import os
import re
import pathlib
import pytest
# small migration filename/header tests; keep imports minimal


MIGRATION_FILENAME = "2026-03-22-add-similarity-cache.sql"
MIGRATION_PATH = pathlib.Path("migrations") / MIGRATION_FILENAME


def _strip_sql_comments(sql: str) -> str:
    """Remove SQL single-line (-- ...) and C-style (/* ... */) comments.

    This is a best-effort stripper sufficient for the test's purpose.
    """
    # remove block comments
    sql = re.sub(r"/\*.*?\*/", "", sql, flags=re.S)
    # remove line comments
    sql = re.sub(r"--.*?$", "", sql, flags=re.M)
    return sql.strip()


def test_migration_file_exists_and_header():
    # file must exist
    assert MIGRATION_PATH.exists(), f"Migration file {MIGRATION_PATH} not found"

    text = MIGRATION_PATH.read_text(encoding="utf8")

    # header should reference the filename and purpose
    assert MIGRATION_FILENAME in text.splitlines()[0], (
        "First line should include the filename"
    )
    assert "similarity" in text.lower(), "Header should mention similarity"


def test_optional_apply_migration_safe():
    # If TEST_DB_URL is set, try to apply the SQL only if it contains non-comment statements.
    db_url = os.environ.get("TEST_DB_URL")
    sql = MIGRATION_PATH.read_text(encoding="utf8")
    stripped = _strip_sql_comments(sql)

    # If there is no DB url, consider this a filename/header validation test only.
    if not db_url:
        pytest.skip("TEST_DB_URL not set; skipping DB apply step")

    # If the SQL is empty (only comments), nothing to apply — test passes.
    if not stripped:
        pytest.skip("Migration contains no executable SQL; nothing to apply")

    # Otherwise attempt to execute the SQL. Be conservative: if drivers are missing or
    # connection fails, skip the test rather than failing CI. Only unexpected errors
    # during execution should fail the test.
    try:
        if db_url.startswith("sqlite:"):
            import sqlite3

            # sqlite URL might be sqlite:///path or sqlite:///:memory:
            path = db_url.split("sqlite:", 1)[1]
            # normalize prefixes like ///
            path = path.lstrip("/") or ":memory:"
            conn = sqlite3.connect(path)
            try:
                conn.executescript(sql)
            finally:
                conn.close()
        elif db_url.startswith("postgresql:") or db_url.startswith("postgres:"):
            try:
                import psycopg2
            except Exception as e:  # pragma: no cover - driver may be absent in CI
                pytest.skip(f"psycopg2 not available: {e}")

            # psycopg2 accepts a DSN; rely on that here.
            conn = psycopg2.connect(db_url)
            try:
                cur = conn.cursor()
                cur.execute(sql)
                conn.commit()
            finally:
                conn.close()
        else:
            pytest.skip(f"DB URL scheme not supported by this test: {db_url}")
    except Exception as exc:
        # Unexpected error while applying SQL should fail the test.
        raise