/// <summary>
/// The constructor is private so that only the class itself can create an instance.
/// </summary>
private WordsCache()
{
settings = PluginSettings.Instance();
dbProvider = DBConnectionStringProvider.Instance();
settings.DBConnectionString = dbProvider.ProvideDBConnectionString("CrawlWave.ServerPlugins.WordExtraction");
dbcon = new SqlConnection(settings.DBConnectionString);
words = new Hashtable();
stemming = Stemming.Instance();
culture = new CultureInfo("el-GR");
LoadCache();
}
/// <summary>
/// The private constructor of the WordExtractor class
/// </summary>
private WordExtractor()
{
mutex = new Mutex();
settings = PluginSettings.Instance();
regStripTags = new Regex("<[^>]*>", RegexOptions.CultureInvariant | RegexOptions.Multiline | RegexOptions.IgnoreCase | RegexOptions.Compiled); //<[^>]+> or >(?:(?<t>[^<]*))
regStripScripts = new Regex(@"(?i)<script([^>])*>(\w|\W)*</script([^>])*>", RegexOptions.CultureInvariant | RegexOptions.Multiline | RegexOptions.IgnoreCase | RegexOptions.Compiled); //@"(?i)<script([^>])*>(\w|\W)*</script([^>])*>" or @"<script[^>]*>(\w|\W)*?</script[^>]*>"
regTitleTags = new Regex("<\\s*title[^>]*>[^<]*<\\s*/title\\s*>", RegexOptions.CultureInvariant | RegexOptions.Multiline | RegexOptions.IgnoreCase | RegexOptions.Compiled);
regKeywordTags = new Regex("<meta\\s*name\\s*=\\s*\"keywords\"\\s*content\\s*=\\s*\"[^>]*\">", RegexOptions.CultureInvariant | RegexOptions.Multiline | RegexOptions.IgnoreCase | RegexOptions.Compiled);
regDescriptionTags = new Regex("<meta\\s*name\\s*=\\s*\"description\"\\s*content\\s*=\\s*\"[^>]*\">", RegexOptions.CultureInvariant | RegexOptions.Multiline | RegexOptions.IgnoreCase | RegexOptions.Compiled);
stemming = Stemming.Instance();
slStopWordsEnglish = new SortedList(arStopWordsEnglish.Length);
slStopWordsGreek = new SortedList(arStopWordsGreek.Length);
culture = new CultureInfo("el-GR");
InitializeWordLists();
}
