"""Unit tests for identifier sanitization."""

import re

import pytest

from iac_reverse.generator.sanitize import sanitize_identifier


TERRAFORM_IDENTIFIER_RE = re.compile(r"^[a-zA-Z_][a-zA-Z0-9_]*$")


class TestSanitizeIdentifierNormalNames:
    def test_simple_name_passes_through(self):
        assert sanitize_identifier("nginx") == "nginx"

    def test_name_with_underscores_passes_through(self):
        assert sanitize_identifier("my_app") == "my_app"

    def test_alphanumeric_name_passes_through(self):
        assert sanitize_identifier("app123") == "app123"


class TestSanitizeIdentifierHyphens:
    def test_hyphens_replaced_with_underscore(self):
        assert sanitize_identifier("my-app") == "my_app"

    def test_multiple_hyphens(self):
        assert sanitize_identifier("my-cool-app") == "my_cool_app"


class TestSanitizeIdentifierLeadingDigits:
    def test_leading_digit_gets_underscore_prefix(self):
        assert sanitize_identifier("123abc") == "_123abc"

    def test_all_digits(self):
        result = sanitize_identifier("12345")
        assert result == "_12345"
        assert TERRAFORM_IDENTIFIER_RE.match(result)


class TestSanitizeIdentifierSpaces:
    def test_spaces_replaced_with_underscore(self):
        assert sanitize_identifier("my app") == "my_app"

    def test_multiple_spaces_collapse(self):
        assert sanitize_identifier("my   app") == "my_app"


class TestSanitizeIdentifierUnicode:
    def test_unicode_replaced(self):
        # é is replaced with underscore, trailing underscore preserved
        assert sanitize_identifier("café") == "caf_"

    def test_all_unicode(self):
        result = sanitize_identifier("日本語")
        assert result == "_resource"

    def test_emoji_replaced(self):
        result = sanitize_identifier("app🚀name")
        assert result == "app_name"


class TestSanitizeIdentifierEmptyAndSpecial:
    def test_empty_string_returns_resource(self):
        assert sanitize_identifier("") == "_resource"

    def test_all_special_chars_returns_resource(self):
        assert sanitize_identifier("@#$%^&*") == "_resource"

    def test_single_special_char(self):
        assert sanitize_identifier("!") == "_resource"


class TestSanitizeIdentifierConsecutiveSpecialChars:
    def test_multiple_consecutive_special_chars_collapse(self):
        assert sanitize_identifier("a---b") == "a_b"

    def test_mixed_special_chars_collapse(self):
        assert sanitize_identifier("a-.-b") == "a_b"

    def test_leading_special_chars_collapse(self):
        # Leading hyphens become underscore (valid identifier start)
        result = sanitize_identifier("---abc")
        assert result == "_abc"


class TestSanitizeIdentifierAlwaysValid:
    """Verify the result always matches the Terraform identifier regex."""

    @pytest.mark.parametrize("name", [
        "nginx",
        "my-app",
        "123abc",
        "my app",
        "café",
        "",
        "@#$%^&*",
        "a---b",
        "___",
        "hello_world_123",
        "日本語テスト",
        "  leading spaces",
        "trailing  ",
        "MixedCase-Name_123",
        "a",
        "_",
        "0",
    ])
    def test_result_matches_terraform_regex(self, name):
        result = sanitize_identifier(name)
        assert TERRAFORM_IDENTIFIER_RE.match(result), (
            f"sanitize_identifier({name!r}) = {result!r} does not match "
            f"Terraform identifier pattern"
        )