Skip to content

Fix: Loosing data if XML was downloaded and uploaded again #1054

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
McNamara84 merged 10 commits into from
Apr 10, 2026
Merged

Fix: Loosing data if XML was downloaded and uploaded again #1054

Show file tree
Hide file tree
Changes from 7 commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
e409ea3
Add XML round-trip data loss tests
McNamara84 Apr 10, 2026
cbf9219
Refactor XML tests to use jsdom and real jQuery
McNamara84 Apr 10, 2026
ac991c3
Export descriptions, relatedWorks and funders
McNamara84 Apr 10, 2026
f1fb58b
Add XML round-trip data loss tests
McNamara84 Apr 10, 2026
fa0b9d5
Revise import tests for contact persons & XPath
McNamara84 Apr 10, 2026
6de4455
Auto-add author rows; fix funder id parsing
McNamara84 Apr 10, 2026
3a63cde
Use XPath resolver for namespaced XML parsing
McNamara84 Apr 10, 2026
b9b62e7
Add XPath fallback; guard author-row creation
McNamara84 Apr 10, 2026
60bd70f
Support non-namespaced XML for geo/funders
McNamara84 Apr 10, 2026
dfb7fa0
Fallback for non-namespaced dates; export STC
McNamara84 Apr 10, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
69 changes: 48 additions & 21 deletions js/mappingXmlToInputFields.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,10 +3,12 @@
* in the dropdown based on the visible text matching the `resourceTypeGeneral` attribute.
*
* @param {Document} xmlDoc - The XML document containing the resourceType element.
* @param {Function} resolver - The namespace resolver function.
*/
function processResourceType(xmlDoc) {
// Extract the resourceType element
const resourceNode = xmlDoc.querySelector("resourceType");
function processResourceType(xmlDoc, resolver) {
// Extract the resourceType element using XPath (querySelector fails on namespaced XML)
const result = xmlDoc.evaluate(".//ns:resourceType", xmlDoc, resolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null);
const resourceNode = result.singleNodeValue;
if (!resourceNode) {
console.error("No resourceType element found in XML");
return;
Expand Down Expand Up @@ -390,8 +392,11 @@ function processContactPersons(xmlDoc) {
.first();

if ($row.length === 0) {
console.warn(`No matching author row found for contact person: ${givenName} ${familyName}`);
continue;
// No matching author found — add a new author row for the contact person
$("#button-author-add").click();
$row = $("div[data-creator-row]").last();
$row.find('input[name="familynames[]"]').val(familyName);
$row.find('input[name="givennames[]"]').val(givenName);
}

// Mark the row as contact person
Expand Down Expand Up @@ -451,7 +456,13 @@ function processContactPersonsFromDataCite(xmlDoc) {
})
.first();

if ($row.length === 0) continue;
if ($row.length === 0) {
// No matching author found — add a new author row for the contact person
$("#button-author-add").click();
$row = $("div[data-creator-row]").last();
$row.find('input[name="familynames[]"]').val(familyName);
$row.find('input[name="givennames[]"]').val(givenName);
}

$row.find('input[name="contacts[]"]').prop("checked", true);
$row.find(".contact-person-input").show();
Expand Down Expand Up @@ -914,26 +925,38 @@ function parseTemporalData(dateNode) {
/**
* Extract spatial coordinates and description from a geoLocation node.
* @param {Element} node - The geoLocation XML element.
* @param {Document} xmlDoc - The XML document (needed for XPath evaluation).
* @param {Function} resolver - The namespace resolver function.
* @returns {Object} Parsed location data.
*/
function getGeoLocationData(node) {
const place = node.querySelector("geoLocationPlace")?.textContent || "";
const boxNode = node.querySelector("geoLocationBox");
const pointNode = node.querySelector("geoLocationPoint");
function getGeoLocationData(node, xmlDoc, resolver) {
function getText(contextNode, localName) {
const result = xmlDoc.evaluate("ns:" + localName, contextNode, resolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null);
return result.singleNodeValue?.textContent || "";
}

function getNode(contextNode, localName) {
const result = xmlDoc.evaluate("ns:" + localName, contextNode, resolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null);
return result.singleNodeValue;
}

const place = getText(node, "geoLocationPlace");
const boxNode = getNode(node, "geoLocationBox");
const pointNode = getNode(node, "geoLocationPoint");

if (boxNode) {
return {
place,
latitudeMin: boxNode.querySelector("southBoundLatitude")?.textContent || "",
latitudeMax: boxNode.querySelector("northBoundLatitude")?.textContent || "",
longitudeMin: boxNode.querySelector("westBoundLongitude")?.textContent || "",
longitudeMax: boxNode.querySelector("eastBoundLongitude")?.textContent || "",
latitudeMin: getText(boxNode, "southBoundLatitude"),
latitudeMax: getText(boxNode, "northBoundLatitude"),
longitudeMin: getText(boxNode, "westBoundLongitude"),
longitudeMax: getText(boxNode, "eastBoundLongitude"),
};
}

if (pointNode) {
const lat = pointNode.querySelector("pointLatitude")?.textContent || "";
const lon = pointNode.querySelector("pointLongitude")?.textContent || "";
const lat = getText(pointNode, "pointLatitude");
const lon = getText(pointNode, "pointLongitude");
return {
place,
latitudeMin: lat,
Expand Down Expand Up @@ -1004,7 +1027,7 @@ function processSpatialTemporalCoverages(xmlDoc, resolver) {
const dateNodes = xmlDoc.evaluate('//ns:dates/ns:date[@dateType="Coverage" or @dateType="Collected"]', xmlDoc, resolver, XPathResult.ORDERED_NODE_SNAPSHOT_TYPE, null);

for (let i = 0; i < geoLocationNodes.snapshotLength; i++) {
const geoData = getGeoLocationData(geoLocationNodes.snapshotItem(i));
const geoData = getGeoLocationData(geoLocationNodes.snapshotItem(i), xmlDoc, resolver);
const temporalData = parseTemporalData(dateNodes.snapshotItem(i));

const $lastRow = $('textarea[name="tscDescription[]"]').last().closest("[tsc-row]");
Expand Down Expand Up @@ -1286,8 +1309,9 @@ function processFunders(xmlDoc, resolver) {
const funderNode = funderNodes.snapshotItem(i);
// Extract data from XML
const funderName = getNodeText(funderNode, "ns:funderName", xmlDoc, resolver);
const funderId = getNodeText(funderNode, "ns:funderIdentifier", xmlDoc, resolver);
const funderIdTyp = funderNode.querySelector("funderIdentifier")?.getAttribute("funderIdentifierType") || "";
const funderIdNode = xmlDoc.evaluate("ns:funderIdentifier", funderNode, resolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
const funderId = funderIdNode ? funderIdNode.textContent.trim() : "";
const funderIdTyp = funderIdNode?.getAttribute("funderIdentifierType") || "";
const awardTitle = getNodeText(funderNode, "ns:awardTitle", xmlDoc, resolver);
const awardNumberNode = xmlDoc.evaluate("ns:awardNumber", funderNode, resolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
const awardNumber = awardNumberNode ? awardNumberNode.textContent.trim() : "";
Expand Down Expand Up @@ -1410,7 +1434,7 @@ async function loadXmlToForm(xmlDoc) {
}
}

processResourceType(xmlDoc);
processResourceType(xmlDoc, resolver);
// Process titles
processTitles(xmlDoc, resolver, titleTypeMapping);
// Processing Creators
Expand Down Expand Up @@ -1469,6 +1493,9 @@ if (typeof module !== 'undefined' && module.exports) {
parseTemporalData,
getGeoLocationData,
fillSpatialFields,
processUsedInstruments
processUsedInstruments,
processDescriptions,
processRelatedWorks,
processFunders
};
}
76 changes: 67 additions & 9 deletions tests/js/contactPersonLoading.test.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,9 +42,29 @@ describe('processContactPersons (ISO)', () => {
<input type="text" name="cpOnlineResource[]" value="" />
</div>
</div>
<button type="button" id="button-author-add"></button>
</div>
`;

// Wire up click handler to simulate adding a new author row
$('#button-author-add').on('click', function () {
const $newRow = $(`
<div class="row" data-creator-row>
<input type="checkbox" name="contacts[]" />
<input type="text" name="familynames[]" value="" />
<input type="text" name="givennames[]" value="" />
<input type="text" name="orcids[]" value="" />
<div class="contact-person-input" style="display: none;">
<input type="email" name="cpEmail[]" value="" />
</div>
<div class="contact-person-input" style="display: none;">
<input type="text" name="cpOnlineResource[]" value="" />
</div>
</div>
`);
$('#group-author').append($newRow);
});

global.Tagify = jest.fn().mockImplementation(() => ({
addTags: jest.fn(),
settings: { whitelist: [] },
Expand Down Expand Up @@ -175,7 +195,7 @@ describe('processContactPersons (ISO)', () => {
expect($firstRow.find('input[name="contacts[]"]').prop('checked')).toBe(true);
});

test('does not match when names differ completely', () => {
test('creates new author row when names differ completely', () => {
const xmlDoc = makeIsoXml({
familyName: 'Unknown',
givenName: 'Person',
Expand All @@ -184,10 +204,20 @@ describe('processContactPersons (ISO)', () => {

mappingModule.processContactPersons(xmlDoc);

// Neither row should be marked as CP
$('div[data-creator-row]').each(function () {
expect($(this).find('input[name="contacts[]"]').prop('checked')).toBe(false);
});
// A third author row should have been created
const $rows = $('div[data-creator-row]');
expect($rows.length).toBe(3);

// Original rows should not be marked as CP
expect($rows.eq(0).find('input[name="contacts[]"]').prop('checked')).toBe(false);
expect($rows.eq(1).find('input[name="contacts[]"]').prop('checked')).toBe(false);

// New row should be marked as CP with correct data
const $newRow = $rows.eq(2);
expect($newRow.find('input[name="contacts[]"]').prop('checked')).toBe(true);
expect($newRow.find('input[name="familynames[]"]').val()).toBe('Unknown');
expect($newRow.find('input[name="givennames[]"]').val()).toBe('Person');
expect($newRow.find('input[name="cpEmail[]"]').val()).toBe('[email protected]');
});

test('handles XML with no pointOfContact gracefully', () => {
Expand Down Expand Up @@ -309,9 +339,28 @@ describe('processContactPersonsFromDataCite (fallback)', () => {
<input type="text" name="cpOnlineResource[]" value="" />
</div>
</div>
<button type="button" id="button-author-add"></button>
</div>
`;

// Wire up click handler to simulate adding a new author row
$('#button-author-add').on('click', function () {
const $newRow = $(`
<div class="row" data-creator-row>
<input type="checkbox" name="contacts[]" />
<input type="text" name="familynames[]" value="" />
<input type="text" name="givennames[]" value="" />
<div class="contact-person-input" style="display: none;">
<input type="email" name="cpEmail[]" value="" />
</div>
<div class="contact-person-input" style="display: none;">
<input type="text" name="cpOnlineResource[]" value="" />
</div>
</div>
`);
$('#group-author').append($newRow);
});

global.Tagify = jest.fn().mockImplementation(() => ({
addTags: jest.fn(),
settings: { whitelist: [] },
Expand Down Expand Up @@ -407,17 +456,26 @@ describe('processContactPersonsFromDataCite (fallback)', () => {
expect($firstRow.find('input[name="contacts[]"]').prop('checked')).toBe(true);
});

test('does nothing when no matching author found in DataCite fallback', () => {
test('creates new author row when no matching author found in DataCite fallback', () => {
const xmlDoc = makeDataCiteXml({
familyName: 'Unknown',
givenName: 'Person',
});

expect(() => mappingModule.processContactPersonsFromDataCite(xmlDoc)).not.toThrow();

$('div[data-creator-row]').each(function () {
expect($(this).find('input[name="contacts[]"]').prop('checked')).toBe(false);
});
// A second author row should have been created
const $rows = $('div[data-creator-row]');
expect($rows.length).toBe(2);

// Original row should not be marked as CP
expect($rows.eq(0).find('input[name="contacts[]"]').prop('checked')).toBe(false);

// New row should be marked as CP with correct data
const $newRow = $rows.eq(1);
expect($newRow.find('input[name="contacts[]"]').prop('checked')).toBe(true);
expect($newRow.find('input[name="familynames[]"]').val()).toBe('Unknown');
expect($newRow.find('input[name="givennames[]"]').val()).toBe('Person');
});

test('does nothing when DataCite XML has no ContactPerson contributor', () => {
Expand Down
65 changes: 36 additions & 29 deletions tests/js/mappingXmlToInputFields.module.test.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -438,42 +438,47 @@ describe('mappingXmlToInputFields module coverage', () => {
});

describe('getGeoLocationData', () => {
const nsResolver = (prefix) => prefix === 'ns' ? 'http://datacite.org/schema/kernel-4' : null;

test('returns empty data for node without location info', () => {
const parser = new DOMParser();
const xmlDoc = parser.parseFromString('<geoLocation></geoLocation>', 'text/xml');
const geoNode = xmlDoc.querySelector('geoLocation');
const xmlDoc = parser.parseFromString(
'<ns:geoLocation xmlns:ns="http://datacite.org/schema/kernel-4"></ns:geoLocation>',
'text/xml'
);
const geoNode = xmlDoc.documentElement;

const result = mappingModule.getGeoLocationData(geoNode);
const result = mappingModule.getGeoLocationData(geoNode, xmlDoc, nsResolver);
expect(result.latitudeMin).toBe('');
expect(result.longitudeMin).toBe('');
});

test('extracts place name', () => {
const parser = new DOMParser();
const xmlDoc = parser.parseFromString(
'<geoLocation><geoLocationPlace>Berlin</geoLocationPlace></geoLocation>',
'<ns:geoLocation xmlns:ns="http://datacite.org/schema/kernel-4"><ns:geoLocationPlace>Berlin</ns:geoLocationPlace></ns:geoLocation>',
'text/xml'
);
const geoNode = xmlDoc.querySelector('geoLocation');
const geoNode = xmlDoc.documentElement;

const result = mappingModule.getGeoLocationData(geoNode);
const result = mappingModule.getGeoLocationData(geoNode, xmlDoc, nsResolver);
expect(result.place).toBe('Berlin');
});

test('extracts point coordinates', () => {
const parser = new DOMParser();
const xmlDoc = parser.parseFromString(
`<geoLocation>
<geoLocationPoint>
<pointLatitude>52.5</pointLatitude>
<pointLongitude>13.4</pointLongitude>
</geoLocationPoint>
</geoLocation>`,
`<ns:geoLocation xmlns:ns="http://datacite.org/schema/kernel-4">
<ns:geoLocationPoint>
<ns:pointLatitude>52.5</ns:pointLatitude>
<ns:pointLongitude>13.4</ns:pointLongitude>
</ns:geoLocationPoint>
</ns:geoLocation>`,
'text/xml'
);
const geoNode = xmlDoc.querySelector('geoLocation');
const geoNode = xmlDoc.documentElement;

const result = mappingModule.getGeoLocationData(geoNode);
const result = mappingModule.getGeoLocationData(geoNode, xmlDoc, nsResolver);
// For point, lat/lon are duplicated to min and max
expect(result.latitudeMin).toBe('52.5');
expect(result.latitudeMax).toBe('52.5');
Expand All @@ -484,19 +489,19 @@ describe('mappingXmlToInputFields module coverage', () => {
test('extracts bounding box coordinates', () => {
const parser = new DOMParser();
const xmlDoc = parser.parseFromString(
`<geoLocation>
<geoLocationBox>
<northBoundLatitude>53</northBoundLatitude>
<southBoundLatitude>52</southBoundLatitude>
<eastBoundLongitude>14</eastBoundLongitude>
<westBoundLongitude>13</westBoundLongitude>
</geoLocationBox>
</geoLocation>`,
`<ns:geoLocation xmlns:ns="http://datacite.org/schema/kernel-4">
<ns:geoLocationBox>
<ns:northBoundLatitude>53</ns:northBoundLatitude>
<ns:southBoundLatitude>52</ns:southBoundLatitude>
<ns:eastBoundLongitude>14</ns:eastBoundLongitude>
<ns:westBoundLongitude>13</ns:westBoundLongitude>
</ns:geoLocationBox>
</ns:geoLocation>`,
'text/xml'
);
const geoNode = xmlDoc.querySelector('geoLocation');
const geoNode = xmlDoc.documentElement;

const result = mappingModule.getGeoLocationData(geoNode);
const result = mappingModule.getGeoLocationData(geoNode, xmlDoc, nsResolver);
expect(result.latitudeMin).toBe('52');
expect(result.latitudeMax).toBe('53');
expect(result.longitudeMin).toBe('13');
Expand Down Expand Up @@ -541,36 +546,38 @@ describe('mappingXmlToInputFields module coverage', () => {
});

describe('processResourceType', () => {
const nsResolver = (prefix) => prefix === 'ns' ? 'http://datacite.org/schema/kernel-4' : null;

test('handles missing resourceType node', () => {
const parser = new DOMParser();
const xmlDoc = parser.parseFromString('<root></root>', 'text/xml');

// Should not throw
expect(() => {
mappingModule.processResourceType(xmlDoc);
mappingModule.processResourceType(xmlDoc, nsResolver);
}).not.toThrow();
});

test('handles missing resourceTypeGeneral attribute', () => {
const parser = new DOMParser();
const xmlDoc = parser.parseFromString(
'<resource><resourceType>Research Data</resourceType></resource>',
'<ns:resource xmlns:ns="http://datacite.org/schema/kernel-4"><ns:resourceType>Research Data</ns:resourceType></ns:resource>',
'text/xml'
);

expect(() => {
mappingModule.processResourceType(xmlDoc);
mappingModule.processResourceType(xmlDoc, nsResolver);
}).not.toThrow();
});

test('selects matching option in dropdown', () => {
const parser = new DOMParser();
const xmlDoc = parser.parseFromString(
'<resource><resourceType resourceTypeGeneral="Dataset">Research Data</resourceType></resource>',
'<ns:resource xmlns:ns="http://datacite.org/schema/kernel-4"><ns:resourceType resourceTypeGeneral="Dataset">Research Data</ns:resourceType></ns:resource>',
'text/xml'
);

mappingModule.processResourceType(xmlDoc);
mappingModule.processResourceType(xmlDoc, nsResolver);

const select = document.querySelector('#input-resourceinformation-resourcetype');
expect(select.options[0].selected).toBe(true);
Expand Down
Loading
Loading