Spaces:
Sleeping
Sleeping
File size: 8,157 Bytes
f3a9c70 b9648f5 f3a9c70 b9648f5 f3a9c70 b9648f5 698579d f3a9c70 698579d f3a9c70 c67e5d3 f3a9c70 698579d f3a9c70 c67e5d3 f3a9c70 698579d b9648f5 698579d 4d78b95 698579d b9648f5 5be16b9 b9648f5 698579d f3a9c70 698579d f3a9c70 698579d f3a9c70 698579d f3a9c70 698579d f3a9c70 698579d b9648f5 698579d f3a9c70 b9648f5 f3a9c70 b9648f5 f3a9c70 698579d 4d78b95 698579d f3a9c70 b9648f5 f3a9c70 698579d |
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 |
import streamlit as st
from PyPDF2 import PdfReader
from concurrent.futures import ThreadPoolExecutor
from base64 import b64encode
from fpdf import FPDF
import io, string, re, math
from io import StringIO
# Importing the Fastify Class
from fast_reader import Fastify_Reader
def pdf_extract_text(pdf_docs):
'''
Basic function for extracting text from the PDFs
'''
text = ""
for pdf in pdf_docs:
pdf_reader = PdfReader(pdf)
for page in pdf_reader.pages:
text += page.extract_text()
return text
def text_to_pdf_fastify(text):
'''
Basic function to apply fastification on the input text and convert it to bytes for PDF rendering
'''
# Applying the Fastify Logic
bold_text = Fastify_Reader(text).fastify()
bold_text = bold_text.encode('latin-1', 'ignore').decode('latin-1') #since fpdf works with latin-1 encoding
# Creating the PDF
pdf = FPDF()
pdf.add_page()
pdf.set_font("Arial", size = 12)
pdf.multi_cell(0, 10, txt = bold_text, markdown=True)
return bytes(pdf.output())
def text_to_pdf(text):
'''
Basic function on the input text and convert it to bytes for PDF rendering
'''
text = text.encode('latin-1', 'ignore').decode('latin-1') #since fpdf works with latin-1 encoding
# Creating the PDF
pdf = FPDF()
pdf.add_page()
pdf.set_font("Arial", size = 12)
pdf.multi_cell(0, 10, txt = text, markdown=True)
return bytes(pdf.output())
#Setting the page config
st.set_page_config(page_title="Fastify Reader",
page_icon=":books:",
layout="wide")
# Due to browser cache and streamlit issue, sometimes the PDFs are not rendered properly.
note_text = """
If the PDF is not being rendered by your browser, <br>
 1. Try this link - (https://akarshrajsingh7-fastify-reader.hf.space/) <br>
 2. Download the PDF and open it in a PDF viewer.
"""
# Sidebar
with st.sidebar:
st.image("Logo.jpg")
st.markdown("<div style='text-align: center;'>How fast can you read?</div>", unsafe_allow_html=True)
# Main Page
tab1, tab2= st.tabs(["Input Text", "PDF file"])
# First tab where Text is input
with tab1:
user_input = st.text_input("Enter some text")
# Compare Check Box
compare = st.checkbox('Compare with Fastified Text', value=False, key='compare')
# Submit Button
if st.button("Submit", key="input-text"):
#Progess Bar for the processing
with st.spinner("Processing"):
text = user_input
# Generating base64 encoded text bytes for PDF rendering
original_pdf = b64encode(text_to_pdf(text)).decode("utf-8")
base64_pdf = b64encode(text_to_pdf_fastify(text)).decode("utf-8")
# Embedding the PDFs in the HTML
original_display = f'<embed src="data:application/pdf;base64,{original_pdf}" width = "100%" height = 600 type="application/pdf" download="original.pdf">'
pdf_display = f'<embed src="data:application/pdf;base64,{base64_pdf}" width = "100%" height = 600 type="application/pdf" download="Modified.pdf">'
# Compare Logic implementation
if compare:
col1, col2, col3 = st.columns(3)
with col3:
st.download_button(label="Download Fastified PDF", data=text_to_pdf_fastify(text), file_name='output.pdf', mime='application/pdf')
# Side by Side comparison
col1, col2 = st.columns([1, 1], gap="small")
with col1:
with st.container(border = True):
st.markdown("<div style='text-align: center;'><strong>Original PDF viewer</strong></div>", unsafe_allow_html=True)
st.markdown(original_display, unsafe_allow_html=True)
with col2:
with st.container(border = True):
st.markdown("<div style='text-align: center;'><strong>Fastified PDF viewer</strong></div>", unsafe_allow_html=True)
st.markdown(pdf_display, unsafe_allow_html=True)
# Browser Cache Note
st.markdown(f"""
<div style='background-color: #FFD580; border-radius: 5px;'>
<p style='color: black;'><strong>Note</strong> - {note_text}</p>
</div>
""", unsafe_allow_html=True)
else:
# No Comparisons
col1, col2, col3 = st.columns(3)
with col2:
st.download_button(label="Download Fastified PDF", data=text_to_pdf_fastify(text), file_name='output.pdf', mime='application/pdf')
with st.container(border = True):
st.markdown("<div style='text-align: center;'><strong>Fastified PDF viewer</strong></div>", unsafe_allow_html=True)
st.markdown(pdf_display, unsafe_allow_html=True)
# Added support for PDFs having text
with tab2:
uploaded_file = st.file_uploader("Upload a PDF file", type="pdf", accept_multiple_files=True)
# Compare Check Box
compare = st.checkbox('Compare with Fastified Text', value=False, key='compare_pdf')
# Submit Button
if st.button("Submit", key="pdf"):
#Progess Bar for the processing
with st.spinner("Processing"):
text = pdf_extract_text(uploaded_file)
# Generating base64 encoded text bytes for PDF rendering
original_pdf = b64encode(text_to_pdf(text)).decode("utf-8")
base64_pdf = b64encode(text_to_pdf_fastify(text)).decode("utf-8")
# Embedding the PDFs in the HTML
original_display = f'<embed src="data:application/pdf;base64,{original_pdf}" width = "100%" height = 600 type="application/pdf">'
pdf_display = f'<embed src="data:application/pdf;base64,{base64_pdf}" width = "100%" height = 600 type="application/pdf">'
# Compare Logic implementation
if compare:
col1, col2, col3 = st.columns(3)
with col3:
st.download_button(label="Download Fastified PDF", data=text_to_pdf_fastify(text), file_name='output.pdf', mime='application/pdf')
# Side by Side comparison
col1, col2 = st.columns([1, 1], gap="small")
with col1:
with st.container(border = True):
st.markdown("<div style='text-align: center;'><strong>Original PDF viewer</strong></div>", unsafe_allow_html=True)
st.markdown(original_display, unsafe_allow_html=True)
with col2:
with st.container(border = True):
st.markdown("<div style='text-align: center;'><strong>Fastified PDF viewer</strong></div>", unsafe_allow_html=True)
st.markdown(pdf_display, unsafe_allow_html=True)
# Browser Cache Note
st.markdown(f"""
<div style='background-color: #FFD580; border-radius: 5px;'>
<p style='color: black;'><strong>Note</strong> - {note_text}</p>
</div>
""", unsafe_allow_html=True)
else:
# No Comparison
col1, col2, col3 = st.columns(3)
with col2:
st.download_button(label="Download Fastified PDF", data=text_to_pdf_fastify(text), file_name='output.pdf', mime='application/pdf')
with st.container(border = True):
st.markdown("<div style='text-align: center;'><strong>Fastified PDF viewer</strong></div>", unsafe_allow_html=True)
st.markdown(pdf_display, unsafe_allow_html=True)
|