{"id":2462,"date":"2018-08-08T00:40:39","date_gmt":"2018-08-07T15:40:39","guid":{"rendered":"https:\/\/pandanote.info\/?p=2462"},"modified":"2019-10-22T11:45:06","modified_gmt":"2019-10-22T02:45:06","slug":"apache-solr%e3%82%92%e5%a7%8b%e3%82%81%e3%81%be%e3%81%97%e3%81%9f2-dataimporthandler%e3%81%ae%e6%8b%a1%e5%bc%b5%e7%94%a8%e3%81%ae%e3%82%b3%e3%83%bc%e3%83%89%e3%82%92%e3%81%a1%e3%82%87%e3%81%84","status":"publish","type":"post","link":"https:\/\/pandanote.info\/?p=2462","title":{"rendered":"\u3010\u8ffd\u8a18\u3057\u307e\u3057\u305f\u3002\u3011Apache Solr\u3092\u6025\u907d\u59cb\u3081\u307e\u3057\u305f(2): DataImportHandler\u306e\u62e1\u5f35\u7528\u306e\u30b3\u30fc\u30c9\u3092\u3061\u3087\u3044\u3068\u8ffd\u52a0\u3057\u3066\u30017-Zip\u3067\u5727\u7e2e\u3055\u308c\u305f\u30c7\u30fc\u30bf\u3092\u30a4\u30f3\u30dd\u30fc\u30c8\u3057\u3066\u307f\u305f\u3002"},"content":{"rendered":"<h2>\u306f\u3058\u3081\u306b<\/h2>\n<p><a href=\"https:\/\/pandanote.info\/?p=2441\">\u524d\u306e\u8a18\u4e8b<\/a>\u3067\u3001NEologd\u306e\u5165\u3063\u3066\u3044\u308bkuromoji\u3092\u7d44\u307f\u8fbc\u3093\u3066\u307f\u307e\u3057\u305f\u306e\u3067\u3001\u6b21\u306e\u95a2\u9580\u306b\u6311\u307f\u305f\u3044\u3068\u601d\u3044\u307e\u3059\u3002<\/p>\n<p>\u5b9f\u306f\u3001\u30a4\u30f3\u30c7\u30c3\u30af\u30b9\u3092\u884c\u3046\u5bfe\u8c61\u3068\u306a\u308b\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u304c7-zip\u3067\u5727\u7e2e\u3055\u308c\u3066\u304a\u308a\u307e\u3057\u3066\u3001\u3053\u308c\u304c\u3088\u3093\u3069\u3053\u308d\u306a\u3044\u4e8b\u60c5\u306b\u3088\u308a\u5c55\u958b\u3057\u3066\u4f7f\u3046\u306e\u304c\u96e3\u3057\u3044\u305f\u3081\u3001Apache Solr\u306b\u306f\u3067\u304d\u308c\u3070\u30b7\u30a7\u30eb\u306e\u30b3\u30de\u30f3\u30c9\u30d7\u30ed\u30f3\u30d7\u30c8\u304b\u3089<\/p>\n<div class=\"code\">$ 7z x somefile.7z<\/div>\n<p>&nbsp;<br \/>\n\u3068\u5b9f\u884c\u5f8c\u306bPostTool\u3092\u4f7f\u3063\u3066\u30c7\u30fc\u30bf\u3092\u30a4\u30f3\u30dd\u30fc\u30c8\u3092\u3059\u308b\u3053\u3068\u306a\u304f\u30017-zip\u3067\u5727\u7e2e\u3055\u308c\u305f\u72b6\u614b\u306e\u307e\u307eDataImportHandler\u3078\u306e\u5165\u529b\u3068\u3057\u3066\u4e0e\u3048\u305f\u3044\u308f\u3051\u3067\u3059\u3002<\/p>\n<p>\u2026\u3068\u3044\u3046\u611f\u3058\u3067\u3084\u308a\u305f\u3044\u3053\u3068\u3092\u6574\u7406\u3057\u3066\u304b\u3089\u3001Apache Solr(7.4.0)\u306e\u30bd\u30fc\u30b9\u30b3\u30fc\u30c9\u3092\u78ba\u8a8d\u3057\u3066\u307f\u308b\u3068\u3001DataImportHandler\u7d4c\u7531\u306e\u30d5\u30a1\u30a4\u30eb\u306e\u30a4\u30f3\u30dd\u30fc\u30c8\u306f\u975e\u5727\u7e2e\u306e\u3082\u306e\u306e\u307f\u304c\u30b5\u30dd\u30fc\u30c8\u3055\u308c\u3066\u3044\u308b\u3053\u3068\u304c\u308f\u304b\u308a\u307e\u3057\u305f\u3002<\/p>\n<p>\u305d\u3053\u3067\u3001DataImportHandler\u30677-zip\u3067\u5727\u7e2e\u3055\u308c\u305f\u30d5\u30a1\u30a4\u30eb\u306e\u30a4\u30f3\u30dd\u30fc\u30c8\u3092\u30b5\u30dd\u30fc\u30c8\u3059\u308b\u30b3\u30fc\u30c9\u3092\u5b9f\u88c5\u3057\u3066\u304b\u3089\u3001DataImportHandler\u306e\u8a2d\u5b9a\u3092\u884c\u3044\u3001\u3055\u3089\u306b\u305d\u306e\u52d5\u4f5c\u78ba\u8a8d\u307e\u3067\u3092\u884c\u3044\u307e\u3057\u305f\u3002<\/p>\n<p>\u3053\u306e\u8a18\u4e8b\u3067\u306f\u4e0a\u8a18\u306e\u4f5c\u696d\u306e\u6d41\u308c\u306b\u3064\u3044\u3066\u66f8\u3044\u3066\u3044\u304d\u307e\u3059\u3002<\/p>\n<h2>7-zip\u30b5\u30dd\u30fc\u30c8\u306e\u5b9f\u88c5\u3002<\/h2>\n<p>7-Zip\u30b5\u30dd\u30fc\u30c8\u3092\u5b9f\u88c5\u3059\u308b\u305f\u3081\u306b\u306f\u3001\u4ee5\u4e0b\u306e\u30af\u30e9\u30b9\u304c\u5fc5\u8981\u3067\u3059\u3002<\/p>\n<ol>\n<li>7-Zip\u3067\u5727\u7e2e\u3057\u305f\u30d5\u30a1\u30a4\u30eb\u3092\u8aad\u307f\u8fbc\u3080\u305f\u3081\u306e\u5165\u529b\u30b9\u30c8\u30ea\u30fc\u30e0(InputStream)\u3002<\/li>\n<li>\u4e0a\u8a18\u306e\u5165\u529b\u30b9\u30c8\u30ea\u30fc\u30e0\u3092\u5229\u7528\u3059\u308b\u305f\u3081\u306e\u30c7\u30fc\u30bf\u30bd\u30fc\u30b9(DataSource)\u3002<\/li>\n<\/ol>\n<p>\u4e0a\u8a18\u306e\u5b9f\u88c5\u306b\u3064\u3044\u3066\u306fScala\u3067\u3044\u304d\u306a\u308a\u66f8\u3051\u308b\u3068\u304b\u3063\u3053\u3088\u3055\u305d\u3046\u306a\u611f\u3058\u304c\u3057\u306a\u3044\u3067\u3082\u306a\u3044\u306e\u3067\u3059\u3051\u3069\u3001Apache Solr\u306b\u7d44\u307f\u8fbc\u3093\u3060\u4e0a\u3067\u306e\u52d5\u4f5c\u306e\u78ba\u8a8d\u3092\u512a\u5148\u3057\u305f\u3044\u306e\u3067\u3001\u3068\u308a\u3042\u3048\u305aJava\u3067\u5b9f\u88c5\u3057\u3066\u304b\u3089Scala\u3078\u306e\u79fb\u690d\u3092\u8a66\u307f\u308b\u3053\u3068\u306b\u3057\u307e\u3057\u305f(Scala\u3078\u306e\u79fb\u690d\u304c\u3067\u304d\u305f\u5834\u5408\u306b\u306f\u3001\u3053\u306e\u8a18\u4e8b\u3092\u66f4\u65b0\u3057\u307e\u3059)\u3002<\/p>\n<h3>7-zip\u7528InputStream\u306e\u5b9f\u88c5\u4f8b\u3002<\/h3>\n<p>7-zip\u7528InputStream\u306e\u5b9f\u88c5\u4f8b\u3068\u3057\u3066\u3001SevenZFileInputStream\u30af\u30e9\u30b9\u3092\u5b9a\u7fa9\u3057\u3001\u4ee5\u4e0b\u306e\u30b3\u30fc\u30c9\u4f8b\u306e\u3088\u3046\u306b\u5b9f\u88c5\u3057\u307e\u3057\u305f\u3002\u3053\u308c\u306fInputStream\u30af\u30e9\u30b9\u3092\u62e1\u5f35\u3057\u305f\u3082\u306e\u3067\u3001\u30d5\u30a1\u30a4\u30eb\u304b\u3089\u8aad\u307f\u8fbc\u3093\u3060(\u5727\u7e2e\u6e08\u306e)\u30c7\u30fc\u30bf\u3092\u30af\u30e9\u30b9\u5185\u90e8\u3067commons-compress\u306b\u542b\u307e\u308c\u3066\u3044\u308bSevenZFile\u30af\u30e9\u30b9\u306b\u6e21\u3057\u3066\u5c55\u958b\u3057\u3066\u3044\u307e\u3059\u3002\u5b9f\u306f\u5143\u30cd\u30bf\u306fScala\u3067\u66f8\u3044\u3066\u3044\u305f\u306e\u3067\u3001\u7d50\u679c\u7684\u306b\u306fScala\u304b\u3089Java\u306b\u79fb\u690d\u3059\u308b\u3053\u3068\u3068\u306a\u308a\u307e\u3057\u305f\u3002<br \/>\n<script src=\"https:\/\/gist.github.com\/pandanote-info\/a583141ab8b2c2a00832d4a8702ad6e4.js\"><\/script><\/p>\n<h3>7-zip\u3092\u30b5\u30dd\u30fc\u30c8\u3059\u308bDataSource\u306e\u5b9f\u88c5\u4f8b\u3002<\/h3>\n<p>7-zip\u3092\u30b5\u30dd\u30fc\u30c8\u3059\u308bDataSource\u306e\u5b9f\u88c5\u4f8b\u3068\u3057\u3066\u3001SevenZFileDataSource\u30af\u30e9\u30b9\u3092\u5b9a\u7fa9\u3057\u3001\u4ee5\u4e0b\u306e\u30b3\u30fc\u30c9\u4f8b\u306e\u3088\u3046\u306b\u5b9f\u88c5\u3057\u307e\u3057\u305f\u3002\u3053\u308c\u306fApache Solr\u306eDataImportHandler\u306b\u540c\u68b1\u3055\u308c\u3066\u3044\u308bFileDataSource\u30af\u30e9\u30b9\u3092\u62e1\u5f35\u3057\u305f\u3082\u306e\u3067\u3001\u8aad\u307f\u8fbc\u3093\u3060\u30d5\u30a1\u30a4\u30eb\u306e\u62e1\u5f35\u5b50\u306b\u3088\u3063\u3066\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u52d5\u4f5c\u304c\u5207\u308a\u66ff\u308f\u308a\u307e\u3059\u3002<\/p>\n<ol>\n<li>\u8aad\u307f\u8fbc\u3093\u3060\u30d5\u30a1\u30a4\u30eb\u306e\u62e1\u5f35\u5b50\u304c&#8221;7z&#8221;\u3067\u3042\u3063\u305f\u5834\u5408\u306b\u9650\u308a\u3001\u524d\u7bc0\u3067\u5b9a\u7fa9\u3057\u305fSevenZFileInputStream\u30af\u30e9\u30b9\u3092\u4f7f\u3063\u3066\u5165\u529b\u30b9\u30c8\u30ea\u30fc\u30e0\u3092\u4f5c\u6210\u3057\u307e\u3059\u3002<\/li>\n<li>1.\u4ee5\u5916\u306e\u5834\u5408\u306b\u306f\u62e1\u5f35\u5143\u3067\u3042\u308bFileDataSource\u30af\u30e9\u30b9\u3068\u540c\u3058\u52d5\u4f5c\u3068\u306a\u308a\u307e\u3059\u3002<\/li>\n<\/ol>\n<p><script src=\"https:\/\/gist.github.com\/pandanote-info\/b2345df83de14cd9e95b8412c0eb9879.js\"><\/script><\/p>\n<h3>JAR\u30d5\u30a1\u30a4\u30eb\u306e\u30d3\u30eb\u30c9<\/h3>\n<p>\u4e0a\u8a18\u306e2\u500b\u306e\u30af\u30e9\u30b9\u3092\u307e\u3068\u3081\u305f\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u3092\u4f5c\u6210\u3057\u3001JAR\u30d5\u30a1\u30a4\u30eb\u3092\u30d3\u30eb\u30c9\u3057\u307e\u3059\u3002<\/p>\n<p>\u306a\u304a\u3001\u4f5c\u6210\u3057\u305f\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u306fGitHub\u306b\u7f6e\u304d\u307e\u3057\u305f\u3002\u4ee5\u4e0b\u306eURL\u3067\u53d6\u5f97\u3067\u304d\u307e\u3059\u3002<\/p>\n<p><a href=\"https:\/\/github.com\/pandanote-info\/SevenZDataImporter\">https:\/\/github.com\/pandanote-info\/SevenZDataImporter<\/a><\/p>\n<p>\u3053\u3053\u3067\u3082\u3001<del datetime=\"2018-08-06T13:38:18+00:00\">\u30d8\u30bf\u30ec\u3066<\/del>\u3067\u304d\u308b\u3060\u3051\u65e9\u304f\u78ba\u5b9f\u306b\u52d5\u4f5c\u3055\u305b\u308b\u3053\u3068\u3092\u512a\u5148\u3057\u3001Eclipse+Maven\u306e\u7d44\u307f\u5408\u308f\u305b\u3067\u30d3\u30eb\u30c9\u74b0\u5883\u3092\u69cb\u7bc9\u3057\u3001\u30d3\u30eb\u30c9\u3059\u308b\u3053\u3068\u3068\u3057\u307e\u3057\u305f\u3002<\/p>\n<p>\u30d3\u30eb\u30c9\u304c\u7d42\u308f\u3063\u305f\u3089\u3001\u3067\u304d\u3042\u304c\u3063\u305fJAR\u30d5\u30a1\u30a4\u30eb\u3092DataImportHandler\u304c\u3042\u308b\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\u3068\u540c\u3058\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\u306b\u30b3\u30d4\u30fc\u3057\u3066\u304a\u304d\u307e\u3059\u3002<\/p>\n<h2>DataImportHandler\u53ca\u3073\u95a2\u9023\u3057\u305f\u8a2d\u5b9a\u3002<\/h2>\n<p>7-zip\u306e\u30b5\u30dd\u30fc\u30c8\u7528\u306eJAR\u30d5\u30a1\u30a4\u30eb\u3092\u8ffd\u52a0\u3057\u305f\u3089\u3001\u6b21\u306fDataImportHandler\u672c\u4f53\u306e\u8a2d\u5b9a\u3068JAR\u30d5\u30a1\u30a4\u30eb\u8aad\u307f\u8fbc\u307f\u306e\u305f\u3081\u306eApache Solr\u306e\u8a2d\u5b9a\u30d5\u30a1\u30a4\u30eb(solrconfig.xml)\u306e\u8a18\u8ff0\u3092\u884c\u3044\u307e\u3059\u3002<\/p>\n<h3>DataImportHandler\u672c\u4f53\u306e\u8a2d\u5b9a\u3002<\/h3>\n<p>\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u8a2d\u5b9a\u30d5\u30a1\u30a4\u30eb(dih-config.xml)\u3092\u8a18\u8ff0\u3057\u307e\u3059\u3002<\/p>\n<p><script src=\"https:\/\/gist.github.com\/pandanote-info\/6f1c112bf3281b0a6cf21594f9cb5f1d.js\"><\/script><\/p>\n<p>\u6ce8\u610f\u304c\u5fc5\u8981\u306a\u70b9\u306f\u4ee5\u4e0b\u306e\u901a\u308a\u3067\u3059\u3002<\/p>\n<ol>\n<li>dataSource\u30bf\u30b0\u306etype\u5c5e\u6027\u306b\u306f\u3001\u4eca\u56de\u4f5c\u6210\u3057\u305fDataSource\u306e\u62e1\u5f35\u30af\u30e9\u30b9(SevenZFileDataSource\u30af\u30e9\u30b9)\u3092<strong>\u30d1\u30c3\u30b1\u30fc\u30b8\u540d\u3082\u542b\u3081\u3066<\/strong>\u6307\u5b9a\u3057\u307e\u3059\u3002<\/li>\n<li>\u30a4\u30f3\u30dd\u30fc\u30c8\u306e\u5bfe\u8c61\u3068\u306a\u308b\u30c7\u30fc\u30bf\u306f\u30b5\u30fc\u30d0\u5074\u306e\u30ea\u30bd\u30fc\u30b9\u3068\u3057\u3066\u8aad\u307f\u8fbc\u3080\u3053\u3068\u3068\u3057\u3001\u30c7\u30fc\u30bf\u306e\u7f6e\u304d\u5834\u6240(\u672c\u8a18\u4e8b\u306e\u8a2d\u5b9a\u3067\u306f7-zip\u3067\u5727\u7e2e\u3055\u308c\u3066\u3044\u308b\u30d5\u30a1\u30a4\u30eb\u304c\u3042\u308b\u30c7\u30a3\u30ec\u30af\u30c8\u30ea)\u306fApache Solr\u306e\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u5148\u306e\u30c7\u30a3\u30ec\u30af\u30c8\u30ea(solr.install.dir\u30d7\u30ed\u30d1\u30c6\u30a3\u306b\u30bb\u30c3\u30c8\u3055\u308c\u3066\u3044\u307e\u3059\u3002)\u304b\u3089\u306e\u76f8\u5bfe\u30d1\u30b9\u3067\u6307\u5b9a\u3057\u3066\u3044\u307e\u3059\u3002<\/li>\n<\/ol>\n<p>\u8a18\u8ff0\u304c\u7d42\u308f\u3063\u305f\u3089\u3001dih-config.xml\u30d5\u30a1\u30a4\u30eb\u3092\u30a4\u30f3\u30dd\u30fc\u30c8\u3057\u305f\u3044\u30b3\u30a2\u306e\u30a4\u30f3\u30b9\u30bf\u30f3\u30b9\u304c\u4f5c\u6210\u3055\u308c\u3066\u3044\u308b\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\u306econf\u306e\u4e0b\u306b\u7f6e\u304d\u307e\u3059\u3002<\/p>\n<h3>solrconfig.xml\u306e\u8a2d\u5b9a\u3002<\/h3>\n<p>\u524d\u9805\u3067\u8a2d\u5b9a\u3057\u305fdih-config.xml\u30d5\u30a1\u30a4\u30eb\u3092\u8aad\u307f\u8fbc\u3080\u305f\u3081\u306e\u8a2d\u5b9a\u3092\u30a4\u30f3\u30dd\u30fc\u30c8\u3057\u305f\u3044\u30b3\u30a2\u306esolrconfig.xml\u306b\u8ffd\u8a18\u3057\u307e\u3059\u3002\u8ffd\u8a18\u3057\u305f\u8a2d\u5b9a\u306f\u4ee5\u4e0b\u306e\u901a\u308a\u3067\u3059\u3002<\/p>\n<p><script src=\"https:\/\/gist.github.com\/pandanote-info\/8a6ea76dc2dd4b676eeef075b79d37fc.js\"><\/script><\/p>\n<p>\u4e0a\u8a18\u306e\u8a2d\u5b9a\u3092solrconfig.xml\u306econfig\u30bf\u30b0\u306e\u5185\u5074\u306b\u8a18\u8ff0\u3057\u307e\u3059\u3002<\/p>\n<h2>\u8a66\u904b\u8ee2\u3057\u3066\u307f\u305f\u3002<\/h2>\n<h3>DataImportHandler\u306e\u8a66\u904b\u8ee2\u3002<\/h3>\n<p>\u8a66\u3057\u306b\u65e5\u672c\u8a9e\u7248Wikipedia\u306e\u30c0\u30f3\u30d7\u30d5\u30a1\u30a4\u30eb\u304b\u3089\u5fc5\u8981\u305d\u3046\u306a\u30c7\u30fc\u30bf\u3092\u53d6\u308a\u51fa\u3057\u3066\u3001\u4f5c\u6210\u3057\u305f\u30b3\u30a2\u306b\u30a4\u30f3\u30dd\u30fc\u30c8\u3057\u3066\u307f\u307e\u3057\u305f\u3002<\/p>\n<p>DataHandler\u3092\u7528\u3044\u3066\u30a4\u30f3\u30dd\u30fc\u30c8\u3092\u884c\u3046\u305f\u3081\u306b\u306f\u3001\u4ee5\u4e0b\u306e\u30b3\u30de\u30f3\u30c9\u3092\u5b9f\u884c\u3057\u307e\u3059\u3002<\/p>\n<div class=\"code\">[panda@pandanote.info refsearch]$ curl &apos;http:\/\/localhost:8983\/solr\/panda\/dataimport?command=full-import&#038;clean=true&#038;commit=true&apos;<br \/>\n{<br \/>\n  &#8220;responseHeader&#8221;:{<br \/>\n    &#8220;status&#8221;:0,<br \/>\n    &#8220;QTime&#8221;:52},<br \/>\n  &#8220;initArgs&#8221;:[<br \/>\n    &#8220;defaults&#8221;,[<br \/>\n      &#8220;config&#8221;,&#8221;dih-config.xml&#8221;]],<br \/>\n  &#8220;command&#8221;:&#8221;full-import&#8221;,<br \/>\n  &#8220;status&#8221;:&#8221;idle&#8221;,<br \/>\n  &#8220;importResponse&#8221;:&#8221;&#8221;,<br \/>\n  &#8220;statusMessages&#8221;:{}}<\/div>\n<p>&nbsp;<br \/>\n\u30a4\u30f3\u30dd\u30fc\u30c8\u306e\u9014\u4e2d\u7d4c\u904e\u3092\u8abf\u3079\u308b\u305f\u3081\u306b\u306f\u4ee5\u4e0b\u306e\u30b3\u30de\u30f3\u30c9\u3092\u5b9f\u884c\u3059\u308b\u306e\u3067\u3059\u304c\u2026<\/p>\n<div class=\"code\">[panda@pandanote.info refsearch]$ curl &apos;http:\/\/localhost:8983\/solr\/panda\/dataimport?command=status&apos;<\/div>\n<p>&nbsp;<br \/>\n\u30a4\u30f3\u30dd\u30fc\u30c8\u304c\u7d42\u4e86\u3059\u308b\u307e\u3067\u306e\u9593\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306a\u611f\u3058\u306e\u30ec\u30b9\u30dd\u30f3\u30b9\u304c\u8fd4\u3055\u308c\u307e\u3059\u3002<\/p>\n<div class=\"code\">[panda@pandanote.info refsearch]$ curl &apos;http:\/\/localhost:8983\/solr\/panda\/dataimport?command=status&apos;<br \/>\n{<br \/>\n  &#8220;responseHeader&#8221;:{<br \/>\n    &#8220;status&#8221;:0,<br \/>\n    &#8220;QTime&#8221;:0},<br \/>\n  &#8220;initArgs&#8221;:[<br \/>\n    &#8220;defaults&#8221;,[<br \/>\n      &#8220;config&#8221;,&#8221;dih-config.xml&#8221;]],<br \/>\n  &#8220;command&#8221;:&#8221;status&#8221;,<br \/>\n  &#8220;status&#8221;:&#8221;busy&#8221;,<br \/>\n  &#8220;importResponse&#8221;:&#8221;A command is still running&#8230;&#8221;,<br \/>\n  &#8220;statusMessages&#8221;:{<br \/>\n    &#8220;Time Elapsed&#8221;:&#8221;0:0:26.222&#8243;,<br \/>\n    &#8220;Total Requests made to DataSource&#8221;:&#8221;0&#8243;,<br \/>\n    &#8220;Total Rows Fetched&#8221;:&#8221;2600&#8243;,<br \/>\n    &#8220;Total Documents Processed&#8221;:&#8221;2598&#8243;,<br \/>\n    &#8220;Total Documents Skipped&#8221;:&#8221;0&#8243;,<br \/>\n    &#8220;Full Dump Started&#8221;:&#8221;2018-08-04 14:27:15&#8243;}}<\/div>\n<p>&nbsp;<br \/>\n\u30a4\u30f3\u30dd\u30fc\u30c8\u304c\u7d42\u4e86\u3059\u308b\u3068\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306a\u7d50\u679c\u304c\u8fd4\u3055\u308c\u307e\u3059\u3002<\/p>\n<div class=\"code\">[panda@pandanote.info refsearch]$ curl &apos;http:\/\/localhost:8983\/solr\/panda\/dataimport?command=status&apos;<br \/>\n{<br \/>\n  &#8220;responseHeader&#8221;:{<br \/>\n    &#8220;status&#8221;:0,<br \/>\n    &#8220;QTime&#8221;:3},<br \/>\n  &#8220;initArgs&#8221;:[<br \/>\n    &#8220;defaults&#8221;,[<br \/>\n      &#8220;config&#8221;,&#8221;dih-config.xml&#8221;]],<br \/>\n  &#8220;command&#8221;:&#8221;status&#8221;,<br \/>\n  &#8220;status&#8221;:&#8221;idle&#8221;,<br \/>\n  &#8220;importResponse&#8221;:&#8221;&#8221;,<br \/>\n  &#8220;statusMessages&#8221;:{<br \/>\n    &#8220;Total Requests made to DataSource&#8221;:&#8221;0&#8243;,<br \/>\n    &#8220;Total Rows Fetched&#8221;:&#8221;2343194&#8243;,<br \/>\n    &#8220;Total Documents Processed&#8221;:&#8221;2343148&#8243;,<br \/>\n    &#8220;Total Documents Skipped&#8221;:&#8221;0&#8243;,<br \/>\n    &#8220;Full Dump Started&#8221;:&#8221;2018-08-04 14:27:15&#8243;,<br \/>\n    &#8220;&#8221;:&#8221;Indexing completed. Added\/Updated: 2343148 documents. Deleted 0 documents.&#8221;,<br \/>\n    &#8220;Committed&#8221;:&#8221;2018-08-04 16:53:45&#8243;,<br \/>\n    &#8220;Time taken&#8221;:&#8221;2:26:29.709&#8243;}}<\/div>\n<p>&nbsp;<br \/>\n&#8220;Total Rows Fetched&#8221;\u3068&#8221;Total Documents Processed&#8221;\u306e\u6570\u306b\u5dee\u304c\u3042\u308b\u306e\u304c\u3061\u3087\u3063\u3068\u6c17\u306b\u306f\u306a\u308a\u307e\u3059\u304c\u3001\u3053\u306e\u5dee\u5206\u3068\u4eca\u56de\u4f7f\u7528\u3057\u305f\u65e5\u672c\u8a9e\u7248\u306eWikipedia\u306e\u30c0\u30f3\u30d7\u30d5\u30a1\u30a4\u30eb\u306e\u500b\u6570\u304c(\u305f\u307e\u305f\u307e\u304b\u3082\u3057\u308c\u307e\u305b\u3093\u304c)\u4e00\u81f4\u3059\u308b\u306e\u3067\u3001\u305d\u3046\u3044\u3046\u3082\u306e\u304c\u4e00\u7dd2\u304f\u305f\u306b\u306a\u3063\u3066\u30ab\u30a6\u30f3\u30c8\u3055\u308c\u3066\u3044\u308b\u3093\u3060\u308d\u3046\u306a\u3041\u2026\u3068\u4f55\u306e\u6839\u62e0\u3082\u306a\u304f\u63a8\u6e2c\u3057\u3066\u3053\u3053\u3067\u306f\u3072\u3068\u307e\u305a\u554f\u984c\u8996\u3057\u306a\u3044\u3053\u3068\u306b\u3057\u307e\u3059\u3002<\/p>\n<p>\u4e0a\u8a18\u306e\u30a4\u30f3\u30dd\u30fc\u30c8\u306e\u5b9f\u884c\u6642\u306b&#8217;commit=true&#8217;\u3092\u30af\u30a8\u30ea\u6587\u5b57\u5217\u306b\u6307\u5b9a\u3057\u3066\u3044\u308b\u306e\u3067\u3059\u304c\u3001Apache Solr\u306eAdmin\u753b\u9762\u306e&#8221;Overview&#8221;\u306e&#8221;Statistics&#8221;\u306e&#8221;Current&#8221;\u306e\u9805\u76ee\u304c&#8221;false&#8221;\u306e\u307e\u307e\u3067\u5909\u5316\u3057\u306a\u304b\u3063\u305f\u306e\u3067\u3001\u4ee5\u4e0b\u306e\u30b3\u30de\u30f3\u30c9\u3092\u5b9f\u884c\u3057\u307e\u3059\u3002<\/p>\n<div class=\"code\">[panda@pandanote.info refsearch]$ curl -X GET &apos;http:\/\/localhost:8983\/solr\/panda\/update?commit=true&apos;<br \/>\n{<br \/>\n  &#8220;responseHeader&#8221;:{<br \/>\n    &#8220;status&#8221;:0,<br \/>\n    &#8220;QTime&#8221;:735}}<\/div>\n<p>&nbsp;<br \/>\n\u3059\u308b\u3068\u3001Apache Solr\u306eAdmin\u753b\u9762\u306e&#8221;Overview&#8221;\u306e&#8221;Statistics&#8221;\u306e&#8221;Current&#8221;\u306e\u9805\u76ee\u304c&#8221;true&#8221;\u306b\u5909\u5316\u3057\u307e\u3059(\u4e0b\u56f3\u306e\u8d64\u77e2\u5370)\u3002<br \/>\n<a href=\"https:\/\/pandanote.info\/?attachment_id=2484\" rel=\"attachment wp-att-2484\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/pandanote.info\/wordpress\/wp-content\/uploads\/2018\/08\/lucene_kuromoji_scene2-1-1024x487.png\" alt=\"\" width=\"665\" height=\"316\" class=\"alignnone size-large wp-image-2484\" srcset=\"https:\/\/pandanote.info\/wordpress\/wp-content\/uploads\/2018\/08\/lucene_kuromoji_scene2-1-1024x487.png 1024w, https:\/\/pandanote.info\/wordpress\/wp-content\/uploads\/2018\/08\/lucene_kuromoji_scene2-1-300x143.png 300w, https:\/\/pandanote.info\/wordpress\/wp-content\/uploads\/2018\/08\/lucene_kuromoji_scene2-1-768x365.png 768w, https:\/\/pandanote.info\/wordpress\/wp-content\/uploads\/2018\/08\/lucene_kuromoji_scene2-1-660x314.png 660w, https:\/\/pandanote.info\/wordpress\/wp-content\/uploads\/2018\/08\/lucene_kuromoji_scene2-1.png 1221w\" sizes=\"auto, (max-width: 665px) 100vw, 665px\" \/><\/a><\/p>\n<h3>\u691c\u7d22\u306e\u8a66\u904b\u8ee2\u3002<\/h3>\n<p>\u8a66\u3057\u306bApache Solr\u306eAdmin\u753b\u9762\u306e&#8221;Query&#8221;\u3067\u3001\u300c\u767d\u91d1\u9ad8\u8f2a\u99c5\u300d\u3092\u30ad\u30fc\u30ef\u30fc\u30c9\u3068\u3057\u3066\u691c\u7d22\u3057\u3066\u307f\u307e\u3059\u3002<br \/>\n<a href=\"https:\/\/pandanote.info\/?attachment_id=2485\" rel=\"attachment wp-att-2485\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/pandanote.info\/wordpress\/wp-content\/uploads\/2018\/08\/lucene_update_scene3-1-1024x517.png\" alt=\"\" width=\"665\" height=\"336\" class=\"alignnone size-large wp-image-2485\" srcset=\"https:\/\/pandanote.info\/wordpress\/wp-content\/uploads\/2018\/08\/lucene_update_scene3-1-1024x517.png 1024w, https:\/\/pandanote.info\/wordpress\/wp-content\/uploads\/2018\/08\/lucene_update_scene3-1-300x151.png 300w, https:\/\/pandanote.info\/wordpress\/wp-content\/uploads\/2018\/08\/lucene_update_scene3-1-768x388.png 768w, https:\/\/pandanote.info\/wordpress\/wp-content\/uploads\/2018\/08\/lucene_update_scene3-1-660x333.png 660w, https:\/\/pandanote.info\/wordpress\/wp-content\/uploads\/2018\/08\/lucene_update_scene3-1.png 1226w\" sizes=\"auto, (max-width: 665px) 100vw, 665px\" \/><\/a><br \/>\n\u691c\u7d22\u7d50\u679c\u306e\u5148\u982d\u306b\u767d\u91d1\u9ad8\u8f2a\u99c5\u3068\u306f\u4e00\u898b\u306a\u3093\u306e\u95a2\u4fc2\u3082\u306a\u3055\u305d\u3046\u306a\u5efa\u7269\u304c\u767b\u5834\u3057\u3066\u3044\u307e\u3059\u304c\u3001\u3053\u306e\u5efa\u7269\u306f\u767d\u91d1\u9ad8\u8f2a\u99c5\u76f4\u7d50\u306e\u518d\u958b\u767a\u30a8\u30ea\u30a2\u306e\u4e00\u89d2\u306b\u5efa\u3063\u3066\u3044\u308b\u30d3\u30eb\u3067\u3059\u3002\u307e\u305f\u3001\u4e0a\u56f3\u3067\u306f\u8868\u793a\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u304c\u3001\u3053\u306e\u8a18\u4e8b\u306e\u5f8c\u308d\u306e\u65b9\u306b\u300c\u767d\u91d1\u9ad8\u8f2a\u99c5\u300d\u306e\u6587\u5b57\u5217\u304c\u767b\u5834\u3057\u3066\u3044\u307e\u3059\u3002\u3088\u3063\u3066\u3001\u691c\u7d22\u30a8\u30f3\u30b8\u30f3\u7528\u306e\u30a4\u30f3\u30c7\u30c3\u30af\u30b9\u306f\u6b63\u5e38\u306b\u751f\u6210\u3067\u304d\u3066\u3044\u308b\u3082\u306e\u3068\u5224\u65ad\u3067\u304d\u307e\u3059\u3002<\/p>\n<h2>\u307e\u3068\u3081<\/h2>\n<p>\u3053\u306e\u8a18\u4e8b\u3067\u306f\u3001DataImportHandler\u3068\u305d\u306e\u62e1\u5f35\u4f8b\u306b\u3064\u3044\u3066\u66f8\u304d\u307e\u3057\u305f\u3002<\/p>\n<p>\u4eca\u56de\u306e\u62e1\u5f35\u7528\u306e\u30b3\u30fc\u30c9\u306f\u78ba\u5b9f\u306b\u52d5\u4f5c\u3055\u305b\u308b\u3053\u3068\u3092\u512a\u5148\u3055\u305b\u305f\u305f\u3081\u306b\u3001\u6700\u8fd1\u63a8\u3057\u3066\u3044\u308bScala\u3067\u306f\u306a\u304fJava\u3067\u8a18\u8ff0\u3057\u3066\u3057\u307e\u3044\u307e\u3057\u305f\u304c\u3001\u6298\u3092\u898b\u3066Scala\u306b\u66f8\u304d\u63db\u3048\u308b\u4e88\u5b9a\u3067\u3059\u3002<\/p>\n<p>\u3053\u306e\u8a18\u4e8b\u306f\u4ee5\u4e0a\u3067\u3059\u3002<\/p>\n<h3>pom.xml\u306e\u5909\u66f4[2019\/10\/22\u8ffd\u8a18]<\/h3>\n<p>commons-compress\u306b\u8106\u5f31\u6027\u304c\u898b\u3064\u304b\u3063\u305f\u3068\u306e\u3053\u3068\u306a\u306e\u3067\u3001pom.xml\u306e\u8a18\u8ff0\u3092\u5909\u66f4\u3057\u307e\u3057\u305f\u3002<\/p>\n<h2>\u53c2\u8003\u6587\u732e<\/h2>\n<ul>\n<li><a href=\"http:\/\/blog.thedigitalgroup.com\/data-import-handler-import-data-from-xml-files-which-are-in-solr-xml-format\">Data Import Handler \u2013 import data from XML files which are in Solr xml format<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>\u306f\u3058\u3081\u306b \u524d\u306e\u8a18\u4e8b\u3067\u3001NEologd\u306e\u5165\u3063\u3066\u3044\u308bkuromoji\u3092\u7d44\u307f\u8fbc\u3093\u3066\u307f\u307e\u3057\u305f\u306e\u3067\u3001\u6b21\u306e\u95a2\u9580\u306b\u6311\u307f\u305f\u3044\u3068\u601d\u3044\u307e\u3059\u3002 \u5b9f\u306f\u3001\u30a4\u30f3\u30c7\u30c3\u30af\u30b9\u3092\u884c\u3046\u5bfe\u8c61\u3068\u306a\u308b\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u304c7-zip\u3067\u5727\u7e2e\u3055\u308c\u3066\u304a\u308a\u307e\u3057\u3066\u3001\u3053\u308c\u304c\u3088\u3093\u3069\u3053\u308d\u306a\u3044\u4e8b\u60c5\u306b\u3088\u308a\u5c55\u958b\u3057\u3066\u4f7f\u3046\u306e\u304c\u96e3\u3057\u3044\u305f\u3081\u3001Apache Solr\u306b\u306f\u3067\u304d\u308c\u3070\u30b7\u30a7\u30eb\u306e\u30b3\u30de\u30f3\u30c9\u30d7\u30ed\u30f3\u30d7\u30c8\u304b\u3089 $ 7z x somefile.7z &nbsp; \u3068\u5b9f\u884c\u5f8c\u306bPostT\u2026 <span class=\"read-more\"><a href=\"https:\/\/pandanote.info\/?p=2462\">Read More &raquo;<\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":2485,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[35,19,8,26,15],"tags":[],"class_list":["post-2462","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-apache-solr","category-eclipse","category-fedora","category-github","category-pc"],"_links":{"self":[{"href":"https:\/\/pandanote.info\/index.php?rest_route=\/wp\/v2\/posts\/2462","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/pandanote.info\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/pandanote.info\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/pandanote.info\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/pandanote.info\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2462"}],"version-history":[{"count":23,"href":"https:\/\/pandanote.info\/index.php?rest_route=\/wp\/v2\/posts\/2462\/revisions"}],"predecessor-version":[{"id":5444,"href":"https:\/\/pandanote.info\/index.php?rest_route=\/wp\/v2\/posts\/2462\/revisions\/5444"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/pandanote.info\/index.php?rest_route=\/wp\/v2\/media\/2485"}],"wp:attachment":[{"href":"https:\/\/pandanote.info\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2462"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/pandanote.info\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2462"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/pandanote.info\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2462"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}