Update app.py

app.py

@@ -3,112 +3,61 @@ import subprocess
 import uuid
 import os
 import requests
-import re
-
 
 def get_pdf(pdf_link):
-  # Generate a unique filename
-  unique_filename = f"input/downloaded_paper_{uuid.uuid4().hex}.pdf"
-
-  # Send a GET request to the PDF link
-  response = requests.get(pdf_link)
+    # Generate a unique filename
+    unique_filename = f"input/downloaded_paper_{uuid.uuid4().hex}.pdf"
 
-  if response.status_code == 200:
-      # Save the PDF content to a local file
-      with open(unique_filename, 'wb') as pdf_file:
-          pdf_file.write(response.content)
-      print("PDF downloaded successfully.")
-  else:
-      print("Failed to download the PDF.")
-  return unique_filename #.split('/')[-1][:-4]
+    # Send a GET request to the PDF link
+    response = requests.get(pdf_link)
 
+    if response.status_code == 200:
+        # Save the PDF content to a local file
+        with open(unique_filename, 'wb') as pdf_file:
+            pdf_file.write(response.content)
+        print("PDF downloaded successfully.")
+    else:
+        print("Failed to download the PDF.")
+    return unique_filename
 
 def nougat_ocr(file_name):
-
-  #unique_filename = f"/content/output/downloaded_paper_{uuid.uuid4().hex}.pdf"
-  # Command to run
-  cli_command = [
-      'nougat',
-      #'--out', unique_filename,
-      '--out', 'output',
-      'pdf', f'{file_name}',
-      '--checkpoint', 'nougat',
-      '--markdown'
-  ]
-
-  # Run the command and capture its output
-  #completed_process = 
-  subprocess.run(cli_command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
-
-  return #unique_filename
-
+    # Command to run
+    cli_command = [
+        'nougat',
+        '--out', 'output',
+        'pdf', f'{file_name}',
+        '--checkpoint', 'nougat',
+        '--markdown'
+    ]
+    subprocess.run(cli_command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
 
 def predict(pdf_file, pdf_link):
-  if pdf_file is None:
-    if pdf_link == '':
-      print("No file is uploaded and No link is provided")
-      return "No data provided. Upload a pdf file or provide a pdf link and try again!"
+    if pdf_file is None:
+        if pdf_link == '':
+            print("No file is uploaded and No link is provided")
+            return "No data provided. Upload a pdf file or provide a pdf link and try again!", "", ""
+        else:
+            print(f'pdf_link is - {pdf_link}')
+            file_name = get_pdf(pdf_link)
+            print(f'file_name is - {file_name}')
     else:
-      print(f'pdf_link is - {pdf_link}')
-      file_name = get_pdf(pdf_link)
-      print(f'file_name is - {file_name}')
-  else:
-    file_name = pdf_file.name
-    print(file_name)
-    pdf_name = pdf_file.name.split('/')[-1].split('.')[0]
-    print(pdf_name)
-
-  # Call nougat
-  nougat_ocr(file_name)
-  #print("BACKKKK")
-
-  # Open the file for reading
-  file_name = file_name.split('/')[-1][:-4]
-  with open(f'output/{file_name}.mmd', 'r') as file:
-      content = file.read()
-  # switch math delimiters
-  content = content.replace(r'\(', '$').replace(r'\)', '$').replace(r'\[', '$$').replace(r'\]', '$$')
-  return content
-
-
-
-
-def nougat_ocr1(file_name):
-  print('******* inside nougat_ocr *******')
-  # CLI Command to run
-  cli_command = [
-      'nougat',
-      '--out', 'output',
-      'pdf', f'{file_name}',
-      '--checkpoint', 'nougat',
-      '--markdown'
-  ]
-
-  # Run the command and get .mmd file in an output folder
-  subprocess.run(cli_command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
-  return
-
-
-def predict1(pdf_file):
-  print('******* inside predict *******')
-  print(f"temporary file - {pdf_file.name}")
-  pdf_name = pdf_file.name.split('/')[-1].split('.')[0]
-  print(f"pdf file name - {pdf_name}")
-    
-  #! Get prediction for a PDF using nougat
-  nougat_ocr(pdf_file.name)
-  print("BAACCKKK")
-  
-  # Open the multimarkdown (.mmd) file for reading
-  with open(f'output/{pdf_name}.mmd', 'r') as file:
-      content = file.read() 
-      
-  return content
-
-def process_example(pdf_file,pdf_link):
- ocr_content = predict(pdf_file,pdf_link)
- return gr.update(value=ocr_content)
-      
+        file_name = pdf_file.name
+        print(file_name)
+        pdf_name = pdf_file.name.split('/')[-1].split('.')[0]
+        print(pdf_name)
+
+    # Call nougat
+    nougat_ocr(file_name)
+
+    # Open the file for reading
+    file_name = file_name.split('/')[-1][:-4]
+    output_path = f'output/{file_name}.mmd'
+    with open(output_path, 'r') as file:
+        content = file.read()
+    # Switch math delimiters
+    content = content.replace(r'\(', '$').replace(r'\)', '$').replace(r'\[', '$$').replace(r'\]', '$$')
+    return content, content, output_path
+
 css = """
   #mkd {
     height: 500px; 
@@ -117,42 +66,44 @@ css = """
   }
 """
 
+# JavaScript function to copy content to clipboard automatically
+js_auto_copy = """
+function autoCopyToClipboard() {
+    var content = document.getElementById('markdown-content').value;
+    navigator.clipboard.writeText(content).then(function() {
+        console.log('Content copied to clipboard');
+    }).catch(function(error) {
+        console.error('Error copying content to clipboard: ', error);
+    });
+}
+"""
+
 with gr.Blocks(css=css) as demo:
-  gr.HTML("<h1><center>Nougat: Neural Optical Understanding for Academic Documents<center><h1>")
-  gr.HTML("<h3><center>Lukas Blecher et al. <a href='https://arxiv.org/pdf/2308.13418.pdf' target='_blank'>Paper</a>, <a href='https://facebookresearch.github.io/nougat/'>Project</a><center></h3>")
-
-  with gr.Row():
-    mkd = gr.Markdown('<h4><center>Upload a PDF</center></h4>',scale=1)
-    mkd = gr.Markdown('<h4><center><i>OR</i></center></h4>',scale=1)
-    mkd = gr.Markdown('<h4><center>Provide a PDF link</center></h4>',scale=1)
-  
-  with gr.Row(equal_height=True):
-    pdf_file = gr.File(label='PDF📃', file_count='single', scale=1)
-    pdf_link = gr.Textbox(placeholder='Enter an Arxiv link here', label='PDF link🔗🌐', scale=1)
-
-  with gr.Row():
-    btn = gr.Button('Run NOUGAT🍫')
-    clr = gr.Button('Clear🚿')
-
-  output_headline = gr.Markdown("<h3>PDF converted to markup language through Nougat-OCR👇:</h3>")
-  parsed_output = gr.Markdown(elem_id='mkd', value='📃🔤OCR Output')
-  
-  btn.click(predict, [pdf_file, pdf_link], parsed_output )
-  clr.click(lambda : (gr.update(value=None), 
-                      gr.update(value=None),
-                      gr.update(value=None)), 
-             [], 
-             [pdf_file, pdf_link, parsed_output]
-            )
-
-  gr.Examples(
-      [["input/nougat.pdf", ""], [None, "https://arxiv.org/pdf/2308.08316.pdf"]],
-      inputs = [pdf_file, pdf_link],
-      outputs = parsed_output,
-      fn=process_example,
-      cache_examples=True,
-      label='Click on any Examples below to get Nougat OCR results quickly:'
-  )
-    
+    gr.HTML("<h1><center>Nougat: Neural Optical Understanding for Academic Documents<center><h1>")
+    gr.HTML("<h3><center>Lukas Blecher et al. <a href='https://arxiv.org/pdf/2308.13418.pdf' target='_blank'>Paper</a>, <a href='https://facebookresearch.github.io/nougat/'>Project</a><center></h3>")
+
+    with gr.Row():
+        mkd = gr.Markdown('<h4><center>Upload a PDF</center></h4>', scale=1)
+        mkd = gr.Markdown('<h4><center><i>OR</i></center></h4>', scale=1)
+        mkd = gr.Markdown('<h4><center>Provide a PDF link</center></h4>', scale=1)
+
+    with gr.Row(equal_height=True):
+        pdf_file = gr.File(label='PDF📃', file_count='single', scale=1)
+        pdf_link = gr.Textbox(placeholder='Enter an Arxiv link here', label='PDF link🔗🌐', scale=1)
+
+    with gr.Row():
+        btn = gr.Button('Run NOUGAT🍫')
+        clr = gr.Button('Clear🚿')
+        dwn = gr.Button('Download📥')
+
+    output_headline = gr.Markdown("<h3>PDF converted to markup language through Nougat-OCR👇:</h3>")
+    parsed_output = gr.Markdown(elem_id='mkd', value='📃🔤OCR Output')
+    markdown_hidden = gr.Textbox(elem_id='markdown-content', visible=False)
+    download_link = gr.File(elem_id='download-link', visible=False)
+
+    btn.click(predict, [pdf_file, pdf_link], [parsed_output, markdown_hidden, download_link], _js=js_auto_copy)
+    clr.click(lambda: (gr.update(value=None), gr.update(value=None), gr.update(value=None)), [], [pdf_file, pdf_link, parsed_output, markdown_hidden, download_link])
+    dwn.click(None, [download_link], None)
+
 demo.queue()
 demo.launch(debug=True)