Update app.py

app.py

@@ -65,13 +65,10 @@ class SafeGeocoder:
             self.cache[location] = None
             return None
 
-# NuExtract Functions
 def extract_info(template, text):
     try:
-        # Format prompt according to NuExtract-1.5 requirements
         prompt = f"<|input|>\n### Template:\n{template}\n### Text:\n{text}\n\n<|output|>"
         
-        # Call API
         payload = {
             "inputs": prompt,
             "parameters": {
@@ -82,7 +79,6 @@ def extract_info(template, text):
         
         response = requests.post(API_URL, headers=headers, json=payload)
         
-        # If the model is loading, inform the user
         if response.status_code == 503:
             response_json = response.json()
             if "error" in response_json and "loading" in response_json["error"]:
@@ -92,22 +88,18 @@ def extract_info(template, text):
         if response.status_code != 200:
             return f"❌ API Error: {response.status_code}", response.text
         
-        # Process result
         result = response.json()
         
-        # Handle different response formats
         if isinstance(result, list) and len(result) > 0:
             result_text = result[0].get("generated_text", "")
         else:
             result_text = str(result)
         
-        # Split at output marker if present
         if "<|output|>" in result_text:
             json_text = result_text.split("<|output|>")[1].strip()
         else:
             json_text = result_text
         
-        # Try to parse as JSON
         try:
             extracted = json.loads(json_text)
             formatted = json.dumps(extracted, indent=2)
@@ -119,16 +111,12 @@ def extract_info(template, text):
         return f"❌ Error: {str(e)}", "{}"
 
 def create_map(df, location_col):
-    # Initialize map with satellite imagery which shows greenery
     m = folium.Map(
         location=[20, 0],
         zoom_start=2, 
-        control_scale=True,
-        width='100%',
-        height='100%'
+        control_scale=True
     )
     
-    # Add the satellite tile layer - this will show green areas
     folium.TileLayer(
         tiles=MAP_TILES["GreenMap"]["url"],
         attr=MAP_TILES["GreenMap"]["attr"],
@@ -137,11 +125,9 @@ def create_map(df, location_col):
         control=False
     ).add_to(m)
     
-    # Add plugins
     Fullscreen().add_to(m)
     MeasureControl(position='topright', primary_length_unit='kilometers').add_to(m)
     
-    # Process markers
     geocoder = SafeGeocoder()
     coords = []
     marker_cluster = MarkerCluster(name="Locations").add_to(m)
@@ -153,13 +139,11 @@ def create_map(df, location_col):
             
         location = str(row[location_col]).strip()
         
-        # Get additional info
         additional_info = ""
         for col in df.columns:
             if col != location_col and not pd.isna(row[col]):
                 additional_info += f"<br><b>{col}:</b> {row[col]}"
         
-        # Parse locations
         try:
             locations = [loc.strip() for loc in location.split(',') if loc.strip()]
             if not locations:
@@ -167,7 +151,6 @@ def create_map(df, location_col):
         except:
             locations = [location]
             
-        # Process each location
         for loc in locations:
             point = geocoder.get_coords(loc)
             if point:
@@ -190,11 +173,9 @@ def create_map(df, location_col):
                 coords.append(point)
                 processed_count += 1
     
-    # Set bounds
     if coords:
         m.fit_bounds(coords)
     
-    # Add custom font CSS and ensure proper styling
     custom_css = """
     <style>
     @import url('https://fonts.googleapis.com/css2?family=Source+Sans+Pro:wght@400;600&display=swap');
@@ -219,7 +200,6 @@ def process_excel(file, places_column):
         return None, "No file uploaded", None
     
     try:
-        # Handle file
         if hasattr(file, 'name'):
             df = pd.read_excel(file.name)
         elif isinstance(file, bytes):
@@ -232,15 +212,12 @@ def process_excel(file, places_column):
         if places_column not in df.columns:
             return None, f"Column '{places_column}' not found in the Excel file. Available columns: {', '.join(df.columns)}", None
         
-        # Create map
         map_html, processed_count = create_map(df, places_column)
         
-        # Save processed data
         with tempfile.NamedTemporaryFile(suffix=".xlsx", delete=False) as tmp:
             processed_path = tmp.name
             df.to_excel(processed_path, index=False)
         
-        # Stats
         total_locations = df[places_column].count()
         success_rate = (processed_count / total_locations * 100) if total_locations > 0 else 0
         
@@ -253,9 +230,6 @@ def process_excel(file, places_column):
         print(f"Error processing file: {e}\n{trace}")
         return None, f"Error processing file: {str(e)}", None
 
-# Create separate interfaces for each tab to avoid conflicts
-
-# CSS for improved styling
 custom_css = """
 <style>
 @import url('https://fonts.googleapis.com/css2?family=Source+Sans+Pro:wght@300;400;600;700&display=swap');
@@ -299,135 +273,30 @@ h2 {
     text-align: center;
     transition: all 0.3s ease;
 }
-</style>
-"""
 
-# Text Extraction tab as a separate Blocks interface
-with gr.Blocks(css=custom_css) as extraction_interface:
-    gr.HTML("""
-    <div class="info-box">
-        <h3 style="margin-top: 0;">Extract Structured Data from Text</h3>
-        <p>Use NuExtract-1.5 to automatically extract structured information from historical texts. Define the JSON template for the data you want to extract.</p>
-    </div>
-    """)
-    
-    with gr.Row():
-        with gr.Column():
-            template = gr.Textbox(
-                label="JSON Template", 
-                value='{"earthquake location": "", "dateline location": ""}',
-                lines=5
-            )
-            text = gr.Textbox(
-                label="Text to Extract From",
-                value="Neues Erdbeben in Japan. Aus Tokio wird berichtet, daß in Yokohama bei einem Erdbeben sechs Personen getötet und 22 verwundet, in Tokio vier getötet und 22 verwundet wurden. In Yokohama seien 6VV Häuser zerstört worden. Die telephonische und telegraphische Verbindung zwischen Tokio und Osaka ist unterbrochen worden. Der Trambahnverkehr in Tokio liegt still. Auch der Eisenbahnverkehr zwischen Tokio und Yokohama ist unterbrochen. In Sngamo, einer Vorstadt von Tokio sind Brände ausgebrochen. Ein Eisenbahnzug stürzte in den Vajugawafluß zwischen Gotemba und Tokio. Sechs Züge wurden umgeworfen. Mit dem letzten japanischen Erdbeben sind seit eineinhalb Jahrtausenden bis heute in Japan 229 größere Erdbeben zu verzeichnen gewesen.",
-                lines=8
-            )
-            extract_btn = gr.Button("Extract Information", variant="primary")
-        
-        with gr.Column():
-            status = gr.Textbox(label="Status")
-            output = gr.Textbox(label="Output", lines=10)
-    
-    extract_btn.click(
-        fn=extract_info,
-        inputs=[template, text],
-        outputs=[status, output]
-    )
+/* Fix for map container spacing */
+#map-container {
+    height: 65vh !important;
+    margin-bottom: 0 !important;
+    padding-bottom: 0 !important;
+}
 
-# Mapping tab as a separate Blocks interface
-with gr.Blocks(css=custom_css) as mapping_interface:
-    gr.HTML("""
-    <div class="info-box">
-        <h3 style="margin-top: 0;">Map Your Historical Locations</h3>
-        <p>Upload an Excel file containing location data to create an interactive map visualization. The tool will geocode your locations and display them on a map.</p>
-    </div>
-    """)
-    
-    with gr.Row():
-        with gr.Column():
-            excel_file = gr.File(
-                label="Upload Excel File",
-                file_types=[".xlsx", ".xls"],
-                elem_classes="file-upload-box"
-            )
-            places_column = gr.Textbox(
-                label="Location Column Name",
-                value="dateline_locations",
-                placeholder="e.g., 'dateline_locations', 'earthquake_locations', or 'place_of_distribution'"
-            )
-            process_btn = gr.Button("Generate Map", variant="primary")
-        
-        with gr.Column():
-            map_output = gr.HTML(
-                label="Interactive Map",
-                value="""
-                <div style="text-align:center; height:70vh; width:100%; display:flex; align-items:center; justify-content:center; 
-                          background-color:#f5f5f5; border:1px solid #e0e0e0; border-radius:8px;">
-                    <div>
-                        <img src="https://cdn-icons-png.flaticon.com/512/854/854878.png" width="100">
-                        <p style="margin-top:20px; color:#666;">Your map will appear here after processing</p>
-                    </div>
-                </div>
-                """,
-                elem_id="map_container"
-            )
-            stats_output = gr.Textbox(
-                label="Location Statistics",
-                lines=2
-            )
-            processed_file = gr.File(
-                label="Download Processed Data",
-                visible=True,
-                interactive=False
-            )
-    
-    def process_and_map(file, column):
-        if file is None:
-            return None, "Please upload an Excel file", None
-        
-        try:
-            map_html, stats, processed_path = process_excel(file, column)
-            
-            if map_html and processed_path:
-                # Create responsive container for the map that fills the available space
-                # Remove extra height that was causing empty space below
-                responsive_html = f"""
-                <div style="width:100%; height:60vh; margin:0 0 -150px 0; padding:0; border:1px solid #e0e0e0; border-radius:8px; overflow:hidden; position:relative;">
-                    <style>
-                    /* Fix map sizing issues */
-                    .leaflet-container {{
-                        width: 100% !important;
-                        height: 100% !important;
-                        position: absolute !important;
-                        top: 0;
-                        left: 0;
-                    }}
-                    /* Hide any overflow that might cause extra space */
-                    #map_container {{
-                        overflow: hidden !important;
-                        margin-bottom: 0 !important;
-                    }}
-                    </style>
-                    {map_html}
-                </div>
-                """
-                return responsive_html, stats, processed_path
-            else:
-                return None, stats, None
-        except Exception as e:
-            import traceback
-            trace = traceback.format_exc()
-            print(f"Error in process_and_map: {e}\n{trace}")
-            return None, f"Error: {str(e)}", None
-    
-    process_btn.click(
-        fn=process_and_map,
-        inputs=[excel_file, places_column],
-        outputs=[map_output, stats_output, processed_file]
-    )
+/* Stats box styling */
+.stats-box {
+    margin-top: 10px !important;
+    margin-bottom: 0 !important;
+    padding: 10px;
+    background: #f8f9fa;
+    border-radius: 4px;
+}
+
+/* Remove extra space around components */
+.gr-box {
+    margin-bottom: 0 !important;
+}
+</style>
+"""
 
-# Main app with proper tab separation
 with gr.Blocks(css=custom_css, title="Historical Data Analysis") as demo:
     gr.HTML("""
     <div style="text-align: center; margin-bottom: 1rem">
@@ -438,16 +307,115 @@ with gr.Blocks(css=custom_css, title="Historical Data Analysis") as demo:
     
     with gr.Tabs() as tabs:
         with gr.TabItem("🔍 Text Extraction"):
-            # Instead of duplicating content, use the interface
-            extraction_interface.render()
+            gr.HTML("""
+            <div class="info-box">
+                <h3 style="margin-top: 0;">Extract Structured Data from Text</h3>
+                <p>Use NuExtract-1.5 to automatically extract structured information from historical texts.</p>
+            </div>
+            """)
+            
+            with gr.Row():
+                with gr.Column():
+                    template = gr.Textbox(
+                        label="JSON Template", 
+                        value='{"earthquake location": "", "dateline location": ""}',
+                        lines=5
+                    )
+                    text = gr.Textbox(
+                        label="Text to Extract From",
+                        value="Neues Erdbeben in Japan. Aus Tokio wird berichtet...",
+                        lines=8
+                    )
+                    extract_btn = gr.Button("Extract Information", variant="primary")
+                
+                with gr.Column():
+                    status = gr.Textbox(label="Status")
+                    output = gr.Textbox(label="Output", lines=10)
             
+            extract_btn.click(
+                fn=extract_info,
+                inputs=[template, text],
+                outputs=[status, output]
+            )
+        
         with gr.TabItem("📍 Location Mapping"):
-            # Instead of duplicating content, use the interface
-            mapping_interface.render()
+            gr.HTML("""
+            <div class="info-box">
+                <h3 style="margin-top: 0;">Map Your Historical Locations</h3>
+                <p>Upload an Excel file containing location data to create an interactive map visualization.</p>
+            </div>
+            """)
+            
+            with gr.Row():
+                with gr.Column():
+                    excel_file = gr.File(
+                        label="Upload Excel File",
+                        file_types=[".xlsx", ".xls"],
+                        elem_classes="file-upload-box"
+                    )
+                    places_column = gr.Textbox(
+                        label="Location Column Name",
+                        value="dateline_locations",
+                        placeholder="Enter the column containing locations"
+                    )
+                    process_btn = gr.Button("Generate Map", variant="primary")
+                
+                with gr.Column():
+                    map_output = gr.HTML(
+                        label="Interactive Map",
+                        value="""
+                        <div style="text-align:center; height:65vh; width:100%; display:flex; align-items:center; justify-content:center; 
+                                background-color:#f5f5f5; border:1px solid #e0e0e0; border-radius:8px;">
+                            <div>
+                                <img src="https://cdn-icons-png.flaticon.com/512/854/854878.png" width="100">
+                                <p style="margin-top:20px; color:#666;">Your map will appear here after processing</p>
+                            </div>
+                        </div>
+                        """,
+                        elem_id="map-container"
+                    )
+                    stats_output = gr.Textbox(
+                        label="Location Statistics",
+                        lines=2,
+                        elem_classes="stats-box"
+                    )
+                    processed_file = gr.File(
+                        label="Download Processed Data",
+                        visible=True,
+                        interactive=False
+                    )
+            
+            def process_and_map(file, column):
+                if file is None:
+                    return None, "Please upload an Excel file", None
+                
+                try:
+                    map_html, stats, processed_path = process_excel(file, column)
+                    
+                    if map_html and processed_path:
+                        responsive_html = f"""
+                        <div style="width:100%; height:65vh; margin:0; padding:0; border:1px solid #e0e0e0; border-radius:8px; overflow:hidden;">
+                            {map_html}
+                        </div>
+                        """
+                        return responsive_html, stats, processed_path
+                    else:
+                        return None, stats, None
+                except Exception as e:
+                    import traceback
+                    trace = traceback.format_exc()
+                    print(f"Error in process_and_map: {e}\n{trace}")
+                    return None, f"Error: {str(e)}", None
+            
+            process_btn.click(
+                fn=process_and_map,
+                inputs=[excel_file, places_column],
+                outputs=[map_output, stats_output, processed_file]
+            )
     
     gr.HTML("""
     <div style="text-align: center; margin-top: 2rem; padding-top: 1rem; border-top: 1px solid #eee; font-size: 0.9rem; color: #666;">
-        <p>Made with <span style="color: #e25555;">❤</span> for historical data research</p>
+        <p>Made with <span style="color: #e25555;">❤</span> for historical research</p>
     </div>
     """)