test

Author: heyronjmilton

Backend/__pycache__/pyqsorter.cpython-310.pyc

@@ -0,0 +1,63 @@
+import re
+
+def remove_extra_whitespace(input_file, output_file):
+    with open(input_file, 'r') as file:
+        content = file.read()
+
+    # Remove unwanted characters before numbering
+    content = re.sub(r'(?<=\n)\s*-+\s*', '', content)
+
+    # Remove Roman numbering and add decimal numbering
+    decimal_number = 1
+    content = re.sub(r'(?<=\n)([IVXLCDM]+\.)(?=\s)', lambda match: str(decimal_number) + '.', content)
+    decimal_number += 1
+
+    # Remove extra white spaces
+    content = re.sub(' +', ' ', content)
+
+    with open(output_file, 'w') as file:
+        file.write(content)
+
+
+def number_questions(input_filename, output_filename):
+    section_count = 0
+    question_count = 0
+    current_section = ""
+
+    with open(input_filename, 'r') as input_file:
+        lines = input_file.readlines()
+
+    with open(output_filename, 'w') as output_file:
+        for line in lines:
+            # Check if the line starts with "Module X:"
+            if re.match(r'^Module \d+:', line):
+                section_count += 1
+                question_count = 0
+                current_section = re.findall(r'^Module \d+', line)[0]
+                output_file.write(line)
+            # Check if the line starts with "1.", "(a)", or "(i)"
+            elif re.match(r'^\d+\.|^[(a-z)]\.|^[(i)]\.', line):
+                question_count += 1
+                # Modify the line to include the correct question number
+                modified_line = re.sub(r'^(\d+\.|^[(a-z)]\.|^[(i)]\.)', str(question_count) + '.', line)
+                # Replace the section number if necessary
+                modified_line = modified_line.replace(current_section, 'Module ' + str(section_count))
+                output_file.write(modified_line)
+            else:
+                output_file.write(line)
+
+
+# Usage example
+input_file = 'Local_Storage\Generated_Files\cluster_questions.txt'  # Replace with your input file path
+temp_file = 'temp_output.txt'  # Replace with a temporary output file path
+output_file = 'final_output.txt'  # Replace with your final output file path
+
+# Step 1: Remove extra whitespace
+remove_extra_whitespace(input_file, temp_file)
+
+# Step 2: Number the questions
+number_questions(temp_file, output_file)
+
+# Step 3: Clean up the temporary file
+import os
+os.remove(temp_file)

Backend/__pycache__/t1.cpython-310.pyc

@@ -0,0 +1,24 @@
+import re
+
+def remove_extra_whitespace(input_file, output_file):
+    with open(input_file, 'r') as file:
+        content = file.read()
+
+    # Remove unwanted characters before numbering
+    content = re.sub(r'(?<=\n)\s*-+\s*', '', content)
+
+    # Remove Roman numbering and add decimal numbering
+    decimal_number = 1
+    content = re.sub(r'(?<=\n)([IVXLCDM]+\.)(?=\s)', lambda match: str(decimal_number) + '.', content)
+    decimal_number += 1
+
+    # Remove extra white spaces
+    content = re.sub(' +', ' ', content)
+
+    with open(output_file, 'w') as file:
+        file.write(content)
+
+# Usage example
+input_file = 'Local_Storage\Generated_Files\cluster_questions.txt'  # Replace with your input file path
+output_file = 'output.txt'  # Replace with your output file path
+remove_extra_whitespace(input_file, output_file)

Backend/__pycache__/updated_sorter.cpython-310.pyc

@@ -0,0 +1,33 @@
+import re
+
+def number_questions(input_filename, output_filename):
+    section_count = 0
+    question_count = 0
+    current_section = ""
+
+    with open(input_filename, 'r') as input_file:
+        lines = input_file.readlines()
+
+    with open(output_filename, 'w') as output_file:
+        for line in lines:
+            # Check if the line starts with "Module X:"
+            if re.match(r'^Module \d+:', line):
+                section_count += 1
+                question_count = 0
+                current_section = re.findall(r'^Module \d+', line)[0]
+                output_file.write(line)
+            # Check if the line starts with "1.", "(a)", or "(i)"
+            elif re.match(r'^\d+\.|^[(a-z)]\.|^[(i)]\.', line):
+                question_count += 1
+                # Modify the line to include the correct question number
+                modified_line = re.sub(r'^(\d+\.|^[(a-z)]\.|^[(i)]\.)', str(question_count) + '.', line)
+                # Replace the section number if necessary
+                modified_line = modified_line.replace(current_section, 'Module ' + str(section_count))
+                output_file.write(modified_line)
+            else:
+                output_file.write(line)
+
+# Usage
+input_filename = "output.txt"  # Replace with the actual input filename
+output_filename = "numbered_questions.txt"  # Replace with the desired output filename
+number_questions(input_filename, output_filename)

Backend/cluster_processor.py

@@ -0,0 +1,70 @@
+from pprint import pprint
+
+
+def process_file(file_path):
+    # Read the file
+    with open(file_path, 'r') as file:
+        lines = file.readlines()
+
+    # Process the lines
+    processed_data = {}
+    current_section = None
+    current_subsection = None
+    current_questions = []
+    for line in lines:
+        line = line.strip()
+
+        # Skip empty lines
+        if not line:
+            continue
+
+        # Check if it's a section
+        if line.startswith("PART"):
+            current_section = line
+            processed_data[current_section] = []
+            current_subsection = None
+            current_questions = []
+            continue
+
+        # Check if it's a subsection
+        if line.startswith(("I.", "II.", "III.", "IV.", "V.", "VI.", "VII.", "VIII.", "IX.")):
+            current_subsection = line
+            current_questions = []
+            continue
+
+        # Add question to the current subsection's questions
+        if current_subsection:
+            current_questions.append(line)
+
+        # Check if it's the end of a subsection
+        if line.startswith("***"):
+            if current_section and current_subsection:
+                processed_data[current_section].append({'subsection': current_subsection, 'questions': current_questions})
+                current_subsection = None
+                current_questions = []
+
+    # Print debug information
+    print("Processed Data:")
+    pprint(processed_data)
+
+    # Format the extracted information
+    formatted_data = ''
+    for section, subsections in processed_data.items():
+        formatted_data += section + '\n\n'
+        for subsection_data in subsections:
+            formatted_data += subsection_data['subsection'] + '\n'
+            formatted_data += '\n'.join(subsection_data['questions']) + '\n\n'
+
+    # Save the processed data
+    output_file_path = file_path + '_processed.txt'
+    try:
+        with open(output_file_path, 'w') as output_file:
+            output_file.write(formatted_data)
+        print(f"Processing complete. Processed data saved to: {output_file_path}")
+    except Exception as e:
+        print("Error occurred while saving processed data:")
+        print(str(e))
+
+
+# Usage: Provide the file path as a parameter to the process_file function
+process_file('Local_Storage\pyqs_text\qp.txt')