Upload app.py

app.py

@@ -25,7 +25,9 @@ from scipy import stats
 from scipy.cluster.hierarchy import dendrogram, linkage
 import networkx as nx
 from matplotlib.patches import Rectangle
-
+import os
+import urllib.request
+from pathlib import Path
 warnings.filterwarnings('ignore')
 
 # 设置绘图样式
@@ -57,40 +59,99 @@ STOPWORDS = set([
 ])
 
 
+def download_chinese_font():
+    """自动下载中文字体到项目目录"""
+    font_dir = Path("fonts")
+    font_dir.mkdir(exist_ok=True)
+
+    font_path = font_dir / "SourceHanSansSC-Regular.otf"
+
+    if font_path.exists():
+        print(f"✅ 字体已存在: {font_path}")
+        return str(font_path)
+
+    print("📥 正在下载思源黑体...")
+
+    # 使用 GitHub 镜像源（更稳定）
+    font_urls = [
+        "https://github.com/adobe-fonts/source-han-sans/raw/release/OTF/SimplifiedChinese/SourceHanSansSC-Regular.otf",
+        "https://ghproxy.com/https://github.com/adobe-fonts/source-han-sans/raw/release/OTF/SimplifiedChinese/SourceHanSansSC-Regular.otf",
+        "https://cdn.jsdelivr.net/gh/adobe-fonts/source-han-sans@release/OTF/SimplifiedChinese/SourceHanSansSC-Regular.otf"
+    ]
+
+    for url in font_urls:
+        try:
+            print(f"尝试从 {url[:50]}... 下载")
+            urllib.request.urlretrieve(url, font_path)
+            print(f"✅ 字体下载成功: {font_path}")
+            return str(font_path)
+        except Exception as e:
+            print(f"⚠️ 下载失败: {e}")
+            continue
+
+    print("❌ 所有字体源下载失败")
+    return None
+
+
 def get_chinese_font():
-    """根据操作系统获取中文字体路径"""
+    """获取中文字体路径（优先下载）"""
+    # 1. 优先使用下载的字体
+    downloaded_font = download_chinese_font()
+    if downloaded_font and os.path.exists(downloaded_font):
+        return downloaded_font
+
+    # 2. 尝试系统字体（Debian Trixie）
+    system_fonts = [
+        '/usr/share/fonts/opentype/noto/NotoSansCJK-Regular.ttc',
+        '/usr/share/fonts/truetype/wqy/wqy-zenhei.ttc',
+        '/usr/share/fonts/truetype/noto/NotoSansCJK-Regular.ttc',
+    ]
+
+    for font in system_fonts:
+        if os.path.exists(font):
+            print(f"✅ 找到系统字体: {font}")
+            return font
+
+    # 3. Windows/Mac 备用
     system = platform.system()
     if system == 'Windows':
-        fonts = [
-            'C:/Windows/Fonts/msyh.ttc',
-            'C:/Windows/Fonts/simhei.ttf',
-            'C:/Windows/Fonts/simsun.ttc',
-        ]
+        win_fonts = ['C:/Windows/Fonts/msyh.ttc', 'C:/Windows/Fonts/simhei.ttf']
+        for font in win_fonts:
+            if os.path.exists(font):
+                return font
     elif system == 'Darwin':
-        fonts = [
-            '/System/Library/Fonts/STHeiti Light.ttc',
-            '/Library/Fonts/Arial Unicode.ttf',
-        ]
-    else:
-        fonts = [
-            '/usr/share/fonts/truetype/wqy/wqy-microhei.ttc',
-            '/usr/share/fonts/truetype/droid/DroidSansFallbackFull.ttf',
-        ]
-
-    for font in fonts:
-        if os.path.exists(font):
-            return font
+        mac_fonts = ['/System/Library/Fonts/STHeiti Light.ttc']
+        for font in mac_fonts:
+            if os.path.exists(font):
+                return font
+
+    print("⚠️ 未找到任何中文字体")
     return None
 
 
+# 初始化字体
 CHINESE_FONT = get_chinese_font()
 
+# 配置 Matplotlib
 if CHINESE_FONT:
-    if platform.system() == 'Windows':
-        plt.rcParams['font.sans-serif'] = ['Microsoft YaHei', 'SimHei']
-    else:
-        plt.rcParams['font.sans-serif'] = ['Arial Unicode MS', 'DejaVu Sans']
-plt.rcParams['axes.unicode_minus'] = False
+    import matplotlib.pyplot as plt
+    from matplotlib import font_manager
+
+    # 注册字体
+    font_manager.fontManager.addfont(CHINESE_FONT)
+    font_prop = font_manager.FontProperties(fname=CHINESE_FONT)
+
+    plt.rcParams['font.sans-serif'] = [font_prop.get_name()]
+    plt.rcParams['font.family'] = 'sans-serif'
+    plt.rcParams['axes.unicode_minus'] = False
+
+    print(f"✅ Matplotlib 已配置字体: {font_prop.get_name()}")
+else:
+    import matplotlib.pyplot as plt
+
+    plt.rcParams['font.sans-serif'] = ['DejaVu Sans']
+    plt.rcParams['axes.unicode_minus'] = False
+    print("⚠️ 使用默认字体（可能不支持中文）")
 
 
 class TourismDataAnalyzer: