Legislation axis: Bill schema, OpenStates ingest, validator + provenance

The legislative-process corpus, parallel to the U.S. Code statute corpus. schemas/bill.schema.json + scripts/ingest_legislation.py (deterministic, stdlib-only, reads per-state JSONL from the depot); validate.py gains legislation/ as a third tree; Makefile 'legislation' target. Raw JSONL stays off-repo on the depot (gitignored); the per-state SHA-256 manifest is the committed provenance anchor. Vintage 2026-07-01. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-06 17:24:31 -04:00
parent 246d014a4e
commit 7764501bcf
7 changed files with 669 additions and 2 deletions
@@ -0,0 +1,50 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "Bill",
+  "description": "A legislative bill: a proposed change to law, with its version chain, action timeline, sponsors, and votes. The legislative-process corpus (OpenStates/OCD source), parallel to the LegalText statute corpus.",
+  "type": "object",
+  "required": [
+    "type",
+    "title",
+    "jurisdiction",
+    "legislature",
+    "session",
+    "identifier",
+    "citation",
+    "status",
+    "source",
+    "source_identifier",
+    "retrieved_at",
+    "confidence",
+    "tags"
+  ],
+  "properties": {
+    "type": { "type": "string", "enum": ["Bill"] },
+    "title": { "type": "string" },
+    "description": { "type": "string" },
+    "jurisdiction": { "type": "string" },
+    "legislature": { "type": "string" },
+    "session": { "type": "string" },
+    "identifier": { "type": "string" },
+    "citation": { "type": "string" },
+    "classification": { "type": "array" },
+    "subjects": { "type": "array" },
+    "status": { "type": "string", "enum": ["enacted", "passed", "failed", "vetoed", "pending", "withdrawn"] },
+    "chapter_law": { "type": "string" },
+    "primary_sponsors": { "type": "array" },
+    "version_count": { "type": "integer" },
+    "action_count": { "type": "integer" },
+    "vote_count": { "type": "integer" },
+    "first_action": { "type": "string" },
+    "last_action": { "type": "string" },
+    "source": { "type": "string", "enum": ["official", "openstates"] },
+    "source_identifier": { "type": "string" },
+    "source_url": { "type": "string" },
+    "source_hash": { "type": "string" },
+    "vintage": { "type": "string" },
+    "source_snapshot": { "type": "string" },
+    "retrieved_at": { "type": "string" },
+    "confidence": { "type": "string", "enum": ["official", "reported", "inferred", "unverified"] },
+    "tags": { "type": "array" }
+  }
+}