Initial Commit

.gitignore

@@ -0,0 +1 @@
+*.pyc

app.py

@@ -0,0 +1,87 @@
+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
+
+#importing the 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):
+
+    bold_text = Fastify_Reader(text).fastify()
+    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):
+    pdf = FPDF()
+    pdf.add_page()
+    pdf.set_font("Arial", size = 12)
+    pdf.multi_cell(0, 10, txt = text, markdown=True)
+    return bytes(pdf.output())
+
+st.set_page_config(layout="wide")
+st.header("fastify Reader :books:")
+tab1, tab2= st.tabs(["PDF file", "Text File"])
+
+with tab1:
+    st.header("PDF File")
+    uploaded_file = st.file_uploader("Upload a PDF file", type="pdf", accept_multiple_files=True)
+    
+    if st.button("Submit", key="pdf"):
+            with st.spinner("Processing"):
+                    text = pdf_extract_text(uploaded_file)
+                    
+                    original_pdf = b64encode(text_to_pdf(text)).decode("utf-8")
+                    base64_pdf = b64encode(text_to_pdf_fastify(text)).decode("utf-8")
+
+                    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">'
+                    
+                    col1, col2 = st.columns([1, 1], gap="small")
+                    with col1:
+                        with st.container(border = True):
+                            st.markdown(original_display, unsafe_allow_html=True)
+                    with col2:
+                        with st.container(border = True):
+                            st.markdown(pdf_display, unsafe_allow_html=True)
+                    st.download_button(label="Download as PDF", data=text_to_pdf_fastify(text), file_name='output.pdf', mime='application/pdf')
+    
+
+with tab2:
+        st.header("Input Text")
+        user_input = st.text_input("Enter some text")
+        
+        if st.button("Submit", key="input-text"):
+            with st.spinner("Processing"):
+                text = user_input
+
+                original_pdf = b64encode(text_to_pdf(text)).decode("utf-8")
+                base64_pdf = b64encode(text_to_pdf_fastify(text)).decode("utf-8")
+
+                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">'
+                
+                col1, col2 = st.columns([1, 1], gap="small")
+                with col1:
+                    with st.container(border = True):
+                        st.markdown(original_display, unsafe_allow_html=True)
+                with col2:
+                    with st.container(border = True):
+                        st.markdown(pdf_display, unsafe_allow_html=True)
+                st.download_button(label="Download as PDF", data=text_to_pdf_fastify(text), file_name='output.pdf', mime='application/pdf')

fast_reader.py

@@ -0,0 +1,38 @@
+import string
+
+class Fastify_Reader:
+	'''
+	Class to implement the fastify Fast Reader. The intention is to enable the users to 
+	read text faster by bolding some parts of the words.
+	'''
+	def __init__(self, data):
+		self.text = data
+		self.offset_factor = 1.6
+	
+	def _get_offset(self, word: str):
+		word_stripped = word.translate(str.maketrans('', '', string.punctuation))
+		fixation = int(len(word_stripped) / self.offset_factor)
+		return fixation if fixation != 0 else 1
+	
+	def fastify_word(self, word: str):
+		if '-' in word:
+			part_1, part_2 = word.split('-')
+			part_1 = f"**{part_1[:self._get_offset(part_1)]}**{part_1[self._get_offset(part_1):]}"
+			part_2 = f"**{part_2[:self._get_offset(part_2)]}**{part_2[self._get_offset(part_2):]}"
+			fastify_word = f"{part_1}-{part_2}"
+		else:
+			fastify_word = f"**{word[:self._get_offset(word)]}**{word[self._get_offset(word):]}"
+		return fastify_word
+	
+	def fastify_line(self, line: str):
+		fastify_line = ""
+		for word in line.split():
+			fastify_line += f"{self.fastify_word(word)} "
+		return fastify_line.strip()
+	
+	def fastify(self):
+		fastify_text = ""
+		for line in self.text.split('\n'):
+			fastify_text += f"{self.fastify_line(line)}\n"
+		fastify_text = fastify_text.replace("****","")
+		return fastify_text.strip()

requirements.txt

@@ -0,0 +1,2 @@
+PyPDF2==3.0.1
+fpdf2==2.7.8