@v1nvn/readability 0.43.0 → 0.45.0

package/src/types/jsdom.d.ts

@@ -0,0 +1,15 @@
+declare module 'jsdom' {
+  export interface JSDOMOptions {
+    readonly contentType?: string;
+    readonly pretendToBeVisual?: boolean;
+    readonly referrer?: string;
+    readonly runScripts?: 'dangerously' | 'outside-only';
+    readonly url?: string;
+  }
+
+  export class JSDOM {
+    public readonly window: typeof globalThis & Window;
+    public constructor(input?: string, options?: JSDOMOptions);
+    public serialize(): string;
+  }
+}

package/src/types/turndown-plugin-gfm.d.ts

@@ -0,0 +1,11 @@
+declare module 'turndown-plugin-gfm' {
+  import type TurndownService from 'turndown';
+
+  export type TurndownPlugin = (service: TurndownService) => void;
+
+  export const gfm: TurndownPlugin;
+  export const tables: TurndownPlugin;
+  export const strikethrough: TurndownPlugin;
+  export const taskListItems: TurndownPlugin;
+  export const highlightedCodeBlock: TurndownPlugin;
+}

package/dist/assets/cli-BE_Ml3rh.js

@@ -1,76 +0,0 @@
-import { ft as describeError, ht as parseQuietly, j as readHtmlFile, mt as HelpRequested, t as extractArticleFromHtml } from "./extract-Cyv5qfGN.js";
-import { Command, InvalidArgumentError, Option } from "commander";
-//#region src/cli.ts
-var FORMATS = [
-	"html",
-	"json",
-	"md"
-];
-function parseMaxChars(value) {
-	const n = Number(value);
-	if (!Number.isInteger(n)) throw new InvalidArgumentError("must be an integer");
-	return n;
-}
-function buildProgram() {
-	return new Command("readability extract").argument("[file]", "HTML file; stdin when omitted").addOption(new Option("--format <fmt>", "output format").choices(FORMATS).default("md")).option("--max-chars <n>", "truncate the output", parseMaxChars);
-}
-function parseArgs(argv) {
-	const program = buildProgram();
-	const parsed = parseQuietly(program, argv.slice(1));
-	if (parsed === void 0 || parsed instanceof HelpRequested) return parsed;
-	const { format, maxChars } = parsed.opts();
-	return {
-		file: parsed.args.at(0),
-		format,
-		maxChars
-	};
-}
-async function readHtml(file, stream) {
-	if (file !== void 0) return readHtmlFile(file);
-	const chunks = [];
-	for await (const chunk of stream) if (typeof chunk === "string") chunks.push(chunk);
-	else chunks.push(Buffer.from(chunk).toString("utf8"));
-	return chunks.join("");
-}
-function payloadText(result) {
-	const first = result.content.at(0);
-	return first !== void 0 && "text" in first ? first.text : "";
-}
-async function runCli(argv) {
-	if (argv[0] !== "extract") {
-		process.stderr.write(buildProgram().helpInformation());
-		return 2;
-	}
-	const parsed = parseArgs(argv);
-	if (parsed instanceof HelpRequested) {
-		process.stdout.write(`${parsed.command.helpInformation()}\n`);
-		return 0;
-	}
-	if (parsed === void 0) {
-		process.stderr.write(buildProgram().helpInformation());
-		return 2;
-	}
-	try {
-		const html = await readHtml(parsed.file, process.stdin);
-		const pipelineFormat = parsed.format === "html" ? "html" : "markdown";
-		const result = extractArticleFromHtml({
-			html,
-			format: pipelineFormat,
-			...parsed.maxChars !== void 0 ? { maxChars: parsed.maxChars } : {}
-		});
-		if (result.isError) {
-			process.stderr.write(`${payloadText(result)}\n`);
-			return 1;
-		}
-		if (parsed.format === "json") process.stdout.write(`${JSON.stringify(result.structuredContent, null, 2)}\n`);
-		else process.stdout.write(`${payloadText(result)}\n`);
-		return 0;
-	} catch (err) {
-		process.stderr.write(`${describeError(err)}\n`);
-		return 1;
-	}
-}
-//#endregion
-export { runCli };
-
-//# sourceMappingURL=cli-BE_Ml3rh.js.map

package/dist/assets/cli-BE_Ml3rh.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"cli-BE_Ml3rh.js","names":[],"sources":["../../src/cli.ts"],"sourcesContent":["import { HelpRequested, parseQuietly } from '@v1nvn/agentic-core';\nimport { Command, InvalidArgumentError, Option } from 'commander';\n\nimport { describeError } from './errors.js';\nimport { extractArticleFromHtml } from './tools/extract.js';\nimport { readHtmlFile } from './tools/html-source.js';\n\nimport type { CallToolResult } from '@modelcontextprotocol/sdk/types.js';\nimport type { Readable } from 'node:stream';\n\ntype CliFormat = 'html' | 'json' | 'md';\n\nexport interface ParsedArgs {\n  readonly file: string | undefined;\n  readonly format: CliFormat;\n  readonly maxChars: number | undefined;\n}\n\nconst FORMATS: readonly CliFormat[] = ['html', 'json', 'md'];\n\nfunction parseMaxChars(value: string): number {\n  const n = Number(value);\n  if (!Number.isInteger(n)) {\n    throw new InvalidArgumentError('must be an integer');\n  }\n  return n;\n}\n\nexport function buildProgram(): Command {\n  return new Command('readability extract')\n    .argument('[file]', 'HTML file; stdin when omitted')\n    .addOption(\n      new Option('--format <fmt>', 'output format')\n        .choices(FORMATS)\n        .default('md'),\n    )\n    .option('--max-chars <n>', 'truncate the output', parseMaxChars);\n}\n\nexport function parseArgs(\n  argv: readonly string[],\n): HelpRequested | ParsedArgs | undefined {\n  const program = buildProgram();\n  const parsed = parseQuietly(program, argv.slice(1));\n  if (parsed === undefined || parsed instanceof HelpRequested) {\n    return parsed;\n  }\n  const { format, maxChars } = parsed.opts<{\n    format: CliFormat;\n    maxChars: number | undefined;\n  }>();\n  return { file: parsed.args.at(0), format, maxChars };\n}\n\n// The stream is injected rather than reading process.stdin directly so the\n// path is testable. Chunks may be Buffer (process.stdin) or string\n// (Readable.from), so both are handled.\nexport async function readHtml(\n  file: string | undefined,\n  stream: Readable,\n): Promise<string> {\n  if (file !== undefined) {\n    return readHtmlFile(file);\n  }\n  const chunks: string[] = [];\n  for await (const chunk of stream) {\n    if (typeof chunk === 'string') {\n      chunks.push(chunk);\n    } else {\n      chunks.push(Buffer.from(chunk as Uint8Array).toString('utf8'));\n    }\n  }\n  return chunks.join('');\n}\n\nfunction payloadText(result: CallToolResult): string {\n  const first = result.content.at(0);\n  return first !== undefined && 'text' in first ? first.text : '';\n}\n\nexport async function runCli(argv: readonly string[]): Promise<number> {\n  if (argv[0] !== 'extract') {\n    process.stderr.write(buildProgram().helpInformation());\n    return 2;\n  }\n\n  const parsed = parseArgs(argv);\n  if (parsed instanceof HelpRequested) {\n    process.stdout.write(`${parsed.command.helpInformation()}\\n`);\n    return 0;\n  }\n  if (parsed === undefined) {\n    process.stderr.write(buildProgram().helpInformation());\n    return 2;\n  }\n\n  try {\n    const html = await readHtml(parsed.file, process.stdin);\n    // json reuses the markdown pipeline; the structured object is serialized below.\n    const pipelineFormat = parsed.format === 'html' ? 'html' : 'markdown';\n    const result = extractArticleFromHtml({\n      html,\n      format: pipelineFormat,\n      ...(parsed.maxChars !== undefined ? { maxChars: parsed.maxChars } : {}),\n    });\n\n    if (result.isError) {\n      process.stderr.write(`${payloadText(result)}\\n`);\n      return 1;\n    }\n\n    if (parsed.format === 'json') {\n      process.stdout.write(\n        `${JSON.stringify(result.structuredContent, null, 2)}\\n`,\n      );\n    } else {\n      process.stdout.write(`${payloadText(result)}\\n`);\n    }\n    return 0;\n  } catch (err) {\n    process.stderr.write(`${describeError(err)}\\n`);\n    return 1;\n  }\n}\n"],"mappings":";;;AAkBA,IAAM,UAAgC;CAAC;CAAQ;CAAQ;AAAI;AAE3D,SAAS,cAAc,OAAuB;CAC5C,MAAM,IAAI,OAAO,KAAK;CACtB,IAAI,CAAC,OAAO,UAAU,CAAC,GACrB,MAAM,IAAI,qBAAqB,oBAAoB;CAErD,OAAO;AACT;AAEA,SAAgB,eAAwB;CACtC,OAAO,IAAI,QAAQ,qBAAqB,CAAC,CACtC,SAAS,UAAU,+BAA+B,CAAC,CACnD,UACC,IAAI,OAAO,kBAAkB,eAAe,CAAC,CAC1C,QAAQ,OAAO,CAAC,CAChB,QAAQ,IAAI,CACjB,CAAC,CACA,OAAO,mBAAmB,uBAAuB,aAAa;AACnE;AAEA,SAAgB,UACd,MACwC;CACxC,MAAM,UAAU,aAAa;CAC7B,MAAM,SAAS,aAAa,SAAS,KAAK,MAAM,CAAC,CAAC;CAClD,IAAI,WAAW,KAAA,KAAa,kBAAkB,eAC5C,OAAO;CAET,MAAM,EAAE,QAAQ,aAAa,OAAO,KAGjC;CACH,OAAO;EAAE,MAAM,OAAO,KAAK,GAAG,CAAC;EAAG;EAAQ;CAAS;AACrD;AAKA,eAAsB,SACpB,MACA,QACiB;CACjB,IAAI,SAAS,KAAA,GACX,OAAO,aAAa,IAAI;CAE1B,MAAM,SAAmB,CAAC;CAC1B,WAAW,MAAM,SAAS,QACxB,IAAI,OAAO,UAAU,UACnB,OAAO,KAAK,KAAK;MAEjB,OAAO,KAAK,OAAO,KAAK,KAAmB,CAAC,CAAC,SAAS,MAAM,CAAC;CAGjE,OAAO,OAAO,KAAK,EAAE;AACvB;AAEA,SAAS,YAAY,QAAgC;CACnD,MAAM,QAAQ,OAAO,QAAQ,GAAG,CAAC;CACjC,OAAO,UAAU,KAAA,KAAa,UAAU,QAAQ,MAAM,OAAO;AAC/D;AAEA,eAAsB,OAAO,MAA0C;CACrE,IAAI,KAAK,OAAO,WAAW;EACzB,QAAQ,OAAO,MAAM,aAAa,CAAC,CAAC,gBAAgB,CAAC;EACrD,OAAO;CACT;CAEA,MAAM,SAAS,UAAU,IAAI;CAC7B,IAAI,kBAAkB,eAAe;EACnC,QAAQ,OAAO,MAAM,GAAG,OAAO,QAAQ,gBAAgB,EAAE,GAAG;EAC5D,OAAO;CACT;CACA,IAAI,WAAW,KAAA,GAAW;EACxB,QAAQ,OAAO,MAAM,aAAa,CAAC,CAAC,gBAAgB,CAAC;EACrD,OAAO;CACT;CAEA,IAAI;EACF,MAAM,OAAO,MAAM,SAAS,OAAO,MAAM,QAAQ,KAAK;EAEtD,MAAM,iBAAiB,OAAO,WAAW,SAAS,SAAS;EAC3D,MAAM,SAAS,uBAAuB;GACpC;GACA,QAAQ;GACR,GAAI,OAAO,aAAa,KAAA,IAAY,EAAE,UAAU,OAAO,SAAS,IAAI,CAAC;EACvE,CAAC;EAED,IAAI,OAAO,SAAS;GAClB,QAAQ,OAAO,MAAM,GAAG,YAAY,MAAM,EAAE,GAAG;GAC/C,OAAO;EACT;EAEA,IAAI,OAAO,WAAW,QACpB,QAAQ,OAAO,MACb,GAAG,KAAK,UAAU,OAAO,mBAAmB,MAAM,CAAC,EAAE,GACvD;OAEA,QAAQ,OAAO,MAAM,GAAG,YAAY,MAAM,EAAE,GAAG;EAEjD,OAAO;CACT,SAAS,KAAK;EACZ,QAAQ,OAAO,MAAM,GAAG,cAAc,GAAG,EAAE,GAAG;EAC9C,OAAO;CACT;AACF"}