{ "manifestVersion": 1, "dataset": { "id": "data-gov-ro", "name": "Romania open data catalogue (data.gov.ro)", "description": "The full catalogue of data.gov.ro, Romania's national open data portal: every published dataset, every downloadable file with its direct URL, and every publishing institution, refreshed daily. Metadata is standardised on the way in — licenses mapped to canonical identifiers, file formats normalised and bucketed into families, Romanian titles given accent-folded search columns — so the whole portal is searchable and joinable with plain SQL, and any tabular file it lists is one read_csv_auto() away.", "sourceUrl": "https://data.gov.ro/", "license": { "id": "CC-BY-4.0", "name": "Creative Commons Attribution 4.0 International", "url": "https://data.gov.ro/pages/licence", "attribution": "Catalogue metadata from data.gov.ro, the Romanian Government open data portal.", "notes": "This dataset republishes catalogue METADATA only (titles, descriptions, URLs, formats, license ids) — none of the files the catalogue points at. Each underlying dataset carries its own license, recorded per row in license_id (verbatim) and license_std (standardised): mostly CC-BY-4.0 and OGL-ROU-1.0 (both attribution licenses requiring credit to the publishing institution named in the organizations table), but not-specified occurs and at least one dataset is CC-BY-NC-4.0 (non-commercial). Anyone reusing the underlying files must check license_std for that dataset first — this catalogue's own license does not extend to them." }, "cadence": "daily", "tags": [ "romania", "open-data", "government", "catalogue", "ckan", "metadata" ], "sources": [] }, "ingest": { "id": "01M0YSBF6PDT7M5K34WHS2V01Z", "startedAt": "2026-08-26T10:20:18.518Z", "snapshotDate": "2026-08-26", "catalogSnapshotId": 4, "params": { "rows": 100, "maxPages": 0 } }, "baseUrl": "https://data-directory.fsn1.your-objectstorage.com/public/data-gov-ro", "catalog": { "url": "https://data-directory.fsn1.your-objectstorage.com/catalog/data-gov-ro/v/01M0YSBF6PDT7M5K34WHS2V01Z/catalog.ducklake", "latestUrl": "https://data-directory.fsn1.your-objectstorage.com/catalog/data-gov-ro/catalog.ducklake", "sha256": "929935accedb206644751c8e25d5073ef8dc208a2ef1648af480f9dd66804c88", "duckdbVersion": "v1.5.5", "attachExample": "ATTACH 'ducklake:https://data-directory.fsn1.your-objectstorage.com/catalog/data-gov-ro/catalog.ducklake' AS lake (READ_ONLY); SELECT * FROM lake.main.datasets LIMIT 5;" }, "tables": [ { "name": "datasets", "description": "One row per dataset (CKAN \"package\") published on data.gov.ro, carrying the most recent metadata the portal reports for it. A dataset is a titled collection of one or more downloadable files (see the resources table) owned by one public institution (see organizations). Rows are updated in place as institutions edit their metadata; first_seen_date / last_seen_date give the window over which this catalogue observed the dataset, so newly published datasets are the rows with a recent first_seen_date.", "rowCount": 5226, "lastRunRows": 5226, "totalBytes": 493543, "sortBy": [ "title_lc", "dataset_id" ], "searchColumns": [ "title" ], "primaryKey": [ "dataset_id" ], "writeMode": "upsert", "storage": "lake", "columns": [ { "name": "dataset_id", "type": "VARCHAR", "nullable": false, "description": "CKAN package id — a UUID for datasets created since ~2015, a legacy slug for the oldest ones. Stable across metadata edits; the primary key, and what resources.dataset_id joins to.", "min": "00138538-d1f2-4209-a14c-e4c12b6792f4", "max": "ffe7edc5-8f06-461e-8e74-c06fc9350b43", "distinctApprox": 5845 }, { "name": "name", "type": "VARCHAR", "nullable": false, "description": "URL slug of the dataset, unique on the portal. dataset_url is derived from it." }, { "name": "title", "type": "VARCHAR", "nullable": false, "description": "Display title as written by the publishing institution, usually in Romanian. Falls back to the slug when the portal reports no title." }, { "name": "title_lc", "type": "VARCHAR", "nullable": false, "description": "title, lowercased and accent-folded (ș/ş/s all match), for case- and accent-insensitive search. Query this, not lower(title) — a function on a column cannot use parquet statistics, and Romanian titles mix cedilla and comma diacritics inconsistently.", "min": "- lista organisme private autorizate romane autorizate de anpdca", "max": "– pni anghel saligny – stadiu implementare – 30 iunie 2023" }, { "name": "description", "type": "TEXT", "nullable": true, "description": "Free-text description (\"notes\") as written by the publisher, usually in Romanian. Quality varies from careful documentation to empty." }, { "name": "organization_id", "type": "VARCHAR", "nullable": true, "description": "Id of the publishing institution; joins to organizations.organization_id. Null only for the rare orphaned dataset the portal reports without an owner." }, { "name": "organization_name", "type": "VARCHAR", "nullable": true, "description": "URL slug of the publishing institution, denormalised for filtering without a join." }, { "name": "license_id", "type": "VARCHAR", "nullable": true, "description": "The portal's raw license id, verbatim. Messy by inheritance: 'uk-ogl' is stock CKAN's id that data.gov.ro reuses for the Romanian Open Government License, and null / 'notspecified' both occur. Prefer license_std for filtering." }, { "name": "license_std", "type": "VARCHAR", "nullable": false, "description": "Standardised license identifier, derived: CC-BY-4.0, OGL-ROU-1.0, ODC-PDDL-1.0, CC0-1.0, CC-BY-NC-4.0, ODbL-1.0 …; not-specified when the publisher chose none, other: for anything unmapped. 'uk-ogl' maps to OGL-ROU-1.0 because the portal itself titles it exactly that (its license page: datasets published before the 2020 CC-BY-4.0 recommendation are under Licența pentru o Guvernare Deschisă OGL-ROU 1.0 and remain so). Check this column before reusing the underlying files." }, { "name": "tags", "type": "JSON", "nullable": true, "description": "Tag names as a JSON string array, e.g. [\"CAEN\", \"NACE\"]. Null when the publisher set none — most datasets. Free vocabulary, not a taxonomy." }, { "name": "groups", "type": "JSON", "nullable": true, "description": "Portal category (CKAN group) names as a JSON string array. Null when the dataset is in no category — the common case on this portal." }, { "name": "resource_count", "type": "INTEGER", "nullable": false, "description": "Number of usable resource rows this dataset contributes to the resources table.", "unit": "resources" }, { "name": "metadata_created", "type": "TIMESTAMP", "nullable": true, "description": "When the dataset was created on the portal, as reported — a naive local-time wall clock with no timezone, stored verbatim. Null on the oldest datasets, migrated in bulk in 2013 before the portal kept creation times." }, { "name": "metadata_modified", "type": "TIMESTAMP", "nullable": true, "description": "When the dataset metadata was last edited, as reported by the portal (naive local-time wall clock, stored verbatim). The freshness signal: recently maintained datasets have a recent value." }, { "name": "dataset_url", "type": "VARCHAR", "nullable": false, "description": "Human-readable dataset page on the portal." }, { "name": "first_seen_date", "type": "DATE", "nullable": false, "description": "First run day (UTC) on which this catalogue saw the dataset. Maintained by the upsert loader — never overwritten, only widened. A recent value means a newly published dataset." }, { "name": "last_seen_date", "type": "DATE", "nullable": false, "description": "Most recent run day (UTC) on which the portal still listed the dataset. A stale value means the dataset was removed or hidden upstream; rows are never deleted here." } ], "files": [ { "url": "https://data-directory.fsn1.your-objectstorage.com/public/data-gov-ro/v/01M0YSBF6PDT7M5K34WHS2V01Z/datasets.parquet", "sizeBytes": 493543, "rowCount": 5226, "etag": "\"b18dd9159d993f95901c7efd4dd0890c\"", "stats": { "title_lc": { "min": "- lista organisme private autorizate romane autorizate de anpdca", "max": "– pni anghel saligny – stadiu implementare – 30 iunie 2023" }, "dataset_id": { "min": "00138538-d1f2-4209-a14c-e4c12b6792f4", "max": "ffe7edc5-8f06-461e-8e74-c06fc9350b43" } } } ], "example": [ { "dataset_id": "f50d6352-8bd9-40f5-b64b-9a43cc72b50f", "name": "lista-organisme-private-autorizate-romane-autorizate-de-anpdca", "title": "- Lista Organisme Private Autorizate române autorizate de ANPDCA", "title_lc": "- lista organisme private autorizate romane autorizate de anpdca", "description": "Lista Organisme Private Autorizate române autorizate de ANPDCA să desfășoare activități și servicii în adopția internă, conform HG 233/2012 modificată prin HG 579/2016", "organization_id": "75425491-cb6a-41cc-9bdc-c4842752b4ab", "organization_name": "autoritatea-nationala-pentru-protectia-drepturilor-copilului-si-adoptie", "license_id": "uk-ogl", "license_std": "OGL-ROU-1.0", "tags": "[\"adoptie\"]", "groups": null, "resource_count": 2, "metadata_created": "2018-06-25T15:14:36.028Z", "metadata_modified": "2018-09-17T13:28:06.665Z", "dataset_url": "https://data.gov.ro/dataset/lista-organisme-private-autorizate-romane-autorizate-de-anpdca", "first_seen_date": "2026-08-26T00:00:00.000Z", "last_seen_date": "2026-08-26T00:00:00.000Z" }, { "dataset_id": "e2ab42bd-afdb-4193-9db5-5a0f245b66fb", "name": "07-13-11-2022", "title": "07-13.11.2022", "title_lc": "07-13.11.2022", "description": "DATE DESCHISE", "organization_id": "2ce9f7f5-21df-4312-af3d-184214a3ae61", "organization_name": "inspectoratul-general-pentru-imigrari", "license_id": "CC-BY-4.0", "license_std": "CC-BY-4.0", "tags": "[\"AZIL\",\"UCRAINA\"]", "groups": null, "resource_count": 1, "metadata_created": "2022-11-16T12:44:44.892Z", "metadata_modified": "2022-11-16T12:46:35.333Z", "dataset_url": "https://data.gov.ro/dataset/07-13-11-2022", "first_seen_date": "2026-08-26T00:00:00.000Z", "last_seen_date": "2026-08-26T00:00:00.000Z" } ] }, { "name": "resources", "description": "One row per downloadable file or endpoint (\"resource\") attached to a dataset on data.gov.ro. This is the actionable table: download_url is a direct link DuckDB can often read in place (e.g. read_csv_auto(download_url) for format = 'CSV'). Filter format_group = 'tabular' for files that load as tables. Rows update in place as institutions replace files; join datasets via dataset_id for the title, license and publisher.", "rowCount": 39543, "lastRunRows": 39543, "totalBytes": 3313383, "sortBy": [ "dataset_id", "resource_id" ], "searchColumns": [ "name" ], "primaryKey": [ "resource_id" ], "writeMode": "upsert", "storage": "lake", "columns": [ { "name": "resource_id", "type": "VARCHAR", "nullable": false, "description": "CKAN resource id (UUID). Stable across file replacements; the primary key.", "min": "0000b018-ad09-4632-b069-3b54822e23f4", "max": "ffff0368-2a82-49a4-82f2-d3a5654656f0", "distinctApprox": 31360 }, { "name": "dataset_id", "type": "VARCHAR", "nullable": false, "description": "Id of the dataset this file belongs to; joins to datasets.dataset_id.", "min": "00138538-d1f2-4209-a14c-e4c12b6792f4", "max": "ffe7edc5-8f06-461e-8e74-c06fc9350b43" }, { "name": "name", "type": "VARCHAR", "nullable": true, "description": "File name or resource title as the publisher wrote it." }, { "name": "name_lc", "type": "VARCHAR", "nullable": true, "description": "name, lowercased and accent-folded, for case- and accent-insensitive search. Query this, not lower(name)." }, { "name": "description", "type": "TEXT", "nullable": true, "description": "Free-text description of the file, usually Romanian; often empty." }, { "name": "format", "type": "VARCHAR", "nullable": true, "description": "File format, standardised from the portal's free text: trimmed, leading dot stripped, uppercased — 'csv', '.csv' and 'CSV' all become 'CSV'. Publisher-declared, so it can still lie about the bytes behind the URL." }, { "name": "format_group", "type": "VARCHAR", "nullable": true, "description": "Format bucketed into a standard family, derived from format: tabular (CSV/XLSX/ODS/PARQUET…), structured (JSON/XML/RDF…), geospatial (GeoJSON/SHP/KML…), document (PDF/DOC/HTML…), archive (ZIP/RAR…), image, api, or other. The one-predicate answer to \"which files can I actually load as data\"." }, { "name": "mimetype", "type": "VARCHAR", "nullable": true, "description": "MIME type as recorded by the portal." }, { "name": "size_bytes", "type": "BIGINT", "nullable": true, "description": "File size in bytes as recorded by the portal. Null for external links and datastore resources; BIGINT because bulk uploads exceed 2 GiB.", "unit": "bytes" }, { "name": "download_url", "type": "VARCHAR", "nullable": true, "description": "Direct download URL. For uploaded files it is served by the portal itself; for linked resources it points at the institution's own server and can rot. This is the column that turns the catalogue into data: pass it to read_csv_auto / read_parquet / read_json_auto in DuckDB." }, { "name": "created", "type": "TIMESTAMP", "nullable": true, "description": "When the resource was added, as reported by the portal (naive local-time wall clock, stored verbatim)." }, { "name": "last_modified", "type": "TIMESTAMP", "nullable": true, "description": "When the file behind the resource last changed, as reported (naive local-time wall clock, stored verbatim). Null when the portal never recorded a modification." }, { "name": "datastore_active", "type": "BOOLEAN", "nullable": true, "description": "True when the file is also loaded into the portal's own DataStore (queryable via its datastore_search API), not just stored as a blob." }, { "name": "first_seen_date", "type": "DATE", "nullable": false, "description": "First run day (UTC) on which this catalogue saw the resource. Maintained by the upsert loader — never overwritten, only widened." }, { "name": "last_seen_date", "type": "DATE", "nullable": false, "description": "Most recent run day (UTC) on which the portal still listed the resource. A stale value means the file was removed or replaced upstream." } ], "files": [ { "url": "https://data-directory.fsn1.your-objectstorage.com/public/data-gov-ro/v/01M0YSBF6PDT7M5K34WHS2V01Z/resources.parquet", "sizeBytes": 3313383, "rowCount": 39543, "etag": "\"b5a50cff792a0b486bfddff86bccd8b4\"", "stats": { "dataset_id": { "min": "00138538-d1f2-4209-a14c-e4c12b6792f4", "max": "ffe7edc5-8f06-461e-8e74-c06fc9350b43" }, "resource_id": { "min": "0000b018-ad09-4632-b069-3b54822e23f4", "max": "ffff0368-2a82-49a4-82f2-d3a5654656f0" } } } ], "example": [ { "resource_id": "01c5935f-7cc5-4381-94b6-10864e37d5d4", "dataset_id": "00138538-d1f2-4209-a14c-e4c12b6792f4", "name": "Situaţia-plăţilor-restante-mai-mari-de-90-de-zile-înregistrate-la-nivelul-bugetului-general-al-unităţilor/subdiviziunilor-adminisitrativ-teritoriale-la-data-de-31.01.2015-", "name_lc": "situatia-platilor-restante-mai-mari-de-90-de-zile-inregistrate-la-nivelul-bugetului-general-al-unitatilor/subdiviziunilor-adminisitrativ-teritoriale-la-data-de-31.01.2015-", "description": null, "format": "XLS", "format_group": "tabular", "mimetype": null, "size_bytes": null, "download_url": "https://data.gov.ro/dataset/00138538-d1f2-4209-a14c-e4c12b6792f4/resource/01c5935f-7cc5-4381-94b6-10864e37d5d4/download/arierateuat31012015.xls", "created": "2018-08-08T13:17:38.380Z", "last_modified": "2018-08-08T13:17:37.808Z", "datastore_active": false, "first_seen_date": "2026-08-26T00:00:00.000Z", "last_seen_date": "2026-08-26T00:00:00.000Z" }, { "resource_id": "0384d7a5-637c-4a64-9132-c2f834407e44", "dataset_id": "00138538-d1f2-4209-a14c-e4c12b6792f4", "name": "ArierateBGCianuarie2017.xls", "name_lc": "arieratebgcianuarie2017.xls", "description": null, "format": "XLS", "format_group": "tabular", "mimetype": null, "size_bytes": null, "download_url": "https://data.gov.ro/dataset/00138538-d1f2-4209-a14c-e4c12b6792f4/resource/0384d7a5-637c-4a64-9132-c2f834407e44/download/arieratebgcianuarie2017.xls", "created": "2018-08-03T08:36:10.342Z", "last_modified": "2018-08-03T08:36:10.091Z", "datastore_active": false, "first_seen_date": "2026-08-26T00:00:00.000Z", "last_seen_date": "2026-08-26T00:00:00.000Z" } ] }, { "name": "organizations", "description": "One row per publishing institution (\"organization\") on data.gov.ro — ministries, agencies, county councils, city halls. dataset_count makes it the leaderboard of who actually publishes; join from datasets.organization_id for everything else. Rows update in place; institutions are effectively never deleted.", "rowCount": 130, "lastRunRows": 130, "totalBytes": 16589, "sortBy": [ "title_lc", "organization_id" ], "searchColumns": [ "title" ], "primaryKey": [ "organization_id" ], "writeMode": "upsert", "storage": "lake", "columns": [ { "name": "organization_id", "type": "VARCHAR", "nullable": false, "description": "CKAN organization id (UUID). Stable; the primary key.", "min": "001b671a-b2fe-4a10-9036-ed1183699bcd", "max": "fe2a426f-a95a-4a5b-9115-6754f9abfb2c", "distinctApprox": 137 }, { "name": "name", "type": "VARCHAR", "nullable": true, "description": "URL slug of the institution on the portal. organization_url is derived from it." }, { "name": "title", "type": "VARCHAR", "nullable": false, "description": "Institution name as displayed on the portal, in Romanian. Falls back to the slug, then the id, when the portal reports no title." }, { "name": "title_lc", "type": "VARCHAR", "nullable": false, "description": "title, lowercased and accent-folded, for case- and accent-insensitive search. Query this, not lower(title).", "min": "administratia fluviala a dunarii de jos galati", "max": "unitatea executiva pentru finantarea invatamantului superior, cercetarii, dezvoltarii si inovarii" }, { "name": "description", "type": "TEXT", "nullable": true, "description": "Self-description of the institution, usually Romanian; often empty." }, { "name": "image_url", "type": "VARCHAR", "nullable": true, "description": "Logo URL as configured on the portal." }, { "name": "created", "type": "TIMESTAMP", "nullable": true, "description": "When the institution joined the portal, as reported (naive local-time wall clock, stored verbatim)." }, { "name": "dataset_count", "type": "INTEGER", "nullable": false, "description": "Number of active datasets this institution had in the most recent catalogue snapshot. Recomputed every run, so it tracks the portal, not our history.", "unit": "datasets" }, { "name": "organization_url", "type": "VARCHAR", "nullable": true, "description": "Institution page on the portal, listing all its datasets." }, { "name": "first_seen_date", "type": "DATE", "nullable": false, "description": "First run day (UTC) on which this catalogue saw the institution. Maintained by the upsert loader." }, { "name": "last_seen_date", "type": "DATE", "nullable": false, "description": "Most recent run day (UTC) on which the institution still had at least one dataset listed." } ], "files": [ { "url": "https://data-directory.fsn1.your-objectstorage.com/public/data-gov-ro/v/01M0YSBF6PDT7M5K34WHS2V01Z/organizations.parquet", "sizeBytes": 16589, "rowCount": 130, "etag": "\"5adab3de03a1fd8c392b099ed429dd63\"", "stats": { "title_lc": { "min": "administratia fluviala a dunarii de jos galati", "max": "unitatea executiva pentru finantarea invatamantului superior, cercetarii, dezvoltarii si inovarii" }, "organization_id": { "min": "001b671a-b2fe-4a10-9036-ed1183699bcd", "max": "fe2a426f-a95a-4a5b-9115-6754f9abfb2c" } } } ], "example": [ { "organization_id": "1ab59ede-8897-4137-852f-cfb32625cb97", "name": "administratia-fluviala-a-dunarii-de-jos-galati", "title": "Administrația Fluvială a Dunării de Jos Galați", "title_lc": "administratia fluviala a dunarii de jos galati", "description": null, "image_url": null, "created": "2025-02-28T11:05:29.872Z", "dataset_count": 1, "organization_url": "https://data.gov.ro/organization/administratia-fluviala-a-dunarii-de-jos-galati", "first_seen_date": "2026-08-26T00:00:00.000Z", "last_seen_date": "2026-08-26T00:00:00.000Z" }, { "organization_id": "a58aa693-eabc-4985-b11a-6b6d7afecd61", "name": "administratia-fondului-cultural-national", "title": "Administrația Fondului Cultural Național", "title_lc": "administratia fondului cultural national", "description": null, "image_url": "https://data.gov.ro/base/images/logoinst/logo.jpg", "created": "2016-11-28T15:44:19.174Z", "dataset_count": 10, "organization_url": "https://data.gov.ro/organization/administratia-fondului-cultural-national", "first_seen_date": "2026-08-26T00:00:00.000Z", "last_seen_date": "2026-08-26T00:00:00.000Z" } ] } ], "queryHints": { "examples": [ { "title": "Search the catalogue for a topic, diacritics-insensitively", "sql": "SELECT d.title, o.title AS institution, d.license_std, d.resource_count, d.dataset_url\nFROM datasets d\nLEFT JOIN organizations o ON o.organization_id = d.organization_id\nWHERE d.title_lc LIKE '%sanatate%'\nORDER BY d.metadata_modified DESC NULLS LAST\nLIMIT 25", "description": "Query title_lc, never lower(title): the folded column matches \"sanatate\" against \"sănătate\" and is the sort column, so a prefix predicate prunes." }, { "title": "Files DuckDB can load directly, for one dataset", "sql": "SELECT r.name, r.format, r.size_bytes, r.download_url\nFROM resources r\nJOIN datasets d ON d.dataset_id = r.dataset_id\nWHERE d.name = 'siruta' AND r.format_group = 'tabular'\nORDER BY r.resource_id", "description": "format_group = 'tabular' is the standardised filter; download_url feeds read_csv_auto / st_read straight from the portal." }, { "title": "Who publishes, and how much", "sql": "SELECT title, dataset_count, organization_url\nFROM organizations\nORDER BY dataset_count DESC\nLIMIT 20" }, { "title": "What appeared on the portal recently", "sql": "SELECT title, organization_name, first_seen_date, dataset_url\nFROM datasets\nWHERE first_seen_date >= current_date - INTERVAL 30 DAY\nORDER BY first_seen_date DESC", "description": "first_seen_date is maintained by the loader: new datasets carry a recent one." } ] }, "generatedAt": "2026-08-26T10:23:51.732Z" }