Google published a report on it’s effort to migrate code to the latest dependencies – an often thankless task fraught with risk. Google’s code migrations involved: changing 32-bit IDs in the 500-plus-million-line codebase for Google Ads to 64-bit IDs; converting its old JUnit3 testing library to\u00a0JUnit4; and replacing the Joda time library with Java’s standard java.time package. The 32-bit ID’s were particularly rough because they were often generically defined types that were not easily searchable.<\/p>\n\n\n\n
They used a collection of AI tools as well as manual code reviews and touch-ups to achieve their goal. They emphasize that LLMs should be viewed as complementary to traditional migration techniques that rely on Abstract Syntax Trees (ASTs), grep-like searches, Kythe<\/a>, and custom scripts because LLMs can be very expensive.<\/p>\n\n\n\n The results?<\/p>\n\n\n\n With LLM assistance, it took just three months to migrate 5,359 files and modify 149,000 lines of code to complete the JUnit3-JUnit4 transition. Approximately 87 percent of the code generated by AI ended up being committed with no changes. For the Joda-Java time framework switch, the authors estimate a time saving of 89 percent compared to the projected manual change time.<\/p>\n<\/blockquote>\n\n\n\n Links:<\/p>\n\n\n\n Google published a report on it’s effort to migrate code to the latest dependencies – an often thankless task fraught with risk. Google’s code migrations involved: changing 32-bit IDs in the 500-plus-million-line codebase for Google Ads to 64-bit IDs; converting its old JUnit3 testing library to\u00a0JUnit4; and replacing the Joda time library with Java’s standard java.time package. The 32-bit ID’s were particularly rough because they were often generically defined types that were not easily searchable. They used a collection of…<\/p>\n\n
\n