d3i-szct/paste/util/xlsx.py

from typing import Union, List, Optional, Dict, Any

import pandas as pd

from paste.util import ufont


def cm_to_excel_units(cm):
    """
    厘米转Excel列宽单位。

    :param cm: 厘米单位
    """
    return cm / 2.54 * 7  # 1英寸=2.54厘米, 1Excel单位=1/7英寸


def auto_width_cm(series: pd.Series, font_name='Microsoft YaHei', font_size=11, min_cm=1.5, max_cm=20):
    """
    自动列宽计算方法（区分中英文）。

    :param series: pandas Series (数据列)
    :param font_name: 字体名称
    :param font_size: 字号
    :param min_cm: 最小列宽(厘米)
    :param max_cm: 最大列宽(厘米)
    :return: 建议的列宽(厘米)
    """
    # 获取精确字体度量
    en_width_cm, cn_width_cm = ufont.get_font_metrics(font_name, font_size)

    def calculate_text_width(text):
        """计算文本总宽度"""
        cn_count = 0
        en_count = 0
        for char in str(text):
            if '\u4e00' <= char <= '\u9fff':
                cn_count += 1
            else:
                en_count += 1

        _total_width = (cn_count * cn_width_cm) + (en_count * en_width_cm)
        return _total_width

    # 计算列标题宽度
    title_width = calculate_text_width(series.name)

    # 计算数据内容最大宽度
    content_width = series.astype(str).apply(calculate_text_width).max()

    # 取最大值并增加边距，15%额外边距
    total_width = max(title_width, content_width) * 1.2

    return max(min(total_width, max_cm), min_cm)


def auto_column_width(df, worksheet):
    """
    根据内容自动设置列的宽度。

    :param df: pandas DataFrame
    :param worksheet: 工作表
    """
    _font_name_set = ufont.get_fonts()
    for col_num, col_name in enumerate(df.columns):
        # 计算列宽
        width_cm = auto_width_cm(df[col_name], font_name=_font_name_set[0], font_size=11)
        # 设置列宽
        worksheet.set_column(col_num, col_num, cm_to_excel_units(width_cm))


def apply_header_style(df, worksheet, workbook, **kwargs):
    """
    应用表头样式。

    :param df: 原始 DataFrame
    :param worksheet: xlsxwriter worksheet对象
    :param workbook: xlsxwriter workbook对象
    :param kwargs: 样式参数
    :return: 无
    """
    _style_sheet = {
        'font_size': 12,
        'bg_color': '#F2F2F2',
        'border': 1,
        'bold': True,
    }
    _header_style = workbook.add_format({**_style_sheet, **kwargs})

    for col_num, value in enumerate(df.columns.values):
        worksheet.write(0, col_num, value, _header_style)


def apply_data_style(df, worksheet, workbook, **kwargs):
    """
    应用数据单元格样式。

    :param df: 原始 DataFrame
    :param worksheet: xlsxwriter worksheet对象
    :param workbook: xlsxwriter workbook对象
    :param kwargs: 样式参数
    :return: 无
    """
    _style_sheet = {
        'font_size': 12,
        'border': 1,
    }
    _cell_style = workbook.add_format({**_style_sheet, **kwargs})

    for row in range(1, len(df) + 1):
        for col in range(0, len(df.columns)):
            worksheet.write(row, col, df.iloc[row - 1, col], _cell_style)


def insert_text_to_column(
        worksheet,
        workbook,
        column: int,
        start_row: int,
        texts: Union[str, List[str]],
        text_format: Optional[Dict[str, Any]] = None
) -> None:
    """
    向Excel表格的指定列插入文本。

    :param worksheet: xlsxwriter worksheet
    :param workbook: xlsxwriter workbook
    :param column: 列号
    :param start_row: 开始插入的行号(1-based)
    :param texts: 要插入的文本(字符串或字符串列表)
    :param text_format: 格式字典，None则使用默认格式
    :return: None
    """
    # 设置默认格式
    default_format = {
        'font_size': 12,
    }

    # 合并用户自定义格式
    fmt = workbook.add_format({**default_format, **(text_format or {})})

    # 转换列号为数字索引(1-based)
    if isinstance(column, str):
        col_idx = ord(column.upper()) - ord('A') + 1
    else:
        col_idx = column

    # 确保texts是列表形式
    if isinstance(texts, str):
        texts = [texts]

    # 处理每行数据
    for i, text in enumerate(texts):
        row_num = start_row + i
        worksheet.write(row_num, col_idx, text, fmt)