Automating Away Regex

Regular expressions are a potent tool for pattern matching and text manipulation.

Codeium, as an free AI Code Generator, takes regex to the next level by offering real-time suggestions and an in-IDE chat. Today, we'll see how Codeium's in-IDE chat will handle crafting regular expressions.

To evaluate the responses from Codeium, we'll use an existing regex website, regex101, to evaluate Codeium's output.

Emails

For the initial test, I prompted Codeium's chat to generate an email pattern in python. The AI responded with the following:

import re

email_regex = r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'

# Example usage:
email = 'example@email.com'
if re.match(email_regex, email):
    print('Valid email address')
else:
    print('Invalid email address')

Let's see how it stacks up to regex101.

Matched

name@company.com

firstname+lastname@example.com

name@company.co.jp

name@c.cc

Not Matched

name@cc

email@company

name

Social Security Numbers

Let's now try asking Codeium's chat if it can generate a regex for Social Secuirty Numbers. The AI responded with:

import re

pattern = r'\d{3}-\d{2}-\d{4}'

ssn = '123-45-6789'
if re.match(pattern, ssn):
    print("Valid social security number")
else:
    print("Invalid social security number")

Let's see it's performance against regex101.

Matched

843-29-2913

289-20-2812

929-29-8481

Not Matched

188 34 4526

aaa-aa-aaaa

939-23-3921

In conclusion, Codeium demonstrated quite the capability in generating regular expressions. Thopugh not guaranteed to always be 100% perfect, the ability to ask Codeium chat with to come up with regex workflows ensures productive coding experience.