feat: add ebook MIME types, fix azw3/mobi detection collision, trust undetectable ebook formats

This commit is contained in:
2026-07-31 13:25:46 +02:00
parent 534630ab4e
commit 977dac35d9
2 changed files with 99 additions and 1 deletions
+20 -1
View File
@@ -22,6 +22,15 @@ const OUTPUT_MIME_TYPES = {
ttf: 'font/ttf',
otf: 'font/otf',
woff: 'font/woff',
epub: 'application/epub+zip',
fb2: 'application/x-fictionbook+xml',
lrf: 'application/octet-stream',
mobi: 'application/x-mobipocket-ebook',
pdb: 'application/vnd.palm',
rb: 'application/octet-stream',
snb: 'application/octet-stream',
tcr: 'application/octet-stream',
azw3: 'application/vnd.amazon.ebook',
};
export async function detectInputMime(filePath) {
@@ -44,9 +53,19 @@ const UNDETECTABLE_TEXT_FORMATS = {
csv: 'text/csv',
};
const UNDETECTABLE_EBOOK_FORMATS = {
fb2: 'application/x-fictionbook+xml',
lrf: 'application/octet-stream',
pdb: 'application/vnd.palm',
rb: 'application/octet-stream',
snb: 'application/octet-stream',
tcr: 'application/octet-stream',
};
function normalizeFormat(format) {
if (format === 'jpg') return 'jpeg';
if (format === 'heif') return 'heic';
if (format === 'azw3') return 'mobi';
return format;
}
@@ -61,7 +80,7 @@ export async function resolveInputFormat(filePath, declaredFormat) {
const detected = await detectInputMime(filePath);
if (!detected) {
const fallbackMime = UNDETECTABLE_TEXT_FORMATS[declaredFormat];
const fallbackMime = UNDETECTABLE_TEXT_FORMATS[declaredFormat] ?? UNDETECTABLE_EBOOK_FORMATS[declaredFormat];
if (fallbackMime) {
return { mime: fallbackMime, valid: true };
}
+79
View File
@@ -113,6 +113,85 @@ describe('outputMimeType — fonts', () => {
});
});
describe('outputMimeType — ebooks', () => {
it('returns the correct MIME type for each ebook target format', () => {
expect(outputMimeType('epub')).toBe('application/epub+zip');
expect(outputMimeType('fb2')).toBe('application/x-fictionbook+xml');
expect(outputMimeType('mobi')).toBe('application/x-mobipocket-ebook');
expect(outputMimeType('azw3')).toBe('application/vnd.amazon.ebook');
expect(outputMimeType('pdb')).toBe('application/vnd.palm');
expect(outputMimeType('lrf')).toBe('application/octet-stream');
expect(outputMimeType('rb')).toBe('application/octet-stream');
expect(outputMimeType('snb')).toBe('application/octet-stream');
expect(outputMimeType('tcr')).toBe('application/octet-stream');
});
});
describe('resolveInputFormat — azw3/mobi collision', () => {
function buildMobiFamilyBuffer() {
// PDB header: 8-byte "BOOKMOBI" type+creator magic at offset 60, shared by both
// real .mobi and real .azw3 files (confirmed in file-type's source).
const buffer = Buffer.alloc(68);
buffer.write('BOOKMOBI', 60, 'ascii');
return buffer;
}
it('confirms file-type reports mobi-family content as ext "mobi" regardless of which of the two formats it is (documents the collision this fix works around)', async () => {
const fixturePath = path.join(import.meta.dirname, 'fixtures', 'sample-mobi-family.bin');
await fs.writeFile(fixturePath, buildMobiFamilyBuffer());
const detected = await detectInputMime(fixturePath);
expect(detected).toEqual({ ext: 'mobi', mime: 'application/x-mobipocket-ebook' });
await fs.unlink(fixturePath);
});
it('accepts a real mobi-family file declared as mobi', async () => {
const fixturePath = path.join(import.meta.dirname, 'fixtures', 'sample-mobi-family.bin');
await fs.writeFile(fixturePath, buildMobiFamilyBuffer());
const result = await resolveInputFormat(fixturePath, 'mobi');
expect(result).toEqual({ mime: 'application/x-mobipocket-ebook', valid: true });
await fs.unlink(fixturePath);
});
it('accepts a real mobi-family file declared as azw3 despite file-type reporting it as mobi', async () => {
const fixturePath = path.join(import.meta.dirname, 'fixtures', 'sample-mobi-family.bin');
await fs.writeFile(fixturePath, buildMobiFamilyBuffer());
const result = await resolveInputFormat(fixturePath, 'azw3');
expect(result).toEqual({ mime: 'application/x-mobipocket-ebook', valid: true });
await fs.unlink(fixturePath);
});
});
describe('resolveInputFormat — undetectable ebook formats', () => {
const undetectableFormats = {
fb2: 'application/x-fictionbook+xml',
lrf: 'application/octet-stream',
pdb: 'application/vnd.palm',
rb: 'application/octet-stream',
snb: 'application/octet-stream',
tcr: 'application/octet-stream',
};
it.each(Object.entries(undetectableFormats))(
'trusts the declared format for undetectable %s files',
async (declaredFormat, expectedMime) => {
const fixturePath = path.join(import.meta.dirname, 'fixtures', `sample.${declaredFormat}`);
await fs.writeFile(fixturePath, 'arbitrary bytes with no recognizable magic number');
const result = await resolveInputFormat(fixturePath, declaredFormat);
expect(result).toEqual({ mime: expectedMime, valid: true });
await fs.unlink(fixturePath);
}
);
});
describe('resolveInputFormat — dfont', () => {
it('confirms file-type alone misidentifies the dfont fixture as ico (documents the bug this fix works around)', async () => {
const fixturePath = path.join(import.meta.dirname, 'fixtures', 'sample.dfont');