,IAAI,QAAQ;AAAA,QACpC,eAAe,SAAS,IAAI,mBAAmB;AAAA,QAC/C,eAAe,SAAS,IAAI,KAAK;AAAA;AAAA,MACnC;AAAA,IACF;AAEA,QAAI,CAAC,WAAW,YAAY,EAAE,SAASA,WAAU,GAAG;AAClD,aAAO;AAAA,QACL,eAAe,SAAS,IAAI,cAAc;AAAA,QAC1C,eAAe,SAAS,IAAI,KAAK;AAAA,QACjC,eAAe,SAAS,IAAI,KAAK;AAAA,QACjC,eAAe,SAAS,IAAI,gBAAgB;AAAA;AAAA,QAE5C,eAAe,SAAS,IAAI,wBAAwB;AAAA,QACpD,eAAe,SAAS,IAAI,MAAM;AAAA,QAClC,eAAe,SAAS,IAAI,QAAQ;AAAA,QACpC,eAAe,SAAS,IAAI,WAAW;AAAA,QACvC,eAAe,SAAS,IAAI,gBAAgB;AAAA,QAC5C,eAAe,SAAS,IAAI,SAAS;AAAA,QACrC,eAAe,SAAS,IAAI,mBAAmB;AAAA,QAC/C,eAAe,SAAS,IAAI,KAAK;AAAA;AAAA,MACnC;AAAA,IACF;AAEA,QAAI,CAAC,KAAK,GAAG;AACX,aAAO;AAAA;AAAA,QAEL,eAAe,SAAS,KAAK,IAAI;AAAA,MACnC;AAAA,IACF;AAEA,UAAM,IAAI,MAAM,sCAAsC;AAAA,EACxD;AAGA,WAAS,mBAAmBA,aAAY;AACtC,QAAI,CAAC,KAAK,EAAE,SAASA,WAAU,GAAG;AAChC,aAAO;AAAA,QACL,gBAAgB,YAAY,IAAI;AAAA,QAChC,gBAAgB,YAAY,IAAI;AAAA,MAClC;AAAA,IACF;AAEA,QAAI,CAAC,cAAc,EAAE,SAASA,WAAU,GAAG;AACzC,aAAO,CAAC,gBAAgB,YAAY,IAAI,mBAAmB;AAAA,IAC7D;AAEA,QAAI,CAAC,WAAW,EAAE,SAASA,WAAU,GAAG;AACtC,aAAO;AAAA;AAAA,QAEL,gBAAgB,YAAY,UAAU;AAAA,QACtC,gBAAgB,YAAY,UAAU;AAAA,MACxC;AAAA,IACF;AAEA,QAAI,CAAC,SAAS,EAAE,SAASA,WAAU,GAAG;AACpC,aAAO;AAAA,QACL,gBAAgB,YAAY,IAAI;AAAA;AAAA,QAEhC,gBAAgB,YAAY,IAAI;AAAA,MAClC;AAAA,IACF;AACA,QAAI,CAAC,YAAY,EAAE,SAASA,WAAU,GAAG;AACvC,aAAO;AAAA,QACL,gBAAgB,YAAY,IAAI;AAAA;AAAA;AAAA,QAGhC,gBAAgB,YAAY,IAAI;AAAA,MAClC;AAAA,IACF;AAEA,QAAIA,gBAAe,OAAO;AACxB,aAAO;AAAA,QACL,gBAAgB,YAAY,KAAK;AAAA,MACnC;AAAA,IACF;AAEA,UAAM,IAAI,MAAM,sCAAsC;AAAA,EACxD;AACF;",
+  "sourcesContent": ["import fs from 'fs';\nimport yargs from 'yargs';\nimport createMatchOperator, {candidateSearch, matchDetection} from './index.js';\nimport createDebugLogger from 'debug';\nimport {MarcRecord} from '@natlibfi/marc-record';\nimport {uniqArray} from '@natlibfi/marc-record-validators-melinda/dist/utils.js';\n\ncli();\n\n// eslint-disable-next-line max-lines-per-function\nasync function cli() {\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:cli');\n  const args = yargs(process.argv.slice(2))\n    .scriptName('melinda-record-matching-js')\n    .epilog('Copyright (C) 2022-2023 University Of Helsinki (The National Library Of Finland)')\n    .usage('$0 <file> [options] and env variable info in README')\n    .usage('Installed globally: $0 <file> [options] and env variable info in README')\n    .usage('Not installed: npx $0 <file> [options] and env variable info in README')\n    .usage('Build from source: node dist/index.js <file> [options] and env variable info in README')\n    .showHelpOnFail(true)\n    .example([['$ node /dist/cli.js record.json']])\n    .env('MELINDA_RECORD_MATCH')\n    .version()\n    .positional('file', {type: 'string', describe: 'Json file of records to match'})\n    .options({\n      t: {type: 'string', default: 'IDS', alias: 'searchType', describe: 'IDS, STANDARD_IDS, COMPONENT, CONTENT or CONTENTALT'},\n      m: {type: 'number', default: 1, alias: 'maxMatches', describe: ''},\n      c: {type: 'number', default: 1000, alias: 'maxCandidates', describe: ''},\n      s: {type: 'boolean', default: false, alias: 'returnStrategy', describe: ''},\n      q: {type: 'boolean', default: false, alias: 'returnQuery', describe: ''},\n      n: {type: 'boolean', default: false, alias: 'returnNonMatches', describe: ''}\n    })\n    .check((args) => {\n      const [file] = args._;\n      if (file === undefined) {\n        throw new Error('No file argument given');\n      }\n\n      if (!fs.existsSync(file)) {\n        throw new Error(`File ${file} does not exist`);\n      }\n\n      if (args.sruUrl === undefined) {\n        throw new Error('Setup sru url');\n      }\n\n      if (!['IDS', 'STANDARD_IDS', 'COMPONENT', 'CONTENT', 'CONTENTALT', 'YSO'].includes(args.searchType)) {\n        throw new Error('Invalid search type');\n      }\n\n      return true;\n    })\n    .parseSync();\n\n  const [file] = args._;\n  const {searchType} = args;\n  debug(JSON.stringify(args));\n\n  const detection = {\n    threshold: 0.8999,\n    strategy: generateStrategy(searchType)\n  };\n\n  const search = {\n    url: args.sruUrl, searchSpec: generateSearchSpec(searchType)\n  };\n\n  const matchOperator = await createMatchOperator({detection, search, ...args});\n\n  const fileRaw = fs.readFileSync(file, 'utf8');\n  const record = new MarcRecord(JSON.parse(fileRaw), {subfieldValues: false});\n\n  const result = await matchOperator({record});\n  const matchCount = result.matches.length;\n  const matchIds = result.matches.map(matchA => matchA.candidate.id);\n  const nonMatchCount = result.nonMatches?.length || result.nonMatchCount;\n  const nonMatchIds = result.nonMatches?.map(matchA => matchA.candidate.id) || [];\n  const uniqueNonMatchIds = uniqArray(nonMatchIds);\n  const uniqueNonMatchCount = uniqueNonMatchIds.length;\n  const candidateCount = result.candidateCount;\n\n  debug(`Matches (${matchCount}) ${JSON.stringify(matchIds)}`);\n  debug(`NonMatches (${nonMatchCount}) ${JSON.stringify(nonMatchIds)}`);\n  debug(`Unique nonMatches (${uniqueNonMatchCount}) ${JSON.stringify(uniqueNonMatchIds)}`);\n  debug(`Candidates (${candidateCount})`);\n\n  debug(JSON.stringify(result));\n\n  // DEVELOP: print results to output file\n\n  function generateStrategy(searchType) {\n    if (['IDS'].includes(searchType)) {\n      return [\n        matchDetection.features.bib.melindaId(),\n        matchDetection.features.bib.allSourceIds(),\n        matchDetection.features.bib.f773() // Host data\n      ];\n    }\n\n    // We could have differing strategy for STANDARD_IDS\n    // Let's not run title in strategy when we found the candidates through standard_ids search\n\n    if (['STANDARD_IDS'].includes(searchType)) {\n      return [\n        matchDetection.features.bib.hostComponent(),\n        matchDetection.features.bib.isbn(),\n        matchDetection.features.bib.issn(),\n        matchDetection.features.bib.publisherNumber(),\n        // matchDetection.features.bib.sid(),\n        matchDetection.features.bib.otherStandardIdentifier(),\n        // Let's not use the same title matchDetection here\n        //matchDetection.features.bib.title(),\n        matchDetection.features.bib.authors(),\n        // We probably should have some leeway here for notated music as BK etc.\n        matchDetection.features.bib.recordType(),\n        // Use publicationTimeAllowConsYearsMulti to\n        //  - ignore one year differences in publicationTime\n        //  - extract publicationTimes from f008, f26x and reprint notes in f500\n        //  - do not substract points for mismatching (normal) publicationTime, if there's a match between\n        //       normal publicationTime and a reprintPublicationTime\n        //  - do not subract points for mismatchin (normal) publiscationTime if there's a match between \n        //       normal publicationTime and a copyrightPublicationTime\n        matchDetection.features.bib.publicationTimeAllowConsYearsMulti(),\n        matchDetection.features.bib.language(),\n        matchDetection.features.bib.bibliographicLevel(),\n        matchDetection.features.bib.f773() // Host data\n      ];\n    }\n\n    if (['COMPONENT'].includes(searchType)) {\n      return [\n        matchDetection.features.bib.hostComponent(),\n        matchDetection.features.bib.otherStandardIdentifier(),\n        matchDetection.features.bib.recordType(),\n        matchDetection.features.bib.title(),\n        matchDetection.features.bib.language(),\n        matchDetection.features.bib.authors(),\n        matchDetection.features.bib.bibliographicLevel(),\n        matchDetection.features.bib.f773() // Host data\n      ];\n    }\n\n    if (['CONTENT', 'CONTENTALT'].includes(searchType)) {\n      return [\n        matchDetection.features.bib.hostComponent(),\n        matchDetection.features.bib.isbn(),\n        matchDetection.features.bib.issn(),\n        matchDetection.features.bib.publisherNumber(),\n        // matchDetection.features.bib.sid(),\n        matchDetection.features.bib.otherStandardIdentifier(),\n        matchDetection.features.bib.title(),\n        matchDetection.features.bib.authors(),\n        matchDetection.features.bib.recordType(),\n        matchDetection.features.bib.publicationTime(),\n        matchDetection.features.bib.language(),\n        matchDetection.features.bib.bibliographicLevel(),\n        matchDetection.features.bib.f773() // Host data\n      ];\n    }\n\n    if (['YSO']) {\n      return [\n        // matchDetection.features.bib.sid(), // SIDs might be relevant on the auth side as well?\n        matchDetection.features.auth.yso()\n      ];\n    }\n\n    throw new Error('Unsupported match validation package');\n  }\n\n\n  function generateSearchSpec(searchType) {\n    if (['IDS'].includes(searchType)) {\n      return [\n        candidateSearch.searchTypes.bib.melindaId,\n        candidateSearch.searchTypes.bib.sourceIds\n      ];\n    }\n\n    if (['STANDARD_IDS'].includes(searchType)) {\n      return [candidateSearch.searchTypes.bib.standardIdentifiers];\n    }\n\n    if (['COMPONENT'].includes(searchType)) {\n      return [\n        //candidateSearch.searchTypes.bib.sourceIds,\n        candidateSearch.searchTypes.component.hostIdMelinda,\n        candidateSearch.searchTypes.component.hostIdOtherSource\n      ];\n    }\n\n    if (['CONTENT'].includes(searchType)) {\n      return [\n        candidateSearch.searchTypes.bib.hostComponents,\n        //candidateSearch.searchTypes.bib.titleAuthor,\n        candidateSearch.searchTypes.bib.title\n      ];\n    }\n    if (['CONTENTALT'].includes(searchType)) {\n      return [\n        candidateSearch.searchTypes.bib.hostComponents,\n        // titleAuthorYearAlternates searches for matchCandidates\n        // with alternate queries, starting from more tight searches\n        candidateSearch.searchTypes.bib.titleAuthorYearAlternates\n      ];\n    }\n\n    if (searchType === 'YSO') {\n      return [\n        candidateSearch.searchTypes.auth.authURX\n      ];\n    }\n\n    throw new Error('Unsupported match validation package');\n  }\n}\n"],
+  "mappings": "AAAA,OAAO,QAAQ;AACf,OAAO,WAAW;AAClB,OAAO,uBAAsB,iBAAiB,sBAAqB;AACnE,OAAO,uBAAuB;AAC9B,SAAQ,kBAAiB;AACzB,SAAQ,iBAAgB;AAExB,IAAI;AAGJ,eAAe,MAAM;AACnB,QAAM,QAAQ,kBAAkB,uCAAuC;AACvE,QAAM,OAAO,MAAM,QAAQ,KAAK,MAAM,CAAC,CAAC,EACrC,WAAW,4BAA4B,EACvC,OAAO,kFAAkF,EACzF,MAAM,qDAAqD,EAC3D,MAAM,yEAAyE,EAC/E,MAAM,wEAAwE,EAC9E,MAAM,wFAAwF,EAC9F,eAAe,IAAI,EACnB,QAAQ,CAAC,CAAC,iCAAiC,CAAC,CAAC,EAC7C,IAAI,sBAAsB,EAC1B,QAAQ,EACR,WAAW,QAAQ,EAAC,MAAM,UAAU,UAAU,gCAA+B,CAAC,EAC9E,QAAQ;AAAA,IACP,GAAG,EAAC,MAAM,UAAU,SAAS,OAAO,OAAO,cAAc,UAAU,sDAAqD;AAAA,IACxH,GAAG,EAAC,MAAM,UAAU,SAAS,GAAG,OAAO,cAAc,UAAU,GAAE;AAAA,IACjE,GAAG,EAAC,MAAM,UAAU,SAAS,KAAM,OAAO,iBAAiB,UAAU,GAAE;AAAA,IACvE,GAAG,EAAC,MAAM,WAAW,SAAS,OAAO,OAAO,kBAAkB,UAAU,GAAE;AAAA,IAC1E,GAAG,EAAC,MAAM,WAAW,SAAS,OAAO,OAAO,eAAe,UAAU,GAAE;AAAA,IACvE,GAAG,EAAC,MAAM,WAAW,SAAS,OAAO,OAAO,oBAAoB,UAAU,GAAE;AAAA,EAC9E,CAAC,EACA,MAAM,CAACA,UAAS;AACf,UAAM,CAACC,KAAI,IAAID,MAAK;AACpB,QAAIC,UAAS,QAAW;AACtB,YAAM,IAAI,MAAM,wBAAwB;AAAA,IAC1C;AAEA,QAAI,CAAC,GAAG,WAAWA,KAAI,GAAG;AACxB,YAAM,IAAI,MAAM,QAAQA,KAAI,iBAAiB;AAAA,IAC/C;AAEA,QAAID,MAAK,WAAW,QAAW;AAC7B,YAAM,IAAI,MAAM,eAAe;AAAA,IACjC;AAEA,QAAI,CAAC,CAAC,OAAO,gBAAgB,aAAa,WAAW,cAAc,KAAK,EAAE,SAASA,MAAK,UAAU,GAAG;AACnG,YAAM,IAAI,MAAM,qBAAqB;AAAA,IACvC;AAEA,WAAO;AAAA,EACT,CAAC,EACA,UAAU;AAEb,QAAM,CAAC,IAAI,IAAI,KAAK;AACpB,QAAM,EAAC,WAAU,IAAI;AACrB,QAAM,KAAK,UAAU,IAAI,CAAC;AAE1B,QAAM,YAAY;AAAA,IAChB,WAAW;AAAA,IACX,UAAU,iBAAiB,UAAU;AAAA,EACvC;AAEA,QAAM,SAAS;AAAA,IACb,KAAK,KAAK;AAAA,IAAQ,YAAY,mBAAmB,UAAU;AAAA,EAC7D;AAEA,QAAM,gBAAgB,MAAM,oBAAoB,EAAC,WAAW,QAAQ,GAAG,KAAI,CAAC;AAE5E,QAAM,UAAU,GAAG,aAAa,MAAM,MAAM;AAC5C,QAAM,SAAS,IAAI,WAAW,KAAK,MAAM,OAAO,GAAG,EAAC,gBAAgB,MAAK,CAAC;AAE1E,QAAM,SAAS,MAAM,cAAc,EAAC,OAAM,CAAC;AAC3C,QAAM,aAAa,OAAO,QAAQ;AAClC,QAAM,WAAW,OAAO,QAAQ,IAAI,YAAU,OAAO,UAAU,EAAE;AACjE,QAAM,gBAAgB,OAAO,YAAY,UAAU,OAAO;AAC1D,QAAM,cAAc,OAAO,YAAY,IAAI,YAAU,OAAO,UAAU,EAAE,KAAK,CAAC;AAC9E,QAAM,oBAAoB,UAAU,WAAW;AAC/C,QAAM,sBAAsB,kBAAkB;AAC9C,QAAM,iBAAiB,OAAO;AAE9B,QAAM,YAAY,UAAU,KAAK,KAAK,UAAU,QAAQ,CAAC,EAAE;AAC3D,QAAM,eAAe,aAAa,KAAK,KAAK,UAAU,WAAW,CAAC,EAAE;AACpE,QAAM,sBAAsB,mBAAmB,KAAK,KAAK,UAAU,iBAAiB,CAAC,EAAE;AACvF,QAAM,eAAe,cAAc,GAAG;AAEtC,QAAM,KAAK,UAAU,MAAM,CAAC;AAI5B,WAAS,iBAAiBE,aAAY;AACpC,QAAI,CAAC,KAAK,EAAE,SAASA,WAAU,GAAG;AAChC,aAAO;AAAA,QACL,eAAe,SAAS,IAAI,UAAU;AAAA,QACtC,eAAe,SAAS,IAAI,aAAa;AAAA,QACzC,eAAe,SAAS,IAAI,KAAK;AAAA;AAAA,MACnC;AAAA,IACF;AAKA,QAAI,CAAC,cAAc,EAAE,SAASA,WAAU,GAAG;AACzC,aAAO;AAAA,QACL,eAAe,SAAS,IAAI,cAAc;AAAA,QAC1C,eAAe,SAAS,IAAI,KAAK;AAAA,QACjC,eAAe,SAAS,IAAI,KAAK;AAAA,QACjC,eAAe,SAAS,IAAI,gBAAgB;AAAA;AAAA,QAE5C,eAAe,SAAS,IAAI,wBAAwB;AAAA;AAAA;AAAA,QAGpD,eAAe,SAAS,IAAI,QAAQ;AAAA;AAAA,QAEpC,eAAe,SAAS,IAAI,WAAW;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,QAQvC,eAAe,SAAS,IAAI,mCAAmC;AAAA,QAC/D,eAAe,SAAS,IAAI,SAAS;AAAA,QACrC,eAAe,SAAS,IAAI,mBAAmB;AAAA,QAC/C,eAAe,SAAS,IAAI,KAAK;AAAA;AAAA,MACnC;AAAA,IACF;AAEA,QAAI,CAAC,WAAW,EAAE,SAASA,WAAU,GAAG;AACtC,aAAO;AAAA,QACL,eAAe,SAAS,IAAI,cAAc;AAAA,QAC1C,eAAe,SAAS,IAAI,wBAAwB;AAAA,QACpD,eAAe,SAAS,IAAI,WAAW;AAAA,QACvC,eAAe,SAAS,IAAI,MAAM;AAAA,QAClC,eAAe,SAAS,IAAI,SAAS;AAAA,QACrC,eAAe,SAAS,IAAI,QAAQ;AAAA,QACpC,eAAe,SAAS,IAAI,mBAAmB;AAAA,QAC/C,eAAe,SAAS,IAAI,KAAK;AAAA;AAAA,MACnC;AAAA,IACF;AAEA,QAAI,CAAC,WAAW,YAAY,EAAE,SAASA,WAAU,GAAG;AAClD,aAAO;AAAA,QACL,eAAe,SAAS,IAAI,cAAc;AAAA,QAC1C,eAAe,SAAS,IAAI,KAAK;AAAA,QACjC,eAAe,SAAS,IAAI,KAAK;AAAA,QACjC,eAAe,SAAS,IAAI,gBAAgB;AAAA;AAAA,QAE5C,eAAe,SAAS,IAAI,wBAAwB;AAAA,QACpD,eAAe,SAAS,IAAI,MAAM;AAAA,QAClC,eAAe,SAAS,IAAI,QAAQ;AAAA,QACpC,eAAe,SAAS,IAAI,WAAW;AAAA,QACvC,eAAe,SAAS,IAAI,gBAAgB;AAAA,QAC5C,eAAe,SAAS,IAAI,SAAS;AAAA,QACrC,eAAe,SAAS,IAAI,mBAAmB;AAAA,QAC/C,eAAe,SAAS,IAAI,KAAK;AAAA;AAAA,MACnC;AAAA,IACF;AAEA,QAAI,CAAC,KAAK,GAAG;AACX,aAAO;AAAA;AAAA,QAEL,eAAe,SAAS,KAAK,IAAI;AAAA,MACnC;AAAA,IACF;AAEA,UAAM,IAAI,MAAM,sCAAsC;AAAA,EACxD;AAGA,WAAS,mBAAmBA,aAAY;AACtC,QAAI,CAAC,KAAK,EAAE,SAASA,WAAU,GAAG;AAChC,aAAO;AAAA,QACL,gBAAgB,YAAY,IAAI;AAAA,QAChC,gBAAgB,YAAY,IAAI;AAAA,MAClC;AAAA,IACF;AAEA,QAAI,CAAC,cAAc,EAAE,SAASA,WAAU,GAAG;AACzC,aAAO,CAAC,gBAAgB,YAAY,IAAI,mBAAmB;AAAA,IAC7D;AAEA,QAAI,CAAC,WAAW,EAAE,SAASA,WAAU,GAAG;AACtC,aAAO;AAAA;AAAA,QAEL,gBAAgB,YAAY,UAAU;AAAA,QACtC,gBAAgB,YAAY,UAAU;AAAA,MACxC;AAAA,IACF;AAEA,QAAI,CAAC,SAAS,EAAE,SAASA,WAAU,GAAG;AACpC,aAAO;AAAA,QACL,gBAAgB,YAAY,IAAI;AAAA;AAAA,QAEhC,gBAAgB,YAAY,IAAI;AAAA,MAClC;AAAA,IACF;AACA,QAAI,CAAC,YAAY,EAAE,SAASA,WAAU,GAAG;AACvC,aAAO;AAAA,QACL,gBAAgB,YAAY,IAAI;AAAA;AAAA;AAAA,QAGhC,gBAAgB,YAAY,IAAI;AAAA,MAClC;AAAA,IACF;AAEA,QAAIA,gBAAe,OAAO;AACxB,aAAO;AAAA,QACL,gBAAgB,YAAY,KAAK;AAAA,MACnC;AAAA,IACF;AAEA,UAAM,IAAI,MAAM,sCAAsC;AAAA,EACxD;AACF;",
   "names": ["args", "file", "searchType"]
 }

package/dist/index.js

@@ -5,6 +5,7 @@ export { candidateSearch, matchDetection };
 export default ({ detection: detectionOptions, search: searchOptions, maxMatches = 1, maxCandidates = 25, returnStrategy = false, returnQuery = false, returnNonMatches = false }) => {
   const debug = createDebugLogger("@natlibfi/melinda-record-matching:index");
   const debugData = debug.extend("data");
+  const debugDev = debug.extend("dev");
   debugData(`DetectionOptions: ${JSON.stringify(detectionOptions)}`);
   debugData(`SearchOptions: ${JSON.stringify(searchOptions)}`);
   debugData(`MaxMatches: ${JSON.stringify(maxMatches)}`);
@@ -20,7 +21,7 @@ export default ({ detection: detectionOptions, search: searchOptions, maxMatches
     async function iterate({ initialState = {}, matches = [], candidateCount = 0, nonMatches = [], duplicateCount = 0, nonMatchCount = 0, matchErrors = [] }) {
       debugData(`Starting next matcher iteration.`);
       const { records, ...state } = await search(initialState);
-      debugData(`Current state: ${JSON.stringify(state)}, matches: ${matches.length}, candidateCount: ${candidateCount}, nonMatches: ${nonMatches.length}, nonMatchCount: ${nonMatchCount}, matchErrors: ${matchErrors.length}`);
+      debugDev(`Current state: ${JSON.stringify(state)}, matches: ${matches.length}, candidateCount: ${candidateCount}, nonMatches: ${nonMatches.length}, duplicateCount: ${duplicateCount}, nonMatchCount: ${nonMatchCount}, matchErrors: ${matchErrors.length}`);
       const recordSetSize = records.length;
       const newCandidateCount = candidateCount + recordSetSize;
       if (recordSetSize > 0) {
@@ -34,7 +35,7 @@ export default ({ detection: detectionOptions, search: searchOptions, maxMatches
       return returnResult({ matches, state, stopReason: "", nonMatches, nonMatchCount, candidateCount: newCandidateCount, duplicateCount, matchErrors });
       function handleRecordSet() {
         debug(`Checking record set of ${recordSetSize} candidate records for possible matches, found by ${state.searchCounter} search for ${state.query}`);
-        const matchResult = iterateRecords({ records, recordSetSize, maxMatches, matches, nonMatches, nonMatchCount });
+        const matchResult = iterateRecords({ records, recordSetSize, maxMatches, matches, nonMatches, nonMatchCount, duplicateCount });
         const newDuplicateCount = duplicateCount + matchResult.duplicateCount;
         const newNonMatchCount = nonMatchCount + matchResult.nonMatchCount;
         const { newMatches, newNonMatches, newMatchErrors } = handleMatchResult(matchResult, matches, nonMatches, matchErrors);
@@ -122,8 +123,9 @@ export default ({ detection: detectionOptions, search: searchOptions, maxMatches
       const [candidate] = records;
       const newRecordCount = candidate ? recordCount + 1 : recordCount;
       if (candidate) {
-        if (candidateNotInMatches(matches.concat(nonMatches), candidate)) {
-          const { record: candidateRecord, id: candidateId } = candidate;
+        const { record: candidateRecord, id: candidateId } = candidate;
+        const allMatches = matches.concat(nonMatches);
+        if (candidateNotInMatches(allMatches, candidate)) {
           const recordBExternal = { id: candidate.id, recordSource: "databaseRecord", label: `db-${candidate.id}` };
           try {
             debug(`Running matchDetection for record ${candidateId} (${newRecordCount}/${recordSetSize})`);
@@ -136,7 +138,9 @@ export default ({ detection: detectionOptions, search: searchOptions, maxMatches
             return iterateRecords({ records: records.slice(1), recordSetSize, maxMatches: maxMatches2, matches, recordMatches, recordCount: newRecordCount, recordNonMatches, recordDuplicateCount, recordNonMatchCount, recordMatchErrors: newRecordMatchErrors });
           }
         }
-        return iterateRecords({ records: records.slice(1), recordSetSize, maxMatches: maxMatches2, matches, recordMatches, recordCount: newRecordCount, recordNonMatches, recordDuplicateCount: recordDuplicateCount + 1, recordNonMatchCount, recordMatchErrors });
+        debug(`Matching for ${candidateId} already done (${recordDuplicateCount} before)`);
+        const newRecordDuplicateCount = recordDuplicateCount + 1;
+        return iterateRecords({ records: records.slice(1), recordSetSize, maxMatches: maxMatches2, matches, recordMatches, recordCount: newRecordCount, recordNonMatches, recordDuplicateCount: newRecordDuplicateCount, recordNonMatchCount, recordMatchErrors });
       }
       debug(`No more candidates, record set (${recordCount}/${recordSetSize}) done, ${recordMatches.length} matches found, ${recordDuplicateCount} candidates already handled, ${returnNonMatches ? `${recordNonMatches.length}` : `${recordNonMatchCount}`} nonMatches found.`);
       return { matches: recordMatches, nonMatches: returnNonMatches ? recordNonMatches : [], duplicateCount: recordDuplicateCount, nonMatchCount: recordNonMatchCount, matchErrors: recordMatchErrors };
@@ -168,28 +172,27 @@ export default ({ detection: detectionOptions, search: searchOptions, maxMatches
         const newRecordMatches = isMatch ? recordMatches.concat(newMatch) : recordMatches;
         const newRecordNonMatches = isMatch ? recordNonMatches : recordNonMatches.concat(newMatch);
         const newRecordNonMatchCount = isMatch ? recordNonMatchCount : recordNonMatchCount + 1;
-        debugData(`- Total matches after this detection: ${matches.concat(newRecordMatches).length} (max: ${maxMatches2})`);
+        debugDev(`- Total matches after this detection: ${matches.concat(newRecordMatches).length} (max: ${maxMatches2})`);
         if (returnNonMatches) {
-          debugData(`- Total nonMatches after this detection: ${nonMatches.concat(newRecordNonMatches).length}`);
+          debugDev(`- Total nonMatches after this detection: ${nonMatches.concat(newRecordNonMatches).length}`);
         }
-        debugData(`- Total nonMatchCount after this detection: ${recordNonMatchCount}`);
+        debugDev(`- Total nonMatchCount after this detection: ${recordNonMatchCount}`);
         if (maxMatchesFound({ matches: matches.concat(newRecordMatches), maxMatches: maxMatches2 })) {
           debug(`MaxMatches (${maxMatches2}) reached, handled candidates in record set: ${newRecordCount} non-handled candidates in record set ${recordSetSize - newRecordCount}`);
           return { matches: newRecordMatches, nonMatches: returnNonMatches ? newRecordNonMatches : [], duplicateCount: recordDuplicateCount, nonMatchCount: newRecordNonMatchCount, matchErrors: recordMatchErrors };
         }
-        return iterateRecords({ records: records.slice(1), recordSetSize, maxMatches: maxMatches2, matches, recordMatches: newRecordMatches, recordCount: newRecordCount, recordNonMatches: returnNonMatches ? newRecordNonMatches : [], duplicateCount: recordDuplicateCount, recordNonMatchCount: newRecordNonMatchCount, matchErrors: recordMatchErrors });
+        return iterateRecords({ records: records.slice(1), recordSetSize, maxMatches: maxMatches2, matches, recordMatches: newRecordMatches, recordCount: newRecordCount, recordNonMatches: returnNonMatches ? newRecordNonMatches : [], recordDuplicateCount, recordNonMatchCount: newRecordNonMatchCount, matchErrors: recordMatchErrors });
       }
-      function candidateNotInMatches(matches2, candidate2) {
-        debug(`Checking that record ${candidate2.id} is not already included in ${matches2.length} matches/nonMatches`);
+      function candidateNotInMatches(allMatches, candidate2) {
+        debug(`Checking that record ${candidate2.id} is not already included in ${allMatches.length} matches/nonMatches`);
         const newCandidateId = candidate2.id;
-        debugData(`newCandidateId: ${newCandidateId}`);
-        const result = matches2.find(({ candidate: candidate3 }) => candidate3.id === newCandidateId);
-        debugData(`Result: ${result}`);
+        debugData(`-- newCandidateId: ${newCandidateId}`);
+        const result = allMatches.find(({ candidate: candidate3 }) => candidate3.id === newCandidateId);
         if (result) {
-          debug(`${candidate2.id} was already handled.`);
+          debug(`-- ${newCandidateId} was already handled.`);
           return false;
         }
-        debug(`${candidate2.id} not found in matches/nonMatches`);
+        debugDev(`-- ${newCandidateId} not found in ${allMatches.length} matches/nonMatches`);
         return true;
       }
     }

package/dist/index.js.map

@@ -1,7 +1,7 @@
 {
   "version": 3,
   "sources": ["../src/index.js"],
-  "sourcesContent": ["import createDebugLogger from 'debug';\nimport createSearchInterface, * as candidateSearch from './candidate-search/index.js';\nimport createDetectionInterface, * as matchDetection from './match-detection/index.js';\n//import inspect from 'util';\n\nexport {candidateSearch, matchDetection};\n\nexport default ({detection: detectionOptions, search: searchOptions, maxMatches = 1, maxCandidates = 25, returnStrategy = false, returnQuery = false, returnNonMatches = false}) => {\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:index');\n  const debugData = debug.extend('data');\n\n  debugData(`DetectionOptions: ${JSON.stringify(detectionOptions)}`);\n  debugData(`SearchOptions: ${JSON.stringify(searchOptions)}`);\n  debugData(`MaxMatches: ${JSON.stringify(maxMatches)}`);\n  debugData(`MaxCandidates: ${JSON.stringify(maxCandidates)}`);\n  debugData(`ReturnStrategy: ${JSON.stringify(returnStrategy)}`);\n  debugData(`ReturnQuery: ${JSON.stringify(returnQuery)}`);\n  debugData(`ReturnNonMatches: ${JSON.stringify(returnNonMatches)}`);\n\n\n  const detect = createDetectionInterface(detectionOptions, returnStrategy);\n\n  return prepareSearch;\n\n  async function prepareSearch({record, recordExternal = {recordSource: 'incomingRecord', label: 'ic'}}) {\n\n    const {search} = await createSearchInterface({...searchOptions, record, maxCandidates, recordExternal});\n    return iterate({});\n\n    // candidateCount : amount of candidate records retrived from SRU for matching, NOT including current record set\n    // matches : candidates that have been detected as matches by current matcher job\n    // nonMatches : candidates that have been detected as non-matches by current matcher job (only if returnNonMatches is 'true')\n    // duplicateCount : amount of candidate records that were retrieved from the SRU but not handled further because they were already found in the matches/nonMatches\n\n    // state.totalRecords : amount of candidate records available to the current query (undefined, if there was no queries left)\n    // state.query : current query (undefined if there was no queries left)\n    // state.searchCounter : sequence for current search for current query (undefined, if there we no queries left)\n    // state.queryCandidateCounter: amount of candidate records retrieved from SRU for matching for current query, including the current record set (undefined if there were no queries left)\n    // state.queriesLeft : amount of queries left\n    // state.queryCounter : sequence for current query\n    // state.maxedQueries : queries that resulted in more than serverMaxResults hits\n\n    async function iterate({initialState = {}, matches = [], candidateCount = 0, nonMatches = [], duplicateCount = 0, nonMatchCount = 0, matchErrors = []}) {\n      debugData(`Starting next matcher iteration.`);\n      const {records, ...state} = await search(initialState);\n\n      debugData(`Current state: ${JSON.stringify(state)}, matches: ${matches.length}, candidateCount: ${candidateCount}, nonMatches: ${nonMatches.length}, nonMatchCount: ${nonMatchCount}, matchErrors: ${matchErrors.length}`);\n      const recordSetSize = records.length;\n      const newCandidateCount = candidateCount + recordSetSize;\n\n\n      if (recordSetSize > 0) {\n        return handleRecordSet();\n      }\n\n      if (state.queriesLeft > 0) {\n        debug(`Empty record set ${state.searchCounter} for ${state.query}, but there are ${state.queriesLeft} queries left`);\n        return iterate({initialState: state, matches, candidateCount: newCandidateCount, nonMatches, nonMatchCount, duplicateCount, matchErrors});\n      }\n\n      debug(`No (more) candidate records to check, no more queries left, matches: ${matches.length}`);\n      return returnResult({matches, state, stopReason: '', nonMatches, nonMatchCount, candidateCount: newCandidateCount, duplicateCount, matchErrors});\n\n      function handleRecordSet() {\n        debug(`Checking record set of ${recordSetSize} candidate records for possible matches, found by ${state.searchCounter} search for ${state.query}`);\n\n        const matchResult = iterateRecords({records, recordSetSize, maxMatches, matches, nonMatches, nonMatchCount});\n\n        const newDuplicateCount = duplicateCount + matchResult.duplicateCount;\n        const newNonMatchCount = nonMatchCount + matchResult.nonMatchCount;\n        const {newMatches, newNonMatches, newMatchErrors} = handleMatchResult(matchResult, matches, nonMatches, matchErrors);\n\n        if (maxMatchesFound({matches: newMatches, maxMatches})) {\n          return returnResult({matches: newMatches, state, stopReason: 'maxMatches', nonMatches: newNonMatches, duplicateCount: newDuplicateCount, candidateCount: newCandidateCount, nonMatchCount: newNonMatchCount, matchErrors: newMatchErrors});\n        }\n\n        if (maxCandidatesRetrieved(newCandidateCount, maxCandidates)) {\n          return returnResult({matches: newMatches, state, stopReason: 'maxCandidates', nonMatches: newNonMatches, duplicateCount: newDuplicateCount, candidateCount: newCandidateCount, nonMatchCount: newNonMatchCount, matchErrors: newMatchErrors});\n        }\n\n        return iterate({initialState: state, matches: newMatches, candidateCount: newCandidateCount, nonMatches: newNonMatches, duplicateCount: newDuplicateCount, nonMatchCount: newNonMatchCount, matchErrors: newMatchErrors});\n      }\n\n      function handleMatchResult(matchResult, matches, nonMatches, matchErrors) {\n        debugData(`- Amount of new matches from record set: ${matchResult.matches.length}`);\n        if (returnNonMatches) {\n          debugData(`- Amount of new nonMatches from record set: ${matchResult.nonMatches.length}`);\n        }\n\n        const newMatches = matches.concat(returnQuery ? addQuery(matchResult.matches) : matchResult.matches);\n        const newNonMatches = returnNonMatches ? nonMatches.concat(returnQuery ? addQuery(matchResult.nonMatches) : matchResult.nonMatches) : [];\n        const newMatchErrors = matchErrors.concat(matchResult.matchErrors);\n\n        debugData(`- Total amount of matches: ${newMatches.length}`);\n        if (returnNonMatches) {\n          debugData(`- Total amount of nonMatches: ${newNonMatches.length}`);\n        }\n\n        debugData(`MatchResult: ${JSON.stringify(matchResult)}`);\n        debugData(`Old matchErrors: ${JSON.stringify(matchErrors)}, matchErrors from matchResult: ${JSON.stringify(matchResult.matchErrors)}, New matchErrors: ${JSON.stringify(newMatchErrors)}`);\n\n        debugData(`- Total amount of matchErrors: ${newMatchErrors.length}`);\n\n        return {newMatches, newNonMatches, newMatchErrors};\n      }\n\n      function addQuery(matches) {\n        debugData(`Adding query ${state.query} to matches`);\n        return matches.map((match) => ({...match, matchQuery: state.query}));\n      }\n\n      function maxCandidatesRetrieved(candidateCount, maxCandidates) {\n        debugData(`Total amount of candidate records retrieved: ${newCandidateCount} (max: ${maxCandidates})`);\n        if (maxCandidates && candidateCount >= maxCandidates) {\n          debug(`Stopped matching because maximum number of candidate records ${candidateCount} / ${maxCandidates} have been retrieved`);\n          return true;\n        }\n      }\n    }\n\n    // matches : array of matching candidate records\n    // nonMatches : array of nonMatching candidate records (if returnNonMatches option is true, otherwise empty array)\n    // - candidate.id\n    // - candidate.record\n    // - probability\n    // - strategy (if returnStrategy option is true)\n    // - threshold (if returnStrategy option is true)\n    // - matchQuery (if returnQuery option is true)\n    // failures: array of conversionFailures from candidate-search and matchErrors from matchDetection in error format {status, payload: {message, id}} if returnFailures is true\n\n    // we could have here also returnRecords/returnMatchRecords/returnNonMatchRecord options that could be turned false for not to return actual record data\n\n    // matchStatus.status: boolean, true if matcher retrieved and handled all found candidate records, false if it did not\n    // matchStatus.stopReason: string ('maxMatches','maxCandidates','maxedQueries','conversionFailures', empty string/undefined), reason for stopping retrieving or handling the candidate records\n    // - only one stopReason is returned (if there would be several possible stopReasons, stopReason is picked in the above order)\n    // - currently stopReason can be non-empty also in cases where status is true, if matcher hit the stop reason when handling the last available candidate record\n\n    function returnResult({matches, state, stopReason, nonMatches, duplicateCount, candidateCount, nonMatchCount, matchErrors}) {\n      const matchErrorCount = matchErrors.length;\n      checkCounts({matches, nonMatches, candidateCount, duplicateCount, nonMatchCount, matchErrorCount});\n      const matchStatus = getMatchState(state, stopReason, matchErrorCount);\n      // add nonMatches to result only if returnNonMatches is 'true', otherwise nonMatches have not been gathered\n      const matchesResult = returnNonMatches ? {matches, matchStatus, nonMatches, candidateCount} : {matches, matchStatus, candidateCount};\n      const result = matchesResult;\n      debugData(`${JSON.stringify(result)}`);\n      return result;\n\n      // note that in cases where the matching has been stopped because of maxMatches checkCounts won't (in most cases) match\n\n      function checkCounts({matches, nonMatches, candidateCount, duplicateCount, nonMatchCount, matchErrorCount}) {\n        const matchCount = matches.length;\n        debugData(`Return nonMatches: ${returnNonMatches}`);\n        const chosenNonMatchCount = returnNonMatches ? nonMatches.length : nonMatchCount;\n        const totalHandled = matchCount + chosenNonMatchCount + duplicateCount;\n        debug(`candidateCount: ${candidateCount}, matches: ${matchCount}, nonMatches: ${chosenNonMatchCount}, duplicateCount: ${duplicateCount}, matchErrorCount: ${matchErrorCount}`);\n        debug(`We got result for ${totalHandled} / ${candidateCount} retrieved candidates`);\n        if (totalHandled !== candidateCount) {\n          debug(`WARNING: Missing results for ${candidateCount - totalHandled} candidates`);\n          return;\n        }\n        return;\n      }\n\n      function getMatchState(state, stopReason, matchErrorCount) {\n        debugData(`${JSON.stringify(state)}`);\n        debug(`We had ${matchErrorCount} retrieved candidates that errored in matchDetection.`);\n        debug(`Queries left ${state.queriesLeft}, Searches for current query left: ${state.resultSetOffset && state.resultSetOffset <= state.totalRecords}, non-retrieved records: ${state.totalRecords - state.queryCandidateCounter}, maxedQueries (${state.maxedQueries.length}): ${state.maxedQueries}`);\n\n        debugData(`StopReason: <${stopReason}>`);\n\n        const searchesLeft = state.resultSetOffset && state.resultSetOffset <= state.totalRecords;\n        const nonRetrieved = searchesLeft ? state.totalRecords - state.queryCandidateCounter : 0;\n        debugData(`nonRetrieved: ${nonRetrieved}`);\n\n        // matchStatus.stopReason: string ('maxMatches','maxCandidates','maxedQueries', empty string/undefined), reason for stopping retrieving or handling the candidate records\n        // 'maxMatches' and 'maxCandidates' are in stopReason, 'maxedQueries', 'conversionFailures' and 'matchErrors' are created here\n\n        if (state.queriesLeft > 0 || nonRetrieved > 0 || state.maxedQueries.length > 0 || matchErrorCount > 0) {\n          const maxedQueriesStopReason = state.maxedQueries.length > 0 ? 'maxedQueries' : undefined;\n          const matchErrorsStopReason = matchErrorCount > 0 ? 'matchErrors' : undefined;\n          const newStopReason = stopReason === '' || stopReason === undefined ? maxedQueriesStopReason || matchErrorsStopReason : stopReason;\n          debugData(`MaxedQueriesStopReason: <${maxedQueriesStopReason}>`);\n          debugData(`MatchErrorsStopReason <${matchErrorsStopReason}>`);\n          debugData(`NewStopReason: <${newStopReason}>`);\n          debug(`Match status: false`);\n          return {status: false, stopReason: newStopReason};\n        }\n\n        debug(`Match status: true`);\n        return {status: true, stopReason};\n      }\n    }\n\n    // NOTES:\n    // - we could optimize by creating the featureSet for the incoming record once and using it for all database/candidateRecords\n    // - if creating the featureSet for the incoming record fails we have an unprocessable entity\n    // - if creating the featureSet for a candidate record fails we could skip that candidate - but list the case as a detectionFailure, same as conversionFailures\n\n    function iterateRecords({records, recordSetSize, maxMatches, matches = [], nonMatches = [], recordMatches = [], recordNonMatches = [], recordCount = 0, recordDuplicateCount = 0, recordNonMatchCount = 0, recordMatchErrors = []}) {\n\n      // recordSetSize : total amount of records in the current record set\n      // recordCount : amount of records from the current record set that have been handled\n      // maxMatches : setting for maximum amount found by current matcher job before the matcher job is stopped\n      // recordDuplicateCount : amount of records from the current record set that are already included in matches/nonMatches results\n      // recordNonMatchCount: amount of records from the current record set that are nonMatches (only is returnNonMatches setting is false)\n\n      // records : non-handled records in the current record set\n      // matches : found matches in the current matcher job\n      // recordMatches : found matches in the current record set\n      // recordNonMatches : found nonMatches in the current record set (only if returnNonMatches setting is true)\n      // recordMatchErrors: errored matchDetection in the current record set\n\n      const [candidate] = records;\n      const newRecordCount = candidate ? recordCount + 1 : recordCount;\n\n      // The matcher uses same matchDetection strategy for candidates from all candidate-searches -> matchDetection result for the same candidate is always same\n      // Exceptions would happen if the candidate would have been updated in the database between candidate searches\n      // Note that if returnNonMatches is false, matcher won't remember candidates that didn't match, so they will be matched again everytime they are retrieved by\n      // different candidate search queries. Same candidate search query won't have duplicate records.\n\n      /* We could optimize and detect all retrieved candidates at once\n      const candidateRecords = records.map(record => record.record);\n      const recordsIsArray = Array.isArray(candidateRecords);\n      debug(`records is an array: ${recordsIsArray}`);\n      const result = detect(record, candidateRecords);\n      debugData(`${JSON.stringify(result)}`);\n      */\n\n      if (candidate) {\n        if (candidateNotInMatches(matches.concat(nonMatches), candidate)) {\n          const {record: candidateRecord, id: candidateId} = candidate;\n          const recordBExternal = {id: candidate.id, recordSource: 'databaseRecord', label: `db-${candidate.id}`};\n          try {\n            debug(`Running matchDetection for record ${candidateId} (${newRecordCount}/${recordSetSize})`);\n            // we should handle errors from detection somehow - ie. cases where either record or candidateRecord errors\n            const detectionResult = detect({recordA: record, recordB: candidateRecord, recordAExternal: recordExternal, recordBExternal});\n\n            return handleDetectionResult(detectionResult, candidateId, candidateRecord);\n          } catch (error) {\n            debug(`MatchDetection errored: database record ${candidateId}: ${error}`);\n\n            const matchError = {status: 422, payload: {message: `Matching errored for database record ${candidateId}. ${error.message}.`, id: candidateId}};\n            const newRecordMatchErrors = recordMatchErrors.concat(matchError);\n            return iterateRecords({records: records.slice(1), recordSetSize, maxMatches, matches, recordMatches, recordCount: newRecordCount, recordNonMatches, recordDuplicateCount, recordNonMatchCount, recordMatchErrors: newRecordMatchErrors});\n          }\n        }\n\n        return iterateRecords({records: records.slice(1), recordSetSize, maxMatches, matches, recordMatches, recordCount: newRecordCount, recordNonMatches, recordDuplicateCount: recordDuplicateCount + 1, recordNonMatchCount, recordMatchErrors});\n      }\n\n      debug(`No more candidates, record set (${recordCount}/${recordSetSize}) done, ${recordMatches.length} matches found, ${recordDuplicateCount} candidates already handled, ${returnNonMatches ? `${recordNonMatches.length}` : `${recordNonMatchCount}`} nonMatches found.`);\n      return {matches: recordMatches, nonMatches: returnNonMatches ? recordNonMatches : [], duplicateCount: recordDuplicateCount, nonMatchCount: recordNonMatchCount, matchErrors: recordMatchErrors};\n\n      function handleDetectionResult(detectionResult, candidateId, candidateRecord) {\n        debugData(`MatchDetection results for ${candidateId} (${newRecordCount}/${recordSetSize}): ${JSON.stringify(detectionResult)}`);\n\n        if (detectionResult.match || returnNonMatches) {\n          debug(`${detectionResult.match ? `Record ${candidateId} (${newRecordCount}/${recordSetSize}) is a match!` : `Record ${candidateId} (${newRecordCount}/${recordSetSize}) is NOT a match!`}`);\n          debugData(`Strategy: ${JSON.stringify(detectionResult.strategy)}, Threshold: ${JSON.stringify(detectionResult.threshold)}`);\n\n          const matchResult = {\n            probability: Math.round(detectionResult.probability * 100)/100,\n            candidate: {\n              id: candidateId,\n              record: candidateRecord\n            }\n          };\n          const strategyResult = {\n            strategy: detectionResult.strategy,\n            threshold: detectionResult.threshold\n          };\n          const newMatch = returnStrategy ? {...matchResult, ...strategyResult} : {...matchResult};\n\n          debugData(`${JSON.stringify(newMatch)}`);\n\n          return handleRecordMatch(detectionResult.match, newMatch);\n        }\n\n        const newRecordNonMatchCount = recordNonMatchCount + 1;\n        debugData(`- Total nonMatches after this detection: ${newRecordNonMatchCount}`);\n\n        return iterateRecords({records: records.slice(1), recordSetSize, maxMatches, matches, recordMatches, recordCount: newRecordCount, recordNonMatches, recordDuplicateCount, recordNonMatchCount: newRecordNonMatchCount, recordMatchErrors});\n      }\n\n      function handleRecordMatch(isMatch, newMatch) {\n        const newRecordMatches = isMatch ? recordMatches.concat(newMatch) : recordMatches;\n        const newRecordNonMatches = isMatch ? recordNonMatches : recordNonMatches.concat(newMatch);\n        const newRecordNonMatchCount = isMatch ? recordNonMatchCount : recordNonMatchCount + 1;\n\n        debugData(`- Total matches after this detection: ${matches.concat(newRecordMatches).length} (max: ${maxMatches})`);\n\n        if (returnNonMatches) {\n          debugData(`- Total nonMatches after this detection: ${nonMatches.concat(newRecordNonMatches).length}`);\n        }\n        debugData(`- Total nonMatchCount after this detection: ${recordNonMatchCount}`);\n\n        if (maxMatchesFound({matches: matches.concat(newRecordMatches), maxMatches})) {\n          debug(`MaxMatches (${maxMatches}) reached, handled candidates in record set: ${newRecordCount} non-handled candidates in record set ${recordSetSize - newRecordCount}`);\n          return {matches: newRecordMatches, nonMatches: returnNonMatches ? newRecordNonMatches : [], duplicateCount: recordDuplicateCount, nonMatchCount: newRecordNonMatchCount, matchErrors: recordMatchErrors};\n        }\n\n        return iterateRecords({records: records.slice(1), recordSetSize, maxMatches, matches, recordMatches: newRecordMatches, recordCount: newRecordCount, recordNonMatches: returnNonMatches ? newRecordNonMatches : [], duplicateCount: recordDuplicateCount, recordNonMatchCount: newRecordNonMatchCount, matchErrors: recordMatchErrors});\n      }\n\n      function candidateNotInMatches(matches, candidate) {\n        debug(`Checking that record ${candidate.id} is not already included in ${matches.length} matches/nonMatches`);\n        const newCandidateId = candidate.id;\n        debugData(`newCandidateId: ${newCandidateId}`);\n        const result = matches.find(({candidate}) => candidate.id === newCandidateId);\n        debugData(`Result: ${result}`);\n        if (result) {\n          debug(`${candidate.id} was already handled.`);\n          return false;\n        }\n        debug(`${candidate.id} not found in matches/nonMatches`);\n        return true;\n      }\n    }\n\n    function maxMatchesFound({matches, maxMatches}) {\n      if (maxMatches && matches.length >= maxMatches) {\n        debug(`Stopping recordSet iteration: maxMatches (${maxMatches}) for matcher job found.`);\n        return true;\n      }\n    }\n  }\n};\n"],
-  "mappings": "AAAA,OAAO,uBAAuB;AAC9B,OAAO,4BAA4B,qBAAqB;AACxD,OAAO,+BAA+B,oBAAoB;AAG1D,SAAQ,iBAAiB;AAEzB,eAAe,CAAC,EAAC,WAAW,kBAAkB,QAAQ,eAAe,aAAa,GAAG,gBAAgB,IAAI,iBAAiB,OAAO,cAAc,OAAO,mBAAmB,MAAK,MAAM;AAClL,QAAM,QAAQ,kBAAkB,yCAAyC;AACzE,QAAM,YAAY,MAAM,OAAO,MAAM;AAErC,YAAU,qBAAqB,KAAK,UAAU,gBAAgB,CAAC,EAAE;AACjE,YAAU,kBAAkB,KAAK,UAAU,aAAa,CAAC,EAAE;AAC3D,YAAU,eAAe,KAAK,UAAU,UAAU,CAAC,EAAE;AACrD,YAAU,kBAAkB,KAAK,UAAU,aAAa,CAAC,EAAE;AAC3D,YAAU,mBAAmB,KAAK,UAAU,cAAc,CAAC,EAAE;AAC7D,YAAU,gBAAgB,KAAK,UAAU,WAAW,CAAC,EAAE;AACvD,YAAU,qBAAqB,KAAK,UAAU,gBAAgB,CAAC,EAAE;AAGjE,QAAM,SAAS,yBAAyB,kBAAkB,cAAc;AAExE,SAAO;AAEP,iBAAe,cAAc,EAAC,QAAQ,iBAAiB,EAAC,cAAc,kBAAkB,OAAO,KAAI,EAAC,GAAG;AAErG,UAAM,EAAC,OAAM,IAAI,MAAM,sBAAsB,EAAC,GAAG,eAAe,QAAQ,eAAe,eAAc,CAAC;AACtG,WAAO,QAAQ,CAAC,CAAC;AAejB,mBAAe,QAAQ,EAAC,eAAe,CAAC,GAAG,UAAU,CAAC,GAAG,iBAAiB,GAAG,aAAa,CAAC,GAAG,iBAAiB,GAAG,gBAAgB,GAAG,cAAc,CAAC,EAAC,GAAG;AACtJ,gBAAU,kCAAkC;AAC5C,YAAM,EAAC,SAAS,GAAG,MAAK,IAAI,MAAM,OAAO,YAAY;AAErD,gBAAU,kBAAkB,KAAK,UAAU,KAAK,CAAC,cAAc,QAAQ,MAAM,qBAAqB,cAAc,iBAAiB,WAAW,MAAM,oBAAoB,aAAa,kBAAkB,YAAY,MAAM,EAAE;AACzN,YAAM,gBAAgB,QAAQ;AAC9B,YAAM,oBAAoB,iBAAiB;AAG3C,UAAI,gBAAgB,GAAG;AACrB,eAAO,gBAAgB;AAAA,MACzB;AAEA,UAAI,MAAM,cAAc,GAAG;AACzB,cAAM,oBAAoB,MAAM,aAAa,QAAQ,MAAM,KAAK,mBAAmB,MAAM,WAAW,eAAe;AACnH,eAAO,QAAQ,EAAC,cAAc,OAAO,SAAS,gBAAgB,mBAAmB,YAAY,eAAe,gBAAgB,YAAW,CAAC;AAAA,MAC1I;AAEA,YAAM,wEAAwE,QAAQ,MAAM,EAAE;AAC9F,aAAO,aAAa,EAAC,SAAS,OAAO,YAAY,IAAI,YAAY,eAAe,gBAAgB,mBAAmB,gBAAgB,YAAW,CAAC;AAE/I,eAAS,kBAAkB;AACzB,cAAM,0BAA0B,aAAa,qDAAqD,MAAM,aAAa,eAAe,MAAM,KAAK,EAAE;AAEjJ,cAAM,cAAc,eAAe,EAAC,SAAS,eAAe,YAAY,SAAS,YAAY,cAAa,CAAC;AAE3G,cAAM,oBAAoB,iBAAiB,YAAY;AACvD,cAAM,mBAAmB,gBAAgB,YAAY;AACrD,cAAM,EAAC,YAAY,eAAe,eAAc,IAAI,kBAAkB,aAAa,SAAS,YAAY,WAAW;AAEnH,YAAI,gBAAgB,EAAC,SAAS,YAAY,WAAU,CAAC,GAAG;AACtD,iBAAO,aAAa,EAAC,SAAS,YAAY,OAAO,YAAY,cAAc,YAAY,eAAe,gBAAgB,mBAAmB,gBAAgB,mBAAmB,eAAe,kBAAkB,aAAa,eAAc,CAAC;AAAA,QAC3O;AAEA,YAAI,uBAAuB,mBAAmB,aAAa,GAAG;AAC5D,iBAAO,aAAa,EAAC,SAAS,YAAY,OAAO,YAAY,iBAAiB,YAAY,eAAe,gBAAgB,mBAAmB,gBAAgB,mBAAmB,eAAe,kBAAkB,aAAa,eAAc,CAAC;AAAA,QAC9O;AAEA,eAAO,QAAQ,EAAC,cAAc,OAAO,SAAS,YAAY,gBAAgB,mBAAmB,YAAY,eAAe,gBAAgB,mBAAmB,eAAe,kBAAkB,aAAa,eAAc,CAAC;AAAA,MAC1N;AAEA,eAAS,kBAAkB,aAAaA,UAASC,aAAYC,cAAa;AACxE,kBAAU,4CAA4C,YAAY,QAAQ,MAAM,EAAE;AAClF,YAAI,kBAAkB;AACpB,oBAAU,+CAA+C,YAAY,WAAW,MAAM,EAAE;AAAA,QAC1F;AAEA,cAAM,aAAaF,SAAQ,OAAO,cAAc,SAAS,YAAY,OAAO,IAAI,YAAY,OAAO;AACnG,cAAM,gBAAgB,mBAAmBC,YAAW,OAAO,cAAc,SAAS,YAAY,UAAU,IAAI,YAAY,UAAU,IAAI,CAAC;AACvI,cAAM,iBAAiBC,aAAY,OAAO,YAAY,WAAW;AAEjE,kBAAU,8BAA8B,WAAW,MAAM,EAAE;AAC3D,YAAI,kBAAkB;AACpB,oBAAU,iCAAiC,cAAc,MAAM,EAAE;AAAA,QACnE;AAEA,kBAAU,gBAAgB,KAAK,UAAU,WAAW,CAAC,EAAE;AACvD,kBAAU,oBAAoB,KAAK,UAAUA,YAAW,CAAC,mCAAmC,KAAK,UAAU,YAAY,WAAW,CAAC,sBAAsB,KAAK,UAAU,cAAc,CAAC,EAAE;AAEzL,kBAAU,kCAAkC,eAAe,MAAM,EAAE;AAEnE,eAAO,EAAC,YAAY,eAAe,eAAc;AAAA,MACnD;AAEA,eAAS,SAASF,UAAS;AACzB,kBAAU,gBAAgB,MAAM,KAAK,aAAa;AAClD,eAAOA,SAAQ,IAAI,CAAC,WAAW,EAAC,GAAG,OAAO,YAAY,MAAM,MAAK,EAAE;AAAA,MACrE;AAEA,eAAS,uBAAuBG,iBAAgBC,gBAAe;AAC7D,kBAAU,gDAAgD,iBAAiB,UAAUA,cAAa,GAAG;AACrG,YAAIA,kBAAiBD,mBAAkBC,gBAAe;AACpD,gBAAM,gEAAgED,eAAc,MAAMC,cAAa,sBAAsB;AAC7H,iBAAO;AAAA,QACT;AAAA,MACF;AAAA,IACF;AAmBA,aAAS,aAAa,EAAC,SAAS,OAAO,YAAY,YAAY,gBAAgB,gBAAgB,eAAe,YAAW,GAAG;AAC1H,YAAM,kBAAkB,YAAY;AACpC,kBAAY,EAAC,SAAS,YAAY,gBAAgB,gBAAgB,eAAe,gBAAe,CAAC;AACjG,YAAM,cAAc,cAAc,OAAO,YAAY,eAAe;AAEpE,YAAM,gBAAgB,mBAAmB,EAAC,SAAS,aAAa,YAAY,eAAc,IAAI,EAAC,SAAS,aAAa,eAAc;AACnI,YAAM,SAAS;AACf,gBAAU,GAAG,KAAK,UAAU,MAAM,CAAC,EAAE;AACrC,aAAO;AAIP,eAAS,YAAY,EAAC,SAAAJ,UAAS,YAAAC,aAAY,gBAAAE,iBAAgB,gBAAAE,iBAAgB,eAAAC,gBAAe,iBAAAC,iBAAe,GAAG;AAC1G,cAAM,aAAaP,SAAQ;AAC3B,kBAAU,sBAAsB,gBAAgB,EAAE;AAClD,cAAM,sBAAsB,mBAAmBC,YAAW,SAASK;AACnE,cAAM,eAAe,aAAa,sBAAsBD;AACxD,cAAM,mBAAmBF,eAAc,cAAc,UAAU,iBAAiB,mBAAmB,qBAAqBE,eAAc,sBAAsBE,gBAAe,EAAE;AAC7K,cAAM,qBAAqB,YAAY,MAAMJ,eAAc,uBAAuB;AAClF,YAAI,iBAAiBA,iBAAgB;AACnC,gBAAM,gCAAgCA,kBAAiB,YAAY,aAAa;AAChF;AAAA,QACF;AACA;AAAA,MACF;AAEA,eAAS,cAAcK,QAAOC,aAAYF,kBAAiB;AACzD,kBAAU,GAAG,KAAK,UAAUC,MAAK,CAAC,EAAE;AACpC,cAAM,UAAUD,gBAAe,uDAAuD;AACtF,cAAM,gBAAgBC,OAAM,WAAW,sCAAsCA,OAAM,mBAAmBA,OAAM,mBAAmBA,OAAM,YAAY,4BAA4BA,OAAM,eAAeA,OAAM,qBAAqB,mBAAmBA,OAAM,aAAa,MAAM,MAAMA,OAAM,YAAY,EAAE;AAEnS,kBAAU,gBAAgBC,WAAU,GAAG;AAEvC,cAAM,eAAeD,OAAM,mBAAmBA,OAAM,mBAAmBA,OAAM;AAC7E,cAAM,eAAe,eAAeA,OAAM,eAAeA,OAAM,wBAAwB;AACvF,kBAAU,iBAAiB,YAAY,EAAE;AAKzC,YAAIA,OAAM,cAAc,KAAK,eAAe,KAAKA,OAAM,aAAa,SAAS,KAAKD,mBAAkB,GAAG;AACrG,gBAAM,yBAAyBC,OAAM,aAAa,SAAS,IAAI,iBAAiB;AAChF,gBAAM,wBAAwBD,mBAAkB,IAAI,gBAAgB;AACpE,gBAAM,gBAAgBE,gBAAe,MAAMA,gBAAe,SAAY,0BAA0B,wBAAwBA;AACxH,oBAAU,4BAA4B,sBAAsB,GAAG;AAC/D,oBAAU,0BAA0B,qBAAqB,GAAG;AAC5D,oBAAU,mBAAmB,aAAa,GAAG;AAC7C,gBAAM,qBAAqB;AAC3B,iBAAO,EAAC,QAAQ,OAAO,YAAY,cAAa;AAAA,QAClD;AAEA,cAAM,oBAAoB;AAC1B,eAAO,EAAC,QAAQ,MAAM,YAAAA,YAAU;AAAA,MAClC;AAAA,IACF;AAOA,aAAS,eAAe,EAAC,SAAS,eAAe,YAAAC,aAAY,UAAU,CAAC,GAAG,aAAa,CAAC,GAAG,gBAAgB,CAAC,GAAG,mBAAmB,CAAC,GAAG,cAAc,GAAG,uBAAuB,GAAG,sBAAsB,GAAG,oBAAoB,CAAC,EAAC,GAAG;AAclO,YAAM,CAAC,SAAS,IAAI;AACpB,YAAM,iBAAiB,YAAY,cAAc,IAAI;AAerD,UAAI,WAAW;AACb,YAAI,sBAAsB,QAAQ,OAAO,UAAU,GAAG,SAAS,GAAG;AAChE,gBAAM,EAAC,QAAQ,iBAAiB,IAAI,YAAW,IAAI;AACnD,gBAAM,kBAAkB,EAAC,IAAI,UAAU,IAAI,cAAc,kBAAkB,OAAO,MAAM,UAAU,EAAE,GAAE;AACtG,cAAI;AACF,kBAAM,qCAAqC,WAAW,KAAK,cAAc,IAAI,aAAa,GAAG;AAE7F,kBAAM,kBAAkB,OAAO,EAAC,SAAS,QAAQ,SAAS,iBAAiB,iBAAiB,gBAAgB,gBAAe,CAAC;AAE5H,mBAAO,sBAAsB,iBAAiB,aAAa,eAAe;AAAA,UAC5E,SAAS,OAAO;AACd,kBAAM,2CAA2C,WAAW,KAAK,KAAK,EAAE;AAExE,kBAAM,aAAa,EAAC,QAAQ,KAAK,SAAS,EAAC,SAAS,wCAAwC,WAAW,KAAK,MAAM,OAAO,KAAK,IAAI,YAAW,EAAC;AAC9I,kBAAM,uBAAuB,kBAAkB,OAAO,UAAU;AAChE,mBAAO,eAAe,EAAC,SAAS,QAAQ,MAAM,CAAC,GAAG,eAAe,YAAAA,aAAY,SAAS,eAAe,aAAa,gBAAgB,kBAAkB,sBAAsB,qBAAqB,mBAAmB,qBAAoB,CAAC;AAAA,UACzO;AAAA,QACF;AAEA,eAAO,eAAe,EAAC,SAAS,QAAQ,MAAM,CAAC,GAAG,eAAe,YAAAA,aAAY,SAAS,eAAe,aAAa,gBAAgB,kBAAkB,sBAAsB,uBAAuB,GAAG,qBAAqB,kBAAiB,CAAC;AAAA,MAC7O;AAEA,YAAM,mCAAmC,WAAW,IAAI,aAAa,WAAW,cAAc,MAAM,mBAAmB,oBAAoB,gCAAgC,mBAAmB,GAAG,iBAAiB,MAAM,KAAK,GAAG,mBAAmB,EAAE,oBAAoB;AACzQ,aAAO,EAAC,SAAS,eAAe,YAAY,mBAAmB,mBAAmB,CAAC,GAAG,gBAAgB,sBAAsB,eAAe,qBAAqB,aAAa,kBAAiB;AAE9L,eAAS,sBAAsB,iBAAiB,aAAa,iBAAiB;AAC5E,kBAAU,8BAA8B,WAAW,KAAK,cAAc,IAAI,aAAa,MAAM,KAAK,UAAU,eAAe,CAAC,EAAE;AAE9H,YAAI,gBAAgB,SAAS,kBAAkB;AAC7C,gBAAM,GAAG,gBAAgB,QAAQ,UAAU,WAAW,KAAK,cAAc,IAAI,aAAa,kBAAkB,UAAU,WAAW,KAAK,cAAc,IAAI,aAAa,mBAAmB,EAAE;AAC1L,oBAAU,aAAa,KAAK,UAAU,gBAAgB,QAAQ,CAAC,gBAAgB,KAAK,UAAU,gBAAgB,SAAS,CAAC,EAAE;AAE1H,gBAAM,cAAc;AAAA,YAClB,aAAa,KAAK,MAAM,gBAAgB,cAAc,GAAG,IAAE;AAAA,YAC3D,WAAW;AAAA,cACT,IAAI;AAAA,cACJ,QAAQ;AAAA,YACV;AAAA,UACF;AACA,gBAAM,iBAAiB;AAAA,YACrB,UAAU,gBAAgB;AAAA,YAC1B,WAAW,gBAAgB;AAAA,UAC7B;AACA,gBAAM,WAAW,iBAAiB,EAAC,GAAG,aAAa,GAAG,eAAc,IAAI,EAAC,GAAG,YAAW;AAEvF,oBAAU,GAAG,KAAK,UAAU,QAAQ,CAAC,EAAE;AAEvC,iBAAO,kBAAkB,gBAAgB,OAAO,QAAQ;AAAA,QAC1D;AAEA,cAAM,yBAAyB,sBAAsB;AACrD,kBAAU,4CAA4C,sBAAsB,EAAE;AAE9E,eAAO,eAAe,EAAC,SAAS,QAAQ,MAAM,CAAC,GAAG,eAAe,YAAAA,aAAY,SAAS,eAAe,aAAa,gBAAgB,kBAAkB,sBAAsB,qBAAqB,wBAAwB,kBAAiB,CAAC;AAAA,MAC3O;AAEA,eAAS,kBAAkB,SAAS,UAAU;AAC5C,cAAM,mBAAmB,UAAU,cAAc,OAAO,QAAQ,IAAI;AACpE,cAAM,sBAAsB,UAAU,mBAAmB,iBAAiB,OAAO,QAAQ;AACzF,cAAM,yBAAyB,UAAU,sBAAsB,sBAAsB;AAErF,kBAAU,yCAAyC,QAAQ,OAAO,gBAAgB,EAAE,MAAM,UAAUA,WAAU,GAAG;AAEjH,YAAI,kBAAkB;AACpB,oBAAU,4CAA4C,WAAW,OAAO,mBAAmB,EAAE,MAAM,EAAE;AAAA,QACvG;AACA,kBAAU,+CAA+C,mBAAmB,EAAE;AAE9E,YAAI,gBAAgB,EAAC,SAAS,QAAQ,OAAO,gBAAgB,GAAG,YAAAA,YAAU,CAAC,GAAG;AAC5E,gBAAM,eAAeA,WAAU,gDAAgD,cAAc,yCAAyC,gBAAgB,cAAc,EAAE;AACtK,iBAAO,EAAC,SAAS,kBAAkB,YAAY,mBAAmB,sBAAsB,CAAC,GAAG,gBAAgB,sBAAsB,eAAe,wBAAwB,aAAa,kBAAiB;AAAA,QACzM;AAEA,eAAO,eAAe,EAAC,SAAS,QAAQ,MAAM,CAAC,GAAG,eAAe,YAAAA,aAAY,SAAS,eAAe,kBAAkB,aAAa,gBAAgB,kBAAkB,mBAAmB,sBAAsB,CAAC,GAAG,gBAAgB,sBAAsB,qBAAqB,wBAAwB,aAAa,kBAAiB,CAAC;AAAA,MACvU;AAEA,eAAS,sBAAsBV,UAASW,YAAW;AACjD,cAAM,wBAAwBA,WAAU,EAAE,+BAA+BX,SAAQ,MAAM,qBAAqB;AAC5G,cAAM,iBAAiBW,WAAU;AACjC,kBAAU,mBAAmB,cAAc,EAAE;AAC7C,cAAM,SAASX,SAAQ,KAAK,CAAC,EAAC,WAAAW,WAAS,MAAMA,WAAU,OAAO,cAAc;AAC5E,kBAAU,WAAW,MAAM,EAAE;AAC7B,YAAI,QAAQ;AACV,gBAAM,GAAGA,WAAU,EAAE,uBAAuB;AAC5C,iBAAO;AAAA,QACT;AACA,cAAM,GAAGA,WAAU,EAAE,kCAAkC;AACvD,eAAO;AAAA,MACT;AAAA,IACF;AAEA,aAAS,gBAAgB,EAAC,SAAS,YAAAD,YAAU,GAAG;AAC9C,UAAIA,eAAc,QAAQ,UAAUA,aAAY;AAC9C,cAAM,6CAA6CA,WAAU,0BAA0B;AACvF,eAAO;AAAA,MACT;AAAA,IACF;AAAA,EACF;AACF;",
+  "sourcesContent": ["import createDebugLogger from 'debug';\nimport createSearchInterface, * as candidateSearch from './candidate-search/index.js';\nimport createDetectionInterface, * as matchDetection from './match-detection/index.js';\n//import inspect from 'util';\n\nexport {candidateSearch, matchDetection};\n\nexport default ({detection: detectionOptions, search: searchOptions, maxMatches = 1, maxCandidates = 25, returnStrategy = false, returnQuery = false, returnNonMatches = false}) => {\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:index');\n  const debugData = debug.extend('data');\n  const debugDev = debug.extend('dev');\n\n\n  debugData(`DetectionOptions: ${JSON.stringify(detectionOptions)}`);\n  debugData(`SearchOptions: ${JSON.stringify(searchOptions)}`);\n  debugData(`MaxMatches: ${JSON.stringify(maxMatches)}`);\n  debugData(`MaxCandidates: ${JSON.stringify(maxCandidates)}`);\n  debugData(`ReturnStrategy: ${JSON.stringify(returnStrategy)}`);\n  debugData(`ReturnQuery: ${JSON.stringify(returnQuery)}`);\n  debugData(`ReturnNonMatches: ${JSON.stringify(returnNonMatches)}`);\n\n\n  const detect = createDetectionInterface(detectionOptions, returnStrategy);\n\n  return prepareSearch;\n\n  async function prepareSearch({record, recordExternal = {recordSource: 'incomingRecord', label: 'ic'}}) {\n\n    const {search} = await createSearchInterface({...searchOptions, record, maxCandidates, recordExternal});\n    return iterate({});\n\n    // candidateCount : amount of candidate records retrived from SRU for matching, NOT including current record set\n    // matches : candidates that have been detected as matches by current matcher job\n    // nonMatches : candidates that have been detected as non-matches by current matcher job (only if returnNonMatches is 'true')\n    // duplicateCount : amount of candidate records that were retrieved from the SRU but not handled further because they were already found in the matches/nonMatches\n    // nonMatchCount : amount of candidate records that were detexted as nonMatches by current mathcer job\n\n    // state.totalRecords : amount of candidate records available to the current query (undefined, if there was no queries left)\n    // state.query : current query (undefined if there was no queries left)\n    // state.searchCounter : sequence for current search for current query (undefined, if there we no queries left)\n    // state.queryCandidateCounter: amount of candidate records retrieved from SRU for matching for current query, including the current record set (undefined if there were no queries left)\n    // state.queriesLeft : amount of queries left\n    // state.queryCounter : sequence for current query\n    // state.maxedQueries : queries that resulted in more than serverMaxResults hits\n\n    async function iterate({initialState = {}, matches = [], candidateCount = 0, nonMatches = [], duplicateCount = 0, nonMatchCount = 0, matchErrors = []}) {\n      debugData(`Starting next matcher iteration.`);\n      const {records, ...state} = await search(initialState);\n\n      debugDev(`Current state: ${JSON.stringify(state)}, matches: ${matches.length}, candidateCount: ${candidateCount}, nonMatches: ${nonMatches.length}, duplicateCount: ${duplicateCount}, nonMatchCount: ${nonMatchCount}, matchErrors: ${matchErrors.length}`);\n      const recordSetSize = records.length;\n      const newCandidateCount = candidateCount + recordSetSize;\n\n      if (recordSetSize > 0) {\n        return handleRecordSet();\n      }\n\n      if (state.queriesLeft > 0) {\n        debug(`Empty record set ${state.searchCounter} for ${state.query}, but there are ${state.queriesLeft} queries left`);\n        return iterate({initialState: state, matches, candidateCount: newCandidateCount, nonMatches, nonMatchCount, duplicateCount, matchErrors});\n      }\n\n      debug(`No (more) candidate records to check, no more queries left, matches: ${matches.length}`);\n      return returnResult({matches, state, stopReason: '', nonMatches, nonMatchCount, candidateCount: newCandidateCount, duplicateCount, matchErrors});\n\n      function handleRecordSet() {\n        debug(`Checking record set of ${recordSetSize} candidate records for possible matches, found by ${state.searchCounter} search for ${state.query}`);\n\n        const matchResult = iterateRecords({records, recordSetSize, maxMatches, matches, nonMatches, nonMatchCount, duplicateCount});\n\n        const newDuplicateCount = duplicateCount + matchResult.duplicateCount;\n        const newNonMatchCount = nonMatchCount + matchResult.nonMatchCount;\n        const {newMatches, newNonMatches, newMatchErrors} = handleMatchResult(matchResult, matches, nonMatches, matchErrors);\n\n        if (maxMatchesFound({matches: newMatches, maxMatches})) {\n          return returnResult({matches: newMatches, state, stopReason: 'maxMatches', nonMatches: newNonMatches, duplicateCount: newDuplicateCount, candidateCount: newCandidateCount, nonMatchCount: newNonMatchCount, matchErrors: newMatchErrors});\n        }\n\n        if (maxCandidatesRetrieved(newCandidateCount, maxCandidates)) {\n          return returnResult({matches: newMatches, state, stopReason: 'maxCandidates', nonMatches: newNonMatches, duplicateCount: newDuplicateCount, candidateCount: newCandidateCount, nonMatchCount: newNonMatchCount, matchErrors: newMatchErrors});\n        }\n\n        return iterate({initialState: state, matches: newMatches, candidateCount: newCandidateCount, nonMatches: newNonMatches, duplicateCount: newDuplicateCount, nonMatchCount: newNonMatchCount, matchErrors: newMatchErrors});\n      }\n\n      function handleMatchResult(matchResult, matches, nonMatches, matchErrors) {\n        debugData(`- Amount of new matches from record set: ${matchResult.matches.length}`);\n        if (returnNonMatches) {\n          debugData(`- Amount of new nonMatches from record set: ${matchResult.nonMatches.length}`);\n        }\n\n        const newMatches = matches.concat(returnQuery ? addQuery(matchResult.matches) : matchResult.matches);\n        const newNonMatches = returnNonMatches ? nonMatches.concat(returnQuery ? addQuery(matchResult.nonMatches) : matchResult.nonMatches) : [];\n        const newMatchErrors = matchErrors.concat(matchResult.matchErrors);\n\n        debugData(`- Total amount of matches: ${newMatches.length}`);\n        if (returnNonMatches) {\n          debugData(`- Total amount of nonMatches: ${newNonMatches.length}`);\n        }\n\n        debugData(`MatchResult: ${JSON.stringify(matchResult)}`);\n        debugData(`Old matchErrors: ${JSON.stringify(matchErrors)}, matchErrors from matchResult: ${JSON.stringify(matchResult.matchErrors)}, New matchErrors: ${JSON.stringify(newMatchErrors)}`);\n\n        debugData(`- Total amount of matchErrors: ${newMatchErrors.length}`);\n\n        return {newMatches, newNonMatches, newMatchErrors};\n      }\n\n      function addQuery(matches) {\n        debugData(`Adding query ${state.query} to matches`);\n        return matches.map((match) => ({...match, matchQuery: state.query}));\n      }\n\n      function maxCandidatesRetrieved(candidateCount, maxCandidates) {\n        debugData(`Total amount of candidate records retrieved: ${newCandidateCount} (max: ${maxCandidates})`);\n        if (maxCandidates && candidateCount >= maxCandidates) {\n          debug(`Stopped matching because maximum number of candidate records ${candidateCount} / ${maxCandidates} have been retrieved`);\n          return true;\n        }\n      }\n    }\n\n    // matches : array of matching candidate records\n    // nonMatches : array of nonMatching candidate records (if returnNonMatches option is true, otherwise empty array)\n    // - candidate.id\n    // - candidate.record\n    // - probability\n    // - strategy (if returnStrategy option is true)\n    // - threshold (if returnStrategy option is true)\n    // - matchQuery (if returnQuery option is true)\n    // failures: array of conversionFailures from candidate-search and matchErrors from matchDetection in error format {status, payload: {message, id}} if returnFailures is true\n\n    // we could have here also returnRecords/returnMatchRecords/returnNonMatchRecord options that could be turned false for not to return actual record data\n\n    // matchStatus.status: boolean, true if matcher retrieved and handled all found candidate records, false if it did not\n    // matchStatus.stopReason: string ('maxMatches','maxCandidates','maxedQueries','conversionFailures', empty string/undefined), reason for stopping retrieving or handling the candidate records\n    // - only one stopReason is returned (if there would be several possible stopReasons, stopReason is picked in the above order)\n    // - currently stopReason can be non-empty also in cases where status is true, if matcher hit the stop reason when handling the last available candidate record\n\n    function returnResult({matches, state, stopReason, nonMatches, duplicateCount, candidateCount, nonMatchCount, matchErrors}) {\n      const matchErrorCount = matchErrors.length;\n      checkCounts({matches, nonMatches, candidateCount, duplicateCount, nonMatchCount, matchErrorCount});\n      const matchStatus = getMatchState(state, stopReason, matchErrorCount);\n      // add nonMatches to result only if returnNonMatches is 'true', otherwise nonMatches have not been gathered\n      const matchesResult = returnNonMatches ? {matches, matchStatus, nonMatches, candidateCount} : {matches, matchStatus, candidateCount};\n      const result = matchesResult;\n      debugData(`${JSON.stringify(result)}`);\n      return result;\n\n      // note that in cases where the matching has been stopped because of maxMatches checkCounts won't (in most cases) match\n\n      function checkCounts({matches, nonMatches, candidateCount, duplicateCount, nonMatchCount, matchErrorCount}) {\n        const matchCount = matches.length;\n        debugData(`Return nonMatches: ${returnNonMatches}`);\n        const chosenNonMatchCount = returnNonMatches ? nonMatches.length : nonMatchCount;\n        const totalHandled = matchCount + chosenNonMatchCount + duplicateCount;\n        debug(`candidateCount: ${candidateCount}, matches: ${matchCount}, nonMatches: ${chosenNonMatchCount}, duplicateCount: ${duplicateCount}, matchErrorCount: ${matchErrorCount}`);\n        debug(`We got result for ${totalHandled} / ${candidateCount} retrieved candidates`);\n        // NOTE: this counts something wrong!\n        if (totalHandled !== candidateCount) {\n          debug(`WARNING: Missing results for ${candidateCount - totalHandled} candidates`);\n          return;\n        }\n        return;\n      }\n\n      function getMatchState(state, stopReason, matchErrorCount) {\n        debugData(`${JSON.stringify(state)}`);\n        debug(`We had ${matchErrorCount} retrieved candidates that errored in matchDetection.`);\n        debug(`Queries left ${state.queriesLeft}, Searches for current query left: ${state.resultSetOffset && state.resultSetOffset <= state.totalRecords}, non-retrieved records: ${state.totalRecords - state.queryCandidateCounter}, maxedQueries (${state.maxedQueries.length}): ${state.maxedQueries}`);\n\n        debugData(`StopReason: <${stopReason}>`);\n\n        const searchesLeft = state.resultSetOffset && state.resultSetOffset <= state.totalRecords;\n        const nonRetrieved = searchesLeft ? state.totalRecords - state.queryCandidateCounter : 0;\n        debugData(`nonRetrieved: ${nonRetrieved}`);\n\n        // matchStatus.stopReason: string ('maxMatches','maxCandidates','maxedQueries', empty string/undefined), reason for stopping retrieving or handling the candidate records\n        // 'maxMatches' and 'maxCandidates' are in stopReason, 'maxedQueries', 'conversionFailures' and 'matchErrors' are created here\n\n        if (state.queriesLeft > 0 || nonRetrieved > 0 || state.maxedQueries.length > 0 || matchErrorCount > 0) {\n          const maxedQueriesStopReason = state.maxedQueries.length > 0 ? 'maxedQueries' : undefined;\n          const matchErrorsStopReason = matchErrorCount > 0 ? 'matchErrors' : undefined;\n          const newStopReason = stopReason === '' || stopReason === undefined ? maxedQueriesStopReason || matchErrorsStopReason : stopReason;\n          debugData(`MaxedQueriesStopReason: <${maxedQueriesStopReason}>`);\n          debugData(`MatchErrorsStopReason <${matchErrorsStopReason}>`);\n          debugData(`NewStopReason: <${newStopReason}>`);\n          debug(`Match status: false`);\n          return {status: false, stopReason: newStopReason};\n        }\n\n        debug(`Match status: true`);\n        return {status: true, stopReason};\n      }\n    }\n\n    // NOTES:\n    // - we could optimize by creating the featureSet for the incoming record once and using it for all database/candidateRecords\n    // - if creating the featureSet for the incoming record fails we have an unprocessable entity\n    // - if creating the featureSet for a candidate record fails we could skip that candidate - but list the case as a detectionFailure, same as conversionFailures\n\n    function iterateRecords({records, recordSetSize, maxMatches, matches = [], nonMatches = [], recordMatches = [], recordNonMatches = [], recordCount = 0, recordDuplicateCount = 0, recordNonMatchCount = 0, recordMatchErrors = []}) {\n\n      // recordSetSize : total amount of records in the current record set\n      // recordCount : amount of records from the current record set that have been handled\n      // maxMatches : setting for maximum amount found by current matcher job before the matcher job is stopped\n      // recordDuplicateCount : amount of records from the current record set that are already included in matches/nonMatches results\n      // recordNonMatchCount: amount of records from the current record set that are nonMatches (only is returnNonMatches setting is false)\n\n      // records : non-handled records in the current record set\n      // matches : found matches in the current matcher job\n      // nonMatches: found nonMatches in the current matcher job\n      // recordMatches : found matches in the current record set\n      // recordNonMatches : found nonMatches in the current record set (only if returnNonMatches setting is true)\n      // recordMatchErrors: errored matchDetection in the current record set\n\n      const [candidate] = records;\n      const newRecordCount = candidate ? recordCount + 1 : recordCount;\n\n      // The matcher uses same matchDetection strategy for candidates from all candidate-searches -> matchDetection result for the same candidate is always same\n      // Exceptions would happen if the candidate would have been updated in the database between candidate searches\n      // Note that if returnNonMatches is false, matcher won't remember candidates that didn't match, so they will be matched again everytime they are retrieved by\n      // different candidate search queries. Same candidate search query won't have duplicate records.\n\n      /* We could optimize and detect all retrieved candidates at once\n      const candidateRecords = records.map(record => record.record);\n      const recordsIsArray = Array.isArray(candidateRecords);\n      debug(`records is an array: ${recordsIsArray}`);\n      const result = detect(record, candidateRecords);\n      debugData(`${JSON.stringify(result)}`);\n      */\n\n      if (candidate) {\n        const {record: candidateRecord, id: candidateId} = candidate;\n        const allMatches = matches.concat(nonMatches);\n        if (candidateNotInMatches(allMatches, candidate)) {\n          const recordBExternal = {id: candidate.id, recordSource: 'databaseRecord', label: `db-${candidate.id}`};\n          try {\n            debug(`Running matchDetection for record ${candidateId} (${newRecordCount}/${recordSetSize})`);\n            // we should handle errors from detection somehow - ie. cases where either record or candidateRecord errors\n            const detectionResult = detect({recordA: record, recordB: candidateRecord, recordAExternal: recordExternal, recordBExternal});\n\n            return handleDetectionResult(detectionResult, candidateId, candidateRecord);\n          } catch (error) {\n            debug(`MatchDetection errored: database record ${candidateId}: ${error}`);\n\n            const matchError = {status: 422, payload: {message: `Matching errored for database record ${candidateId}. ${error.message}.`, id: candidateId}};\n            const newRecordMatchErrors = recordMatchErrors.concat(matchError);\n            return iterateRecords({records: records.slice(1), recordSetSize, maxMatches, matches, recordMatches, recordCount: newRecordCount, recordNonMatches, recordDuplicateCount, recordNonMatchCount, recordMatchErrors: newRecordMatchErrors});\n          }\n        }\n        debug(`Matching for ${candidateId} already done (${recordDuplicateCount} before)`);\n        const newRecordDuplicateCount = recordDuplicateCount + 1;\n        return iterateRecords({records: records.slice(1), recordSetSize, maxMatches, matches, recordMatches, recordCount: newRecordCount, recordNonMatches, recordDuplicateCount: newRecordDuplicateCount, recordNonMatchCount, recordMatchErrors});\n      }\n\n      debug(`No more candidates, record set (${recordCount}/${recordSetSize}) done, ${recordMatches.length} matches found, ${recordDuplicateCount} candidates already handled, ${returnNonMatches ? `${recordNonMatches.length}` : `${recordNonMatchCount}`} nonMatches found.`);\n      return {matches: recordMatches, nonMatches: returnNonMatches ? recordNonMatches : [], duplicateCount: recordDuplicateCount, nonMatchCount: recordNonMatchCount, matchErrors: recordMatchErrors};\n\n      function handleDetectionResult(detectionResult, candidateId, candidateRecord) {\n        debugData(`MatchDetection results for ${candidateId} (${newRecordCount}/${recordSetSize}): ${JSON.stringify(detectionResult)}`);\n\n        if (detectionResult.match || returnNonMatches) {\n          debug(`${detectionResult.match ? `Record ${candidateId} (${newRecordCount}/${recordSetSize}) is a match!` : `Record ${candidateId} (${newRecordCount}/${recordSetSize}) is NOT a match!`}`);\n          debugData(`Strategy: ${JSON.stringify(detectionResult.strategy)}, Threshold: ${JSON.stringify(detectionResult.threshold)}`);\n\n          const matchResult = {\n            probability: Math.round(detectionResult.probability * 100)/100,\n            candidate: {\n              id: candidateId,\n              record: candidateRecord\n            }\n          };\n          const strategyResult = {\n            strategy: detectionResult.strategy,\n            threshold: detectionResult.threshold\n          };\n          const newMatch = returnStrategy ? {...matchResult, ...strategyResult} : {...matchResult};\n\n          debugData(`${JSON.stringify(newMatch)}`);\n\n          return handleRecordMatch(detectionResult.match, newMatch);\n        }\n\n        const newRecordNonMatchCount = recordNonMatchCount + 1;\n        debugData(`- Total nonMatches after this detection: ${newRecordNonMatchCount}`);\n\n        return iterateRecords({records: records.slice(1), recordSetSize, maxMatches, matches, recordMatches, recordCount: newRecordCount, recordNonMatches, recordDuplicateCount, recordNonMatchCount: newRecordNonMatchCount, recordMatchErrors});\n      }\n\n      function handleRecordMatch(isMatch, newMatch) {\n        const newRecordMatches = isMatch ? recordMatches.concat(newMatch) : recordMatches;\n        const newRecordNonMatches = isMatch ? recordNonMatches : recordNonMatches.concat(newMatch);\n        const newRecordNonMatchCount = isMatch ? recordNonMatchCount : recordNonMatchCount + 1;\n\n        debugDev(`- Total matches after this detection: ${matches.concat(newRecordMatches).length} (max: ${maxMatches})`);\n\n        if (returnNonMatches) {\n          debugDev(`- Total nonMatches after this detection: ${nonMatches.concat(newRecordNonMatches).length}`);\n        }\n        debugDev(`- Total nonMatchCount after this detection: ${recordNonMatchCount}`);\n\n        if (maxMatchesFound({matches: matches.concat(newRecordMatches), maxMatches})) {\n          debug(`MaxMatches (${maxMatches}) reached, handled candidates in record set: ${newRecordCount} non-handled candidates in record set ${recordSetSize - newRecordCount}`);\n          return {matches: newRecordMatches, nonMatches: returnNonMatches ? newRecordNonMatches : [], duplicateCount: recordDuplicateCount, nonMatchCount: newRecordNonMatchCount, matchErrors: recordMatchErrors};\n        }\n\n        return iterateRecords({records: records.slice(1), recordSetSize, maxMatches, matches, recordMatches: newRecordMatches, recordCount: newRecordCount, recordNonMatches: returnNonMatches ? newRecordNonMatches : [], recordDuplicateCount, recordNonMatchCount: newRecordNonMatchCount, matchErrors: recordMatchErrors});\n      }\n\n      function candidateNotInMatches(allMatches, candidate) {\n        debug(`Checking that record ${candidate.id} is not already included in ${allMatches.length} matches/nonMatches`);\n        const newCandidateId = candidate.id;\n        debugData(`-- newCandidateId: ${newCandidateId}`);\n        const result = allMatches.find(({candidate}) => candidate.id === newCandidateId);\n        //debugData(`Result: ${JSON.stringify(result)}`);\n        if (result) {\n          debug(`-- ${newCandidateId} was already handled.`);\n          return false;\n        }\n        debugDev(`-- ${newCandidateId} not found in ${allMatches.length} matches/nonMatches`);\n        return true;\n      }\n    }\n\n    function maxMatchesFound({matches, maxMatches}) {\n      if (maxMatches && matches.length >= maxMatches) {\n        debug(`Stopping recordSet iteration: maxMatches (${maxMatches}) for matcher job found.`);\n        return true;\n      }\n    }\n  }\n};\n"],
+  "mappings": "AAAA,OAAO,uBAAuB;AAC9B,OAAO,4BAA4B,qBAAqB;AACxD,OAAO,+BAA+B,oBAAoB;AAG1D,SAAQ,iBAAiB;AAEzB,eAAe,CAAC,EAAC,WAAW,kBAAkB,QAAQ,eAAe,aAAa,GAAG,gBAAgB,IAAI,iBAAiB,OAAO,cAAc,OAAO,mBAAmB,MAAK,MAAM;AAClL,QAAM,QAAQ,kBAAkB,yCAAyC;AACzE,QAAM,YAAY,MAAM,OAAO,MAAM;AACrC,QAAM,WAAW,MAAM,OAAO,KAAK;AAGnC,YAAU,qBAAqB,KAAK,UAAU,gBAAgB,CAAC,EAAE;AACjE,YAAU,kBAAkB,KAAK,UAAU,aAAa,CAAC,EAAE;AAC3D,YAAU,eAAe,KAAK,UAAU,UAAU,CAAC,EAAE;AACrD,YAAU,kBAAkB,KAAK,UAAU,aAAa,CAAC,EAAE;AAC3D,YAAU,mBAAmB,KAAK,UAAU,cAAc,CAAC,EAAE;AAC7D,YAAU,gBAAgB,KAAK,UAAU,WAAW,CAAC,EAAE;AACvD,YAAU,qBAAqB,KAAK,UAAU,gBAAgB,CAAC,EAAE;AAGjE,QAAM,SAAS,yBAAyB,kBAAkB,cAAc;AAExE,SAAO;AAEP,iBAAe,cAAc,EAAC,QAAQ,iBAAiB,EAAC,cAAc,kBAAkB,OAAO,KAAI,EAAC,GAAG;AAErG,UAAM,EAAC,OAAM,IAAI,MAAM,sBAAsB,EAAC,GAAG,eAAe,QAAQ,eAAe,eAAc,CAAC;AACtG,WAAO,QAAQ,CAAC,CAAC;AAgBjB,mBAAe,QAAQ,EAAC,eAAe,CAAC,GAAG,UAAU,CAAC,GAAG,iBAAiB,GAAG,aAAa,CAAC,GAAG,iBAAiB,GAAG,gBAAgB,GAAG,cAAc,CAAC,EAAC,GAAG;AACtJ,gBAAU,kCAAkC;AAC5C,YAAM,EAAC,SAAS,GAAG,MAAK,IAAI,MAAM,OAAO,YAAY;AAErD,eAAS,kBAAkB,KAAK,UAAU,KAAK,CAAC,cAAc,QAAQ,MAAM,qBAAqB,cAAc,iBAAiB,WAAW,MAAM,qBAAqB,cAAc,oBAAoB,aAAa,kBAAkB,YAAY,MAAM,EAAE;AAC3P,YAAM,gBAAgB,QAAQ;AAC9B,YAAM,oBAAoB,iBAAiB;AAE3C,UAAI,gBAAgB,GAAG;AACrB,eAAO,gBAAgB;AAAA,MACzB;AAEA,UAAI,MAAM,cAAc,GAAG;AACzB,cAAM,oBAAoB,MAAM,aAAa,QAAQ,MAAM,KAAK,mBAAmB,MAAM,WAAW,eAAe;AACnH,eAAO,QAAQ,EAAC,cAAc,OAAO,SAAS,gBAAgB,mBAAmB,YAAY,eAAe,gBAAgB,YAAW,CAAC;AAAA,MAC1I;AAEA,YAAM,wEAAwE,QAAQ,MAAM,EAAE;AAC9F,aAAO,aAAa,EAAC,SAAS,OAAO,YAAY,IAAI,YAAY,eAAe,gBAAgB,mBAAmB,gBAAgB,YAAW,CAAC;AAE/I,eAAS,kBAAkB;AACzB,cAAM,0BAA0B,aAAa,qDAAqD,MAAM,aAAa,eAAe,MAAM,KAAK,EAAE;AAEjJ,cAAM,cAAc,eAAe,EAAC,SAAS,eAAe,YAAY,SAAS,YAAY,eAAe,eAAc,CAAC;AAE3H,cAAM,oBAAoB,iBAAiB,YAAY;AACvD,cAAM,mBAAmB,gBAAgB,YAAY;AACrD,cAAM,EAAC,YAAY,eAAe,eAAc,IAAI,kBAAkB,aAAa,SAAS,YAAY,WAAW;AAEnH,YAAI,gBAAgB,EAAC,SAAS,YAAY,WAAU,CAAC,GAAG;AACtD,iBAAO,aAAa,EAAC,SAAS,YAAY,OAAO,YAAY,cAAc,YAAY,eAAe,gBAAgB,mBAAmB,gBAAgB,mBAAmB,eAAe,kBAAkB,aAAa,eAAc,CAAC;AAAA,QAC3O;AAEA,YAAI,uBAAuB,mBAAmB,aAAa,GAAG;AAC5D,iBAAO,aAAa,EAAC,SAAS,YAAY,OAAO,YAAY,iBAAiB,YAAY,eAAe,gBAAgB,mBAAmB,gBAAgB,mBAAmB,eAAe,kBAAkB,aAAa,eAAc,CAAC;AAAA,QAC9O;AAEA,eAAO,QAAQ,EAAC,cAAc,OAAO,SAAS,YAAY,gBAAgB,mBAAmB,YAAY,eAAe,gBAAgB,mBAAmB,eAAe,kBAAkB,aAAa,eAAc,CAAC;AAAA,MAC1N;AAEA,eAAS,kBAAkB,aAAaA,UAASC,aAAYC,cAAa;AACxE,kBAAU,4CAA4C,YAAY,QAAQ,MAAM,EAAE;AAClF,YAAI,kBAAkB;AACpB,oBAAU,+CAA+C,YAAY,WAAW,MAAM,EAAE;AAAA,QAC1F;AAEA,cAAM,aAAaF,SAAQ,OAAO,cAAc,SAAS,YAAY,OAAO,IAAI,YAAY,OAAO;AACnG,cAAM,gBAAgB,mBAAmBC,YAAW,OAAO,cAAc,SAAS,YAAY,UAAU,IAAI,YAAY,UAAU,IAAI,CAAC;AACvI,cAAM,iBAAiBC,aAAY,OAAO,YAAY,WAAW;AAEjE,kBAAU,8BAA8B,WAAW,MAAM,EAAE;AAC3D,YAAI,kBAAkB;AACpB,oBAAU,iCAAiC,cAAc,MAAM,EAAE;AAAA,QACnE;AAEA,kBAAU,gBAAgB,KAAK,UAAU,WAAW,CAAC,EAAE;AACvD,kBAAU,oBAAoB,KAAK,UAAUA,YAAW,CAAC,mCAAmC,KAAK,UAAU,YAAY,WAAW,CAAC,sBAAsB,KAAK,UAAU,cAAc,CAAC,EAAE;AAEzL,kBAAU,kCAAkC,eAAe,MAAM,EAAE;AAEnE,eAAO,EAAC,YAAY,eAAe,eAAc;AAAA,MACnD;AAEA,eAAS,SAASF,UAAS;AACzB,kBAAU,gBAAgB,MAAM,KAAK,aAAa;AAClD,eAAOA,SAAQ,IAAI,CAAC,WAAW,EAAC,GAAG,OAAO,YAAY,MAAM,MAAK,EAAE;AAAA,MACrE;AAEA,eAAS,uBAAuBG,iBAAgBC,gBAAe;AAC7D,kBAAU,gDAAgD,iBAAiB,UAAUA,cAAa,GAAG;AACrG,YAAIA,kBAAiBD,mBAAkBC,gBAAe;AACpD,gBAAM,gEAAgED,eAAc,MAAMC,cAAa,sBAAsB;AAC7H,iBAAO;AAAA,QACT;AAAA,MACF;AAAA,IACF;AAmBA,aAAS,aAAa,EAAC,SAAS,OAAO,YAAY,YAAY,gBAAgB,gBAAgB,eAAe,YAAW,GAAG;AAC1H,YAAM,kBAAkB,YAAY;AACpC,kBAAY,EAAC,SAAS,YAAY,gBAAgB,gBAAgB,eAAe,gBAAe,CAAC;AACjG,YAAM,cAAc,cAAc,OAAO,YAAY,eAAe;AAEpE,YAAM,gBAAgB,mBAAmB,EAAC,SAAS,aAAa,YAAY,eAAc,IAAI,EAAC,SAAS,aAAa,eAAc;AACnI,YAAM,SAAS;AACf,gBAAU,GAAG,KAAK,UAAU,MAAM,CAAC,EAAE;AACrC,aAAO;AAIP,eAAS,YAAY,EAAC,SAAAJ,UAAS,YAAAC,aAAY,gBAAAE,iBAAgB,gBAAAE,iBAAgB,eAAAC,gBAAe,iBAAAC,iBAAe,GAAG;AAC1G,cAAM,aAAaP,SAAQ;AAC3B,kBAAU,sBAAsB,gBAAgB,EAAE;AAClD,cAAM,sBAAsB,mBAAmBC,YAAW,SAASK;AACnE,cAAM,eAAe,aAAa,sBAAsBD;AACxD,cAAM,mBAAmBF,eAAc,cAAc,UAAU,iBAAiB,mBAAmB,qBAAqBE,eAAc,sBAAsBE,gBAAe,EAAE;AAC7K,cAAM,qBAAqB,YAAY,MAAMJ,eAAc,uBAAuB;AAElF,YAAI,iBAAiBA,iBAAgB;AACnC,gBAAM,gCAAgCA,kBAAiB,YAAY,aAAa;AAChF;AAAA,QACF;AACA;AAAA,MACF;AAEA,eAAS,cAAcK,QAAOC,aAAYF,kBAAiB;AACzD,kBAAU,GAAG,KAAK,UAAUC,MAAK,CAAC,EAAE;AACpC,cAAM,UAAUD,gBAAe,uDAAuD;AACtF,cAAM,gBAAgBC,OAAM,WAAW,sCAAsCA,OAAM,mBAAmBA,OAAM,mBAAmBA,OAAM,YAAY,4BAA4BA,OAAM,eAAeA,OAAM,qBAAqB,mBAAmBA,OAAM,aAAa,MAAM,MAAMA,OAAM,YAAY,EAAE;AAEnS,kBAAU,gBAAgBC,WAAU,GAAG;AAEvC,cAAM,eAAeD,OAAM,mBAAmBA,OAAM,mBAAmBA,OAAM;AAC7E,cAAM,eAAe,eAAeA,OAAM,eAAeA,OAAM,wBAAwB;AACvF,kBAAU,iBAAiB,YAAY,EAAE;AAKzC,YAAIA,OAAM,cAAc,KAAK,eAAe,KAAKA,OAAM,aAAa,SAAS,KAAKD,mBAAkB,GAAG;AACrG,gBAAM,yBAAyBC,OAAM,aAAa,SAAS,IAAI,iBAAiB;AAChF,gBAAM,wBAAwBD,mBAAkB,IAAI,gBAAgB;AACpE,gBAAM,gBAAgBE,gBAAe,MAAMA,gBAAe,SAAY,0BAA0B,wBAAwBA;AACxH,oBAAU,4BAA4B,sBAAsB,GAAG;AAC/D,oBAAU,0BAA0B,qBAAqB,GAAG;AAC5D,oBAAU,mBAAmB,aAAa,GAAG;AAC7C,gBAAM,qBAAqB;AAC3B,iBAAO,EAAC,QAAQ,OAAO,YAAY,cAAa;AAAA,QAClD;AAEA,cAAM,oBAAoB;AAC1B,eAAO,EAAC,QAAQ,MAAM,YAAAA,YAAU;AAAA,MAClC;AAAA,IACF;AAOA,aAAS,eAAe,EAAC,SAAS,eAAe,YAAAC,aAAY,UAAU,CAAC,GAAG,aAAa,CAAC,GAAG,gBAAgB,CAAC,GAAG,mBAAmB,CAAC,GAAG,cAAc,GAAG,uBAAuB,GAAG,sBAAsB,GAAG,oBAAoB,CAAC,EAAC,GAAG;AAelO,YAAM,CAAC,SAAS,IAAI;AACpB,YAAM,iBAAiB,YAAY,cAAc,IAAI;AAerD,UAAI,WAAW;AACb,cAAM,EAAC,QAAQ,iBAAiB,IAAI,YAAW,IAAI;AACnD,cAAM,aAAa,QAAQ,OAAO,UAAU;AAC5C,YAAI,sBAAsB,YAAY,SAAS,GAAG;AAChD,gBAAM,kBAAkB,EAAC,IAAI,UAAU,IAAI,cAAc,kBAAkB,OAAO,MAAM,UAAU,EAAE,GAAE;AACtG,cAAI;AACF,kBAAM,qCAAqC,WAAW,KAAK,cAAc,IAAI,aAAa,GAAG;AAE7F,kBAAM,kBAAkB,OAAO,EAAC,SAAS,QAAQ,SAAS,iBAAiB,iBAAiB,gBAAgB,gBAAe,CAAC;AAE5H,mBAAO,sBAAsB,iBAAiB,aAAa,eAAe;AAAA,UAC5E,SAAS,OAAO;AACd,kBAAM,2CAA2C,WAAW,KAAK,KAAK,EAAE;AAExE,kBAAM,aAAa,EAAC,QAAQ,KAAK,SAAS,EAAC,SAAS,wCAAwC,WAAW,KAAK,MAAM,OAAO,KAAK,IAAI,YAAW,EAAC;AAC9I,kBAAM,uBAAuB,kBAAkB,OAAO,UAAU;AAChE,mBAAO,eAAe,EAAC,SAAS,QAAQ,MAAM,CAAC,GAAG,eAAe,YAAAA,aAAY,SAAS,eAAe,aAAa,gBAAgB,kBAAkB,sBAAsB,qBAAqB,mBAAmB,qBAAoB,CAAC;AAAA,UACzO;AAAA,QACF;AACA,cAAM,gBAAgB,WAAW,kBAAkB,oBAAoB,UAAU;AACjF,cAAM,0BAA0B,uBAAuB;AACvD,eAAO,eAAe,EAAC,SAAS,QAAQ,MAAM,CAAC,GAAG,eAAe,YAAAA,aAAY,SAAS,eAAe,aAAa,gBAAgB,kBAAkB,sBAAsB,yBAAyB,qBAAqB,kBAAiB,CAAC;AAAA,MAC5O;AAEA,YAAM,mCAAmC,WAAW,IAAI,aAAa,WAAW,cAAc,MAAM,mBAAmB,oBAAoB,gCAAgC,mBAAmB,GAAG,iBAAiB,MAAM,KAAK,GAAG,mBAAmB,EAAE,oBAAoB;AACzQ,aAAO,EAAC,SAAS,eAAe,YAAY,mBAAmB,mBAAmB,CAAC,GAAG,gBAAgB,sBAAsB,eAAe,qBAAqB,aAAa,kBAAiB;AAE9L,eAAS,sBAAsB,iBAAiB,aAAa,iBAAiB;AAC5E,kBAAU,8BAA8B,WAAW,KAAK,cAAc,IAAI,aAAa,MAAM,KAAK,UAAU,eAAe,CAAC,EAAE;AAE9H,YAAI,gBAAgB,SAAS,kBAAkB;AAC7C,gBAAM,GAAG,gBAAgB,QAAQ,UAAU,WAAW,KAAK,cAAc,IAAI,aAAa,kBAAkB,UAAU,WAAW,KAAK,cAAc,IAAI,aAAa,mBAAmB,EAAE;AAC1L,oBAAU,aAAa,KAAK,UAAU,gBAAgB,QAAQ,CAAC,gBAAgB,KAAK,UAAU,gBAAgB,SAAS,CAAC,EAAE;AAE1H,gBAAM,cAAc;AAAA,YAClB,aAAa,KAAK,MAAM,gBAAgB,cAAc,GAAG,IAAE;AAAA,YAC3D,WAAW;AAAA,cACT,IAAI;AAAA,cACJ,QAAQ;AAAA,YACV;AAAA,UACF;AACA,gBAAM,iBAAiB;AAAA,YACrB,UAAU,gBAAgB;AAAA,YAC1B,WAAW,gBAAgB;AAAA,UAC7B;AACA,gBAAM,WAAW,iBAAiB,EAAC,GAAG,aAAa,GAAG,eAAc,IAAI,EAAC,GAAG,YAAW;AAEvF,oBAAU,GAAG,KAAK,UAAU,QAAQ,CAAC,EAAE;AAEvC,iBAAO,kBAAkB,gBAAgB,OAAO,QAAQ;AAAA,QAC1D;AAEA,cAAM,yBAAyB,sBAAsB;AACrD,kBAAU,4CAA4C,sBAAsB,EAAE;AAE9E,eAAO,eAAe,EAAC,SAAS,QAAQ,MAAM,CAAC,GAAG,eAAe,YAAAA,aAAY,SAAS,eAAe,aAAa,gBAAgB,kBAAkB,sBAAsB,qBAAqB,wBAAwB,kBAAiB,CAAC;AAAA,MAC3O;AAEA,eAAS,kBAAkB,SAAS,UAAU;AAC5C,cAAM,mBAAmB,UAAU,cAAc,OAAO,QAAQ,IAAI;AACpE,cAAM,sBAAsB,UAAU,mBAAmB,iBAAiB,OAAO,QAAQ;AACzF,cAAM,yBAAyB,UAAU,sBAAsB,sBAAsB;AAErF,iBAAS,yCAAyC,QAAQ,OAAO,gBAAgB,EAAE,MAAM,UAAUA,WAAU,GAAG;AAEhH,YAAI,kBAAkB;AACpB,mBAAS,4CAA4C,WAAW,OAAO,mBAAmB,EAAE,MAAM,EAAE;AAAA,QACtG;AACA,iBAAS,+CAA+C,mBAAmB,EAAE;AAE7E,YAAI,gBAAgB,EAAC,SAAS,QAAQ,OAAO,gBAAgB,GAAG,YAAAA,YAAU,CAAC,GAAG;AAC5E,gBAAM,eAAeA,WAAU,gDAAgD,cAAc,yCAAyC,gBAAgB,cAAc,EAAE;AACtK,iBAAO,EAAC,SAAS,kBAAkB,YAAY,mBAAmB,sBAAsB,CAAC,GAAG,gBAAgB,sBAAsB,eAAe,wBAAwB,aAAa,kBAAiB;AAAA,QACzM;AAEA,eAAO,eAAe,EAAC,SAAS,QAAQ,MAAM,CAAC,GAAG,eAAe,YAAAA,aAAY,SAAS,eAAe,kBAAkB,aAAa,gBAAgB,kBAAkB,mBAAmB,sBAAsB,CAAC,GAAG,sBAAsB,qBAAqB,wBAAwB,aAAa,kBAAiB,CAAC;AAAA,MACvT;AAEA,eAAS,sBAAsB,YAAYC,YAAW;AACpD,cAAM,wBAAwBA,WAAU,EAAE,+BAA+B,WAAW,MAAM,qBAAqB;AAC/G,cAAM,iBAAiBA,WAAU;AACjC,kBAAU,sBAAsB,cAAc,EAAE;AAChD,cAAM,SAAS,WAAW,KAAK,CAAC,EAAC,WAAAA,WAAS,MAAMA,WAAU,OAAO,cAAc;AAE/E,YAAI,QAAQ;AACV,gBAAM,MAAM,cAAc,uBAAuB;AACjD,iBAAO;AAAA,QACT;AACA,iBAAS,MAAM,cAAc,iBAAiB,WAAW,MAAM,qBAAqB;AACpF,eAAO;AAAA,MACT;AAAA,IACF;AAEA,aAAS,gBAAgB,EAAC,SAAS,YAAAD,YAAU,GAAG;AAC9C,UAAIA,eAAc,QAAQ,UAAUA,aAAY;AAC9C,cAAM,6CAA6CA,WAAU,0BAA0B;AACvF,eAAO;AAAA,MACT;AAAA,IACF;AAAA,EACF;AACF;",
   "names": ["matches", "nonMatches", "matchErrors", "candidateCount", "maxCandidates", "duplicateCount", "nonMatchCount", "matchErrorCount", "state", "stopReason", "maxMatches", "candidate"]
 }

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

@@ -1,7 +1,7 @@
 {
   "version": 3,
   "sources": ["../../../../src/match-detection/features/bib/publication-time-allow-cons-years-multi.js"],
-  "sourcesContent": ["\nimport createDebugLogger from 'debug';\nimport {testStringOrNumber} from '../../../matching-utils.js';\n\n// We should also get copyright time and copyright/publication times from 26x\n// We should also get publishing time type from f008\n// We should get reprint times from f500 $a \"Lis\u00E4painos/Lis\u00E4painokset:\"\n\nexport default () => ({\n  name: 'Publication time, allow consequent years, years from multiple sources',\n  extract: ({record, recordExternal}) => {\n    const debug = createDebugLogger('@natlibfi/melinda-record-matching:match-detection:features/bib/publication-time-allow-cons-years-multi');\n    const label = recordExternal && recordExternal.label ? recordExternal.label : 'record';\n\n    const f008Values = extractF008Values(record);\n    debug(`${label}: f008: ${JSON.stringify(f008Values)}`);\n\n    const f26xValues = extractF26xValues(record);\n    debug(`${label}: f26x: ${JSON.stringify(f26xValues)}`);\n\n    const f500Values = extractF500Years(record);\n    debug(`${label}: f500: ${JSON.stringify(f500Values)}`);\n\n    // We should get copyrightYear from f008Date2 to copyrightYears when f008YearType = 'r'\n    // Is the original year (f008Date2) in f008YearType === 'r' comparable to copyrightYear?\n    // We should handle unknown years (here or comparison?)\n    // We should handle year ranges for continuing resources / collections\n\n    const normalYears = [...new Set(f26xValues.normalYears.concat(f008Values.f008Date1).filter(value => value && value !== '    ' && value !== '||||'))].sort();\n    const copyrightYears = [...new Set(f26xValues.copyrightYears)].sort();\n    const reprintYears = [...new Set(f500Values)].sort();\n\n    const combined = {normalYears, copyrightYears, reprintYears};\n\n    debug(`Combined: ${JSON.stringify(combined)}`);\n\n    return combined;\n\n    function extractF008Values(record) {\n      // Record should have only one f008 - in case of several, we handle the first one\n      const value = record.get(/^008$/u)?.[0]?.value || undefined;\n      if (value && testStringOrNumber(value)) {\n        const f008Date1 = extractF008Date1(value);\n        const f008Date2 = extractF008Date2(value);\n        const f008YearType = extractF008YearType(value);\n        return {f008Date1, f008Date2, f008YearType};\n      }\n      return {f008Date1: undefined, f008Date2: undefined, f008YearType: undefined};\n\n      function extractF008Date1(value) {\n        return String(value).slice(7, 11);\n      }\n\n      function extractF008Date2(value) {\n        return String(value).slice(11, 15);\n      }\n\n      function extractF008YearType(value) {\n        return String(value).slice(6, 7);\n      }\n    }\n\n    function extractF26xValues(record) {\n      const copyrightRegex = /^(?<copyrightPrefix>cop|cop.|c|\u00A9|p|\u2117)/u;\n\n      const pubNormalSubFieldValues = extractPubNormalSubfieldValues(record, copyrightRegex);\n      debug(`Normal years: ${JSON.stringify(pubNormalSubFieldValues)}`);\n\n      const pubF264CopySubFieldValues = extractPubF264CopySubfieldValues(record);\n      debug(`F264 copyright years: ${JSON.stringify(pubF264CopySubFieldValues)}`);\n\n      const pubF260CopySubFieldValues = extractPubF260CopySubfieldValues(record, copyrightRegex);\n      debug(`F260 copyright years: ${JSON.stringify(pubF260CopySubFieldValues)}`);\n\n      return {normalYears: pubNormalSubFieldValues, copyrightYears: [...pubF260CopySubFieldValues, ...pubF264CopySubFieldValues]};\n\n      function extractPubNormalSubfieldValues(record, copyrightRegex) {\n        return record.get(/^26[04]$/u)\n          .filter((field) => !(field.tag === '264' && field.ind2 === '4'))\n          .map(({subfields}) => subfields)\n          .flat()\n          .filter(({code}) => code && code === 'c')\n          .filter(({value}) => value && !copyrightRegex.test(value))\n          .map(({value}) => value)\n          .map((value) => removeNonAlphaNumeric(value));\n      }\n\n      function extractPubF264CopySubfieldValues(record, copyrightRegex) {\n        return record.get(/^264$/u)\n          .filter((field) => field.ind2 === '4')\n          .map(({subfields}) => subfields)\n          .flat()\n          .filter(({code}) => code && code === 'c')\n          .filter(({value}) => value)\n          .map(({value}) => value)\n          .map((value) => value.replace(copyrightRegex, ''))\n          .map((value) => removeNonAlphaNumeric(value));\n      }\n\n      function extractPubF260CopySubfieldValues(record, copyrightRegex) {\n        return record.get(/^260$/u)\n          .map(({subfields}) => subfields)\n          .flat()\n          .filter(({code}) => code && code === 'c')\n          .filter(({value}) => value && copyrightRegex.test(value))\n          .map(({value}) => value)\n          .map((value) => value.replace(copyrightRegex, ''))\n          .map((value) => removeNonAlphaNumeric(value));\n      }\n\n      function removeNonAlphaNumeric(value) {\n        debug(`Cleaning: ${JSON.stringify(value)}`);\n        const nonAlphaNumericRegex = /[^A-Za-z0-9]/ug;\n        return value ? value.replace(nonAlphaNumericRegex, '') : value;\n      }\n    }\n\n    function extractF500Years(record) {\n\n      const reprintRegex = /(?<reprint>Lis\u00E4painokset:|Lis\u00E4painos:)/u;\n      const reprintFieldContents = record.get(/^500$/u)\n        .map(({subfields}) => subfields)\n        .flat()\n        .filter(({code}) => code === 'a')\n        .map(({value}) => value);\n      //.filter(value => value.test(reprintRegex));\n\n      debug(`f500 reprint field contents: ${JSON.stringify(reprintFieldContents)}`);\n\n      const filteredF500 = reprintFieldContents.filter((content) => content && content.match(reprintRegex));\n\n      debug(`f500 reprint field contents (filtered): ${JSON.stringify(filteredF500)}`);\n\n      const reprintYears = extractReprintYears(filteredF500);\n\n      return reprintYears;\n    }\n\n    function extractReprintYears(contents) {\n      const yearRegex = /[0-9][0-9][0-9][0-9]/gu;\n      const years = contents.map(content => content.match(yearRegex))\n        .flat();\n      debug(`${JSON.stringify(years)}`);\n      const uniqYears = [...new Set(years)].sort();\n      debug(`${JSON.stringify(uniqYears)}`);\n      return uniqYears;\n    }\n\n  },\n  compare: (a, b) => {\n    const debug = createDebugLogger('@natlibfi/melinda-record-matching:match-detection:features/bib/publication-time-allow-cons-years-multi');\n    debug(`Comparing ${JSON.stringify(a)} to ${JSON.stringify(b)}`);\n\n    const [firstA] = a.normalYears ? a.normalYears : a;\n    const [firstB] = b.normalYears ? b.normalYears : b;\n\n    debug(`Comparing ${JSON.stringify(firstA)} to ${JSON.stringify(firstB)}`);\n\n    if (firstA === firstB) {\n      return 0.1;\n    }\n\n    // If either of years is a non string/number, values are not comparable\n    if (!testStringOrNumber(firstA) || !testStringOrNumber(firstB)) {\n      return 0;\n    }\n\n    const firstANumber = parseInt(firstA, 10);\n    const firstBNumber = parseInt(firstB, 10);\n\n    // Handle consequent years as a match\n    // see publication-time for a version that does not handle consequent years as a match\n    if (!(isNaN(firstANumber) || isNaN(firstBNumber)) &&\n      (firstANumber + 1 === firstBNumber || firstANumber - 1 === firstBNumber)) {\n      return 0.1;\n    }\n\n    // We should do something with copyrightYears, too\n\n    // Do not give minus points if a normal publishing year is found in normal years\n    const bNormalInANormal = a.normalYears.filter(aValue => b.normalYears.some(bValue => aValue === bValue));\n    const aNormalInBNormal = b.normalYears.filter(bValue => a.normalYears.some(aValue => bValue === aValue));\n    debug(`BNorm in ANorm: ${JSON.stringify(bNormalInANormal)}`);\n    debug(`ANorm in BNorm: ${JSON.stringify(aNormalInBNormal)}`);\n\n    if (bNormalInANormal > 0 || aNormalInBNormal > 0) {\n      return 0;\n    }\n\n    // Do not give minus points if a normal publishing year is found in reprint years\n    const bNormalInAReprint = a.reprintYears.filter(aValue => b.normalYears.some(bValue => aValue === bValue));\n    const aNormalInBReprint = b.reprintYears.filter(bValue => a.normalYears.some(aValue => bValue === aValue));\n    debug(`BNorm in AReprint: ${JSON.stringify(bNormalInAReprint)}`);\n    debug(`ANorm in BReprint: ${JSON.stringify(aNormalInBReprint)}`);\n\n    if (bNormalInAReprint > 0 || aNormalInBReprint > 0) {\n      return 0;\n    }\n\n    // Do not give minus points if a normal publishing year is found in copyright years\n    const bNormalInACopyright = a.copyrightYears.filter(aValue => b.normalYears.some(bValue => aValue === bValue));\n    const aNormalInBCopyright= b.copyrightYears.filter(bValue => a.normalYears.some(aValue => bValue === aValue));\n    debug(`BNorm in ACopyright: ${JSON.stringify(bNormalInACopyright)}`);\n    debug(`ANorm in BCopyright: ${JSON.stringify(aNormalInBCopyright)}`);\n\n    if (bNormalInACopyright > 0 || aNormalInBCopyright > 0) {\n      return 0;\n    }\n\n\n\n\n\n    return -1;\n\n  }\n});\n\n// https://www.loc.gov/marc/bibliographic/bd008.html\n// field 008\n// 06 - Type of date/Publication status\n// 07-10 - Date 1\n// 11-14 - Date 2\n//\n// 06 - Type of date/Publication status\n// b - No dates given; B.C. date involved\n// c - Continuing resource currently published\n// d - Continuing resource ceased publication\n// e - Detailed date\n// i - Inclusive dates of collection\n// k - Range of years of bulk of collection\n// m - Multiple dates\n// n - Dates unknown\n// p - Date of distribution/release/issue and production/recording session when different\n// q - Questionable date\n// r - Reprint/reissue date and original date\n// s - Single known date/probable date\n// t - Publication date and copyright date\n// u - Continuing resource status unknown\n// | - No attempt to code\n//\n// 07-10 - Date 1\n// 1-9 - Date digit\n// # - Date element is not applicable\n// u - Date element is totally or partially unknown\n// |||| - No attempt to code\n//\n// 11-14 - Date 2\n// 1-9 - Date digit\n// # - Date element is not applicable\n// u - Date element is totally or partially unknown\n// |||| - No attempt to code\n//\n\n"],
-  "mappings": "AACA,OAAO,uBAAuB;AAC9B,SAAQ,0BAAyB;AAMjC,eAAe,OAAO;AAAA,EACpB,MAAM;AAAA,EACN,SAAS,CAAC,EAAC,QAAQ,eAAc,MAAM;AACrC,UAAM,QAAQ,kBAAkB,wGAAwG;AACxI,UAAM,QAAQ,kBAAkB,eAAe,QAAQ,eAAe,QAAQ;AAE9E,UAAM,aAAa,kBAAkB,MAAM;AAC3C,UAAM,GAAG,KAAK,WAAW,KAAK,UAAU,UAAU,CAAC,EAAE;AAErD,UAAM,aAAa,kBAAkB,MAAM;AAC3C,UAAM,GAAG,KAAK,WAAW,KAAK,UAAU,UAAU,CAAC,EAAE;AAErD,UAAM,aAAa,iBAAiB,MAAM;AAC1C,UAAM,GAAG,KAAK,WAAW,KAAK,UAAU,UAAU,CAAC,EAAE;AAOrD,UAAM,cAAc,CAAC,GAAG,IAAI,IAAI,WAAW,YAAY,OAAO,WAAW,SAAS,EAAE,OAAO,WAAS,SAAS,UAAU,UAAU,UAAU,MAAM,CAAC,CAAC,EAAE,KAAK;AAC1J,UAAM,iBAAiB,CAAC,GAAG,IAAI,IAAI,WAAW,cAAc,CAAC,EAAE,KAAK;AACpE,UAAM,eAAe,CAAC,GAAG,IAAI,IAAI,UAAU,CAAC,EAAE,KAAK;AAEnD,UAAM,WAAW,EAAC,aAAa,gBAAgB,aAAY;AAE3D,UAAM,aAAa,KAAK,UAAU,QAAQ,CAAC,EAAE;AAE7C,WAAO;AAEP,aAAS,kBAAkBA,SAAQ;AAEjC,YAAM,QAAQA,QAAO,IAAI,QAAQ,IAAI,CAAC,GAAG,SAAS;AAClD,UAAI,SAAS,mBAAmB,KAAK,GAAG;AACtC,cAAM,YAAY,iBAAiB,KAAK;AACxC,cAAM,YAAY,iBAAiB,KAAK;AACxC,cAAM,eAAe,oBAAoB,KAAK;AAC9C,eAAO,EAAC,WAAW,WAAW,aAAY;AAAA,MAC5C;AACA,aAAO,EAAC,WAAW,QAAW,WAAW,QAAW,cAAc,OAAS;AAE3E,eAAS,iBAAiBC,QAAO;AAC/B,eAAO,OAAOA,MAAK,EAAE,MAAM,GAAG,EAAE;AAAA,MAClC;AAEA,eAAS,iBAAiBA,QAAO;AAC/B,eAAO,OAAOA,MAAK,EAAE,MAAM,IAAI,EAAE;AAAA,MACnC;AAEA,eAAS,oBAAoBA,QAAO;AAClC,eAAO,OAAOA,MAAK,EAAE,MAAM,GAAG,CAAC;AAAA,MACjC;AAAA,IACF;AAEA,aAAS,kBAAkBD,SAAQ;AACjC,YAAM,iBAAiB;AAEvB,YAAM,0BAA0B,+BAA+BA,SAAQ,cAAc;AACrF,YAAM,iBAAiB,KAAK,UAAU,uBAAuB,CAAC,EAAE;AAEhE,YAAM,4BAA4B,iCAAiCA,OAAM;AACzE,YAAM,yBAAyB,KAAK,UAAU,yBAAyB,CAAC,EAAE;AAE1E,YAAM,4BAA4B,iCAAiCA,SAAQ,cAAc;AACzF,YAAM,yBAAyB,KAAK,UAAU,yBAAyB,CAAC,EAAE;AAE1E,aAAO,EAAC,aAAa,yBAAyB,gBAAgB,CAAC,GAAG,2BAA2B,GAAG,yBAAyB,EAAC;AAE1H,eAAS,+BAA+BA,SAAQE,iBAAgB;AAC9D,eAAOF,QAAO,IAAI,WAAW,EAC1B,OAAO,CAAC,UAAU,EAAE,MAAM,QAAQ,SAAS,MAAM,SAAS,IAAI,EAC9D,IAAI,CAAC,EAAC,UAAS,MAAM,SAAS,EAC9B,KAAK,EACL,OAAO,CAAC,EAAC,KAAI,MAAM,QAAQ,SAAS,GAAG,EACvC,OAAO,CAAC,EAAC,MAAK,MAAM,SAAS,CAACE,gBAAe,KAAK,KAAK,CAAC,EACxD,IAAI,CAAC,EAAC,MAAK,MAAM,KAAK,EACtB,IAAI,CAAC,UAAU,sBAAsB,KAAK,CAAC;AAAA,MAChD;AAEA,eAAS,iCAAiCF,SAAQE,iBAAgB;AAChE,eAAOF,QAAO,IAAI,QAAQ,EACvB,OAAO,CAAC,UAAU,MAAM,SAAS,GAAG,EACpC,IAAI,CAAC,EAAC,UAAS,MAAM,SAAS,EAC9B,KAAK,EACL,OAAO,CAAC,EAAC,KAAI,MAAM,QAAQ,SAAS,GAAG,EACvC,OAAO,CAAC,EAAC,MAAK,MAAM,KAAK,EACzB,IAAI,CAAC,EAAC,MAAK,MAAM,KAAK,EACtB,IAAI,CAAC,UAAU,MAAM,QAAQE,iBAAgB,EAAE,CAAC,EAChD,IAAI,CAAC,UAAU,sBAAsB,KAAK,CAAC;AAAA,MAChD;AAEA,eAAS,iCAAiCF,SAAQE,iBAAgB;AAChE,eAAOF,QAAO,IAAI,QAAQ,EACvB,IAAI,CAAC,EAAC,UAAS,MAAM,SAAS,EAC9B,KAAK,EACL,OAAO,CAAC,EAAC,KAAI,MAAM,QAAQ,SAAS,GAAG,EACvC,OAAO,CAAC,EAAC,MAAK,MAAM,SAASE,gBAAe,KAAK,KAAK,CAAC,EACvD,IAAI,CAAC,EAAC,MAAK,MAAM,KAAK,EACtB,IAAI,CAAC,UAAU,MAAM,QAAQA,iBAAgB,EAAE,CAAC,EAChD,IAAI,CAAC,UAAU,sBAAsB,KAAK,CAAC;AAAA,MAChD;AAEA,eAAS,sBAAsB,OAAO;AACpC,cAAM,aAAa,KAAK,UAAU,KAAK,CAAC,EAAE;AAC1C,cAAM,uBAAuB;AAC7B,eAAO,QAAQ,MAAM,QAAQ,sBAAsB,EAAE,IAAI;AAAA,MAC3D;AAAA,IACF;AAEA,aAAS,iBAAiBF,SAAQ;AAEhC,YAAM,eAAe;AACrB,YAAM,uBAAuBA,QAAO,IAAI,QAAQ,EAC7C,IAAI,CAAC,EAAC,UAAS,MAAM,SAAS,EAC9B,KAAK,EACL,OAAO,CAAC,EAAC,KAAI,MAAM,SAAS,GAAG,EAC/B,IAAI,CAAC,EAAC,MAAK,MAAM,KAAK;AAGzB,YAAM,gCAAgC,KAAK,UAAU,oBAAoB,CAAC,EAAE;AAE5E,YAAM,eAAe,qBAAqB,OAAO,CAAC,YAAY,WAAW,QAAQ,MAAM,YAAY,CAAC;AAEpG,YAAM,2CAA2C,KAAK,UAAU,YAAY,CAAC,EAAE;AAE/E,YAAMG,gBAAe,oBAAoB,YAAY;AAErD,aAAOA;AAAA,IACT;AAEA,aAAS,oBAAoB,UAAU;AACrC,YAAM,YAAY;AAClB,YAAM,QAAQ,SAAS,IAAI,aAAW,QAAQ,MAAM,SAAS,CAAC,EAC3D,KAAK;AACR,YAAM,GAAG,KAAK,UAAU,KAAK,CAAC,EAAE;AAChC,YAAM,YAAY,CAAC,GAAG,IAAI,IAAI,KAAK,CAAC,EAAE,KAAK;AAC3C,YAAM,GAAG,KAAK,UAAU,SAAS,CAAC,EAAE;AACpC,aAAO;AAAA,IACT;AAAA,EAEF;AAAA,EACA,SAAS,CAAC,GAAG,MAAM;AACjB,UAAM,QAAQ,kBAAkB,wGAAwG;AACxI,UAAM,aAAa,KAAK,UAAU,CAAC,CAAC,OAAO,KAAK,UAAU,CAAC,CAAC,EAAE;AAE9D,UAAM,CAAC,MAAM,IAAI,EAAE,cAAc,EAAE,cAAc;AACjD,UAAM,CAAC,MAAM,IAAI,EAAE,cAAc,EAAE,cAAc;AAEjD,UAAM,aAAa,KAAK,UAAU,MAAM,CAAC,OAAO,KAAK,UAAU,MAAM,CAAC,EAAE;AAExE,QAAI,WAAW,QAAQ;AACrB,aAAO;AAAA,IACT;AAGA,QAAI,CAAC,mBAAmB,MAAM,KAAK,CAAC,mBAAmB,MAAM,GAAG;AAC9D,aAAO;AAAA,IACT;AAEA,UAAM,eAAe,SAAS,QAAQ,EAAE;AACxC,UAAM,eAAe,SAAS,QAAQ,EAAE;AAIxC,QAAI,EAAE,MAAM,YAAY,KAAK,MAAM,YAAY,OAC5C,eAAe,MAAM,gBAAgB,eAAe,MAAM,eAAe;AAC1E,aAAO;AAAA,IACT;AAKA,UAAM,mBAAmB,EAAE,YAAY,OAAO,YAAU,EAAE,YAAY,KAAK,YAAU,WAAW,MAAM,CAAC;AACvG,UAAM,mBAAmB,EAAE,YAAY,OAAO,YAAU,EAAE,YAAY,KAAK,YAAU,WAAW,MAAM,CAAC;AACvG,UAAM,mBAAmB,KAAK,UAAU,gBAAgB,CAAC,EAAE;AAC3D,UAAM,mBAAmB,KAAK,UAAU,gBAAgB,CAAC,EAAE;AAE3D,QAAI,mBAAmB,KAAK,mBAAmB,GAAG;AAChD,aAAO;AAAA,IACT;AAGA,UAAM,oBAAoB,EAAE,aAAa,OAAO,YAAU,EAAE,YAAY,KAAK,YAAU,WAAW,MAAM,CAAC;AACzG,UAAM,oBAAoB,EAAE,aAAa,OAAO,YAAU,EAAE,YAAY,KAAK,YAAU,WAAW,MAAM,CAAC;AACzG,UAAM,sBAAsB,KAAK,UAAU,iBAAiB,CAAC,EAAE;AAC/D,UAAM,sBAAsB,KAAK,UAAU,iBAAiB,CAAC,EAAE;AAE/D,QAAI,oBAAoB,KAAK,oBAAoB,GAAG;AAClD,aAAO;AAAA,IACT;AAGA,UAAM,sBAAsB,EAAE,eAAe,OAAO,YAAU,EAAE,YAAY,KAAK,YAAU,WAAW,MAAM,CAAC;AAC7G,UAAM,sBAAqB,EAAE,eAAe,OAAO,YAAU,EAAE,YAAY,KAAK,YAAU,WAAW,MAAM,CAAC;AAC5G,UAAM,wBAAwB,KAAK,UAAU,mBAAmB,CAAC,EAAE;AACnE,UAAM,wBAAwB,KAAK,UAAU,mBAAmB,CAAC,EAAE;AAEnE,QAAI,sBAAsB,KAAK,sBAAsB,GAAG;AACtD,aAAO;AAAA,IACT;AAMA,WAAO;AAAA,EAET;AACF;",
+  "sourcesContent": ["\nimport createDebugLogger from 'debug';\nimport {testStringOrNumber} from '../../../matching-utils.js';\n\n// We should also get copyright time and copyright/publication times from 26x\n// We should also get publishing time type from f008\n// We should get reprint times from f500 $a \"Lis\u00E4painos/Lis\u00E4painokset:\"\n\nexport default () => ({\n  name: 'Publication time, allow consequent years, years from multiple sources',\n  extract: ({record, recordExternal}) => {\n    const debug = createDebugLogger('@natlibfi/melinda-record-matching:match-detection:features/bib/publication-time-allow-cons-years-multi');\n    const label = recordExternal && recordExternal.label ? recordExternal.label : 'record';\n\n    const f008Values = extractF008Values(record);\n    debug(`${label}: f008: ${JSON.stringify(f008Values)}`);\n\n    const f26xValues = extractF26xValues(record);\n    debug(`${label}: f26x: ${JSON.stringify(f26xValues)}`);\n\n    const f500Values = extractF500Years(record);\n    debug(`${label}: f500: ${JSON.stringify(f500Values)}`);\n\n    // We should get copyrightYear from f008Date2 to copyrightYears when f008YearType = 'r'\n    // Is the original year (f008Date2) in f008YearType === 'r' comparable to copyrightYear?\n    // We should handle unknown years (here or comparison?)\n    // We should handle year ranges for continuing resources / collections\n\n    const normalYears = [...new Set(f26xValues.normalYears.concat(f008Values.f008Date1).filter(value => value && value !== '    ' && value !== '||||'))].sort();\n    const copyrightYears = [...new Set(f26xValues.copyrightYears)].sort();\n    const reprintYears = [...new Set(f500Values)].sort();\n\n    const combined = {normalYears, copyrightYears, reprintYears};\n\n    debug(`Combined: ${JSON.stringify(combined)}`);\n\n    return combined;\n\n    function extractF008Values(record) {\n      // Record should have only one f008 - in case of several, we handle the first one\n      const value = record.get(/^008$/u)?.[0]?.value || undefined;\n      if (value && testStringOrNumber(value)) {\n        const f008Date1 = extractF008Date1(value);\n        const f008Date2 = extractF008Date2(value);\n        const f008YearType = extractF008YearType(value);\n        return {f008Date1, f008Date2, f008YearType};\n      }\n      return {f008Date1: undefined, f008Date2: undefined, f008YearType: undefined};\n\n      function extractF008Date1(value) {\n        return String(value).slice(7, 11);\n      }\n\n      function extractF008Date2(value) {\n        return String(value).slice(11, 15);\n      }\n\n      function extractF008YearType(value) {\n        return String(value).slice(6, 7);\n      }\n    }\n\n    function extractF26xValues(record) {\n      const copyrightRegex = /^(?<copyrightPrefix>cop|cop.|c|\u00A9|p|\u2117)/u;\n\n      const pubNormalSubFieldValues = extractPubNormalSubfieldValues(record, copyrightRegex);\n      debug(`Normal years: ${JSON.stringify(pubNormalSubFieldValues)}`);\n\n      const pubF264CopySubFieldValues = extractPubF264CopySubfieldValues(record);\n      debug(`F264 copyright years: ${JSON.stringify(pubF264CopySubFieldValues)}`);\n\n      const pubF260CopySubFieldValues = extractPubF260CopySubfieldValues(record, copyrightRegex);\n      debug(`F260 copyright years: ${JSON.stringify(pubF260CopySubFieldValues)}`);\n\n      return {normalYears: pubNormalSubFieldValues, copyrightYears: [...pubF260CopySubFieldValues, ...pubF264CopySubFieldValues]};\n\n      function extractPubNormalSubfieldValues(record, copyrightRegex) {\n        return record.get(/^26[04]$/u)\n          .filter((field) => !(field.tag === '264' && field.ind2 === '4'))\n          .map(({subfields}) => subfields)\n          .flat()\n          .filter(({code}) => code && code === 'c')\n          .filter(({value}) => value && !copyrightRegex.test(value))\n          .map(({value}) => value)\n          .map((value) => removeNonAlphaNumeric(value));\n      }\n\n      function extractPubF264CopySubfieldValues(record, copyrightRegex) {\n        return record.get(/^264$/u)\n          .filter((field) => field.ind2 === '4')\n          .map(({subfields}) => subfields)\n          .flat()\n          .filter(({code}) => code && code === 'c')\n          .filter(({value}) => value)\n          .map(({value}) => value)\n          .map((value) => value.replace(copyrightRegex, ''))\n          .map((value) => removeNonAlphaNumeric(value));\n      }\n\n      function extractPubF260CopySubfieldValues(record, copyrightRegex) {\n        return record.get(/^260$/u)\n          .map(({subfields}) => subfields)\n          .flat()\n          .filter(({code}) => code && code === 'c')\n          .filter(({value}) => value && copyrightRegex.test(value))\n          .map(({value}) => value)\n          .map((value) => value.replace(copyrightRegex, ''))\n          .map((value) => removeNonAlphaNumeric(value));\n      }\n\n      function removeNonAlphaNumeric(value) {\n        debug(`Cleaning: ${JSON.stringify(value)}`);\n        const nonAlphaNumericRegex = /[^A-Za-z0-9]/ug;\n        return value ? value.replace(nonAlphaNumericRegex, '') : value;\n      }\n    }\n\n    function extractF500Years(record) {\n\n      const reprintRegex = /(?<reprint>Lis\u00E4painokset:|Lis\u00E4painos:)/u;\n      const reprintFieldContents = record.get(/^500$/u)\n        .map(({subfields}) => subfields)\n        .flat()\n        .filter(({code}) => code === 'a')\n        .map(({value}) => value);\n      //.filter(value => value.test(reprintRegex));\n\n      debug(`f500 reprint field contents: ${JSON.stringify(reprintFieldContents)}`);\n\n      const filteredF500 = reprintFieldContents.filter((content) => content && content.match(reprintRegex));\n\n      debug(`f500 reprint field contents (filtered): ${JSON.stringify(filteredF500)}`);\n\n      const reprintYears = extractReprintYears(filteredF500);\n\n      return reprintYears;\n    }\n\n    function extractReprintYears(contents) {\n      const yearRegex = /[0-9][0-9][0-9][0-9]/gu;\n      const years = contents.map(content => content.match(yearRegex))\n        .flat();\n      debug(`${JSON.stringify(years)}`);\n      const uniqYears = [...new Set(years)].sort();\n      debug(`${JSON.stringify(uniqYears)}`);\n      return uniqYears;\n    }\n\n  },\n  compare: (a, b) => {\n    const debug = createDebugLogger('@natlibfi/melinda-record-matching:match-detection:features/bib/publication-time-allow-cons-years-multi');\n    debug(`Comparing ${JSON.stringify(a)} to ${JSON.stringify(b)}`);\n\n    const [firstA] = a.normalYears ? a.normalYears : a;\n    const [firstB] = b.normalYears ? b.normalYears : b;\n\n    debug(`Comparing ${JSON.stringify(firstA)} to ${JSON.stringify(firstB)}`);\n\n    if (firstA === firstB) {\n      return 0.1;\n    }\n\n    // If either of years is a non string/number, values are not comparable\n    if (!testStringOrNumber(firstA) || !testStringOrNumber(firstB)) {\n      return 0;\n    }\n\n    const firstANumber = parseInt(firstA, 10);\n    const firstBNumber = parseInt(firstB, 10);\n\n    // Handle consequent years as a match\n    // see publication-time for a version that does not handle consequent years as a match\n    if (!(isNaN(firstANumber) || isNaN(firstBNumber)) &&\n      (firstANumber + 1 === firstBNumber || firstANumber - 1 === firstBNumber)) {\n      return 0.1;\n    }\n\n    // We should do something with copyrightYears, too\n\n    // Do not give minus points if a normal publishing year is found in normal years\n    const bNormalInANormal = a.normalYears.filter(aValue => b.normalYears.some(bValue => aValue === bValue));\n    const aNormalInBNormal = b.normalYears.filter(bValue => a.normalYears.some(aValue => bValue === aValue));\n    debug(`BNorm in ANorm: ${JSON.stringify(bNormalInANormal)}`);\n    debug(`ANorm in BNorm: ${JSON.stringify(aNormalInBNormal)}`);\n\n    if (bNormalInANormal > 0 || aNormalInBNormal > 0) {\n      return 0;\n    }\n\n    // Do not give minus points if a normal publishing year is found in reprint years\n    const bNormalInAReprint = a.reprintYears.filter(aValue => b.normalYears.some(bValue => aValue === bValue));\n    const aNormalInBReprint = b.reprintYears.filter(bValue => a.normalYears.some(aValue => bValue === aValue));\n    debug(`BNorm in AReprint: ${JSON.stringify(bNormalInAReprint)}`);\n    debug(`ANorm in BReprint: ${JSON.stringify(aNormalInBReprint)}`);\n\n    if (bNormalInAReprint > 0 || aNormalInBReprint > 0) {\n      return 0;\n    }\n\n    // Do not give minus points if a normal publishing year is found in copyright years\n\n    const bNormalInACopyright = a.copyrightYears.filter(aValue => b.normalYears.some(bValue => aValue === bValue));\n    const aNormalInBCopyright= b.copyrightYears.filter(bValue => a.normalYears.some(aValue => bValue === aValue));\n    debug(`BNorm in ACopyright: ${JSON.stringify(bNormalInACopyright)}`);\n    debug(`ANorm in BCopyright: ${JSON.stringify(aNormalInBCopyright)}`);\n\n    if (bNormalInACopyright > 0 || aNormalInBCopyright > 0) {\n      return 0;\n    }\n\n\n\n\n\n    return -1;\n\n  }\n});\n\n// https://www.loc.gov/marc/bibliographic/bd008.html\n// field 008\n// 06 - Type of date/Publication status\n// 07-10 - Date 1\n// 11-14 - Date 2\n//\n// 06 - Type of date/Publication status\n// b - No dates given; B.C. date involved\n// c - Continuing resource currently published\n// d - Continuing resource ceased publication\n// e - Detailed date\n// i - Inclusive dates of collection\n// k - Range of years of bulk of collection\n// m - Multiple dates\n// n - Dates unknown\n// p - Date of distribution/release/issue and production/recording session when different\n// q - Questionable date\n// r - Reprint/reissue date and original date\n// s - Single known date/probable date\n// t - Publication date and copyright date\n// u - Continuing resource status unknown\n// | - No attempt to code\n//\n// 07-10 - Date 1\n// 1-9 - Date digit\n// # - Date element is not applicable\n// u - Date element is totally or partially unknown\n// |||| - No attempt to code\n//\n// 11-14 - Date 2\n// 1-9 - Date digit\n// # - Date element is not applicable\n// u - Date element is totally or partially unknown\n// |||| - No attempt to code\n//\n\n"],
+  "mappings": "AACA,OAAO,uBAAuB;AAC9B,SAAQ,0BAAyB;AAMjC,eAAe,OAAO;AAAA,EACpB,MAAM;AAAA,EACN,SAAS,CAAC,EAAC,QAAQ,eAAc,MAAM;AACrC,UAAM,QAAQ,kBAAkB,wGAAwG;AACxI,UAAM,QAAQ,kBAAkB,eAAe,QAAQ,eAAe,QAAQ;AAE9E,UAAM,aAAa,kBAAkB,MAAM;AAC3C,UAAM,GAAG,KAAK,WAAW,KAAK,UAAU,UAAU,CAAC,EAAE;AAErD,UAAM,aAAa,kBAAkB,MAAM;AAC3C,UAAM,GAAG,KAAK,WAAW,KAAK,UAAU,UAAU,CAAC,EAAE;AAErD,UAAM,aAAa,iBAAiB,MAAM;AAC1C,UAAM,GAAG,KAAK,WAAW,KAAK,UAAU,UAAU,CAAC,EAAE;AAOrD,UAAM,cAAc,CAAC,GAAG,IAAI,IAAI,WAAW,YAAY,OAAO,WAAW,SAAS,EAAE,OAAO,WAAS,SAAS,UAAU,UAAU,UAAU,MAAM,CAAC,CAAC,EAAE,KAAK;AAC1J,UAAM,iBAAiB,CAAC,GAAG,IAAI,IAAI,WAAW,cAAc,CAAC,EAAE,KAAK;AACpE,UAAM,eAAe,CAAC,GAAG,IAAI,IAAI,UAAU,CAAC,EAAE,KAAK;AAEnD,UAAM,WAAW,EAAC,aAAa,gBAAgB,aAAY;AAE3D,UAAM,aAAa,KAAK,UAAU,QAAQ,CAAC,EAAE;AAE7C,WAAO;AAEP,aAAS,kBAAkBA,SAAQ;AAEjC,YAAM,QAAQA,QAAO,IAAI,QAAQ,IAAI,CAAC,GAAG,SAAS;AAClD,UAAI,SAAS,mBAAmB,KAAK,GAAG;AACtC,cAAM,YAAY,iBAAiB,KAAK;AACxC,cAAM,YAAY,iBAAiB,KAAK;AACxC,cAAM,eAAe,oBAAoB,KAAK;AAC9C,eAAO,EAAC,WAAW,WAAW,aAAY;AAAA,MAC5C;AACA,aAAO,EAAC,WAAW,QAAW,WAAW,QAAW,cAAc,OAAS;AAE3E,eAAS,iBAAiBC,QAAO;AAC/B,eAAO,OAAOA,MAAK,EAAE,MAAM,GAAG,EAAE;AAAA,MAClC;AAEA,eAAS,iBAAiBA,QAAO;AAC/B,eAAO,OAAOA,MAAK,EAAE,MAAM,IAAI,EAAE;AAAA,MACnC;AAEA,eAAS,oBAAoBA,QAAO;AAClC,eAAO,OAAOA,MAAK,EAAE,MAAM,GAAG,CAAC;AAAA,MACjC;AAAA,IACF;AAEA,aAAS,kBAAkBD,SAAQ;AACjC,YAAM,iBAAiB;AAEvB,YAAM,0BAA0B,+BAA+BA,SAAQ,cAAc;AACrF,YAAM,iBAAiB,KAAK,UAAU,uBAAuB,CAAC,EAAE;AAEhE,YAAM,4BAA4B,iCAAiCA,OAAM;AACzE,YAAM,yBAAyB,KAAK,UAAU,yBAAyB,CAAC,EAAE;AAE1E,YAAM,4BAA4B,iCAAiCA,SAAQ,cAAc;AACzF,YAAM,yBAAyB,KAAK,UAAU,yBAAyB,CAAC,EAAE;AAE1E,aAAO,EAAC,aAAa,yBAAyB,gBAAgB,CAAC,GAAG,2BAA2B,GAAG,yBAAyB,EAAC;AAE1H,eAAS,+BAA+BA,SAAQE,iBAAgB;AAC9D,eAAOF,QAAO,IAAI,WAAW,EAC1B,OAAO,CAAC,UAAU,EAAE,MAAM,QAAQ,SAAS,MAAM,SAAS,IAAI,EAC9D,IAAI,CAAC,EAAC,UAAS,MAAM,SAAS,EAC9B,KAAK,EACL,OAAO,CAAC,EAAC,KAAI,MAAM,QAAQ,SAAS,GAAG,EACvC,OAAO,CAAC,EAAC,MAAK,MAAM,SAAS,CAACE,gBAAe,KAAK,KAAK,CAAC,EACxD,IAAI,CAAC,EAAC,MAAK,MAAM,KAAK,EACtB,IAAI,CAAC,UAAU,sBAAsB,KAAK,CAAC;AAAA,MAChD;AAEA,eAAS,iCAAiCF,SAAQE,iBAAgB;AAChE,eAAOF,QAAO,IAAI,QAAQ,EACvB,OAAO,CAAC,UAAU,MAAM,SAAS,GAAG,EACpC,IAAI,CAAC,EAAC,UAAS,MAAM,SAAS,EAC9B,KAAK,EACL,OAAO,CAAC,EAAC,KAAI,MAAM,QAAQ,SAAS,GAAG,EACvC,OAAO,CAAC,EAAC,MAAK,MAAM,KAAK,EACzB,IAAI,CAAC,EAAC,MAAK,MAAM,KAAK,EACtB,IAAI,CAAC,UAAU,MAAM,QAAQE,iBAAgB,EAAE,CAAC,EAChD,IAAI,CAAC,UAAU,sBAAsB,KAAK,CAAC;AAAA,MAChD;AAEA,eAAS,iCAAiCF,SAAQE,iBAAgB;AAChE,eAAOF,QAAO,IAAI,QAAQ,EACvB,IAAI,CAAC,EAAC,UAAS,MAAM,SAAS,EAC9B,KAAK,EACL,OAAO,CAAC,EAAC,KAAI,MAAM,QAAQ,SAAS,GAAG,EACvC,OAAO,CAAC,EAAC,MAAK,MAAM,SAASE,gBAAe,KAAK,KAAK,CAAC,EACvD,IAAI,CAAC,EAAC,MAAK,MAAM,KAAK,EACtB,IAAI,CAAC,UAAU,MAAM,QAAQA,iBAAgB,EAAE,CAAC,EAChD,IAAI,CAAC,UAAU,sBAAsB,KAAK,CAAC;AAAA,MAChD;AAEA,eAAS,sBAAsB,OAAO;AACpC,cAAM,aAAa,KAAK,UAAU,KAAK,CAAC,EAAE;AAC1C,cAAM,uBAAuB;AAC7B,eAAO,QAAQ,MAAM,QAAQ,sBAAsB,EAAE,IAAI;AAAA,MAC3D;AAAA,IACF;AAEA,aAAS,iBAAiBF,SAAQ;AAEhC,YAAM,eAAe;AACrB,YAAM,uBAAuBA,QAAO,IAAI,QAAQ,EAC7C,IAAI,CAAC,EAAC,UAAS,MAAM,SAAS,EAC9B,KAAK,EACL,OAAO,CAAC,EAAC,KAAI,MAAM,SAAS,GAAG,EAC/B,IAAI,CAAC,EAAC,MAAK,MAAM,KAAK;AAGzB,YAAM,gCAAgC,KAAK,UAAU,oBAAoB,CAAC,EAAE;AAE5E,YAAM,eAAe,qBAAqB,OAAO,CAAC,YAAY,WAAW,QAAQ,MAAM,YAAY,CAAC;AAEpG,YAAM,2CAA2C,KAAK,UAAU,YAAY,CAAC,EAAE;AAE/E,YAAMG,gBAAe,oBAAoB,YAAY;AAErD,aAAOA;AAAA,IACT;AAEA,aAAS,oBAAoB,UAAU;AACrC,YAAM,YAAY;AAClB,YAAM,QAAQ,SAAS,IAAI,aAAW,QAAQ,MAAM,SAAS,CAAC,EAC3D,KAAK;AACR,YAAM,GAAG,KAAK,UAAU,KAAK,CAAC,EAAE;AAChC,YAAM,YAAY,CAAC,GAAG,IAAI,IAAI,KAAK,CAAC,EAAE,KAAK;AAC3C,YAAM,GAAG,KAAK,UAAU,SAAS,CAAC,EAAE;AACpC,aAAO;AAAA,IACT;AAAA,EAEF;AAAA,EACA,SAAS,CAAC,GAAG,MAAM;AACjB,UAAM,QAAQ,kBAAkB,wGAAwG;AACxI,UAAM,aAAa,KAAK,UAAU,CAAC,CAAC,OAAO,KAAK,UAAU,CAAC,CAAC,EAAE;AAE9D,UAAM,CAAC,MAAM,IAAI,EAAE,cAAc,EAAE,cAAc;AACjD,UAAM,CAAC,MAAM,IAAI,EAAE,cAAc,EAAE,cAAc;AAEjD,UAAM,aAAa,KAAK,UAAU,MAAM,CAAC,OAAO,KAAK,UAAU,MAAM,CAAC,EAAE;AAExE,QAAI,WAAW,QAAQ;AACrB,aAAO;AAAA,IACT;AAGA,QAAI,CAAC,mBAAmB,MAAM,KAAK,CAAC,mBAAmB,MAAM,GAAG;AAC9D,aAAO;AAAA,IACT;AAEA,UAAM,eAAe,SAAS,QAAQ,EAAE;AACxC,UAAM,eAAe,SAAS,QAAQ,EAAE;AAIxC,QAAI,EAAE,MAAM,YAAY,KAAK,MAAM,YAAY,OAC5C,eAAe,MAAM,gBAAgB,eAAe,MAAM,eAAe;AAC1E,aAAO;AAAA,IACT;AAKA,UAAM,mBAAmB,EAAE,YAAY,OAAO,YAAU,EAAE,YAAY,KAAK,YAAU,WAAW,MAAM,CAAC;AACvG,UAAM,mBAAmB,EAAE,YAAY,OAAO,YAAU,EAAE,YAAY,KAAK,YAAU,WAAW,MAAM,CAAC;AACvG,UAAM,mBAAmB,KAAK,UAAU,gBAAgB,CAAC,EAAE;AAC3D,UAAM,mBAAmB,KAAK,UAAU,gBAAgB,CAAC,EAAE;AAE3D,QAAI,mBAAmB,KAAK,mBAAmB,GAAG;AAChD,aAAO;AAAA,IACT;AAGA,UAAM,oBAAoB,EAAE,aAAa,OAAO,YAAU,EAAE,YAAY,KAAK,YAAU,WAAW,MAAM,CAAC;AACzG,UAAM,oBAAoB,EAAE,aAAa,OAAO,YAAU,EAAE,YAAY,KAAK,YAAU,WAAW,MAAM,CAAC;AACzG,UAAM,sBAAsB,KAAK,UAAU,iBAAiB,CAAC,EAAE;AAC/D,UAAM,sBAAsB,KAAK,UAAU,iBAAiB,CAAC,EAAE;AAE/D,QAAI,oBAAoB,KAAK,oBAAoB,GAAG;AAClD,aAAO;AAAA,IACT;AAIA,UAAM,sBAAsB,EAAE,eAAe,OAAO,YAAU,EAAE,YAAY,KAAK,YAAU,WAAW,MAAM,CAAC;AAC7G,UAAM,sBAAqB,EAAE,eAAe,OAAO,YAAU,EAAE,YAAY,KAAK,YAAU,WAAW,MAAM,CAAC;AAC5G,UAAM,wBAAwB,KAAK,UAAU,mBAAmB,CAAC,EAAE;AACnE,UAAM,wBAAwB,KAAK,UAAU,mBAAmB,CAAC,EAAE;AAEnE,QAAI,sBAAsB,KAAK,sBAAsB,GAAG;AACtD,aAAO;AAAA,IACT;AAMA,WAAO;AAAA,EAET;AACF;",
   "names": ["record", "value", "copyrightRegex", "reprintYears"]
 }

package/dist/matching-utils.js

@@ -91,8 +91,8 @@ export function stringBefore(string, substring) {
   return string.substring(0, pos);
 }
 export function preferenceSortRecords(x, y) {
-  debug(`sortRecords: RECORD COMPARISON
-${JSON.stringify(x)} vs
+  debug(`sortRecords: RECORD COMPARISON`);
+  debugData(`{JSON.stringify(x)} vs
 ${JSON.stringify(y)}`);
   const xFikka = hasLow(x.record, "FIKKA");
   const yFikka = hasLow(y.record, "FIKKA");

package/dist/matching-utils.js.map

@@ -1,7 +1,7 @@
 {
   "version": 3,
   "sources": ["../src/matching-utils.js"],
-  "sourcesContent": ["import createDebugLogger from 'debug';\n\nconst debug = createDebugLogger('@natlibfi/melinda-record-matching:utils');\nconst debugData = debug.extend('data');\n\nexport function getMelindaIdsF035(record) {\n\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:melinda-id');\n  const debugData = debug.extend('data');\n\n  const f035s = record.getFields('035');\n\n  if (f035s.length < 1) {\n    debug(`No f035s found.`);\n    return [];\n  }\n\n  const allF035MelindaIds = [].concat(...f035s.map(field => toMelindaIds(field)));\n  const f035MelindaIds = [...new Set(allF035MelindaIds)];\n\n  debugData(`Fields (${f035s.length}): ${JSON.stringify(f035s)}`);\n  debugData(`Ids (${allF035MelindaIds.length}): ${JSON.stringify(allF035MelindaIds)}`);\n  debugData(`Unique ids (${f035MelindaIds.length}): ${JSON.stringify(f035MelindaIds)}`);\n\n  return f035MelindaIds;\n}\n\nexport function toMelindaIds({subfields}, subfieldsToParse = ['a', 'z']) {\n  const melindaIdRegExp = /^(?<prefix>\\(FI-MELINDA\\)|FCC)(?<id>\\d{9})$/u;\n\n  return subfields\n    .filter(sub => subfieldsToParse.includes(sub.code))\n    .filter(sub => testStringOrNumber(sub.value) && melindaIdRegExp.test(String(sub.value)))\n    .map(({value}) => testStringOrNumber(value) ? String(value).replace(melindaIdRegExp, '$<id>') : '');\n}\n\nexport function validateSidFieldSubfieldCounts(field) {\n  // Valid SID-fields have just one $c and one $b\n  debugData(`Validating SID field ${JSON.stringify(field)}`);\n  const countC = countSubfields(field, 'c');\n  const countB = countSubfields(field, 'b');\n  debug(`Found ${countC} sf $cs and ${countB} sf $bs. IsValid: ${countC === 1 && countB === 1}`);\n\n  return countC === 1 && countB === 1;\n}\n\nfunction countSubfields(field, subfieldCode) {\n  // debug(`Counting subfields ${subfieldCode}`);\n  return field.subfields.filter(({code}) => code === subfieldCode).length;\n}\n\nexport function getSubfieldValues(field, subfieldCode) {\n  debugData(`Get subfield(s) $${subfieldCode} from ${JSON.stringify(field)}`);\n  return field.subfields\n    .filter(({code}) => code === subfieldCode)\n    .map(({value}) => testStringOrNumber(value) ? String(value) : '')\n    .filter(value => value);\n}\n\nexport function testStringOrNumber(value) {\n  if (typeof value === 'string' || typeof value === 'number') {\n    return true;\n  }\n  return false;\n}\n\nexport function extractSubfieldsFromField(field, subfieldCodes) {\n  if (field === undefined || field.subfields === undefined) {\n    return [];\n  }\n  const resultSubfields = field.subfields\n    .filter(({code}) => subfieldCodes.includes(code))\n    .map(({code, value}) => ({code, value: testStringOrNumber(value) ? String(value) : ''}))\n    .filter(value => value);\n  return resultSubfields;\n}\n\nexport function uniqueSubfields(subfields) {\n  return subfields.reduce((arr, e) => {\n    if (!arr.find(item => item.code === e.code && item.value === e.value)) {\n      const newArr = arr.concat(e);\n      return newArr;\n    }\n    return arr;\n  }, []);\n}\n\nexport function getMatchCounts(aValues, bValues) {\n\n  const matchingValues = getMatchingValuesAmount(aValues, bValues);\n\n  return {\n    maxValues: aValues.length > bValues.length ? aValues.length : bValues.length,\n    // possibleMatchingValues: amount of identifiers in set of less identifiers (we cannot more values than these)\n    possibleMatchValues: aValues.length > bValues.length ? bValues.length : aValues.length,\n    matchingValues\n  };\n\n  function getMatchingValuesAmount(aValues, bValues) {\n    if (bValues.length > aValues.length) {\n      return aValues.filter(aValue => bValues.some(bValue => aValue === bValue)).length;\n    }\n    if (aValues.length > bValues.length) {\n      return bValues.filter(bValue => aValues.some(aValue => bValue === aValue)).length;\n    }\n\n    // If we have same amount of values, we'll check matches both ways, to avoid mixups in cases\n    // there would be duplicate values\n    const aToB = aValues.filter(aValue => bValues.some(bValue => aValue === bValue)).length;\n    const bToA = bValues.filter(bValue => aValues.some(aValue => bValue === aValue)).length;\n\n    return aToB < bToA ? aToB : bToA;\n  }\n}\n\n\nexport function stringAfter(string, substring) {\n  const pos = string.indexOf(substring);\n  if (pos === -1) {\n    return string;\n  }\n  return string.substring(pos+substring.length);\n}\n\nexport function stringBefore(string, substring) {\n  const pos = string.indexOf(substring);\n  if (pos === -1) {\n    return string;\n  }\n  return string.substring(0, pos);\n}\n\n// We sort records here (put FIKKA and low-cased records first, ref MELINDA-3492)\n// NB! this only sorts the records the current set. If the best stuff would come in a later set and this set contains good enough record, we'll never reach the best...\n// Still this would alleviate the issue when maxMatches === 1...\nexport function preferenceSortRecords(x, y) {\n  debug(`sortRecords: RECORD COMPARISON\\n${JSON.stringify(x)} vs\\n${JSON.stringify(y)}`);\n  // Prefer the record with a FIKKA LOW tag:\n  const xFikka = hasLow(x.record, 'FIKKA');\n  const yFikka = hasLow(y.record, 'FIKKA');\n\n  if (xFikka && !yFikka) {\n    debug('sortRecords: prefer FIKKA');\n    return -1;\n  }\n  if (yFikka && !xFikka) {\n    return 1;\n  }\n\n  // Prefer downcased:\n  const xAllCaps = hasAllCapsTitle(x.record);\n  const yAllCaps = hasAllCapsTitle(y.record);\n\n  if (!xAllCaps && yAllCaps) {\n    debug('sortRecords: prefer non-all caps');\n    return -1; // x is better\n  }\n  if (!yAllCaps && xAllCaps) {\n    return 1; // y is better\n  }\n  // Default:\n  return 0;\n\n  function hasLow(record, lowTag) {\n    return record.fields?.some(f => f.tag === 'LOW' && f.subfields?.some(sf => sf.code === 'a' && sf.value === lowTag));\n  }\n\n  function hasAllCapsTitle(record) {\n    const f245 = record.fields?.find(f => f.tag === '245');\n    if (!f245) {\n      debugData(`WARNING: No f245 found for ALL CAPS check`);\n      return false;\n    }\n\n    const title = f245.subfields.filter(sf => ['a', 'b', 'c'].includes(sf.code)).map(sf => sf.value).join(' ');\n    if (title.match(/[A-Z]/u) && !title.match(/[a-z]/u)) {\n      return true;\n    }\n    return false;\n  }\n}"],
-  "mappings": "AAAA,OAAO,uBAAuB;AAE9B,MAAM,QAAQ,kBAAkB,yCAAyC;AACzE,MAAM,YAAY,MAAM,OAAO,MAAM;AAE9B,gBAAS,kBAAkB,QAAQ;AAExC,QAAMA,SAAQ,kBAAkB,8CAA8C;AAC9E,QAAMC,aAAYD,OAAM,OAAO,MAAM;AAErC,QAAM,QAAQ,OAAO,UAAU,KAAK;AAEpC,MAAI,MAAM,SAAS,GAAG;AACpB,IAAAA,OAAM,iBAAiB;AACvB,WAAO,CAAC;AAAA,EACV;AAEA,QAAM,oBAAoB,CAAC,EAAE,OAAO,GAAG,MAAM,IAAI,WAAS,aAAa,KAAK,CAAC,CAAC;AAC9E,QAAM,iBAAiB,CAAC,GAAG,IAAI,IAAI,iBAAiB,CAAC;AAErD,EAAAC,WAAU,WAAW,MAAM,MAAM,MAAM,KAAK,UAAU,KAAK,CAAC,EAAE;AAC9D,EAAAA,WAAU,QAAQ,kBAAkB,MAAM,MAAM,KAAK,UAAU,iBAAiB,CAAC,EAAE;AACnF,EAAAA,WAAU,eAAe,eAAe,MAAM,MAAM,KAAK,UAAU,cAAc,CAAC,EAAE;AAEpF,SAAO;AACT;AAEO,gBAAS,aAAa,EAAC,UAAS,GAAG,mBAAmB,CAAC,KAAK,GAAG,GAAG;AACvE,QAAM,kBAAkB;AAExB,SAAO,UACJ,OAAO,SAAO,iBAAiB,SAAS,IAAI,IAAI,CAAC,EACjD,OAAO,SAAO,mBAAmB,IAAI,KAAK,KAAK,gBAAgB,KAAK,OAAO,IAAI,KAAK,CAAC,CAAC,EACtF,IAAI,CAAC,EAAC,MAAK,MAAM,mBAAmB,KAAK,IAAI,OAAO,KAAK,EAAE,QAAQ,iBAAiB,OAAO,IAAI,EAAE;AACtG;AAEO,gBAAS,+BAA+B,OAAO;AAEpD,YAAU,wBAAwB,KAAK,UAAU,KAAK,CAAC,EAAE;AACzD,QAAM,SAAS,eAAe,OAAO,GAAG;AACxC,QAAM,SAAS,eAAe,OAAO,GAAG;AACxC,QAAM,SAAS,MAAM,eAAe,MAAM,qBAAqB,WAAW,KAAK,WAAW,CAAC,EAAE;AAE7F,SAAO,WAAW,KAAK,WAAW;AACpC;AAEA,SAAS,eAAe,OAAO,cAAc;AAE3C,SAAO,MAAM,UAAU,OAAO,CAAC,EAAC,KAAI,MAAM,SAAS,YAAY,EAAE;AACnE;AAEO,gBAAS,kBAAkB,OAAO,cAAc;AACrD,YAAU,oBAAoB,YAAY,SAAS,KAAK,UAAU,KAAK,CAAC,EAAE;AAC1E,SAAO,MAAM,UACV,OAAO,CAAC,EAAC,KAAI,MAAM,SAAS,YAAY,EACxC,IAAI,CAAC,EAAC,MAAK,MAAM,mBAAmB,KAAK,IAAI,OAAO,KAAK,IAAI,EAAE,EAC/D,OAAO,WAAS,KAAK;AAC1B;AAEO,gBAAS,mBAAmB,OAAO;AACxC,MAAI,OAAO,UAAU,YAAY,OAAO,UAAU,UAAU;AAC1D,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAEO,gBAAS,0BAA0B,OAAO,eAAe;AAC9D,MAAI,UAAU,UAAa,MAAM,cAAc,QAAW;AACxD,WAAO,CAAC;AAAA,EACV;AACA,QAAM,kBAAkB,MAAM,UAC3B,OAAO,CAAC,EAAC,KAAI,MAAM,cAAc,SAAS,IAAI,CAAC,EAC/C,IAAI,CAAC,EAAC,MAAM,MAAK,OAAO,EAAC,MAAM,OAAO,mBAAmB,KAAK,IAAI,OAAO,KAAK,IAAI,GAAE,EAAE,EACtF,OAAO,WAAS,KAAK;AACxB,SAAO;AACT;AAEO,gBAAS,gBAAgB,WAAW;AACzC,SAAO,UAAU,OAAO,CAAC,KAAK,MAAM;AAClC,QAAI,CAAC,IAAI,KAAK,UAAQ,KAAK,SAAS,EAAE,QAAQ,KAAK,UAAU,EAAE,KAAK,GAAG;AACrE,YAAM,SAAS,IAAI,OAAO,CAAC;AAC3B,aAAO;AAAA,IACT;AACA,WAAO;AAAA,EACT,GAAG,CAAC,CAAC;AACP;AAEO,gBAAS,eAAe,SAAS,SAAS;AAE/C,QAAM,iBAAiB,wBAAwB,SAAS,OAAO;AAE/D,SAAO;AAAA,IACL,WAAW,QAAQ,SAAS,QAAQ,SAAS,QAAQ,SAAS,QAAQ;AAAA;AAAA,IAEtE,qBAAqB,QAAQ,SAAS,QAAQ,SAAS,QAAQ,SAAS,QAAQ;AAAA,IAChF;AAAA,EACF;AAEA,WAAS,wBAAwBC,UAASC,UAAS;AACjD,QAAIA,SAAQ,SAASD,SAAQ,QAAQ;AACnC,aAAOA,SAAQ,OAAO,YAAUC,SAAQ,KAAK,YAAU,WAAW,MAAM,CAAC,EAAE;AAAA,IAC7E;AACA,QAAID,SAAQ,SAASC,SAAQ,QAAQ;AACnC,aAAOA,SAAQ,OAAO,YAAUD,SAAQ,KAAK,YAAU,WAAW,MAAM,CAAC,EAAE;AAAA,IAC7E;AAIA,UAAM,OAAOA,SAAQ,OAAO,YAAUC,SAAQ,KAAK,YAAU,WAAW,MAAM,CAAC,EAAE;AACjF,UAAM,OAAOA,SAAQ,OAAO,YAAUD,SAAQ,KAAK,YAAU,WAAW,MAAM,CAAC,EAAE;AAEjF,WAAO,OAAO,OAAO,OAAO;AAAA,EAC9B;AACF;AAGO,gBAAS,YAAY,QAAQ,WAAW;AAC7C,QAAM,MAAM,OAAO,QAAQ,SAAS;AACpC,MAAI,QAAQ,IAAI;AACd,WAAO;AAAA,EACT;AACA,SAAO,OAAO,UAAU,MAAI,UAAU,MAAM;AAC9C;AAEO,gBAAS,aAAa,QAAQ,WAAW;AAC9C,QAAM,MAAM,OAAO,QAAQ,SAAS;AACpC,MAAI,QAAQ,IAAI;AACd,WAAO;AAAA,EACT;AACA,SAAO,OAAO,UAAU,GAAG,GAAG;AAChC;AAKO,gBAAS,sBAAsB,GAAG,GAAG;AAC1C,QAAM;AAAA,EAAmC,KAAK,UAAU,CAAC,CAAC;AAAA,EAAQ,KAAK,UAAU,CAAC,CAAC,EAAE;AAErF,QAAM,SAAS,OAAO,EAAE,QAAQ,OAAO;AACvC,QAAM,SAAS,OAAO,EAAE,QAAQ,OAAO;AAEvC,MAAI,UAAU,CAAC,QAAQ;AACrB,UAAM,2BAA2B;AACjC,WAAO;AAAA,EACT;AACA,MAAI,UAAU,CAAC,QAAQ;AACrB,WAAO;AAAA,EACT;AAGA,QAAM,WAAW,gBAAgB,EAAE,MAAM;AACzC,QAAM,WAAW,gBAAgB,EAAE,MAAM;AAEzC,MAAI,CAAC,YAAY,UAAU;AACzB,UAAM,kCAAkC;AACxC,WAAO;AAAA,EACT;AACA,MAAI,CAAC,YAAY,UAAU;AACzB,WAAO;AAAA,EACT;AAEA,SAAO;AAEP,WAAS,OAAO,QAAQ,QAAQ;AAC9B,WAAO,OAAO,QAAQ,KAAK,OAAK,EAAE,QAAQ,SAAS,EAAE,WAAW,KAAK,QAAM,GAAG,SAAS,OAAO,GAAG,UAAU,MAAM,CAAC;AAAA,EACpH;AAEA,WAAS,gBAAgB,QAAQ;AAC/B,UAAM,OAAO,OAAO,QAAQ,KAAK,OAAK,EAAE,QAAQ,KAAK;AACrD,QAAI,CAAC,MAAM;AACT,gBAAU,2CAA2C;AACrD,aAAO;AAAA,IACT;AAEA,UAAM,QAAQ,KAAK,UAAU,OAAO,QAAM,CAAC,KAAK,KAAK,GAAG,EAAE,SAAS,GAAG,IAAI,CAAC,EAAE,IAAI,QAAM,GAAG,KAAK,EAAE,KAAK,GAAG;AACzG,QAAI,MAAM,MAAM,QAAQ,KAAK,CAAC,MAAM,MAAM,QAAQ,GAAG;AACnD,aAAO;AAAA,IACT;AACA,WAAO;AAAA,EACT;AACF;",
+  "sourcesContent": ["import createDebugLogger from 'debug';\n\nconst debug = createDebugLogger('@natlibfi/melinda-record-matching:utils');\nconst debugData = debug.extend('data');\n\nexport function getMelindaIdsF035(record) {\n\n  const debug = createDebugLogger('@natlibfi/melinda-record-matching:melinda-id');\n  const debugData = debug.extend('data');\n\n  const f035s = record.getFields('035');\n\n  if (f035s.length < 1) {\n    debug(`No f035s found.`);\n    return [];\n  }\n\n  const allF035MelindaIds = [].concat(...f035s.map(field => toMelindaIds(field)));\n  const f035MelindaIds = [...new Set(allF035MelindaIds)];\n\n  debugData(`Fields (${f035s.length}): ${JSON.stringify(f035s)}`);\n  debugData(`Ids (${allF035MelindaIds.length}): ${JSON.stringify(allF035MelindaIds)}`);\n  debugData(`Unique ids (${f035MelindaIds.length}): ${JSON.stringify(f035MelindaIds)}`);\n\n  return f035MelindaIds;\n}\n\nexport function toMelindaIds({subfields}, subfieldsToParse = ['a', 'z']) {\n  const melindaIdRegExp = /^(?<prefix>\\(FI-MELINDA\\)|FCC)(?<id>\\d{9})$/u;\n\n  return subfields\n    .filter(sub => subfieldsToParse.includes(sub.code))\n    .filter(sub => testStringOrNumber(sub.value) && melindaIdRegExp.test(String(sub.value)))\n    .map(({value}) => testStringOrNumber(value) ? String(value).replace(melindaIdRegExp, '$<id>') : '');\n}\n\nexport function validateSidFieldSubfieldCounts(field) {\n  // Valid SID-fields have just one $c and one $b\n  debugData(`Validating SID field ${JSON.stringify(field)}`);\n  const countC = countSubfields(field, 'c');\n  const countB = countSubfields(field, 'b');\n  debug(`Found ${countC} sf $cs and ${countB} sf $bs. IsValid: ${countC === 1 && countB === 1}`);\n\n  return countC === 1 && countB === 1;\n}\n\nfunction countSubfields(field, subfieldCode) {\n  // debug(`Counting subfields ${subfieldCode}`);\n  return field.subfields.filter(({code}) => code === subfieldCode).length;\n}\n\nexport function getSubfieldValues(field, subfieldCode) {\n  debugData(`Get subfield(s) $${subfieldCode} from ${JSON.stringify(field)}`);\n  return field.subfields\n    .filter(({code}) => code === subfieldCode)\n    .map(({value}) => testStringOrNumber(value) ? String(value) : '')\n    .filter(value => value);\n}\n\nexport function testStringOrNumber(value) {\n  if (typeof value === 'string' || typeof value === 'number') {\n    return true;\n  }\n  return false;\n}\n\nexport function extractSubfieldsFromField(field, subfieldCodes) {\n  if (field === undefined || field.subfields === undefined) {\n    return [];\n  }\n  const resultSubfields = field.subfields\n    .filter(({code}) => subfieldCodes.includes(code))\n    .map(({code, value}) => ({code, value: testStringOrNumber(value) ? String(value) : ''}))\n    .filter(value => value);\n  return resultSubfields;\n}\n\nexport function uniqueSubfields(subfields) {\n  return subfields.reduce((arr, e) => {\n    if (!arr.find(item => item.code === e.code && item.value === e.value)) {\n      const newArr = arr.concat(e);\n      return newArr;\n    }\n    return arr;\n  }, []);\n}\n\nexport function getMatchCounts(aValues, bValues) {\n\n  const matchingValues = getMatchingValuesAmount(aValues, bValues);\n\n  return {\n    maxValues: aValues.length > bValues.length ? aValues.length : bValues.length,\n    // possibleMatchingValues: amount of identifiers in set of less identifiers (we cannot more values than these)\n    possibleMatchValues: aValues.length > bValues.length ? bValues.length : aValues.length,\n    matchingValues\n  };\n\n  function getMatchingValuesAmount(aValues, bValues) {\n    if (bValues.length > aValues.length) {\n      return aValues.filter(aValue => bValues.some(bValue => aValue === bValue)).length;\n    }\n    if (aValues.length > bValues.length) {\n      return bValues.filter(bValue => aValues.some(aValue => bValue === aValue)).length;\n    }\n\n    // If we have same amount of values, we'll check matches both ways, to avoid mixups in cases\n    // there would be duplicate values\n    const aToB = aValues.filter(aValue => bValues.some(bValue => aValue === bValue)).length;\n    const bToA = bValues.filter(bValue => aValues.some(aValue => bValue === aValue)).length;\n\n    return aToB < bToA ? aToB : bToA;\n  }\n}\n\n\nexport function stringAfter(string, substring) {\n  const pos = string.indexOf(substring);\n  if (pos === -1) {\n    return string;\n  }\n  return string.substring(pos+substring.length);\n}\n\nexport function stringBefore(string, substring) {\n  const pos = string.indexOf(substring);\n  if (pos === -1) {\n    return string;\n  }\n  return string.substring(0, pos);\n}\n\n// We sort records here (put FIKKA and low-cased records first, ref MELINDA-3492)\n// NB! this only sorts the records the current set. If the best stuff would come in a later set and this set contains good enough record, we'll never reach the best...\n// Still this would alleviate the issue when maxMatches === 1...\nexport function preferenceSortRecords(x, y) {\n  debug(`sortRecords: RECORD COMPARISON`);\n  debugData(`{JSON.stringify(x)} vs\\n${JSON.stringify(y)}`);\n  // Prefer the record with a FIKKA LOW tag:\n  const xFikka = hasLow(x.record, 'FIKKA');\n  const yFikka = hasLow(y.record, 'FIKKA');\n\n  if (xFikka && !yFikka) {\n    debug('sortRecords: prefer FIKKA');\n    return -1;\n  }\n  if (yFikka && !xFikka) {\n    return 1;\n  }\n\n  // Prefer downcased:\n  const xAllCaps = hasAllCapsTitle(x.record);\n  const yAllCaps = hasAllCapsTitle(y.record);\n\n  if (!xAllCaps && yAllCaps) {\n    debug('sortRecords: prefer non-all caps');\n    return -1; // x is better\n  }\n  if (!yAllCaps && xAllCaps) {\n    return 1; // y is better\n  }\n  // Default:\n  return 0;\n\n  function hasLow(record, lowTag) {\n    return record.fields?.some(f => f.tag === 'LOW' && f.subfields?.some(sf => sf.code === 'a' && sf.value === lowTag));\n  }\n\n  function hasAllCapsTitle(record) {\n    const f245 = record.fields?.find(f => f.tag === '245');\n    if (!f245) {\n      debugData(`WARNING: No f245 found for ALL CAPS check`);\n      return false;\n    }\n\n    const title = f245.subfields.filter(sf => ['a', 'b', 'c'].includes(sf.code)).map(sf => sf.value).join(' ');\n    if (title.match(/[A-Z]/u) && !title.match(/[a-z]/u)) {\n      return true;\n    }\n    return false;\n  }\n}"],
+  "mappings": "AAAA,OAAO,uBAAuB;AAE9B,MAAM,QAAQ,kBAAkB,yCAAyC;AACzE,MAAM,YAAY,MAAM,OAAO,MAAM;AAE9B,gBAAS,kBAAkB,QAAQ;AAExC,QAAMA,SAAQ,kBAAkB,8CAA8C;AAC9E,QAAMC,aAAYD,OAAM,OAAO,MAAM;AAErC,QAAM,QAAQ,OAAO,UAAU,KAAK;AAEpC,MAAI,MAAM,SAAS,GAAG;AACpB,IAAAA,OAAM,iBAAiB;AACvB,WAAO,CAAC;AAAA,EACV;AAEA,QAAM,oBAAoB,CAAC,EAAE,OAAO,GAAG,MAAM,IAAI,WAAS,aAAa,KAAK,CAAC,CAAC;AAC9E,QAAM,iBAAiB,CAAC,GAAG,IAAI,IAAI,iBAAiB,CAAC;AAErD,EAAAC,WAAU,WAAW,MAAM,MAAM,MAAM,KAAK,UAAU,KAAK,CAAC,EAAE;AAC9D,EAAAA,WAAU,QAAQ,kBAAkB,MAAM,MAAM,KAAK,UAAU,iBAAiB,CAAC,EAAE;AACnF,EAAAA,WAAU,eAAe,eAAe,MAAM,MAAM,KAAK,UAAU,cAAc,CAAC,EAAE;AAEpF,SAAO;AACT;AAEO,gBAAS,aAAa,EAAC,UAAS,GAAG,mBAAmB,CAAC,KAAK,GAAG,GAAG;AACvE,QAAM,kBAAkB;AAExB,SAAO,UACJ,OAAO,SAAO,iBAAiB,SAAS,IAAI,IAAI,CAAC,EACjD,OAAO,SAAO,mBAAmB,IAAI,KAAK,KAAK,gBAAgB,KAAK,OAAO,IAAI,KAAK,CAAC,CAAC,EACtF,IAAI,CAAC,EAAC,MAAK,MAAM,mBAAmB,KAAK,IAAI,OAAO,KAAK,EAAE,QAAQ,iBAAiB,OAAO,IAAI,EAAE;AACtG;AAEO,gBAAS,+BAA+B,OAAO;AAEpD,YAAU,wBAAwB,KAAK,UAAU,KAAK,CAAC,EAAE;AACzD,QAAM,SAAS,eAAe,OAAO,GAAG;AACxC,QAAM,SAAS,eAAe,OAAO,GAAG;AACxC,QAAM,SAAS,MAAM,eAAe,MAAM,qBAAqB,WAAW,KAAK,WAAW,CAAC,EAAE;AAE7F,SAAO,WAAW,KAAK,WAAW;AACpC;AAEA,SAAS,eAAe,OAAO,cAAc;AAE3C,SAAO,MAAM,UAAU,OAAO,CAAC,EAAC,KAAI,MAAM,SAAS,YAAY,EAAE;AACnE;AAEO,gBAAS,kBAAkB,OAAO,cAAc;AACrD,YAAU,oBAAoB,YAAY,SAAS,KAAK,UAAU,KAAK,CAAC,EAAE;AAC1E,SAAO,MAAM,UACV,OAAO,CAAC,EAAC,KAAI,MAAM,SAAS,YAAY,EACxC,IAAI,CAAC,EAAC,MAAK,MAAM,mBAAmB,KAAK,IAAI,OAAO,KAAK,IAAI,EAAE,EAC/D,OAAO,WAAS,KAAK;AAC1B;AAEO,gBAAS,mBAAmB,OAAO;AACxC,MAAI,OAAO,UAAU,YAAY,OAAO,UAAU,UAAU;AAC1D,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAEO,gBAAS,0BAA0B,OAAO,eAAe;AAC9D,MAAI,UAAU,UAAa,MAAM,cAAc,QAAW;AACxD,WAAO,CAAC;AAAA,EACV;AACA,QAAM,kBAAkB,MAAM,UAC3B,OAAO,CAAC,EAAC,KAAI,MAAM,cAAc,SAAS,IAAI,CAAC,EAC/C,IAAI,CAAC,EAAC,MAAM,MAAK,OAAO,EAAC,MAAM,OAAO,mBAAmB,KAAK,IAAI,OAAO,KAAK,IAAI,GAAE,EAAE,EACtF,OAAO,WAAS,KAAK;AACxB,SAAO;AACT;AAEO,gBAAS,gBAAgB,WAAW;AACzC,SAAO,UAAU,OAAO,CAAC,KAAK,MAAM;AAClC,QAAI,CAAC,IAAI,KAAK,UAAQ,KAAK,SAAS,EAAE,QAAQ,KAAK,UAAU,EAAE,KAAK,GAAG;AACrE,YAAM,SAAS,IAAI,OAAO,CAAC;AAC3B,aAAO;AAAA,IACT;AACA,WAAO;AAAA,EACT,GAAG,CAAC,CAAC;AACP;AAEO,gBAAS,eAAe,SAAS,SAAS;AAE/C,QAAM,iBAAiB,wBAAwB,SAAS,OAAO;AAE/D,SAAO;AAAA,IACL,WAAW,QAAQ,SAAS,QAAQ,SAAS,QAAQ,SAAS,QAAQ;AAAA;AAAA,IAEtE,qBAAqB,QAAQ,SAAS,QAAQ,SAAS,QAAQ,SAAS,QAAQ;AAAA,IAChF;AAAA,EACF;AAEA,WAAS,wBAAwBC,UAASC,UAAS;AACjD,QAAIA,SAAQ,SAASD,SAAQ,QAAQ;AACnC,aAAOA,SAAQ,OAAO,YAAUC,SAAQ,KAAK,YAAU,WAAW,MAAM,CAAC,EAAE;AAAA,IAC7E;AACA,QAAID,SAAQ,SAASC,SAAQ,QAAQ;AACnC,aAAOA,SAAQ,OAAO,YAAUD,SAAQ,KAAK,YAAU,WAAW,MAAM,CAAC,EAAE;AAAA,IAC7E;AAIA,UAAM,OAAOA,SAAQ,OAAO,YAAUC,SAAQ,KAAK,YAAU,WAAW,MAAM,CAAC,EAAE;AACjF,UAAM,OAAOA,SAAQ,OAAO,YAAUD,SAAQ,KAAK,YAAU,WAAW,MAAM,CAAC,EAAE;AAEjF,WAAO,OAAO,OAAO,OAAO;AAAA,EAC9B;AACF;AAGO,gBAAS,YAAY,QAAQ,WAAW;AAC7C,QAAM,MAAM,OAAO,QAAQ,SAAS;AACpC,MAAI,QAAQ,IAAI;AACd,WAAO;AAAA,EACT;AACA,SAAO,OAAO,UAAU,MAAI,UAAU,MAAM;AAC9C;AAEO,gBAAS,aAAa,QAAQ,WAAW;AAC9C,QAAM,MAAM,OAAO,QAAQ,SAAS;AACpC,MAAI,QAAQ,IAAI;AACd,WAAO;AAAA,EACT;AACA,SAAO,OAAO,UAAU,GAAG,GAAG;AAChC;AAKO,gBAAS,sBAAsB,GAAG,GAAG;AAC1C,QAAM,gCAAgC;AACtC,YAAU;AAAA,EAA2B,KAAK,UAAU,CAAC,CAAC,EAAE;AAExD,QAAM,SAAS,OAAO,EAAE,QAAQ,OAAO;AACvC,QAAM,SAAS,OAAO,EAAE,QAAQ,OAAO;AAEvC,MAAI,UAAU,CAAC,QAAQ;AACrB,UAAM,2BAA2B;AACjC,WAAO;AAAA,EACT;AACA,MAAI,UAAU,CAAC,QAAQ;AACrB,WAAO;AAAA,EACT;AAGA,QAAM,WAAW,gBAAgB,EAAE,MAAM;AACzC,QAAM,WAAW,gBAAgB,EAAE,MAAM;AAEzC,MAAI,CAAC,YAAY,UAAU;AACzB,UAAM,kCAAkC;AACxC,WAAO;AAAA,EACT;AACA,MAAI,CAAC,YAAY,UAAU;AACzB,WAAO;AAAA,EACT;AAEA,SAAO;AAEP,WAAS,OAAO,QAAQ,QAAQ;AAC9B,WAAO,OAAO,QAAQ,KAAK,OAAK,EAAE,QAAQ,SAAS,EAAE,WAAW,KAAK,QAAM,GAAG,SAAS,OAAO,GAAG,UAAU,MAAM,CAAC;AAAA,EACpH;AAEA,WAAS,gBAAgB,QAAQ;AAC/B,UAAM,OAAO,OAAO,QAAQ,KAAK,OAAK,EAAE,QAAQ,KAAK;AACrD,QAAI,CAAC,MAAM;AACT,gBAAU,2CAA2C;AACrD,aAAO;AAAA,IACT;AAEA,UAAM,QAAQ,KAAK,UAAU,OAAO,QAAM,CAAC,KAAK,KAAK,GAAG,EAAE,SAAS,GAAG,IAAI,CAAC,EAAE,IAAI,QAAM,GAAG,KAAK,EAAE,KAAK,GAAG;AACzG,QAAI,MAAM,MAAM,QAAQ,KAAK,CAAC,MAAM,MAAM,QAAQ,GAAG;AACnD,aAAO;AAAA,IACT;AACA,WAAO;AAAA,EACT;AACF;",
   "names": ["debug", "debugData", "aValues", "bValues"]
 }

package/package.json

@@ -13,7 +13,7 @@
 		"url": "https://github.com/NatLibFi/melinda-record-matching-js"
 	},
 	"license": "MIT",
-	"version": "5.1.6",
+	"version": "5.1.7-alpha.1",
 	"type": "module",
 	"main": "./dist/index.js",
 	"bin": "./dist/cli.js",

package/src/candidate-search/candidate-search-utils.js

@@ -6,13 +6,18 @@ export function toQueries(identifiers, queryString) {
   const debugData = debug.extend('data');
 
   // We quote the identifier, if it contains a slash! (Slash in non-quoted SRU-search breaks search.)
-  const quotedIdentifiers = identifiers.map(identifier => identifier.match(/\//u) ? `"${identifier}"` : `${identifier}`);
+  // We also quote the identifier, if it starts with caret (f028 searches fail without caret and quotes...)
+  const quotedIdentifiers = identifiers.map(identifier => identifier.match(/\//u) || identifier.match(/\^/u) ? `"${identifier}"` : `${identifier}`);
 
-  // Aleph supports only two queries with or -operator (This is not actually true)
-  const pairs = toPairs(quotedIdentifiers);
-  const queries = pairs.map(([a, b]) => b ? `${queryString}=${a} or ${queryString}=${b}` : `${queryString}=${a}`);
+  // We can't pair queries with starting caret and without (ie. left anchored queries with non-left anchored queries)
+  const caretPairs = toPairs(quotedIdentifiers.filter(identifier => identifier.match(/\^/u)));
+  const nonCaretPairs = toPairs(quotedIdentifiers.filter(identifier => !identifier.match(/\^/u)));
 
+  const pairs = nonCaretPairs.concat(caretPairs);
   debugData(`Pairs (${pairs.length}): ${JSON.stringify(pairs)}`);
+
+  // Aleph supports only two queries with or -operator (This is not actually true)
+  const queries = pairs.map(([a, b]) => b ? `${queryString}=${a} or ${queryString}=${b}` : `${queryString}=${a}`);
   debugData(`Queries (${queries.length}): ${JSON.stringify(queries)}`);
 
   return queries;

package/src/candidate-search/query-list/bib.js

@@ -479,9 +479,9 @@ export function bibStandardIdentifiers(record) {
         const b = subfields.find(sf => sf.code === 'b');
         // TODO: normalize?
         if (b) {
-          return [a.value, `${b.value} ${a.value}`];
+          return [`^${a.value}`, `^${b.value} ${a.value}`];
         }
-        return [a.value];
+        return [`^${a.value}`];
       }
     }
 

package/src/cli.js

@@ -3,6 +3,7 @@ import yargs from 'yargs';
 import createMatchOperator, {candidateSearch, matchDetection} from './index.js';
 import createDebugLogger from 'debug';
 import {MarcRecord} from '@natlibfi/marc-record';
+import {uniqArray} from '@natlibfi/marc-record-validators-melinda/dist/utils.js';
 
 cli();
 
@@ -70,8 +71,22 @@ async function cli() {
   const record = new MarcRecord(JSON.parse(fileRaw), {subfieldValues: false});
 
   const result = await matchOperator({record});
+  const matchCount = result.matches.length;
+  const matchIds = result.matches.map(matchA => matchA.candidate.id);
+  const nonMatchCount = result.nonMatches?.length || result.nonMatchCount;
+  const nonMatchIds = result.nonMatches?.map(matchA => matchA.candidate.id) || [];
+  const uniqueNonMatchIds = uniqArray(nonMatchIds);
+  const uniqueNonMatchCount = uniqueNonMatchIds.length;
+  const candidateCount = result.candidateCount;
+
+  debug(`Matches (${matchCount}) ${JSON.stringify(matchIds)}`);
+  debug(`NonMatches (${nonMatchCount}) ${JSON.stringify(nonMatchIds)}`);
+  debug(`Unique nonMatches (${uniqueNonMatchCount}) ${JSON.stringify(uniqueNonMatchIds)}`);
+  debug(`Candidates (${candidateCount})`);
+
   debug(JSON.stringify(result));
 
+  // DEVELOP: print results to output file
 
   function generateStrategy(searchType) {
     if (['IDS'].includes(searchType)) {
@@ -102,7 +117,9 @@ async function cli() {
         //  - ignore one year differences in publicationTime
         //  - extract publicationTimes from f008, f26x and reprint notes in f500
         //  - do not substract points for mismatching (normal) publicationTime, if there's a match between
-        //       normal publicationTime and a reprintPublication time
+        //       normal publicationTime and a reprintPublicationTime
+        //  - do not subract points for mismatchin (normal) publiscationTime if there's a match between 
+        //       normal publicationTime and a copyrightPublicationTime
         matchDetection.features.bib.publicationTimeAllowConsYearsMulti(),
         matchDetection.features.bib.language(),
         matchDetection.features.bib.bibliographicLevel(),

package/src/index.js

@@ -8,6 +8,8 @@ export {candidateSearch, matchDetection};
 export default ({detection: detectionOptions, search: searchOptions, maxMatches = 1, maxCandidates = 25, returnStrategy = false, returnQuery = false, returnNonMatches = false}) => {
   const debug = createDebugLogger('@natlibfi/melinda-record-matching:index');
   const debugData = debug.extend('data');
+  const debugDev = debug.extend('dev');
+
 
   debugData(`DetectionOptions: ${JSON.stringify(detectionOptions)}`);
   debugData(`SearchOptions: ${JSON.stringify(searchOptions)}`);
@@ -31,6 +33,7 @@ export default ({detection: detectionOptions, search: searchOptions, maxMatches
     // matches : candidates that have been detected as matches by current matcher job
     // nonMatches : candidates that have been detected as non-matches by current matcher job (only if returnNonMatches is 'true')
     // duplicateCount : amount of candidate records that were retrieved from the SRU but not handled further because they were already found in the matches/nonMatches
+    // nonMatchCount : amount of candidate records that were detexted as nonMatches by current mathcer job
 
     // state.totalRecords : amount of candidate records available to the current query (undefined, if there was no queries left)
     // state.query : current query (undefined if there was no queries left)
@@ -44,11 +47,10 @@ export default ({detection: detectionOptions, search: searchOptions, maxMatches
       debugData(`Starting next matcher iteration.`);
       const {records, ...state} = await search(initialState);
 
-      debugData(`Current state: ${JSON.stringify(state)}, matches: ${matches.length}, candidateCount: ${candidateCount}, nonMatches: ${nonMatches.length}, nonMatchCount: ${nonMatchCount}, matchErrors: ${matchErrors.length}`);
+      debugDev(`Current state: ${JSON.stringify(state)}, matches: ${matches.length}, candidateCount: ${candidateCount}, nonMatches: ${nonMatches.length}, duplicateCount: ${duplicateCount}, nonMatchCount: ${nonMatchCount}, matchErrors: ${matchErrors.length}`);
       const recordSetSize = records.length;
       const newCandidateCount = candidateCount + recordSetSize;
 
-
       if (recordSetSize > 0) {
         return handleRecordSet();
       }
@@ -64,7 +66,7 @@ export default ({detection: detectionOptions, search: searchOptions, maxMatches
       function handleRecordSet() {
         debug(`Checking record set of ${recordSetSize} candidate records for possible matches, found by ${state.searchCounter} search for ${state.query}`);
 
-        const matchResult = iterateRecords({records, recordSetSize, maxMatches, matches, nonMatches, nonMatchCount});
+        const matchResult = iterateRecords({records, recordSetSize, maxMatches, matches, nonMatches, nonMatchCount, duplicateCount});
 
         const newDuplicateCount = duplicateCount + matchResult.duplicateCount;
         const newNonMatchCount = nonMatchCount + matchResult.nonMatchCount;
@@ -154,6 +156,7 @@ export default ({detection: detectionOptions, search: searchOptions, maxMatches
         const totalHandled = matchCount + chosenNonMatchCount + duplicateCount;
         debug(`candidateCount: ${candidateCount}, matches: ${matchCount}, nonMatches: ${chosenNonMatchCount}, duplicateCount: ${duplicateCount}, matchErrorCount: ${matchErrorCount}`);
         debug(`We got result for ${totalHandled} / ${candidateCount} retrieved candidates`);
+        // NOTE: this counts something wrong!
         if (totalHandled !== candidateCount) {
           debug(`WARNING: Missing results for ${candidateCount - totalHandled} candidates`);
           return;
@@ -206,6 +209,7 @@ export default ({detection: detectionOptions, search: searchOptions, maxMatches
 
       // records : non-handled records in the current record set
       // matches : found matches in the current matcher job
+      // nonMatches: found nonMatches in the current matcher job
       // recordMatches : found matches in the current record set
       // recordNonMatches : found nonMatches in the current record set (only if returnNonMatches setting is true)
       // recordMatchErrors: errored matchDetection in the current record set
@@ -227,8 +231,9 @@ export default ({detection: detectionOptions, search: searchOptions, maxMatches
       */
 
       if (candidate) {
-        if (candidateNotInMatches(matches.concat(nonMatches), candidate)) {
-          const {record: candidateRecord, id: candidateId} = candidate;
+        const {record: candidateRecord, id: candidateId} = candidate;
+        const allMatches = matches.concat(nonMatches);
+        if (candidateNotInMatches(allMatches, candidate)) {
           const recordBExternal = {id: candidate.id, recordSource: 'databaseRecord', label: `db-${candidate.id}`};
           try {
             debug(`Running matchDetection for record ${candidateId} (${newRecordCount}/${recordSetSize})`);
@@ -244,8 +249,9 @@ export default ({detection: detectionOptions, search: searchOptions, maxMatches
             return iterateRecords({records: records.slice(1), recordSetSize, maxMatches, matches, recordMatches, recordCount: newRecordCount, recordNonMatches, recordDuplicateCount, recordNonMatchCount, recordMatchErrors: newRecordMatchErrors});
           }
         }
-
-        return iterateRecords({records: records.slice(1), recordSetSize, maxMatches, matches, recordMatches, recordCount: newRecordCount, recordNonMatches, recordDuplicateCount: recordDuplicateCount + 1, recordNonMatchCount, recordMatchErrors});
+        debug(`Matching for ${candidateId} already done (${recordDuplicateCount} before)`);
+        const newRecordDuplicateCount = recordDuplicateCount + 1;
+        return iterateRecords({records: records.slice(1), recordSetSize, maxMatches, matches, recordMatches, recordCount: newRecordCount, recordNonMatches, recordDuplicateCount: newRecordDuplicateCount, recordNonMatchCount, recordMatchErrors});
       }
 
       debug(`No more candidates, record set (${recordCount}/${recordSetSize}) done, ${recordMatches.length} matches found, ${recordDuplicateCount} candidates already handled, ${returnNonMatches ? `${recordNonMatches.length}` : `${recordNonMatchCount}`} nonMatches found.`);
@@ -287,32 +293,32 @@ export default ({detection: detectionOptions, search: searchOptions, maxMatches
         const newRecordNonMatches = isMatch ? recordNonMatches : recordNonMatches.concat(newMatch);
         const newRecordNonMatchCount = isMatch ? recordNonMatchCount : recordNonMatchCount + 1;
 
-        debugData(`- Total matches after this detection: ${matches.concat(newRecordMatches).length} (max: ${maxMatches})`);
+        debugDev(`- Total matches after this detection: ${matches.concat(newRecordMatches).length} (max: ${maxMatches})`);
 
         if (returnNonMatches) {
-          debugData(`- Total nonMatches after this detection: ${nonMatches.concat(newRecordNonMatches).length}`);
+          debugDev(`- Total nonMatches after this detection: ${nonMatches.concat(newRecordNonMatches).length}`);
         }
-        debugData(`- Total nonMatchCount after this detection: ${recordNonMatchCount}`);
+        debugDev(`- Total nonMatchCount after this detection: ${recordNonMatchCount}`);
 
         if (maxMatchesFound({matches: matches.concat(newRecordMatches), maxMatches})) {
           debug(`MaxMatches (${maxMatches}) reached, handled candidates in record set: ${newRecordCount} non-handled candidates in record set ${recordSetSize - newRecordCount}`);
           return {matches: newRecordMatches, nonMatches: returnNonMatches ? newRecordNonMatches : [], duplicateCount: recordDuplicateCount, nonMatchCount: newRecordNonMatchCount, matchErrors: recordMatchErrors};
         }
 
-        return iterateRecords({records: records.slice(1), recordSetSize, maxMatches, matches, recordMatches: newRecordMatches, recordCount: newRecordCount, recordNonMatches: returnNonMatches ? newRecordNonMatches : [], duplicateCount: recordDuplicateCount, recordNonMatchCount: newRecordNonMatchCount, matchErrors: recordMatchErrors});
+        return iterateRecords({records: records.slice(1), recordSetSize, maxMatches, matches, recordMatches: newRecordMatches, recordCount: newRecordCount, recordNonMatches: returnNonMatches ? newRecordNonMatches : [], recordDuplicateCount, recordNonMatchCount: newRecordNonMatchCount, matchErrors: recordMatchErrors});
       }
 
-      function candidateNotInMatches(matches, candidate) {
-        debug(`Checking that record ${candidate.id} is not already included in ${matches.length} matches/nonMatches`);
+      function candidateNotInMatches(allMatches, candidate) {
+        debug(`Checking that record ${candidate.id} is not already included in ${allMatches.length} matches/nonMatches`);
         const newCandidateId = candidate.id;
-        debugData(`newCandidateId: ${newCandidateId}`);
-        const result = matches.find(({candidate}) => candidate.id === newCandidateId);
-        debugData(`Result: ${result}`);
+        debugData(`-- newCandidateId: ${newCandidateId}`);
+        const result = allMatches.find(({candidate}) => candidate.id === newCandidateId);
+        //debugData(`Result: ${JSON.stringify(result)}`);
         if (result) {
-          debug(`${candidate.id} was already handled.`);
+          debug(`-- ${newCandidateId} was already handled.`);
           return false;
         }
-        debug(`${candidate.id} not found in matches/nonMatches`);
+        debugDev(`-- ${newCandidateId} not found in ${allMatches.length} matches/nonMatches`);
         return true;
       }
     }

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

@@ -198,6 +198,7 @@ export default () => ({
     }
 
     // Do not give minus points if a normal publishing year is found in copyright years
+
     const bNormalInACopyright = a.copyrightYears.filter(aValue => b.normalYears.some(bValue => aValue === bValue));
     const aNormalInBCopyright= b.copyrightYears.filter(bValue => a.normalYears.some(aValue => bValue === aValue));
     debug(`BNorm in ACopyright: ${JSON.stringify(bNormalInACopyright)}`);

package/src/matching-utils.js

@@ -134,7 +134,8 @@ export function stringBefore(string, substring) {
 // NB! this only sorts the records the current set. If the best stuff would come in a later set and this set contains good enough record, we'll never reach the best...
 // Still this would alleviate the issue when maxMatches === 1...
 export function preferenceSortRecords(x, y) {
-  debug(`sortRecords: RECORD COMPARISON\n${JSON.stringify(x)} vs\n${JSON.stringify(y)}`);
+  debug(`sortRecords: RECORD COMPARISON`);
+  debugData(`{JSON.stringify(x)} vs\n${JSON.stringify(y)}`);
   // Prefer the record with a FIKKA LOW tag:
   const xFikka = hasLow(x.record, 'FIKKA');
   const yFikka = hasLow(y.record, 'FIKKA');