refdatakit 0.1.0__py3-none-any.whl

refdatakit/data/datasets/manifest.json

@@ -0,0 +1 @@
+{"datasets":[{"additional_sources":[{"attribution":"Unicode CLDR 49; only language entries marked official are included. Full license notice: licenses/UNICODE-3.0.txt.","data_as_of":"2026-11-08","fields":["official_languages"],"license":"Unicode-3.0","source_url":"https://raw.githubusercontent.com/unicode-org/cldr-json/a198dbf17e1d2314a76b84b30904b87a5f8618bb/cldr-json/cldr-core/supplemental/territoryInfo.json"}],"attribution":"GeoNames countryInfo.txt; language list ordering follows the source speaker ordering.","data_as_of":"2026-11-08","license":"CC BY 4.0","path":"datasets/countries/data.json","sha256":"2f5cfd2eb9c604547e716975dd0a749020935f4960eee541f4c9c1df44cf914e","source_url":"https://download.geonames.org/export/dump/countryInfo.txt"},{"attribution":"Wikidata contributors, items Q459723, Q158087, Q330158, Q501696, Q19594930, Q379382, Q876023, and Q459732","license":"CC0-1.0","path":"datasets/subdivisions/by-country/BD.json","sha256":"9e6dd3676804e1941ccfb90e2462c1ea806fea1aee2ec8a4e0f10ed5a779cb38","source_url":"https://www.wikidata.org/w/api.php?action=wbgetentities&ids=Q459723%7CQ158087%7CQ330158%7CQ501696%7CQ19594930%7CQ379382%7CQ876023%7CQ459732&props=labels%7Cclaims&languages=en%7Cbn&format=json"},{"additional_sources":[{"attribution":"Wikipedia contributors (English)","fields":["name","aliases"],"license":"CC BY-SA 4.0","source_url":"https://en.wikipedia.org/wiki/Chattogram"},{"attribution":"Bangladesh institutional master data supplied by a RefDataKit contributor in bangladesh_complete_institutions_master.json.","fields":["name","aliases"],"license":"MIT","source_url":"https://github.com/rezwan4029/refdatakit"},{"attribution":"Bengali renderings prepared by RefDataKit contributors from the English names in the supplied dataset.","fields":["localized_names.bn"],"license":"MIT","source_url":"https://github.com/rezwan4029/refdatakit"}],"attribution":"Wikidata contributors, items Q747840, Q376749, Q1354, Q243325, Q1006303, Q322155, Q994514, and Q466221","license":"CC0-1.0","path":"datasets/cities/by-country/BD.json","sha256":"8d1da8effe66c842ee7cc1bf438ff43fcffab15362bcdec54396a3228609966c","source_url":"https://www.wikidata.org/w/api.php?action=wbgetentities&ids=Q747840%7CQ376749%7CQ1354%7CQ243325%7CQ1006303%7CQ322155%7CQ994514%7CQ466221&props=labels%7Cclaims&languages=en%7Cbn&format=json"},{"attribution":"Wikidata contributors, items Q9270","license":"CC0-1.0","path":"datasets/cities/by-country/BT.json","sha256":"6897a82eb28a84bdb8a79177f0a145711515ebef338ffef174170ad323b169db","source_url":"https://www.wikidata.org/w/api.php?action=wbgetentities&ids=Q9270&props=labels%7Cclaims&languages=en&format=json"},{"attribution":"Wikidata contributors, items Q35381, Q489744, Q215277, Q3522428, Q867213, Q319366, Q810963, Q13360574","license":"CC0-1.0","path":"datasets/cities/by-country/LK.json","sha256":"484b855fb9a134787d9dde50a1b5da5a8f886adee9eac9151652d155294e80a3","source_url":"https://www.wikidata.org/w/api.php?action=wbgetentities&ids=Q13360574%7CQ215277%7CQ319366%7CQ3522428%7CQ35381%7CQ489744%7CQ810963%7CQ867213&props=labels%7Cclaims&languages=en&format=json"},{"additional_sources":[{"attribution":"Wikipedia contributors (English)","fields":["population for wikidata:Q3038674 (4,815, 2022 census)"],"license":"CC BY-SA 4.0","source_url":"https://en.wikipedia.org/wiki/Gan_(Laamu_Atoll)"}],"attribution":"Wikidata contributors, items Q9347, Q3038674","license":"CC0-1.0","path":"datasets/cities/by-country/MV.json","sha256":"50f037085acfd0d564dea5c4bbda1fa744315735c98d5a70b01362a8010b3b72","source_url":"https://www.wikidata.org/w/api.php?action=wbgetentities&ids=Q3038674%7CQ9347&props=labels%7Cclaims&languages=en&format=json"},{"attribution":"Wikidata contributors, items Q3037, Q1517030, Q576437, Q6647, Q6640, Q8254","license":"CC0-1.0","path":"datasets/cities/by-country/NP.json","sha256":"f7bd0a71e6b4beb01ad0644708505d1a673cadfa6a625c1e7d15299588ddb590","source_url":"https://www.wikidata.org/w/api.php?action=wbgetentities&ids=Q1517030%7CQ3037%7CQ576437%7CQ6640%7CQ6647%7CQ8254&props=labels%7Cclaims&languages=en&format=json"},{"attribution":"Wikidata contributors, items Q334","license":"CC0-1.0","path":"datasets/cities/by-country/SG.json","sha256":"2e549c2c2671fb2d0773dab5d9a95d5c4c7c7a801f534d0a1d6043e4dddd2bb3","source_url":"https://www.wikidata.org/w/api.php?action=wbgetentities&ids=Q334&props=labels%7Cclaims&languages=en%7Cms%7Cta%7Czh&format=json"},{"additional_sources":[{"attribution":"Wikipedia contributors (Bengali)","fields":["names.languages (bengali)"],"license":"CC BY-SA 4.0","source_url":"https://bn.wikipedia.org"},{"attribution":"Bangladesh institutional master data supplied by a RefDataKit contributor in bangladesh_complete_institutions_master.json.","fields":["names.en","entity_type","tags","ownership","city_id"],"license":"MIT","source_url":"https://github.com/rezwan4029/refdatakit"},{"attribution":"Bengali renderings prepared by RefDataKit contributors from the English names in the supplied dataset.","fields":["names.languages.bn"],"license":"MIT","source_url":"https://github.com/rezwan4029/refdatakit"}],"attribution":"Wikidata contributors, items Q1207503, Q1480421, Q29025023, Q3350920, Q4855005, Q4855319, Q506330, Q5233952, Q7494644, Q7895267","license":"CC0-1.0","path":"datasets/institutions/by-country/BD.json","sha256":"8b42214e6d91c72528234272f920c01a1992f6d07a7fe4ea8fe1e3d9c82c2585","source_url":"https://www.wikidata.org/w/api.php?action=wbgetentities&ids=Q1207503%7CQ1480421%7CQ29025023%7CQ3350920%7CQ4855005%7CQ4855319%7CQ506330%7CQ5233952%7CQ7494644%7CQ7895267&props=labels%7Cclaims&languages=bn%7Cen&format=json"},{"additional_sources":[{"attribution":"Wikipedia contributors (English)","fields":["names.en for wikidata:Q4314988 (official full name)"],"license":"CC BY-SA 4.0","source_url":"https://en.wikipedia.org/wiki/Jigme_Dorji_Wangchuck_National_Referral_Hospital"},{"attribution":"WHO Regional Office for South-East Asia","fields":["names.en for wikidata:Q4314988 (official full name)"],"license":"Not stated by source; public web page used for factual verification","source_url":"https://apps.searo.who.int/PHI/Institute/Details/104"},{"attribution":"RefDataKit contributors; localized names translated from English names in this contribution.","fields":["names.languages.dz"],"license":"MIT","source_url":"https://github.com/rezwan4029/refdatakit"}],"attribution":"Wikidata contributors, items Q2640138, Q4201619, Q4314988, Q86663201","license":"CC0-1.0","path":"datasets/institutions/by-country/BT.json","sha256":"23d18fd87d122a96b756e0033827ed31f9dcbd35eb07b71fa8ede4483ab64a64","source_url":"https://www.wikidata.org/w/api.php?action=wbgetentities&ids=Q2640138%7CQ4201619%7CQ4314988%7CQ86663201&props=labels%7Cclaims&languages=dz%7Cen&format=json"},{"additional_sources":[{"attribution":"Wikipedia contributors (Sinhala)","fields":["names.languages (sinhala)"],"license":"CC BY-SA 4.0","source_url":"https://si.wikipedia.org"},{"attribution":"Wikipedia contributors (Tamil)","fields":["names.languages (tamil)"],"license":"CC BY-SA 4.0","source_url":"https://ta.wikipedia.org"},{"attribution":"University of Ruhuna","fields":["city_id for wikidata:Q12975239 (main campus Wellamadama, Matara)"],"license":"Not stated by source; public web page used for factual verification","source_url":"https://www.ruh.ac.lk/index.php/en/about/university-history"},{"attribution":"Wikipedia contributors (English)","fields":["city_id for wikidata:Q12975239","names.languages.si for wikidata:Q12975239 (infobox Sinhala name)"],"license":"CC BY-SA 4.0","source_url":"https://en.wikipedia.org/wiki/University_of_Ruhuna"},{"attribution":"RefDataKit contributors; localized names translated from English names in this contribution.","fields":["names.languages.si","names.languages.ta"],"license":"MIT","source_url":"https://github.com/rezwan4029/refdatakit"}],"attribution":"Wikidata contributors, items Q12975239, Q16988751, Q24942979, Q3083280, Q3399947, Q3523254, Q3534731, Q4869912, Q5316328, Q6121967, Q6470509, Q720953, Q720958","license":"CC0-1.0","path":"datasets/institutions/by-country/LK.json","sha256":"21d2651ce9245d06c0946df12cccaf43f03afa2a1ac1e4f280bd4965166028da","source_url":"https://www.wikidata.org/w/api.php?action=wbgetentities&ids=Q12975239%7CQ16988751%7CQ24942979%7CQ3083280%7CQ3399947%7CQ3523254%7CQ3534731%7CQ4869912%7CQ5316328%7CQ6121967%7CQ6470509%7CQ720953%7CQ720958&props=labels%7Cclaims&languages=en%7Csi%7Cta&format=json"},{"additional_sources":[{"attribution":"Wikipedia contributors (Divehi)","fields":["names.languages (divehi)"],"license":"CC BY-SA 4.0","source_url":"https://dv.wikipedia.org"},{"attribution":"Wikipedia contributors (English)","fields":["city_id for wikidata:Q5520449 (Gan, Laamu Atoll)"],"license":"CC BY-SA 4.0","source_url":"https://en.wikipedia.org/wiki/Gan_Regional_Hospital"},{"attribution":"RefDataKit contributors; localized names translated from English names in this contribution.","fields":["names.languages.dv"],"license":"MIT","source_url":"https://github.com/rezwan4029/refdatakit"}],"attribution":"Wikidata contributors, items Q25110403, Q4120538, Q4651138, Q5520449, Q6024972","license":"CC0-1.0","path":"datasets/institutions/by-country/MV.json","sha256":"8ec7fa14ae48f74a606f62027d2cf0324dcba207303dbebee26a4a21bae72a70","source_url":"https://www.wikidata.org/w/api.php?action=wbgetentities&ids=Q25110403%7CQ4120538%7CQ4651138%7CQ5520449%7CQ6024972&props=labels%7Cclaims&languages=dv%7Cen&format=json"},{"additional_sources":[{"attribution":"Wikipedia contributors (Nepali)","fields":["names.languages (nepali)"],"license":"CC BY-SA 4.0","source_url":"https://ne.wikipedia.org"},{"attribution":"Kathmandu University","fields":["city_id for wikidata:Q6376965 (Dhulikhel campus; Wikidata P131 lists Kathmandu District only)"],"license":"Not stated by source; public web page used for factual verification","source_url":"https://ku.edu.np/"},{"attribution":"Wikipedia contributors (English)","fields":["city_id for wikidata:Q588239 (Kirtipur campus)","city_id for wikidata:Q6376965"],"license":"CC BY-SA 4.0","source_url":"https://en.wikipedia.org/wiki/Kathmandu_University"}],"attribution":"Wikidata contributors, items Q13181748, Q13184064, Q13186297, Q15196996, Q3630498, Q4833866, Q5269864, Q588239, Q6365469, Q6376965","license":"CC0-1.0","path":"datasets/institutions/by-country/NP.json","sha256":"a8d4012d81a20321f6963cb24f527ec4761c77dffc922474afa723466b6bf03e","source_url":"https://www.wikidata.org/w/api.php?action=wbgetentities&ids=Q13181748%7CQ13184064%7CQ13186297%7CQ15196996%7CQ3630498%7CQ4833866%7CQ5269864%7CQ588239%7CQ6365469%7CQ6376965&props=labels%7Cclaims&languages=en%7Cne&format=json"},{"additional_sources":[{"attribution":"Wikipedia contributors (Malay)","fields":["names.languages (malay)"],"license":"CC BY-SA 4.0","source_url":"https://ms.wikipedia.org"},{"attribution":"Wikipedia contributors (Tamil)","fields":["names.languages (tamil)"],"license":"CC BY-SA 4.0","source_url":"https://ta.wikipedia.org"},{"attribution":"Wikipedia contributors (Chinese)","fields":["names.languages (chinese)"],"license":"CC BY-SA 4.0","source_url":"https://zh.wikipedia.org"},{"attribution":"RefDataKit contributors; localized names translated from English names in this contribution.","fields":["names.languages.ms","names.languages.ta"],"license":"MIT","source_url":"https://github.com/rezwan4029/refdatakit"}],"attribution":"Wikidata contributors, items Q11081251, Q1320916, Q16999402, Q494179, Q6332329, Q6979219, Q721064, Q738236, Q7522983, Q7523022, Q7682145, Q950609","license":"CC0-1.0","path":"datasets/institutions/by-country/SG.json","sha256":"c9023f29bba75258b51fc1b9d4a2979fb1b1fbf4638326cde73add1a126fa87c","source_url":"https://www.wikidata.org/w/api.php?action=wbgetentities&ids=Q11081251%7CQ1320916%7CQ16999402%7CQ494179%7CQ6332329%7CQ6979219%7CQ721064%7CQ738236%7CQ7522983%7CQ7523022%7CQ7682145%7CQ950609&props=labels%7Cclaims&languages=en%7Cms%7Cta%7Czh&format=json"}],"vocabularies":{"entity_tags":["hospital","k12_school","medical_college","nursing_home","polytechnic","technical_training_institute","university"]}}

refdatakit/data/datasets/subdivisions/by-country/BD.json

@@ -0,0 +1 @@
+[{"code":"BD-A","country_code":"BD","level":"division","localized_names":[{"language":"bn","name":"বরিশাল বিভাগ"}],"name":"Barisal Division"},{"code":"BD-B","country_code":"BD","level":"division","localized_names":[{"language":"bn","name":"চট্টগ্রাম বিভাগ"}],"name":"Chattogram Division"},{"code":"BD-C","country_code":"BD","level":"division","localized_names":[{"language":"bn","name":"ঢাকা বিভাগ"}],"name":"Dhaka Division"},{"code":"BD-D","country_code":"BD","level":"division","localized_names":[{"language":"bn","name":"খুলনা বিভাগ"}],"name":"Khulna Division"},{"code":"BD-H","country_code":"BD","level":"division","localized_names":[{"language":"bn","name":"ময়মনসিংহ বিভাগ"}],"name":"Mymensingh Division"},{"code":"BD-E","country_code":"BD","level":"division","localized_names":[{"language":"bn","name":"রাজশাহী বিভাগ"}],"name":"Rajshahi Division"},{"code":"BD-F","country_code":"BD","level":"division","localized_names":[{"language":"bn","name":"রংপুর বিভাগ"}],"name":"Rangpur Division"},{"code":"BD-G","country_code":"BD","level":"division","localized_names":[{"language":"bn","name":"সিলেট বিভাগ"}],"name":"Sylhet Division"}]

refdatakit/data/schemas/city.schema.json

@@ -0,0 +1,84 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "City or Locality",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["id", "name", "country_code"],
+  "properties": {
+    "id": {
+      "type": "string",
+      "pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]*$",
+      "description": "Stable identifier that must not be derived from a mutable display name."
+    },
+    "name": {
+      "type": "string",
+      "minLength": 1
+    },
+    "country_code": {
+      "type": "string",
+      "pattern": "^[A-Z]{2}$"
+    },
+    "subdivision_code": {
+      "type": "string",
+      "pattern": "^[A-Z]{2}-[A-Z0-9]{1,3}$"
+    },
+    "coordinates": {
+      "$ref": "#/$defs/coordinates"
+    },
+    "population": {
+      "type": "integer",
+      "minimum": 0
+    },
+    "localized_names": {
+      "type": "array",
+      "items": {
+        "$ref": "#/$defs/localized_name"
+      }
+    },
+    "aliases": {
+      "type": "array",
+      "uniqueItems": true,
+      "items": {
+        "type": "string",
+        "minLength": 1
+      }
+    }
+  },
+  "$defs": {
+    "language": {
+      "type": "string",
+      "pattern": "^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$"
+    },
+    "localized_name": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": ["language", "name"],
+      "properties": {
+        "language": {
+          "$ref": "#/$defs/language"
+        },
+        "name": {
+          "type": "string",
+          "minLength": 1
+        }
+      }
+    },
+    "coordinates": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": ["latitude", "longitude"],
+      "properties": {
+        "latitude": {
+          "type": "number",
+          "minimum": -90,
+          "maximum": 90
+        },
+        "longitude": {
+          "type": "number",
+          "minimum": -180,
+          "maximum": 180
+        }
+      }
+    }
+  }
+}

refdatakit/data/schemas/country.schema.json

@@ -0,0 +1,98 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "Country",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["code", "name", "official_languages"],
+  "properties": {
+    "code": {
+      "type": "string",
+      "pattern": "^[A-Z]{2}$",
+      "description": "ISO 3166-1 alpha-2 code."
+    },
+    "name": {
+      "type": "string",
+      "minLength": 1
+    },
+    "alpha3_code": {
+      "type": "string",
+      "pattern": "^[A-Z]{3}$"
+    },
+    "numeric_code": {
+      "type": "string",
+      "pattern": "^[0-9]{3}$"
+    },
+    "official_languages": {
+      "type": "array",
+      "uniqueItems": true,
+      "items": {
+        "$ref": "#/$defs/language"
+      },
+      "description": "Known nationally official languages. An empty array means no value has been contributed or verified; it does not assert that the country has no official language."
+    },
+    "commonly_spoken_languages": {
+      "type": "array",
+      "uniqueItems": true,
+      "items": {
+        "$ref": "#/$defs/language"
+      },
+      "description": "Known commonly spoken languages from the sources listed in the manifest. An empty array means no value has been contributed or verified."
+    },
+    "centroid": {
+      "$ref": "#/$defs/coordinates",
+      "description": "Approximate country-level representative point; not a precise address."
+    },
+    "localized_names": {
+      "type": "array",
+      "items": {
+        "$ref": "#/$defs/localized_name"
+      }
+    },
+    "aliases": {
+      "type": "array",
+      "uniqueItems": true,
+      "items": {
+        "type": "string",
+        "minLength": 1
+      }
+    }
+  },
+  "$defs": {
+    "language": {
+      "type": "string",
+      "pattern": "^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$",
+      "description": "BCP 47 language tag."
+    },
+    "localized_name": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": ["language", "name"],
+      "properties": {
+        "language": {
+          "$ref": "#/$defs/language"
+        },
+        "name": {
+          "type": "string",
+          "minLength": 1
+        }
+      }
+    },
+    "coordinates": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": ["latitude", "longitude"],
+      "properties": {
+        "latitude": {
+          "type": "number",
+          "minimum": -90,
+          "maximum": 90
+        },
+        "longitude": {
+          "type": "number",
+          "minimum": -180,
+          "maximum": 180
+        }
+      }
+    }
+  }
+}

refdatakit/data/schemas/entity.schema.json

@@ -0,0 +1,174 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "Universal Directory Entity",
+  "type": "object",
+  "additionalProperties": false,
+  "required": [
+    "id",
+    "names",
+    "entity_type",
+    "country_code",
+    "city_id",
+    "tags"
+  ],
+  "properties": {
+    "id": {
+      "type": "string",
+      "pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]*$",
+      "description": "Stable identifier that must not be derived from a mutable display name."
+    },
+    "names": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": [
+        "en",
+        "languages"
+      ],
+      "properties": {
+        "en": {
+          "type": "string",
+          "minLength": 1
+        },
+        "languages": {
+          "type": "object",
+          "propertyNames": {
+            "pattern": "^[a-z]{2}$"
+          },
+          "additionalProperties": {
+            "type": "string",
+            "minLength": 1
+          },
+          "description": "Partial names keyed by ISO 639-1 code for verified official non-English languages; unavailable translations may be omitted."
+        }
+      }
+    },
+    "entity_type": {
+      "enum": [
+        "school",
+        "college",
+        "university",
+        "corporation",
+        "civic_organization",
+        "religious_building",
+        "other"
+      ]
+    },
+    "country_code": {
+      "type": "string",
+      "pattern": "^[A-Z]{2}$"
+    },
+    "ownership": {
+      "type": "string",
+      "enum": [
+        "public",
+        "private"
+      ],
+      "description": "Optional public or private ownership classification when supported by the source."
+    },
+    "city_id": {
+      "type": "string",
+      "pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]*$"
+    },
+    "tags": {
+      "type": "array",
+      "minItems": 1,
+      "uniqueItems": true,
+      "items": {
+        "$ref": "#/$defs/tag"
+      },
+      "description": "Controlled classifications for an institution; multiple tags may apply."
+    },
+    "localized_aliases": {
+      "type": "array",
+      "items": {
+        "$ref": "#/$defs/localized_alias"
+      }
+    },
+    "languages": {
+      "type": "array",
+      "uniqueItems": true,
+      "items": {
+        "$ref": "#/$defs/language"
+      },
+      "description": "Languages used for instruction, services, or public-facing operations."
+    },
+    "website": {
+      "type": "string",
+      "format": "uri"
+    },
+    "domains": {
+      "type": "array",
+      "uniqueItems": true,
+      "items": {
+        "type": "string",
+        "format": "hostname"
+      }
+    },
+    "external_ids": {
+      "type": "array",
+      "uniqueItems": true,
+      "items": {
+        "$ref": "#/$defs/external_id"
+      }
+    }
+  },
+  "$defs": {
+    "tag": {
+      "type": "string",
+      "enum": [
+        "hospital",
+        "k12_school",
+        "medical_college",
+        "nursing_home",
+        "polytechnic",
+        "technical_training_institute",
+        "university"
+      ],
+      "description": "Generated from datasets/manifest.json vocabularies.entity_tags."
+    },
+    "language": {
+      "type": "string",
+      "pattern": "^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$",
+      "description": "BCP 47 language tag."
+    },
+    "localized_alias": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": [
+        "language",
+        "value"
+      ],
+      "properties": {
+        "language": {
+          "$ref": "#/$defs/language"
+        },
+        "value": {
+          "type": "string",
+          "minLength": 1
+        }
+      }
+    },
+    "external_id": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": [
+        "system",
+        "value"
+      ],
+      "properties": {
+        "system": {
+          "type": "string",
+          "minLength": 1
+        },
+        "value": {
+          "type": "string",
+          "minLength": 1
+        },
+        "url": {
+          "type": "string",
+          "format": "uri"
+        }
+      }
+    }
+  }
+}

refdatakit/data/schemas/manifest.schema.json

@@ -0,0 +1,94 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "RefDataKit Dataset Manifest",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["datasets", "vocabularies"],
+  "properties": {
+    "vocabularies": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": ["entity_tags"],
+      "properties": {
+        "entity_tags": {
+          "type": "array",
+          "minItems": 1,
+          "uniqueItems": true,
+          "items": {
+            "type": "string",
+            "pattern": "^[a-z][a-z0-9_]*$"
+          }
+        }
+      }
+    },
+    "datasets": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": ["path", "source_url", "license", "attribution", "sha256"],
+        "properties": {
+          "path": {
+            "type": "string",
+            "pattern": "^datasets/.+\\.json$"
+          },
+          "source_url": {
+            "type": "string",
+            "format": "uri"
+          },
+          "license": {
+            "type": "string",
+            "minLength": 1
+          },
+          "attribution": {
+            "type": "string",
+            "minLength": 1
+          },
+          "data_as_of": {
+            "type": "string",
+            "format": "date"
+          },
+          "additional_sources": {
+            "type": "array",
+            "items": {
+              "type": "object",
+              "additionalProperties": false,
+              "required": ["source_url", "license", "attribution", "fields"],
+              "properties": {
+                "source_url": {
+                  "type": "string",
+                  "format": "uri"
+                },
+                "license": {
+                  "type": "string",
+                  "minLength": 1
+                },
+                "attribution": {
+                  "type": "string",
+                  "minLength": 1
+                },
+                "data_as_of": {
+                  "type": "string",
+                  "format": "date"
+                },
+                "fields": {
+                  "type": "array",
+                  "minItems": 1,
+                  "uniqueItems": true,
+                  "items": {
+                    "type": "string",
+                    "minLength": 1
+                  }
+                }
+              }
+            }
+          },
+          "sha256": {
+            "type": "string",
+            "pattern": "^[a-f0-9]{64}$"
+          }
+        }
+      }
+    }
+  }
+}

refdatakit/data/schemas/subdivision.schema.json

@@ -0,0 +1,65 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "Administrative Subdivision",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["code", "country_code", "name", "level"],
+  "properties": {
+    "code": {
+      "type": "string",
+      "pattern": "^[A-Z]{2}-[A-Z0-9]{1,3}$",
+      "description": "ISO 3166-2 code when available; otherwise a stable country-scoped code."
+    },
+    "country_code": {
+      "type": "string",
+      "pattern": "^[A-Z]{2}$"
+    },
+    "name": {
+      "type": "string",
+      "minLength": 1
+    },
+    "level": {
+      "type": "string",
+      "minLength": 1,
+      "description": "Country-specific administrative level."
+    },
+    "parent_code": {
+      "type": "string",
+      "pattern": "^[A-Z]{2}-[A-Z0-9]{1,3}$"
+    },
+    "localized_names": {
+      "type": "array",
+      "items": {
+        "$ref": "#/$defs/localized_name"
+      }
+    },
+    "aliases": {
+      "type": "array",
+      "uniqueItems": true,
+      "items": {
+        "type": "string",
+        "minLength": 1
+      }
+    }
+  },
+  "$defs": {
+    "language": {
+      "type": "string",
+      "pattern": "^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$"
+    },
+    "localized_name": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": ["language", "name"],
+      "properties": {
+        "language": {
+          "$ref": "#/$defs/language"
+        },
+        "name": {
+          "type": "string",
+          "minLength": 1
+        }
+      }
+    }
+  }
+}

refdatakit/data.py

@@ -0,0 +1,48 @@
+from __future__ import annotations
+
+import json
+from importlib.resources import files
+from pathlib import Path
+from typing import Any
+
+from .country_codes import CountryCode
+
+
+def _records(relative_path: str) -> list[dict[str, Any]]:
+    resource = files("refdatakit").joinpath("data", "datasets", *relative_path.split("/"))
+    try:
+        return json.loads(resource.read_text(encoding="utf-8"))
+    except FileNotFoundError:
+        repository_file = Path(__file__).resolve().parents[4] / "datasets" / relative_path
+        try:
+            return json.loads(repository_file.read_text(encoding="utf-8"))
+        except FileNotFoundError:
+            return []
+
+
+def _country_path(country_code: CountryCode, kind: str) -> str:
+    if not isinstance(country_code, CountryCode):
+        raise TypeError("country_code must be a CountryCode member")
+    return f"{kind}/by-country/{country_code}.json"
+
+
+def get_countries() -> list[dict[str, Any]]:
+    return _records("countries/data.json")
+
+
+def get_country(country_code: CountryCode) -> dict[str, Any] | None:
+    if not isinstance(country_code, CountryCode):
+        raise TypeError("country_code must be a CountryCode member")
+    return next((country for country in get_countries() if country["code"] == country_code), None)
+
+
+def get_cities(country_code: CountryCode) -> list[dict[str, Any]]:
+    return _records(_country_path(country_code, "cities"))
+
+
+def get_subdivisions(country_code: CountryCode) -> list[dict[str, Any]]:
+    return _records(_country_path(country_code, "subdivisions"))
+
+
+def get_institutions(country_code: CountryCode) -> list[dict[str, Any]]:
+    return _records(_country_path(country_code, "institutions"))