@natlibfi/marc-record-validators-melinda 12.0.6 → 12.0.7

package/dist/merge-fields/worldKnowledge.js

@@ -14,7 +14,59 @@ export function valueCarriesMeaning(tag, subfieldCode, value) {
   }
   return true;
 }
+const synonyms = [
+  { tags: ["700", "710", "711", "730"], code: "i", "fin": "Sis\xE4lt\xE4\xE4 (ekspressio)", "swe": "Inneh\xE5ller (uttryck)" },
+  { tags: ["700", "710", "711", "730"], code: "i", "fin": "Sis\xE4lt\xE4\xE4 (teos)", "swe": "Inneh\xE5ller (verk)" },
+  { tags: ["700", "710", "711", "730"], code: "l", "fin": "Englanti", "swe": "Engelska" },
+  { tags: ["700", "710", "711", "730"], code: "l", "fin": "Ruotsi", "swe": "Svenska" },
+  { tags: ["700", "710", "711", "730"], code: "l", "fin": "Suomi", "swe": "Finska" }
+  // There might eventually be need for a list of terms is given language (eg. engl. paperback and softcover)
+];
+export function getSynonyms(term, tag = void 0, subfieldCode = void 0, preferredLanguage = void 0, ignoreCase = true, relevantLanguagesString = "fin swe") {
+  if (!term) {
+    return [];
+  }
+  const relevantLanguges = relevantLanguagesString.split(/\s+/u);
+  const normalizedTerm = ignoreCase ? term.toLowerCase() : term;
+  const synonymsWithTag = tag ? synonyms.filter((s) => s.tags.includes(tag)) : synonyms;
+  if (synonymsWithTag.length === 0) {
+    return [];
+  }
+  const synonymsWithTagAndCode = subfieldCode ? synonymsWithTag.filter((s) => s.code === subfieldCode) : synonymsWithTag;
+  const matchingSynonyms = synonymsWithTagAndCode.filter((s) => termAndLangMatch(s));
+  if (preferredLanguage && matchingSynonyms.length > 0) {
+    return matchingSynonyms.map((s) => s[preferredLanguage]);
+  }
+  return matchingSynonyms;
+  function termAndLangMatch(synonym) {
+    if (relevantLanguges.includes("fin")) {
+      if (ignoreCase && synonym.fin.toLowerCase() === normalizedTerm) {
+        return true;
+      }
+      if (!ignoreCase && synonym.fin === term) {
+        return true;
+      }
+    }
+    if (relevantLanguges.includes("swe")) {
+      if (ignoreCase && synonym.swe.toLowerCase() === normalizedTerm) {
+        return true;
+      }
+      if (!ignoreCase && synonym.swe === term) {
+        return true;
+      }
+    }
+    return false;
+  }
+}
+export function getSynonym(tag, subfieldCode, originalValue) {
+  const finnishForm = getSynonyms(originalValue, tag, subfieldCode, "fin");
+  if (finnishForm.length === 1) {
+    return finnishForm[0];
+  }
+  return originalValue;
+}
 export function normalizeForSamenessCheck(tag, subfieldCode, originalValue) {
+  originalValue = getSynonym(tag, subfieldCode, originalValue);
   if (subfieldCode === "a" && ["100", "600", "700", "800"].includes(tag)) {
     return normalizePersonalName(originalValue);
   }

package/dist/merge-fields/worldKnowledge.js.map

@@ -1,7 +1,7 @@
 {
   "version": 3,
   "sources": ["../../src/merge-fields/worldKnowledge.js"],
-  "sourcesContent": ["//import {nvdebug} from '../utils';\n\nexport function valueCarriesMeaning(tag, subfieldCode, value) {\n  // Some data is pretty meaningless and as meaningless is pretty close to nothing, this meaningless data should no prevent merge.\n  // The list below is incomples (swedish translations etc)\n  if (tag === '260' || tag === '264') {\n    // We drop these, instead of normalizing, as KV does not put this information in place...\n    if (subfieldCode === 'a') {\n      if (value.match(/^[^a-z]*(?:Kustannuspaikka tuntematon|S\\.l)[^a-z]*$/ui)) {\n        return false;\n      }\n    }\n    if (subfieldCode === 'b') {\n      if (value.match(/^[^a-z]*(?:Kustantaja tuntematon|S\\.n)[^a-z]*$/ui)) {\n        return false;\n      }\n    }\n    return true;\n  }\n  return true;\n}\n\nexport function normalizeForSamenessCheck(tag, subfieldCode, originalValue) {\n  // NB! These work only for non-repeatable subfields!\n  // Repeatable subfields are currently handled in mergeSubfields.js. Only non-repeatable subfields block field merge,\n  // (This split is suboptiomal... Minimum fix: make this disctinction cleaner...)\n  if (subfieldCode === 'a' && ['100', '600', '700', '800'].includes(tag)) {\n    return normalizePersonalName(originalValue);\n  }\n\n  // NB! originalValue should already be lowercased, stripped on initial '[' chars and postpunctuation.\n  if (tag === '250' && subfieldCode === 'a') {\n    return normalizeEditionStatement(originalValue);\n  }\n\n  // 506 - Restrictions on Access Note (R), $a - Terms governing access (NR)\n  if (tag === '506' && subfieldCode === 'a') {\n    return normalize506a(originalValue);\n  }\n\n  if (tag === '534' && subfieldCode === 'p') {\n    return normalizeOriginalVersionNoteIntroductoryPhrase(originalValue);\n  }\n\n  return originalValue;\n}\n\n\nfunction normalizePersonalName(originalValue) {\n  // Use more readable \"Forename Surname\" format in comparisons:\n  return originalValue.replace(/^([^,]+), ([^,]+)$/u, '$2 $1');\n}\n\nconst sallittu506a = ['sallittu kaikenik\u00E4isille', 'sallittu', 's']; // downcased, without punctuation\nfunction normalize506a(originalValue) {\n  if (sallittu506a.includes(originalValue)) {\n    return sallittu506a[0];\n  }\n  return originalValue;\n}\n\nconst introductoryPhrasesMeaning1 = ['alkuper\u00E4inen', 'alkuper\u00E4isen julkaisutiedot', 'alun perin julkaistu', 'alunperin julkaistu'];\nfunction normalizeOriginalVersionNoteIntroductoryPhrase(originalValue) {\n  // MELKEHITYS-1935-ish:\n  if (introductoryPhrasesMeaning1.includes(originalValue)) {\n    return introductoryPhrasesMeaning1[0];\n  }\n\n  return originalValue;\n}\n\nfunction normalizeEditionStatement(originalValue) {\n  const value = originalValue;\n\n  // As normalization tries to translate things info Finnish, use this for similarity check only!\n  if (value.match(/^[1-9][0-9]*(?:\\.|:a|nd|rd|st|th) (?:ed\\.?|edition|p\\.?|painos|uppl\\.?|upplagan)[.\\]]*$/ui)) {\n    const nth = value.replace(/[^0-9].*$/u, '');\n    return `${nth}. painos`;\n  }\n\n  // Quick and dirty fix for\n  if (value.match(/^[1-9][0-9]*(?:\\.|:a|nd|rd|st|th)(?: f\u00F6rnyade|,? rev\\.| uud\\.| uudistettu) (?:ed\\.?|edition|p\\.?|painos|uppl\\.?|upplagan)[.\\]]*$/ui)) {\n    const nth = value.replace(/[^0-9].*$/u, '');\n    return `${nth}. uudistettu painos`;\n  }\n\n  if (value.match(/^(?:First|F\u00F6rsta|Ensimm\u00E4inen) (?:ed\\.?|edition|p\\.?|painos|uppl\\.?|upplagan)[.\\]]*$/ui)) {\n    return `1. painos`;\n  }\n\n  if (value.match(/^(?:Andra|Second|Toinen) (?:ed\\.?|edition|p\\.?|painos|uppl\\.?|upplagan)[.\\]]*$/ui)) {\n    return `2. painos`;\n  }\n\n  if (value.match(/^(?:Kolmas|Third|Tredje) (?:ed\\.?|edition|p\\.?|painos|uppl\\.?|upplagan)[.\\]]*$/ui)) {\n    return `3. painos`;\n  }\n\n  if (value.match(/^(?:Fourth|Fj\u00E4rde|Nelj\u00E4s) (?:ed\\.?|edition|p\\.?|painos|uppl\\.?|upplagan)[.\\]]*$/ui)) {\n    return `4. painos`;\n  }\n\n  return originalValue;\n}\n"],
-  "mappings": "AAEO,gBAAS,oBAAoB,KAAK,cAAc,OAAO;AAG5D,MAAI,QAAQ,SAAS,QAAQ,OAAO;AAElC,QAAI,iBAAiB,KAAK;AACxB,UAAI,MAAM,MAAM,uDAAuD,GAAG;AACxE,eAAO;AAAA,MACT;AAAA,IACF;AACA,QAAI,iBAAiB,KAAK;AACxB,UAAI,MAAM,MAAM,kDAAkD,GAAG;AACnE,eAAO;AAAA,MACT;AAAA,IACF;AACA,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAEO,gBAAS,0BAA0B,KAAK,cAAc,eAAe;AAI1E,MAAI,iBAAiB,OAAO,CAAC,OAAO,OAAO,OAAO,KAAK,EAAE,SAAS,GAAG,GAAG;AACtE,WAAO,sBAAsB,aAAa;AAAA,EAC5C;AAGA,MAAI,QAAQ,SAAS,iBAAiB,KAAK;AACzC,WAAO,0BAA0B,aAAa;AAAA,EAChD;AAGA,MAAI,QAAQ,SAAS,iBAAiB,KAAK;AACzC,WAAO,cAAc,aAAa;AAAA,EACpC;AAEA,MAAI,QAAQ,SAAS,iBAAiB,KAAK;AACzC,WAAO,+CAA+C,aAAa;AAAA,EACrE;AAEA,SAAO;AACT;AAGA,SAAS,sBAAsB,eAAe;AAE5C,SAAO,cAAc,QAAQ,uBAAuB,OAAO;AAC7D;AAEA,MAAM,eAAe,CAAC,+BAA4B,YAAY,GAAG;AACjE,SAAS,cAAc,eAAe;AACpC,MAAI,aAAa,SAAS,aAAa,GAAG;AACxC,WAAO,aAAa,CAAC;AAAA,EACvB;AACA,SAAO;AACT;AAEA,MAAM,8BAA8B,CAAC,mBAAgB,kCAA+B,wBAAwB,qBAAqB;AACjI,SAAS,+CAA+C,eAAe;AAErE,MAAI,4BAA4B,SAAS,aAAa,GAAG;AACvD,WAAO,4BAA4B,CAAC;AAAA,EACtC;AAEA,SAAO;AACT;AAEA,SAAS,0BAA0B,eAAe;AAChD,QAAM,QAAQ;AAGd,MAAI,MAAM,MAAM,2FAA2F,GAAG;AAC5G,UAAM,MAAM,MAAM,QAAQ,cAAc,EAAE;AAC1C,WAAO,GAAG,GAAG;AAAA,EACf;AAGA,MAAI,MAAM,MAAM,oIAAoI,GAAG;AACrJ,UAAM,MAAM,MAAM,QAAQ,cAAc,EAAE;AAC1C,WAAO,GAAG,GAAG;AAAA,EACf;AAEA,MAAI,MAAM,MAAM,uFAAuF,GAAG;AACxG,WAAO;AAAA,EACT;AAEA,MAAI,MAAM,MAAM,kFAAkF,GAAG;AACnG,WAAO;AAAA,EACT;AAEA,MAAI,MAAM,MAAM,kFAAkF,GAAG;AACnG,WAAO;AAAA,EACT;AAEA,MAAI,MAAM,MAAM,mFAAmF,GAAG;AACpG,WAAO;AAAA,EACT;AAEA,SAAO;AACT;",
+  "sourcesContent": ["//import {nvdebug} from '../utils.js';\n\n// NB! This file (or at least synonyms) should eventually be moved away from merge to '..'.\n\n\nexport function valueCarriesMeaning(tag, subfieldCode, value) {\n  // Some data is pretty meaningless and as meaningless is pretty close to nothing, this meaningless data should no prevent merge.\n  // The list below is incomples (swedish translations etc)\n  if (tag === '260' || tag === '264') {\n    // We drop these, instead of normalizing, as KV does not put this information in place...\n    if (subfieldCode === 'a') {\n      if (value.match(/^[^a-z]*(?:Kustannuspaikka tuntematon|S\\.l)[^a-z]*$/ui)) {\n        return false;\n      }\n    }\n    if (subfieldCode === 'b') {\n      if (value.match(/^[^a-z]*(?:Kustantaja tuntematon|S\\.n)[^a-z]*$/ui)) {\n        return false;\n      }\n    }\n    return true;\n  }\n  return true;\n}\n\nconst synonyms = [\n  {tags: ['700', '710', '711', '730'], code: 'i', 'fin': 'Sis\u00E4lt\u00E4\u00E4 (ekspressio)', 'swe': 'Inneh\u00E5ller (uttryck)'},\n  {tags: ['700', '710', '711', '730'], code: 'i', 'fin': 'Sis\u00E4lt\u00E4\u00E4 (teos)', 'swe': 'Inneh\u00E5ller (verk)'},\n  {tags: ['700', '710', '711', '730'], code: 'l', 'fin': 'Englanti', 'swe': 'Engelska'},\n  {tags: ['700', '710', '711', '730'], code: 'l', 'fin': 'Ruotsi', 'swe': 'Svenska'},\n  {tags: ['700', '710', '711', '730'], code: 'l', 'fin': 'Suomi', 'swe': 'Finska'}\n  // There might eventually be need for a list of terms is given language (eg. engl. paperback and softcover)\n];\n\nexport function getSynonyms(term, tag = undefined, subfieldCode = undefined, preferredLanguage = undefined, ignoreCase = true, relevantLanguagesString = 'fin swe',) {\n  if (!term) {\n    return [];\n  }\n  //nvdebug(`WP1 CANDS: ${synonyms.length} FOR '${term}'`);\n  const relevantLanguges = relevantLanguagesString.split(/\\s+/u);\n  const normalizedTerm = ignoreCase ? term.toLowerCase() : term;\n  const synonymsWithTag = tag ? synonyms.filter(s => s.tags.includes(tag)) : synonyms;\n  if (synonymsWithTag.length === 0) {\n    return [];\n  }\n  //nvdebug(`WP2 (FILTER ${tag}) CANDS: ${synonymsWithTag.length}`);\n  const synonymsWithTagAndCode = subfieldCode ? synonymsWithTag.filter(s => s.code === subfieldCode) : synonymsWithTag;\n  //nvdebug(`WP3 (FILTER $${subfieldCode}) CANDS: ${synonymsWithTagAndCode.length}:\\n${JSON.stringify(synonymsWithTagAndCode)}`);\n  const matchingSynonyms = synonymsWithTagAndCode.filter(s => termAndLangMatch(s));\n\n  if (preferredLanguage && matchingSynonyms.length > 0) {\n    //console.log(`USING PREFERRED LANG '${preferredLanguage}' for TERM '${term}':\\n${JSON.stringify(matchingSynonyms)}`);\n    return matchingSynonyms.map(s => s[preferredLanguage]);\n  }\n  return matchingSynonyms;\n\n  function termAndLangMatch(synonym) {\n    if (relevantLanguges.includes('fin')) {\n      if (ignoreCase && synonym.fin.toLowerCase() === normalizedTerm ) {\n        return true;\n      }\n      if (!ignoreCase && synonym.fin === term) {\n        return true;\n      }\n    }\n\n    if (relevantLanguges.includes('swe')) {\n      if (ignoreCase && synonym.swe.toLowerCase() === normalizedTerm ) {\n        return true;\n      }\n      if (!ignoreCase && synonym.swe === term) {\n        return true;\n      }\n    }\n    return false;\n  }\n}\n\nexport function getSynonym(tag, subfieldCode, originalValue) {\n  const finnishForm = getSynonyms(originalValue, tag, subfieldCode, 'fin');\n  if (finnishForm.length === 1) {\n    //nvdebug(`FINNISH FORM FOR ${tag}$${subfieldCode}: '${finnishForm[0]}'`);\n    return finnishForm[0];\n  }\n  return originalValue;\n}\n\nexport function normalizeForSamenessCheck(tag, subfieldCode, originalValue) {\n  // NB! These work only for non-repeatable subfields!\n  // Repeatable subfields are currently handled in mergeSubfields.js. Only non-repeatable subfields block field merge,\n  // (This split is suboptiomal... Minimum fix: make this distinction cleaner...)\n\n  //nvdebug(`TRYING TO DO ${tag}$${subfieldCode} '${originalValue}'`);\n  originalValue = getSynonym(tag, subfieldCode, originalValue);\n\n  if (subfieldCode === 'a' && ['100', '600', '700', '800'].includes(tag)) { // \"Etunimi Sukunimi\"...\n    return normalizePersonalName(originalValue);\n  }\n\n  // NB! originalValue should already be lowercased, stripped on initial '[' chars and postpunctuation.\n  if (tag === '250' && subfieldCode === 'a') {\n    return normalizeEditionStatement(originalValue);\n  }\n\n  // 506 - Restrictions on Access Note (R), $a - Terms governing access (NR)\n  if (tag === '506' && subfieldCode === 'a') {\n    return normalize506a(originalValue);\n  }\n\n  if (tag === '534' && subfieldCode === 'p') {\n    return normalizeOriginalVersionNoteIntroductoryPhrase(originalValue);\n  }\n\n  return originalValue;\n}\n\n\nfunction normalizePersonalName(originalValue) {\n  // Use more readable \"Forename Surname\" format in comparisons:\n  return originalValue.replace(/^([^,]+), ([^,]+)$/u, '$2 $1');\n}\n\nconst sallittu506a = ['sallittu kaikenik\u00E4isille', 'sallittu', 's']; // downcased, without punctuation\nfunction normalize506a(originalValue) {\n  if (sallittu506a.includes(originalValue)) {\n    return sallittu506a[0];\n  }\n  return originalValue;\n}\n\nconst introductoryPhrasesMeaning1 = ['alkuper\u00E4inen', 'alkuper\u00E4isen julkaisutiedot', 'alun perin julkaistu', 'alunperin julkaistu'];\nfunction normalizeOriginalVersionNoteIntroductoryPhrase(originalValue) {\n  // MELKEHITYS-1935-ish:\n  if (introductoryPhrasesMeaning1.includes(originalValue)) {\n    return introductoryPhrasesMeaning1[0];\n  }\n\n  return originalValue;\n}\n\nfunction normalizeEditionStatement(originalValue) {\n  const value = originalValue;\n\n  // As normalization tries to translate things info Finnish, use this for similarity check only!\n  if (value.match(/^[1-9][0-9]*(?:\\.|:a|nd|rd|st|th) (?:ed\\.?|edition|p\\.?|painos|uppl\\.?|upplagan)[.\\]]*$/ui)) {\n    const nth = value.replace(/[^0-9].*$/u, '');\n    return `${nth}. painos`;\n  }\n\n  // Quick and dirty fix for\n  if (value.match(/^[1-9][0-9]*(?:\\.|:a|nd|rd|st|th)(?: f\u00F6rnyade|,? rev\\.| uud\\.| uudistettu) (?:ed\\.?|edition|p\\.?|painos|uppl\\.?|upplagan)[.\\]]*$/ui)) {\n    const nth = value.replace(/[^0-9].*$/u, '');\n    return `${nth}. uudistettu painos`;\n  }\n\n  if (value.match(/^(?:First|F\u00F6rsta|Ensimm\u00E4inen) (?:ed\\.?|edition|p\\.?|painos|uppl\\.?|upplagan)[.\\]]*$/ui)) {\n    return `1. painos`;\n  }\n\n  if (value.match(/^(?:Andra|Second|Toinen) (?:ed\\.?|edition|p\\.?|painos|uppl\\.?|upplagan)[.\\]]*$/ui)) {\n    return `2. painos`;\n  }\n\n  if (value.match(/^(?:Kolmas|Third|Tredje) (?:ed\\.?|edition|p\\.?|painos|uppl\\.?|upplagan)[.\\]]*$/ui)) {\n    return `3. painos`;\n  }\n\n  if (value.match(/^(?:Fourth|Fj\u00E4rde|Nelj\u00E4s) (?:ed\\.?|edition|p\\.?|painos|uppl\\.?|upplagan)[.\\]]*$/ui)) {\n    return `4. painos`;\n  }\n\n  return originalValue;\n}\n"],
+  "mappings": "AAKO,gBAAS,oBAAoB,KAAK,cAAc,OAAO;AAG5D,MAAI,QAAQ,SAAS,QAAQ,OAAO;AAElC,QAAI,iBAAiB,KAAK;AACxB,UAAI,MAAM,MAAM,uDAAuD,GAAG;AACxE,eAAO;AAAA,MACT;AAAA,IACF;AACA,QAAI,iBAAiB,KAAK;AACxB,UAAI,MAAM,MAAM,kDAAkD,GAAG;AACnE,eAAO;AAAA,MACT;AAAA,IACF;AACA,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAEA,MAAM,WAAW;AAAA,EACf,EAAC,MAAM,CAAC,OAAO,OAAO,OAAO,KAAK,GAAG,MAAM,KAAK,OAAO,kCAAyB,OAAO,0BAAsB;AAAA,EAC7G,EAAC,MAAM,CAAC,OAAO,OAAO,OAAO,KAAK,GAAG,MAAM,KAAK,OAAO,4BAAmB,OAAO,uBAAmB;AAAA,EACpG,EAAC,MAAM,CAAC,OAAO,OAAO,OAAO,KAAK,GAAG,MAAM,KAAK,OAAO,YAAY,OAAO,WAAU;AAAA,EACpF,EAAC,MAAM,CAAC,OAAO,OAAO,OAAO,KAAK,GAAG,MAAM,KAAK,OAAO,UAAU,OAAO,UAAS;AAAA,EACjF,EAAC,MAAM,CAAC,OAAO,OAAO,OAAO,KAAK,GAAG,MAAM,KAAK,OAAO,SAAS,OAAO,SAAQ;AAAA;AAEjF;AAEO,gBAAS,YAAY,MAAM,MAAM,QAAW,eAAe,QAAW,oBAAoB,QAAW,aAAa,MAAM,0BAA0B,WAAY;AACnK,MAAI,CAAC,MAAM;AACT,WAAO,CAAC;AAAA,EACV;AAEA,QAAM,mBAAmB,wBAAwB,MAAM,MAAM;AAC7D,QAAM,iBAAiB,aAAa,KAAK,YAAY,IAAI;AACzD,QAAM,kBAAkB,MAAM,SAAS,OAAO,OAAK,EAAE,KAAK,SAAS,GAAG,CAAC,IAAI;AAC3E,MAAI,gBAAgB,WAAW,GAAG;AAChC,WAAO,CAAC;AAAA,EACV;AAEA,QAAM,yBAAyB,eAAe,gBAAgB,OAAO,OAAK,EAAE,SAAS,YAAY,IAAI;AAErG,QAAM,mBAAmB,uBAAuB,OAAO,OAAK,iBAAiB,CAAC,CAAC;AAE/E,MAAI,qBAAqB,iBAAiB,SAAS,GAAG;AAEpD,WAAO,iBAAiB,IAAI,OAAK,EAAE,iBAAiB,CAAC;AAAA,EACvD;AACA,SAAO;AAEP,WAAS,iBAAiB,SAAS;AACjC,QAAI,iBAAiB,SAAS,KAAK,GAAG;AACpC,UAAI,cAAc,QAAQ,IAAI,YAAY,MAAM,gBAAiB;AAC/D,eAAO;AAAA,MACT;AACA,UAAI,CAAC,cAAc,QAAQ,QAAQ,MAAM;AACvC,eAAO;AAAA,MACT;AAAA,IACF;AAEA,QAAI,iBAAiB,SAAS,KAAK,GAAG;AACpC,UAAI,cAAc,QAAQ,IAAI,YAAY,MAAM,gBAAiB;AAC/D,eAAO;AAAA,MACT;AACA,UAAI,CAAC,cAAc,QAAQ,QAAQ,MAAM;AACvC,eAAO;AAAA,MACT;AAAA,IACF;AACA,WAAO;AAAA,EACT;AACF;AAEO,gBAAS,WAAW,KAAK,cAAc,eAAe;AAC3D,QAAM,cAAc,YAAY,eAAe,KAAK,cAAc,KAAK;AACvE,MAAI,YAAY,WAAW,GAAG;AAE5B,WAAO,YAAY,CAAC;AAAA,EACtB;AACA,SAAO;AACT;AAEO,gBAAS,0BAA0B,KAAK,cAAc,eAAe;AAM1E,kBAAgB,WAAW,KAAK,cAAc,aAAa;AAE3D,MAAI,iBAAiB,OAAO,CAAC,OAAO,OAAO,OAAO,KAAK,EAAE,SAAS,GAAG,GAAG;AACtE,WAAO,sBAAsB,aAAa;AAAA,EAC5C;AAGA,MAAI,QAAQ,SAAS,iBAAiB,KAAK;AACzC,WAAO,0BAA0B,aAAa;AAAA,EAChD;AAGA,MAAI,QAAQ,SAAS,iBAAiB,KAAK;AACzC,WAAO,cAAc,aAAa;AAAA,EACpC;AAEA,MAAI,QAAQ,SAAS,iBAAiB,KAAK;AACzC,WAAO,+CAA+C,aAAa;AAAA,EACrE;AAEA,SAAO;AACT;AAGA,SAAS,sBAAsB,eAAe;AAE5C,SAAO,cAAc,QAAQ,uBAAuB,OAAO;AAC7D;AAEA,MAAM,eAAe,CAAC,+BAA4B,YAAY,GAAG;AACjE,SAAS,cAAc,eAAe;AACpC,MAAI,aAAa,SAAS,aAAa,GAAG;AACxC,WAAO,aAAa,CAAC;AAAA,EACvB;AACA,SAAO;AACT;AAEA,MAAM,8BAA8B,CAAC,mBAAgB,kCAA+B,wBAAwB,qBAAqB;AACjI,SAAS,+CAA+C,eAAe;AAErE,MAAI,4BAA4B,SAAS,aAAa,GAAG;AACvD,WAAO,4BAA4B,CAAC;AAAA,EACtC;AAEA,SAAO;AACT;AAEA,SAAS,0BAA0B,eAAe;AAChD,QAAM,QAAQ;AAGd,MAAI,MAAM,MAAM,2FAA2F,GAAG;AAC5G,UAAM,MAAM,MAAM,QAAQ,cAAc,EAAE;AAC1C,WAAO,GAAG,GAAG;AAAA,EACf;AAGA,MAAI,MAAM,MAAM,oIAAoI,GAAG;AACrJ,UAAM,MAAM,MAAM,QAAQ,cAAc,EAAE;AAC1C,WAAO,GAAG,GAAG;AAAA,EACf;AAEA,MAAI,MAAM,MAAM,uFAAuF,GAAG;AACxG,WAAO;AAAA,EACT;AAEA,MAAI,MAAM,MAAM,kFAAkF,GAAG;AACnG,WAAO;AAAA,EACT;AAEA,MAAI,MAAM,MAAM,kFAAkF,GAAG;AACnG,WAAO;AAAA,EACT;AAEA,MAAI,MAAM,MAAM,mFAAmF,GAAG;AACpG,WAAO;AAAA,EACT;AAEA,SAAO;AACT;",
   "names": []
 }

package/dist/merge-fields.test.js

@@ -1,4 +1,4 @@
-import assert from "node:assert";
+import assert from "node:assert/strict";
 import { MarcRecord } from "@natlibfi/marc-record";
 import validatorFactory from "./merge-fields/index.js";
 import { READERS } from "@natlibfi/fixura";
@@ -36,6 +36,6 @@ async function callback({ getFixture, fix = false, tagPattern = false }) {
     return;
   }
   await validator.fix(record);
-  assert.deepEqual(record, expectedResult);
+  assert.deepEqual(record, new MarcRecord(expectedResult));
 }
 //# sourceMappingURL=merge-fields.test.js.map

package/dist/merge-fields.test.js.map

@@ -1,7 +1,7 @@
 {
   "version": 3,
   "sources": ["../src/merge-fields.test.js"],
-  "sourcesContent": ["import assert from 'node:assert';\nimport {MarcRecord} from '@natlibfi/marc-record';\nimport validatorFactory from './merge-fields/index.js';\nimport {READERS} from '@natlibfi/fixura';\nimport generateTests from '@natlibfi/fixugen';\nimport createDebugLogger from 'debug';\n\n\ngenerateTests({\n  callback,\n  path: [import.meta.dirname, '..', 'test-fixtures', 'merge-fields'],\n  useMetadataFile: true,\n  recurse: false,\n  fixura: {\n    reader: READERS.JSON\n  },\n  hooks: {\n    before: async () => {\n      testValidatorFactory();\n    }\n  }\n});\nconst debug = createDebugLogger('@natlibfi/marc-record-validators-melinda/merge-fields:test');\n\nasync function testValidatorFactory() {\n  const validator = await validatorFactory();\n\n  assert.equal(typeof validator, 'object');\n  assert.equal(typeof validator.description, 'string');\n  assert.equal(typeof validator.validate, 'function');\n}\n\nasync function callback({getFixture, fix = false, tagPattern = false}) {\n  debug(`Run test using tag pattern ${tagPattern}`);\n\n  const validator = await validatorFactory(tagPattern);\n  const record = new MarcRecord(getFixture('record.json'));\n  const expectedResult = getFixture('expectedResult.json');\n  // console.log(expectedResult); // eslint-disable-line\n\n  // NB! This validator will only use tags matching /^[1678](?:00|10|11|30)$/ unless tagPattern is specified!\n  if (!fix) {\n    const result = await validator.validate(record);\n    assert.deepEqual(result, expectedResult);\n    return;\n  }\n\n  await validator.fix(record);\n  assert.deepEqual(record, expectedResult);\n}\n"],
-  "mappings": "AAAA,OAAO,YAAY;AACnB,SAAQ,kBAAiB;AACzB,OAAO,sBAAsB;AAC7B,SAAQ,eAAc;AACtB,OAAO,mBAAmB;AAC1B,OAAO,uBAAuB;AAG9B,cAAc;AAAA,EACZ;AAAA,EACA,MAAM,CAAC,YAAY,SAAS,MAAM,iBAAiB,cAAc;AAAA,EACjE,iBAAiB;AAAA,EACjB,SAAS;AAAA,EACT,QAAQ;AAAA,IACN,QAAQ,QAAQ;AAAA,EAClB;AAAA,EACA,OAAO;AAAA,IACL,QAAQ,YAAY;AAClB,2BAAqB;AAAA,IACvB;AAAA,EACF;AACF,CAAC;AACD,MAAM,QAAQ,kBAAkB,4DAA4D;AAE5F,eAAe,uBAAuB;AACpC,QAAM,YAAY,MAAM,iBAAiB;AAEzC,SAAO,MAAM,OAAO,WAAW,QAAQ;AACvC,SAAO,MAAM,OAAO,UAAU,aAAa,QAAQ;AACnD,SAAO,MAAM,OAAO,UAAU,UAAU,UAAU;AACpD;AAEA,eAAe,SAAS,EAAC,YAAY,MAAM,OAAO,aAAa,MAAK,GAAG;AACrE,QAAM,8BAA8B,UAAU,EAAE;AAEhD,QAAM,YAAY,MAAM,iBAAiB,UAAU;AACnD,QAAM,SAAS,IAAI,WAAW,WAAW,aAAa,CAAC;AACvD,QAAM,iBAAiB,WAAW,qBAAqB;AAIvD,MAAI,CAAC,KAAK;AACR,UAAM,SAAS,MAAM,UAAU,SAAS,MAAM;AAC9C,WAAO,UAAU,QAAQ,cAAc;AACvC;AAAA,EACF;AAEA,QAAM,UAAU,IAAI,MAAM;AAC1B,SAAO,UAAU,QAAQ,cAAc;AACzC;",
+  "sourcesContent": ["import assert from 'node:assert/strict';\nimport {MarcRecord} from '@natlibfi/marc-record';\nimport validatorFactory from './merge-fields/index.js';\nimport {READERS} from '@natlibfi/fixura';\nimport generateTests from '@natlibfi/fixugen';\nimport createDebugLogger from 'debug';\n\n\ngenerateTests({\n  callback,\n  path: [import.meta.dirname, '..', 'test-fixtures', 'merge-fields'],\n  useMetadataFile: true,\n  recurse: false,\n  fixura: {\n    reader: READERS.JSON\n  },\n  hooks: {\n    before: async () => {\n      testValidatorFactory();\n    }\n  }\n});\nconst debug = createDebugLogger('@natlibfi/marc-record-validators-melinda/merge-fields:test');\n\nasync function testValidatorFactory() {\n  const validator = await validatorFactory();\n\n  assert.equal(typeof validator, 'object');\n  assert.equal(typeof validator.description, 'string');\n  assert.equal(typeof validator.validate, 'function');\n}\n\nasync function callback({getFixture, fix = false, tagPattern = false}) {\n  debug(`Run test using tag pattern ${tagPattern}`);\n\n  const validator = await validatorFactory(tagPattern);\n  const record = new MarcRecord(getFixture('record.json'));\n  const expectedResult = getFixture('expectedResult.json');\n  // console.log(expectedResult); // eslint-disable-line\n\n  // NB! This validator will only use tags matching /^[1678](?:00|10|11|30)$/ unless tagPattern is specified!\n  if (!fix) {\n    const result = await validator.validate(record);\n    assert.deepEqual(result, expectedResult);\n    return;\n  }\n\n  await validator.fix(record);\n  assert.deepEqual(record, new MarcRecord(expectedResult));\n}\n"],
+  "mappings": "AAAA,OAAO,YAAY;AACnB,SAAQ,kBAAiB;AACzB,OAAO,sBAAsB;AAC7B,SAAQ,eAAc;AACtB,OAAO,mBAAmB;AAC1B,OAAO,uBAAuB;AAG9B,cAAc;AAAA,EACZ;AAAA,EACA,MAAM,CAAC,YAAY,SAAS,MAAM,iBAAiB,cAAc;AAAA,EACjE,iBAAiB;AAAA,EACjB,SAAS;AAAA,EACT,QAAQ;AAAA,IACN,QAAQ,QAAQ;AAAA,EAClB;AAAA,EACA,OAAO;AAAA,IACL,QAAQ,YAAY;AAClB,2BAAqB;AAAA,IACvB;AAAA,EACF;AACF,CAAC;AACD,MAAM,QAAQ,kBAAkB,4DAA4D;AAE5F,eAAe,uBAAuB;AACpC,QAAM,YAAY,MAAM,iBAAiB;AAEzC,SAAO,MAAM,OAAO,WAAW,QAAQ;AACvC,SAAO,MAAM,OAAO,UAAU,aAAa,QAAQ;AACnD,SAAO,MAAM,OAAO,UAAU,UAAU,UAAU;AACpD;AAEA,eAAe,SAAS,EAAC,YAAY,MAAM,OAAO,aAAa,MAAK,GAAG;AACrE,QAAM,8BAA8B,UAAU,EAAE;AAEhD,QAAM,YAAY,MAAM,iBAAiB,UAAU;AACnD,QAAM,SAAS,IAAI,WAAW,WAAW,aAAa,CAAC;AACvD,QAAM,iBAAiB,WAAW,qBAAqB;AAIvD,MAAI,CAAC,KAAK;AACR,UAAM,SAAS,MAAM,UAAU,SAAS,MAAM;AAC9C,WAAO,UAAU,QAAQ,cAAc;AACvC;AAAA,EACF;AAEA,QAAM,UAAU,IAAI,MAAM;AAC1B,SAAO,UAAU,QAAQ,IAAI,WAAW,cAAc,CAAC;AACzD;",
   "names": []
 }

package/dist/normalize-dashes.js

@@ -1,5 +1,5 @@
 import clone from "clone";
-import { fieldToString, isControlSubfieldCode, nvdebug } from "./utils.js";
+import { fieldToString, isContentSubfieldCode, nvdebug } from "./utils.js";
 export default function() {
   return {
     description: 'Normalize various dashes to "-"',
@@ -43,7 +43,7 @@ function fixDashes(field) {
   field.subfields.forEach((sf) => subfieldFixDashes(sf));
   return field;
   function subfieldFixDashes(subfield) {
-    if (isControlSubfieldCode(subfield.code)) {
+    if (!isContentSubfieldCode(subfield.code, field.tag)) {
       return;
     }
     subfield.value = subfield.value.replace(/[\u2010\u2011\u2012\u2013\u2014\u2015]/ug, "-");

package/dist/normalize-dashes.js.map

@@ -1,7 +1,7 @@
 {
   "version": 3,
   "sources": ["../src/normalize-dashes.js"],
-  "sourcesContent": ["//import createDebugLogger from 'debug';\nimport clone from 'clone';\nimport {fieldToString, isControlSubfieldCode, nvdebug} from './utils.js';\n\n// Author(s): Nicholas Volk\nexport default function () {\n\n  return {\n    description: 'Normalize various dashes to \"-\"',\n    validate, fix\n  };\n\n  function fix(record) {\n    nvdebug(`FIX ME`);\n    record.fields.forEach(field => {\n      fixDashes(field);\n    });\n\n    const res = {message: [], fix: [], valid: true};\n    return res;\n  }\n\n  function validate(record) {\n    const res = {message: []};\n\n    nvdebug(`VALIDATE ME`);\n    record.fields?.forEach(field => {\n      validateField(field, res);\n    });\n\n    res.valid = !(res.message.length >= 1);\n    return res;\n  }\n\n  function validateField(field, res) {\n    const orig = fieldToString(field);\n    nvdebug(` VALIDATE FIELD '${orig}'`);\n\n    const normalizedField = fixDashes(clone(field));\n    const mod = fieldToString(normalizedField);\n    if (orig === mod) { // Fail as the input is \"broken\"/\"crap\"/sumthing\n      return;\n    }\n    res.message.push(`'TODO: ${orig}' => '${mod}'`);\n    return;\n  }\n}\n\n\nfunction fixDashes(field) {\n  if (!field.subfields) {\n    return field;\n  }\n\n  nvdebug(`Dashing ${fieldToString(field)}`);\n\n  field.subfields.forEach(sf => subfieldFixDashes(sf));\n\n  return field;\n\n  function subfieldFixDashes(subfield) {\n    if (isControlSubfieldCode(subfield.code)) {\n      return;\n    }\n    // Normalize dashes U+2010 ... U+2015 to '-':\n    subfield.value = subfield.value.replace(/[\\u2010\\u2011\\u2012\\u2013\\u2014\\u2015]/ug, '-');\n  }\n\n}\n"],
-  "mappings": "AACA,OAAO,WAAW;AAClB,SAAQ,eAAe,uBAAuB,eAAc;AAG5D,0BAA2B;AAEzB,SAAO;AAAA,IACL,aAAa;AAAA,IACb;AAAA,IAAU;AAAA,EACZ;AAEA,WAAS,IAAI,QAAQ;AACnB,YAAQ,QAAQ;AAChB,WAAO,OAAO,QAAQ,WAAS;AAC7B,gBAAU,KAAK;AAAA,IACjB,CAAC;AAED,UAAM,MAAM,EAAC,SAAS,CAAC,GAAG,KAAK,CAAC,GAAG,OAAO,KAAI;AAC9C,WAAO;AAAA,EACT;AAEA,WAAS,SAAS,QAAQ;AACxB,UAAM,MAAM,EAAC,SAAS,CAAC,EAAC;AAExB,YAAQ,aAAa;AACrB,WAAO,QAAQ,QAAQ,WAAS;AAC9B,oBAAc,OAAO,GAAG;AAAA,IAC1B,CAAC;AAED,QAAI,QAAQ,EAAE,IAAI,QAAQ,UAAU;AACpC,WAAO;AAAA,EACT;AAEA,WAAS,cAAc,OAAO,KAAK;AACjC,UAAM,OAAO,cAAc,KAAK;AAChC,YAAQ,oBAAoB,IAAI,GAAG;AAEnC,UAAM,kBAAkB,UAAU,MAAM,KAAK,CAAC;AAC9C,UAAM,MAAM,cAAc,eAAe;AACzC,QAAI,SAAS,KAAK;AAChB;AAAA,IACF;AACA,QAAI,QAAQ,KAAK,UAAU,IAAI,SAAS,GAAG,GAAG;AAC9C;AAAA,EACF;AACF;AAGA,SAAS,UAAU,OAAO;AACxB,MAAI,CAAC,MAAM,WAAW;AACpB,WAAO;AAAA,EACT;AAEA,UAAQ,WAAW,cAAc,KAAK,CAAC,EAAE;AAEzC,QAAM,UAAU,QAAQ,QAAM,kBAAkB,EAAE,CAAC;AAEnD,SAAO;AAEP,WAAS,kBAAkB,UAAU;AACnC,QAAI,sBAAsB,SAAS,IAAI,GAAG;AACxC;AAAA,IACF;AAEA,aAAS,QAAQ,SAAS,MAAM,QAAQ,4CAA4C,GAAG;AAAA,EACzF;AAEF;",
+  "sourcesContent": ["//import createDebugLogger from 'debug';\nimport clone from 'clone';\nimport {fieldToString, isContentSubfieldCode, nvdebug} from './utils.js';\n\n// Author(s): Nicholas Volk\nexport default function () {\n\n  return {\n    description: 'Normalize various dashes to \"-\"',\n    validate, fix\n  };\n\n  function fix(record) {\n    nvdebug(`FIX ME`);\n    record.fields.forEach(field => {\n      fixDashes(field);\n    });\n\n    const res = {message: [], fix: [], valid: true};\n    return res;\n  }\n\n  function validate(record) {\n    const res = {message: []};\n\n    nvdebug(`VALIDATE ME`);\n    record.fields?.forEach(field => {\n      validateField(field, res);\n    });\n\n    res.valid = !(res.message.length >= 1);\n    return res;\n  }\n\n  function validateField(field, res) {\n    const orig = fieldToString(field);\n    nvdebug(` VALIDATE FIELD '${orig}'`);\n\n    const normalizedField = fixDashes(clone(field));\n    const mod = fieldToString(normalizedField);\n    if (orig === mod) { // Fail as the input is \"broken\"/\"crap\"/sumthing\n      return;\n    }\n    res.message.push(`'TODO: ${orig}' => '${mod}'`);\n    return;\n  }\n}\n\n\nfunction fixDashes(field) {\n  if (!field.subfields) {\n    return field;\n  }\n\n  nvdebug(`Dashing ${fieldToString(field)}`);\n\n  field.subfields.forEach(sf => subfieldFixDashes(sf));\n\n  return field;\n\n  function subfieldFixDashes(subfield) {\n    if (!isContentSubfieldCode(subfield.code, field.tag)) {\n      return;\n    }\n    // Normalize dashes U+2010 ... U+2015 to '-':\n    subfield.value = subfield.value.replace(/[\\u2010\\u2011\\u2012\\u2013\\u2014\\u2015]/ug, '-');\n  }\n\n}\n"],
+  "mappings": "AACA,OAAO,WAAW;AAClB,SAAQ,eAAe,uBAAuB,eAAc;AAG5D,0BAA2B;AAEzB,SAAO;AAAA,IACL,aAAa;AAAA,IACb;AAAA,IAAU;AAAA,EACZ;AAEA,WAAS,IAAI,QAAQ;AACnB,YAAQ,QAAQ;AAChB,WAAO,OAAO,QAAQ,WAAS;AAC7B,gBAAU,KAAK;AAAA,IACjB,CAAC;AAED,UAAM,MAAM,EAAC,SAAS,CAAC,GAAG,KAAK,CAAC,GAAG,OAAO,KAAI;AAC9C,WAAO;AAAA,EACT;AAEA,WAAS,SAAS,QAAQ;AACxB,UAAM,MAAM,EAAC,SAAS,CAAC,EAAC;AAExB,YAAQ,aAAa;AACrB,WAAO,QAAQ,QAAQ,WAAS;AAC9B,oBAAc,OAAO,GAAG;AAAA,IAC1B,CAAC;AAED,QAAI,QAAQ,EAAE,IAAI,QAAQ,UAAU;AACpC,WAAO;AAAA,EACT;AAEA,WAAS,cAAc,OAAO,KAAK;AACjC,UAAM,OAAO,cAAc,KAAK;AAChC,YAAQ,oBAAoB,IAAI,GAAG;AAEnC,UAAM,kBAAkB,UAAU,MAAM,KAAK,CAAC;AAC9C,UAAM,MAAM,cAAc,eAAe;AACzC,QAAI,SAAS,KAAK;AAChB;AAAA,IACF;AACA,QAAI,QAAQ,KAAK,UAAU,IAAI,SAAS,GAAG,GAAG;AAC9C;AAAA,EACF;AACF;AAGA,SAAS,UAAU,OAAO;AACxB,MAAI,CAAC,MAAM,WAAW;AACpB,WAAO;AAAA,EACT;AAEA,UAAQ,WAAW,cAAc,KAAK,CAAC,EAAE;AAEzC,QAAM,UAAU,QAAQ,QAAM,kBAAkB,EAAE,CAAC;AAEnD,SAAO;AAEP,WAAS,kBAAkB,UAAU;AACnC,QAAI,CAAC,sBAAsB,SAAS,MAAM,MAAM,GAAG,GAAG;AACpD;AAAA,IACF;AAEA,aAAS,QAAQ,SAAS,MAAM,QAAQ,4CAA4C,GAAG;AAAA,EACzF;AAEF;",
   "names": []
 }

package/dist/normalizeFieldForComparison.js

@@ -1,20 +1,13 @@
 import clone from "clone";
 import { fieldStripPunctuation } from "./punctuation2.js";
-import { fieldToString, isControlSubfieldCode } from "./utils.js";
+import { fieldToString, isContentSubfieldCode } from "./utils.js";
 import { fieldNormalizeControlNumbers } from "./normalize-identifiers.js";
 import createDebugLogger from "debug";
 import { normalizePartData, subfieldContainsPartData } from "./normalizeSubfieldValueForComparison.js";
+import { isEnnakkotietoSubfield } from "./prepublicationUtils.js";
+import { getSynonym } from "./merge-fields/worldKnowledge.js";
 const debug = createDebugLogger("@natlibfi/melinda-marc-record-merge-reducers:normalizeFieldForComparison");
 const debugDev = debug.extend("dev");
-export function isEnnakkotietoSubfieldG(subfield) {
-  if (valuelessSubfield(subfield)) {
-    return false;
-  }
-  if (subfield.code !== "g") {
-    return false;
-  }
-  return subfield.value.match(/^ENNAKKOTIETO\.?$/gui);
-}
 function debugFieldComparison(oldField, newField) {
   const oldString = fieldToString(oldField);
   const newString = fieldToString(newField);
@@ -39,13 +32,13 @@ function containsCorporateName(tag = "???", subfieldCode = void 0) {
   return false;
 }
 function skipAllSubfieldNormalizations(value, subfieldCode, tag) {
-  if (isEnnakkotietoSubfieldG({ "code": subfieldCode, value })) {
+  if (isEnnakkotietoSubfield({ "code": subfieldCode, value })) {
     return true;
   }
   if (tag === "035" && ["a", "z"].includes(subfieldCode)) {
     return true;
   }
-  if (isControlSubfieldCode(subfieldCode)) {
+  if (!isContentSubfieldCode(subfieldCode, tag)) {
     return true;
   }
   return false;
@@ -167,6 +160,8 @@ function removeDecomposedDiacritics(value = "") {
   return String(value).replace(/\p{Diacritic}/gu, "");
 }
 function normalizeSubfieldValue(value, subfieldCode, tag) {
+  value = removeCharsThatDontCarryMeaning(value, tag, subfieldCode);
+  value = getSynonym(tag, subfieldCode, value);
   value = subfieldValueLowercase(value, subfieldCode, tag);
   value = normalizePartData(value, subfieldCode, tag);
   value = value.replace(/^\[([^[\]]+)\]/gu, "$1");
@@ -203,7 +198,7 @@ function normalizeField(field) {
   return field;
 }
 export function cloneAndNormalizeFieldForComparison(field) {
-  const clonedField = clone(field);
+  const clonedField = cloneAndRemovePunctuation(field);
   if (fieldSkipNormalization(field)) {
     return clonedField;
   }
@@ -212,7 +207,6 @@ export function cloneAndNormalizeFieldForComparison(field) {
       return;
     }
     sf.value = normalizeSubfieldValue(sf.value, sf.code, field.tag);
-    sf.value = removeCharsThatDontCarryMeaning(sf.value, field.tag, sf.code);
   });
   normalizeField(clonedField);
   fieldRemoveDecomposedDiacritics(clonedField);

package/dist/normalizeFieldForComparison.js.map

@@ -1,7 +1,7 @@
 {
   "version": 3,
   "sources": ["../src/normalizeFieldForComparison.js"],
-  "sourcesContent": ["/*\n  Note that this file contains very powerful normalizations and spells that are:\n  - meant for comparing similarity/mergability of two fields (clone, normalize, compare),\n  - and NOT for modifying the actual field!\n\n  This is mainly used by melinda-marc-record-merge-reducers. However, also removeInferiorDataFields fixer also used this.\n  Thus it is here. However, most of the testing is done via merge-reducers...\n*/\nimport clone from 'clone';\nimport {fieldStripPunctuation} from './punctuation2.js';\nimport {fieldToString, isControlSubfieldCode} from './utils.js';\n\nimport {fieldNormalizeControlNumbers/*, normalizeControlSubfieldValue*/} from './normalize-identifiers.js';\nimport createDebugLogger from 'debug';\nimport {normalizePartData, subfieldContainsPartData} from './normalizeSubfieldValueForComparison.js';\n\nconst debug = createDebugLogger('@natlibfi/melinda-marc-record-merge-reducers:normalizeFieldForComparison');\n//const debugData = debug.extend('data');\nconst debugDev = debug.extend('dev');\n\nexport function isEnnakkotietoSubfieldG(subfield) {\n  if (valuelessSubfield(subfield)) {\n    return false;\n  }\n  if (subfield.code !== 'g') {\n    return false;\n  }\n  return subfield.value.match(/^ENNAKKOTIETO\\.?$/gui);\n}\n\nfunction debugFieldComparison(oldField, newField) { // NB: Debug-only function!\n  /*\n  // We may drop certain subfields:\n  if (oldField.subfields.length === newField.subfields.length) {\n    oldField.subfields.forEach((subfield, index) => {\n      const newValue = newField.subfields[index].value;\n      if (subfield.value !== newValue) {\n        nvdebug(`NORMALIZE SUBFIELD: '${subfield.value}' => '${newValue}'`, debugDev);\n      }\n    });\n  }\n  */\n  const oldString = fieldToString(oldField);\n  const newString = fieldToString(newField);\n  if (oldString === newString) {\n    return;\n  }\n  //nvdebug(`NORMALIZE FIELD:\\n '${fieldToString(oldField)}' =>\\n '${fieldToString(newField)}'`, debugDev);\n}\n\nfunction containsHumanName(tag = '???', subfieldCode = undefined) {\n  // NB! This set is for bibs! Auth has 400... What else...\n  if (['100', '600', '700', '800'].includes(tag)) {\n    if (subfieldCode === undefined || subfieldCode === 'a') {\n      return true;\n    }\n  }\n  // Others?\n  return false;\n}\n\nfunction containsCorporateName(tag = '???', subfieldCode = undefined) {\n  // NB! This set is for bibs! Auth has 400... What else...\n  if (['110', '610', '710', '810'].includes(tag)) {\n    if (subfieldCode === undefined || subfieldCode === 'a') {\n      return true;\n    }\n  }\n  // Others?\n  return false;\n}\n\nfunction skipAllSubfieldNormalizations(value, subfieldCode, tag) {\n\n  if (isEnnakkotietoSubfieldG({'code': subfieldCode, value})) {\n    return true;\n  }\n\n  if (tag === '035' && ['a', 'z'].includes(subfieldCode)) { // A\n    return true;\n  }\n\n  if (isControlSubfieldCode(subfieldCode)) {\n    return true;\n  }\n  return false;\n}\n\nfunction skipSubfieldLowercase(value, subfieldCode, tag) {\n  // These may contain Roman Numerals...\n  if (subfieldContainsPartData(tag, subfieldCode)) {\n    return true;\n  }\n\n  return skipAllSubfieldNormalizations(value, subfieldCode, tag);\n}\n\nfunction skipAllFieldNormalizations(tag) {\n  if (['LOW', 'SID'].includes(tag)) {\n    return true;\n  }\n  return false;\n}\n\n\nfunction subfieldValueLowercase(value, subfieldCode, tag) {\n  if (skipSubfieldLowercase(value, subfieldCode, tag)) {\n    return value;\n  }\n\n  //return value.toLowerCase();\n  const newValue = value.toLowerCase();\n  if (newValue !== value) {\n    //nvdebug(`SVL ${tag} $${subfieldCode} '${value}' =>`, debugDev);\n    //nvdebug(`SVL ${tag} $${subfieldCode} '${newValue}'`, debugDev);\n    return newValue;\n  }\n  return value;\n}\n\nfunction subfieldLowercase(sf, tag) {\n  if (valuelessSubfield(sf)) {\n    return;\n  }\n  sf.value = subfieldValueLowercase(sf.value, sf.code, tag);\n}\n\nfunction fieldLowercase(field) {\n  if (skipFieldLowercase(field)) {\n    return;\n  }\n\n  field.subfields.forEach(sf => subfieldLowercase(sf, field.tag));\n\n  function skipFieldLowercase(field) {\n    if (skipAllFieldNormalizations(field.tag)) {\n      return true;\n    }\n    // Skip non-interesting fields\n    if (!containsHumanName(field.tag) && !containsCorporateName(field.tag) && !['240', '245', '630'].includes(field.tag)) {\n      return true;\n    }\n\n    return false;\n  }\n}\n\n\nfunction hack490SubfieldA(field) {\n  if (field.tag !== '490') {\n    return;\n  }\n  field.subfields.forEach(sf => removeSarja(sf));\n\n  // NB! This won't work, if the punctuation has not been stripped beforehand!\n  function removeSarja(subfield) {\n    if (valuelessSubfield(subfield)) {\n      return;\n    }\n\n    if (subfield.code !== 'a') {\n      return;\n    }\n    const tmp = subfield.value.replace(/ ?-(?:[a-z]|\u00E4|\u00F6)*sarja$/u, '');\n    if (tmp.length > 0) {\n      subfield.value = tmp;\n      return;\n    }\n  }\n}\n\nexport function tagAndSubfieldCodeReferToIsbn(tag, subfieldCode) {\n  // NB! We don't do this to 020$z!\n  if (subfieldCode === 'z' && ['765', '767', '770', '772', '773', '774', '776', '777', '780', '785', '786', '787'].includes(tag)) {\n    return true;\n  }\n  if (tag === '020' && subfieldCode === 'a') {\n    return true;\n  }\n  return false;\n}\n\nfunction looksLikeIsbn(value) {\n  // Does not check validity!\n  if (value.match(/^(?:[0-9]-?){9}(?:[0-9]-?[0-9]-?[0-9]-?)?[0-9Xx]$/u)) {\n    return true;\n  }\n  return false;\n}\n\nfunction normalizeISBN(field) {\n  if (!field.subfields) {\n    return;\n  }\n\n  //nvdebug(`ISBN-field? ${fieldToString(field)}`);\n  const relevantSubfields = field.subfields.filter(sf => tagAndSubfieldCodeReferToIsbn(field.tag, sf.code) && looksLikeIsbn(sf.value));\n  relevantSubfields.forEach(sf => normalizeIsbnSubfield(sf));\n\n  function normalizeIsbnSubfield(sf) {\n    if (valuelessSubfield(sf)) {\n      return;\n    }\n    //nvdebug(` ISBN-subfield? ${subfieldToString(sf)}`);\n    sf.value = sf.value.replace(/-/ug, '');\n    sf.value = sf.value.replace(/x/u, 'X');\n  }\n\n}\n\nfunction fieldSpecificHacks(field) {\n  normalizeISBN(field); // 020$a, not $z!\n  hack490SubfieldA(field);\n}\n\nexport function fieldTrimSubfieldValues(field) {\n  field.subfields?.forEach((sf) => {\n    if (valuelessSubfield(sf)) {\n      return;\n    }\n    sf.value = sf.value.replace(/^[ \\t\\n]+/u, '');\n    sf.value = sf.value.replace(/[ \\t\\n]+$/u, '');\n    sf.value = sf.value.replace(/[ \\t\\n]+/gu, ' ');\n  });\n}\n\nfunction fieldRemoveDecomposedDiacritics(field) {\n  // Raison d'\u00EAtre/motivation: \"Sir\u00E9n\" and diacriticless \"Siren\" might refer to a same surname, so this normalization\n  // allows us to compare authors and avoid duplicate fields.\n  field.subfields.forEach((sf) => {\n    if (valuelessSubfield(sf)) {\n        return;\n    }\n    sf.value = removeDecomposedDiacritics(sf.value);\n  });\n}\n\nfunction removeDecomposedDiacritics(value = '') {\n  // NB #1: Does nothing to precomposed letters. Do String.normalize('NFD') first, if you want to handle them.\n  // NB #2: Finnish letters '\u00E5', '\u00E4', '\u00F6', '\u00C5', \u00C4', and '\u00D6' should be handled (=precomposed) before calling this. (= keep them as is)\n  // NB #3: Calling our very own fixComposition() before this function handles both #1 and #2.\n  return String(value).replace(/\\p{Diacritic}/gu, '');\n}\n\nfunction normalizeSubfieldValue(value, subfieldCode, tag) {\n  // NB! For comparison of values only\n  /* eslint-disable */\n  value = subfieldValueLowercase(value, subfieldCode, tag);\n\n  // Normalize: s. = sivut = pp.\n  value = normalizePartData(value, subfieldCode, tag);\n  value = value.replace(/^\\[([^[\\]]+)\\]/gu, '$1'); // eslint-disable-line functional/immutable-data\n\n  if (['130', '730'].includes(tag) && subfieldCode === 'a') {\n    value = value.replace(' : ', ', '); // \"Halloween ends (elokuva, 2022)\" vs \"Halloween ends (elokuva : 2023)\"\n  }\n  /* eslint-enable */\n\n  // Not going to do these in the foreseeable future, but keeping them here for discussion:\n  // Possible normalizations include but are not limited to:\n  // \u00F8 => \u00F6? Might be language dependent: 041 $a fin => \u00F6, 041 $a eng => o?\n  // \u00D8 => \u00D6?\n  // \u00DF => ss\n  // \u00FE => th (NB! Both upper and lower case)\n  // ...\n  // Probably nots:\n  // \u00FC => y (probably not, though this correlates with Finnish letter-to-sound rules)\n  // w => v (OK for Finnish sorting in certain cases, but we are not here, are we?)\n  // I guess we should use decomposed values in code here. (Not sure what composition my examples above use.)\n  return value;\n}\n\nexport function cloneAndRemovePunctuation(field) {\n  const clonedField = clone(field);\n  if (fieldSkipNormalization(field)) {\n    return clonedField;\n  }\n  fieldStripPunctuation(clonedField);\n  fieldTrimSubfieldValues(clonedField);\n  debugDev('PUNC');\n  debugFieldComparison(field, clonedField);\n\n  return clonedField;\n}\n\nfunction removeCharsThatDontCarryMeaning(value, tag, subfieldCode) {\n  if (tag === '080') {\n    return value;\n  }\n\n  // 3\" refers to inches, but as this is for comparison only we don't mind...\n  value = value.replace(/['\u2018\u2019\"\u201E\u201C\u201D\u00AB\u00BB]/gu, ''); // MET-570 et al. Subset of https://hexdocs.pm/ex_unicode/Unicode.Category.QuoteMarks.html\n  // MRA-273: Handle X00$a name initials.\n  // NB #1: that we remove spaces for comparison (as it simpler), though actually space should be used. Doesn't matter as this is comparison only.\n  // NB #2: we might/should eventually write a validator/fixer that adds those spaces. After that point, this expection should become obsolete.\n  if (subfieldCode === 'a' && ['100', '400', '600', '700', '800'].includes(tag)) { // 400 is used in auth records. It's not a bib field at all.\n    value = value.replace(/([A-Z]|\u00C5|\u00C4|\u00D6)\\. +/ugi, '$1.');\n  }\n\n  return value;\n}\n\nfunction normalizeField(field) {\n  //sf.value = removeDecomposedDiacritics(sf.value);\n  fieldStripPunctuation(field);\n  fieldLowercase(field);\n  fieldNormalizeControlNumbers(field); // FIN11 vs FI-MELINDA etc.\n  return field;\n}\n\nexport function cloneAndNormalizeFieldForComparison(field) {\n  // NB! This new field is for comparison purposes only.\n  // Some of the normalizations might be considered a bit overkill for other purposes.\n  const clonedField = clone(field);\n  if (fieldSkipNormalization(field)) {\n    return clonedField;\n  }\n  clonedField.subfields.forEach((sf) => { // Do this for all fields or some fields?\n    if (valuelessSubfield(sf)) {\n      return;\n    }\n    sf.value = normalizeSubfieldValue(sf.value, sf.code, field.tag);\n    sf.value = removeCharsThatDontCarryMeaning(sf.value, field.tag, sf.code);\n  });\n\n  normalizeField(clonedField);\n  fieldRemoveDecomposedDiacritics(clonedField);\n  fieldSpecificHacks(clonedField);\n  fieldTrimSubfieldValues(clonedField);\n\n\n  debugFieldComparison(field, clonedField); // For debugging purposes only\n\n  return clonedField;\n}\n\nfunction fieldSkipNormalization(field) {\n  if (!field.subfields || ['018', '066', '080', '083'].includes(field.tag)) {\n    return true;\n  }\n  return false;\n}\n\nfunction valuelessSubfield(sf) {\n  return sf.value === undefined;\n}"],
-  "mappings": "AAQA,OAAO,WAAW;AAClB,SAAQ,6BAA4B;AACpC,SAAQ,eAAe,6BAA4B;AAEnD,SAAQ,oCAAsE;AAC9E,OAAO,uBAAuB;AAC9B,SAAQ,mBAAmB,gCAA+B;AAE1D,MAAM,QAAQ,kBAAkB,0EAA0E;AAE1G,MAAM,WAAW,MAAM,OAAO,KAAK;AAE5B,gBAAS,wBAAwB,UAAU;AAChD,MAAI,kBAAkB,QAAQ,GAAG;AAC/B,WAAO;AAAA,EACT;AACA,MAAI,SAAS,SAAS,KAAK;AACzB,WAAO;AAAA,EACT;AACA,SAAO,SAAS,MAAM,MAAM,sBAAsB;AACpD;AAEA,SAAS,qBAAqB,UAAU,UAAU;AAYhD,QAAM,YAAY,cAAc,QAAQ;AACxC,QAAM,YAAY,cAAc,QAAQ;AACxC,MAAI,cAAc,WAAW;AAC3B;AAAA,EACF;AAEF;AAEA,SAAS,kBAAkB,MAAM,OAAO,eAAe,QAAW;AAEhE,MAAI,CAAC,OAAO,OAAO,OAAO,KAAK,EAAE,SAAS,GAAG,GAAG;AAC9C,QAAI,iBAAiB,UAAa,iBAAiB,KAAK;AACtD,aAAO;AAAA,IACT;AAAA,EACF;AAEA,SAAO;AACT;AAEA,SAAS,sBAAsB,MAAM,OAAO,eAAe,QAAW;AAEpE,MAAI,CAAC,OAAO,OAAO,OAAO,KAAK,EAAE,SAAS,GAAG,GAAG;AAC9C,QAAI,iBAAiB,UAAa,iBAAiB,KAAK;AACtD,aAAO;AAAA,IACT;AAAA,EACF;AAEA,SAAO;AACT;AAEA,SAAS,8BAA8B,OAAO,cAAc,KAAK;AAE/D,MAAI,wBAAwB,EAAC,QAAQ,cAAc,MAAK,CAAC,GAAG;AAC1D,WAAO;AAAA,EACT;AAEA,MAAI,QAAQ,SAAS,CAAC,KAAK,GAAG,EAAE,SAAS,YAAY,GAAG;AACtD,WAAO;AAAA,EACT;AAEA,MAAI,sBAAsB,YAAY,GAAG;AACvC,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAEA,SAAS,sBAAsB,OAAO,cAAc,KAAK;AAEvD,MAAI,yBAAyB,KAAK,YAAY,GAAG;AAC/C,WAAO;AAAA,EACT;AAEA,SAAO,8BAA8B,OAAO,cAAc,GAAG;AAC/D;AAEA,SAAS,2BAA2B,KAAK;AACvC,MAAI,CAAC,OAAO,KAAK,EAAE,SAAS,GAAG,GAAG;AAChC,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAGA,SAAS,uBAAuB,OAAO,cAAc,KAAK;AACxD,MAAI,sBAAsB,OAAO,cAAc,GAAG,GAAG;AACnD,WAAO;AAAA,EACT;AAGA,QAAM,WAAW,MAAM,YAAY;AACnC,MAAI,aAAa,OAAO;AAGtB,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAEA,SAAS,kBAAkB,IAAI,KAAK;AAClC,MAAI,kBAAkB,EAAE,GAAG;AACzB;AAAA,EACF;AACA,KAAG,QAAQ,uBAAuB,GAAG,OAAO,GAAG,MAAM,GAAG;AAC1D;AAEA,SAAS,eAAe,OAAO;AAC7B,MAAI,mBAAmB,KAAK,GAAG;AAC7B;AAAA,EACF;AAEA,QAAM,UAAU,QAAQ,QAAM,kBAAkB,IAAI,MAAM,GAAG,CAAC;AAE9D,WAAS,mBAAmBA,QAAO;AACjC,QAAI,2BAA2BA,OAAM,GAAG,GAAG;AACzC,aAAO;AAAA,IACT;AAEA,QAAI,CAAC,kBAAkBA,OAAM,GAAG,KAAK,CAAC,sBAAsBA,OAAM,GAAG,KAAK,CAAC,CAAC,OAAO,OAAO,KAAK,EAAE,SAASA,OAAM,GAAG,GAAG;AACpH,aAAO;AAAA,IACT;AAEA,WAAO;AAAA,EACT;AACF;AAGA,SAAS,iBAAiB,OAAO;AAC/B,MAAI,MAAM,QAAQ,OAAO;AACvB;AAAA,EACF;AACA,QAAM,UAAU,QAAQ,QAAM,YAAY,EAAE,CAAC;AAG7C,WAAS,YAAY,UAAU;AAC7B,QAAI,kBAAkB,QAAQ,GAAG;AAC/B;AAAA,IACF;AAEA,QAAI,SAAS,SAAS,KAAK;AACzB;AAAA,IACF;AACA,UAAM,MAAM,SAAS,MAAM,QAAQ,4BAA4B,EAAE;AACjE,QAAI,IAAI,SAAS,GAAG;AAClB,eAAS,QAAQ;AACjB;AAAA,IACF;AAAA,EACF;AACF;AAEO,gBAAS,8BAA8B,KAAK,cAAc;AAE/D,MAAI,iBAAiB,OAAO,CAAC,OAAO,OAAO,OAAO,OAAO,OAAO,OAAO,OAAO,OAAO,OAAO,OAAO,OAAO,KAAK,EAAE,SAAS,GAAG,GAAG;AAC9H,WAAO;AAAA,EACT;AACA,MAAI,QAAQ,SAAS,iBAAiB,KAAK;AACzC,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAEA,SAAS,cAAc,OAAO;AAE5B,MAAI,MAAM,MAAM,oDAAoD,GAAG;AACrE,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAEA,SAAS,cAAc,OAAO;AAC5B,MAAI,CAAC,MAAM,WAAW;AACpB;AAAA,EACF;AAGA,QAAM,oBAAoB,MAAM,UAAU,OAAO,QAAM,8BAA8B,MAAM,KAAK,GAAG,IAAI,KAAK,cAAc,GAAG,KAAK,CAAC;AACnI,oBAAkB,QAAQ,QAAM,sBAAsB,EAAE,CAAC;AAEzD,WAAS,sBAAsB,IAAI;AACjC,QAAI,kBAAkB,EAAE,GAAG;AACzB;AAAA,IACF;AAEA,OAAG,QAAQ,GAAG,MAAM,QAAQ,OAAO,EAAE;AACrC,OAAG,QAAQ,GAAG,MAAM,QAAQ,MAAM,GAAG;AAAA,EACvC;AAEF;AAEA,SAAS,mBAAmB,OAAO;AACjC,gBAAc,KAAK;AACnB,mBAAiB,KAAK;AACxB;AAEO,gBAAS,wBAAwB,OAAO;AAC7C,QAAM,WAAW,QAAQ,CAAC,OAAO;AAC/B,QAAI,kBAAkB,EAAE,GAAG;AACzB;AAAA,IACF;AACA,OAAG,QAAQ,GAAG,MAAM,QAAQ,cAAc,EAAE;AAC5C,OAAG,QAAQ,GAAG,MAAM,QAAQ,cAAc,EAAE;AAC5C,OAAG,QAAQ,GAAG,MAAM,QAAQ,cAAc,GAAG;AAAA,EAC/C,CAAC;AACH;AAEA,SAAS,gCAAgC,OAAO;AAG9C,QAAM,UAAU,QAAQ,CAAC,OAAO;AAC9B,QAAI,kBAAkB,EAAE,GAAG;AACvB;AAAA,IACJ;AACA,OAAG,QAAQ,2BAA2B,GAAG,KAAK;AAAA,EAChD,CAAC;AACH;AAEA,SAAS,2BAA2B,QAAQ,IAAI;AAI9C,SAAO,OAAO,KAAK,EAAE,QAAQ,mBAAmB,EAAE;AACpD;AAEA,SAAS,uBAAuB,OAAO,cAAc,KAAK;AAGxD,UAAQ,uBAAuB,OAAO,cAAc,GAAG;AAGvD,UAAQ,kBAAkB,OAAO,cAAc,GAAG;AAClD,UAAQ,MAAM,QAAQ,oBAAoB,IAAI;AAE9C,MAAI,CAAC,OAAO,KAAK,EAAE,SAAS,GAAG,KAAK,iBAAiB,KAAK;AACxD,YAAQ,MAAM,QAAQ,OAAO,IAAI;AAAA,EACnC;AAcA,SAAO;AACT;AAEO,gBAAS,0BAA0B,OAAO;AAC/C,QAAM,cAAc,MAAM,KAAK;AAC/B,MAAI,uBAAuB,KAAK,GAAG;AACjC,WAAO;AAAA,EACT;AACA,wBAAsB,WAAW;AACjC,0BAAwB,WAAW;AACnC,WAAS,MAAM;AACf,uBAAqB,OAAO,WAAW;AAEvC,SAAO;AACT;AAEA,SAAS,gCAAgC,OAAO,KAAK,cAAc;AACjE,MAAI,QAAQ,OAAO;AACjB,WAAO;AAAA,EACT;AAGA,UAAQ,MAAM,QAAQ,iBAAiB,EAAE;AAIzC,MAAI,iBAAiB,OAAO,CAAC,OAAO,OAAO,OAAO,OAAO,KAAK,EAAE,SAAS,GAAG,GAAG;AAC7E,YAAQ,MAAM,QAAQ,wBAAwB,KAAK;AAAA,EACrD;AAEA,SAAO;AACT;AAEA,SAAS,eAAe,OAAO;AAE7B,wBAAsB,KAAK;AAC3B,iBAAe,KAAK;AACpB,+BAA6B,KAAK;AAClC,SAAO;AACT;AAEO,gBAAS,oCAAoC,OAAO;AAGzD,QAAM,cAAc,MAAM,KAAK;AAC/B,MAAI,uBAAuB,KAAK,GAAG;AACjC,WAAO;AAAA,EACT;AACA,cAAY,UAAU,QAAQ,CAAC,OAAO;AACpC,QAAI,kBAAkB,EAAE,GAAG;AACzB;AAAA,IACF;AACA,OAAG,QAAQ,uBAAuB,GAAG,OAAO,GAAG,MAAM,MAAM,GAAG;AAC9D,OAAG,QAAQ,gCAAgC,GAAG,OAAO,MAAM,KAAK,GAAG,IAAI;AAAA,EACzE,CAAC;AAED,iBAAe,WAAW;AAC1B,kCAAgC,WAAW;AAC3C,qBAAmB,WAAW;AAC9B,0BAAwB,WAAW;AAGnC,uBAAqB,OAAO,WAAW;AAEvC,SAAO;AACT;AAEA,SAAS,uBAAuB,OAAO;AACrC,MAAI,CAAC,MAAM,aAAa,CAAC,OAAO,OAAO,OAAO,KAAK,EAAE,SAAS,MAAM,GAAG,GAAG;AACxE,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAEA,SAAS,kBAAkB,IAAI;AAC7B,SAAO,GAAG,UAAU;AACtB;",
+  "sourcesContent": ["/*\n  Note that this file contains very powerful normalizations and spells that are:\n  - meant for comparing similarity/mergability of two fields (clone, normalize, compare),\n  - and NOT for modifying the actual field!\n\n  This is mainly used by melinda-marc-record-merge-reducers. However, also removeInferiorDataFields fixer also used this.\n  Thus it is here. However, most of the testing is done via merge-reducers...\n*/\nimport clone from 'clone';\nimport {fieldStripPunctuation} from './punctuation2.js';\nimport {fieldToString, isContentSubfieldCode} from './utils.js';\n\nimport {fieldNormalizeControlNumbers/*, normalizeControlSubfieldValue*/} from './normalize-identifiers.js';\nimport createDebugLogger from 'debug';\nimport {normalizePartData, subfieldContainsPartData} from './normalizeSubfieldValueForComparison.js';\nimport {isEnnakkotietoSubfield} from './prepublicationUtils.js';\nimport {getSynonym} from './merge-fields/worldKnowledge.js';\n\nconst debug = createDebugLogger('@natlibfi/melinda-marc-record-merge-reducers:normalizeFieldForComparison');\n//const debugData = debug.extend('data');\nconst debugDev = debug.extend('dev');\n\nfunction debugFieldComparison(oldField, newField) { // NB: Debug-only function!\n  /*\n  // We may drop certain subfields:\n  if (oldField.subfields.length === newField.subfields.length) {\n    oldField.subfields.forEach((subfield, index) => {\n      const newValue = newField.subfields[index].value;\n      if (subfield.value !== newValue) {\n        nvdebug(`NORMALIZE SUBFIELD: '${subfield.value}' => '${newValue}'`, debugDev);\n      }\n    });\n  }\n  */\n  const oldString = fieldToString(oldField);\n  const newString = fieldToString(newField);\n  if (oldString === newString) {\n    return;\n  }\n  //nvdebug(`NORMALIZE FIELD:\\n '${fieldToString(oldField)}' =>\\n '${fieldToString(newField)}'`, debugDev);\n}\n\nfunction containsHumanName(tag = '???', subfieldCode = undefined) {\n  // NB! This set is for bibs! Auth has 400... What else...\n  if (['100', '600', '700', '800'].includes(tag)) {\n    if (subfieldCode === undefined || subfieldCode === 'a') {\n      return true;\n    }\n  }\n  // Others?\n  return false;\n}\n\nfunction containsCorporateName(tag = '???', subfieldCode = undefined) {\n  // NB! This set is for bibs! Auth has 410... What else...\n  if (['110', '610', '710', '810'].includes(tag)) {\n    if (subfieldCode === undefined || subfieldCode === 'a') {\n      return true;\n    }\n  }\n  // Others?\n  return false;\n}\n\nfunction skipAllSubfieldNormalizations(value, subfieldCode, tag) {\n\n  if (isEnnakkotietoSubfield({'code': subfieldCode, value})) {\n    return true;\n  }\n\n  if (tag === '035' && ['a', 'z'].includes(subfieldCode)) {\n    return true;\n  }\n\n  if (!isContentSubfieldCode(subfieldCode, tag)) {\n    return true;\n  }\n  return false;\n}\n\nfunction skipSubfieldLowercase(value, subfieldCode, tag) {\n  // These may contain Roman Numerals...\n  if (subfieldContainsPartData(tag, subfieldCode)) {\n    return true;\n  }\n\n  return skipAllSubfieldNormalizations(value, subfieldCode, tag);\n}\n\nfunction skipAllFieldNormalizations(tag) {\n  if (['LOW', 'SID'].includes(tag)) {\n    return true;\n  }\n  return false;\n}\n\n\nfunction subfieldValueLowercase(value, subfieldCode, tag) {\n  if (skipSubfieldLowercase(value, subfieldCode, tag)) {\n    return value;\n  }\n\n  //return value.toLowerCase();\n  const newValue = value.toLowerCase();\n  if (newValue !== value) {\n    //nvdebug(`SVL ${tag} $${subfieldCode} '${value}' =>`, debugDev);\n    //nvdebug(`SVL ${tag} $${subfieldCode} '${newValue}'`, debugDev);\n    return newValue;\n  }\n  return value;\n}\n\nfunction subfieldLowercase(sf, tag) {\n  if (valuelessSubfield(sf)) {\n    return;\n  }\n  sf.value = subfieldValueLowercase(sf.value, sf.code, tag);\n}\n\nfunction fieldLowercase(field) {\n  if (skipFieldLowercase(field)) {\n    return;\n  }\n\n  field.subfields.forEach(sf => subfieldLowercase(sf, field.tag));\n\n  function skipFieldLowercase(field) {\n    if (skipAllFieldNormalizations(field.tag)) {\n      return true;\n    }\n    // Skip non-interesting fields\n    if (!containsHumanName(field.tag) && !containsCorporateName(field.tag) && !['240', '245', '630'].includes(field.tag)) {\n      return true;\n    }\n\n    return false;\n  }\n}\n\n\nfunction hack490SubfieldA(field) {\n  if (field.tag !== '490') {\n    return;\n  }\n  field.subfields.forEach(sf => removeSarja(sf));\n\n  // NB! This won't work, if the punctuation has not been stripped beforehand!\n  function removeSarja(subfield) {\n    if (valuelessSubfield(subfield)) {\n      return;\n    }\n\n    if (subfield.code !== 'a') {\n      return;\n    }\n    const tmp = subfield.value.replace(/ ?-(?:[a-z]|\u00E4|\u00F6)*sarja$/u, '');\n    if (tmp.length > 0) {\n      subfield.value = tmp;\n      return;\n    }\n  }\n}\n\nexport function tagAndSubfieldCodeReferToIsbn(tag, subfieldCode) {\n  // NB! We don't do this to 020$z!\n  if (subfieldCode === 'z' && ['765', '767', '770', '772', '773', '774', '776', '777', '780', '785', '786', '787'].includes(tag)) {\n    return true;\n  }\n  if (tag === '020' && subfieldCode === 'a') {\n    return true;\n  }\n  return false;\n}\n\nfunction looksLikeIsbn(value) {\n  // Does not check validity!\n  if (value.match(/^(?:[0-9]-?){9}(?:[0-9]-?[0-9]-?[0-9]-?)?[0-9Xx]$/u)) {\n    return true;\n  }\n  return false;\n}\n\nfunction normalizeISBN(field) {\n  if (!field.subfields) {\n    return;\n  }\n\n  //nvdebug(`ISBN-field? ${fieldToString(field)}`);\n  const relevantSubfields = field.subfields.filter(sf => tagAndSubfieldCodeReferToIsbn(field.tag, sf.code) && looksLikeIsbn(sf.value));\n  relevantSubfields.forEach(sf => normalizeIsbnSubfield(sf));\n\n  function normalizeIsbnSubfield(sf) {\n    if (valuelessSubfield(sf)) {\n      return;\n    }\n    //nvdebug(` ISBN-subfield? ${subfieldToString(sf)}`);\n    sf.value = sf.value.replace(/-/ug, '');\n    sf.value = sf.value.replace(/x/u, 'X');\n  }\n\n}\n\nfunction fieldSpecificHacks(field) {\n  normalizeISBN(field); // 020$a, not $z!\n  hack490SubfieldA(field);\n}\n\nexport function fieldTrimSubfieldValues(field) {\n  field.subfields?.forEach((sf) => {\n    if (valuelessSubfield(sf)) {\n      return;\n    }\n    sf.value = sf.value.replace(/^[ \\t\\n]+/u, '');\n    sf.value = sf.value.replace(/[ \\t\\n]+$/u, '');\n    sf.value = sf.value.replace(/[ \\t\\n]+/gu, ' ');\n  });\n}\n\nfunction fieldRemoveDecomposedDiacritics(field) {\n  // Raison d'\u00EAtre/motivation: \"Sir\u00E9n\" and diacriticless \"Siren\" might refer to a same surname, so this normalization\n  // allows us to compare authors and avoid duplicate fields.\n  field.subfields.forEach((sf) => {\n    if (valuelessSubfield(sf)) {\n        return;\n    }\n    sf.value = removeDecomposedDiacritics(sf.value);\n  });\n}\n\nfunction removeDecomposedDiacritics(value = '') {\n  // NB #1: Does nothing to precomposed letters. Do String.normalize('NFD') first, if you want to handle them.\n  // NB #2: Finnish letters '\u00E5', '\u00E4', '\u00F6', '\u00C5', \u00C4', and '\u00D6' should be handled (=precomposed) before calling this. (= keep them as is)\n  // NB #3: Calling our very own fixComposition() before this function handles both #1 and #2.\n  return String(value).replace(/\\p{Diacritic}/gu, '');\n}\n\nfunction normalizeSubfieldValue(value, subfieldCode, tag) {\n  // NB! For comparison of values only\n  /* beslint-disable */\n  value = removeCharsThatDontCarryMeaning(value, tag, subfieldCode);\n  value = getSynonym(tag, subfieldCode, value); // Must be done before punc stripping and lowercasing...\n  value = subfieldValueLowercase(value, subfieldCode, tag);\n\n\n  // Normalize: s. = sivut = pp.\n  value = normalizePartData(value, subfieldCode, tag);\n  value = value.replace(/^\\[([^[\\]]+)\\]/gu, '$1');\n\n  if (['130', '730'].includes(tag) && subfieldCode === 'a') {\n    value = value.replace(' : ', ', '); // \"Halloween ends (elokuva, 2022)\" vs \"Halloween ends (elokuva : 2023)\"\n  }\n  /* beslint-enable */\n\n  // Not going to do these in the foreseeable future, but keeping them here for discussion:\n  // Possible normalizations include but are not limited to:\n  // \u00F8 => \u00F6? Might be language dependent: 041 $a fin => \u00F6, 041 $a eng => o?\n  // \u00D8 => \u00D6?\n  // \u00DF => ss\n  // \u00FE => th (NB! Both upper and lower case)\n  // ...\n  // Probably nots:\n  // \u00FC => y (probably not, though this correlates with Finnish letter-to-sound rules)\n  // w => v (OK for Finnish sorting in certain cases, but we are not here, are we?)\n  // I guess we should use decomposed values in code here. (Not sure what composition my examples above use.)\n  return value;\n}\n\nexport function cloneAndRemovePunctuation(field) {\n  const clonedField = clone(field);\n  if (fieldSkipNormalization(field)) {\n    return clonedField;\n  }\n  fieldStripPunctuation(clonedField);\n  fieldTrimSubfieldValues(clonedField);\n  debugDev('PUNC');\n  debugFieldComparison(field, clonedField);\n\n  return clonedField;\n}\n\nfunction removeCharsThatDontCarryMeaning(value, tag, subfieldCode) {\n  if (tag === '080') {\n    return value;\n  }\n\n  // 3\" refers to inches, but as this is for comparison only we don't mind...\n  value = value.replace(/['\u2018\u2019\"\u201E\u201C\u201D\u00AB\u00BB]/gu, ''); // MET-570 et al. Subset of https://hexdocs.pm/ex_unicode/Unicode.Category.QuoteMarks.html\n  // MRA-273: Handle X00$a name initials.\n  // NB #1: that we remove spaces for comparison (as it simpler), though actually space should be used. Doesn't matter as this is comparison only.\n  // NB #2: we might/should eventually write a validator/fixer that adds those spaces. After that point, this expection should become obsolete.\n  if (subfieldCode === 'a' && ['100', '400', '600', '700', '800'].includes(tag)) { // 400 is used in auth records. It's not a bib field at all.\n    value = value.replace(/([A-Z]|\u00C5|\u00C4|\u00D6)\\. +/ugi, '$1.');\n  }\n\n  return value;\n}\n\nfunction normalizeField(field) {\n  //sf.value = removeDecomposedDiacritics(sf.value);\n  fieldStripPunctuation(field);\n  fieldLowercase(field);\n  fieldNormalizeControlNumbers(field); // FIN11 vs FI-MELINDA etc.\n  return field;\n}\n\nexport function cloneAndNormalizeFieldForComparison(field) {\n  // NB! This new field is for comparison purposes only.\n  // Some of the normalizations might be considered a bit overkill for other purposes.\n  const clonedField = cloneAndRemovePunctuation(field); // was only clone(field)\n\n  if (fieldSkipNormalization(field)) {\n    return clonedField;\n  }\n  clonedField.subfields.forEach((sf) => { // Do this for all fields or some fields?\n    if (valuelessSubfield(sf)) {\n      return;\n    }\n\n    sf.value = normalizeSubfieldValue(sf.value, sf.code, field.tag);\n    //sf.value = normalizeForSamenessCheck(field.tag, sf.code, sf.value);\n\n\n  });\n\n  normalizeField(clonedField);\n  fieldRemoveDecomposedDiacritics(clonedField);\n  fieldSpecificHacks(clonedField);\n  fieldTrimSubfieldValues(clonedField);\n\n\n  debugFieldComparison(field, clonedField); // For debugging purposes only\n\n  return clonedField;\n}\n\nfunction fieldSkipNormalization(field) {\n  if (!field.subfields || ['018', '066', '080', '083'].includes(field.tag)) {\n    return true;\n  }\n  return false;\n}\n\nfunction valuelessSubfield(sf) {\n  return sf.value === undefined;\n}"],
+  "mappings": "AAQA,OAAO,WAAW;AAClB,SAAQ,6BAA4B;AACpC,SAAQ,eAAe,6BAA4B;AAEnD,SAAQ,oCAAsE;AAC9E,OAAO,uBAAuB;AAC9B,SAAQ,mBAAmB,gCAA+B;AAC1D,SAAQ,8BAA6B;AACrC,SAAQ,kBAAiB;AAEzB,MAAM,QAAQ,kBAAkB,0EAA0E;AAE1G,MAAM,WAAW,MAAM,OAAO,KAAK;AAEnC,SAAS,qBAAqB,UAAU,UAAU;AAYhD,QAAM,YAAY,cAAc,QAAQ;AACxC,QAAM,YAAY,cAAc,QAAQ;AACxC,MAAI,cAAc,WAAW;AAC3B;AAAA,EACF;AAEF;AAEA,SAAS,kBAAkB,MAAM,OAAO,eAAe,QAAW;AAEhE,MAAI,CAAC,OAAO,OAAO,OAAO,KAAK,EAAE,SAAS,GAAG,GAAG;AAC9C,QAAI,iBAAiB,UAAa,iBAAiB,KAAK;AACtD,aAAO;AAAA,IACT;AAAA,EACF;AAEA,SAAO;AACT;AAEA,SAAS,sBAAsB,MAAM,OAAO,eAAe,QAAW;AAEpE,MAAI,CAAC,OAAO,OAAO,OAAO,KAAK,EAAE,SAAS,GAAG,GAAG;AAC9C,QAAI,iBAAiB,UAAa,iBAAiB,KAAK;AACtD,aAAO;AAAA,IACT;AAAA,EACF;AAEA,SAAO;AACT;AAEA,SAAS,8BAA8B,OAAO,cAAc,KAAK;AAE/D,MAAI,uBAAuB,EAAC,QAAQ,cAAc,MAAK,CAAC,GAAG;AACzD,WAAO;AAAA,EACT;AAEA,MAAI,QAAQ,SAAS,CAAC,KAAK,GAAG,EAAE,SAAS,YAAY,GAAG;AACtD,WAAO;AAAA,EACT;AAEA,MAAI,CAAC,sBAAsB,cAAc,GAAG,GAAG;AAC7C,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAEA,SAAS,sBAAsB,OAAO,cAAc,KAAK;AAEvD,MAAI,yBAAyB,KAAK,YAAY,GAAG;AAC/C,WAAO;AAAA,EACT;AAEA,SAAO,8BAA8B,OAAO,cAAc,GAAG;AAC/D;AAEA,SAAS,2BAA2B,KAAK;AACvC,MAAI,CAAC,OAAO,KAAK,EAAE,SAAS,GAAG,GAAG;AAChC,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAGA,SAAS,uBAAuB,OAAO,cAAc,KAAK;AACxD,MAAI,sBAAsB,OAAO,cAAc,GAAG,GAAG;AACnD,WAAO;AAAA,EACT;AAGA,QAAM,WAAW,MAAM,YAAY;AACnC,MAAI,aAAa,OAAO;AAGtB,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAEA,SAAS,kBAAkB,IAAI,KAAK;AAClC,MAAI,kBAAkB,EAAE,GAAG;AACzB;AAAA,EACF;AACA,KAAG,QAAQ,uBAAuB,GAAG,OAAO,GAAG,MAAM,GAAG;AAC1D;AAEA,SAAS,eAAe,OAAO;AAC7B,MAAI,mBAAmB,KAAK,GAAG;AAC7B;AAAA,EACF;AAEA,QAAM,UAAU,QAAQ,QAAM,kBAAkB,IAAI,MAAM,GAAG,CAAC;AAE9D,WAAS,mBAAmBA,QAAO;AACjC,QAAI,2BAA2BA,OAAM,GAAG,GAAG;AACzC,aAAO;AAAA,IACT;AAEA,QAAI,CAAC,kBAAkBA,OAAM,GAAG,KAAK,CAAC,sBAAsBA,OAAM,GAAG,KAAK,CAAC,CAAC,OAAO,OAAO,KAAK,EAAE,SAASA,OAAM,GAAG,GAAG;AACpH,aAAO;AAAA,IACT;AAEA,WAAO;AAAA,EACT;AACF;AAGA,SAAS,iBAAiB,OAAO;AAC/B,MAAI,MAAM,QAAQ,OAAO;AACvB;AAAA,EACF;AACA,QAAM,UAAU,QAAQ,QAAM,YAAY,EAAE,CAAC;AAG7C,WAAS,YAAY,UAAU;AAC7B,QAAI,kBAAkB,QAAQ,GAAG;AAC/B;AAAA,IACF;AAEA,QAAI,SAAS,SAAS,KAAK;AACzB;AAAA,IACF;AACA,UAAM,MAAM,SAAS,MAAM,QAAQ,4BAA4B,EAAE;AACjE,QAAI,IAAI,SAAS,GAAG;AAClB,eAAS,QAAQ;AACjB;AAAA,IACF;AAAA,EACF;AACF;AAEO,gBAAS,8BAA8B,KAAK,cAAc;AAE/D,MAAI,iBAAiB,OAAO,CAAC,OAAO,OAAO,OAAO,OAAO,OAAO,OAAO,OAAO,OAAO,OAAO,OAAO,OAAO,KAAK,EAAE,SAAS,GAAG,GAAG;AAC9H,WAAO;AAAA,EACT;AACA,MAAI,QAAQ,SAAS,iBAAiB,KAAK;AACzC,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAEA,SAAS,cAAc,OAAO;AAE5B,MAAI,MAAM,MAAM,oDAAoD,GAAG;AACrE,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAEA,SAAS,cAAc,OAAO;AAC5B,MAAI,CAAC,MAAM,WAAW;AACpB;AAAA,EACF;AAGA,QAAM,oBAAoB,MAAM,UAAU,OAAO,QAAM,8BAA8B,MAAM,KAAK,GAAG,IAAI,KAAK,cAAc,GAAG,KAAK,CAAC;AACnI,oBAAkB,QAAQ,QAAM,sBAAsB,EAAE,CAAC;AAEzD,WAAS,sBAAsB,IAAI;AACjC,QAAI,kBAAkB,EAAE,GAAG;AACzB;AAAA,IACF;AAEA,OAAG,QAAQ,GAAG,MAAM,QAAQ,OAAO,EAAE;AACrC,OAAG,QAAQ,GAAG,MAAM,QAAQ,MAAM,GAAG;AAAA,EACvC;AAEF;AAEA,SAAS,mBAAmB,OAAO;AACjC,gBAAc,KAAK;AACnB,mBAAiB,KAAK;AACxB;AAEO,gBAAS,wBAAwB,OAAO;AAC7C,QAAM,WAAW,QAAQ,CAAC,OAAO;AAC/B,QAAI,kBAAkB,EAAE,GAAG;AACzB;AAAA,IACF;AACA,OAAG,QAAQ,GAAG,MAAM,QAAQ,cAAc,EAAE;AAC5C,OAAG,QAAQ,GAAG,MAAM,QAAQ,cAAc,EAAE;AAC5C,OAAG,QAAQ,GAAG,MAAM,QAAQ,cAAc,GAAG;AAAA,EAC/C,CAAC;AACH;AAEA,SAAS,gCAAgC,OAAO;AAG9C,QAAM,UAAU,QAAQ,CAAC,OAAO;AAC9B,QAAI,kBAAkB,EAAE,GAAG;AACvB;AAAA,IACJ;AACA,OAAG,QAAQ,2BAA2B,GAAG,KAAK;AAAA,EAChD,CAAC;AACH;AAEA,SAAS,2BAA2B,QAAQ,IAAI;AAI9C,SAAO,OAAO,KAAK,EAAE,QAAQ,mBAAmB,EAAE;AACpD;AAEA,SAAS,uBAAuB,OAAO,cAAc,KAAK;AAGxD,UAAQ,gCAAgC,OAAO,KAAK,YAAY;AAChE,UAAQ,WAAW,KAAK,cAAc,KAAK;AAC3C,UAAQ,uBAAuB,OAAO,cAAc,GAAG;AAIvD,UAAQ,kBAAkB,OAAO,cAAc,GAAG;AAClD,UAAQ,MAAM,QAAQ,oBAAoB,IAAI;AAE9C,MAAI,CAAC,OAAO,KAAK,EAAE,SAAS,GAAG,KAAK,iBAAiB,KAAK;AACxD,YAAQ,MAAM,QAAQ,OAAO,IAAI;AAAA,EACnC;AAcA,SAAO;AACT;AAEO,gBAAS,0BAA0B,OAAO;AAC/C,QAAM,cAAc,MAAM,KAAK;AAC/B,MAAI,uBAAuB,KAAK,GAAG;AACjC,WAAO;AAAA,EACT;AACA,wBAAsB,WAAW;AACjC,0BAAwB,WAAW;AACnC,WAAS,MAAM;AACf,uBAAqB,OAAO,WAAW;AAEvC,SAAO;AACT;AAEA,SAAS,gCAAgC,OAAO,KAAK,cAAc;AACjE,MAAI,QAAQ,OAAO;AACjB,WAAO;AAAA,EACT;AAGA,UAAQ,MAAM,QAAQ,iBAAiB,EAAE;AAIzC,MAAI,iBAAiB,OAAO,CAAC,OAAO,OAAO,OAAO,OAAO,KAAK,EAAE,SAAS,GAAG,GAAG;AAC7E,YAAQ,MAAM,QAAQ,wBAAwB,KAAK;AAAA,EACrD;AAEA,SAAO;AACT;AAEA,SAAS,eAAe,OAAO;AAE7B,wBAAsB,KAAK;AAC3B,iBAAe,KAAK;AACpB,+BAA6B,KAAK;AAClC,SAAO;AACT;AAEO,gBAAS,oCAAoC,OAAO;AAGzD,QAAM,cAAc,0BAA0B,KAAK;AAEnD,MAAI,uBAAuB,KAAK,GAAG;AACjC,WAAO;AAAA,EACT;AACA,cAAY,UAAU,QAAQ,CAAC,OAAO;AACpC,QAAI,kBAAkB,EAAE,GAAG;AACzB;AAAA,IACF;AAEA,OAAG,QAAQ,uBAAuB,GAAG,OAAO,GAAG,MAAM,MAAM,GAAG;AAAA,EAIhE,CAAC;AAED,iBAAe,WAAW;AAC1B,kCAAgC,WAAW;AAC3C,qBAAmB,WAAW;AAC9B,0BAAwB,WAAW;AAGnC,uBAAqB,OAAO,WAAW;AAEvC,SAAO;AACT;AAEA,SAAS,uBAAuB,OAAO;AACrC,MAAI,CAAC,MAAM,aAAa,CAAC,OAAO,OAAO,OAAO,KAAK,EAAE,SAAS,MAAM,GAAG,GAAG;AACxE,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAEA,SAAS,kBAAkB,IAAI;AAC7B,SAAO,GAAG,UAAU;AACtB;",
   "names": ["field"]
 }

package/dist/prepublicationUtils.js

@@ -136,7 +136,7 @@ export function removeWorsePrepubField594s(record) {
   nonBest.forEach((field) => record.removeField(field));
 }
 export function isEnnakkotietoSubfield(subfield) {
-  if (subfield.code !== "9" && subfield.code !== "g") {
+  if (!["g", "9", "7"].includes(subfield.code)) {
     return false;
   }
   if (subfield.value.length <= 13) {

package/dist/prepublicationUtils.js.map

@@ -1,7 +1,7 @@
 {
   "version": 3,
   "sources": ["../src/prepublicationUtils.js"],
-  "sourcesContent": ["import {fieldHasSubfield, nvdebug, nvdebugFieldArray} from './utils.js';\nimport createDebugLogger from 'debug';\n\nconst debug = createDebugLogger('@natlibfi/marc-record-validators-melinda:prepublicationUtils');\n//const debugData = debug.extend('data');\nconst debugDev = debug.extend('dev');\n\nconst KONEELLISESTI_TUOTETTU_TIETUE = 1; // Best\nconst TARKISTETTU_ENNAKKOTIETO = 2;\nconst ENNAKKOTIETO = 3;\n//const EI_TASOA = 4;\n\nconst encodingLevelPreferenceArray = [' ', '1', '3', '4', '5', '2', '7', 'u', 'z', '8']; // MET-145\nconst prepublicationLevelIndex = encodingLevelPreferenceArray.indexOf('8');\n\nexport function prepublicationLevelIsKoneellisestiTuotettuTietueOrTarkistettuEnnakkotieto(prepublicationLevel) {\n  return prepublicationLevel === KONEELLISESTI_TUOTETTU_TIETUE || prepublicationLevel === TARKISTETTU_ENNAKKOTIETO;\n}\n\n\nexport function encodingLevelIsBetterThanPrepublication(encodingLevel) {\n  const index = encodingLevelPreferenceArray.indexOf(encodingLevel);\n  return index > -1 && index < prepublicationLevelIndex;\n}\n\n// These three functions below all refer to field 500:\nexport function fieldRefersToKoneellisestiTuotettuTietue(field) {\n  return field.subfields?.some(sf => sf.code === 'a' && sf.value.match(/^Koneellisesti tuotettu tietue/u));\n}\n\n\nexport function fieldRefersToTarkistettuEnnakkotieto(field) {\n  return field.subfields?.some(sf => sf.code === 'a' && sf.value.match(/^tarkistettu ennakkotieto/ui));\n}\n\n\nexport function fieldRefersToEnnakkotieto(field) {\n  // NB! This no longer matches 'TARKISTETTU ENNAKKOTIETO' case! Bug or Feature?\n  if (field.subfields?.some(sf => sf.code === 'a' && sf.value.match(/^ennakkotieto(?:$|[. ])/ui))) {\n    return true;\n  }\n\n  // MRA-420: \"EI VIEL\u00C4 ILMESTYNYT\" is a Helmet note, that is semantically similar to ENNAKKOTIETO:\n  return field.subfields?.some(sf => sf.code === 'a' && sf.value.match(/^EI VIEL\u00C4 ILMESTYNYT/u));\n}\n\n\nexport function firstFieldHasBetterPrepubEncodingLevel(field1, field2) {\n  if (fieldRefersToKoneellisestiTuotettuTietue(field2)) {\n    return false;\n  }\n  if (fieldRefersToKoneellisestiTuotettuTietue(field1)) {\n    return true;\n  }\n  if (fieldRefersToTarkistettuEnnakkotieto(field2)) {\n    return false;\n  }\n  if (fieldRefersToTarkistettuEnnakkotieto(field1)) {\n    return true;\n  }\n  if (fieldRefersToEnnakkotieto(field2)) {\n    return false;\n  }\n  if (fieldRefersToEnnakkotieto(field1)) {\n    return true;\n  }\n  return false;\n}\n\nexport function getRelevant5XXFields(record, f500 = false, f594 = false) {\n  const cands = actualGetFields();\n  //nvdebugFieldArray(cands, 'gR5XXa: ', debugDev);\n  const filtered = cands.filter(field => hasRelevantPrepubData(field));\n  //nvdebugFieldArray(filtered, 'gR5XXb: ', debugDev);\n  return filtered;\n\n  //return actualGetFields().filter(field => hasRelevantPrepubData(field));\n\n  function hasRelevantPrepubData(field) {\n    // Check prepub ($a):\n    if (!fieldRefersToKoneellisestiTuotettuTietue(field) && !fieldRefersToTarkistettuEnnakkotieto(field) && !fieldRefersToEnnakkotieto(field)) {\n      return false;\n    }\n    // Check relevance (594$5):\n    if (field.tag === '500') {\n      return field.subfields.every(sf => sf.code !== '5'); //true;\n    }\n    return field.subfields.some(sf => sf.code === '5' && ['FENNI', 'FIKKA', 'VIOLA'].includes(sf.value));\n  }\n\n  function actualGetFields() {\n    if (f500 && f594) {\n      return record.get(/^(?:500|594)$/u);\n    }\n    if (f500) {\n      return record.get(/^500$/u);\n    }\n    if (f594) {\n      return record.get(/^594$/u);\n    }\n    return [];\n  }\n\n}\n\n\n// Very similar to getPrepublicationLevel() in melinda-record-match-validator's getPrepublicationLevel()...\n// We should use that and not have a copy here...\nexport function getPrepublicationLevel(record, f500 = false, f594 = false) {\n  // Smaller return value is better\n  const fields = getRelevant5XXFields(record, f500, f594);\n\n  if (!fields) {\n    return null;\n  }\n  if (fields.some(f => fieldRefersToKoneellisestiTuotettuTietue(f))) {\n    return KONEELLISESTI_TUOTETTU_TIETUE;\n  }\n\n  if (fields.some(f => fieldRefersToTarkistettuEnnakkotieto(f))) {\n    return TARKISTETTU_ENNAKKOTIETO;\n  }\n\n  if (fields.some(f => fieldRefersToEnnakkotieto(f))) {\n    return ENNAKKOTIETO;\n  }\n\n  return null;\n}\n\n\nexport function baseHasEqualOrHigherEncodingLevel(baseEncodingLevel, sourceEncodingLevel) {\n  const baseIndex = encodingLevelPreferenceArray.indexOf(baseEncodingLevel);\n  const sourceIndex = encodingLevelPreferenceArray.indexOf(sourceEncodingLevel);\n\n  if (baseIndex === -1) {\n    // Base wins if both are bad:\n    return sourceIndex === -1;\n  }\n  return baseIndex <= sourceIndex;\n}\n\n\nfunction hasFikkaLOW(record) {\n  return record.fields.some(field => field.tag === 'LOW' && fieldHasSubfield(field, 'a', 'FIKKA'));\n}\n\n\nfunction hasNatLibFi042(record) {\n  return record.fields.some(field => field.tag === '042' && (fieldHasSubfield(field, 'a', 'finb') || fieldHasSubfield(field, 'a', 'finbd')));\n}\n\n\nexport function isFikkaRecord(record) {\n  // NB! Does not include Humaniora. Pienpainatteet (not that they'd have duplicates)?\n  return hasFikkaLOW(record) && hasNatLibFi042(record);\n}\n\n\nexport function getEncodingLevel(record) {\n  return record.leader.substring(17, 18);\n}\n\n\nexport function deleteAllPrepublicationNotesFromField500InNonPubRecord(record) {\n  const encodingLevel = getEncodingLevel(record);\n  // Skip prepublication (or theoretically even worse) records:\n  if (!encodingLevelIsBetterThanPrepublication(encodingLevel)) {\n  //if (['2', '8'].includes(encodingLevel)) { // MET-306: added '2' here\n    return;\n  }\n\n  // MET-306: keep \"koneellisesti tuotettu tietue\" if encoding level is '2':\n  const f500 = getRelevant5XXFields(record, true, false).filter(field => encodingLevel === '2' ? !fieldRefersToKoneellisestiTuotettuTietue(field) : true);\n  if (f500.length === 0) {\n    return;\n  }\n\n\n  nvdebug(`Delete all ${f500.length} instance(s) of field 500`, debugDev);\n  f500.forEach(field => record.removeField(field));\n}\n\n\nexport function removeWorsePrepubField500s(record) {\n  // Remove lower-level entries:\n  const fields = getRelevant5XXFields(record, true, false); // 500=false, 594=true\n  nvdebugFieldArray(fields, '  Candidates for non-best 500 b4 filtering: ', debugDev);\n  const nonBest = fields.filter(field => fields.some(field2 => firstFieldHasBetterPrepubEncodingLevel(field2, field)));\n  nvdebugFieldArray(nonBest, '  Remove non-best 500: ', debugDev);\n  nonBest.forEach(field => record.removeField(field));\n}\n\n\nexport function removeWorsePrepubField594s(record) {\n  // Remove lower-level entries:\n  const fields594 = getRelevant5XXFields(record, false, true); // 500=false, 594=true\n  nvdebugFieldArray(fields594, '  Candidates for non-best 594 b4 filtering: ', debugDev);\n  const nonBest = fields594.filter(field => fields594.some(field2 => firstFieldHasBetterPrepubEncodingLevel(field2, field)));\n  nvdebugFieldArray(nonBest, '  Remove non-best 594: ', debugDev);\n  nonBest.forEach(field => record.removeField(field));\n}\n\n\nexport function isEnnakkotietoSubfield(subfield) {\n  if (subfield.code !== '9' && subfield.code !== 'g') {\n    return false;\n  }\n  // Length <= 13 allows punctuation, but does not require it:\n  if (subfield.value.length <= 13) {\n    const coreString = subfield.value.substr(0, 12);\n    if (coreString.toLowerCase() === 'ennakkotieto') { // Lowercase term first seen in MET-575\n      return true;\n    }\n  }\n  return false;\n}\n\nexport function isEnnakkotietoField(field) {\n  return field.subfields.some(sf => isEnnakkotietoSubfield(sf));\n}\n\nexport function isKingOfTheHill(field, opposingFields) {\n  // Field is no better than at least one of the opposing fields\n  return opposingFields.every(opposingField => firstFieldHasBetterPrepubEncodingLevel(field, opposingField));\n}\n\n"],
-  "mappings": "AAAA,SAAQ,kBAAkB,SAAS,yBAAwB;AAC3D,OAAO,uBAAuB;AAE9B,MAAM,QAAQ,kBAAkB,8DAA8D;AAE9F,MAAM,WAAW,MAAM,OAAO,KAAK;AAEnC,MAAM,gCAAgC;AACtC,MAAM,2BAA2B;AACjC,MAAM,eAAe;AAGrB,MAAM,+BAA+B,CAAC,KAAK,KAAK,KAAK,KAAK,KAAK,KAAK,KAAK,KAAK,KAAK,GAAG;AACtF,MAAM,2BAA2B,6BAA6B,QAAQ,GAAG;AAElE,gBAAS,0EAA0E,qBAAqB;AAC7G,SAAO,wBAAwB,iCAAiC,wBAAwB;AAC1F;AAGO,gBAAS,wCAAwC,eAAe;AACrE,QAAM,QAAQ,6BAA6B,QAAQ,aAAa;AAChE,SAAO,QAAQ,MAAM,QAAQ;AAC/B;AAGO,gBAAS,yCAAyC,OAAO;AAC9D,SAAO,MAAM,WAAW,KAAK,QAAM,GAAG,SAAS,OAAO,GAAG,MAAM,MAAM,iCAAiC,CAAC;AACzG;AAGO,gBAAS,qCAAqC,OAAO;AAC1D,SAAO,MAAM,WAAW,KAAK,QAAM,GAAG,SAAS,OAAO,GAAG,MAAM,MAAM,6BAA6B,CAAC;AACrG;AAGO,gBAAS,0BAA0B,OAAO;AAE/C,MAAI,MAAM,WAAW,KAAK,QAAM,GAAG,SAAS,OAAO,GAAG,MAAM,MAAM,2BAA2B,CAAC,GAAG;AAC/F,WAAO;AAAA,EACT;AAGA,SAAO,MAAM,WAAW,KAAK,QAAM,GAAG,SAAS,OAAO,GAAG,MAAM,MAAM,uBAAuB,CAAC;AAC/F;AAGO,gBAAS,uCAAuC,QAAQ,QAAQ;AACrE,MAAI,yCAAyC,MAAM,GAAG;AACpD,WAAO;AAAA,EACT;AACA,MAAI,yCAAyC,MAAM,GAAG;AACpD,WAAO;AAAA,EACT;AACA,MAAI,qCAAqC,MAAM,GAAG;AAChD,WAAO;AAAA,EACT;AACA,MAAI,qCAAqC,MAAM,GAAG;AAChD,WAAO;AAAA,EACT;AACA,MAAI,0BAA0B,MAAM,GAAG;AACrC,WAAO;AAAA,EACT;AACA,MAAI,0BAA0B,MAAM,GAAG;AACrC,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAEO,gBAAS,qBAAqB,QAAQ,OAAO,OAAO,OAAO,OAAO;AACvE,QAAM,QAAQ,gBAAgB;AAE9B,QAAM,WAAW,MAAM,OAAO,WAAS,sBAAsB,KAAK,CAAC;AAEnE,SAAO;AAIP,WAAS,sBAAsB,OAAO;AAEpC,QAAI,CAAC,yCAAyC,KAAK,KAAK,CAAC,qCAAqC,KAAK,KAAK,CAAC,0BAA0B,KAAK,GAAG;AACzI,aAAO;AAAA,IACT;AAEA,QAAI,MAAM,QAAQ,OAAO;AACvB,aAAO,MAAM,UAAU,MAAM,QAAM,GAAG,SAAS,GAAG;AAAA,IACpD;AACA,WAAO,MAAM,UAAU,KAAK,QAAM,GAAG,SAAS,OAAO,CAAC,SAAS,SAAS,OAAO,EAAE,SAAS,GAAG,KAAK,CAAC;AAAA,EACrG;AAEA,WAAS,kBAAkB;AACzB,QAAI,QAAQ,MAAM;AAChB,aAAO,OAAO,IAAI,gBAAgB;AAAA,IACpC;AACA,QAAI,MAAM;AACR,aAAO,OAAO,IAAI,QAAQ;AAAA,IAC5B;AACA,QAAI,MAAM;AACR,aAAO,OAAO,IAAI,QAAQ;AAAA,IAC5B;AACA,WAAO,CAAC;AAAA,EACV;AAEF;AAKO,gBAAS,uBAAuB,QAAQ,OAAO,OAAO,OAAO,OAAO;AAEzE,QAAM,SAAS,qBAAqB,QAAQ,MAAM,IAAI;AAEtD,MAAI,CAAC,QAAQ;AACX,WAAO;AAAA,EACT;AACA,MAAI,OAAO,KAAK,OAAK,yCAAyC,CAAC,CAAC,GAAG;AACjE,WAAO;AAAA,EACT;AAEA,MAAI,OAAO,KAAK,OAAK,qCAAqC,CAAC,CAAC,GAAG;AAC7D,WAAO;AAAA,EACT;AAEA,MAAI,OAAO,KAAK,OAAK,0BAA0B,CAAC,CAAC,GAAG;AAClD,WAAO;AAAA,EACT;AAEA,SAAO;AACT;AAGO,gBAAS,kCAAkC,mBAAmB,qBAAqB;AACxF,QAAM,YAAY,6BAA6B,QAAQ,iBAAiB;AACxE,QAAM,cAAc,6BAA6B,QAAQ,mBAAmB;AAE5E,MAAI,cAAc,IAAI;AAEpB,WAAO,gBAAgB;AAAA,EACzB;AACA,SAAO,aAAa;AACtB;AAGA,SAAS,YAAY,QAAQ;AAC3B,SAAO,OAAO,OAAO,KAAK,WAAS,MAAM,QAAQ,SAAS,iBAAiB,OAAO,KAAK,OAAO,CAAC;AACjG;AAGA,SAAS,eAAe,QAAQ;AAC9B,SAAO,OAAO,OAAO,KAAK,WAAS,MAAM,QAAQ,UAAU,iBAAiB,OAAO,KAAK,MAAM,KAAK,iBAAiB,OAAO,KAAK,OAAO,EAAE;AAC3I;AAGO,gBAAS,cAAc,QAAQ;AAEpC,SAAO,YAAY,MAAM,KAAK,eAAe,MAAM;AACrD;AAGO,gBAAS,iBAAiB,QAAQ;AACvC,SAAO,OAAO,OAAO,UAAU,IAAI,EAAE;AACvC;AAGO,gBAAS,uDAAuD,QAAQ;AAC7E,QAAM,gBAAgB,iBAAiB,MAAM;AAE7C,MAAI,CAAC,wCAAwC,aAAa,GAAG;AAE3D;AAAA,EACF;AAGA,QAAM,OAAO,qBAAqB,QAAQ,MAAM,KAAK,EAAE,OAAO,WAAS,kBAAkB,MAAM,CAAC,yCAAyC,KAAK,IAAI,IAAI;AACtJ,MAAI,KAAK,WAAW,GAAG;AACrB;AAAA,EACF;AAGA,UAAQ,cAAc,KAAK,MAAM,6BAA6B,QAAQ;AACtE,OAAK,QAAQ,WAAS,OAAO,YAAY,KAAK,CAAC;AACjD;AAGO,gBAAS,2BAA2B,QAAQ;AAEjD,QAAM,SAAS,qBAAqB,QAAQ,MAAM,KAAK;AACvD,oBAAkB,QAAQ,gDAAgD,QAAQ;AAClF,QAAM,UAAU,OAAO,OAAO,WAAS,OAAO,KAAK,YAAU,uCAAuC,QAAQ,KAAK,CAAC,CAAC;AACnH,oBAAkB,SAAS,2BAA2B,QAAQ;AAC9D,UAAQ,QAAQ,WAAS,OAAO,YAAY,KAAK,CAAC;AACpD;AAGO,gBAAS,2BAA2B,QAAQ;AAEjD,QAAM,YAAY,qBAAqB,QAAQ,OAAO,IAAI;AAC1D,oBAAkB,WAAW,gDAAgD,QAAQ;AACrF,QAAM,UAAU,UAAU,OAAO,WAAS,UAAU,KAAK,YAAU,uCAAuC,QAAQ,KAAK,CAAC,CAAC;AACzH,oBAAkB,SAAS,2BAA2B,QAAQ;AAC9D,UAAQ,QAAQ,WAAS,OAAO,YAAY,KAAK,CAAC;AACpD;AAGO,gBAAS,uBAAuB,UAAU;AAC/C,MAAI,SAAS,SAAS,OAAO,SAAS,SAAS,KAAK;AAClD,WAAO;AAAA,EACT;AAEA,MAAI,SAAS,MAAM,UAAU,IAAI;AAC/B,UAAM,aAAa,SAAS,MAAM,OAAO,GAAG,EAAE;AAC9C,QAAI,WAAW,YAAY,MAAM,gBAAgB;AAC/C,aAAO;AAAA,IACT;AAAA,EACF;AACA,SAAO;AACT;AAEO,gBAAS,oBAAoB,OAAO;AACzC,SAAO,MAAM,UAAU,KAAK,QAAM,uBAAuB,EAAE,CAAC;AAC9D;AAEO,gBAAS,gBAAgB,OAAO,gBAAgB;AAErD,SAAO,eAAe,MAAM,mBAAiB,uCAAuC,OAAO,aAAa,CAAC;AAC3G;",
+  "sourcesContent": ["import {fieldHasSubfield, nvdebug, nvdebugFieldArray} from './utils.js';\nimport createDebugLogger from 'debug';\n\nconst debug = createDebugLogger('@natlibfi/marc-record-validators-melinda:prepublicationUtils');\n//const debugData = debug.extend('data');\nconst debugDev = debug.extend('dev');\n\nconst KONEELLISESTI_TUOTETTU_TIETUE = 1; // Best\nconst TARKISTETTU_ENNAKKOTIETO = 2;\nconst ENNAKKOTIETO = 3;\n//const EI_TASOA = 4;\n\nconst encodingLevelPreferenceArray = [' ', '1', '3', '4', '5', '2', '7', 'u', 'z', '8']; // MET-145\nconst prepublicationLevelIndex = encodingLevelPreferenceArray.indexOf('8');\n\nexport function prepublicationLevelIsKoneellisestiTuotettuTietueOrTarkistettuEnnakkotieto(prepublicationLevel) {\n  return prepublicationLevel === KONEELLISESTI_TUOTETTU_TIETUE || prepublicationLevel === TARKISTETTU_ENNAKKOTIETO;\n}\n\n\nexport function encodingLevelIsBetterThanPrepublication(encodingLevel) {\n  const index = encodingLevelPreferenceArray.indexOf(encodingLevel);\n  return index > -1 && index < prepublicationLevelIndex;\n}\n\n// These three functions below all refer to field 500:\nexport function fieldRefersToKoneellisestiTuotettuTietue(field) {\n  return field.subfields?.some(sf => sf.code === 'a' && sf.value.match(/^Koneellisesti tuotettu tietue/u));\n}\n\n\nexport function fieldRefersToTarkistettuEnnakkotieto(field) {\n  return field.subfields?.some(sf => sf.code === 'a' && sf.value.match(/^tarkistettu ennakkotieto/ui));\n}\n\n\nexport function fieldRefersToEnnakkotieto(field) {\n  // NB! This no longer matches 'TARKISTETTU ENNAKKOTIETO' case! Bug or Feature?\n  if (field.subfields?.some(sf => sf.code === 'a' && sf.value.match(/^ennakkotieto(?:$|[. ])/ui))) {\n    return true;\n  }\n\n  // MRA-420: \"EI VIEL\u00C4 ILMESTYNYT\" is a Helmet note, that is semantically similar to ENNAKKOTIETO:\n  return field.subfields?.some(sf => sf.code === 'a' && sf.value.match(/^EI VIEL\u00C4 ILMESTYNYT/u));\n}\n\n\nexport function firstFieldHasBetterPrepubEncodingLevel(field1, field2) {\n  if (fieldRefersToKoneellisestiTuotettuTietue(field2)) {\n    return false;\n  }\n  if (fieldRefersToKoneellisestiTuotettuTietue(field1)) {\n    return true;\n  }\n  if (fieldRefersToTarkistettuEnnakkotieto(field2)) {\n    return false;\n  }\n  if (fieldRefersToTarkistettuEnnakkotieto(field1)) {\n    return true;\n  }\n  if (fieldRefersToEnnakkotieto(field2)) {\n    return false;\n  }\n  if (fieldRefersToEnnakkotieto(field1)) {\n    return true;\n  }\n  return false;\n}\n\nexport function getRelevant5XXFields(record, f500 = false, f594 = false) {\n  const cands = actualGetFields();\n  //nvdebugFieldArray(cands, 'gR5XXa: ', debugDev);\n  const filtered = cands.filter(field => hasRelevantPrepubData(field));\n  //nvdebugFieldArray(filtered, 'gR5XXb: ', debugDev);\n  return filtered;\n\n  //return actualGetFields().filter(field => hasRelevantPrepubData(field));\n\n  function hasRelevantPrepubData(field) {\n    // Check prepub ($a):\n    if (!fieldRefersToKoneellisestiTuotettuTietue(field) && !fieldRefersToTarkistettuEnnakkotieto(field) && !fieldRefersToEnnakkotieto(field)) {\n      return false;\n    }\n    // Check relevance (594$5):\n    if (field.tag === '500') {\n      return field.subfields.every(sf => sf.code !== '5'); //true;\n    }\n    return field.subfields.some(sf => sf.code === '5' && ['FENNI', 'FIKKA', 'VIOLA'].includes(sf.value));\n  }\n\n  function actualGetFields() {\n    if (f500 && f594) {\n      return record.get(/^(?:500|594)$/u);\n    }\n    if (f500) {\n      return record.get(/^500$/u);\n    }\n    if (f594) {\n      return record.get(/^594$/u);\n    }\n    return [];\n  }\n\n}\n\n\n// Very similar to getPrepublicationLevel() in melinda-record-match-validator's getPrepublicationLevel()...\n// We should use that and not have a copy here...\nexport function getPrepublicationLevel(record, f500 = false, f594 = false) {\n  // Smaller return value is better\n  const fields = getRelevant5XXFields(record, f500, f594);\n\n  if (!fields) {\n    return null;\n  }\n  if (fields.some(f => fieldRefersToKoneellisestiTuotettuTietue(f))) {\n    return KONEELLISESTI_TUOTETTU_TIETUE;\n  }\n\n  if (fields.some(f => fieldRefersToTarkistettuEnnakkotieto(f))) {\n    return TARKISTETTU_ENNAKKOTIETO;\n  }\n\n  if (fields.some(f => fieldRefersToEnnakkotieto(f))) {\n    return ENNAKKOTIETO;\n  }\n\n  return null;\n}\n\n\nexport function baseHasEqualOrHigherEncodingLevel(baseEncodingLevel, sourceEncodingLevel) {\n  const baseIndex = encodingLevelPreferenceArray.indexOf(baseEncodingLevel);\n  const sourceIndex = encodingLevelPreferenceArray.indexOf(sourceEncodingLevel);\n\n  if (baseIndex === -1) {\n    // Base wins if both are bad:\n    return sourceIndex === -1;\n  }\n  return baseIndex <= sourceIndex;\n}\n\n\nfunction hasFikkaLOW(record) {\n  return record.fields.some(field => field.tag === 'LOW' && fieldHasSubfield(field, 'a', 'FIKKA'));\n}\n\n\nfunction hasNatLibFi042(record) {\n  return record.fields.some(field => field.tag === '042' && (fieldHasSubfield(field, 'a', 'finb') || fieldHasSubfield(field, 'a', 'finbd')));\n}\n\n\nexport function isFikkaRecord(record) {\n  // NB! Does not include Humaniora. Pienpainatteet (not that they'd have duplicates)?\n  return hasFikkaLOW(record) && hasNatLibFi042(record);\n}\n\n\nexport function getEncodingLevel(record) {\n  return record.leader.substring(17, 18);\n}\n\n\nexport function deleteAllPrepublicationNotesFromField500InNonPubRecord(record) {\n  const encodingLevel = getEncodingLevel(record);\n  // Skip prepublication (or theoretically even worse) records:\n  if (!encodingLevelIsBetterThanPrepublication(encodingLevel)) {\n  //if (['2', '8'].includes(encodingLevel)) { // MET-306: added '2' here\n    return;\n  }\n\n  // MET-306: keep \"koneellisesti tuotettu tietue\" if encoding level is '2':\n  const f500 = getRelevant5XXFields(record, true, false).filter(field => encodingLevel === '2' ? !fieldRefersToKoneellisestiTuotettuTietue(field) : true);\n  if (f500.length === 0) {\n    return;\n  }\n\n\n  nvdebug(`Delete all ${f500.length} instance(s) of field 500`, debugDev);\n  f500.forEach(field => record.removeField(field));\n}\n\n\nexport function removeWorsePrepubField500s(record) {\n  // Remove lower-level entries:\n  const fields = getRelevant5XXFields(record, true, false); // 500=false, 594=true\n  nvdebugFieldArray(fields, '  Candidates for non-best 500 b4 filtering: ', debugDev);\n  const nonBest = fields.filter(field => fields.some(field2 => firstFieldHasBetterPrepubEncodingLevel(field2, field)));\n  nvdebugFieldArray(nonBest, '  Remove non-best 500: ', debugDev);\n  nonBest.forEach(field => record.removeField(field));\n}\n\n\nexport function removeWorsePrepubField594s(record) {\n  // Remove lower-level entries:\n  const fields594 = getRelevant5XXFields(record, false, true); // 500=false, 594=true\n  nvdebugFieldArray(fields594, '  Candidates for non-best 594 b4 filtering: ', debugDev);\n  const nonBest = fields594.filter(field => fields594.some(field2 => firstFieldHasBetterPrepubEncodingLevel(field2, field)));\n  nvdebugFieldArray(nonBest, '  Remove non-best 594: ', debugDev);\n  nonBest.forEach(field => record.removeField(field));\n}\n\n\nexport function isEnnakkotietoSubfield(subfield) {\n  if (!['g', '9', '7'].includes(subfield.code)) {\n    return false;\n  }\n  // Length <= 13 allows punctuation, but does not require it:\n  if (subfield.value.length <= 13) {\n    const coreString = subfield.value.substr(0, 12);\n    if (coreString.toLowerCase() === 'ennakkotieto') { // Lowercase term first seen in MET-575\n      return true;\n    }\n  }\n  return false;\n}\n\nexport function isEnnakkotietoField(field) {\n  return field.subfields.some(sf => isEnnakkotietoSubfield(sf));\n}\n\nexport function isKingOfTheHill(field, opposingFields) {\n  // Field is no better than at least one of the opposing fields\n  return opposingFields.every(opposingField => firstFieldHasBetterPrepubEncodingLevel(field, opposingField));\n}\n\n"],
+  "mappings": "AAAA,SAAQ,kBAAkB,SAAS,yBAAwB;AAC3D,OAAO,uBAAuB;AAE9B,MAAM,QAAQ,kBAAkB,8DAA8D;AAE9F,MAAM,WAAW,MAAM,OAAO,KAAK;AAEnC,MAAM,gCAAgC;AACtC,MAAM,2BAA2B;AACjC,MAAM,eAAe;AAGrB,MAAM,+BAA+B,CAAC,KAAK,KAAK,KAAK,KAAK,KAAK,KAAK,KAAK,KAAK,KAAK,GAAG;AACtF,MAAM,2BAA2B,6BAA6B,QAAQ,GAAG;AAElE,gBAAS,0EAA0E,qBAAqB;AAC7G,SAAO,wBAAwB,iCAAiC,wBAAwB;AAC1F;AAGO,gBAAS,wCAAwC,eAAe;AACrE,QAAM,QAAQ,6BAA6B,QAAQ,aAAa;AAChE,SAAO,QAAQ,MAAM,QAAQ;AAC/B;AAGO,gBAAS,yCAAyC,OAAO;AAC9D,SAAO,MAAM,WAAW,KAAK,QAAM,GAAG,SAAS,OAAO,GAAG,MAAM,MAAM,iCAAiC,CAAC;AACzG;AAGO,gBAAS,qCAAqC,OAAO;AAC1D,SAAO,MAAM,WAAW,KAAK,QAAM,GAAG,SAAS,OAAO,GAAG,MAAM,MAAM,6BAA6B,CAAC;AACrG;AAGO,gBAAS,0BAA0B,OAAO;AAE/C,MAAI,MAAM,WAAW,KAAK,QAAM,GAAG,SAAS,OAAO,GAAG,MAAM,MAAM,2BAA2B,CAAC,GAAG;AAC/F,WAAO;AAAA,EACT;AAGA,SAAO,MAAM,WAAW,KAAK,QAAM,GAAG,SAAS,OAAO,GAAG,MAAM,MAAM,uBAAuB,CAAC;AAC/F;AAGO,gBAAS,uCAAuC,QAAQ,QAAQ;AACrE,MAAI,yCAAyC,MAAM,GAAG;AACpD,WAAO;AAAA,EACT;AACA,MAAI,yCAAyC,MAAM,GAAG;AACpD,WAAO;AAAA,EACT;AACA,MAAI,qCAAqC,MAAM,GAAG;AAChD,WAAO;AAAA,EACT;AACA,MAAI,qCAAqC,MAAM,GAAG;AAChD,WAAO;AAAA,EACT;AACA,MAAI,0BAA0B,MAAM,GAAG;AACrC,WAAO;AAAA,EACT;AACA,MAAI,0BAA0B,MAAM,GAAG;AACrC,WAAO;AAAA,EACT;AACA,SAAO;AACT;AAEO,gBAAS,qBAAqB,QAAQ,OAAO,OAAO,OAAO,OAAO;AACvE,QAAM,QAAQ,gBAAgB;AAE9B,QAAM,WAAW,MAAM,OAAO,WAAS,sBAAsB,KAAK,CAAC;AAEnE,SAAO;AAIP,WAAS,sBAAsB,OAAO;AAEpC,QAAI,CAAC,yCAAyC,KAAK,KAAK,CAAC,qCAAqC,KAAK,KAAK,CAAC,0BAA0B,KAAK,GAAG;AACzI,aAAO;AAAA,IACT;AAEA,QAAI,MAAM,QAAQ,OAAO;AACvB,aAAO,MAAM,UAAU,MAAM,QAAM,GAAG,SAAS,GAAG;AAAA,IACpD;AACA,WAAO,MAAM,UAAU,KAAK,QAAM,GAAG,SAAS,OAAO,CAAC,SAAS,SAAS,OAAO,EAAE,SAAS,GAAG,KAAK,CAAC;AAAA,EACrG;AAEA,WAAS,kBAAkB;AACzB,QAAI,QAAQ,MAAM;AAChB,aAAO,OAAO,IAAI,gBAAgB;AAAA,IACpC;AACA,QAAI,MAAM;AACR,aAAO,OAAO,IAAI,QAAQ;AAAA,IAC5B;AACA,QAAI,MAAM;AACR,aAAO,OAAO,IAAI,QAAQ;AAAA,IAC5B;AACA,WAAO,CAAC;AAAA,EACV;AAEF;AAKO,gBAAS,uBAAuB,QAAQ,OAAO,OAAO,OAAO,OAAO;AAEzE,QAAM,SAAS,qBAAqB,QAAQ,MAAM,IAAI;AAEtD,MAAI,CAAC,QAAQ;AACX,WAAO;AAAA,EACT;AACA,MAAI,OAAO,KAAK,OAAK,yCAAyC,CAAC,CAAC,GAAG;AACjE,WAAO;AAAA,EACT;AAEA,MAAI,OAAO,KAAK,OAAK,qCAAqC,CAAC,CAAC,GAAG;AAC7D,WAAO;AAAA,EACT;AAEA,MAAI,OAAO,KAAK,OAAK,0BAA0B,CAAC,CAAC,GAAG;AAClD,WAAO;AAAA,EACT;AAEA,SAAO;AACT;AAGO,gBAAS,kCAAkC,mBAAmB,qBAAqB;AACxF,QAAM,YAAY,6BAA6B,QAAQ,iBAAiB;AACxE,QAAM,cAAc,6BAA6B,QAAQ,mBAAmB;AAE5E,MAAI,cAAc,IAAI;AAEpB,WAAO,gBAAgB;AAAA,EACzB;AACA,SAAO,aAAa;AACtB;AAGA,SAAS,YAAY,QAAQ;AAC3B,SAAO,OAAO,OAAO,KAAK,WAAS,MAAM,QAAQ,SAAS,iBAAiB,OAAO,KAAK,OAAO,CAAC;AACjG;AAGA,SAAS,eAAe,QAAQ;AAC9B,SAAO,OAAO,OAAO,KAAK,WAAS,MAAM,QAAQ,UAAU,iBAAiB,OAAO,KAAK,MAAM,KAAK,iBAAiB,OAAO,KAAK,OAAO,EAAE;AAC3I;AAGO,gBAAS,cAAc,QAAQ;AAEpC,SAAO,YAAY,MAAM,KAAK,eAAe,MAAM;AACrD;AAGO,gBAAS,iBAAiB,QAAQ;AACvC,SAAO,OAAO,OAAO,UAAU,IAAI,EAAE;AACvC;AAGO,gBAAS,uDAAuD,QAAQ;AAC7E,QAAM,gBAAgB,iBAAiB,MAAM;AAE7C,MAAI,CAAC,wCAAwC,aAAa,GAAG;AAE3D;AAAA,EACF;AAGA,QAAM,OAAO,qBAAqB,QAAQ,MAAM,KAAK,EAAE,OAAO,WAAS,kBAAkB,MAAM,CAAC,yCAAyC,KAAK,IAAI,IAAI;AACtJ,MAAI,KAAK,WAAW,GAAG;AACrB;AAAA,EACF;AAGA,UAAQ,cAAc,KAAK,MAAM,6BAA6B,QAAQ;AACtE,OAAK,QAAQ,WAAS,OAAO,YAAY,KAAK,CAAC;AACjD;AAGO,gBAAS,2BAA2B,QAAQ;AAEjD,QAAM,SAAS,qBAAqB,QAAQ,MAAM,KAAK;AACvD,oBAAkB,QAAQ,gDAAgD,QAAQ;AAClF,QAAM,UAAU,OAAO,OAAO,WAAS,OAAO,KAAK,YAAU,uCAAuC,QAAQ,KAAK,CAAC,CAAC;AACnH,oBAAkB,SAAS,2BAA2B,QAAQ;AAC9D,UAAQ,QAAQ,WAAS,OAAO,YAAY,KAAK,CAAC;AACpD;AAGO,gBAAS,2BAA2B,QAAQ;AAEjD,QAAM,YAAY,qBAAqB,QAAQ,OAAO,IAAI;AAC1D,oBAAkB,WAAW,gDAAgD,QAAQ;AACrF,QAAM,UAAU,UAAU,OAAO,WAAS,UAAU,KAAK,YAAU,uCAAuC,QAAQ,KAAK,CAAC,CAAC;AACzH,oBAAkB,SAAS,2BAA2B,QAAQ;AAC9D,UAAQ,QAAQ,WAAS,OAAO,YAAY,KAAK,CAAC;AACpD;AAGO,gBAAS,uBAAuB,UAAU;AAC/C,MAAI,CAAC,CAAC,KAAK,KAAK,GAAG,EAAE,SAAS,SAAS,IAAI,GAAG;AAC5C,WAAO;AAAA,EACT;AAEA,MAAI,SAAS,MAAM,UAAU,IAAI;AAC/B,UAAM,aAAa,SAAS,MAAM,OAAO,GAAG,EAAE;AAC9C,QAAI,WAAW,YAAY,MAAM,gBAAgB;AAC/C,aAAO;AAAA,IACT;AAAA,EACF;AACA,SAAO;AACT;AAEO,gBAAS,oBAAoB,OAAO;AACzC,SAAO,MAAM,UAAU,KAAK,QAAM,uBAAuB,EAAE,CAAC;AAC9D;AAEO,gBAAS,gBAAgB,OAAO,gBAAgB;AAErD,SAAO,eAAe,MAAM,mBAAiB,uCAAuC,OAAO,aAAa,CAAC;AAC3G;",
   "names": []
 }

package/dist/punctuation2.js

@@ -1,7 +1,7 @@
 import { validateSingleField } from "./ending-punctuation.js";
-import { tagToDataProvenanceSubfieldCode } from "./merge-fields/dataProvenance.js";
+import { tagToDataProvenanceSubfieldCode } from "./dataProvenanceUtils.js";
 import { fieldGetUnambiguousTag } from "./subfield6Utils.js";
-import { fieldToString, isControlSubfieldCode, nvdebug } from "./utils.js";
+import { fieldToString, isContentSubfieldCode, nvdebug } from "./utils.js";
 import clone from "clone";
 const descriptionString = "Remove invalid and add valid punctuation to data fields";
 export default function() {
@@ -32,7 +32,7 @@ function isIrrelevantSubfield(subfield, tag) {
   if (subfield.code === dataProvenanceSubfieldCode) {
     return true;
   }
-  return isControlSubfieldCode(subfield.code);
+  return !isContentSubfieldCode(subfield.code);
 }
 function getNextRelevantSubfield(field, currSubfieldIndex) {
   return field.subfields.find((subfield, index) => index > currSubfieldIndex && !isIrrelevantSubfield(subfield, field.tag));
@@ -73,14 +73,14 @@ const removeCommaBeforeLanguageSubfieldL = { "followedBy": "l", "remove": /,$/u
 const removeCommaBeforeTitleSubfieldT = { "followedBy": "t", "remove": /,$/u };
 const X00RemoveDotAfterBracket = { "code": "cq", "context": /\)\.$/u, "remove": /\.$/u };
 const cleanPuncBeforeLanguage = { "code": "atvxyz", "followedBy": "l", "context": puncIsProbablyPunc, "remove": / *[.,:;]$/u };
-const addX00aComma = { "add": ",", "code": "abcqej", "followedBy": "cdeg", "context": doesNotEndInPunc, "contextRHS": allowsPuncRHS };
+const addX00aComma = { "add": ",", "code": "abcqejt", "followedBy": "cdegnr", "context": doesNotEndInPunc, "contextRHS": allowsPuncRHS };
 const addX00dComma = { "name": 'X00$d ending in "-" does not get comma', "add": ",", "code": "d", "followedBy": "cdeg", "context": /[^-,.!]$/u, "contextRHS": allowsPuncRHS };
 const addX00aComma2 = { "add": ",", "code": "abcdej", "followedBy": "cdeg", "context": /(?:[A-Z]|Å|Ä|Ö)\.$/u, "contextRHS": allowsPuncRHS };
 const addX00Dot = { "add": ".", "code": "abcdetv", "followedBy": "fklptu", "context": needsPuncAfterAlphanumeric };
 const addEntryFieldFinalDot = { "name": "X00 final dot", "add": ".", "code": "abcdefghijklmnopqrstuvwxyz", "followedBy": "#", "context": /[^.)!?-]$/u };
-const addX10iColon = { name: "Punctuate relationship information", add: ":", code: "i", context: defaultNeedsPuncAfter2 };
+const addXX0iColon = { name: "Punctuate relationship information", add: ":", code: "i", context: defaultNeedsPuncAfter2 };
 const addX10bDot = { "name": "Add X10 pre-$b dot", "add": ".", "code": "ab", "followedBy": "b", "context": defaultNeedsPuncAfter2 };
-const addX10eComma = { "add": ",", "code": "abe", "followedBy": "e", "context": defaultNeedsPuncAfter2 };
+const addX10Comma = { "add": ",", "code": "abet", "followedBy": "en", "context": defaultNeedsPuncAfter2 };
 const addX10Dot = { "name": "Add X10 final dot", "add": ".", "code": "abet", "followedBy": "tu#", "context": needsPuncAfterAlphanumeric };
 const addColonToRelationshipInformation = { "name": "Add ':' to 7X0 $i relationship info", "add": ":", "code": "i", "context": defaultNeedsPuncAfter2 };
 const addX11Spacecolon = { name: "611 space colon(y :-)", add: " :", code: "nd", followedBy: "dc", "context": defaultNeedsPuncAfter2 };
@@ -149,10 +149,10 @@ const cleanCrappyPunctuationRules = {
   "830": remove490And830Whatever,
   "946": crappy24X
 };
-const cleanLegalX00Comma = { "code": "abcde", "followedBy": "cdegj", "context": /.,$/u, "remove": /,$/u };
+const cleanLegalX00Comma = { "code": "abcdetn", "followedBy": "cdegjnr", "context": /.,$/u, "remove": /,$/u };
 const cleanLegalX00bDot = { "code": "b", "followedBy": "t#", context: /^[IVXLCDM]+\.$/u, "remove": /\.$/u };
 const cleanLegalX00iColon = { "code": "i", "followedBy": "a", "remove": / *:$/u };
-const cleanLegalX00Dot = { "code": "abcdetvl", "followedBy": "tu#", "context": /(?:[a-z0-9)]|å|ä|ö)\.$/u, "remove": /\.$/u };
+const cleanLegalX00Dot = { "code": "abcdetkvl", "followedBy": "tklu#", "context": /(?:[a-z0-9)]|å|ä|ö)\.$/u, "remove": /\.$/u };
 const cleanDotBeforeLanguageSubfieldL = { "name": "pre-language-$l dot", "followedBy": "l", "context": /.\.$/u, "remove": /\.$/u };
 const legalEntryField = [cleanDotBeforeLanguageSubfieldL];
 const legalX11SpaceColon = { name: "legal X11 spacecolony", code: "nd", followedBy: "dc", context: / :$/u, remove: / :$/u };
@@ -227,8 +227,8 @@ const cleanValidPunctuationRules = {
   "946": clean24X
 };
 const addToAllEntryFields = [addDotBeforeLanguageSubfieldL, addSemicolonBeforeVolumeDesignation, addColonToRelationshipInformation, addEntryFieldFinalDot];
-const addX00 = [addX00aComma, addX00aComma2, addX00Dot, addX00dComma, ...addToAllEntryFields];
-const addX10 = [addX10iColon, addX10bDot, addX10eComma, addX10Dot, ...addToAllEntryFields];
+const addX00 = [addXX0iColon, addX00aComma, addX00aComma2, addX00Dot, addX00dComma, ...addToAllEntryFields];
+const addX10 = [addXX0iColon, addX10bDot, addX10Comma, addX10Dot, ...addToAllEntryFields];
 const addX11 = [...addToAllEntryFields, addX11Spacecolon];
 const addX30 = [...addToAllEntryFields];
 const add24X = [