Finding repeated strings in code repositories and its applications to code-clone detection

Although researchers have created many advanced code-clone detection techniques, more effort is required to realize wide adaptation of these techniques in the industry. One of the reasons behind this is the reliance of these advanced techniques on lexing and parsing programs. Modern programming languages have complex lexical conventions and grammar, which evolve constantly. Therefore, using advanced code-clone detection techniques requires substantial and continuous effort. This paper proposes a lightweight language-independent method to detect code clones by simply finding repeated strings in a code repository, relying on neither lexing nor parsing. The proposed method is based on an efficient technique developed in a bio-informatics context to find repeated strings. We refer to the repeated strings in the source-code as weak Type-1 clones. Because the proposed technique normalizes newlines, tabs, and white spaces into a single white space, it can find clones in which newline positions or indentations are changed, as often in the case when copy-pasting occurs. Although the proposed method only finds verbatim copies, it also makes interesting observations regarding repository structures. Many developers may prefer the proposed simple approach because it is easier to understand than other advanced techniques that use heuristics, approximation, and machine learning.