Using Deep Learning to Generate Complete Log Statements

TL;DR

This paper introduces LANCE, a deep learning approach that automatically generates complete log statements in Java code, including message content, log level, and injection points, to assist developers in effective logging practices.

Contribution

LANCE is the first model supporting comprehensive decision-making for log statement placement, content, and level using a large-scale transformer trained on millions of Java methods.

Findings

Properly identifies log injection points in 65.9% of cases

Selects correct log level in 66.2% of cases

Generates fully correct log statements in 15.2% of cases

Abstract

Logging is a practice widely adopted in several phases of the software lifecycle. For example, during software development log statements allow engineers to verify and debug the system by exposing fine-grained information of the running software. While the benefits of logging are undisputed, taking proper decisions about where to inject log statements, what information to log, and at which log level (e.g., error, warning) is crucial for the logging effectiveness. In this paper, we present LANCE (Log stAtemeNt reCommEnder), the first approach supporting developers in all these decisions. LANCE features a Text-To-Text-Transfer-Transformer (T5) model that has been trained on 6,894,456 Java methods. LANCE takes as input a Java method and injects in it a full log statement, including a human-comprehensible logging message and properly choosing the needed log level and the statement location. Our results show that LANCE is able to (i) properly identify the location in the code where to inject the statement in 65.9% of Java methods requiring it; (ii) selecting the proper log level in 66.2% of cases; and (iii) generate a completely correct log statement including a meaningful logging message in 15.2% of cases.