public FactoryFileSeparator(DirectoryInfo di)
{
foreach (var fi in di.GetFiles("*.txt", SearchOption.AllDirectories))
{
K_Google.AddFile(fi);
FileSeprator(fi);
}
}
public Web(string url)
{
K_Google.AddWeb(url);
List <string> lstSub = new List <string>();
// Séparateur de mot
Char[] delimiter = new char[] { '[', ']', '#', '^', '¦', '|', '£', '<', '>', '_', '$', '\n', '\r', '.', ' ', ',', '\'', '!', '?', '(', ')', '%', '&', '"', '=', '+', '{', '}', '*', ';', ':', '\\', '-', '/' };
// Tableau stockant les mots
String[] substrings;
// Regex controlant si l'url rentré par l'utilisateur est bien une url
Regex urlRegex = new Regex("(http|https):\\/\\/(\\w+:{0,1}\\w*@)?(\\S+)(:[0-9]+)?(\\/|\\/([\\w#!:.?+=&%@!\\-]))?");
using (WebClient webClient = new WebClient())
{
// Si l'adresse est bien un url recupere le code source et en garde que le text
if (url != "" && urlRegex.IsMatch(url))
{
Uri uri = new Uri(url);
SetOccurence(Separator(getTextInHTML(uri)), null, lstOccurence, url);
}
}
}
public WordOnTxt(DirectoryInfo di)
{
string _encoding = "1252";
foreach (var fi in di.GetFiles("*.txt", SearchOption.AllDirectories))
{
K_Google.AddFile(fi);
List <string> lstWord = new List <string>();
using (FileStream fs = File.OpenRead(fi.FullName))
{
Ude.CharsetDetector cdet = new Ude.CharsetDetector();
cdet.Feed(fs);
cdet.DataEnd();
if (cdet.Charset != null)
{
_encoding = cdet.Charset;
//Console.WriteLine(_encoding);
}
else
{
Console.WriteLine("Detection failed.");
}
}
string path = fi.DirectoryName + "\\" + fi.Name;
Console.WriteLine(path);
StreamReader Reader = new StreamReader(path, Encoding.GetEncoding(_encoding));
string polpi = Reader.ReadToEnd();
Reader.Close();
polpi = polpi.ToLower();
Char[] delimiter = new char[] { '[', ']', '#', '^', '¦', '|', '£', '<', '>', '_', '$', '\n', '\r', '.', ' ', ',', '\'', '!', '?', '(', ')', '%', '&', '"', '=', '+', '{', '}', '*', ';', ':', '\\', '-', '/' };
String[] substrings = polpi.Split(delimiter);
//List<string> lstSub = new List<string>(substrings);
List <string> lstSub = new List <string>();
foreach (string word in substrings)
{
if (word.Count() > 0)
{
lstSub.Add(word);
}
}
lstSub.Sort();
foreach (var substring in lstSub)
{
if (!lstWord.Contains(substring))
{
lstWord.Add(substring);
}
}
lstSub.Sort();
foreach (var word in lstWord)
{
AddWord(word);
}
List <string> lstWord2 = new List <string>();
foreach (var substring in lstSub)
{
if (!lstWord2.Contains(substring))
{
Ocurrence ocucu = new Ocurrence(fi, substring);
if (!lstOccurence.Contains(ocucu))
{
lstOccurence.Add(ocucu);
lstWord2.Add(substring);
}
}
else
{
foreach (Ocurrence occurence in lstOccurence)
{
if (occurence.Word == substring)
{
occurence.IncreamentOccurence();
}
}
}
}
}
foreach (Ocurrence ocu in lstOccurence)
{
ocu.SendToDataBase();
}
}
