相关概念
站内搜索
站内搜索通俗来讲是一个网站或商城的“大门口”，一般在形式上包括两个要件：搜索入口和搜索结果页面，但在其后台架构上是比较复杂的，其核心要件包括：中文分词技术、页面抓取技术、建立索引、对搜索结果排序以及对搜索关键词的统计、分析、关联、推荐等。
比较常见的就是电商网站中首页的搜索框，它可以根据关键词（分词）、分类、商品简介、详情等搜索商品信息，可以根据相关度、价格、销量做排序。
全文检索
全文检索是将对站内的网页、文档内容进行分词，然后形成索引，再通过关键词查询匹配索引库中的索引，从而得到索引结果，最后将索引页内容展现给用户。
Lucene.Net
Lucene.net是Lucene的.net移植版本，用C#编写，它完成了全文检索的功能——预先把数据拆分成原子（字/词），保存到磁盘中；查询时把关键字也拆分成原子（字/词），再根据（字/词）进行匹配，返回结果。
Nuget安装“Lucene.Net”和“Lucene.Net.Analysis.PanGu”（盘古分词，一个第三方的分词器）
lucene.net七大对象
1、Analysis
分词器，负责把字符串拆分成原子，包含了标准分词，直接空格拆分。项目中用的是盘古中文分词。
2、Document
数据结构，定义存储数据的格式
3、Index：索引的读写类
4、QueryParser：查询解析器，负责解析查询语句
5、Search：负责各种查询类，命令解析后得到就是查询类
6、Store：索引存储类，负责文件夹等等
7、Util：常见工具类库
git地址：https://github.com/apache/lucenenet/releases/tag/Lucene.Net_3_0_3_RC2_final
索引库-写示例
代码语言：javascript
复制
List<Commodity> commodityList = GetList();//获取数据源
FSDirectory directory = FSDirectory.Open(StaticConstant.TestIndexPath);//文件夹
//经过分词以后把内容写入到硬盘
//PanGuAnalyzer 盘古分词；中华人民共和国，从后往前匹配，匹配到和词典一样的词，就保存起来；建议大家去看看盘古分词的官网；词典是可以我们手动去维护；
//城会玩---网络流行词--默认没有，盘古分词，可以由我们自己把这些词给添加进去；
using (IndexWriter writer = new IndexWriter(directory, new PanGuAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED))//索引写入器
{
foreach (Commodity commdity in commodityList)
{
for (int k = 0; k < 10; k++)
{
Document doc = new Document();//一条数据
doc.Add(new Field("id", commdity.Id.ToString(), Field.Store.NO, Field.Index.NOT_ANALYZED));//一个字段 列名 值 是否保存值 是否分词
doc.Add(new Field("title", commdity.Title, Field.Store.YES, Field.Index.ANALYZED));
doc.Add(new Field("url", commdity.Url, Field.Store.NO, Field.Index.NOT_ANALYZED));
doc.Add(new Field("imageurl", commdity.ImageUrl, Field.Store.NO, Field.Index.NOT_ANALYZED));
doc.Add(new Field("content", "this is lucene working,powerful tool " + k, Field.Store.YES, Field.Index.ANALYZED));
doc.Add(new NumericField("price", Field.Store.YES, true).SetDoubleValue((double)(commdity.Price + k)));
//doc.Add(new NumericField("time", Field.Store.YES, true).SetLongValue(DateTime.Now.ToFileTimeUtc()));
doc.Add(new NumericField("time", Field.Store.YES, true).SetIntValue(int.Parse(DateTime.Now.ToString("yyyyMMdd")) + k));
writer.AddDocument(doc);//写进去
}
}
writer.Optimize();//优化 就是合并
}</code></pre></div></div><figure class=""><div class="rno-markdown-img-url" style="text-align:center"><div class="rno-markdown-img-url-inner" style="width:100%"><div style="width:100%"><img src="https://cdn.static.attains.cn/app/developer-bbs/upload/1723218123258895356.png" /></div></div></div></figure><figure class=""><div class="rno-markdown-img-url" style="text-align:center"><div class="rno-markdown-img-url-inner" style="width:70.16%"><div style="width:100%"><img src="https://cdn.static.attains.cn/app/developer-bbs/upload/1723218123617454158.png" /></div></div></div></figure><figure class=""><div class="rno-markdown-img-url" style="text-align:center"><div class="rno-markdown-img-url-inner" style="width:100%"><div style="width:100%"><img src="https://cdn.static.attains.cn/app/developer-bbs/upload/1723218123824697157.png" /></div></div></div></figure><figure class=""><div class="rno-markdown-img-url" style="text-align:center"><div class="rno-markdown-img-url-inner" style="width:65.69%"><div style="width:100%"><img src="https://cdn.static.attains.cn/app/developer-bbs/upload/1723218124087689020.png" /></div></div></div></figure><h3 id="dp884" name="%E7%B4%A2%E5%BC%95%E5%BA%93%E2%80%94%E2%80%94%E8%AF%BB%E7%A4%BA%E4%BE%8B"> 索引库——读示例</h3><div class="rno-markdown-code"><div class="rno-markdown-code-toolbar"><div class="rno-markdown-code-toolbar-info"><div class="rno-markdown-code-toolbar-item is-type"><span class="is-m-hidden">代码语言：</span>javascript</div></div><div class="rno-markdown-code-toolbar-opt"><div class="rno-markdown-code-toolbar-copy"><i class="icon-copy"></i><span class="is-m-hidden">复制</span></div></div></div><div class="developer-code-block"><pre class="prism-token token line-numbers language-javascript"><code class="language-javascript" style="margin-left:0"> FSDirectory dir = FSDirectory.Open(StaticConstant.TestIndexPath);
IndexSearcher searcher = new IndexSearcher(dir);//查找器
{
FuzzyQuery query = new FuzzyQuery(new Term("title", "高中政治"));
//TermQuery query = new TermQuery(new Term("title", "周年"));//包含
TopDocs docs = searcher.Search(query, null, 10000);//找到的数据
foreach (ScoreDoc sd in docs.ScoreDocs)
{
Document doc = searcher.Doc(sd.Doc);
Console.WriteLine("***************************************");
Console.WriteLine(string.Format("id={0}", doc.Get("id")));
Console.WriteLine(string.Format("title={0}", doc.Get("title")));
Console.WriteLine(string.Format("time={0}", doc.Get("time")));
Console.WriteLine(string.Format("price={0}", doc.Get("price")));
Console.WriteLine(string.Format("content={0}", doc.Get("content")));
}
Console.WriteLine("1一共命中了{0}个", docs.TotalHits);
}
QueryParser parser = new QueryParser(Version.LUCENE_30, "title", new PanGuAnalyzer());//解析器
{
// string keyword = "高中政治人教新课标选修生活中的法律常识";
string keyword = "高中政治 人 教 新课 标 选修 生活 中的 法律常识";
{
Query query = parser.Parse(keyword);
TopDocs docs = searcher.Search(query, null, 10000);//找到的数据
int i = 0;
foreach (ScoreDoc sd in docs.ScoreDocs)
{
if (i++ < 1000)
{
Document doc = searcher.Doc(sd.Doc);
Console.WriteLine("***************************************");
Console.WriteLine(string.Format("id={0}", doc.Get("id")));
Console.WriteLine(string.Format("title={0}", doc.Get("title")));
Console.WriteLine(string.Format("time={0}", doc.Get("time")));
Console.WriteLine(string.Format("price={0}", doc.Get("price")));
}
}
Console.WriteLine($"一共命中{docs.TotalHits}");
}
{
Query query = parser.Parse(keyword);
NumericRangeFilter<int> timeFilter = NumericRangeFilter.NewIntRange("time", 20090101, 20201231, true, true);//过滤
SortField sortPrice = new SortField("price", SortField.DOUBLE, false);//false::降序
SortField sortTime = new SortField("time", SortField.INT, true);//true:升序
Sort sort = new Sort(sortTime, sortPrice);//排序 哪个前哪个后
TopDocs docs = searcher.Search(query, timeFilter, 10000, sort);//找到的数据
//可以做什么？就可以分页查询！
int i = 0;
foreach (ScoreDoc sd in docs.ScoreDocs)
{
if (i++ < 1000)
{
Document doc = searcher.Doc(sd.Doc);
Console.WriteLine("***************************************");
Console.WriteLine(string.Format("id={0}", doc.Get("id")));
Console.WriteLine(string.Format("title={0}", doc.Get("title")));
Console.WriteLine(string.Format("time={0}", doc.Get("time")));
Console.WriteLine(string.Format("price={0}", doc.Get("price")));
}
}
Console.WriteLine("3一共命中了{0}个", docs.TotalHits);
}
}</code></pre></div></div><figure class=""><div class="rno-markdown-img-url" style="text-align:center"><div class="rno-markdown-img-url-inner" style="width:91.08%"><div style="width:100%"><img src="https://cdn.static.attains.cn/app/developer-bbs/upload/1723218124357562390.png" /></div></div></div></figure><figure class=""><div class="rno-markdown-img-url" style="text-align:center"><div class="rno-markdown-img-url-inner" style="width:100%"><div style="width:100%"><img src="https://cdn.static.attains.cn/app/developer-bbs/upload/1723218124642135245.png" /></div></div></div></figure><figure class=""><div class="rno-markdown-img-url" style="text-align:center"><div class="rno-markdown-img-url-inner" style="width:100%"><div style="width:100%"><img src="https://cdn.static.attains.cn/app/developer-bbs/upload/1723218125041460222.png" /></div></div></div></figure><figure class=""><div class="rno-markdown-img-url" style="text-align:center"><div class="rno-markdown-img-url-inner" style="width:44.65%"><div style="width:100%"><img src="https://cdn.static.attains.cn/app/developer-bbs/upload/1723218125334952875.png" /></div></div></div></figure><h3 id="5qi32" name="%E5%A4%9A%E7%BA%BF%E7%A8%8B%E5%86%99%E5%85%A5%E7%B4%A2%E5%BC%95%E5%BA%93%E7%A4%BA%E4%BE%8B"> 多线程写入索引库示例</h3><div class="rno-markdown-code"><div class="rno-markdown-code-toolbar"><div class="rno-markdown-code-toolbar-info"><div class="rno-markdown-code-toolbar-item is-type"><span class="is-m-hidden">代码语言：</span>javascript</div></div><div class="rno-markdown-code-toolbar-opt"><div class="rno-markdown-code-toolbar-copy"><i class="icon-copy"></i><span class="is-m-hidden">复制</span></div></div></div><div class="developer-code-block"><pre class="prism-token token line-numbers language-javascript"><code class="language-javascript" style="margin-left:0"> try
{
logger.Debug(string.Format("{0} BuildIndex开始",DateTime.Now));
List<Task> taskList = new List<Task>();
TaskFactory taskFactory = new TaskFactory();
CTS = new CancellationTokenSource();
//30个表 30个线程 不用折腾，一线程一表 平均分配
//30个表 18个线程 1到12号2个表 13到18是一个表？ 错的！前12个线程活儿多，后面的活少
//自己去想想，怎么样可以做，随便配置线程数量，但是可以均匀分配任务？
for (int i = 1; i < 31; i++)
{
IndexBuilderPerThread thread = new IndexBuilderPerThread(i, i.ToString("000"), CTS);
PathSuffixList.Add(i.ToString("000"));
taskList.Add(taskFactory.StartNew(thread.Process));//开启一个线程 里面创建索引
}
taskList.Add(taskFactory.ContinueWhenAll(taskList.ToArray(), MergeIndex));
Task.WaitAll(taskList.ToArray());
logger.Debug(string.Format("BuildIndex{0}", CTS.IsCancellationRequested ? "失败" : "成功"));
}
catch (Exception ex)
{
logger.Error("BuildIndex出现异常", ex);
}
finally
{
logger.Debug(string.Format("{0} BuildIndex结束", DateTime.Now));
}</code></pre></div></div><div class="rno-markdown-code"><div class="rno-markdown-code-toolbar"><div class="rno-markdown-code-toolbar-info"><div class="rno-markdown-code-toolbar-item is-type"><span class="is-m-hidden">代码语言：</span>javascript</div></div><div class="rno-markdown-code-toolbar-opt"><div class="rno-markdown-code-toolbar-copy"><i class="icon-copy"></i><span class="is-m-hidden">复制</span></div></div></div><div class="developer-code-block"><pre class="prism-token token line-numbers language-javascript"><code class="language-javascript" style="margin-left:0"> private static void MergeIndex(Task[] tasks)
{
try
{
if (CTS.IsCancellationRequested) return;
ILuceneBulid builder = new LuceneBulid();
builder.MergeIndex(PathSuffixList.ToArray());
}
catch (Exception ex)
{
CTS.Cancel();
logger.Error("MergeIndex出现异常", ex);
}
}</code></pre></div></div><p> ///<summary></p><div class="rno-markdown-code"><div class="rno-markdown-code-toolbar"><div class="rno-markdown-code-toolbar-info"><div class="rno-markdown-code-toolbar-item is-type"><span class="is-m-hidden">代码语言：</span>javascript</div></div><div class="rno-markdown-code-toolbar-opt"><div class="rno-markdown-code-toolbar-copy"><i class="icon-copy"></i><span class="is-m-hidden">复制</span></div></div></div><div class="developer-code-block"><pre class="prism-token token line-numbers language-javascript"><code class="language-javascript" style="margin-left:0"> /// 将索引合并到上级目录
/// </summary>
/// <param name="sourceDir">子文件夹名</param>
public void MergeIndex(string[] childDirs)
{
Console.WriteLine("MergeIndex Start");
IndexWriter writer = null;
try
{
if (childDirs == null || childDirs.Length == 0) return;
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_30);
string rootPath = StaticConstant.IndexPath;
DirectoryInfo dirInfo = Directory.CreateDirectory(rootPath);
LuceneIO.Directory directory = LuceneIO.FSDirectory.Open(dirInfo);
writer = new IndexWriter(directory, analyzer, true, IndexWriter.MaxFieldLength.LIMITED);//删除原有的
LuceneIO.Directory[] dirNo = childDirs.Select(dir => LuceneIO.FSDirectory.Open(Directory.CreateDirectory(string.Format("{0}\\{1}", rootPath, dir)))).ToArray();
writer.MergeFactor = 100;//控制多个segment合并的频率，默认10
writer.UseCompoundFile = true;//创建符合文件 减少索引文件数量
writer.AddIndexesNoOptimize(dirNo);
}
finally
{
if (writer != null)
{
writer.Optimize();
writer.Close();
}
Console.WriteLine("MergeIndex End");
}
}</code></pre></div></div>
