理解solr工作原理：lucene

我会带着你远行 2022-11-13 10:28 165阅读 0赞

### 文章目录 ###

*  1, 下载lucene, 获取demo相关jar包
 *  2, 源代码实现明细
 *   *  org.apache.lucene.demo.IndexFiles : StandardAnalyzer index阶段
     *  org.apache.lucene.demo.SearchFiles : StandardAnalyzer query阶段
     *  StandardAnalyzer 中文分词示例: index, query
 *  3, 中文词库下载：同义词，停用词

lucene demo样例演示：如何创建索引，如何检索数据 [https://lucene.apache.org/core/8\_6\_0/demo/index.html][https_lucene.apache.org_core_8_6_0_demo_index.html]

# 1, 下载lucene, 获取demo相关jar包 #

[https://lucene.apache.org/core/downloads.html][https_lucene.apache.org_core_downloads.html]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2V5ZW9mZWFnbGU_size_16_color_FFFFFF_t_70]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2V5ZW9mZWFnbGU_size_16_color_FFFFFF_t_70 1]

# 2, 源代码实现明细 #

配置pom.xml

<dependency>
                <groupId>org.apache.lucene</groupId>
                <artifactId>lucene-demo</artifactId>
                <version>8.6.0</version>
            </dependency>
            
            <dependency>
                <groupId>org.apache.lucene</groupId>
                <artifactId>lucene-core</artifactId>
                <version>8.6.0</version>
            </dependency>
          
            <dependency>
                <groupId>org.apache.lucene</groupId>
                <artifactId>lucene-queryparser</artifactId>
                <version>8.6.0</version>
            </dependency>

## org.apache.lucene.demo.IndexFiles : StandardAnalyzer index阶段 ##

*  使用 StandardAnalyzer 来解析文件内容  
    ![在这里插入图片描述][20210329103134580.png]

// Index all text files under a directory.
    public class IndexFiles { 
      /** Index all text files under a directory. */
      public static void main(String[] args) { 
        //指定源文档的路径：绝对路径 或 相对路径
        //cmd> ls D:\download\lucene-7.7.3\demo\txt\
        // 123.txt 456.txt hello123.txt hello12345678.txt
        String docsPath = "D:\\download\\lucene-7.7.3\\demo\\txt";
        //指定索引存放的位置：绝对路径 或 相对路径
        String indexPath = "D:\\download\\lucene-7.7.3\\demo\\index1";
        //是创建索引/ 还是更新索引
        boolean create = true;
    
        final Path docDir = Paths.get(docsPath);
        Date start = new Date();
        System.out.println("Indexing to directory '" + indexPath + "'...");
    
        Directory indexPathDir = FSDirectory.open(Paths.get(indexPath));
        Analyzer analyzer = new StandardAnalyzer();
        IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
    
        if (create) { 
          // Create a new index in the directory, removing old indexs
          iwc.setOpenMode(OpenMode.CREATE);
        } else { 
          // Add new documents to an existing index:
          iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);
        }
    
        IndexWriter writer = new IndexWriter(indexPathDir, iwc);
        indexDocs(writer, docDir);
    
        // NOTE: if you want to maximize search performance,
        // you can optionally call forceMerge here. This can be
        // a terribly costly operation, so generally it's only
        // worth it when your index is relatively static (ie
        // you're done adding documents to it):
        //
        // writer.forceMerge(1);
        writer.close();
        Date end = new Date();
        System.out.println(end.getTime() - start.getTime() + " total milliseconds");
      }
    
      /** * Indexes the given file using the given writer, or if a directory is given, * * NOTE: This method indexes one document per input file. This is slow. For good * throughput, put multiple documents into your input file(s). An example of this is * in the benchmark module, which can create "line doc" files, one document per line, * using the * <a href="../../../../../contrib-benchmark/org/apache/lucene/benchmark/byTask/tasks/WriteLineDocTask.html" * >WriteLineDocTask</a>. * * @param writer Writer to the index where the given file/dir info will be stored * @param path The file to index, or the directory to recurse into to find files to index */
      static void indexDocs(final IndexWriter writer, Path path) throws IOException { 
        if (Files.isDirectory(path)) { 
          Files.walkFileTree(path, new SimpleFileVisitor<Path>() { 
            @Override
            public FileVisitResult visitFile(Path file, BasicFileAttributes attrs) throws IOException { 
              try { 
                indexDoc(writer, file, attrs.lastModifiedTime().toMillis());
              } catch (IOException ignore) { 
                // don't index files that can't be read.
              }
              return FileVisitResult.CONTINUE;
            }
          });
        } else { 
          indexDoc(writer, path, Files.getLastModifiedTime(path).toMillis());
        }
      }
    
      /** Indexes a single document */
      static void indexDoc(IndexWriter writer, Path file, long lastModified) throws IOException { 
        try (InputStream stream = Files.newInputStream(file)) { 
          // make a new, empty document
          Document doc = new Document();
          
          // Add the path of the file as a field named "path". Use a
          Field pathField = new StringField("path", file.toString(), Field.Store.YES);
          doc.add(pathField);
          
          // Add the last modified date of the file a field named "modified".
          doc.add(new LongPoint("modified", lastModified));
          
          // Add the contents of the file to a field named "contents". Specify a Reader,
          // so that the text of the file is tokenized and indexed, but not stored.
          doc.add(new TextField("contents", new BufferedReader(new InputStreamReader(stream, StandardCharsets.UTF_8))));
          
          if (writer.getConfig().getOpenMode() == OpenMode.CREATE) { 
            // New index, so we just add the document (no old document can be there):
            System.out.println("adding " + file);
            writer.addDocument(doc);
          } else { 
            // Existing index (an old copy of this document may have been indexed) so 
            // we use updateDocument instead to replace the old one matching the exact 
            // path, if present:
            System.out.println("updating " + file);
            writer.updateDocument(new Term("path", file.toString()), doc);
          }
        }
      }
    }

## org.apache.lucene.demo.SearchFiles : StandardAnalyzer query阶段 ##

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2V5ZW9mZWFnbGU_size_16_color_FFFFFF_t_70 2]

// search demo.
    public class SearchFiles { 
        public static void main(String[] args) throws Exception { 
            //指定索引存放的位置：绝对路径 或 相对路径
            String index = "D:\\download\\lucene-7.7.3\\demo\\index1";
            //搜索的文本内容
            String queryString = "hello";
            //搜索的文本内容 --- 从哪个索引字段检索
            String field = "contents";
            //分页大小
            int hitsPerPage = 10;
            //是否查看：更详细的内容( 搜索配置的score )
            boolean raw = true;
    
            IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(index)));
            IndexSearcher searcher = new IndexSearcher(reader);
            Analyzer analyzer = new StandardAnalyzer();
    
            QueryParser parser = new QueryParser(field, analyzer);
            Query query = parser.parse(queryString);
            System.out.println("Searching for: " + query.toString(field));
            doSearch(searcher, query, hitsPerPage, raw);
            reader.close();
        }
    
        //查询
        public static void doSearch(IndexSearcher searcher, Query query, int hitsPerPage, boolean raw) throws IOException { 
            BufferedReader in = new BufferedReader(new InputStreamReader(System.in, StandardCharsets.UTF_8));
            // Collect enough docs to show 5 pages
            TopDocs results = searcher.search(query, 5 * hitsPerPage);
            ScoreDoc[] hits = results.scoreDocs;
    
            int numTotalHits = Math.toIntExact(results.totalHits.value);
            System.out.println(numTotalHits + " total matching documents ");
    
            System.out.println("\n\n>>>>>>>> doc details >>>>>>>>>");
            for (int i = 0; i < numTotalHits; i++) { 
                if (raw) {                               // output raw format
                    System.out.println("doc=" + hits[i].doc + " score=" + hits[i].score);
                    //doc=2 score=0.29767057
                }
    
                Document doc = searcher.doc(hits[i].doc);
                String path = doc.get("path");
                if (path != null) { 
                    System.out.println((i + 1) + ". " + path);
                    //1. D:\download\lucene-7.7.3\demo\txt\hello123.txt
                    String title = doc.get("title");
                    if (title != null) { 
                        System.out.println(" Title: " + doc.get("title"));
                    }
                } else { 
                    System.out.println((i + 1) + ". " + "No path for this document");
                }
              System.out.println();
            }
        }
    }

## StandardAnalyzer 中文分词示例: index, query ##

@org.junit.Test
        public void analyzeTest() throws IOException { 
            StringReader stopwords = new StringReader("the \n bigger");
            StringReader stringReader = new StringReader("The quick BIGGER brown fox jumped over the bigger lazy dog. ");
    
            //StandardAnalyzer: 内置 LowerCaseFilter, StopFilter
            StandardAnalyzer analyzer = new StandardAnalyzer(stopwords);
            TokenStream tokenStream = analyzer.tokenStream("contents, ", stringReader);
            // final StandardTokenizer src = new StandardTokenizer();
            // TokenStream tok = new LowerCaseFilter(src);
            // tok = new StopFilter(tok, stopwords);
            tokenStream.reset();
            CharTermAttribute term = tokenStream.addAttribute(CharTermAttribute.class);
            while (tokenStream.incrementToken()) { 
                System.out.print("[" + term.toString() + "] ");
                //[quick] [brown] [fox] [jumped] [over] [lazy] [dog]
            }
            tokenStream.close();
        }

# 3, 中文词库下载：同义词，停用词 #

*  链接地址： [https://github.com/fighting41love/funNLP][https_github.com_fighting41love_funNLP]
 *  直接下载github文件：将 github.com 替换为 raw.githubusercontent.com，并去除 /blob:

url="https://github.com/guotong1988/chinese_dictionary/blob/master/dict_synonym.txt"
    echo $url|sed -e 's@github.com@raw.githubusercontent.com@' -e 's@blob/@@'

生成solr格式的 停用词：逗号分隔

public static void main(String[] args) throws IOException { 
            // 创建字符流对象，并根据已创建的字节流对象创建字符流对象
            String file = "D:\\download\\solr-近义词，停用词\\synonym.txt";
            String outfile = "D:\\download\\solr-近义词，停用词\\synonym2.txt";
            BufferedWriter bw = new BufferedWriter(new FileWriter(outfile));
            BufferedReader raf = new BufferedReader(new FileReader(file));
    
            //同义词
            //Aa01A01= 人 士 人物 人士 人氏 人选
            //Aa01A02= 人类 生人 全人类
            String s = null;
            while ((s = raf.readLine()) != null) { 
                String[] arr = s.split("=");
                if (arr.length < 2) continue;
                String[] arr2 = arr[1].split("\\s");
    
                for (int i=0;i <arr2.length; i++){ 
                    if (i != arr2.length -1 ){ 
                        if ( ! arr2[i].trim().equals("")){ 
                            System.out.print(arr2[i]+",");
                            bw.write(arr2[i]+",");
                        }
                    }else { 
                        System.out.print(arr2[i]);
                         bw.write(arr2[i]);
                    }
                }
                System.out.println();
                bw.write("\n");
            }
            bw.flush();
            bw.close();
            raf.close();
    }
    //人,士,人物,人士,人氏,人选
    //人类,生人,全人类
    //人手,人员,人口,人丁,口,食指
    //劳力,劳动力,工作者

[https_lucene.apache.org_core_8_6_0_demo_index.html]: https://lucene.apache.org/core/8_6_0/demo/index.html
[https_lucene.apache.org_core_downloads.html]: https://lucene.apache.org/core/downloads.html
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2V5ZW9mZWFnbGU_size_16_color_FFFFFF_t_70]: /images/20221022/d7be59bf9de544f7becf71fd2a2878f2.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2V5ZW9mZWFnbGU_size_16_color_FFFFFF_t_70 1]: https://img-blog.csdnimg.cn/20210326172356253.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2V5ZW9mZWFnbGU=,size_16,color_FFFFFF,t_70
[20210329103134580.png]: https://img-blog.csdnimg.cn/20210329103134580.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2V5ZW9mZWFnbGU_size_16_color_FFFFFF_t_70 2]: https://img-blog.csdnimg.cn/20210329102529509.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2V5ZW9mZWFnbGU=,size_16,color_FFFFFF,t_70
[https_github.com_fighting41love_funNLP]: https://github.com/fighting41love/funNLP