feat(pipeline): F1 regulation registry — DB-backed license/source-type lookup

Migrates REGULATION_LICENSE_MAP (135 entries) and SOURCE_REGULATION_CLASSIFICATION (58 entries) from hardcoded Python dicts to compliance.regulation_registry table. - SQL migration: 002_regulation_registry.sql (table + indexes + trigger) - Migration script: f1_migrate_regulation_registry.py (162 rows, --dry-run) - RegulationRegistry cache: 5min TTL, prefix fallback, graceful degradation - control_generator._classify_regulation() delegates to DB with dict fallback - source_type_classification.classify_source_regulation() delegates to DB - 34 new tests (lookup, cache, degradation, migration data consistency) - 421 total tests pass, 0 regressions Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-05-03 23:14:06 +02:00
parent 4fd2bfefcd
commit 9437e029d0
7 changed files with 850 additions and 30 deletions
@@ -0,0 +1,72 @@
+-- Migration 002: Regulation Registry (Block F1)
+-- Schema: compliance
+-- Run: ssh macmini "docker exec -i bp-core-postgres psql -U breakpilot -d breakpilot_db" < control-pipeline/migrations/002_regulation_registry.sql
+
+SET search_path TO compliance, public;
+
+-- ========================================
+-- regulation_registry
+-- ========================================
+-- Central registry for all regulations, laws, guidelines, and frameworks
+-- referenced by the control pipeline. Replaces hardcoded Python dicts
+-- (REGULATION_LICENSE_MAP, SOURCE_REGULATION_CLASSIFICATION).
+
+CREATE TABLE IF NOT EXISTS regulation_registry (
+    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+
+    -- regulation_id: machine key (e.g. "eu_2016_679", "nist_sp_800_53")
+    regulation_id VARCHAR(100) UNIQUE NOT NULL,
+
+    -- Display names
+    regulation_name_de TEXT,
+    regulation_name_en TEXT,
+    regulation_short VARCHAR(50),
+
+    -- License classification (3-rule system)
+    license_rule INTEGER NOT NULL DEFAULT 1
+        CHECK (license_rule IN (1, 2, 3)),
+    license_type VARCHAR(50),          -- EU_LAW, DE_LAW, CC-BY-SA-4.0, etc.
+    attribution TEXT,                   -- Required for Rule 2 (CC-BY)
+
+    -- Source classification
+    source_type VARCHAR(20) NOT NULL DEFAULT 'law'
+        CHECK (source_type IN ('law', 'guideline', 'standard', 'framework', 'restricted')),
+
+    -- Metadata
+    jurisdiction VARCHAR(10),           -- DE, EU, AT, CH, US, FR, ES, NL, IT, HU, INT
+    category VARCHAR(50),
+    celex VARCHAR(30),                  -- EU CELEX number if applicable
+    url TEXT,
+
+    -- Lifecycle
+    status VARCHAR(20) NOT NULL DEFAULT 'active'
+        CHECK (status IN ('active', 'needs_review', 'deprecated')),
+
+    created_at TIMESTAMPTZ DEFAULT NOW(),
+    updated_at TIMESTAMPTZ DEFAULT NOW()
+);
+
+-- Indexes
+CREATE INDEX IF NOT EXISTS idx_reg_registry_status
+    ON regulation_registry(status);
+CREATE INDEX IF NOT EXISTS idx_reg_registry_jurisdiction
+    ON regulation_registry(jurisdiction);
+CREATE INDEX IF NOT EXISTS idx_reg_registry_source_type
+    ON regulation_registry(source_type);
+CREATE INDEX IF NOT EXISTS idx_reg_registry_license_rule
+    ON regulation_registry(license_rule);
+
+-- Updated-at trigger
+CREATE OR REPLACE FUNCTION update_regulation_registry_updated_at()
+RETURNS TRIGGER AS $$
+BEGIN
+    NEW.updated_at = NOW();
+    RETURN NEW;
+END;
+$$ LANGUAGE plpgsql;
+
+DROP TRIGGER IF EXISTS trg_regulation_registry_updated_at ON regulation_registry;
+CREATE TRIGGER trg_regulation_registry_updated_at
+    BEFORE UPDATE ON regulation_registry
+    FOR EACH ROW
+    EXECUTE FUNCTION update_regulation_registry_updated_at();