@natlibfi/marc-record-validators-melinda 13.0.4 → 13.0.5

package/src/punctuation2.js

@@ -60,7 +60,8 @@ function isIrrelevantSubfield(subfield, tag) {
   if (subfield.code === dataProvenanceSubfieldCode) {
     return true;
   }
-  return !isContentSubfieldCode(subfield.code); // Currently this contains other stuff as well ($3, $4, $7, $9...)
+  // control subfields, data provenance subfields etc do not affect the punctuation of the previous field
+  return !isContentSubfieldCode(subfield.code);
 }
 
 
@@ -129,7 +130,7 @@ const cleanPuncBeforeLanguage = {'code': 'atvxyz', 'followedBy': 'l', 'context':
 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)\.$/u, 'contextRHS': allowsPuncRHS};
-const addX00Dot = {'add': '.', 'code': 'abcdetv', 'followedBy': 'fklptu', 'context': needsPuncAfterAlphanumeric};
+const addX00Dot = {'name': 'addX00Dot', 'add': '.', 'code': 'abcdetv', 'followedBy': 'fklptu', 'context': needsPuncAfterAlphanumeric};
 const addEntryFieldFinalDot = {'name': 'X00 final dot', 'add': '.', 'code': 'abcdefghijklmnopqrstuvwxyz', 'followedBy': '#', 'context': /[^.)!?-]$/u};
 
 
@@ -144,7 +145,7 @@ const addX11Spacecolon = {name: '611 space colon(y :-)', add: ' :', code: 'nd',
 const addDotBeforeLanguageSubfieldL = {'name': 'Add dot before $l', 'add': '.', 'code': 'abepst', 'followedBy': 'l', 'context': doesNotEndInPunc};
 
 // 490:
-const addSemicolonBeforeVolumeDesignation = {'name': 'Add " ;" before $v', 'add': ' ;', 'code': 'atxyz', 'followedBy': 'v', 'context': /[^;]$/u};
+const addSemicolonBeforeVolumeDesignation = {'name': 'Add " ;" before $v', 'add': ' ;', 'followedBy': 'v', 'context': /[^;]$/u};
 
 const NONE = 0;
 const ADD = 2;
@@ -245,7 +246,9 @@ const legalX10punc = [cleanLegalX10Comma, cleanLegalX10Dot, cleanX00eDot, ...leg
 
 const cleanLegalSeriesTitle = [ // 490 and 830
   {'code': 'a', 'followedBy': 'a', 'remove': / =$/u},
-  {'code': 'axyz', 'followedBy': 'xyz', 'remove': /,$/u, 'context': /.,$/u},
+  {'code': 'a', 'followedBy': 'n', 'remove': /\.$/u}, // f830-only
+  {'code': 'n', 'followedBy': 'p', 'remove': /,$/u}, // f830-only
+  {'code': 'anpxyz', 'followedBy': 'xyz', 'remove': /,$/u, 'context': /.,$/u},
   {'code': 'axyz', 'followedBy': 'v', 'remove': / *;$/u}
 ];
 
@@ -299,7 +302,7 @@ const cleanValidPunctuationRules = {
   '611': legalX11Punc,
   '630': legalEntryField,
   // Experimental, MET366-ish (end punc in internationally valid, but we don't use it here in Finland):
-  '648': [{'code': 'a', 'content': /^[0-9]+\.$/u, 'ind2': ['4'], 'remove': /\.$/u}],
+  '648': [{'code': 'a', 'context': /^[0-9]+\.$/u, 'ind2': ['4'], 'remove': /\.$/u}],
   '700': legalX00punc,
   '710': legalX10punc,
   '711': legalX11Punc,
@@ -313,13 +316,18 @@ const cleanValidPunctuationRules = {
 
 
 // Overgeneralizes a bit: eg. addColonToRelationshipInformation only applies to 700/710 but as others don't have $i, it's fine.
+// Also addSemicolonBeforeVolumeDesignation applies only to 8XX:
 const addToAllEntryFields = [addDotBeforeLanguageSubfieldL, addSemicolonBeforeVolumeDesignation, addColonToRelationshipInformation, addEntryFieldFinalDot];
 
 
 const addX00 = [addXX0iColon, addX00aComma, addX00aComma2, addX00Dot, addX00dComma, ...addToAllEntryFields];
 const addX10 = [addXX0iColon, addX10bDot, addX10Comma, addX10Dot, ...addToAllEntryFields];
 const addX11 = [...addToAllEntryFields, addX11Spacecolon];
-const addX30 = [...addToAllEntryFields];
+const addX30 = [
+  ...addToAllEntryFields,
+  {'name': 'X30$a dot', 'code': 'a', 'followedBy': 'knp', 'add': '.', 'context': needsPuncAfterAlphanumeric},
+  {'name': 'X30 final dot', 'code': 'adfghklmnoprstv', 'followedBy': '#', 'add': '.', 'context': needsPuncAfterAlphanumeric}
+];
 
 const add24X = [
   {'code': 'i', 'followedBy': 'a', 'add': ':', 'context': needsPuncAfterAlphanumeric},
@@ -339,7 +347,7 @@ const add245 = [
 
 const addSeriesTitle = [ // 490 and 830
   {'code': 'a', 'followedBy': 'a', 'add': ' =', 'context': defaultNeedsPuncAfter2},
-  {'code': 'axyz', 'followedBy': 'xy', 'add': ',', 'context': defaultNeedsPuncAfter2},
+  {'code': 'anpxyz', 'followedBy': 'pxy', 'add': ',', 'context': defaultNeedsPuncAfter2},
   addSemicolonBeforeVolumeDesignation //  eg. 490$axyz-$v
 ];
 
@@ -521,7 +529,7 @@ function applyPunctuationRules(field, subfield1, subfield2, ruleArray = null, op
 
   //nvdebug(`OP=${operation} ${tag2}: '${subfield1.code}: ${subfield1.value}' ??? '${subfield2 ? subfield2.code : '#'}'`, debugDev);
   const candRules = ruleArray[tag2];
-  candRules.every(rule => { // uses "every", not "forEach", so that only one rule is applies to the given subfields
+  candRules.every(rule => { // uses "every", not "forEach", so that only one rule is applied to the given subfields
     //debugRule(rule);
     if (!checkRule(rule, field, subfield1, subfield2)) {
       return true;
@@ -578,21 +586,21 @@ export function fieldStripPunctuation(field) {
   return field;
 }
 
-export function fieldFixPunctuation(field) {
+export function fieldFixPunctuation(field, externalEndPunctuation = false) {
   if (!field.subfields) {
     return field;
   }
   //nvdebug(`################### fieldFixPunctuation() TEST ${fieldToString(field)}`, debugDev);
 
   field.subfields.forEach((sf, i) => {
-    // NB! instead of next subfield, we should actually get next *non-control-subfield*!!!
-    // (In plain English: We should skip $0 - $9 at least, maybe $w as well...)
+    // NB! instead of next subfield, we get next *non-control-subfield*!!!
+    // (In plain English: We skip $0 ... $9 at least, maybe $w as well...)
     // We'll need some magic for field 257 here, do we? (Also Finnish lexicons vs global lexicons in 65X fields)
     subfieldFixPunctuation(field, sf, getNextRelevantSubfield(field, i));
   });
 
   // Use shared code for final punctuation (sadly this does not fix intermediate punc):
-  if (field.useExternalEndPunctuation) {
+  if (externalEndPunctuation || field.useExternalEndPunctuation) {
     // addFinalPunctuation(field); // local version. use shared code instead.
     validateSingleField(field, false, true); // NB! Don't use field.tag as second argument! It's a string, not an int. 3rd arg must be true (=fix)
   }

package/src/punctuation2.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 './punctuation2.js';
 import {READERS} from '@natlibfi/fixura';
@@ -42,5 +42,5 @@ async function callback({getFixture, fix = false}) {
   }
 
   await validator.fix(record);
-  assert.deepEqual(record, expectedResult);
+  assert.deepEqual(record, new MarcRecord(expectedResult));
 }

package/src/sortSubfields.js

@@ -126,7 +126,7 @@ const subfieldSortOrder = [
   {'tag': '800', 'sortOrder': sortOrderForX00},
   {'tag': '810', 'sortOrder': sortOrderForX10},
   {'tag': '811', 'sortOrder': sortOrderForX11},
-  {'tag': '830', 'sortOrder': ['a', 'n', 'x', 'v']}, // INCOMPLETE, SAME AS 490? APPARENTLY NOT...
+  {'tag': '830', 'sortOrder': ['a', 'n', 'p', 'x', 'v']}, // Sort of an extension of f490...
   {'tag': '856', 'sortOrder': ['3', 'u', 'q', 'x', 'y', 'z', '5']}, // incomplete, LoC examples are inconclusive
   {'tag': '880', 'sortOrder': ['a']},
   {'tag': '946', 'sortOrder': sortOrderFor246},

package/test-fixtures/cyrillux-usemarcon-replacement/f10/metadata.json

@@ -1,5 +1,5 @@
 {
-  "description": "Fix Cyrillux-related stuff: split 410 to 490 and 810, and split 440 to 490 and 810",
+  "description": "Fix Cyrillux-related stuff: split 410 to 490 and 810, and split 440 to 490 and 830",
   "comment": "Also note few indicator changes",
   "only": false,
   "fix": true

package/test-fixtures/merge-fields/f04/expectedResult.json

@@ -7,8 +7,7 @@
       { "code": "d", "value": "1890-1940," },
       { "code": "e", "value": "säveltäjä," },
       { "code": "e", "value": "sanoittaja," },
-      { "code": "e", "value": "sovittaja." },
-      { "code": "0", "value": "(FI-ASTERI-N)000123456" }
+      { "code": "e", "value": "sovittaja." }
     ]}
   ]
 }

package/test-fixtures/merge-fields/f04/record.json

@@ -7,8 +7,7 @@
     ]},
     { "tag": "100", "ind1": "1", "ind2": " ", "subfields": [
       { "code": "a", "value": "Sukunimi, Etunimi," },
-      { "code": "e", "value": "sovittaja." },
-      { "code": "0", "value": "(FI-ASTERI-N)000123456" }
+      { "code": "e", "value": "sovittaja." }
     ]},
     { "tag": "700", "ind1": "1", "ind2": " ", "subfields": [
       { "code": "a", "value": "Sukunimi, Etunimi," },

package/test-fixtures/merge-fields/f700_01/expectedResult.json

@@ -0,0 +1,18 @@
+{
+  "_validationOptions": {},
+  "leader": "12345cam a22123454i 4500",
+  "fields": [
+    { "tag": "700", "ind1": "1", "ind2": " ", "subfields": [
+        { "code": "a", "value": "Sukunimi, A." },
+        { "code": "0", "value": "(FI-ASTERI-N)000000111" }
+    ]},
+    { "tag": "700", "ind1": "1", "ind2": " ", "subfields": [
+        { "code": "a", "value": "Sukunimi, B." },
+        { "code": "q", "value": "(Börje)," },
+        { "code": "d", "value": "1234-1299." },
+        { "code": "0", "value": "(FI-ASTERI-N)000000123" }
+    ]}
+
+
+  ]
+}

package/test-fixtures/merge-fields/f700_01/metadata.json

@@ -0,0 +1,5 @@
+{
+  "description": "F700/01: don't merge years from a non-authorized pair, but merge them from authorized",
+  "only": true,
+  "fix": true
+}

package/test-fixtures/merge-fields/f700_01/record.json

@@ -0,0 +1,24 @@
+{
+  "leader": "12345cam a22123454i 4500",
+  "fields": [
+    { "tag": "700", "ind1": "1", "ind2": " ", "subfields": [
+        { "code": "a", "value": "Sukunimi, A." },
+        { "code": "0", "value": "(FI-ASTERI-N)000000111" }
+    ]},
+    { "tag": "700", "ind1": "1", "ind2": " ", "subfields": [
+        { "code": "a", "value": "Sukunimi, A.," },
+        { "code": "d", "value": "1234-1299." }
+    ]},
+    { "tag": "700", "ind1": "1", "ind2": " ", "subfields": [
+        { "code": "a", "value": "Sukunimi, B." },
+        { "code": "q", "value": "(Börje)" },
+        { "code": "0", "value": "(FI-ASTERI-N)000000123" }
+    ]},
+    { "tag": "700", "ind1": "1", "ind2": " ", "subfields": [
+        { "code": "a", "value": "Sukunimi, B.," },
+        { "code": "d", "value": "1234-1299." },
+        { "code": "0", "value": "(FI-ASTERI-N)000000123" }
+    ]}
+
+  ]
+}

package/test-fixtures/merge-fields/f830_01/expectedResult.json

@@ -0,0 +1,20 @@
+{
+  "_validationOptions": {},
+  "fields": [
+    { "tag": "830", "ind1": " ", "ind2": "0", "subfields": [
+      { "code": "a", "value": "Annales." },
+      { "code": "n", "value": "Series B," },
+      { "code": "p", "value": "Humaniora ;" },
+      { "code": "v", "value": "153, 4" }
+    ] },
+    { "tag": "830", "ind1": " ", "ind2": "0", "subfields": [
+      { "code": "a", "value": "Annales." },
+      { "code": "n", "value": "Series B," },
+      { "code": "x", "value": "0066-2011 ;" },
+      { "code": "v", "value": "153, 4" },
+      { "code": "0", "value": "(FI-ASTERI-W)000015651" }
+    ] }
+  ],
+  "leader": "01331cam a22003498i 4500"
+
+}

package/test-fixtures/merge-fields/f830_01/metadata.json

@@ -0,0 +1,6 @@
+{
+  "description": "f830/01: fields should not merge, as $0 vs $p blocks pairing",
+  "fix": true,
+  "only": false,
+  "tagPattern": "^830$"
+}

package/test-fixtures/merge-fields/f830_01/record.json

@@ -0,0 +1,20 @@
+{
+  "_validationOptions": {},
+  "fields": [
+    { "tag": "830", "ind1": " ", "ind2": "0", "subfields": [
+      { "code": "a", "value": "Annales." },
+      { "code": "n", "value": "Series B," },
+      { "code": "p", "value": "Humaniora ;" },
+      { "code": "v", "value": "153, 4" }
+    ] },
+    { "tag": "830", "ind1": " ", "ind2": "0", "subfields": [
+      { "code": "a", "value": "Annales." },
+      { "code": "n", "value": "Series B," },
+      { "code": "x", "value": "0066-2011 ;" },
+      { "code": "v", "value": "153, 4" },
+      { "code": "0", "value": "(FI-ASTERI-W)000015651" }
+    ] }
+  ],
+  "leader": "01331cam a22003498i 4500"
+
+}