alexmandClaude
ea0a7efa78
Features for the next six months (accessible HTML export, paperpack and
Lode on packages, the personal bundle):
- Zipped packages: the oracle writes and reads `.sct.zip` archives under
the rules of spec/12 §12.2; validate.py and load.py accept them; a
byte-identical zip of the tiny package joins the fixtures, and two
broken archives (traversal, symbolic link) join fixtures/invalid.
- The target set of targeted F3 (spec/08 §8.10) is computed by the
oracle and pinned by vectors/targets.jsonl under each digit rule; the
rule now covers cells as well as sentences and the leaves of anchored
containers, and defines a node's section.
- scienting-checklist/1 (provisional): a conformance check of an export,
covered by a receipt as ["checklist", id, hash] (spec/08 §8.11), with a
WCAG 2.1 AA fixture and its receipt.
- QA reports are signed like receipts (spec/08 §8.9).
- A `description` annotation body with role alt or long, so an
accessible export can find a confirmed figure description; the layer
fixture carries one, and the store's body-kind constraint allows it.
- scienting-spot-check/1, the seed payload, is registered with a schema.
- exercise, submission and grade are provisional until a course has
used them.
Audit fixes, each with a vector or a broken package where one was
missing:
- Folder packages: symbolic links are refused on validate and load,
manifest paths must not collide under case folding, listed files are
matched by exact name, files are hashed in chunks under a size limit.
- Files are compared byte for byte, so CR LF, a byte order mark, NaN,
a lone surrogate or invalid UTF-8 is refused instead of translated;
integers beyond 2^53 are read as doubles, as canonical JSON writes them.
- Receipts: signature.key must equal by and the key must be valid when
signed; a qa receipt's nodes must be the sample at the original's
hashes, its scope must name qa.of, its errors must be sampled nodes;
statuses are computed once, iteratively, so chains of spot-checks
hundreds deep settle; Base64 and manifest shape errors become refusals
instead of tracebacks; counts and the fidelity of roster-less packages
are recomputed.
- The gate enforces rule 11 of spec/11 §11.4: changed nodes are
validated against the node schema and the references between nodes
are checked, so a set to a bad value, an insert with unknown
properties or a delete of a referenced header cell is refused; a
relabel to null drops the label; a reclassify drops foreign
attributes; a split strips whitespace across runs; ids.jsonl order
follows spec/04 §4.4 in every state; a move after itself is refused.
- Anchors: the relabel rule requires that nothing else changed below the
node; an alias chain ending in a deletion no longer crashes resolve.
- Notation: a script after an empty group applies to the previous atom
({}^{14}C); letters are defined by Unicode block in spec/05 §5.4 and
the oracle; \left) is complex.
- Page fingerprints delete whitespace before folding, so "10 -20" and
"10-20" fold alike (spec/07 §7.1).
- Grades are summed with exact decimals; the reviewer error bound is
computed with integer arithmetic.
- receipts and revocations are keyed by (doc_key, id) in SQL, since one
revocation may be carried by several packages.
Checking:
- tools/stress.py: seeded randomized property tests over canonical JSON,
normalization, notation, random correction walks, anchor resolution,
Merkle roots, spot-check samples, error bounds, fingerprints, mutated
archives and packages, rights and spot-check chains; CI runs it.
- check.py verifies every count and version the prose states against
the repository, the zipped fixture and crafted archives, the checklist
coverage, and nine more broken packages.
- CONTRIBUTING.md gains a release checklist.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
745 lines
19 KiB
JSON
745 lines
19 KiB
JSON
{
|
|
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
"$id": "https://scient.ing/ns/schemas/annotation.schema.json",
|
|
"title": "Annotation",
|
|
"description": "One line of annotations.jsonl in scienting-layer/1: a W3C Web Annotation; spec/18-layers.md.",
|
|
"type": "object",
|
|
"properties": {
|
|
"@context": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"minItems": 2
|
|
},
|
|
"id": {
|
|
"type": "string",
|
|
"pattern": "^urn:scienting:annotation:[a-z0-9][a-z0-9._-]*/[a-hjkmnp-tv-z][0-9a-hjkmnp-tv-z]{6,25}$"
|
|
},
|
|
"type": {
|
|
"const": "Annotation"
|
|
},
|
|
"layer": {
|
|
"type": "string",
|
|
"pattern": "^urn:scienting:layer:[a-z0-9][a-z0-9._-]*/[a-hjkmnp-tv-z][0-9a-hjkmnp-tv-z]{6,25}$"
|
|
},
|
|
"motivation": {
|
|
"enum": [
|
|
"commenting",
|
|
"describing",
|
|
"linking",
|
|
"questioning",
|
|
"assessing",
|
|
"tagging",
|
|
"classifying",
|
|
"identifying",
|
|
"editing",
|
|
"highlighting",
|
|
"bookmarking",
|
|
"replying",
|
|
"moderating"
|
|
]
|
|
},
|
|
"creator": {
|
|
"$ref": "common.schema.json#/$defs/agent"
|
|
},
|
|
"created": {
|
|
"$ref": "common.schema.json#/$defs/time"
|
|
},
|
|
"modified": {
|
|
"$ref": "common.schema.json#/$defs/time"
|
|
},
|
|
"body": {
|
|
"oneOf": [
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "TextualBody"
|
|
},
|
|
"value": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"format": {
|
|
"enum": [
|
|
"text/plain",
|
|
"text/markdown"
|
|
]
|
|
},
|
|
"language": {
|
|
"$ref": "common.schema.json#/$defs/language"
|
|
},
|
|
"kind": {
|
|
"const": "gloss"
|
|
},
|
|
"audience": {
|
|
"enum": [
|
|
"novice",
|
|
"student",
|
|
"expert"
|
|
]
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"kind",
|
|
"value",
|
|
"audience"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "SpecificResource"
|
|
},
|
|
"source": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"kind": {
|
|
"const": "claim-link"
|
|
},
|
|
"pin": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"role": {
|
|
"enum": [
|
|
"states",
|
|
"uses",
|
|
"disputes"
|
|
]
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"kind",
|
|
"source",
|
|
"role"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "SpecificResource"
|
|
},
|
|
"source": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"kind": {
|
|
"const": "symbol"
|
|
},
|
|
"pin": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"symbol": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"kind",
|
|
"source"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "TextualBody"
|
|
},
|
|
"value": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"format": {
|
|
"enum": [
|
|
"text/plain",
|
|
"text/markdown"
|
|
]
|
|
},
|
|
"language": {
|
|
"$ref": "common.schema.json#/$defs/language"
|
|
},
|
|
"kind": {
|
|
"const": "comment"
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"kind",
|
|
"value"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "TextualBody"
|
|
},
|
|
"value": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"format": {
|
|
"enum": [
|
|
"text/plain",
|
|
"text/markdown"
|
|
]
|
|
},
|
|
"language": {
|
|
"$ref": "common.schema.json#/$defs/language"
|
|
},
|
|
"kind": {
|
|
"const": "caveat"
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"kind",
|
|
"value"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "TextualBody"
|
|
},
|
|
"value": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"format": {
|
|
"enum": [
|
|
"text/plain",
|
|
"text/markdown"
|
|
]
|
|
},
|
|
"language": {
|
|
"$ref": "common.schema.json#/$defs/language"
|
|
},
|
|
"kind": {
|
|
"const": "question"
|
|
},
|
|
"for": {
|
|
"enum": [
|
|
"reader",
|
|
"group",
|
|
"authors"
|
|
]
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"kind",
|
|
"value"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "TextualBody"
|
|
},
|
|
"value": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"format": {
|
|
"enum": [
|
|
"text/plain",
|
|
"text/markdown"
|
|
]
|
|
},
|
|
"language": {
|
|
"$ref": "common.schema.json#/$defs/language"
|
|
},
|
|
"kind": {
|
|
"const": "exercise"
|
|
},
|
|
"exercise": {
|
|
"$ref": "exercise.schema.json"
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"kind",
|
|
"value",
|
|
"exercise"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "TextualBody"
|
|
},
|
|
"value": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"format": {
|
|
"enum": [
|
|
"text/plain",
|
|
"text/markdown"
|
|
]
|
|
},
|
|
"language": {
|
|
"$ref": "common.schema.json#/$defs/language"
|
|
},
|
|
"kind": {
|
|
"const": "citation-context"
|
|
},
|
|
"reference": {
|
|
"$ref": "common.schema.json#/$defs/nodeId"
|
|
},
|
|
"verdict": {
|
|
"enum": [
|
|
"supports",
|
|
"partly",
|
|
"does-not",
|
|
"cannot-tell"
|
|
]
|
|
},
|
|
"reason": {
|
|
"enum": [
|
|
"method",
|
|
"value",
|
|
"background",
|
|
"contrast",
|
|
"other"
|
|
]
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"kind",
|
|
"value",
|
|
"reference"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "SpecificResource"
|
|
},
|
|
"source": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"kind": {
|
|
"const": "prerequisite"
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"kind",
|
|
"source"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "SpecificResource"
|
|
},
|
|
"source": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"kind": {
|
|
"const": "crosslink"
|
|
},
|
|
"selector": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "AnchorSelector"
|
|
},
|
|
"anchor": {
|
|
"$ref": "anchor.schema.json"
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"anchor"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
"minItems": 1
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"kind",
|
|
"source",
|
|
"selector"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "TextualBody"
|
|
},
|
|
"value": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"format": {
|
|
"enum": [
|
|
"text/plain",
|
|
"text/markdown"
|
|
]
|
|
},
|
|
"language": {
|
|
"$ref": "common.schema.json#/$defs/language"
|
|
},
|
|
"kind": {
|
|
"const": "translation"
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"kind",
|
|
"value",
|
|
"language"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "TextualBody"
|
|
},
|
|
"value": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"format": {
|
|
"enum": [
|
|
"text/plain",
|
|
"text/markdown"
|
|
]
|
|
},
|
|
"language": {
|
|
"$ref": "common.schema.json#/$defs/language"
|
|
},
|
|
"kind": {
|
|
"const": "description"
|
|
},
|
|
"role": {
|
|
"enum": [
|
|
"alt",
|
|
"long"
|
|
]
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"kind",
|
|
"value",
|
|
"role"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "TextualBody"
|
|
},
|
|
"value": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"format": {
|
|
"enum": [
|
|
"text/plain",
|
|
"text/markdown"
|
|
]
|
|
},
|
|
"language": {
|
|
"$ref": "common.schema.json#/$defs/language"
|
|
},
|
|
"kind": {
|
|
"const": "generated"
|
|
},
|
|
"generator": {
|
|
"type": "object",
|
|
"properties": {
|
|
"model": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"run": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
}
|
|
},
|
|
"required": [
|
|
"model",
|
|
"run"
|
|
],
|
|
"additionalProperties": false
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"kind",
|
|
"value",
|
|
"generator"
|
|
],
|
|
"additionalProperties": false
|
|
}
|
|
]
|
|
},
|
|
"target": {
|
|
"oneOf": [
|
|
{
|
|
"oneOf": [
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "SpecificResource"
|
|
},
|
|
"source": {
|
|
"type": "string",
|
|
"pattern": "^urn:scienting:doc:[a-z0-9][a-z0-9._-]*/[a-z0-9][a-z0-9._-]*$"
|
|
},
|
|
"selector": {
|
|
"type": "array",
|
|
"items": {
|
|
"oneOf": [
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "AnchorSelector"
|
|
},
|
|
"anchor": {
|
|
"$ref": "anchor.schema.json"
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"anchor"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "TextQuoteSelector"
|
|
},
|
|
"exact": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"prefix": {
|
|
"type": "string"
|
|
},
|
|
"suffix": {
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"exact"
|
|
],
|
|
"additionalProperties": false
|
|
}
|
|
]
|
|
},
|
|
"minItems": 1
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"source",
|
|
"selector"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "SpecificResource"
|
|
},
|
|
"source": {
|
|
"type": "string",
|
|
"pattern": "^urn:scienting:annotation:[a-z0-9][a-z0-9._-]*/[a-hjkmnp-tv-z][0-9a-hjkmnp-tv-z]{6,25}$"
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"source"
|
|
],
|
|
"additionalProperties": false
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"type": "array",
|
|
"items": {
|
|
"oneOf": [
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "SpecificResource"
|
|
},
|
|
"source": {
|
|
"type": "string",
|
|
"pattern": "^urn:scienting:doc:[a-z0-9][a-z0-9._-]*/[a-z0-9][a-z0-9._-]*$"
|
|
},
|
|
"selector": {
|
|
"type": "array",
|
|
"items": {
|
|
"oneOf": [
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "AnchorSelector"
|
|
},
|
|
"anchor": {
|
|
"$ref": "anchor.schema.json"
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"anchor"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "TextQuoteSelector"
|
|
},
|
|
"exact": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"prefix": {
|
|
"type": "string"
|
|
},
|
|
"suffix": {
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"exact"
|
|
],
|
|
"additionalProperties": false
|
|
}
|
|
]
|
|
},
|
|
"minItems": 1
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"source",
|
|
"selector"
|
|
],
|
|
"additionalProperties": false
|
|
},
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "SpecificResource"
|
|
},
|
|
"source": {
|
|
"type": "string",
|
|
"pattern": "^urn:scienting:annotation:[a-z0-9][a-z0-9._-]*/[a-hjkmnp-tv-z][0-9a-hjkmnp-tv-z]{6,25}$"
|
|
}
|
|
},
|
|
"required": [
|
|
"type",
|
|
"source"
|
|
],
|
|
"additionalProperties": false
|
|
}
|
|
]
|
|
},
|
|
"minItems": 1
|
|
}
|
|
]
|
|
},
|
|
"status": {
|
|
"enum": [
|
|
"proposed",
|
|
"confirmed",
|
|
"rejected",
|
|
"withdrawn"
|
|
]
|
|
},
|
|
"receipt": {
|
|
"$ref": "common.schema.json#/$defs/recordId"
|
|
},
|
|
"rights_use": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
}
|
|
},
|
|
"required": [
|
|
"@context",
|
|
"id",
|
|
"type",
|
|
"layer",
|
|
"motivation",
|
|
"creator",
|
|
"created",
|
|
"body",
|
|
"target",
|
|
"status"
|
|
],
|
|
"additionalProperties": false,
|
|
"allOf": [
|
|
{
|
|
"if": {
|
|
"properties": {
|
|
"status": {
|
|
"const": "confirmed"
|
|
}
|
|
}
|
|
},
|
|
"then": {
|
|
"required": [
|
|
"receipt"
|
|
]
|
|
}
|
|
}
|
|
]
|
|
}
|