public void ExternalIndexBuildTest()
        {
            var stream = new MemoryStream();
            var postingsListBuilder = new MixedPostingsListBuilder <string>(RangeThreshold);
            var buildableIndex      = new DictonaryBasedExternalBuildableIndex <string>(postingsListBuilder, stream);

            var docs = new (DocumentId Id, string[] Text)[]
        static void BuildExternalIndex()
        {
            PrepareOutputDirectory(externalIndexPath);

            var reader = new CorpusZipReader <IList <char> >(wikiPath, charDataSerializer);

            using var buildableIndex = new BlockedExternalBuildableIndex <int>(
                      DictonaryBasedExternalBuildableIndex <int> .GetCreateMethodWithVarintPostingsLists(),
                      externalIndexPath,
                      BlockSize);
            var indexBuilder = new IndexBuilder <int, IEnumerable <int> >(buildableIndex);
            var processor    = new WikitextProcessor();

            indexBuilder.IndexCorpus(processor.Transform(reader.Read()));

            using var index = buildableIndex.Build();

            var serializer = new ExternalIndexSerializer <int>();

            serializer.Serialize(externalIndexPath, index);
        }
Beispiel #3
0
 public void BuildBlockedExternalIndexTest_DictionaryBased_VarintPostingsList()
 {
     BuildBlockedExternalIndexTest(DictonaryBasedExternalBuildableIndex <string> .GetCreateMethodWithVarintPostingsLists());
 }