Open Data Catalog v2.0.0
dataset.json
Go to the documentation of this file.
1 {
2  "id": "http://dkan/api/v1/schema/dataset",
3  "title": "Project Open Data Dataset",
4  "description": "The metadata format for all federal open data. Validates a single JSON object entry (as opposed to entire Data.json catalog).",
5  "type": "object",
6  "required": [
7  "title",
8  "description",
9  "identifier",
10  "accessLevel",
11  "modified",
12  "keyword"
13  ],
14  "properties": {
15  "@type": {
16  "title": "Metadata Context",
17  "type": "string",
18  "description": "IRI for the JSON-LD data type. This should be dcat:Dataset for each Dataset.",
19  "default": "dcat:Dataset"
20  },
21  "title": {
22  "title": "Title",
23  "description": "Human-readable name of the asset. Should be in plain English and include sufficient detail to facilitate search and discovery.",
24  "type": "string",
25  "minLength": 1
26  },
27  "identifier": {
28  "title": "Unique Identifier",
29  "description": "A unique identifier for the dataset or API as maintained within an Agency catalog or database.",
30  "type": "string",
31  "minLength": 1
32  },
33  "description": {
34  "title": "Description",
35  "description": "Human-readable description (e.g., an abstract) with sufficient detail to enable a user to quickly understand whether the asset is of interest.",
36  "type": "string",
37  "minLength": 1
38  },
39  "accessLevel": {
40  "description": "The degree to which this dataset could be made publicly-available, regardless of whether it has been made available. Choices: public (Data asset is or could be made publicly available to all without restrictions), restricted public (Data asset is available under certain use restrictions), or non-public (Data asset is not available to members of the public).",
41  "title": "Public Access Level",
42  "type": "string",
43  "enum": [
44  "public",
45  "restricted public",
46  "non-public"
47  ],
48  "default": "public"
49  },
50  "accrualPeriodicity": {
51  "title": "Frequency",
52  "description": "Frequency with which dataset is published.",
53  "type": "string",
54  "enum": [
55  "R/P10Y",
56  "R/P4Y",
57  "R/P1Y",
58  "R/P2M",
59  "R/P3.5D",
60  "R/P1D",
61  "R/P2W",
62  "R/P6M",
63  "R/P2Y",
64  "R/P3Y",
65  "R/P0.33W",
66  "R/P0.33M",
67  "R/PT1S",
68  "R/P1M",
69  "R/P3M",
70  "R/P0.5M",
71  "R/P4M",
72  "R/P1W",
73  "R/PT1H",
74  "irregular"
75  ],
76  "enumNames": [
77  "Decennial",
78  "Quadrennial",
79  "Annual",
80  "Bimonthly",
81  "Semiweekly",
82  "Daily",
83  "Biweekly",
84  "Semiannual",
85  "Biennial",
86  "Triennial",
87  "Three times a week",
88  "Three times a month",
89  "Continuously updated",
90  "Monthly",
91  "Quarterly",
92  "Semimonthly",
93  "Three times a year",
94  "Weekly",
95  "Hourly",
96  "Irregular"
97  ]
98  },
99  "describedBy": {
100  "title": "Data Dictionary",
101  "description": "URL to the data dictionary for the dataset or API. Note that documentation other than a data dictionary can be referenced using Related Documents as shown in the expanded fields.",
102  "type": "string",
103  "format": "uri"
104  },
105  "describedByType": {
106  "title": "Data Dictionary Type",
107  "description": "The machine-readable file format (IANA Media Type or MIME Type) of the distribution’s describedBy URL.",
108  "type": "string"
109  },
110  "issued": {
111  "title": "Release Date",
112  "description": "Date of formal issuance.",
113  "type": "string"
114  },
115  "modified": {
116  "title": "Last Update",
117  "description": "Most recent date on which the dataset was changed, updated or modified.",
118  "type": "string"
119  },
120  "license": {
121  "title": "License",
122  "description": "The license dataset or API is published with. See <a href=\"https://project-open-data.cio.gov/open-licenses/\">Open Licenses</a> for more information.",
123  "type": "string",
124  "format": "uri"
125  },
126  "spatial": {
127  "title": "Spatial",
128  "description": "The <a href=\"https://project-open-data.cio.gov/v1.1/schema/#spatial\">spatial coverage</a> of the dataset. Could include a spatial region like a bounding box or a named place.",
129  "type": "string",
130  "minLength": 1
131  },
132  "temporal": {
133  "title": "Temporal",
134  "description": "The <a href=\"https://project-open-data.cio.gov/v1.1/schema/#temporal\">start and end dates</a> for which the dataset is applicable, separated by a \"/\" (i.e., 2000-01-15T00:45:00Z/2010-01-15T00:06:00Z).",
135  "type": "string"
136  },
137  "isPartOf": {
138  "title": "Collection",
139  "description": "The collection of which the dataset is a subset.",
140  "type": "string",
141  "minLength": 1
142  },
143  "publisher": {
144  "$schema": "http://json-schema.org/draft-04/schema#",
145  "id": "https://project-open-data.cio.gov/v1.1/schema/organization.json#",
146  "title": "Organization",
147  "description": "A Dataset Publisher Organization.",
148  "type": "object",
149  "required": [
150  "name"
151  ],
152  "properties": {
153  "@type": {
154  "title": "Metadata Context",
155  "description": "IRI for the JSON-LD data type. This should be org:Organization for each publisher",
156  "type": "string",
157  "default": "org:Organization"
158  },
159  "name": {
160  "title": "Publisher Name",
161  "description": "",
162  "type": "string",
163  "minLength": 1
164  },
165  "subOrganizationOf": {
166  "title": "Parent Organization",
167  "type": "string"
168  }
169  }
170  },
171  "contactPoint": {
172  "$schema": "http://json-schema.org/draft-04/schema#",
173  "id": "https://project-open-data.cio.gov/v1.1/schema/vcard.json#",
174  "title": "Project Open Data ContactPoint vCard",
175  "description": "A Dataset ContactPoint as a vCard object.",
176  "type": "object",
177  "required": [
178  "fn",
179  "hasEmail"
180  ],
181  "properties": {
182  "@type": {
183  "title": "Metadata Context",
184  "description": "IRI for the JSON-LD data type. This should be vcard:Contact for contactPoint.",
185  "enum": [
186  "vcard:Contact"
187  ],
188  "type": "string"
189  },
190  "fn": {
191  "title": "Contact Name",
192  "description": "A full formatted name, e.g. Firstname Lastname.",
193  "type": "string",
194  "minLength": 1
195  },
196  "hasEmail": {
197  "title": "Email",
198  "description": "Email address for the contact name.",
199  "pattern": "^mailto:[\\w\\_\\~\\!\\$\\&\\'\\(\\)\\*\\+\\,\\;\\=\\:.-][email protected][\\w.-]+\\.[\\w.-]+?$|[\\w\\_\\~\\!\\$\\&\\'\\(\\)\\*\\+\\,\\;\\=\\:.-][email protected][\\w.-]+\\.[\\w.-]+?$",
200  "type": "string"
201  }
202  }
203  },
204  "theme": {
205  "title": "Category",
206  "description": "Main thematic category of the dataset.",
207  "type": "array",
208  "items": {
209  "type": "string",
210  "title": "Category",
211  "minLength": 1
212  },
213  "uniqueItems": true
214  },
215  "keyword": {
216  "title": "Tags",
217  "description": "Tags (or keywords) help users discover your dataset; please include terms that would be used by technical and non-technical users.",
218  "type": "array",
219  "items": {
220  "type": "string",
221  "title": "Tag",
222  "minLength": 1
223  },
224  "minItems": 1
225  },
226  "distribution": {
227  "title": "Distribution",
228  "description": "A distribution is a container for the data object. Each distribution should contain one accessURL or downloadURL. When providing a downloadURL, also include the format of the file.",
229  "type": "array",
230  "items": {
231  "title": "Data File",
232  "type": "object",
233  "properties": {
234  "@type": {
235  "title": "Metadata Context",
236  "description": "IRI for the JSON-LD data type. This should be dcat:Distribution for each Distribution.",
237  "default": "dcat:Distribution",
238  "type": "string",
239  "readOnly": true
240  },
241  "title": {
242  "title": "Title",
243  "description": "Human-readable name of the file.",
244  "type": "string",
245  "minLength": 1
246  },
247  "description": {
248  "title": "Description",
249  "description": "Human-readable description of the file.",
250  "type": "string",
251  "minLength": 1
252  },
253  "format": {
254  "title": "Format",
255  "description": "A human-readable description of the file format of a distribution (i.e. csv, pdf, xml, kml, etc.).",
256  "type": "string",
257  "examples": [
258  "arcgis",
259  "csv",
260  "esri rest",
261  "geojson",
262  "json",
263  "kml",
264  "pdf",
265  "tsv",
266  "xls",
267  "xlsx",
268  "xml",
269  "zip"
270  ]
271  },
272  "mediaType": {
273  "title": "Media Type",
274  "description": "The machine-readable file format (<a href=\"https://www.iana.org/assignments/media-types/media-types.xhtml\">IANA Media Type or MIME Type</a>) of the distribution’s downloadURL.",
275  "type": "string"
276  },
277  "downloadURL": {
278  "title": "Download URL",
279  "description": "URL providing direct access to a downloadable file of a dataset.",
280  "type": "string",
281  "format": "uri"
282  },
283  "accessURL": {
284  "title": "Access URL",
285  "description": "URL providing indirect access to a dataset.",
286  "type": "string",
287  "format": "uri"
288  },
289  "conformsTo": {
290  "title": "Data Standard",
291  "description": "URL providing indirect access to a dataset.",
292  "type": "string",
293  "format": "uri"
294  },
295  "describedBy": {
296  "title": "Data Dictionary",
297  "description": "URL to the data dictionary for the distribution found at the downloadURL.",
298  "type": "string",
299  "format": "uri"
300  },
301  "describedByType": {
302  "title": "Data Dictionary Type",
303  "description": "The machine-readable file format (IANA Media Type or MIME Type) of the distribution’s describedBy URL.",
304  "pattern": "^[a-z]+?$",
305  "type": "string"
306  }
307  },
308  "minItems": 1,
309  "uniqueItems": true
310  }
311  },
312  "references": {
313  "title": "Related Documents",
314  "description": "Related documents such as technical information about a dataset, developer documentation, etc.",
315  "type": "array",
316  "items": {
317  "type": "string",
318  "format": "uri"
319  }
320  }
321  }
322 }