Tudor Sitaru
7e6ded29e2
Build and Push Docker Images / Build Backend (FastAPI) (push) Successful in 12s
Build and Push Docker Images / Build Frontend (Next.js) (push) Successful in 52s
Build and Push Docker Images / Trigger Portainer Update (push) Has been cancelled
Build and Push Docker Images / Build Pipeline (Meltano + dbt + Airflow) (push) Has been cancelled
Mirrors the existing legacy KS2 pattern to fill the gap before EES hosted KS4 data. Four files changed: - tap-uk-ees: LegacyKS4Stream downloads each year's DfE Compare School Performance ZIP, extracts england_ks4final.csv, maps 416 legacy columns to Singer fields, strips % suffixes. Registered in discover_streams(). TapUKEES.config_jsonschema gains legacy_ks4_urls setting. - stg_legacy_ks4.sql: safe_numeric casts + NULL placeholders for columns not present in legacy format (ebacc_avg_score, gcse_grade_91_pct, prior_attainment_avg, sen_pct). - int_ks4_with_lineage.sql: adds all_ks4 CTE unioning stg_ees_ks4 and stg_legacy_ks4, matching the int_ks2_with_lineage pattern. - _stg_sources.yml + meltano.yml: source declaration and setting definition for legacy_ks4. URLs configured per-year once provided. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
110 lines
3.2 KiB
YAML
110 lines
3.2 KiB
YAML
project_id: school-compare-pipeline
|
|
default_environment: production
|
|
|
|
plugins:
|
|
extractors:
|
|
- name: tap-uk-gias
|
|
namespace: uk_gias
|
|
pip_url: ./plugins/extractors/tap-uk-gias
|
|
executable: tap-uk-gias
|
|
settings:
|
|
- name: download_url
|
|
kind: string
|
|
description: GIAS bulk CSV download URL
|
|
|
|
- name: tap-uk-ees
|
|
namespace: uk_ees
|
|
pip_url: ./plugins/extractors/tap-uk-ees
|
|
executable: tap-uk-ees
|
|
settings:
|
|
- name: base_url
|
|
kind: string
|
|
value: https://content.explore-education-statistics.service.gov.uk/api/v1
|
|
- name: datasets
|
|
kind: array
|
|
description: List of EES dataset configs to extract
|
|
- name: legacy_ks2_urls
|
|
kind: object
|
|
description: "Year code → URL mapping for legacy KS2 CSVs"
|
|
- name: legacy_ks4_urls
|
|
kind: object
|
|
description: "Year code → URL mapping for legacy KS4 ZIPs (england_ks4final.csv inside)"
|
|
config:
|
|
legacy_ks2_urls:
|
|
"201516": "http://10.0.1.224:8081/filebrowser/api/public/dl/R9jjXFWa?inline=true"
|
|
"201617": "http://10.0.1.224:8081/filebrowser/api/public/dl/tIwJPVQS?inline=true"
|
|
"201718": "http://10.0.1.224:8081/filebrowser/api/public/dl/GO7SKE0p?inline=true"
|
|
"201819": "http://10.0.1.224:8081/filebrowser/api/public/dl/jchDEHsv?inline=true"
|
|
|
|
- name: tap-uk-ofsted
|
|
namespace: uk_ofsted
|
|
pip_url: ./plugins/extractors/tap-uk-ofsted
|
|
executable: tap-uk-ofsted
|
|
settings:
|
|
- name: mi_url
|
|
kind: string
|
|
description: Ofsted Management Information download URL
|
|
|
|
- name: tap-uk-parent-view
|
|
namespace: uk_parent_view
|
|
pip_url: ./plugins/extractors/tap-uk-parent-view
|
|
executable: tap-uk-parent-view
|
|
|
|
- name: tap-uk-fbit
|
|
namespace: uk_fbit
|
|
pip_url: ./plugins/extractors/tap-uk-fbit
|
|
executable: tap-uk-fbit
|
|
settings:
|
|
- name: base_url
|
|
kind: string
|
|
value: https://financial-benchmarking-and-insights-tool.education.gov.uk/api
|
|
|
|
- name: tap-uk-idaci
|
|
namespace: uk_idaci
|
|
pip_url: ./plugins/extractors/tap-uk-idaci
|
|
executable: tap-uk-idaci
|
|
|
|
loaders:
|
|
- name: target-postgres
|
|
variant: meltanolabs
|
|
pip_url: meltanolabs-target-postgres
|
|
config:
|
|
host: $PG_HOST
|
|
port: $PG_PORT
|
|
user: $PG_USER
|
|
password: $PG_PASSWORD
|
|
database: $PG_DATABASE
|
|
default_target_schema: raw
|
|
|
|
utilities:
|
|
- name: dbt-postgres
|
|
variant: dbt-labs
|
|
pip_url: dbt-postgres~=1.10
|
|
config:
|
|
project_dir: $MELTANO_PROJECT_ROOT/transform
|
|
profiles_dir: $MELTANO_PROJECT_ROOT/transform
|
|
|
|
environments:
|
|
- name: dev
|
|
config:
|
|
plugins:
|
|
loaders:
|
|
- name: target-postgres
|
|
config:
|
|
host: localhost
|
|
port: 5432
|
|
user: postgres
|
|
password: postgres
|
|
database: school_compare
|
|
- name: production
|
|
config:
|
|
plugins:
|
|
loaders:
|
|
- name: target-postgres
|
|
config:
|
|
host: ${PG_HOST}
|
|
port: ${PG_PORT}
|
|
user: ${PG_USER}
|
|
password: ${PG_PASSWORD}
|
|
database: ${PG_DATABASE}
|