c3b-assets 0.3.0 → 0.5.0

package/README.md

@@ -1,7 +1,7 @@
 # c3b-assets
 
-Fingerprints a project's images and syncs them to a [Bunny](https://bunny.net) storage zone, so images never live in
-git and never need uploading by hand. Writes `d8e-asset-manifest.json`, which [d8e](https://codeberg.org/colab47/d8e)
+Fingerprints a project's images, audio and video and syncs them to a [Bunny](https://bunny.net) storage zone, so
+media never lives in git and never needs uploading by hand. Writes `d8e-asset-manifest.json`, which [d8e](https://codeberg.org/colab47/d8e)
 (1.2.0+) uses to point every reference at the CDN.
 
 ## How it works
@@ -23,7 +23,8 @@ images out of `dist/`.
 
 It only ever lists, uploads to and deletes inside the zone's `colab-asset-manager/` folder (the tool's old name,
 kept so existing zones need no re-upload) — files uploaded by hand anywhere else in the zone are never touched.
-Supported: `avif`, `gif`, `jpeg`, `jpg`, `png`, `svg`, `webp`.
+Supported: images `avif`, `gif`, `jpeg`, `jpg`, `png`, `svg`, `webp`; audio `mp3`, `m4a`, `ogg`, `wav`; video `mp4`,
+`webm`. Anything else under `src/asset/` (fonts, say) stays in git and in `dist/`.
 
 It runs on your machine only, never at deploy: the storage key stays off Heroku and Vercel, and staging can't delete
 production's images.
@@ -51,7 +52,7 @@ npm install -g c3b-assets@latest
   `uk.`, `ny.`, `la.`, `sg.`, `se.`, `br.`, `jh.` (Johannesburg) or `syd.storage.bunnycdn.com`.
 - `cdnUrl`: the pull zone connected to that storage zone.
 
-### 3. Gitignore the images
+### 3. Gitignore the media
 
 ```
 src/asset/**/*.avif
@@ -61,6 +62,12 @@ src/asset/**/*.jpg
 src/asset/**/*.png
 src/asset/**/*.svg
 src/asset/**/*.webp
+src/asset/**/*.mp3
+src/asset/**/*.m4a
+src/asset/**/*.ogg
+src/asset/**/*.wav
+src/asset/**/*.mp4
+src/asset/**/*.webm
 ```
 
 If the images are already committed, also run `git rm -r --cached src/asset` once (it keeps your local copies). Their
@@ -77,9 +84,16 @@ your shell profile or a password manager — never in the repo.
 c3b-assets             # status: src/asset/ against the manifest — new, changed, missing, retired. Changes nothing, no key needed
 c3b-assets u           # upload: fingerprint, upload new images, write d8e-asset-manifest.json (deletes need --allow-removals)
 c3b-assets s           # sync: download the images the manifest lists that are missing locally, then upload as "u"
+c3b-assets a           # adopt: no manifest yet (a repo started over)? rebuild it from what the zone holds, then download
 c3b-assets --help      # the commands and flags
 ```
 
+`a` is for a checkout that has no `d8e-asset-manifest.json` but whose zone already has the images — a repo
+started over, or a project joining an existing zone: it lists the tool's folder in the zone, reads every stored
+image back to its manifest key (`colab-asset-manager/arch/x.2ed3ab61.webp` → `asset/arch/x.webp`), writes the
+manifest and downloads as `s` does. A key stored under several fingerprints keeps the most recently changed copy
+and retires the rest from today. It refuses to run over an existing manifest.
+
 Flags: `--dry-run` (report, change nothing), `--allow-removals` (see Safety checks). The version is printed first, so
 you can tell which install is running.
 
@@ -112,7 +126,7 @@ into `src/asset/` (`c3b-assets s` on each) and run `c3b-assets u` again — it r
   those deletions is deleted with them (Bunny keeps empty folders otherwise).
 - Only files this project's manifest has listed are ever retired or deleted. If two projects share a storage zone,
   neither touches the other's images.
-- The download step of `s` only fetches image files, and only from this project's `cdnUrl` folder — the manifest is
+- The download step of `s` only fetches image, audio and video files, and only from this project's `cdnUrl` folder — the manifest is
   a committed file, so a tampered entry can't plant something else in `src/asset/`.
 - `storageHost` must be a Bunny storage endpoint (`storage.bunnycdn.com`, optionally region-prefixed): the storage
   key is sent to it, and the config is committed.

package/adopt.js

@@ -0,0 +1,34 @@
+// `c3b-assets a` (adopt): the manifest rebuilt from what the zone holds, for a checkout that has
+// none — a repo started over, or a project joining a zone that already has its images. Every
+// file under the tool's folder is read back to its manifest key: colab-asset-manager/arch/x.2ed3ab61.webp
+// is asset/arch/x.webp at ${ cdnUrl }/colab-asset-manager/arch/x.2ed3ab61.webp. Only images; a
+// key stored under more than one fingerprint keeps the most recently changed copy and retires
+// the rest from today, as an upload would have.
+export function manifestFromZone(entries, { cdnUrl, folder, assetExtensions, today }) {
+    const chosen = new Map();
+    const retired = {};
+    const skipped = [];
+
+    for (const entry of entries) {
+        const match = entry.path.match(/^(.*)\.([0-9a-f]{8})\.([^./]+)$/);
+        if (!match || !assetExtensions.includes(match[3].toLowerCase()) || !entry.path.startsWith(`${ folder }/`)) {
+            skipped.push(entry.path);
+            continue;
+        }
+        const key = `asset/${ match[1].slice(folder.length + 1) }.${ match[3] }`;
+        const current = chosen.get(key);
+        if (!current) {
+            chosen.set(key, entry);
+        } else if ((entry.changed ?? '') > (current.changed ?? '')) {
+            retired[current.path] = today;
+            chosen.set(key, entry);
+        } else {
+            retired[entry.path] = today;
+        }
+    }
+
+    const assets = Object.fromEntries([...chosen].sort(([a], [b]) => a.localeCompare(b))
+            .map(([key, entry]) => [key, `${ cdnUrl }/${ encodeURI(entry.path) }`]));
+
+    return { assets, retired: Object.fromEntries(Object.entries(retired).sort(([a], [b]) => a.localeCompare(b))), skipped };
+}

package/bunny.js

@@ -13,8 +13,9 @@ export function createStorage({ host, zone, accessKey }) {
         });
     }
 
-    // Every file under `folder`, as paths relative to the zone root (e.g. colab-asset-manager/asset/logo.1a2b3c4d.svg).
-    async function listFiles(folder) {
+    // Every file under `folder`, with when it last changed, as paths relative to the zone root
+    // (e.g. colab-asset-manager/asset/logo.1a2b3c4d.svg).
+    async function listEntries(folder) {
         const response = await request('GET', folder + '/');
         // a folder that doesn't exist yet just means nothing has been uploaded
         if (response.status === 404) {
@@ -28,15 +29,19 @@ export function createStorage({ host, zone, accessKey }) {
         for (const entry of await response.json()) {
             const path = folder + '/' + entry.ObjectName;
             if (entry.IsDirectory) {
-                files.push(...await listFiles(path));
+                files.push(...await listEntries(path));
             } else {
-                files.push(path);
+                files.push({ path, changed: entry.LastChanged ?? null });
             }
         }
 
         return files;
     }
 
+    async function listFiles(folder) {
+        return (await listEntries(folder)).map((entry) => entry.path);
+    }
+
     async function upload(path, content) {
         // Bunny rejects the upload if the stored bytes don't match this, so a truncated upload can't
         // end up being served from a URL that's cached forever.
@@ -58,5 +63,5 @@ export function createStorage({ host, zone, accessKey }) {
         }
     }
 
-    return { listFiles, upload, remove };
+    return { listEntries, listFiles, upload, remove };
 }

package/c3b-assets.js

@@ -4,13 +4,14 @@ import { existsSync, globSync, mkdirSync, readFileSync, writeFileSync } from 'fs
 import { basename, dirname, extname, join, relative, resolve, sep } from 'path';
 import { fileURLToPath } from 'url';
 import { createStorage } from './bunny.js';
+import { manifestFromZone } from './adopt.js';
 
 // Printed first so it's obvious which installed version is running (same as d8e does).
 const packageJsonPath = join(dirname(fileURLToPath(import.meta.url)), 'package.json');
 const { version } = JSON.parse(readFileSync(packageJsonPath, 'utf8'));
 console.log(`c3b-assets version: ${ version }`);
 
-// Fingerprints every image under src/asset/, uploads the ones Bunny doesn't have yet, and writes
+// Fingerprints every image, audio and video file under src/asset/, uploads the ones Bunny doesn't have yet, and writes
 // d8e-asset-manifest.json (asset path under src/ -> CDN URL) for d8e to rewrite references with.
 // Files in Bunny that nothing references any more are deleted once they've been unreferenced
 // for GRACE_DAYS — pages already in browser caches, sent emails and older staging builds still
@@ -23,7 +24,9 @@ const SRC = resolve('src');
 const ASSET_DIR = resolve(SRC, 'asset');
 const CONFIG = resolve('c3b-assets.json');
 const MANIFEST = resolve('d8e-asset-manifest.json');
-const IMAGE_EXTENSIONS = ['avif', 'gif', 'jpeg', 'jpg', 'png', 'svg', 'webp'];
+// what c3b-assets manages: images, audio and video; anything else under src/asset/ (fonts, say)
+// stays in git and in dist/
+const ASSET_EXTENSIONS = ['avif', 'gif', 'jpeg', 'jpg', 'png', 'svg', 'webp', 'mp3', 'm4a', 'ogg', 'wav', 'mp4', 'webm'];
 
 // Everything c3b-assets uploads lives under this folder in the storage zone, and it only ever
 // lists or deletes inside it — files uploaded by hand elsewhere in the zone are never touched.
@@ -36,8 +39,9 @@ const DAY_MS = 24 * 60 * 60 * 1000;
 // The commands and flags the tool accepts, each with its one-line description. `--help` prints them;
 // anything not listed here is rejected rather than silently ignored.
 const COMMANDS = {
-    'u': 'upload: fingerprint src/asset/, upload new images, write d8e-asset-manifest.json, delete retired files',
-    's': 'sync: download images the manifest lists that are missing locally, then upload (as "u")'
+    'u': 'upload: fingerprint src/asset/, upload new files, write d8e-asset-manifest.json, delete retired files',
+    's': 'sync: download files the manifest lists that are missing locally, then upload (as "u")',
+    'a': 'adopt: for a checkout with no manifest, rebuild d8e-asset-manifest.json from what the zone holds, then download'
 };
 const FLAGS = {
     '--dry-run': 'report what would be uploaded, downloaded, deleted and written, change nothing',
@@ -118,7 +122,7 @@ function readConfig() {
 // Bunny. The fingerprint comes from the content, so changing an image always gives it a new name.
 function scanImages() {
     const images = [];
-    for (const file of globSync(`${ ASSET_DIR }/**/*.{${ IMAGE_EXTENSIONS.join(',') }}`)) {
+    for (const file of globSync(`${ ASSET_DIR }/**/*.{${ ASSET_EXTENSIONS.join(',') }}`)) {
         const content = readFileSync(file);
         const hash = fingerprint(content);
         const ext = extname(file);
@@ -210,7 +214,7 @@ function requireStorageKey() {
 function status() {
     console.log(`zone ${ config.storageZone } -> ${ config.cdnUrl }`);
     if (!existsSync(ASSET_DIR)) {
-        console.log(`${ ASSET_DIR } not found — run "c3b-assets s" to download the manifest's images`);
+        console.log(`${ ASSET_DIR } not found — run "c3b-assets s" to download the manifest's files`);
 
         return;
     }
@@ -221,7 +225,7 @@ function status() {
     const retired = Object.entries(previous.retired ?? {});
     const due = retired.filter(([, since]) => (Date.now() - new Date(since)) / DAY_MS >= GRACE_DAYS).length;
 
-    console.log(`${ images.length } images in src/asset/, ${ Object.keys(previous.assets ?? {}).length } in the manifest`);
+    console.log(`${ images.length } files in src/asset/, ${ Object.keys(previous.assets ?? {}).length } in the manifest`);
     for (const key of added) {
         console.log(`  new      ${ key }`);
     }
@@ -239,10 +243,10 @@ function status() {
     if (toUpload === 0 && missing.length === 0 && due === 0) {
         console.log('Everything in src/asset/ is uploaded and in the manifest.');
     } else if (missing.length > 0) {
-        console.log(`Run "c3b-assets s" to download ${ missing.length } missing image(s)`
+        console.log(`Run "c3b-assets s" to download ${ missing.length } missing file(s)`
                 + (toUpload > 0 ? ` and upload ${ toUpload }.` : '.'));
     } else {
-        console.log(`Run "c3b-assets u" to upload ${ toUpload } image(s)`
+        console.log(`Run "c3b-assets u" to upload ${ toUpload } file(s)`
                 + (due > 0 ? `, with --allow-removals to delete ${ due } retired file(s).` : '.'));
     }
 }
@@ -261,7 +265,7 @@ async function upload(accessKey) {
     const localKeys = new Set(images.map((image) => image.key));
     const missing = Object.keys(previous.assets ?? {}).filter((key) => !localKeys.has(key));
     if (missing.length > 0 && !allowRemovals) {
-        fail(`${ missing.length } image(s) in the manifest aren't in src/asset/ (e.g. ${ missing[0] }). `
+        fail(`${ missing.length } file(s) in the manifest aren't in src/asset/ (e.g. ${ missing[0] }). `
                 + 'Run "c3b-assets s" to download them, or add --allow-removals if you removed them on purpose.');
     }
 
@@ -282,7 +286,7 @@ async function upload(accessKey) {
                 + 'Add --allow-removals to delete them from Bunny, once this branch is what production serves.');
     }
 
-    console.log(`${ images.length } images, ${ toUpload.length } to upload, ${ toDelete.length } to delete, `
+    console.log(`${ images.length } files, ${ toUpload.length } to upload, ${ toDelete.length } to delete, `
             + `${ Object.keys(retired).length } waiting out the ${ GRACE_DAYS }-day grace period`);
 
     for (const image of toUpload) {
@@ -387,9 +391,9 @@ async function pullImages() {
             fail(`refusing to write outside src/asset/: ${ key }`);
         }
         // The manifest is a committed file, so what it points at is only trusted as far as this
-        // project's own CDN folder, and only ever written as an image.
-        if (!IMAGE_EXTENSIONS.includes(extname(key).slice(1).toLowerCase())) {
-            fail(`refusing to download ${ key }: not an image`);
+        // project's own CDN folder, and only ever written as an image, audio or video file.
+        if (!ASSET_EXTENSIONS.includes(extname(key).slice(1).toLowerCase())) {
+            fail(`refusing to download ${ key }: not an image, audio or video file`);
         }
         if (remotePathOf(url) === null) {
             fail(`refusing to download ${ key } from outside ${ CDN_PREFIX }: ${ url }`);
@@ -432,8 +436,35 @@ async function pullImages() {
             + (dryRun ? ' — dry run, nothing written' : ''));
 }
 
+// A checkout with no manifest (a repo started over) adopts what the zone already holds: the
+// manifest is rebuilt from the zone's listing and the images downloaded as "s" would.
+async function adopt() {
+    if (existsSync(MANIFEST)) {
+        fail('d8e-asset-manifest.json already exists — "a" is for a checkout without one; use "s" to sync');
+    }
+    const storage = createStorage({ host: config.storageHost, zone: config.storageZone, accessKey: requireStorageKey() });
+    const entries = await storage.listEntries(FOLDER);
+    const today = new Date().toISOString().slice(0, 10);
+    const manifest = manifestFromZone(entries, { cdnUrl: config.cdnUrl, folder: FOLDER, assetExtensions: ASSET_EXTENSIONS, today });
+
+    for (const key of Object.keys(manifest.assets)) {
+        console.log(`  adopt   ${ key }`);
+    }
+    for (const path of manifest.skipped) {
+        console.log(`  skip    ${ path } (not an image c3b-assets stored)`);
+    }
+    console.log(`${ Object.keys(manifest.assets).length } image(s) on Bunny, ${ Object.keys(manifest.retired).length } older copies retired`
+            + (dryRun ? ' — dry run, nothing written' : ''));
+    if (dryRun) {
+        return;
+    }
+    writeFileSync(MANIFEST, JSON.stringify({ assets: manifest.assets, retired: manifest.retired }, null, 2) + '\n');
+    await pullImages();
+}
+
 // Bunny API errors (wrong key, wrong zone or region) print as one line rather than a stack trace
 const run = command === 'u' ? () => upload(requireStorageKey())
         : command === 's' ? sync
-                : async () => status();
+                : command === 'a' ? adopt
+                        : async () => status();
 run().catch((error) => fail(error.message));

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "c3b-assets",
-  "version": "0.3.0",
+  "version": "0.5.0",
   "description": "Fingerprints a project's images and syncs them to a Bunny storage zone, writing the d8e-asset-manifest.json d8e reads.",
   "license": "GPL-3.0",
   "type": "module",
@@ -9,7 +9,8 @@
   },
   "files": [
     "c3b-assets.js",
-    "bunny.js"
+    "bunny.js",
+    "adopt.js"
   ],
   "engines": {
     "node": ">=22"