RunFuzzyMatchSequential(
string[] wordsLookup,
IEnumerable<string> files)
{
// Sequential workflow -> how can we parallelize this work?
// The collection 'matchSet' cannot be shared among threads
var matchSet = new HashSet<WordDistanceStruct>();
foreach (var file in files)
{
string readText = File.ReadAllText(file);
var words = readText.Split(punctuation.Value)
.Where(w => !IgnoreWords.Contains(w))
.AsSet();
foreach (var wl in wordsLookup)
{
var bestMatch = JaroWinklerModule.bestMatch(words, wl, threshold);
matchSet.AddRange(bestMatch);
}
}
return PrintSummary(matchSet);
}
public static (bool Matched, string Word) CpuMatch(string word)
{
var match = JaroWinklerModule.bestMatch(WordsToSearch, word, 0.9);
return(match.Any() ? (true, match.First().Match) : (false, null));
}
