selfcites.py

import re
import sys

# open and read the first argument
with open(sys.argv[1], "r") as in_file:
    bibliography = in_file.read()

# Make sets of the citekeys found in the file, and of the entries
# The self_keys regex matches an upper or lower case cite, citep, citeyear, citeauthor,
# citeyearpar, and then anything between that and the first bracket
# The self_keys regex doesn't handle lists of keys
self_keys = set(
    re.findall(r"\\[C|c]ite[t|p|year|author|yearpar]?.*?\{\s*(.+?)\}", bibliography)
)
entries = set(re.findall(r"@.+?{(.+?)\,", bibliography))

# Print the information
print("I found these self citing keys:\n", "\n".join(self_keys))
print("I found these entries:\n", "\n".join(entries))
print(
    "These self citing keys are not in the entries:\n", "\n".join(self_keys - entries)
)