Update app.py

app.py

@@ -6,6 +6,7 @@ import io
 import base64
 import matplotlib.gridspec as gridspec
 import math
+import re  # 新增正则模块
 
 SPLIT_TIME = "17:30"
 BUSINESS_START = "09:30"
@@ -14,187 +15,196 @@ BORDER_COLOR = '#A9A9A9'
 DATE_COLOR = '#A9A9A9'
 
 def process_schedule(file):
-"""处理上传的 Excel 文件，生成排序和分组后的打印内容"""
-try:
-# 读取 Excel，跳过前 8 行
-df = pd.read_excel(file, skiprows=8)
-
-# 提取所需列 (G9, H9, J9)
-df = df.iloc[:, [6, 7, 9]] # G, H, J 列
-df.columns = ['Hall', 'StartTime', 'EndTime']
-
-# 清理数据
-df = df.dropna(subset=['Hall', 'StartTime', 'EndTime'])
-
-# 关键修改：影厅格式转换为带LaTeX上标井号
-df['Hall'] = df['Hall'].str.extract(r'(\d+)号').astype(str) + r'$^{\#}$' # <-- 修正后的表达式
-
-# 保存原始时间字符串用于诊断
-df['original_end'] = df['EndTime']
-
-# 转换时间为 datetime 对象
-base_date = datetime.today().date()
-df['StartTime'] = pd.to_datetime(df['StartTime'])
-df['EndTime'] = pd.to_datetime(df['EndTime'])
-
-# 设置基准时间
-business_start = datetime.strptime(f"{base_date} {BUSINESS_START}", "%Y-%m-%d %H:%M")
-business_end = datetime.strptime(f"{base_date} {BUSINESS_END}", "%Y-%m-%d %H:%M")
-
-# 处理跨天情况
-if business_end < business_start:
-business_end += timedelta(days=1)
-
-# 标准化所有时间到同一天
-for idx, row in df.iterrows():
-end_time = row['EndTime']
-if end_time.hour < 9:
-df.at[idx, 'EndTime'] = end_time + timedelta(days=1)
-
-if row['StartTime'].hour >= 21 and end_time.hour < 9:
-df.at[idx, 'EndTime'] = end_time + timedelta(days=1)
-
-# 筛选营业时间内的场次
-df['time_for_comparison'] = df['EndTime'].apply(
-lambda x: datetime.combine(base_date, x.time())
-)
-
-df.loc[df['time_for_comparison'].dt.hour < 9, 'time_for_comparison'] += timedelta(days=1)
-
-valid_times = (
-((df['time_for_comparison'] >= datetime.combine(base_date, business_start.time())) &
-(df['time_for_comparison'] <= datetime.combine(base_date + timedelta(days=1), business_end.time())))
-)
-
-df = df[valid_times]
-
-# 按散场时间排序
-df = df.sort_values('EndTime')
-
-# 分割数据
-split_time = datetime.strptime(f"{base_date} {SPLIT_TIME}", "%Y-%m-%d %H:%M")
-split_time_for_comparison = df['time_for_comparison'].apply(
-lambda x: datetime.combine(base_date, split_time.time())
-)
-
-part1 = df[df['time_for_comparison'] <= split_time_for_comparison].copy()
-part2 = df[df['time_for_comparison'] > split_time_for_comparison].copy()
-
-# 格式化时间显示
-for part in [part1, part2]:
-part['EndTime'] = part['EndTime'].dt.strftime('%-I:%M')
-
-# 关键修改：精确读取C6单元格
-date_df = pd.read_excel(
-file,
-skiprows=5, # 跳过前5行（0-4）
-nrows=1, # 只读1行
-usecols=[2], # 第三列（C列）
-header=None # 无表头
-)
-date_cell = date_df.iloc[0, 0]
-
-try:
-# 处理不同日期格式
-if isinstance(date_cell, str):
-date_str = datetime.strptime(date_cell, '%Y-%m-%d').strftime('%Y-%m-%d')
-else:
-date_str = pd.to_datetime(date_cell).strftime('%Y-%m-%d')
-except:
-date_str = datetime.today().strftime('%Y-%m-%d')
-
-return part1[['Hall', 'EndTime']], part2[['Hall', 'EndTime']], date_str
-
-except Exception as e:
-st.error(f"处理文件时出错: {str(e)}")
-return None, None, None
+    """处理上传的 Excel 文件，生成排序和分组后的打印内容"""
+    try:
+        # 读取 Excel，跳过前 8 行
+        df = pd.read_excel(file, skiprows=8)
+        
+        # 提取所需列 (G9, H9, J9)
+        df = df.iloc[:, [6, 7, 9]]  # G, H, J 列
+        df.columns = ['Hall', 'StartTime', 'EndTime']
+        
+        # 清理数据
+        df = df.dropna(subset=['Hall', 'StartTime', 'EndTime'])
+        
+        # 转换影厅格式为带LaTeX上标井号
+        df['Hall'] = df['Hall'].str.extract(r'(\d+)号').astype(str) + r'$^{\#}$'
+        
+        # 保存原始时间字符串用于诊断
+        df['original_end'] = df['EndTime']
+        
+        # 转换时间为 datetime 对象
+        base_date = datetime.today().date()
+        df['StartTime'] = pd.to_datetime(df['StartTime'])
+        df['EndTime'] = pd.to_datetime(df['EndTime'])
+        
+        # 设置基准时间
+        business_start = datetime.strptime(f"{base_date} {BUSINESS_START}", "%Y-%m-%d %H:%M")
+        business_end = datetime.strptime(f"{base_date} {BUSINESS_END}", "%Y-%m-%d %H:%M")
+        
+        # 处理跨天情况
+        if business_end < business_start:
+            business_end += timedelta(days=1)
+        
+        # 标准化所有时间到同一天
+        for idx, row in df.iterrows():
+            end_time = row['EndTime']
+            if end_time.hour < 9:
+                df.at[idx, 'EndTime'] = end_time + timedelta(days=1)
+            
+            if row['StartTime'].hour >= 21 and end_time.hour < 9:
+                df.at[idx, 'EndTime'] = end_time + timedelta(days=1)
+        
+        # 筛选营业时间内的场次
+        df['time_for_comparison'] = df['EndTime'].apply(
+            lambda x: datetime.combine(base_date, x.time())
+        )
+        
+        df.loc[df['time_for_comparison'].dt.hour < 9, 'time_for_comparison'] += timedelta(days=1)
+        
+        valid_times = (
+            ((df['time_for_comparison'] >= datetime.combine(base_date, business_start.time())) &
+             (df['time_for_comparison'] <= datetime.combine(base_date + timedelta(days=1), business_end.time())))
+        )
+        
+        df = df[valid_times]
+        
+        # 按散场时间排序
+        df = df.sort_values('EndTime')
+        
+        # 分割数据
+        split_time = datetime.strptime(f"{base_date} {SPLIT_TIME}", "%Y-%m-%d %H:%M")
+        split_time_for_comparison = df['time_for_comparison'].apply(
+            lambda x: datetime.combine(base_date, split_time.time())
+        )
+        
+        part1 = df[df['time_for_comparison'] <= split_time_for_comparison].copy()
+        part2 = df[df['time_for_comparison'] > split_time_for_comparison].copy()
+        
+        # 格式化时间显示
+        for part in [part1, part2]:
+            part['EndTime'] = part['EndTime'].dt.strftime('%-I:%M')
+        
+        # 读取日期信息
+        date_df = pd.read_excel(
+            file,
+            skiprows=5,
+            nrows=1,
+            usecols=[2],
+            header=None
+        )
+        date_cell = date_df.iloc[0, 0]
+        
+        try:
+            if isinstance(date_cell, str):
+                date_str = datetime.strptime(date_cell, '%Y-%m-%d').strftime('%Y-%m-%d')
+            else:
+                date_str = pd.to_datetime(date_cell).strftime('%Y-%m-%d')
+        except:
+            date_str = datetime.today().strftime('%Y-%m-%d')
+        
+        return part1[['Hall', 'EndTime']], part2[['Hall', 'EndTime']], date_str
+    
+    except Exception as e:
+        st.error(f"处理文件时出错: {str(e)}")
+        return None, None, None
 
 def create_print_layout(data, title, date_str):
-"""创建打印布局"""
-if data.empty:
-return None
-
-# 设置 A5 纸张竖向尺寸
-fig = plt.figure(figsize=(5.83, 8.27), dpi=300)
-plt.subplots_adjust(left=0.05, right=0.95, top=0.95, bottom=0.05)
-
-# 设置字体
-plt.rcParams['font.family'] = 'sans-serif'
-plt.rcParams['font.sans-serif'] = ['Arial Unicode MS']
-
-# 计算行数和总数
-total_items = len(data)
-num_cols = 3
-num_rows = math.ceil(total_items / num_cols)
-
-# 创建网格
-gs = gridspec.GridSpec(num_rows + 1, num_cols, hspace=0.1, wspace=0.1, height_ratios=[1] * num_rows + [0.2])
-
-base_fontsize = min(30, 265 / num_rows)
-
-data_values = data.values.tolist()
-
-while len(data_values) % 3 != 0:
-data_values.append(['', ''])
-
-rows_per_col = math.ceil(len(data_values) / 3)
-
-sorted_data = [['', '']] * len(data_values)
-
-for i, item in enumerate(data_values):
-if item[0] and item[1]:
-row = i % rows_per_col
-col = i // rows_per_col
-new_index = row * 3 + col
-if new_index < len(sorted_data):
-sorted_data[new_index] = item
-
-for idx, (hall, end_time) in enumerate(sorted_data):
-if hall and end_time:
-row = idx // 3
-col = idx % 3
-
-ax = plt.subplot(gs[row, col])
-
-for spine in ax.spines.values():
-spine.set_color(BORDER_COLOR)
-spine.set_linewidth(0.5)
-
-display_text = f"{hall}{end_time}"
-ax.text(0.5, 0.5, display_text,
-fontsize=base_fontsize,
-fontweight='bold',
-ha='center',
-va='center')
-
-ax.set_xlim(-0.02, 1.02)
-ax.set_ylim(-0.02, 1.02)
-
-ax.set_xticks([])
-ax.set_yticks([])
-
-# 添加日期信息
-ax_date = plt.subplot(gs[0, 0])
-ax_date.text(0.05, 0.95, f"{date_str} {title}",
-fontsize=base_fontsize * 0.4,
-color=DATE_COLOR,
-fontweight='bold',
-ha='left',
-va='top')
-
-for spine in ax_date.spines.values():
-spine.set_visible(False)
-ax_date.set_xticks([])
-ax_date.set_yticks([])
-
-# 转换为图片
-buffer = io.BytesIO()
-plt.savefig(buffer, format='png', bbox_inches='tight', pad_inches=0.05)
-buffer.seek(0)
-image_base64 = base64.b64encode(buffer.getvalue()).decode()
-plt.close()
-
-return f'data:image/png;base64,{image_base64}'
+    """创建打印布局"""
+    if data.empty:
+        return None
+        
+    # 设置 A5 纸张横向尺寸
+    fig = plt.figure(figsize=(5.83, 8.27), dpi=300)
+    plt.subplots_adjust(left=0.05, right=0.95, top=0.95, bottom=0.05)
+    
+    # 设置字体
+    plt.rcParams['font.family'] = 'sans-serif'
+    plt.rcParams['font.sans-serif'] = ['Arial Unicode MS']
+    
+    # 计算行数和总数
+    total_items = len(data)
+    num_cols = 3
+    num_rows = math.ceil(total_items / num_cols)
+    
+    # 创建网格
+    gs = gridspec.GridSpec(num_rows + 1, num_cols, hspace=0.1, wspace=0.1, height_ratios=[1] * num_rows + [0.2])
+    
+    # 计算最大字符数
+    max_char_count = 0
+    for hall, end_time in data.values:
+        # 清理LaTeX标记并计算实际显示字符数
+        clean_hall = re.sub(r'\$.*?\$', '#', hall)
+        clean_text = f"{clean_hall}{end_time}"
+        current_count = len(clean_text)
+        max_char_count = max(max_char_count, current_count)
+    
+    # 动态计算基础字号（确保最长文本占90%宽度）
+    cell_width_inches = 5.83 / 3  # 每列宽度（A5横向）
+    available_width = cell_width_inches * 0.9 * 72  # 转换为点数（1英寸=72点）
+    avg_char_width = 0.6  # 经验值（Arial字体字符宽度系数）
+    base_fontsize = available_width / (max_char_count * avg_char_width)
+    base_fontsize = min(30, base_fontsize)  # 最大不超过30pt
+    
+    # 填充数据
+    data_values = data.values.tolist()
+    while len(data_values) % 3 != 0:
+        data_values.append(['', ''])
+        
+    sorted_data = [['', '']] * len(data_values)
+    
+    for i, item in enumerate(data_values):
+        if item[0] and item[1]:
+            row = i % math.ceil(len(data_values)/3)
+            col = i // math.ceil(len(data_values)/3)
+            new_index = row * 3 + col
+            if new_index < len(sorted_data):
+                sorted_data[new_index] = item
+    
+    for idx, (hall, end_time) in enumerate(sorted_data):
+        if hall and end_time:
+            row = idx // 3
+            col = idx % 3
+            
+            ax = plt.subplot(gs[row, col])
+            
+            for spine in ax.spines.values():
+                spine.set_color(BORDER_COLOR)
+                spine.set_linewidth(0.5)
+            
+            ax.text(0.5, 0.5, f"{hall}{end_time}",
+                    fontsize=base_fontsize,
+                    fontweight='bold',
+                    ha='center',
+                    va='center')
+            
+            ax.set_xlim(-0.02, 1.02)
+            ax.set_ylim(-0.02, 1.02)
+            ax.set_xticks([])
+            ax.set_yticks([])
+    
+    # 添加日期信息
+    ax_date = plt.subplot(gs[0, 0])
+    ax_date.text(0.05, 0.95, f"{date_str} {title}",
+                 fontsize=base_fontsize * 0.4,
+                 color=DATE_COLOR,
+                 fontweight='bold',
+                 ha='left',
+                 va='top')
+    
+    for spine in ax_date.spines.values():
+        spine.set_visible(False)
+    ax_date.set_xticks([])
+    ax_date.set_yticks([])
+    
+    # 转换为图片
+    buffer = io.BytesIO()
+    plt.savefig(buffer, format='png', bbox_inches='tight', pad_inches=0.05)
+    buffer.seek(0)
+    image_base64 = base64.b64encode(buffer.getvalue()).decode()
+    plt.close()
+    
+    return f'data:image/png;base64,{image_base64}'
 
 # Streamlit 界面
 st.set_page_config(page_title="散厅时间快捷打印", layout="wide")
@@ -203,24 +213,24 @@ st.title("散厅时间快捷打印")
 uploaded_file = st.file_uploader("上传【放映场次核对表.xls】文件", type=["xls", "xlsx"])
 
 if uploaded_file:
-part1, part2, date_str = process_schedule(uploaded_file)
-
-if part1 is not None and part2 is not None:
-part1_image = create_print_layout(part1, "A", date_str)
-part2_image = create_print_layout(part2, "C", date_str)
-
-col1, col2 = st.columns(2)
-
-with col1:
-st.subheader("白班散场预览（时间 ≤ 17:30）")
-if part1_image:
-st.image(part1_image)
-else:
-st.info("白班部分没有数据")
-
-with col2:
-st.subheader("夜班散场预览（时间 > 17:30）")
-if part2_image:
-st.image(part2_image)
-else:
-st.info("夜班部分没有数据")
+    part1, part2, date_str = process_schedule(uploaded_file)
+    
+    if part1 is not None and part2 is not None:
+        part1_image = create_print_layout(part1, "A", date_str)
+        part2_image = create_print_layout(part2, "C", date_str)
+        
+        col1, col2 = st.columns(2)
+        
+        with col1:
+            st.subheader("白班散场预览（时间 ≤ 17:30）")
+            if part1_image:
+                st.image(part1_image)
+            else:
+                st.info("白班部分没有数据")
+        
+        with col2:
+            st.subheader("夜班散场预览（时间 > 17:30）")
+            if part2_image:
+                st.image(part2_image)
+            else:
+                st.info("夜班部分没有数据")