Spaces:
Sleeping
Sleeping
File size: 10,813 Bytes
5a99cc1 ad5ca2c bfc7f18 25c9941 cd77918 bfc7f18 365522e 6a8bd53 15cd602 ad5ca2c bfc7f18 5a99cc1 6a8bd53 ad5ca2c bfc7f18 ad5ca2c bfc7f18 ad5ca2c bfc7f18 cd77918 f9cf3d0 d792040 f9cf3d0 bfc7f18 d792040 bfc7f18 f9cf3d0 cd77918 f9cf3d0 d792040 bfc7f18 25c9941 cd77918 25c9941 bfc7f18 ad5ca2c d6482c4 365522e ad5ca2c 6a8bd53 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 |
import streamlit as st
import pdf2image
import utils
import numpy as np
import cv2
import os
import io
from PIL import Image
import shutil
import time
# get https://github.com/oschwartz10612/poppler-windows/releases/tag/v22.01.0-0
# poppler-utils:
# Installed: 22.02.0-2ubuntu0.4
# install https://github.com/UB-Mannheim/tesseract/wiki
#page extraction disabled
def is_new_pdf_upload(uploaded_file):
if 'last_pdf_uploaded_file' in st.session_state:
# Check if the newly uploaded file is different from the last one
if (uploaded_file.name != st.session_state.last_pdf_uploaded_file['name'] or
uploaded_file.size != st.session_state.last_pdf_uploaded_file['size']):
st.session_state.last_pdf_uploaded_file = {'name': uploaded_file.name, 'size': uploaded_file.size}
# st.write("A new src image file has been uploaded.")
return True
else:
# st.write("The same src image file has been re-uploaded.")
return False
else:
# st.write("This is the first file upload detected.")
st.session_state.last_pdf_uploaded_file = {'name': uploaded_file.name, 'size': uploaded_file.size}
return True
# Store current file details in session state
big_text = """
<div style='text-align: center;'>
<h1 style='font-size: 30x;'>Locked PDF Ingestion</h1>
</div>
"""
# Display the styled text
st.markdown(big_text, unsafe_allow_html=True)
if 'is_initialized' not in st.session_state:
pdf_path = 'uploaded_pdf/data_sheet.pdf'
st.session_state['is_initialized'] = True
# page_count = utils.get_pdf_page_count(pdf_path)
# print("page_count=",page_count)
# page_count=5
# print("new page_count=",page_count)
# read_pdf_progress_bar = st.progress(0)
# st.session_state.color_image_list = []
# st.session_state.gray_image_np_list = []
# for page_number in range(page_count):
# image = pdf2image.convert_from_path(pdf_path, first_page=page_number+1, last_page=page_number+1)
# st.session_state.color_image_list.append(image[0])
# progress_percentage = (page_number) / (page_count-1)
# read_pdf_progress_bar.progress(progress_percentage)
# gray_pdf_image_np_list = []
# read_pdf_progress_bar.progress(0)
# for index, image in enumerate(st.session_state.color_image_list):
# image_np = np.array(image)
# st.session_state.gray_image_np_list.append(cv2.cvtColor(np.array(image_np), cv2.COLOR_BGR2GRAY))
# progress_percentage = (index) / (page_count - 1)
# read_pdf_progress_bar.progress(progress_percentage)
# # cv2.line(st.session_state.gray_image_np_list[37], (174, 227), (174, 1790), 0, 2)
# # cv2.line(st.session_state.gray_image_np_list[37], (1550, 227), (1550, 1790), 0, 2)
# # cv2.line(st.session_state.gray_image_np_list[38], (226,227),(226,1444), 0,3)
# # cv2.line(st.session_state.gray_image_np_list[38], (1601,227),(1601,1444), 0,2)
# st.session_state.img_index = 0
# st.session_state.stop_button_clicked=False
# # st.image(st.session_state.gray_image_np_list[38])
uploaded_locked_pdf_file = st.file_uploader("Upload a locked pdf",
type=['pdf'])
st.markdown(
f'<a href="https://ikmtechnology.github.io/ikmtechnology/data_sheet.pdf" target="_blank">Sample 1 download and then upload to above</a>',
unsafe_allow_html=True)
if uploaded_locked_pdf_file is not None:
if is_new_pdf_upload(uploaded_locked_pdf_file):
# To see details
# file_details = {"FileName": uploaded_driving_video_file.name, "FileType": uploaded_driving_video_file.type, "FileSize": uploaded_driving_video_file.size}
# st.write(file_details)
save_path = './uploaded_videos'
if not os.path.exists(save_path):
os.makedirs(save_path)
with open(os.path.join(save_path, uploaded_locked_pdf_file.name), "wb") as f:
f.write(uploaded_locked_pdf_file.getbuffer()) # Write the file to the specified location
st.success(f'Saved file temp_{uploaded_locked_pdf_file.name} in {save_path}')
st.session_state.uploaded_pdf_path=os.path.join(save_path, uploaded_locked_pdf_file.name)
st.session_state.page_count = utils.get_pdf_page_count(st.session_state.uploaded_pdf_path)
print("page_count=",st.session_state.page_count)
if 'extracted_text' in st.session_state:
del st.session_state.extracted_text
st.rerun()
if 'page_count' in st.session_state:
st.write(f"total page count = {st.session_state.page_count}")
if 'num_pages_to_extract'not in st.session_state:
st.session_state.num_pages_to_extract = st.slider('Number of pages to extract:', min_value=1, max_value=st.session_state.page_count, value=5, key='num_pages_to_extract_slider')
else:
st.session_state.num_pages_to_extract = st.slider('Number of pages to extract:', min_value=1, max_value=st.session_state.page_count, value=st.session_state.num_pages_to_extract , key='num_pages_to_extract_slider')
st.write(f"num of pages to extract {st.session_state.num_pages_to_extract}")
if 'run_button' in st.session_state and st.session_state.run_button == True:
st.session_state.running = True
else:
st.session_state.running = False
read_pdf_progress_bar = st.progress(0)
if st.button('Extract Pages', disabled=st.session_state.running, key='run_button'):
st.session_state.color_image_list = []
st.session_state.gray_image_np_list = []
st.session_state.pdf_figures_image_list=[]
pdf_tables_image_list=[]
st.session_state.pdf_text_list=[]
for page_number in range(st.session_state.num_pages_to_extract):
image = pdf2image.convert_from_path(st.session_state.uploaded_pdf_path, first_page=page_number+1, last_page=page_number+1)
st.session_state.color_image_list.append(image[0])
progress_percentage = (page_number) / (st.session_state.num_pages_to_extract-1)
read_pdf_progress_bar.progress(progress_percentage)
read_pdf_progress_bar.progress(0)
for index, image in enumerate(st.session_state.color_image_list):
image_np = np.array(image)
st.session_state.gray_image_np_list.append(cv2.cvtColor(np.array(image_np), cv2.COLOR_BGR2GRAY))
progress_percentage = (index) / (st.session_state.num_pages_to_extract - 1)
read_pdf_progress_bar.progress(progress_percentage)
st.session_state.extracted_text = ""
for index, gray_pdf_image_np in enumerate(st.session_state.gray_image_np_list):
print("index="+str(index))
figures_image_list,tables_image_list,text=utils.gray_pdf_image_np_to_text(index,gray_pdf_image_np, debug=True)
st.session_state.pdf_figures_image_list.append(figures_image_list)
pdf_tables_image_list.append(tables_image_list)
st.session_state.pdf_text_list.append(text)
st.session_state.extracted_text=st.session_state.extracted_text+f"<Page {index+1} start>\n" + text + f"\n<Page {index+1} end>\n>"
# st.write(text)
# print(text)
progress_percentage = (index) / (st.session_state.num_pages_to_extract - 1)
read_pdf_progress_bar.progress(progress_percentage)
#add_animation_to_image()
#st.session_state['video_generated'] = True
st.rerun()
if 'extracted_text' in st.session_state:
string_buffer = io.StringIO(st.session_state.extracted_text)
txt_file_path=uploaded_locked_pdf_file.name.replace(".pdf", ".txt")
st.download_button(label="Download Extraction txt File",
data=string_buffer.getvalue(),
file_name=txt_file_path,
mime="text/plain")
# st.image(Image.fromarray(bgr_image))
# for index,pdf_text in enumerate(st.session_state.pdf_text_list):
for index, gray_pdf_image_np in enumerate(st.session_state.gray_image_np_list):
st.write(f"Page {index+1} \n\n {st.session_state.pdf_text_list[index]}\n")
if not st.session_state.pdf_figures_image_list[index]:
st.write("no figures")
else:
for pdf_figure_text_image in st.session_state.pdf_figures_image_list[index]:
st.write(pdf_figure_text_image[0])
st.image(Image.fromarray(pdf_figure_text_image[1]))
# for index, gray_pdf_image_np in enumerate(st.session_state.gray_image_np_list[0:5], start=0):
# print("index="+str(index))
#
# text=utils.gray_pdf_image_np_to_text(index,gray_pdf_image_np, debug=True)
# st.write(text)
#if 'img_index' not in st.session_state:
# if st.button("Stop"):
# st.session_state.stop_button_clicked = True
# st.write(str(st.session_state.img_index+1) +"/" + str(len(st.session_state.color_image_list)))
# st.image(st.session_state.gray_image_np_list[st.session_state.img_index], use_column_width=True)
# if not st.session_state.stop_button_clicked:
# if st.session_state.img_index < len(st.session_state.color_image_list) - 1:
# st.session_state.img_index += 1
# time.sleep(3)
# st.rerun()
# col1, col2 = st.columns(2)
# with col1:
# if st.button("Previous"):
# print("Previous pressed")
# # Decrease index, wrap around if it goes below 0
# print("st.session_state.img_index =", str(st.session_state.img_index))
# if st.session_state.img_index > 0:
# print("case 1 before st.session_state.img_index =",str(st.session_state.img_index))
# st.session_state.img_index -= 1
# print("case 2 after st.session_state.img_index =", str(st.session_state.img_index))
# else:
# print("case 2 st.session_state.img_index =", str(st.session_state.img_index))
# st.session_state.img_index = len(st.session_state.color_image_list) - 1
# with col2:
# if st.button("Next"):
#
# print("Next pressed")
# # Increase index, wrap around if it goes past the last image
# if st.session_state.img_index < len(st.session_state.color_image_list) - 1:
# st.session_state.img_index += 1
#
# else:
# st.session_state.img_index = 0
# #
# total_pages = 100
# print(f"total_pages = {total_pages}")
# st.write(f"total_pages = {total_pages}")
# for page_number in range(total_pages):
# pdf_image_list = convert_from_path(pdf_path)
# images = convert_from_path(pdf_path, first_page=page_number + 1, last_page=page_number + 1)
# progress = (page_number + 1) / total_pages * 100
# print(f"Progress: {progress:.2f}%")
# print("done") |