"""XlsxParser 单元测试"""

import pytest
from openpyxl import Workbook

from exceptions import ParseError
from parsers.xlsx_parser import XlsxParser


@pytest.fixture
def parser():
    return XlsxParser()


def _create_xlsx(path, sheets=None):
    """
    创建测试用 XLSX 文件。

    Args:
        path: 输出文件路径
        sheets: dict，key 为 sheet 名称，value 为二维列表（行×列的数据）
                如果为 None，创建空工作簿
    """
    wb = Workbook()
    # 删除默认 sheet
    wb.remove(wb.active)

    if sheets:
        for sheet_name, rows in sheets.items():
            ws = wb.create_sheet(title=sheet_name)
            for row in rows:
                ws.append(row)

    wb.save(str(path))


def _create_xlsx_with_merge(path, sheet_name, rows, merges):
    """
    创建带合并单元格的 XLSX 文件。

    Args:
        path: 输出文件路径
        sheet_name: 工作表名称
        rows: 二维列表（行×列的数据）
        merges: 合并区域列表，如 ["A1:B1", "A2:A3"]
    """
    wb = Workbook()
    wb.remove(wb.active)
    ws = wb.create_sheet(title=sheet_name)

    for row in rows:
        ws.append(row)

    for merge_range in merges:
        ws.merge_cells(merge_range)

    wb.save(str(path))


class TestSupportedExtensions:
    def test_supports_xlsx(self, parser):
        assert ".xlsx" in parser.supported_extensions()

    def test_only_one_extension(self, parser):
        assert len(parser.supported_extensions()) == 1


class TestParse:
    def test_simple_table(self, parser, tmp_path):
        """基本表格转换为 Markdown"""
        xlsx_path = tmp_path / "simple.xlsx"
        _create_xlsx(xlsx_path, {
            "Sheet1": [
                ["Name", "Age"],
                ["Alice", 30],
                ["Bob", 25],
            ]
        })
        result = parser.parse(str(xlsx_path))
        assert "## Sheet1" in result
        assert "| Name | Age |" in result
        assert "| --- | --- |" in result
        assert "| Alice | 30 |" in result
        assert "| Bob | 25 |" in result

    def test_multiple_sheets(self, parser, tmp_path):
        """多个工作表各自生成标题和表格"""
        xlsx_path = tmp_path / "multi.xlsx"
        _create_xlsx(xlsx_path, {
            "Users": [["Name"], ["Alice"]],
            "Orders": [["ID"], ["001"]],
        })
        result = parser.parse(str(xlsx_path))
        assert "## Users" in result
        assert "## Orders" in result
        assert "| Name |" in result
        assert "| ID |" in result

    def test_empty_sheet_skipped(self, parser, tmp_path):
        """空工作表应被跳过"""
        xlsx_path = tmp_path / "empty_sheet.xlsx"
        _create_xlsx(xlsx_path, {
            "Empty": [],
            "Data": [["Col1"], ["Val1"]],
        })
        result = parser.parse(str(xlsx_path))
        assert "## Empty" not in result
        assert "## Data" in result

    def test_all_empty_sheets(self, parser, tmp_path):
        """所有工作表都为空时返回空字符串"""
        xlsx_path = tmp_path / "all_empty.xlsx"
        _create_xlsx(xlsx_path, {"Empty1": [], "Empty2": []})
        result = parser.parse(str(xlsx_path))
        assert result.strip() == ""

    def test_pipe_escaped(self, parser, tmp_path):
        """单元格中的 | 应被转义为 |"""
        xlsx_path = tmp_path / "pipe.xlsx"
        _create_xlsx(xlsx_path, {
            "Sheet1": [["Header"], ["value|with|pipes"]],
        })
        result = parser.parse(str(xlsx_path))
        assert "|" in result
        assert "value|with|pipes" in result

    def test_newline_escaped(self, parser, tmp_path):
        """单元格中的换行符应被转义为 <br>"""
        xlsx_path = tmp_path / "newline.xlsx"
        _create_xlsx(xlsx_path, {
            "Sheet1": [["Header"], ["line1\nline2"]],
        })
        result = parser.parse(str(xlsx_path))
        assert "line1<br>line2" in result

    def test_backtick_escaped(self, parser, tmp_path):
        """单元格中的反引号应被转义为 &#96;"""
        xlsx_path = tmp_path / "backtick.xlsx"
        _create_xlsx(xlsx_path, {
            "Sheet1": [["Header"], ["code `snippet`"]],
        })
        result = parser.parse(str(xlsx_path))
        assert "&#96;" in result

    def test_none_cell_becomes_empty(self, parser, tmp_path):
        """None 值的单元格应显示为空"""
        xlsx_path = tmp_path / "none.xlsx"
        _create_xlsx(xlsx_path, {
            "Sheet1": [["A", "B"], ["val", None]],
        })
        result = parser.parse(str(xlsx_path))
        assert "| val |  |" in result

    def test_merged_cells(self, parser, tmp_path):
        """合并单元格应填充左上角的值"""
        xlsx_path = tmp_path / "merged.xlsx"
        _create_xlsx_with_merge(
            xlsx_path,
            sheet_name="Data",
            rows=[
                ["Category", "Value"],
                ["Fruit", 10],
                [None, 20],  # A3 will be merged with A2
            ],
            merges=["A2:A3"],
        )
        result = parser.parse(str(xlsx_path))
        assert "## Data" in result
        # The merged cell (A3) should have the value from A2 ("Fruit")
        lines = result.split("\n")
        data_lines = [l for l in lines if l.startswith("| ") and "---" not in l and "Category" not in l]
        assert len(data_lines) == 2
        # Both data rows should contain "Fruit"
        assert all("Fruit" in line for line in data_lines)

    def test_sheet_name_as_heading(self, parser, tmp_path):
        """工作表名称应作为 ## 标题"""
        xlsx_path = tmp_path / "named.xlsx"
        _create_xlsx(xlsx_path, {
            "Sales Report": [["Month", "Revenue"], ["Jan", "1000"]],
        })
        result = parser.parse(str(xlsx_path))
        assert "## Sales Report" in result

    def test_nonexistent_file_raises(self, parser):
        with pytest.raises(ParseError) as exc_info:
            parser.parse("/nonexistent/path/file.xlsx")
        assert "file.xlsx" in exc_info.value.file_name
        assert exc_info.value.reason != ""

    def test_corrupted_file_raises(self, parser, tmp_path):
        xlsx_path = tmp_path / "corrupted.xlsx"
        xlsx_path.write_bytes(b"this is not an xlsx file")
        with pytest.raises(ParseError) as exc_info:
            parser.parse(str(xlsx_path))
        assert "corrupted.xlsx" in exc_info.value.file_name

    def test_parse_error_contains_filename(self, parser):
        with pytest.raises(ParseError) as exc_info:
            parser.parse("/no/such/report.xlsx")
        assert exc_info.value.file_name == "report.xlsx"

    def test_numeric_values(self, parser, tmp_path):
        """数值类型应正确转换为字符串"""
        xlsx_path = tmp_path / "numeric.xlsx"
        _create_xlsx(xlsx_path, {
            "Sheet1": [["Int", "Float"], [42, 3.14]],
        })
        result = parser.parse(str(xlsx_path))
        assert "42" in result
        assert "3.14" in result

    def test_crlf_escaped(self, parser, tmp_path):
        """\\r\\n 应被转义为 <br>"""
        xlsx_path = tmp_path / "crlf.xlsx"
        _create_xlsx(xlsx_path, {
            "Sheet1": [["Header"], ["line1\r\nline2"]],
        })
        result = parser.parse(str(xlsx_path))
        assert "line1<br>line2" in result