Find abbreviations

abbreviations_regexpt.py

# find abbreviations and their positions (start and end indexes) in the text

import re

text = "США и ООН обсуждали события на G20 и 2FA. Также упоминался NASA."

# Regular expression for abbreviations
pattern = r'\b[A-ZА-ЯЁ0-9]{2,}\b'

# Use re.finditer to get match objects with position info
matches = re.finditer(pattern, text)

# Collect (matched abbreviation, start_index, end_index)
results = [(match.group(), match.start(), match.end()) for match in matches]

# Print results
for abbr, start, end in results:
    print(f"Found '{abbr}' at index {start}-{end}")

    
# Output
# Found 'США' at index 0-3
# Found 'ООН' at index 6-9
# Found 'G20' at index 35-38
# Found '2FA' at index 41-44
# Found 'NASA' at index 64-68