For book-keeping it's important to respect a naming convention.

The full name of a json file is too long to be retained. Ntuples are produced using a json file, so to keep track of the used json file, the ntuples are stored under a directory having the short name of the json file.

The convention is the following:

{runMin}-{runMax}_{rerecoName|Prompt}_v{versionID}

runMin is the first run of the json
runMax is the last run of the json
rerecoName is the official name of the reprocessing or use "Prompt" if prompt reco
every json file is produced with a version number _v1 or _v2, etc. Use the same

For example, for the json file:

 /afs/cern.ch/cms/CAF/CMSCOMM/COMM_DQM/certification/Collisions12/8TeV/Reprocessing/Cert_190456-208686_8TeV_22Jan2013ReReco_Collisions12_JSON.txt

the jsonName should be: 190456-208686_22Jan_v1