"""测试所有 XLS Readers 的一致性。"""

import pytest
from readers.xls import unstructured, markitdown, pandas


class TestXlsReadersConsistency:
    """验证所有 XLS Readers 解析同一文件时核心文字内容一致。"""

    def test_parsers_importable(self):
        """测试所有 parser 模块可以正确导入。"""
        # 验证模块导入成功
        assert unstructured is not None
        assert markitdown is not None
        assert pandas is not None
        assert hasattr(unstructured, 'parse')
        assert hasattr(markitdown, 'parse')
        assert hasattr(pandas, 'parse')

    def test_parser_functions_callable(self):
        """测试 parse 函数是可调用的。"""
        assert callable(unstructured.parse)
        assert callable(markitdown.parse)
        assert callable(pandas.parse)

    def test_all_readers_parse_same_content(self, simple_xls_path):
        """测试所有 Readers 解析同一文件时核心内容一致。"""
        # 收集所有 readers 的解析结果
        parsers = [
            ("unstructured", unstructured.parse),
            ("markitdown", markitdown.parse),
            ("pandas", pandas.parse),
        ]

        successful_results = []
        for name, parser in parsers:
            content, error = parser(simple_xls_path)
            if content is not None and content.strip():
                successful_results.append((name, content))

        # 至少应该有一个 reader 成功解析，或者都不解析也可以
        if len(successful_results) > 0:
            # 验证所有成功的 readers 都包含核心内容
            core_texts = ["姓名", "年龄", "城市", "张三", "李四"]
            for name, content in successful_results:
                # 至少包含一个核心文本
                assert any(text in content for text in core_texts), \
                    f"{name} 解析结果不包含核心内容"