{"id":2215,"date":"2023-05-03T20:51:03","date_gmt":"2023-05-03T12:51:03","guid":{"rendered":"https:\/\/www.appblog.cn\/?p=2215"},"modified":"2023-05-04T05:42:12","modified_gmt":"2023-05-03T21:42:12","slug":"springboot-lucene-chapter-4-getting-started-code","status":"publish","type":"post","link":"https:\/\/www.appblog.cn\/index.php\/2023\/05\/03\/springboot-lucene-chapter-4-getting-started-code\/","title":{"rendered":"SpringBoot+Lucene\u7b2c\u56db\u7bc7 \u2014 \u5165\u95e8\u4ee3\u7801"},"content":{"rendered":"<p>\u9700\u6c42\uff1a\u901a\u8fc7\u5173\u952e\u5b57\u641c\u7d22\u6587\u4ef6\uff0c\u51e1\u662f\u6587\u4ef6\u540d\u6216\u6587\u4ef6\u5185\u5bb9\u5305\u62ec\u5173\u952e\u5b57\u7684\u6587\u4ef6\u90fd\u9700\u8981\u627e\u51fa\u6765\uff1a\u4e0b\u56fe\uff08\u662f\u4e00\u5806\u6587\u4ef6\u5217\u8868\uff09<\/p>\n<h3>pom.xml<\/h3>\n<pre><code class=\"language-xml\">&lt;dependency&gt;\n    &lt;groupId&gt;org.apache.lucene&lt;\/groupId&gt;\n    &lt;artifactId&gt;lucene-core&lt;\/artifactId&gt;\n    &lt;version&gt;4.10.2&lt;\/version&gt;\n&lt;\/dependency&gt;\n&lt;dependency&gt;\n    &lt;groupId&gt;org.apache.lucene&lt;\/groupId&gt;\n    &lt;artifactId&gt;lucene-analyzers-common&lt;\/artifactId&gt;\n    &lt;version&gt;4.10.2&lt;\/version&gt;\n&lt;\/dependency&gt;\n&lt;dependency&gt;\n    &lt;groupId&gt;org.apache.lucene&lt;\/groupId&gt;\n    &lt;artifactId&gt;lucene-queryparser&lt;\/artifactId&gt;\n    &lt;version&gt;4.10.2&lt;\/version&gt;\n&lt;\/dependency&gt;\n&lt;dependency&gt;\n    &lt;groupId&gt;com.janeluo&lt;\/groupId&gt;\n    &lt;artifactId&gt;ikanalyzer&lt;\/artifactId&gt;\n    &lt;version&gt;2012_u6&lt;\/version&gt;\n&lt;\/dependency&gt;\n\n&lt;!--\u4e2d\u6587\u5206\u8bcd\u5668--&gt;\n&lt;dependency&gt;\n    &lt;groupId&gt;org.apache.lucene&lt;\/groupId&gt;\n    &lt;artifactId&gt;lucene-analyzers-smartcn&lt;\/artifactId&gt;\n    &lt;version&gt;7.6.0&lt;\/version&gt;\n&lt;\/dependency&gt;\n&lt;!--\u6587\u4ef6IO\u64cd\u4f5c--&gt;\n&lt;dependency&gt;\n    &lt;groupId&gt;commons-io&lt;\/groupId&gt;\n    &lt;artifactId&gt;commons-io&lt;\/artifactId&gt;\n    &lt;version&gt;2.6&lt;\/version&gt;\n&lt;\/dependency&gt;<\/code><\/pre>\n<h3>\u4ee3\u7801<\/h3>\n<pre><code class=\"language-java\">import ch.qos.logback.core.net.SyslogOutputStream;\nimport org.apache.commons.io.FileUtils;\nimport org.apache.lucene.analysis.Analyzer;\nimport org.apache.lucene.analysis.standard.StandardAnalyzer;\nimport org.apache.lucene.document.*;\nimport org.apache.lucene.index.*;\nimport org.apache.lucene.search.IndexSearcher;\nimport org.apache.lucene.search.ScoreDoc;\nimport org.apache.lucene.search.TermQuery;\nimport org.apache.lucene.search.TopDocs;\nimport org.apache.lucene.store.Directory;\nimport org.apache.lucene.store.FSDirectory;\nimport org.apache.lucene.util.Version;\nimport org.junit.Test;\n\nimport java.io.File;\n\npublic class FileTest {\n    \/**\n     * \u521b\u5efa\u7d22\u5f15\n     * @throws Exception\n     *\/\n    @Test\n    public void createIndex() throws Exception{\n        \/\/\u7d22\u5f15\u5e93\u5b58\u653e\u7684\u4f4d\u7f6e\uff0c\u4e5f\u53ef\u4ee5\u653e\u5728\u786c\u76d8\n        Directory directory = FSDirectory.open(new File(&quot;.\/index&quot;));\n        \/\/\u6807\u51c6\u7684\u5206\u8bcd\u5668\n        Analyzer analyzer = new StandardAnalyzer();\n        \/\/\u521b\u5efa\u8f93\u51fa\u6d41write\n        IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_4_10_2, analyzer);\n        IndexWriter indexWriter = new IndexWriter(directory, config);\n\n        \/\/\u521b\u5efaFiled\u57df\n        File f = new File(&quot;F:\\\\a&quot;);\n        \/\/\u627e\u5230\u4e0b\u9762\u7684\u6240\u6709\u5f85\u641c\u7d22\u7684\u6587\u4ef6\n        File[] listFiles = f.listFiles();\n        for (File file:listFiles) {\n            \/\/\u521b\u5efa\u6587\u6863\u5bf9\u8c61\n            Document document = new Document();\n            \/\/\u6587\u4ef6\u540d\u79f0\n            String file_name = file.getName();\n            Field fileNameFiled=new TextField(&quot;fileName&quot;, file_name, Field.Store.YES);\n            \/\/\u6587\u4ef6\u5927\u5c0f\n            long file_size = FileUtils.sizeOf(file);\n            Field fileSizeField = new LongField(&quot;fileSize&quot;, file_size,Field.Store.YES);\n            \/\/\u6587\u4ef6\u8def\u5f84\n            String file_path = file.getPath();\n            Field filePathField = new StoredField(&quot;filePath&quot;, file_path);\n            \/\/\u6587\u4ef6\u5185\u5bb9\n            String file_content = FileUtils.readFileToString(file, &quot;utf8&quot;);\n            Field fileContentField = new TextField(&quot;fileContent&quot;, file_content, Field.Store.YES);\n\n            \/\/\u4fdd\u5b58\u5230\u6587\u4ef6\u5bf9\u8c61\u91cc\n            document.add(fileNameFiled);\n            document.add(fileSizeField);\n            document.add(filePathField);\n            document.add(fileContentField);\n\n            \/\/\u5199\u5230\u7d22\u5f15\u5e93\n            indexWriter.addDocument(document);\n        }\n        \/\/\u5173\u95ed\n        indexWriter.close();\n    }\n\n    \/**\n     * \u67e5\u8be2\u7d22\u5f15\n     * @throws Exception\n     *\/\n    @Test\n    public void searchIndex() throws Exception{\n        \/\/\u7b2c\u4e00\u6b65\uff0c\u67e5\u8be2\u51c6\u5907\u5de5\u4f5c\uff0c\u521b\u5efaDirectory\u5bf9\u8c61\n        Directory dir = FSDirectory.open(new File(&quot;.\/index&quot;));\n        \/\/\u521b\u5efaIndexReader\u5bf9\u8c61\n        IndexReader reader = DirectoryReader.open(dir);\n        \/\/\u521b\u5efaIndexSearch\u5bf9\u8c61\n        IndexSearcher search = new IndexSearcher(reader);\n\n        \/\/\u7b2c\u4e8c\u6b65\uff0c\u95ef\u5c06\u67e5\u8be2\u6761\u4ef6\u5bf9\u8c61\n        TermQuery query = new TermQuery(new Term(&quot;fileContent&quot;, &quot;what&quot;));\n        \/\/\u7b2c\u4e09\u6b65\uff1a\u6267\u884c\u67e5\u8be2\uff0c\u53c2\u6570\uff081\uff1a\u67e5\u8be2\u6761\u4ef6\u5bf9\u8c61\uff0c2\uff1a\u67e5\u8be2\u7ed3\u679c\u8fd4\u56de\u7684\u6700\u5927\u503c\uff09\n        TopDocs topDocs = search.search(query, 10);\n        \/\/\u7b2c\u56db\u6b65\uff1a\u5904\u7406\u67e5\u8be2\u7ed3\u679c\n        \/\/\u8f93\u51fa\u7ed3\u679c\u6570\u91cf\n        System.out.print(&quot;\u67e5\u8be2\u7ed3\u679c\u6570\u91cf\uff1a&quot; + topDocs.totalHits);\n        \/\/\u53d6\u5f97\u7ed3\u679c\u96c6\n        ScoreDoc[] scoreDocs = topDocs.scoreDocs;\n        for (ScoreDoc scoreDoc:scoreDocs) {\n            System.out.println(&quot;\u5f53\u524ddoc\u5f97\u5206:&quot; + scoreDoc.score);\n            \/\/\u6839\u636e\u6587\u6863\u5bf9\u8c61ID\u53d6\u5f97\u6587\u6863\u5bf9\u8c61\n            Document doc=search.doc(scoreDoc.doc);\n            System.out.println(&quot;\u6587\u4ef6\u540d\u79f0\uff1a&quot; + doc.get(&quot;fileName&quot;));\n            System.out.println(&quot;\u6587\u4ef6\u8def\u5f84\uff1a&quot; + doc.get(&quot;filePath&quot;));\n            System.out.println(&quot;\u6587\u4ef6\u5927\u5c0f\uff1a&quot; + doc.get(&quot;fileSize&quot;));\n            System.out.println(&quot;=======================================&quot;);\n        }\n        \/\/\u5173\u95edIndexReader\u5bf9\u8c61\n        reader.close();\n    }\n}<\/code><\/pre>\n<p><code>searchIndex()<\/code>\u65b9\u6cd5\u8fd0\u884c\u540e\u51fa\u73b0\u7c7b\u4f3c\u7684\u7d22\u5f15\u5e93\uff0c\u5219\u8868\u793a\u6210\u529f<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.appblog.cn\/wp-content\/uploads\/2023\/05\/SpringBootLucene\u5206\u8bcd\u67e5\u8be2\u6d4b\u8bd5\u4ee3\u7801.png\" alt=\"\" \/><\/p>\n<p><code>searchIndex()<\/code>\u6267\u884c\u76f8\u5e94\u7684\u641c\u7d22\u6761\u4ef6\u4e4b\u540e\uff1a<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.appblog.cn\/wp-content\/uploads\/2023\/05\/SpringBootLucene\u5206\u8bcd\u67e5\u8be2\u7ed3\u679c.png\" alt=\"\" \/><\/p>\n<p>\u901a\u8fc7\u4ee5\u4e0a\u7684\u4e24\u6bb5\u4ee3\u7801\u6211\u4eec\u5b9e\u73b0\u4e86\u521b\u5efa\u7d22\u5f15\u4e0e\u67e5\u8be2\u7d22\u5f15<\/p>\n<p>\u7b2c\u4e00\u6bb5\u4ee3\u7801\u505a\u4e86\u8fd9\u4e48\u51e0\u4e2a\u4e8b\uff1a<\/p>\n<ul>\n<li>\u5c06\u6211\u4eec\u8981\u67e5\u8be2\u7684\u6bcf\u4e2a\u6587\u6863\uff0c\u6784\u5efa\u4e86\u6587\u6863\u5bf9\u8c61\u3002\u6587\u6863\u5bf9\u8c61\u91cc\u9762\u5b58\u653e\u7684\u5c31\u662f\u8be5\u6587\u6863\u7684\u4fe1\u606f\uff08\u6587\u4ef6\u540d\uff0c\u5927\u5c0f\uff0c\u5185\u5bb9\uff0c\u8def\u5f84\u7b49\uff09<\/li>\n<li>\u5c06\u8be5\u6587\u6863\u5bf9\u8c61\u6254\u8fdb\u7d22\u5f15\u5e93\uff08\u81ea\u52a8\u521b\u5efa\u4e86\u7d22\u5f15\uff09<\/li>\n<li>\u7d22\u5f15\u5e93\u5b58\u653e\u5728<code>.\/index<\/code>\u76ee\u5f55\u4e0b<\/li>\n<\/ul>\n<p>\u7b2c\u4e8c\u6bb5\u4ee3\u7801\uff1a<\/p>\n<p>\u5c31\u662f\u5230\u7d22\u5f15\u5e93\u7684\u76ee\u5f55\u4e0b\uff0c\u627efileContent\u91cc\u9762\u6709<code>whatt<\/code>\u7684\u6587\u6863\uff0c\u7136\u540e\u8f93\u51fa\u4e86\u8be5\u6587\u6863\u7684\u4fe1\u606f<\/p>\n<p>\u4e2d\u6587\u5206\u8bcd\u5668\uff1a<\/p>\n<p>\u6211\u4eec\u8fd8\u662f\u9762\u4e34\u4e00\u4e2a\u95ee\u9898\uff1a\u5982\u4f55\u901a\u8fc7\u201c\u5168\u6587\u201d \u641c\u5230\u6211\u4eec\u60f3\u8981\u7684\u201c\u5168\u6587\u68c0\u7d22.txt\u201d\u6587\u6863\uff1f<\/p>\n<p>\u6211\u4eec\u901a\u8fc7lukeall\u67e5\u770b\u7d22\u5f15\uff0c\u627e\u5230\u4e86\u539f\u56e0\u3002\u90a3\u5c31\u662f\u6ca1\u6709\u6b63\u786e\u7684\u5206\u8bcd\uff0c\u662f\u56e0\u4e3a\u6211\u4eec\u5728\u4ee3\u7801\u4e2d\u4f7f\u7528\u7684\u662f\u5b98\u65b9\u63a8\u8350\u7684\u6807\u51c6\u5206\u8bcd\u5668\uff0c\u800c\u8fd9\u4e2a\u5206\u8bcd\u5668\uff0c\u662f\u8001\u5916\u7684\uff0c\u4e0d\u80fd\u5bf9\u4e2d\u6587\u8fdb\u884c\u5206\u8bcd\uff0c\u6240\u4ee5\u6211\u4eec\u8981\u4f7f\u7528\u4e2d\u6587\u5206\u8bcd\u5668\u3002\u800c\u73b0\u5728lucene\u7684\u4e2d\u6587\u5206\u8bcd\u5668\uff1aCJK\u8bcd\u5668\uff0csmartChinese\u5206\u8bcd\u5668<\/p>\n<ul>\n<li>CJK\u5206\u8bcd\u5668\uff1a\u662f\u4e8c\u5206\u6cd5\uff1a\u4e3e\u4f8b\uff1a\u6211\u7231\u5199\u4ee3\u7801\uff0c\u5206\u6210\uff1a\u6211\u7231\uff0c\u7231\u5199\uff0c\u5199\u4ee3\uff0c\u4ee3\u7801<\/li>\n<li>smartChinese\uff1a\u6269\u5c55\u6027\u4e0d\u592a\u597d<\/li>\n<li>\u5e02\u573a\u7528\u7684\u6709\uff1a\u5e96\u4e01\u89e3\u725b\uff0cmmseg4j\uff0c\u4f46\u662f\u8fd9\u4e24\u4e2a\u4f5c\u8005\u591a\u5e74\u6ca1\u6709\u66f4\u65b0\u4e86<\/li>\n<\/ul>\n<p>\u8fd9\u91cc\u4e3b\u8981\u4ecb\u7ecdIK\u5206\u8bcd\u5668\u7684\u4f7f\u7528\uff1a<\/p>\n<pre><code class=\"language-xml\">&lt;dependency&gt;\n    &lt;groupId&gt;com.janeluo&lt;\/groupId&gt;\n    &lt;artifactId&gt;ikanalyzer&lt;\/artifactId&gt;\n    &lt;version&gt;2012_u6&lt;\/version&gt;\n&lt;\/dependency&gt;<\/code><\/pre>\n<p>\u4e4b\u524d\u7684\u4ee3\u7801\u91cc\u7528\u7684\u662f\u6807\u51c6\u5206\u8bcd\u5668\uff0c\u8001\u5916\u7684\uff0c\u4e0d\u652f\u6301\u4e2d\u6587\u5206\u8bcd\uff0c\u4e0b\u9762\u6362Ik\u5206\u8bcd\u5668<\/p>\n<pre><code class=\"language-java\">\/\/\u6807\u51c6\u7684\u5206\u8bcd\u5668\n\/\/Analyzer analyzer = new StandardAnalyzer();\n\/\/\u4e0b\u9762\u66ff\u6362\u4e3aik\u5206\u8bcd\u5668\nAnalyzer analyzer = new IKAnalyzer();<\/code><\/pre>\n<p>\u518d\u6267\u884c\u67e5\u8be2\u65b9\u6cd5\uff0c\u53ef\u4ee5\u770b\u5230\u4e2d\u6587\u67e5\u8be2\u6761\u4ef6\u4e5f\u53ef\u4ee5\u7684\u5230\u7ed3\u679c\u5728\u8fd9\u91cc\u63d2\u5165\u56fe\u7247\u63cf\u8ff0<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.appblog.cn\/wp-content\/uploads\/2023\/05\/SpringBootLucene\u4e2d\u6587\u5206\u8bcd\u67e5\u8be2\u7ed3\u679c.png\" alt=\"\" \/><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u9700\u6c42\uff1a\u901a\u8fc7\u5173\u952e\u5b57\u641c\u7d22\u6587\u4ef6\uff0c\u51e1\u662f\u6587\u4ef6\u540d\u6216\u6587\u4ef6\u5185\u5bb9\u5305\u62ec\u5173\u952e\u5b57\u7684\u6587\u4ef6\u90fd\u9700\u8981\u627e\u51fa\u6765\uff1a\u4e0b\u56fe\uff08\u662f\u4e00\u5806\u6587\u4ef6\u5217\u8868\uff09 pom.x [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[560],"tags":[559],"class_list":["post-2215","post","type-post","status-publish","format-standard","hentry","category-lucene","tag-lucene"],"_links":{"self":[{"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/posts\/2215","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/comments?post=2215"}],"version-history":[{"count":0,"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/posts\/2215\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/media?parent=2215"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/categories?post=2215"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/tags?post=2215"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}