larvit/adf-codec
3
0
Fork 0
Code Pull Requests 1 Actions Activity

Corpus 2e1: the carve-out escapes and the claimed line #19

Merged
lilleman merged 2 commits from carve-outs into main 2026-08-26 22:29:41 +02:00
Conversation 0 Commits 2 Files Changed 11
+372 -34
11 changed files with 372 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files
corpus/README.md
+1 -1
View File
@@ -4,7 +4,7 @@ One directory per contract kind, each landing with its milestone:
- `round-trip/` — `<name>.json` + `<name>.md`: the markdown `adfToMarkdown` must emit for that
document, byte for byte, and that `markdownToAdf` must read back to it (AGENTS.md §2). Grouped
by node family.
by what the fixture exercises.
- `normalization/` — `<name>.md` + `<name>.json`: markdown input, and the document
`markdownToAdf` must build from it. One-way; the markdown is not canonical.
- `errors/` — `<name>.md`: markdown input that must not convert. A `<name>.error` beside it
corpus/round-trip/combinations/carve-out-directive.json
+73
View File
@@ -0,0 +1,73 @@
{
"content": [
{
"content": [
{
"text": "Write :mention[@Mikael]{id=5b10a2} to tag someone.",
"type": "text"
}
],
"type": "paragraph"
},
{
"content": [
{
"text": "::syncBlock {localId=x}",
"type": "text"
}
],
"type": "paragraph"
},
{
"content": [
{
"text": ":::panel warning",
"type": "text"
}
],
"type": "paragraph"
},
{
"content": [
{
"text": "Stand-up at 10:30, shipped :tada:, {maxLevel} deep, a ::syncBlock mid-line.",
"type": "text"
}
],
"type": "paragraph"
},
{
"content": [
{
"attrs": {
"text": "In review"
},
"type": "status"
},
{
"text": "{color} decides.",
"type": "text"
}
],
"type": "paragraph"
},
{
"content": [
{
"text": ":status[nope]{color=red} vs ",
"type": "text"
},
{
"attrs": {
"color": "red",
"text": "yep"
},
"type": "status"
}
],
"type": "paragraph"
}
],
"type": "doc",
"version": 1
}
corpus/round-trip/combinations/carve-out-directive.md
+11
View File
@@ -0,0 +1,11 @@
Write \:mention[@Mikael]{id=5b10a2} to tag someone.
\::syncBlock {localId=x}
\:::panel warning
Stand-up at 10:30, shipped :tada:, {maxLevel} deep, a ::syncBlock mid-line.
:status[In review]\{color} decides.
\:status[nope]{color=red} vs :status[yep]{color=red}
corpus/round-trip/combinations/carve-out-pipe-table.json
+60
View File
@@ -0,0 +1,60 @@
{
"content": [
{
"content": [
{
"text": "| Part | Qty |",
"type": "text"
}
],
"type": "paragraph"
},
{
"content": [
{
"text": "Pass a | b to the shell.",
"type": "text"
}
],
"type": "paragraph"
},
{
"content": [
{
"content": [
{
"content": [
{
"text": "| --- | --- |",
"type": "text"
}
],
"type": "paragraph"
}
],
"type": "listItem"
}
],
"type": "bulletList"
},
{
"attrs": {
"panelType": "info"
},
"content": [
{
"content": [
{
"text": "| a | b |",
"type": "text"
}
],
"type": "paragraph"
}
],
"type": "panel"
}
],
"type": "doc",
"version": 1
}
corpus/round-trip/combinations/carve-out-pipe-table.md
+9
View File
@@ -0,0 +1,9 @@
\| Part | Qty |
Pass a | b to the shell.
- \| --- | --- |
:::panel info
\| a | b |
:::
corpus/round-trip/combinations/carve-out-strike.json
+69
View File
@@ -0,0 +1,69 @@
{
"content": [
{
"content": [
{
"text": "~~not strike~~",
"type": "text"
}
],
"type": "paragraph"
},
{
"content": [
{
"marks": [
{
"type": "strike"
}
],
"text": "gone",
"type": "text"
},
{
"text": " but ~~kept~~",
"type": "text"
}
],
"type": "paragraph"
},
{
"content": [
{
"text": "A ~ B ~ C",
"type": "text"
}
],
"type": "paragraph"
},
{
"content": [
{
"text": "~",
"type": "text"
},
{
"marks": [
{
"type": "strike"
}
],
"text": "a",
"type": "text"
}
],
"type": "paragraph"
},
{
"content": [
{
"text": "~~~not~~~",
"type": "text"
}
],
"type": "paragraph"
}
],
"type": "doc",
"version": 1
}
corpus/round-trip/combinations/carve-out-strike.md
+9
View File
@@ -0,0 +1,9 @@
\~~not strike~~
~~gone~~ but \~~kept~~
A ~ B ~ C
\~~~a~~
\~\~~not~~~
corpus/round-trip/combinations/closing-fence-line.json
+83
View File
@@ -0,0 +1,83 @@
{
"content": [
{
"attrs": {
"panelType": "info"
},
"content": [
{
"content": [
{
"content": [
{
"content": [
{
"text": ":::",
"type": "text"
}
],
"type": "paragraph"
}
],
"type": "listItem"
}
],
"type": "bulletList"
},
{
"content": [
{
"content": [
{
"text": ":::",
"type": "text"
}
],
"type": "paragraph"
}
],
"type": "blockquote"
},
{
"content": [
{
"text": ":::",
"type": "text"
}
],
"type": "paragraph"
},
{
"content": [
{
"text": "::: x",
"type": "text"
}
],
"type": "paragraph"
},
{
"content": [
{
"text": "::",
"type": "text"
}
],
"type": "paragraph"
}
],
"type": "panel"
},
{
"content": [
{
"text": ":::",
"type": "text"
}
],
"type": "paragraph"
}
],
"type": "doc",
"version": 1
}
corpus/round-trip/combinations/closing-fence-line.md
+13
View File
@@ -0,0 +1,13 @@
:::panel info
- \:::
> \:::
\:::
\::: x
\::
:::
\:::
src/corpus.test.ts
+5 -1
View File
@@ -13,7 +13,7 @@ const corpusRoot = join(dirname(fileURLToPath(import.meta.url)), '..', 'corpus')
const roundTripRoot = join(corpusRoot, 'round-trip')
const unspellableRoot = join(corpusRoot, 'unspellable')
const emittingDirectories = ['block-nodes', 'commonmark-subset', 'inline-nodes', 'opaque-carry']
const emittingDirectories = ['block-nodes', 'combinations', 'commonmark-subset', 'inline-nodes', 'opaque-carry']
function directoryNames(root: string): string[] {
return readdirSync(root, { withFileTypes: true })
@@ -86,6 +86,8 @@ function fenceNestingFault(markdown: string): string | undefined {
const run = colons[1]?.length ?? 0
const enclosing = open[open.length - 1]
if (colons[2] === '') {
if (enclosing === undefined) return `${JSON.stringify(line)} closes no open container`
if (run < enclosing) return `${JSON.stringify(line)} is shorter than the ${enclosing} colons it would close`
open.pop()
continue
}
@@ -99,6 +101,8 @@ test('the fence nesting check catches a fence a container cannot hold', () => {
assert.equal(fenceNestingFault(':::panel info\n- :::panel warning\n B\n :::\n:::'), '"- :::panel warning" sits in a container fenced with 3 colons')
assert.equal(fenceNestingFault(':::panel info\n- - :::panel warning\n B\n :::\n:::'), '"- - :::panel warning" sits in a container fenced with 3 colons')
assert.equal(fenceNestingFault(':::panel info\n10. :::panel warning\n B\n :::\n:::'), '"10. :::panel warning" sits in a container fenced with 3 colons')
assert.equal(fenceNestingFault('::::panel info\n:::\n::::'), '":::" is shorter than the 4 colons it would close')
assert.equal(fenceNestingFault('Text\n:::\n'), '":::" closes no open container')
assert.equal(fenceNestingFault('::::panel info\n- - :::panel warning\n B\n :::\n::::'), undefined)
assert.equal(fenceNestingFault(':::tableCell\n```text\n:::::::panel warning\n:::\n```\n:::'), undefined)
})
todo.md
+39 -32
View File
@@ -84,37 +84,41 @@ detail is settled at its own milestone.
attribute fallback 2e owes, since the reservation leaves that node no other spelling
whatever 1d decides for its `localId`.
- [ ] **2e — Carve-outs and combinations.** Fixtures and emitter together, into
`corpus/round-trip/combinations/`: the three carve-outs and their escapes, mark runs — the
longest-run rule, attributes included — and the runs a carry breaks, a mark spelling that
cannot open where it sits (`un**-real**istic`; the spec owes the carry a trigger),
attribute canonicalization, a pipe cell's whitespace edges and `\u007c` for a `|` inside a
quoted attribute value, documents combining nodes rather than isolating one, and a
paragraph line inside a container body shaped like a closing fence (`:::`, `::: x`).
Guard `fenceNestingFault`'s bare-run pop here too — a run shorter than the open fence is a
fault, not a close — which today's emitter cannot reach.
Two moves land before the attribute spelling changes. One mark vocabulary:
`emphasisSpellings`, `linkAttributes` and the `code`/`link` names join
`inline-directives.ts`, which holds four of the nine marks while the rest are branch
literals in the emitter — and the parser (3) needs every name to make `:em[x]` the named
error `spec/flavour.md` promises. And `escaping: 'attribute'` earns its keep at the
`\u007c` rule or collapses into `none`: nothing the escaper does tells the two apart
today, since a carried segment holds only spaces, tabs and newlines.
The carry's fallback triggers land here too: `spec/flavour.md` carries a node its section
cannot spell — an attrs key no section lists, a value that is not the section's type, an
arg slot holding no bare token, marks no nesting spells — where the emitter still refuses,
which leaves the refusals a container's own spelling owns. The `\u007c` rule is wider than
the pipe: a quoted attribute value spells `` ` ``, `&` and `<` raw today, so a backtick
pair in an `inlineCard`'s `data`, a `status`'s `style` or the inline carry's `json` reads
back as a code span, an entity or raw HTML inside the value. One escape settles all four,
and the pick decides whether a directive or a code span wins where they overlap (3). The
carry spells `escaping: 'none'` meanwhile, which is what makes `tryPipeCell` refuse the
pipe form for a carry whose JSON holds a pipe.
The gate gains the collision property here: no two corpus documents may emit the same
bytes — one spelling for two documents is a round-trip break no parser can undo, and it is
provable without one. It also settles the emitter's one known approximation: delimiter
flanking is exact, but CommonMark's *matching* — the multiple-of-3 rule and the way a run
splits across several openers — is not modelled. No reachable violation has been found by
hand; the property test is what decides it.
`corpus/round-trip/combinations/`.
- [ ] **2e1 — The carve-outs and the claimed line.** The three carve-outs
and their escapes, and a paragraph line inside a container body shaped like a closing
fence (`:::`, `::: x`). Guard `fenceNestingFault`'s bare-run pop here too — a run shorter
than the open fence is a fault, not a close — which today's emitter cannot reach.
- [ ] **2e2 — Mark runs and the runs a carry breaks.** The longest-run rule, attributes
included, and a mark spelling that cannot open where it sits (`un**-real**istic`; the spec
owes the carry a trigger). One mark vocabulary lands here, before 2e3 changes the
attribute spelling: `emphasisSpellings`, `linkAttributes` and the `code`/`link` names join
`inline-directives.ts`, which holds four of the nine marks while the rest are branch
literals in the emitter — and the parser (3) needs every name to make `:em[x]` the named
error `spec/flavour.md` promises.
- [ ] **2e3 — Attribute canonicalization and the quoted value's escape.** Attribute
canonicalization, a pipe cell's whitespace edges, and `\u007c` for a `|` inside a quoted
attribute value. The rule is wider than the pipe: a quoted value spells `` ` ``, `&` and
`<` raw today, so a backtick pair in an `inlineCard`'s `data`, a `status`'s `style` or the
inline carry's `json` reads back as a code span, an entity or raw HTML inside the value.
One escape settles all four, and the pick decides whether a directive or a code span wins
where they overlap (3). `escaping: 'attribute'` earns its keep at that rule or collapses
into `none`: nothing the escaper does tells the two apart today, since a carried segment
holds only spaces, tabs and newlines.
- [ ] **2e4 — The carry's fallback triggers.** `spec/flavour.md` carries a node its section
cannot spell — an attrs key no section lists, a value that is not the section's type, an
arg slot holding no bare token, marks no nesting spells — where the emitter still refuses,
which leaves the refusals a container's own spelling owns. The carry spells
`escaping: 'none'`, which is what makes `tryPipeCell` refuse the pipe form for a carry
whose JSON holds a pipe.
- [ ] **2e5 — Combined documents and the collision property.** Documents combining nodes rather
than isolating one, and the gate's collision property: no two corpus documents may emit
the same bytes — one spelling for two documents is a round-trip break no parser can undo,
and it is provable without one. It also settles the emitter's one known approximation:
delimiter flanking is exact, but CommonMark's *matching* — the multiple-of-3 rule and the
way a run splits across several openers — is not modelled. No reachable violation has been
found by hand; the property test is what decides it, and 2e1's `carve-out-strike` pins a
second backslash only flanking-without-matching emits.
- [ ] **2f — The attributes CommonMark cannot hold.** 1d's settled answer: the block nodes
CommonMark spells — `blockquote`, `bulletList`, `codeBlock`, `heading`, `listItem`,
`orderedList`, `paragraph`, `rule` — get directive sections in `spec/flavour.md` carrying
@@ -137,7 +141,10 @@ detail is settled at its own milestone.
assumes — CommonMark flanking, as for `*` — which `spec/flavour.md` does not yet pin, and
the precedence between a directive and the constructs a raw attribute value opens inside it —
a code span, an entity, raw HTML — which one directive alone already reaches until 2e's
escape lands.
escape lands. Whether a claimed line interrupts a paragraph is pinned for the plain case and
unstated for the lazy one: a closing fence on the line after a blockquote's open paragraph is
lazy continuation in CommonMark, which would swallow the fence and leave the container
unclosed. 2e1's `closing-fence-line` orders its blockquote away from that edge meanwhile.
`src/` gets its hierarchy at the same split — `adf/`,
`markdown/`, `html/`, the grammar module shared inside `markdown/` — while the rename is
still mechanical. Three files do not move whole: `block-directives.ts` and