|
| 1 | +name: Schema & Quality Validation |
| 2 | + |
| 3 | +on: |
| 4 | + pull_request: |
| 5 | + paths: |
| 6 | + - 'data/latest/*.jsonl' |
| 7 | + - 'data/latest/*.jsonl.gz' |
| 8 | + - 'schema/bigv.schema.json' |
| 9 | + - 'tools/influx-validate' |
| 10 | + - '.github/workflows/validate.yml' |
| 11 | + push: |
| 12 | + branches: |
| 13 | + - main |
| 14 | + paths: |
| 15 | + - 'data/latest/*.jsonl' |
| 16 | + - 'data/latest/*.jsonl.gz' |
| 17 | + - 'schema/bigv.schema.json' |
| 18 | + |
| 19 | +jobs: |
| 20 | + validate: |
| 21 | + runs-on: ubuntu-latest |
| 22 | + |
| 23 | + steps: |
| 24 | + - name: Checkout code |
| 25 | + uses: actions/checkout@v4 |
| 26 | + |
| 27 | + - name: Set up Python |
| 28 | + uses: actions/setup-python@v5 |
| 29 | + with: |
| 30 | + python-version: '3.11' |
| 31 | + cache: 'pip' |
| 32 | + |
| 33 | + - name: Install dependencies |
| 34 | + run: | |
| 35 | + pip install -r requirements.txt |
| 36 | +
|
| 37 | + - name: Validate test fixtures |
| 38 | + run: | |
| 39 | + echo "=== Validating test fixtures ===" |
| 40 | + python3 tools/influx-validate -s schema/bigv.schema.json test/fixtures/valid.jsonl |
| 41 | +
|
| 42 | + echo "" |
| 43 | + echo "=== Testing invalid fixture (should fail) ===" |
| 44 | + if python3 tools/influx-validate -s schema/bigv.schema.json test/fixtures/invalid.jsonl; then |
| 45 | + echo "ERROR: invalid.jsonl should have failed validation" |
| 46 | + exit 1 |
| 47 | + else |
| 48 | + echo "✓ invalid.jsonl correctly failed validation" |
| 49 | + fi |
| 50 | +
|
| 51 | + - name: Validate latest data (if exists) |
| 52 | + run: | |
| 53 | + # Validate plain JSONL |
| 54 | + if [ -f data/latest/latest.jsonl ]; then |
| 55 | + echo "=== Validating data/latest/latest.jsonl ===" |
| 56 | + python3 tools/influx-validate -s schema/bigv.schema.json data/latest/latest.jsonl |
| 57 | + else |
| 58 | + echo "⚠ data/latest/latest.jsonl not found (OK for initial commits)" |
| 59 | + fi |
| 60 | +
|
| 61 | + # Validate compressed JSONL |
| 62 | + if [ -f data/latest/latest.jsonl.gz ]; then |
| 63 | + echo "=== Validating data/latest/latest.jsonl.gz ===" |
| 64 | + python3 tools/influx-validate -s schema/bigv.schema.json data/latest/latest.jsonl.gz |
| 65 | +
|
| 66 | + if [ -f data/latest/manifest.json ]; then |
| 67 | + echo "=== Validating with manifest ===" |
| 68 | + python3 tools/influx-validate -s schema/bigv.schema.json -m data/latest/manifest.json data/latest/latest.jsonl.gz |
| 69 | + fi |
| 70 | + else |
| 71 | + echo "⚠ data/latest/latest.jsonl.gz not found (OK for initial commits)" |
| 72 | + fi |
| 73 | +
|
| 74 | + - name: STRICT Quality Gate Validation (main branch only) |
| 75 | + if: github.event_name == 'push' && github.ref == 'refs/heads/main' |
| 76 | + run: | |
| 77 | + echo "🔒 ENFORCING SINGLE-PATH PIPELINE COMPLIANCE" |
| 78 | + echo "==========================================" |
| 79 | + echo "" |
| 80 | + echo "All data merged to main branch MUST pass through influx-harvest pipeline" |
| 81 | + echo "and comply with strict quality gates." |
| 82 | + echo "" |
| 83 | +
|
| 84 | + # Strict validation of plain JSONL (if exists) |
| 85 | + if [ -f data/latest/latest.jsonl ]; then |
| 86 | + echo "=== STRICT VALIDATION: data/latest/latest.jsonl ===" |
| 87 | + python3 tools/influx-validate --strict -s schema/bigv.schema.json data/latest/latest.jsonl |
| 88 | + echo "✓ Plain JSONL passed strict quality gate validation" |
| 89 | + else |
| 90 | + echo "⚠ data/latest/latest.jsonl not found" |
| 91 | + fi |
| 92 | +
|
| 93 | + # Strict validation of compressed JSONL (if exists) |
| 94 | + if [ -f data/latest/latest.jsonl.gz ]; then |
| 95 | + echo "=== STRICT VALIDATION: data/latest/latest.jsonl.gz ===" |
| 96 | + python3 tools/influx-validate --strict -s schema/bigv.schema.json data/latest/latest.jsonl.gz |
| 97 | +
|
| 98 | + if [ -f data/latest/manifest.json ]; then |
| 99 | + echo "=== STRICT VALIDATION with manifest ===" |
| 100 | + python3 tools/influx-validate --strict -s schema/bigv.schema.json -m data/latest/manifest.json data/latest/latest.jsonl.gz |
| 101 | + fi |
| 102 | + echo "✓ Compressed JSONL passed strict quality gate validation" |
| 103 | + else |
| 104 | + echo "⚠ data/latest/latest.jsonl.gz not found" |
| 105 | + fi |
| 106 | +
|
| 107 | + echo "" |
| 108 | + echo "🎉 ALL STRICT VALIDATIONS PASSED" |
| 109 | + echo "Data quality and single-path pipeline compliance verified" |
| 110 | +
|
| 111 | + - name: Validate schema itself |
| 112 | + run: | |
| 113 | + echo "=== Checking schema validity ===" |
| 114 | + python3 -c " |
| 115 | + import json |
| 116 | + from jsonschema import Draft7Validator |
| 117 | +
|
| 118 | + with open('schema/bigv.schema.json') as f: |
| 119 | + schema = json.load(f) |
| 120 | +
|
| 121 | + Draft7Validator.check_schema(schema) |
| 122 | + print('✓ Schema is valid JSON Schema Draft-07') |
| 123 | + " |
0 commit comments