Update app.py

app.py

@@ -1,59 +1,50 @@
-import pdfplumber
-import pandas as pd
-import re
 import gradio as gr
+from ALNISF import process_pdf as process_alnisf
+from federal_electric import process_pdf as process_federal_electric
+from bhel import process_pdf as process_bhel
 
-# Individual processing functions
-def process_bhel(pdf_file):
-    # Place the BHEL-specific code logic here
-    return process_common(pdf_file, "BHEL Output.xlsx")
-
-def process_federal_electric(pdf_file):
-    # Place the Federal Electric-specific code logic here
-    return process_common(pdf_file, "Federal Electric Output.xlsx")
-
-def process_al_nisf(pdf_file):
-    # Place the AL-NISF-specific code logic here
-    return process_common(pdf_file, "AL-NISF Output.xlsx")
-
-def process_common(pdf_file, output_name):
+# Wrapper function to handle multiple extractors
+def process_file(pdf_file, extractor):
     """
-    Generalized function for processing PDFs
+    Processes the uploaded PDF using the selected extractor.
+    Args:
+        pdf_file: Uploaded PDF file.
+        extractor: The selected extractor script (ALNISF, Federal Electric, BHEL).
+    Returns:
+        The extracted file and status message.
     """
-    # Replace this with common or specific processing logic
-    with pdfplumber.open(pdf_file.name) as pdf:
-        text = ""
-        for page in pdf.pages:
-            text += page.extract_text()
-
-    # Example: Create dummy DataFrame
-    data = {"Text": text}
-    df = pd.DataFrame([data])
-    df.to_excel(output_name, index=False)
-    return output_name
-
-# Dropdown processing function
-def main_process(pdf_file, format_choice):
-    if format_choice == "BHEL":
-        return process_bhel(pdf_file)
-    elif format_choice == "Federal Electric":
+    if extractor == "ALNISF":
+        return process_alnisf(pdf_file)
+    elif extractor == "Federal Electric":
         return process_federal_electric(pdf_file)
-    elif format_choice == "AL-NISF":
-        return process_al_nisf(pdf_file)
+    elif extractor == "BHEL":
+        return process_bhel(pdf_file)
     else:
-        return None
+        return None, "Invalid extractor selected."
 
-# Gradio interface
-iface = gr.Interface(
-    fn=main_process,
-    inputs=[
-        gr.File(label="Upload PDF", file_types=[".pdf"]),
-        gr.Dropdown(choices=["BHEL", "Federal Electric", "AL-NISF"], label="Select Format")
-    ],
-    outputs=gr.File(label="Download Processed File"),
-    title="Consolidated PO Data Extractor",
-    description="Select the format and upload a PDF to extract and download the data."
-)
+# Gradio interface setup
+def create_main_interface():
+    """
+    Creates the main Gradio interface that integrates all extractors.
+    """
+    return gr.Interface(
+        fn=process_file,
+        inputs=[
+            gr.File(label="Upload PDF", file_types=[".pdf"]),
+            gr.Radio(
+                ["ALNISF", "Federal Electric", "BHEL"],
+                label="Select Extractor",
+                value="ALNISF"
+            ),
+        ],
+        outputs=[
+            gr.File(label="Download Extracted Data"),
+            gr.Textbox(label="Status"),
+        ],
+        title="Unified PO Data Extraction App",
+        description="Upload a Purchase Order PDF and select the extractor (ALNISF, Federal Electric, BHEL) to process the file and download the extracted data.",
+    )
 
 if __name__ == "__main__":
-    iface.launch()
+    interface = create_main_interface()
+    interface.launch()