"""测试 XLSX Reader 的解析功能。"""

import pytest
import os
from readers.xlsx import XlsxReader


class TestPandasXlsxReaderParse:
    """测试 XLSX Reader 的 parse 方法。"""

    def test_normal_file(self, temp_xlsx):
        """测试正常 XLSX 文件解析。"""
        # 创建包含数据的测试文件
        file_path = temp_xlsx(data=[
            ["列1", "列2", "列3"],
            ["数据1", "数据2", "数据3"],
            ["测试A", "测试B", "测试C"],
        ])

        reader = XlsxReader()
        content, failures = reader.parse(file_path)

        # 验证解析成功
        assert content is not None, f"解析失败: {failures}"
        assert len(failures) == 0 or all("成功" in f or not f for f in failures)

        # 验证关键内容存在
        assert "列1" in content or "列2" in content
        assert "数据1" in content or "数据2" in content
        assert "测试A" in content or "测试B" in content

    def test_file_not_exists(self, tmp_path):
        """测试文件不存在的情况。"""
        non_existent_file = str(tmp_path / "non_existent.xlsx")

        reader = XlsxReader()
        content, failures = reader.parse(non_existent_file)

        # 验证返回 None 和错误信息
        assert content is None
        assert len(failures) > 0
        assert any("不存在" in f or "找不到" in f for f in failures)

    def test_empty_file(self, temp_xlsx):
        """测试空 XLSX 文件。"""
        # 创建没有任何内容的文件
        file_path = temp_xlsx()

        reader = XlsxReader()
        content, failures = reader.parse(file_path)

        # 空文件可能返回 None、空字符串或只包含表格结构
        assert content is None or len(content.strip()) < 50  # 允许有基本的表格结构

    def test_corrupted_file(self, temp_xlsx, tmp_path):
        """测试损坏的 XLSX 文件。"""
        # 先创建正常文件
        file_path = temp_xlsx(data=[["测试", "内容"]])

        # 破坏文件内容 - 完全覆盖文件
        with open(file_path, "wb") as f:
            f.write(b"corrupted content that is not a valid xlsx file")

        reader = XlsxReader()
        content, failures = reader.parse(file_path)

        # 验证返回 None 和错误信息
        assert content is None
        assert len(failures) > 0

    def test_special_chars(self, temp_xlsx):
        """测试特殊字符处理。"""
        special_data = [
            ["中文", "Emoji😀", "特殊符号©"],
            ["测试内容", "🎉🚀", "®™°±"],
            ["Hello你好", "World世界", "混合内容"],
        ]

        file_path = temp_xlsx(data=special_data)

        reader = XlsxReader()
        content, failures = reader.parse(file_path)

        assert content is not None, f"解析失败: {failures}"

        # 验证各种特殊字符都被正确处理
        assert "中文" in content
        assert "😀" in content or "🎉" in content  # 至少包含一个 emoji
        assert "©" in content or "®" in content  # 至少包含一个特殊符号
        assert "Hello" in content or "World" in content


class TestPandasXlsxReaderSupports:
    """测试 XLSX Reader 的 supports 方法。"""

    def test_supports_xlsx_extension(self):
        """测试识别 .xlsx 扩展名。"""
        reader = XlsxReader()
        assert reader.supports("test.xlsx") is True

    def test_supports_uppercase_extension(self):
        """测试识别大写扩展名。"""
        reader = XlsxReader()
        assert reader.supports("TEST.XLSX") is True

    def test_rejects_unsupported_format(self):
        """测试拒绝不支持的格式。"""
        reader = XlsxReader()
        assert reader.supports("test.pdf") is False
        assert reader.supports("test.txt") is False

    def test_supports_path_with_spaces(self):
        """测试包含空格的路径。"""
        reader = XlsxReader()
        assert reader.supports("path with spaces/test.xlsx") is True

    def test_supports_absolute_path(self):
        """测试绝对路径。"""
        reader = XlsxReader()
        assert reader.supports("/absolute/path/test.xlsx") is True
        assert reader.supports("C:\\Windows\\path\\test.xlsx") is True