Learning Regexes to Extract Network Names from Hostnames
Matthew J. Luckie, Alexander Marder, Bradley Huffaker, kc claffy · Asian Internet Engineering Conference · 2021
We present the design, implementation, evaluation, and validation of a system that automatically learns regular expressions (regexes) to extract network names from Internet hostnames assigned by operators using their own conventions. Our fully automated method does not rely on a human to provide a starting regex, labeled examples of valid extractions, or a dictionary of network names. Our method first learns the dictionary of network names, and then automatically generates and evaluates regexes that extract these names. We validate our dictionary against ground truth, finding that 97.3% of the names our regexes extract are valid names for the networks.