From 7c5f9a3fa964d0bc19bf762f786129ddb3e43cde Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Wed, 3 Sep 2014 16:13:01 -0400 Subject: [PATCH 001/129] create v1.1 catalog.json --- schema/1_1_final/catalog.json | 12 ++++++++++++ 1 file changed, 12 insertions(+) create mode 100644 schema/1_1_final/catalog.json diff --git a/schema/1_1_final/catalog.json b/schema/1_1_final/catalog.json new file mode 100644 index 00000000..1eaadcf1 --- /dev/null +++ b/schema/1_1_final/catalog.json @@ -0,0 +1,12 @@ +{ + "$schema": "http://json-schema.org/draft-04/schema#", + "id": "http://project-open-data.github.io/schema/1_0_final/catalog.json#", + "title": "Data.json object", + "description": "Validates an entire collection of common core metadata JSON objects. Agencies produce said collections in the form of Data.json files.", + "type": "array", + "items":{ + "$ref":"single_entry.json", + "minItems": 1, + "uniqueItems": true + } +} From 9606715e91087f5294fa0eca15be0c4f3b64ecce Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Wed, 3 Sep 2014 16:13:53 -0400 Subject: [PATCH 002/129] create v1.1 single_entry.json --- schema/1_1_final/single_entry.json | 430 +++++++++++++++++++++++++++++ 1 file changed, 430 insertions(+) create mode 100644 schema/1_1_final/single_entry.json diff --git a/schema/1_1_final/single_entry.json b/schema/1_1_final/single_entry.json new file mode 100644 index 00000000..d2f6c890 --- /dev/null +++ b/schema/1_1_final/single_entry.json @@ -0,0 +1,430 @@ +{ + "$schema": "http://json-schema.org/draft-04/schema#", + "id": "http://project-open-data.github.io/schema/1_0_final/single_entry.json#", + "title": "Common Core Metadata Schema", + "description": "The metadata format for all federal open data. Validates a single JSON object entry (as opposed to entire Data.json catalog).", + "type": "object", + "required": ["title", "description", "keyword", "modified", "publisher", "contactPoint", "mbox", "identifier", "accessLevel"], + "properties": { + "accessLevel": { + "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)", + "title": "Public Access Level", + "enum": ["public", "restricted public", "non-public"] + }, + "accessLevelComment": { + "title":"Access Level Comment", + "description":"An explanation for the selected \"accessLevel\" including instructions for how to access a restricted file, if applicable, or explanation for why a \"non-public\" or \"restricted public\" data assetis not \"public,\" if applicable. Text, 255 characters.", + "anyOf": [ + { + "type": "string", + "minLength": 1, + "maxLength":255 + }, + { + "type": "null" + } + ] + }, + "accessURL": { + "title":"Download URL", + "description":"URL providing direct access to the downloadable distribution of a dataset.", + "anyOf": [ + { + "type": "string", + "format": "uri" + }, + { + "type": "null" + } + ] + }, + "accrualPeriodicity": { + "title":"Frequency", + "description":"Frequency with which dataset is published.", + "anyOf": [ + { + "enum": ["Annual", "Bimonthly", "Semiweekly", "Daily", "Biweekly", "Semiannual", "Biennial", "Triennial", + "Three times a week", "Three times a month", "Continuously updated", "Monthly", "Quarterly", "Semimonthly", + "Three times a year", "Weekly", "Completely irregular"] + }, + { + "type": "null" + } + ] + }, + "bureauCode": { + "title":"Bureau Code", + "description":"Federal agencies, combined agency and bureau code from OMB Circular A-11, Appendix C in the format of 015:010.", + "anyOf": [ + { + "type": "array", + "items": { + "type": "string", + "pattern": "[0-9]{3}:[0-9]{2}" + }, + "minItems": 1, + "uniqueItems": true + }, + { + "type": "null" + } + ] + }, + "contactPoint": { + "title":"Contact Name", + "description":"Contact person’s name for the asset.", + "type": "string" + }, + "dataDictionary": { + "title":"Data Dictionary", + "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.", + "anyOf": [ + { + "type": "string", + "format": "uri" + }, + { + "type": "null" + } + ] + }, + "dataQuality": { + "title":"Data Quality", + "description":"Whether the dataset meets the agency’s Information Quality Guidelines (true/false).", + "anyOf": [ + { + "type": "boolean" + }, + { + "type": "null" + } + ] + }, + "description": { + "title" : "Description", + "description": "Human-readable description (e.g., an abstract) with sufficient detail to enable a user to quickly understand whether the asset is of interest.", + "type": "string" + }, + "distribution": { + "title":"Distribution", + "description":"Holds multiple download URLs for datasets composed of multiple files and/or file types", + "anyOf": [ + { + "type": "array", + "items": { + "type": "object", + "required": ["accessURL", "format"], + "properties": { + "accessURL": { + "title":"Download URL", + "description":"URL providing direct access to the downloadable distribution of a dataset.", + "type": "string", + "format": "uri" + }, + "format": { + "title":"Format", + "description":"The file format or API type of the distribution.", + "pattern": "^[-\\w]+/[-\\w]+(\\.[-\\w]+)*([+][-\\w]+)?$", + "type": "string" + } + } + }, + "minItems": 1, + "uniqueItems": true + }, + { + "type": "null" + } + ] + }, + "format": { + "title":"Format", + "description":"The file format or API type of the distribution.", + "anyOf": [ + { + "pattern": "^[-\\w]+/[-\\w]+(\\.[-\\w]+)*([+][-\\w]+)?$", + "type": "string" + }, + { + "type": "null" + } + ] + }, + "identifier": { + "title":"Unique Identifier", + "description":"A unique identifier for the dataset or API as maintained within an Agency catalog or database.", + "type": "string", + "pattern": "[\\w]+" + }, + "issued": { + "title":"Release Date", + "description":"Date of formal issuance.", + "anyOf": [ + { + "type": "string", + "pattern": "^([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?$" + }, + { + "type": "string", + "pattern": "^P(?=\\w*\\d)(?:\\d+Y|Y)?(?:\\d+M|M)?(?:\\d+W|W)?(?:\\d+D|D)?(?:T(?:\\d+H|H)?(?:\\d+M|M)?(?:\\d+(?:\\­.\\d{1,2})?S|S)?)?$" + }, + { + "type": "string", + "pattern": "^([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?(\\/)([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?$" + }, + { + "type": "string", + "pattern": "^([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?(\\/)P(?=\\w*\\d)(?:\\d+Y|Y)?(?:\\d+M|M)?(?:\\d+W|W)?(?:\\d+D|D)?(?:T(?:\\d+H|H)?(?:\\d+M|M)?(?:\\d+(?:\\­.\\d{1,2})?S|S)?)?$" + }, + { + "type": "string", + "pattern": "^P(?=\\w*\\d)(?:\\d+Y|Y)?(?:\\d+M|M)?(?:\\d+W|W)?(?:\\d+D|D)?(?:T(?:\\d+H|H)?(?:\\d+M|M)?(?:\\d+(?:\\­.\\d{1,2})?S|S)?)?\\/([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?$" + }, + { + "type": "string", + "pattern": "^R\\d*\\/([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?\\/P(?=\\w*\\d)(?:\\d+Y|Y)?(?:\\d+M|M)?(?:\\d+W|W)?(?:\\d+D|D)?(?:T(?:\\d+H|H)?(?:\\d+M|M)?(?:\\d+(?:\\­.\\d{1,2})?S|S)?)?$" + }, + { + "type": "null" + } + ] + }, + "keyword": { + "title": "Tags", + "description": "Tags (or keywords) help users discover your dataset; please include terms that would be used by technical and non-technical users.", + "type": "array", + "items": { + "type": "string", + "minLength": 1 + }, + "minItems": 1 + }, + "landingPage": { + "title":"Homepage URL", + "description":"Alternative landing page used to redirect user to a contextual, Agency-hosted “homepage” for the Dataset or API when selecting this resource from the Data.gov user interface.", + "anyOf": [ + { + "type": "string", + "format": "uri" + }, + { + "type": "null" + } + ] + }, + "language": { + "title":"Language", + "description":"The language of the dataset.", + "anyOf": [ + { + "type": "array", + "items": { + "type": "string", + "pattern": "^(((([A-Za-z]{2,3}(-([A-Za-z]{3}(-[A-Za-z]{3}){0,2}))?)|[A-Za-z]{4}|[A-Za-z]{5,8})(-([A-Za-z]{4}))?(-([A-Za-z]{2}|[0-9]{3}))?(-([A-Za-z0-9]{5,8}|[0-9][A-Za-z0-9]{3}))*(-([0-9A-WY-Za-wy-z](-[A-Za-z0-9]{2,8})+))*(-(x(-[A-Za-z0-9]{1,8})+))?)|(x(-[A-Za-z0-9]{1,8})+)|((en-GB-oed|i-ami|i-bnn|i-default|i-enochian|i-hak|i-klingon|i-lux|i-mingo|i-navajo|i-pwn|i-tao|i-tay|i-tsu|sgn-BE-FR|sgn-BE-NL|sgn-CH-DE)|(art-lojban|cel-gaulish|no-bok|no-nyn|zh-guoyu|zh-hakka|zh-min|zh-min-nan|zh-xiang)))$" + } + }, + { + "type": "null" + } + ] + }, + "license": { + "title":"License", + "description":"The license dataset or API is published with. See Open Licenses for more information.", + "anyOf": [ + { + "type": "string", + "minLength": 1 + }, + { + "type": "null" + } + ] + }, + "mbox": { + "title":"Contact Email", + "description":"Contact person’s email address.", + "type": "string", + "format": "email" + }, + "modified": { + "title": "Last Update", + "description": "Most recent date on which the dataset was changed, updated or modified.", + "anyOf": [ + { + "type": "string", + "pattern": "^([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?$" + }, + { + "type": "string", + "pattern": "^P(?=\\w*\\d)(?:\\d+Y|Y)?(?:\\d+M|M)?(?:\\d+W|W)?(?:\\d+D|D)?(?:T(?:\\d+H|H)?(?:\\d+M|M)?(?:\\d+(?:\\­.\\d{1,2})?S|S)?)?$" + }, + { + "type": "string", + "pattern": "^([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?(\\/)([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?$" + }, + { + "type": "string", + "pattern": "^([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?(\\/)P(?=\\w*\\d)(?:\\d+Y|Y)?(?:\\d+M|M)?(?:\\d+W|W)?(?:\\d+D|D)?(?:T(?:\\d+H|H)?(?:\\d+M|M)?(?:\\d+(?:\\­.\\d{1,2})?S|S)?)?$" + }, + { + "type": "string", + "pattern": "^P(?=\\w*\\d)(?:\\d+Y|Y)?(?:\\d+M|M)?(?:\\d+W|W)?(?:\\d+D|D)?(?:T(?:\\d+H|H)?(?:\\d+M|M)?(?:\\d+(?:\\­.\\d{1,2})?S|S)?)?\\/([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?$" + }, + { + "type": "string", + "pattern": "^R\\d*\\/([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?\\/P(?=\\w*\\d)(?:\\d+Y|Y)?(?:\\d+M|M)?(?:\\d+W|W)?(?:\\d+D|D)?(?:T(?:\\d+H|H)?(?:\\d+M|M)?(?:\\d+(?:\\­.\\d{1,2})?S|S)?)?$" + } + ] + }, + "PrimaryITInvestmentUII": { + "title":"Primary IT Investment UII", + "description":"For linking a dataset with an IT Unique Investment Identifier (UII)", + "anyOf": [ + { + "type": "string", + "pattern": "[0-9]{3}-[0-9]{9}" + }, + { + "type": "null" + } + ] + }, + "programCode": { + "title":"Program Code", + "description":"Federal agencies, list the primary program related to this data asset, from the Federal Program Inventory. Use the format of 015:001", + "anyOf": [ + { + "type": "array", + "items": { + "type": "string", + "pattern": "[0-9]{3}:[0-9]{3}" + }, + "minItems": 1, + "uniqueItems": true + }, + { + "type": "null" + } + ] + }, + "publisher": { + "title":"Publisher", + "description": "The publishing entity.", + "type": "string" + }, + "references": { + "title":"Related Documents", + "description":"Related documents such as technical information about a dataset, developer documentation, etc.", + "anyOf": [ + { + "type": "array", + "items": { + "type": "string", + "format": "uri" + }, + "minItems": 1, + "uniqueItems": true + }, + { + "type": "null" + } + ] + }, + "spatial": { + "title":"Spatial", + "description":"The range of spatial applicability of a dataset. Could include a spatial region like a bounding box or a named place.", + "anyOf": [ + { + "type": "string", + "minLength": 1 + }, + { + "type": "null" + } + ] + }, + "systemOfRecords": { + "title":"System of Records", + "description":"If the systems is designated as a system of records under the Privacy Act of 1974, provide the URL to the System of Records Notice related to this dataset.", + "anyOf": [ + { + "type": "string", + "minLength": 1 + }, + { + "type": "null" + } + ] + }, + "temporal": { + "title":"Temporal", + "description":"The range of temporal applicability of a dataset (i.e., a start and end date of applicability for the data).", + "anyOf": [ + { + "type": "string", + "pattern": "^([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?$" + }, + { + "type": "string", + "pattern": "^P(?=\\w*\\d)(?:\\d+Y|Y)?(?:\\d+M|M)?(?:\\d+W|W)?(?:\\d+D|D)?(?:T(?:\\d+H|H)?(?:\\d+M|M)?(?:\\d+(?:\\­.\\d{1,2})?S|S)?)?$" + }, + { + "type": "string", + "pattern": "^([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?(\\/)([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?$" + }, + { + "type": "string", + "pattern": "^([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?(\\/)P(?=\\w*\\d)(?:\\d+Y|Y)?(?:\\d+M|M)?(?:\\d+W|W)?(?:\\d+D|D)?(?:T(?:\\d+H|H)?(?:\\d+M|M)?(?:\\d+(?:\\­.\\d{1,2})?S|S)?)?$" + }, + { + "type": "string", + "pattern": "^P(?=\\w*\\d)(?:\\d+Y|Y)?(?:\\d+M|M)?(?:\\d+W|W)?(?:\\d+D|D)?(?:T(?:\\d+H|H)?(?:\\d+M|M)?(?:\\d+(?:\\­.\\d{1,2})?S|S)?)?\\/([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?$" + }, + { + "type": "string", + "pattern": "^R\\d*\\/([\\+-]?\\d{4}(?!\\d{2}\\b))((-?)((0[1-9]|1[0-2])(\\3([12]\\d|0[1-9]|3[01]))?|W([0-4]\\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\\d|[12]\\d{2}|3([0-5]\\d|6[1-6])))([T\\s]((([01]\\d|2[0-3])((:?)[0-5]\\d)?|24\\:?00)([\\.,]\\d+(?!:))?)?(\\17[0-5]\\d([\\.,]\\d+)?)?([zZ]|([\\+-])([01]\\d|2[0-3]):?([0-5]\\d)?)?)?)?\\/P(?=\\w*\\d)(?:\\d+Y|Y)?(?:\\d+M|M)?(?:\\d+W|W)?(?:\\d+D|D)?(?:T(?:\\d+H|H)?(?:\\d+M|M)?(?:\\d+(?:\\­.\\d{1,2})?S|S)?)?$" + }, + { + "type": "null" + } + ] + }, + "theme": { + "title":"Category", + "description":"Main thematic category of the dataset.", + "anyOf": [ + { + "type": "array", + "items": { + "type": "string", + "minLength": 1 + }, + "minItems": 1, + "uniqueItems": true + }, + { + "type": "null" + } + ] + }, + "title": { + "title": "Title", + "description": "Human-readable name of the asset. Should be in plain English and include sufficient detail to facilitate search and discovery.", + "type": "string" + }, + "webService": { + "title":"Endpoint", + "description":"Endpoint of web service to access dataset.", + "anyOf": [ + { + "type": "string", + "format": "uri" + }, + { + "type": "null" + } + ] + } + } +} From 7b2c928a7dd1f432261b4cf6977ad99a5ef18866 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Wed, 3 Sep 2014 16:15:11 -0400 Subject: [PATCH 003/129] Create catalog-sample-extended.csv --- v1.1/examples/catalog-sample-extended.csv | 4 ++++ 1 file changed, 4 insertions(+) create mode 100644 v1.1/examples/catalog-sample-extended.csv diff --git a/v1.1/examples/catalog-sample-extended.csv b/v1.1/examples/catalog-sample-extended.csv new file mode 100644 index 00000000..db3ff2f2 --- /dev/null +++ b/v1.1/examples/catalog-sample-extended.csv @@ -0,0 +1,4 @@ +title,description,keyword,modified,publisher,contactPoint,mbox,identifier,accessLevel,bureauCode,programCode,accessLevelComment,accessURL,webService,format,license,spatial,temporal,theme,dataDictionary,dataQuality,accrualPeriodicity,landingPage,language,PrimaryITInvestmentUII,references,issued,systemOfRecords +Office Locations,A list of the agency's office locations and contact information.,"keyword1, keyword2",2013-01-01,Agency Name,John Smith,john.smith@agency.gov,1,Public,019:20,019:011,,http://www.agency.gov/data/raw/locations.zip,,text/csv,public domain,United States of America,2013-01-01,Energy,http://www.agency.gov/data/information/locations,TRUE,monthly,,en-US,021-006227212,http://www.agency.gov/data/information/locations/document.doc,2013-07-09,http://www.gpo.gov/fdsys/pkg/FR-2008-12-19/html/E8-29846.htm +Commercial ABC Survey,A full export of the results of the Commercial ABC Survey results from 2001-2012. ,"keyword1, keyword3",2013-02-01,Agency Name,Jane Smith,jane.smith@agency.gov,2,Restricted Public,019:00,019:004,"Due to the sensitive nature of some survey responses, the complete survey results are restricted to academic research and requires registration with the agency library. For access, email data-registration@library.agency.gov.",,,application/xml,public domain,United States of America,2001-01-01/2012-12-31,Education,http://www.agency.gov/data/information/database,TRUE,annual,http://www.agency.gov/data/information/database,en-US,007-000001372,"http://www.agency.gov/bureau1/document3.doc, http://www.agency.gov/bureau1/document5.txt",2012-12-31,http://www.gpo.gov/fdsys/pkg/FR-2011-08-30/html/2011-22167.htm +"System Data API - California, 2012",A restful web service for a system's California data set from 2012.,"keyword2, keyword3, keyword4",2012-12-15,Agency Name,Bill Smith,bill.smith@agency.gov,3,Public,019:50,019:026,,http://www.agency.gov/data/raw/system_2012.csv,http://www.agency.gov/data/raw/data_api.json,"text/csv, application/json",creative commons Cco,"California, United States",2012-01-01T00:45:00Z/2012-12-31T23:06:00Z,"Health, Education",http://www.agency.gov/data/information/system_api,TRUE,completely irregular,http://www.agency.gov/developer/system,en-US,007-000006298,http://www.agency.gov/bureau1/document3.pdf,2013-01-31,http://www.gpo.gov/fdsys/pkg/FR-2011-09-08/html/2011-22903.htm From d3c8770976a77dae264dafc01fd8394cf6ddc077 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Wed, 3 Sep 2014 16:15:41 -0400 Subject: [PATCH 004/129] Create catalog-sample-extended.json --- v1.1/examples/catalog-sample-extended.json | 94 ++++++++++++++++++++++ 1 file changed, 94 insertions(+) create mode 100644 v1.1/examples/catalog-sample-extended.json diff --git a/v1.1/examples/catalog-sample-extended.json b/v1.1/examples/catalog-sample-extended.json new file mode 100644 index 00000000..3a1edce7 --- /dev/null +++ b/v1.1/examples/catalog-sample-extended.json @@ -0,0 +1,94 @@ +[ + { + "title": "Data Catalog", + "description": "Version 1.0", + "keyword": ["catalog"], + "modified": "2013-05-09", + "publisher": "US Department of X", + "contactPoint": "John Doe", + "mbox": "john.doe@agency.gov", + "identifier": "1", + "accessLevel": "public", + "distribution": [ + { + "accessURL": "http://agency.gov/data.json", + "format": "application/json" + } + ] + }, + { + "title": "Public Elementary/Secondary Listing", + "description": "The purpose of the CCD nonfiscal surveys is to provide a listing of all schools and agencies providing free public elementary and secondary education, along with basic descriptive statistical information on each school and agency listed. Penalties apply for misuse, seehttp://nces.ed.gov/ncesglobal/data_usage_agreement.asp for more details.", + "keyword": ["education","schools","children","locations","gis"], + "modified": "2011-11-19T12:00:00Z", + "publisher": "US Department of Education", + "contactPoint": "Jane Doe", + "mbox": "Jane.doe@ed.gov", + "identifier": "gov-doe-nces-1121", + "accessLevel": "public", + "bureauCode": ["018:10"], + "programCode": ["018:001"], + "accessLevelComment": null, + "distribution": [ + { + "accessURL": "https://explore.data.gov/views/ykv5-fn9t/rows.csv?accessType=DOWNLOAD", + "format": "text/csv" + } + ], + "webService": "http://explore.data.gov/api/views/ykv5-fn9t/rows.json", + "license": "Public Domain", + "spatial": "United States", + "temporal": "2009-09-01T12:00:00Z/2010-05-31T12:00:00Z", + "theme": ["education"], + "dataDictionary": "http://nces.ed.gov/ccd/pdf/INsc09101a.pdf", + "dataQuality": true, + "issued": "2011-11-22", + "accrualPeriodicity": "Annual", + "language": ["en-US"], + "primaryITInvestmentUII": "021-006227212", + "references": ["http://nces.ed.gov/ccd/data/txt/psu091alay.html","http://nces.ed.gov/ccd/data/txt/psu091s23ay.doc"], + "landingPage": "http://ed.gov/developer", + "systemOfRecords": "http://nces.ed.gov/ccd/" + }, + { + "title": "Public Elementary/Secondary Other Listing", + "description": "The purpose of the alt-CCD nonfiscal surveys is to provide a listing of all schools and agencies providing free public elementary and secondary education, along with basic descriptive statistical information on each school and agency listed. Penalties apply for misuse, seehttp://nces.ed.gov/ncesglobal/data_usage_agreement.asp for more details.", + "keyword": ["education","schools","gis"], + "modified": "2010-11-19T12:00:00Z", + "publisher": "US Department of Education", + "contactPoint": "Jane Doe", + "mbox": "Jane.doe@ed.gov", + "identifier": "gov-doe-nces-1120", + "accessLevel": "public", + "bureauCode": ["018:10"], + "programCode": ["018:001"], + "accessLevelComment": null, + "distribution": [ + { + "accessURL": "https://explore.data.gov/views/ykv5-fn9s/rows.csv?accessType=DOWNLOAD", + "format": "text/csv" + }, + { + "accessURL": "https://explore.data.gov/views/ykv5-fn9s/rows.json?accessType=DOWNLOAD", + "format": "application/json" + }, + { + "accessURL": "https://explore.data.gov/views/ykv5-fn9s/rows.xml?accessType=DOWNLOAD", + "format": "application/xml" + } + ], + "webService": "http://explore.data.gov/api/views/ykv5-fn9s/rows.json", + "license": "Public Domain", + "spatial": "United States", + "temporal": "2008-09-01T12:00:00Z/2009-05-31T12:00:00Z", + "theme": ["education"], + "dataDictionary": "http://nces.ed.gov/ccd/pdf/INsc09101a.pdf", + "dataQuality": true, + "issued": "2010-11-22", + "accrualPeriodicity": "Annual", + "language": ["en-US"], + "primaryITInvestmentUII": "021-006227212", + "references": ["http://nces.ed.gov/ccd/data/txt/psu091alay.txt"], + "landingPage": "http://ed.gov/developer", + "systemOfRecords": "http://nces.ed.gov/ccd/" + }] From c6cc1aea58ecfb59fd575e8c3925fd736f8d10c1 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Wed, 3 Sep 2014 16:16:37 -0400 Subject: [PATCH 005/129] Create catalog-sample.csv --- v1.1/examples/catalog-sample.csv | 4 ++++ 1 file changed, 4 insertions(+) create mode 100644 v1.1/examples/catalog-sample.csv diff --git a/v1.1/examples/catalog-sample.csv b/v1.1/examples/catalog-sample.csv new file mode 100644 index 00000000..e3814684 --- /dev/null +++ b/v1.1/examples/catalog-sample.csv @@ -0,0 +1,4 @@ +title,description,keyword,modified,publisher,contactPoint,mbox,identifier,accessLevel,bureauCode,programCode,accessLevelComment,accessURL,webService,format,license,spatial,temporal,,,,,,,,, +Office Locations,A list of the agency's office locations and contact information.,"keyword1, keyword2",2013-01-01,Agency Name,John Smith,john.smith@agency.gov,1,Public,019:20,019:011,,http://www.agency.gov/data/raw/locations.zip,,text/csv,public domain,United States of America,2013-01-01,,,,,,,,, +Commercial ABC Survey,A full export of the results of the Commercial ABC Survey results from 2001-2012. ,"keyword1, keyword3",2013-02-01,Agency Name,Jane Smith,jane.smith@agency.gov,2,Restricted Public,019:00,019:004,"Due to the sensitive nature of some survey responses, the complete survey results are restricted to academic research and requires registration with the agency library. For access, email data-registration@library.agency.gov.",,,application/xml,public domain,United States of America,2001-01-01/2012-12-31,,,,,,,,, +"System Data API - California, 2012",A restful web service for a system's California data set from 2012.,"keyword2, keyword3, keyword4",2012-12-15,Agency Name,Bill Smith,bill.smith@agency.gov,3,Public,019:50,019:026,,http://www.agency.gov/data/raw/system_2012.csv,http://www.agency.gov/data/raw/data_api.json,"text/csv, application/json",creative commons Cco,"California, United States",2012-01-01T00:45:00Z/2012-12-31T23:06:00Z,,,,,,,,, From c7aab5a0f0385332298da2116e7b4ccf83c5426d Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Wed, 3 Sep 2014 16:18:21 -0400 Subject: [PATCH 006/129] Create catalog-sample.json --- v1.1/examples/catalog-sample.json | 69 +++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) create mode 100644 v1.1/examples/catalog-sample.json diff --git a/v1.1/examples/catalog-sample.json b/v1.1/examples/catalog-sample.json new file mode 100644 index 00000000..24ead8ba --- /dev/null +++ b/v1.1/examples/catalog-sample.json @@ -0,0 +1,69 @@ +[ + { + "title": "Data Catalog", + "description": "Version 1.0", + "keyword": ["catalog"], + "modified": "2013-05-09", + "publisher": "US Department of X", + "contactPoint": "John Doe", + "mbox": "john.doe@agency.gov", + "identifier": "1", + "accessLevel": "public", + "bureauCode": ["018:10"], + "programCode": ["018:001"], + "accessURL": "http://agency.gov/data.json", + "format": "application/json" + + }, + { + "title": "Public Elementary/Secondary Listing", + "description": "The purpose of the CCD nonfiscal surveys is to provide a listing of all schools and agencies providing free public elementary and secondary education, along with basic descriptive statistical information on each school and agency listed. Penalties apply for misuse, seehttp://nces.ed.gov/ncesglobal/data_usage_agreement.asp for more details.", + "keyword": ["education","schools","children","locations","gis"], + "modified": "2011-11-19T12:00:00Z", + "publisher": "US Department of Education", + "contactPoint": "Jane Doe", + "mbox": "Jane.doe@ed.gov", + "identifier": "gov-doe-nces-1121", + "accessLevel": "public", + "bureauCode": "018:10", + "programCode": "018:001", + "accessLevelComment": "", + "accessURL": "https://explore.data.gov/views/ykv5-fn9t/rows.csv?accessType=DOWNLOAD", + "format": "text/csv", + "webService": "http://explore.data.gov/api/views/ykv5-fn9t/rows.json", + "license": "Public Domain", + "spatial": "United States", + "temporal": "2009-09-01T12:00:00Z/2010-05-31T12:00:00Z" + }, + { + "title": "Public Elementary/Secondary Other Listing", + "description": "The purpose of the alt-CCD nonfiscal surveys is to provide a listing of all schools and agencies providing free public elementary and secondary education, along with basic descriptive statistical information on each school and agency listed. Penalties apply for misuse, seehttp://nces.ed.gov/ncesglobal/data_usage_agreement.asp for more details.", + "keyword": ["education","schools","gis"], + "modified": "2010-11-19T12:00:00Z", + "publisher": "US Department of Education", + "contactPoint": "Jane Doe", + "mbox": "Jane.doe@ed.gov", + "identifier": "gov-doe-nces-1120", + "accessLevel": "public", + "bureauCode": ["018:10"], + "programCode": ["018:001"], + "accessLevelComment": "", + "distribution": [ + { + "accessURL": "https://explore.data.gov/views/ykv5-fn9s/rows.csv?accessType=DOWNLOAD", + "format": "text/csv" + }, + { + "accessURL": "https://explore.data.gov/views/ykv5-fn9s/rows.json?accessType=DOWNLOAD", + "format": "application/json" + }, + { + "accessURL": "https://explore.data.gov/views/ykv5-fn9s/rows.xml?accessType=DOWNLOAD", + "format": "application/xml" + } + ], + "webService": "http://explore.data.gov/api/views/ykv5-fn9s/rows.json", + "license": "Public Domain", + "spatial": "United States", + "temporal": "2008-09-01T12:00:00Z/2009-05-31T12:00:00Z" + }] From efee30425ccda102a6380fa47e12b773434f6d5d Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Wed, 3 Sep 2014 16:19:49 -0400 Subject: [PATCH 007/129] Create catalog-template-extended.csv --- v1.1/examples/catalog-template-extended.csv | 2 ++ 1 file changed, 2 insertions(+) create mode 100644 v1.1/examples/catalog-template-extended.csv diff --git a/v1.1/examples/catalog-template-extended.csv b/v1.1/examples/catalog-template-extended.csv new file mode 100644 index 00000000..34d0d811 --- /dev/null +++ b/v1.1/examples/catalog-template-extended.csv @@ -0,0 +1,2 @@ +title,description,keyword,modified,publisher,contactPoint,mbox,identifier,accessLevel,bureauCode,programCode,accessLevelComment,accessURL,webService,format,license,spatial,temporal,theme,dataDictionary,dataQuality,accrualPeriodicity,landingPage,language,PrimaryITInvestmentUII,references,issued,systemOfRecords +,,,,,,,,,,,,,,,,,,,,,,,,,,, From bc5f5aeb4b1076adacb5a71dac54cbbb76299da4 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Wed, 3 Sep 2014 16:21:11 -0400 Subject: [PATCH 008/129] Create catalog-template-extended.json --- v1.1/examples/catalog-template-extended.json | 96 ++++++++++++++++++++ 1 file changed, 96 insertions(+) create mode 100644 v1.1/examples/catalog-template-extended.json diff --git a/v1.1/examples/catalog-template-extended.json b/v1.1/examples/catalog-template-extended.json new file mode 100644 index 00000000..703cb14f --- /dev/null +++ b/v1.1/examples/catalog-template-extended.json @@ -0,0 +1,96 @@ +[ + { + "title": "Data Catalog", + "description": "Version 1.0", + "keyword": ["catalog"], + "modified": "", + "publisher": "", + "contactPoint": "", + "mbox": "", + "identifier": "", + "accessLevel": "public", + "bureauCode": [""], + "programCode": [""], + "distribution": [ + { + "accessURL": "", + "format": "application/json" + } + ] + }, + { + "title": "", + "description": "", + "keyword": ["",""], + "modified": "", + "publisher": "", + "contactPoint": "", + "mbox": "", + "identifier": "", + "accessLevel": "", + "bureauCode": [""], + "programCode": [""], + "accessLevelComment": "", + "distribution": [ + { + "accessURL": "", + "format": "" + } + ], + "webService": "", + "license": "", + "spatial": "", + "temporal": "", + "theme": [""], + "dataDictionary": "", + "dataQuality": , + "issued": "", + "accrualPeriodicity": "", + "language": [""], + "primaryITInvestmentUII": "", + "references": ["",""], + "landingPage": "", + "systemOfRecords": "" + }, + { + "title": "", + "description": "", + "keyword": ["",""], + "modified": "", + "publisher": "", + "contactPoint": "", + "mbox": "", + "identifier": "", + "accessLevel": "", + "bureauCode": [""], + "programCode": [""], + "accessLevelComment": "", + "distribution": [ + { + "accessURL": "", + "format": "" + }, + { + "accessURL": "", + "format": "" + }, + { + "accessURL": "", + "format": "" + } + ], + "webService": "", + "license": "", + "spatial": "", + "temporal": "", + "theme": [""], + "dataDictionary": "", + "dataQuality": , + "issued": "", + "accrualPeriodicity": "", + "language": [""], + "primaryITInvestmentUII": "", + "references": [""], + "landingPage": "", + "systemOfRecords": "" + }] From 6bb15ebd67591964f34ba01c2599a5223b2944d9 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Wed, 3 Sep 2014 16:22:08 -0400 Subject: [PATCH 009/129] Create catalog-template.csv --- v1.1/examples/catalog-template.csv | 2 ++ 1 file changed, 2 insertions(+) create mode 100644 v1.1/examples/catalog-template.csv diff --git a/v1.1/examples/catalog-template.csv b/v1.1/examples/catalog-template.csv new file mode 100644 index 00000000..2a9986f8 --- /dev/null +++ b/v1.1/examples/catalog-template.csv @@ -0,0 +1,2 @@ +title,description,keyword,modified,publisher,contactPoint,mbox,identifier,accessLevel,bureauCode,programCode,accessLevelComment,accessURL,webService,format,license,spatial,temporal,,,,,,,,,, +,,,,,,,,,,,,,,,,,,,,,,,,,,, From 5cf8d5790fbe91bbbf42dcc3b9c05bac9bdf8b45 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Wed, 3 Sep 2014 16:22:56 -0400 Subject: [PATCH 010/129] Create catalog-template.json --- v1.1/examples/catalog-template.json | 68 +++++++++++++++++++++++++++++ 1 file changed, 68 insertions(+) create mode 100644 v1.1/examples/catalog-template.json diff --git a/v1.1/examples/catalog-template.json b/v1.1/examples/catalog-template.json new file mode 100644 index 00000000..17dec4ba --- /dev/null +++ b/v1.1/examples/catalog-template.json @@ -0,0 +1,68 @@ +[ + { + "title": "Data Catalog", + "description": "Version 1.0", + "keyword": ["catalog"], + "modified": "", + "publisher": "", + "contactPoint": "", + "mbox": "", + "identifier": "", + "accessLevel": "", + "bureauCode": [""], + "programCode": [""], + "accessURL": "", + "format": "application/json" + }, + { + "title": "", + "description": "", + "keyword": ["",""], + "modified": "", + "publisher": "", + "contactPoint": "", + "mbox": "", + "identifier": "", + "accessLevel": "", + "bureauCode": [""], + "programCode": [""], + "accessLevelComment": "", + "accessURL": "", + "format": "", + "webService": "", + "license": "", + "spatial": "", + "temporal": "" + }, + { + "title": "", + "description": "", + "keyword": ["",""], + "modified": "", + "publisher": "", + "contactPoint": "", + "mbox": "", + "identifier": "", + "accessLevel": "", + "bureauCode": [""], + "programCode": [""], + "accessLevelComment": "", + "distribution": [ + { + "accessURL": "", + "format": "" + }, + { + "accessURL": "", + "format": "" + }, + { + "accessURL": "", + "format": "" + } + ], + "webService": "", + "license": "", + "spatial": "", + "temporal": "" + }] From dab47068c3b8bdc1e030acda4495f85337e1d455 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Thu, 4 Sep 2014 15:19:38 -0400 Subject: [PATCH 011/129] updating accessLevelComment to rights --- v1.1/schema.md | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index fbf18f78..78a7cbfb 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -79,7 +79,7 @@ Field | Label | Definition -------------- | -------------- | -------------- bureauCode | Bureau Code | Federal agencies, combined agency and bureau code from [OMB Circular A-11, Appendix C](http://www.whitehouse.gov/sites/default/files/omb/assets/a11_current_year/app_c.pdf) in the format of `015:11`. programCode | Program Code | Federal agencies, list the primary program related to this data asset, from the [Federal Program Inventory](http://goals.performance.gov/sites/default/files/images/FederalProgramInventory_FY13_MachineReadable_091613.xls). Use the format of `015:001` -accessLevelComment | Access Level Comment | An explanation for the selected “accessLevel” including instructions for how to access a restricted file, if applicable, or explanation for why a “non-public” or “restricted public” data asset is not “public,” if applicable. Text, 255 characters. +rights | Rights | This may include information regarding access or restrictions based on privacy, security, or other policies. This should also serve as an explanation for the selected “accessLevel” including instructions for how to access a restricted file, if applicable, or explanation for why a “non-public” or “restricted public” data asset is not “public,” if applicable. Text, 255 characters. accessURL | Download URL | URL providing direct access to the downloadable distribution of a dataset. webService | Endpoint | Endpoint of web service to access dataset. format | Format | The file format or API type of the distribution. @@ -123,15 +123,6 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | This field refers to degree to which this dataset *could be made available* to the public, regardless of whether it is currently available to the public. For example, if a member of the public can walk into your agency and obtain a dataset, that entry is **public** even if there are no files online. A *restricted public* dataset is one only available under certain conditions or to certain audiences (such as researchers who sign a waiver). A *non-public* dataset is one that could never be made available to the public for privacy, security, or other reasons as determined by your agency. **Example** | `{"accessLevel":"public"}` -{: .table .table-striped} -**Field ** | **accessLevelComment** ------ | ----- -**Cardinality** | (0,1) -**Required** | Yes, if accessLevel is "restricted public" or "non-public" -**Accepted Values** | String -**Usage Notes** | An explanation for the selected “accessLevel” including instructions for how to access a restricted file, if applicable, or explanation for why a “non-public” or “restricted public” data asset is not “public,” if applicable. -**Example** | `{"accessLevelComment":"This dataset contains Personally Identifiable Information and could not be released for public access. A statistical analysis of the data contained herein, stripped of all personal identifiers, is available at http://another.website.gov/dataset."}` - {: .table .table-striped} **Field ** | **accessURL** ----- | ----- @@ -337,6 +328,17 @@ If there is a need to reflect that the dataset is continually updated, ISO 8601 **Usage Notes** | Enclose each URL within strings. Separate multiple URLs with a comma. **Example** | `{"references":["http://www.agency.gov/legumes/legumes_data_documentation.html"]}` or if multiple URLs, `{"references":["http://www.agency.gov/legumes/legumes_data_documentation.html","http://www.agency.gov/fruits/fruit_data_documentation.html"]}` + +{: .table .table-striped} +**Field ** | **rights** +----- | ----- +**Cardinality** | (0,1) +**Required** | Yes, if accessLevel is "restricted public" or "non-public" +**Accepted Values** | String +**Usage Notes** | This may include information regarding access or restrictions based on privacy, security, or other policies. This should also serve as an explanation for the selected “accessLevel” including instructions for how to access a restricted file, if applicable, or explanation for why a “non-public” or “restricted public” data asset is not “public,” if applicable. +**Example** | `{"rights":"This dataset contains Personally Identifiable Information and could not be released for public access. A statistical analysis of the data contained herein, stripped of all personal identifiers, is available at http://another.website.gov/dataset."}` + + {: .table .table-striped} **Field ** | **spatial** ----- | ----- From d8bcd3d9bdd8e1b3a032e0a4d5a66709c55089c2 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Thu, 4 Sep 2014 15:21:00 -0400 Subject: [PATCH 012/129] adding expanded guidance for systemOfRecords --- v1.1/schema.md | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/v1.1/schema.md b/v1.1/schema.md index 78a7cbfb..8caa3010 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -348,6 +348,15 @@ If there is a need to reflect that the dataset is continually updated, ISO 8601 **Usage Notes** | This field should contain one of the following types of content: (1) a bounding coordinate box for the dataset represented in latitude / longitude pairs where the coordinates are specified in decimal degrees and in the order of: minimum longitude, minimum latitude, maximum longitude, maximum latitude; (2) a latitude / longitude pair (in decimal degrees) representing a point where the dataset is relevant; (3) a geographic feature expressed in [Geography Markup Language using the Simple Features Profile](http://www.ogcnetwork.net/gml-sf); or (4) a geographic feature from the [GeoNames database](http://www.geonames.org). **Example** | `{"spatial":"Lincoln, Nebraska"}` +{: .table .table-striped} +**Field** | **systemOfRecords** +----- | ----- +**Cardinality** | (0,1) +**Required** | No +**Accepted Values** | String (URL) +**Usage Notes** | This field should a URL to the System of Records Notice (SORN) that relates to the dataset, specifically from FederalRegister.gov. +**Example** | `{"https://www.federalregister.gov/articles/2002/04/08/02-7376/privacy-act-of-1974-publication-in-full-of-all-notices-of-systems-of-records-including-several-new#p-361"}` + {: .table .table-striped} **Field ** | **temporal** ----- | ----- From 5e08fb794d5fe51a935b2070ca5914115ca328e7 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Thu, 4 Sep 2014 15:30:46 -0400 Subject: [PATCH 013/129] Create metadata-resources.md --- v1.1/metadata-resources.md | 226 +++++++++++++++++++++++++++++++++++++ 1 file changed, 226 insertions(+) create mode 100644 v1.1/metadata-resources.md diff --git a/v1.1/metadata-resources.md b/v1.1/metadata-resources.md new file mode 100644 index 00000000..2a900623 --- /dev/null +++ b/v1.1/metadata-resources.md @@ -0,0 +1,226 @@ +--- +published: true +layout: default +title: Metadata Resources +permalink: "/metadata-resources/" +filename: "metadata-resources.md" +--- + +This section provides further background and resources to assist agencies in implementing the [common core metadata schema](/schema/). + +In addition to template and sample files we also produce Common Core Metadata schema in JSON schema format. [JSON schema](http://json-schema.org/) describes a JSON data format. It can be used to automatically validate Data.json files and to generate forms for creating JSON. + +### Terms and Abbreviations ### +* **POD** - [Project Open Data](/schema) +* **JSON** - [JavaScript Object Notation](http://json.org/) +* **DCAT** - [Data Catalog Vocabulary](http://www.w3.org/TR/vocab-dcat/) +* **CKAN** - [CKAN software](http://ckan.org/) +* **Schema.org** - [schema.org](http://schema.org/) + +### JSON Schema Files ### + +* 1.0 Final Schema: [Single Entry](/schema/1_0_final/single_entry.json) and [Catalog](/schema/1_0_final/catalog.json) + + +### Template Data Files + + + + +
+ +### Sample Data Files + + + + +
+ + +### Use Cases + +A) Starting from a spreadsheet + +Some agencies may initially build or maintain data catalogs through large spreadsheets. In order to then generate a data.json file from this, simply import the spreadsheet (in the form of a CSV file) into the [Catalog Generator](http://project-open-data.github.com/catalog-generator/), translate the metadata as needed, and then generate an appropriately formatted JSON file. + +B) Translating a data file from another schema + +If your agency has a JSON catalog with a different metadata schema and need to convert it to the prescribed schema needed for the data.json file, one can import the file into [Catalog Generator](http://project-open-data.github.com/catalog-generator/), adjust the metadata as needed and export the results again as the appropriately formatted JSON file. + +C) Utilizing CKAN + +[CKAN](http://www.CKAN.org) is a popular, open-source data catalog that can be installed independently or run as a service. Even if an agency hasn't begun a data catalog, adopting CKAN can provide a robust and feature-rich solution with which to begin maintaining an internal or external catalog. In addition to providing an effective means of organizing the agency's data catalog, CKAN provides several opportunities for generating the needed data.json file. CKAN provides a convenient CSV export that can then be imported into the [Catalog Generator](http://project-open-data.github.com/catalog-generator/) for conversion into an appropriately formatted JSON file. Alternatively, CKAN provides a JSON API of the data catalog which can then be altered to provide an automatic update for the appropriately formatted JSON file. + +D) Using Socrata + +[Socrata](http://www.socrata.com/open-data-portal/) is a popular, open data catalog that is run as a service. Agencies that have not adapted a data catalog yet, can use Socrata without having to install or setup any servers or software. In addition to providing rich visualizations and data management features, Socrata **natively supports data.json** so any datasets managed through Socrata will be automatically exposed correctly. Socrata also supports all the extended metadata fields through it's extensible metadata features. + +E) Manual translating a data file from another system + +Agencies may also manage their data catalogs through various database solutions such as Access, an asset management system, document management system, geoportal, or assorted proprietary systems. Regardless of which system an agency employs, it should include a fundamental export option which allows the catalog to be exported as a CSV file, which can then be imported into the [Catalog Generator](http://project-open-data.github.com/catalog-generator/) for conversation to an appropriately formatted JSON file. Depending on the solutions' varied further functionality, some of them may also provide APIs which can then be configured to maintain the data.json file. If not, they may instead support XML and JSON exports, which can then be converted to the proper format. + +F) Convert from CSV to JSON. + +In order to generate appropriately formatted JSON, simply import an appropriately formatted CSV into the [Catalog Generator](http://project-open-data.github.com/catalog-generator/), ensure that the metadata fields line up, and re-export the file. + + + +"Common Core" Required Fields Equivalents +----------------------------- + +{: .table .table-striped} +Label | *POD* | *CKAN* | *DCAT* | *Schema.org* +------- | ------- | ------- | ------- | ------- +Title | *title* | *title* | [dct:title](http://www.w3.org/TR/vocab-dcat/#Property:distribution_title) | [schema:name](http://schema.org/name) +Description | *description* | *notes* | [dct:description](http://www.w3.org/TR/vocab-dcat/#Property:dataset_description) | [schema:description](http://schema.org/description) +Tags | *keyword* | *tags* | [dcat:keyword](http://www.w3.org/TR/vocab-dcat/#Property:dataset_keyword) | [schema:keywords](http://schema.org/keywords) +Last Update | *modified* | *n/a* | [dct:modified](http://www.w3.org/TR/vocab-dcat/#Property:dataset_update_date) | [schema:dateModified](http://schema.org/dateModified) +Publisher | *publisher* | *organization* → *title* | [dct:publisher](http://www.w3.org/TR/vocab-dcat/#Property:dataset_publisher) | [schema:publisher](http://schema.org/publisher) +Contact Name | *contactPoint* | *maintainer* | [dcat:contactPoint](http://www.w3.org/TR/vocab-dcat/#Property:dataset_contactPoint) | *n/a* +Contact Email | *mbox* | *maintainer_email* | [foaf:mbox](http://xmlns.com/foaf/spec/#term_mbox) | *n/a* +Unique Identifier | *identifier* | *id* | [dct:identifier](http://www.w3.org/TR/vocab-dcat/#Property:dataset_identifier) | *n/a* +Public Access Level | *accessLevel* | *n/a* | *n/a* | *n/a* + +"Common Core" Required if Applicable Fields +------------------------------------------- + +{: .table .table-striped} +Label | *POD* | *CKAN* | *DCAT* | *Schema.org* +------- | ------- | ------- | ------- | ------- +Bureau Code | *bureauCode* | *n/a* | *n/a* | *n/a* +Program Code | *programCode* | *n/a* | *n/a* | *n/a* +Access Level Comment| *accessLevelComment* | *n/a* | *n/a* | *n/a* +Data Dictionary | *dataDictionary* | *n/a* | *n/a* | *n/a* +Download URL | *accessURL* | *resources* → *url* | [dcat:downloadURL](http://www.w3.org/TR/vocab-dcat/#Property:distribution_downloadurl) (recommended) or [dcat:accessURL](http://www.w3.org/TR/vocab-dcat/#Property:distribution_accessurl) (deprecated) | [schema:contentUrl](http://schema.org/contentUrl) +Endpoint | *webService* | *resources* → *url* | [dcat:accessURL](http://www.w3.org/TR/vocab-dcat/#Property:distribution_accessurl) | *n/a* +Format | *format* | *resources* → *mimetype* | [dcat:mediaType](http://www.w3.org/TR/vocab-dcat/#Property:distribution_media_type) (recommended) or [dct:format](http://www.w3.org/TR/vocab-dcat/#Property:distribution_format) (deprecated) | [schema:encodingFormat](http://schema.org/encodingFormat) +License | *license* | *license_title* | [dct:license](http://www.w3.org/TR/vocab-dcat/#Property:distribution_license) | *n/a* +Spatial | *spatial* | *n/a* | [dct:spatial](http://www.w3.org/TR/vocab-dcat/#Property:dataset_spatial) | [schema:spatial](http://schema.org/spatial) +Temporal | *temporal* | *n/a* | [dct:temporal](http://www.w3.org/TR/vocab-dcat/#Property:dataset_temporal) | [schema:temporal](http://schema.org/temporal) + +Expanded Fields +--------------- + +{: .table .table-striped} +Label | *POD* | *CKAN* | *DCAT* | *Schema.org* +------- | ------- | ------- | ------- | ------- +Release Date | *issued* | *n/a* | [dct:issued](http://www.w3.org/TR/vocab-dcat/#Property:dataset_release_date) | [schema:datePublished](http://schema.org/datePublished) +Frequency | *accrualPeriodicity* | *n/a* | [dct:accrualPeriodicity](http://www.w3.org/TR/vocab-dcat/#Property:dataset_frequency) | *n/a* +Language | *language* | *n/a* | [dct:language](http://www.w3.org/TR/vocab-dcat/#Property:dataset_language) | [schema:inLanguage](http://schema.org/inLanguage) +Data Quality | *dataQuality* | *n/a* | *n/a* | *n/a* +Category | *theme* | *groups* | [dcat:theme](http://www.w3.org/TR/vocab-dcat/#Property:dataset_theme) | [schema:about](http://schema.org/about) +Related Documents | *references* | *n/a* | [dct:references](http://dublincore.org/documents/dcmi-terms/#terms-references) | *n/a* +Homepage URL | *landingPage* | *n/a* | [dcat:landingPage](http://www.w3.org/ns/dcat#Property:dataset_landingpage) | [schema:url](http://schema.org/url) +System of Records | *systemOfRecords* | *n/a* | *n/a* | *n/a* + +Mapping POD to Other Metadata Specifications +--------------------------------------------- + +Below is a set of mappings that will help users of other common metadata schemas map their content to the defined POD fields. +The mapping is from the POD field to the XPATH(s) in the common metadata schema where the corresponding information may be found. + +###FGDC CSDGM + +Established by Office of Management and Budget Circular A-16, the Federal Geographic Data Committee ([FGDC](ttp://www.fgdc.gov)) promotes the coordinated development, use, sharing, and dissemination of geographic data. +The [Content Standard for Digital Geospatial Metadata](http://www.fgdc.gov/metadata/csdgm) aims to provide a common set of terminology and definitions for the documentation of digital geospatial data. + +{: .table .table-striped} +| POD Field | *FGDC CSDGM*| +|------- | ------- | +|title | /metadata/idinfo/citation/citeinfo/title | +|description | /metadata/idinfo/descript/abstract | +|keyword | /metadata/idinfo/keywords/theme/themekey
/metadata/idinfo/keywords/place/placekey
/metadata/idinfo/keywords/temporal/tempkey | +|modified | /metadata/idinfo/citation/citeinfo/pubdate | +|publisher | /metadata/idinfo/citation/citeinfo/pubinfo/publish
/metadata/distinfo/distrib/cntinfo/cntperp/cntper
/metadata/distinfo/distrib/cntinfo/cntorgp/cntorg | +|contactPoint | /metadata/idinfo/ptcontac/cntinfo/cntorgp/cntper | +|mbox | /metadata/idinfo/ptcontac/cntinfo/cntemail | +|identifier | CSDGM does not include a unique identifier in the metadata itself. Common practice is to use a URL to the metadata document as unique identifier. | +|accessLevel | /metadata/idinfo/accconst
/metadata/idinfo/useconst
/metadata/distinfo/distliab | +|dataDictionary | /metadata/idinfo/keywords/theme/themekt
/metadata/eainfo/overview/eadetcit | +|accessURL | /metadata/distinfo/stdorder/digform/digtopt/onlinopt/computer/networka/networkr | +|webService | /metadata/idinfo/citation/citeinfo/onlink
/metadata/distinfo/stdorder/digform/digtopt/onlinopt/computer/networka/networkr | +|format | /metadata/distinfo/storder/digform/digtinfo/fname | +|license | /metadata/distinfo/distliab | +|spatial | /metadata/idinfo/spdom/bounding | +|temporal | /metadata/idinfo/timeperd/timeinfo (might be one date or range. If range, separate start/end with comma) | + + +###ISO 19115:2003 + +[ISO 19115:2003](http://www.iso.org/iso/catalogue_detail.htm?csnumber=26020) defines the schema required for describing geographic information and services. It provides information about the identification, the extent, the quality, the spatial and temporal schema, spatial reference, and distribution of digital geographic data. + +{: .table .table-striped} +| POD Field | *ISO 19115:2003* | +|------- | ------- | +|title | //gmd:identificationInfo/gmd:MD_DataIdentification/gmd:citation/gmd:CI_Citation/gmd:title/gco:CharacterString | +|description | //gmd:identificationInfo/gmd:MD_DataIdentification/gmd:abstract/gco:CharacterString | +|keyword | //gmd:topicCategory/gmd:MD_TopicCategoryCode
//gmd:descriptiveKeywords/gmd:MD_Keywords/gmd:keyword/gco:CharacterString | +|modified | /gmd:MD_Metadata/gmd:dateStamp/gco:Date
/gmd:MD_Metadata/gmd:dateStamp/gco:DateTime | +|publisher | //gmd:identificationInfo/gmd:MD_DataIdentification/gmd:pointOfContact/gmd:CI_ResponsibleParty/gmd:organisationName/gco:CharacterString[../../gmd:role/gmd:CI_RoleCode/@codeListValue='publisher']
//gmd:identificationInfo/gmd:MD_DataIdentification/gmd:citation/gmd:CI_Citation/gmd:citedResponsibleParty/gmd:CI_ResponsibleParty/gmd:organisationName/gco:CharacterString[../../gmd:role/gmd:CI_RoleCode/@codeListValue='publisher']
//gmd:distributionInfo/gmd:MD_Distribution/gmd:distributor/gmd:MD_Distributor/gmd:distributorContact/gmd:CI_ResponsibleParty/gmd:organisationName | +|contactPoint | //gmd:identificationInfo/gmd:MD_DataIdentification/gmd:pointOfContact/gmd:CI_ResponsibleParty/gmd:individualName/gco:CharacterString
//gmd:identificationInfo/gmd:MD_DataIdentification/gmd:pointOfContact/gmd:CI_ResponsibleParty/gmd:organisationName/gco:CharacterString | +|mbox | //gmd:identificationInfo/gmd:MD_DataIdentification/gmd:pointOfContact/gmd:CI_ResponsibleParty/gmd:contactInfo/gmd:CI_Contact/gmd:address/gmd:CI_Address/gmd:electronicMailAddress/gco:CharacterString | +|identifier | //gmd:fileIdentifier/gco:CharacterString | +|accessLevel | //gmd:identificationInfo/gmd:MD_DataIdentification/gmd:resourceConstraints/gmd:MD_Constraints/gmd:useLimitation/gco:CharacterString | +|dataDictionary | //gmd:contentInfo/gmd:MD_FeatureCatalogueDescription/gmd:featureCatalogueCitation/gmd:CI_Citation/gmd:citedResponsibleParty/gmd:CI_ResponsibleParty/gmd:contactInfo/gmd:CI_Contact/gmd:onlineResource/gmd:CI_OnlineResource/gmd:linkage | +|accessURL | //gmd:distributionInfo/gmd:MD_Distribution/gmd:transferOptions/gmd:MD_DigitalTransferOptions/gmd:onLine/gmd:CI_OnlineResource/gmd:linkage/gmd:URL[../../gmd:function/gmd:CI_OnLineFunctionCode/@codeListValue='download'] | +|webService | | +|format | //gmd:distributionInfo/gmd:MD_Distribution/gmd:distributionFormat/gmd:MD_Format/gmd:name/gco:CharacterString | +|license | | +|spatial | //gmd:identificationInfo/gmd:MD_DataIdentification/gmd:extent/gmd:EX_Extent/gmd:geographicElement/gmd:EX_GeographicBoundingBox | +|temporal | //gmd:identificationInfo/gmd:MD_DataIdentification/gmd:extent/gmd:EX_Extent/gmd:temporalElement/gmd:EX_TemporalExtent/gmd:extent/gml:TimePeriod/gml:begin/gml:TimeInstant/gml:timePosition
/gmd:MD_Metadata/gmd:identificationInfo/gmd:MD_DataIdentification/gmd:extent/gmd:EX_Extent/gmd:temporalElement/gmd:EX_TemporalExtent/gmd:extent/gml32:TimePeriod/gml32:begin/gml32:TimeInstant/gml32:timePosition
/gmd:MD_Metadata/gmd:identificationInfo/gmd:MD_DataIdentification/gmd:extent/gmd:EX_Extent/gmd:temporalElement/gmd:EX_TemporalExtent/gmd:extent/gml:TimePeriod/gml:beginPosition
/gmd:MD_Metadata/gmd:identificationInfo/gmd:MD_DataIdentification/gmd:extent/gmd:EX_Extent/gmd:temporalElement/gmd:EX_TemporalExtent/gmd:extent/gml32:TimePeriod/gml32:beginPosition

/gmd:MD_Metadata/gmd:identificationInfo/gmd:MD_DataIdentification/gmd:extent/gmd:EX_Extent/gmd:temporalElement/gmd:EX_TemporalExtent/gmd:extent/gml:TimePeriod/gml:end/gml:TimeInstant/gml:timePosition
/gmd:MD_Metadata/gmd:identificationInfo/gmd:MD_DataIdentification/gmd:extent/gmd:EX_Extent/gmd:temporalElement/gmd:EX_TemporalExtent/gmd:extent/gml32:TimePeriod/gml32:end/gml32:TimeInstant/gml32:timePosition
/gmd:MD_Metadata/gmd:identificationInfo/gmd:MD_DataIdentification/gmd:extent/gmd:EX_Extent/gmd:temporalElement/gmd:EX_TemporalExtent/gmd:extent/gml:TimePeriod/gml:endPosition
/gmd:MD_Metadata/gmd:identificationInfo/gmd:MD_DataIdentification/gmd:extent/gmd:EX_Extent/gmd:temporalElement/gmd:EX_TemporalExtent/gmd:extent/gml32:TimePeriod/gml32:endPosition | + + +### ISO 19119:2005 + +[ISO 19119:2005](http://www.iso.org/iso/home/store/catalogue_tc/catalogue_detail.htm?csnumber=39890) identifies and defines the architecture patterns for service interfaces used for geographic information, defines its relationship to the Open Systems Environment model, presents a geographic services taxonomy and a list of example geographic services placed in the services taxonomy. It also prescribes how to create a platform-neutral service specification, how to derive conformant platform-specific service specifications, and provides guidelines for the selection and specification of geographic services from both platform-neutral and platform-specific perspectives. + +{: .table .table-striped} +| POD Field | *ISO 19119:2005* | +|------- | ------- | +|title | /gmd:MD_Metadata/gmd:identificationInfo/srv:SV_ServiceIdentification/gmd:citation/gmd:CI_Citation/gmd:title/gco:CharacterString | +|description | /gmd:MD_Metadata/gmd:identificationInfo/srv:SV_ServiceIdentification/gmd:abstract/gco:CharacterString | +|keyword | /gmd:MD_Metadata/gmd:identificationInfo/srv:SV_ServiceIdentification/gmd:descriptiveKeywords/gmd:MD_Keywords/gmd:keyword/gco:CharacterString | +|modified | /gmd:MD_Metadata/gmd:dateStamp/gco:Date
/gmd:MD_Metadata/gmd:dateStamp/gco:DateTime | +|publisher | /gmd:MD_Metadata/gmd:contact/gmd:CI_ResponsibleParty/gmd:organisationName/gco:CharacterString | +|contactPoint | /gmd:MD_Metadata/gmd:contact/gmd:CI_ResponsibleParty/gmd:individualName/gco:CharacterString | +|mbox | /gmd:MD_Metadata/gmd:contact/gmd:CI_ResponsibleParty/gmd:contactInfo/gmd:CI_Contact/gmd:address/gmd:CI_Address/gmd:electronicMailAddress/gco:CharacterString | +|identifier | /gmd:MD_Metadata/gmd:fileIdentifier/gco:CharacterString | +|accessLevel | /gmd:MD_Metadata/gmd:identificationInfo/srv:SV_ServiceIdentification/gmd:resourceConstraints/gmd:MD_Constraints/gmd:useLimitation/gco:CharacterString | +|dataDictionary | | +|accessURL | | +|webService | /gmd:MD_Metadata/gmd:identificationInfo/srv:SV_ServiceIdentification/srv:containsOperations/srv:SV_OperationMetadata/srv:connectPoint/gmd:CI_OnlineResource/gmd:linkage/gmd:URL | +|format | /gmd:MD_Metadata/gmd:identificationInfo/srv:SV_ServiceIdentification/srv:serviceType/gco:LocalName | +|license | | +|spatial | /gmd:MD_Metadata/gmd:identificationInfo/srv:SV_ServiceIdentification/srv:extent/gmd:EX_Extent/gmd:geographicElement/gmd:EX_GeographicBoundingBox | +|temporal | /gmd:MD_Metadata/gmd:identificationInfo/srv:SV_ServiceIdentification/srv:extent/gmd:EX_Extent/gmd:temporalElement/gmd:EX_TemporalExtent/gmd:extent/gml:TimePeriod/gml:begin/gml:TimeInstant/gml:timePosition
/gmd:MD_Metadata/gmd:identificationInfo/srv:SV_ServiceIdentification/srv:extent/gmd:EX_Extent/gmd:temporalElement/gmd:EX_TemporalExtent/gmd:extent/gml32:TimePeriod/gml32:begin/gml32:TimeInstant/gml32:timePosition
/gmd:MD_Metadata/gmd:identificationInfo/srv:SV_ServiceIdentification/srv:extent/gmd:EX_Extent/gmd:temporalElement/gmd:EX_TemporalExtent/gmd:extent/gml:TimePeriod/gml:beginPosition
/gmd:MD_Metadata/gmd:identificationInfo/srv:SV_ServiceIdentification/srv:extent/gmd:EX_Extent/gmd:temporalElement/gmd:EX_TemporalExtent/gmd:extent/gml32:TimePeriod/gml32:beginPosition

/gmd:MD_Metadata/gmd:identificationInfo/srv:SV_ServiceIdentification/srv:extent/gmd:EX_Extent/gmd:temporalElement/gmd:EX_TemporalExtent/gmd:extent/gml:TimePeriod/gml:end/gml:TimeInstant/gml:timePosition
/gmd:MD_Metadata/gmd:identificationInfo/srv:SV_ServiceIdentification/srv:extent/gmd:EX_Extent/gmd:temporalElement/gmd:EX_TemporalExtent/gmd:extent/gml32:TimePeriod/gml32:end/gml32:TimeInstant/gml32:timePosition
/gmd:MD_Metadata/gmd:identificationInfo/srv:SV_ServiceIdentification/srv:extent/gmd:EX_Extent/gmd:temporalElement/gmd:EX_TemporalExtent/gmd:extent/gml:TimePeriod/gml:endPosition
/gmd:MD_Metadata/gmd:identificationInfo/srv:SV_ServiceIdentification/srv:extent/gmd:EX_Extent/gmd:temporalElement/gmd:EX_TemporalExtent/gmd:extent/gml32:TimePeriod/gml32:endPosition" | + + +### Namespaces + +The above XPATHs assume the following namespaces: + +{: .table .table-striped} +| Prefix | *URI* | +|------- | ------- | +| gmd | http://www.isotc211.org/2005/gmd | +| gco | http://www.isotc211.org/2005/gco | +| gml | http://www.opengis.net/gml | +| gml32 | http://www.opengis.net/gml/3.2 | +| srv | http://www.isotc211.org/2005/srv | + + + + + From 274399b84686c980dfd7efe71809ecba6dcd2435 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Thu, 4 Sep 2014 16:06:30 -0400 Subject: [PATCH 014/129] Create iso8601_guidance.md --- iso8601_guidance.md | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 iso8601_guidance.md diff --git a/iso8601_guidance.md b/iso8601_guidance.md new file mode 100644 index 00000000..15d4300d --- /dev/null +++ b/iso8601_guidance.md @@ -0,0 +1,32 @@ +--- +layout: default +title: ISO 8601 Guidance +permalink: /iso8601_guidance/ +filename: iso8601_guidance.md +--- + + +### accrualPeriodicity + + +| Term | ISO-8601 | +|---|---| +| Decennial | R/P10Y | +| Quadrennial | R/P4Y | +| Annual | R/P1Y | +| Bimonthly | R/P2M *or* R/P0.5M | +| Semiweekly | R/P3.5D | +| Daily | R/P1D | +| Biweekly | R/P2W *or* R/P0.5W | +| Semiannual | R/P6M | +| Biennial | R/P2Y | +| Triennial | R/P3Y | +| Three times a week | R/P0.33W | +| Three times a month | R/P0.33M | +| Continuously updated | R/PT1S | +| Monthly | R/P1M | +| Quarterly | R/P3M | +| Semimonthly | R/P0.5M | +| Three times a year | R/P4M | +| Weekly | R/P1W | + From 582fe16c20df74f54f76a599d294dec1dc06da39 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Thu, 4 Sep 2014 16:14:07 -0400 Subject: [PATCH 015/129] Update schema.md Seeking to address https://github.com/project-open-data/project-open-data.github.io/issues/292. Note that this is accompanied by an appendix that is [still under construction](https://github.com/project-open-data/project-open-data.github.io/blob/metadata-v-1.1/iso8601_guidance.md#accrualperiodicity). --- v1.1/schema.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 8caa3010..02d554ed 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -137,9 +137,9 @@ Further Metadata Field Guidance (alphabetical by field) ----- | ----- **Cardinality** | (0,1) **Required** | No -**Accepted Values** | See usage notes -**Usage Notes** | Must be a value from [DCCDAccrualPeriodicity](http://www.ukoln.ac.uk/metadata/dcmi/collection-DCCDAccrualPeriodicity/): "Annual","Bimonthly","Semiweekly","Daily","Biweekly","Semiannual","Biennial","Triennial","Three times a week","Three times a month","Continuously updated","Monthly","Quarterly","Semimonthly","Three times a year","Weekly","Completely irregular" -**Example** | `{"accrualPeriodicity":"Annual"}` +**Accepted Values** | ISO 8601 Repeating Duration (or `irregular`) +**Usage Notes** | Must be an ISO 8601 repeating duration unless this is not possible because the accrual periodicity is completely irregular, in which case the value should simply be `irregular`. The value should not include a start or end date but rather simply express the duration of time between data publishing. For example, a dataset which is updated on an annual basis would be `R/P1Y`; every three months would be `R/P3M`; weekly would be `R/P1W`; and daily would be `R/P1D`. Further examples and documenation [can be found here](/iso8601_guidance.md#accrualperiodicity). +**Example** | `{"accrualPeriodicity":"R/P1Y"}` {: .table .table-striped} **Field ** | **bureauCode** From 3789c6521b1a7830fe37a6aced2eabc8ae5513df Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Thu, 4 Sep 2014 16:57:23 -0400 Subject: [PATCH 016/129] new extended guidance for `publisher` Following through on with https://github.com/project-open-data/project-open-data.github.io/issues/296. --- v1.1/schema.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 02d554ed..1da4d161 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -315,9 +315,9 @@ If there is a need to reflect that the dataset is continually updated, ISO 8601 ----- | ----- **Cardinality** | (1,1) **Required** | Yes, always -**Accepted Values** | String -**Usage Notes** | The plaintext name of the entity publishing this dataset. -**Example** | `{"publisher":"U.S. Department of Education"}` +**Accepted Values** | Object +**Usage Notes** | The plaintext name of the entity publishing this dataset. Where greater specificity is desired, include as many levels of publisher as is useful, in ascending order, using the below format. +**Example** | `{"publisher":{"name": "U.S. Department of Commerce"}` or if multiple levels, `"publisher": {"name": "National Weather Service", "subOrganizationOf": {"name": "National Oceanic and Atmospheric Administration", "subOrganizationOf": {"name": "U.S. Department of Commerce"}}}` {: .table .table-striped} **Field ** | **references** From 8eb32ce5ccdb484a10ffd9c4e31267213df25db9 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Thu, 4 Sep 2014 17:11:40 -0400 Subject: [PATCH 017/129] adding language for `isPartOf` --- v1.1/schema.md | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/v1.1/schema.md b/v1.1/schema.md index 1da4d161..20e091e1 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -104,6 +104,7 @@ dataQuality | Data Quality | Whether the dataset meets the agency's In distribution | Distribution | Holds multiple download URLs for datasets composed of multiple files and/or file types accrualPeriodicity | Frequency | Frequency with which dataset is published. landingPage | Homepage URL | Alternative landing page used to redirect user to a contextual, Agency-hosted "homepage" for the Dataset or API when selecting this resource from the Data.gov user interface. +isPartOf | isPartOf | The collection of which the dataset is a subset. language | Language | The language of the dataset. PrimaryITInvestmentUII | Primary IT Investment UII | For linking a dataset with an IT Unique Investment Identifier (UII) references | Related Documents | Related documents such as technical information about a dataset, developer documentation, etc. @@ -227,6 +228,15 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | This field allows third parties to maintain a consistent record for datasets even if title or URLs are updated. Agencies may integrate an existing system for maintaining unique identifiers or enter arbitrary characters for this field. However, each identifier **must** be unique across the agency's catalog and remain fixed. Characters should be alphanumeric. **Example** | `{"identifier":"1344"}` +{: .table .table-striped} +**Field ** | **isPartOf** +----- | ----- +**Cardinality** | (0,1) +**Required** | No +**Accepted Values** | String +**Usage Notes** | This field allows the grouping of multiple datasets into a "collection". This field should be employed by the individual datasets that together make up a collection. The value for this field should the the `identifier` of the parent dataset. +**Example** | `{"isPartOf":"1344"}` + {: .table .table-striped} **Field ** | **issued** ----- | ----- From 1c93d7fd43e3bb4117ee7d3677a7cdf1495c82ce Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Fri, 5 Sep 2014 17:34:08 -0400 Subject: [PATCH 018/129] accessURL, downloadURL, webService * refined accessURL * added downloadURL * removed webService addressing #335, #291 --- v1.1/schema.md | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 20e091e1..dd9a74fc 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -80,8 +80,8 @@ Field | Label | Definition bureauCode | Bureau Code | Federal agencies, combined agency and bureau code from [OMB Circular A-11, Appendix C](http://www.whitehouse.gov/sites/default/files/omb/assets/a11_current_year/app_c.pdf) in the format of `015:11`. programCode | Program Code | Federal agencies, list the primary program related to this data asset, from the [Federal Program Inventory](http://goals.performance.gov/sites/default/files/images/FederalProgramInventory_FY13_MachineReadable_091613.xls). Use the format of `015:001` rights | Rights | This may include information regarding access or restrictions based on privacy, security, or other policies. This should also serve as an explanation for the selected “accessLevel” including instructions for how to access a restricted file, if applicable, or explanation for why a “non-public” or “restricted public” data asset is not “public,” if applicable. Text, 255 characters. -accessURL | Download URL | URL providing direct access to the downloadable distribution of a dataset. -webService | Endpoint | Endpoint of web service to access dataset. +accessURL | Access URL | URL providing indirect access to a dataset, for example via API or a graphical interface. +downloadURL | Download URL | URL providing direct access to a downloadable file of a dataset. format | Format | The file format or API type of the distribution. license | License | The license with which the dataset or API is published. See [Open Licenses](/open-licenses/) for more information. spatial | Spatial | The range of spatial applicability of a dataset. Could include a spatial region like a bounding box or a named place. @@ -127,11 +127,11 @@ Further Metadata Field Guidance (alphabetical by field) {: .table .table-striped} **Field ** | **accessURL** ----- | ----- -**Cardinality** | (0,1) -**Required** | Yes, if the file is available for public download. +**Cardinality** | (0,n) +**Required** | Yes, if the file is accessible indirectly, through means other than direct download. **Accepted Values** | String (URL) -**Usage Notes** | This must be the **direct** download URL. Use **homepage** for landing or disambiguation pages, or **references** for documentation pages. For multiple downloads, use **distribution** to include as many **accessURL** entries as you need. -**Example** | `{"accessURL":"http://www.agency.gov/vegetables/listofvegetables.csv"}` +**Usage Notes** | This should be the URL for an indirect means of accessing the data, such as API documentation, a 'wizard' or other graphical interface which is used to generate a download, feed, or a request form for the data. This should not be a **direct** download URL. It is usually assumed that accessURL is an HTML webpage. +**Example** | `{"accessURL":"http://www.agency.gov/api/vegetables/"}` {: .table .table-striped} **Field ** | **accrualPeriodicity** @@ -210,6 +210,16 @@ Further Metadata Field Guidance (alphabetical by field) } ] + +{: .table .table-striped} +**Field ** | **downloadURL** +----- | ----- +**Cardinality** | (0,n) +**Required** | Yes, if the file is available for public download. +**Accepted Values** | String (URL) +**Usage Notes** | This must be the **direct** download URL. Other means of accessing the dataset should be expressed using **accessURL**. +**Example** | `{"downloadURL":"http://www.agency.gov/vegetables/listofvegetables.csv"}` + {: .table .table-striped} **Field ** | **format** ----- | ----- @@ -398,15 +408,6 @@ Updated every 5 minutes beginning on February 15, 2010 would be represented as: **Usage Notes** | Acronyms should be avoided. **Example** | `{"title":"Types of Vegetables"}` -{: .table .table-striped} -**Field ** | **webService** ------ | ----- -**Cardinality** | (0,1) -**Required** | Yes, if the dataset has an API -**Accepted Values** | String (URL) -**Usage Notes** | This field will serve to delineate the web services offered by an agency and will be used to aggregate cross-government API catalogs. -**Example** | `{"webService":"http://www.agency.gov/vegetables/vegetables.json"}` - Rationale for Metadata Nomenclature ---------------------- From 6c376cf7f93553ecab62502792d0eaa91f745a0a Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Mon, 8 Sep 2014 17:14:00 -0400 Subject: [PATCH 019/129] update format and add mediatype --- v1.1/schema.md | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index dd9a74fc..1540474c 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -82,8 +82,9 @@ programCode | Program Code | Federal agencies, list the primary program rel rights | Rights | This may include information regarding access or restrictions based on privacy, security, or other policies. This should also serve as an explanation for the selected “accessLevel” including instructions for how to access a restricted file, if applicable, or explanation for why a “non-public” or “restricted public” data asset is not “public,” if applicable. Text, 255 characters. accessURL | Access URL | URL providing indirect access to a dataset, for example via API or a graphical interface. downloadURL | Download URL | URL providing direct access to a downloadable file of a dataset. -format | Format | The file format or API type of the distribution. +format | Format | A human-readable description of the file format of a dataset. license | License | The license with which the dataset or API is published. See [Open Licenses](/open-licenses/) for more information. +mediaType | MIME Type | The machine-readable file format ([IANA MIME Type](http://en.wikipedia.org/wiki/Internet_media_type)) of a dataset. spatial | Spatial | The range of spatial applicability of a dataset. Could include a spatial region like a bounding box or a named place. temporal | Temporal | The range of temporal applicability of a dataset (i.e., a start and end date of applicability for the data). @@ -224,10 +225,10 @@ Further Metadata Field Guidance (alphabetical by field) **Field ** | **format** ----- | ----- **Cardinality** | (0,1) -**Required** | Yes, if the file is available for public download. +**Required** | No **Accepted Values** | String -**Usage Notes** | This must describe the exact files available at **accessURL** using [MIME Types](http://en.wikipedia.org/wiki/Internet_media_type). _[Also note [Office Open XML MIME types](http://blogs.msdn.com/b/vsofficedeveloper/archive/2008/05/08/office-2007-open-xml-mime-types.aspx)]_ -**Example** | `{"format":"application/json"}` +**Usage Notes** | This should be a human-readable description of the file format of the dataset, that provides useful information that might not be apparent from `mediaType`. +**Example** | `{"format":"A CSV spreadsheet compressed in a ZIP file."}` {: .table .table-striped} **Field ** | **identifier** @@ -301,6 +302,15 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | - **Example** | `{"mbox":"joe@agency.gov"}` +{: .table .table-striped} +**Field ** | **mediaType** +----- | ----- +**Cardinality** | (0,1) +**Required** | Yes, if the file is available for public download. +**Accepted Values** | String +**Usage Notes** | This must describe the exact files available at **downloadURL** using [MIME Types](http://en.wikipedia.org/wiki/Internet_media_type). _[Also note [Office Open XML MIME types](http://blogs.msdn.com/b/vsofficedeveloper/archive/2008/05/08/office-2007-open-xml-mime-types.aspx)]_ +**Example** | `{"mediaType":"application/json"}` + {: .table .table-striped} **Field ** | **modified** ----- | ----- From 921d5ca57df8d02e747906e617a177613022c8c9 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Mon, 8 Sep 2014 17:53:33 -0400 Subject: [PATCH 020/129] use markdown syntax for named anchor/id and links --- v1.1/schema.md | 124 ++++++++++++++++++++++++------------------------- 1 file changed, 62 insertions(+), 62 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 1540474c..ef0f1ba9 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -116,8 +116,8 @@ systemOfRecords | System of Records | If the systems is designated as a syst Further Metadata Field Guidance (alphabetical by field) ------------------------------- -{: .table .table-striped} -**Field ** | **accessLevel** +{: .table .table-striped #accessLevel} +**Field [#](#accessLevel){: .permalink}** | **accessLevel** ----- | ----- **Cardinality** | (1,1) **Required** | Yes, always @@ -125,8 +125,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | This field refers to degree to which this dataset *could be made available* to the public, regardless of whether it is currently available to the public. For example, if a member of the public can walk into your agency and obtain a dataset, that entry is **public** even if there are no files online. A *restricted public* dataset is one only available under certain conditions or to certain audiences (such as researchers who sign a waiver). A *non-public* dataset is one that could never be made available to the public for privacy, security, or other reasons as determined by your agency. **Example** | `{"accessLevel":"public"}` -{: .table .table-striped} -**Field ** | **accessURL** +{: .table .table-striped #accessURL} +**Field [#](#accessURL){: .permalink}** | **accessURL** ----- | ----- **Cardinality** | (0,n) **Required** | Yes, if the file is accessible indirectly, through means other than direct download. @@ -134,8 +134,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | This should be the URL for an indirect means of accessing the data, such as API documentation, a 'wizard' or other graphical interface which is used to generate a download, feed, or a request form for the data. This should not be a **direct** download URL. It is usually assumed that accessURL is an HTML webpage. **Example** | `{"accessURL":"http://www.agency.gov/api/vegetables/"}` -{: .table .table-striped} -**Field ** | **accrualPeriodicity** +{: .table .table-striped #accrualPeriodicity} +**Field [#](#accrualPeriodicity){: .permalink}** | **accrualPeriodicity** ----- | ----- **Cardinality** | (0,1) **Required** | No @@ -143,8 +143,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | Must be an ISO 8601 repeating duration unless this is not possible because the accrual periodicity is completely irregular, in which case the value should simply be `irregular`. The value should not include a start or end date but rather simply express the duration of time between data publishing. For example, a dataset which is updated on an annual basis would be `R/P1Y`; every three months would be `R/P3M`; weekly would be `R/P1W`; and daily would be `R/P1D`. Further examples and documenation [can be found here](/iso8601_guidance.md#accrualperiodicity). **Example** | `{"accrualPeriodicity":"R/P1Y"}` -{: .table .table-striped} -**Field ** | **bureauCode** +{: .table .table-striped #bureauCode} +**Field [#](#bureauCode){: .permalink}** | **bureauCode** ----- | ----- **Cardinality** | (0,n) **Required** | Yes, for United States Federal Government agencies @@ -152,8 +152,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | Represent each bureau responsible for the dataset according to the codes found in [OMB Circular A-11, Appendix C](http://www.whitehouse.gov/sites/default/files/omb/assets/a11_current_year/app_c.pdf). Start with the agency code, then a colon, then the bureau code. **Example** | The Office of the Solicitor (86) at the Department of the Interior (010) would be: `{"bureauCode":["010:86"]}`. If a second bureau was also responsible, the format like this: `{"bureauCode":["010:86","010:04"]}`. -{: .table .table-striped} -**Field ** | **contactPoint** +{: .table .table-striped #contactPoint} +**Field [#](#contactPoint){: .permalink}** | **contactPoint** ----- | ----- **Cardinality** | (1,1) **Required** | Yes, always @@ -161,8 +161,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | - **Example** | `{"contactPoint":"John Brown"}` -{: .table .table-striped} -**Field ** | **dataDictionary** +{: .table .table-striped #dataDictionary} +**Field [#](#dataDictionary){: .permalink}** | **dataDictionary** ----- | ----- **Cardinality** | (0,1) **Required** | No (Documentation that is not specifically a data dictionary belongs in "references") @@ -170,8 +170,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | - **Example** | `{"dataDictionary":"http://www.agency.gov/vegetables/dictionary.html"}` -{: .table .table-striped} -**Field ** | **dataQuality** +{: .table .table-striped #dataQuality} +**Field [#](#dataQuality){: .permalink}** | **dataQuality** ----- | ----- **Cardinality** | (0,1) **Required** | No @@ -179,8 +179,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | Indicates whether a dataset conforms to the agency's information quality guidelines. **Example** | `{"dataQuality":true}` -{: .table .table-striped} -**Field ** | **description** +{: .table .table-striped #description} +**Field [#](#description){: .permalink}** | **description** ----- | ----- **Cardinality** | (1,1) **Required** | Yes, always @@ -188,8 +188,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | This should be human-readable and understandable to an average person. **Example** | `{"description":"This dataset contains a list of vegetables, including nutrition information and seasonality. Includes details on tomatoes, which are really fruit but considered a vegetable in this dataset."}` -{: .table .table-striped} -**Field ** | **distribution** +{: .table .table-striped #distribution} +**Field [#](#distribution){: .permalink}** | **distribution** ----- | ----- **Cardinality** | (0,n) **Required** | No @@ -212,8 +212,8 @@ Further Metadata Field Guidance (alphabetical by field) ] -{: .table .table-striped} -**Field ** | **downloadURL** +{: .table .table-striped #downloadURL} +**Field [#](#downloadURL){: .permalink}** | **downloadURL** ----- | ----- **Cardinality** | (0,n) **Required** | Yes, if the file is available for public download. @@ -221,8 +221,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | This must be the **direct** download URL. Other means of accessing the dataset should be expressed using **accessURL**. **Example** | `{"downloadURL":"http://www.agency.gov/vegetables/listofvegetables.csv"}` -{: .table .table-striped} -**Field ** | **format** +{: .table .table-striped #format} +**Field [#](#format){: .permalink}** | **format** ----- | ----- **Cardinality** | (0,1) **Required** | No @@ -230,8 +230,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | This should be a human-readable description of the file format of the dataset, that provides useful information that might not be apparent from `mediaType`. **Example** | `{"format":"A CSV spreadsheet compressed in a ZIP file."}` -{: .table .table-striped} -**Field ** | **identifier** +{: .table .table-striped #identifier} +**Field [#](#identifier){: .permalink}** | **identifier** ----- | ----- **Cardinality** | (1,1) **Required** | Yes, always @@ -239,8 +239,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | This field allows third parties to maintain a consistent record for datasets even if title or URLs are updated. Agencies may integrate an existing system for maintaining unique identifiers or enter arbitrary characters for this field. However, each identifier **must** be unique across the agency's catalog and remain fixed. Characters should be alphanumeric. **Example** | `{"identifier":"1344"}` -{: .table .table-striped} -**Field ** | **isPartOf** +{: .table .table-striped #isPartOf} +**Field [#](#isPartOf){: .permalink}** | **isPartOf** ----- | ----- **Cardinality** | (0,1) **Required** | No @@ -248,8 +248,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | This field allows the grouping of multiple datasets into a "collection". This field should be employed by the individual datasets that together make up a collection. The value for this field should the the `identifier` of the parent dataset. **Example** | `{"isPartOf":"1344"}` -{: .table .table-striped} -**Field ** | **issued** +{: .table .table-striped #issued} +**Field [#](#issued){: .permalink}** | **issued** ----- | ----- **Cardinality** | (0,1) **Required** | No @@ -257,8 +257,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | Dates should be [ISO 8601](http://en.wikipedia.org/wiki/ISO_8601) of least resolution. In other words, as much of YYYY-MM-DDThh:mm:ss.sTZD as is relevant to this dataset. **Example** | `{"issued":"2001-01-15"}` -{: .table .table-striped} -**Field ** | **keyword** +{: .table .table-striped #keyword} +**Field [#](#keyword){: .permalink}** | **keyword** ----- | ----- **Cardinality** | (1,n) **Required** | Yes, always @@ -266,8 +266,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | Surround each keyword with quotes. Separate keywords with commas. Avoid duplicate keywords in the same record. **Example** | `{"keyword":["vegetables","veggies","greens","leafy","spinach","kale","nutrition"]}` -{: .table .table-striped} -**Field ** | **landingPage** +{: .table .table-striped #landingPage} +**Field [#](#landingPage){: .permalink}** | **landingPage** ----- | ----- **Cardinality** | (0,1) **Required** | No @@ -275,8 +275,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | This field is not intended for an agency's homepage (e.g. www.agency.gov), but rather if a dataset has a human-friendly hub or landing page that users should be directed to for all resources tied to the dataset. This allows agencies to better specify what a visitor receives after selecting one of the agency's datasets on Data.gov or in third-party mashups. **Example** | `{"landingPage":"http://www.agency.gov/vegetables"}` -{: .table .table-striped} -**Field ** | **language** +{: .table .table-striped #language} +**Field [#](#language){: .permalink}** | **language** ----- | ----- **Cardinality** | (0,n) **Required** | No @@ -284,8 +284,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | This should adhere to the [RFC 5646](http://tools.ietf.org/html/rfc5646) standard. This [language subtag lookup](http://rishida.net/utils/subtags/) provides a good tool for checking and verifying language codes. A language tag is comprised of either one or two parts, the language subtag (such as en for English, sp for Spanish, wo for Wolof) and the regional subtag (such as US for United States, GB for Great Britain, MX for Mexico), separated by a hyphen. Regional subtags should only be provided when needed to distinguish a language tag from another one (such as American vs. British English). **Example** | `{"language":["en-US"]}` or if multiple languages, `{"language":["es-MX","wo","nv","en-US"]}` -{: .table .table-striped} -**Field ** | **license** +{: .table .table-striped #license} +**Field [#](#license){: .permalink}** | **license** ----- | ----- **Cardinality** | (0,1) **Required** | No @@ -293,8 +293,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | See list of licenses. **Example** | `{"license":""}` -{: .table .table-striped} -**Field ** | **mbox** +{: .table .table-striped #mbox} +**Field [#](#mbox){: .permalink}** | **mbox** ----- | ----- **Cardinality** | (1,1) **Required** | Yes, always @@ -302,8 +302,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | - **Example** | `{"mbox":"joe@agency.gov"}` -{: .table .table-striped} -**Field ** | **mediaType** +{: .table .table-striped #mediaType} +**Field [#](#mediaType){: .permalink}** | **mediaType** ----- | ----- **Cardinality** | (0,1) **Required** | Yes, if the file is available for public download. @@ -311,8 +311,8 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | This must describe the exact files available at **downloadURL** using [MIME Types](http://en.wikipedia.org/wiki/Internet_media_type). _[Also note [Office Open XML MIME types](http://blogs.msdn.com/b/vsofficedeveloper/archive/2008/05/08/office-2007-open-xml-mime-types.aspx)]_ **Example** | `{"mediaType":"application/json"}` -{: .table .table-striped} -**Field ** | **modified** +{: .table .table-striped #modified} +**Field [#](#modified){: .permalink}** | **modified** ----- | ----- **Cardinality** | (1,1) **Required** | Yes, always @@ -322,8 +322,8 @@ Further Metadata Field Guidance (alphabetical by field) If there is a need to reflect that the dataset is continually updated, ISO 8601 formatting can account for this by [giving the duration](http://en.wikipedia.org/wiki/ISO_8601#Durations). For instance, `P1D` for daily, `P2W` for every two weeks, and `PT5M` for every five minutes. **Example** | `{"modified":"2012-01-15"}` or `{"modified":"P1D"}` -{: .table .table-striped} -**Field ** | **PrimaryITInvestmentUII** +{: .table .table-striped #PrimaryITInvestmentUII} +**Field [#](#PrimaryITInvestmentUII){: .permalink}** | **PrimaryITInvestmentUII** ----- | ----- **Cardinality** | (0,1) **Required** | No @@ -331,8 +331,8 @@ If there is a need to reflect that the dataset is continually updated, ISO 8601 **Usage Notes** | Use to link a given dataset with its related IT Unique Investment Identifier, which can often be found in Exhibit 53 documents. **Example** | `{"PrimaryITInvestmentUII":"023-000000001"}` -{: .table .table-striped} -**Field ** | **programCode** +{: .table .table-striped #programCode} +**Field [#](#programCode){: .permalink}** | **programCode** ----- | ----- **Cardinality** | (0,n) **Required** | Yes, for United States Federal Government Agencies @@ -340,8 +340,8 @@ If there is a need to reflect that the dataset is continually updated, ISO 8601 **Usage Notes** | Provide an array of programs related to this data asset, from the [Federal Program Inventory](http://goals.performance.gov/sites/default/files/images/FederalProgramInventory_FY13_MachineReadable_091613.xls). **Example** | `{"programCode":["015:001"]}` or if multiple programs, `{"programCode":["015:001","015:002"]}` -{: .table .table-striped} -**Field ** | **publisher** +{: .table .table-striped #publisher} +**Field [#](#publisher){: .permalink}** | **publisher** ----- | ----- **Cardinality** | (1,1) **Required** | Yes, always @@ -349,8 +349,8 @@ If there is a need to reflect that the dataset is continually updated, ISO 8601 **Usage Notes** | The plaintext name of the entity publishing this dataset. Where greater specificity is desired, include as many levels of publisher as is useful, in ascending order, using the below format. **Example** | `{"publisher":{"name": "U.S. Department of Commerce"}` or if multiple levels, `"publisher": {"name": "National Weather Service", "subOrganizationOf": {"name": "National Oceanic and Atmospheric Administration", "subOrganizationOf": {"name": "U.S. Department of Commerce"}}}` -{: .table .table-striped} -**Field ** | **references** +{: .table .table-striped #references} +**Field [#](#references){: .permalink}** | **references** ----- | ----- **Cardinality** | (0,n) **Required** | No @@ -359,8 +359,8 @@ If there is a need to reflect that the dataset is continually updated, ISO 8601 **Example** | `{"references":["http://www.agency.gov/legumes/legumes_data_documentation.html"]}` or if multiple URLs, `{"references":["http://www.agency.gov/legumes/legumes_data_documentation.html","http://www.agency.gov/fruits/fruit_data_documentation.html"]}` -{: .table .table-striped} -**Field ** | **rights** +{: .table .table-striped #rights} +**Field [#](#rights){: .permalink}** | **rights** ----- | ----- **Cardinality** | (0,1) **Required** | Yes, if accessLevel is "restricted public" or "non-public" @@ -369,8 +369,8 @@ If there is a need to reflect that the dataset is continually updated, ISO 8601 **Example** | `{"rights":"This dataset contains Personally Identifiable Information and could not be released for public access. A statistical analysis of the data contained herein, stripped of all personal identifiers, is available at http://another.website.gov/dataset."}` -{: .table .table-striped} -**Field ** | **spatial** +{: .table .table-striped #spatial} +**Field [#](#spatial){: .permalink}** | **spatial** ----- | ----- **Cardinality** | (0,1) **Required** | Yes, if the dataset is spatial @@ -378,8 +378,8 @@ If there is a need to reflect that the dataset is continually updated, ISO 8601 **Usage Notes** | This field should contain one of the following types of content: (1) a bounding coordinate box for the dataset represented in latitude / longitude pairs where the coordinates are specified in decimal degrees and in the order of: minimum longitude, minimum latitude, maximum longitude, maximum latitude; (2) a latitude / longitude pair (in decimal degrees) representing a point where the dataset is relevant; (3) a geographic feature expressed in [Geography Markup Language using the Simple Features Profile](http://www.ogcnetwork.net/gml-sf); or (4) a geographic feature from the [GeoNames database](http://www.geonames.org). **Example** | `{"spatial":"Lincoln, Nebraska"}` -{: .table .table-striped} -**Field** | **systemOfRecords** +{: .table .table-striped #systemOfRecords} +**Field [#](#systemOfRecords){: .permalink}** | **systemOfRecords** ----- | ----- **Cardinality** | (0,1) **Required** | No @@ -387,8 +387,8 @@ If there is a need to reflect that the dataset is continually updated, ISO 8601 **Usage Notes** | This field should a URL to the System of Records Notice (SORN) that relates to the dataset, specifically from FederalRegister.gov. **Example** | `{"https://www.federalregister.gov/articles/2002/04/08/02-7376/privacy-act-of-1974-publication-in-full-of-all-notices-of-systems-of-records-including-several-new#p-361"}` -{: .table .table-striped} -**Field ** | **temporal** +{: .table .table-striped #temporal} +**Field [#](#temporal){: .permalink}** | **temporal** ----- | ----- **Cardinality** | (0,1) **Required** | Yes, if applicable @@ -400,8 +400,8 @@ If there is a need to reflect that the dataset is continually updated, ISO 8601 Updated every 5 minutes beginning on February 15, 2010 would be represented as: `R/2010-02-15/PT5M`. **Example** | `{"temporal":"2000-01-15T00:45:00Z/2010-01-15T00:06:00Z"}` or `{"temporal":"R/2000-01-15T00:45:00Z/P1W"}` -{: .table .table-striped} -**Field ** | **theme** +{: .table .table-striped #theme} +**Field [#](#theme){: .permalink}** | **theme** ----- | ----- **Cardinality** | (0,n) **Required** | No @@ -409,8 +409,8 @@ Updated every 5 minutes beginning on February 15, 2010 would be represented as: **Usage Notes** | Separate multiple categories with a comma. Could include [ISO Topic Categories](http://www.isotopicmaps.org/). **Examples** | `{"theme":["vegetables"]}` or if multiple categories, `{"theme":["vegetables","produce"]}` -{: .table .table-striped} -**Field ** | **title** +{: .table .table-striped #title} +**Field [#](#title){: .permalink}** | **title** ----- | ----- **Cardinality** | (1,1) **Required** | Yes, always From baa01780f7dd2c314937171068b0abe0da7c870c Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Mon, 8 Sep 2014 18:17:12 -0400 Subject: [PATCH 021/129] updating distribution guidance, part 1 In response to #217, #248 I still need to update the expanded guidance --- v1.1/schema.md | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index ef0f1ba9..f4f5cdf3 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -41,6 +41,8 @@ The [Implementation Guidance](/implementation-guide/) available as a part of Pro Where optional fields are included in a catalog file but are unpopulated, they may be represented by a `null` value. They should not be represented by an empty string (`""`). +When a record has an `accessURL` or `downloadURL`, they should be contained as objects within a `distribution`. Any object may be described by `title`, `description`, `format`, or `mediaType`, though when an object contains `downloadURL`, it must be accompanied by `mediatype`. + The Project Open Data schema is case sensitive. The schema uses a camel case convention where the first letter of some words within a field are capitalized (usually all words but the first one). While it may seem subtle which characters are uppercase and lowercase, it is necessary to follow the exact same casing as defined in the schema documented here. For example: > Correct: `contactPoint` @@ -79,15 +81,26 @@ Field | Label | Definition -------------- | -------------- | -------------- bureauCode | Bureau Code | Federal agencies, combined agency and bureau code from [OMB Circular A-11, Appendix C](http://www.whitehouse.gov/sites/default/files/omb/assets/a11_current_year/app_c.pdf) in the format of `015:11`. programCode | Program Code | Federal agencies, list the primary program related to this data asset, from the [Federal Program Inventory](http://goals.performance.gov/sites/default/files/images/FederalProgramInventory_FY13_MachineReadable_091613.xls). Use the format of `015:001` -rights | Rights | This may include information regarding access or restrictions based on privacy, security, or other policies. This should also serve as an explanation for the selected “accessLevel” including instructions for how to access a restricted file, if applicable, or explanation for why a “non-public” or “restricted public” data asset is not “public,” if applicable. Text, 255 characters. -accessURL | Access URL | URL providing indirect access to a dataset, for example via API or a graphical interface. -downloadURL | Download URL | URL providing direct access to a downloadable file of a dataset. -format | Format | A human-readable description of the file format of a dataset. +distribution | Distribution | Represents a specific available form of a dataset in the form of download or access URLs, along with metadata specific to that form. license | License | The license with which the dataset or API is published. See [Open Licenses](/open-licenses/) for more information. -mediaType | MIME Type | The machine-readable file format ([IANA MIME Type](http://en.wikipedia.org/wiki/Internet_media_type)) of a dataset. +rights | Rights | This may include information regarding access or restrictions based on privacy, security, or other policies. This should also serve as an explanation for the selected “accessLevel” including instructions for how to access a restricted file, if applicable, or explanation for why a “non-public” or “restricted public” data asset is not “public,” if applicable. Text, 255 characters. spatial | Spatial | The range of spatial applicability of a dataset. Could include a spatial region like a bounding box or a named place. temporal | Temporal | The range of temporal applicability of a dataset (i.e., a start and end date of applicability for the data). +"Common Core" Distribution Fields +------------------------------------------- +Within a record, `distribution` is used to aggregate the metadata specific to a dataset's resources (`accessURL` and `downloadURL`), which may be described using the following fields. Each distribution should contain one `accessURL` or `downloadURL`. `downloadURL` should always be accompanied by `mediaType`. + +{: .table .table-striped} +Field | Label | Definition +-------------- | -------------- | -------------- +accessURL | Access URL | URL providing indirect access to a dataset, for example via API or a graphical interface. +downloadURL | Download URL | URL providing direct access to a downloadable file of a dataset. +description | Description | Human-readable description of the distribution. +format | Format | A human-readable description of the file format of a distribution. +mediaType | MIME Type | The machine-readable file format ([IANA MIME Type](http://en.wikipedia.org/wiki/Internet_media_type)) of a distribution. +title | Title | Human-readable name of the distribution. + Beyond Common Core -- Extending the Schema ------------------------------------------ "Extensional" and/or domain specific metadata can easily be added using other vocabularies even if it is not a term (entity/property) that will get indexed by the major search engines - it could still be indexed by other custom search engines and by Data.gov. Agencies are encouraged to extend their metadata descriptions using elements from the "Expanded Fields" list shown below, or from any well-known vocabulary (including Dublin Core, FGDC, ISO 19115, NIEM, and a growing number of vocabularies published at [Vocab.Data.gov](http://vocab.data.gov)) as long as they are properly assigned. @@ -102,7 +115,6 @@ Field | Label | Definition theme | Category | Main thematic category of the dataset. dataDictionary | Data Dictionary | 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. dataQuality | Data Quality | Whether the dataset meets the agency's Information Quality Guidelines (true/false). -distribution | Distribution | Holds multiple download URLs for datasets composed of multiple files and/or file types accrualPeriodicity | Frequency | Frequency with which dataset is published. landingPage | Homepage URL | Alternative landing page used to redirect user to a contextual, Agency-hosted "homepage" for the Dataset or API when selecting this resource from the Data.gov user interface. isPartOf | isPartOf | The collection of which the dataset is a subset. From 5e20ba6b20e5d8680b22f7a32dd7ee94b4a49d51 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Mon, 8 Sep 2014 18:43:52 -0400 Subject: [PATCH 022/129] adding css for child fields --- assets/css/site.css | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/assets/css/site.css b/assets/css/site.css index 8eebd7d5..bacc6399 100644 --- a/assets/css/site.css +++ b/assets/css/site.css @@ -648,7 +648,9 @@ background-color : #e3e3e3; .icon-fullscreen { background-position: -456px -144px; } - +.child-field { + border-left : 10em solid #fff; +} @media (max-width: 979px) { .navbar .nav-collapse .nav.pull-right { float: none; From cd7a5279da361de7df3e5843ad16aa37ca77fb77 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Mon, 8 Sep 2014 18:44:09 -0400 Subject: [PATCH 023/129] updating distribution guidance, part 2 In response to #217, #248 --- v1.1/schema.md | 127 +++++++++++++++++++++++++++++++------------------ 1 file changed, 81 insertions(+), 46 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index f4f5cdf3..da6a8d6a 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -41,7 +41,7 @@ The [Implementation Guidance](/implementation-guide/) available as a part of Pro Where optional fields are included in a catalog file but are unpopulated, they may be represented by a `null` value. They should not be represented by an empty string (`""`). -When a record has an `accessURL` or `downloadURL`, they should be contained as objects within a `distribution`. Any object may be described by `title`, `description`, `format`, or `mediaType`, though when an object contains `downloadURL`, it must be accompanied by `mediatype`. +When a record has an **accessURL** or **downloadURL**, they should be contained as objects within a **distribution**. Any object may be described by **title**, **description**, **format**, or **mediaType**, though when an object contains **downloadURL**, it must be accompanied by **mediaType**. The Project Open Data schema is case sensitive. The schema uses a camel case convention where the first letter of some words within a field are capitalized (usually all words but the first one). While it may seem subtle which characters are uppercase and lowercase, it is necessary to follow the exact same casing as defined in the schema documented here. For example: @@ -89,7 +89,7 @@ temporal | Temporal | The range of temporal applicability of a dataset (i. "Common Core" Distribution Fields ------------------------------------------- -Within a record, `distribution` is used to aggregate the metadata specific to a dataset's resources (`accessURL` and `downloadURL`), which may be described using the following fields. Each distribution should contain one `accessURL` or `downloadURL`. `downloadURL` should always be accompanied by `mediaType`. +Within a record, **distribution** is used to aggregate the metadata specific to a dataset's resources (**accessURL** and **downloadURL**), which may be described using the following fields. Each distribution should contain one **accessURL** or **downloadURL**. **downloadURL** should always be accompanied by **mediaType**. {: .table .table-striped} Field | Label | Definition @@ -137,15 +137,6 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | This field refers to degree to which this dataset *could be made available* to the public, regardless of whether it is currently available to the public. For example, if a member of the public can walk into your agency and obtain a dataset, that entry is **public** even if there are no files online. A *restricted public* dataset is one only available under certain conditions or to certain audiences (such as researchers who sign a waiver). A *non-public* dataset is one that could never be made available to the public for privacy, security, or other reasons as determined by your agency. **Example** | `{"accessLevel":"public"}` -{: .table .table-striped #accessURL} -**Field [#](#accessURL){: .permalink}** | **accessURL** ------ | ----- -**Cardinality** | (0,n) -**Required** | Yes, if the file is accessible indirectly, through means other than direct download. -**Accepted Values** | String (URL) -**Usage Notes** | This should be the URL for an indirect means of accessing the data, such as API documentation, a 'wizard' or other graphical interface which is used to generate a download, feed, or a request form for the data. This should not be a **direct** download URL. It is usually assumed that accessURL is an HTML webpage. -**Example** | `{"accessURL":"http://www.agency.gov/api/vegetables/"}` - {: .table .table-striped #accrualPeriodicity} **Field [#](#accrualPeriodicity){: .permalink}** | **accrualPeriodicity** ----- | ----- @@ -204,37 +195,62 @@ Further Metadata Field Guidance (alphabetical by field) **Field [#](#distribution){: .permalink}** | **distribution** ----- | ----- **Cardinality** | (0,n) -**Required** | No -**Accepted Values** | See Usage Notes -**Usage Notes** | Distribution is a concatenation, as appropriate, of the following elements: **accessURL** and **format**. If an entry has only one dataset, enter details for that one; if it has multiple datasets (such as a bulk download and an API), separate entries as seen below: - - "distribution": [ - { - "accessURL":"https://explore.data.gov/views/ykv5-fn9t/rows.csv?accessType=DOWNLOAD", - "format":"text/csv" - }, - { - "accessURL":"https://explore.data.gov/views/ykv5-fn9t/rows.json?accessType=DOWNLOAD", - "format":"application/json" - }, - { - "accessURL":"https://explore.data.gov/views/ykv5-fn9t/rows.xml?accessType=DOWNLOAD", - "format":"text/xml" - } - ] - - -{: .table .table-striped #downloadURL} -**Field [#](#downloadURL){: .permalink}** | **downloadURL** +**Required** | Yes, if the dataset has an **accessURL** or **downloadURL**. +**Accepted Values** | Array of Objects +**Usage Notes** | Distribution is a concatenation, as appropriate, of the following elements: **accessURL**, **downloadURL**, **description**, **format**, **mediaType**, and **title**. If an entry has only one form, enter details for that one; if it has multiple forms (such as a bulk download and an API), separate entries as seen below: +**Example** | + "distribution": [ + { + "description": "Vegetable data as a CSV file", + "downloadURL": "http://www.agency.gov/vegetables/listofvegetables.csv", + "format": "CSV", + "mediaType": "text/csv", + "title": "vegetables.csv" + }, + { + "description": "Vegetable data as a zipped CSV file with attached data dictionary", + "downloadURL": "http://www.agency.gov/vegetables/vegetables-all.zip", + "format": "Zipped CSV", + "mediaType": "application/zip", + "title": "vegetables-all.zip" + }, + { + "accessURL": "http://www.agency.gov/api/vegetables/", + "description": "A fully queryable REST API with JSON and XML output", + "format": "API", + "title": "Vegetables REST API" + } + ] + +{: .table .table-striped .child-field #distribution-accessURL} +**Field [#](#distribution-accessURL){: .permalink}** | **distribution → accessURL** +----- | ----- +**Cardinality** | (0,n) +**Required** | Yes, if the file is accessible indirectly, through means other than direct download. +**Accepted Values** | String (URL) +**Usage Notes** | This should be the URL for an indirect means of accessing the data, such as API documentation, a 'wizard' or other graphical interface which is used to generate a download, feed, or a request form for the data. This should not be a **direct** download URL. It is usually assumed that accessURL is an HTML webpage. +**Example** | `{"accessURL":"http://www.agency.gov/api/vegetables/"}` + +{: .table .table-striped .child-field #distribution-downloadURL} +**Field [#](#distribution-downloadURL){: .permalink}** | **distribution → downloadURL** ----- | ----- **Cardinality** | (0,n) **Required** | Yes, if the file is available for public download. **Accepted Values** | String (URL) -**Usage Notes** | This must be the **direct** download URL. Other means of accessing the dataset should be expressed using **accessURL**. +**Usage Notes** | This must be the **direct** download URL. Other means of accessing the dataset should be expressed using **accessURL**. This should always be accompanied by **mediaType**. **Example** | `{"downloadURL":"http://www.agency.gov/vegetables/listofvegetables.csv"}` -{: .table .table-striped #format} -**Field [#](#format){: .permalink}** | **format** +{: .table .table-striped .child-field #distribution-description} +**Field [#](#distribution-description){: .permalink}** | **distribution → description** +----- | ----- +**Cardinality** | (1,1) +**Required** | Yes, always +**Accepted Values** | String +**Usage Notes** | This should be a human-readable description of the distribution. +**Example** | `{"description":"Vegetable data as a zipped CSV file with attached data dictionary"}` + +{: .table .table-striped .child-field #distribution-format} +**Field [#](#distribution-format){: .permalink}** | **distribution → format** ----- | ----- **Cardinality** | (0,1) **Required** | No @@ -242,6 +258,25 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | This should be a human-readable description of the file format of the dataset, that provides useful information that might not be apparent from `mediaType`. **Example** | `{"format":"A CSV spreadsheet compressed in a ZIP file."}` +{: .table .table-striped .child-field #distribution-mediaType} +**Field [#](#distribution-mediaType){: .permalink}** | **distribution → mediaType** +----- | ----- +**Cardinality** | (0,1) +**Required** | Yes, if the file is available for public download. +**Accepted Values** | String +**Usage Notes** | This must describe the exact files available at **downloadURL** using [MIME Types](http://en.wikipedia.org/wiki/Internet_media_type). _[Also note [Office Open XML MIME types](http://blogs.msdn.com/b/vsofficedeveloper/archive/2008/05/08/office-2007-open-xml-mime-types.aspx)]_ +**Example** | `{"mediaType":"application/csv"}` + +{: .table .table-striped .child-field #distribution-title} +**Field [#](#distribution-title){: .permalink}** | **distribution → title** +----- | ----- +**Cardinality** | (1,1) +**Required** | Yes, always +**Accepted Values** | String +**Usage Notes** | This should be a useful title for the distribution. Acronyms should be avoided. +**Example** | `{"title":"Spreadsheet"}` + + {: .table .table-striped #identifier} **Field [#](#identifier){: .permalink}** | **identifier** ----- | ----- @@ -314,15 +349,6 @@ Further Metadata Field Guidance (alphabetical by field) **Usage Notes** | - **Example** | `{"mbox":"joe@agency.gov"}` -{: .table .table-striped #mediaType} -**Field [#](#mediaType){: .permalink}** | **mediaType** ------ | ----- -**Cardinality** | (0,1) -**Required** | Yes, if the file is available for public download. -**Accepted Values** | String -**Usage Notes** | This must describe the exact files available at **downloadURL** using [MIME Types](http://en.wikipedia.org/wiki/Internet_media_type). _[Also note [Office Open XML MIME types](http://blogs.msdn.com/b/vsofficedeveloper/archive/2008/05/08/office-2007-open-xml-mime-types.aspx)]_ -**Example** | `{"mediaType":"application/json"}` - {: .table .table-striped #modified} **Field [#](#modified){: .permalink}** | **modified** ----- | ----- @@ -406,7 +432,16 @@ If there is a need to reflect that the dataset is continually updated, ISO 8601 **Required** | Yes, if applicable **Accepted Values** | ISO 8601 Date **Usage Notes** | This field should contain an interval of time defined by start and end dates. Dates should be formatted as pairs of {start datetime/end datetime} in the [ISO 8601](http://en.wikipedia.org/wiki/ISO_8601) format. ISO 8601 specifies that datetimes can be formatted in a number of ways, including a simple four-digit year (eg. 2013) to a much more specific YYYY-MM-DDTHH:MM:SSZ, where the T specifies a seperator between the date and time and time is expressed in 24 hour notation in the UTC (Zulu) time zone. (e.g., 2011-02-14T12:00:00Z/2013-07-04T19:34:00Z). Use a solidus ("/") to separate start and end times. - + +{: .table .table-striped #title} +**Field [#](#title){: .permalink}** | **title** +----- | ----- +**Cardinality** | (1,1) +**Required** | Yes, always +**Accepted Values** | String +**Usage Notes** | Acronyms should be avoided. +**Example** | `{"title":"Types of Vegetables"}` + If there is a need to reflect that the dataset is continually updated, ISO 8601 formatting can account for this [with repeating intervals](http://en.wikipedia.org/wiki/ISO_8601#Time_intervals). For instance, updated monthly starting in January 2010 and continuing through the present would be represented as: `R/2010-01/P1M`. Updated every 5 minutes beginning on February 15, 2010 would be represented as: `R/2010-02-15/PT5M`. From 1b53820b77dbcb410c6413f4952528423477226b Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Mon, 8 Sep 2014 18:53:44 -0400 Subject: [PATCH 024/129] Fixing syntax of distribution json example --- v1.1/schema.md | 49 ++++++++++++++++++++++++++----------------------- 1 file changed, 26 insertions(+), 23 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index da6a8d6a..518f886b 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -198,29 +198,32 @@ Further Metadata Field Guidance (alphabetical by field) **Required** | Yes, if the dataset has an **accessURL** or **downloadURL**. **Accepted Values** | Array of Objects **Usage Notes** | Distribution is a concatenation, as appropriate, of the following elements: **accessURL**, **downloadURL**, **description**, **format**, **mediaType**, and **title**. If an entry has only one form, enter details for that one; if it has multiple forms (such as a bulk download and an API), separate entries as seen below: -**Example** | - "distribution": [ - { - "description": "Vegetable data as a CSV file", - "downloadURL": "http://www.agency.gov/vegetables/listofvegetables.csv", - "format": "CSV", - "mediaType": "text/csv", - "title": "vegetables.csv" - }, - { - "description": "Vegetable data as a zipped CSV file with attached data dictionary", - "downloadURL": "http://www.agency.gov/vegetables/vegetables-all.zip", - "format": "Zipped CSV", - "mediaType": "application/zip", - "title": "vegetables-all.zip" - }, - { - "accessURL": "http://www.agency.gov/api/vegetables/", - "description": "A fully queryable REST API with JSON and XML output", - "format": "API", - "title": "Vegetables REST API" - } - ] +**Example** | See below + +~~~ +"distribution": [ + { + "description": "Vegetable data as a CSV file", + "downloadURL": "http://www.agency.gov/vegetables/listofvegetables.csv", + "format": "CSV", + "mediaType": "text/csv", + "title": "vegetables.csv" + }, + { + "description": "Vegetable data as a zipped CSV file with attached data dictionary", + "downloadURL": "http://www.agency.gov/vegetables/vegetables-all.zip", + "format": "Zipped CSV", + "mediaType": "application/zip", + "title": "vegetables-all.zip" + }, + { + "accessURL": "http://www.agency.gov/api/vegetables/", + "description": "A fully queryable REST API with JSON and XML output", + "format": "API", + "title": "Vegetables REST API" + } + ] +~~~ {: .table .table-striped .child-field #distribution-accessURL} **Field [#](#distribution-accessURL){: .permalink}** | **distribution → accessURL** From a29db455e1e18a42be5cb9ec68abfbd2d82debb4 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Mon, 8 Sep 2014 18:55:01 -0400 Subject: [PATCH 025/129] updating cardinality for distribution items --- v1.1/schema.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 518f886b..477d0055 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -228,7 +228,7 @@ Further Metadata Field Guidance (alphabetical by field) {: .table .table-striped .child-field #distribution-accessURL} **Field [#](#distribution-accessURL){: .permalink}** | **distribution → accessURL** ----- | ----- -**Cardinality** | (0,n) +**Cardinality** | (0,1) **Required** | Yes, if the file is accessible indirectly, through means other than direct download. **Accepted Values** | String (URL) **Usage Notes** | This should be the URL for an indirect means of accessing the data, such as API documentation, a 'wizard' or other graphical interface which is used to generate a download, feed, or a request form for the data. This should not be a **direct** download URL. It is usually assumed that accessURL is an HTML webpage. @@ -237,7 +237,7 @@ Further Metadata Field Guidance (alphabetical by field) {: .table .table-striped .child-field #distribution-downloadURL} **Field [#](#distribution-downloadURL){: .permalink}** | **distribution → downloadURL** ----- | ----- -**Cardinality** | (0,n) +**Cardinality** | (0,1) **Required** | Yes, if the file is available for public download. **Accepted Values** | String (URL) **Usage Notes** | This must be the **direct** download URL. Other means of accessing the dataset should be expressed using **accessURL**. This should always be accompanied by **mediaType**. @@ -246,7 +246,7 @@ Further Metadata Field Guidance (alphabetical by field) {: .table .table-striped .child-field #distribution-description} **Field [#](#distribution-description){: .permalink}** | **distribution → description** ----- | ----- -**Cardinality** | (1,1) +**Cardinality** | (0,1) **Required** | Yes, always **Accepted Values** | String **Usage Notes** | This should be a human-readable description of the distribution. @@ -273,7 +273,7 @@ Further Metadata Field Guidance (alphabetical by field) {: .table .table-striped .child-field #distribution-title} **Field [#](#distribution-title){: .permalink}** | **distribution → title** ----- | ----- -**Cardinality** | (1,1) +**Cardinality** | (0,1) **Required** | Yes, always **Accepted Values** | String **Usage Notes** | This should be a useful title for the distribution. Acronyms should be avoided. From 26a93266da162e7d07f7e1703bbc901b6f31209e Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Mon, 8 Sep 2014 19:04:28 -0400 Subject: [PATCH 026/129] adding instructions for no accessURL/downloadURL In response to #157 --- catalog.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/catalog.md b/catalog.md index f8da6503..f21ab3c5 100644 --- a/catalog.md +++ b/catalog.md @@ -41,6 +41,8 @@ The JSON representation of the catalog should track directly with any other opti Where optional fields are included in a catalog file but are unpopulated, they may be represented by a `null` value. They should not be represented by an empty string (`""`). +If a dataset has not yet been published or is not accessible, this may be indicated by the absence of `accessURL` or `downloadURL` (and thus `distribution`) in the record. + The JSON catalog files should only use UTF-8 character encoding. ### RDFa Lite From 355ef4ebced833689b7c658848f439bb63115cd7 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Mon, 8 Sep 2014 19:12:18 -0400 Subject: [PATCH 027/129] Simplify usage notes for distribution --- v1.1/schema.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 477d0055..e37493a5 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -197,7 +197,7 @@ Further Metadata Field Guidance (alphabetical by field) **Cardinality** | (0,n) **Required** | Yes, if the dataset has an **accessURL** or **downloadURL**. **Accepted Values** | Array of Objects -**Usage Notes** | Distribution is a concatenation, as appropriate, of the following elements: **accessURL**, **downloadURL**, **description**, **format**, **mediaType**, and **title**. If an entry has only one form, enter details for that one; if it has multiple forms (such as a bulk download and an API), separate entries as seen below: +**Usage Notes** | This is a container for one or multiple `distribution` objects which group together the fields: **accessURL**, **downloadURL**, **description**, **format**, **mediaType**, and **title**. **Example** | See below ~~~ From 9b15ac418dff8b9b90eb08b1af7204d440ecf716 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Mon, 8 Sep 2014 19:14:55 -0400 Subject: [PATCH 028/129] correcting capitalization for primaryITInvestment In response to #284 --- v1.1/schema.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index e37493a5..d981415c 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -119,7 +119,7 @@ accrualPeriodicity | Frequency | Frequency with which dataset is publ landingPage | Homepage URL | Alternative landing page used to redirect user to a contextual, Agency-hosted "homepage" for the Dataset or API when selecting this resource from the Data.gov user interface. isPartOf | isPartOf | The collection of which the dataset is a subset. language | Language | The language of the dataset. -PrimaryITInvestmentUII | Primary IT Investment UII | For linking a dataset with an IT Unique Investment Identifier (UII) +primaryITInvestmentUII | primary IT Investment UII | For linking a dataset with an IT Unique Investment Identifier (UII) references | Related Documents | Related documents such as technical information about a dataset, developer documentation, etc. issued | Release Date | Date of formal issuance. systemOfRecords | System of Records | If the systems is designated as a system of records under the Privacy Act of 1974, provide the URL to the System of Records Notice related to this dataset. @@ -363,14 +363,14 @@ Further Metadata Field Guidance (alphabetical by field) If there is a need to reflect that the dataset is continually updated, ISO 8601 formatting can account for this by [giving the duration](http://en.wikipedia.org/wiki/ISO_8601#Durations). For instance, `P1D` for daily, `P2W` for every two weeks, and `PT5M` for every five minutes. **Example** | `{"modified":"2012-01-15"}` or `{"modified":"P1D"}` -{: .table .table-striped #PrimaryITInvestmentUII} -**Field [#](#PrimaryITInvestmentUII){: .permalink}** | **PrimaryITInvestmentUII** +{: .table .table-striped #primaryITInvestmentUII} +**Field [#](#primaryITInvestmentUII){: .permalink}** | **primaryITInvestmentUII** ----- | ----- **Cardinality** | (0,1) **Required** | No **Accepted Values** | String **Usage Notes** | Use to link a given dataset with its related IT Unique Investment Identifier, which can often be found in Exhibit 53 documents. -**Example** | `{"PrimaryITInvestmentUII":"023-000000001"}` +**Example** | `{"primaryITInvestmentUII":"023-000000001"}` {: .table .table-striped #programCode} **Field [#](#programCode){: .permalink}** | **programCode** From b447a664d2f336d4e3e7fcc229b7fb6f4191a133 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Tue, 9 Sep 2014 17:45:49 -0400 Subject: [PATCH 029/129] moving file to v1.1 folder --- {schema => v1.1/schema}/1_1_final/catalog.json | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename {schema => v1.1/schema}/1_1_final/catalog.json (100%) diff --git a/schema/1_1_final/catalog.json b/v1.1/schema/1_1_final/catalog.json similarity index 100% rename from schema/1_1_final/catalog.json rename to v1.1/schema/1_1_final/catalog.json From 540570a2b3425a33dc6b40519bc1b04d77e835ab Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Tue, 9 Sep 2014 17:46:54 -0400 Subject: [PATCH 030/129] moving 2nd file to v1.1 folder --- {schema => v1.1/schema}/1_1_final/single_entry.json | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename {schema => v1.1/schema}/1_1_final/single_entry.json (100%) diff --git a/schema/1_1_final/single_entry.json b/v1.1/schema/1_1_final/single_entry.json similarity index 100% rename from schema/1_1_final/single_entry.json rename to v1.1/schema/1_1_final/single_entry.json From cfd0e1a03a98744d0f991e2ec7fdf213e8b5f2d7 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Tue, 9 Sep 2014 19:52:15 -0400 Subject: [PATCH 031/129] Adds fields and guidance to specify schema version This is to help address #309 --- v1.1/schema.md | 42 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index d981415c..c4267b99 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -53,6 +53,11 @@ The Project Open Data schema is case sensitive. The schema uses a camel case con Links to downloadable examples of metadata files developed in this and other formats in [the metadata resources](/metadata-resources/). Tools to help agencies produce and maintain their data inventories are [available on GitHub](http://www.github.com/project-open-data) and hosted at [Labs.Data.gov](http://labs.data.gov). +Schema Version Declaration (Required) +----------------------------- +In order to distinguish the schema version being used publishers are required to specify the relevant URI using the `$schema` field at the beginning of their data.json file. Version 1.1 of the schema should be identified with the following URI: http://projectopendata.PLACEHOLDER.gov/v1.1/schema. Optionally, publishers may also use the `$ref` field to reference the default [JSON Schema](http://json-schema.org/) file used to define the schema (http://projectopendata.PLACEHOLDER.gov/v1.1/schema/catalog.json) or they may refer to their own JSON Schema file where they have extended the schema. These fields are both part of a JSON object that also contains a listing of all datasets under the `dataset` field. See the [Catalog section](#Catalog) under *Further Metadata Field Guidance* for more details. + + "Common Core" Required Fields ----------------------------- The following "common core" fields are required, to be used to describe each entry: @@ -125,7 +130,42 @@ issued | Release Date | Date of formal issuance. systemOfRecords | System of Records | If the systems is designated as a system of records under the Privacy Act of 1974, provide the URL to the System of Records Notice related to this dataset. -Further Metadata Field Guidance (alphabetical by field) +Further Metadata Field Guidance +------------------------------- +Additional details for each field are provided here broken down into sections for the overarching [Catalog](#Catalog), each [dataset](#dataset), and each dataset's [distribution](#distribution). + +Catalog Fields {#Catalog} +------------------------------- + +{: .table .table-striped #schema} +**Field [#](#schema){: .permalink}** | **$schema** +----- | ----- +**Cardinality** | (1,1) +**Required** | Yes, always +**Accepted Values** | String (URL) +**Usage Notes** | This is used to identify the schema version using a URI. The URI for version 1.1 of the schema is `http://projectopendata.PLACEHOLDER.gov/v1.1/schema` +**Example** | `{"$schema": "http://projectopendata.PLACEHOLDER.gov/v1.1/schema"}` + +{: .table .table-striped #ref} +**Field [#](#ref){: .permalink}** | **$ref** +----- | ----- +**Cardinality** | (0,1) +**Required** | No +**Accepted Values** | String (URL) +**Usage Notes** | This is used to specify a [JSON Schema](http://json-schema.org/) file that defines all fields. By default, it is recommended that the canonical JSON Schema file is referenced (http://projectopendata.PLACEHOLDER.gov/v1.1/schema/catalog.json) but if the schema had been extended, publishers may reference a file that defines those extensions. +**Example** | `{"$ref": "http://projectopendata.PLACEHOLDER.gov/v1.1/schema/catalog.json"}` + +{: .table .table-striped #dataset} +**Field [#](#dataset){: .permalink}** | **dataset** +----- | ----- +**Cardinality** | (1,n) +**Required** | Yes, always +**Accepted Values** | Array of Objects +**Usage Notes** | This field is a container for an array of Dataset objects. See [Dataset Fields](#Dataset) below for details +**Example** | `{"dataset": [...]}` + + +Dataset Fields {#Dataset} ------------------------------- {: .table .table-striped #accessLevel} From b27b723c0019657761be206749f922c24159cf07 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Wed, 10 Sep 2014 11:55:31 -0400 Subject: [PATCH 032/129] updating contactPoint directions In response to https://github.com/project-open-data/project-open-data.github.io/issues/358 --- v1.1/schema.md | 41 ++++++++++++++++++++++++++++------------- 1 file changed, 28 insertions(+), 13 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index c4267b99..d886835b 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -72,8 +72,7 @@ description | Description | Human-readable description (e.g., a keyword | Tags | Tags (or keywords) help users discover your dataset; please include terms that would be used by technical and non-technical users. modified | Last Update | Most recent date on which the dataset was changed, updated or modified. publisher | Publisher | The publishing entity. -contactPoint | Contact Name | Contact person's name for the asset. -mbox | Contact Email | Contact person's email address. +contactPoint | Contact Name and Email | Contact person's name and email for the asset. identifier | Unique Identifier | A unique identifier for the dataset or API as maintained within an Agency catalog or database. accessLevel | Public Access Level | 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) @@ -200,9 +199,34 @@ Dataset Fields {#Dataset} ----- | ----- **Cardinality** | (1,1) **Required** | Yes, always +**Accepted Values** | vCard object +**Usage Notes** | This is a container for two fields that together make up the contact information for the dataset. **contactPoint** should always contain both the person's appropriately formatted full name (**fn**) and email (**hasEmail**). +**Example** | See below + +~~~ + "contactPoint": { + "fn": "Jane Doe", + "hasEmail": "mailto:jane.doe@agency.gov" + } +~~~ + +{: .table .table-striped .child-field #contactPoint-fn} +**Field [#](#contactPoint-fn){: .permalink}** | **contactPoint → fn** +----- | ----- +**Cardinality** | (1,1) +**Required** | Yes, always **Accepted Values** | String -**Usage Notes** | - -**Example** | `{"contactPoint":"John Brown"}` +**Usage Notes** | This should include included with **hasEmail** as part of a record's **contactPoint** (see above example). +**Example** | `{"fn": "Jane Doe"}` + +{: .table .table-striped .child-field #contactPoint-hasEmail} +**Field [#](#contactPoint-hasEmail){: .permalink}** | **contactPoint → hasEmail** +----- | ----- +**Cardinality** | (1,1) +**Required** | Yes, always +**Accepted Values** | String +**Usage Notes** | This should be formatted per vCard specifications (see example below) and included with **fn** as part of a record's **contactPoint** (see above example). +**Example** | `{"hasEmail": "mailto:jane.doe@agency.gov"}` {: .table .table-striped #dataDictionary} **Field [#](#dataDictionary){: .permalink}** | **dataDictionary** @@ -383,15 +407,6 @@ Dataset Fields {#Dataset} **Usage Notes** | See list of licenses. **Example** | `{"license":""}` -{: .table .table-striped #mbox} -**Field [#](#mbox){: .permalink}** | **mbox** ------ | ----- -**Cardinality** | (1,1) -**Required** | Yes, always -**Accepted Values** | Email address -**Usage Notes** | - -**Example** | `{"mbox":"joe@agency.gov"}` - {: .table .table-striped #modified} **Field [#](#modified){: .permalink}** | **modified** ----- | ----- From ce1bf8f3088f99ffeae261e26005893dfa149470 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Wed, 10 Sep 2014 16:52:01 -0400 Subject: [PATCH 033/129] new property names for schema version declaration As discussed in #309 --- v1.1/schema.md | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index d886835b..d1f2ec31 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -55,7 +55,7 @@ Links to downloadable examples of metadata files developed in this and other for Schema Version Declaration (Required) ----------------------------- -In order to distinguish the schema version being used publishers are required to specify the relevant URI using the `$schema` field at the beginning of their data.json file. Version 1.1 of the schema should be identified with the following URI: http://projectopendata.PLACEHOLDER.gov/v1.1/schema. Optionally, publishers may also use the `$ref` field to reference the default [JSON Schema](http://json-schema.org/) file used to define the schema (http://projectopendata.PLACEHOLDER.gov/v1.1/schema/catalog.json) or they may refer to their own JSON Schema file where they have extended the schema. These fields are both part of a JSON object that also contains a listing of all datasets under the `dataset` field. See the [Catalog section](#Catalog) under *Further Metadata Field Guidance* for more details. +In order to distinguish the schema version being used publishers are required to specify the relevant URI using the `conformsTo` field at the beginning of their data.json file. Version 1.1 of the schema should be identified with the following URI: http://projectopendata.PLACEHOLDER.gov/v1.1/schema. Optionally, publishers may also use the `describedBy` field to reference the default [JSON Schema](http://json-schema.org/) file used to define the schema (http://projectopendata.PLACEHOLDER.gov/v1.1/schema/catalog.json) or they may refer to their own JSON Schema file where they have extended the schema. These fields are both part of a JSON object that also contains a listing of all datasets under the `dataset` field. See the [Catalog section](#Catalog) under *Further Metadata Field Guidance* for more details. "Common Core" Required Fields @@ -136,23 +136,23 @@ Additional details for each field are provided here broken down into sections fo Catalog Fields {#Catalog} ------------------------------- -{: .table .table-striped #schema} -**Field [#](#schema){: .permalink}** | **$schema** +{: .table .table-striped #conformsTo} +**Field [#](#conformsTo){: .permalink}** | **conformsTo** ----- | ----- **Cardinality** | (1,1) **Required** | Yes, always **Accepted Values** | String (URL) **Usage Notes** | This is used to identify the schema version using a URI. The URI for version 1.1 of the schema is `http://projectopendata.PLACEHOLDER.gov/v1.1/schema` -**Example** | `{"$schema": "http://projectopendata.PLACEHOLDER.gov/v1.1/schema"}` +**Example** | `{"conformsTo": "http://projectopendata.PLACEHOLDER.gov/v1.1/schema"}` -{: .table .table-striped #ref} -**Field [#](#ref){: .permalink}** | **$ref** +{: .table .table-striped #describedBy} +**Field [#](#describedBy){: .permalink}** | **describedBy** ----- | ----- **Cardinality** | (0,1) **Required** | No **Accepted Values** | String (URL) **Usage Notes** | This is used to specify a [JSON Schema](http://json-schema.org/) file that defines all fields. By default, it is recommended that the canonical JSON Schema file is referenced (http://projectopendata.PLACEHOLDER.gov/v1.1/schema/catalog.json) but if the schema had been extended, publishers may reference a file that defines those extensions. -**Example** | `{"$ref": "http://projectopendata.PLACEHOLDER.gov/v1.1/schema/catalog.json"}` +**Example** | `{"describedBy": "http://projectopendata.PLACEHOLDER.gov/v1.1/schema/catalog.json"}` {: .table .table-striped #dataset} **Field [#](#dataset){: .permalink}** | **dataset** From d806d3b40dacb99171f0841263ff530086d3c713 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Thu, 11 Sep 2014 11:28:40 -0400 Subject: [PATCH 034/129] updating example urls to cio.gov --- v1.1/schema.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index d1f2ec31..9b7f1b91 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -55,7 +55,7 @@ Links to downloadable examples of metadata files developed in this and other for Schema Version Declaration (Required) ----------------------------- -In order to distinguish the schema version being used publishers are required to specify the relevant URI using the `conformsTo` field at the beginning of their data.json file. Version 1.1 of the schema should be identified with the following URI: http://projectopendata.PLACEHOLDER.gov/v1.1/schema. Optionally, publishers may also use the `describedBy` field to reference the default [JSON Schema](http://json-schema.org/) file used to define the schema (http://projectopendata.PLACEHOLDER.gov/v1.1/schema/catalog.json) or they may refer to their own JSON Schema file where they have extended the schema. These fields are both part of a JSON object that also contains a listing of all datasets under the `dataset` field. See the [Catalog section](#Catalog) under *Further Metadata Field Guidance* for more details. +In order to distinguish the schema version being used publishers are required to specify the relevant URI using the `conformsTo` field at the beginning of their data.json file. Version 1.1 of the schema should be identified with the following URI: http://project-open-data.cio.gov/v1.1/schema. Optionally, publishers may also use the `describedBy` field to reference the default [JSON Schema](http://json-schema.org/) file used to define the schema (http://project-open-data.cio.gov/v1.1/schema/catalog.json) or they may refer to their own JSON Schema file where they have extended the schema. These fields are both part of a JSON object that also contains a listing of all datasets under the `dataset` field. See the [Catalog section](#Catalog) under *Further Metadata Field Guidance* for more details. "Common Core" Required Fields @@ -142,8 +142,8 @@ Catalog Fields {#Catalog} **Cardinality** | (1,1) **Required** | Yes, always **Accepted Values** | String (URL) -**Usage Notes** | This is used to identify the schema version using a URI. The URI for version 1.1 of the schema is `http://projectopendata.PLACEHOLDER.gov/v1.1/schema` -**Example** | `{"conformsTo": "http://projectopendata.PLACEHOLDER.gov/v1.1/schema"}` +**Usage Notes** | This is used to identify the schema version using a URI. The URI for version 1.1 of the schema is `http://project-open-data.cio.gov/v1.1/schema` +**Example** | `{"conformsTo": "http://project-open-data.cio.gov/v1.1/schema"}` {: .table .table-striped #describedBy} **Field [#](#describedBy){: .permalink}** | **describedBy** @@ -151,8 +151,8 @@ Catalog Fields {#Catalog} **Cardinality** | (0,1) **Required** | No **Accepted Values** | String (URL) -**Usage Notes** | This is used to specify a [JSON Schema](http://json-schema.org/) file that defines all fields. By default, it is recommended that the canonical JSON Schema file is referenced (http://projectopendata.PLACEHOLDER.gov/v1.1/schema/catalog.json) but if the schema had been extended, publishers may reference a file that defines those extensions. -**Example** | `{"describedBy": "http://projectopendata.PLACEHOLDER.gov/v1.1/schema/catalog.json"}` +**Usage Notes** | This is used to specify a [JSON Schema](http://json-schema.org/) file that defines all fields. By default, it is recommended that the canonical JSON Schema file is referenced (http://project-open-data.cio.gov/v1.1/schema/catalog.json) but if the schema had been extended, publishers may reference a file that defines those extensions. +**Example** | `{"describedBy": "http://project-open-data.cio.gov/v1.1/schema/catalog.json"}` {: .table .table-striped #dataset} **Field [#](#dataset){: .permalink}** | **dataset** From b7b9e2586bea7b3df90415a3f77b54b68f05b594 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Thu, 11 Sep 2014 12:21:38 -0400 Subject: [PATCH 035/129] first pass at changelog update for v1.1 --- metadata-changelog.md | 32 +++++++++++++++++++++++++++++--- 1 file changed, 29 insertions(+), 3 deletions(-) diff --git a/metadata-changelog.md b/metadata-changelog.md index eef541f5..e5bbab1d 100644 --- a/metadata-changelog.md +++ b/metadata-changelog.md @@ -5,12 +5,38 @@ title: Common Core Metadata Changelog permalink: /metadata-changelog/ filename: metadata-changelog.md --- -This page lists changes to the common core metadata schema by version. Latest changes at the top. Consult repository history for explanations. - -This document is currently a DRAFT. +This page lists changes to the common core metadata schema by version. Latest changes at the top. Consult [repository history](https://github.com/project-open-data/project-open-data.github.io/issues?q=is%3Aopen) for explanations. ## Changelog +### Version 1.1 FINAL - ??????? + +Updates to version 1.0 common core metadata: + +* Renames "accessLevelComment" field to "rights" to better alight with DCAT +* Renames "mbox" field to "hasEmail" and moves to within "contactPoint" to better align with vCard +* Aligns "accrualPeriodicity" field to ISO 8601 +* Aligns "contactPoint" field to vCard + +* Changes "accessURL" field to represent indirect access and to exist only within "distribution" +* Changes "format" field to a human readable description and to exist only within "distribution" +* Changes "distribution" field to become required-if-applicable and to always contain the "accessURL" or "downloadURL" fields +* Changes "primaryITInvestmentUII" to the correct capitalization +* Changes "publisher" field to allow for multiple levels of organizations + +* Removes "webService" field + +* Adds required "catalog" field to wrap the entire data.json file +* Adds "conformsTo" field, required at the catalog level and optional at the individual record level +* Adds optional "describedBy" field +* Adds optional "description" field for use within "distribution" +* Adds required-if-applicable "downloadURL" field +* Adds required "fn" field as part of "contactPoint" +* Adds optional "isPartOf" field +* Adds required-if-applicable "mediaType" field +* Adds optional "title" field for use within "distribution" + + ### Version 1.0 FINAL - 9/20/2013 Updates to original draft metadata: From cb3e09a85672a15a8e1d362e0f4ab69eb2477352 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Thu, 11 Sep 2014 12:22:30 -0400 Subject: [PATCH 036/129] trying to fix line breaks --- metadata-changelog.md | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) diff --git a/metadata-changelog.md b/metadata-changelog.md index e5bbab1d..6459f22a 100644 --- a/metadata-changelog.md +++ b/metadata-changelog.md @@ -13,28 +13,28 @@ This page lists changes to the common core metadata schema by version. Latest ch Updates to version 1.0 common core metadata: -* Renames "accessLevelComment" field to "rights" to better alight with DCAT -* Renames "mbox" field to "hasEmail" and moves to within "contactPoint" to better align with vCard -* Aligns "accrualPeriodicity" field to ISO 8601 -* Aligns "contactPoint" field to vCard +* Renames "accessLevelComment" field to "rights" to better alight with DCAT +* Renames "mbox" field to "hasEmail" and moves to within "contactPoint" to better align with vCard +* Aligns "accrualPeriodicity" field to ISO 8601 +* Aligns "contactPoint" field to vCard -* Changes "accessURL" field to represent indirect access and to exist only within "distribution" -* Changes "format" field to a human readable description and to exist only within "distribution" -* Changes "distribution" field to become required-if-applicable and to always contain the "accessURL" or "downloadURL" fields -* Changes "primaryITInvestmentUII" to the correct capitalization -* Changes "publisher" field to allow for multiple levels of organizations +* Changes "accessURL" field to represent indirect access and to exist only within "distribution" +* Changes "format" field to a human readable description and to exist only within "distribution" +* Changes "distribution" field to become required-if-applicable and to always contain the "accessURL" or "downloadURL" fields +* Changes "primaryITInvestmentUII" to the correct capitalization +* Changes "publisher" field to allow for multiple levels of organizations -* Removes "webService" field +* Removes "webService" field -* Adds required "catalog" field to wrap the entire data.json file -* Adds "conformsTo" field, required at the catalog level and optional at the individual record level -* Adds optional "describedBy" field -* Adds optional "description" field for use within "distribution" -* Adds required-if-applicable "downloadURL" field -* Adds required "fn" field as part of "contactPoint" -* Adds optional "isPartOf" field -* Adds required-if-applicable "mediaType" field -* Adds optional "title" field for use within "distribution" +* Adds required "catalog" field to wrap the entire data.json file +* Adds "conformsTo" field, required at the catalog level and optional at the individual record level +* Adds optional "describedBy" field +* Adds optional "description" field for use within "distribution" +* Adds required-if-applicable "downloadURL" field +* Adds required "fn" field as part of "contactPoint" +* Adds optional "isPartOf" field +* Adds required-if-applicable "mediaType" field +* Adds optional "title" field for use within "distribution" ### Version 1.0 FINAL - 9/20/2013 From be7513f3fc3fb77cf66d07c0c8f9696337aa369f Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Fri, 12 Sep 2014 16:42:52 -0400 Subject: [PATCH 037/129] adds conformsTo to schema dataset/distribution --- v1.1/schema.md | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/v1.1/schema.md b/v1.1/schema.md index 9b7f1b91..8d1e0207 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -194,6 +194,16 @@ Dataset Fields {#Dataset} **Usage Notes** | Represent each bureau responsible for the dataset according to the codes found in [OMB Circular A-11, Appendix C](http://www.whitehouse.gov/sites/default/files/omb/assets/a11_current_year/app_c.pdf). Start with the agency code, then a colon, then the bureau code. **Example** | The Office of the Solicitor (86) at the Department of the Interior (010) would be: `{"bureauCode":["010:86"]}`. If a second bureau was also responsible, the format like this: `{"bureauCode":["010:86","010:04"]}`. + +{: .table .table-striped #dataset-conformsTo} +**Field [#](#dataset-conformsTo){: .permalink}** | **conformsTo** +----- | ----- +**Cardinality** | (0,1) +**Required** | No +**Accepted Values** | String (URL) +**Usage Notes** | This is used to identify a standardized specification the dataset conforms to +**Example** | `{"conformsTo": "http://www.xbrl.org/Specification/XBRL-2.1/REC-2003-12-31/XBRL-2.1-REC-2003-12-31+corrected-errata-2013-02-20.html"}` + {: .table .table-striped #contactPoint} **Field [#](#contactPoint){: .permalink}** | **contactPoint** ----- | ----- @@ -298,6 +308,15 @@ Dataset Fields {#Dataset} **Usage Notes** | This should be the URL for an indirect means of accessing the data, such as API documentation, a 'wizard' or other graphical interface which is used to generate a download, feed, or a request form for the data. This should not be a **direct** download URL. It is usually assumed that accessURL is an HTML webpage. **Example** | `{"accessURL":"http://www.agency.gov/api/vegetables/"}` +{: .table .table-striped .child-field #distribution-conformsTo} +**Field [#](#distribution-conformsTo){: .permalink}** | **distribution → conformsTo** +----- | ----- +**Cardinality** | (0,1) +**Required** | No +**Accepted Values** | String (URL) +**Usage Notes** | This is used to identify a standardized specification the distribution conforms to +**Example** | `{"conformsTo": "http://www.xbrl.org/Specification/XBRL-2.1/REC-2003-12-31/XBRL-2.1-REC-2003-12-31+corrected-errata-2013-02-20.html"}` + {: .table .table-striped .child-field #distribution-downloadURL} **Field [#](#distribution-downloadURL){: .permalink}** | **distribution → downloadURL** ----- | ----- From 69453649abc101b5c50c0e9f196336b9c542754c Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Fri, 12 Sep 2014 17:11:53 -0400 Subject: [PATCH 038/129] adding describedBy and describedByType to schema --- v1.1/schema.md | 39 +++++++++++++++++++++++++++++---------- 1 file changed, 29 insertions(+), 10 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 8d1e0207..8d9c31c0 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -117,7 +117,7 @@ Agencies are encouraged to use the following expanded fields when appropriate. A Field | Label | Definition -------------- | -------------- | -------------- theme | Category | Main thematic category of the dataset. -dataDictionary | Data Dictionary | 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. +describedBy | Data Dictionary | 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. dataQuality | Data Quality | Whether the dataset meets the agency's Information Quality Guidelines (true/false). accrualPeriodicity | Frequency | Frequency with which dataset is published. landingPage | Homepage URL | Alternative landing page used to redirect user to a contextual, Agency-hosted "homepage" for the Dataset or API when selecting this resource from the Data.gov user interface. @@ -238,15 +238,6 @@ Dataset Fields {#Dataset} **Usage Notes** | This should be formatted per vCard specifications (see example below) and included with **fn** as part of a record's **contactPoint** (see above example). **Example** | `{"hasEmail": "mailto:jane.doe@agency.gov"}` -{: .table .table-striped #dataDictionary} -**Field [#](#dataDictionary){: .permalink}** | **dataDictionary** ------ | ----- -**Cardinality** | (0,1) -**Required** | No (Documentation that is not specifically a data dictionary belongs in "references") -**Accepted Values** | String (URL) -**Usage Notes** | - -**Example** | `{"dataDictionary":"http://www.agency.gov/vegetables/dictionary.html"}` - {: .table .table-striped #dataQuality} **Field [#](#dataQuality){: .permalink}** | **dataQuality** ----- | ----- @@ -256,6 +247,16 @@ Dataset Fields {#Dataset} **Usage Notes** | Indicates whether a dataset conforms to the agency's information quality guidelines. **Example** | `{"dataQuality":true}` +{: .table .table-striped #dataset-describedBy} +**Field [#](#dataset-describedBy){: .permalink}** | **describedBy** +----- | ----- +**Cardinality** | (0,1) +**Required** | No +**Accepted Values** | String (URL) +**Usage Notes** | This is used to specify a data dictionary or schema that defines fields or column headings in the dataset. If this is a machine readable file, it's recommended to be specified with [describedBy](#distribution-describedBy) at the distribution level along with the associated `describedByType`. At the dataset level it's assumed to be a human readable HTML webpage. Documentation that is not specifically a data dictionary belongs in "references" +**Example** | `{"describedBy": "http://release.niem.gov/niem/domains/jxdm/4.1/jxdm.xsd"}` + + {: .table .table-striped #description} **Field [#](#description){: .permalink}** | **description** ----- | ----- @@ -326,6 +327,24 @@ Dataset Fields {#Dataset} **Usage Notes** | This must be the **direct** download URL. Other means of accessing the dataset should be expressed using **accessURL**. This should always be accompanied by **mediaType**. **Example** | `{"downloadURL":"http://www.agency.gov/vegetables/listofvegetables.csv"}` +{: .table .table-striped .child-field #distribution-describedBy} +**Field [#](#distribution-describedBy){: .permalink}** | **distribution → describedBy** +----- | ----- +**Cardinality** | (0,1) +**Required** | No +**Accepted Values** | String (URL) +**Usage Notes** | This is used to specify a data dictionary or schema that defines fields or column headings in the distribution. If this is a machine readable file the media type should be specified with `describedByType` - otherwise it's assumed to be a human readable HTML webpage. +**Example** | `{"describedBy": "http://www.agency.gov/vegetables/schema.json"}` + +{: .table .table-striped .child-field #distribution-describedByType} +**Field [#](#distribution-describedByType){: .permalink}** | **distribution → describedByType** +----- | ----- +**Cardinality** | (0,1) +**Required** | No +**Accepted Values** | String (URL) +**Usage Notes** | This is used to identify the [media type](http://en.wikipedia.org/wiki/Internet_media_type) (MIME type) of the URL used for the distribution's `describedBy` field. This is especially important if `describedBy` is a machine readable file. +**Example** | `{"describedByType": "application/schema+json"}` + {: .table .table-striped .child-field #distribution-description} **Field [#](#distribution-description){: .permalink}** | **distribution → description** ----- | ----- From a7b011bda2ce85d2d1da0b211d8ce2ce5462c3a0 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Fri, 12 Sep 2014 17:16:50 -0400 Subject: [PATCH 039/129] Updating conformsTo details --- v1.1/schema.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 8d9c31c0..30e6ecdf 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -141,7 +141,7 @@ Catalog Fields {#Catalog} ----- | ----- **Cardinality** | (1,1) **Required** | Yes, always -**Accepted Values** | String (URL) +**Accepted Values** | String (URI) **Usage Notes** | This is used to identify the schema version using a URI. The URI for version 1.1 of the schema is `http://project-open-data.cio.gov/v1.1/schema` **Example** | `{"conformsTo": "http://project-open-data.cio.gov/v1.1/schema"}` @@ -200,8 +200,8 @@ Dataset Fields {#Dataset} ----- | ----- **Cardinality** | (0,1) **Required** | No -**Accepted Values** | String (URL) -**Usage Notes** | This is used to identify a standardized specification the dataset conforms to +**Accepted Values** | String (URI) +**Usage Notes** | This is used to identify a standardized specification the dataset conforms to. If this is a technical specification associated with a particular serialization of a distribution, this should be specified with [conformsTo](#distribution-conformsTo) at the distribution level. **Example** | `{"conformsTo": "http://www.xbrl.org/Specification/XBRL-2.1/REC-2003-12-31/XBRL-2.1-REC-2003-12-31+corrected-errata-2013-02-20.html"}` {: .table .table-striped #contactPoint} @@ -314,9 +314,9 @@ Dataset Fields {#Dataset} ----- | ----- **Cardinality** | (0,1) **Required** | No -**Accepted Values** | String (URL) +**Accepted Values** | String (URI) **Usage Notes** | This is used to identify a standardized specification the distribution conforms to -**Example** | `{"conformsTo": "http://www.xbrl.org/Specification/XBRL-2.1/REC-2003-12-31/XBRL-2.1-REC-2003-12-31+corrected-errata-2013-02-20.html"}` +**Example** | `{"conformsTo": "http://www.agency.gov/vegetables-data-standard/"}` {: .table .table-striped .child-field #distribution-downloadURL} **Field [#](#distribution-downloadURL){: .permalink}** | **distribution → downloadURL** From 82097f60379e7819219b7506c56bff3df099bfbe Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Fri, 12 Sep 2014 17:37:59 -0400 Subject: [PATCH 040/129] updates to describedBy to schema dataset also adds describedByType to dataset level --- v1.1/schema.md | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 30e6ecdf..4234da24 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -253,9 +253,17 @@ Dataset Fields {#Dataset} **Cardinality** | (0,1) **Required** | No **Accepted Values** | String (URL) -**Usage Notes** | This is used to specify a data dictionary or schema that defines fields or column headings in the dataset. If this is a machine readable file, it's recommended to be specified with [describedBy](#distribution-describedBy) at the distribution level along with the associated `describedByType`. At the dataset level it's assumed to be a human readable HTML webpage. Documentation that is not specifically a data dictionary belongs in "references" -**Example** | `{"describedBy": "http://release.niem.gov/niem/domains/jxdm/4.1/jxdm.xsd"}` +**Usage Notes** | This is used to specify a data dictionary or schema that defines fields or column headings in the dataset. If this is a machine readable file, it's recommended to be specified with [describedBy](#distribution-describedBy) at the distribution level along with the associated `describedByType`. At the dataset level it's assumed to be a human readable HTML webpage or PDF document. Documentation that is not specifically a data dictionary belongs in "references" +**Example** | `{"describedBy": "http://www.agency.gov/vegetables/definitions.pdf"}` +{: .table .table-striped .child-field #distribution-describedByType} +**Field [#](#distribution-describedByType){: .permalink}** | **distribution → describedByType** +----- | ----- +**Cardinality** | (0,1) +**Required** | No +**Accepted Values** | String (URL) +**Usage Notes** | This is used to identify the [media type](http://en.wikipedia.org/wiki/Internet_media_type) (MIME type) of the URL used for the dataset's `describedBy` field. This should be specified if `describedBy` is not an HTML webpage. +**Example** | `{"describedByType": "application/pdf"}` {: .table .table-striped #description} **Field [#](#description){: .permalink}** | **description** From 14ae7c53eb14dd295a3c8497c772eb2be73d1a55 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Fri, 12 Sep 2014 17:39:44 -0400 Subject: [PATCH 041/129] Updating conformsTo details --- v1.1/schema.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 4234da24..f6ecbffb 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -201,7 +201,7 @@ Dataset Fields {#Dataset} **Cardinality** | (0,1) **Required** | No **Accepted Values** | String (URI) -**Usage Notes** | This is used to identify a standardized specification the dataset conforms to. If this is a technical specification associated with a particular serialization of a distribution, this should be specified with [conformsTo](#distribution-conformsTo) at the distribution level. +**Usage Notes** | This is used to identify a standardized specification the dataset conforms to. If this is a technical specification associated with a particular serialization of a distribution, this should be specified with [conformsTo](#distribution-conformsTo) at the distribution level. It's recommended that this be a URI that serves as a unique identifier for the standard. The URI may or may not also be a URL that provides documentation of the specification. **Example** | `{"conformsTo": "http://www.xbrl.org/Specification/XBRL-2.1/REC-2003-12-31/XBRL-2.1-REC-2003-12-31+corrected-errata-2013-02-20.html"}` {: .table .table-striped #contactPoint} @@ -323,7 +323,7 @@ Dataset Fields {#Dataset} **Cardinality** | (0,1) **Required** | No **Accepted Values** | String (URI) -**Usage Notes** | This is used to identify a standardized specification the distribution conforms to +**Usage Notes** | This is used to identify a standardized specification the distribution conforms to. It's recommended that this be a URI that serves as a unique identifier for the standard. The URI may or may not also be a URL that provides documentation of the specification. **Example** | `{"conformsTo": "http://www.agency.gov/vegetables-data-standard/"}` {: .table .table-striped .child-field #distribution-downloadURL} From ef2c178f6fe0ccb11eb4534820dd57f228b8ef48 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Fri, 12 Sep 2014 17:43:30 -0400 Subject: [PATCH 042/129] distribution titles and descriptions are optional --- v1.1/schema.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index f6ecbffb..c2709f13 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -357,7 +357,7 @@ Dataset Fields {#Dataset} **Field [#](#distribution-description){: .permalink}** | **distribution → description** ----- | ----- **Cardinality** | (0,1) -**Required** | Yes, always +**Required** | No **Accepted Values** | String **Usage Notes** | This should be a human-readable description of the distribution. **Example** | `{"description":"Vegetable data as a zipped CSV file with attached data dictionary"}` @@ -384,7 +384,7 @@ Dataset Fields {#Dataset} **Field [#](#distribution-title){: .permalink}** | **distribution → title** ----- | ----- **Cardinality** | (0,1) -**Required** | Yes, always +**Required** | No **Accepted Values** | String **Usage Notes** | This should be a useful title for the distribution. Acronyms should be avoided. **Example** | `{"title":"Spreadsheet"}` From 412a73811be692317a582bf13fe348775c369315 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Fri, 12 Sep 2014 17:48:14 -0400 Subject: [PATCH 043/129] add additional fields to distribution example --- v1.1/schema.md | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index c2709f13..8af55732 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -280,7 +280,7 @@ Dataset Fields {#Dataset} **Cardinality** | (0,n) **Required** | Yes, if the dataset has an **accessURL** or **downloadURL**. **Accepted Values** | Array of Objects -**Usage Notes** | This is a container for one or multiple `distribution` objects which group together the fields: **accessURL**, **downloadURL**, **description**, **format**, **mediaType**, and **title**. +**Usage Notes** | This is a container for one or multiple `distribution` objects which group together the fields: **accessURL**, **conformsTo**, **downloadURL**, **describedBy**, **describedByType**, **description**, **format**, **mediaType**, and **title**. **Example** | See below ~~~ @@ -291,6 +291,16 @@ Dataset Fields {#Dataset} "format": "CSV", "mediaType": "text/csv", "title": "vegetables.csv" + }, + { + "conformsTo": "http://www.agency.gov/vegetables-data-standard/", + "describedBy": "http://www.agency.gov/vegetables/schema.xsd", + "describedByType": "text/xml", + "description": "Vegetable data as an XML file", + "downloadURL": "http://www.agency.gov/vegetables/listofvegetables.xml", + "format": "XML", + "mediaType": "text/xml", + "title": "vegetables.xml" }, { "description": "Vegetable data as a zipped CSV file with attached data dictionary", From a87c2cf0ea981e25d459e568de9bc2360dc51a15 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Fri, 12 Sep 2014 17:51:37 -0400 Subject: [PATCH 044/129] update distribution example so titles match URL --- v1.1/schema.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 8af55732..c8b86c5e 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -290,7 +290,7 @@ Dataset Fields {#Dataset} "downloadURL": "http://www.agency.gov/vegetables/listofvegetables.csv", "format": "CSV", "mediaType": "text/csv", - "title": "vegetables.csv" + "title": "listofvegetables.csv" }, { "conformsTo": "http://www.agency.gov/vegetables-data-standard/", @@ -300,7 +300,7 @@ Dataset Fields {#Dataset} "downloadURL": "http://www.agency.gov/vegetables/listofvegetables.xml", "format": "XML", "mediaType": "text/xml", - "title": "vegetables.xml" + "title": "listofvegetables.xml" }, { "description": "Vegetable data as a zipped CSV file with attached data dictionary", From 39c942fbf8e4a51c0bb4f45081adaf23444286e4 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Fri, 12 Sep 2014 17:53:17 -0400 Subject: [PATCH 045/129] typo on isPartOf --- v1.1/schema.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index c8b86c5e..da293386 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -415,7 +415,7 @@ Dataset Fields {#Dataset} **Cardinality** | (0,1) **Required** | No **Accepted Values** | String -**Usage Notes** | This field allows the grouping of multiple datasets into a "collection". This field should be employed by the individual datasets that together make up a collection. The value for this field should the the `identifier` of the parent dataset. +**Usage Notes** | This field allows the grouping of multiple datasets into a "collection". This field should be employed by the individual datasets that together make up a collection. The value for this field should match the `identifier` of the parent dataset. **Example** | `{"isPartOf":"1344"}` {: .table .table-striped #issued} From a2626739889a6718b9ad8e908b86237e74e9308a Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Fri, 12 Sep 2014 18:03:35 -0400 Subject: [PATCH 046/129] Updating guidance for date fields in schema The change on `modified` was also brought up with #323 --- v1.1/schema.md | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index da293386..c3eba00d 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -469,10 +469,8 @@ Dataset Fields {#Dataset} **Cardinality** | (1,1) **Required** | Yes, always **Accepted Values** | ISO 8601 Date -**Usage Notes** | Dates should be [ISO 8601](http://en.wikipedia.org/wiki/ISO_8601) of least resolution. In other words, as much of YYYY-MM-DDThh:mm:ss.sTZD as is relevant to this dataset. If this file is brand-new, enter the **issued** date here as well. - -If there is a need to reflect that the dataset is continually updated, ISO 8601 formatting can account for this by [giving the duration](http://en.wikipedia.org/wiki/ISO_8601#Durations). For instance, `P1D` for daily, `P2W` for every two weeks, and `PT5M` for every five minutes. -**Example** | `{"modified":"2012-01-15"}` or `{"modified":"P1D"}` +**Usage Notes** | Dates should be [ISO 8601](http://en.wikipedia.org/wiki/ISO_8601) of highest resolution. In other words, as much of YYYY-MM-DDThh:mm:ss.sTZD as is relevant to this dataset. If this file is brand-new, enter the **issued** date here as well. If there is a need to reflect that the dataset is continually updated, ISO 8601 formatting can account for this [with repeating intervals](http://en.wikipedia.org/wiki/ISO_8601#Time_intervals). For instance, `R/P1D` for daily, `R/P2W` for every two weeks, and `R/PT5M` for every five minutes. ++**Example** | `{"modified":"2012-01-15"}` or `{"modified":"R/P1D"} {: .table .table-striped #primaryITInvestmentUII} **Field [#](#primaryITInvestmentUII){: .permalink}** | **primaryITInvestmentUII** @@ -545,7 +543,8 @@ If there is a need to reflect that the dataset is continually updated, ISO 8601 **Cardinality** | (0,1) **Required** | Yes, if applicable **Accepted Values** | ISO 8601 Date -**Usage Notes** | This field should contain an interval of time defined by start and end dates. Dates should be formatted as pairs of {start datetime/end datetime} in the [ISO 8601](http://en.wikipedia.org/wiki/ISO_8601) format. ISO 8601 specifies that datetimes can be formatted in a number of ways, including a simple four-digit year (eg. 2013) to a much more specific YYYY-MM-DDTHH:MM:SSZ, where the T specifies a seperator between the date and time and time is expressed in 24 hour notation in the UTC (Zulu) time zone. (e.g., 2011-02-14T12:00:00Z/2013-07-04T19:34:00Z). Use a solidus ("/") to separate start and end times. +**Usage Notes** | This field should contain an interval of time defined by start and end dates. Dates should be formatted as pairs of {start datetime/end datetime} in the [ISO 8601](http://en.wikipedia.org/wiki/ISO_8601) format. ISO 8601 specifies that datetimes can be formatted in a number of ways, including a simple four-digit year (eg. 2013) to a much more specific YYYY-MM-DDTHH:MM:SSZ, where the T specifies a seperator between the date and time and time is expressed in 24 hour notation in the UTC (Zulu) time zone. (e.g., 2011-02-14T12:00:00Z/2013-07-04T19:34:00Z). Use a solidus ("/") to separate start and end times. If there is a need to reflect that the dataset is continually updated, ISO 8601 formatting can account for this [with repeating intervals](http://en.wikipedia.org/wiki/ISO_8601#Time_intervals). For instance, updated monthly starting in January 2010 and continuing through the present would be represented as: `R/2010-01/P1M`. Updated every 5 minutes beginning on February 15, 2010 would be represented as: `R/2010-02-15/PT5M`. +**Example** | `{"temporal":"2000-01-15T00:45:00Z/2010-01-15T00:06:00Z"}` or `{"temporal":"R/2000-01-15T00:45:00Z/P1W"}` {: .table .table-striped #title} **Field [#](#title){: .permalink}** | **title** @@ -556,11 +555,6 @@ If there is a need to reflect that the dataset is continually updated, ISO 8601 **Usage Notes** | Acronyms should be avoided. **Example** | `{"title":"Types of Vegetables"}` -If there is a need to reflect that the dataset is continually updated, ISO 8601 formatting can account for this [with repeating intervals](http://en.wikipedia.org/wiki/ISO_8601#Time_intervals). For instance, updated monthly starting in January 2010 and continuing through the present would be represented as: `R/2010-01/P1M`. - -Updated every 5 minutes beginning on February 15, 2010 would be represented as: `R/2010-02-15/PT5M`. -**Example** | `{"temporal":"2000-01-15T00:45:00Z/2010-01-15T00:06:00Z"}` or `{"temporal":"R/2000-01-15T00:45:00Z/P1W"}` - {: .table .table-striped #theme} **Field [#](#theme){: .permalink}** | **theme** ----- | ----- From 21684dcd8c3a4b3fab017fd56a97892ebc840720 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Fri, 12 Sep 2014 18:24:14 -0400 Subject: [PATCH 047/129] Update to summary table for distribution fields --- v1.1/schema.md | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index c3eba00d..5a496d1d 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -98,12 +98,15 @@ Within a record, **distribution** is used to aggregate the metadata specific to {: .table .table-striped} Field | Label | Definition -------------- | -------------- | -------------- -accessURL | Access URL | URL providing indirect access to a dataset, for example via API or a graphical interface. -downloadURL | Download URL | URL providing direct access to a downloadable file of a dataset. -description | Description | Human-readable description of the distribution. -format | Format | A human-readable description of the file format of a distribution. -mediaType | MIME Type | The machine-readable file format ([IANA MIME Type](http://en.wikipedia.org/wiki/Internet_media_type)) of a distribution. -title | Title | Human-readable name of the distribution. +accessURL | Access URL | URL providing indirect access to a dataset, for example via API or a graphical interface +conformsTo | Data Standard | URI used to identify a standardized specification the distribution conforms to +describedBy | Data Dictionary | URL to the data dictionary for the distribution found at the `downloadURL`. Note that documentation other than a data dictionary can be referenced using Related Documents as shown in the expanded fields. +describedByType | Data Dictionary Type | The machine-readable file format ([IANA Media Type](http://www.iana.org/assignments/media-types) or [MIME Type](http://en.wikipedia.org/wiki/Internet_media_type)) of the distribution's `describedBy` URL +description | Description | Human-readable description of the distribution. +downloadURL | Download URL | URL providing direct access to a downloadable file of a dataset +format | Format | A human-readable description of the file format of a distribution. +mediaType | Media Type | The machine-readable file format ([IANA Media Type](http://www.iana.org/assignments/media-types) or [MIME Type](http://en.wikipedia.org/wiki/Internet_media_type)) of the distribution's `downloadURL`. +title | Title | Human-readable name of the distribution. Beyond Common Core -- Extending the Schema ------------------------------------------ From 2053e87a8a350b98219613985adf3272d0a71209 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Fri, 12 Sep 2014 18:48:27 -0400 Subject: [PATCH 048/129] Updates description of schema Expanded Fields --- v1.1/schema.md | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 5a496d1d..28f7b529 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -117,20 +117,21 @@ Expanded Fields Agencies are encouraged to use the following expanded fields when appropriate. Agencies may freely augment these fields with their own. {: .table .table-striped} -Field | Label | Definition --------------- | -------------- | -------------- -theme | Category | Main thematic category of the dataset. -describedBy | Data Dictionary | 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. -dataQuality | Data Quality | Whether the dataset meets the agency's Information Quality Guidelines (true/false). -accrualPeriodicity | Frequency | Frequency with which dataset is published. -landingPage | Homepage URL | Alternative landing page used to redirect user to a contextual, Agency-hosted "homepage" for the Dataset or API when selecting this resource from the Data.gov user interface. -isPartOf | isPartOf | The collection of which the dataset is a subset. -language | Language | The language of the dataset. -primaryITInvestmentUII | primary IT Investment UII | For linking a dataset with an IT Unique Investment Identifier (UII) -references | Related Documents | Related documents such as technical information about a dataset, developer documentation, etc. -issued | Release Date | Date of formal issuance. -systemOfRecords | System of Records | If the systems is designated as a system of records under the Privacy Act of 1974, provide the URL to the System of Records Notice related to this dataset. - +Field | Label | Definition +-------------- | -------------- | -------------- +accrualPeriodicity | Frequency | Frequency with which dataset is published. +conformsTo | Data Standard | URI used to identify a standardized specification the dataset conforms to +describedBy | Data Dictionary | URL to the data dictionary for the dataset. Note that documentation other than a data dictionary can be referenced using Related Documents (`references`). +describedByType | Data Dictionary Type | The machine-readable file format ([IANA Media Type](http://www.iana.org/assignments/media-types) or [MIME Type](http://en.wikipedia.org/wiki/Internet_media_type)) of the dataset's Data Dictionary (`describedBy`) +dataQuality | Data Quality | Whether the dataset meets the agency's Information Quality Guidelines (true/false). +isPartOf | Collection | The collection of which the dataset is a subset. +issued | Release Date | Date of formal issuance. +language | Language | The language of the dataset. +landingPage | Homepage URL | Alternative landing page used to redirect user to a contextual, Agency-hosted "homepage" for the Dataset or API when selecting this resource from the Data.gov user interface. +primaryITInvestmentUII | Primary IT Investment UII | For linking a dataset with an IT Unique Investment Identifier (UII) +references | Related Documents | Related documents such as technical information about a dataset, developer documentation, etc. +systemOfRecords | System of Records | If the systems is designated as a system of records under the Privacy Act of 1974, provide the URL to the System of Records Notice related to this dataset. +theme | Category | Main thematic category of the dataset. Further Metadata Field Guidance ------------------------------- From b257d1c488ec8c1e9f866d3213dc3330b2ce16a7 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Fri, 12 Sep 2014 18:52:57 -0400 Subject: [PATCH 049/129] Updates to Required-if-Applicable Fields summary --- v1.1/schema.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 28f7b529..2158fa18 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -78,7 +78,7 @@ accessLevel | Public Access Level | The degree to which this dataset **coul "Common Core" Required-if-Applicable Fields ------------------------------------------- -The following fields must be used to describe each dataset if they are applicable. U.S. Federal agencies must fill out BureauCode and ProgramCode. +The following fields must be used to describe each dataset if they are applicable. U.S. Federal agencies must fill out bureauCode and programCode. {: .table .table-striped} Field | Label | Definition @@ -86,7 +86,7 @@ Field | Label | Definition bureauCode | Bureau Code | Federal agencies, combined agency and bureau code from [OMB Circular A-11, Appendix C](http://www.whitehouse.gov/sites/default/files/omb/assets/a11_current_year/app_c.pdf) in the format of `015:11`. programCode | Program Code | Federal agencies, list the primary program related to this data asset, from the [Federal Program Inventory](http://goals.performance.gov/sites/default/files/images/FederalProgramInventory_FY13_MachineReadable_091613.xls). Use the format of `015:001` distribution | Distribution | Represents a specific available form of a dataset in the form of download or access URLs, along with metadata specific to that form. -license | License | The license with which the dataset or API is published. See [Open Licenses](/open-licenses/) for more information. +license | License | The license or non-license (i.e. Public Domain) status with which the dataset or API has been published. See [Open Licenses](/open-licenses/) for more information. rights | Rights | This may include information regarding access or restrictions based on privacy, security, or other policies. This should also serve as an explanation for the selected “accessLevel” including instructions for how to access a restricted file, if applicable, or explanation for why a “non-public” or “restricted public” data asset is not “public,” if applicable. Text, 255 characters. spatial | Spatial | The range of spatial applicability of a dataset. Could include a spatial region like a bounding box or a named place. temporal | Temporal | The range of temporal applicability of a dataset (i.e., a start and end date of applicability for the data). From 483f6f5547d46693e947c32a245ee7b97025b34d Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Fri, 12 Sep 2014 19:16:01 -0400 Subject: [PATCH 050/129] Denoting which fields are specific to Federal Gov --- v1.1/schema.md | 59 ++++++++++++++++++++++++++++++-------------------- 1 file changed, 35 insertions(+), 24 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 2158fa18..8156ea15 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -81,15 +81,15 @@ accessLevel | Public Access Level | The degree to which this dataset **coul The following fields must be used to describe each dataset if they are applicable. U.S. Federal agencies must fill out bureauCode and programCode. {: .table .table-striped} -Field | Label | Definition --------------- | -------------- | -------------- -bureauCode | Bureau Code | Federal agencies, combined agency and bureau code from [OMB Circular A-11, Appendix C](http://www.whitehouse.gov/sites/default/files/omb/assets/a11_current_year/app_c.pdf) in the format of `015:11`. -programCode | Program Code | Federal agencies, list the primary program related to this data asset, from the [Federal Program Inventory](http://goals.performance.gov/sites/default/files/images/FederalProgramInventory_FY13_MachineReadable_091613.xls). Use the format of `015:001` -distribution | Distribution | Represents a specific available form of a dataset in the form of download or access URLs, along with metadata specific to that form. -license | License | The license or non-license (i.e. Public Domain) status with which the dataset or API has been published. See [Open Licenses](/open-licenses/) for more information. -rights | Rights | This may include information regarding access or restrictions based on privacy, security, or other policies. This should also serve as an explanation for the selected “accessLevel” including instructions for how to access a restricted file, if applicable, or explanation for why a “non-public” or “restricted public” data asset is not “public,” if applicable. Text, 255 characters. -spatial | Spatial | The range of spatial applicability of a dataset. Could include a spatial region like a bounding box or a named place. -temporal | Temporal | The range of temporal applicability of a dataset (i.e., a start and end date of applicability for the data). +Field | Label | Definition +-------------- | -------------- | -------------- +bureauCode[USG](#USG-note) | Bureau Code | Federal agencies, combined agency and bureau code from [OMB Circular A-11, Appendix C](http://www.whitehouse.gov/sites/default/files/omb/assets/a11_current_year/app_c.pdf) in the format of `015:11`. +programCode[USG](#USG-note) | Program Code | Federal agencies, list the primary program related to this data asset, from the [Federal Program Inventory](http://goals.performance.gov/sites/default/files/images/FederalProgramInventory_FY13_MachineReadable_091613.xls). Use the format of `015:001` +distribution | Distribution | Represents a specific available form of a dataset in the form of download or access URLs, along with metadata specific to that form. +license | License | The license or non-license (i.e. Public Domain) status with which the dataset or API has been published. See [Open Licenses](/open-licenses/) for more information. +rights | Rights | This may include information regarding access or restrictions based on privacy, security, or other policies. This should also serve as an explanation for the selected “accessLevel” including instructions for how to access a restricted file, if applicable, or explanation for why a “non-public” or “restricted public” data asset is not “public,” if applicable. Text, 255 characters. +spatial | Spatial | The range of spatial applicability of a dataset. Could include a spatial region like a bounding box or a named place. +temporal | Temporal | The range of temporal applicability of a dataset (i.e., a start and end date of applicability for the data). "Common Core" Distribution Fields ------------------------------------------- @@ -117,21 +117,21 @@ Expanded Fields Agencies are encouraged to use the following expanded fields when appropriate. Agencies may freely augment these fields with their own. {: .table .table-striped} -Field | Label | Definition --------------- | -------------- | -------------- -accrualPeriodicity | Frequency | Frequency with which dataset is published. -conformsTo | Data Standard | URI used to identify a standardized specification the dataset conforms to -describedBy | Data Dictionary | URL to the data dictionary for the dataset. Note that documentation other than a data dictionary can be referenced using Related Documents (`references`). -describedByType | Data Dictionary Type | The machine-readable file format ([IANA Media Type](http://www.iana.org/assignments/media-types) or [MIME Type](http://en.wikipedia.org/wiki/Internet_media_type)) of the dataset's Data Dictionary (`describedBy`) -dataQuality | Data Quality | Whether the dataset meets the agency's Information Quality Guidelines (true/false). -isPartOf | Collection | The collection of which the dataset is a subset. -issued | Release Date | Date of formal issuance. -language | Language | The language of the dataset. -landingPage | Homepage URL | Alternative landing page used to redirect user to a contextual, Agency-hosted "homepage" for the Dataset or API when selecting this resource from the Data.gov user interface. -primaryITInvestmentUII | Primary IT Investment UII | For linking a dataset with an IT Unique Investment Identifier (UII) -references | Related Documents | Related documents such as technical information about a dataset, developer documentation, etc. -systemOfRecords | System of Records | If the systems is designated as a system of records under the Privacy Act of 1974, provide the URL to the System of Records Notice related to this dataset. -theme | Category | Main thematic category of the dataset. +Field | Label | Definition +-------------- | -------------- | -------------- +accrualPeriodicity | Frequency | Frequency with which dataset is published. +conformsTo | Data Standard | URI used to identify a standardized specification the dataset conforms to +describedBy | Data Dictionary | URL to the data dictionary for the dataset. Note that documentation other than a data dictionary can be referenced using Related Documents (`references`). +describedByType | Data Dictionary Type | The machine-readable file format ([IANA Media Type](http://www.iana.org/assignments/media-types) or [MIME Type](http://en.wikipedia.org/wiki/Internet_media_type)) of the dataset's Data Dictionary (`describedBy`) +dataQuality[USG](#USG-note) | Data Quality | Whether the dataset meets the agency's Information Quality Guidelines (true/false). +isPartOf | Collection | The collection of which the dataset is a subset. +issued | Release Date | Date of formal issuance. +language | Language | The language of the dataset. +landingPage | Homepage URL | Alternative landing page used to redirect user to a contextual, Agency-hosted "homepage" for the Dataset or API when selecting this resource from the Data.gov user interface. +primaryITInvestmentUII[USG](#USG-note) | Primary IT Investment UII | For linking a dataset with an IT Unique Investment Identifier (UII) +references | Related Documents | Related documents such as technical information about a dataset, developer documentation, etc. +systemOfRecords[USG](#USG-note) | System of Records | If the systems is designated as a system of records under the Privacy Act of 1974, provide the URL to the System of Records Notice related to this dataset. +theme | Category | Main thematic category of the dataset. Further Metadata Field Guidance ------------------------------- @@ -578,6 +578,17 @@ Dataset Fields {#Dataset} **Example** | `{"title":"Types of Vegetables"}` + +Federal Government Fields {#USG-note} +---------------------- +USG — Fields specific to the U.S. Federal Government have been denoted with the USG superscript. +The Project Open Data schema has been developed as part of a U.S Federal Government open data policy. However, every attempt +has been made to align the schema with existing international standards and to provide opportunities for re-use and interoperability +with state and local government as well as non-profits, academic institutions, and businesses. There are however some fields +that have been introduced specifically for use by the U.S. Federal Government and have special meaning in that context. These fields +are: **bureauCode**, **programCode**, **dataQuality**, **primaryITInvestmentUII**, and **systemOfRecords**. Non-federal data +publishers are encouraged to make use of this schema, but these fields should not be seen as required and may not be relevant for those entities. + Rationale for Metadata Nomenclature ---------------------- We sought to be platform-independent and to align as much as possible with existing open standards. From aa77be2d13b2254414fd3ccec6014300984d1534 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Fri, 12 Sep 2014 19:24:34 -0400 Subject: [PATCH 051/129] Typo on schema for dataset describedByType --- v1.1/schema.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 2158fa18..6b664162 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -260,8 +260,8 @@ Dataset Fields {#Dataset} **Usage Notes** | This is used to specify a data dictionary or schema that defines fields or column headings in the dataset. If this is a machine readable file, it's recommended to be specified with [describedBy](#distribution-describedBy) at the distribution level along with the associated `describedByType`. At the dataset level it's assumed to be a human readable HTML webpage or PDF document. Documentation that is not specifically a data dictionary belongs in "references" **Example** | `{"describedBy": "http://www.agency.gov/vegetables/definitions.pdf"}` -{: .table .table-striped .child-field #distribution-describedByType} -**Field [#](#distribution-describedByType){: .permalink}** | **distribution → describedByType** +{: .table .table-striped #dataset-describedByType} +**Field [#](#dataset-describedByType){: .permalink}** | **describedByType** ----- | ----- **Cardinality** | (0,1) **Required** | No From 9848958936e09da93a5bbea2fe3dcbf98526d5a6 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Fri, 12 Sep 2014 19:27:30 -0400 Subject: [PATCH 052/129] title was included twice in schema --- v1.1/schema.md | 9 --------- 1 file changed, 9 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 6b664162..7b073a6a 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -550,15 +550,6 @@ Dataset Fields {#Dataset} **Usage Notes** | This field should contain an interval of time defined by start and end dates. Dates should be formatted as pairs of {start datetime/end datetime} in the [ISO 8601](http://en.wikipedia.org/wiki/ISO_8601) format. ISO 8601 specifies that datetimes can be formatted in a number of ways, including a simple four-digit year (eg. 2013) to a much more specific YYYY-MM-DDTHH:MM:SSZ, where the T specifies a seperator between the date and time and time is expressed in 24 hour notation in the UTC (Zulu) time zone. (e.g., 2011-02-14T12:00:00Z/2013-07-04T19:34:00Z). Use a solidus ("/") to separate start and end times. If there is a need to reflect that the dataset is continually updated, ISO 8601 formatting can account for this [with repeating intervals](http://en.wikipedia.org/wiki/ISO_8601#Time_intervals). For instance, updated monthly starting in January 2010 and continuing through the present would be represented as: `R/2010-01/P1M`. Updated every 5 minutes beginning on February 15, 2010 would be represented as: `R/2010-02-15/PT5M`. **Example** | `{"temporal":"2000-01-15T00:45:00Z/2010-01-15T00:06:00Z"}` or `{"temporal":"R/2000-01-15T00:45:00Z/P1W"}` -{: .table .table-striped #title} -**Field [#](#title){: .permalink}** | **title** ------ | ----- -**Cardinality** | (1,1) -**Required** | Yes, always -**Accepted Values** | String -**Usage Notes** | Acronyms should be avoided. -**Example** | `{"title":"Types of Vegetables"}` - {: .table .table-striped #theme} **Field [#](#theme){: .permalink}** | **theme** ----- | ----- From 7157e81377333eb81b1590b90224c6cb106dce06 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Sun, 14 Sep 2014 15:57:52 -0400 Subject: [PATCH 053/129] 4 small updates to /schema text 3x needed edits: * new version number * removing reference to endpoint field * update bottom line reference to accessLevelComment to rights * removing reference to 'new' --- v1.1/schema.md | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 7b073a6a..938af45d 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -14,7 +14,7 @@ This is not the official version of the common core metadata schema. This is an This section contains guidance to support the use of the common core metadata to list agency datasets and application programming interfaces (APIs) as hosted at agency.gov/data. -Updates to the metadata schema can be found in the [changelog](/metadata-changelog). Current metadata version: 1.0 FINAL as of 9/20/13. +Updates to the metadata schema can be found in the [changelog](/metadata-changelog). Current metadata version: 1.1 FINAL as of [DATE OF MERGE]. Standard Metadata Vocabulary ---------------------------- @@ -29,7 +29,7 @@ A dataset is an identifiable collection of structured data objects unified by so A Web API (**A**pplication **P**rogramming **I**nterface) allows computer programs to dynamically query a dataset using the World Wide Web. For example, a dataset [of farmers markets](https://explore.data.gov/Agriculture/Farmers-Markets-Geographic-Data/wfna-38ey) may be made available for download as a single file (e.g., a CSV), or may be made available to developers through a Web API, such that a computer program could use a ZIP Code to retrieve a list of farmers markets in the ZIP Code area. -The catalog file for each agency should list all of the agency's datasets that can be made public, regardless of whether they are distributed by a file download or through a Web API. The **Endpoint** data element is used to indicate which datasets offer Web APIs (see below for more information on Common Core and Extended metadata elements). +The catalog file for each agency should list all of the agency's datasets that can be made public, regardless of whether they are distributed by a file download or through a Web API. Metadata File Format -- JSON @@ -575,17 +575,17 @@ We sought to be platform-independent and to align as much as possible with exist To that end, our JSON key names are directly drawn from [DCAT](http://www.w3.org/TR/vocab-dcat/), with a few exceptions. -We added the new **accessLevel** field to help easily sort datasets into our three existing categories: public, restricted public, and non-public. This field means an agency can run a basic filter against its enterprise data catalog to generate a public-facing list of datasets that are, or *could one day be*, made publicly available (or, in the case of restricted data, available under certain conditions). This field also makes it easy for anyone to generate a list of datasets that *could* be made available but have not yet been released by filtering **accessLevel** to *public* and **accessURL** to *blank*. +We added the **accessLevel** field to help easily sort datasets into our three existing categories: public, restricted public, and non-public. This field means an agency can run a basic filter against its enterprise data catalog to generate a public-facing list of datasets that are, or *could one day be*, made publicly available (or, in the case of restricted data, available under certain conditions). This field also makes it easy for anyone to generate a list of datasets that *could* be made available but have not yet been released by filtering **accessLevel** to *public* and **accessURL** to *blank*. -We added the new **accessLevelComment** field for data stewards to explain how to access restricted public datasets, and for agencies to have a place to record (even if only internally) the reason for not releasing a non-public dataset. +We added the **rights** field (formerly _accessLevelComment_) for data stewards to explain how to access restricted public datasets, and for agencies to have a place to record (even if only internally) the reason for not releasing a non-public dataset. -We added the new **systemOfRecords** field for data stewards to optionally link to a relevant System of Records Notice URL. A System of Records is a group of any records under the control of any agency from which information is retrieved by the name of the individual or by some identifying number, symbol, or other identifier assigned to the individual. +We added the **systemOfRecords** field for data stewards to optionally link to a relevant System of Records Notice URL. A System of Records is a group of any records under the control of any agency from which information is retrieved by the name of the individual or by some identifying number, symbol, or other identifier assigned to the individual. -We added the new **bureauCode** field to ensure every dataset is connected in a standard way with an agency bureau. +We added the **bureauCode** field to ensure every dataset is connected in a standard way with an agency bureau. -We added the new **programCode** field to ensure that when applicable, every dataset is connected in a standard way with an agency program office. +We added the **programCode** field to ensure that when applicable, every dataset is connected in a standard way with an agency program office. -We added the new **dataQuality** to indicate whether or not the data meets an agency’s Information Quality Guidelines. +We added the **dataQuality** to indicate whether or not the data meets an agency’s Information Quality Guidelines. Additional Information From 5d1b5b1d6ba6317ed912ffcb406e9ed119b55de6 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Sun, 14 Sep 2014 16:04:30 -0400 Subject: [PATCH 054/129] updating version control reference In reference to #357 --- catalog.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/catalog.md b/catalog.md index f21ab3c5..376393aa 100644 --- a/catalog.md +++ b/catalog.md @@ -59,7 +59,7 @@ Agencies must follow the provided [specification](/schema/). We have built a [c Inclusion of the Public Data Listing as a Record ------------------------------------------------ -Each 'data.json' catalog file should include a record for the data asset that is the data catalog itself. Contact Name and Contact Email can be used to provide a PoC for the 'data.json' efforts; Description can be used to clarify which version of the common core metadata schema the agency is currently using; and Last Update can be used to indicate the date when the Public Data Listing was last modified. +Each 'data.json' catalog file should include a record for the data asset that is the data catalog itself. Contact Name and Contact Email can be used to provide a PoC for the 'data.json' efforts; Data Standard (_conformsTo_) can be used to clarify which version of the common core metadata schema the agency is currently using; and Last Update can be used to indicate the date when the Public Data Listing was last modified. Presentation ------------ From 7863afbb36289fe97cdaaa7f606fc307155c6162 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Mon, 15 Sep 2014 17:13:23 -0400 Subject: [PATCH 055/129] Moving programCode and bureauCode to required But only for federal agencies. See #247 --- v1.1/schema.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 01f86b97..8dbc94bc 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -60,7 +60,7 @@ In order to distinguish the schema version being used publishers are required to "Common Core" Required Fields ----------------------------- -The following "common core" fields are required, to be used to describe each entry: +The following "common core" fields are required, to be used to describe each entry. Only U.S. Federal agencies are required to fill out `bureauCode` and `programCode`. *(Consult the 'Further Metadata Field Guidance' section lower in the page to learn more about the use of each element, including the range of valid entries where appropriate. Consult the [schema maps](/metadata-resources#common-core-required-fields-equivalents) to find the equivalent DCAT, Schema.org, and CKAN fields.)* @@ -75,16 +75,16 @@ publisher | Publisher | The publishing entity. contactPoint | Contact Name and Email | Contact person's name and email for the asset. identifier | Unique Identifier | A unique identifier for the dataset or API as maintained within an Agency catalog or database. accessLevel | Public Access Level | 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) +bureauCode[USG](#USG-note) | Bureau Code | Federal agencies, combined agency and bureau code from [OMB Circular A-11, Appendix C](http://www.whitehouse.gov/sites/default/files/omb/assets/a11_current_year/app_c.pdf) in the format of `015:11`. +programCode[USG](#USG-note) | Program Code | Federal agencies, list the primary program related to this data asset, from the [Federal Program Inventory](http://goals.performance.gov/sites/default/files/images/FederalProgramInventory_FY13_MachineReadable_091613.xls). Use the format of `015:001` "Common Core" Required-if-Applicable Fields ------------------------------------------- -The following fields must be used to describe each dataset if they are applicable. U.S. Federal agencies must fill out bureauCode and programCode. +The following fields must be used to describe each dataset if they are applicable. {: .table .table-striped} Field | Label | Definition -------------- | -------------- | -------------- -bureauCode[USG](#USG-note) | Bureau Code | Federal agencies, combined agency and bureau code from [OMB Circular A-11, Appendix C](http://www.whitehouse.gov/sites/default/files/omb/assets/a11_current_year/app_c.pdf) in the format of `015:11`. -programCode[USG](#USG-note) | Program Code | Federal agencies, list the primary program related to this data asset, from the [Federal Program Inventory](http://goals.performance.gov/sites/default/files/images/FederalProgramInventory_FY13_MachineReadable_091613.xls). Use the format of `015:001` distribution | Distribution | Represents a specific available form of a dataset in the form of download or access URLs, along with metadata specific to that form. license | License | The license or non-license (i.e. Public Domain) status with which the dataset or API has been published. See [Open Licenses](/open-licenses/) for more information. rights | Rights | This may include information regarding access or restrictions based on privacy, security, or other policies. This should also serve as an explanation for the selected “accessLevel” including instructions for how to access a restricted file, if applicable, or explanation for why a “non-public” or “restricted public” data asset is not “public,” if applicable. Text, 255 characters. From 0f783d5d3a9a26873b654009e23ad6ad01a29e00 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Tue, 23 Sep 2014 17:37:08 -0400 Subject: [PATCH 056/129] adding a section for version 1.1 links --- catalog.md | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/catalog.md b/catalog.md index 376393aa..82edc060 100644 --- a/catalog.md +++ b/catalog.md @@ -72,6 +72,20 @@ Agencies must have present a table/list of each dataset in the /data page. The The page must be populated from the machine-readable catalog file (e.g. data.xml or data.json) following the [specification](/schema/) described above. Agencies are encouraged to add functionality to assist end-user discoverability. Additional functions might be sorting, filtering or paging to help make a more digestible list. Agencies are also encouraged to add more to the standard schema which might further assist end-user discoverability and usability (e.g. thumbnails). +Version 1.1 Update +------------------ + +In the year since the release of the Open Data Policy, agencies and the public have suggested several updates to the metadata schema. In the interest of stability, these updates have been tied together into a methodical update to a version 1.1 of the common core schema. Each issue has been rigorously discussed in its own issue thread and at the [July government-wide offsite session](https://github.com/project-open-data/project-open-data.github.io/issues/325) dedicated to this update. + +* These updates have been managed through [issues in a single milestone](https://github.com/project-open-data/project-open-data.github.io/milestones/Next%20Version%20of%20Common%20Core%20Metadata%20Schema%20(1.0%20-%3E%201.1.). +* Each issue within the milestone contains the related discussion and a link to the proposed edits. +* Those proposed edits can also be found bundled in [this combined pull request](https://github.com/project-open-data/project-open-data.github.io/pull/357). +* [Example data.json file with the version 1.1 schema](https://gist.github.com/philipashlock/21ff607527863fba200b). +* [Preview of the new updately metadata schema page](http://project-open-data.civicagency.org/v1.1/schema/). +* [Changelog for the version 1.1 schema](http://project-open-data.civicagency.org/metadata-changelog/). +* [Event signup for Oct. 15 webinar on the version 1.1 update](https://www.digitalgov.gov/event/open-data-policy-common-core-metadata-v-1-1-updates/) + + Supplemental Information ------------------------ From 0e5b2adc31ddd031c60d936111bcec7fe8ea3089 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Tue, 23 Sep 2014 17:37:45 -0400 Subject: [PATCH 057/129] fixing link --- catalog.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/catalog.md b/catalog.md index 82edc060..29691f77 100644 --- a/catalog.md +++ b/catalog.md @@ -77,7 +77,7 @@ Version 1.1 Update In the year since the release of the Open Data Policy, agencies and the public have suggested several updates to the metadata schema. In the interest of stability, these updates have been tied together into a methodical update to a version 1.1 of the common core schema. Each issue has been rigorously discussed in its own issue thread and at the [July government-wide offsite session](https://github.com/project-open-data/project-open-data.github.io/issues/325) dedicated to this update. -* These updates have been managed through [issues in a single milestone](https://github.com/project-open-data/project-open-data.github.io/milestones/Next%20Version%20of%20Common%20Core%20Metadata%20Schema%20(1.0%20-%3E%201.1.). +* These updates have been managed through [issues in a single milestone](https://github.com/project-open-data/project-open-data.github.io/milestones/Next%20Version%20of%20Common%20Core%20Metadata%20Schema%20(1.0%20-%3E%201.1.)). * Each issue within the milestone contains the related discussion and a link to the proposed edits. * Those proposed edits can also be found bundled in [this combined pull request](https://github.com/project-open-data/project-open-data.github.io/pull/357). * [Example data.json file with the version 1.1 schema](https://gist.github.com/philipashlock/21ff607527863fba200b). From 61f594fda36c5300ca591c0880a99e6035f0a4e6 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Tue, 23 Sep 2014 17:38:36 -0400 Subject: [PATCH 058/129] Those -> The --- catalog.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/catalog.md b/catalog.md index 29691f77..34d02600 100644 --- a/catalog.md +++ b/catalog.md @@ -79,7 +79,7 @@ In the year since the release of the Open Data Policy, agencies and the public h * These updates have been managed through [issues in a single milestone](https://github.com/project-open-data/project-open-data.github.io/milestones/Next%20Version%20of%20Common%20Core%20Metadata%20Schema%20(1.0%20-%3E%201.1.)). * Each issue within the milestone contains the related discussion and a link to the proposed edits. -* Those proposed edits can also be found bundled in [this combined pull request](https://github.com/project-open-data/project-open-data.github.io/pull/357). +* The proposed edits can also be found bundled in [this combined pull request](https://github.com/project-open-data/project-open-data.github.io/pull/357). * [Example data.json file with the version 1.1 schema](https://gist.github.com/philipashlock/21ff607527863fba200b). * [Preview of the new updately metadata schema page](http://project-open-data.civicagency.org/v1.1/schema/). * [Changelog for the version 1.1 schema](http://project-open-data.civicagency.org/metadata-changelog/). From afab88d29ad2ca432ce459d965866600c61243e4 Mon Sep 17 00:00:00 2001 From: Gray Brooks Date: Wed, 24 Sep 2014 14:06:12 -0400 Subject: [PATCH 059/129] correcting example listed for systemOfRecords --- v1.1/schema.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/v1.1/schema.md b/v1.1/schema.md index 8dbc94bc..e819ddb1 100644 --- a/v1.1/schema.md +++ b/v1.1/schema.md @@ -539,7 +539,7 @@ Dataset Fields {#Dataset} **Required** | No **Accepted Values** | String (URL) **Usage Notes** | This field should a URL to the System of Records Notice (SORN) that relates to the dataset, specifically from FederalRegister.gov. -**Example** | `{"https://www.federalregister.gov/articles/2002/04/08/02-7376/privacy-act-of-1974-publication-in-full-of-all-notices-of-systems-of-records-including-several-new#p-361"}` +**Example** | `{"systemOfRecords":"https://www.federalregister.gov/articles/2002/04/08/02-7376/privacy-act-of-1974-publication-in-full-of-all-notices-of-systems-of-records-including-several-new#p-361"}` {: .table .table-striped #temporal} **Field [#](#temporal){: .permalink}** | **temporal** From 38e1193f4bf12374e33b696fe963be2f473f1201 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Tue, 30 Sep 2014 17:23:58 -0400 Subject: [PATCH 060/129] Overhaul v1.1 changelog. Adds links to issues --- metadata-changelog.md | 43 ++++++++++++++++++++----------------------- 1 file changed, 20 insertions(+), 23 deletions(-) diff --git a/metadata-changelog.md b/metadata-changelog.md index 6459f22a..ddf4a33a 100644 --- a/metadata-changelog.md +++ b/metadata-changelog.md @@ -9,32 +9,29 @@ This page lists changes to the common core metadata schema by version. Latest ch ## Changelog -### Version 1.1 FINAL - ??????? +### Version 1.1 (Draft as of Sept 30 2014) Updates to version 1.0 common core metadata: -* Renames "accessLevelComment" field to "rights" to better alight with DCAT -* Renames "mbox" field to "hasEmail" and moves to within "contactPoint" to better align with vCard -* Aligns "accrualPeriodicity" field to ISO 8601 -* Aligns "contactPoint" field to vCard - -* Changes "accessURL" field to represent indirect access and to exist only within "distribution" -* Changes "format" field to a human readable description and to exist only within "distribution" -* Changes "distribution" field to become required-if-applicable and to always contain the "accessURL" or "downloadURL" fields -* Changes "primaryITInvestmentUII" to the correct capitalization -* Changes "publisher" field to allow for multiple levels of organizations - -* Removes "webService" field - -* Adds required "catalog" field to wrap the entire data.json file -* Adds "conformsTo" field, required at the catalog level and optional at the individual record level -* Adds optional "describedBy" field -* Adds optional "description" field for use within "distribution" -* Adds required-if-applicable "downloadURL" field -* Adds required "fn" field as part of "contactPoint" -* Adds optional "isPartOf" field -* Adds required-if-applicable "mediaType" field -* Adds optional "title" field for use within "distribution" +* Adds required "catalog" object to wrap the entire data.json file ([#309](https://github.com/project-open-data/project-open-data.github.io/issues/309)) +* Adds `conformsTo` field, required at the catalog level to specify the schema and optional at the dataset and distribution level ([#309](https://github.com/project-open-data/project-open-data.github.io/issues/309), [#362](https://github.com/project-open-data/project-open-data.github.io/issues/362)) +* Adds optional `describedBy` field at the catalog, dataset, and distribution level ([#291](https://github.com/project-open-data/project-open-data.github.io/issues/291), [#309](https://github.com/project-open-data/project-open-data.github.io/issues/309)) +* Renames `accessLevelComment` field to `rights` ([#353](https://github.com/project-open-data/project-open-data.github.io/issues/353)) +* Changes `contactPoint` field to an object that contains the name (`fn`) and email address (`hasEmail`) ([#358](https://github.com/project-open-data/project-open-data.github.io/issues/358)) +* Renames `mbox` field to `hasEmail` and moves to within `contactPoint` ([#358](https://github.com/project-open-data/project-open-data.github.io/issues/358)) +* Adds `fn` field as part of `contactPoint` replacing earlier use of `contactPoint` ([#358](https://github.com/project-open-data/project-open-data.github.io/issues/358)) +* Changes `accrualPeriodicity` field to use ISO 8601 date syntax ([#292](https://github.com/project-open-data/project-open-data.github.io/issues/292)) +* Changes `primaryITInvestmentUII` to use capitalization consistent with the rest of the schema ([#284](https://github.com/project-open-data/project-open-data.github.io/issues/284)) +* Changes `publisher` field to an object that allows multiple levels of organizations ([#296](https://github.com/project-open-data/project-open-data.github.io/issues/296)) +* Changes `distribution` field to become required-if-applicable and to always contain the `accessURL` or `downloadURL` fields ([#217](https://github.com/project-open-data/project-open-data.github.io/issues/217)) +* Changes `accessURL` field to represent indirect access and to exist only within `distribution` ([#217](https://github.com/project-open-data/project-open-data.github.io/issues/217), [#335](https://github.com/project-open-data/project-open-data.github.io/issues/335)) +* Changes `format` field to a human readable description and to exist only within `distribution` ([#272](https://github.com/project-open-data/project-open-data.github.io/issues/272), [#293](https://github.com/project-open-data/project-open-data.github.io/issues/293)) +* Adds required-if-applicable `mediaType` field to replace earlier use of `format` ([#272](https://github.com/project-open-data/project-open-data.github.io/issues/272)) +* Adds required-if-applicable `downloadURL` field to replace earlier use of `accessURL` ([#335](https://github.com/project-open-data/project-open-data.github.io/issues/335)) +* Adds optional `description` field for use within `distribution` ([#248](https://github.com/project-open-data/project-open-data.github.io/issues/248)) +* Adds optional `title` field for use within `distribution` ([#248](https://github.com/project-open-data/project-open-data.github.io/issues/248)) +* Adds optional `isPartOf` field to group datasets as a collection ([#258](https://github.com/project-open-data/project-open-data.github.io/issues/258)) +* Removes `webService` field. APIs can be described within a `distribution` using `accessURL` and `format` ([#291](https://github.com/project-open-data/project-open-data.github.io/issues/291)) ### Version 1.0 FINAL - 9/20/2013 From e01f27292b366874eeda7565c0a18a7178937ab3 Mon Sep 17 00:00:00 2001 From: Philip Ashlock Date: Tue, 30 Sep 2014 17:40:38 -0400 Subject: [PATCH 061/129] Upgrade to Bootstrap 3.2.0 --- _includes/footer.html | 2 +- _includes/header.html | 47 +- _layouts/default.html | 2 +- assets/css/bootstrap.css | 7117 +++++++++++++++++++++++++++++++------- assets/css/site.css | 7 +- 5 files changed, 5890 insertions(+), 1285 deletions(-) diff --git a/_includes/footer.html b/_includes/footer.html index 6ed3c0e6..dfbc4b85 100644 --- a/_includes/footer.html +++ b/_includes/footer.html @@ -1,5 +1,5 @@
-