schema/article.schema.json

{ "$schema": "https://json-schema.org/draft/2020-12/schema", "$id": "emergence/article.schema.json", "title": "Scraped article (unverified lane intake)", "type": "object", "required": ["id", "status", "source_id", "via", "url", "title", "scraped_at", "date"], "properties": { "id": { "type": "string", "pattern": "^art_[a-f0-9]{12}$" }, "status": { "const": "unverified" }, "source_id": { "type": "string" }, "source_name": { "type": "string" }, "via": { "type": "string", "description": "transport: rss | google-news-rss | ..." }, "url": { "type": "string", "format": "uri" }, "url_direct": { "type": ["string", "null"], "format": "uri" }, "title": { "type": "string", "minLength": 1 }, "summary": { "type": ["string", "null"] }, "published_at": { "type": ["string", "null"] }, "scraped_at": { "type": "string" }, "date": { "type": "string", "pattern": "^\\d{4}-\\d{2}-\\d{2}$" } } }