Skip to content

fix: doc-api story regressions and export app.xml stats #2478

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
harbournick merged 3 commits into from
Mar 19, 2026
Merged

fix: doc-api story regressions and export app.xml stats #2478

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a24145b
fix: doc-api story regressions and export app.xml stats
harbournick Mar 19, 2026
37c4841
Merge branch 'main' into nick/fix-doc-api-stories-regressions
harbournick Mar 19, 2026
79395b6
fix: child export app.xml stats to use main document counts
harbournick Mar 19, 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
4 changes: 4 additions & 0 deletions packages/super-editor/src/core/Editor.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2901,6 +2901,9 @@ export class Editor extends EventEmitter<EditorEventMap> {
const numberingData = this.converter.convertedXml['word/numbering.xml'];
const numbering = this.converter.schemaToXml(numberingData.elements[0]);

const appXmlData = this.converter.convertedXml['docProps/app.xml'];
const appXml = appXmlData?.elements?.[0] ? this.converter.schemaToXml(appXmlData.elements[0]) : null;

// Export core.xml (contains dcterms:created timestamp)
const coreXmlData = this.converter.convertedXml['docProps/core.xml'];
const coreXml = coreXmlData?.elements?.[0] ? this.converter.schemaToXml(coreXmlData.elements[0]) : null;
Expand All @@ -2913,6 +2916,7 @@ export class Editor extends EventEmitter<EditorEventMap> {
'word/numbering.xml': String(numbering),
'word/styles.xml': String(styles),
...updatedHeadersFooters,
...(appXml ? { 'docProps/app.xml': String(appXml) } : {}),
Comment thread
harbournick marked this conversation as resolved.
...(coreXml ? { 'docProps/core.xml': String(coreXml) } : {}),
};

Expand Down
25 changes: 25 additions & 0 deletions packages/super-editor/src/tests/regression/opc-package-metadata-roundtrip.test.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,12 @@ const TEST_DOC = 'blank-doc.docx';

const CT_CUSTOM = 'application/vnd.openxmlformats-officedocument.custom-properties+xml';
const REL_CUSTOM = 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/custom-properties';
const WORD_STAT_TEXT = 'Alpha beta gamma';

function readXmlTagValue(xml, tagName) {
const match = xml.match(new RegExp(`<${tagName}>([^<]*)</${tagName}>`));
return match?.[1] ?? null;
}

describe('OPC package metadata: custom-properties registration', () => {
it('getUpdatedDocs includes correct [Content_Types].xml and _rels/.rels for new custom.xml', async () => {
Expand Down Expand Up @@ -122,4 +128,23 @@ describe('OPC package metadata: custom-properties registration', () => {
editor.destroy();
}
});

it('getUpdatedDocs includes refreshed docProps/app.xml statistics', async () => {
const { docx, media, mediaFiles, fonts } = await loadTestDataForEditorTests(TEST_DOC);
const { editor } = initTestEditor({ content: docx, media, mediaFiles, fonts, isHeadless: true });

try {
editor.commands.insertContent(WORD_STAT_TEXT);

const updatedDocs = await editor.exportDocx({ getUpdatedDocs: true });
const appXml = updatedDocs['docProps/app.xml'];

expect(appXml).toBeTruthy();
expect(readXmlTagValue(appXml, 'Words')).toBe('3');
expect(readXmlTagValue(appXml, 'Characters')).toBe('14');
expect(readXmlTagValue(appXml, 'CharactersWithSpaces')).toBe('16');
} finally {
editor.destroy();
}
});
});
41 changes: 23 additions & 18 deletions tests/doc-api-stories/tests/content-controls/all-commands.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,6 +84,7 @@ const ALL_CONTENT_CONTROL_COMMAND_IDS = [
'contentControls.group.wrap',
'contentControls.group.ungroup',
] as const;
const COMMAND_STORY_TIMEOUT_MS = 60_000;

type ContentControlsCommandId = (typeof ALL_CONTENT_CONTROL_COMMAND_IDS)[number];

Expand Down Expand Up @@ -2082,30 +2083,34 @@ describe('document-api story: all content-controls commands', () => {
});

for (const scenario of scenarios) {
it(`${scenario.operationId}: executes and saves source/result docs`, async () => {
const sessionId = makeSessionId(scenario.operationId.replace(/\./g, '-'));
it(
`${scenario.operationId}: executes and saves source/result docs`,
async () => {
const sessionId = makeSessionId(scenario.operationId.replace(/\./g, '-'));

try {
await openSeedDocument(sessionId, scenario.seedDoc ?? BASE_CONTENT_CONTROLS_DOC);
try {
await openSeedDocument(sessionId, scenario.seedDoc ?? BASE_CONTENT_CONTROLS_DOC);

const fixture = scenario.prepare ? await scenario.prepare(sessionId) : null;
const fixture = scenario.prepare ? await scenario.prepare(sessionId) : null;

await saveSource(sessionId, scenario.operationId);
await saveSource(sessionId, scenario.operationId);

const result = await scenario.run(sessionId, fixture);
const result = await scenario.run(sessionId, fixture);

if (READ_OPERATION_IDS.has(scenario.operationId)) {
assertReadShape(scenario.operationId, result);
await saveReadOutput(scenario.operationId, result);
} else {
assertMutationSuccess(scenario.operationId, result, scenario.allowNoOpFailure === true);
}
if (READ_OPERATION_IDS.has(scenario.operationId)) {
assertReadShape(scenario.operationId, result);
await saveReadOutput(scenario.operationId, result);
} else {
assertMutationSuccess(scenario.operationId, result, scenario.allowNoOpFailure === true);
}

await saveResult(sessionId, scenario.operationId);
} finally {
await closeSession(sessionId).catch(() => {});
}
});
await saveResult(sessionId, scenario.operationId);
} finally {
await closeSession(sessionId).catch(() => {});
}
},
COMMAND_STORY_TIMEOUT_MS,
);
}

it('writes source/result artifacts for every content-controls command', async () => {
Expand Down
168 changes: 79 additions & 89 deletions tests/doc-api-stories/tests/fields/word-stat-fields-roundtrip.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,38 +13,49 @@ const FIXTURE_DOC = path.resolve(import.meta.dirname, 'fixtures', 'numwords.docx
// OOXML inspection helpers (local to this story)
// ---------------------------------------------------------------------------

type ExportedComplexField = {
fieldType: string;
instruction: string;
cachedText: string;
dirty: boolean;
};

type StoryField = {
address?: unknown;
fieldType?: string;
resolvedText?: string;
};

async function readDocxPart(docPath: string, partPath: string): Promise<string> {
const { stdout } = await execFileAsync('unzip', ['-p', docPath, partPath], {
maxBuffer: ZIP_MAX_BUFFER_BYTES,
});
return stdout;
}

/** Extracts all field instruction texts from a document.xml string. */
function extractFieldInstructions(documentXml: string): string[] {
const matches = [...documentXml.matchAll(/<w:instrText[^>]*>([^<]*)<\/w:instrText>/g)];
return matches.map((m) => m[1].trim());
}

/** Extracts text elements (w:t) from field cached result runs. */
function extractCachedFieldResults(documentXml: string): string[] {
// Find all w:t elements that appear between w:fldChar separate and end
const results: string[] = [];
const fieldRegex = /<w:fldChar[^>]*w:fldCharType="separate"[^>]*\/?>[\s\S]*?<w:fldChar[^>]*w:fldCharType="end"/g;

for (const match of documentXml.matchAll(fieldRegex)) {
const segment = match[0];
const textMatches = [...segment.matchAll(/<w:t[^>]*>([^<]*)<\/w:t>/g)];
for (const tm of textMatches) {
results.push(tm[1]);
}
function extractExportedComplexFields(documentXml: string): ExportedComplexField[] {
const complexFieldPattern =
/<w:fldChar[^>]*w:fldCharType="begin"([^>]*)\/?>[\s\S]*?<w:instrText[^>]*>([^<]*)<\/w:instrText>[\s\S]*?<w:fldChar[^>]*w:fldCharType="separate"[^>]*\/?>([\s\S]*?)<w:fldChar[^>]*w:fldCharType="end"/g;
const exportedFields: ExportedComplexField[] = [];

for (const match of documentXml.matchAll(complexFieldPattern)) {
const beginAttributes = match[1] ?? '';
const instruction = (match[2] ?? '').trim();
const cachedSegment = match[3] ?? '';
const cachedText = [...cachedSegment.matchAll(/<w:t[^>]*>([^<]*)<\/w:t>/g)]
.map((textMatch) => textMatch[1])
.join('');
const fieldType = instruction.split(/\s+/)[0]?.toUpperCase() ?? '';

exportedFields.push({
fieldType,
instruction,
cachedText,
dirty: beginAttributes.includes('w:dirty="true"'),
});
}
return results;
}

/** Checks whether w:updateFields is present in settings.xml. */
function hasUpdateFields(settingsXml: string): boolean {
return /<w:updateFields\b[^>]*w:val="true"/.test(settingsXml);
return exportedFields;
}

/** Extracts a simple element's text value from app.xml. */
Expand All @@ -53,11 +64,6 @@ function extractAppStat(appXml: string, tagName: string): string | null {
return match?.[1] ?? null;
}

/** Checks for w:dirty attribute on fldChar begin elements. */
function hasDirtyField(documentXml: string): boolean {
return /w:dirty="true"/.test(documentXml);
}

// ---------------------------------------------------------------------------
// Test helpers
// ---------------------------------------------------------------------------
Expand All @@ -78,11 +84,28 @@ describe('word-stat-fields roundtrip', () => {
const api = client as any;

async function openSession(docPath: string, sessionId: string) {
await api.doc.open({ filePath: docPath, sessionId });
await api.doc.open({ doc: docPath, sessionId });
}

async function saveSession(sessionId: string, savePath: string) {
await api.doc.save({ sessionId, filePath: savePath });
await api.doc.save({ sessionId, out: savePath, force: true });
}

function toStoryField(item: any): StoryField {
return (item?.domain ?? item ?? {}) as StoryField;
}

async function listFields(sessionId: string): Promise<StoryField[]> {
const listResult = unwrap<any>(await api.doc.fields.list({ sessionId }));
return Array.isArray(listResult?.items) ? listResult.items.map(toStoryField) : [];
}

function listFieldTypes(items: StoryField[]): string[] {
return items.map((item) => item.fieldType ?? '');
}

function findFieldByType(items: StoryField[], fieldType: string): StoryField | undefined {
return items.find((item) => item.fieldType === fieldType);
}

// ─────────────────────────────────────────────────────────────────────────
Expand All @@ -94,14 +117,7 @@ describe('word-stat-fields roundtrip', () => {
const sessionId = sid('phase-a');
await openSession(docPath, sessionId);

const listResult = await api.doc.fields.list({ sessionId });
const items = unwrap<any[]>(listResult)?.items ?? listResult?.items ?? [];

// The fixture has NUMWORDS, NUMCHARS, and NUMPAGES fields
const fieldTypes = items.map((item: any) => {
const domain = item?.domain ?? item;
return domain?.fieldType;
});
const fieldTypes = listFieldTypes(await listFields(sessionId));

expect(fieldTypes).toContain('NUMWORDS');
expect(fieldTypes).toContain('NUMCHARS');
Expand All @@ -124,25 +140,19 @@ describe('word-stat-fields roundtrip', () => {

// Inspect exported document.xml
const documentXml = await readDocxPart(savedPath, 'word/document.xml');
const exportedFields = extractExportedComplexFields(documentXml);
const exportedFieldByType = new Map(exportedFields.map((field) => [field.fieldType, field]));

// Should contain field instructions for our stat fields
const instructions = extractFieldInstructions(documentXml);
const hasNumwords = instructions.some((instr) => instr.includes('NUMWORDS'));
const hasNumchars = instructions.some((instr) => instr.includes('NUMCHARS'));
const hasNumpages = instructions.some((instr) => instr.includes('NUMPAGES'));

expect(hasNumwords).toBe(true);
expect(hasNumchars).toBe(true);
expect(hasNumpages).toBe(true);
expect(exportedFieldByType.has('NUMWORDS')).toBe(true);
expect(exportedFieldByType.has('NUMCHARS')).toBe(true);
expect(exportedFieldByType.has('NUMPAGES')).toBe(true);

// Should have fldChar structure (complex fields, not fldSimple)
expect(documentXml).toContain('w:fldCharType="begin"');
expect(documentXml).toContain('w:fldCharType="separate"');
expect(documentXml).toContain('w:fldCharType="end"');

// Should have cached result runs between separate and end
const cachedResults = extractCachedFieldResults(documentXml);
expect(cachedResults.length).toBeGreaterThanOrEqual(3);
expect(exportedFields).toHaveLength(3);

// Inspect docProps/app.xml — stat values should be present and consistent
const appXml = await readDocxPart(savedPath, 'docProps/app.xml');
Expand All @@ -161,17 +171,16 @@ describe('word-stat-fields roundtrip', () => {
// Characters (no spaces) must be ≤ CharactersWithSpaces (internal consistency)
expect(Number(charsValue)).toBeLessThanOrEqual(Number(charsWithSpaces));

// The NUMWORDS cached result in the field should match the app.xml Words value
// (both are computed from the same helper during export)
const numwordsCachedResult = cachedResults.find((r) => r && /^\d+$/.test(r.trim()));
if (numwordsCachedResult) {
expect(wordsValue).toBe(numwordsCachedResult.trim());
}
expect(exportedFieldByType.get('NUMWORDS')?.cachedText).toBe(wordsValue);
expect(exportedFieldByType.get('NUMCHARS')?.cachedText).toBe(charsValue);
expect(exportedFieldByType.get('NUMPAGES')?.cachedText).toBe(extractAppStat(appXml, 'Pages'));

// Dirty-flag policy: NUMWORDS and NUMCHARS should NOT be dirty (no
// uninterpreted switches). NUMPAGES may or may not be dirty depending
// on whether pagination was available in the test environment.
// We verify the structural invariant rather than a blanket dirty check.
expect(exportedFieldByType.get('NUMWORDS')?.dirty).toBe(false);
expect(exportedFieldByType.get('NUMCHARS')?.dirty).toBe(false);
const settingsXml = await readDocxPart(savedPath, 'word/settings.xml').catch(() => '');
if (settingsXml) {
expect(settingsXml).toContain('w:settings');
Expand All @@ -190,17 +199,12 @@ describe('word-stat-fields roundtrip', () => {

await openSession(docPath, sessionId);

// Get initial field list
const initialList = await api.doc.fields.list({ sessionId });
const initialItems = unwrap<any[]>(initialList)?.items ?? initialList?.items ?? [];
const numwordsField = initialItems.find((item: any) => {
const domain = item?.domain ?? item;
return domain?.fieldType === 'NUMWORDS';
});
const initialItems = await listFields(sessionId);
const numwordsField = findFieldByType(initialItems, 'NUMWORDS');

expect(numwordsField).toBeTruthy();

const initialResolvedText = numwordsField?.domain?.resolvedText ?? numwordsField?.resolvedText ?? '';
const initialResolvedText = numwordsField?.resolvedText ?? '';

// Append text to change the word count
await api.doc.create.paragraph({
Expand All @@ -209,32 +213,25 @@ describe('word-stat-fields roundtrip', () => {
text: 'These extra words change the count significantly',
});

// Rebuild the NUMWORDS field
const address = numwordsField?.domain?.address ?? numwordsField?.address;
if (address) {
await api.doc.fields.rebuild({ sessionId, target: address });
const address = numwordsField?.address;
expect(address).toBeTruthy();

// Check the value changed
const updatedList = await api.doc.fields.list({ sessionId });
const updatedItems = unwrap<any[]>(updatedList)?.items ?? updatedList?.items ?? [];
const updatedNumwords = updatedItems.find((item: any) => {
const domain = item?.domain ?? item;
return domain?.fieldType === 'NUMWORDS';
});
await api.doc.fields.rebuild({ sessionId, target: address });

const updatedResolvedText = updatedNumwords?.domain?.resolvedText ?? updatedNumwords?.resolvedText ?? '';
const updatedItems = await listFields(sessionId);
const updatedNumwords = findFieldByType(updatedItems, 'NUMWORDS');
const updatedResolvedText = updatedNumwords?.resolvedText ?? '';

// After adding words, the count should be different from the original
expect(updatedResolvedText).not.toBe(initialResolvedText);
}
// After adding words, the count should be different from the original
expect(updatedResolvedText).not.toBe(initialResolvedText);

// Save and re-inspect OOXML
const savedPath = outPath('phase-d-exported.docx');
await saveSession(sessionId, savedPath);

const documentXml = await readDocxPart(savedPath, 'word/document.xml');
const instructions = extractFieldInstructions(documentXml);
expect(instructions.some((instr) => instr.includes('NUMWORDS'))).toBe(true);
const exportedFields = extractExportedComplexFields(documentXml);
expect(exportedFields.some((field) => field.fieldType === 'NUMWORDS')).toBe(true);

await api.doc.close({ sessionId, discard: true });
});
Expand All @@ -255,14 +252,7 @@ describe('word-stat-fields roundtrip', () => {
// Reopen the exported file
const secondSessionId = sid('phase-e-second');
await openSession(firstSavedPath, secondSessionId);

const listResult = await api.doc.fields.list({ sessionId: secondSessionId });
const items = unwrap<any[]>(listResult)?.items ?? listResult?.items ?? [];

const fieldTypes = items.map((item: any) => {
const domain = item?.domain ?? item;
return domain?.fieldType;
});
const fieldTypes = listFieldTypes(await listFields(secondSessionId));

// Fields should still be discoverable after roundtrip
expect(fieldTypes).toContain('NUMWORDS');
Expand Down
Loading
Loading