184 lines
3.9 KiB
JSON
184 lines
3.9 KiB
JSON
{
|
|
"$defs": {
|
|
"ExtractionBlock": {
|
|
"additionalProperties": false,
|
|
"properties": {
|
|
"block_id": {
|
|
"maxLength": 128,
|
|
"minLength": 1,
|
|
"pattern": "^[a-zA-Z0-9][a-zA-Z0-9._:-]*$",
|
|
"title": "Block Id",
|
|
"type": "string"
|
|
},
|
|
"normalization_map": {
|
|
"items": {
|
|
"maxItems": 2,
|
|
"minItems": 2,
|
|
"prefixItems": [
|
|
{
|
|
"type": "integer"
|
|
},
|
|
{
|
|
"type": "integer"
|
|
}
|
|
],
|
|
"type": "array"
|
|
},
|
|
"maxItems": 100000,
|
|
"title": "Normalization Map",
|
|
"type": "array"
|
|
},
|
|
"normalized_text": {
|
|
"maxLength": 100000,
|
|
"title": "Normalized Text",
|
|
"type": "string"
|
|
},
|
|
"ordinal": {
|
|
"minimum": 0,
|
|
"title": "Ordinal",
|
|
"type": "integer"
|
|
},
|
|
"original_text": {
|
|
"maxLength": 100000,
|
|
"title": "Original Text",
|
|
"type": "string"
|
|
},
|
|
"page": {
|
|
"anyOf": [
|
|
{
|
|
"minimum": 1,
|
|
"type": "integer"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null,
|
|
"title": "Page"
|
|
},
|
|
"schema_version": {
|
|
"const": 1,
|
|
"default": 1,
|
|
"title": "Schema Version",
|
|
"type": "integer"
|
|
},
|
|
"time_end_ms": {
|
|
"anyOf": [
|
|
{
|
|
"minimum": 0,
|
|
"type": "integer"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null,
|
|
"title": "Time End Ms"
|
|
},
|
|
"time_start_ms": {
|
|
"anyOf": [
|
|
{
|
|
"minimum": 0,
|
|
"type": "integer"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null,
|
|
"title": "Time Start Ms"
|
|
}
|
|
},
|
|
"required": [
|
|
"block_id",
|
|
"ordinal",
|
|
"original_text",
|
|
"normalized_text",
|
|
"normalization_map"
|
|
],
|
|
"title": "ExtractionBlock",
|
|
"type": "object"
|
|
}
|
|
},
|
|
"additionalProperties": false,
|
|
"properties": {
|
|
"blocks": {
|
|
"items": {
|
|
"$ref": "#/$defs/ExtractionBlock"
|
|
},
|
|
"maxItems": 100000,
|
|
"title": "Blocks",
|
|
"type": "array"
|
|
},
|
|
"extraction_id": {
|
|
"pattern": "^[a-f0-9]{64}$",
|
|
"title": "Extraction Id",
|
|
"type": "string"
|
|
},
|
|
"normalization_profile": {
|
|
"const": "unicode-nfc-lf-v1",
|
|
"title": "Normalization Profile",
|
|
"type": "string"
|
|
},
|
|
"parser_config_sha256": {
|
|
"pattern": "^[a-f0-9]{64}$",
|
|
"title": "Parser Config Sha256",
|
|
"type": "string"
|
|
},
|
|
"parser_name": {
|
|
"maxLength": 100,
|
|
"minLength": 1,
|
|
"title": "Parser Name",
|
|
"type": "string"
|
|
},
|
|
"parser_version": {
|
|
"maxLength": 100,
|
|
"minLength": 1,
|
|
"title": "Parser Version",
|
|
"type": "string"
|
|
},
|
|
"schema_version": {
|
|
"const": 1,
|
|
"default": 1,
|
|
"title": "Schema Version",
|
|
"type": "integer"
|
|
},
|
|
"source_revision_id": {
|
|
"maxLength": 128,
|
|
"minLength": 1,
|
|
"pattern": "^[a-zA-Z0-9][a-zA-Z0-9._:-]*$",
|
|
"title": "Source Revision Id",
|
|
"type": "string"
|
|
},
|
|
"status": {
|
|
"enum": [
|
|
"complete",
|
|
"partial",
|
|
"unavailable"
|
|
],
|
|
"title": "Status",
|
|
"type": "string"
|
|
},
|
|
"warnings": {
|
|
"default": [],
|
|
"items": {
|
|
"type": "string"
|
|
},
|
|
"title": "Warnings",
|
|
"type": "array"
|
|
}
|
|
},
|
|
"required": [
|
|
"extraction_id",
|
|
"source_revision_id",
|
|
"parser_name",
|
|
"parser_version",
|
|
"parser_config_sha256",
|
|
"normalization_profile",
|
|
"status",
|
|
"blocks"
|
|
],
|
|
"title": "ExtractionRecord",
|
|
"type": "object"
|
|
}
|