further cleanup

docker-compose.yml

@@ -1,5 +1,5 @@
 ---
-version: '3'
+version: '3.9'
 services:
   zookeeper:
     image: confluentinc/cp-zookeeper:${CONF_VER}
@@ -13,7 +13,7 @@ services:
       start_period: 15s
       interval: 5s
       timeout: 10s
-      retries: 10
+      retries: 30
     environment:
       ZOOKEEPER_CLIENT_PORT: 2181
       ZOOKEEPER_TICK_TIME: 2000
@@ -34,7 +34,7 @@ services:
       start_period: 15s
       interval: 5s
       timeout: 10s
-      retries: 20
+      retries: 30
     environment:
       KAFKA_BROKER_ID: 1
       KAFKA_ZOOKEEPER_CONNECT: 'zookeeper:2181'
@@ -67,18 +67,16 @@ services:
       - "8081:8081"
     healthcheck:
       test: nc -z localhost 8081 || exit -1
-      start_period: 15s
-      interval: 5s
-      timeout: 10s
-      retries: 10
+      start_period: 30s
+      interval: 20s
+      timeout: 60s
+      retries: 300
     environment:
       SCHEMA_REGISTRY_HOST_NAME: schema-registry
       SCHEMA_REGISTRY_KAFKASTORE_BOOTSTRAP_SERVERS: 'broker:29092'
       SCHEMA_REGISTRY_LISTENERS: http://0.0.0.0:8081
 
   connect:
-    # image: cnfldemos/cp-server-connect-datagen:0.5.0-6.2.0
-    # image: confluentinc/cp-server-connect:${CONF_VER}
     build:
       context: ./kafka-connect
       dockerfile: Dockerfile    
@@ -95,7 +93,7 @@ services:
       start_period: 15s
       interval: 5s
       timeout: 10s
-      retries: 10      
+      retries: 30      
     environment:
       CONNECT_BOOTSTRAP_SERVERS: 'broker:29092'
       CONNECT_REST_ADVERTISED_HOST_NAME: connect
@@ -130,7 +128,6 @@ services:
         condition: service_healthy
       connect:
         condition: service_healthy
-      # - ksqldb-server
     ports:
       - "9021:9021"
     healthcheck:
@@ -138,7 +135,7 @@ services:
       start_period: 15s
       interval: 5s
       timeout: 10s
-      retries: 10      
+      retries: 30      
     environment:
       CONTROL_CENTER_BOOTSTRAP_SERVERS: 'broker:29092'
       CONTROL_CENTER_CONNECT_CONNECT-DEFAULT_CLUSTER: 'http://connect:8083'
@@ -180,77 +177,24 @@ services:
       /usr/bin/mc policy set public minio/mastodon;
       exit 0;
       "
-  
-  # jupyter:
-  #   image: jupyter/scipy-notebook
-  #   ports:
-  #     - "8888:8888"
-  #   volumes:
-  #     - ./notebooks:/home/jovyan/
-  #   environment:
-  #     JUPYTER_ENABLE_LAB: "yes"
-  #     JUPYTER_RUNTIME_DIR: "/tmp"
-  #   command: "start-notebook.sh --NotebookApp.token='' --NotebookApp.password=''"
 
-
-
-  # ksqldb-server:
-  #   image: confluentinc/cp-ksqldb-server:${CONF_VER}
-  #   platform: linux/amd64
-  #   hostname: ksqldb-server
-  #   container_name: ksqldb-server
-  #   depends_on:
-  #     - broker
-  #     - connect
-  #   ports:
-  #     - "8088:8088"
-  #   environment:
-  #     KSQL_CONFIG_DIR: "/etc/ksql"
-  #     KSQL_BOOTSTRAP_SERVERS: "broker:29092"
-  #     KSQL_HOST_NAME: ksqldb-server
-  #     KSQL_LISTENERS: "http://0.0.0.0:8088"
-  #     KSQL_CACHE_MAX_BYTES_BUFFERING: 0
-  #     KSQL_KSQL_SCHEMA_REGISTRY_URL: "http://schema-registry:8081"
-  #     KSQL_PRODUCER_INTERCEPTOR_CLASSES: "io.confluent.monitoring.clients.interceptor.MonitoringProducerInterceptor"
-  #     KSQL_CONSUMER_INTERCEPTOR_CLASSES: "io.confluent.monitoring.clients.interceptor.MonitoringConsumerInterceptor"
-  #     KSQL_KSQL_CONNECT_URL: "http://connect:8083"
-  #     KSQL_KSQL_LOGGING_PROCESSING_TOPIC_REPLICATION_FACTOR: 1
-  #     KSQL_KSQL_LOGGING_PROCESSING_TOPIC_AUTO_CREATE: 'true'
-  #     KSQL_KSQL_LOGGING_PROCESSING_STREAM_AUTO_CREATE: 'true'
-
-  # ksqldb-cli:
-  #   image: confluentinc/cp-ksqldb-cli:${CONF_VER}
-  #   platform: linux/amd64
-  #   container_name: ksqldb-cli
-  #   depends_on:
-  #     - broker
-  #     - connect
-  #     - ksqldb-server
-  #   entrypoint: /bin/sh
-  #   tty: true
-
-
-  # elasticsearch:
-  #   image: docker.elastic.co/elasticsearch/elasticsearch:${ELST_VER}
-  #   platform: linux/amd64
-  #   container_name: elasticsearch
-  #   ports:
-  #     - 9200:9200
-  #   environment:
-  #     xpack.security.enabled: "false"
-  #     ES_JAVA_OPTS: "-Xms1g -Xmx1g"
-  #     discovery.type: "single-node"
-
-
-  # kibana:
-  #   image: docker.elastic.co/kibana/kibana:${ELST_VER}
-  #   platform: linux/amd64
-  #   container_name: kibana
-  #   hostname: kibana
-  #   depends_on:
-  #     - elasticsearch
-  #   ports:
-  #     - 5601:5601
-  #   environment:
-  #     xpack.security.enabled: "false"
-  #     discovery.type: "single-node"
+  jupyter:
+    image: jupyter/scipy-notebook
+    ports:
+      - "8888:8888"
+    healthcheck:
+      test: nc -z localhost 8888 || exit -1
+      start_period: 15s
+      interval: 5s
+      timeout: 10s
+      retries: 10
+    volumes:
+      - ./notebooks:/home/jovyan/
+    user: root
+    environment:
+      JUPYTER_ENABLE_LAB: "yes"
+      JUPYTER_RUNTIME_DIR: "/tmp"
+      NB_USER: simonaubury
+      CHOWN_HOME: 'yes'
+      CHOWN_HOME_OPTS: '-R' 
+    command: "start-notebook.sh --allow-root --ip=0.0.0.0  --NotebookApp.token='' --NotebookApp.password=''"

duckdb/go.sql

@@ -87,6 +87,22 @@ select
 , mastodon_text
 from read_parquet('20230213/mastodon-topic/partition=0/*.parquet');
 
+insert into toots
+select
+  m_id          
+, created_at    
+, created_at_str
+, app           
+, url           
+, base_url      
+, language      
+, favourites    
+, username      
+, bot           
+, tags          
+, characters    
+, mastodon_text
+from read_parquet('20230216/mastodon-topic/partition=0/*.parquet');
 
 
 create table all_toots

kafka-connect/Dockerfile

@@ -1,6 +1,3 @@
-# FROM confluentinc/cp-server-connect-base:7.3.1
 FROM confluentinc/cp-server-connect:7.1.0
 
 RUN   confluent-hub install --no-prompt confluentinc/kafka-connect-s3:10.3.0
-
-# ENTRYPOINT ["tail", "-f", "/dev/null"]