Most users of low-code platforms, such as Excel and PowerApps, write programs in domain-specific formula languages to carry out nontrivial tasks. Often users can write most of the program they want, but introduce small mistakes that yield broken formulas. These mistakes, which can be both syntactic and semantic, are hard for low-code users to identify and fix, even though they can be resolved with just a few edits. We formalize the problem of producing such edits as the last-mile repair problem. To address this problem, we developed LaMirage, a LAst-MIle RepAir-engine GEnerator that combines symbolic and neural techniques to perform last-mile repair in low-code formula languages. LaMirage takes a grammar and a set of domain-specific constraints/rules, which jointly approximate the target language, and uses these to generate a repair engine that can fix formulas in that language. To tackle the challenges of localizing errors and ranking candidate repairs, LaMirage leverages neural techniques, whereas it relies on symbolic methods to generate candidate edits. This combination allows LaMirage to find repairs that satisfy the provided grammar and constraints, and then pick the most natural repair. We compare LaMirage to state-of-the-art neural and symbolic approaches on 400 real Excel and Power Fx formulas, where LaMirage outperforms all baselines. We release these benchmarks to encourage subsequent work in low-code domains.

Visualizations are widely used to communicate findings and make data-driven decisions. Unfortunately creating bespoke and reproducible visualizations requires the use of procedural tools such as matplotlib. These tools present a steep learning curve as their documentation often lacks sufficient usage examples to help beginners get started or accomplish a specific task. Forums such as StackOverflow have long helped developers search for code online and adapt it for their use. However, developers still have to sift through search results and understand the code before adapting it for their use.We built a tool called VizSmith which enables code reuse for visualizations by mining visualization code from Kaggle notebooks and creating a database of 7176 reusable Python functions. Given a dataset, columns to visualize and a text query from the user, VizSmith searches this database for appropriate functions, runs them and displays the generated visualizations to the user. At the core of VizSmith is a novel metamorphic testing based approach to automatically assess the reusability of functions, which improves end-to-end synthesis performance by 10% and cuts the number of execution failures by 50%.

While input-output examples are a natural form of specification for program synthesis engines, they can be imprecise for domains such as table transformations. In this paper, we investigate how extracting readily-available information about the user intent behind these input-output examples helps speed up synthesis and reduce overfitting. We present Gauss, a synthesis algorithm for table transformations that accepts partial input-output examples, along with user intent graphs. Gauss includes a novel conflict-resolution reasoning algorithm over graphs that enables it to learn from mistakes made during the search and use that knowledge to explore the space of programs even faster. It also ensures the final program is consistent with the user intent specification, reducing overfitting. We implement Gauss for the domain of table transformations (supporting Pandas and R), and compare it to three state-of-the-art synthesizers accepting only input-output examples. We find that it is able to reduce the search space by 56×, 73× and 664× on average, resulting in 7×, 26× and 7× speedups in synthesis times on average, respectively.

Traditional automatic program repair (APR) tools rely on a test-suite as a repair specification. But test suites even when available are not of specification quality, limiting the performance and hence viability of test-suite based repair. On the other hand, static analysis-based bug finding tools are seeing increasing adoption in industry but still face challenges since the reported violations are viewed as not easily actionable. We propose a novel solution that solves both these challenges through a technique for automatically generating high-quality patches for static analysis violations by learning from examples. Our approach uses the static analyzer as an oracle and does not require a test suite. We realize our solution in a system, Phoenix, that implements a fully-automated pipeline that mines and cleans patches for static analysis violations from the wild, learns generalized executable repair strategies as programs in a novel Domain Specific Language (DSL), and then instantiates concrete repairs from them on new unseen violations. Using Phoenix we mine a corpus of 5,389 unique violations and patches from 517 Github projects. In a cross-validation study on this corpus Phoenix successfully produced 4,596 bug-fixes, with a recall of 85% and a precision of 54%. When applied to the latest revisions of a further5 Github projects, Phoenix produced 94 correct patches to previously unknown bugs, 19 of which have already been accepted and merged by the development teams. To the best of our knowledge this constitutes, by far the largest application of any automatic patch generation technology to large-scale real-world systems

Developers nowadays have to contend with a growing number of APIs. While in the long-term they are very useful to developers, many modern APIs have an incredibly steep learning curve, due to their hundreds of functions handling many arguments, obscure documentation, and frequently changing semantics. For APIs that perform data transformations, novices can often provide an I/O example demonstrating the desired transformation, but may be stuck on how to translate it to the API. A programming-by-example synthesis engine that takes such I/O examples and directly produces programs in the target API could help such novices. Such an engine presents unique challenges due to the breadth of real-world APIs, and the often-complex constraints over function arguments. We present a generator-based synthesis approach to contend with these problems. This approach uses a program candidate generator, which encodes basic constraints on the space of programs. We introduce neural-backed operators which can be seamlessly integrated into the program generator. To improve the efficiency of the search, we simply use these operators at non-deterministic decision points, instead of relying on domain-specific heuristics. We implement this technique for the Python pandas library in AutoPandas. AutoPandas supports 119 pandas dataframe transformation functions. We evaluate AutoPandas on 26 real-world benchmarks and find it solves 17 of them.

Bounded model checking based debugging solutions search for mutations of program expressions that produce the expected output for a currently failing test. However, the current localization tools are not regression aware: they do not use information from the passing tests in their localization formula. On the other hand, the current repair tools attempt to guarantee regression freedom: when provided with a set of passing tests, they guarantee that none of these tests can break due to the suggested repair patch, thereby constructing a large repair formula.