/// <summary>
/// Create index by content of paragraph in page.
/// </summary>
/// <param name="pageID"></param>
private void IndexByParagraph(string pageID)
{
string xmlString;
oneNote.GetPageContent(pageID, out xmlString);
var des = XDocument.Parse(xmlString).Descendants(One + "OE");
currentPageTitle = GetPageTitle(pageID);
currentNotebookTitle = GetPageNotebookTitle(pageID);
if (isDebug)
{
Console.WriteLine("\t" + des.Count() + " Paragraphs");
}
if (des.Count() > 0)
{
foreach (var el in des)
{
var paraID = el.Attribute("objectID").Value;
var text = GetTextFromNode(el);
if (text == null)
{
continue;
}
var paragraphText = RemoveUnwantedTags(text);
lucene.AddDocument(new Tuple <string, string, string>(pageID, paraID, paragraphText));
}
}
}
/// <summary>
/// Take a xml string which follows the standard of
/// </summary>
/// <param name="outputXML"></param>
public void BuildIndex(string outputXML)
{
var info = XDocument.Parse(outputXML);
var pageList = info.Descendants(One + "Page");
int totalCount = pageList.Count();
Console.WriteLine("All Count" + totalCount);
double count = 0;
foreach (var n in pageList)
{
count += 1;
progressRate = count / totalCount;
currentPageTitle = n.Attribute("name").Value;
Console.Write("Adding " + currentPageTitle);
var pageID = n.Attribute("ID").Value;
String xmlString;
oneNote.GetPageContent(pageID, out xmlString);
var doc = XDocument.Parse(xmlString);
var des = doc.Descendants(One + "OE");
Console.WriteLine("\t" + des.Count() + " Paragraphs");
var documentList = new List <Tuple <string, string> >();
foreach (var el in des)
{
var parId = el.Attribute("objectID");
var text = el.Element(One + "T");
if (parId == null || text == null || text.Value.Length <= 2)
{
continue;
}
var id = parId.Value + " " + pageID;
var par = RemoveUnwantedTags(text.Value);
//Console.WriteLine(id + "\t" + par + "\n");
documentList.Add(new Tuple <string, string>(id, par));
}
lucene.AddDocument(documentList);
}
}
