import os

import re

# Path to the directory containing SQL scripts

directory_path = '/path/to/sql/scripts'

# Regex pattern to match table names (very basic for demonstration)

# This pattern looks for words that come after "FROM" or "JOIN" followed by optional schema names

pattern = re.compile(r'\bFROM\b\s+([a-zA-Z0-9_\.]+)|\bJOIN\b\s+([a-zA-Z0-9_\.]+)', re.IGNORECASE)

# Set to store unique object names

object_names = set()

# Loop through each file in the directory

for filename in os.listdir(directory_path):

    if filename.endswith('.sql'):  # Check if the file is a SQL file

        filepath = os.path.join(directory_path, filename)

        with open(filepath, 'r') as file:

            content = file.read()

            # Find all matches in the file content

            matches = pattern.findall(content)

            for match in matches:

                # Each match is a tuple because of the groups in the pattern; we add both

                object_names.update(match)

# Remove empty strings that may have been added to the set

object_names.discard('')

print("Found object names:")

for name in object_names:

    print(name)