/// <summary>
/// Reads all the words of a text file filename and sets the
/// important (wanted) words into the sorted list sc.
/// The occurrence of every word in the text is regarded.
/// </summary>
/// <param name="sc"></param>
/// <param name="filename"></param>
/// <param name="language"></param>
/// <returns></returns>
public static bool ReadHTMLFile(out SortedList <string, TagCloudControl.StringItem> sc, string filename, TagCloud.TagCloudControl.TextLanguage language)
{
// give all entries the same timestamp
long last = DateTime.Now.Ticks;
// read the exclude and include strings for the language into an include and an exclude list
FillExcludeIncludeList(language, true);
// read the exclude and include strings for HTML files and add them to the include and exclude list
FillExcludeIncludeList(TagCloud.TagCloudControl.TextLanguage.HTML, false);
sc = new SortedList <string, TagCloudControl.StringItem>();
try
{
if (!File.Exists(filename))
{
return(false);
}
FileStream objFStreamRead = new FileStream(filename, FileMode.Open, FileAccess.Read, FileShare.Read);
StreamReader objSReader = new StreamReader(objFStreamRead, System.Text.Encoding.Default);
string line;
string delimStr = "\t#$&'=/<>+:“„;,. !?(){}[]\\–-_\"»«";
char[] delimiter = delimStr.ToCharArray();
string trimStr = "–-";
char[] trimmer = trimStr.ToCharArray();
while ((line = objSReader.ReadLine()) != null)
{
line = line.Trim(trimmer);
string[] words = line.Split(delimiter);
foreach (string word in words)
{
string newword = word.Trim(trimmer);
// HTML filtered words
if (WantedHTMLWord(newword))
{
// Language filtered words
if (WantedWord(newword))
{
if (!sc.ContainsKey(newword))
{
sc.Add(newword, new TagCloudControl.StringItem(newword, 1, true, last));
}
else
{
// get the previous occurrence
int ind = sc.IndexOfKey(newword);
double occ = sc.Values[ind].Occurrence;
sc.RemoveAt(ind);
sc.Add(newword, new TagCloudControl.StringItem(newword, occ + 1, true, last));
}
}
}
} // foreach
} // while
objSReader.Close();
return(true);
}
catch
{
return(false);
}
}
/// <summary>
/// Sets the strings which should be excluded into the exclude list.
/// Sets the strings which should be included into the include list.
/// The strings are read from a file, depending on the parameter language.
/// If clear == true, the lists will be cleared before being filled, else the
/// new strings will be appended to the lists.
/// </summary>
/// <param name="language"></param>
/// <param name="clear"></param>
/// <returns></returns>
private static int FillExcludeIncludeList(TagCloud.TagCloudControl.TextLanguage language, bool clear)
{
if (clear)
{
ExcludeList.Clear();
IncludeList.Clear();
}
try
{
string txtfile = Path.GetDirectoryName(Assembly.GetExecutingAssembly().Location);
switch (language)
{
case TagCloudControl.TextLanguage.German:
txtfile = Path.Combine(txtfile, "ExcludeList-de.txt");
break;
case TagCloudControl.TextLanguage.HTML:
txtfile = Path.Combine(txtfile, "ExcludeList-html.txt");
break;
default: // default is english
txtfile = Path.Combine(txtfile, "ExcludeList-en.txt");
break;
}
if (!File.Exists(txtfile))
{
return(0);
}
FileStream objFStreamRead = new FileStream(txtfile, FileMode.Open, FileAccess.Read, FileShare.Read);
StreamReader objSReader = new StreamReader(objFStreamRead, System.Text.Encoding.Default);
bool exclude = false;
bool include = false;
string line;
while ((line = objSReader.ReadLine()) != null)
{
line = line.Trim();
if (line.StartsWith("Exclude:"))
{
exclude = true;
include = false;
}
if (line.StartsWith("Include:"))
{
exclude = false;
include = true;
}
string[] items = line.Split(',');
if (exclude)
{
foreach (string item in items)
{
if ((!ExcludeList.Contains(item)) && (item != "Exclude:"))
{
ExcludeList.Add(item);
}
}
}
if (include)
{
foreach (string item in items)
{
if ((!IncludeList.Contains(item)) && (item != "Include:"))
{
IncludeList.Add(item);
}
}
}
}
objSReader.Close();
return(ExcludeList.Count);
}
catch
{
return(0);
}
}
