Suggesting application programming interfaces based on feature and context analysis

A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a device to cause the device to:

• extract at least one feature of an input function code based on application of one or more text analytics to one or more inputs pertaining to the input function code, wherein said extracting comprises applying one or more natural language processing techniques to the input function code to infer (i) at least one action represented in the input function code and (ii) at least one argument of the at least one action represented in the input function code;
• derive at least one item of context-related information from the input function code;
• generate a suggestion comprising one or more application programming interfaces, wherein said generating comprises comparing (i) the at least one feature of the input function code and (ii) the at least one item of context-related information to a database, and wherein the database comprises (a) feature data and (b) context-related information pertaining to multiple application programming interfaces;
• output the suggestion to at least one user, wherein said outputting comprises prioritizing the one or more application programming interfaces within the suggestion based on frequency of use of the one or more application programming interfaces, and wherein said outputting comprises outputting the suggestion in a code-editor side-view;
• update the suggestion based on one or more additional items of input pertaining to the input function code;
• and
• output the updated suggestion to the at least one user in the code-editor side-view.

A system comprising:

• a memory;
• and
• at least one processor operably coupled to the memory and configured for:
• extracting at least one feature of an input function code based on application of one or more text analytics to one or more inputs pertaining to the input function code, wherein said extracting comprises applying one or more natural language processing techniques to the input function code to infer (i) at least one action represented in the input function code and (ii) at least one argument of the at least one action represented in the input function code;
• deriving at least one item of context-related information from the input function code;
• generating a suggestion comprising one or more application programming interfaces, wherein said generating comprises comparing (i) the at least one feature of the input function code and (ii) the at least one item of context-related information to a database, and wherein the database comprises (a) feature data and (b) context-related information pertaining to multiple application programming interfaces;
• outputting the suggestion to at least one user, wherein said outputting comprises prioritizing the one or more application programming interfaces within the suggestion based on frequency of use of the one or more application programming interfaces, and wherein said outputting comprises outputting the suggestion in a code-editor side-view;
• updating the suggestion based on one or more additional items of input pertaining to the input function code;
• and
• outputting the updated suggestion to the at least one user in the code-editor side-view.

A computer-implemented method, comprising:

• automatically identifying one or more features from each of multiple function codes, wherein each of the multiple function codes is associated with a particular application programming interface;
• automatically identifying one or more items of context-related information pertaining to each of the multiple function codes;
• generating a database by storing (i) the one or more identified features and (ii) the one or more identified items of context-related information;
• extracting at least one feature of an input function code based on application of one or more text analytics to one or more inputs pertaining to the input function code, wherein said extracting comprises applying one or more natural language processing techniques to the input function code to infer (i) at least one action represented in the input function code and (ii) at least one argument of the at least one action represented in the input function code;
• deriving at least one item of context-related information from the input function code;
• generating a suggestion comprising one or more application programming interfaces, wherein said generating comprises comparing (i) the at least one feature of the input function code and (ii) the at least one item of context-related information to the generated database;
• outputting the suggestion to at least one user, wherein said outputting comprises prioritizing the one or more application programming interfaces within the suggestion based on frequency of use of the one or more application programming interfaces, and wherein said outputting comprises outputting the suggestion in a code-editor side-view;
• updating the suggestion based on one or more additional items of input pertaining to the input function code;
• and
• outputting the updated suggestion to the at least one user in the code-editor side-view;
• wherein the method is carried out by at least one computing device.