Fengcai Wen, Emad Aghajani, Csaba Nagy, Michele Lanza, G. Bavota
{"title":"Siri,编写下一个方法","authors":"Fengcai Wen, Emad Aghajani, Csaba Nagy, Michele Lanza, G. Bavota","doi":"10.1109/ICSE43902.2021.00025","DOIUrl":null,"url":null,"abstract":"Code completion is one of the killer features of Integrated Development Environments (IDEs), and researchers have proposed different methods to improve its accuracy. While these techniques are valuable to speed up code writing, they are limited to recommendations related to the next few tokens a developer is likely to type given the current context. In the best case, they can recommend a few APIs that a developer is likely to use next. We present FeaRS, a novel retrieval-based approach that, given the current code a developer is writing in the IDE, can recommend the next complete method (i.e., signature and method body) that the developer is likely to implement. To do this, FeaRS exploits \"implementation patterns\" (i.e., groups of methods usually implemented within the same task) learned by mining thousands of open source projects. We instantiated our approach to the specific context of Android apps. A large-scale empirical evaluation we performed across more than 20k apps shows encouraging preliminary results, but also highlights future challenges to overcome.","PeriodicalId":305167,"journal":{"name":"2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"13","resultStr":"{\"title\":\"Siri, Write the Next Method\",\"authors\":\"Fengcai Wen, Emad Aghajani, Csaba Nagy, Michele Lanza, G. Bavota\",\"doi\":\"10.1109/ICSE43902.2021.00025\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Code completion is one of the killer features of Integrated Development Environments (IDEs), and researchers have proposed different methods to improve its accuracy. While these techniques are valuable to speed up code writing, they are limited to recommendations related to the next few tokens a developer is likely to type given the current context. In the best case, they can recommend a few APIs that a developer is likely to use next. We present FeaRS, a novel retrieval-based approach that, given the current code a developer is writing in the IDE, can recommend the next complete method (i.e., signature and method body) that the developer is likely to implement. To do this, FeaRS exploits \\\"implementation patterns\\\" (i.e., groups of methods usually implemented within the same task) learned by mining thousands of open source projects. We instantiated our approach to the specific context of Android apps. A large-scale empirical evaluation we performed across more than 20k apps shows encouraging preliminary results, but also highlights future challenges to overcome.\",\"PeriodicalId\":305167,\"journal\":{\"name\":\"2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-03-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"13\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICSE43902.2021.00025\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSE43902.2021.00025","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Code completion is one of the killer features of Integrated Development Environments (IDEs), and researchers have proposed different methods to improve its accuracy. While these techniques are valuable to speed up code writing, they are limited to recommendations related to the next few tokens a developer is likely to type given the current context. In the best case, they can recommend a few APIs that a developer is likely to use next. We present FeaRS, a novel retrieval-based approach that, given the current code a developer is writing in the IDE, can recommend the next complete method (i.e., signature and method body) that the developer is likely to implement. To do this, FeaRS exploits "implementation patterns" (i.e., groups of methods usually implemented within the same task) learned by mining thousands of open source projects. We instantiated our approach to the specific context of Android apps. A large-scale empirical evaluation we performed across more than 20k apps shows encouraging preliminary results, but also highlights future challenges to overcome.