Update app.py

app.py

@@ -1,156 +1,106 @@
 import gradio as gr
 import pandas as pd
-import os
-import tempfile
-import chardet
+from io import BytesIO
 
-def detect_encoding(file_path):
-    """
-    Function to detect file encoding
-    """
-    with open(file_path, 'rb') as f:
-        result = chardet.detect(f.read())
-    return result['encoding']
+def convert_file(input_file, conversion_type):
+    # Check if a file was uploaded
+    if input_file is None:
+        raise ValueError("Please upload a file.")
 
-def merge_csv_files(files):
-    """
-    Function to merge multiple CSV files into one
-    
-    Args:
-        files: List of uploaded CSV files
-    
-    Returns:
-        Path to the merged CSV file and status message
-    """
-    if not files or len(files) == 0:
-        return None, "No files were uploaded. Please select CSV files to merge."
-    
-    if len(files) > 30:
-        return None, "Maximum 30 files can be merged at once."
-    
+    # Determine if input_file is a file-like object or a file path string.
     try:
-        # Read all files into DataFrame list
-        dataframes = []
-        for file in files:
-            # Detect file encoding
-            encoding = detect_encoding(file.name)
-            try:
-                df = pd.read_csv(file.name, encoding=encoding)
-            except UnicodeDecodeError:
-                # Try other encodings if detected encoding fails
-                encodings_to_try = ['cp949', 'euc-kr', 'latin1', 'ISO-8859-1']
-                for enc in encodings_to_try:
-                    try:
-                        df = pd.read_csv(file.name, encoding=enc)
-                        break
-                    except UnicodeDecodeError:
-                        continue
-                else:
-                    return None, f"Could not determine encoding for '{os.path.basename(file.name)}'."
-            
-            dataframes.append(df)
-        
-        # Merge all DataFrames
-        if dataframes:
-            merged_df = pd.concat(dataframes, ignore_index=True)
-            
-            # Save to temporary file
-            with tempfile.NamedTemporaryFile(delete=False, suffix='.csv') as tmp:
-                output_path = tmp.name
-            
-            # Save merged data in Excel-compatible format (UTF-8 with BOM)
-            merged_df.to_csv(output_path, index=False, encoding='utf-8-sig')
-            
-            return output_path, f"Successfully merged {len(files)} files. Please open with UTF-8 encoding in Excel."
-        else:
-            return None, "No data to merge."
+        # Try reading from file-like object
+        file_bytes = input_file.read()
+        file_name = input_file.name
+    except AttributeError:
+        # If there's an AttributeError, treat input_file as a file path.
+        file_name = input_file
+        with open(file_name, "rb") as f:
+            file_bytes = f.read()
     
-    except Exception as e:
-        return None, f"Error occurred: {str(e)}"
+    file_extension = file_name.lower().split('.')[-1]
+    df = None
+    output_file = None
+    converted_format = None
+
+    # Conversion: CSV to Parquet
+    if conversion_type == "CSV to Parquet":
+        if file_extension != "csv":
+            raise ValueError("For CSV to Parquet conversion, please upload a CSV file.")
+        df = pd.read_csv(BytesIO(file_bytes))
+        output_file = "output.parquet"
+        df.to_parquet(output_file, index=False)
+        converted_format = "Parquet"
+    # Conversion: Parquet to CSV
+    elif conversion_type == "Parquet to CSV":
+        if file_extension != "parquet":
+            raise ValueError("For Parquet to CSV conversion, please upload a Parquet file.")
+        df = pd.read_parquet(BytesIO(file_bytes))
+        output_file = "output.csv"
+        df.to_csv(output_file, index=False)
+        converted_format = "CSV"
+    else:
+        raise ValueError("Invalid conversion type selected.")
 
-# Create a stylish Gradio interface
-with gr.Blocks(title="CSVFusion") as app:
-    gr.Markdown(
-        """
-        # 📊 CSVFusion: Intelligent File Merger
-        
-        *Seamlessly combine multiple CSV files into one unified dataset*
-        
-        ---
-        """
+    # Generate a preview of the top 10 rows
+    preview = df.head(10).to_string(index=False)
+    info_message = (
+        f"Input file: {file_name}\n"
+        f"Converted file format: {converted_format}\n\n"
+        f"Preview (Top 10 Rows):\n{preview}"
     )
+    return output_file, info_message
+
+# Custom CSS for a modern and sleek look
+custom_css = """
+body {
+    background-color: #f4f4f4;
+    font-family: 'Helvetica Neue', Arial, sans-serif;
+}
+.gradio-container {
+    max-width: 900px;
+    margin: 40px auto;
+    padding: 20px;
+    background-color: #ffffff;
+    border-radius: 12px;
+    box-shadow: 0 8px 16px rgba(0,0,0,0.1);
+}
+h1, h2 {
+    color: #333333;
+}
+.gradio-input, .gradio-output {
+    margin-bottom: 20px;
+}
+.gradio-button {
+    background-color: #4CAF50 !important;
+    color: white !important;
+    border: none !important;
+    padding: 10px 20px !important;
+    font-size: 16px !important;
+    border-radius: 6px !important;
+    cursor: pointer;
+}
+.gradio-button:hover {
+    background-color: #45a049 !important;
+}
+"""
+
+with gr.Blocks(css=custom_css, title="CSV <-> Parquet Converter") as demo:
+    gr.Markdown("# CSV <-> Parquet Converter")
+    gr.Markdown("Upload a CSV or Parquet file and select the conversion type. The app converts the file to the opposite format and displays a preview of the top 10 rows.")
     
     with gr.Row():
-        with gr.Column(scale=2):
-            gr.Markdown("""
-            ### How to use CSVFusion:
-            1. Upload up to 30 CSV files using the panel on the right
-            2. Click the "Merge Files" button
-            3. Download your consolidated CSV file
-            
-            ### Features:
-            - Automatic encoding detection
-            - Handles various CSV formats
-            - Excel-compatible output (UTF-8)
-            - Preserves all data columns
-            """)
-        
-        with gr.Column(scale=3):
-            input_files = gr.File(
-                file_count="multiple",
-                label="Upload CSV Files (Max 30)",
-                file_types=[".csv"],
-                elem_id="file_upload"
-            )
+        with gr.Column(scale=1):
+            input_file = gr.File(label="Upload CSV or Parquet File")
+        with gr.Column(scale=1):
+            conversion_type = gr.Radio(choices=["CSV to Parquet", "Parquet to CSV"], label="Conversion Type")
     
-    with gr.Row():
-        merge_button = gr.Button("Merge Files", variant="primary", size="lg")
+    convert_button = gr.Button("Convert", elem_classes=["gradio-button"])
     
     with gr.Row():
-        with gr.Column():
-            status = gr.Textbox(label="Status", placeholder="Ready to merge your files...")
-        with gr.Column():
-            output_file = gr.File(label="Download Merged CSV")
-    
-    # Add custom CSS for better visual appeal
-    gr.HTML("""
-    <style>
-    .gradio-container {
-        background: linear-gradient(to right, #f9f9f9, #ffffff);
-        border-radius: 12px;
-    }
-    #file_upload {
-        border: 2px dashed #3498db;
-        border-radius: 8px;
-        padding: 20px;
-        transition: all 0.3s;
-    }
-    #file_upload:hover {
-        border-color: #2980b9;
-        box-shadow: 0 0 10px rgba(52, 152, 219, 0.3);
-    }
-    .footer {
-        text-align: center;
-        margin-top: 30px;
-        color: #7f8c8d;
-        font-size: 0.9em;
-    }
-    </style>
-    """)
+        output_file = gr.File(label="Converted File")
+        preview = gr.Textbox(label="Preview (Top 10 Rows)", lines=15)
     
-    # Add footer
-    gr.HTML("""
-    <div class="footer">
-        <p>CSVFusion © 2025 - A powerful tool for data professionals</p>
-    </div>
-    """)
-    
-    merge_button.click(
-        fn=merge_csv_files,
-        inputs=[input_files],
-        outputs=[output_file, status]
-    )
+    convert_button.click(fn=convert_file, inputs=[input_file, conversion_type], outputs=[output_file, preview])
 
-# Run the app
-if __name__ == "__main__":
-    app.launch()
+demo.launch()