从零开始搭建.NET Core版搜索引擎（八）--查询结果高亮显示

很多搜索引擎的检索结果都会将匹配的关键词高亮显示出来，便于用户的快速识别，Lucene.NET当然也提供高亮功能。

---

1.高亮功能实现

1.1.安装Lucene.NET.HighLight

Lucene.NET的高亮功能由Lucene.NET.HighLight包实现，使用NuGet管理器安装，建议与Lucene.NET保持相同版本。

1.2.修改查询方法

高亮显示是一个锦上添花的功能，所以打算把是否高亮设置为搜索输入项的可配置项，同时高亮的功能实现也在具体的查询方法中体现。

搜索输入项修SingleSearchOption改为:

public class SingleSearchOption:SearchOptionBase
{
    /// <summary>
    /// 检索关键词
    /// </summary>
    public string Keyword { get; set; }
 
    /// <summary>
    /// 限定检索域
    /// </summary>
    public List<string> Fields { get; set; }
 
    /// <summary>
    /// 是否高亮显示
    /// </summary>
    public bool IsHightLight { get; set; }
 
    public SingleSearchOption(string keyword,List<string> fields,int maxHits=100,bool isHightLight=false)
    {
        if (string.IsNullOrWhiteSpace(keyword))
        {
            throw new ArgumentException("搜索关键词不能为空");
        }
        Keyword = keyword;
        Fields = fields;
        MaxHits = maxHits;
        IsHightLight = isHightLight;
    }
 
}

查询方法SingleSearch修改为：

public SingleSearchResult SingleSearch(SingleSearchOption option)
{
    SingleSearchResult result = new SingleSearchResult();
    Stopwatch watch=Stopwatch.StartNew();
    using (Lucene.Net.Index.DirectoryReader reader = DirectoryReader.Open(Directory))
    {
        //实例化索引检索器
        IndexSearcher searcher = new IndexSearcher(reader);
        var queryParser = new MultiFieldQueryParser(LuceneVersion.LUCENE_48, option.Fields.ToArray(), Analyzer);
        Query query = queryParser.Parse(option.Keyword);
        var matches = searcher.Search(query, option.MaxHits).ScoreDocs;
 
        #region 高亮
 
        QueryScorer scorer = new QueryScorer(query);
        Highlighter highlighter = new Highlighter(scorer);
 
        #endregion
 
        result.TotalHits = matches.Count();
        foreach (var match in matches)
        {
            var doc = searcher.Doc(match.Doc);
            SearchResultItem item = new SearchResultItem();
            item.Score = match.Score;
            item.EntityId = doc.GetField(CoreConstant.EntityId).GetStringValue();
            item.EntityName = doc.GetField(CoreConstant.EntityType).GetStringValue();
            String storedField = doc.Get(option.Fields[0]);
            if (option.IsHightLight)//高亮
            {
                TokenStream stream = TokenSources.GetAnyTokenStream(reader, match.Doc, option.Fields[0], doc, Analyzer);
                IFragmenter fragmenter = new SimpleSpanFragmenter(scorer);
                highlighter.TextFragmenter = fragmenter;
                string fragment = highlighter.GetBestFragment(stream, storedField);
                item.FieldValue = fragment;
            }
            else
            {
                item.FieldValue = storedField;
            }
            result.Items.Add(item);
        }
    }
    watch.Stop();
    result.Elapsed = watch.ElapsedMilliseconds;
    return result;
}

1.3.高亮测试示例

简单的高亮功能就修改完成了，使用WebAPI接口测试一下

在返回结果中可以看到，检索结果中的关键词“设计”均被加上了"</B/><//B/>"的标签。

2.高亮功能原理

在上面的示例中使用了Lucene.NET最简单的高亮效果，其原理并不复杂，了解其原理也能帮助我们实现更多更丰富的效果。简单来讲就是将查询结果进行二次处理，找到匹配关键字的位置，并添加样式重写查询结果。其大致流程如下。

2.1.QueryScorer实例化

QueryScorer scorer = new QueryScorer(query);

QueryScorer实现了Lucene.Net.Search.Highlight.IScorer接口，根据找到的唯一查询词的数量对文本片段进行评分。其构造函数的参数是当前的查询示例Query，此外可选项有IndexReader实例、需要高亮显示的Field的名称。

public QueryScorer(Query query) => this.Init(query, (string) null, (IndexReader) null, true);
 
public QueryScorer(Query query, string field) => this.Init(query, field, (IndexReader) null, true);
 
public QueryScorer(Query query, IndexReader reader, string field) => this.Init(query, field, reader, true);
 
public QueryScorer(Query query, IndexReader reader, string field, string defaultField)
{
  this.defaultField = defaultField.Intern();
  this.Init(query, field, reader, true);
}
 
public QueryScorer(Query query, string field, string defaultField)
{
  this.defaultField = defaultField.Intern();
  this.Init(query, field, (IndexReader) null, true);
}

2.2.HighLighter实例化

Highlighter highlighter = new Highlighter(scorer);

HighLighter类从其名字上就能看出来用于高亮标记文本中的对应项。

public Highlighter(IScorer fragmentScorer)
  : this((IFormatter) new SimpleHTMLFormatter(), fragmentScorer)
{
}
 
public Highlighter(IFormatter formatter, IScorer fragmentScorer)
  : this(formatter, (IEncoder) new DefaultEncoder(), fragmentScorer)
{
}
 
public Highlighter(IFormatter formatter, IEncoder encoder, IScorer fragmentScorer)
{
  this._formatter = formatter;
  this._encoder = encoder;
  this._fragmentScorer = fragmentScorer;
}

2.3.获取TokenStream

TokenStream可以说是这里核心了，通过之前Lucene.NET的工作流程我们知道，文本会被分割成TokenStream，里面记录的每个Token的位置。通过TokenStream就能快速的找到需要添加高亮效果的分词。

TokenStream stream = TokenSources.GetAnyTokenStream(reader, match.Doc, option.Fields[0], doc, Analyzer);

从Token集合中获取当前IndexReader、匹配文档Document和Analyzer对应的Token Stream。

public static TokenStream GetAnyTokenStream(
  IndexReader reader,
  int docId,
  string field,
  Document doc,
  Analyzer analyzer)
{
  TokenStream tokenStream = (TokenStream) null;
  Terms terms = reader.GetTermVectors(docId)?.GetTerms(field);
  if (terms != null)
    tokenStream = TokenSources.GetTokenStream(terms);
  return tokenStream ?? TokenSources.GetTokenStream(doc, field, analyzer);
}

2.4.设置Fragment

IFragmenter fragmenter = new SimpleSpanFragmenter(scorer);
highlighter.TextFragmenter = fragmenter;

实例化实现IFragmenter接口的类，用于将文本拆分成不同大小的片段，而不是单个的字。

/// <param name="queryScorer"><see cref="T:Lucene.Net.Search.Highlight.QueryScorer" /> that was used to score hits</param>
public SimpleSpanFragmenter(QueryScorer queryScorer)
  : this(queryScorer, 100)
{
}
 
/// <param name="queryScorer"><see cref="T:Lucene.Net.Search.Highlight.QueryScorer" /> that was used to score hits</param>
/// <param name="fragmentSize">size in bytes of each fragment</param>
public SimpleSpanFragmenter(QueryScorer queryScorer, int fragmentSize)
{
  this.fragmentSize = fragmentSize;
  this.queryScorer = queryScorer;
}

2.5.替换关键字样式

String storedField = doc.Get(option.Fields[0]);
string fragment = highlighter.GetBestFragment(stream, storedField);

最后一步就是将找到的关键字添加样式。

public string[] GetBestFragments(TokenStream tokenStream, string text, int maxNumFragments)
{
  maxNumFragments = Math.Max(1, maxNumFragments);
  TextFragment[] bestTextFragments = this.GetBestTextFragments(tokenStream, text, true, maxNumFragments);
  List<string> stringList = new List<string>();
  for (int index = 0; index < bestTextFragments.Length; ++index)
  {
    if (bestTextFragments[index] != null && (double) bestTextFragments[index].Score > 0.0)
      stringList.Add(bestTextFragments[index].ToString());
  }
  return stringList.ToArray();
}

注意：这个过程有一点需要注意，那就是使用的Analyzer–或者进一步讲是使用的分词器–要前后保持一致。如果创建索引和查询时使用的分词器不同，关键词与结果匹配不上不说，由于分词结果的差异，关键词的位置也会出现偏移。

---

项目地址：https://github.com/ludewig/Muyan.Search