2

app.py

@@ -1,6 +1,5 @@
 """
 图表问答数据集审核系统 - Gradio 5.x 应用
-用于人工审核每个图表对应的问题和答案是否合理正确
 """
 import gradio as gr
 from data_manager import DataManager, data_manager
@@ -12,7 +11,6 @@ import base64
 # ============== 全局状态 ==============
 
 class AppState:
-    """应用状态管理"""
     def __init__(self):
         self.current_source: str = ""
         self.current_chart_type: str = ""
@@ -20,28 +18,21 @@ class AppState:
         self.current_model: str = ""
         self.all_paths: List[Dict] = []
         self.current_index: int = -1
-        
-        # 初始化时获取所有路径
         self.refresh_paths()
     
     def refresh_paths(self):
-        """刷新所有图表路径"""
         self.all_paths = data_manager.get_all_chart_paths()
     
     def get_current_path(self) -> Optional[Dict]:
-        """获取当前路径信息"""
         if 0 <= self.current_index < len(self.all_paths):
             return self.all_paths[self.current_index]
         return None
     
     def set_position(self, source: str, chart_type: str, chart_id: str, model: str):
-        """设置当前位置"""
         self.current_source = source
         self.current_chart_type = chart_type
         self.current_chart_id = chart_id
         self.current_model = model
-        
-        # 更新索引
         for i, path in enumerate(self.all_paths):
             if (path['source'] == source and 
                 path['chart_type'] == chart_type and 
@@ -51,7 +42,6 @@ class AppState:
                 break
     
     def navigate(self, direction: int) -> bool:
-        """导航到上一个或下一个图表"""
         new_index = self.current_index + direction
         if 0 <= new_index < len(self.all_paths):
             self.current_index = new_index
@@ -65,90 +55,35 @@ class AppState:
 
 state = AppState()
 
-
 # ============== UI 更新函数 ==============
 
-def get_dataset_choices() -> Tuple[List[str], List[str], List[str], List[str]]:
-    """获取数据集的选择项"""
-    structure = data_manager.get_dataset_structure()
-    sources = list(structure.get('sources', {}).keys())
-    chart_types = []
-    charts = []
-    models = []
-    
-    if state.current_source:
-        source_data = structure['sources'].get(state.current_source, {})
-        chart_types = list(source_data.get('chart_types', {}).keys())
-        
-        if state.current_chart_type:
-            charts = data_manager.get_chart_list(state.current_source, state.current_chart_type)
-            ct_data = source_data.get('chart_types', {}).get(state.current_chart_type, {})
-            models = ct_data.get('models', [])
-            
-    return sources, chart_types, charts, models
-
 def update_chart_type_dropdown(source: str):
-    """更新图表类型下拉框"""
     state.current_source = source
     structure = data_manager.get_dataset_structure()
     chart_types = list(structure.get('sources', {}).get(source, {}).get('chart_types', {}).keys())
     return gr.Dropdown(choices=chart_types, value=chart_types[0] if chart_types else None)
 
 def update_chart_dropdown(source: str, chart_type: str):
-    """更新图表和模型下拉框"""
     state.current_source = source
     state.current_chart_type = chart_type
     charts = data_manager.get_chart_list(source, chart_type)
     structure = data_manager.get_dataset_structure()
     ct_data = structure.get('sources', {}).get(source, {}).get('chart_types', {}).get(chart_type, {})
     models = ct_data.get('models', [])
-    
     return (
         gr.Dropdown(choices=charts, value=charts[0] if charts else None),
         gr.Dropdown(choices=models, value=models[0] if models else None)
     )
 
 def create_embedded_html(html_content: str, chart_id: str = "") -> str:
-    """创建嵌入式的 HTML 显示"""
     if not html_content:
-        return f"""
-        <div style="display:flex;flex-direction:column;align-items:center;justify-content:center;
-                    min-height:750px;color:#999;border:2px dashed #ddd;border-radius:12px;background:#fafafa;">
-            <div style="font-size:48px;margin-bottom:16px;">📭</div>
-            <div style="font-size:18px;font-weight:500;">暂无图表内容</div>
-            <div style="font-size:14px;margin-top:8px;">图表 ID: {chart_id or '未知'}</div>
-            <div style="font-size:12px;margin-top:16px;color:#888;">请检查数据集目录中是否存在该图表的 HTML 文件</div>
-        </div>
-        """
-    
-    # 使用 base64 编码 HTML 内容，避免引号转义问题
-    html_bytes = html_content.encode('utf-8')
-    html_base64 = base64.b64encode(html_bytes).decode('utf-8')
-    
-    # 增加高度为 750px
-    iframe_html = f"""
-    <iframe 
-        src="data:text/html;base64,{html_base64}"
-        style="width:100%;height:750px;border:1px solid #e0e0e0;border-radius:8px;background:#fff;"
-        sandbox="allow-scripts allow-same-origin"
-        loading="lazy"
-    ></iframe>
-    """
-    return iframe_html
+        return f'<div style="display:flex;min-height:750px;align-items:center;justify-content:center;background:#fafafa;border:2px dashed #ddd;">暂无图表内容 (ID: {chart_id})</div>'
+    html_base64 = base64.b64encode(html_content.encode('utf-8')).decode('utf-8')
+    return f'<iframe src="data:text/html;base64,{html_base64}" style="width:100%;height:750px;border:1px solid #e0e0e0;background:#fff;" sandbox="allow-scripts allow-same-origin"></iframe>'
 
 def load_chart_data(source: str, chart_type: str, chart_id: str, model: str):
-    """加载图表数据并返回所有 UI 更新"""
     if not all([source, chart_type, chart_id, model]):
-        return [
-            create_embedded_html(""),  # html_display
-            "### ⚠️ 请在上方选择完整数据路径",  # label_info
-            "[]",  # qa_data
-            "等待加载数据...",  # status_text
-            "请在上方选择图表",  # progress_text
-            "{}",  # current_qa_reviews
-            gr.Radio(choices=[], value=None),  # qa_selector
-            ""  # debug_info
-        ]
+        return [create_embedded_html(""), "### 请选择路径", "[]", "等待加载...", "请选择图表", "{}", gr.Radio(choices=[]), ""]
     
     state.set_position(source, chart_type, chart_id, model)
     chart_data = data_manager.get_chart_data(source, chart_type, chart_id)
@@ -156,268 +91,126 @@ def load_chart_data(source: str, chart_type: str, chart_id: str, model: str):
     label_info = chart_data.get('label_info', {})
     
     embedded_html = create_embedded_html(html_content, chart_id)
-    debug_info = f"📁 {source}/{chart_type}/{chart_id} | HTML: {len(html_content)} 字符"
-    
-    if label_info:
-        label_text = f"""
-| 属性 | 值 |
-|------|-----|
-| **编号** | {label_info.get('Number', '-')} |
-| **类型** | {label_info.get('Type', '-')} |
-| **来源** | {label_info.get('Source', '-')} |
-| **主题** | {label_info.get('Topic', '-')} |
-| **描述** | {label_info.get('Describe', '-')} |
-| **链接** | [查看原图]({label_info.get('Weblink', '#')}) |
-"""
-    else:
-        label_text = "⚠️ 暂无标签信息"
+    label_text = f"| 属性 | 值 |\n|---|---|\n" + "\n".join([f"| **{k}** | {v} |" for k, v in label_info.items()])
     
     qa_list = data_manager.get_qa_list(source, chart_type, model, chart_id)
-    
-    existing_reviews = {}
-    for review in data_manager.get_reviews_by_chart(chart_id, model):
-        existing_reviews[review['qa_id']] = review
-        
-    progress_text = f"进度: 当前第 {state.current_index + 1} 个 / 共 {len(state.all_paths)} 个"
+    existing_reviews = {r['qa_id']: r for r in data_manager.get_reviews_by_chart(chart_id, model)}
     
     stats = data_manager.get_review_stats()
-    status_text = f"总览: 已审核 {stats['total']} 笔 | ✅正确: {stats['correct']} | ❌错误: {stats['incorrect']} | ✏️需修改: {stats['needs_modification']}"
-    
-    qa_choices = [f"Q{i+1}: {qa.question[:50]}..." for i, qa in enumerate(qa_list)] if qa_list else []
+    status_msg = f"已审核: {stats['total']} | ✅正确: {stats['correct']} | ❌错误: {stats['incorrect']}"
+    progress_msg = f"进度: {state.current_index + 1} / {len(state.all_paths)}"
+    qa_choices = [f"Q{i+1}: {qa.question[:40]}..." for i, qa in enumerate(qa_list)]
     
     return [
-        embedded_html,
-        label_text,
+        embedded_html, label_text, 
         json.dumps([{"id": qa.id, "question": qa.question, "answer": qa.answer} for qa in qa_list]),
-        status_text,
-        progress_text,
-        json.dumps(existing_reviews),
+        status_msg, progress_msg, json.dumps(existing_reviews),
         gr.Radio(choices=qa_choices, value=qa_choices[0] if qa_choices else None),
-        debug_info
+        f"Path: {source}/{chart_type}/{chart_id}"
     ]
 
-def navigate_prev():
-    """导航到上一个图表"""
-    if state.navigate(-1):
-        path = state.get_current_path()
-        if path:
-            return (
-                gr.Dropdown(value=path['source']),
-                gr.Dropdown(value=path['chart_type']),
-                gr.Dropdown(value=path['chart_id']),
-                gr.Dropdown(value=path['model'])
-            )
-    return [gr.Dropdown(), gr.Dropdown(), gr.Dropdown(), gr.Dropdown()]
-
-def navigate_next():
-    """导航到下一个图表"""
-    if state.navigate(1):
-        path = state.get_current_path()
-        if path:
-            return (
-                gr.Dropdown(value=path['source']),
-                gr.Dropdown(value=path['chart_type']),
-                gr.Dropdown(value=path['chart_id']),
-                gr.Dropdown(value=path['model'])
-            )
-    return [gr.Dropdown(), gr.Dropdown(), gr.Dropdown(), gr.Dropdown()]
-
-def save_review_handler(
-    qa_id: str, chart_id: str, source: str, chart_type: str, model: str,
-    original_question: str, original_answer: str, status: str,
-    modified_question: str, modified_answer: str, issue_type: str,
-    comment: str, reviewer: str
-) -> str:
-    """保存审核记录"""
-    if not qa_id:
-        return "❌ 请先选择一个问答对"
-        
-    review_data = {
-        "qa_id": qa_id, "chart_id": chart_id, "source": source,
-        "chart_type": chart_type, "model": model,
-        "original_question": original_question, "original_answer": original_answer,
-        "status": status, "modified_question": modified_question,
-        "modified_answer": modified_answer, "issue_type": issue_type,
-        "comment": comment, "reviewer": reviewer
-    }
-    
-    data_manager.save_review(review_data)
-    stats = data_manager.get_review_stats()
-    return f"✅ 已保存! 已审核: {stats['total']} | ✅正确: {stats['correct']} | ❌错误: {stats['incorrect']} | ✏️需修改: {stats['needs_modification']}"
-
 def export_reviews_handler():
-    """导出审核记录并返回文件供下载"""
-    # 将文件保存到当前目录
     output_path = data_manager.export_reviews("./reviews_export.json")
-    # 更新 gr.File 组件使其显示并提供下载
     return gr.update(value=output_path, visible=True)
 
-
 # ============== 创建 Gradio 界面 ==============
 
 def create_ui():
-    # 调整了最小高度为 750px 适配放大后的 iframe
-    custom_css = """
-    .chart-container {
-        min-height: 750px; 
-    }
-    .control-panel {
-        background: #f8f9fa;
-        padding: 15px;
-        border-radius: 8px;
-        margin-bottom: 10px;
-    }
-    .debug-panel {
-        font-size: 12px;
-        color: #666;
-        padding: 8px;
-        background: #f5f5f5;
-        border-radius: 4px;
-        margin-top: 10px;
-    }
-    """
+    custom_css = ".chart-container { min-height: 750px; } .nav-row { background: #f8f9fa; padding: 10px; border-radius: 8px; }"
     
     with gr.Blocks(title="图表问答数据集审核系统", theme=gr.themes.Soft(), css=custom_css) as app:
-        
+        # 内部状态
         qa_data_json = gr.State(value="[]")
         current_reviews_json = gr.State(value="{}")
         
-        # ==================== 顶部标题与数据导航区 ====================
         gr.Markdown("# 📊 图表问答数据集审核系统")
         
+        # 顶部导航
         with gr.Row():
-            status_text = gr.Textbox(value="等待加载数据...", interactive=False, show_label=False, scale=2)
-            progress_text = gr.Textbox(value="请在下方选择图表", interactive=False, show_label=False, scale=1)
+            status_text = gr.Textbox(label="统计", interactive=False, scale=2)
+            progress_text = gr.Textbox(label="进度", interactive=False, scale=1)
             
-        with gr.Row(elem_classes=["control-panel"]):
-            source_dropdown = gr.Dropdown(label="数据来源 (Source)", choices=[], interactive=True, scale=1)
-            chart_type_dropdown = gr.Dropdown(label="图表类型 (Chart Type)", choices=[], interactive=True, scale=1)
-            chart_dropdown = gr.Dropdown(label="图表 ID", choices=[], interactive=True, scale=1)
-            model_dropdown = gr.Dropdown(label="模型 (Model)", choices=[], interactive=True, scale=1)
-            reviewer_input = gr.Textbox(label="审核人", value="default", interactive=True, scale=1)
+        with gr.Row(elem_classes=["nav-row"]):
+            source_drop = gr.Dropdown(label="数据来源", choices=[], allow_custom_value=True)
+            type_drop = gr.Dropdown(label="图表类型", choices=[], allow_custom_value=True)
+            id_drop = gr.Dropdown(label="图表 ID", choices=[], allow_custom_value=True)
+            model_drop = gr.Dropdown(label="模型", choices=[], allow_custom_value=True)
+            reviewer = gr.Textbox(label="审核人", value="admin")
             
         with gr.Row():
-            prev_btn = gr.Button("⬅️ 上一个图表", variant="secondary")
-            next_btn = gr.Button("➡️ 下一个图表", variant="primary")
-            export_btn = gr.Button("📦 生成并导出审核记录")
-            
-        # 下载文件的容器，默认隐藏，生成后显示
-        download_file = gr.File(label="点击下方链接下载", visible=False)
+            prev_btn = gr.Button("⬅️ 上一个")
+            next_btn = gr.Button("➡️ 下一个")
+            export_btn = gr.Button("📦 导出记录", variant="secondary")
+            download_file = gr.File(label="下载导出的 JSON", visible=False)
 
-        # ==================== 主内容区 (左右并排) ====================
+        # 主体：左右排版
         with gr.Row():
-            # ===== 左侧：图表展示 (宽度占比 60%) =====
-            with gr.Column(scale=6, min_width=500):
-                gr.Markdown("### 📈 图表展示")
-                html_display = gr.HTML(
-                    value="<div style='text-align:center;padding:50px;color:#999;'>请在上方选择完整路径以加载图表</div>",
-                    elem_classes=["chart-container"]
-                )
-                debug_info = gr.Textbox(label="调试信息", value="", interactive=False, show_label=False, elem_classes=["debug-panel"])
-
-            # ===== 右侧：标签信息和 QA 审核 (宽度占比 40%) =====
-            with gr.Column(scale=4, min_width=400):
-                # 将元数据折叠，给下方的问答留出更多空间
-                with gr.Accordion("📝 图表标签信息 (Metadata)", open=False):
-                    label_display = gr.Markdown(value="暂无信息")
-                
-                gr.Markdown("### ❓ 问答审核")
+            with gr.Column(scale=6): # 左侧图表
+                html_display = gr.HTML(elem_classes=["chart-container"])
+                debug_info = gr.Markdown()
                 
-                current_qa_id = gr.Textbox(visible=False, value="")
+            with gr.Column(scale=4): # 右侧审核
+                with gr.Accordion("📝 元数据", open=False):
+                    label_display = gr.Markdown()
                 
-                qa_selector = gr.Radio(label="1. 选择要审核的问答对", choices=[], interactive=True)
-                
-                qa_question_display = gr.Textbox(label="原始问题", interactive=False, lines=2, value="")
-                qa_answer_display = gr.Textbox(label="原始答案", interactive=False, lines=2, value="")
+                qa_selector = gr.Radio(label="选择问答对")
+                current_qa_id = gr.Textbox(visible=False)
+                orig_q = gr.Textbox(label="原始问题", interactive=False, lines=2)
+                orig_a = gr.Textbox(label="原始答案", interactive=False)
                 
                 gr.Markdown("---")
-                gr.Markdown("#### 2. 录入审核结果")
-                
-                status_radio = gr.Radio(
-                    label="判定结果",
-                    choices=[("✅ 正确", "correct"), ("❌ 错误", "incorrect"), ("✏️ 需修改", "needs_modification"), ("⏳ 待定", "pending")],
-                    value="pending", interactive=True
-                )
-                
-                issue_type_dropdown = gr.Dropdown(
-                    label="问题错误类型 (若有)",
-                    choices=["问题歧义", "答案错误", "图表不清晰", "问题不合理", "答案格式错误", "其他"],
-                    interactive=True, value=""
-                )
-                
-                modified_question = gr.Textbox(label="修改后的问题", placeholder="如需修改问题，请在此输入...", lines=2, interactive=True, value="")
-                modified_answer = gr.Textbox(label="修改后的答案", placeholder="如需修改答案，请在此输入...", lines=2, interactive=True, value="")
-                comment_textbox = gr.Textbox(label="评论/备注", placeholder="请输入审核意见或备注...", lines=2, interactive=True, value="")
-                
-                save_btn = gr.Button("💾 保存当前 QA 审核结果", variant="primary", size="lg")
-                save_result = gr.Textbox(label="", visible=False)
-                
-        # ==================== 事件绑定 ====================
-        
+                status_radio = gr.Radio(label="判定结果", choices=[("✅ 正确", "correct"), ("❌ 错误", "incorrect"), ("✏️ 需修改", "needs_modification")], value="correct")
+                issue_type = gr.Dropdown(label="错误类型", choices=["答案错误", "问题模糊", "图文不符", "其他"])
+                mod_q = gr.Textbox(label="修改问题", lines=2)
+                mod_a = gr.Textbox(label="修改答案")
+                comment = gr.Textbox(label="备注")
+                save_btn = gr.Button("💾 保存当前审核", variant="primary")
+                save_msg = gr.Textbox(label="系统提示", visible=False)
+
+        # --- 事件绑定 ---
         def init_dataset():
-            structure = data_manager.get_dataset_structure()
-            sources = list(structure.get('sources', {}).keys())
-            return gr.Dropdown(choices=sources, value=sources[0] if sources else None)
+            s = list(data_manager.get_dataset_structure().get('sources', {}).keys())
+            return gr.update(choices=s, value=s[0] if s else None)
             
-        app.load(fn=init_dataset, outputs=[source_dropdown])
-        
-        source_dropdown.change(fn=update_chart_type_dropdown, inputs=[source_dropdown], outputs=[chart_type_dropdown])
-        chart_type_dropdown.change(fn=update_chart_dropdown, inputs=[source_dropdown, chart_type_dropdown], outputs=[chart_dropdown, model_dropdown])
-        
-        # 联动加载数据
-        load_inputs = [source_dropdown, chart_type_dropdown, chart_dropdown, model_dropdown]
-        load_outputs = [html_display, label_display, qa_data_json, status_text, progress_text, current_reviews_json, qa_selector, debug_info]
-        model_dropdown.change(fn=load_chart_data, inputs=load_inputs, outputs=load_outputs)
-        chart_dropdown.change(fn=load_chart_data, inputs=load_inputs, outputs=load_outputs)
-        
-        # QA 选择器
-        def on_qa_selected(qa_index_str, qa_json, reviews_json):
-            if not qa_index_str or not qa_json:
-                return ["", "", "", gr.Radio(value="pending"), "", "", "", ""]
-            try:
-                qa_list = json.loads(qa_json)
-                reviews = json.loads(reviews_json)
-                index = int(qa_index_str.split(":")[0].replace("Q", "")) - 1
-                qa = qa_list[index]
-                review = reviews.get(qa['id'], {})
-                return [
-                    qa['id'], qa['question'], qa['answer'],
-                    gr.Radio(value=review.get('status', 'pending')),
-                    review.get('issue_type', ''),
-                    review.get('modified_question', ''),
-                    review.get('modified_answer', ''),
-                    review.get('comment', '')
-                ]
-            except Exception as e:
-                print(f"Error in on_qa_selected: {e}")
-                return ["", "", "", gr.Radio(value="pending"), "", "", "", ""]
-                
-        qa_selector.change(
-            fn=on_qa_selected,
-            inputs=[qa_selector, qa_data_json, current_reviews_json],
-            outputs=[current_qa_id, qa_question_display, qa_answer_display, status_radio, issue_type_dropdown, modified_question, modified_answer, comment_textbox]
-        )
+        app.load(fn=init_dataset, outputs=[source_drop])
+        source_drop.change(fn=update_chart_type_dropdown, inputs=[source_drop], outputs=[type_drop])
+        type_drop.change(fn=update_chart_dropdown, inputs=[source_drop, type_drop], outputs=[id_drop, model_drop])
         
-        prev_btn.click(fn=navigate_prev, outputs=[source_dropdown, chart_type_dropdown, chart_dropdown, model_dropdown])
-        next_btn.click(fn=navigate_next, outputs=[source_dropdown, chart_type_dropdown, chart_dropdown, model_dropdown])
+        load_args = dict(fn=load_chart_data, inputs=[source_drop, type_drop, id_drop, model_drop], outputs=[html_display, label_display, qa_data_json, status_text, progress_text, current_reviews_json, qa_selector, debug_info])
+        id_drop.change(**load_args)
+        model_drop.change(**load_args)
+
+        def on_qa_select(sel, qa_json, rev_json):
+            if not sel: return [""] * 8
+            qa_list = json.loads(qa_json)
+            revs = json.loads(rev_json)
+            idx = int(sel.split(":")[0][1:]) - 1
+            qa = qa_list[idx]
+            r = revs.get(qa['id'], {})
+            return [qa['id'], qa['question'], qa['answer'], r.get('status', 'correct'), r.get('issue_type', ''), r.get('modified_question', ''), r.get('modified_answer', ''), r.get('comment', '')]
+
+        qa_selector.change(fn=on_qa_select, inputs=[qa_selector, qa_data_json, current_reviews_json], outputs=[current_qa_id, orig_q, orig_a, status_radio, issue_type, mod_q, mod_a, comment])
         
+        # 导航
+        nav_out = [source_drop, type_drop, id_drop, model_drop]
+        prev_btn.click(fn=lambda: (state.navigate(-1), *[gr.update(value=v) for v in [state.current_source, state.current_chart_type, state.current_chart_id, state.current_model]])[1:], outputs=nav_out)
+        next_btn.click(fn=lambda: (state.navigate(1), *[gr.update(value=v) for v in [state.current_source, state.current_chart_type, state.current_chart_id, state.current_model]])[1:], outputs=nav_out)
+
         save_btn.click(
-            fn=save_review_handler,
-            inputs=[current_qa_id, chart_dropdown, source_dropdown, chart_type_dropdown, model_dropdown, qa_question_display, qa_answer_display, status_radio, modified_question, modified_answer, issue_type_dropdown, comment_textbox, reviewer_input],
-            outputs=[save_result]
-        ).then(fn=lambda: gr.Textbox(visible=True), outputs=[save_result])
-        
-        # 导出并显示下载文件组件
-        export_btn.click(
-            fn=export_reviews_handler,
-            outputs=[download_file]
-        )
+            fn=lambda *args: (data_manager.save_review({
+                "qa_id": args[0], "chart_id": args[1], "source": args[2], "chart_type": args[3], "model": args[4],
+                "original_question": args[5], "original_answer": args[6], "status": args[7],
+                "modified_question": args[8], "modified_answer": args[9], "issue_type": args[10],
+                "comment": args[11], "reviewer": args[12]
+            }), "✅ 已保存记录")[1],
+            inputs=[current_qa_id, id_drop, source_drop, type_drop, model_drop, orig_q, orig_a, status_radio, mod_q, mod_a, issue_type, comment, reviewer],
+            outputs=[save_msg]
+        ).then(fn=lambda: gr.update(visible=True), outputs=[save_msg])
+
+        export_btn.click(fn=export_reviews_handler, outputs=[download_file])
+
+        return app # <--- 关键点：确保在这里 return
 
-# ============== 主入口 ==============
 if __name__ == "__main__":
     app = create_ui()
-    app.launch(
-        server_name="0.0.0.0",
-        server_port=7860,
-        share=True
-    )
+    app.launch(server_name="0.0.0.0", server_port=7860)