{"id":320222,"date":"2021-03-25T09:01:09","date_gmt":"2021-03-25T09:01:09","guid":{"rendered":"http:\/\/savepearlharbor.com\/?p=320222"},"modified":"-0001-11-30T00:00:00","modified_gmt":"-0001-11-29T21:00:00","slug":"","status":"publish","type":"post","link":"https:\/\/savepearlharbor.com\/?p=320222","title":{"rendered":"\u0423\u043c\u043d\u044b\u0435 \u043f\u043e\u0433\u043e\u0434\u043d\u044b\u0435 \u043f\u0440\u0438\u043b\u043e\u0436\u0435\u043d\u0438\u044f \u0441 Flink SQL"},"content":{"rendered":"\n
\n
<\/figcaption><\/figure>\n

\u0418\u043d\u043e\u0433\u0434\u0430 \u0442\u0440\u0435\u0431\u0443\u0435\u0442\u0441\u044f \u043f\u043e\u043b\u0443\u0447\u0430\u0442\u044c, \u043c\u0430\u0440\u0448\u0440\u0443\u0442\u0438\u0437\u0438\u0440\u043e\u0432\u0430\u0442\u044c, \u043f\u0440\u0435\u043e\u0431\u0440\u0430\u0437\u043e\u0432\u044b\u0432\u0430\u0442\u044c, \u0437\u0430\u043f\u0440\u0430\u0448\u0438\u0432\u0430\u0442\u044c \u0438 \u0430\u043d\u0430\u043b\u0438\u0437\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0432\u0441\u0435 \u0434\u0430\u043d\u043d\u044b\u0435 \u043e \u043f\u043e\u0433\u043e\u0434\u0435 \u0432 \u0421\u043e\u0435\u0434\u0438\u043d\u0435\u043d\u043d\u044b\u0445 \u0428\u0442\u0430\u0442\u0430\u0445 — \u043f\u043e \u043c\u0435\u0440\u0435 \u043f\u043e\u044f\u0432\u043b\u0435\u043d\u0438\u044f \u044d\u0442\u0438\u0445 \u0434\u0430\u043d\u043d\u044b\u0445. \u0421 FLaNK \u044d\u0442\u043e \u0434\u043e\u0432\u043e\u043b\u044c\u043d\u043e \u0442\u0440\u0438\u0432\u0438\u0430\u043b\u044c\u043d\u044b\u0439 \u043f\u0440\u043e\u0446\u0435\u0441\u0441. <\/p>\n

<\/figcaption><\/figure>\n
<\/figcaption><\/figure>\n
<\/figcaption><\/figure>\n

\u041e\u0442 Kafka \u0434\u043e Kudu, \u0434\u043b\u044f \u043b\u044e\u0431\u043e\u0439 \u0441\u0445\u0435\u043c\u044b \u0438 \u043b\u044e\u0431\u043e\u0433\u043e \u0442\u0438\u043f\u0430 \u0434\u0430\u043d\u043d\u044b\u0445, \u0431\u0435\u0437 \u043d\u0430\u043f\u0438\u0441\u0430\u043d\u0438\u044f \u043a\u043e\u0434\u0430 \u2013 \u043f\u043e\u0442\u0440\u0435\u0431\u0443\u0435\u0442\u0441\u044f \u0432\u0441\u0435\u0433\u043e \u0434\u0432\u0430 \u0448\u0430\u0433\u0430. <\/p>\n

<\/figcaption><\/figure>\n

\u0412\u043e\u0442 \u044d\u0442\u0438 \u0441\u0445\u0435\u043c\u044b: \u0438\u0445 \u043c\u043e\u0436\u043d\u043e \u0441\u043e\u0437\u0434\u0430\u0432\u0430\u0442\u044c, \u0440\u0435\u043a\u0434\u0430\u043a\u0442\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0438 \u0441\u0440\u0430\u0432\u043d\u0438\u0432\u0430\u0442\u044c. Schema Registry \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u0442 Swagger API, \u043f\u043e\u044d\u0442\u043e\u043c\u0443 \u043d\u0435 \u0431\u0443\u0434\u0435\u0442 \u043f\u0440\u043e\u0431\u043b\u0435\u043c \u0441 \u043d\u0430\u0441\u0442\u0440\u043e\u0439\u043a\u043e\u0439 CI\/CD & DevOps \u043f\u0430\u0439\u043f\u043b\u0430\u0439\u043d\u043e\u0432:<\/p>\n

<\/figcaption><\/figure>\n
<\/figcaption><\/figure>\n

\u041f\u0440\u043e\u0432\u0435\u0440\u043a\u0430 \u0434\u0430\u043d\u043d\u044b\u0445 \u043f\u043e \u0441\u0445\u0435\u043c\u0435 \u0441 \u0432\u0430\u0448\u0438\u043c \u0443\u0440\u043e\u0432\u043d\u0435\u043c \u0434\u043e\u043f\u0443\u0441\u043a\u0430. \u0415\u0441\u043b\u0438 \u0432\u044b \u0445\u043e\u0442\u0438\u0442\u0435, \u0447\u0442\u043e\u0431\u044b \u0431\u044b\u043b\u0438 \u0440\u0430\u0437\u0440\u0435\u0448\u0435\u043d\u044b \u0434\u043e\u043f\u043e\u043b\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0435 \u043f\u043e\u043b\u044f, \u0442\u043e \u0432\u044b \u044d\u0442\u043e \u043f\u043e\u043b\u0443\u0447\u0438\u0442\u0435. <\/p>\n

<\/figcaption><\/figure>\n

\u0414\u0430\u043b\u0435\u0435 \u044d\u0442\u0438 \u0434\u0430\u043d\u043d\u044b\u0435 \u0433\u043e\u0442\u043e\u0432\u044b \u043a \u0430\u043d\u0430\u043b\u0438\u0437\u0443, \u043d\u0430\u043f\u0440\u0438\u043c\u0435\u0440 \u0432 BI \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0435 Cloudera DataViz. <\/p>\n

<\/figcaption><\/figure>\n

\u0411\u044b\u0441\u0442\u0440\u043e \u0430\u043d\u0430\u043b\u0438\u0437\u0438\u0440\u0443\u0439\u0442\u0435 \u0441\u0432\u043e\u0438 \u0434\u0430\u043d\u043d\u044b\u0435 \u0432 Apache Kudu \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e Apache Hue \u0438 Apache Impala.<\/p>\n

<\/figcaption><\/figure>\n

\u0414\u0430\u0432\u0430\u0439\u0442\u0435 \u0432\u043e\u0437\u044c\u043c\u0435\u043c \u0434\u0430\u043d\u043d\u044b\u0435 \u0432\u0441\u0435\u0445 \u043c\u0435\u0442\u0435\u043e\u0441\u0442\u0430\u043d\u0446\u0438\u0439 \u0421\u0428\u0410, \u0434\u0430\u0436\u0435 \u0435\u0441\u043b\u0438 \u043e\u043d\u0438 \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u044f\u044e\u0442 \u0441\u043e\u0431\u043e\u0439 \u0437\u0430\u0430\u0440\u0445\u0438\u0432\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u044b\u0439 \u043a\u0430\u0442\u0430\u043b\u043e\u0433 \u0441 \u043c\u043d\u043e\u0436\u0435\u0441\u0442\u0432\u043e\u043c \u0444\u0430\u0439\u043b\u043e\u0432 XML. <\/p>\n

<\/figcaption><\/figure>\n

NiFi \u0444\u043b\u043e\u0443 \u0441\u043e\u0441\u0442\u043e\u0438\u0442 \u0438\u0437 \u0441\u043b\u0435\u0434\u0443\u044e\u0449\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432:<\/p>\n

    \n
  1. \n

    GenerateFlowFile — <\/strong>\u0438\u043c\u043e\u0440\u0442 \u043f\u0435\u0440\u0435\u043e\u0434\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043e\u0431\u043d\u043e\u0432\u043b\u0435\u043d\u0438\u0439 \u043e \u043f\u043e\u0433\u043e\u0434\u0435 \u043e\u0442 NOAA<\/p>\n<\/li>\n

  2. \n

    InvokeHTTP — <\/strong>\u0437\u0430\u0433\u0440\u0443\u0437\u043a\u0430 \u0434\u0430\u043d\u043d\u044b\u0445 \u043e \u043f\u043e\u0433\u043e\u0434\u0435 \u0432 ZIP \u0430\u0440\u0445\u0438\u0432<\/p>\n<\/li>\n

  3. \n

    CompressContent — <\/strong>\u0434\u043a\u043e\u043c\u043f\u0440\u0435\u0441\u0441\u0438\u044f ZIP<\/p>\n<\/li>\n

  4. \n

    UnpackContent — <\/strong>\u044d\u043a\u0441\u0442\u0440\u0430\u043a\u0442 \u0444\u0430\u0439\u043b\u043e\u0432 \u0438\u0437 ZIP \u0430\u0440\u0445\u0438\u0432\u0430<\/p>\n<\/li>\n

  5. \n

    *RouteOnAttribute — <\/strong>\u0444\u0438\u043b\u044c\u0442\u0440\u0430\u0446\u0438\u044f \u0442\u043e\u043b\u044c\u043a\u043e \u043f\u043e \u0430\u044d\u0440\u043e\u043f\u043e\u0440\u0442\u0430\u043c (${filename:startsWith(‘K’)}). \u043e\u043f\u0446\u0438\u043e\u043d\u0430\u043b\u044c\u043d\u043e<\/strong>.<\/p>\n<\/li>\n

  6. \n

    *QueryRecord<\/strong> — XMLReader \u0432 JsonRecordSetWriter.   Query<\/strong>:  SELECT * FROM FLOWFILE WHERE NOT location LIKE ‘%Unknown%’.  \u041d\u0443\u0436\u043d\u043e \u0434\u043b\u044f \u0443\u0434\u0430\u043b\u0435\u043d\u0438\u044f \u043d\u0435\u0438\u0434\u0435\u043d\u0442\u0438\u0444\u0438\u0446\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u044b\u0445 \u043b\u043e\u043a\u0430\u0446\u0438\u0439.  \u043e\u043f\u0446\u0438\u043e\u043d\u0430\u043b\u044c\u043d\u043e<\/strong>.<\/p>\n<\/li>\n

  7. \n

    \u042d\u043a\u0441\u043f\u043e\u0440\u0442 \u0432 \u0445\u0440\u0430\u043d\u0438\u043b\u0438\u0449\u0435. \u041c\u043e\u0436\u043d\u043e \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c PutKudu, PutORC, PutHDFS, PutHiveStreaming, PutHbaseRecord, PutDatabaseRecord, PublishKafkaRecord2* \u0438\u043b\u0438 \u0434\u0440\u0443\u0433\u0438\u0435 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u044b.<\/p>\n<\/li>\n<\/ol>\n

    \u0412\u0441\u0435 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u044b \u043c\u043e\u0436\u043d\u043e \u043b\u0435\u0433\u043a\u043e \u0430\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u0437\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0432 NiFi.<\/strong> <\/p>\n

    <\/figcaption><\/figure>\n

    \u0421 \u043f\u043e\u043c\u043e\u0449\u044c\u044e \u0440\u0435\u0435\u0441\u0442\u0440\u0430 \u0441\u0445\u0435\u043c \u0434\u043e\u0441\u0442\u0443\u043f\u043d\u044b \u0432\u0441\u0435 \u0434\u0430\u043d\u043d\u044b\u0435 \u0432\u0430\u0448\u0435\u0439 \u0442\u0435\u043c\u044b — \u0434\u0430\u0436\u0435 \u0432 \u0444\u043e\u0440\u043c\u0430\u0442\u0435 Avro. <\/p>\n

    \"\"
    <\/figcaption><\/figure>\n

    \u041f\u0440\u0438\u043c\u0435\u0440 \u0441\u043e\u043e\u0431\u0449\u0435\u043d\u0438\u044f \u0432 Json:<\/p>\n

    [ {<\/code><\/p>\n

      \"credit\" : \"NOAA's National Weather Service\",<\/code><\/p>\n

      \"credit_URL\" : \"http:\/\/weather.gov\/\",<\/code><\/p>\n

      \"image\" : {<\/code><\/p>\n

        \"url\" : \"http:\/\/weather.gov\/images\/xml_logo.gif\",<\/code><\/p>\n

        \"title\" : \"NOAA's National Weather Service\",<\/code><\/p>\n

        \"link\" : \"http:\/\/weather.gov\"<\/code><\/p>\n

      },<\/code><\/p>\n

      \"suggested_pickup\" : \"15 minutes after the hour\",<\/code><\/p>\n

      \"suggested_pickup_period\" : 60,<\/code><\/p>\n

      \"location\" : \"Stanley Municipal Airport, ND\",<\/code><\/p>\n

      \"station_id\" : \"K08D\",<\/code><\/p>\n

      \"latitude\" : 48.3008,<\/code><\/p>\n

      \"longitude\" : -102.4064,<\/code><\/p>\n

      \"observation_time\" : \"Last Updated on Jul 10 2020, 9:55 am CDT\",<\/code><\/p>\n

      \"observation_time_rfc822\" : \"Fri, 10 Jul 2020 09:55:00 -0500\",<\/code><\/p>\n

      \"weather\" : \"Fair\",<\/code><\/p>\n

      \"temperature_string\" : \"66.0 F (19.0 C)\",<\/code><\/p>\n

      \"temp_f\" : 66.0,<\/code><\/p>\n

      \"temp_c\" : 19.0,<\/code><\/p>\n

      \"relative_humidity\" : 83,<\/code><\/p>\n

      \"wind_string\" : \"South at 6.9 MPH (6 KT)\",<\/code><\/p>\n

      \"wind_dir\" : \"South\",<\/code><\/p>\n

      \"wind_degrees\" : 180,<\/code><\/p>\n

      \"wind_mph\" : 6.9,<\/code><\/p>\n

      \"wind_kt\" : 6,<\/code><\/p>\n

      \"pressure_in\" : 30.03,<\/code><\/p>\n

      \"dewpoint_string\" : \"60.8 F (16.0 C)\",<\/code><\/p>\n

      \"dewpoint_f\" : 60.8,<\/code><\/p>\n

      \"dewpoint_c\" : 16.0,<\/code><\/p>\n

      \"visibility_mi\" : 10.0,<\/code><\/p>\n

      \"icon_url_base\" : \"http:\/\/forecast.weather.gov\/images\/wtf\/small\/\",<\/code><\/p>\n

      \"two_day_history_url\" : \"http:\/\/www.weather.gov\/data\/obhistory\/K08D.html\",<\/code><\/p>\n

      \"icon_url_name\" : \"skc.png\",<\/code><\/p>\n

      \"ob_url\" : \"http:\/\/www.weather.gov\/data\/METAR\/K08D.1.txt\",<\/code><\/p>\n

      \"disclaimer_url\" : \"http:\/\/weather.gov\/disclaimer.html\",<\/code><\/p>\n

      \"copyright_url\" : \"http:\/\/weather.gov\/disclaimer.html\",<\/code><\/p>\n

      \"privacy_policy_url\" : \"http:\/\/weather.gov\/notice.html\"<\/code><\/p>\n

    } ]<\/code><\/p>\n

    \n

    \u041a\u043e\u0434<\/strong><\/p>\n

    \u0413\u043e\u0442\u043e\u0432\u044b\u0439 \u0441\u043a\u0440\u0438\u043f\u0442: https:\/\/github.com\/tspannhw\/ApacheConAtHome2020\/blob\/main\/scripts\/setup.sh<\/strong><\/a><\/p>\n

    NiFi \u0444\u043b\u043e\u0443:
    https:\/\/github.com\/tspannhw\/ClouderaFlowManagementWorkshop\/tree\/main\/flows<\/strong><\/a><\/p>\n

    SQL<\/strong><\/p>\n

    \n\n\n\n\n\n\n\n\n\n
    \n<\/td>\n\n

    INSERT INTO weathernj<\/p>\n<\/td>\n<\/tr>\n

    \n<\/td>\n\n

    SELECT `location`, station_id,latitude,longitude,observation_time,weather,<\/p>\n<\/td>\n<\/tr>\n

    \n<\/td>\n\n

    temperature_string, temp_f,temp_c,relative_humidity,wind_string,wind_dir,wind_degrees,wind_mph,<\/p>\n<\/td>\n<\/tr>\n

    \n<\/td>\n\n

    wind_kt, pressure_in,dewpoint_string,dewpoint_f,dewpoint_c<\/p>\n<\/td>\n<\/tr>\n

    \n<\/td>\n\n

    FROM weather<\/p>\n<\/td>\n<\/tr>\n

    \n<\/td>\n\n

    WHERE<\/p>\n<\/td>\n<\/tr>\n

    \n<\/td>\n\n

        `location` is not null and `location` <> ‘null’ and trim(`location`) <> » and `location` like ‘%NJ’;<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

     <\/strong><\/p>\n

    Kafka Insert<\/strong><\/p>\n

    https:\/\/github.com\/tspannhw\/ApacheConAtHome2020\/blob\/main\/flinksql\/weathernj.sql<\/strong><\/a><\/p>\n

    \u0421\u0445\u0435\u043c\u044b<\/strong><\/p>\n

    https:\/\/github.com\/tspannhw\/ApacheConAtHome2020\/blob\/main\/schemas\/weathernj.avsc<\/strong><\/a><\/p>\n

    https:\/\/github.com\/tspannhw\/ApacheConAtHome2020\/blob\/main\/schemas\/weather.avsc<\/strong><\/a> <\/strong><\/p>\n

    \u041f\u0440\u0438\u043c\u0435\u0440 \u0432\u044b\u0432\u043e\u0434\u0430 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u0430 \u0432 Slack<\/strong><\/p>\n

    Location Cincinnati\/Northern Kentucky International Airport, KY Station KCVG
    Temperature: 49.0 F (9.4 C)
    Humdity: 83
    Wind East at 3.5 MPH (3 KT)
    Overcast
    Dewpoint 44.1 F (6.7 C)Observed at Tue, 27 Oct 2020 11:52:00 -0400—- tracking info —-          UUID: 2cb6bd67-148c-497d-badf-dfffb4906b89
      Kafka offset: 0
    Kafka Timestamp: 1603818351260
    =========================================================<\/p>\n<\/div>\n

    \u0441\u0441\u044b\u043b\u043a\u0430 \u043d\u0430 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b \u0441\u0442\u0430\u0442\u044c\u0438 https:\/\/habr.com\/ru\/company\/cloudera\/blog\/547050\/<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"\n

    \n
    <\/figcaption><\/figure>\n

    \u0418\u043d\u043e\u0433\u0434\u0430 \u0442\u0440\u0435\u0431\u0443\u0435\u0442\u0441\u044f \u043f\u043e\u043b\u0443\u0447\u0430\u0442\u044c, \u043c\u0430\u0440\u0448\u0440\u0443\u0442\u0438\u0437\u0438\u0440\u043e\u0432\u0430\u0442\u044c, \u043f\u0440\u0435\u043e\u0431\u0440\u0430\u0437\u043e\u0432\u044b\u0432\u0430\u0442\u044c, \u0437\u0430\u043f\u0440\u0430\u0448\u0438\u0432\u0430\u0442\u044c \u0438 \u0430\u043d\u0430\u043b\u0438\u0437\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0432\u0441\u0435 \u0434\u0430\u043d\u043d\u044b\u0435 \u043e \u043f\u043e\u0433\u043e\u0434\u0435 \u0432 \u0421\u043e\u0435\u0434\u0438\u043d\u0435\u043d\u043d\u044b\u0445 \u0428\u0442\u0430\u0442\u0430\u0445 — \u043f\u043e \u043c\u0435\u0440\u0435 \u043f\u043e\u044f\u0432\u043b\u0435\u043d\u0438\u044f \u044d\u0442\u0438\u0445 \u0434\u0430\u043d\u043d\u044b\u0445. \u0421 FLaNK \u044d\u0442\u043e \u0434\u043e\u0432\u043e\u043b\u044c\u043d\u043e \u0442\u0440\u0438\u0432\u0438\u0430\u043b\u044c\u043d\u044b\u0439 \u043f\u0440\u043e\u0446\u0435\u0441\u0441. <\/p>\n

    <\/figcaption><\/figure>\n
    <\/figcaption><\/figure>\n
    <\/figcaption><\/figure>\n

    \u041e\u0442 Kafka \u0434\u043e Kudu, \u0434\u043b\u044f \u043b\u044e\u0431\u043e\u0439 \u0441\u0445\u0435\u043c\u044b \u0438 \u043b\u044e\u0431\u043e\u0433\u043e \u0442\u0438\u043f\u0430 \u0434\u0430\u043d\u043d\u044b\u0445, \u0431\u0435\u0437 \u043d\u0430\u043f\u0438\u0441\u0430\u043d\u0438\u044f \u043a\u043e\u0434\u0430 \u2013 \u043f\u043e\u0442\u0440\u0435\u0431\u0443\u0435\u0442\u0441\u044f \u0432\u0441\u0435\u0433\u043e \u0434\u0432\u0430 \u0448\u0430\u0433\u0430. <\/p>\n

    <\/figcaption><\/figure>\n

    \u0412\u043e\u0442 \u044d\u0442\u0438 \u0441\u0445\u0435\u043c\u044b: \u0438\u0445 \u043c\u043e\u0436\u043d\u043e \u0441\u043e\u0437\u0434\u0430\u0432\u0430\u0442\u044c, \u0440\u0435\u043a\u0434\u0430\u043a\u0442\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0438 \u0441\u0440\u0430\u0432\u043d\u0438\u0432\u0430\u0442\u044c. Schema Registry \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u0442 Swagger API, \u043f\u043e\u044d\u0442\u043e\u043c\u0443 \u043d\u0435 \u0431\u0443\u0434\u0435\u0442 \u043f\u0440\u043e\u0431\u043b\u0435\u043c \u0441 \u043d\u0430\u0441\u0442\u0440\u043e\u0439\u043a\u043e\u0439 CI\/CD & DevOps \u043f\u0430\u0439\u043f\u043b\u0430\u0439\u043d\u043e\u0432:<\/p>\n

    <\/figcaption><\/figure>\n
    <\/figcaption><\/figure>\n

    \u041f\u0440\u043e\u0432\u0435\u0440\u043a\u0430 \u0434\u0430\u043d\u043d\u044b\u0445 \u043f\u043e \u0441\u0445\u0435\u043c\u0435 \u0441 \u0432\u0430\u0448\u0438\u043c \u0443\u0440\u043e\u0432\u043d\u0435\u043c \u0434\u043e\u043f\u0443\u0441\u043a\u0430. \u0415\u0441\u043b\u0438 \u0432\u044b \u0445\u043e\u0442\u0438\u0442\u0435, \u0447\u0442\u043e\u0431\u044b \u0431\u044b\u043b\u0438 \u0440\u0430\u0437\u0440\u0435\u0448\u0435\u043d\u044b \u0434\u043e\u043f\u043e\u043b\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0435 \u043f\u043e\u043b\u044f, \u0442\u043e \u0432\u044b \u044d\u0442\u043e \u043f\u043e\u043b\u0443\u0447\u0438\u0442\u0435. <\/p>\n

    <\/figcaption><\/figure>\n

    \u0414\u0430\u043b\u0435\u0435 \u044d\u0442\u0438 \u0434\u0430\u043d\u043d\u044b\u0435 \u0433\u043e\u0442\u043e\u0432\u044b \u043a \u0430\u043d\u0430\u043b\u0438\u0437\u0443, \u043d\u0430\u043f\u0440\u0438\u043c\u0435\u0440 \u0432 BI \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0435 Cloudera DataViz. <\/p>\n

    <\/figcaption><\/figure>\n

    \u0411\u044b\u0441\u0442\u0440\u043e \u0430\u043d\u0430\u043b\u0438\u0437\u0438\u0440\u0443\u0439\u0442\u0435 \u0441\u0432\u043e\u0438 \u0434\u0430\u043d\u043d\u044b\u0435 \u0432 Apache Kudu \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e Apache Hue \u0438 Apache Impala.<\/p>\n

    <\/figcaption><\/figure>\n

    \u0414\u0430\u0432\u0430\u0439\u0442\u0435 \u0432\u043e\u0437\u044c\u043c\u0435\u043c \u0434\u0430\u043d\u043d\u044b\u0435 \u0432\u0441\u0435\u0445 \u043c\u0435\u0442\u0435\u043e\u0441\u0442\u0430\u043d\u0446\u0438\u0439 \u0421\u0428\u0410, \u0434\u0430\u0436\u0435 \u0435\u0441\u043b\u0438 \u043e\u043d\u0438 \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u044f\u044e\u0442 \u0441\u043e\u0431\u043e\u0439 \u0437\u0430\u0430\u0440\u0445\u0438\u0432\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u044b\u0439 \u043a\u0430\u0442\u0430\u043b\u043e\u0433 \u0441 \u043c\u043d\u043e\u0436\u0435\u0441\u0442\u0432\u043e\u043c \u0444\u0430\u0439\u043b\u043e\u0432 XML. <\/p>\n

    <\/figcaption><\/figure>\n

    NiFi \u0444\u043b\u043e\u0443 \u0441\u043e\u0441\u0442\u043e\u0438\u0442 \u0438\u0437 \u0441\u043b\u0435\u0434\u0443\u044e\u0449\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432:<\/p>\n

      \n
    1. \n

      GenerateFlowFile — <\/strong>\u0438\u043c\u043e\u0440\u0442 \u043f\u0435\u0440\u0435\u043e\u0434\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043e\u0431\u043d\u043e\u0432\u043b\u0435\u043d\u0438\u0439 \u043e \u043f\u043e\u0433\u043e\u0434\u0435 \u043e\u0442 NOAA<\/p>\n<\/li>\n

    2. \n

      InvokeHTTP — <\/strong>\u0437\u0430\u0433\u0440\u0443\u0437\u043a\u0430 \u0434\u0430\u043d\u043d\u044b\u0445 \u043e \u043f\u043e\u0433\u043e\u0434\u0435 \u0432 ZIP \u0430\u0440\u0445\u0438\u0432<\/p>\n<\/li>\n

    3. \n

      CompressContent — <\/strong>\u0434\u043a\u043e\u043c\u043f\u0440\u0435\u0441\u0441\u0438\u044f ZIP<\/p>\n<\/li>\n

    4. \n

      UnpackContent — <\/strong>\u044d\u043a\u0441\u0442\u0440\u0430\u043a\u0442 \u0444\u0430\u0439\u043b\u043e\u0432 \u0438\u0437 ZIP \u0430\u0440\u0445\u0438\u0432\u0430<\/p>\n<\/li>\n

    5. \n

      *RouteOnAttribute — <\/strong>\u0444\u0438\u043b\u044c\u0442\u0440\u0430\u0446\u0438\u044f \u0442\u043e\u043b\u044c\u043a\u043e \u043f\u043e \u0430\u044d\u0440\u043e\u043f\u043e\u0440\u0442\u0430\u043c (${filename:startsWith(‘K’)}). \u043e\u043f\u0446\u0438\u043e\u043d\u0430\u043b\u044c\u043d\u043e<\/strong>.<\/p>\n<\/li>\n

    6. \n

      *QueryRecord<\/strong> — XMLReader \u0432 JsonRecordSetWriter.   Query<\/strong>:  SELECT * FROM FLOWFILE WHERE NOT location LIKE ‘%Unknown%’.  \u041d\u0443\u0436\u043d\u043e \u0434\u043b\u044f \u0443\u0434\u0430\u043b\u0435\u043d\u0438\u044f \u043d\u0435\u0438\u0434\u0435\u043d\u0442\u0438\u0444\u0438\u0446\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u044b\u0445 \u043b\u043e\u043a\u0430\u0446\u0438\u0439.  \u043e\u043f\u0446\u0438\u043e\u043d\u0430\u043b\u044c\u043d\u043e<\/strong>.<\/p>\n<\/li>\n

    7. \n

      \u042d\u043a\u0441\u043f\u043e\u0440\u0442 \u0432 \u0445\u0440\u0430\u043d\u0438\u043b\u0438\u0449\u0435. \u041c\u043e\u0436\u043d\u043e \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c PutKudu, PutORC, PutHDFS, PutHiveStreaming, PutHbaseRecord, PutDatabaseRecord, PublishKafkaRecord2* \u0438\u043b\u0438 \u0434\u0440\u0443\u0433\u0438\u0435 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u044b.<\/p>\n<\/li>\n<\/ol>\n

      \u0412\u0441\u0435 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u044b \u043c\u043e\u0436\u043d\u043e \u043b\u0435\u0433\u043a\u043e \u0430\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u0437\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0432 NiFi.<\/strong> <\/p>\n

      <\/figcaption><\/figure>\n

      \u0421 \u043f\u043e\u043c\u043e\u0449\u044c\u044e \u0440\u0435\u0435\u0441\u0442\u0440\u0430 \u0441\u0445\u0435\u043c \u0434\u043e\u0441\u0442\u0443\u043f\u043d\u044b \u0432\u0441\u0435 \u0434\u0430\u043d\u043d\u044b\u0435 \u0432\u0430\u0448\u0435\u0439 \u0442\u0435\u043c\u044b — \u0434\u0430\u0436\u0435 \u0432 \u0444\u043e\u0440\u043c\u0430\u0442\u0435 Avro. <\/p>\n

      <\/figcaption><\/figure>\n

      \u041f\u0440\u0438\u043c\u0435\u0440 \u0441\u043e\u043e\u0431\u0449\u0435\u043d\u0438\u044f \u0432 Json:<\/p>\n

      [ {<\/code><\/p>\n

        \"credit\" : \"NOAA's National Weather Service\",<\/code><\/p>\n

        \"credit_URL\" : \"http:\/\/weather.gov\/\",<\/code><\/p>\n

        \"image\" : {<\/code><\/p>\n

          \"url\" : \"http:\/\/weather.gov\/images\/xml_logo.gif\",<\/code><\/p>\n

          \"title\" : \"NOAA's National Weather Service\",<\/code><\/p>\n

          \"link\" : \"http:\/\/weather.gov\"<\/code><\/p>\n

        },<\/code><\/p>\n

        \"suggested_pickup\" : \"15 minutes after the hour\",<\/code><\/p>\n

        \"suggested_pickup_period\" : 60,<\/code><\/p>\n

        \"location\" : \"Stanley Municipal Airport, ND\",<\/code><\/p>\n

        \"station_id\" : \"K08D\",<\/code><\/p>\n

        \"latitude\" : 48.3008,<\/code><\/p>\n

        \"longitude\" : -102.4064,<\/code><\/p>\n

        \"observation_time\" : \"Last Updated on Jul 10 2020, 9:55 am CDT\",<\/code><\/p>\n

        \"observation_time_rfc822\" : \"Fri, 10 Jul 2020 09:55:00 -0500\",<\/code><\/p>\n

        \"weather\" : \"Fair\",<\/code><\/p>\n

        \"temperature_string\" : \"66.0 F (19.0 C)\",<\/code><\/p>\n

        \"temp_f\" : 66.0,<\/code><\/p>\n

        \"temp_c\" : 19.0,<\/code><\/p>\n

        \"relative_humidity\" : 83,<\/code><\/p>\n

        \"wind_string\" : \"South at 6.9 MPH (6 KT)\",<\/code><\/p>\n

        \"wind_dir\" : \"South\",<\/code><\/p>\n

        \"wind_degrees\" : 180,<\/code><\/p>\n

        \"wind_mph\" : 6.9,<\/code><\/p>\n

        \"wind_kt\" : 6,<\/code><\/p>\n

        \"pressure_in\" : 30.03,<\/code><\/p>\n

        \"dewpoint_string\" : \"60.8 F (16.0 C)\",<\/code><\/p>\n

        \"dewpoint_f\" : 60.8,<\/code><\/p>\n

        \"dewpoint_c\" : 16.0,<\/code><\/p>\n

        \"visibility_mi\" : 10.0,<\/code><\/p>\n

        \"icon_url_base\" : \"http:\/\/forecast.weather.gov\/images\/wtf\/small\/\",<\/code><\/p>\n

        \"two_day_history_url\" : \"http:\/\/www.weather.gov\/data\/obhistory\/K08D.html\",<\/code><\/p>\n

        \"icon_url_name\" : \"skc.png\",<\/code><\/p>\n

        \"ob_url\" : \"http:\/\/www.weather.gov\/data\/METAR\/K08D.1.txt\",<\/code><\/p>\n

        \"disclaimer_url\" : \"http:\/\/weather.gov\/disclaimer.html\",<\/code><\/p>\n

        \"copyright_url\" : \"http:\/\/weather.gov\/disclaimer.html\",<\/code><\/p>\n

        \"privacy_policy_url\" : \"http:\/\/weather.gov\/notice.html\"<\/code><\/p>\n

      } ]<\/code><\/p>\n

      \n

      \u041a\u043e\u0434<\/strong><\/p>\n

      \u0413\u043e\u0442\u043e\u0432\u044b\u0439 \u0441\u043a\u0440\u0438\u043f\u0442: https:\/\/github.com\/tspannhw\/ApacheConAtHome2020\/blob\/main\/scripts\/setup.sh<\/strong><\/a><\/p>\n

      NiFi \u0444\u043b\u043e\u0443:
      https:\/\/github.com\/tspannhw\/ClouderaFlowManagementWorkshop\/tree\/main\/flows<\/strong><\/a><\/p>\n

      SQL<\/strong><\/p>\n

      \n\n\n\n\n\n\n\n\n\n
      \n<\/td>\n\n

      INSERT INTO weathernj<\/p>\n<\/td>\n<\/tr>\n

      \n<\/td>\n\n

      SELECT `location`, station_id,latitude,longitude,observation_time,weather,<\/p>\n<\/td>\n<\/tr>\n

      \n<\/td>\n\n

      temperature_string, temp_f,temp_c,relative_humidity,wind_string,wind_dir,wind_degrees,wind_mph,<\/p>\n<\/td>\n<\/tr>\n

      \n<\/td>\n\n

      wind_kt, pressure_in,dewpoint_string,dewpoint_f,dewpoint_c<\/p>\n<\/td>\n<\/tr>\n

      \n<\/td>\n\n

      FROM weather<\/p>\n<\/td>\n<\/tr>\n

      \n<\/td>\n\n

      WHERE<\/p>\n<\/td>\n<\/tr>\n

      \n<\/td>\n\n

          `location` is not null and `location` <> ‘null’ and trim(`location`) <> » and `location` like ‘%NJ’;<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

       <\/strong><\/p>\n

      Kafka Insert<\/strong><\/p>\n

      https:\/\/github.com\/tspannhw\/ApacheConAtHome2020\/blob\/main\/flinksql\/weathernj.sql<\/strong><\/a><\/p>\n

      \u0421\u0445\u0435\u043c\u044b<\/strong><\/p>\n

      https:\/\/github.com\/tspannhw\/ApacheConAtHome2020\/blob\/main\/schemas\/weathernj.avsc<\/strong><\/a><\/p>\n

      https:\/\/github.com\/tspannhw\/ApacheConAtHome2020\/blob\/main\/schemas\/weather.avsc<\/strong><\/a> <\/strong><\/p>\n

      \u041f\u0440\u0438\u043c\u0435\u0440 \u0432\u044b\u0432\u043e\u0434\u0430 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u0430 \u0432 Slack<\/strong><\/p>\n

      Location Cincinnati\/Northern Kentucky International Airport, KY Station KCVG
      Temperature: 49.0 F (9.4 C)
      Humdity: 83
      Wind East at 3.5 MPH (3 KT)
      Overcast
      Dewpoint 44.1 F (6.7 C)Observed at Tue, 27 Oct 2020 11:52:00 -0400—- tracking info —-          UUID: 2cb6bd67-148c-497d-badf-dfffb4906b89
        Kafka offset: 0
      Kafka Timestamp: 1603818351260
      =========================================================<\/p>\n<\/div>\n

      \u0441\u0441\u044b\u043b\u043a\u0430 \u043d\u0430 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b \u0441\u0442\u0430\u0442\u044c\u0438 https:\/\/habr.com\/ru\/company\/cloudera\/blog\/547050\/<\/a>
      <\/br><\/br><\/br><\/br><\/br><\/br><\/br><\/br><\/p>\n<\/p>\n<\/hr>\n<\/div>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[],"tags":[],"class_list":["post-320222","post","type-post","status-publish","format-standard","hentry"],"_links":{"self":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/320222","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=320222"}],"version-history":[{"count":0,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/320222\/revisions"}],"wp:attachment":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=320222"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=320222"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=320222"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}