fix(baoyu-fetch): bump jsdom to ^30 so pages with browser-serialized CSS parse (#198)

Browsers serialize the `background` shorthand in its full form, which carries
both a background-origin and a background-clip box value:

    background: none left top / auto no-repeat scroll padding-box border-box rgba(0, 0, 0, 0)

jsdom <30 fails to parse that value (its parser pushes both box keywords twice
and bails out), and `replaceBackgroundShorthand` then dereferences the
`undefined` result:

    TypeError: undefined is not an object (evaluating 'bgValues.length')
      at replaceBackgroundShorthand (jsdom/lib/jsdom/living/css/helpers/shorthand-properties.js:220)
      at prepareProperties (.../shorthand-properties.js:1415)
      at set cssText (.../CSSStyleDeclaration-impl.js:145)

The throw happens during `adoptAttributes`, so it takes down the whole
`new JSDOM(html)` call rather than degrading. Any page captured from a live DOM
carries this CSS — WeChat article pages (`mp.weixin.qq.com/s/...`) fail 100% of
the time on the generic adapter, with the CLI reporting only the bare message
`undefined is not an object (evaluating 'bgValues.length')` and writing no
output file.

jsdom 30.0.1 parses the value correctly, which fixes the crash. Bumped in both
the workspace package and the vendored skill copy so they stay in sync.

Added a regression test that feeds browser-serialized `background` through
`convertHtmlToMarkdown`. Verified it actually pins the behaviour: the test fails
on jsdom 29.0.2 with the exact trace above and passes on 30.0.1.

Test suite: 70 pass / 1 fail before and after, the single failure being the
pre-existing Windows path-separator assertion in profile.test.ts.

Co-authored-by: sanshengai <269852131+sanshengai@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
叁笙早安 AI
2026-09-09 14:26:34 +08:00
committed by GitHub
parent 40e37fab99
commit 52f3d500db
5 changed files with 42 additions and 19 deletions
BIN
View File
Binary file not shown.
+1 -1
View File
@@ -48,7 +48,7 @@
"@mozilla/readability": "^0.6.0",
"chrome-launcher": "^1.2.1",
"defuddle": "^0.17.0",
"jsdom": "^29.0.2",
"jsdom": "^30.0.1",
"remark-gfm": "^4.0.1",
"remark-parse": "^11.0.0",
"turndown": "^7.2.0",
@@ -35,6 +35,27 @@ Body text.
});
});
describe("convertHtmlToMarkdown CSS robustness", () => {
// Browsers serialize the `background` shorthand in its full form, which carries
// both a background-origin and a background-clip box value. Any page captured
// from a live DOM (CDP, DevTools copy, WeChat article pages, ...) is full of it.
// jsdom <30 failed to parse that value and then crashed while rebuilding the
// shorthand, taking down the whole document parse.
test("parses browser-serialized background shorthand without crashing", async () => {
const html = `<!doctype html><html><head><title>Local Title</title></head><body>
<article style="background: none left top / auto no-repeat scroll padding-box border-box rgba(0, 0, 0, 0); color: rgb(0, 0, 0);">
<h1>Article Heading</h1>
<p style="background: padding-box border-box; font-size: 16px;">First paragraph carrying enough prose that the extractor keeps the article body instead of discarding it as boilerplate.</p>
<p>Second paragraph so the readability heuristics have a real block of content to score against and retain.</p>
</article>
</body></html>`;
const result = await convertHtmlToMarkdown(html, "https://example.com/post");
expect(result.markdown).toContain("First paragraph");
});
});
describe("convertHtmlToMarkdown remote fallback", () => {
test("does not call defuddle.md when the remote fallback option is disabled", async () => {
let fetchCalls = 0;
+19 -17
View File
@@ -8,7 +8,7 @@
"@mozilla/readability": "^0.6.0",
"chrome-launcher": "^1.2.1",
"defuddle": "^0.17.0",
"jsdom": "^29.0.2",
"jsdom": "^30.0.1",
"remark-gfm": "^4.0.1",
"remark-parse": "^11.0.0",
"turndown": "^7.2.0",
@@ -22,29 +22,25 @@
"@xmldom/xmldom": "0.8.13",
},
"packages": {
"@asamuzakjp/css-color": ["@asamuzakjp/css-color@5.1.11", "", { "dependencies": { "@asamuzakjp/generational-cache": "^1.0.1", "@csstools/css-calc": "^3.2.0", "@csstools/css-color-parser": "^4.1.0", "@csstools/css-parser-algorithms": "^4.0.0", "@csstools/css-tokenizer": "^4.0.0" } }, "sha512-KVw6qIiCTUQhByfTd78h2yD1/00waTmm9uy/R7Ck/ctUyAPj+AEDLkQIdJW0T8+qGgj3j5bpNKK7Q3G+LedJWg=="],
"@asamuzakjp/css-color": ["@asamuzakjp/css-color@6.0.5", "", { "dependencies": { "@csstools/css-calc": "^3.2.1", "@csstools/css-color-parser": "^4.1.9", "@csstools/css-parser-algorithms": "^4.0.0", "@csstools/css-tokenizer": "^4.0.0", "lru-cache": "^11.5.2" } }, "sha512-mbhpPMmnw/kwW19aRNmSUl1QzLbdGo1SCuE49BT98MNwqF6zaHb3o2owssFc/PEO/4t2UjqtCNwocuDtJornzA=="],
"@asamuzakjp/dom-selector": ["@asamuzakjp/dom-selector@7.1.1", "", { "dependencies": { "@asamuzakjp/generational-cache": "^1.0.1", "@asamuzakjp/nwsapi": "^2.3.9", "bidi-js": "^1.0.3", "css-tree": "^3.2.1", "is-potential-custom-element-name": "^1.0.1" } }, "sha512-67RZDnYRc8H/8MLDgQCDE//zoqVFwajkepHZgmXrbwybzXOEwOWGPYGmALYl9J2DOLfFPPs6kKCqmbzV895hTQ=="],
"@asamuzakjp/generational-cache": ["@asamuzakjp/generational-cache@1.0.1", "", {}, "sha512-wajfB8KqzMCN2KGNFdLkReeHncd0AslUSrvHVvvYWuU8ghncRJoA50kT3zP9MVL0+9g4/67H+cdvBskj9THPzg=="],
"@asamuzakjp/nwsapi": ["@asamuzakjp/nwsapi@2.3.9", "", {}, "sha512-n8GuYSrI9bF7FFZ/SjhwevlHc8xaVlb/7HmHelnc/PZXBD2ZR49NnN9sMMuDdEGPeeRQ5d0hqlSlEpgCX3Wl0Q=="],
"@asamuzakjp/dom-selector": ["@asamuzakjp/dom-selector@8.3.2", "", { "dependencies": { "bidi-js": "^1.0.3", "css-tree": "^3.2.1", "is-potential-custom-element-name": "^1.0.1", "lru-cache": "^11.5.2" } }, "sha512-93Z1N+BQNXysodoicpOIyNh2drHfz/CTf9nnT0FEx72GJcIiwgydD7tGAr78j41LsYn3hlRn+LdGPuBLn1Bl8Q=="],
"@bramus/specificity": ["@bramus/specificity@2.4.2", "", { "dependencies": { "css-tree": "^3.0.0" }, "bin": { "specificity": "bin/cli.js" } }, "sha512-ctxtJ/eA+t+6q2++vj5j7FYX3nRu311q1wfYH3xjlLOsczhlhxAg2FWNUXhpGvAw3BWo1xBcvOV6/YLc2r5FJw=="],
"@csstools/color-helpers": ["@csstools/color-helpers@6.0.2", "", {}, "sha512-LMGQLS9EuADloEFkcTBR3BwV/CGHV7zyDxVRtVDTwdI2Ca4it0CCVTT9wCkxSgokjE5Ho41hEPgb8OEUwoXr6Q=="],
"@csstools/color-helpers": ["@csstools/color-helpers@6.1.0", "", {}, "sha512-064IFJdjTfUqnjpCVpMOdbr8FLQBhinbZj6yRv2An2E41O/pLEXqfFRWqGq/SxlE5PEUYTlvWsG2r8MswAVvkg=="],
"@csstools/css-calc": ["@csstools/css-calc@3.2.0", "", { "peerDependencies": { "@csstools/css-parser-algorithms": "^4.0.0", "@csstools/css-tokenizer": "^4.0.0" } }, "sha512-bR9e6o2BDB12jzN/gIbjHa5wLJ4UjD1CB9pM7ehlc0ddk6EBz+yYS1EV2MF55/HUxrHcB/hehAyt5vhsA3hx7w=="],
"@csstools/css-calc": ["@csstools/css-calc@3.3.0", "", { "peerDependencies": { "@csstools/css-parser-algorithms": "^4.0.0", "@csstools/css-tokenizer": "^4.0.0" } }, "sha512-c5ihYsPkdG6JCkU2zTMm4+k6r7RXuGxtWYhu5DHMIiF1FHzrfmHL5so11AoFpUv/tu61xfcmT4AmKoFfMPoqdQ=="],
"@csstools/css-color-parser": ["@csstools/css-color-parser@4.1.0", "", { "dependencies": { "@csstools/color-helpers": "^6.0.2", "@csstools/css-calc": "^3.2.0" }, "peerDependencies": { "@csstools/css-parser-algorithms": "^4.0.0", "@csstools/css-tokenizer": "^4.0.0" } }, "sha512-U0KhLYmy2GVj6q4T3WaAe6NPuFYCPQoE3b0dRGxejWDgcPp8TP7S5rVdM5ZrFaqu4N67X8YaPBw14dQSYx3IyQ=="],
"@csstools/css-color-parser": ["@csstools/css-color-parser@4.1.10", "", { "dependencies": { "@csstools/color-helpers": "^6.1.0", "@csstools/css-calc": "^3.3.0" }, "peerDependencies": { "@csstools/css-parser-algorithms": "^4.0.0", "@csstools/css-tokenizer": "^4.0.0" } }, "sha512-UZhQLIUyJaaMepqehrCODwCg2KW25vFvLWBmqYFaPclYvvxzj/sG8LBOhBFCp11i9uE7t1EyS+RAoV9tztPFyw=="],
"@csstools/css-parser-algorithms": ["@csstools/css-parser-algorithms@4.0.0", "", { "peerDependencies": { "@csstools/css-tokenizer": "^4.0.0" } }, "sha512-+B87qS7fIG3L5h3qwJ/IFbjoVoOe/bpOdh9hAjXbvx0o8ImEmUsGXN0inFOnk2ChCFgqkkGFQ+TpM5rbhkKe4w=="],
"@csstools/css-syntax-patches-for-csstree": ["@csstools/css-syntax-patches-for-csstree@1.1.3", "", { "peerDependencies": { "css-tree": "^3.2.1" }, "optionalPeers": ["css-tree"] }, "sha512-SH60bMfrRCJF3morcdk57WklujF4Jr/EsQUzqkarfHXEFcAR1gg7fS/chAE922Sehgzc1/+Tz5H3Ypa1HiEKrg=="],
"@csstools/css-syntax-patches-for-csstree": ["@csstools/css-syntax-patches-for-csstree@1.1.7", "", { "peerDependencies": { "css-tree": "^3.2.1" }, "optionalPeers": ["css-tree"] }, "sha512-fQ+05118eQS1cofO3aJpB5efgpBZMvIzwr/sbC8kDLVA5XLG8q1kJV5yzrUAI1f7lvhPnm8fgIjzFB8/O/5Dig=="],
"@csstools/css-tokenizer": ["@csstools/css-tokenizer@4.0.0", "", {}, "sha512-QxULHAm7cNu72w97JUNCBFODFaXpbDg+dP8b/oWFAZ2MTRppA3U00Y2L1HqaS4J6yBqxwa/Y3nMBaxVKbB/NsA=="],
"@exodus/bytes": ["@exodus/bytes@1.15.0", "", { "peerDependencies": { "@noble/hashes": "^1.8.0 || ^2.0.0" }, "optionalPeers": ["@noble/hashes"] }, "sha512-UY0nlA+feH81UGSHv92sLEPLCeZFjXOuHhrIo0HQydScuQc8s0A7kL/UdgwgDq8g8ilksmuoF35YVTNphV2aBQ=="],
"@exodus/bytes": ["@exodus/bytes@1.15.1", "", { "peerDependencies": { "@noble/hashes": "^1.8.0 || ^2.0.0" }, "optionalPeers": ["@noble/hashes"] }, "sha512-S6mL0yNB/Abt9Ei4tq8gDhcczc4S3+vQ4ra7vxnAf+YHC02srtqxKKZghx2Dq6p0e66THKwR6r8N6P95wEty7Q=="],
"@mixmark-io/domino": ["@mixmark-io/domino@2.2.0", "", {}, "sha512-Y28PR25bHXUg88kCV7nivXrP2Nj2RueZ3/l/jdx6J9f8J4nsEGcgX0Qe6lt7Pa+J79+kPiJU3LguR6O/6zrLOw=="],
@@ -126,7 +122,7 @@
"is-wsl": ["is-wsl@2.2.0", "", { "dependencies": { "is-docker": "^2.0.0" } }, "sha512-fKzAra0rGJUUBwGBgNkHZuToZcn+TtXHpeCgmkMJMMYx1sQDYaCSyjJBSCa2nH1DGm7s3n1oBnohoVTBaN7Lww=="],
"jsdom": ["jsdom@29.0.2", "", { "dependencies": { "@asamuzakjp/css-color": "^5.1.5", "@asamuzakjp/dom-selector": "^7.0.6", "@bramus/specificity": "^2.4.2", "@csstools/css-syntax-patches-for-csstree": "^1.1.1", "@exodus/bytes": "^1.15.0", "css-tree": "^3.2.1", "data-urls": "^7.0.0", "decimal.js": "^10.6.0", "html-encoding-sniffer": "^6.0.0", "is-potential-custom-element-name": "^1.0.1", "lru-cache": "^11.2.7", "parse5": "^8.0.0", "saxes": "^6.0.0", "symbol-tree": "^3.2.4", "tough-cookie": "^6.0.1", "undici": "^7.24.5", "w3c-xmlserializer": "^5.0.0", "webidl-conversions": "^8.0.1", "whatwg-mimetype": "^5.0.0", "whatwg-url": "^16.0.1", "xml-name-validator": "^5.0.0" }, "peerDependencies": { "canvas": "^3.0.0" }, "optionalPeers": ["canvas"] }, "sha512-9VnGEBosc/ZpwyOsJBCQ/3I5p7Q5ngOY14a9bf5btenAORmZfDse1ZEheMiWcJ3h81+Fv7HmJFdS0szo/waF2w=="],
"jsdom": ["jsdom@30.0.1", "", { "dependencies": { "@asamuzakjp/css-color": "^6.0.5", "@asamuzakjp/dom-selector": "^8.3.0", "@bramus/specificity": "^2.4.2", "@csstools/css-syntax-patches-for-csstree": "^1.1.7", "@exodus/bytes": "^1.15.1", "css-tree": "^3.2.1", "data-urls": "^7.0.0", "decimal.js": "^10.6.0", "html-encoding-sniffer": "^6.0.0", "is-potential-custom-element-name": "^1.0.1", "lru-cache": "^11.5.2", "parse5": "^8.0.1", "saxes": "^6.0.0", "symbol-tree": "^3.2.4", "tough-cookie": "^6.0.2", "undici": "^8.9.0", "w3c-xmlserializer": "^5.0.0", "webidl-conversions": "^8.0.1", "whatwg-mimetype": "^5.0.0", "whatwg-url": "^17.1.0", "xml-name-validator": "^5.0.0" }, "peerDependencies": { "canvas": "^3.2.3" }, "optionalPeers": ["canvas"] }, "sha512-52v7mUVUfNQVYYqE1lcdaymWL0njO7lTLUog6ZvW2U5KsbiLk/GnZlVJ+qx0xfNJZ6Gn+KSpPNE52vurbxZwrA=="],
"lighthouse-logger": ["lighthouse-logger@2.0.2", "", { "dependencies": { "debug": "^4.4.1", "marky": "^1.2.2" } }, "sha512-vWl2+u5jgOQuZR55Z1WM0XDdrJT6mzMP8zHUct7xTlWhuQs+eV0g+QL0RQdFjT54zVmbhLCP8vIVpy1wGn/gCg=="],
@@ -134,7 +130,7 @@
"longest-streak": ["longest-streak@3.1.0", "", {}, "sha512-9Ri+o0JYgehTaVBBDoMqIl8GXtbWg711O3srftcHhZ0dqnETqLaoIK0x17fUw9rFSlK/0NlsKe0Ahhyl5pXE2g=="],
"lru-cache": ["lru-cache@11.3.5", "", {}, "sha512-NxVFwLAnrd9i7KUBxC4DrUhmgjzOs+1Qm50D3oF1/oL+r1NpZ4gA7xvG0/zJ8evR7zIKn4vLf7qTNduWFtCrRw=="],
"lru-cache": ["lru-cache@11.5.2", "", {}, "sha512-4pfM1Ff0x50o0tQwb5ucw/RzNyD0/YJME6IVcStalZuMWxdt3sR3huStTtxz4PUmvZfRguvDejasvQ2kifR11g=="],
"markdown-table": ["markdown-table@3.0.4", "", {}, "sha512-wiYz4+JrLyb/DqW2hkFJxP7Vd7JuTDm77fvbM8VfEQdmSMqcImWeeRbHwZjBjIFki/VaMK2BhFi7oUUZeM5bqw=="],
@@ -250,7 +246,7 @@
"tldts-core": ["tldts-core@7.0.28", "", {}, "sha512-7W5Efjhsc3chVdFhqtaU0KtK32J37Zcr9RKtID54nG+tIpcY79CQK/veYPODxtD/LJ4Lue66jvrQzIX2Z2/pUQ=="],
"tough-cookie": ["tough-cookie@6.0.1", "", { "dependencies": { "tldts": "^7.0.5" } }, "sha512-LktZQb3IeoUWB9lqR5EWTHgW/VTITCXg4D21M+lvybRVdylLrRMnqaIONLVb5mav8vM19m44HIcGq4qASeu2Qw=="],
"tough-cookie": ["tough-cookie@6.0.2", "", { "dependencies": { "tldts": "^7.0.5" } }, "sha512-exgYmnmL/sJpR3upZfXG5PoatXQii55xAiXGXzY+sROLZ/Y+SLcp9PgJNI9Vz37HpQ74WvDcLT8eqm+kV3FzrA=="],
"tr46": ["tr46@6.0.0", "", { "dependencies": { "punycode": "^2.3.1" } }, "sha512-bLVMLPtstlZ4iMQHpFHTR7GAGj2jxi8Dg0s2h2MafAE4uSWF98FC/3MomU51iQAMf8/qDUbKWf5GxuvvVcXEhw=="],
@@ -262,7 +258,7 @@
"uhyphen": ["uhyphen@0.2.0", "", {}, "sha512-qz3o9CHXmJJPGBdqzab7qAYuW8kQGKNEuoHFYrBwV6hWIMcpAmxDLXojcHfFr9US1Pe6zUswEIJIbLI610fuqA=="],
"undici": ["undici@7.25.0", "", {}, "sha512-xXnp4kTyor2Zq+J1FfPI6Eq3ew5h6Vl0F/8d9XU5zZQf1tX9s2Su1/3PiMmUANFULpmksxkClamIZcaUqryHsQ=="],
"undici": ["undici@8.10.0", "", {}, "sha512-HvltHd7avK13QIw/oLe4qoOLyoVSoafqJ2jYOrtMRBkbYT31eiBQ8O0ehRKZiEZCMEyLFQNIADpgCWC5fALvYQ=="],
"undici-types": ["undici-types@7.19.2", "", {}, "sha512-qYVnV5OEm2AW8cJMCpdV20CDyaN3g0AjDlOGf1OW4iaDEx8MwdtChUp4zu4H0VP3nDRF/8RKWH+IPp9uW0YGZg=="],
@@ -286,7 +282,7 @@
"whatwg-mimetype": ["whatwg-mimetype@5.0.0", "", {}, "sha512-sXcNcHOC51uPGF0P/D4NVtrkjSU2fNsm9iog4ZvZJsL3rjoDAzXZhkm2MWt1y+PUdggKAYVoMAIYcs78wJ51Cw=="],
"whatwg-url": ["whatwg-url@16.0.1", "", { "dependencies": { "@exodus/bytes": "^1.11.0", "tr46": "^6.0.0", "webidl-conversions": "^8.0.1" } }, "sha512-1to4zXBxmXHV3IiSSEInrreIlu02vUOvrhxJJH5vcxYTBDAx51cqZiKdyTxlecdKNSjj8EcxGBxNf6Vg+945gw=="],
"whatwg-url": ["whatwg-url@17.1.0", "", { "dependencies": { "@exodus/bytes": "^1.15.1", "tr46": "^6.0.0", "webidl-conversions": "^8.0.1" } }, "sha512-3GeworPmc2ZfEEHP7lEbUfBX/L75wdEsi0rLNhXcXxnoN5jyq0SL5gCy06SGW2cyTIZdTvWIDQNQoza++vKeaw=="],
"ws": ["ws@8.20.0", "", { "peerDependencies": { "bufferutil": "^4.0.1", "utf-8-validate": ">=5.0.2" }, "optionalPeers": ["bufferutil", "utf-8-validate"] }, "sha512-sAt8BhgNbzCtgGbt2OxmpuryO63ZoDk/sqaB/znQm94T4fCEsy/yV+7CdC1kJhOU9lboAEU7R3kquuycDoibVA=="],
@@ -296,10 +292,16 @@
"zwitch": ["zwitch@2.0.4", "", {}, "sha512-bXE4cR/kVZhKZX/RjPEflHaKVhUVl85noU3v6b8apfQEc1x4A+zBxjZ4lN8LqGd6WZ3dl98pY4o717VFmoPp+A=="],
"data-urls/whatwg-url": ["whatwg-url@16.0.1", "", { "dependencies": { "@exodus/bytes": "^1.11.0", "tr46": "^6.0.0", "webidl-conversions": "^8.0.1" } }, "sha512-1to4zXBxmXHV3IiSSEInrreIlu02vUOvrhxJJH5vcxYTBDAx51cqZiKdyTxlecdKNSjj8EcxGBxNf6Vg+945gw=="],
"dom-serializer/entities": ["entities@4.5.0", "", {}, "sha512-V0hjH4dGPh9Ao5p0MoRY6BVqtwCjhz6vI5LT8AJ55H+4g9/4vbHx1I54fS0XuclLhDHArPQCiMjDxjaL8fPxhw=="],
"html-encoding-sniffer/@exodus/bytes": ["@exodus/bytes@1.15.0", "", { "peerDependencies": { "@noble/hashes": "^1.8.0 || ^2.0.0" }, "optionalPeers": ["@noble/hashes"] }, "sha512-UY0nlA+feH81UGSHv92sLEPLCeZFjXOuHhrIo0HQydScuQc8s0A7kL/UdgwgDq8g8ilksmuoF35YVTNphV2aBQ=="],
"htmlparser2/entities": ["entities@7.0.1", "", {}, "sha512-TWrgLOFUQTH994YUyl1yT4uyavY5nNB5muff+RtWaqNVCAK408b5ZnnbNAUEWLTCpum9w6arT70i1XdQ4UeOPA=="],
"mdast-util-find-and-replace/escape-string-regexp": ["escape-string-regexp@5.0.0", "", {}, "sha512-/veY75JbMK4j1yjvuUxuVsiS/hr/4iHs9FTT6cgTexxdE0Ly/glccBAkloH/DofkjRbZU3bnoj38mOmhkZ0lHw=="],
"data-urls/whatwg-url/@exodus/bytes": ["@exodus/bytes@1.15.0", "", { "peerDependencies": { "@noble/hashes": "^1.8.0 || ^2.0.0" }, "optionalPeers": ["@noble/hashes"] }, "sha512-UY0nlA+feH81UGSHv92sLEPLCeZFjXOuHhrIo0HQydScuQc8s0A7kL/UdgwgDq8g8ilksmuoF35YVTNphV2aBQ=="],
}
}
@@ -12,7 +12,7 @@
"@mozilla/readability": "^0.6.0",
"chrome-launcher": "^1.2.1",
"defuddle": "^0.17.0",
"jsdom": "^29.0.2",
"jsdom": "^30.0.1",
"remark-gfm": "^4.0.1",
"remark-parse": "^11.0.0",
"turndown": "^7.2.0",