code-yeongyu/oh-my-openagent / packages/shared-skills/skills/ulw-research
ulw-research
UnverifiedRuns maximum-saturation research with a cooperating team, claim-graph gating, and a cited, QA'd deliverable. Use when the user explicitly asks for research or a deep investigation, including any 'ulw' research wording.
scripts/conversion-probe-classes.test.ts
View on GitHubimport { describe, expect, test } from "bun:test"
import { probeConversion } from "./conversion-probe.mjs"
import { snapshotFromHtml } from "./source-snapshot.mjs"
// One table per class of conversion artifact. Each row is one form: the raw source, the converted
// text (BUILTIN = the built-in snapshot of the raw HTML), and the exact `altered` and `lost` lists.
// `attributes: false` is the built-in snapshot path, which writes no attribute text and no syntax.
type Row = { form: string; raw: string; converted: string; altered: string[]; lost: string[]; attributes?: boolean }
const BUILTIN = "\u0000builtin"
function check(row: Row) {
const builtin = row.converted === BUILTIN
const converted = builtin ? snapshotFromHtml(row.raw) : row.converted
const result = probeConversion(row.raw, converted, { attributes: builtin ? false : (row.attributes ?? true) })
expect({ altered: result.altered, lost: result.lost }).toEqual({ altered: row.altered, lost: row.lost })
}
const rows = (table: Row[]) => table.map((row) => [row.form, row] as const)
const OL = "<ol><li>Alpha</li><li>Beta</li></ol>"
const PANDOC_NOTE =
'<p>Margin 12%<a href="#fn1" id="fnref1"><sup>1</sup></a></p><section><ol><li id="fn1"><p>Filing.<a href="#fnref1">back</a></p></li></ol></section>'
const CONVERTER_DIGITS: Row[] = [
{ form: "ol -> '1. '", raw: OL, converted: "1. Alpha\n2. Beta", altered: [], lost: [] },
{ form: "ol -> '1) '", raw: OL, converted: "1) Alpha\n2) Beta", altered: [], lost: [] },
{ form: "ol -> '(1) '", raw: OL, converted: "(1) Alpha\n(2) Beta", altered: [], lost: [] },
{
form: "KO ol with numbers in the items",
raw: "<ol><li>\uB9E4\uCD9C 3\uC870 \uC6D0</li><li>\uC601\uC5C5\uC774\uC775 1,250\uC5B5 \uC6D0</li></ol>",
converted: "1. \uB9E4\uCD9C 3\uC870 \uC6D0\n2. \uC601\uC5C5\uC774\uC775 1,250\uC5B5 \uC6D0",
altered: [],
lost: [],
},
{ form: "indented markers (spaces, tab)", raw: OL, converted: " 1. Alpha\n\t2. Beta", altered: [], lost: [] },
{
form: "ol start=3",
raw: '<ol start="3"><li>x</li><li>y</li></ol>',
converted: "3. x\n4. y",
altered: [],
lost: [],
},
{
form: "ol start=3 renumbered from 1 by the converter",
raw: '<ol start="3"><li>x</li></ol>',
converted: "1. x",
altered: ["1"],
lost: [],
},
{
form: "nested ol",
raw: "<ol><li>A<ol><li>B</li><li>C</li></ol></li><li>D</li></ol>",
converted: "1. A\n 1. B\n 2. C\n2. D",
altered: [],
lost: [],
},
{
form: "ol inside a blockquote",
raw: "<blockquote><ol><li>A</li></ol></blockquote>",
converted: "> 1. A",
altered: [],
lost: [],
},
{
form: "footnote list (references ol)",
raw: '<p>Revenue rose 4%.<sup><a href="#cite_note-1">[1]</a></sup></p><ol class="references"><li id="cite_note-1">Annual report.</li></ol>',
converted: "Revenue rose 4%.[[1]](#cite_note-1)\n\n1. Annual report.",
altered: [],
lost: [],
},
{
form: "pandoc footnote -> [^1] and [^1]: definition",
raw: PANDOC_NOTE,
converted: "Margin 12%[^1]\n\n[^1]: Filing.",
altered: [],
lost: [],
},
{
form: "pandoc footnote -> markdownify list",
raw: PANDOC_NOTE,
converted: "Margin 12%[1](#fn1)\n\n1. Filing.[back](#fnref1)",
altered: [],
lost: [],
},
{
form: "KO footnote list",
raw: '<p>\uB9E4\uCD9C 3,234\uC5B5 \uC6D0<sup><a href="#n1">1</a></sup></p><ol><li id="n1">\uC0AC\uC5C5\uBCF4\uACE0\uC11C</li></ol>',
converted: "\uB9E4\uCD9C 3,234\uC5B5 \uC6D0[1](#n1)\n\n1. \uC0AC\uC5C5\uBCF4\uACE0\uC11C",
altered: [],
lost: [],
},
{
form: "table of contents as nested ol",
raw: '<ol><li><a href="#intro">Intro</a><ol><li><a href="#scope">Scope</a></li></ol></li><li><a href="#method">Method</a></li></ol>',
converted: "1. [Intro](#intro)\n 1. [Scope](#scope)\n2. [Method](#method)",
altered: [],
lost: [],
},
{
form: "table of contents numbers written in the source",
raw: '<ul><li><a href="#s1"><span>1</span> Intro</a><ul><li><a href="#s1-1"><span>1.1</span> Scope</a></li></ul></li></ul>',
converted: "- [1 Intro](#s1)\n - [1.1 Scope](#s1-1)",
altered: [],
lost: [],
},
{
form: "table of contents number the converter invented",
raw: '<ul><li><a href="#scope">Scope</a></li></ul>',
converted: "- [1.1 Scope](#scope)",
altered: ["1.1"],
lost: [],
},
{
form: "heading number written in the source",
raw: "<h2>3. Results</h2>",
converted: "## 3. Results",
altered: [],
lost: [],
},
{
form: "KO heading number written in the source",
raw: "<h2>2\uC7A5 \uACB0\uACFC</h2>",
converted: "## 2\uC7A5 \uACB0\uACFC",
altered: [],
lost: [],
},
{
form: "heading number the converter invented",
raw: "<h2>Results</h2>",
converted: "## 3 Results",
altered: ["3"],
lost: [],
},
{
form: "setext heading '2. Method' beside an ol",
raw: "<h2>2. Method</h2><ol><li>x</li><li>y</li></ol>",
converted: "2. Method\n---------\n\n1. x\n2. y",
altered: [],
lost: [],
},
{
form: "numbered paragraph, escaped by the converter",
raw: "<p>1. Alpha</p>",
converted: "1\\. Alpha",
altered: [],
lost: [],
},
{ form: "numbered paragraph, unescaped", raw: "<p>1. Alpha</p>", converted: "1. Alpha", altered: [], lost: [] },
{ form: "bare '1. ' with no ol in the source", raw: "<p>Alpha</p>", converted: "1. Alpha", altered: ["1"], lost: [] },
{
form: "ul source written as '1. '",
raw: "<ul><li>Alpha</li></ul>",
converted: "1. Alpha",
altered: ["1"],
lost: [],
},
{
form: "KO bare '1. ' with no ol",
raw: "<p>\uB9E4\uCD9C \uC99D\uAC00</p>",
converted: "1. \uB9E4\uCD9C \uC99D\uAC00",
altered: ["1"],
lost: [],
},
{
form: "more markers than ol items",
raw: "<ol><li>Alpha</li></ol>",
converted: "1. Alpha\n2. Beta",
altered: ["2"],
lost: [],
},
{
form: "lazy numbering '1. 1. 1.' over a three-item ol",
raw: "<ol><li>a</li><li>b</li><li>c</li></ol>",
converted: "1. a\n1. b\n1. c",
altered: [],
lost: [],
},
{
form: "lazy numbering at start=3",
raw: '<ol start="3"><li>x</li><li>y</li></ol>',
converted: "3. x\n3. y",
altered: [],
lost: [],
},
{
form: "KO lazy numbering",
raw: "<ol><li>\uB9E4\uCD9C</li><li>\uBE44\uC6A9</li></ol>",
converted: "1. \uB9E4\uCD9C\n1. \uBE44\uC6A9",
altered: [],
lost: [],
},
{
form: "lazy numbering with more markers than ol items",
raw: "<ol><li>a</li><li>b</li></ol>",
converted: "1. a\n1. b\n1. c",
altered: ["1"],
lost: [],
},
{
form: "built-in path: no marker exemption",
raw: "<ol><li>Alpha</li></ol>",
converted: "1. Alpha",
altered: ["1"],
lost: [],
attributes: false,
},
{
form: "inline link target digits",
raw: '<p><a href="https://example.com/2024/03/report-4">Report</a></p>',
converted: "[Report](https://example.com/2024/03/report-4)",
altered: [],
lost: [],
},
{
form: "image src, alt and title digits",
raw: '<p><img src="chart-640x480.png" alt="Chart 2023" title="Fig 4"></p>',
converted: '',
altered: [],
lost: [],
},
{
form: "autolink",
raw: '<p><a href="https://example.com/2024">https://example.com/2024</a></p>',
converted: "<https://example.com/2024>",
altered: [],
lost: [],
},
{
form: "reference-style links with numeric labels",
raw: '<p><a href="https://example.com/r/7">report</a> and <a href="https://example.com/r/9">data</a></p>',
converted: "[report][1] and [data][2]\n\n[1]: https://example.com/r/7\n[2]: https://example.com/r/9",
altered: [],
lost: [],
},
{
form: "KO reference-style link",
raw: '<p><a href="https://example.kr/b/2024">\uBCF4\uACE0\uC11C</a></p>',
converted: "[\uBCF4\uACE0\uC11C][1]\n\n[1]: https://example.kr/b/2024",
altered: [],
lost: [],
},
{
form: "reference label with no definition",
raw: "<p>report</p>",
converted: "[report][1]",
altered: ["1"],
lost: [],
},
{
form: "reference definition with a title",
raw: '<p><a href="https://example.com/r/7" title="Fig 4">report</a></p>',
converted: '[report][1]\n\n[1]: https://example.com/r/7 "Fig 4"',
altered: [],
lost: [],
},
{
form: "footnote definition text is prose, not link syntax",
raw: '<p>Margin<sup><a href="#note">1</a></sup> per <a href="https://s.example/4.22">source</a>.</p><ol><li id="note">Rate 4.2<sup>2</sup>.</li></ol>',
converted: "Margin[^1] per source.\n\n[^1]: Rate 4.22.",
altered: ["4.22"],
lost: ["4.2", "2"],
},
{
form: "KO footnote definition text is prose",
raw: '<p>\uB9E4\uCD9C<sup><a href="#n">1</a></sup> <a href="https://s.example/3,234">\uCD9C\uCC98</a></p><ol><li id="n">\uB9E4\uCD9C 3,23<sup>4</sup>\uC5B5 \uC6D0</li></ol>',
converted: "\uB9E4\uCD9C[^1] \uCD9C\uCC98\n\n[^1]: \uB9E4\uCD9C 3,234\uC5B5 \uC6D0",
altered: ["3,234"],
lost: ["3,23", "4"],
},
{
form: "footnote definition with no use keeps its label a candidate",
raw: "<p>Filing.</p>",
converted: "[^1]: Filing.",
altered: ["1"],
lost: [],
},
{
form: "attribute digit written into prose",
raw: '<p><a href="/p/42">page</a></p>',
converted: "page 42",
altered: ["42"],
lost: [],
},
{
form: "built-in path: attribute digit in link syntax",
raw: '<p><a href="/p/42">page</a></p>',
converted: "[page](/p/42)",
altered: ["42"],
lost: [],
attributes: false,
},
{
form: "href page number beside a glued footnote",
raw: '<p>Output reached 10<sup>9</sup> kWh</p><p><a href="https://b.example/b?pg=PA109">book</a></p>',
converted: "Output reached 109 kWh\n\n[book](https://b.example/b?pg=PA109)",
altered: ["109"],
lost: ["10", "9"],
},
]
const SIGNS: Row[] = [
{
form: "U+2212 written as a hyphen",
raw: "fell \u22123.5 points",
converted: "fell -3.5 points",
altered: [],
lost: [],
},
{
form: "U+2212 dropped",
raw: "fell \u22123.5 points",
converted: "fell 3.5 points",
altered: ["3.5"],
lost: ["\u22123.5"],
},
{ form: "hyphen-minus dropped", raw: "fell -3.5", converted: "fell 3.5", altered: ["3.5"], lost: ["-3.5"] },
{
form: "en dash minus after a space dropped",
raw: "fell \u20135%",
converted: "fell 5%",
altered: ["5"],
lost: ["\u20135"],
},
{ form: "en dash minus written as a hyphen", raw: "fell \u20135%", converted: "fell -5%", altered: [], lost: [] },
{
form: "hyphen after a space written as U+2212",
raw: "change -4.2",
converted: "change \u22124.2",
altered: [],
lost: [],
},
{ form: "U+2212 inside parentheses dropped", raw: "(\u22125)", converted: "(5)", altered: ["5"], lost: ["\u22125"] },
{
form: "U+2212 after one letter dropped",
raw: "\u0394\u22125 points",
converted: "\u03945 points",
altered: ["5"],
lost: ["\u22125"],
},
{ form: "hyphen after one letter dropped", raw: "x-5", converted: "x5", altered: ["5"], lost: ["-5"] },
{
form: "U+2212 after one letter written as a hyphen",
raw: "\u0394\u22125",
converted: "\u0394-5",
altered: [],
lost: [],
},
{ form: "en dash after one letter is a connector", raw: "A\u20135", converted: "A5", altered: [], lost: [] },
{ form: "range after a digit with U+2212", raw: "2019\u22122023", converted: "2019-2023", altered: [], lost: [] },
{ form: "range after a digit with an en dash", raw: "2019\u20132023", converted: "2019-2023", altered: [], lost: [] },
{ form: "ISO date", raw: "2026-10-26", converted: "2026-10-26", altered: [], lost: [] },
{
form: "hyphen after Hangul dropped",
raw: "\uAC10\uC18C\uC728-3.5%",
converted: "\uAC10\uC18C\uC728 3.5%",
altered: ["3.5"],
lost: ["-3.5"],
},
{
form: "U+2212 after Hangul dropped",
raw: "\uC804\uB144 \uB300\uBE44\u22122.1%",
converted: "\uC804\uB144 \uB300\uBE44 2.1%",
altered: ["2.1"],
lost: ["\u22122.1"],
},
{
form: "U+2212 after Hangul written as a hyphen",
raw: "\uC99D\uAC10\uB960\u22122.1%",
converted: "\uC99D\uAC10\uB960-2.1%",
altered: [],
lost: [],
},
{ form: "identifier cite_note-7", raw: "cite_note-7", converted: "cite_note7", altered: [], lost: [] },
{ form: "identifier ISO-8601", raw: "ISO-8601", converted: "ISO 8601", altered: [], lost: [] },
{ form: "identifier UTF-8", raw: "UTF-8 text", converted: "UTF8 text", altered: [], lost: [] },
{ form: "identifier COVID-19", raw: "COVID-19 cases", converted: "COVID 19 cases", altered: [], lost: [] },
{ form: "two-letter code AB-12", raw: "AB-12", converted: "AB12", altered: [], lost: [] },
{ form: "digit-letter code 3x-5", raw: "3x-5", converted: "3x5", altered: [], lost: [] },
{ form: "exponent minus dropped", raw: "1e-5", converted: "1e5", altered: ["5"], lost: ["-5"] },
{ form: "exponent U+2212 written as a hyphen", raw: "2.5E\u22123", converted: "2.5E-3", altered: [], lost: [] },
{
form: "superscript exponent flattened onto its base",
raw: "<p>10<sup>\u22125</sup></p>",
converted: "10-5",
altered: ["5"],
lost: ["\u22125"],
},
{
form: "superscript exponent written with a caret",
raw: "<p>10<sup>\u22125</sup></p>",
converted: "10^-5",
altered: [],
lost: [],
},
{
form: "negative cells kept",
raw: "<table><tr><td>Q4</td><td>-5</td><td>\u22123.2</td></tr></table>",
converted: "| Q4 | -5 | -3.2 |",
altered: [],
lost: [],
},
{
form: "negative cells lose their sign",
raw: "<table><tr><td>Q4</td><td>-5</td><td>\u22123.2</td></tr></table>",
converted: "| Q4 | 5 | 3.2 |",
altered: ["5", "3.2"],
lost: ["-5", "\u22123.2"],
},
{
form: "KO negative cell",
raw: "<table><tr><th>\uC99D\uAC10</th><td>\u22122.1%</td></tr></table>",
converted: "| \uC99D\uAC10 | -2.1% |",
altered: [],
lost: [],
},
{
form: "built-in path: negative cell",
raw: "<table><tr><td>Q4</td><td>\u22123.2</td></tr></table>",
converted: BUILTIN,
altered: [],
lost: [],
},
{ form: "plus sign carries no sign", raw: "+7", converted: "7", altered: [], lost: [] },
{
form: "minus with a space after it is not a sign",
raw: "change - 5",
converted: "change 5",
altered: [],
lost: [],
},
{
form: "Markdown bullet before a number",
raw: "<ul><li>5 sites</li></ul>",
converted: "- 5 sites",
altered: [],
lost: [],
},
{
form: "Markdown bullet before a negative number",
raw: "<ul><li>-5 C</li></ul>",
converted: "- -5 C",
altered: [],
lost: [],
},
]
const GROUPING: Row[] = [
{
form: "td | td | td",
raw: "<table><tr><td>3</td><td>250</td><td>100</td></tr></table>",
converted: "| 3 | 250 | 100 |",
altered: [],
lost: [],
},
{
form: "th | td",
raw: "<table><tr><th>12</th><td>345</td></tr></table>",
converted: "| 12 | 345 |",
altered: [],
lost: [],
},
{
form: "tr / tr",
raw: "<table><tr><td>12</td></tr><tr><td>345</td></tr></table>",
converted: "| 12 |\n| 345 |",
altered: [],
lost: [],
},
{ form: "ul li / li", raw: "<ul><li>3</li><li>250</li></ul>", converted: "- 3\n- 250", altered: [], lost: [] },
{ form: "ol li / li", raw: "<ol><li>3</li><li>250</li></ol>", converted: "1. 3\n2. 250", altered: [], lost: [] },
{ form: "p / p", raw: "<p>3</p><p>250</p>", converted: "3\n\n250", altered: [], lost: [] },
{ form: "div / div", raw: "<div>12</div><div>345</div>", converted: "12\n345", altered: [], lost: [] },
{ form: "h2 / p", raw: "<h2>12</h2><p>345</p>", converted: "## 12\n\n345", altered: [], lost: [] },
{ form: "dt / dd", raw: "<dl><dt>12</dt><dd>345</dd></dl>", converted: "12\n: 345", altered: [], lost: [] },
{
form: "blockquote / p",
raw: "<blockquote>12</blockquote><p>345</p>",
converted: "> 12\n\n345",
altered: [],
lost: [],
},
{ form: "br -> line break", raw: "<p>12<br>345</p>", converted: "12\n345", altered: [], lost: [] },
{
form: "br kept as <br> in a Markdown cell",
raw: "<table><tr><td>2,500<br>300</td></tr></table>",
converted: "| 2,500<br>300 |",
altered: [],
lost: [],
},
{
form: "br flattened to a space (real artifact)",
raw: "<p>12<br>345</p>",
converted: "12 345",
altered: ["12 345"],
lost: ["12", "345"],
},
{
form: "li holding two paragraphs, flattened",
raw: "<ul><li><p>in 2023</p><p>500 sites</p></li></ul>",
converted: "in 2023 500 sites",
altered: [],
lost: [],
},
{
form: "comma group then a space, one paragraph",
raw: "<p>1,250\n300</p>",
converted: "1,250 300",
altered: [],
lost: [],
},
{
form: "comma group | next cell",
raw: "<table><tr><td>1,250</td><td>300</td></tr></table>",
converted: "| 1,250 | 300 |",
altered: [],
lost: [],
},
{
form: "period decimal | next cell",
raw: "<table><tr><td>1.234</td><td>567</td></tr></table>",
converted: "| 1.234 | 567 |",
altered: [],
lost: [],
},
{
form: "KO td | td | td",
raw: "<table><tr><td>\uB9E4\uCD9C</td><td>3,234</td><td>\uC5B5\uC6D0</td></tr></table>",
converted: "| \uB9E4\uCD9C | 3,234 | \uC5B5\uC6D0 |",
altered: [],
lost: [],
},
{
form: "KO li / li",
raw: "<ul><li>12</li><li>345\uBA85</li></ul>",
converted: "- 12\n- 345\uBA85",
altered: [],
lost: [],
},
{
form: "KO p / p",
raw: "<p>12</p><p>345\uC5B5 \uC6D0</p>",
converted: "12\n\n345\uC5B5 \uC6D0",
altered: [],
lost: [],
},
{
form: "spaces inside one cell group",
raw: "<table><tr><td>1 234 567</td><td>8</td></tr></table>",
converted: "| 1 234 567 | 8 |",
altered: [],
lost: [],
},
{ form: "NBSP groups", raw: "1\u00a0234\u00a0567", converted: "1 234 567", altered: [], lost: [] },
{ form: "narrow NBSP groups", raw: "1\u202f234\u202f567", converted: "1 234 567", altered: [], lost: [] },
{
form: "thin space entity groups",
raw: "<p>1 234 567</p>",
converted: "1 234 567",
altered: [],
lost: [],
},
{ form: "figure space entity groups", raw: "<p>1 234</p>", converted: "1 234", altered: [], lost: [] },
{
form: "span-split groups",
raw: "<p><span>1</span> <span>234</span> <span>567</span></p>",
converted: "1 234 567",
altered: [],
lost: [],
},
{
form: "source newline between spans is a space",
raw: "<p><span>1</span>\n<span>234</span></p>",
converted: "1 234",
altered: [],
lost: [],
},
{
form: "KO space group with a unit",
raw: "<p>1 234 567\uC6D0</p>",
converted: "1 234 567\uC6D0",
altered: [],
lost: [],
},
{
form: "KO comma group in a cell",
raw: "<table><tr><td>3,234\uC5B5 \uC6D0</td></tr></table>",
converted: "| 3,234\uC5B5 \uC6D0 |",
altered: [],
lost: [],
},
{
form: "converter hard wrap inside a space group",
raw: "<p>Population 1 234 567 people</p>",
converted: "Population 1 234\n567 people",
altered: [],
lost: [],
},
{
form: "KO hard wrap inside a space group",
raw: "<p>\uC778\uAD6C 1 234 567\uBA85</p>",
converted: "\uC778\uAD6C 1 234\n567\uBA85",
altered: [],
lost: [],
},
{
form: "hard wrap between two separate numbers",
raw: "<p>in 2023 500 sites</p>",
converted: "in 2023\n500 sites",
altered: [],
lost: [],
},
{
form: "a wrap is not rejoined when the raw side holds both halves too",
raw: "<p>12 345 and 12 and 345</p>",
converted: "12\n345 and 12 and 345",
altered: ["12", "345"],
lost: ["12 345"],
},
{
form: "a blank line never rejoins a group",
raw: "<p>Population 1 234 567 people</p>",
converted: "Population 1 234\n\n567 people",
altered: ["1 234", "567"],
lost: ["1 234 567"],
},
{
form: "footnote glued onto a space group",
raw: "<p>1 234<sup>5</sup></p>",
converted: "1 2345",
altered: ["1", "2345"],
lost: ["1 234", "5"],
},
{
form: "built-in path: td | td | td",
raw: "<table><tr><td>3</td><td>250</td><td>100</td></tr></table>",
converted: BUILTIN,
altered: [],
lost: [],
},
{
form: "built-in path: li / li",
raw: "<ul><li>12</li><li>345</li></ul>",
converted: BUILTIN,
altered: [],
lost: [],
},
{
form: "built-in path: br inside a paragraph is joined by the snapshot, so it is flagged",
raw: "<p>12<br>345</p>",
converted: BUILTIN,
altered: ["12 345"],
lost: ["12", "345"],
},
{
form: "built-in path: br between cells' lines",
raw: "<table><tr><td>12</td></tr><tr><td>345</td></tr></table>",
converted: BUILTIN,
altered: [],
lost: [],
},
{
form: "built-in path: KO space group in a cell",
raw: "<table><tr><td>1 234 567\uC6D0</td><td>8</td></tr></table>",
converted: BUILTIN,
altered: [],
lost: [],
},
]
// Markdown markup a converter writes beside a sign must not change how the sign reads: the text the
// markup closes (or opens) decides, as it does in the raw HTML. One row per markup x dash x context.
type Shape = { form: string; html: (c: string) => string; md: (c: string) => string; opaque?: boolean }
const MARKUP: Shape[] = [
{ form: "**", html: (c) => `<b>${c}</b>`, md: (c) => `**${c}**` },
{ form: "*", html: (c) => `<i>${c}</i>`, md: (c) => `*${c}*` },
{ form: "_", html: (c) => `<em>${c}</em>`, md: (c) => `_${c}_` },
{ form: "__", html: (c) => `<strong>${c}</strong>`, md: (c) => `__${c}__` },
{ form: "~~", html: (c) => `<del>${c}</del>`, md: (c) => `~~${c}~~` },
{ form: "`", html: (c) => `<code>${c}</code>`, md: (c) => `\`${c}\`` },
{ form: "``", html: (c) => `<code>${c}</code>`, md: (c) => `\`\`${c}\`\`` },
{ form: "[](url)", html: (c) => `<a href="/c">${c}</a>`, md: (c) => `[${c}](/c)` },
{ form: "[][ref]", html: (c) => `<a href="/c">${c}</a>`, md: (c) => `[${c}][c]` },
{ form: "[] shortcut", html: (c) => `<a href="/c">${c}</a>`, md: (c) => `[${c}]` },
]
const DASHES = [
["hyphen", "-"],
["en dash", "\u2013"],
["U+2212", "\u2212"],
] as const
const CLOSED = [
{ form: "a digit", text: "2019", gap: "", after: "2023", signed: (_dash: string) => false },
{ form: "a Latin word", text: "COVID", gap: "", after: "19", signed: (_dash: string) => false },
{ form: "one Latin letter", text: "x", gap: "", after: "5", signed: (dash: string) => dash !== "\u2013" },
{ form: "KO Hangul", text: "\uAC10\uC18C", gap: "", after: "3", signed: (_dash: string) => true },
{ form: "a space", text: "fell", gap: " ", after: "5", signed: (_dash: string) => true },
]
// Every closer shape a CommonMark converter writes after text: inline links and images with a
// "title", 'title' or (title), a target with balanced parentheses or in <...>, collapsed and full
// reference forms, a linked image, and backslash escapes. An escaped closer is skipped like the raw
// character it stands for; an escaped opener (`opaque`) is a real character, so every dash after it is a sign.
const IMG = '<img src="i.png" alt="x"'
const CLOSER_SHAPES: Shape[] = [
{ form: '[](url "title")', html: (c) => `<a href="/c" title="t">${c}</a>`, md: (c) => `[${c}](/c "t")` },
{ form: "[](url 'title')", html: (c) => `<a href="/c" title="t">${c}</a>`, md: (c) => `[${c}](/c 't')` },
{ form: "[](url (title))", html: (c) => `<a href="/c" title="t">${c}</a>`, md: (c) => `[${c}](/c (t))` },
{
form: '[](url "title with \\" and )")',
html: (c) => `<a href="/c" title='a " )'>${c}</a>`,
md: (c) => `[${c}](/c "a \\" )")`,
},
{ form: "[](url_(x))", html: (c) => `<a href="/F_(x)">${c}</a>`, md: (c) => `[${c}](/F_(x))` },
{ form: '[](url_(x) "title")', html: (c) => `<a href="/F_(x)" title="t">${c}</a>`, md: (c) => `[${c}](/F_(x) "t")` },
{ form: "[](<url with a space>)", html: (c) => `<a href="/a b">${c}</a>`, md: (c) => `[${c}](</a b>)` },
{ form: "[][] collapsed", html: (c) => `<a href="/c">${c}</a>`, md: (c) => `[${c}][]` },
{
form: '[**text**](url "title")',
html: (c) => `<a href="/c" title="t"><b>${c}</b></a>`,
md: (c) => `[**${c}**](/c "t")`,
},
{
form: '**[text](url "title")**',
html: (c) => `<b><a href="/c" title="t">${c}</a></b>`,
md: (c) => `**[${c}](/c "t")**`,
},
{ form: "", html: (c) => `${c}${IMG}>`, md: (c) => `${c}` },
{ form: '', html: (c) => `${c}${IMG} title="t">`, md: (c) => `${c}` },
{ form: "", html: (c) => `${c}${IMG} title="t">`, md: (c) => `${c}` },
{ form: ".png)", html: (c) => `${c}<img src="a_(b).png" alt="x">`, md: (c) => `${c}.png)` },
{
form: '.png "title")',
html: (c) => `${c}<img src="a_(b).png" alt="x" title="t">`,
md: (c) => `${c}.png "t")`,
},
{ form: "", html: (c) => `${c}<img src="a b.png" alt="x">`, md: (c) => `${c}` },
{ form: "![][ref]", html: (c) => `${c}${IMG}>`, md: (c) => `${c}![x][i]` },
{ form: "[](url)", html: (c) => `${c}<a href="/p">${IMG}></a>`, md: (c) => `${c}[](/p)` },
{ form: "****", html: (c) => `${c}<b>${IMG}></b>`, md: (c) => `${c}****` },
...["*", "_", "]", ")", "~", "`"].map((x): Shape => ({
form: `escaped \\${x}`,
html: (c) => `${c}${x}`,
md: (c) => `${c}\\${x}`,
})),
...["[", "("].map((x): Shape => ({
form: `escaped \\${x} (an opener)`,
html: (c) => `${c}${x}`,
md: (c) => `${c}\\${x}`,
opaque: true,
})),
]
const closerRows = (shapes: Shape[]): Row[] =>
shapes.flatMap((m) =>
DASHES.flatMap(([dash, d]) =>
CLOSED.flatMap((c) => {
const raw = `<p>${m.html(c.text)}${c.gap}${d}${c.after}</p>`
const kept: Row = {
form: `${m.form} closing ${c.form}, then a ${dash}`,
raw,
converted: `${m.md(c.text)}${c.gap}${d}${c.after}`,
altered: [],
lost: [],
}
if (!(m.opaque || c.signed(d))) return [kept]
return [
kept,
{
form: `${m.form} closing ${c.form}, ${dash} dropped`,
raw,
converted: `${m.md(c.text)}${c.gap}${c.after}`,
altered: [c.after],
lost: [`${d}${c.after}`],
},
]
}),
),
)
const SIGN_MARKUP: Row[] = [
...closerRows(MARKUP),
...closerRows(CLOSER_SHAPES),
...MARKUP.flatMap((m) => [
...DASHES.flatMap(([dash, d]) => [
{
form: `${m.form} around a ${dash} number after a space`,
raw: `<p>fell ${m.html(`${d}5`)}</p>`,
converted: `fell ${m.md(`${d}5`)}`,
altered: [],
lost: [],
},
{
form: `${m.form} around a ${dash} number at line start`,
raw: `<p>${m.html(`${d}5`)} pts</p>`,
converted: `${m.md(`${d}5`)} pts`,
altered: [],
lost: [],
},
{
form: `${m.form} opened between a ${dash} and its digits`,
raw: `<p>fell ${d}${m.html("5")}</p>`,
converted: `fell ${d}${m.md("5")}`,
altered: [],
lost: [],
},
]),
{
form: `${m.form} around a number whose U+2212 was dropped`,
raw: `<p>fell ${m.html("\u22125")}</p>`,
converted: `fell ${m.md("5")}`,
altered: ["5"],
lost: ["\u22125"],
},
]),
{
form: "reviewer: **2019**-2023",
raw: "<p><b>2019</b>-2023</p>",
converted: "**2019**-2023",
altered: [],
lost: [],
},
{ form: "reviewer: *UTF*-8", raw: "<p><i>UTF</i>-8</p>", converted: "*UTF*-8", altered: [], lost: [] },
{ form: "reviewer: `v1`-2", raw: "<p><code>v1</code>-2</p>", converted: "`v1`-2", altered: [], lost: [] },
{
form: "image before a minus: the alt text is not the context",
raw: '<p>Q <img src="i.png" alt="chart">\u22125</p>',
converted: "Q -5",
altered: [],
lost: [],
},
{
form: "KO image before a minus",
raw: '<p>\uC99D\uAC10 <img src="i.png" alt="\uADF8\uB9BC">\u22122.1%</p>',
converted: "\uC99D\uAC10 -2.1%",
altered: [],
lost: [],
},
{
form: "autolink closer before one letter's minus",
raw: '<p><a href="https://x.example/a">https://x.example/a</a>\u22125</p>',
converted: "<https://x.example/a>-5",
altered: [],
lost: [],
},
{
form: "identifier kept through markup: **cite_note**-7",
raw: "<p><b>cite_note</b>-7</p>",
converted: "**cite_note**-7",
altered: [],
lost: [],
},
{
form: "two letters split by markup stay an identifier",
raw: "<p>a<b>b</b>\u22125</p>",
converted: "a**b**-5",
altered: [],
lost: [],
},
{
form: "reviewer r5: titled link before an en dash range",
raw: 'From <a href="/wiki/1990" title="1990">1990</a>\u20132000',
converted: 'From [1990](/wiki/1990 "1990")\u20132000',
altered: [],
lost: [],
},
{
form: "reviewer r5: titled link before a hyphen range",
raw: 'From <a href="/wiki/1990" title="1990">1990</a>-2000',
converted: 'From [1990](/wiki/1990 "1990")-2000',
altered: [],
lost: [],
},
{
form: "reviewer r5: titled link on a word",
raw: '<p><a href="/x" title="t">ab</a>-5</p>',
converted: '[ab](/x "t")-5',
altered: [],
lost: [],
},
{
form: "reviewer r5: titled image after a word",
raw: '<p>ab<img alt="x" title="t" src="i.png">-5</p>',
converted: 'ab-5',
altered: [],
lost: [],
},
{
form: "reviewer r5: image target with parentheses after a space",
raw: '<p>fell <img src="a_(b).png" alt="x">-5</p>',
converted: "fell .png)-5",
altered: [],
lost: [],
},
{ form: "reviewer r5: escaped brackets", raw: "x[3]-5", converted: "x\\[3\\]-5", altered: [], lost: [] },
{ form: "reviewer r5: escaped asterisk", raw: "foo*-5", converted: "foo\\*-5", altered: [], lost: [] },
{ form: "reviewer r5: escaped underscore", raw: "ab_-5", converted: "ab\\_-5", altered: [], lost: [] },
{
form: "link target digits after balanced parentheses are link syntax",
raw: '<p><a href="/wiki/File_(2019)_v9.png">pic</a></p>',
converted: "[pic](/wiki/File_(2019)_v9.png)",
altered: [],
lost: [],
},
{
form: "titled link target digits are link syntax",
raw: '<p><a href="/r/7" title="Fig (4)">pic</a></p>',
converted: '[pic](/r/7 "Fig (4)")',
altered: [],
lost: [],
},
]
// Raw inline HTML a converter leaves inside its Markdown (pandoc's gfm writer keeps <sup>, <sub>,
// sized <img>, <span> and <br>): read with the html-lite tag reader, a sup, sub or break tag is a
// boundary as on the raw side (`opaque`: every dash after it is a sign), any other tag or comment
// is dropped with its attributes, like a Markdown closer or opener.
const HTML_SHAPES: Shape[] = [
{ form: "<sup>", html: (c) => `<sup>${c}</sup>`, md: (c) => `<sup>${c}</sup>`, opaque: true },
{ form: "<sub>", html: (c) => `<sub>${c}</sub>`, md: (c) => `<sub>${c}</sub>`, opaque: true },
{ form: "<br> after the text", html: (c) => `${c}<br>`, md: (c) => `${c}<br>`, opaque: true },
{ form: "<br /> after the text", html: (c) => `${c}<br>`, md: (c) => `${c}<br />`, opaque: true },
{ form: "<span>", html: (c) => `<span>${c}</span>`, md: (c) => `<span>${c}</span>` },
{ form: '<span class="x">', html: (c) => `<span class="x">${c}</span>`, md: (c) => `<span class="x">${c}</span>` },
{ form: "<em> written for <i>", html: (c) => `<i>${c}</i>`, md: (c) => `<em>${c}</em>` },
{
form: '<a href="/wiki/1990">',
html: (c) => `<a href="/wiki/1990">${c}</a>`,
md: (c) => `<a href="/wiki/1990">${c}</a>`,
},
{
form: '<a href title="Fig (4)">',
html: (c) => `<a href="/c" title="Fig (4)">${c}</a>`,
md: (c) => `<a href="/c" title="Fig (4)">${c}</a>`,
},
{
form: '<img width="320"> after the text',
html: (c) => `${c}<img src="i.png" width="320">`,
md: (c) => `${c}<img src="i.png" width="320">`,
},
{
form: "<img src=a2019.png /> after the text",
html: (c) => `${c}<img src="a2019.png" alt="x">`,
md: (c) => `${c}<img src=a2019.png alt=x />`,
},
{
form: "<!-- comment 7 --> after the text",
html: (c) => `${c}<!-- comment 7 -->`,
md: (c) => `${c}<!-- comment 7 -->`,
},
{ form: "**<span>**", html: (c) => `<b><span>${c}</span></b>`, md: (c) => `**<span>${c}</span>**` },
{
form: "<span>[link](url)</span>",
html: (c) => `<span><a href="/c">${c}</a></span>`,
md: (c) => `<span>[${c}](/c)</span>`,
},
]
const RAW_HTML: Row[] = [
...closerRows(HTML_SHAPES),
{
form: "reviewer r6: pandoc 10<sup>-5</sup>",
raw: "<p>10<sup>-5</sup> m</p>",
converted: "10<sup>-5</sup> m",
altered: [],
lost: [],
},
{
form: "reviewer r6: pandoc 10<sup>U+2212 5</sup>",
raw: "<p>10<sup>\u22125</sup> m</p>",
converted: "10<sup>\u22125</sup> m",
altered: [],
lost: [],
},
{
form: "reviewer r6: pandoc 10<sup>9</sup>",
raw: "<p>Output reached 10<sup>9</sup> kWh</p>",
converted: "Output reached 10<sup>9</sup> kWh",
altered: [],
lost: [],
},
{
form: "reviewer r6: <span>a</span>-5",
raw: "<p><span>a</span>-5</p>",
converted: "<span>a</span>-5",
altered: [],
lost: [],
},
{
form: 'reviewer r6: <img src="a2019.png">',
raw: '<p><img src="a2019.png"></p>',
converted: '<img src="a2019.png">',
altered: [],
lost: [],
},
{
form: "reviewer r6: <img src=x width=320> before a number",
raw: "<p><img src=x width=320> 5 apples</p>",
converted: "<img src=x width=320> 5 apples",
altered: [],
lost: [],
},
{
form: "KO <img width=320> before a number",
raw: "<p><img src=x width=320> \uC0AC\uACFC 5\uAC1C</p>",
converted: "<img src=x width=320> \uC0AC\uACFC 5\uAC1C",
altered: [],
lost: [],
},
{
form: "reviewer r6: 2019<sup>a</sup>-2023",
raw: "<p>2019<sup>a</sup>-2023</p>",
converted: "2019<sup>a</sup>-2023",
altered: [],
lost: [],
},
{
form: "KO 3,234<sup>1</sup>\uC5B5 kept as raw HTML",
raw: "<p>\uB9E4\uCD9C 3,234<sup>1</sup>\uC5B5 \uC6D0</p>",
converted: "\uB9E4\uCD9C 3,234<sup>1</sup>\uC5B5 \uC6D0",
altered: [],
lost: [],
},
{
form: "a superscript the converter flattened is still altered",
raw: "<p>10<sup>-5</sup> m</p>",
converted: "10-5 m",
altered: ["5"],
lost: ["-5"],
},
{
form: "a glued footnote is still altered next to raw HTML",
raw: "<p>4.2<sup>2</sup> <span>bn</span></p>",
converted: "4.22 <span>bn</span>",
altered: ["4.22"],
lost: ["4.2", "2"],
},
{
form: "an img width written into prose is still altered",
raw: "<p><img src=x width=320> 5</p>",
converted: "320 5",
altered: ["320"],
lost: [],
},
{
form: "an autolink is not a tag",
raw: '<p><a href="https://x.example/2024">https://x.example/2024</a></p>',
converted: "<https://x.example/2024>",
altered: [],
lost: [],
},
{ form: "an escaped \\< is text, not a tag", raw: "<p>a<b>7</p>", converted: "a\\<b>7", altered: [], lost: [] },
{ form: "a < with no tag end stays text", raw: "<p>a <sup 5</p>", converted: "a <sup 5", altered: [], lost: [] },
{
form: "a tag never spans a blank line",
raw: "<p>a <span</p><p>5 x></p>",
converted: "a <span\n\n5 x>",
altered: [],
lost: [],
},
]
// A reference definition's title may sit alone on the next line (CommonMark): its digits are link
// syntax there too. Only the title is read across the line break; text after it makes it prose.
const REF_TITLES: Row[] = [
...[
['"Fig 2019"', "double quotes"],
["'Fig 2019'", "single quotes"],
["(Fig 2019)", "parentheses"],
].flatMap(([title, form]) => [
{
form: `title in ${form} on the next line, indented`,
raw: '<p><a href="/x" title="Fig 2019">fig</a></p>',
converted: `[fig][1]\n\n[1]: /x\n ${title}`,
altered: [],
lost: [],
},
{
form: `title in ${form} on the next line, not indented`,
raw: '<p><a href="/x" title="Fig 2019">fig</a></p>',
converted: `[fig][1]\n\n[1]: /x\n${title}\n`,
altered: [],
lost: [],
},
]),
{
form: "KO title on the next line",
raw: '<p><a href="/x" title="\uADF8\uB9BC 2019">\uADF8\uB9BC</a></p>',
converted: '[\uADF8\uB9BC][1]\n\n[1]: /x\n "\uADF8\uB9BC 2019"',
altered: [],
lost: [],
},
{
form: "two definitions, the first with its title on the next line",
raw: '<p><a href="/x" title="Fig 2019">a</a> <a href="/y/7">b</a></p>',
converted: '[a][1] [b][2]\n\n[1]: /x\n "Fig 2019"\n[2]: /y/7',
altered: [],
lost: [],
},
{
form: "a quoted line with text after it is prose, not a title",
raw: '<p><a href="/x" title="Fig 2019">fig</a></p>',
converted: '[fig][1]\n\n[1]: /x\n"Fig 2019" was cited',
altered: ["2019"],
lost: [],
},
{
form: "a next-line title digit the source does not hold is altered",
raw: '<p><a href="/x" title="Fig">fig</a></p>',
converted: '[fig][1]\n\n[1]: /x\n "Fig 2019"',
altered: ["2019"],
lost: [],
},
]
// Declared out of scope (references/fact-ledger.md): constructs outside the CommonMark inline grammar,
// the html-lite tag set and the named-entity table. Each row ASSERTS the safe-direction report, so
// the boundary is tested: the numbers are altered and `source snapshot --replace` recovers.
const OUT_OF_SCOPE: Row[] = [
{
form: "custom converter syntax: a Hugo figure shortcode",
raw: '<figure><img src="chart-2019.png" width="640"></figure>',
converted: '{{< figure src="chart-2019.png" width="640" >}}',
altered: ["2019", "640"],
lost: [],
},
{
form: "custom converter syntax: pandoc image attributes {width=640}",
raw: '<p><img src="i.png" alt="x" width="640"></p>',
converted: "{width=640}",
altered: ["640"],
lost: [],
},
{
form: "LaTeX: \\frac{3}{4} for a vulgar fraction",
raw: "<p>\u00BE of sites</p>",
converted: "$\\frac{3}{4}$ of sites",
altered: ["3", "4"],
lost: [],
},
{
form: "KO LaTeX: \\frac{3}{4}",
raw: "<p>\uC0AC\uC774\uD2B8\uC758 \u00BE</p>",
converted: "\uC0AC\uC774\uD2B8\uC758 $\\frac{3}{4}$",
altered: ["3", "4"],
lost: [],
},
{
form: "MathJax: \\sqrt[3]{8} for a cube root",
raw: "<p>\u221B8</p>",
converted: "\\(\\sqrt[3]{8}\\)",
altered: ["3"],
lost: [],
},
{
form: "non-CommonMark table: AsciiDoc cols",
raw: "<table><tr><td>A</td><td>B</td></tr></table>",
converted: '[cols="1,3"]\n|===\n| A | B\n|===',
altered: ["1,3"],
lost: [],
},
{
form: "non-CommonMark table: a colspan cell repeated per column",
raw: '<table><tr><td colspan="2">5</td></tr></table>',
converted: "| 5 | 5 |",
altered: ["5"],
lost: [],
},
{
form: "footnote extension beyond pandoc's: a numbered back-reference title",
raw: '<p>Margin 12%<sup><a href="#fn-a">a</a></sup></p><p id="fn-a">Filing.</p>',
converted: 'Margin 12%[^a]\n\n[^a]: Filing. [\u21A9](#fnref-a "Jump back to footnote 2 in the text")',
altered: ["2"],
lost: [],
},
{
form: "reference definition with its destination on the next line",
raw: '<p><a href="/x/2019">fig</a></p>',
converted: "[fig][1]\n\n[1]:\n /x/2019",
altered: ["2019"],
lost: [],
},
{
form: "an unescaped & whose text spells a reference (turndown)",
raw: "<p>Type &minus;5 to negate</p>",
converted: "Type −5 to negate",
altered: ["\u22125"],
lost: ["5"],
},
{
form: "a legacy reference without its semicolon ( )",
raw: "<p>1 234 567</p>",
converted: "1\u00A0234 567",
altered: ["1 234 567"],
lost: ["1", "234 567"],
},
{
form: "a numeric reference padded past 6 hex digits",
raw: "<p>−5</p>",
converted: "\u22125",
altered: ["\u22125"],
lost: ["00002212", "5"],
},
]
// Named character references whose decoded character the probe reads as a sign or a separator (or
// as markup), decoded on the raw side as a converter decodes them: each in a sign position and a
// separator position, EN and KO, kept as the decoded character, plus the sign position with the
// character dropped (a sign is lost; any other character changes nothing).
const ENTITIES: [string, string][] = [
["minus", "\u2212"],
["ndash", "\u2013"],
["mdash", "\u2014"],
["hyphen", "\u2010"],
["dash", "\u2010"],
["thinsp", "\u2009"],
["ThinSpace", "\u2009"],
["numsp", "\u2007"],
["puncsp", "\u2008"],
["hairsp", "\u200A"],
["VeryThinSpace", "\u200A"],
["ensp", "\u2002"],
["emsp", "\u2003"],
["emsp13", "\u2004"],
["emsp14", "\u2005"],
["MediumSpace", "\u205F"],
["nbsp", "\u00A0"],
["NonBreakingSpace", "\u00A0"],
["comma", ","],
["period", "."],
["plus", "+"],
["lowbar", "_"],
["ast", "*"],
["midast", "*"],
["grave", "`"],
["DiacriticalGrave", "`"],
["lpar", "("],
["rpar", ")"],
["lsqb", "["],
["lbrack", "["],
["rsqb", "]"],
["rbrack", "]"],
]
const SIGN_CHARS = new Set(["\u2212", "\u2013"])
const ENTITY_ROWS: Row[] = ENTITIES.flatMap(([name, ch]) => {
const e = `&${name};`
return [
{
form: `&${name}; in a sign position`,
raw: `<p>fell ${e}5 pts</p>`,
converted: `fell ${ch}5 pts`,
altered: [],
lost: [],
},
{
form: `KO &${name}; in a sign position`,
raw: `<p>\uAC10\uC18C${e}3%</p>`,
converted: `\uAC10\uC18C${ch}3%`,
altered: [],
lost: [],
},
{
form: `&${name}; as a separator`,
raw: `<p>1${e}234${e}567 people</p>`,
converted: `1${ch}234${ch}567 people`,
altered: [],
lost: [],
},
{
form: `KO &${name}; as a separator`,
raw: `<p>\uC778\uAD6C 1${e}234${e}567\uBA85</p>`,
converted: `\uC778\uAD6C 1${ch}234${ch}567\uBA85`,
altered: [],
lost: [],
},
{
form: `&${name}; in a sign position, dropped`,
raw: `<p>fell ${e}5 pts</p>`,
converted: "fell 5 pts",
altered: SIGN_CHARS.has(ch) ? ["5"] : [],
lost: SIGN_CHARS.has(ch) ? [`${ch}5`] : [],
},
{
form: `KO &${name}; in a sign position, dropped`,
raw: `<p>\uAC10\uC18C${e}3%</p>`,
converted: "\uAC10\uC18C3%",
altered: SIGN_CHARS.has(ch) ? ["3"] : [],
lost: SIGN_CHARS.has(ch) ? [`${ch}3`] : [],
},
{
form: `&${name}; kept as the reference in a sign position`,
raw: `<p>fell ${e}5 pts</p>`,
converted: `fell ${e}5 pts`,
altered: [],
lost: [],
},
{
form: `KO &${name}; kept as the reference in a sign position`,
raw: `<p>\uAC10\uC18C${e}3%</p>`,
converted: `\uAC10\uC18C${e}3%`,
altered: [],
lost: [],
},
{
form: `&${name}; kept as the reference as a separator`,
raw: `<p>1${e}234${e}567 people</p>`,
converted: `1${e}234${e}567 people`,
altered: [],
lost: [],
},
{
form: `KO &${name}; kept as the reference as a separator`,
raw: `<p>\uC778\uAD6C 1${e}234${e}567\uBA85</p>`,
converted: `\uC778\uAD6C 1${e}234${e}567\uBA85`,
altered: [],
lost: [],
},
{
form: `&${name}; in a verbatim plain-text copy (sign position)`,
raw: `fell ${e}5 pts`,
converted: `fell ${e}5 pts`,
altered: [],
lost: [],
},
{
form: `&${name}; in a verbatim plain-text copy (separator)`,
raw: `1${e}234${e}567 people`,
converted: `1${e}234${e}567 people`,
altered: [],
lost: [],
},
]
})
ENTITY_ROWS.push(
{
form: "reviewer r5: − in a text with no tags",
raw: "x −3.5%",
converted: "x \u22123.5%",
altered: [],
lost: [],
},
{
form: "reviewer r5:   groups in a text with no tags",
raw: "1 234 567",
converted: "1\u2009234\u2009567",
altered: [],
lost: [],
},
{
form: "reviewer r5: − in a paragraph",
raw: "<p>x −3.5%</p>",
converted: "x\u00A0\u22123.5%",
altered: [],
lost: [],
},
{
form: "an unterminated reference in a text with no tags stays literal",
raw: "a < b & c 5",
converted: "a < b & c 5",
altered: [],
lost: [],
},
{
form: "reviewer r6: 'Rate −5 and 1 234' copied verbatim",
raw: "Rate −5 and 1 234",
converted: "Rate −5 and 1 234",
altered: [],
lost: [],
},
{
form: "KO verbatim copy with − and  ",
raw: "\uC99D\uAC10 −5%, \uC778\uAD6C 1 234\uBA85",
converted: "\uC99D\uAC10 −5%, \uC778\uAD6C 1 234\uBA85",
altered: [],
lost: [],
},
{
form: "a sign the converted side spells as another reference is still dropped",
raw: "<p>fell −5 pts</p>",
converted: "fell 5 pts",
altered: ["5"],
lost: ["\u22125"],
},
{
form: "a separator spelled as a reference on the converted side still joins two numbers",
raw: "<p>12</p><p>345</p>",
converted: "12 345",
altered: ["12 345"],
lost: ["12", "345"],
},
)
describe("conversion probe classes (one row per form, EN and KO)", () => {
test.each(rows(CONVERTER_DIGITS))("converter-emitted digits: %s", (_form, row) => check(row))
test.each(rows(SIGNS))("signs and separators around numbers: %s", (_form, row) => check(row))
test.each(rows(GROUPING))("grouping boundaries: %s", (_form, row) => check(row))
test.each(rows(SIGN_MARKUP))("sign context through Markdown markup: %s", (_form, row) => check(row))
test.each(rows(ENTITY_ROWS))("named character references on both sides: %s", (_form, row) => check(row))
test.each(rows(RAW_HTML))("raw inline HTML in the converted Markdown: %s", (_form, row) => check(row))
test.each(rows(REF_TITLES))("reference definition titles on the next line: %s", (_form, row) => check(row))
test.each(rows(OUT_OF_SCOPE))("declared out of scope (reported as altered): %s", (_form, row) => check(row))
})
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |