Revert "chore: clean out unused "bases" and utils (#53234)"

This reverts commit 4dec57a.

.github/labeler.yml

@@ -14,3 +14,7 @@ area/documentation:
 CDK:
   - airbyte-cdk/*
   - airbyte-cdk/**/*
+
+normalization:
+  - airbyte-integrations/bases/base-normalization/*
+  - airbyte-integrations/bases/base-normalization/**/*

.pre-commit-config.yaml

@@ -6,6 +6,8 @@ exclude: |
     ^.*?/node_modules/.*$|
 
     ^.*?/charts/.*$|
+    ^airbyte-integrations/bases/base-normalization/.*$|
+    ^.*?/normalization_test_output/.*$|
 
     ^.*?/pnpm-lock\.yaml$|
     ^.*?/source-amplitude/unit_tests/api_data/zipped\.json$|

airbyte-integrations/bases/base-java/.dockerignore

@@ -0,0 +1,5 @@
+*
+!Dockerfile
+!build
+!javabase.sh
+!run_with_normalization.sh

airbyte-integrations/bases/base-java/Dockerfile

@@ -0,0 +1,34 @@
+### WARNING ###
+# The Java connector Dockerfiles will soon be deprecated.
+# This Dockerfile is not used to build the connector image we publish to DockerHub.
+# The new logic to build the connector image is declared with Dagger here:
+# https://github.com/airbytehq/airbyte/blob/master/tools/ci_connector_ops/ci_connector_ops/pipelines/actions/environments.py#L649
+
+# If you need to add a custom logic to build your connector image, you can do it by adding a finalize_build.sh or finalize_build.py script in the connector folder.
+# Please reach out to the Connectors Operations team if you have any question.
+ARG JDK_VERSION=17.0.8
+FROM amazoncorretto:${JDK_VERSION}
+COPY --from=airbyte/integration-base:dev /airbyte /airbyte
+
+RUN yum update -y && yum install -y tar openssl && yum clean all
+
+WORKDIR /airbyte
+
+# Add the Datadog Java APM agent
+ADD https://dtdg.co/latest-java-tracer dd-java-agent.jar
+
+COPY javabase.sh .
+COPY run_with_normalization.sh .
+
+# airbyte base commands
+ENV AIRBYTE_SPEC_CMD "/airbyte/javabase.sh --spec"
+ENV AIRBYTE_CHECK_CMD "/airbyte/javabase.sh --check"
+ENV AIRBYTE_DISCOVER_CMD "/airbyte/javabase.sh --discover"
+ENV AIRBYTE_READ_CMD "/airbyte/javabase.sh --read"
+ENV AIRBYTE_WRITE_CMD "/airbyte/javabase.sh --write"
+
+ENV AIRBYTE_ENTRYPOINT "/airbyte/base.sh"
+ENTRYPOINT ["/airbyte/base.sh"]
+
+LABEL io.airbyte.version=0.1.2
+LABEL io.airbyte.name=airbyte/integration-base-java

airbyte-integrations/bases/base-java/build.gradle

@@ -0,0 +1,3 @@
+plugins {
+    id 'airbyte-docker-legacy'
+}

airbyte-integrations/bases/base-java/javabase.sh

@@ -0,0 +1,33 @@
+#!/usr/bin/env bash
+
+set -e
+
+# if IS_CAPTURE_HEAP_DUMP_ON_ERROR is set to true, then will capture Heap dump on OutOfMemory error
+if [[ $IS_CAPTURE_HEAP_DUMP_ON_ERROR = true ]]; then
+
+  arrayOfSupportedConnectors=("source-postgres" "source-mssql" "source-mysql" )
+
+  # The heap dump would be captured only in case when java-based connector fails with OutOfMemory error
+  if [[ " ${arrayOfSupportedConnectors[*]} " =~ " $APPLICATION " ]]; then
+      JAVA_OPTS=$JAVA_OPTS" -XX:+HeapDumpOnOutOfMemoryError -XX:HeapDumpPath=/data/dump.hprof"
+      export JAVA_OPTS
+      echo "Added JAVA_OPTS=$JAVA_OPTS"
+      echo "APPLICATION=$APPLICATION"
+  fi
+fi
+#30781 - Allocate 32KB for log4j appender buffer to ensure that each line is logged in a single println
+JAVA_OPTS=$JAVA_OPTS" -Dlog4j.encoder.byteBufferSize=32768 -Dlog4j2.configurationFile=log4j2.xml"
+#needed because we make ThreadLocal.get(Thread) accessible in IntegrationRunner.stopOrphanedThreads
+JAVA_OPTS=$JAVA_OPTS" --add-opens=java.base/java.lang=ALL-UNNAMED"
+# tell jooq to be quiet (https://stackoverflow.com/questions/28272284/how-to-disable-jooqs-self-ad-message-in-3-4)
+JAVA_OPTS=$JAVA_OPTS" -Dorg.jooq.no-logo=true -Dorg.jooq.no-tips=true"
+export JAVA_OPTS
+
+# Wrap run script in a script so that we can lazy evaluate the value of APPLICATION. APPLICATION is
+# set by the dockerfile that inherits base-java, so it cannot be evaluated when base-java is built.
+# We also need to make sure that stdin of the script is piped to the stdin of the java application.
+if [[ $A = --write ]]; then
+  cat <&0 | /airbyte/bin/"$APPLICATION" "$@"
+else
+  /airbyte/bin/"$APPLICATION" "$@"
+fi

airbyte-integrations/bases/base-java/run_with_normalization.sh

@@ -0,0 +1,61 @@
+#!/bin/bash
+# Intentionally no set -e, because we want to run normalization even if the destination fails
+set -o pipefail
+
+/airbyte/base.sh $@
+destination_exit_code=$?
+echo '{"type": "LOG","log":{"level":"INFO","message":"Destination process done (exit code '"$destination_exit_code"')"}}'
+
+# store original args
+args=$@
+
+while [ $# -ne 0 ]; do
+  case "$1" in
+  --config)
+    CONFIG_FILE="$2"
+    shift 2
+    ;;
+  *)
+    # move on
+    shift
+    ;;
+  esac
+done
+
+# restore original args after shifts
+set -- $args
+
+USE_1S1T_FORMAT="false"
+if [[ -s "$CONFIG_FILE" ]]; then
+  USE_1S1T_FORMAT=$(jq -r '.use_1s1t_format' "$CONFIG_FILE")
+fi
+
+if test "$1" != 'write'
+then
+  normalization_exit_code=0
+elif test "$NORMALIZATION_TECHNIQUE" = 'LEGACY' && test "$USE_1S1T_FORMAT" != "true"
+then
+  echo '{"type": "LOG","log":{"level":"INFO","message":"Starting in-connector normalization"}}'
+  # Normalization tries to create this file from the connector config and crashes if it already exists
+  # so just nuke it and let normalization recreate it.
+  # Use -f to avoid error if it doesn't exist, since it's only created for certain SSL modes.
+  rm -f ca.crt
+  # the args in a write command are `write --catalog foo.json --config bar.json`
+  # so if we remove the `write`, we can just pass the rest directly into normalization
+  /airbyte/entrypoint.sh run ${@:2} --integration-type $AIRBYTE_NORMALIZATION_INTEGRATION | java -cp "/airbyte/lib/*" io.airbyte.cdk.integrations.destination.normalization.NormalizationLogParser
+  normalization_exit_code=$?
+  echo '{"type": "LOG","log":{"level":"INFO","message":"In-connector normalization done (exit code '"$normalization_exit_code"')"}}'
+else
+  echo '{"type": "LOG","log":{"level":"INFO","message":"Skipping in-connector normalization"}}'
+  normalization_exit_code=0
+fi
+
+if test $destination_exit_code -ne 0
+then
+  exit $destination_exit_code
+elif test $normalization_exit_code -ne 0
+then
+  exit $normalization_exit_code
+else
+  exit 0
+fi

airbyte-integrations/bases/base-normalization/.dockerignore

@@ -0,0 +1,13 @@
+*
+!Dockerfile
+!entrypoint.sh
+!build/sshtunneling.sh
+!setup.py
+!normalization
+!dbt-project-template
+!dbt-project-template-mssql
+!dbt-project-template-mysql
+!dbt-project-template-oracle
+!dbt-project-template-clickhouse
+!dbt-project-template-snowflake
+!dbt-project-template-redshift

airbyte-integrations/bases/base-normalization/.gitignore

@@ -0,0 +1,51 @@
+build/
+logs/
+dbt-project-template/models/generated/
+dbt-project-template/test_output.log
+dbt_modules/
+secrets/
+dist/
+
+integration_tests/normalization_test_output/*/*/macros
+integration_tests/normalization_test_output/*/*/tests
+integration_tests/normalization_test_output/**/*.json
+integration_tests/normalization_test_output/**/*.log
+integration_tests/normalization_test_output/**/*.md
+integration_tests/normalization_test_output/**/*.sql
+integration_tests/normalization_test_output/**/*.yml
+!integration_tests/normalization_test_output/**/*dbt_project.yml
+!integration_tests/normalization_test_output/**/generated/sources.yml
+
+# We keep a minimal/restricted subset of sql files for all destinations to avoid noise in diff
+# Simple Streams
+!integration_tests/normalization_test_output/**/dedup_exchange_rate*.sql
+!integration_tests/normalization_test_output/**/DEDUP_EXCHANGE_RATE*.sql
+!integration_tests/normalization_test_output/**/exchange_rate.sql
+!integration_tests/normalization_test_output/**/EXCHANGE_RATE.sql
+!integration_tests/normalization_test_output/**/test_simple_streams/first_output/airbyte_views/**/multiple_column_names_conflicts_stg.sql
+# Nested Streams
+# Parent table
+!integration_tests/normalization_test_output/**/nested_stream_with*_names_ab*.sql
+!integration_tests/normalization_test_output/**/nested_stream_with*_names_scd.sql
+!integration_tests/normalization_test_output/**/nested_stream_with*_names.sql
+!integration_tests/normalization_test_output/**/NESTED_STREAM_WITH*_NAMES_AB*.sql
+!integration_tests/normalization_test_output/**/NESTED_STREAM_WITH*_NAMES_SCD.sql
+!integration_tests/normalization_test_output/**/NESTED_STREAM_WITH*_NAMES.sql
+# Nested table
+!integration_tests/normalization_test_output/**/nested_stream_with_*_partition_ab1.sql
+!integration_tests/normalization_test_output/**/nested_stream_with_*_data_ab1.sql
+!integration_tests/normalization_test_output/**/nested_stream_with*_partition_scd.sql
+!integration_tests/normalization_test_output/**/nested_stream_with*_data_scd.sql
+!integration_tests/normalization_test_output/**/nested_stream_with*_partition.sql
+!integration_tests/normalization_test_output/**/nested_stream_with*_data.sql
+!integration_tests/normalization_test_output/**/NESTED_STREAM_WITH_*_PARTITION_AB1.sql
+!integration_tests/normalization_test_output/**/NESTED_STREAM_WITH_*_DATA_AB1.sql
+!integration_tests/normalization_test_output/**/NESTED_STREAM_WITH*_PARTITION_SCD.sql
+!integration_tests/normalization_test_output/**/NESTED_STREAM_WITH*_DATA_SCD.sql
+!integration_tests/normalization_test_output/**/NESTED_STREAM_WITH*_PARTITION.sql
+!integration_tests/normalization_test_output/**/NESTED_STREAM_WITH*_DATA.sql
+
+# but we keep all sql files for Postgres
+!integration_tests/normalization_test_output/postgres/**/*.sql
+integration_tests/normalization_test_output/postgres/**/dbt_data_tests
+integration_tests/normalization_test_output/postgres/**/dbt_schema_tests

airbyte-integrations/bases/base-normalization/Dockerfile

@@ -0,0 +1,37 @@
+FROM fishtownanalytics/dbt:1.0.0
+COPY --from=airbyte/base-airbyte-protocol-python:0.1.1 /airbyte /airbyte
+
+# Install SSH Tunneling dependencies
+RUN apt-get update && apt-get install -y jq sshpass
+
+WORKDIR /airbyte
+COPY entrypoint.sh .
+COPY build/sshtunneling.sh .
+
+WORKDIR /airbyte/normalization_code
+COPY normalization ./normalization
+COPY setup.py .
+COPY dbt-project-template/ ./dbt-template/
+
+# Install python dependencies
+WORKDIR /airbyte/base_python_structs
+
+# workaround for https://github.com/yaml/pyyaml/issues/601
+# this should be fixed in the airbyte/base-airbyte-protocol-python image
+RUN pip install "Cython<3.0" "pyyaml==5.4" --no-build-isolation
+
+RUN pip install .
+
+WORKDIR /airbyte/normalization_code
+RUN pip install .
+
+WORKDIR /airbyte/normalization_code/dbt-template/
+# Download external dbt dependencies
+RUN dbt deps
+
+WORKDIR /airbyte
+ENV AIRBYTE_ENTRYPOINT "/airbyte/entrypoint.sh"
+ENTRYPOINT ["/airbyte/entrypoint.sh"]
+
+LABEL io.airbyte.version=0.4.3
+LABEL io.airbyte.name=airbyte/normalization

airbyte-integrations/bases/base-normalization/build.gradle

@@ -0,0 +1,57 @@
+plugins {
+    id 'airbyte-docker-legacy'
+    id 'airbyte-python'
+}
+
+dependencies {
+    testFixtures(project(':airbyte-cdk:java:airbyte-cdk:airbyte-cdk-dependencies'))
+}
+
+// we need to access the sshtunneling script from airbyte-workers for ssh support
+def copySshScript = tasks.register('copySshScript', Copy) {
+    from "${project(':airbyte-cdk:java:airbyte-cdk:airbyte-cdk-dependencies').buildDir}/resources/testFixtures"
+    into "${buildDir}"
+    include "sshtunneling.sh"
+}
+copySshScript.configure {
+    dependsOn project(':airbyte-cdk:java:airbyte-cdk:airbyte-cdk-dependencies').tasks.named('processTestFixturesResources')
+}
+
+// make sure the copy task above worked (if it fails, it fails silently annoyingly)
+def checkSshScriptCopy = tasks.register('checkSshScriptCopy') {
+    doFirst {
+        assert file("${buildDir}/sshtunneling.sh").exists() : "Copy of sshtunneling.sh failed."
+    }
+}
+checkSshScriptCopy.configure {
+    dependsOn copySshScript
+}
+
+def generate = tasks.register('generate')
+generate.configure {
+    dependsOn checkSshScriptCopy
+}
+
+tasks.named('check').configure {
+    dependsOn generate
+}
+
+tasks.named("jar").configure {
+    dependsOn copySshScript
+}
+
+[
+        'bigquery',
+        'mysql',
+        'postgres',
+        'redshift',
+        'snowflake',
+        'oracle',
+        'mssql',
+        'clickhouse',
+        'tidb',
+].each {destinationName ->
+    tasks.matching { it.name == 'integrationTestPython' }.configureEach {
+        dependsOn project(":airbyte-integrations:connectors:destination-$destinationName").tasks.named('assemble')
+    }
+}

airbyte-integrations/bases/base-normalization/clickhouse.Dockerfile

@@ -0,0 +1,36 @@
+FROM ghcr.io/dbt-labs/dbt-core:1.3.1
+COPY --from=airbyte/base-airbyte-protocol-python:0.1.1 /airbyte /airbyte
+
+# Install SSH Tunneling dependencies
+RUN apt-get update && apt-get install -y jq sshpass
+WORKDIR /airbyte
+COPY entrypoint.sh .
+COPY build/sshtunneling.sh .
+
+WORKDIR /airbyte/normalization_code
+COPY normalization ./normalization
+COPY setup.py .
+COPY dbt-project-template/ ./dbt-template/
+
+# Install python dependencies
+WORKDIR /airbyte/base_python_structs
+
+# workaround for https://github.com/yaml/pyyaml/issues/601
+# this should be fixed in the airbyte/base-airbyte-protocol-python image
+RUN pip install "Cython<3.0" "pyyaml==5.4" --no-build-isolation
+
+RUN pip install .
+
+WORKDIR /airbyte/normalization_code
+RUN pip install .
+
+WORKDIR /airbyte/normalization_code/dbt-template/
+RUN pip install "dbt-clickhouse>=1.4.0"
+# Download external dbt dependencies
+RUN dbt deps
+
+WORKDIR /airbyte
+ENV AIRBYTE_ENTRYPOINT "/airbyte/entrypoint.sh"
+ENTRYPOINT ["/airbyte/entrypoint.sh"]
+
+LABEL io.airbyte.name=airbyte/normalization-clickhouse