common/Utilities.py

from collections import OrderedDict
from datetime import datetime
import pandas as pd
import os


def read_text_file(file_path):
  with open(file_path, 'r') as file:
    content = file.read()
  return content

# FILTER FUNCTION
def filter_profiles_by_input(profiles, data_dictionary):
    """Interactive filtering with step-by-step criteria selection and data dictionary integration"""
    print("\n=== FILTER SETTINGS ===")

    # Get column names from the data dictionary
    try:
        dd_columns = data_dictionary.get_columns()  # Use get_columns() from your DataDictionary class
        if not dd_columns:
            raise RuntimeError("Data dictionary returned no columns.")
    except Exception as e:
        raise RuntimeError(f"Failed to retrieve columns from data dictionary: {str(e)}")

    print("Available columns:")
    for col in sorted(dd_columns):
        print(f"  • {col}")
    
    remaining_columns = set(dd_columns)
    filtered_profiles = profiles
    
    while True:
        if not remaining_columns:
            print("\nNo more columns available for filtering.")
            break
        
        print("\nColumns available to filter on:")
        for col in sorted(remaining_columns):
            print(f"  • {col}")
        
        column = input("\nEnter column name to filter (press Enter to finish): ").strip()
        
        if not column:
            break  # Stop filtering when user presses Enter
        
        if column not in remaining_columns:
            print(f"\nError: Column '{column}' not found or already used for filtering.")
            continue

        value = input(f"Enter value to filter for '{column}' (press Enter to skip): ").strip()
        
        if not value:
            print("\nNo value entered. Skipping this filter.")
            continue
        
        new_filtered_profiles = [
            profile for profile in filtered_profiles
            if value.lower() in str(profile.get_attributes().get(column, "")).lower()
        ]
        
        if not new_filtered_profiles:
            print(f"\nNo matches for '{column}' containing '{value}'. Returning to previous state.")
            continue
        
        filtered_profiles = new_filtered_profiles
        remaining_columns.remove(column)
        
        print(f"\nFound {len(filtered_profiles)} matching profiles")
        print(f"Profiles filtered out: {len(profiles) - len(filtered_profiles)}")
        
        confirm = input("\nProceed with another filter? (Yes/No): ").strip().lower()
        while confirm not in ['yes', 'no']:
            confirm = input("Invalid input. Please enter 'Yes' or 'No': ").strip().lower()
        
        if confirm == 'no':
            break
    
    return filtered_profiles



def generate_file_excerpt(file_path, pattern, max_chars=5000):
    # Step 1: Read the file content
    with open(file_path, 'r') as file:
        lines = file.readlines()

    # Step 2: Extract lines starting with "pattern"
    extracted_lines = [line.replace(pattern, '').strip() for line in lines if line.startswith(pattern) and len(line.split()) >= 6]

    # Step 3: Join all extracted lines into a single string
    full_text = '\n'.join(extracted_lines)

    # Step 4: Return the first max_chars characters
    return full_text[-max_chars:]  # Taking the last max_chars characters


def generate_dict_from_file(file_name, column_name1, column_name2):
    df = pd.read_excel(file_name, usecols=[column_name1, column_name2], engine='openpyxl')  # Specify the engine

    # Convert the DataFrame to a dictionary with Questions as keys and Answers as values
    ordered_dict = OrderedDict(zip(df[column_name1], df[column_name2]))

    return ordered_dict

def find_latest_timestamped_file(directory, filename_pattern):
    """Finds the file with the latest timestamp within a given directory.

    Args:
        directory: The directory to search for files.
        filename_pattern: The pattern to match filenames (e.g., "interview_results.xlsx").

    Returns:
        The path to the latest timestamped file, or None if no matching files were found.
    """

    files = [f for f in os.listdir(directory) if f.endswith(filename_pattern)]
    if not files:
        print(f"Unable to find file with {filename_pattern} in {directory}")
        return None

    latest_file = sorted(files, key=lambda f: os.path.getmtime(os.path.join(directory, f)), reverse=True)[0]
    return os.path.join(directory, latest_file)
  
  
def generate_pivot_table(original_table, index, columns, values):
    # Step 1: Flatten all SurveyEntry objects into a DataFrame
    df = pd.json_normalize(entry.dict() for report in original_table for entry in report.Entries)
    
    # Step 2: Extract the original order of 'columns' (e.g., questions)
    original_order = df[columns].drop_duplicates().tolist()
    
    # Step 3: Pivot the DataFrame
    summary_df = df.pivot(index=index, columns=columns, values=values)
    
    # Step 4: Reindex to preserve the original order of columns
    summary_df = summary_df.reindex(columns=original_order).reset_index().fillna("No Response")
    
    # Return the summary DataFrame
    return summary_df