alrahma_sunday_school/scripts/compare_sql.py

#!/usr/bin/env python3

import re
import sys
from collections import defaultdict
from pathlib import Path


# Matches common SQL statements containing a table name.
TABLE_PATTERNS = [
    re.compile(
        r'^\s*CREATE\s+TABLE\s+(?:IF\s+NOT\s+EXISTS\s+)?[`"\[]?([^`"\]\s(.]+)',
        re.IGNORECASE,
    ),
    re.compile(
        r'^\s*INSERT\s+INTO\s+[`"\[]?([^`"\]\s(.]+)',
        re.IGNORECASE,
    ),
    re.compile(
        r'^\s*UPDATE\s+[`"\[]?([^`"\]\s(.]+)',
        re.IGNORECASE,
    ),
    re.compile(
        r'^\s*ALTER\s+TABLE\s+[`"\[]?([^`"\]\s(.]+)',
        re.IGNORECASE,
    ),
    re.compile(
        r'^\s*DELETE\s+FROM\s+[`"\[]?([^`"\]\s(.]+)',
        re.IGNORECASE,
    ),
]


def extract_table_name(line):
    """Return table name if the line starts a recognizable table statement."""
    for pattern in TABLE_PATTERNS:
        match = pattern.search(line)
        if match:
            return match.group(1)
    return None


def normalize_line(line):
    """
    Normalize a line for comparison.

    Removes leading/trailing whitespace but otherwise leaves SQL intact.
    """
    return line.strip()


def parse_sql_file(filename):
    """
    Parse SQL into table -> list of (line_number, original_line).

    Once a table-related statement is detected, following lines are associated
    with that table until another table statement begins.
    """
    tables = defaultdict(list)

    current_table = None

    with open(filename, "r", encoding="utf-8", errors="replace") as f:
        for line_number, line in enumerate(f, start=1):
            table = extract_table_name(line)

            if table:
                current_table = table

            if current_table:
                cleaned = normalize_line(line)

                # Ignore completely blank lines.
                if cleaned:
                    tables[current_table].append(
                        (line_number, line.rstrip("\n"))
                    )

    return tables


def line_multiset(lines):
    """
    Convert lines into:
        normalized_line -> list of occurrences

    Keeping occurrences means duplicate INSERT rows are handled correctly.
    """
    result = defaultdict(list)

    for line_number, text in lines:
        result[normalize_line(text)].append((line_number, text))

    return result


def compare_table(table, lines1, lines2, file1, file2):
    data1 = line_multiset(lines1)
    data2 = line_multiset(lines2)

    all_lines = sorted(set(data1) | set(data2))

    only_file1 = []
    only_file2 = []

    for normalized in all_lines:
        occurrences1 = data1.get(normalized, [])
        occurrences2 = data2.get(normalized, [])

        common_count = min(len(occurrences1), len(occurrences2))

        only_file1.extend(occurrences1[common_count:])
        only_file2.extend(occurrences2[common_count:])

    if not only_file1 and not only_file2:
        return False

    print()
    print("=" * 100)
    print(f"TABLE: {table}")
    print("=" * 100)

    if only_file1:
        print(f"\nOnly in {file1}:")
        for line_number, text in only_file1:
            print(f"  Line {line_number}: {text}")

    if only_file2:
        print(f"\nOnly in {file2}:")
        for line_number, text in only_file2:
            print(f"  Line {line_number}: {text}")

    return True


def compare_sql_files(file1, file2):
    tables1 = parse_sql_file(file1)
    tables2 = parse_sql_file(file2)

    all_tables = sorted(set(tables1) | set(tables2))

    print(f"Comparing:")
    print(f"  File 1: {file1}")
    print(f"  File 2: {file2}")
    print()

    differences = 0

    for table in all_tables:
        if table not in tables1:
            print()
            print("=" * 100)
            print(f"TABLE: {table}")
            print("=" * 100)
            print(f"Table exists only in {file2}")
            differences += 1
            continue

        if table not in tables2:
            print()
            print("=" * 100)
            print(f"TABLE: {table}")
            print("=" * 100)
            print(f"Table exists only in {file1}")
            differences += 1
            continue

        if compare_table(
            table,
            tables1[table],
            tables2[table],
            file1,
            file2,
        ):
            differences += 1

    print()
    print("=" * 100)

    if differences == 0:
        print("No table differences found.")
    else:
        print(f"{differences} table(s) contain differences.")


def main():
    if len(sys.argv) != 3:
        script = Path(sys.argv[0]).name
        print(f"Usage: python {script} file1.sql file2.sql")
        sys.exit(1)

    file1 = sys.argv[1]
    file2 = sys.argv[2]

    if not Path(file1).is_file():
        print(f"File not found: {file1}")
        sys.exit(1)

    if not Path(file2).is_file():
        print(f"File not found: {file2}")
        sys.exit(1)

    compare_sql_files(file1, file2)


if __name__ == "__main__":
    main()