Update app.py

app.py

@@ -1,9 +1,8 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 """
-Capricode Pro Master - 精准代码视觉感知系统 (终极版)
-UI增强 & 引擎扩展 - 为大型语言模型提供20种主流语言的精准识别
-经过混合语言压力测试并已修复所有已知逻辑漏洞
+Capricode Pro Master - 精准代码视觉感知系统 (史诗进化版)
+集成项目分析器，支持.zip文件上传分析，完美兼容免费部署环境
 """
 import gradio as gr
 import time
@@ -12,7 +11,14 @@ from dataclasses import dataclass
 from typing import Dict, List, Tuple, Any
 from collections import defaultdict
 
-# ==================== 精准语言识别引擎 (终极版) ====================
+# --- 新增的库 ---
+import os
+import zipfile
+import tempfile
+import shutil
+import matplotlib.pyplot as plt
+
+# ==================== 精准语言识别引擎 (保持不变) ====================
 @dataclass
 class LanguageSignature:
     patterns: List[Tuple[re.Pattern, float]]
@@ -21,162 +27,26 @@ class LanguageSignature:
     file_extensions: List[str]
 
 class PrecisionLanguageDetector:
+    # ... 核心引擎代码与上一版完全相同，此处折叠以节省篇幅 ...
+    # (在最终代码中，这部分是完整存在的)
     def __init__(self):
         self.languages = {}
         self._compile_precision_patterns()
-
     def _compile_precision_patterns(self):
-        """编译所有20种语言的精准特征，并为定义级特征赋予绝对权重"""
-        self.languages = {
-            'python': LanguageSignature(
-                patterns=[(re.compile(r'def\s+\w+\s*\([^)]*\)\s*:'), 9.0), (re.compile(r'class\s+\w+\s*\(?[^)]*\)?\s*:'), 8.5), (re.compile(r'import\s+[\w.]+'), 6.0)],
-                keywords={'def': 8.0, 'class': 7.0, 'import': 6.0, 'elif': 5.0, 'async': 6.0, 'await': 6.0},
-                exclusive_patterns=[(re.compile(r'if __name__ == "__main__":'), 20.0), (re.compile(r'f"[^"]*"'), 12.0)],
-                file_extensions=['.py', '.pyw']
-            ),
-            'javascript': LanguageSignature(
-                patterns=[(re.compile(r'function\s*.*\s*\{'), 8.0), (re.compile(r'console\.log\s*\('), 7.0), (re.compile(r'(const|let|var)\s+\w+\s*='), 8.0)],
-                keywords={'function': 7.0, 'const': 6.0, 'let': 6.0, 'console': 5.0, 'document': 6.0, 'async': 5.0, 'await': 5.0},
-                exclusive_patterns=[(re.compile(r'document\.getElementById\s*\('), 15.0)],
-                file_extensions=['.js', '.jsx', '.mjs']
-            ),
-            'java': LanguageSignature(
-                patterns=[(re.compile(r'public\s+class\s+\w+'), 10.0), (re.compile(r'System\.out\.println\s*\('), 9.0), (re.compile(r'import\s+java\.'), 8.0)],
-                keywords={'public': 8.0, 'class': 8.0, 'static': 7.0, 'void': 6.0, 'String': 7.0, 'System': 7.0, 'new': 5.0},
-                exclusive_patterns=[(re.compile(r'public\s+static\s+void\s+main\s*\(\s*String\s*\[\]\s*args\s*\)'), 25.0)],
-                file_extensions=['.java']
-            ),
-            'cpp': LanguageSignature(
-                patterns=[(re.compile(r'#include\s*<[a-zA-Z_]+>'), 10.0), (re.compile(r'using\s+namespace\s+std;'), 9.0), (re.compile(r'std::cout'), 8.0)],
-                keywords={'#include': 9.0, 'iostream': 8.0, 'std': 7.0, 'cout': 7.0, 'vector': 6.0, 'int': 5.0, 'main': 6.0},
-                exclusive_patterns=[(re.compile(r'#include\s*<iostream>'), 18.0)],
-                file_extensions=['.cpp', '.cxx', '.h', '.hpp']
-            ),
-            'html': LanguageSignature(
-                patterns=[(re.compile(r'<\s*head\s*>'), 8.0), (re.compile(r'<\s*body\s*>'), 8.0), (re.compile(r'<\s*/\s*\w+\s*>'), 6.0)],
-                keywords={'div': 5.0, 'p': 4.0, 'a': 4.0, 'href': 5.0, 'class': 3.0, 'id': 3.0},
-                exclusive_patterns=[(re.compile(r'<!DOCTYPE\s+html>', re.IGNORECASE), 100.0)], # 绝对权重
-                file_extensions=['.html', '.htm']
-            ),
-            'css': LanguageSignature(
-                patterns=[(re.compile(r'[\w\s.#-]+\s*\{'), 8.0), (re.compile(r'[\w-]+\s*:\s*[^;]+;'), 9.0)],
-                keywords={'color': 6.0, 'background-color': 7.0, 'margin': 5.0, 'padding': 5.0, 'font-size': 6.0, 'display': 6.0},
-                exclusive_patterns=[(re.compile(r'@media\s*\(.+\)\s*\{'), 15.0)],
-                file_extensions=['.css']
-            ),
-            'sql': LanguageSignature(
-                patterns=[(re.compile(r'(SELECT|CREATE|INSERT|UPDATE|DELETE|FROM|WHERE)', re.IGNORECASE), 10.0)],
-                keywords={'SELECT': 9.0, 'FROM': 8.0, 'WHERE': 7.0, 'JOIN': 7.0, 'GROUP BY': 8.0, 'ORDER BY': 7.0, 'CREATE TABLE': 9.0},
-                exclusive_patterns=[(re.compile(r'CREATE\s+TABLE', re.IGNORECASE), 18.0)],
-                file_extensions=['.sql']
-            ),
-            'csharp': LanguageSignature(
-                patterns=[(re.compile(r'using\s+System;'), 10.0), (re.compile(r'namespace\s+\w+'), 9.0)],
-                keywords={'namespace': 9.0, 'public': 7.0, 'class': 7.0, 'static': 6.0, 'void': 5.0, 'string': 7.0, 'var': 6.0},
-                exclusive_patterns=[(re.compile(r'static\s+void\s+Main\s*\(\s*string\s*\[\]\s*args\s*\)'), 25.0), (re.compile(r'Console\.WriteLine\s*\('), 15.0)],
-                file_extensions=['.cs']
-            ),
-            'go': LanguageSignature(
-                patterns=[(re.compile(r'package\s+main'), 10.0), (re.compile(r'import\s*\(\s*'), 8.0), (re.compile(r'func\s+\w+\s*\([^)]*\)\s*\{'), 9.0)],
-                keywords={'package': 9.0, 'import': 8.0, 'func': 9.0, 'fmt': 7.0, 'Println': 6.0},
-                exclusive_patterns=[(re.compile(r'func\s+main\s*\(\s*\)'), 20.0), (re.compile(r':='), 12.0)],
-                file_extensions=['.go']
-            ),
-            'rust': LanguageSignature(
-                patterns=[(re.compile(r'fn\s+\w+\s*\([^)]*\)\s*\{'), 10.0), (re.compile(r'use\s+std::'), 9.0), (re.compile(r'let\s+(mut\s+)?\w+'), 8.0)],
-                keywords={'fn': 9.0, 'let': 8.0, 'mut': 7.0, 'use': 8.0, 'struct': 7.0},
-                exclusive_patterns=[(re.compile(r'fn\s+main\s*\(\s*\)'), 20.0), (re.compile(r'println!\s*\('), 18.0)],
-                file_extensions=['.rs']
-            ),
-            'kotlin': LanguageSignature(
-                patterns=[(re.compile(r'fun\s+\w+\s*\([^)]*\)'), 10.0), (re.compile(r'val\s+\w+'), 8.0)],
-                keywords={'package': 8.0, 'import': 7.0, 'fun': 9.0, 'val': 8.0, 'var': 7.0, 'println': 6.0, 'class': 7.0},
-                exclusive_patterns=[(re.compile(r'fun\s+main\s*\(\s*args:\s*Array<String>\s*\)'), 25.0)],
-                file_extensions=['.kt', '.kts']
-            ),
-            'ruby': LanguageSignature(
-                patterns=[(re.compile(r'def\s+\w+'), 10.0), (re.compile(r'require\s+[\'"]\w+[\'"]'), 8.0), (re.compile(r'^\s*end\s*$'), 7.0)],
-                keywords={'def': 9.0, 'end': 8.0, 'require': 7.0, 'puts': 6.0, 'class': 7.0},
-                exclusive_patterns=[(re.compile(r'# frozen_string_literal: true'), 15.0), (re.compile(r':\w+'), 10.0)],
-                file_extensions=['.rb']
-            ),
-            'swift': LanguageSignature(
-                patterns=[(re.compile(r'import\s+(UIKit|Foundation)'), 10.0), (re.compile(r'func\s+\w+\s*\([^)]*\)\s*\{'), 9.0)],
-                keywords={'import': 8.0, 'func': 9.0, 'let': 8.0, 'var': 8.0, 'class': 7.0, 'print': 6.0},
-                exclusive_patterns=[(re.compile(r'@IBOutlet'), 18.0), (re.compile(r'import\s+SwiftUI'), 20.0)],
-                file_extensions=['.swift']
-            ),
-            'php': LanguageSignature(
-                patterns=[(re.compile(r'function\s+\w+\s*\([^)]*\)'), 7.0), (re.compile(r'\$\w+'), 9.0), (re.compile(r'echo\s+'), 6.0)],
-                keywords={'function': 7.0, 'echo': 6.0, 'class': 6.0, 'public': 6.0},
-                exclusive_patterns=[(re.compile(r'<\?php'), 100.0)], # 绝对权重
-                file_extensions=['.php']
-            ),
-            'typescript': LanguageSignature(
-                patterns=[(re.compile(r'interface\s+\w+'), 10.0), (re.compile(r':\s*(string|number|boolean|any)'), 9.0)],
-                keywords={'interface': 9.0, 'type': 8.0, 'public': 7.0, 'private': 7.0, 'enum': 7.0},
-                exclusive_patterns=[(re.compile(r'public\s+constructor\s*\('), 18.0)],
-                file_extensions=['.ts', '.tsx']
-            ),
-            'r': LanguageSignature(
-                patterns=[(re.compile(r'library\s*\(\w+\)'), 10.0), (re.compile(r'\w+\s*<-\s*'), 9.0)],
-                keywords={'library': 9.0, 'function': 7.0, 'if': 5.0, 'else': 5.0},
-                exclusive_patterns=[(re.compile(r'install\.packages\s*\('), 20.0), (re.compile(r'<-'), 15.0)],
-                file_extensions=['.r']
-            ),
-            'bash': LanguageSignature(
-                patterns=[(re.compile(r'if\s+\[.*\]'), 8.0), (re.compile(r'^\s*fi\s*$'), 7.0), (re.compile(r'echo\s+'), 6.0)],
-                keywords={'if': 7.0, 'then': 7.0, 'fi': 7.0, 'for': 6.0, 'do': 6.0, 'done': 6.0, 'echo': 6.0},
-                exclusive_patterns=[(re.compile(r'#!/bin?/(ba|z|k)?sh'), 100.0)], # 绝对权重
-                file_extensions=['.sh']
-            ),
-            'dockerfile': LanguageSignature(
-                patterns=[(re.compile(r'^(FROM|RUN|CMD|COPY|ADD|WORKDIR|EXPOSE)\s+', re.MULTILINE), 10.0)],
-                keywords={'FROM': 10.0, 'RUN': 9.0, 'CMD': 8.0, 'COPY': 8.0, 'WORKDIR': 7.0, 'EXPOSE': 7.0},
-                exclusive_patterns=[(re.compile(r'^FROM\s+'), 20.0)],
-                file_extensions=['Dockerfile']
-            ),
-            'yaml': LanguageSignature(
-                patterns=[(re.compile(r'^\s*[\w-]+\s*:\s*.*'), 9.0), (re.compile(r'^\s*-\s+'), 8.0)],
-                keywords={'version': 6.0, 'services': 7.0, 'steps': 7.0, 'jobs': 7.0, 'name': 5.0, 'image': 6.0},
-                exclusive_patterns=[],
-                file_extensions=['.yml', '.yaml']
-            ),
-             'xml': LanguageSignature(
-                patterns=[(re.compile(r'<(\w+)\s*.*>.*</\1>'), 9.0), (re.compile(r'<\?xml[^>]*\?>'), 10.0)],
-                keywords={},
-                exclusive_patterns=[(re.compile(r'<\?xml\s+version="1.0"'), 100.0)], # 绝对权重
-                file_extensions=['.xml']
-            ),
-        }
-
+        self.languages = {'python': LanguageSignature(patterns=[(re.compile(r'def\s+\w+\s*\([^)]*\)\s*:'), 9.0), (re.compile(r'class\s+\w+\s*\(?[^)]*\)?\s*:'), 8.5), (re.compile(r'import\s+[\w.]+'), 6.0)], keywords={'def': 8.0, 'class': 7.0, 'import': 6.0, 'elif': 5.0, 'async': 6.0, 'await': 6.0}, exclusive_patterns=[(re.compile(r'if __name__ == "__main__":'), 20.0), (re.compile(r'f"[^"]*"'), 12.0)], file_extensions=['.py', '.pyw']), 'javascript': LanguageSignature(patterns=[(re.compile(r'function\s*.*\s*\{'), 8.0), (re.compile(r'console\.log\s*\('), 7.0), (re.compile(r'(const|let|var)\s+\w+\s*='), 8.0)], keywords={'function': 7.0, 'const': 6.0, 'let': 6.0, 'console': 5.0, 'document': 6.0, 'async': 5.0, 'await': 5.0}, exclusive_patterns=[(re.compile(r'document\.getElementById\s*\('), 15.0)], file_extensions=['.js', '.jsx', '.mjs']), 'java': LanguageSignature(patterns=[(re.compile(r'public\s+class\s+\w+'), 10.0), (re.compile(r'System\.out\.println\s*\('), 9.0), (re.compile(r'import\s+java\.'), 8.0)], keywords={'public': 8.0, 'class': 8.0, 'static': 7.0, 'void': 6.0, 'String': 7.0, 'System': 7.0, 'new': 5.0}, exclusive_patterns=[(re.compile(r'public\s+static\s+void\s+main\s*\(\s*String\s*\[\]\s*args\s*\)'), 25.0)], file_extensions=['.java']), 'cpp': LanguageSignature(patterns=[(re.compile(r'#include\s*<[a-zA-Z_]+>'), 10.0), (re.compile(r'using\s+namespace\s+std;'), 9.0), (re.compile(r'std::cout'), 8.0)], keywords={'#include': 9.0, 'iostream': 8.0, 'std': 7.0, 'cout': 7.0, 'vector': 6.0, 'int': 5.0, 'main': 6.0}, exclusive_patterns=[(re.compile(r'#include\s*<iostream>'), 18.0)], file_extensions=['.cpp', '.cxx', '.h', '.hpp']), 'html': LanguageSignature(patterns=[(re.compile(r'<\s*head\s*>'), 8.0), (re.compile(r'<\s*body\s*>'), 8.0), (re.compile(r'<\s*/\s*\w+\s*>'), 6.0)], keywords={'div': 5.0, 'p': 4.0, 'a': 4.0, 'href': 5.0, 'class': 3.0, 'id': 3.0}, exclusive_patterns=[(re.compile(r'<!DOCTYPE\s+html>', re.IGNORECASE), 100.0)], file_extensions=['.html', '.htm']), 'css': LanguageSignature(patterns=[(re.compile(r'[\w\s.#-]+\s*\{'), 8.0), (re.compile(r'[\w-]+\s*:\s*[^;]+;'), 9.0)], keywords={'color': 6.0, 'background-color': 7.0, 'margin': 5.0, 'padding': 5.0, 'font-size': 6.0, 'display': 6.0}, exclusive_patterns=[(re.compile(r'@media\s*\(.+\)\s*\{'), 15.0)], file_extensions=['.css']), 'sql': LanguageSignature(patterns=[(re.compile(r'(SELECT|CREATE|INSERT|UPDATE|DELETE|FROM|WHERE)', re.IGNORECASE), 10.0)], keywords={'SELECT': 9.0, 'FROM': 8.0, 'WHERE': 7.0, 'JOIN': 7.0, 'GROUP BY': 8.0, 'ORDER BY': 7.0, 'CREATE TABLE': 9.0}, exclusive_patterns=[(re.compile(r'CREATE\s+TABLE', re.IGNORECASE), 18.0)], file_extensions=['.sql']), 'csharp': LanguageSignature(patterns=[(re.compile(r'using\s+System;'), 10.0), (re.compile(r'namespace\s+\w+'), 9.0)], keywords={'namespace': 9.0, 'public': 7.0, 'class': 7.0, 'static': 6.0, 'void': 5.0, 'string': 7.0, 'var': 6.0}, exclusive_patterns=[(re.compile(r'static\s+void\s+Main\s*\(\s*string\s*\[\]\s*args\s*\)'), 25.0), (re.compile(r'Console\.WriteLine\s*\('), 15.0)], file_extensions=['.cs']), 'go': LanguageSignature(patterns=[(re.compile(r'package\s+main'), 10.0), (re.compile(r'import\s*\(\s*'), 8.0), (re.compile(r'func\s+\w+\s*\([^)]*\)\s*\{'), 9.0)], keywords={'package': 9.0, 'import': 8.0, 'func': 9.0, 'fmt': 7.0, 'Println': 6.0}, exclusive_patterns=[(re.compile(r'func\s+main\s*\(\s*\)'), 20.0), (re.compile(r':='), 12.0)], file_extensions=['.go']), 'rust': LanguageSignature(patterns=[(re.compile(r'fn\s+\w+\s*\([^)]*\)\s*\{'), 10.0), (re.compile(r'use\s+std::'), 9.0), (re.compile(r'let\s+(mut\s+)?\w+'), 8.0)], keywords={'fn': 9.0, 'let': 8.0, 'mut': 7.0, 'use': 8.0, 'struct': 7.0}, exclusive_patterns=[(re.compile(r'fn\s+main\s*\(\s*\)'), 20.0), (re.compile(r'println!\s*\('), 18.0)], file_extensions=['.rs']), 'kotlin': LanguageSignature(patterns=[(re.compile(r'fun\s+\w+\s*\([^)]*\)'), 10.0), (re.compile(r'val\s+\w+'), 8.0)], keywords={'package': 8.0, 'import': 7.0, 'fun': 9.0, 'val': 8.0, 'var': 7.0, 'println': 6.0, 'class': 7.0}, exclusive_patterns=[(re.compile(r'fun\s+main\s*\(\s*args:\s*Array<String>\s*\)'), 25.0)], file_extensions=['.kt', '.kts']), 'ruby': LanguageSignature(patterns=[(re.compile(r'def\s+\w+'), 10.0), (re.compile(r'require\s+[\'"]\w+[\'"]'), 8.0), (re.compile(r'^\s*end\s*$'), 7.0)], keywords={'def': 9.0, 'end': 8.0, 'require': 7.0, 'puts': 6.0, 'class': 7.0}, exclusive_patterns=[(re.compile(r'# frozen_string_literal: true'), 15.0), (re.compile(r':\w+'), 10.0)], file_extensions=['.rb']), 'swift': LanguageSignature(patterns=[(re.compile(r'import\s+(UIKit|Foundation)'), 10.0), (re.compile(r'func\s+\w+\s*\([^)]*\)\s*\{'), 9.0)], keywords={'import': 8.0, 'func': 9.0, 'let': 8.0, 'var': 8.0, 'class': 7.0, 'print': 6.0}, exclusive_patterns=[(re.compile(r'@IBOutlet'), 18.0), (re.compile(r'import\s+SwiftUI'), 20.0)], file_extensions=['.swift']), 'php': LanguageSignature(patterns=[(re.compile(r'function\s+\w+\s*\([^)]*\)'), 7.0), (re.compile(r'\$\w+'), 9.0), (re.compile(r'echo\s+'), 6.0)], keywords={'function': 7.0, 'echo': 6.0, 'class': 6.0, 'public': 6.0}, exclusive_patterns=[(re.compile(r'<\?php'), 100.0)], file_extensions=['.php']), 'typescript': LanguageSignature(patterns=[(re.compile(r'interface\s+\w+'), 10.0), (re.compile(r':\s*(string|number|boolean|any)'), 9.0)], keywords={'interface': 9.0, 'type': 8.0, 'public': 7.0, 'private': 7.0, 'enum': 7.0}, exclusive_patterns=[(re.compile(r'public\s+constructor\s*\('), 18.0)], file_extensions=['.ts', '.tsx']), 'r': LanguageSignature(patterns=[(re.compile(r'library\s*\(\w+\)'), 10.0), (re.compile(r'\w+\s*<-\s*'), 9.0)], keywords={'library': 9.0, 'function': 7.0, 'if': 5.0, 'else': 5.0}, exclusive_patterns=[(re.compile(r'install\.packages\s*\('), 20.0), (re.compile(r'<-'), 15.0)], file_extensions=['.r']), 'bash': LanguageSignature(patterns=[(re.compile(r'if\s+\[.*\]'), 8.0), (re.compile(r'^\s*fi\s*$'), 7.0), (re.compile(r'echo\s+'), 6.0)], keywords={'if': 7.0, 'then': 7.0, 'fi': 7.0, 'for': 6.0, 'do': 6.0, 'done': 6.0, 'echo': 6.0}, exclusive_patterns=[(re.compile(r'#!/bin?/(ba|z|k)?sh'), 100.0)], file_extensions=['.sh']), 'dockerfile': LanguageSignature(patterns=[(re.compile(r'^(FROM|RUN|CMD|COPY|ADD|WORKDIR|EXPOSE)\s+', re.MULTILINE), 10.0)], keywords={'FROM': 10.0, 'RUN': 9.0, 'CMD': 8.0, 'COPY': 8.0, 'WORKDIR': 7.0, 'EXPOSE': 7.0}, exclusive_patterns=[(re.compile(r'^FROM\s+'), 20.0)], file_extensions=['Dockerfile']), 'yaml': LanguageSignature(patterns=[(re.compile(r'^\s*[\w-]+\s*:\s*.*'), 9.0), (re.compile(r'^\s*-\s+'), 8.0)], keywords={'version': 6.0, 'services': 7.0, 'steps': 7.0, 'jobs': 7.0, 'name': 5.0, 'image': 6.0}, exclusive_patterns=[], file_extensions=['.yml', '.yaml']), 'xml': LanguageSignature(patterns=[(re.compile(r'<(\w+)\s*.*>.*</\1>'), 9.0), (re.compile(r'<\?xml[^>]*\?>'), 10.0)], keywords={}, exclusive_patterns=[(re.compile(r'<\?xml\s+version="1.0"'), 100.0)], file_extensions=['.xml'])}
     def detect_with_line_info(self, code: str) -> Dict[str, Any]:
         start_time = time.time()
         if not code or not code.strip(): return self._empty_result()
-        code = code.strip()
-        lines = code.split('\n')
-        scores = defaultdict(float)
-        line_evidence = {lang: [] for lang in self.languages}
-        exclusive_matches = defaultdict(float)
-
-        # 1. 独占模式检测
+        code = code.strip(); lines = code.split('\n'); scores = defaultdict(float); line_evidence = {lang: [] for lang in self.languages}; exclusive_matches = defaultdict(float)
         for lang, signature in self.languages.items():
             for pattern, weight in signature.exclusive_patterns:
                 for i, line in enumerate(lines, 1):
-                    if pattern.search(line):
-                        exclusive_matches[lang] += weight
-                        line_evidence[lang].append(f"第{i}行: {line.strip()[:50]}...")
-
-        # 2. 检查是否有绝对权重匹配
+                    if pattern.search(line): exclusive_matches[lang] += weight; line_evidence[lang].append(f"第{i}行: {line.strip()[:50]}...")
         if exclusive_matches:
             best_lang_exclusive = max(exclusive_matches, key=exclusive_matches.get)
-            if exclusive_matches[best_lang_exclusive] >= 100.0:
-                 return self._build_absolute_result(best_lang_exclusive, lines, start_time)
-
-        # 3. 如果没有绝对权重匹配，则继续进行常规检测
+            if exclusive_matches[best_lang_exclusive] >= 100.0: return self._build_absolute_result(best_lang_exclusive, lines, start_time)
         for lang, signature in self.languages.items():
-            score = exclusive_matches.get(lang, 0) # 继承独占分数
-            lang_evidence = []
+            score = exclusive_matches.get(lang, 0); lang_evidence = []
             for pattern, weight in signature.patterns:
                 for i, line in enumerate(lines, 1):
                     if pattern.search(line): score += weight; lang_evidence.append(f"第{i}行 (正则): {line.strip()[:50]}...")
@@ -184,21 +54,10 @@ class PrecisionLanguageDetector:
                 keyword_pattern = re.compile(r'\b' + re.escape(keyword) + r'\b', re.IGNORECASE if lang in ['html', 'sql', 'dockerfile'] else 0)
                 for i, line in enumerate(lines, 1):
                     if keyword_pattern.search(line): score += weight; lang_evidence.append(f"第{i}行 (关键词): '{keyword}'")
-
-            if score > 0:
-                scores[lang] = score
-                line_evidence[lang].extend(list(dict.fromkeys(lang_evidence)))
-
+            if score > 0: scores[lang] = score; line_evidence[lang].extend(list(dict.fromkeys(lang_evidence)))
         if not scores: return self._unknown_result(lines, start_time)
-
-        best_lang = max(scores, key=scores.get)
-        best_score = scores[best_lang]
-        total_score = sum(scores.values())
-        confidence = best_score / total_score if total_score > 0 else 0.0
-        processing_time = (time.time() - start_time) * 1000
-
+        best_lang = max(scores, key=scores.get); best_score = scores[best_lang]; total_score = sum(scores.values()); confidence = best_score / total_score if total_score > 0 else 0.0; processing_time = (time.time() - start_time) * 1000
         return {'language': best_lang, 'confidence': round(min(confidence * 1.2, 0.999), 3), 'score': round(best_score, 2), 'total_lines': len(lines), 'line_evidence': line_evidence[best_lang][:15], 'processing_time_ms': round(processing_time, 2), 'code_preview': self._get_code_preview(lines), 'all_scores': {k: round(v, 2) for k, v in sorted(scores.items(), key=lambda item: item[1], reverse=True) if v > 0}, 'detection_stats': self._get_detection_stats(scores, lines, best_lang)}
-
     def _get_code_preview(self, lines: List[str]) -> Dict[str, Any]:
         if not lines: return {}
         functions, classes, imports, comments = [], [], [], []
@@ -209,22 +68,14 @@ class PrecisionLanguageDetector:
             elif re.match(r'(import|from|#include|using|require|use|library|package)\s+', line_clean): imports.append(f"第{i}行: {line_clean}")
             elif re.match(r'(#|//|--|/\*|<!--)', line_clean): comments.append(f"第{i}行: {line_clean}")
         return {'total_lines': len(lines), 'functions_count': len(functions), 'classes_count': len(classes), 'imports_count': len(imports), 'comments_count': len(comments), 'code_density': round((len(lines) - len(comments)) / len(lines), 3) if lines else 0, 'sample_functions': functions[:3], 'sample_classes': classes[:2], 'sample_imports': imports[:3]}
-
-    # ★★★ FIX: This function now accepts the decided primary_language ★★★
     def _get_detection_stats(self, scores: Dict[str, float], lines: List[str], primary_language: str) -> Dict[str, Any]:
         if not scores: return {}
-        total_score = sum(scores.values())
-        max_score = max(scores.values(), default=0)
-        quality = '确定性' if max_score >= 100 else '极高' if max_score > 50 else '高' if max_score > 25 else '中'
+        total_score = sum(scores.values()); max_score = max(scores.values(), default=0); quality = '确定性' if max_score >= 100 else '极高' if max_score > 50 else '高' if max_score > 25 else '中'
         return {'languages_detected': len(scores), 'primary_language': primary_language, 'score_distribution': {lang: round(score/total_score*100, 1) for lang, score in scores.items() if score > 0}, 'total_score': round(total_score, 2), 'detection_quality': quality}
-
     def _empty_result(self) -> Dict[str, Any]: return {'language': 'unknown', 'confidence': 0.0, 'message': '代码为空', 'total_lines': 0, 'line_evidence': [], 'processing_time_ms': 0.1, 'code_preview': {}, 'detection_stats': {}, 'all_scores': {}}
-
     def _unknown_result(self, lines: List[str], start_time: float) -> Dict[str, Any]: return {'language': 'unknown', 'confidence': 0.0, 'message': '无法识别编程语言', 'total_lines': len(lines), 'line_evidence': [], 'processing_time_ms': round((time.time() - start_time) * 1000, 2), 'code_preview': self._get_code_preview(lines), 'detection_stats': {}, 'all_scores': {}}
-
     def _build_absolute_result(self, lang: str, lines: List[str], start_time: float) -> Dict[str, Any]:
-        all_scores = defaultdict(float)
-        line_evidence = defaultdict(list)
+        all_scores = defaultdict(float); line_evidence = defaultdict(list)
         for current_lang, signature in self.languages.items():
             score = 0
             for pattern, weight in signature.exclusive_patterns + signature.patterns:
@@ -239,16 +90,13 @@ class PrecisionLanguageDetector:
                          score += weight
                          if current_lang == lang: line_evidence[lang].append(f"第{i}行 (关键词): '{keyword}'")
             if score > 0: all_scores[current_lang] = score
-
         best_score = all_scores[lang]
         return {'language': lang, 'confidence': 0.999, 'score': round(best_score, 2), 'total_lines': len(lines), 'line_evidence': list(dict.fromkeys(line_evidence[lang]))[:15], 'processing_time_ms': round((time.time() - start_time) * 1000, 2), 'code_preview': self._get_code_preview(lines), 'detection_method': 'absolute_exclusive_pattern', 'all_scores': {k: round(v, 2) for k, v in sorted(all_scores.items(), key=lambda item: item[1], reverse=True) if v > 0}, 'detection_stats': self._get_detection_stats(all_scores, lines, lang)}
 
 # 全局实例
 precision_detector = PrecisionLanguageDetector()
-
 # CSS样式
 custom_css = ":root{--primary:#6366f1;--primary-dark:#4f46e5;--secondary:#10b981;--accent:#f59e0b;--danger:#ef4444;--bg-primary:#fff;--bg-secondary:#f8fafc;--bg-card:#fff;--border:#e2e8f0;--text-primary:#1e293b;--text-secondary:#64748b;--text-muted:#94a3b8;--shadow:0 1px 3px 0 rgba(0,0,0,.1),0 1px 2px -1px rgba(0,0,0,.1);--shadow-lg:0 10px 15px -3px rgba(0,0,0,.1),0 4px 6px -4px rgba(0,0,0,.1)}.gradio-container{background:linear-gradient(135deg,#f8fafc 0%,#e2e8f0 100%)!important;min-height:100vh;font-family:Inter,-apple-system,BlinkMacSystemFont,sans-serif!important}.pro-card{background:var(--bg-card)!important;border:1px solid var(--border)!important;border-radius:12px!important;box-shadow:var(--shadow)!important;padding:24px!important;margin-bottom:20px!important;transition:all .3s cubic-bezier(.4,0,.2,1)!important}.pro-card:hover{box-shadow:var(--shadow-lg)!important;transform:translateY(-2px)!important}.header-section{text-align:center!important;margin-bottom:40px!important;background:linear-gradient(135deg,var(--primary) 0%,var(--primary-dark) 100%)!important;border-radius:16px!important;padding:40px 32px!important;color:#fff!important}.app-title{font-size:3rem!important;font-weight:800!important;margin-bottom:12px!important;background:linear-gradient(135deg,#fff 0%,#f1f5f9 100%)!important;-webkit-background-clip:text!important;-webkit-text-fill-color:transparent!important;background-clip:text!important}.app-subtitle{font-size:1.25rem!important;font-weight:400!important;opacity:.9!important;margin-bottom:0!important}.stats-grid{display:grid!important;grid-template-columns:repeat(auto-fit,minmax(180px,1fr))!important;gap:16px!important;margin:20px 0!important}.stat-card{background:#fff!important;border-radius:8px!important;padding:16px!important;text-align:center!important;border:1px solid var(--border)!important}.stat-value{font-size:2rem!important;font-weight:700!important;color:var(--primary)!important;margin-bottom:4px!important}.stat-label{font-size:.875rem!important;color:var(--text-secondary)!important;font-weight:500!important}.evidence-panel{background:var(--bg-secondary)!important;border:1px solid var(--border)!important;border-radius:8px!important;padding:16px!important;max-height:300px!important;overflow-y:auto!important;font-family:Monaco,Menlo,Consolas,monospace!important;font-size:.875rem!important}.evidence-item{padding:8px 12px!important;margin:4px 0!important;background:#fff!important;border-radius:6px!important;border-left:4px solid var(--primary)!important}.confidence-high{color:var(--secondary)!important;font-weight:700!important}.confidence-medium{color:var(--accent)!important;font-weight:600!important}.confidence-low{color:var(--danger)!important;font-weight:600!important}.btn-primary{background:linear-gradient(135deg,var(--primary) 0%,var(--primary-dark) 100%)!important;color:#fff!important;border:none!important;border-radius:8px!important;padding:12px 24px!important;font-weight:600!important;transition:all .3s ease!important}.btn-primary:hover{transform:translateY(-1px)!important;box-shadow:0 4px 12px rgba(99,102,241,.3)!important}"
-
 # 显示格式化辅助类
 class DisplayFormatter:
     @staticmethod
@@ -284,49 +132,170 @@ class DisplayFormatter:
         preview = result.get('code_preview', {})
         if not preview: return "<div style='text-align: center; color: #64748b;'>无代码质量数据</div>"
         return f"""<div style="padding: 20px;"><h4 style="margin-bottom: 16px;">代码结构指标 (通用)</h4><div class="stats-grid"><div class="stat-card"><div class="stat-value">{preview.get('functions_count',0)}</div><div class="stat-label">函数/方法</div></div><div class="stat-card"><div class="stat-value">{preview.get('classes_count',0)}</div><div class="stat-label">类/结构体</div></div><div class="stat-card"><div class="stat-value">{preview.get('imports_count',0)}</div><div class="stat-label">导入/包含</div></div><div class="stat-card"><div class="stat-value">{preview.get('code_density',0):.1%}</div><div class="stat-label">代码密度</div></div></div></div>"""
+    # ★★★ 新增：项目分析结果的格式化函数 ★★★
+    @staticmethod
+    def format_project_tree(tree_string):
+        if not tree_string: return "项目为空或无法解析。"
+        return f"```\n{tree_string}\n```"
+    @staticmethod
+    def format_language_distribution_plot(lang_stats):
+        if not lang_stats: return None
+        # 按文件数量排序
+        sorted_stats = sorted(lang_stats.items(), key=lambda item: item[1]['count'], reverse=True)
+        langs = [item[0].upper() for item in sorted_stats]
+        counts = [item[1]['count'] for item in sorted_stats]
+        
+        fig, ax = plt.subplots(figsize=(10, 8))
+        bars = ax.barh(langs, counts, color='#6366f1')
+        ax.invert_yaxis()
+        ax.set_xlabel('文件数量 (File Count)')
+        ax.set_title('项目语言分布 (Project Language Distribution)')
+        ax.bar_label(bars, padding=3)
+        plt.tight_layout()
+        return fig
+
+# ★★★ 新增：项目分析核心逻辑 ★★★
+def analyze_project_zip(zip_file):
+    if zip_file is None:
+        return ("请先上传一个 .zip 文件。", None, {})
+    
+    # 创建一个安全的临时目录
+    temp_dir = tempfile.mkdtemp()
+    
+    try:
+        # 确保上传的是zip文件
+        if not zipfile.is_zipfile(zip_file.name):
+            return ("上传的不是一个有效的 .zip 文件。", None, {})
+            
+        # 解压文件到临时目录
+        with zipfile.ZipFile(zip_file.name, 'r') as zf:
+            zf.extractall(temp_dir)
+            
+        project_tree_str = ""
+        language_stats = defaultdict(lambda: {'count': 0, 'lines': 0})
+        total_files = 0
+        
+        # 遍历解压后的目录和文件
+        for root, _, files in os.walk(temp_dir):
+            # 计算当前目录深度用于缩进
+            level = root.replace(temp_dir, '').count(os.sep)
+            indent = ' ' * 4 * level
+            project_tree_str += f"{indent}📂 {os.path.basename(root)}/\n"
+            
+            sub_indent = ' ' * 4 * (level + 1)
+            for filename in files:
+                total_files += 1
+                file_path = os.path.join(root, filename)
+                try:
+                    # 读取文件内容，忽略无法解码的二进制文件
+                    with open(file_path, 'r', encoding='utf-8') as f:
+                        content = f.read()
+                except Exception:
+                    # 如果是二进制文件等，则标记为 "Binary"
+                    project_tree_str += f"{sub_indent}📄 {filename} [Binary or Unreadable]\n"
+                    continue
 
-# Gradio界面
+                # 调用我们的核心引擎进行分析
+                result = precision_detector.detect_with_line_info(content)
+                lang = result['language']
+                
+                project_tree_str += f"{sub_indent}📄 {filename}  ->  [{lang.upper()}]\n"
+                
+                if lang != 'unknown':
+                    language_stats[lang]['count'] += 1
+                    language_stats[lang]['lines'] += result['total_lines']
+
+        if total_files == 0:
+            return ("这是一个空的 .zip 文件。", None, {})
+            
+        return project_tree_str, language_stats, language_stats # 返回三次以匹配输出
+
+    except Exception as e:
+        return (f"分析过程中出现错误: {e}", None, {})
+    finally:
+        # ★★★ 关键：无论成功失败，都必须清理临时目录 ★★★
+        shutil.rmtree(temp_dir)
+
+# Gradio界面 (已升级为双模式)
 def create_enhanced_interface():
     with gr.Blocks(title="Capricode Pro Master", css=custom_css, theme=gr.themes.Soft(primary_hue="indigo", secondary_hue="emerald")) as demo:
-        gr.HTML("""<div class='header-section'><div class="app-title">🚀 Capricode Pro Master</div><div class="app-subtitle">精准代码视觉感知系统 (终极版)</div></div>""")
-        with gr.Row(equal_height=False):
-            with gr.Column(scale=1):
-                with gr.Column(elem_classes="pro-card"):
-                    gr.Markdown("### 📝 代码输入区域")
-                    code_input = gr.Textbox(label="", placeholder="请在此处粘贴代码... 已支持20种主流语言!", lines=15, show_label=False)
-                    with gr.Row():
-                        detect_btn = gr.Button("🔍 开始分析", variant="primary", elem_classes="btn-primary")
-                        clear_btn = gr.Button("🗑️ 一键清空")
-            with gr.Column(scale=1):
+        gr.HTML("""<div class='header-section'><div class="app-title">🚀 Capricode Pro Master</div><div class="app-subtitle">精准代码视觉感知系统 (双模式：单文件 & 项目分析)</div></div>""")
+        
+        with gr.Tabs():
+            # --- 模式一：单文件分析器 ---
+            with gr.TabItem("单文件分析器 (Single File Analyzer)"):
+                with gr.Row(equal_height=False):
+                    with gr.Column(scale=1):
+                        with gr.Column(elem_classes="pro-card"):
+                            gr.Markdown("### 📝 代码输入区域")
+                            code_input = gr.Textbox(label="", placeholder="请在此处粘贴代码...", lines=15, show_label=False)
+                            with gr.Row():
+                                detect_btn = gr.Button("🔍 分析代码片段", variant="primary", elem_classes="btn-primary")
+                                clear_btn = gr.Button("🗑️ 清空")
+                    with gr.Column(scale=1):
+                        with gr.Column(elem_classes="pro-card"):
+                            gr.Markdown("### 🎯 主要检测结果")
+                            with gr.Row(): detected_language, confidence_score = gr.HTML(label="识别语言"), gr.HTML(label="置信度")
+                            with gr.Row(): processing_time, total_lines = gr.Textbox(label="处理时间", interactive=False), gr.Textbox(label="代码行数", interactive=False)
+                        with gr.Column(elem_classes="pro-card"):
+                            gr.Markdown("### 📊 分析统计"), (stats_display := gr.HTML(value="<div style='text-align: center; color: #64748b;'>等待分析数据...</div>"))
+                with gr.Row():
+                    with gr.Column(scale=1):
+                        with gr.Column(elem_classes="pro-card"): gr.Markdown("### 📍 行数证据详情"), (line_evidence := gr.HTML(value="<div style='text-align: center; color: #64748b; padding: 40px;'>检测证据将在此显示</div>"))
+                    with gr.Column(scale=1):
+                        with gr.Column(elem_classes="pro-card"): gr.Markdown("### 🏗️ 代码结构分析 (通用)"), (code_preview := gr.JSON(label="结构分析", show_label=False))
                 with gr.Column(elem_classes="pro-card"):
-                    gr.Markdown("### 🎯 主要检测结果")
-                    with gr.Row(): detected_language, confidence_score = gr.HTML(label="识别语言"), gr.HTML(label="置信度")
-                    with gr.Row(): processing_time, total_lines = gr.Textbox(label="处理时间", interactive=False), gr.Textbox(label="代码行数", interactive=False)
+                    gr.Markdown("### 📈 可视化分析")
+                    with gr.Tabs():
+                        with gr.TabItem("🔧 语言分布"): language_distribution = gr.HTML(value="<div style='text-align: center; color: #64748b; padding: 40px;'>语言分布可视化将在此显示</div>")
+                        with gr.TabItem("📋 代码质量"): code_quality = gr.HTML(value="<div style='text-align: center; color: #64748b; padding: 40px;'>代码质量分析将在此显示</div>")
+                        with gr.TabItem("🎯 检测详情 (JSON)"): detection_details = gr.JSON(label="详细检测数据", show_label=False)
+
+            # --- 模式二：项目分析器 ---
+            with gr.TabItem("项目分析器 (Project Analyzer)"):
+                with gr.Row():
+                    with gr.Column(scale=1):
+                        with gr.Column(elem_classes="pro-card"):
+                            gr.Markdown("### 📁 上传项目压缩包")
+                            zip_input = gr.File(label="请上传项目的 .zip 文件", file_types=['.zip'], type="file")
+                            project_analyze_btn = gr.Button("🚀 开始扫描整个项目", variant="primary", elem_classes="btn-primary")
+                    with gr.Column(scale=2):
+                        with gr.Column(elem_classes="pro-card"):
+                            gr.Markdown("### 🌳 项目结构 & 语言识别")
+                            project_tree_output = gr.Markdown("项目的文件结构树将在这里显示...", label="Project Structure")
+                
                 with gr.Column(elem_classes="pro-card"):
-                    gr.Markdown("### 📊 分析统计"), (stats_display := gr.HTML(value="<div style='text-align: center; color: #64748b;'>等待分析数据...</div>"))
-        with gr.Row():
-            with gr.Column(scale=1):
-                with gr.Column(elem_classes="pro-card"): gr.Markdown("### 📍 行数证据详情"), (line_evidence := gr.HTML(value="<div style='text-align: center; color: #64748b; padding: 40px;'>检测证据将在此显示</div>"))
-            with gr.Column(scale=1):
-                with gr.Column(elem_classes="pro-card"): gr.Markdown("### 🏗️ 代码结构分析 (通用)"), (code_preview := gr.JSON(label="结构分析", show_label=False))
-        with gr.Column(elem_classes="pro-card"):
-            gr.Markdown("### 📈 可视化分析")
-            with gr.Tabs():
-                with gr.TabItem("🔧 语言分布"): language_distribution = gr.HTML(value="<div style='text-align: center; color: #64748b; padding: 40px;'>语言分布可视化将在此显示</div>")
-                with gr.TabItem("📋 代码质量"): code_quality = gr.HTML(value="<div style='text-align: center; color: #64748b; padding: 40px;'>代码质量分析将在此显示</div>")
-                with gr.TabItem("🎯 检测详情 (JSON)"): detection_details = gr.JSON(label="详细检测数据", show_label=False)
-        test_cases = {'python': 'def main():\n    print("Hello from Python!")\n\nif __name__ == "__main__":\n    main()','java': 'public class HelloWorld {\n    public static void main(String[] args) {\n        System.out.println("Hello, Java!");\n    }\n}','javascript': 'document.addEventListener("DOMContentLoaded", () => {\n    console.log("Hello, JavaScript!");\n});','cpp': '#include <iostream>\n\nint main() {\n    std::cout << "Hello, C++!" << std::endl;\n    return 0;\n}','csharp': 'using System;\n\nnamespace HelloWorldApp {\n    class Program {\n        static void Main(string[] args) {\n            Console.WriteLine("Hello, C#!");\n        }\n    }\n}','go': 'package main\n\nimport "fmt"\n\nfunc main() {\n    fmt.Println("Hello, Go!")\n}','rust': 'fn main() {\n    println!("Hello, Rust!");\n}','php': '<?php\n    echo "Hello, PHP!";\n?>','ruby': 'def say_hello\n  puts "Hello, Ruby!"\nend\n\nsay_hello()','typescript': 'interface User {\n  name: string;\n  id: number;\n}\n\nconst user: User = { name: "TypeScript", id: 0 };\nconsole.log(`Hello, ${user.name}!`);','bash': '#!/bin/bash\n\n# Simple bash script\nMESSAGE="Hello, Bash!"\necho $MESSAGE','dockerfile': 'FROM ubuntu:20.04\n\nRUN apt-get update && apt-get install -y curl\n\nCMD ["echo", "Hello, Docker!"]',}
-        with gr.Column(elem_classes="pro-card"):
-            gr.Markdown("### 🚀 快速测试用例")
-            gr.Examples(examples=[[v] for v in test_cases.values()], inputs=code_input, label="点击示例以快速加载")
+                    gr.Markdown("### 📊 项目语言分布统计")
+                    with gr.Tabs():
+                        with gr.TabItem("📈 按文件数量分布 (Bar Chart)"):
+                             lang_dist_plot = gr.Plot(label="Language Distribution (by file count)")
+                        with gr.TabItem("📋 原始统计数据 (JSON)"):
+                             project_raw_json_output = gr.JSON(label="Raw Analysis Data")
 
-        def precision_analyze(code):
+        # --- 回调函数绑定 ---
+        
+        # 单文件分析器的回调
+        def single_file_precision_analyze(code):
             if not code or not code.strip(): return DisplayFormatter.format_display_result(precision_detector._empty_result())
             return DisplayFormatter.format_display_result(precision_detector.detect_with_line_info(code))
 
-        outputs = [detected_language, confidence_score, processing_time, total_lines, stats_display, line_evidence, code_preview, language_distribution, code_quality, detection_details]
-        detect_btn.click(fn=precision_analyze, inputs=[code_input], outputs=outputs)
-        clear_btn.click(fn=DisplayFormatter.get_empty_display_state, outputs=[code_input] + outputs)
+        single_file_outputs = [detected_language, confidence_score, processing_time, total_lines, stats_display, line_evidence, code_preview, language_distribution, code_quality, detection_details]
+        detect_btn.click(fn=single_file_precision_analyze, inputs=[code_input], outputs=single_file_outputs)
+        clear_btn.click(fn=DisplayFormatter.get_empty_display_state, outputs=[code_input] + single_file_outputs)
+        
+        # 项目分析器的回调
+        def run_project_analysis_and_format(zip_file):
+            tree_str, stats, raw_stats = analyze_project_zip(zip_file)
+            formatted_tree = DisplayFormatter.format_project_tree(tree_str)
+            plot = DisplayFormatter.format_language_distribution_plot(stats)
+            return formatted_tree, plot, raw_stats
+
+        project_analyze_btn.click(
+            fn=run_project_analysis_and_format, 
+            inputs=[zip_input], 
+            outputs=[project_tree_output, lang_dist_plot, project_raw_json_output]
+        )
+
     return demo
 
 # 启动应用