47 lines
1.9 KiB
JSON
47 lines
1.9 KiB
JSON
{
|
|
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
"$id": "chunk-manifest.schema.json",
|
|
"title": "split_document chunk manifest",
|
|
"type": "object",
|
|
"required": ["schema_version", "tool", "created_at", "source", "max_chars", "offset_unit", "chunks", "round_trip_sha256", "self_check"],
|
|
"properties": {
|
|
"schema_version": {"const": "1.0"},
|
|
"tool": {"const": "split_document"},
|
|
"created_at": {"type": "string", "format": "date-time"},
|
|
"source": {
|
|
"type": "object",
|
|
"required": ["path", "resolved_path", "sha256", "size_bytes", "char_count"],
|
|
"properties": {
|
|
"path": {"type": "string"},
|
|
"resolved_path": {"type": "string"},
|
|
"sha256": {"type": "string", "pattern": "^[0-9a-f]{64}$"},
|
|
"size_bytes": {"type": "integer", "minimum": 0},
|
|
"char_count": {"type": "integer", "minimum": 0}
|
|
}
|
|
},
|
|
"max_chars": {"type": "integer", "minimum": 1},
|
|
"offset_unit": {"const": "unicode_codepoint"},
|
|
"chunks": {
|
|
"type": "array",
|
|
"minItems": 1,
|
|
"items": {
|
|
"type": "object",
|
|
"required": ["index", "input_file", "rewritten_file", "start_offset", "end_offset", "char_count", "sha256", "boundary_reason"],
|
|
"properties": {
|
|
"index": {"type": "integer", "minimum": 1},
|
|
"input_file": {"type": "string"},
|
|
"rewritten_file": {"type": "string"},
|
|
"start_offset": {"type": "integer", "minimum": 0},
|
|
"end_offset": {"type": "integer", "minimum": 0},
|
|
"char_count": {"type": "integer", "minimum": 0},
|
|
"sha256": {"type": "string", "pattern": "^[0-9a-f]{64}$"},
|
|
"boundary_reason": {"enum": ["h2", "paragraph", "eof", "oversize_atomic_block"]}
|
|
}
|
|
}
|
|
},
|
|
"round_trip_sha256": {"type": "string", "pattern": "^[0-9a-f]{64}$"},
|
|
"self_check": {"const": true}
|
|
},
|
|
"additionalProperties": false
|
|
}
|