Compress AAABBCCCC into A3B2C4 with regular expressions

string_compressor.py

#!/usr/bin/env python3
import re


def compress_iter(instr):
    """Generate one compressed chunk at a time, e.g. "A3"""
    for match in re.finditer(r'(.)\1{0,}', instr):
        yield match.group()[0] + str(len(match.group()))


def compress(instr: str) -> str:
    """Compress AAABBCCCC into A3B2C4"""
    return ''.join(compress_iter(instr))
    

def test_compressor():
    assert compress('AAAAB') == 'A4B1'
    assert compress('aaaabbcddddee') == 'a4b2c1d4e2'
    assert compress('') == ''
    assert compress(' ') == ' 1'
    assert compress('🤖🤖🤖') == '🤖3'
  
  
if __name__ == '__main__':
    test_compressor()