data_viewer

app.py

@@ -0,0 +1,205 @@
+import gradio as gr
+import json
+import pandas as pd
+from typing import Dict, List
+import numpy as np
+
+def flatten_dict(d: Dict, parent_key: str = '', sep: str = '.') -> Dict:
+    items = []
+    for k, v in d.items():
+        new_key = f"{parent_key}{sep}{k}" if parent_key else k
+        if isinstance(v, dict):
+            items.extend(flatten_dict(v, new_key, sep=sep).items())
+        else:
+            items.append((new_key, v))
+    return dict(items)
+
+def create_preview(text: str, max_length: int = 50) -> str:
+    if not isinstance(text, str):
+        text = str(text)
+    if len(text) <= max_length:
+        return text
+    return text[:max_length] + "..."
+
+class JsonViewer:
+    def __init__(self):
+        self.data = None
+        self.df = None
+    
+    def load_json(self, file):
+        if file is None:
+            return None, None
+        
+        try:
+            # Read JSON file
+            if isinstance(file, str):
+                with open(file, 'r', encoding='utf-8') as f:
+                    self.data = json.load(f)
+            else:
+                content = file.decode('utf-8')
+                self.data = json.loads(content)
+            
+            # Convert to DataFrame
+            if isinstance(self.data, dict):
+                self.df = pd.DataFrame([self.data])
+            elif isinstance(self.data, list):
+                self.df = pd.DataFrame(self.data)
+            else:
+                raise ValueError("JSON must contain either a dictionary or a list of dictionaries")
+            
+            # Create preview for all columns
+            preview_df = self.df.copy()
+            for col in preview_df.columns:
+                preview_df[col] = preview_df[col].apply(create_preview)
+            
+            return preview_df, self.df.index.tolist()
+        except Exception as e:
+            return f"Error loading JSON: {str(e)}", None
+
+    def get_full_row(self, index):
+        if self.df is None or index is None:
+            return "Please load a JSON file first"
+        
+        try:
+            row = self.df.iloc[int(index)]
+            formatted_data = json.dumps(row.to_dict(), indent=2)
+            return formatted_data
+        except Exception as e:
+            return f"Error displaying row: {str(e)}"
+
+def create_interface():
+    viewer = JsonViewer()
+    
+    with gr.Blocks(css="""
+        #full_content { 
+            font-family: monospace;
+        }
+        .content-container {
+            display: flex;
+            flex-wrap: wrap;
+            gap: 20px;
+            padding: 15px;
+            background: #f5f5f5;
+            border-radius: 5px;
+        }
+        .content-section {
+            flex: 1;
+            min-width: 300px;
+            background: white;
+            padding: 15px;
+            border-radius: 5px;
+            box-shadow: 0 1px 3px rgba(0,0,0,0.1);
+        }
+        .section-title {
+            font-weight: bold;
+            color: #444;
+            margin-bottom: 10px;
+            padding-bottom: 5px;
+            border-bottom: 2px solid #eee;
+        }
+        .section-content {
+            white-space: pre-wrap;
+            line-height: 1.5;
+        }
+        .content-key {
+            font-weight: bold;
+            color: #444;
+            padding-right: 10px;
+        }
+        .content-value {
+            display: block;
+            padding-left: 0;
+            margin-top: 5px;
+        }
+    """) as interface:
+        gr.Markdown("# JSON Data Viewer")
+        
+        with gr.Row():
+            file_input = gr.File(label="Upload JSON file")
+        
+        with gr.Row():
+            preview_table = gr.Dataframe(
+                value=pd.DataFrame(),
+                label="Data Preview",
+                interactive=True,
+                wrap=True,
+                row_count=(5, "dynamic")
+            )
+        
+        with gr.Row():
+            full_content = gr.HTML(
+                label="Full Content",
+                elem_id="full_content"
+            )
+        
+        def update_table(file):
+            preview, _ = viewer.load_json(file)
+            if isinstance(preview, pd.DataFrame):
+                return preview
+            return pd.DataFrame()
+        
+        def show_full_content(evt: gr.SelectData):
+            if viewer.df is None:
+                return "Please load a JSON file first"
+            try:
+                row = viewer.df.iloc[evt.index[0]]
+                row_dict = row.to_dict()
+                
+                sections = {
+                    'Video Info': ['vid', 'video_url', 'title', 'category', 'extended_description'],
+                    'Content': ['description'],
+                    'Additional Info': ['vqa']
+                }
+                
+                formatted_sections = []
+                for section_title, keys in sections.items():
+                    section_content = []
+                    for key in keys:
+                        if key in row_dict:
+                            value = row_dict[key]
+                            if isinstance(value, str):
+                                value = value.replace('\\n', '<br>')
+                                value = value.replace('\\"', '"')
+                                value = value.replace('<br>', '<br>&nbsp;&nbsp;&nbsp;&nbsp;')
+                            section_content.append(
+                                f'<span class="content-key">{key}:</span>'
+                                f'<span class="content-value">{value}</span>'
+                            )
+                    
+                    if section_content:
+                        formatted_section = f"""
+                        <div class="content-section">
+                            <div class="section-title">{section_title}</div>
+                            <div class="section-content">
+                                {'<br>'.join(section_content)}
+                            </div>
+                        </div>
+                        """
+                        formatted_sections.append(formatted_section)
+                
+                formatted_data = f"""
+                <div class="content-container">
+                    {''.join(formatted_sections)}
+                </div>
+                """
+                return formatted_data
+            except Exception as e:
+                return f"Error displaying row: {str(e)}"
+        
+        file_input.change(
+            fn=update_table,
+            inputs=[file_input],
+            outputs=[preview_table]
+        )
+        
+        preview_table.select(
+            fn=show_full_content,
+            inputs=None,
+            outputs=[full_content]
+        )
+    
+    return interface
+
+if __name__ == "__main__":
+    demo = create_interface()
+    demo.launch(share=True)