chore: init

.editorconfig

@@ -0,0 +1,9 @@
+root = true
+
+[*]
+charset = utf-8
+end_of_line = lf
+indent_size = 2
+indent_style = space
+insert_final_newline = true
+trim_trailing_whitespace = true

.gitignore

@@ -0,0 +1,130 @@
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+.pnpm-debug.log*
+
+# Diagnostic reports (https://nodejs.org/api/report.html)
+report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
+
+# Runtime data
+pids
+*.pid
+*.seed
+*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+lib-cov
+
+# Coverage directory used by tools like istanbul
+coverage
+*.lcov
+
+# nyc test coverage
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+bower_components
+
+# node-waf configuration
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+build/Release
+
+# Dependency directories
+node_modules/
+jspm_packages/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+web_modules/
+
+# TypeScript cache
+*.tsbuildinfo
+
+# Optional npm cache directory
+.npm
+
+# Optional eslint cache
+.eslintcache
+
+# Optional stylelint cache
+.stylelintcache
+
+# Microbundle cache
+.rpt2_cache/
+.rts2_cache_cjs/
+.rts2_cache_es/
+.rts2_cache_umd/
+
+# Optional REPL history
+.node_repl_history
+
+# Output of 'npm pack'
+*.tgz
+
+# Yarn Integrity file
+.yarn-integrity
+
+# dotenv environment variable files
+.env
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# parcel-bundler cache (https://parceljs.org/)
+.cache
+.parcel-cache
+
+# Next.js build output
+.next
+out
+
+# Nuxt.js build / generate output
+.nuxt
+dist
+
+# Gatsby files
+.cache/
+# Comment in the public line in if your project uses Gatsby and not Next.js
+# https://nextjs.org/blog/next-9-1#public-directory-support
+# public
+
+# vuepress build output
+.vuepress/dist
+
+# vuepress v2.x temp and cache directory
+.temp
+.cache
+
+# Docusaurus cache and generated files
+.docusaurus
+
+# Serverless directories
+.serverless/
+
+# FuseBox cache
+.fusebox/
+
+# DynamoDB Local files
+.dynamodb/
+
+# TernJS port file
+.tern-port
+
+# Stores VSCode versions used for testing VSCode extensions
+.vscode-test
+
+# yarn v2
+.yarn/cache
+.yarn/unplugged
+.yarn/build-state.yml
+.yarn/install-state.gz
+.pnp.*

README.md

@@ -0,0 +1,3 @@
+# Summerflare
+
+[**Summ**aly](https://github.com/syuilo/summaly) ov**er** the Cloud**flare**

package.json

@@ -0,0 +1,13 @@
+{
+  "packageManager": "pnpm@8.3.1",
+  "devDependencies": {
+    "@cloudflare/workers-types": "^4.20230511.0",
+    "vitest": "^0.31.0",
+    "wrangler": "^2.20.0"
+  },
+  "dependencies": {
+    "hono": "^3.1.8",
+    "html-entities": "^2.3.3",
+    "summaly": "^2.7.0"
+  }
+}

src/index.ts

@@ -0,0 +1,35 @@
+import { Hono } from "hono";
+import summary from "./summary";
+
+export interface Env {
+  // Example binding to KV. Learn more at https://developers.cloudflare.com/workers/runtime-apis/kv/
+  // MY_KV_NAMESPACE: KVNamespace;
+  //
+  // Example binding to Durable Object. Learn more at https://developers.cloudflare.com/workers/runtime-apis/durable-objects/
+  // MY_DURABLE_OBJECT: DurableObjectNamespace;
+  //
+  // Example binding to R2. Learn more at https://developers.cloudflare.com/workers/runtime-apis/r2/
+  // MY_BUCKET: R2Bucket;
+  //
+  // Example binding to a Service. Learn more at https://developers.cloudflare.com/workers/runtime-apis/service-bindings/
+  // MY_SERVICE: Fetcher;
+}
+
+const app = new Hono<Env>();
+
+app.get("/url", async (context) => {
+  let url: URL;
+  try {
+    url = new URL(context.req.query("url")!);
+  } catch (e) {
+    return context.json({ error: "Invalid URL" }, 400);
+  }
+  const response = await fetch(url);
+  const rewriter = new HTMLRewriter();
+  const summarized = summary(url, rewriter);
+  const reader = rewriter.transform(response).body!.getReader();
+  while (!(await reader.read()).done);
+  return context.json(await summarized);
+});
+
+export default app;

src/summary/amazon/description.ts

@@ -0,0 +1,49 @@
+import { decode } from "html-entities";
+import clip from "summaly/built/utils/clip";
+import { BufferedTextHandler, assign } from "../common";
+import type { PrioritizedReference } from "../common";
+
+export default function getDescription(url: URL, html: HTMLRewriter) {
+  const result: PrioritizedReference<string | null> = {
+    bits: 3, // 0-7
+    priority: 0,
+    content: null,
+  };
+  html.on(
+    "#productDescription",
+    new BufferedTextHandler((text) => {
+      assign(result, 7, decode(text));
+    })
+  );
+  html.on('meta[property="og:description"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 3, content);
+      }
+    },
+  });
+  html.on('meta[name="twitter:description"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 2, content);
+      }
+    },
+  });
+  html.on('meta[name="description"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 1, content);
+      }
+    },
+  });
+  return new Promise<string | null>((resolve) => {
+    html.onDocument({
+      end() {
+        resolve(result.content && clip(result.content, 300));
+      },
+    });
+  });
+}

src/summary/amazon/image.ts

@@ -0,0 +1,67 @@
+import { assign, toAbsoluteURL } from "../common";
+import type { PrioritizedReference } from "../common";
+
+export default function getImage(url: URL, html: HTMLRewriter) {
+  const result: PrioritizedReference<string | null> = {
+    bits: 4, // 0-15
+    priority: 0,
+    content: null,
+  };
+  html.on("#landingImage", {
+    element(element) {
+      const content = element.getAttribute("src");
+      if (content) {
+        assign(result, 15, content);
+      }
+    },
+  });
+  html.on('meta[property="og:image"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 7, content);
+      }
+    },
+  });
+  html.on('meta[name="twitter:image"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 6, content);
+      }
+    },
+  });
+  html.on('link[rel="image_src"]', {
+    element(element) {
+      const content = element.getAttribute("href");
+      if (content) {
+        assign(result, 5, content);
+      }
+    },
+  });
+  html.on('link[rel="apple-touch-icon"]', {
+    element(element) {
+      const content = element.getAttribute("href");
+      if (content) {
+        assign(result, 4, content);
+      }
+    },
+  });
+  html.on('link[rel="apple-touch-icon image_src"]', {
+    element(element) {
+      const content = element.getAttribute("href");
+      if (content) {
+        assign(result, 3, content);
+      }
+    },
+  });
+  return new Promise<string | null>((resolve) => {
+    html.onDocument({
+      end() {
+        resolve(
+          result.content ? toAbsoluteURL(result.content, url.href) : null
+        );
+      },
+    });
+  });
+}

src/summary/amazon/index.ts

@@ -0,0 +1,72 @@
+import cleanupTitle from "summaly/built/utils/cleanup-title";
+import getCard from "../general/card";
+import getDescription from "./description";
+import getFavicon from "../general/favicon";
+import getImage from "./image";
+import getPlayerUrlCommon from "../general/playerUrlCommon";
+import getPlayerUrlGeneral from "../general/playerUrlGeneral";
+import getPlayerUrlHeight from "../general/playerUrlHeight";
+import getPlayerUrlWidth from "../general/playerUrlWidth";
+import getSiteName from "../general/siteName";
+import getTitle from "./title";
+import getSensitive from "../general/sensitive";
+
+export default function amazon(url: URL, html: HTMLRewriter) {
+  const card = getCard(url, html);
+  const title = getTitle(url, html);
+  const image = getImage(url, html);
+  const player = Promise.all([
+    card,
+    getPlayerUrlGeneral(url, html),
+    getPlayerUrlCommon(url, html),
+    getPlayerUrlWidth(url, html),
+    getPlayerUrlHeight(url, html),
+  ]).then(([card, general, common, width, height]) => {
+    const url = (card !== "summary_large_image" && general) || common;
+    if (url !== null && width !== null && height !== null) {
+      return {
+        url,
+        width,
+        height,
+      };
+    } else {
+      return {
+        url: null,
+        width: null,
+        height: null,
+      };
+    }
+  });
+  const description = getDescription(url, html);
+  const siteName = getSiteName(url, html);
+  const favicon = getFavicon(url, html);
+  const sensitive = getSensitive(url, html);
+
+  return Promise.all([
+    title,
+    image,
+    player,
+    description,
+    siteName,
+    favicon,
+    sensitive,
+  ]).then(
+    ([title, image, player, description, siteName, favicon, sensitive]) => {
+      if (title === null) {
+        return null;
+      }
+      if (siteName !== null) {
+        title = cleanupTitle(title, siteName);
+      }
+      return {
+        title,
+        image,
+        description: title === description ? null : description,
+        player,
+        sitename: siteName,
+        icon: favicon,
+        sensitive,
+      };
+    }
+  );
+}

src/summary/amazon/title.ts

@@ -0,0 +1,47 @@
+import { decode } from "html-entities";
+import clip from "summaly/built/utils/clip";
+import { BufferedTextHandler, assign } from "../common";
+import type { PrioritizedReference } from "../common";
+
+export default function getTitle(url: URL, html: HTMLRewriter) {
+  const result: PrioritizedReference<string | null> = {
+    bits: 3, // 0-7
+    priority: 0,
+    content: null,
+  };
+  html.on(
+    "#title",
+    new BufferedTextHandler((text) => {
+      assign(result, 7, decode(text));
+    })
+  );
+  html.on('meta[property="og:title"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 3, content);
+      }
+    },
+  });
+  html.on('meta[name="twitter:title"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 2, content);
+      }
+    },
+  });
+  html.on(
+    "title",
+    new BufferedTextHandler((text) => {
+      assign(result, 1, decode(text));
+    })
+  );
+  return new Promise<string | null>((resolve) => {
+    html.onDocument({
+      end() {
+        resolve(result.content && clip(result.content, 100));
+      },
+    });
+  });
+}

src/summary/common.ts

@@ -0,0 +1,34 @@
+export interface PrioritizedReference<T> {
+  bits: number;
+  priority: number;
+  content: T;
+}
+
+export function assign<T>(
+  target: PrioritizedReference<T>,
+  priority: PrioritizedReference<T>["priority"],
+  content: PrioritizedReference<T>["content"]
+): void {
+  if (target.priority <= priority) {
+    target.priority = priority;
+    target.content = content;
+  }
+}
+
+export function toAbsoluteURL(url: string, base: string) {
+  if (/^https?:\/\//.test(url)) {
+    return url;
+  } else {
+    return new URL(url, base).href;
+  }
+}
+
+export class BufferedTextHandler {
+  private buffer = "";
+
+  constructor(private readonly callback: (text: string) => void) {}
+
+  text(text: Text) {
+    this.callback((this.buffer += text.text));
+  }
+}

src/summary/general/card.ts

@@ -0,0 +1,25 @@
+import { assign } from "../common";
+import type { PrioritizedReference } from "../common";
+
+export default function getCard(url: URL, html: HTMLRewriter) {
+  const result: PrioritizedReference<string | null> = {
+    bits: 1, // 0-1
+    priority: 0,
+    content: null,
+  };
+  html.on('meta[property="twitter:card"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 1, content);
+      }
+    },
+  });
+  return new Promise<string | null>((resolve) => {
+    html.onDocument({
+      end() {
+        resolve(result.content);
+      },
+    });
+  });
+}

src/summary/general/description.ts

@@ -0,0 +1,42 @@
+import clip from "summaly/built/utils/clip";
+import { assign } from "../common";
+import type { PrioritizedReference } from "../common";
+
+export default function getDescription(url: URL, html: HTMLRewriter) {
+  const result: PrioritizedReference<string | null> = {
+    bits: 2, // 0-3
+    priority: 0,
+    content: null,
+  };
+  html.on('meta[property="og:description"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 3, content);
+      }
+    },
+  });
+  html.on('meta[name="twitter:description"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 2, content);
+      }
+    },
+  });
+  html.on('meta[name="description"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 1, content);
+      }
+    },
+  });
+  return new Promise<string | null>((resolve) => {
+    html.onDocument({
+      end() {
+        resolve(result.content && clip(result.content, 300));
+      },
+    });
+  });
+}

src/summary/general/favicon.ts

@@ -0,0 +1,33 @@
+import { assign, toAbsoluteURL } from "../common";
+import type { PrioritizedReference } from "../common";
+
+export default function getFavicon(url: URL, html: HTMLRewriter) {
+  const result: PrioritizedReference<string> = {
+    bits: 2, // 0-3
+    priority: 0,
+    content: "/favicon.ico",
+  };
+  html.on('link[rel="shortcut icon"]', {
+    element(element) {
+      const content = element.getAttribute("href");
+      if (content) {
+        assign(result, 3, content);
+      }
+    },
+  });
+  html.on('link[rel="icon"]', {
+    element(element) {
+      const content = element.getAttribute("href");
+      if (content) {
+        assign(result, 2, content);
+      }
+    },
+  });
+  return new Promise<string>((resolve) => {
+    html.onDocument({
+      end() {
+        resolve(toAbsoluteURL(result.content, url.href));
+      },
+    });
+  });
+}

src/summary/general/image.ts

@@ -0,0 +1,59 @@
+import { assign, toAbsoluteURL } from "../common";
+import type { PrioritizedReference } from "../common";
+
+export default function getImage(url: URL, html: HTMLRewriter) {
+  const result: PrioritizedReference<string | null> = {
+    bits: 3, // 0-7
+    priority: 0,
+    content: null,
+  };
+  html.on('meta[property="og:image"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 7, content);
+      }
+    },
+  });
+  html.on('meta[name="twitter:image"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 6, content);
+      }
+    },
+  });
+  html.on('link[rel="image_src"]', {
+    element(element) {
+      const content = element.getAttribute("href");
+      if (content) {
+        assign(result, 5, content);
+      }
+    },
+  });
+  html.on('link[rel="apple-touch-icon"]', {
+    element(element) {
+      const content = element.getAttribute("href");
+      if (content) {
+        assign(result, 4, content);
+      }
+    },
+  });
+  html.on('link[rel="apple-touch-icon image_src"]', {
+    element(element) {
+      const content = element.getAttribute("href");
+      if (content) {
+        assign(result, 3, content);
+      }
+    },
+  });
+  return new Promise<string | null>((resolve) => {
+    html.onDocument({
+      end() {
+        resolve(
+          result.content ? toAbsoluteURL(result.content, url.href) : null
+        );
+      },
+    });
+  });
+}

src/summary/general/index.ts

@@ -0,0 +1,72 @@
+import cleanupTitle from "summaly/built/utils/cleanup-title";
+import getCard from "./card";
+import getDescription from "./description";
+import getFavicon from "./favicon";
+import getImage from "./image";
+import getPlayerUrlCommon from "./playerUrlCommon";
+import getPlayerUrlGeneral from "./playerUrlGeneral";
+import getPlayerUrlHeight from "./playerUrlHeight";
+import getPlayerUrlWidth from "./playerUrlWidth";
+import getSiteName from "./siteName";
+import getTitle from "./title";
+import getSensitive from "./sensitive";
+
+export default function general(url: URL, html: HTMLRewriter) {
+  const card = getCard(url, html);
+  const title = getTitle(url, html);
+  const image = getImage(url, html);
+  const player = Promise.all([
+    card,
+    getPlayerUrlGeneral(url, html),
+    getPlayerUrlCommon(url, html),
+    getPlayerUrlWidth(url, html),
+    getPlayerUrlHeight(url, html),
+  ]).then(([card, general, common, width, height]) => {
+    const url = (card !== "summary_large_image" && general) || common;
+    if (url !== null && width !== null && height !== null) {
+      return {
+        url,
+        width,
+        height,
+      };
+    } else {
+      return {
+        url: null,
+        width: null,
+        height: null,
+      };
+    }
+  });
+  const description = getDescription(url, html);
+  const siteName = getSiteName(url, html);
+  const favicon = getFavicon(url, html);
+  const sensitive = getSensitive(url, html);
+
+  return Promise.all([
+    title,
+    image,
+    player,
+    description,
+    siteName,
+    favicon,
+    sensitive,
+  ]).then(
+    ([title, image, player, description, siteName, favicon, sensitive]) => {
+      if (title === null) {
+        return null;
+      }
+      if (siteName !== null) {
+        title = cleanupTitle(title, siteName);
+      }
+      return {
+        title,
+        image,
+        description: title === description ? null : description,
+        player,
+        sitename: siteName,
+        icon: favicon,
+        sensitive,
+      };
+    }
+  );
+}

src/summary/general/playerUrlCommon.ts

@@ -0,0 +1,43 @@
+import { assign, toAbsoluteURL } from "../common";
+import type { PrioritizedReference } from "../common";
+
+export default function getPlayerUrlCommon(url: URL, html: HTMLRewriter) {
+  const result: PrioritizedReference<string | null> = {
+    bits: 2, // 0-3
+    priority: 0,
+    content: null,
+  };
+  html.on('meta[property="og:video"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 3, content);
+      }
+    },
+  });
+  html.on('meta[property="og:video:secure_url"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 2, content);
+      }
+    },
+  });
+  html.on('meta[property="og:video:url"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 1, content);
+      }
+    },
+  });
+  return new Promise<string | null>((resolve) => {
+    html.onDocument({
+      end() {
+        resolve(
+          result.content ? toAbsoluteURL(result.content, url.href) : null
+        );
+      },
+    });
+  });
+}

src/summary/general/playerUrlGeneral.ts

@@ -0,0 +1,35 @@
+import { assign, toAbsoluteURL } from "../common";
+import type { PrioritizedReference } from "../common";
+
+export default function getPlayerUrlGeneral(url: URL, html: HTMLRewriter) {
+  const result: PrioritizedReference<string | null> = {
+    bits: 2, // 0-3
+    priority: 0,
+    content: null,
+  };
+  html.on('meta[property="twitter:player"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 3, content);
+      }
+    },
+  });
+  html.on('meta[name="twitter:player"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 2, content);
+      }
+    },
+  });
+  return new Promise<string | null>((resolve) => {
+    html.onDocument({
+      end() {
+        resolve(
+          result.content ? toAbsoluteURL(result.content, url.href) : null
+        );
+      },
+    });
+  });
+}

src/summary/general/playerUrlHeight.ts

@@ -0,0 +1,42 @@
+import { assign } from "../common";
+import type { PrioritizedReference } from "../common";
+
+export default function getPlayerUrlHeight(url: URL, html: HTMLRewriter) {
+  const result: PrioritizedReference<string | null> = {
+    bits: 2, // 0-3
+    priority: 0,
+    content: null,
+  };
+  html.on('meta[property="twitter:player:height"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 3, content);
+      }
+    },
+  });
+  html.on('meta[name="twitter:player:height"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 2, content);
+      }
+    },
+  });
+  html.on('meta[property="og:video:height"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 1, content);
+      }
+    },
+  });
+  return new Promise<number | null>((resolve) => {
+    html.onDocument({
+      end() {
+        const content = parseInt(result.content!, 10);
+        resolve(Number.isNaN(content) ? null : content);
+      },
+    });
+  });
+}

src/summary/general/playerUrlWidth.ts

@@ -0,0 +1,42 @@
+import { assign } from "../common";
+import type { PrioritizedReference } from "../common";
+
+export default function getPlayerUrlWidth(url: URL, html: HTMLRewriter) {
+  const result: PrioritizedReference<string | null> = {
+    bits: 2, // 0-3
+    priority: 0,
+    content: null,
+  };
+  html.on('meta[property="twitter:player:width"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 3, content);
+      }
+    },
+  });
+  html.on('meta[name="twitter:player:width"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 2, content);
+      }
+    },
+  });
+  html.on('meta[property="og:video:width"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 1, content);
+      }
+    },
+  });
+  return new Promise<number | null>((resolve) => {
+    html.onDocument({
+      end() {
+        const content = parseInt(result.content!, 10);
+        resolve(Number.isNaN(content) ? null : content);
+      },
+    });
+  });
+}

src/summary/general/sensitive.ts

@@ -0,0 +1,22 @@
+import { assign } from "../common";
+import type { PrioritizedReference } from "../common";
+
+export default function getSensitive(url: URL, html: HTMLRewriter) {
+  const result: PrioritizedReference<boolean> = {
+    bits: 1, // 0-1
+    priority: 0,
+    content: false,
+  };
+  html.on('.tweet[data-possibly-sensitive="true"]', {
+    element() {
+      assign(result, 1, true);
+    },
+  });
+  return new Promise<boolean>((resolve) => {
+    html.onDocument({
+      end() {
+        resolve(result.content);
+      },
+    });
+  });
+}

src/summary/general/siteName.ts

@@ -0,0 +1,33 @@
+import { assign } from "../common";
+import type { PrioritizedReference } from "../common";
+
+export default function getSiteName(url: URL, html: HTMLRewriter) {
+  const result: PrioritizedReference<string | null> = {
+    bits: 2, // 0-3
+    priority: 0,
+    content: url.hostname,
+  };
+  html.on('meta[property="og:site_name"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 3, content);
+      }
+    },
+  });
+  html.on('meta[name="application-name"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 2, content);
+      }
+    },
+  });
+  return new Promise<string | null>((resolve) => {
+    html.onDocument({
+      end() {
+        resolve(result.content);
+      },
+    });
+  });
+}

src/summary/general/title.ts

@@ -0,0 +1,41 @@
+import { decode } from "html-entities";
+import clip from "summaly/built/utils/clip";
+import { BufferedTextHandler, assign } from "../common";
+import type { PrioritizedReference } from "../common";
+
+export default function getTitle(url: URL, html: HTMLRewriter) {
+  const result: PrioritizedReference<string | null> = {
+    bits: 2, // 0-3
+    priority: 0,
+    content: null,
+  };
+  html.on('meta[property="og:title"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 3, content);
+      }
+    },
+  });
+  html.on('meta[name="twitter:title"]', {
+    element(element) {
+      const content = element.getAttribute("content");
+      if (content) {
+        assign(result, 2, content);
+      }
+    },
+  });
+  html.on(
+    "title",
+    new BufferedTextHandler((text) => {
+      assign(result, 1, decode(text));
+    })
+  );
+  return new Promise<string | null>((resolve) => {
+    html.onDocument({
+      end() {
+        resolve(result.content && clip(result.content, 100));
+      },
+    });
+  });
+}

src/summary/index.ts

@@ -0,0 +1,28 @@
+import amazon from "./amazon";
+import general from "./general";
+import wikipedia from "./wikipedia";
+
+export default function summary(url: URL, html: HTMLRewriter) {
+  if (
+    url.hostname === "www.amazon.com" ||
+    url.hostname === "www.amazon.co.jp" ||
+    url.hostname === "www.amazon.ca" ||
+    url.hostname === "www.amazon.com.br" ||
+    url.hostname === "www.amazon.com.mx" ||
+    url.hostname === "www.amazon.co.uk" ||
+    url.hostname === "www.amazon.de" ||
+    url.hostname === "www.amazon.fr" ||
+    url.hostname === "www.amazon.it" ||
+    url.hostname === "www.amazon.es" ||
+    url.hostname === "www.amazon.nl" ||
+    url.hostname === "www.amazon.cn" ||
+    url.hostname === "www.amazon.in" ||
+    url.hostname === "www.amazon.au"
+  ) {
+    return amazon(url, html);
+  }
+  if (`.${url.hostname}`.endsWith(".wikipedia.org")) {
+    return wikipedia(url, html);
+  }
+  return general(url, html);
+}

src/summary/wikipedia/index.ts

@@ -0,0 +1,23 @@
+import clip from "summaly/built/utils/clip";
+
+export default async function wikipedia(url: URL, html: HTMLRewriter) {
+  const lang = url.hostname.split(".")[0];
+  const title = url.pathname.split("/")[2];
+  const response = await fetch(
+    `https://${lang}.wikipedia.org/w/api.php?format=json&action=query&prop=extracts&exintro=&explaintext=&titles=${title}`
+  );
+  const json = await response.json<any>();
+  const info = json.query.pages[Object.keys(json.query.pages)[0]];
+  return {
+    title: info.title,
+    icon: "https://wikipedia.org/static/favicon/wikipedia.ico",
+    description: clip(info.extract, 300),
+    thumbnail: `https://wikipedia.org/static/images/project-logos/${lang}wiki.png`,
+    player: {
+      url: null,
+      width: null,
+      height: null,
+    },
+    sitename: "Wikipedia",
+  };
+}

tsconfig.json

@@ -0,0 +1,105 @@
+{
+	"compilerOptions": {
+		/* Visit https://aka.ms/tsconfig.json to read more about this file */
+
+		/* Projects */
+		// "incremental": true,                              /* Enable incremental compilation */
+		// "composite": true,                                /* Enable constraints that allow a TypeScript project to be used with project references. */
+		// "tsBuildInfoFile": "./",                          /* Specify the folder for .tsbuildinfo incremental compilation files. */
+		// "disableSourceOfProjectReferenceRedirect": true,  /* Disable preferring source files instead of declaration files when referencing composite projects */
+		// "disableSolutionSearching": true,                 /* Opt a project out of multi-project reference checking when editing. */
+		// "disableReferencedProjectLoad": true,             /* Reduce the number of projects loaded automatically by TypeScript. */
+
+		/* Language and Environment */
+		"target": "es2021" /* Set the JavaScript language version for emitted JavaScript and include compatible library declarations. */,
+		"lib": [
+			"es2021"
+		] /* Specify a set of bundled library declaration files that describe the target runtime environment. */,
+		"jsx": "react" /* Specify what JSX code is generated. */,
+		// "experimentalDecorators": true,                   /* Enable experimental support for TC39 stage 2 draft decorators. */
+		// "emitDecoratorMetadata": true,                    /* Emit design-type metadata for decorated declarations in source files. */
+		// "jsxFactory": "",                                 /* Specify the JSX factory function used when targeting React JSX emit, e.g. 'React.createElement' or 'h' */
+		// "jsxFragmentFactory": "",                         /* Specify the JSX Fragment reference used for fragments when targeting React JSX emit e.g. 'React.Fragment' or 'Fragment'. */
+		// "jsxImportSource": "",                            /* Specify module specifier used to import the JSX factory functions when using `jsx: react-jsx*`.` */
+		// "reactNamespace": "",                             /* Specify the object invoked for `createElement`. This only applies when targeting `react` JSX emit. */
+		// "noLib": true,                                    /* Disable including any library files, including the default lib.d.ts. */
+		// "useDefineForClassFields": true,                  /* Emit ECMAScript-standard-compliant class fields. */
+
+		/* Modules */
+		"module": "es2022" /* Specify what module code is generated. */,
+		// "rootDir": "./",                                  /* Specify the root folder within your source files. */
+		"moduleResolution": "node" /* Specify how TypeScript looks up a file from a given module specifier. */,
+		// "baseUrl": "./",                                  /* Specify the base directory to resolve non-relative module names. */
+		// "paths": {},                                      /* Specify a set of entries that re-map imports to additional lookup locations. */
+		// "rootDirs": [],                                   /* Allow multiple folders to be treated as one when resolving modules. */
+		// "typeRoots": [],                                  /* Specify multiple folders that act like `./node_modules/@types`. */
+		"types": [
+			"@cloudflare/workers-types"
+		] /* Specify type package names to be included without being referenced in a source file. */,
+		// "allowUmdGlobalAccess": true,                     /* Allow accessing UMD globals from modules. */
+		"resolveJsonModule": true /* Enable importing .json files */,
+		// "noResolve": true,                                /* Disallow `import`s, `require`s or `<reference>`s from expanding the number of files TypeScript should add to a project. */
+
+		/* JavaScript Support */
+		"allowJs": true /* Allow JavaScript files to be a part of your program. Use the `checkJS` option to get errors from these files. */,
+		"checkJs": false /* Enable error reporting in type-checked JavaScript files. */,
+		// "maxNodeModuleJsDepth": 1,                        /* Specify the maximum folder depth used for checking JavaScript files from `node_modules`. Only applicable with `allowJs`. */
+
+		/* Emit */
+		// "declaration": true,                              /* Generate .d.ts files from TypeScript and JavaScript files in your project. */
+		// "declarationMap": true,                           /* Create sourcemaps for d.ts files. */
+		// "emitDeclarationOnly": true,                      /* Only output d.ts files and not JavaScript files. */
+		// "sourceMap": true,                                /* Create source map files for emitted JavaScript files. */
+		// "outFile": "./",                                  /* Specify a file that bundles all outputs into one JavaScript file. If `declaration` is true, also designates a file that bundles all .d.ts output. */
+		// "outDir": "./",                                   /* Specify an output folder for all emitted files. */
+		// "removeComments": true,                           /* Disable emitting comments. */
+		"noEmit": true /* Disable emitting files from a compilation. */,
+		// "importHelpers": true,                            /* Allow importing helper functions from tslib once per project, instead of including them per-file. */
+		// "importsNotUsedAsValues": "remove",               /* Specify emit/checking behavior for imports that are only used for types */
+		// "downlevelIteration": true,                       /* Emit more compliant, but verbose and less performant JavaScript for iteration. */
+		// "sourceRoot": "",                                 /* Specify the root path for debuggers to find the reference source code. */
+		// "mapRoot": "",                                    /* Specify the location where debugger should locate map files instead of generated locations. */
+		// "inlineSourceMap": true,                          /* Include sourcemap files inside the emitted JavaScript. */
+		// "inlineSources": true,                            /* Include source code in the sourcemaps inside the emitted JavaScript. */
+		// "emitBOM": true,                                  /* Emit a UTF-8 Byte Order Mark (BOM) in the beginning of output files. */
+		// "newLine": "crlf",                                /* Set the newline character for emitting files. */
+		// "stripInternal": true,                            /* Disable emitting declarations that have `@internal` in their JSDoc comments. */
+		// "noEmitHelpers": true,                            /* Disable generating custom helper functions like `__extends` in compiled output. */
+		// "noEmitOnError": true,                            /* Disable emitting files if any type checking errors are reported. */
+		// "preserveConstEnums": true,                       /* Disable erasing `const enum` declarations in generated code. */
+		// "declarationDir": "./",                           /* Specify the output directory for generated declaration files. */
+		// "preserveValueImports": true,                     /* Preserve unused imported values in the JavaScript output that would otherwise be removed. */
+
+		/* Interop Constraints */
+		"isolatedModules": true /* Ensure that each file can be safely transpiled without relying on other imports. */,
+		"allowSyntheticDefaultImports": true /* Allow 'import x from y' when a module doesn't have a default export. */,
+		// "esModuleInterop": true /* Emit additional JavaScript to ease support for importing CommonJS modules. This enables `allowSyntheticDefaultImports` for type compatibility. */,
+		// "preserveSymlinks": true,                         /* Disable resolving symlinks to their realpath. This correlates to the same flag in node. */
+		"forceConsistentCasingInFileNames": true /* Ensure that casing is correct in imports. */,
+
+		/* Type Checking */
+		"strict": true /* Enable all strict type-checking options. */,
+		// "noImplicitAny": true,                            /* Enable error reporting for expressions and declarations with an implied `any` type.. */
+		// "strictNullChecks": true,                         /* When type checking, take into account `null` and `undefined`. */
+		// "strictFunctionTypes": true,                      /* When assigning functions, check to ensure parameters and the return values are subtype-compatible. */
+		// "strictBindCallApply": true,                      /* Check that the arguments for `bind`, `call`, and `apply` methods match the original function. */
+		// "strictPropertyInitialization": true,             /* Check for class properties that are declared but not set in the constructor. */
+		// "noImplicitThis": true,                           /* Enable error reporting when `this` is given the type `any`. */
+		// "useUnknownInCatchVariables": true,               /* Type catch clause variables as 'unknown' instead of 'any'. */
+		// "alwaysStrict": true,                             /* Ensure 'use strict' is always emitted. */
+		// "noUnusedLocals": true,                           /* Enable error reporting when a local variables aren't read. */
+		// "noUnusedParameters": true,                       /* Raise an error when a function parameter isn't read */
+		// "exactOptionalPropertyTypes": true,               /* Interpret optional property types as written, rather than adding 'undefined'. */
+		// "noImplicitReturns": true,                        /* Enable error reporting for codepaths that do not explicitly return in a function. */
+		// "noFallthroughCasesInSwitch": true,               /* Enable error reporting for fallthrough cases in switch statements. */
+		// "noUncheckedIndexedAccess": true,                 /* Include 'undefined' in index signature results */
+		// "noImplicitOverride": true,                       /* Ensure overriding members in derived classes are marked with an override modifier. */
+		// "noPropertyAccessFromIndexSignature": true,       /* Enforces using indexed accessors for keys declared using an indexed type */
+		// "allowUnusedLabels": true,                        /* Disable error reporting for unused labels. */
+		// "allowUnreachableCode": true,                     /* Disable error reporting for unreachable code. */
+
+		/* Completeness */
+		// "skipDefaultLibCheck": true,                      /* Skip type checking .d.ts files that are included with TypeScript. */
+		"skipLibCheck": true /* Skip type checking all .d.ts files. */
+	}
+}

wrangler.toml

@@ -0,0 +1,3 @@
+name = "summerflare"
+main = "src/index.ts"
+compatibility_date = "2023-05-13"