-
Notifications
You must be signed in to change notification settings - Fork 7
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #6 from DFE-Digital/schema-task
Emit JSON schema and BigQuery schema
- Loading branch information
Showing
10 changed files
with
229 additions
and
11 deletions.
There are no files selected for viewing
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
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
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
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,73 @@ | ||
| module DfE | ||
| module Analytics | ||
| class EventSchema | ||
| def self.as_json | ||
| path = "#{Gem.loaded_specs['dfe-analytics'].gem_dir}/config/event-schema.json" | ||
| File.read(path) | ||
| end | ||
|
|
||
| def self.as_bigquery_schema | ||
| schema = JSON.parse(as_json) | ||
| required_fields = schema['required'] | ||
|
|
||
| properties = schema['properties'] | ||
|
|
||
| schema = properties.keys.reduce([]) do |bq_schema, json_schema_entry_name| | ||
| json_schema_entry = properties[json_schema_entry_name] | ||
| bigquery_field_type = resolve_bigquery_type(json_schema_entry) | ||
|
|
||
| bigquery_schema_entry = { | ||
| 'mode' => resolve_bigquery_mode(json_schema_entry_name, json_schema_entry, required_fields), | ||
| 'name' => json_schema_entry_name, | ||
| 'type' => bigquery_field_type | ||
| } | ||
|
|
||
| if bigquery_field_type == 'RECORD' | ||
| bigquery_schema_entry['fields'] = [ | ||
| { | ||
| 'mode' => 'REQUIRED', | ||
| 'name' => 'key', | ||
| 'type' => 'STRING' | ||
| }, | ||
| { | ||
| 'mode' => 'REPEATED', | ||
| 'name' => 'value', | ||
| 'type' => 'STRING' | ||
| } | ||
| ] | ||
| end | ||
|
|
||
| bq_schema << bigquery_schema_entry | ||
| bq_schema | ||
| end | ||
|
|
||
| schema.to_json | ||
| end | ||
|
|
||
| def self.resolve_bigquery_mode(json_schema_entry_name, json_schema_entry, required_fields) | ||
| if required_fields.include?(json_schema_entry_name) | ||
| 'REQUIRED' | ||
| elsif json_schema_entry['type'] == 'array' | ||
| 'REPEATED' | ||
| else | ||
| 'NULLABLE' | ||
| end | ||
| end | ||
|
|
||
| def self.resolve_bigquery_type(json_schema_entry) | ||
| json_type = json_schema_entry['type'] | ||
| json_format = json_schema_entry['format'] | ||
|
|
||
| if json_type == 'array' | ||
| 'RECORD' | ||
| elsif json_type == 'string' && json_format == 'date-time' | ||
| 'TIMESTAMP' | ||
| elsif json_type == 'string' | ||
| 'STRING' | ||
| elsif json_type == 'integer' | ||
| 'INTEGER' | ||
| end | ||
| end | ||
| end | ||
| end | ||
| end |
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,13 @@ | ||
| namespace :dfe do | ||
| namespace :analytics do | ||
| desc 'Print out the dfe-analytics JSON schema' | ||
| task :schema do | ||
| puts DfE::Analytics::EventSchema.as_json | ||
| end | ||
|
|
||
| desc 'Print out the dfe-analytics BigQuery schema' | ||
| task :big_query_schema do | ||
| puts DfE::Analytics::EventSchema.as_bigquery_schema | ||
| end | ||
| end | ||
| end |
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
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,23 @@ | ||
| RSpec.describe DfE::Analytics::EventSchema do | ||
| describe '.as_json' do | ||
| it 'returns the JSON schema as an object' do | ||
| schema_on_disk = File.read("#{Gem.loaded_specs['dfe-analytics'].gem_dir}/config/event-schema.json") | ||
|
|
||
| output = described_class.as_json | ||
|
|
||
| expect(output).to be_present | ||
| expect(output).to eq schema_on_disk | ||
| end | ||
| end | ||
|
|
||
| describe '.as_bigquery_schema' do | ||
| it 'transforms the JSON schema into a BQ schema' do | ||
| bq_schema_on_disk = File.read('spec/examples/bigquery_schema.json') | ||
|
|
||
| output = JSON.parse(described_class.as_bigquery_schema) | ||
|
|
||
| expect(output).to be_present | ||
| expect(output).to match_array JSON.parse(bq_schema_on_disk) | ||
| end | ||
| end | ||
| end |
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
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,106 @@ | ||
| [ | ||
| { | ||
| "mode": "REQUIRED", | ||
| "name": "occurred_at", | ||
| "type": "TIMESTAMP" | ||
| }, | ||
| { | ||
| "mode": "REQUIRED", | ||
| "name": "event_type", | ||
| "type": "STRING" | ||
| }, | ||
| { | ||
| "mode": "REQUIRED", | ||
| "name": "environment", | ||
| "type": "STRING" | ||
| }, | ||
| { | ||
| "mode": "NULLABLE", | ||
| "name": "namespace", | ||
| "type": "STRING" | ||
| }, | ||
| { | ||
| "mode": "NULLABLE", | ||
| "name": "user_id", | ||
| "type": "STRING" | ||
| }, | ||
| { | ||
| "mode": "NULLABLE", | ||
| "name": "request_uuid", | ||
| "type": "STRING" | ||
| }, | ||
| { | ||
| "mode": "NULLABLE", | ||
| "name": "request_method", | ||
| "type": "STRING" | ||
| }, | ||
| { | ||
| "mode": "NULLABLE", | ||
| "name": "request_path", | ||
| "type": "STRING" | ||
| }, | ||
| { | ||
| "mode": "NULLABLE", | ||
| "name": "request_user_agent", | ||
| "type": "STRING" | ||
| }, | ||
| { | ||
| "mode": "NULLABLE", | ||
| "name": "request_referer", | ||
| "type": "STRING" | ||
| }, | ||
| { | ||
| "fields": [ | ||
| { | ||
| "mode": "REQUIRED", | ||
| "name": "key", | ||
| "type": "STRING" | ||
| }, | ||
| { | ||
| "mode": "REPEATED", | ||
| "name": "value", | ||
| "type": "STRING" | ||
| } | ||
| ], | ||
| "mode": "REPEATED", | ||
| "name": "request_query", | ||
| "type": "RECORD" | ||
| }, | ||
| { | ||
| "mode": "NULLABLE", | ||
| "name": "response_content_type", | ||
| "type": "STRING" | ||
| }, | ||
| { | ||
| "mode": "NULLABLE", | ||
| "name": "response_status", | ||
| "type": "STRING" | ||
| }, | ||
| { | ||
| "fields": [ | ||
| { | ||
| "mode": "REQUIRED", | ||
| "name": "key", | ||
| "type": "STRING" | ||
| }, | ||
| { | ||
| "mode": "REPEATED", | ||
| "name": "value", | ||
| "type": "STRING" | ||
| } | ||
| ], | ||
| "mode": "REPEATED", | ||
| "name": "data", | ||
| "type": "RECORD" | ||
| }, | ||
| { | ||
| "mode": "NULLABLE", | ||
| "name": "entity_table_name", | ||
| "type": "STRING" | ||
| }, | ||
| { | ||
| "mode": "NULLABLE", | ||
| "name": "anonymised_user_agent_and_ip", | ||
| "type": "STRING" | ||
| } | ||
| ] |
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