lucene .doc里存储的skiplist跳表
http://forfuture1978.iteye.com/blog/546841
见图:
lucene-6.5.1-src/lucene-6.5.1
$ grep "skiplistwriter" * -ril
core/src/java/org/apache/lucene/codecs/lucene50/Lucene50PostingsFormat.java
core/src/java/org/apache/lucene/codecs/lucene50/Lucene50SkipWriter.java
core/src/java/org/apache/lucene/codecs/MultiLevelSkipListReader.java
core/src/java/org/apache/lucene/codecs/MultiLevelSkipListWriter.java
测试代码位置:
lucene-6.5.1-src/lucene-6.5.1
$ vim core/src/test/org/apache/lucene/codecs/lucene50/TestBlockPostingsFormat3.java
/** * checks advancing docs */ public void assertDocsSkipping(int docFreq, PostingsEnum leftDocs, PostingsEnum rightDocs) throws Exception { if (leftDocs == null) { assertNull(rightDocs); return; } int docid = -1; int averageGap = MAXDOC / (1+docFreq); int skipInterval = 16; while (true) { if (random().nextBoolean()) { // nextDoc() docid = leftDocs.nextDoc(); assertEquals(docid, rightDocs.nextDoc()); } else { // advance() int skip = docid + (int) Math.ceil(Math.abs(skipInterval + random().nextGaussian() * averageGap)); docid = leftDocs.advance(skip); assertEquals(docid, rightDocs.advance(skip)); } if (docid == DocIdSetIterator.NO_MORE_DOCS) { return; } // we don't assert freqs, they are allowed to be different } }
/** * checks advancing docs + positions */ public void assertPositionsSkipping(int docFreq, PostingsEnum leftDocs, PostingsEnum rightDocs) throws Exception { if (leftDocs == null || rightDocs == null) { assertNull(leftDocs); assertNull(rightDocs); return; } int docid = -1; int averageGap = MAXDOC / (1+docFreq); int skipInterval = 16; while (true) { if (random().nextBoolean()) { // nextDoc() docid = leftDocs.nextDoc(); assertEquals(docid, rightDocs.nextDoc()); } else { // advance() int skip = docid + (int) Math.ceil(Math.abs(skipInterval + random().nextGaussian() * averageGap)); docid = leftDocs.advance(skip); assertEquals(docid, rightDocs.advance(skip)); } if (docid == DocIdSetIterator.NO_MORE_DOCS) { return; } int freq = leftDocs.freq(); assertEquals(freq, rightDocs.freq()); for (int i = 0; i < freq; i++) { assertEquals(leftDocs.nextPosition(), rightDocs.nextPosition()); // we don't compare the payloads, it's allowed that one is empty etc } } }
标签:
搜索引擎
, elasticsearch
【推荐】国内首个AI IDE,深度理解中文开发场景,立即下载体验Trae
【推荐】编程新体验,更懂你的AI,立即体验豆包MarsCode编程助手
【推荐】抖音旗下AI助手豆包,你的智能百科全书,全免费不限次数
【推荐】轻量又高性能的 SSH 工具 IShell:AI 加持,快人一步
· 记一次.NET内存居高不下排查解决与启示
· 探究高空视频全景AR技术的实现原理
· 理解Rust引用及其生命周期标识(上)
· 浏览器原生「磁吸」效果!Anchor Positioning 锚点定位神器解析
· 没有源码,如何修改代码逻辑?
· 全程不用写代码,我用AI程序员写了一个飞机大战
· MongoDB 8.0这个新功能碉堡了,比商业数据库还牛
· 记一次.NET内存居高不下排查解决与启示
· 白话解读 Dapr 1.15:你的「微服务管家」又秀新绝活了
· DeepSeek 开源周回顾「GitHub 热点速览」