IDF Calibration (Reverse Document Frequency) for document categorization

I doubt the calculation of IDF (Inverse Document Frequency) in the classification of documents. I have more than one category with several documents for training. I calculate the IDF for each term in the document using the following formula:

IDF(t,D)=log(Total Number documents/Number of Document matching term);

My questions:

• What does “Total Number documents in Corpus” mean? Is the document signed from the current category or from all available categories?
• What does “Number of documents matching the term” mean? Does the term match documents with the current category or from all available categories?