Spaces:
Sleeping
Sleeping
Commit
·
3233632
1
Parent(s):
63f05af
streamlit pdf viewer - trial
Browse files- app.py +51 -94
- requirements.txt +1 -0
app.py
CHANGED
@@ -1,3 +1,5 @@
|
|
|
|
|
|
1 |
import streamlit as st
|
2 |
from PyPDF2 import PdfReader
|
3 |
from concurrent.futures import ThreadPoolExecutor
|
@@ -5,11 +7,16 @@ from base64 import b64encode
|
|
5 |
from fpdf import FPDF
|
6 |
import io, string, re, math
|
7 |
from io import StringIO
|
8 |
-
|
|
|
9 |
|
10 |
# Importing the Fastify Class
|
11 |
from fast_reader import Fastify_Reader
|
12 |
|
|
|
|
|
|
|
|
|
13 |
def pdf_extract_text(pdf_docs):
|
14 |
'''
|
15 |
Basic function for extracting text from the PDFs
|
@@ -21,10 +28,11 @@ def pdf_extract_text(pdf_docs):
|
|
21 |
text += page.extract_text()
|
22 |
return text
|
23 |
|
24 |
-
def text_to_pdf_fastify(
|
25 |
'''
|
26 |
Basic function to apply fastification on the input text and convert it to bytes for PDF rendering
|
27 |
'''
|
|
|
28 |
# Applying the Fastify Logic
|
29 |
bold_text = Fastify_Reader(text).fastify()
|
30 |
bold_text = bold_text.encode('latin-1', 'ignore').decode('latin-1') #since fpdf works with latin-1 encoding
|
@@ -36,10 +44,11 @@ def text_to_pdf_fastify(text):
|
|
36 |
pdf.multi_cell(0, 10, txt = bold_text, markdown=True)
|
37 |
return bytes(pdf.output())
|
38 |
|
39 |
-
def text_to_pdf(
|
40 |
'''
|
41 |
Basic function on the input text and convert it to bytes for PDF rendering
|
42 |
'''
|
|
|
43 |
text = text.encode('latin-1', 'ignore').decode('latin-1') #since fpdf works with latin-1 encoding
|
44 |
# Creating the PDF
|
45 |
pdf = FPDF()
|
@@ -80,31 +89,6 @@ with tab1:
|
|
80 |
with st.spinner("Processing"):
|
81 |
text = user_input
|
82 |
|
83 |
-
# Generating base64 encoded text bytes for PDF rendering
|
84 |
-
original_pdf = b64encode(text_to_pdf(text)).decode("utf-8")
|
85 |
-
base64_pdf = b64encode(text_to_pdf_fastify(text)).decode("utf-8")
|
86 |
-
|
87 |
-
# Embedding the PDFs in the HTML
|
88 |
-
original_display = f'<embed src="data:application/pdf;base64,{original_pdf}" width = "100%" height = 600 type="application/pdf" download="original.pdf">'
|
89 |
-
pdf_display = f'<embed src="data:application/pdf;base64,{base64_pdf}" width = "100%" height = 600 type="application/pdf" download="Modified.pdf">'
|
90 |
-
|
91 |
-
# original_display = f"""<embed class="pdfobject" type="application/pdf" title="Original PDF" src="data:application/pdf;base64,{original_pdf}" style=" width: 100%; height: 150%;">"""
|
92 |
-
# pdf_display = f"""<embed class="pdfobject" type="application/pdf" title="Modified PDF" src="data:application/pdf;base64,{base64_pdf}" style=" width: 100%; height: 150%;">"""
|
93 |
-
|
94 |
-
# original_display = f'<iframe src="data:application/pdf;base64,{original_pdf}" width = "100%" height = 600 type="application/pdf" download="original.pdf"></iframe>'
|
95 |
-
# pdf_display = f'<iframe src="data:application/pdf;base64,{base64_pdf}" width = "100%" height = 600 type="application/pdf" download="Modified.pdf"></iframe>'
|
96 |
-
|
97 |
-
# original_display = f"""
|
98 |
-
# <div class="pdf-container" style="height: 500px;">
|
99 |
-
# <embed class="pdfobject" type="application/pdf" title="Modified PDF" src="data:application/pdf;base64,{original_pdf}" style="width: 100%; height: 100%;">
|
100 |
-
# </div>
|
101 |
-
# """
|
102 |
-
# pdf_display = f"""
|
103 |
-
# <div class="pdf-container" style="height: 500px;">
|
104 |
-
# <embed class="pdfobject" type="application/pdf" title="Modified PDF" src="data:application/pdf;base64,{base64_pdf}" style="width: 100%; height: 100%;">
|
105 |
-
# </div>
|
106 |
-
# """
|
107 |
-
|
108 |
# Compare Logic implementation
|
109 |
if compare:
|
110 |
col1, col2, col3 = st.columns(3)
|
@@ -115,34 +99,32 @@ with tab1:
|
|
115 |
col1, col2 = st.columns([1, 1], gap="small")
|
116 |
with col1:
|
117 |
with st.container(border = True):
|
118 |
-
st.markdown("<div style='text-align: center;'><strong>Original PDF viewer</strong></div>", unsafe_allow_html=True)
|
119 |
-
st.markdown(original_display, unsafe_allow_html=True)
|
|
|
120 |
with col2:
|
121 |
with st.container(border = True):
|
122 |
st.markdown("<div style='text-align: center;'><strong>Fastified PDF viewer</strong></div>", unsafe_allow_html=True)
|
123 |
-
st.markdown(pdf_display, unsafe_allow_html=True)
|
|
|
124 |
|
125 |
-
# Browser Cache Note
|
126 |
-
st.markdown(f"""
|
127 |
-
|
128 |
-
|
129 |
-
|
130 |
-
|
131 |
else:
|
132 |
-
# No Comparisons
|
133 |
col1, col2, col3 = st.columns(3)
|
134 |
-
with
|
135 |
st.download_button(label="Download Fastified PDF", data=text_to_pdf_fastify(text), file_name='output.pdf', mime='application/pdf')
|
136 |
-
with st.container(
|
137 |
-
|
138 |
-
st.markdown(
|
|
|
|
|
139 |
|
140 |
-
# Browser Cache Note
|
141 |
-
st.markdown(f"""
|
142 |
-
<div style='background-color: #FFD580; border-radius: 5px;'>
|
143 |
-
<p style='color: black;'><strong>Note</strong> - {note_text}</p>
|
144 |
-
</div>
|
145 |
-
""", unsafe_allow_html=True)
|
146 |
|
147 |
# Added support for PDFs having text
|
148 |
with tab2:
|
@@ -157,34 +139,6 @@ with tab2:
|
|
157 |
with st.spinner("Processing"):
|
158 |
text = pdf_extract_text(uploaded_file)
|
159 |
|
160 |
-
# Generating base64 encoded text bytes for PDF rendering
|
161 |
-
original_pdf = b64encode(text_to_pdf(text)).decode("utf-8")
|
162 |
-
base64_pdf = b64encode(text_to_pdf_fastify(text)).decode("utf-8")
|
163 |
-
|
164 |
-
# Embedding the PDFs in the HTML
|
165 |
-
original_display = f'<embed src="data:application/pdf;base64,{original_pdf}" width = "100%" height = 600 type="application/pdf" download="original.pdf">'
|
166 |
-
pdf_display = f'<embed src="data:application/pdf;base64,{base64_pdf}" width = "100%" height = 600 type="application/pdf" download="Modified.pdf">'
|
167 |
-
|
168 |
-
|
169 |
-
# original_display = f"""<embed class="pdfobject" type="application/pdf" title="Original PDF" src="data:application/pdf;base64,{original_pdf}" style=" width: 100%; height: 150%;">"""
|
170 |
-
# pdf_display = f"""<embed class="pdfobject" type="application/pdf" title="Modified PDF" src="data:application/pdf;base64,{base64_pdf}" style=" width: 100%; height: 150%;">"""
|
171 |
-
|
172 |
-
# original_display = f'<iframe src="data:application/pdf;base64,{original_pdf}" width = "100%" height = 600 type="application/pdf" download="original.pdf"></iframe>'
|
173 |
-
# pdf_display = f'<iframe src="data:application/pdf;base64,{base64_pdf}" width = "100%" height = 600 type="application/pdf" download="Modified.pdf"></iframe>'
|
174 |
-
|
175 |
-
# original_display = f"""
|
176 |
-
# <div class="pdf-container" style="height: 500px;">
|
177 |
-
# <embed class="pdfobject" type="application/pdf" title="Modified PDF" src="data:application/pdf;base64,{original_pdf}" style="width: 100%; height: 100%;">
|
178 |
-
# </div>
|
179 |
-
# """
|
180 |
-
# pdf_display = f"""
|
181 |
-
# <div class="pdf-container" style="height: 500px;">
|
182 |
-
# <embed class="pdfobject" type="application/pdf" title="Modified PDF" src="data:application/pdf;base64,{base64_pdf}" style="width: 100%; height: 100%;">
|
183 |
-
# </div>
|
184 |
-
# """
|
185 |
-
|
186 |
-
|
187 |
-
|
188 |
# Compare Logic implementation
|
189 |
if compare:
|
190 |
col1, col2, col3 = st.columns(3)
|
@@ -193,33 +147,36 @@ with tab2:
|
|
193 |
|
194 |
# Side by Side comparison
|
195 |
col1, col2 = st.columns([1, 1], gap="small")
|
|
|
196 |
with col1:
|
197 |
with st.container(border = True):
|
198 |
st.markdown("<div style='text-align: center;'><strong>Original PDF viewer</strong></div>", unsafe_allow_html=True)
|
199 |
-
|
200 |
with col2:
|
201 |
with st.container(border = True):
|
202 |
st.markdown("<div style='text-align: center;'><strong>Fastified PDF viewer</strong></div>", unsafe_allow_html=True)
|
203 |
-
st.markdown(pdf_display, unsafe_allow_html=True)
|
204 |
-
|
205 |
-
|
206 |
-
|
207 |
-
|
208 |
-
|
209 |
-
|
|
|
210 |
else:
|
211 |
# No Comparison
|
212 |
col1, col2, col3 = st.columns(3)
|
213 |
-
with
|
214 |
st.download_button(label="Download Fastified PDF", data=text_to_pdf_fastify(text), file_name='output.pdf', mime='application/pdf')
|
215 |
-
with st.container(border = True):
|
216 |
-
st.markdown("<div style='text-align: center;'><strong>Fastified PDF viewer</strong></div>", unsafe_allow_html=True)
|
217 |
-
st.markdown(pdf_display, unsafe_allow_html=True)
|
218 |
|
219 |
-
|
220 |
-
|
221 |
-
|
222 |
-
|
223 |
-
|
224 |
-
|
|
|
|
|
|
|
|
|
225 |
|
|
|
1 |
+
import warnings
|
2 |
+
warnings.filterwarnings("ignore")
|
3 |
import streamlit as st
|
4 |
from PyPDF2 import PdfReader
|
5 |
from concurrent.futures import ThreadPoolExecutor
|
|
|
7 |
from fpdf import FPDF
|
8 |
import io, string, re, math
|
9 |
from io import StringIO
|
10 |
+
from streamlit_pdf_viewer import pdf_viewer
|
11 |
+
#import deepcopy
|
12 |
|
13 |
# Importing the Fastify Class
|
14 |
from fast_reader import Fastify_Reader
|
15 |
|
16 |
+
def text_to_binary(text):
|
17 |
+
return ''.join(bin(ord(char))[2:].zfill(8) for char in text)
|
18 |
+
|
19 |
+
|
20 |
def pdf_extract_text(pdf_docs):
|
21 |
'''
|
22 |
Basic function for extracting text from the PDFs
|
|
|
28 |
text += page.extract_text()
|
29 |
return text
|
30 |
|
31 |
+
def text_to_pdf_fastify(txt):
|
32 |
'''
|
33 |
Basic function to apply fastification on the input text and convert it to bytes for PDF rendering
|
34 |
'''
|
35 |
+
text = (txt + '.')[:-1]
|
36 |
# Applying the Fastify Logic
|
37 |
bold_text = Fastify_Reader(text).fastify()
|
38 |
bold_text = bold_text.encode('latin-1', 'ignore').decode('latin-1') #since fpdf works with latin-1 encoding
|
|
|
44 |
pdf.multi_cell(0, 10, txt = bold_text, markdown=True)
|
45 |
return bytes(pdf.output())
|
46 |
|
47 |
+
def text_to_pdf(txt):
|
48 |
'''
|
49 |
Basic function on the input text and convert it to bytes for PDF rendering
|
50 |
'''
|
51 |
+
text = (txt + '.')[:-1]
|
52 |
text = text.encode('latin-1', 'ignore').decode('latin-1') #since fpdf works with latin-1 encoding
|
53 |
# Creating the PDF
|
54 |
pdf = FPDF()
|
|
|
89 |
with st.spinner("Processing"):
|
90 |
text = user_input
|
91 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
92 |
# Compare Logic implementation
|
93 |
if compare:
|
94 |
col1, col2, col3 = st.columns(3)
|
|
|
99 |
col1, col2 = st.columns([1, 1], gap="small")
|
100 |
with col1:
|
101 |
with st.container(border = True):
|
102 |
+
st.markdown("<div style='text-align: center;'><strong>Original PDF viewer</strong></div>", unsafe_allow_html=True)
|
103 |
+
# st.markdown(original_display, unsafe_allow_html=True)
|
104 |
+
pdf_viewer(input = text_to_pdf(text), width = 600)
|
105 |
with col2:
|
106 |
with st.container(border = True):
|
107 |
st.markdown("<div style='text-align: center;'><strong>Fastified PDF viewer</strong></div>", unsafe_allow_html=True)
|
108 |
+
# st.markdown(pdf_display, unsafe_allow_html=True)
|
109 |
+
pdf_viewer(text_to_pdf_fastify(text), width = 600)
|
110 |
|
111 |
+
# # Browser Cache Note
|
112 |
+
# st.markdown(f"""
|
113 |
+
# <div style='background-color: #FFD580; border-radius: 5px;'>
|
114 |
+
# <p style='color: black;'><strong>Note</strong> - {note_text}</p>
|
115 |
+
# </div>
|
116 |
+
# """, unsafe_allow_html=True)
|
117 |
else:
|
118 |
+
# # No Comparisons
|
119 |
col1, col2, col3 = st.columns(3)
|
120 |
+
with col1:
|
121 |
st.download_button(label="Download Fastified PDF", data=text_to_pdf_fastify(text), file_name='output.pdf', mime='application/pdf')
|
122 |
+
with st.container():
|
123 |
+
|
124 |
+
st.markdown("<div><strong>Fastified PDF viewer</strong></div>", unsafe_allow_html=True)
|
125 |
+
# st.markdown(pdf_display, unsafe_allow_html=True)
|
126 |
+
pdf_viewer(text_to_pdf_fastify(text), width = 600)
|
127 |
|
|
|
|
|
|
|
|
|
|
|
|
|
128 |
|
129 |
# Added support for PDFs having text
|
130 |
with tab2:
|
|
|
139 |
with st.spinner("Processing"):
|
140 |
text = pdf_extract_text(uploaded_file)
|
141 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
142 |
# Compare Logic implementation
|
143 |
if compare:
|
144 |
col1, col2, col3 = st.columns(3)
|
|
|
147 |
|
148 |
# Side by Side comparison
|
149 |
col1, col2 = st.columns([1, 1], gap="small")
|
150 |
+
|
151 |
with col1:
|
152 |
with st.container(border = True):
|
153 |
st.markdown("<div style='text-align: center;'><strong>Original PDF viewer</strong></div>", unsafe_allow_html=True)
|
154 |
+
pdf_viewer(text_to_pdf(text), width = 600)
|
155 |
with col2:
|
156 |
with st.container(border = True):
|
157 |
st.markdown("<div style='text-align: center;'><strong>Fastified PDF viewer</strong></div>", unsafe_allow_html=True)
|
158 |
+
# st.markdown(pdf_display, unsafe_allow_html=True)
|
159 |
+
pdf_viewer(text_to_pdf_fastify(text), width = 600)
|
160 |
+
# # Browser Cache Note
|
161 |
+
# st.markdown(f"""
|
162 |
+
# <div style='background-color: #FFD580; border-radius: 5px;'>
|
163 |
+
# <p style='color: black;'><strong>Note</strong> - {note_text}</p>
|
164 |
+
# </div>
|
165 |
+
# """, unsafe_allow_html=True)
|
166 |
else:
|
167 |
# No Comparison
|
168 |
col1, col2, col3 = st.columns(3)
|
169 |
+
with col1:
|
170 |
st.download_button(label="Download Fastified PDF", data=text_to_pdf_fastify(text), file_name='output.pdf', mime='application/pdf')
|
|
|
|
|
|
|
171 |
|
172 |
+
with st.container():
|
173 |
+
st.markdown("<div><strong>Fastified PDF viewer</strong></div>", unsafe_allow_html=True)
|
174 |
+
pdf_viewer(text_to_pdf_fastify(text), width = 500)
|
175 |
+
|
176 |
+
# # Browser Cache Note
|
177 |
+
# st.markdown(f"""
|
178 |
+
# <div style='background-color: #FFD580; border-radius: 5px;'>
|
179 |
+
# <p style='color: black;'><strong>Note</strong> - {note_text}</p>
|
180 |
+
# </div>
|
181 |
+
# """, unsafe_allow_html=True)
|
182 |
|
requirements.txt
CHANGED
@@ -1,2 +1,3 @@
|
|
1 |
PyPDF2==3.0.1
|
2 |
fpdf2==2.7.8
|
|
|
|
1 |
PyPDF2==3.0.1
|
2 |
fpdf2==2.7.8
|
3 |
+
streamlit-pdf-viewer==0.0.7
|