File size: 4,401 Bytes
c9e6420
6bd383d
a73d961
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6bd383d
3c0821a
 
a73d961
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61e3677
3c0821a
 
 
61e3677
3c0821a
61e3677
3c0821a
 
 
 
 
 
 
a73d961
61e3677
3c0821a
 
 
6bd383d
3c0821a
 
61e3677
3c0821a
 
61e3677
3c0821a
 
 
c9e6420
2ab0f0e
b04b188
2ab0f0e
 
c681352
 
 
 
 
 
 
c9e6420
4b3f925
61e3677
 
a73d961
 
 
 
 
 
 
 
2ab0f0e
a73d961
 
 
 
2ab0f0e
a73d961
 
 
 
 
 
 
 
 
2ab0f0e
 
 
 
 
 
 
 
 
a73d961
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
import gradio as gr
import subprocess
import uuid
import os
import requests


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)

  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]


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'
  ]

  # Run the command and capture its output
  #completed_process = 
  subprocess.run(cli_command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)

  return #unique_filename


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!"
    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()
  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'
  ]

  # 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 ocr_content
      
css = """
  #mkd {
    height: 500px; 
    overflow: auto; 
    border: 1px solid #ccc; 
  }
"""

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🚿')
  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:'
  )
    
demo.queue()
demo.launch(debug=True)