# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"([0-9]{4}.G[0-9]{2}(?: [0-9]{4}.G[0-9]{2})* |( )(?=Jednostki))"
test_str = "Dane osobowe po zmianie (dopisane): Surname1 Name1 (RYSZARD, EUGENIA) Zam. 99-100 Muczyn (Geod) 6A, Płeć: K, PESEL: 99945104321 Jednostki Rejestrowe osoby (w gminie): 0001.G16 0002.G56 Surname2 Name2 (ANDRZEJ, AGNIESZKA) Zam. 99-100 Muczyn (Geod) 4A, Płeć: K Jednostki Rejestrowe osoby (w gminie): 0001.G16 0001.G07 0001.G43 Surname1 Name1 Name2 (ANDRZEJ, AGNIESZKA) Zam. 99-100 MUCZYN (Geod) 4A, Płeć: M Jednostki Rejestrowe osoby (w gminie): 0001.G16"
subst = "\\0\\n"
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0, re.MULTILINE)
if result:
print (result)
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html