2

我正在使用带有默认参数的 PostingsSolrHighlighter，它似乎给出了很好的结果。我的用例是针对完整文档搜索文本段落并获取相关片段，这个荧光笔确实提供了匹配文档中最接近的段落。

我需要的自定义是删除似乎与搜索的段落无关的浪费片段。目前，我正在寻找一种简单的方法：删除相对分数为 0.5 或更低的片段。但是我找不到一种方法来获得 Solr 为句子/片段计算的分数，所以我可以丢弃不太需要的分数。

我可以告诉 solr 仅在其分数大于 xyz 分数时才保留片段，或者它可以以某种方式给我片段分数吗？

我仍然想保持结果片段的顺序（根据原始文档中片段的起始位置）。

谢谢。

4

1 回答 1

0

Ok, i could not get any way to ask Solr to return snippets with scores or discard snippets having score less than certain number, but i extended the highlighter and formatter, and now getting snippet with their scores (solr-computed absolute score & relative score). Below is the extension code if needed by someone:

package solrExtension;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import org.apache.lucene.search.Query;
import org.apache.lucene.search.postingshighlight.DefaultPassageFormatter;
import org.apache.lucene.search.postingshighlight.Passage;
import org.apache.lucene.search.postingshighlight.PassageFormatter;
import org.apache.lucene.search.postingshighlight.PostingsHighlighter;
import org.apache.solr.common.params.HighlightParams;
import org.apache.solr.common.util.NamedList;
import org.apache.solr.highlight.PostingsSolrHighlighter;
import org.apache.solr.request.SolrQueryRequest;
import org.apache.solr.search.DocList;


public class CustomPostingsSolrHighlighter extends PostingsSolrHighlighter {


    protected PostingsHighlighter getHighlighter(SolrQueryRequest req) {
        return new customSolrExtendedPostingsHighlighter(req);
    }

    public class customSolrExtendedPostingsHighlighter extends PostingsSolrHighlighter.SolrExtendedPostingsHighlighter {
        public customSolrExtendedPostingsHighlighter(SolrQueryRequest req) {
            super(req);
        }

        @Override
        protected PassageFormatter getFormatter(String fieldName) {
              String preTag = params.getFieldParam(fieldName, HighlightParams.TAG_PRE, "<em>");
              String postTag = params.getFieldParam(fieldName, HighlightParams.TAG_POST, "</em>");
              String ellipsis = params.getFieldParam(fieldName, HighlightParams.TAG_ELLIPSIS, "... ");
              String encoder = params.getFieldParam(fieldName, HighlightParams.ENCODER, "simple");
              return new CustomPassageFormatter(preTag, postTag, ellipsis, "html".equals(encoder));
        }
    }


    public class CustomPassageFormatter extends DefaultPassageFormatter {
        public CustomPassageFormatter() {
            super();
        }

        public CustomPassageFormatter(String preTag, String postTag,
                String ellipsis, boolean escape) {
            super(preTag, postTag, ellipsis, escape);
        }

        @Override
        public String format(Passage passages[], String content) {
            StringBuilder sb = new StringBuilder();
            int pos = 0;
            double psgTtlScore = 0, maxScore=0, score;
            int psgCounts = 0;
            List<CustomPsg> psgGroups = new ArrayList<CustomPsg>();
            for (Passage passage : passages) {
                // don't add ellipsis if it's the first one, or if it's
                // connected.
                if (passage.getStartOffset() > pos && pos > 0) {
                    score = psgTtlScore / psgCounts;
                    if (score > maxScore)
                        maxScore = score;
                    sb.append("[[").append(score).append("]]");
                    psgGroups.add(new CustomPsg(sb.toString(), score));
                    //sb.append(ellipsis);
                    psgTtlScore = 0;
                    psgCounts = 0;
                    sb = new StringBuilder();
                }
                psgTtlScore += passage.getScore();
                psgCounts++;
                pos = passage.getStartOffset();
                for (int i = 0; i < passage.getNumMatches(); i++) {
                    int start = passage.getMatchStarts()[i];
                    int end = passage.getMatchEnds()[i];
                    // it's possible to have overlapping terms
                    if (start > pos) {
                        append(sb, content, pos, start);
                    }
                    if (end > pos) {
                        sb.append(preTag);
                        append(sb, content, Math.max(pos, start), end);
                        sb.append(postTag);
                        pos = end;
                    }
                }
                sb.append("[").append(passage.getScore()).append("]");
                // it's possible a "term" from the analyzer could span a
                // sentence boundary.
                append(sb, content, pos, Math.max(pos, passage.getEndOffset()));
                pos = passage.getEndOffset();
            }
            sb.append("[[").append(psgTtlScore / psgCounts).append("]]");
            psgGroups.add(new CustomPsg(sb.toString(), psgTtlScore / psgCounts));


            sb = new StringBuilder();
            for (CustomPsg psg : psgGroups) {
                sb.append(psg.psg).append("{{").append(psg.score/maxScore).append("}}").append(ellipsis);
            }
            return sb.toString();
        }

        private class CustomPsg {
            public String psg;
            public double score;
            public CustomPsg(String psg, double score) {
                this.psg = psg;
                this.score = score;
            }
        }
    }

}

and with this extended code, i'm getting snippets and their scores in search results, as follows:

.....sions and other areas subject to its jurisdiction[22.847776]. [[22.847776]]{{0.954086}}

..... and the Trustee[19.287382]. [[19.287382]]{{0.805409}}

Number in [ ] indicates score of a single statement, number in [[ ]] indicates avg score (sum of all sentences' scores / sentence count in snippet) of the whole snippet (a snippet may contain multiple sentences), and number in {{ }} indicates snippet's relative score (against other snippet's avg scores).

于 2015-09-02T09:40:22.643 回答