Restructure Extraction-related Code

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():

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
+

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))
+
+'''

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)
+
+
+