@v1nvn/readability 0.41.1 → 0.43.0

package/dist/index.js

@@ -1,5 +1,5 @@
 #!/usr/bin/env node
-import { $ as resolveLazyImages, A as selectorsSchema, B as absolutize, C as extractTablesInputSchema, D as localPathField, E as htmlToMarkdownInputShape, F as detectGating, G as sanitizeHtml, H as renderTable, I as TraceCollector, J as computeTextMetrics, K as isReaderable, L as assembleDiagnostics, M as truncateMarkdown, N as detectPagination, O as outlineInputSchema, P as resolveMetadata, Q as normalizeDocument, R as chunkMarkdown, S as extractSectionInputShape, T as htmlToMarkdownInputSchema, U as resolveHeaderKeys, V as parseTableMatrix, W as resolveCellText, X as nonEmpty, Y as countWords, Z as applySelectors, _ as extractListInputSchema, a as extractLinksOutputShape, at as normalizeSiteKey, b as extractMetadataInputShape, c as extractTablesOutputShape, ct as selectorMisses, d as chunkTextInputSchema, dt as ExtractionError, et as resolveReadabilityOptions, f as chunkTextInputShape, ft as describeError, g as extractLinksInputShape, h as extractLinksInputSchema, ht as shutdownOnSignals, i as extractGridOutputShape, it as addPreset, j as readHtmlFile, k as outlineInputShape, l as outlineOutputShape, lt as logger, m as extractGridInputShape, n as registerExtractTool, nt as isElement, o as extractListOutputShape, ot as presetForSite, p as extractGridInputSchema, pt as toErrorResult, q as formatPayload, r as chunkTextOutputShape, rt as registerResources, s as extractMetadataOutputShape, st as removePreset, t as extractArticleFromHtml, tt as buildDocument, u as outputSchemaShape, ut as loadConfig, v as extractListInputShape, w as extractTablesInputShape, x as extractSectionInputSchema, y as extractMetadataInputSchema, z as toMarkdown } from "./assets/extract-Cn_gf58d.js";
+import { $ as resolveLazyImages, A as selectorsSchema, B as absolutize, C as extractTablesInputSchema, D as localPathField, E as htmlToMarkdownInputShape, F as detectGating, G as sanitizeHtml, H as renderTable, I as TraceCollector, J as computeTextMetrics, K as isReaderable, L as assembleDiagnostics, M as truncateMarkdown, N as detectPagination, O as outlineInputSchema, P as resolveMetadata, Q as normalizeDocument, R as chunkMarkdown, S as extractSectionInputShape, T as htmlToMarkdownInputSchema, U as resolveHeaderKeys, V as parseTableMatrix, W as resolveCellText, X as nonEmpty, Y as countWords, Z as applySelectors, _ as extractListInputSchema, a as extractLinksOutputShape, at as normalizeSiteKey, b as extractMetadataInputShape, c as extractTablesOutputShape, ct as selectorMisses, d as chunkTextInputSchema, dt as ExtractionError, et as resolveReadabilityOptions, f as chunkTextInputShape, ft as describeError, g as extractLinksInputShape, gt as shutdownOnSignals, h as extractLinksInputSchema, i as extractGridOutputShape, it as addPreset, j as readHtmlFile, k as outlineInputShape, l as outlineOutputShape, lt as logger, m as extractGridInputShape, n as registerExtractTool, nt as isElement, o as extractListOutputShape, ot as presetForSite, p as extractGridInputSchema, pt as toErrorResult, q as formatPayload, r as chunkTextOutputShape, rt as registerResources, s as extractMetadataOutputShape, st as removePreset, t as extractArticleFromHtml, tt as buildDocument, u as outputSchemaShape, ut as loadConfig, v as extractListInputShape, w as extractTablesInputShape, x as extractSectionInputSchema, y as extractMetadataInputSchema, z as toMarkdown } from "./assets/extract-Cyv5qfGN.js";
 import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
 import { mkdirSync, readFileSync, readdirSync, statSync, unlinkSync, writeFileSync } from "node:fs";
 import { homedir } from "node:os";
@@ -2249,7 +2249,7 @@ function createServer() {
 }
 //#endregion
 //#region src/index.ts
-if (process.argv[2] === "extract") import("./assets/cli-B7SX_CrL.js").then((m) => m.runCli(process.argv.slice(2))).then((code) => {
+if (process.argv[2] === "extract") import("./assets/cli-BE_Ml3rh.js").then((m) => m.runCli(process.argv.slice(2))).then((code) => {
 	process.exit(code);
 }).catch((err) => {
 	process.stderr.write(`${describeError(err)}\n`);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@v1nvn/readability",
-  "version": "0.41.1",
+  "version": "0.43.0",
   "description": "MCP server that turns rendered (post-JS) HTML into clean Markdown + metadata via Readability, Turndown, and DOMPurify.",
   "type": "module",
   "main": "dist/index.js",
@@ -44,7 +44,7 @@
   "dependencies": {
     "@modelcontextprotocol/sdk": "^1.29.0",
     "@mozilla/readability": "^0.6.0",
-    "@v1nvn/agentic-core": "^0.41.1",
+    "@v1nvn/agentic-core": "^0.43.0",
     "commander": "^15.0.0",
     "dompurify": "^3.4.12",
     "jsdom": "^30.0.1",

package/dist/assets/cli-B7SX_CrL.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"cli-B7SX_CrL.js","names":[],"sources":["../../src/cli.ts"],"sourcesContent":["import { 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(argv: readonly string[]): ParsedArgs | undefined {\n  const program = parseQuietly(buildProgram(), argv.slice(1));\n  if (program === undefined) {\n    return undefined;\n  }\n  const { format, maxChars } = program.opts<{\n    format: CliFormat;\n    maxChars: number | undefined;\n  }>();\n  return { file: program.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 === 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,UAAU,MAAiD;CACzE,MAAM,UAAU,aAAa,aAAa,GAAG,KAAK,MAAM,CAAC,CAAC;CAC1D,IAAI,YAAY,KAAA,GACd;CAEF,MAAM,EAAE,QAAQ,aAAa,QAAQ,KAGlC;CACH,OAAO;EAAE,MAAM,QAAQ,KAAK,GAAG,CAAC;EAAG;EAAQ;CAAS;AACtD;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,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"}