DeepMerge: Learning to Merge Programs
Elizabeth Dinella, Todd Mytkowicz, A. Svyatkovskiy, Christian Bird, Mayur Naik, Shuvendu K. Lahiri
Abstract
In collaborative software development, program merging is <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">the</i> mechanism to integrate changes from multiple programmers. Merge algorithms in modern version control systems report a conflict when changes interfere textually. Merge conflicts require manual intervention and frequently stall modern continuous integration pipelines. Prior work found that, although costly, a large majority of resolutions involve re-arranging text without writing any new code. Inspired by this observation we propose the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">first data-driven approach</i> to resolve merge conflicts with a machine learning model. We realize our approach in a tool <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DeepMerge</small> that uses a novel combination of (i) an edit-aware embedding of merge inputs and (ii) a variation of pointer networks, to construct resolutions from input segments. We also propose an algorithm to localize manual resolutions in a resolved file and employ it to curate a ground-truth dataset comprising 8,719 non-trivial resolutions in JavaScript programs. Our evaluation shows that, on a held out test set, <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DeepMerge</small> can predict correct resolutions for 37% of non-trivial merges, compared to only 4% by a state-of-the-art semistructured merge technique. Furthermore, on the subset of merges with upto 3 lines (comprising 24% of the total dataset), <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DeepMerge</small> can predict correct resolutions with 78% accuracy.