Background
This reared it's head on a project a couple months back - we were finding multiple versions of items that where being indexed from the Master Database.After looking around on the web for a solution, I came across this post about inbound and outbound filter pipelines by the Sitecore Development Team: http://www.sitecore.net/learn/blogs/technical-blogs/sitecore-7-development-team/posts/2013/04/sitecore-7-inbound-and-outbound-filter-pipelines.aspx
The Disaster Waiting to Happen
As Owen Wattley noted in his post, implementing the ApplyInboundIndexVersionFilter to ensure only the latest version goes into the index can cause problems that aren't apparent at first glance."...The problem my team found is as follows:
- Create an item, version 1 goes into the index because it's the latest version
- Add a new version. Version 2 goes into the index because it's now the latest version.
- Version 1 gets blocked by the inbound filter, meaning the index entry for version 1 DOESN'T GET UPDATED OR REMOVED. In the index it is still marked as the latest version. So is version 2. This means you have 2 versions in your index, both marked as the latest version.
You have to be very careful with inbound filters because they don't do as you might expect. I expected that if you set "args.IsExcluded" to true then it would REMOVE that entry from the index, but it doesn't - it ONLY ensures that nothing gets ADDED. That's a subtle but very crucial difference. Once we found this problem we quickly removed the inbound latest version filter. "
The Solution
Luckily, Sitecore star Pavel Veller recommended a solution that would help alleviate these issues. I just took his idea and implemented the solution.As this keeps popping up time and time again in the Sitecore 8.x projects that I have been working on, I wanted to share this implementation with the community.
Hope it helps!
FilterPatchItemCrawler.cs
1: using System;
2: using System.Collections.Generic;
3:
4: using Sitecore.ContentSearch;
5: using Sitecore.ContentSearch.Abstractions;
6: using Sitecore.ContentSearch.Diagnostics;
7: using Sitecore.Data.Items;
8: using Sitecore.Diagnostics;
9: using Sitecore.Globalization;
10:
11: namespace FilterPatch.Library.ContentSearch
12: {
13: public class FilterPatchItemCrawler : SitecoreItemCrawler
14: {
15: protected override void DoAdd(IProviderUpdateContext context, SitecoreIndexableItem indexable)
16: {
17: Assert.ArgumentNotNull((object)context, "context");
18: Assert.ArgumentNotNull((object)indexable, "indexable");
19:
20: this.Index.Locator.GetInstance<IEvent>().RaiseEvent("indexing:adding", (object)context.Index.Name, (object)indexable.UniqueId, (object)indexable.AbsolutePath);
21: if (this.IsExcludedFromIndex(indexable, false))
22: return;
23: foreach (Language language in indexable.Item.Languages)
24: {
25: Item obj1;
26: using (new FilterPatchCachesDisabler())
27: obj1 = indexable.Item.Database.GetItem(indexable.Item.ID, language, Sitecore.Data.Version.Latest);
28: if (obj1 == null)
29: {
30: CrawlingLog.Log.Warn(string.Format("FilterPatchItemCrawler : AddItem : Could not build document data {0} - Latest version could not be found. Skipping.", (object)indexable.Item.Uri), (Exception)null);
31: }
32: else
33: {
34: using (new FilterPatchCachesDisabler())
35: {
36: SitecoreIndexableItem sitecoreIndexableItem = obj1.Versions.GetLatestVersion();
37: IIndexableBuiltinFields indexableBuiltinFields = sitecoreIndexableItem;
38: indexableBuiltinFields.IsLatestVersion = indexableBuiltinFields.Version == obj1.Version.Number;
39: sitecoreIndexableItem.IndexFieldStorageValueFormatter = context.Index.Configuration.IndexFieldStorageValueFormatter;
40:
41: this.Operations.Add(sitecoreIndexableItem, context, this.index.Configuration);
42: }
43: }
44: }
45: this.Index.Locator.GetInstance<IEvent>().RaiseEvent("indexing:added", (object)context.Index.Name, (object)indexable.UniqueId, (object)indexable.AbsolutePath);
46: }
47:
48: protected override void DoUpdate(IProviderUpdateContext context, SitecoreIndexableItem indexable)
49: {
50: Assert.ArgumentNotNull((object)context, "context");
51: Assert.ArgumentNotNull((object)indexable, "indexable");
52: if (this.IndexUpdateNeedDelete(indexable))
53: {
54: this.Index.Locator.GetInstance<IEvent>().RaiseEvent("indexing:deleteitem", (object)this.index.Name, (object)indexable.UniqueId, (object)indexable.AbsolutePath);
55: this.Operations.Delete((IIndexable)indexable, context);
56: }
57: else
58: {
59: this.Index.Locator.GetInstance<IEvent>().RaiseEvent("indexing:updatingitem", (object)this.index.Name, (object)indexable.UniqueId, (object)indexable.AbsolutePath);
60: if (!this.IsExcludedFromIndex(indexable, true))
61: {
62: foreach (Language language in indexable.Item.Languages)
63: {
64: Item obj1;
65: using (new FilterPatchCachesDisabler())
66: obj1 = indexable.Item.Database.GetItem(indexable.Item.ID, language, Sitecore.Data.Version.Latest);
67: if (obj1 == null)
68: {
69: CrawlingLog.Log.Warn(string.Format("FilterPatchItemCrawler : Update : Latest version not found for item {0}. Skipping.", (object)indexable.Item.Uri), (Exception)null);
70: }
71: else
72: {
73: Item[] versions;
74: using (new FilterPatchCachesDisabler())
75: versions = obj1.Versions.GetVersions(false);
76: foreach (Item obj2 in versions)
77: {
78: SitecoreIndexableItem versionIndexable = PrepareIndexableVersion(obj2, context);
79:
80: if (obj2.Version.Equals(obj1.Versions.GetLatestVersion().Version))
81: {
82: Operations.Update(versionIndexable, context, context.Index.Configuration);
83: UpdateClones(context, versionIndexable);
84: }
85: else
86: {
87: Index.Locator.GetInstance<IEvent>().RaiseEvent("indexing:deleteitem", (object)this.index.Name, (object)indexable.UniqueId, (object)indexable.AbsolutePath);
88: Operations.Delete(versionIndexable, context);
89: }
90:
91: }
92: }
93: }
94: this.Index.Locator.GetInstance<IEvent>().RaiseEvent("indexing:updateditem", (object)this.index.Name, (object)indexable.UniqueId, (object)indexable.AbsolutePath);
95: }
96: if (!this.DocumentOptions.ProcessDependencies)
97: return;
98: this.Index.Locator.GetInstance<IEvent>().RaiseEvent("indexing:updatedependents", (object)this.index.Name, (object)indexable.UniqueId, (object)indexable.AbsolutePath);
99: this.UpdateDependents(context, indexable);
100: }
101: }
102:
103: private static SitecoreIndexableItem PrepareIndexableVersion(Item item, IProviderUpdateContext context)
104: {
105: SitecoreIndexableItem sitecoreIndexableItem = (SitecoreIndexableItem)item;
106: ((IIndexableBuiltinFields)sitecoreIndexableItem).IsLatestVersion = item.Versions.IsLatestVersion();
107: sitecoreIndexableItem.IndexFieldStorageValueFormatter = context.Index.Configuration.IndexFieldStorageValueFormatter;
108: return sitecoreIndexableItem;
109: }
110:
111: private void UpdateClones(IProviderUpdateContext context, SitecoreIndexableItem versionIndexable)
112: {
113: IEnumerable<Item> clones;
114: using (new FilterPatchCachesDisabler())
115: clones = versionIndexable.Item.GetClones(false);
116: foreach (Item obj in clones)
117: {
118: SitecoreIndexableItem sitecoreIndexableItem = PrepareIndexableVersion(obj, context);
119: if (!this.IsExcludedFromIndex(obj, false))
120: this.Operations.Update((IIndexable)sitecoreIndexableItem, context, context.Index.Configuration);
121: }
122: }
123: }
124: }
125:
FilterPatchCachesDisabler.cs
1: using System;
2:
3: using Sitecore.Common;
4: using Sitecore.ContentSearch.Utilities;
5: using Sitecore.Data;
6:
7: namespace FilterPatch.Library.ContentSearch
8: {
9: public class FilterPatchCachesDisabler : IDisposable
10: {
11: public FilterPatchCachesDisabler()
12: {
13: Switcher<bool, DatabaseCacheDisabler>.Enter(ContentSearchConfigurationSettings.DisableDatabaseCaches);
14: }
15:
16: public void Dispose()
17: {
18: Switcher<bool, DatabaseCacheDisabler>.Exit();
19: }
20: }
21: }
22:
Your index configuration:
1: <locations hint="list:AddCrawler">
2: <crawler type="FilterPatch.Library.ContentSearch.FilterPatchItemCrawler, FilterPatch.Library">
3: <Database>master</Database>
4: <Root>#Some path#</Root>
5: </crawler>
6: </locations>
