Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[631] WIP: Automatic Data Export to Wikidata/Wikipedia #654

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 7 additions & 2 deletions .env.example
Original file line number Diff line number Diff line change
Expand Up @@ -32,5 +32,10 @@ GITHUB_CLIENT_ID=
GITHUB_CLIENT_SECRET=
GITHUB_ORGANIZATION=Klimatbyran
GITHUB_REDIRECT_URI=http://localhost:5137/auth/callback
JWT_SECRET=""
JWT_EXPIRES_IN=
JWT_SECRET="1"
JWT_EXPIRES_IN=

# Wikidata credentials
WIKIDATA_URL=https://test.wikidata.org #Use https://www.wikidata.org for production
WIKIDATA_USERNAME=
WIKIDATA_PASSWORD=
29 changes: 28 additions & 1 deletion package-lock.json

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

1 change: 1 addition & 0 deletions package.json
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,7 @@
"redis": "^4.7.0",
"sharp": "^0.33.5",
"tsx": "^4.19.2",
"wikibase-edit": "^7.2.3",
"wikibase-sdk": "^10.2.1",
"zod": "^3.23.8"
},
Expand Down
194 changes: 194 additions & 0 deletions scripts/push-existing-verified-data-to-wikidata.ts
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This script is currently for testing and for the optional task to push existing data into wikidata without the garbo pipepline. I think it make sense to keep it for now, if such tasks arise and also some kind of knowledge on how to optionally transform our database model to the wikidata model.

Original file line number Diff line number Diff line change
@@ -0,0 +1,194 @@
import { PrismaClient } from '@prisma/client'
import wikidataConfig from "../src/config/wikidata";
import { bulkCreateOrEditCarbonFootprintClaim, Claim } from '../src/lib/wikidata';

//Currently still in testing the filters filter out only data related to ABB as this company is present in the Sandbox
const entityDownloadId: `Q${number}` = "Q731938";
const entityUploadId: `Q${number}` = "Q238689";

const prisma = new PrismaClient()

const emissionsScope1 = await prisma.scope1.findMany({
select: {
total: true,
unit: true,
metadata: {
select: {
verifiedByUserId: true
}
},
emissions: {
select: {
reportingPeriod: {
select: {
startDate: true,
endDate: true,
reportURL: true,
company: {
select: {
wikidataId: true,
}
}
}
}
}
},
},
where: {
metadata: {some: {verifiedByUserId: {not: null}}},
emissions: {reportingPeriod: {year: "2023"}}
}
})
let claims: Claim[] = [];
let filtered1 = emissionsScope1.filter((emission) => emission.emissions?.reportingPeriod?.company.wikidataId === entityDownloadId);

for(const emission of filtered1) {
if(emission.total !== null && emission.unit !== null && emission.emissions !== null
&& emission.emissions!.reportingPeriod !== null && emission.emissions!.reportingPeriod!.startDate !== null
&& emission.emissions!.reportingPeriod!.endDate !== null && emission.emissions!.reportingPeriod!.reportURL !== null
&& emission.emissions!.reportingPeriod!.company !== null && emission.emissions!.reportingPeriod!.company!.wikidataId !== null) {

claims.push({
startDate: emission.emissions!.reportingPeriod!.startDate.toISOString(),
endDate: emission.emissions!.reportingPeriod!.endDate.toISOString(),
value: emission.total!.toString(),
referenceUrl: emission.emissions!.reportingPeriod!.reportURL!,
scope: wikidataConfig.entities.SCOPE_1
})
}
}


const emissionsScope2 = await prisma.scope2.findMany({
select: {
mb: true,
lb: true,
unknown: true,
unit: true,
metadata: {
select: {
verifiedByUserId: true
}
},
emissions: {
select: {
reportingPeriod: {
select: {
startDate: true,
endDate: true,
reportURL: true,
company: {
select: {
wikidataId: true,
}
}
}
}
}
},
},
where: {
metadata: {some: {verifiedByUserId: {not: null}}},
emissions: {reportingPeriod: {year: "2023"}}

}
})

let filtered2 = emissionsScope2.filter((emission) => emission.emissions?.reportingPeriod?.company.wikidataId === entityDownloadId);

for(const emission of filtered2) {
if(emission.unit !== null && emission.emissions !== null
&& emission.emissions!.reportingPeriod !== null && emission.emissions!.reportingPeriod!.startDate !== null
&& emission.emissions!.reportingPeriod!.endDate !== null && emission.emissions!.reportingPeriod!.reportURL !== null
&& emission.emissions!.reportingPeriod!.company !== null && emission.emissions!.reportingPeriod!.company!.wikidataId !== null) {

if(emission.mb !== null) {
claims.push({
startDate: emission.emissions!.reportingPeriod!.startDate.toISOString(),
endDate: emission.emissions!.reportingPeriod!.endDate.toISOString(),
value: emission.mb!.toString(),
referenceUrl: emission.emissions!.reportingPeriod!.reportURL!,
scope: wikidataConfig.entities.SCOPE_2_MARKET_BASED
})
}

if(emission.lb !== null) {
claims.push({
startDate: emission.emissions!.reportingPeriod!.startDate.toISOString(),
endDate: emission.emissions!.reportingPeriod!.endDate.toISOString(),
value: emission.lb!.toString(),
referenceUrl: emission.emissions!.reportingPeriod!.reportURL!,
scope: wikidataConfig.entities.SCOPE_2_LOCATION_BASED
})
}

if(emission.unknown !== null) {
claims.push({
startDate: emission.emissions!.reportingPeriod!.startDate.toISOString(),
endDate: emission.emissions!.reportingPeriod!.endDate.toISOString(),
value: emission.unknown!.toString(),
referenceUrl: emission.emissions!.reportingPeriod!.reportURL!,
scope: wikidataConfig.entities.SCOPE_2
})
}
}
}

const emissionsScope3 = await prisma.scope3Category.findMany({
select: {
total: true,
unit: true,
category: true,
metadata: {
select: {
verifiedByUserId: true
}
},
scope3: {
select: {
emissions: {
select: {
reportingPeriod: {
select: {
startDate: true,
endDate: true,
reportURL: true,
company: {
select: {
wikidataId: true,
}
}
}
}
}
},
}
}
},
where: {
metadata: {some: {verifiedByUserId: {not: null}}},
scope3: {emissions: {reportingPeriod: {year: "2023"}}}
}
})

let filtered3 = emissionsScope3.filter((emission) => emission.scope3.emissions?.reportingPeriod?.company.wikidataId === entityDownloadId);

for(const emission of filtered3) {
if(emission.unit !== null && emission.scope3 !== null && emission.scope3.emissions !== null
&& emission.scope3.emissions!.reportingPeriod !== null && emission.scope3.emissions!.reportingPeriod!.startDate !== null
&& emission.scope3.emissions!.reportingPeriod!.endDate !== null && emission.scope3.emissions!.reportingPeriod!.reportURL !== null
&& emission.scope3.emissions!.reportingPeriod!.company !== null && emission.scope3.emissions!.reportingPeriod!.company!.wikidataId !== null) {

if(emission.category !== 16) {
claims.push({
startDate: emission.scope3!.emissions!.reportingPeriod!.startDate.toISOString(),
endDate: emission.scope3!.emissions!.reportingPeriod!.endDate.toISOString(),
value: emission.total!.toString(),
referenceUrl: emission.scope3!.emissions!.reportingPeriod!.reportURL!,
scope: wikidataConfig.entities.SCOPE_3,
category: wikidataConfig.translateIdToCategory(emission.category)
})
}
}
}
await bulkCreateOrEditCarbonFootprintClaim(entityUploadId, claims);
Loading