commit-data-engineering-test

airflow-docker/.env

@@ -0,0 +1 @@
+AIRFLOW_UID=1000

airflow-docker/dags/dag_test_raizen.py

@@ -0,0 +1,37 @@
+from textwrap import dedent
+
+from airflow import DAG
+
+from airflow.operators.python import PythonOperator
+from airflow.utils.dates import days_ago
+
+from airflow import DAG
+from airflow.operators.python import PythonOperator, BranchPythonOperator
+from airflow.operators.bash import BashOperator
+from datetime import datetime, timedelta
+
+default_args = {
+    'owner': 'airflow',
+}
+
+with DAG(
+    'dag_test_raizen',  #nome da dag
+    default_args=default_args,
+    description='Test Raizen',
+    schedule_interval=None,
+    start_date=days_ago(2),
+    tags=[],
+) as dag:
+
+#Function
+    task_extractor = BashOperator( 
+      task_id='extracao', 
+      bash_command='python c:/airflow-docker/extractor/main.py', 
+      dag=dag,
+      )
+    task_transformer = BashOperator( 
+      task_id='transformacao', 
+      bash_command='python c:/airflow-docker/transformer/main.py', 
+      dag=dag,
+      )
+    task_extractor >> task_transformer

airflow-docker/docker-compose.yaml

@@ -0,0 +1,246 @@
+---
+version: '3'
+x-airflow-common:
+  &airflow-common
+  # In order to add custom dependencies or upgrade provider packages you can use your extended image.
+  # Comment the image line, place your Dockerfile in the directory where you placed the docker-compose.yaml
+  # and uncomment the "build" line below, Then run `docker-compose build` to build the images.
+  image: ${AIRFLOW_IMAGE_NAME:-apache/airflow:2.4.3}
+  # build: .
+  environment:
+    &airflow-common-env
+    AIRFLOW__CORE__EXECUTOR: CeleryExecutor
+    AIRFLOW__DATABASE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow
+    # For backward compatibility, with Airflow <2.3
+    AIRFLOW__CORE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow
+    AIRFLOW__CELERY__RESULT_BACKEND: db+postgresql://airflow:airflow@postgres/airflow
+    AIRFLOW__CELERY__BROKER_URL: redis://:@redis:6379/0
+    AIRFLOW__CORE__FERNET_KEY: ''
+    AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION: 'true'
+    AIRFLOW__CORE__LOAD_EXAMPLES: 'true'
+    AIRFLOW__API__AUTH_BACKENDS: 'airflow.api.auth.backend.basic_auth'
+    _PIP_ADDITIONAL_REQUIREMENTS: ${_PIP_ADDITIONAL_REQUIREMENTS:-}
+  volumes:
+    - ./dags:/opt/airflow/dags
+    - ./logs:/opt/airflow/logs
+    - ./plugins:/opt/airflow/plugins
+    - ./entrada:/opt/airflow/entrada
+    - ./saida:/opt/airflow/saida
+  user: "${AIRFLOW_UID:-50000}:0"
+  depends_on:
+    &airflow-common-depends-on
+    redis:
+      condition: service_healthy
+    postgres:
+      condition: service_healthy
+
+services:
+  postgres:
+    image: postgres:13
+    environment:
+      POSTGRES_USER: airflow
+      POSTGRES_PASSWORD: airflow
+      POSTGRES_DB: airflow
+    volumes:
+      - postgres-db-volume:/var/lib/postgresql/data
+    healthcheck:
+      test: ["CMD", "pg_isready", "-U", "airflow"]
+      interval: 5s
+      retries: 5
+    restart: always
+
+  redis:
+    image: redis:latest
+    expose:
+      - 6379
+    healthcheck:
+      test: ["CMD", "redis-cli", "ping"]
+      interval: 5s
+      timeout: 30s
+      retries: 50
+    restart: always
+
+  airflow-webserver:
+    <<: *airflow-common
+    command: webserver
+    ports:
+      - 8080:8080
+    healthcheck:
+      test: ["CMD", "curl", "--fail", "http://localhost:8080/health"]
+      interval: 10s
+      timeout: 10s
+      retries: 5
+    restart: always
+    volumes:
+      - ../extractor:/extractor:ro
+      - ../transformer:/transfromer:ro
+      - ../entrada:/entrada
+      - ../saida:/saida
+    depends_on:
+      <<: *airflow-common-depends-on
+      airflow-init:
+        condition: service_completed_successfully
+
+  airflow-scheduler:
+    <<: *airflow-common
+    command: scheduler
+    healthcheck:
+      test: ["CMD-SHELL", 'airflow jobs check --job-type SchedulerJob --hostname "$${HOSTNAME}"']
+      interval: 10s
+      timeout: 10s
+      retries: 5
+    restart: always
+    depends_on:
+      <<: *airflow-common-depends-on
+      airflow-init:
+        condition: service_completed_successfully
+
+  airflow-worker:
+    <<: *airflow-common
+    command: celery worker
+    healthcheck:
+      test:
+        - "CMD-SHELL"
+        - 'celery --app airflow.executors.celery_executor.app inspect ping -d "celery@$${HOSTNAME}"'
+      interval: 10s
+      timeout: 10s
+      retries: 5
+    environment:
+      <<: *airflow-common-env
+      # Required to handle warm shutdown of the celery workers properly
+      # See https://airflow.apache.org/docs/docker-stack/entrypoint.html#signal-propagation
+      DUMB_INIT_SETSID: "0"
+    restart: always
+    depends_on:
+      <<: *airflow-common-depends-on
+      airflow-init:
+        condition: service_completed_successfully
+
+  airflow-triggerer:
+    <<: *airflow-common
+    command: triggerer
+    healthcheck:
+      test: ["CMD-SHELL", 'airflow jobs check --job-type TriggererJob --hostname "$${HOSTNAME}"']
+      interval: 10s
+      timeout: 10s
+      retries: 5
+    restart: always
+    depends_on:
+      <<: *airflow-common-depends-on
+      airflow-init:
+        condition: service_completed_successfully
+
+  airflow-init:
+    <<: *airflow-common
+    entrypoint: /bin/bash
+    # yamllint disable rule:line-length
+    command:
+      - -c
+      - |
+        function ver() {
+          printf "%04d%04d%04d%04d" $${1//./ }
+        }
+        airflow_version=$$(AIRFLOW__LOGGING__LOGGING_LEVEL=INFO && gosu airflow airflow version)
+        airflow_version_comparable=$$(ver $${airflow_version})
+        min_airflow_version=2.2.0
+        min_airflow_version_comparable=$$(ver $${min_airflow_version})
+        if (( airflow_version_comparable < min_airflow_version_comparable )); then
+          echo
+          echo -e "\033[1;31mERROR!!!: Too old Airflow version $${airflow_version}!\e[0m"
+          echo "The minimum Airflow version supported: $${min_airflow_version}. Only use this or higher!"
+          echo
+          exit 1
+        fi
+        if [[ -z "${AIRFLOW_UID}" ]]; then
+          echo
+          echo -e "\033[1;33mWARNING!!!: AIRFLOW_UID not set!\e[0m"
+          echo "If you are on Linux, you SHOULD follow the instructions below to set "
+          echo "AIRFLOW_UID environment variable, otherwise files will be owned by root."
+          echo "For other operating systems you can get rid of the warning with manually created .env file:"
+          echo "    See: https://airflow.apache.org/docs/apache-airflow/stable/howto/docker-compose/index.html#setting-the-right-airflow-user"
+          echo
+        fi
+        one_meg=1048576
+        mem_available=$$(($$(getconf _PHYS_PAGES) * $$(getconf PAGE_SIZE) / one_meg))
+        cpus_available=$$(grep -cE 'cpu[0-9]+' /proc/stat)
+        disk_available=$$(df / | tail -1 | awk '{print $$4}')
+        warning_resources="false"
+        if (( mem_available < 4000 )) ; then
+          echo
+          echo -e "\033[1;33mWARNING!!!: Not enough memory available for Docker.\e[0m"
+          echo "At least 4GB of memory required. You have $$(numfmt --to iec $$((mem_available * one_meg)))"
+          echo
+          warning_resources="true"
+        fi
+        if (( cpus_available < 2 )); then
+          echo
+          echo -e "\033[1;33mWARNING!!!: Not enough CPUS available for Docker.\e[0m"
+          echo "At least 2 CPUs recommended. You have $${cpus_available}"
+          echo
+          warning_resources="true"
+        fi
+        if (( disk_available < one_meg * 10 )); then
+          echo
+          echo -e "\033[1;33mWARNING!!!: Not enough Disk space available for Docker.\e[0m"
+          echo "At least 10 GBs recommended. You have $$(numfmt --to iec $$((disk_available * 1024 )))"
+          echo
+          warning_resources="true"
+        fi
+        if [[ $${warning_resources} == "true" ]]; then
+          echo
+          echo -e "\033[1;33mWARNING!!!: You have not enough resources to run Airflow (see above)!\e[0m"
+          echo "Please follow the instructions to increase amount of resources available:"
+          echo "   https://airflow.apache.org/docs/apache-airflow/stable/howto/docker-compose/index.html#before-you-begin"
+          echo
+        fi
+        mkdir -p /sources/logs /sources/dags /sources/plugins
+        chown -R "${AIRFLOW_UID}:0" /sources/{logs,dags,plugins}
+        exec /entrypoint airflow version
+    # yamllint enable rule:line-length
+    environment:
+      <<: *airflow-common-env
+      _AIRFLOW_DB_UPGRADE: 'true'
+      _AIRFLOW_WWW_USER_CREATE: 'true'
+      _AIRFLOW_WWW_USER_USERNAME: ${_AIRFLOW_WWW_USER_USERNAME:-airflow}
+      _AIRFLOW_WWW_USER_PASSWORD: ${_AIRFLOW_WWW_USER_PASSWORD:-airflow}
+      _PIP_ADDITIONAL_REQUIREMENTS: ''
+    user: "0:0"
+    volumes:
+      - .:/sources
+
+  airflow-cli:
+    <<: *airflow-common
+    profiles:
+      - debug
+    environment:
+      <<: *airflow-common-env
+      CONNECTION_CHECK_MAX_COUNT: "0"
+    # Workaround for entrypoint issue. See: https://github.com/apache/airflow/issues/16252
+    command:
+      - bash
+      - -c
+      - airflow
+
+  # You can enable flower by adding "--profile flower" option e.g. docker-compose --profile flower up
+  # or by explicitly targeted on the command line e.g. docker-compose up flower.
+  # See: https://docs.docker.com/compose/profiles/
+  flower:
+    <<: *airflow-common
+    command: celery flower
+    profiles:
+      - flower
+    ports:
+      - 5555:5555
+    healthcheck:
+      test: ["CMD", "curl", "--fail", "http://localhost:5555/"]
+      interval: 10s
+      timeout: 10s
+      retries: 5
+    restart: always
+    depends_on:
+      <<: *airflow-common-depends-on
+      airflow-init:
+        condition: service_completed_successfully
+
+volumes:
+  postgres-db-volume:

airflow-docker/entrada/[Content_Types].xml

@@ -0,0 +1,2 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types"><Default Extension="bin" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.printerSettings"/><Default Extension="png" ContentType="image/png"/><Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/><Default Extension="xml" ContentType="application/xml"/><Override PartName="/xl/workbook.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet.main+xml"/><Override PartName="/xl/worksheets/sheet1.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.worksheet+xml"/><Override PartName="/xl/pivotCache/pivotCacheDefinition1.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotCacheDefinition+xml"/><Override PartName="/xl/pivotCache/pivotCacheRecords1.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotCacheRecords+xml"/><Override PartName="/xl/pivotCache/pivotCacheDefinition2.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotCacheDefinition+xml"/><Override PartName="/xl/pivotCache/pivotCacheRecords2.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotCacheRecords+xml"/><Override PartName="/xl/pivotCache/pivotCacheDefinition3.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotCacheDefinition+xml"/><Override PartName="/xl/pivotCache/pivotCacheRecords3.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotCacheRecords+xml"/><Override PartName="/xl/pivotCache/pivotCacheDefinition4.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotCacheDefinition+xml"/><Override PartName="/xl/pivotCache/pivotCacheRecords4.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotCacheRecords+xml"/><Override PartName="/xl/pivotCache/pivotCacheDefinition5.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotCacheDefinition+xml"/><Override PartName="/xl/pivotCache/pivotCacheRecords5.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotCacheRecords+xml"/><Override PartName="/xl/pivotCache/pivotCacheDefinition6.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotCacheDefinition+xml"/><Override PartName="/xl/pivotCache/pivotCacheRecords6.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotCacheRecords+xml"/><Override PartName="/xl/theme/theme1.xml" ContentType="application/vnd.openxmlformats-officedocument.theme+xml"/><Override PartName="/xl/styles.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.styles+xml"/><Override PartName="/xl/sharedStrings.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.sharedStrings+xml"/><Override PartName="/xl/pivotTables/pivotTable1.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotTable+xml"/><Override PartName="/xl/pivotTables/pivotTable2.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotTable+xml"/><Override PartName="/xl/pivotTables/pivotTable3.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotTable+xml"/><Override PartName="/xl/pivotTables/pivotTable4.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotTable+xml"/><Override PartName="/xl/pivotTables/pivotTable5.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotTable+xml"/><Override PartName="/xl/pivotTables/pivotTable6.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotTable+xml"/><Override PartName="/xl/pivotTables/pivotTable7.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotTable+xml"/><Override PartName="/xl/pivotTables/pivotTable8.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotTable+xml"/><Override PartName="/xl/pivotTables/pivotTable9.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.pivotTable+xml"/><Override PartName="/xl/drawings/drawing1.xml" ContentType="application/vnd.openxmlformats-officedocument.drawing+xml"/><Override PartName="/xl/charts/chart1.xml" ContentType="application/vnd.openxmlformats-officedocument.drawingml.chart+xml"/><Override PartName="/xl/charts/chart2.xml" ContentType="application/vnd.openxmlformats-officedocument.drawingml.chart+xml"/><Override PartName="/xl/charts/chart3.xml" ContentType="application/vnd.openxmlformats-officedocument.drawingml.chart+xml"/><Override PartName="/xl/charts/chart4.xml" ContentType="application/vnd.openxmlformats-officedocument.drawingml.chart+xml"/><Override PartName="/xl/charts/chart5.xml" ContentType="application/vnd.openxmlformats-officedocument.drawingml.chart+xml"/><Override PartName="/xl/charts/chart6.xml" ContentType="application/vnd.openxmlformats-officedocument.drawingml.chart+xml"/><Override PartName="/xl/charts/chart7.xml" ContentType="application/vnd.openxmlformats-officedocument.drawingml.chart+xml"/><Override PartName="/xl/charts/chart8.xml" ContentType="application/vnd.openxmlformats-officedocument.drawingml.chart+xml"/><Override PartName="/xl/charts/chart9.xml" ContentType="application/vnd.openxmlformats-officedocument.drawingml.chart+xml"/><Override PartName="/xl/calcChain.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.calcChain+xml"/><Override PartName="/docProps/core.xml" ContentType="application/vnd.openxmlformats-package.core-properties+xml"/><Override PartName="/docProps/app.xml" ContentType="application/vnd.openxmlformats-officedocument.extended-properties+xml"/></Types>

airflow-docker/entrada/_rels/.rels

@@ -0,0 +1,2 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId3" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/extended-properties" Target="docProps/app.xml"/><Relationship Id="rId2" Type="http://schemas.openxmlformats.org/package/2006/relationships/metadata/core-properties" Target="docProps/core.xml"/><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="xl/workbook.xml"/></Relationships>

airflow-docker/entrada/docProps/app.xml

@@ -0,0 +1,2 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Properties xmlns="http://schemas.openxmlformats.org/officeDocument/2006/extended-properties" xmlns:vt="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes"><Application>Microsoft Excel</Application><DocSecurity>0</DocSecurity><ScaleCrop>false</ScaleCrop><HeadingPairs><vt:vector size="4" baseType="variant"><vt:variant><vt:lpstr>Planilhas</vt:lpstr></vt:variant><vt:variant><vt:i4>1</vt:i4></vt:variant><vt:variant><vt:lpstr>Intervalos Nomeados</vt:lpstr></vt:variant><vt:variant><vt:i4>1</vt:i4></vt:variant></vt:vector></HeadingPairs><TitlesOfParts><vt:vector size="2" baseType="lpstr"><vt:lpstr>Plan1</vt:lpstr><vt:lpstr>Plan1!OLE_LINK1</vt:lpstr></vt:vector></TitlesOfParts><Company>ANP</Company><LinksUpToDate>false</LinksUpToDate><SharedDoc>false</SharedDoc><HyperlinksChanged>false</HyperlinksChanged><AppVersion>16.0300</AppVersion></Properties>

airflow-docker/entrada/docProps/core.xml

@@ -0,0 +1,2 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<cp:coreProperties xmlns:cp="http://schemas.openxmlformats.org/package/2006/metadata/core-properties" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dcmitype="http://purl.org/dc/dcmitype/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><dc:creator>lrosas</dc:creator><cp:lastModifiedBy>Bruno Renzi Marques</cp:lastModifiedBy><dcterms:created xsi:type="dcterms:W3CDTF">2002-06-13T16:34:05Z</dcterms:created><dcterms:modified xsi:type="dcterms:W3CDTF">2022-09-07T03:42:19Z</dcterms:modified></cp:coreProperties>

airflow-docker/entrada/xl/_rels/workbook.xml.rels

@@ -0,0 +1,2 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId8" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/theme" Target="theme/theme1.xml"/><Relationship Id="rId3" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/pivotCacheDefinition" Target="pivotCache/pivotCacheDefinition2.xml"/><Relationship Id="rId7" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/pivotCacheDefinition" Target="pivotCache/pivotCacheDefinition6.xml"/><Relationship Id="rId2" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/pivotCacheDefinition" Target="pivotCache/pivotCacheDefinition1.xml"/><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/worksheet" Target="worksheets/sheet1.xml"/><Relationship Id="rId6" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/pivotCacheDefinition" Target="pivotCache/pivotCacheDefinition5.xml"/><Relationship Id="rId11" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/calcChain" Target="calcChain.xml"/><Relationship Id="rId5" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/pivotCacheDefinition" Target="pivotCache/pivotCacheDefinition4.xml"/><Relationship Id="rId10" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/sharedStrings" Target="sharedStrings.xml"/><Relationship Id="rId4" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/pivotCacheDefinition" Target="pivotCache/pivotCacheDefinition3.xml"/><Relationship Id="rId9" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles" Target="styles.xml"/></Relationships>