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

feat: add integrationdb ksql scripts #573

Merged
merged 1 commit into from
Nov 30, 2023
Merged
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
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
CREATE OR REPLACE STREAM IF NOT EXISTS MUNICIPALITY_SNAPSHOT_OSLO_STREAM_FLATTEN_GEOLOCATION
WITH (KAFKA_TOPIC='municipality.snapshot.oslo.flatten.geolocation', PARTITIONS=1, VALUE_FORMAT='JSON_SR', KEY_FORMAT='JSON_SR')
WITH (KAFKA_TOPIC='municipality.snapshot.oslo.flatten.geolocation', PARTITIONS=1, VALUE_FORMAT='JSON_SR', KEY_FORMAT='JSON_SR')
AS SELECT
CAST(REDUCE(SPLIT(URL_EXTRACT_PATH(MESSAGEKEY), '/'), '', (s,x) => x) AS INTEGER) msgkey,
IDENTIFICATOR->ID IDENTIFICATOR_ID,
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
CREATE SINK CONNECTOR `MunicipalityIntegrationDbConnector` with (
"topics"= 'municipality.snapshot.oslo.flatten.integrationdb',
"input.data.format"= 'JSON_SR',
"input.key.format"= 'JSON_SR',
"delete.enabled"= false,
"connector.class"= 'PostgresSink',
"name"= 'MunicipalityIntegrationDbConnector',
"kafka.auth.mode"= 'KAFKA_API_KEY',
"kafka.api.key"= '***', --clear value
"kafka.api.secret"= '***', --clear value
"connection.host"= '***', --clear value
"connection.port"= '5432',
"connection.user"= '***', --clear value
"connection.password"= '***', --clear value
"db.name"= 'postgres',
"ssl.mode"= 'require',
"insert.mode"= 'UPSERT',
"table.name.format"= 'Integration.Municipalities',
"table.types"= 'TABLE',
"db.timezone"= 'UTC',
"pk.mode"= 'record_key',
"pk.fields"= 'NisCode',
"auto.create"= false,
"auto.evolve"= false,
"quote.sql.identifiers"= 'ALWAYS',
"batch.sizes"= 3000,
"tasks.max"= 1
);
Original file line number Diff line number Diff line change
@@ -0,0 +1,30 @@
CREATE OR REPLACE STREAM IF NOT EXISTS MUNICIPALITY_SNAPSHOT_OSLO_STREAM_FLATTEN_INTEGRATIONDB
WITH (KAFKA_TOPIC='municipality.snapshot.oslo.flatten.integrationdb', PARTITIONS=1, VALUE_FORMAT='JSON_SR', KEY_FORMAT='JSON_SR')
AS SELECT
CAST(REDUCE(SPLIT(URL_EXTRACT_PATH(MESSAGEKEY), '/'), '', (s,x) => x) AS INTEGER) NisCode,

GEMEENTESTATUS as "Status",

CASE WHEN FILTER(OFFICIELETALEN, (TAAL) => (TAAL = 'nl'))[1] is not null THEN TRUE ELSE FALSE END as "OfficialLanguageDutch",
CASE WHEN FILTER(OFFICIELETALEN, (TAAL) => (TAAL = 'fr'))[1] is not null THEN TRUE ELSE FALSE END as "OfficialLanguageFrench",
CASE WHEN FILTER(OFFICIELETALEN, (TAAL) => (TAAL = 'de'))[1] is not null THEN TRUE ELSE FALSE END as "OfficialLanguageGerman",
CASE WHEN FILTER(OFFICIELETALEN, (TAAL) => (TAAL = 'en'))[1] is not null THEN TRUE ELSE FALSE END as "OfficialLanguageEnglish",

CASE WHEN FILTER(FACILITEITENTALEN, (TAAL) => (TAAL = 'nl'))[1] is not null THEN TRUE ELSE FALSE END as "FacilityLanguageDutch",
CASE WHEN FILTER(FACILITEITENTALEN, (TAAL) => (TAAL = 'fr'))[1] is not null THEN TRUE ELSE FALSE END as "FacilityLanguageFrench",
CASE WHEN FILTER(FACILITEITENTALEN, (TAAL) => (TAAL = 'de'))[1] is not null THEN TRUE ELSE FALSE END as "FacilityLanguageGerman",
CASE WHEN FILTER(FACILITEITENTALEN, (TAAL) => (TAAL = 'en'))[1] is not null THEN TRUE ELSE FALSE END as "FacilityLanguageEnglish",

FILTER(GEMEENTENAMEN, (X) => (X->TAAL = 'nl'))[1]->SPELLING as "NameDutch",
FILTER(GEMEENTENAMEN, (X) => (X->TAAL = 'fr'))[1]->SPELLING as "NameFrench",
FILTER(GEMEENTENAMEN, (X) => (X->TAAL = 'de'))[1]->SPELLING as "NameGerman",
FILTER(GEMEENTENAMEN, (X) => (X->TAAL = 'en'))[1]->SPELLING as "NameEnglish",

IDENTIFICATOR->ID as "PuriId",
IDENTIFICATOR->NAAMRUIMTE as "Namespace",
IDENTIFICATOR->VERSIEID as "VersionString",
PARSE_TIMESTAMP(IDENTIFICATOR->VERSIEID, 'yyyy-MM-dd''T''HH:mm:ssXXX', 'UTC') as "VersionTimestamp",
CASE WHEN IDENTIFICATOR->ID is null THEN TRUE ELSE FALSE END as "IsRemoved"

FROM MUNICIPALITY_SNAPSHOT_OSLO_STREAM
PARTITION BY CAST(REDUCE(SPLIT(URL_EXTRACT_PATH(MESSAGEKEY), '/'), '', (s,x) => x) AS INTEGER);
Loading