The application of machine learning algorithms for source code has grown in the past years. Since these algorithms are quite sensitive to input data, it is not surprising that researchers experiment with input representations. Nowadays, a popular starting point to represent code is by using abstract syntax trees.

Abstract syntax trees have been used for a long time in various SE domains, and in particular in IDEs. API of modern IDEs provides an ability to manipulate ASTs, traverse them, resolve references between code elements, etc. Such algorithms can enrich AST with new data, and therefore may be useful in ML-based code analysis.

In this work, we present PSIMiner — a tool for processing PSI trees from the IntelliJ Platform. PSI trees contain code’s syntax tree as well as functions to work with it. We use our tool to infer types of identifiers in Java ASTs and extend the code2seq model for the method name prediction problem.