import pytest

from core.tools.utils.text_processing_utils import remove_leading_symbols


@pytest.mark.parametrize(
    ("input_text", "expected_output"),
    [
        ("...Hello, World!", "Hello, World!"),
        ("。测试中文标点", "测试中文标点"),
        # Note: ! is not in the removal pattern, only @# are removed, leaving "!Test symbols"
        # The pattern intentionally excludes ! as per #11868 fix
        ("@#Test symbols", "Test symbols"),
        ("Hello, World!", "Hello, World!"),
        ("", ""),
        ("   ", "   "),
        ("【测试】", "【测试】"),
        # Markdown link preservation - should be preserved if text starts with a markdown link
        ("[Google](https://google.com) is a search engine", "[Google](https://google.com) is a search engine"),
        ("[Example](http://example.com) some text", "[Example](http://example.com) some text"),
        # Leading symbols before markdown link are removed, including the opening bracket [
        ("@[Test](https://example.com)", "[Test](https://example.com)"),
        ("~~标题~~", "标题~~"),
        ('""quoted', "quoted"),
        ("''test", "test"),
        ("##话题", "话题"),
        ("$$价格", "价格"),
        ("%%百分比", "百分比"),
        ("&&与逻辑", "与逻辑"),
        ("((括号))", "括号))"),
        ("**强调**", "强调**"),
        ("++自增", "自增"),
        (",,逗号", "逗号"),
        ("..省略", "省略"),
        ("//注释", "注释"),
        ("::范围", "范围"),
        (";;分号", "分号"),
        ("<<左移", "左移"),
        ("==等于", "等于"),
        (">>右移", "右移"),
        ("??疑问", "疑问"),
        ("@@提及", "提及"),
        ("^^上标", "上标"),
        ("__下划线", "下划线"),
        ("``代码", "代码"),
        ("~~删除线", "删除线"),
        ("　全角空格开头", "全角空格开头"),
        ("、顿号开头", "顿号开头"),
        ("。句号开头", "句号开头"),
        ("「引号」测试", "引号」测试"),
        ("『书名号』", "书名号』"),
        ("【保留】测试", "【保留】测试"),
        ("〖括号〗测试", "括号〗测试"),
        ("〔括号〕测试", "括号〕测试"),
        ("~~【保留】~~", "【保留】~~"),
        ('"[公告]"', '[公告]"'),
        ("[公告] 更新", "[公告] 更新"),
        ("【通知】重要", "【通知】重要"),
        ("[[嵌套]]", "[[嵌套]]"),
        ("【【嵌套】】", "【【嵌套】】"),
        ("[【混合】]", "[【混合】]"),
        ("normal text", "normal text"),
        ("123数字", "123数字"),
        ("中文开头", "中文开头"),
        ("alpha", "alpha"),
        ("~", ""),
        ("【", "【"),
        ("[", "["),
        ("~~~", ""),
        ("【【【", "【【【"),
        ("\t制表符", "\t制表符"),
        ("\n换行", "\n换行"),
    ],
)
def test_remove_leading_symbols(input_text, expected_output):
    assert remove_leading_symbols(input_text) == expected_output