Regex Unicode


Python 3.8 required


examples/regex/print_unicode.py
print("\N{GREEK CAPITAL LETTER DELTA}")

print("\u05E9")
print("\u05DC")
print("\u05D5")
print("\u05DD")
print("\u262E")
print("\u1F426")   # "bird"

print("\u05E9\u05DC\u05D5\u05DD \u262E")

examples/regex/mixed.txt
Hello World!
Szia Világ!
!שלום עולם

examples/regex/match_unicode.py
import re

filename = "mixed.txt"

with open(filename) as fh:
    lines = fh.readlines()
for line in lines:
    if re.search('\N{IN HEBREW}', line):
        print(line)