Usage of compression IO functions in apache arrow

I have been implementing a suite of RecordBatchReaders for a genomics toolset. The standard unit of work is a RecordBatch. I ended up implementing a lot of my own compression and IO tools instead of using the existing utilities in the arrow cpp platform because I was confused about them. Are there any clear examples of using the existing compression and file IO utilities to simply get a file stream that inflates standard zlib data? Also, an object diagram for the cpp platform would be helpful in ramping up.