public static Document Document(FileInfo f)
{
// make a new, empty document
Document doc = new Document();
// Add the url as a field named "path". Use a field that is
// indexed (i.e. searchable), but don't tokenize the field into words.
doc.Add(new Field("path", f.FullName.Replace(dirSep, '/'), Field.Store.YES, Field.Index.NOT_ANALYZED));
// Add the last modified date of the file a field named "modified".
// Use a field that is indexed (i.e. searchable), but don't tokenize
// the field into words.
doc.Add(new Field("modified", DateTools.TimeToString(f.LastWriteTime.Millisecond, DateTools.Resolution.MINUTE), Field.Store.YES, Field.Index.NOT_ANALYZED));
// Add the uid as a field, so that index can be incrementally maintained.
// This field is not stored with document, it is indexed, but it is not
// tokenized prior to indexing.
doc.Add(new Field("uid", Uid(f), Field.Store.NO, Field.Index.NOT_ANALYZED));
using (var fileStream = f.OpenRead())
{
var parser = new HTMLParser(fileStream);
// Add the tag-stripped contents as a Reader-valued Text field so it will
// get tokenized and indexed.
doc.Add(new Field("contents", parser.GetReader()));
// Add the summary as a field that is stored and returned with
// hit documents for display.
doc.Add(new Field("summary", parser.GetSummary(), Field.Store.YES, Field.Index.NO));
// Add the title as a field that it can be searched and that is stored.
doc.Add(new Field("title", parser.GetTitle(), Field.Store.YES, Field.Index.ANALYZED));
// return the document
return(doc);
}
}
public static Document Document(FileInfo f)
{
// make a new, empty document
Document doc = new Document();
// Add the url as a field named "path". Use a field that is
// indexed (i.e. searchable), but don't tokenize the field into words.
doc.Add(new Field("path", f.FullName.Replace(dirSep, '/'), Field.Store.YES, Field.Index.NOT_ANALYZED));
// Add the last modified date of the file a field named "modified".
// Use a field that is indexed (i.e. searchable), but don't tokenize
// the field into words.
doc.Add(new Field("modified", DateTools.TimeToString(f.LastWriteTime.Millisecond, DateTools.Resolution.MINUTE), Field.Store.YES, Field.Index.NOT_ANALYZED));
// Add the uid as a field, so that index can be incrementally maintained.
// This field is not stored with document, it is indexed, but it is not
// tokenized prior to indexing.
doc.Add(new Field("uid", Uid(f), Field.Store.NO, Field.Index.NOT_ANALYZED));
using (var fileStream = f.OpenRead())
{
var parser = new HTMLParser(fileStream);
// Add the tag-stripped contents as a Reader-valued Text field so it will
// get tokenized and indexed.
doc.Add(new Field("contents", parser.GetReader()));
// Add the summary as a field that is stored and returned with
// hit documents for display.
doc.Add(new Field("summary", parser.GetSummary(), Field.Store.YES, Field.Index.NO));
// Add the title as a field that it can be searched and that is stored.
doc.Add(new Field("title", parser.GetTitle(), Field.Store.YES, Field.Index.ANALYZED));
// return the document
return doc;
}
}
public static Document Document(System.IO.FileInfo f)
{
// make a new, empty document
Document doc = new Document();
// Add the url as a field named "url". Use an UnIndexed field, so
// that the url is just stored with the document, but is not searchable.
doc.Add(Field.UnIndexed("url", f.FullName.Replace(dirSep, '/')));
// Add the last modified date of the file a field named "modified". Use a
// Keyword field, so that it's searchable, but so that no attempt is made
// to tokenize the field into words.
doc.Add(Field.Keyword("modified", DateField.TimeToString(((f.LastWriteTime.Ticks - 621355968000000000) / 10000))));
// Add the uid as a field, so that index can be incrementally maintained.
// This field is not stored with document, it is indexed, but it is not
// tokenized prior to indexing.
doc.Add(new Field("uid", UID(f), false, true, false));
HTMLParser parser = new HTMLParser(f);
// Add the tag-stripped contents as a Reader-valued Text field so it will
// get tokenized and indexed.
doc.Add(Field.Text("contents", parser.GetReader()));
// Add the summary as an UnIndexed field, so that it is stored and returned
// with hit documents for display.
doc.Add(Field.UnIndexed("summary", parser.GetSummary()));
// Add the title as a separate Text field, so that it can be searched
// separately.
doc.Add(Field.Text("title", parser.GetTitle()));
// return the document
return doc;
}
public static Document Document(System.IO.FileInfo f)
{
// make a new, empty document
Document doc = new Document();
// Add the url as a field named "url". Use an UnIndexed field, so
// that the url is just stored with the document, but is not searchable.
doc.Add(Field.UnIndexed("url", f.FullName.Replace(dirSep, '/')));
// Add the last modified date of the file a field named "modified". Use a
// Keyword field, so that it's searchable, but so that no attempt is made
// to tokenize the field into words.
doc.Add(Field.Keyword("modified", DateField.TimeToString(((f.LastWriteTime.Ticks - 621355968000000000) / 10000))));
// Add the uid as a field, so that index can be incrementally maintained.
// This field is not stored with document, it is indexed, but it is not
// tokenized prior to indexing.
doc.Add(new Field("uid", UID(f), false, true, false));
HTMLParser parser = new HTMLParser(f);
// Add the tag-stripped contents as a Reader-valued Text field so it will
// get tokenized and indexed.
doc.Add(Field.Text("contents", parser.GetReader()));
// Add the summary as an UnIndexed field, so that it is stored and returned
// with hit documents for display.
doc.Add(Field.UnIndexed("summary", parser.GetSummary()));
// Add the title as a separate Text field, so that it can be searched
// separately.
doc.Add(Field.Text("title", parser.GetTitle()));
// return the document
return(doc);
}
