我在对通用索引“sitecore_master_index”、“sitecore_web_index”进行 Sitecore 索引时遇到问题,因为爬虫/索引器会检查数据库中的所有项目,这需要很长时间。
我导入了数千种具有大量规格的产品,并且在产品存储库中确实有数十万个项目。
如果我可以从索引中排除路径,它就不必检查一百万个项目以排除模板。
跟进
我实现了一个自定义爬虫,它排除了被索引的路径列表:
<index id="sitecore_web_index" type="Sitecore.ContentSearch.SolrProvider.SwitchOnRebuildSolrSearchIndex, Sitecore.ContentSearch.SolrProvider">
<param desc="name">$(id)</param>
<param desc="core">sitecore_web_index</param>
<param desc="rebuildcore">sitecore_web_index_sec</param>
<param desc="propertyStore" ref="contentSearch/indexConfigurations/databasePropertyStore" param1="$(id)" />
<configuration ref="contentSearch/indexConfigurations/defaultSolrIndexConfiguration" />
<strategies hint="list:AddStrategy">
<strategy ref="contentSearch/indexConfigurations/indexUpdateStrategies/onPublishEndAsync" />
</strategies>
<locations hint="list:AddCrawler">
<crawler type="Sitecore.ContentSearch.Utilities.Crawler.ExcludePathsItemCrawler, Sitecore.ContentSearch.Utilities">
<Database>web</Database>
<Root>/sitecore</Root>
<ExcludeItemsList hint="list">
<ProductRepository>/sitecore/content/Product Repository</ProductRepository>
</ExcludeItemsList>
</crawler>
</locations>
</index>
此外,我激活了 SwitchOnSolrRebuildIndex,因为它是很棒的 ootb 功能,为 SC 欢呼。
using System.Collections.Generic;
using System.Linq;
using Sitecore.ContentSearch;
using Sitecore.Diagnostics;
namespace Sitecore.ContentSearch.Utilities.Crawler
{
public class ExcludePathsItemCrawler : SitecoreItemCrawler
{
private readonly List<string> excludeItemsList = new List<string>();
public List<string> ExcludeItemsList
{
get
{
return excludeItemsList;
}
}
protected override bool IsExcludedFromIndex(SitecoreIndexableItem indexable, bool checkLocation = false)
{
Assert.ArgumentNotNull(indexable, "item");
if (ExcludeItemsList.Any(path => indexable.AbsolutePath.StartsWith(path)))
{
return true;
}
return base.IsExcludedFromIndex(indexable, checkLocation);
}
}
}