Infer datapackage.json from transformed data files #48
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
switzersc
commented
Jan 14, 2020
| @@ -1,650 +0,0 @@ | |||
| id,organization_id,program_id,name,alternate_name,description,url,email,status,interpretation_services,application_process,wait_time,fees,accreditations,licenses | |||
There was a problem hiding this comment.
Deleting this because we don't use it as far as I can tell.
switzersc
commented
Jan 14, 2020
| @@ -0,0 +1 @@ | |||
| {"profile":"tabular-data-package","resources":[{"format":"csv","mediatype":"text/csv","name":"regular_schedules","path":"tmp/datapackage/data/regular_schedules.csv","schema":{"fields":[{"name":"id","type":"any","format":"default"},{"name":"service_id","type":"any","format":"default"},{"name":"location_id","type":"integer","format":"default"},{"name":"service_at_location_id","type":"any","format":"default"},{"name":"weekday","type":"any","format":"default"},{"name":"opens_at","type":"time","format":"default"},{"name":"closes_at","type":"time","format":"default"}],"missingValues":[""]},"profile":"tabular-data-resource","encoding":"utf-8"},{"format":"csv","mediatype":"text/csv","name":"phones","path":"tmp/datapackage/data/phones.csv","schema":{"fields":[{"name":"id","type":"any","format":"default"},{"name":"location_id","type":"any","format":"default"},{"name":"service_id","type":"any","format":"default"},{"name":"organization_id","type":"any","format":"default"},{"name":"contact_id","type":"any","format":"default"},{"name":"service_at_location_id","type":"any","format":"default"},{"name":"number","type":"any","format":"default"},{"name":"extension","type":"any","format":"default"},{"name":"type","type":"any","format":"default"},{"name":"language","type":"any","format":"default"},{"name":"description","type":"any","format":"default"}],"missingValues":[""]},"profile":"tabular-data-resource","encoding":"utf-8"},{"format":"csv","mediatype":"text/csv","name":"eligibility","path":"tmp/datapackage/data/eligibility.csv","schema":{"fields":[{"name":"id","type":"any","format":"default"},{"name":"service_id","type":"integer","format":"default"},{"name":"eligibility","type":"any","format":"default"}],"missingValues":[""]},"profile":"tabular-data-resource","encoding":"utf-8"},{"format":"csv","mediatype":"text/csv","name":"postal_addresses","path":"tmp/datapackage/data/postal_addresses.csv","schema":{"fields":[{"name":"id","type":"any","format":"default"},{"name":"location_id","type":"any","format":"default"},{"name":"organization_id","type":"integer","format":"default"},{"name":"attention","type":"any","format":"default"},{"name":"address_1","type":"any","format":"default"},{"name":"city","type":"any","format":"default"},{"name":"region","type":"any","format":"default"},{"name":"state_province","type":"any","format":"default"},{"name":"postal_code","type":"integer","format":"default"},{"name":"country","type":"any","format":"default"}],"missingValues":[""]},"profile":"tabular-data-resource","encoding":"utf-8"},{"format":"csv","mediatype":"text/csv","name":"organizations","path":"tmp/datapackage/data/organizations.csv","schema":{"fields":[{"name":"id","type":"integer","format":"default"},{"name":"name","type":"any","format":"default"},{"name":"alternate_name","type":"any","format":"default"},{"name":"description","type":"any","format":"default"},{"name":"email","type":"any","format":"default"},{"name":"url","type":"any","format":"default"},{"name":"tax_status","type":"any","format":"default"},{"name":"tax_id","type":"any","format":"default"},{"name":"year_incorporated","type":"any","format":"default"},{"name":"legal_status","type":"any","format":"default"}],"missingValues":[""]},"profile":"tabular-data-resource","encoding":"utf-8"},{"format":"csv","mediatype":"text/csv","name":"services_at_location","path":"tmp/datapackage/data/services_at_location.csv","schema":{"fields":[{"name":"id","type":"any","format":"default"},{"name":"service_id","type":"integer","format":"default"},{"name":"location_id","type":"integer","format":"default"},{"name":"description","type":"any","format":"default"}],"missingValues":[""]},"profile":"tabular-data-resource","encoding":"utf-8"},{"format":"csv","mediatype":"text/csv","name":"locations","path":"tmp/datapackage/data/locations.csv","schema":{"fields":[{"name":"id","type":"integer","format":"default"},{"name":"organization_id","type":"integer","format":"default"},{"name":"name","type":"any","format":"default"},{"name":"alternate_name","type":"any","format":"default"},{"name":"description","type":"any","format":"default"},{"name":"transportation","type":"any","format":"default"},{"name":"latitude","type":"any","format":"default"},{"name":"longitude","type":"any","format":"default"}],"missingValues":[""]},"profile":"tabular-data-resource","encoding":"utf-8"},{"format":"csv","mediatype":"text/csv","name":"services","path":"tmp/datapackage/data/services.csv","schema":{"fields":[{"name":"id","type":"integer","format":"default"},{"name":"organization_id","type":"integer","format":"default"},{"name":"program_id","type":"any","format":"default"},{"name":"name","type":"any","format":"default"},{"name":"alternate_name","type":"any","format":"default"},{"name":"description","type":"any","format":"default"},{"name":"url","type":"any","format":"default"},{"name":"email","type":"any","format":"default"},{"name":"status","type":"any","format":"default"},{"name":"interpretation_services","type":"any","format":"default"},{"name":"application_process","type":"any","format":"default"},{"name":"wait_time","type":"any","format":"default"},{"name":"fees","type":"any","format":"default"},{"name":"accreditations","type":"any","format":"default"},{"name":"licenses","type":"any","format":"default"}],"missingValues":[""]},"profile":"tabular-data-resource","encoding":"utf-8"}]} | |||
There was a problem hiding this comment.
Would like to pretty print this but didn't know how to get the tests to ignore whitespace when comparing this with the actual output file.
switzersc
commented
Jan 14, 2020
| expect(output_datapackage_json).to eq(datapackage_json_fixture) | ||
| end | ||
|
|
||
| xit "uses default datapackage.json when path is unsafe" do |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Addresses #40
Use the datapackage ruby gem to infer the json schema for the resulting CSV files. There may be additional fields or some HSDS fields may not all be present, so we can't just use a static example datapackage.json file. This PR leaves the default as a fall-back in case the source data has path issues (still figuring out what's necessary for path management with this as a gem).
This PR also makes it so that the datapackage.json is present in the output regardless of whether the files have been zipped. Previously, the json schema was only generated if the files were zipped.
This also closes #46.