System Search Service Implementation Based on a Custom Lexical Search

Abstract

The search bar on any system is a highly employed and advantageous feature that helps make lives easier every day. Users see a tremendous improvement in their efficiencies as the search bar retrieves applications, and documents in a specific folder with just the file name. It helps avoid manual searching throughout the system. However, the existing technology does not help in the retrieval of documents where the search query is generic and about the document, and not just its name. This study presents a developed application that could be used to retrieve documents from anywhere on the system with user input keywords. These keywords are present inside the document and cannot be read by the existing technology of the search bar on the systems. The user can enter vernacular text as the search query on this application’s search bar. The application would accurately retrieve the files, order them according to relevancy, and list them as ready-to-open files with just a click. The program works with the elimination of the redundancy of reading all documents for each search query and using parallel processing to divide the files into batches. The application runs 303418.495ms, approximately 5 minutes, for the first run where it reads all the documents on the system. From the second run onwards, it takes only 20.080ms, approximately 0.02008 seconds.