diff --git a/app.py b/app.py
index 45fc505..78cb723 100644
--- a/app.py
+++ b/app.py
@@ -2,6 +2,9 @@
 from collections import Counter
 import re
 import json
+from extract import extracted_email, extracted_phoneNumber, extracted_name, extracted_education, extracted_wrkexp, extracted_summary
+import os
+from pypdf import PdfReader
 
 app = Flask(__name__)
 
@@ -16,30 +19,44 @@ def editor():
     return render_template('editor.html')
 
 
-@app.route('/submit', methods=['Post'])
+UPLOAD_FOLDER = 'uploads'
+os.makedirs(UPLOAD_FOLDER, exist_ok=True)
+app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
+
+@app.route('/upload', methods=['POST'])
+def upload_file():
+    file = request.files['file']
+    if file:
+        file_path = os.path.join(app.config['UPLOAD_FOLDER'], file.filename)
+        file.save(file_path)
+        reader = PdfReader(file)
+        for i in range(len(reader.pages)):
+            page = reader.pages[i]
+            print(page.extract_text())
+        return jsonify({'message': 'File uploaded successfully', 'file_path': file_path})
+    return jsonify({'error': 'Invalid file type. Only PDFs are allowed.'})
+
+
+@app.route('/submit', methods=['POST'])
 def submit_data():
+
     data = request.json
-    words = re.findall(r'\b\w+\b', data.lower())
-    word_counts = Counter(words)
-    # print(f'Word count: {word_counts}')
-    email = extracted_email(data)
-    phoneNumber = extracted_phoneNumber(data)
-    print(f'Data: {data}, Email: {email}, Phone: {phoneNumber}')
+    #words = re.findall(r'\b\w+\b', data.lower())
+    #word_counts = Counter(words)
+    if isinstance(data, list):
+        datastr = ' '.join(data)
+    email = extracted_email(datastr)
+    phoneNumber = extracted_phoneNumber(datastr)
+    '''
+    name = extracted_name(datastr)
+    education = extracted_education(data)
+    work = extracted_wrkexp(data)
+    summary = extracted_summary(data)
+    #print(f'Data: {data}: , Email:{email} , Phone:{phoneNumber} , Name: {name}, Education: {education}, Summary : {summary}, Work Experience : {work}')
+    '''
     return jsonify({"received_data": data, "email": email, "phone": phoneNumber})
 
 
-def extracted_email(data):
-    email = re.findall("[a-zA-Z0-9!#$%&'*+/=?^_`{|}~-]+@[a-z]+.{4}", data.lower())
-    if email:
-        return email[0]
-    return None
-
-
-def extracted_phoneNumber(data):
-    phone = re.findall(r'\d{3}\W?\d{3}\W?\d{4}', data.lower())
-    if phone:
-        return phone[0]
-    return None
 
 @app.route("/generate", methods=["GET"])
 def generate_pdf():
diff --git a/extract.py b/extract.py
new file mode 100644
index 0000000..2861169
--- /dev/null
+++ b/extract.py
@@ -0,0 +1,76 @@
+
+import re
+
+
+
+def extracted_email(data):
+    email = re.findall("[a-zA-Z0-9!#$%&'*+/=?^_`{|}~-]+@[a-z]+.{4}", data.lower())
+    if email:
+        return email[0]
+    return None
+
+
+def extracted_phoneNumber(data):
+    phone = re.findall(r'\d{3}\W?\d{3}\W?\d{4}', data.lower())
+    if phone:
+        return phone[0]
+    return None
+
+
+def extracted_name(data):
+    ext_name = []
+    pattern = r'\b[A-Z][a-z]*\b|\b[A-Z]+\b'
+    matches = list(re.finditer(pattern, data))
+    if matches:
+        for i in range(2):
+            ext_name.append(matches[i].group())
+        return ext_name
+    return None
+
+
+def extracted_education(data):
+    # logic of this function, collect 10 elements after the word education appears
+    cleaned_data = [item.strip().lower() for item in data]
+    ext_education = []
+    starting_i = -1
+    for i in range(len(cleaned_data) - 1):
+        if cleaned_data[i] == 'education':
+            starting_i = i
+    if starting_i != -1:
+        for j in range(starting_i, (starting_i + 20), 1):
+            ext_education.append(cleaned_data[j])
+        return ext_education
+    return None
+
+
+def extracted_wrkexp(data):
+    # logic of this function, collect 10 elements after the word work experince appears
+    cleaned_data = [item.strip().lower() for item in data]
+    ext_work = []
+    starting_i = -1
+    for i in range(len(cleaned_data) - 1):
+        if ((cleaned_data[i] == 'work' and cleaned_data[i + 1] == 'experience') or
+                cleaned_data[i] == 'employment' or cleaned_data[i] == "experience"):
+            starting_i = i
+    if starting_i != -1:
+        for j in range(starting_i, (starting_i + 10), 1):
+            ext_work.append(cleaned_data[j])
+        return ext_work
+    return None
+
+
+def extracted_summary(data):
+    # logic of this function, collect 10 elements after summary or professional summary appears
+    ext_sum = []
+    starting_i = -1
+    for i in range(len(data) - 1):
+        if data[i].strip().lower() == 'professional summary':
+            starting_i = i
+
+    if starting_i != -1:
+        for j in range(starting_i + 1, (starting_i + 10), 1):
+            ext_sum.append(data[j])
+        return ext_sum
+    else:
+        return None
+
diff --git a/numOfIslands.py b/numOfIslands.py
new file mode 100644
index 0000000..7bdca3d
--- /dev/null
+++ b/numOfIslands.py
@@ -0,0 +1,177 @@
+
+
+grid = [
+    ["1", "1", "1", "1"],
+    ["1", "1", "0", "0"],
+    ["0", "0", "0", "1"],
+    ["0", "0", "1", "1"]
+]
+
+
+
+
+
+
+def enclaves(grid):
+    enclave = 0
+    for r in range(len(grid)):
+        for c in range(len(grid[r])):
+            if grid[r][c]= "1"
+
+
+
+
+
+'''
+
+def numOfIslands(grid):
+    islands = 0
+    maxislandsize = 0
+    for r in range(len(grid)):
+        for c in range(len(grid[r])):
+            if grid[r][c] == "1":
+                islandsize = dfs(grid,r,c)
+                islands += 1
+                if islandsize > maxislandsize:
+                    maxislandsize = islandsize
+    return islands, maxislandsize
+
+
+def dfs(grid,row,col) -> int:
+
+    if row < 0 or col < 0 or row >= len(grid) or col >= len(grid[row]) or grid[row][col] == "0":
+        return 0
+
+    size = 1
+    grid[row][col] = "0"
+    size +=dfs(grid, row - 1, col)
+    size +=dfs(grid,row+1, col)
+    size +=dfs(grid,row,col+1)
+    size +=dfs(grid,row,col-1)
+    return size
+
+
+print(numOfIslands(grid))
+
+
+
+'''
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+def numOfIslands(grid):
+    island = 0
+    for r in range(len(grid)):
+        for c in range(len(grid[r])):
+            if grid[r][c] == "1":
+                bfs(grid, r, c)
+                island += 1
+    return island
+
+
+def dfs(grid, row, col):
+    if row < 0 or col < 0 or row >= len(grid) or col >= len(grid[row]) or grid[row][col] == "0":
+        return
+    grid[row][col] = "0"
+    #transverse_stack = [(row-1, col),(row+1,col),(row,col+1),(row,col-1)] used recursive as oppose to iterative approach
+    dfs(grid, row-1, col)
+    dfs(grid, row, col-1)
+    dfs(grid,row+1,col)
+    dfs(grid,row, col+1)
+
+'''
+def bfs(grid, row,col):
+    que = deque([(row, col)])
+    while que:
+        r,c = popleft()
+
+        if row > 0 and col > 0 and row <= len(grid) and col <= len(grid[0]) and grid[row][col] == "0":
+            continue
+
+    grid[r][c] = "0"
+
+    bfs.append((row, col + 1))
+    bfs.append(grid, row, col - 1)
+    bfs.append(grid, row + 1, col)
+    bfs.append(grid, row - 1, col)
+
+
+
+'''
+
+
+
+
+#print(numOfIslands(grid))
+
+'''
\ No newline at end of file
diff --git a/numOfIslandsDfs.py b/numOfIslandsDfs.py
new file mode 100644
index 0000000..15d69e3
--- /dev/null
+++ b/numOfIslandsDfs.py
@@ -0,0 +1,35 @@
+
+grid = [
+    ["1", "1", "1", "1"],
+    ["1", "1", "0", "0"],
+    ["0", "0", "0", "1"],
+    ["0", "0", "1", "1"]
+]
+
+
+
+def numOfIslands(grid):
+    island = 0
+    disjointed_sets = []
+    for r in range(len(grid)):
+        for c in range(len(grid[r])):
+            if grid[r][c] != '0':
+                x = set()
+                dfs(grid, r, c, x)
+                island += 1
+                disjointed_sets.append(x)
+    return disjointed_sets
+
+
+def dfs(grid, row, col, seen):
+    if row < 0 or col < 0 or row >= len(grid) or col >= len(grid[row]) or grid[row][col] == "0":
+        return
+    seen.add((row,col))
+    grid[row][col] = "0"
+    dfs(grid, row-1, col, seen)
+    dfs(grid, row, col-1, seen)
+    dfs(grid,row+1,col, seen)
+    dfs(grid,row, col+1, seen)
+
+
+
diff --git a/static/script.js b/static/script.js
index ed3c869..23b1f0c 100644
--- a/static/script.js
+++ b/static/script.js
@@ -1,5 +1,6 @@
 const fileInput = document.getElementById("myFile");
 
+fileInput.addEventListener("change", uploadFile);
 fileInput.addEventListener("change", handleFiles);
 
 function handleFiles(event) {
@@ -13,7 +14,7 @@ function handleFiles(event) {
             function(pdf) {
                 let textArray = [];
                 let promises = [];
-                for (let i = 1; i <= pdf.numPages; i++) {
+                for (let i = 0; i < pdf.numPages; i++) {
                     promises.push(extractText(pdf, i, textArray));
                 }
                 Promise.all(promises).then(() => {
@@ -21,6 +22,7 @@ function handleFiles(event) {
                 });
             });
     };
+
     fileReader.readAsArrayBuffer(file);
 }
 
@@ -38,3 +40,16 @@ function extractText(pdf, pageNumber, textArray) {
             console.error("Error reading file", error);
         });
 }
+
+function uploadFile(event){
+    const file = event.target.files[0];
+    const formData = new FormData();
+    formData.append('file', file);
+
+        fetch('/upload',{
+            method:'POST',
+            body: formData,
+        }).catch((error)=>{
+            console.error("Error:", error)
+        });
+}
\ No newline at end of file
diff --git a/structured_json.py b/structured_json.py
new file mode 100644
index 0000000..88df5ac
--- /dev/null
+++ b/structured_json.py
@@ -0,0 +1,157 @@
+import json
+from par import *
+data = {
+  "version": "0.0.1",
+  "format": "orf",
+  "meta": {
+    "name": "John Doe",
+    "sort": "chronological",
+    "sort_order": "asc",
+    "tags": [
+      "tech",
+      "software_development",
+      "backend"
+    ]
+  },
+  "data": {
+    "personal": {
+      "name": "John Doe",
+      "phone_number": "8009001000",
+      "country_code": "+1",
+      "address_line_1": "null",
+      "address_line_2": "null",
+      "city": "Raleigh",
+      "state": "NC",
+      "zip": "null",
+      "country": "us",
+      "email": "john.doe@email.com",
+      "url_linkedin": "null",
+      "url_portfolio": "null",
+      "url_website": "null",
+      "url_other": [
+        {
+          "text": "Facebook",
+          "url": "facebook.com/user"
+        },
+        {
+          "text": "Dribble",
+          "url": "dribble.com/user"
+        }
+      ]
+    },
+    "summary": "to obtain employment in XYZ field.",
+    "education": [
+      {
+        "degree_level": "bachelors",
+        "degree_title": "B.A.",
+        "completed": "true",
+        "institution": "Earlham College",
+        "major": "Computer Science",
+        "minor": "null",
+        "concentration": "null",
+		"gpa": "3.99",
+		"gpa_scale": "4.00",
+        "institution_city": "Richmond",
+        "institution_state": "IN",
+        "institution_zip": "47374",
+        "institution_country": "us",
+        "start_day": 14,
+        "start_month": 9,
+        "start_year": 2014,
+        "end_day": 6,
+        "end_month": 5,
+        "end_year": 2018
+      },
+      {
+        "degree_level": "masters",
+        "degree_title": "M.S.",
+        "completed": "true",
+        "institution": "North Carolina State University",
+        "major": "Computer Engineering",
+        "minor": "null",
+        "concentration": "Computer Architecture & Systems",
+		"gpa": "3.99",
+		"gpa_scale": "4.00",
+        "institution_city": "Raleigh",
+        "institution_state": "NC",
+        "institution_zip": "27607",
+        "institution_country": "us",
+        "start_day": 14,
+        "start_month": 9,
+        "start_year": 2021,
+        "end_day": 6,
+        "end_month": 5,
+        "end_year": 2023
+      }
+    ],
+    "experience": [
+      {
+        "title": "Software Developer",
+        "employer": "XYZ Solutions, Inc",
+        "employer_city": "Lake Villa",
+        "employer_state": "IL",
+        "employer_zip": "60046",
+        "employer_country": "us",
+        "employer_phone_number": "null",
+        "description": [
+		  "Led a major REST API from development to production. Scheduled tasks and sprint goals based on team needs following Agile methods.",
+		  "Replaced 200+ database tables with a new authorization service, achieving greater developer efficiency, lower maintenance cost, and fewer security incidents",
+		  "Reduced response times by 95% (backend: 5s - .5s, frontend: 2m - 0.3s) after detailed performance analysis. Planned and led the execution of an optimization sprint.",
+		  "Reduced client onboarding time from days to hours after migrating to reproducible, version-controlled Infrastructure-as-code solutions.",
+		  "Enabled faster error detection, bugfixes, and reduced downtime through detailed exception tracking, stack trace analysis, and infrastructure health monitoring."
+        ]
+      }
+    ],
+    "skill": [
+      {
+        "name": "c",
+        "proficiency_level": "beginner",
+        "catogory": "programmaing language"
+      },
+      {
+        "name": "c++",
+        "proficiency_level": "intermediate",
+        "category": "programming language"
+      }
+    ],
+    "publication": [
+      {
+        "title": "a groundbreaking research",
+        "url": "https://nature.com/next-einstein",
+        "year": 2018,
+        "credits": "Doe, J., et al",
+        "citation_format": "apa"
+      },
+      {
+        "title": "Yet Another groundbreaking research",
+        "url": "https://nature.com/next-einstein",
+        "year": 2021,
+        "credits": "Doe, J., et al",
+        "citation_format": "apa"
+      }
+    ],
+    "projects": [
+      {
+        "title": "Operating System Kernel Functionalities in XINU Microkernel",
+        "sub_title": "null",
+        "url": "https://github.com/salekinsirajus/realxinu",
+        "description": [
+			"Implemented scheduling algorithms (lottery, MLFQ), Locks (Spin, Active, Priority Inversion), and fork() system call.",
+			"Used C and Assembly"
+        ]
+      },
+      {
+        "title": "Standard for Machine-Readable Resume",
+        "sub_title": "null",
+        "url": "https://github.com/TheOpenResumeProject/OpenResume",
+        "description": [
+          "Came up with a standard so that the data can be separated from formatting",
+          "Built a proof-of-concept using Flask, Python, and JavaScript"
+        ]
+      }
+    ]
+  }
+}
+
+print(data['data']['education'][0]['degree_level'])
+#print(data['meta']["name"])
\ No newline at end of file
diff --git a/templates/editor.html b/templates/editor.html
index 126470d..5aabc30 100644
--- a/templates/editor.html
+++ b/templates/editor.html
@@ -12,12 +12,13 @@ <h1>File Information</h1>
         <p id="fileName">File name will be displayed here</p>
         <div id='pdfContent'></div>
         <button id = 'sendToBackEnd'> Send Data </button>
-
         <div>
             <h3> Extracted Information</h3>
             <p> Email extracted: <span id = 'extractedEmail'></span></p>
             <p> Phone Number extracted:  <span id = 'extractedPhone'></span></p>
         </div>
+
+        
         <script>
             const fileData = sessionStorage.getItem("content");
             const fileContentElement = document.getElementById('pdfContent');
@@ -26,18 +27,16 @@ <h3> Extracted Information</h3>
             if (fileData){
                 fileContentElement.textContent = `Uploaded file's Content: ${JSON.parse(fileData)}`;
                 //fileContentElement.textContent = `Uploaded file's Content: ${fileData}`;
-            
             } else {
                 fileContentElement.textContent = 'No file uploaded';
             }
-
             document.getElementById('sendToBackEnd').addEventListener('click', function(){
                 fetch('/submit',{
                     method: 'POST',
                     headers: {
                         'Content-Type' : 'application/json'
                     },
-                    body: JSON.stringify(fileData) 
+                    body: fileData 
                 })
                 .then(response=> response.json())
                 .then(data => {
diff --git a/trie_pratice.py b/trie_pratice.py
new file mode 100644
index 0000000..0fef141
--- /dev/null
+++ b/trie_pratice.py
@@ -0,0 +1,350 @@
+import PyPDF2
+import matplotlib.pyplot as plt
+from win32gui import FlashWindowEx
+import pdfplumber
+from numOfIslandsDfs import numOfIslands
+import pandas as pd
+import matplotlib.pyplot as plt
+from collections import Counter
+
+
+
+def pdf_opener(path):
+    words = []
+    with pdfplumber.open(path) as pdf:
+        for page in pdf.pages:
+            text = page.extract_text()
+            if text:
+                #text = text.replace("\n", " ")  # Convert newlines to spaces
+                words.append(text.strip())
+    return words
+
+
+conjunctions = [
+    "the", "and", "but", "or", "nor", "for", "yet", "so", "of",
+    "although", "because", "since", "unless", "while", "whereas", "though",
+    "if", "when", "whenever", "where", "wherever", "after", "before",
+    "until", "once", "as", "than", "that", "whether", "even", "though",
+    "provided", "lest", "in", "order", "to", "such", "which", "who",
+    "whose", "whom", "whomever", "whereby", "therefore", "thus", "hence",
+    "moreover", "however", "furthermore", "nevertheless", "consequently",
+    "accordingly", "nonetheless", "besides", "otherwise", "meanwhile",
+    "subsequently", "notwithstanding", "via", "by", "on", "through",
+    "within", "outside", "inside", "between", "among", "throughout",
+    "along", "beyond", "whereupon", "henceforth", "per", "amid", "about",
+    "at", "over", "under", "considering", "concerning", "regarding",
+    "following", "based", "due", "owing", "with", "regard", "pertaining"
+]
+education_words = [
+    "education", "degree", "diploma", "certificate", "certification",
+    "bachelor", "bachelors", "B.S.", "B.S", "M.S.", "M.S", "master", "masters", "doctorate", "phd",
+    "associate", "associates", "major", "minor", "gpa", "cgpa", "grade",
+    "summa", "cum", "laude", "magna", "dean", "honor", "scholarship",
+    "university", "college", "high", "school", "academy", "graduation",
+    "graduated", "expected", "year", "class", "relevant", "coursework",
+    "concentration", "program", "training", "continuing", "professional",
+    "development", "workshops", "seminars", "transcript", "credits",
+    "units", "research", "thesis", "dissertation", "capstone", "project",
+    "extracurricular", "activities", "student", "organizations", "society",
+    "merit", "distinction", "enrollment", "matriculation", "undergrad",
+    "postgraduate", "vocational", "technical", "apprenticeship",
+    "internship", "fellowship", "residency", "mooc", "bootcamp",
+    "elearning", "certifications", "licensure", "institution",
+    "distance", "learning", "stem", "humanities", "business",
+    "engineering", "medical", "law", "psychology", "finance",
+    "accounting", "arts", "science", "technology", "computer",
+    "statistics", "math", "economics", "biology", "chemistry",
+    "physics", "political", "liberal", "communications", "journalism",
+    "literature", "philosophy", "pedagogy", "tesol", "esl", "bilingual",
+    "diversity", "instructional", "curriculum", "assessment", "special",
+    "student", "classroom", "management", "teaching", "professor",
+    "lecturer", "educator", "dean", "chancellor", "advisor", "counselor",
+    "may"
+]
+job_experience_words = [
+    "experience", "work", "employment", "job", "position", "role",
+    "title", "responsibilities", "duties", "achievements", "tasks",
+    "skills", "leadership", "management", "supervision", "collaboration",
+    "communication", "mentoring", "training", "coaching", "development",
+    "strategy", "execution", "performance", "growth", "results",
+    "improvement", "productivity", "innovation", "problem", "solving",
+    "decision", "making", "adaptability", "time", "organization",
+    "project", "deadlines", "clients", "customers", "stakeholders",
+    "vendors", "negotiation", "budget", "revenue", "sales", "marketing",
+    "operations", "technology", "software", "hardware", "engineering",
+    "design", "testing", "support", "helpdesk", "quality", "assurance",
+    "data", "analysis", "documentation", "research", "risk", "consulting",
+    "freelance", "internship", "contract", "temporary", "remote",
+    "onsite", "telecommute", "supervisor", "manager", "director",
+    "senior", "junior", "executive", "associate", "specialist",
+    "consultant", "coordinator", "lead", "head", "president", "founder",
+    "entrepreneur", "owner", "administrator", "trainer", "volunteer",
+    "intern", "entry", "mid", "senior", "contractor", "subcontractor",
+    "freelancer", "startup", "scaling", "cross", "global",
+    "regional", "national", "local", "networking", "client", "meetings",
+    "product", "development", "employee", "onboarding", "reviews",
+    "company", "policies", "kpis", "metrics", "analytics", "pipeline",
+    "crm", "customer", "support", "presentation"]
+
+objective_words = [
+    "seeking", "motivated", "goal", "oriented", "position",
+    "opportunity", "career", "growth", "utilize", "skills",
+    "experience", "contribute", "professional", "dynamic",
+    "challenging", "environment", "learning", "enhance",
+    "expand", "achieve", "success", "innovative", "passionate",
+    "aspiring", "advance", "dedicated", "entry", "results",
+    "driven", "adaptable", "problem", "solving", "leadership",
+    "teamwork", "strategic", "detail", "analytical", "creative",
+    "self", "motivated", "efficient", "people", "oriented",
+    "solution", "focused", "fast", "paced", "impactful",
+    "meaningful", "ambitious", "reliable", "hardworking",
+    "visionary", "excited", "eager", "learn", "proactive",
+    "resourceful", "customer", "focused", "deadline", "driven",
+    "hands", "strong", "work", "ethic", "thrives", "pressure"
+]
+
+'''
+
+education_words = [
+    "Education", "Degree", "Diploma", "Certificate", "Certification",
+    "Bachelor", "Bachelors", "Masters", "Master", "of", "Doctorate", "PhD", "Associates",
+    "Associate", "Major", "Minor", "May", "Dec", "December",
+    "GPA", "CGPA", "Honors", "Summa", "Cum", "Laude", "Magna", "Dean", "Scholarship",
+    "University", "College", "High", "School", "Institution", "Academy",
+    "Graduation", "Completed", "Expected", "Year", "Course", "Courses",
+    "Relevant", "Studies", "Field", "Concentration", "Program", "Training",
+    "Continuing", "Professional", "Development", "Workshops", "Seminars",
+    "Credits", "Units", "Transcript", "Research", "Thesis", "Dissertation",
+    "Capstone", "Project", "Study", "Subjects", "Extracurricular", "Activities",
+    "Organizations", "Clubs", "Societies", "Honor", "Roll", "Academic",
+    "Performance", "Achievement", "Awards", "Merit", "Distinction",
+    "Educational", "Background", "Alma", "Mater", "Enrollment", "Matriculation",
+    "Vocational", "Technical", "Apprenticeship", "Online", "Bootcamp",
+    "MOOC", "E-Learning", "Certifications", "Licensure", "Accredited",
+    "Institution", "Credits", "Internship", "Practicum", "Fellowship",
+    "Residency", "Postgraduate", "Undergraduate", "Doctoral", "Master’s",
+    "Bachelor’s", "Associate’s", "STEM", "Humanities", "Business",
+    "Engineering", "Medical", "Law", "Psychology", "Finance", "Accounting",
+    "Arts", "Science", "Technology", "Computer", "Information", "Systems",
+    "Leadership", "Data", "Analysis", "Statistics", "Math",
+    "Economics", "Biology", "Chemistry", "Physics", "Environmental", "Health",
+    "Social", "Sciences", "History", "Political", "Science", "Liberal",
+    "Studies", "Communications", "Journalism", "Literature", "Philosophy",
+    "Education", "Pedagogy", "Teaching", "TESOL", "ESL", "Bilingual",
+    "Multicultural", "Diversity", "Instructional", "Curriculum", "Assessment",
+    "Educational", "Policy", "Special", "Education", "Counseling", "Development",
+    "Learning", "Methodologies", "Strategies", "Student", "Engagement",
+    "Classroom", "Management", "Education", "Administration"
+]
+
+job_experience_words = [
+    "Experience", "Position", "Job", "Role", "Title", "Responsibilities",
+    "Duties", "Achievements", "Accomplishments", "Tasks", "Skills",
+    "Leadership", "Management", "Team", "Collaboration", "Communication",
+    "Supervision", "Mentoring", "Training", "Coaching", "Development",
+    "Strategy", "Execution", "Performance", "Growth", "Results",
+    "Improvement", "Efficiency", "Productivity", "Innovation", "Solutions",
+    "Problem-solving", "Decision-making", "Initiative", "Adaptability",
+    "Time Management", "Organization", "Project", "Project Management",
+    "Deadline", "Client", "Customer", "Vendor", "Stakeholder",
+    "Negotiation", "Budget", "Cost", "Revenue", "Sales", "Marketing",
+    "Product", "Service", "Operations", "Technology", "Software",
+    "Hardware", "IT", "Engineering", "Development", "Design", "Testing",
+    "Support", "Helpdesk", "Maintenance", "Analysis", "Data", "Reporting",
+    "Documentation", "Research", "Quality", "Compliance", "Risk",
+    "Strategy", "Consulting", "Customer Service", "Support", "Sales",
+    "Client Relations", "Salesforce", "Contract", "Freelance",
+    "Internship", "Part-time", "Full-time", "Temporary", "Remote",
+    "On-site", "Telecommute", "Job Description", "Task", "Function",
+    "Role", "Position", "Supervisor", "Manager", "Director",
+    "Senior", "Junior", "Executive", "Associate", "Specialist",
+    "Consultant", "Coordinator", "Lead", "Head", "President",
+    "Founder", "Entrepreneur", "Owner", "Team Lead", "Team Member",
+    "Assistant", "Administrator", "Trainer", "Trainer", "Supervisor",
+    "Volunteer", "Intern", "Entry-level", "Mid-level", "Senior-level",
+    "Supervisor", "Mentor", "Coach", "Consultant", "Founder",
+    "Executive", "Leader", "Entrepreneur", "Contractor", "Subcontractor",
+    "Freelancer", "Volunteer", "Start-up", "Scaling",
+    "Leadership Development", "Cross-functional", "Cross-team",
+    "Global", "Regional", "National", "Local", "Remote",
+    "Workshops", "Presentations", "Client Meetings", "Customer Engagement",
+    "Training", "Certifications", "Onboarding", "Employee Development",
+    "Company Policies", "Performance Review", "Satisfaction", "Feedback"
+]
+objective_words = [
+    "seeking", "motivated", "goal", "oriented", "position", "opportunity", "career",
+    "develop", "growth", "utilize", "skills", "experience", "contribute", "dynamic",
+    "professional", "challenging", "environment", "learning", "enhance", "expand",
+    "achieve", "success", "innovative", "passionate", "aspiring", "advance",
+    "dedicated", "entry-level", "results-driven", "adaptable", "problem-solving"
+]
+
+'''
+
+
+class TrieNode:
+    def __init__(self):  # constructor method
+        self.children = {}  # initiates a dictionary
+        self.endOfWord = 0  # attribute of the class
+
+    def insert(self, word: str, tag=None):
+        word = word.lower()
+        pointer = self
+        for char in word:  #for each character in word if that char already exists then it has a property which is the end of the word and is a number, add to that number the tag of the existing method
+            if char not in pointer.children:
+                pointer.children[char] = TrieNode()
+            pointer = pointer.children[char]
+        if pointer.endOfWord:
+            pointer.endOfWord = str(pointer.endOfWord) + str(tag)
+        else:
+            pointer.endOfWord = str(tag)
+
+    def search(self, word):
+        word = word.lower()
+        pointer = self
+        for char in word:
+            if char not in pointer.children:
+                return '0'
+            pointer = pointer.children[char]
+        return pointer.endOfWord
+
+
+trie = TrieNode()
+for words in education_words:
+    trie.insert(words, 1)
+for words in job_experience_words:
+    trie.insert(words, 2)
+for words in objective_words:
+    trie.insert(words, 3)
+for words in conjunctions:
+    trie.insert(words, 4)
+
+final_data_list = []
+fixed_data_list = []
+restored_list = []
+pages = pdf_opener('Fake_Resume_Jane_Doe.pdf')  #array of two strings
+process_lines = []
+for page in pages:
+    process_lines += page.split('\n')
+clean_lines = []
+for i in process_lines:
+    clean_lines.append(i.replace(",", ""))
+raw_words = []
+for line in clean_lines:
+    raw_words.append(line.split())
+mapped_words = []
+for line in raw_words:
+    mapping = []
+    fixed_data_list.append(line.copy())
+    #print(line)
+    for word in line:
+        result = trie.search(word)
+        mapping.append(result)
+    restored_list.append(mapping.copy())
+    mapped_words.append(mapping)
+    #print(mapping)
+
+IDsetNonZero = numOfIslands(mapped_words)
+data_table = []
+set_count = 0
+x_counter=0
+for elements in IDsetNonZero:
+    set_count += 1
+    for x, y in elements:
+        x_counter += 1
+        row = {'row':x ,'col':y, 'code':restored_list[x][y]}
+        data_table.append(row)
+df = pd.DataFrame(data_table)
+#df.to_csv('recovered_data_1.csv', index=False)
+
+d_file = pd.read_csv('recovered_data.csv')
+
+
+
+new_rows = []
+for index, row in d_file.iterrows():
+    code = row['code']
+    if 10 <= code <= 99:
+        q = code // 10
+        r = code % 10
+        new_rows.append({'row': row['row'], 'col':row['col'], 'code':q})
+        new_rows.append({'row': row['row'], 'col':row['col'], 'code':r})
+    elif 100 <= code <= 1000:
+        quo = code // 100
+        unit_r = code % 100
+        quao = unit_r // 10
+        quao1 = unit_r % 10
+        new_rows.append({'row': row['row'], 'col': row['col'], 'code': quo})
+        new_rows.append({'row': row['row'], 'col': row['col'], 'code': quao})
+        new_rows.append({'row': row['row'], 'col': row['col'], 'code': quao1})
+    else:
+        new_rows.append(row.to_dict())
+
+pd.set_option('display.max_rows', None)
+pd.set_option('display.max_columns', None)
+p_df = pd.DataFrame(new_rows)
+
+#p_df.to_csv('recovered_data.csv', index=False)
+x_axis = p_df['code']
+y_axis = p_df['row']
+labl = p_df['col']
+
+plt.scatter(x_axis, y_axis, c=labl, cmap='viridis')
+plt.colorbar()
+#plt.show()
+
+education = []
+for dicts in new_rows:
+    if dicts['code'] == 1:
+        education.append(dicts)
+
+row_c = Counter()
+
+for dicts in education:
+    row_c[dicts['row']] += 1
+
+education.clear()
+for r,c in row_c.items():
+    education.append((r,c))
+#print(education)
+
+fltrd = []
+for i in education:
+    if i[1] != 1:
+        fltrd.append(i)
+education = fltrd
+
+#print(education)
+
+final_edu = []
+j_l = []
+for i in education:
+    j_l.append(i[0])
+    cnt = 0
+for j in education:
+    k = j[0]
+    final_edu.append(k)
+
+final_edu_set = set(final_edu)
+
+
+
+longest = 0
+longest_seq = []
+for n in final_edu:
+    if (n-1) not in final_edu_set:
+        current = n
+        current_seq = [current]
+        while (current + 1) in final_edu_set:
+            current += 1
+            current_seq.append(current)
+
+        if len(current_seq) > longest:
+            longest = len(current_seq)
+            longest_seq = current_seq
+#print(fixed_data_list)
+
+extracted_education = []
+for i in longest_seq:
+    extracted_education.append(fixed_data_list[i])
+print(extracted_education)
\ No newline at end of file
diff --git a/uploads/Mujtaba_Resume.pdf b/uploads/Mujtaba_Resume.pdf
new file mode 100644
index 0000000..2ad906b
Binary files /dev/null and b/uploads/Mujtaba_Resume.pdf differ