jaro_winkler_similarity_rapid_fuzz.py

"""
    Connexion to SQL Server 2019
"""

import sys
import json
import pyodbc
from rapidfuzz import distance


def main():
    if len(sys.argv) > 1:
        _, target_string, registered_by = sys.argv
        records = get_research(int(registered_by))
        print(process_data(target_string, records))
    else:
        print("Script Must Have 2 Args")


def get_connection():
    SERVER = "127.0.0.1"
    PORT = "1433"
    DATABASE = "DATABASE_NAME"
    USERNAME = "USERNAME"
    PASSWORD = "PASSWORD"

    connection_string = f"DRIVER={{ODBC Driver 17 for SQL Server}};SERVER={SERVER};PORT={PORT};DATABASE={DATABASE};UID={USERNAME};PWD={PASSWORD}"

    return pyodbc.connect(connection_string)


def get_research(user_id: int):
    SQL_QUERY = f"EXEC dbo.usp_research_approximate_matches {user_id}"
    cursor = get_connection().cursor()
    cursor.execute(SQL_QUERY)

    return cursor.fetchall()


def process_data(target_string: str, records: list):
    result_list = []

    for record in records:
        jaro_winkler = distance.JaroWinkler.similarity(
            target_string.encode("utf-8"), record.title.encode("utf-8")
        )

        if jaro_winkler >= 0.8:
            result_list.append(
                ResearchMatchingProcess(
                    record.research_id, record.title, round(jaro_winkler, 6)
                )
            )

    return json.dumps([result.__dict__ for result in result_list])


class ResearchMatchingProcess:
    def __init__(self, research_id, title, result) -> None:
        self.research_id = research_id
        self.title = title
        self.result = result


if __name__ == "__main__":
    main()