You may implement something as shown below.
Pseudo Code:
ignored = CreateHashTableOfIgnoredWords();
xref = CreateEmptyCrossReference();
foreach(line in ReadAllLines("document file name"))
{
foreach (word in line)
{
xref.AddXref(word, line.Number) if (!ignored.Contains(word));
}
}
xref.Serialize("index file name");
...
CrossReference.AddXref(key, ref)
{
xrefEntry = GetEntry(key) or CreateAndAddNewXrefEntry(key);
xrefEntry.Add(ref);
}
Cheers
Andi