private static void ExecuteExtractiontest(IEnumerable <TextIndexingRequest> content,
string keywordTest,
ITextCache cache = null)
{
var host = new ExtractorHost();
host.RegisterScopedExtractor <PassthroughExtractor>();
host.RegisterScopedExtractor <DefaultTdfExtractor>();
// Testing instance approaching
host.RegisterScopedExtractor(new DefaultHtmlExtractor());
// Testing factory approach
host.RegisterScopedExtractor(p => new DefaultXmlExtractor(p));
host.Initialize();
cache = cache ?? new DefaultIntermediateCacheProvider();
cache.Clear();
var agent = new IndexerAgent(host, cache, (ISearchProvider)cache);
var agentWorker = agent.IndexDocuments(CancellationToken.None, content);
agentWorker.GetAwaiter().GetResult();
var resultsWorker = agent.Search(CancellationToken.None,
new TextSearch(CultureInfo.InvariantCulture,
"REGEX",
keywordTest));
var results = resultsWorker.GetAwaiter().GetResult().ToArray();
Console.WriteLine(results.Length);
Assert.IsTrue(results.Length > 0);
}
public void ExtractorHostTestTextPlain()
{
var host = new ExtractorHost();
host.RegisterScopedExtractor <PassthroughExtractor>();
host.RegisterScopedExtractor <DefaultHtmlExtractor>();
host.Initialize();
using (host.BeginServiceScope(out var extractor)) {
var detailsForHtml = new IndexingRequestDetails(CultureInfo.InvariantCulture,
Encoding.Unicode,
"text/plain",
string.Empty,
string.Empty);
var finalHtml = extractor.ExtractText(
detailsForHtml,
GetTestObjectStream()
);
Assert.IsTrue(finalHtml.ExtractionPointDetails.Any(c => c.Segment.Contains("1")));
Assert.IsTrue(finalHtml.ExtractionPointDetails.Any(c => c.Segment.Contains("2")));
Assert.IsTrue(finalHtml.ExtractionPointDetails.Any(c => c.Segment.Contains("3")));
Assert.IsTrue(finalHtml.ExtractionPointDetails.Any(c => c.Segment.Contains("_")));
Assert.IsTrue(finalHtml.ExtractionPointDetails.Any(c => c.Segment.Contains("4")));
Assert.IsTrue(finalHtml.ExtractionPointDetails.Any(c => c.Segment.Contains("html")));
}
}