\u6700\u8fd1\u306f\u5642\u306e\u30d3\u30c3\u30b0\u30c7\u30fc\u30bf\u7684\u306a\u30b7\u30b9\u30c6\u30e0\u306e\u30a4\u30f3\u30d5\u30e9\u95a2\u9023\u306b\u3082\u624b\u3092\u51fa\u3057\u3064\u3064\u3042\u308b\u306e\u3067\u3059\u304c\u3001\u6c17\u306b\u306a\u3063\u3066\u3044\u308b\u306e\u304cTreasure Data\u306a\u306e\u3067\u3059\u3002<\/p>\n
\u4f55\u3068\u8a00\u3063\u3066\u3082500GB\u307e\u3067\u3001\u7121\u6599\u3067\u30af\u30e9\u30a6\u30c9\u578b\u306eHadoop\u304c\u4f7f\u3048\u308b\u3068\u3044\u3046\u306e\u304c\u304a\u8a66\u3057\u306b\u306f\u6700\u9069\u3002<\/p>\n
\u3055\u3089\u306b\u3001fluentd\u7528\u306e\u30a4\u30f3\u30bf\u30fc\u30d5\u30a7\u30fc\u30b9\u3082\u3042\u308a\u306e\u3001Hive\u3082\u4f7f\u3048\u308b\u306e\u3067\u3059\u3050\u5229\u7528\u3067\u304d\u308b\u72b6\u614b\u306b\u3042\u308a\u306e\u3001\u9b45\u529b\u304c\u305f\u304f\u3055\u3093\u3002<\/p>\n
\u307e\u305a\u306f\u30b5\u30a4\u30f3\u30a2\u30c3\u30d7\u306a\u306e\u3067\u3059\u304c\u3053\u3053\u3044\u3044\u306d\uff01<\/p>\n
Let\u2019s get started with Treasure Data! Treasure Data is a Hadoop-based Cloud Data Warehousing service. Forget about the servers, storage, and infrastructure needed to store your billions of records and focus on analyzing your data instead.<\/em><\/p>\n<\/div>\n \u7c21\u5358\u306b\u8a00\u3046\u3068\u3001\u300c\u30a4\u30f3\u30d5\u30e9\u5468\u308a\u306e\u3053\u3068\u6c17\u306b\u3057\u306a\u3044\u3067\u89e3\u6790\u3060\u3051\u306b\u96c6\u4e2d\u3057\u3066\u304f\u3060\u3055\u3044\uff01\u300d\u3066\u3068\u3053\u308d\u3067\u3057\u3087\u3046\u304b\u3002 \u30af\u30e9\u30a4\u30a2\u30f3\u30c8\u5074\u306e\u30bb\u30c3\u30c8\u30a2\u30c3\u30d7\u306fCentOS\u4f7f\u3063\u3066\u307e\u3059\u304c\u3001\u914d\u5e03\u3055\u308c\u3066\u3044\u308b\u30b7\u30a7\u30eb\u3067\u4e00\u767a\u3067\u3059\u3002 \u65e9\u901f\u306a\u306e\u3067\u3059\u304c\u3001DBT3\u3067\u3082\u8a66\u3057\u3066\u307f\u3088\u3046\u304b\u3068\u601d\u3044\u3001\u30c7\u30fc\u30bf\u3092\u30ed\u30fc\u30c9(import)\u3059\u308b\u3053\u3068\u306b\u3057\u307e\u3057\u305f\u3002 \u30c6\u30fc\u30d6\u30eb\u4f5c\u6210\u306f\u3053\u3093\u306a\u611f\u3058\u3067\u4e00\u77ac\u3067\u3002<\/p>\n $ td account -f<\/p>\n $ td db:create dbt3<\/p>\n $ td table:create dbt3 supplier $ td table:list dbt3 \u7c21\u5358\u3059\u304e\u308b\u30fb\u30fb\u30fb\u30ab\u30e9\u30e0\u5b9a\u7fa9\u3092\u3057\u306a\u304f\u3066\u826f\u3044\u306e\u306f\u5f53\u305f\u308a\u524d\u3060\u3051\u3069\u697d\u3002<\/p>\n \u3055\u3066\u3001dbt3\u306e\u30c7\u30fc\u30bf\u30ed\u30fc\u30c9\u3067\u3059\u304c\u3001\u3055\u304f\u3089VPS\u304b\u3089\u30ed\u30fc\u30c9\u3059\u308b\u306e\u3067\u3001\u30ed\u30fc\u30ab\u30eb\u306b\u306f\u5927\u304d\u306a\u30d5\u30a1\u30a4\u30eb\u306f\u7f6e\u304d\u305f\u304f\u306a\u3044\u3002<\/p>\n \u3068\u3044\u3046\u3053\u3068\u3067\u3001\u5727\u7e2e\u3057\u3066\u304a\u3044\u305ftbl\u30c7\u30fc\u30bf\u3092FIFO\u3067\u6d41\u3057\u8fbc\u3080\u3053\u3068\u306b\u3002<\/p>\n \u305d\u306e\u524d\u306b\u30fb\u30fb\u30fbCSV\u306f\u305d\u306e\u307e\u307e\u3067\u306fimport\u304c\u3067\u304d\u306a\u3044\u3053\u3068\u304c\u5224\u660e\u3002\u3002\u3002<\/p>\n msgpack\u304bjson\u3067\u306a\u3044\u3068\u3060\u3081\u3068\u306e\u3053\u3068\u3002\uff08\u305d\u3082\u305d\u3082msgpack\u3066\u306a\u306b\u304b\u3057\u3089\u306a\u3044\u30fb\u30fb\uff1f\uff1f\uff09<\/p>\n \u7279\u306b\u65b0\u305f\u306a\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u306a\u3069\u30bb\u30c3\u30c8\u30a2\u30c3\u30d7\u306e\u5fc5\u8981\u304c\u306a\u3044\u3001awk\u3067\u5b9f\u884c\u3059\u308b\u3053\u3068\u306b\u3002<\/p>\n \u3053\u3093\u306a\u611f\u3058\u306b \u4e0a\u306e\u4f8b\u306f\u3001dbt3\u306elineitem\u306e\u4f8b\u3067\u3059\u304c\u3001\u4ed6\u306e\u30c6\u30fc\u30d6\u30eb\u3082\u30ab\u30e9\u30e0\u540d\u3068\u6570\u3092\u5909\u3048\u3066\u6d41\u7528\u3067\u304d\u307e\u3059\u3002<\/p>\n \u4ee5\u4e0b\u3001FIFO\u304b\u3089\u306eimport\u306e\u624b\u9806\u3067\u3059\u3002 #!\/bin\/sh<\/p>\n for TABLE in customer nation part partsupp region supplier echo “${TABLE} import start `date`”<\/p>\n # fifo\u306e\u4f5c\u6210 # \u5148\u306bimport\u30b3\u30de\u30f3\u30c9\u3092\u5b9f\u884c # \u30c6\u30fc\u30d6\u30eb\u30c7\u30fc\u30bf\u3092zcat\u3067\u5c55\u958b\u3057\u306a\u304c\u3089\u3001\u5404\u30c6\u30fc\u30d6\u30eb\u3054\u3068\u306b\u4f5c\u6210\u3057\u305fawk\u30b9\u30af\u30ea\u30d7\u30c8\u3092fifo\u306b\u6d41\u3057\u8fbc\u3080 # \u30ec\u30b3\u30fc\u30c9\u4ef6\u6570\u3092\u8abf\u3079\u3066\u7d42\u308f\u308a\uff08Hive\u4fbf\u5229\uff01\uff09 rm -f ${TABLE}.fifo<\/p>\n echo “${TABLE} import done `date`”<\/p>\n done<\/p>\n<\/div>\n \u203blineitem\u3068orders\u306f\u5c65\u6b74\u3063\u307d\u3044\u306e\u3067\u5225\u306e\u7d61\u3080\u3092-t\u3067\u6307\u5b9a\u3057\u307e\u3057\u305f\u3002<\/p>\n lineitem\u3000\u2192\u3000L_SHIPDATE \u30ed\u30fc\u30c9\u5f8c\u306b\u30c6\u30fc\u30d6\u30eb\u30c7\u30fc\u30bf\u3092\u78ba\u8a8d\u3057\u3066\u307f\u307e\u3057\u305f\u3002<\/p>\n $ td table:list dbt3 \u78ba\u304b\u306b\u30c7\u30fc\u30bf\u91cf\u304c\u5897\u3048\u3066\u3044\u307e\u3059\u3002 \u4ee5\u4e0a\u3067\u3068\u308a\u3042\u3048\u305a\u306eimport\u306f\u5b8c\u4e86\u3067\u3059\u3002<\/p>\n \u3042\u3068\u306fDBT3\u306e\u30af\u30a8\u30ea\u3092\u79fb\u690d\u3057\u3066\u3001\u5b9f\u884c\u6642\u9593\u306e\u78ba\u8a8d\u3067\u3059\u306d\u3002 \u3053\u3061\u3089\u306e\u30d6\u30ed\u30b0\u3092\u53c2\u8003\u306b\u3055\u305b\u3066\u3044\u305f\u3060\u304d\u307e\u3057\u305f\u3002 \uff08\u8ffd\u8a181\uff09 skipped: A JSON text must at least contain two octets!: “\\n”<\/p>\n<\/div>\n \uff08\u8ffd\u8a182\uff09 skipped: argument out of range<\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":" \u6700\u8fd1\u306f\u5642\u306e\u30d3\u30c3\u30b0\u30c7\u30fc\u30bf\u7684\u306a\u30b7\u30b9\u30c6\u30e0\u306e\u30a4\u30f3\u30d5\u30e9\u95a2\u9023\u306b\u3082\u624b\u3092\u51fa\u3057\u3064\u3064\u3042\u308b\u306e\u3067\u3059\u304c\u3001\u6c17\u306b\u306a\u3063\u3066\u3044\u308b\u306e\u304cTreasure Data\u306a\u306e\u3067\u3059\u3002 \u4f55\u3068\u8a00\u3063\u3066\u3082500GB\u307e\u3067\u3001\u7121\u6599\u3067\u30af\u30e9\u30a6\u30c9\u578b\u306eHadoop\u304c\u4f7f\u3048\u308b\u3068\u3044\u3046\u306e\u304c\u304a\u8a66\u3057\u306b\u306f… <\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"neve_meta_sidebar":"","neve_meta_container":"","neve_meta_enable_content_width":"","neve_meta_content_width":0,"neve_meta_title_alignment":"","neve_meta_author_avatar":"","neve_post_elements_order":"","neve_meta_disable_header":"","neve_meta_disable_footer":"","neve_meta_disable_title":"","footnotes":""},"categories":[24,22,8,1],"tags":[42],"_links":{"self":[{"href":"https:\/\/a23187.yorozuyah.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/1123"}],"collection":[{"href":"https:\/\/a23187.yorozuyah.com\/blog\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/a23187.yorozuyah.com\/blog\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/a23187.yorozuyah.com\/blog\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/a23187.yorozuyah.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1123"}],"version-history":[{"count":37,"href":"https:\/\/a23187.yorozuyah.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/1123\/revisions"}],"predecessor-version":[{"id":1202,"href":"https:\/\/a23187.yorozuyah.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/1123\/revisions\/1202"}],"wp:attachment":[{"href":"https:\/\/a23187.yorozuyah.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1123"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/a23187.yorozuyah.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1123"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/a23187.yorozuyah.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1123"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\n\u30a4\u30f3\u30d5\u30e9\u3092\u62c5\u5f53\u3059\u308b\u3082\u306e\u3068\u3057\u3066\u306f\u3042\u308a\u304c\u305f\u3044\u304a\u8a00\u8449(T_T)<\/p>\n
\n\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u5f8c\u306ftd\u30b3\u30de\u30f3\u30c9\u3067\u30af\u30e9\u30a4\u30a2\u30f3\u30c8\u64cd\u4f5c\u304c\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u308a\u307e\u3059\u3002<\/p>\n
\n\u65e2\u306bDBT3\u74b0\u5883\u306e\u30c7\u30fc\u30bf\u304c\u3042\u308a\u307e\u3057\u305f\u306e\u3067\u305d\u308c\u3092\u6d41\u7528\u3057\u307e\u3059\u3002<\/p>\n
\n$ td table:create dbt3 customer
\n$ td table:create dbt3 orders
\n$ td table:create dbt3 lineitem
\n$ td table:create dbt3 part
\n$ td table:create dbt3 partsupp
\ntd table:create dbt3 nation
\ntd table:create dbt3 region<\/p>\n
\n+———-+———-+——+——-+——–+——–+
\n| Database | Table | Type | Count | Size | Schema |
\n+———-+———-+——+——-+——–+——–+
\n| dbt3 | customer | log | 0 | 0.0 GB | |
\n| dbt3 | lineitem | log | 0 | 0.0 GB | |
\n| dbt3 | nation | log | 0 | 0.0 GB | |
\n| dbt3 | orders | log | 0 | 0.0 GB | |
\n| dbt3 | part | log | 0 | 0.0 GB | |
\n| dbt3 | partsupp | log | 0 | 0.0 GB | |
\n| dbt3 | region | log | 0 | 0.0 GB | |
\n| dbt3 | supplier | log | 0 | 0.0 GB | |
\n+———-+———-+——+——-+——–+——–+
\n8 rows in set<\/p>\n<\/div>\n
\n\u2192awk\u3067csv\u3092json\u306b\u5909\u63db\u3057\u3066\u307f\u308b<\/a><\/p>\n
\n\u3042\u3089\u304b\u3058\u3081\u4f5c\u3063\u3066\u5727\u7e2e\u3057\u3066\u3042\u3063\u305fdbt3\u7528\u306e\u30c6\u30fc\u30d6\u30eb\u30c7\u30fc\u30bf\u3092\u3001csv\u304b\u3089json\u306b\u5909\u63db\u3057\u306a\u304c\u3089import\u3057\u3066\u3044\u304d\u307e\u3059\u3002<\/p>\n
\ndo<\/p>\n
\nmkfifo ${TABLE}.fifo<\/p>\n
\ntd table:import dbt3 ${TABLE} –json -t CREATED ${TABLE}.fifo &<\/p>\n
\nzcat ${TABLE}.tbl.gz | awk -f csvTojson_${TABLE}.awk > ${TABLE}.fifo<\/p>\n
\necho “${TABLE} count `date`”
\ntd query -d dbt3 -w “select count(*) from ${TABLE}”<\/p>\n
\norders\u3000\u2192\u3000 O_ORDERDATE<\/p>\n
\n+———-+———-+——+———–+———+——–+
\n| Database | Table | Type | Count | Size | Schema |
\n+———-+———-+——+———–+———+——–+
\n| dbt3 | customer | log | 4500000 | 0.2 GB | |
\n| dbt3 | lineitem | log | 179998372 | 3.0 GB | |
\n| dbt3 | nation | log | 25 | 0.0 GB | |
\n| dbt3 | orders | log | 45000000 | 1.2 GB | |
\n| dbt3 | part | log | 6000000 | 0.1 GB | |
\n| dbt3 | partsupp | log | 24000000 | 0.7 GB | |
\n| dbt3 | region | log | 5 | 0.0 GB | |
\n| dbt3 | supplier | log | 300000 | 0.01 GB | |
\n+———-+———-+——+———–+———+——–+
\n8 rows in set<\/p>\n
\ncount(*)\u3057\u306a\u304f\u3066\u3082\u5143\u3005\u8a18\u9332\u3055\u308c\u3066\u308b\u3093\u3067\u3059\u306d\uff01\u77e5\u3089\u306a\u304b\u3063\u305f\u3002\u3002\u3002<\/p>\n<\/div>\n
\nHive\u306a\u306e\u3067\u3001\u4fee\u6b63\u3057\u306a\u304f\u3066\u3082\u305d\u308c\u306a\u308a\u306b\u52d5\u304f\u3068\u306f\u601d\u3044\u307e\u3059\u3002<\/p>\n
\n\u3042\u308a\u304c\u3068\u3046\u3054\u3056\u3044\u307e\u3057\u305f\u3002
\nTreasure Data \u3067\u30e2\u30c6\u30e2\u30c6<\/a>
\nTreasure Data Analytics \u7b2c3\u56de \u301c\u30d6\u30c3\u30af\u30ec\u30d3\u30e5\u30fc\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306b\u3088\u308b\u30c7\u30fc\u30bf\u89e3\u6790\u5165\u9580\uff08\u6e96\u5099\u7de8\uff09\u301c<\/a>
\n\u2192\u3000\u3053\u3061\u3089\u4e2d\u306e\u65b9\u3067\u3059\u306d\uff01\uff1f<\/p>\n
\nimport\u6642\u306b\u3053\u3093\u306a\u30a8\u30e9\u30fc\u304c\u51fa\u308b\u3053\u3068\u304c\u3002\u3053\u308c\u306f\u6539\u884c\u306e\u307f\u306e\u30ec\u30b3\u30fc\u30c9\u3067\u767a\u751f\u3057\u3066\u3044\u308b\u6a21\u69d8\u3002
\nJSON\u306f\u5c11\u306a\u304f\u3068\u3082\u5404\u30ec\u30b3\u30fc\u30c9\u304c16byte\u4ee5\u4e0a\u5fc5\u8981\u3068\u3044\u3046\u3053\u3068\u304b\u306a\uff1f<\/p>\n
\n\u30ec\u30b3\u30fc\u30c9\u306eimport\u304c\u4ee5\u4e0b\u306e\u30a8\u30e9\u30fc\u3067\u5931\u6557\u3057\u3066\u3044\u305f\u306e\u3067\u3001\u8abf\u3079\u3066\u307f\u305f\u3068\u3053\u308d\u3001import\u3059\u308b\u30ec\u30b3\u30fc\u30c9\u306e\u30bf\u30a4\u30e0\u30b9\u30bf\u30f3\u30d7\u306e\u9805\u76ee\u304cUNIXTIME\u3060\u3063\u305f\u306e\u304c\u99c4\u76ee\u3060\u3063\u305f\u307f\u305f\u3044\u3002awk\u3067\u300cstrftime(“%Y\/%m\/%d %H:%M:%S”, systime())\u300d\u306e\u6642\u9593\u30c7\u30fc\u30bf\u3092\u4f5c\u6210\u3057\u3001\u305d\u3053\u3092\u6307\u5b9a\u3059\u308b\u3053\u3068\u3067\u89e3\u6d88\u3057\u307e\u3057\u305f\u3002<\/p>\n