Fix: Serve promoted images with a + without redirecting

Rule conditions see the original path, so chained rules can't encode +s. One
rule per number of +s does it instead, which only fits the free plan's 10
rules if they're shared by all sites, so static files now live under their
hostname (/free.direct-img.link/1/orange%2Bcat).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

.gitignore

@@ -2,6 +2,4 @@ node_modules/
 .wrangler/
 # Filled by scripts/promote.js before each deploy
 promoted/
-public/web/
+public/*direct-img.link/
-public/free/
-public/ai/

README.md

@@ -303,18 +303,20 @@ Every request runs the Worker, which counts toward the free plan's 100,000 reque
 
 - Views come from Cloudflare's zone analytics over the last 7 days, which count static files too, so a promoted image that stops being viewed drops out
 - The top 19,900 with at least `MIN_VIEWS` (20) are promoted, up to `MAX_BYTES` (4 GB) in total. The free plan allows 20,000 static files per deploy
-- Only JPEG, PNG, GIF and WebP are promoted. Static files get their type from their extension, which these have none of, so `public/_headers` declares them all `image/jpeg`, and browsers detect these four formats from the bytes anyway
+- Only JPEG, PNG, GIF and WebP are promoted, and only queries of up to 8 words (see below). Static files get their type from their extension, which these have none of, so `public/_headers` declares them all `image/jpeg`, and browsers detect these four formats from the bytes anyway
 - Images are cached between runs (Actions cache), so only newly promoted ones download from R2
 - An image is dropped once it's 90 days old, the same as the R2 lifecycle rule, so a popular query (e.g. `current us president`) is still searched again instead of staying static forever. It's promoted again the next day if it's still popular
 
-Static files ignore query strings, so a URL Rewrite Rule (`scripts/rules.js`) turns each site's bare queries into their static file's path first. The visitor's URL doesn't change:
+Static files ignore query strings and are shared by all three hostnames, so URL Rewrite Rules (`scripts/rules.js`) turn each bare query into its static file's path, under its hostname, first. The visitor's URL doesn't change:
 
 | Request | Looked up as |
 |---|---|
-| `direct-img.link/orange+cat` | `/web/1/orange%2Bcat` (lowercased, `+` encoded like the file's name) |
+| `direct-img.link/orange+cat` | `/direct-img.link/1/orange%2Bcat` (lowercased, `+` encoded like the file's name) |
-| `free.direct-img.link/Orange+Cat` | `/free/1/orange%2Bcat` |
+| `free.direct-img.link/Orange+Cat` | `/free.direct-img.link/1/orange%2Bcat` |
 
-A promoted file there serves it; otherwise the Worker gets the request, unfolds the path and handles it as before. Requests with any params (`?i=`, `?src=`), a literal `+` (`%2B`) or a trailing slash aren't rewritten and always go to the Worker. Analytics has no query string, so `?i=` views count toward the query's `?i=1`, and only `?i=1` is promoted. The free plan has no `regex_replace`, so the rule encodes up to 10 `+`s; a longer query's static file answers with one extra (free) redirect.
+A promoted file there serves it; otherwise the Worker gets the request, unfolds the path and handles it as before. Requests with any params (`?i=`, `?src=`), a literal `+` (`%2B`) or a trailing slash aren't rewritten and always go to the Worker. Analytics has no query string, so `?i=` views count toward the query's `?i=1`, and only `?i=1` is promoted.
+
+A rule's condition sees the original path, and the free plan has no `regex_replace` and allows one `wildcard_replace` per rule, so there's one rule per number of `+`s (0–7, 8 of the plan's 10). Queries of 9+ words are never promoted.
 
 ### KV: `DIRECT_IMG_CACHE`
 

public/_headers

@@ -1,14 +1,14 @@
 # Promoted images (scripts/promote.js) have no file extension, so they'd go out without a Content-Type. Browsers detect
 # JPEG, PNG, GIF and WebP from the bytes whatever type is declared, so promote.js promotes only those.
-/web/*
+/direct-img.link/*
   Content-Type: image/jpeg
   Cache-Control: public, max-age=604800
   Access-Control-Allow-Origin: *
-/free/*
+/free.direct-img.link/*
   Content-Type: image/jpeg
   Cache-Control: public, max-age=604800
   Access-Control-Allow-Origin: *
-/ai/*
+/ai.direct-img.link/*
   Content-Type: image/jpeg
   Cache-Control: public, max-age=604800
   Access-Control-Allow-Origin: *

scripts/notify.js

@@ -31,11 +31,10 @@ if (r.workers) {
 }
 if (r.workersError) lines.push(`**Worker requests:** couldn't read (${esc(r.workersError)})`);
 
-// web/2/orange+cat → [orange cat](https://direct-img.link/orange+cat?i=2), so each opens on its site
+// free.direct-img.link/1/orange+cat → [orange cat](https://free.direct-img.link/orange+cat) (free), so each opens on its site
-const zone = env.ZONE || "direct-img.link";
 const link = id => {
-  const [f, i, name] = id.split("/");
+  const [host, , name] = id.split("/"), site = host.split(".").length > 2 && host.split(".")[0];
-  return `[${esc(name.replaceAll("+", " "))}](https://${f === "web" ? "" : `${f}.`}${zone}/${name}${i > 1 ? `?i=${i}` : ""})${i > 1 ? ` i=${i}` : ""}${f === "web" ? "" : ` (${f})`}`;
+  return `[${esc(name.replaceAll("+", " "))}](https://${host}/${name})${site ? ` (${site})` : ""}`;
 };
 
 const failed = env.STATUS !== "success";

scripts/promote.js

@@ -4,7 +4,7 @@
 // promoted/report.json for scripts/notify.js. promoted/ is kept between runs (Actions cache), so only new images download.
 import { mkdir, readFile, writeFile, link, rm, readdir } from "node:fs/promises";
 import { dirname } from "node:path";
-import { TTL_SECONDS, siteOf, folder, normalizeQuery, cacheKey, r2Key } from "../src/_utils/keys.js";
+import { TTL_SECONDS, MAX_PLUSES, siteOf, normalizeQuery, cacheKey, r2Key } from "../src/_utils/keys.js";
 import { parseFreeSource } from "../src/_utils/free.js";
 import { parseAiSource } from "../src/_utils/ai.js";
 
@@ -46,9 +46,9 @@ async function parse(host, path) {
   const site = siteOf(host), m = path.match(/^\/([^/.]+)$/), query = m && normalizeQuery(m[1]);
   if (!query || query.length > 200) return null;
   const name = query.replaceAll(" ", "+");
-  if (BAD_NAME.test(query) || Buffer.byteLength(name) > 200) return null;
+  if (BAD_NAME.test(query) || Buffer.byteLength(name) > 200 || name.split("+").length > MAX_PLUSES + 1) return null;
   const src = site === "free" ? parseFreeSource(new URLSearchParams()) : site === "ai" ? parseAiSource(new URLSearchParams()) : null;
-  return { id: `${folder(site)}/1/${name}`, r2: await r2Key(site, cacheKey(site, src, 1, query)) };
+  return { id: `${host}/1/${name}`, r2: await r2Key(site, cacheKey(site, src, 1, query)) };
 }
 
 // Views per image over the last DAYS: one query per host and day, since a query returns at most 10,000 rows. Only 200s
@@ -150,8 +150,8 @@ for (let k = 0; k < ranked.length; k += 4) {
   if (got.some(g => !g.cached)) await sleep(1200 - (Date.now() - started));
 }
 
-// public/<folder>/ holds only this run's images, hard-linked from the cache so they aren't stored twice
+// public/<hostname>/ holds only this run's images, hard-linked from the cache so they aren't stored twice
-for (const f of ["web", "free", "ai"]) await rm(`${OUT}/${f}`, { recursive: true, force: true });
+for (const h of HOSTS) await rm(`${OUT}/${h}`, { recursive: true, force: true });
 for (const id of Object.keys(chosen)) {
   await mkdir(dirname(`${OUT}/${id}`), { recursive: true });
   await link(`${CACHE}/files/${id}`, `${OUT}/${id}`);

scripts/rules.js

@@ -1,25 +1,27 @@
-// Sets the zone's URL Rewrite Rules that turn a bare query into its site's static file path (/orange+cat →
+// Sets the zone's URL Rewrite Rules that turn a bare query into its static file's path, under its hostname
-// /web/1/orange%2Bcat), so a promoted image is served without running the worker and the visitor's URL doesn't change.
+// (free.direct-img.link/Orange+Cat → /free.direct-img.link/1/orange%2Bcat), so a promoted image is served without
-// +s become %2B (the static file's own encoding), since a + would get a redirect to it. Replaces only rules it made.
+// running the worker and the visitor's URL doesn't change. +s become %2B (the static file's own encoding), since a +
+// would get a redirect to it. Replaces only the rules it made earlier.
 //   node scripts/rules.js direct-img.link free.direct-img.link ai.direct-img.link
 // With no hostnames it removes them. Needs CLOUDFLARE_API_TOKEN with Zone > Transform Rules edit.
-import { siteOf, folder } from "../src/_utils/keys.js";
+import { MAX_PLUSES } from "../src/_utils/keys.js";
 
 const env = process.env, hosts = process.argv.slice(2), ZONE = env.ZONE || "direct-img.link", TAG = "direct-img fold:";
-const PHASE = "http_request_transform";
+const PHASE = "http_request_transform", PATH = "http.request.uri.path";
 const api = (path, init) => fetch(`https://api.cloudflare.com/client/v4${path}`, { ...init, headers: { Authorization: `Bearer ${env.CLOUDFLARE_API_TOKEN}`, "Content-Type": "application/json" } }).then(r => r.json());
 // A bare query with no params: not the homepage, assets/, robots.txt or an already folded path. A literal + (%2B) is
 // left to the worker, since a static file's %2B stands for a space.
-const BARE = 'http.request.uri.query eq "" and http.request.uri.path ne "/" and not http.request.uri.path contains "." and not http.request.uri.path wildcard "/*/*" and not lower(http.request.uri.path) contains "%2b"';
+const BARE = `http.host in {${hosts.map(h => JSON.stringify(h)).join(" ")}} and http.request.uri.query eq "" and ${PATH} ne "/" and not ${PATH} contains "." and not ${PATH} wildcard "/*/*" and not lower(${PATH}) contains "%2b"`;
-// Each wildcard_replace encodes one + (the free plan has no regex_replace); a query with more keeps a redirect
+const pluses = n => `"${"*+".repeat(n)}*"`;
-const path = Array.from({ length: 10 }).reduce(e => `wildcard_replace(${e}, "*+*", "\${1}%2B\${2}")`, "lower(http.request.uri.path)");
 
-const mine = Object.entries(Object.groupBy(hosts, h => folder(siteOf(h)))).map(([f, hs]) => ({
+// A rule's condition sees the original path, and the free plan has no regex_replace and allows one wildcard_replace per
-  description: `${TAG} ${f} bare query → /${f}/1/`,
+// rule, so each rule handles an exact number of +s; a query with more always runs the worker
-  expression: `http.host in {${hs.map(h => JSON.stringify(h)).join(" ")}} and ${BARE}`,
+const mine = hosts.length ? Array.from({ length: MAX_PLUSES + 1 }, (_, n) => ({
+  description: `${TAG} bare query with ${n} +`,
+  expression: `${BARE} and ${n ? `${PATH} wildcard ${pluses(n)}` : `not ${PATH} contains "+"`} and not ${PATH} wildcard ${pluses(n + 1)}`,
   action: "rewrite",
-  action_parameters: { uri: { path: { expression: `concat("/${f}/1", ${path})` } } },
+  action_parameters: { uri: { path: { expression: `concat("/", http.host, "/1", ${n ? `wildcard_replace(lower(${PATH}), ${pluses(n)}, "${Array.from({ length: n }, (_, k) => `\${${k + 1}}%2B`).join("")}\${${n + 1}}")` : `lower(${PATH})`})` } } },
-}));
+})) : [];
 
 const zone = (await api(`/zones?name=${ZONE}`)).result[0].id;
 const others = ((await api(`/zones/${zone}/rulesets/phases/${PHASE}/entrypoint`)).result?.rules || [])

src/_utils/keys.js

@@ -13,9 +13,8 @@ export const MAX_INDEX = { "": 40, free: 20, ai: 1000 };
 // "free", "ai" or "" (main site), from the hostname's first label
 export const siteOf = hostname => ["free", "ai"].find(s => hostname.startsWith(`${s}.`)) || "";
 
-// Path prefix each site's ?i= is folded into by the zone's URL Rewrite and Redirect Rules (scripts/rules.js), e.g.
+// Most +s in a query the zone's URL Rewrite Rules (scripts/rules.js) can turn into a static file's path, one rule each
-// /orange+cat?i=2 → /web/2/orange+cat, so promoted images can be static files, which ignore query strings
+export const MAX_PLUSES = 7;
-export const folder = site => site || "web";
 
 export function normalizeQuery(path) {
   const clean = s => s.toLowerCase().trim().replace(/[\x00-\x1f]/g, "").replace(/\/+$/, "").replace(/\s+/g, " ");

src/worker.js

@@ -4,7 +4,7 @@ import { freeImageUrls, parseFreeSource, FREE_UA } from "./_utils/free.js";
 import { isFlickrPlaceholder } from "./_utils/flickr.js";
 import { aiImage, parseAiSource, DEFAULT_AI_SOURCE } from "./_utils/ai.js";
 import { surreal } from "./_utils/surreal.js";
-import { TTL_SECONDS, MAX_INDEX, siteOf, folder, normalizeQuery, cacheKey as keyFor, r2Key as r2KeyFor, sha256 } from "./_utils/keys.js";
+import { TTL_SECONDS, MAX_INDEX, siteOf, normalizeQuery, cacheKey as keyFor, r2Key as r2KeyFor, sha256 } from "./_utils/keys.js";
 import * as LIMITS from "../public/assets/rate-limit.js";
 
 // How long a failed search keeps serving bad.webp before the query is searched again
@@ -365,13 +365,14 @@ async function countHit(env, request, query, site, params) {
   } catch {}
 }
 
-// The zone's URL Rewrite (scripts/rules.js) turns a bare query into its site's static file path (/orange+cat →
+// The zone's URL Rewrite Rules (scripts/rules.js) turn a bare query into its static file's path, under its hostname
-// /web/1/orange%2Bcat) so a promoted image is served without running the worker. Unfolded back here, so the rest of the
+// (free.direct-img.link/orange+cat → /free.direct-img.link/1/orange%2Bcat), so a promoted image is served without
-// worker sees the original request: the rule's %2B were +s, since it leaves a query's own %2B unfolded. Other ?i= in the
+// running the worker. Unfolded back here, so the rest of the worker sees the original request: the rules' %2B were +s,
-// path are still accepted (links from when ?i= was folded too). A folded path for another site is rejected like any slash.
+// since they leave a query's own %2B alone. Links from when ?i= was folded too (/free/2/orange+cat) still work. A folded
+// path for another site is rejected like any slash.
 function unfold(url, site) {
-  const m = url.pathname.match(/^\/(web|free|ai)\/([^/]*)\/([^/]+)$/);
+  const m = url.pathname.match(/^\/([^/]+)\/([^/]*)\/([^/]+)$/);
-  if (!m || m[1] !== folder(site)) return url;
+  if (!m || ![url.hostname, site || "web"].includes(m[1])) return url;
   const u = new URL(url);
   u.pathname = `/${m[3].replace(/%2B/gi, "+")}`;
   if (m[2] && m[2] !== "1") u.searchParams.set("i", m[2]);