feat: read gallery-dl sidecars for reel type and post dates

The .json sidecars published with the ARTMS fetch were inert: the scanner
fed them through the Instaloader path, where `node.edge_media_to_caption`
and `checkIsStory`'s `product_type` are both absent, so nothing happened.

They are now recognised structurally -- flat, with post_shortcode and
type, and none of the markers the other two JSON shapes carry -- and used
for three things:

- `type` sets post.isReel, which post-tabs prefers over every fallback.
  This is Instagram's own classification and it disagrees with ours a
  lot: of 781 items in "official_artms - reels", the sidecars say only
  360 are reels. The other 421 are feed videos the clips endpoint returns
  via include_feed_video, and the directory-based rule counted them all.
- `description` fills the caption where no .txt exists.
- `date` dates a post whose filename could not.

Also fixes date precedence. Only JDownloader highlights lack a date in
the filename, so parseArchiveFilename now marks those as mtime-derived
and the scanner lets any real date replace them -- previously the date
depended on which file the scan reached first.

Verified against real published files: a directory of three type=post and
three type=reel renders 6 in the grid and exactly the 3 reels in the
Reels tab.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
2026-08-17 12:42:54 -04:00
co-authored by Claude Opus 5
parent 89bd5346db
commit 53b1f80e1d
9 changed files with 308 additions and 5 deletions
+82
View File
@@ -0,0 +1,82 @@
import { describe, expect, it } from 'vitest';
import {
GalleryDlSidecar, isGalleryDlSidecar, sidecarDate, sidecarIsReel, sidecarSource,
} from './gallery-dl-sidecar';
// Trimmed from real files published to the archive on 2026-08-16.
const REEL: GalleryDlSidecar = {
post_shortcode: 'Db-lNCoib9m', post_id: '3962768346034323302', type: 'reel',
date: '2026-08-13 11:00:44', post_date: '2026-08-13 11:00:44',
username: 'official_band', fullname: 'Official ARTMS',
description: 'Dancing in the spotlight', count: 1, likes: 22914,
};
const FEED_VIDEO: GalleryDlSidecar = { ...REEL, post_shortcode: 'DbdG9L9jU4m', type: 'post', count: 2 };
const HIGHLIGHT: GalleryDlSidecar = {
post_shortcode: 'BATVdRZi_3', post_id: '18099435932626935', type: 'highlight',
date: '2026-08-08 16:22:09', username: 'official_band', count: 154,
};
describe('isGalleryDlSidecar', () => {
it('accepts a real sidecar', () => {
expect(isGalleryDlSidecar(REEL)).toBe(true);
expect(isGalleryDlSidecar(HIGHLIGHT)).toBe(true);
});
it('rejects an Instaloader GraphQL payload', () => {
expect(isGalleryDlSidecar({ node: { __typename: 'GraphVideo', shortcode: 'x' } })).toBe(false);
expect(isGalleryDlSidecar({ __typename: 'GraphImage', post_shortcode: 'x', type: 'post' })).toBe(false);
});
it('rejects an Instagram export manifest', () => {
expect(isGalleryDlSidecar({ media: [{ uri: 'a.jpg' }] })).toBe(false);
expect(isGalleryDlSidecar([{ media: [] }])).toBe(false);
});
it('rejects junk', () => {
for (const v of [null, undefined, 0, '', 'string', {}, { post_shortcode: 'x' }]) {
expect(isGalleryDlSidecar(v)).toBe(false);
}
});
});
describe('sidecarDate', () => {
it('takes the day from the timestamp', () => {
expect(sidecarDate(REEL)).toBe('2026-08-13');
});
it('falls back to post_date', () => {
expect(sidecarDate({ post_shortcode: 'x', post_date: '2024-01-02 03:04:05' })).toBe('2024-01-02');
});
it('returns empty when there is no usable date', () => {
expect(sidecarDate({ post_shortcode: 'x' })).toBe('');
expect(sidecarDate({ post_shortcode: 'x', date: 'not a date' })).toBe('');
});
});
describe('sidecarIsReel', () => {
it('distinguishes a reel from an ordinary feed video', () => {
// Both are single mp4s -- the lone-video heuristic cannot tell them apart.
expect(sidecarIsReel(REEL)).toBe(true);
expect(sidecarIsReel(FEED_VIDEO)).toBe(false);
});
it('declines to answer for stories and highlights', () => {
expect(sidecarIsReel(HIGHLIGHT)).toBeUndefined();
expect(sidecarIsReel({ post_shortcode: 'x', type: 'story' as const })).toBeUndefined();
expect(sidecarIsReel({ post_shortcode: 'x' })).toBeUndefined();
});
});
describe('sidecarSource', () => {
it('maps type onto the archive source kinds', () => {
expect(sidecarSource(REEL)).toBe('reels');
expect(sidecarSource(FEED_VIDEO)).toBe('posts');
expect(sidecarSource(HIGHLIGHT)).toBe('highlight');
expect(sidecarSource({ post_shortcode: 'x', type: 'story' as const })).toBe('stories');
});
it('is undefined for an unknown type', () => {
expect(sidecarSource({ post_shortcode: 'x' })).toBeUndefined();
});
});