fix: enforce domain format validation (lowercase + hyphens only)

firstdata/schemas/datasource-schema.json

@@ -109,7 +109,8 @@
       "type": "array",
       "description": "Data domains covered by this source",
       "items": {
-        "type": "string"
+        "type": "string",
+        "pattern": "^[a-z0-9]+(-[a-z0-9]+)*$"
       },
       "minItems": 1,
       "examples": [

firstdata/sources/academic/biology/1000-genomes.json

@@ -15,9 +15,9 @@
   "domains": [
     "genomics",
     "genetics",
-    "human genetic variation",
-    "population genetics",
-    "evolutionary biology",
+    "human-genetic-variation",
+    "population-genetics",
+    "evolutionary-biology",
     "bioinformatics"
   ],
   "geographic_scope": "global",
@@ -69,4 +69,4 @@
     ]
   },
   "authority_level": "research"
-}
+}

firstdata/sources/academic/biology/alphafold-db.json

@@ -13,10 +13,10 @@
   "api_url": "https://alphafold.com/api-docs",
   "country": null,
   "domains": [
-    "structural biology",
+    "structural-biology",
     "proteomics",
-    "drug discovery",
-    "molecular biology",
+    "drug-discovery",
+    "molecular-biology",
     "biotechnology",
     "bioinformatics"
   ],

firstdata/sources/academic/biology/ena.json

@@ -16,12 +16,12 @@
     "genomics",
     "transcriptomics",
     "metagenomics",
-    "molecular biology",
+    "molecular-biology",
     "bioinformatics",
     "biodiversity",
-    "environmental sciences",
+    "environmental-sciences",
     "healthcare",
-    "pathogen surveillance"
+    "pathogen-surveillance"
   ],
   "geographic_scope": "global",
   "update_frequency": "daily",

firstdata/sources/academic/biology/genbank.json

@@ -14,7 +14,7 @@
   "country": null,
   "domains": [
     "genomics",
-    "molecular biology",
+    "molecular-biology",
     "genetics",
     "bioinformatics"
   ],

firstdata/sources/academic/biology/pdb.json

@@ -13,13 +13,13 @@
   "api_url": "https://data.rcsb.org",
   "country": null,
   "domains": [
-    "structural biology",
+    "structural-biology",
     "biochemistry",
-    "molecular biology",
-    "computational biology",
-    "drug discovery",
+    "molecular-biology",
+    "computational-biology",
+    "drug-discovery",
     "biotechnology",
-    "protein science"
+    "protein-science"
   ],
   "geographic_scope": "global",
   "update_frequency": "weekly",

firstdata/sources/academic/biology/uk-biobank.json

@@ -18,7 +18,7 @@
     "genomics",
     "epidemiology",
     "biomarkers",
-    "medical imaging",
+    "medical-imaging",
     "demographics",
     "lifestyle",
     "proteomics",
@@ -73,4 +73,4 @@
     ]
   },
   "authority_level": "research"
-}
+}

firstdata/sources/academic/chemistry/chembl.json

@@ -13,15 +13,15 @@
   "api_url": "https://www.ebi.ac.uk/chembl/api/data/docs",
   "country": null,
   "domains": [
-    "drug discovery",
-    "pharmaceutical sciences",
-    "medicinal chemistry",
-    "chemical biology",
+    "drug-discovery",
+    "pharmaceutical-sciences",
+    "medicinal-chemistry",
+    "chemical-biology",
     "bioactivity",
     "pharmacology",
     "toxicology",
     "admet",
-    "agrochemical research",
+    "agrochemical-research",
     "genomics",
     "proteomics"
   ],

firstdata/sources/academic/chemistry/chemspider.json

@@ -14,13 +14,13 @@
   "country": null,
   "domains": [
     "chemistry",
-    "chemical structures",
-    "molecular properties",
-    "pharmaceutical sciences",
-    "materials science",
-    "organic chemistry",
-    "inorganic chemistry",
-    "chemical information"
+    "chemical-structures",
+    "molecular-properties",
+    "pharmaceutical-sciences",
+    "materials-science",
+    "organic-chemistry",
+    "inorganic-chemistry",
+    "chemical-information"
   ],
   "geographic_scope": "global",
   "update_frequency": "daily",

firstdata/sources/academic/chemistry/drugbank.json

@@ -13,15 +13,15 @@
   "api_url": "https://docs.drugbank.com",
   "country": null,
   "domains": [
-    "pharmaceutical sciences",
-    "drug discovery",
-    "drug development",
+    "pharmaceutical-sciences",
+    "drug-discovery",
+    "drug-development",
     "pharmacology",
-    "medicinal chemistry",
+    "medicinal-chemistry",
     "bioinformatics",
     "cheminformatics",
-    "clinical pharmacology",
-    "drug metabolism",
+    "clinical-pharmacology",
+    "drug-metabolism",
     "toxicology"
   ],
   "geographic_scope": "global",

firstdata/sources/academic/economics/bis-statistics.json

@@ -13,16 +13,16 @@
   "api_url": "https://stats.bis.org/api-doc/v2/",
   "country": null,
   "domains": [
-    "international banking",
-    "debt securities",
-    "credit markets",
-    "foreign exchange",
+    "international-banking",
+    "debt-securities",
+    "credit-markets",
+    "foreign-exchange",
     "derivatives",
-    "property prices",
-    "consumer prices",
-    "global liquidity",
-    "payment systems",
-    "central bank statistics"
+    "property-prices",
+    "consumer-prices",
+    "global-liquidity",
+    "payment-systems",
+    "central-bank-statistics"
   ],
   "geographic_scope": "global",
   "update_frequency": "quarterly",

firstdata/sources/academic/economics/conference-board.json

@@ -14,11 +14,11 @@
   "country": null,
   "domains": [
     "economics",
-    "business cycles",
-    "consumer confidence",
-    "labor markets",
+    "business-cycles",
+    "consumer-confidence",
+    "labor-markets",
     "employment",
-    "economic forecasting"
+    "economic-forecasting"
   ],
   "geographic_scope": "global",
   "update_frequency": "monthly",

firstdata/sources/academic/health/ghdx.json

@@ -17,10 +17,10 @@
     "demographics",
     "epidemiology",
     "mortality",
-    "disease burden",
-    "health financing",
-    "risk factors",
-    "health systems"
+    "disease-burden",
+    "health-financing",
+    "risk-factors",
+    "health-systems"
   ],
   "geographic_scope": "global",
   "update_frequency": "irregular",
@@ -68,4 +68,4 @@
     ]
   },
   "authority_level": "research"
-}
+}

firstdata/sources/academic/health/tcga.json

@@ -13,13 +13,13 @@
   "api_url": "https://gdc.cancer.gov/developers/gdc-application-programming-interface-api",
   "country": "US",
   "domains": [
-    "cancer genomics",
+    "cancer-genomics",
     "oncology",
-    "molecular biology",
+    "molecular-biology",
     "genomics",
     "bioinformatics",
-    "precision medicine",
-    "biomedical research"
+    "precision-medicine",
+    "biomedical-research"
   ],
   "geographic_scope": "national",
   "update_frequency": "irregular",
@@ -74,4 +74,4 @@
     ]
   },
   "authority_level": "government"
-}
+}

firstdata/sources/academic/multidisciplinary/owid.json

@@ -13,7 +13,7 @@
   "api_url": "https://docs.owid.io/projects/etl/api/",
   "country": null,
   "domains": [
-    "global development",
+    "global-development",
     "health",
     "energy",
     "environment",

firstdata/sources/academic/physics/cern-open-data.json

@@ -13,13 +13,13 @@
   "api_url": "https://github.com/cernopendata/opendata.cern.ch",
   "country": null,
   "domains": [
-    "particle physics",
-    "high energy physics",
-    "nuclear physics",
-    "experimental physics",
-    "computational physics",
-    "data science",
-    "machine learning"
+    "particle-physics",
+    "high-energy-physics",
+    "nuclear-physics",
+    "experimental-physics",
+    "computational-physics",
+    "data-science",
+    "machine-learning"
   ],
   "geographic_scope": "global",
   "update_frequency": "irregular",

firstdata/sources/academic/physics/crystallography-open-database.json

@@ -14,7 +14,7 @@
   "country": null,
   "domains": [
     "crystallography",
-    "materials science",
+    "materials-science",
     "chemistry",
     "physics",
     "mineralogy"

firstdata/sources/academic/social/afrobarometer.json

@@ -13,21 +13,21 @@
   "api_url": null,
   "country": null,
   "domains": [
-    "democracy and governance",
-    "political participation",
-    "elections and electoral systems",
-    "economic development",
-    "social issues",
-    "public services",
-    "citizen engagement",
-    "human rights",
-    "gender equality",
-    "corruption and accountability",
-    "security and conflict",
-    "youth development",
-    "health and education",
+    "democracy-and-governance",
+    "political-participation",
+    "elections-and-electoral-systems",
+    "economic-development",
+    "social-issues",
+    "public-services",
+    "citizen-engagement",
+    "human-rights",
+    "gender-equality",
+    "corruption-and-accountability",
+    "security-and-conflict",
+    "youth-development",
+    "health-and-education",
     "infrastructure",
-    "environmental issues"
+    "environmental-issues"
   ],
   "geographic_scope": "regional",
   "update_frequency": "irregular",

firstdata/sources/academic/social/asian-barometer.json

@@ -13,13 +13,13 @@
   "api_url": null,
   "country": null,
   "domains": [
-    "political science",
-    "democracy studies",
-    "public opinion",
+    "political-science",
+    "democracy-studies",
+    "public-opinion",
     "governance",
-    "political values",
-    "electoral studies",
-    "social science"
+    "political-values",
+    "electoral-studies",
+    "social-science"
   ],
   "geographic_scope": "regional",
   "update_frequency": "irregular",

firstdata/sources/china/national/china-mps.json

@@ -15,7 +15,7 @@
   "country": "CN",
   "domains": [
     "demographics",
-    "public safety",
+    "public-safety",
     "migration",
     "social"
   ],

firstdata/sources/countries/asia/dosm.json

@@ -15,17 +15,17 @@
   "geographic_scope": "national",
   "country": "MY",
   "domains": [
-    "economic statistics",
-    "social statistics",
-    "demographic statistics",
-    "population & census",
-    "national accounts",
-    "labour market",
-    "prices & inflation",
-    "manufacturing & industry",
+    "economic-statistics",
+    "social-statistics",
+    "demographic-statistics",
+    "population-and-census",
+    "national-accounts",
+    "labour-market",
+    "prices-and-inflation",
+    "manufacturing-and-industry",
     "agriculture",
-    "external trade",
-    "household income & expenditure"
+    "external-trade",
+    "household-income-and-expenditure"
   ],
   "update_frequency": "irregular",
   "data_content": {