my_1_reader.py

# MUSS AUFGERÄUMT WERDEN

import json
import os
import subprocess
import PyPDF2
import csv
import fitz  # PyMuPDF


def extract_text_from_pdf(pdf_path):
    """
    Extracts all text from a PDF file.

    :param pdf_path: Path to the PDF file.
    :return: Extracted text as a string.
    """
    # Open the PDF file
    doc = fitz.open(pdf_path)

    # Initialize an empty string to hold the text
    text = ''

    # Iterate through each page in the PDF
    for page_num in range(len(doc)):
        # Get a page
        page = doc.load_page(page_num)

        # Extract text from the page and add it to the result
        text += page.get_text()

    # Close the document
    doc.close()

    return text


def read_pdfs_from_folder(folder_path):
    """
    Reads all PDF files in the specified folder using PdfReader and extracts their text.

    Parameters:
    - folder_path: The path to the folder containing PDF files.

    Returns:
    - A dictionary with file names as keys and their extracted text as values.
    """
    pdf_texts = {}
    for filename in os.listdir(folder_path):
        if filename.endswith('.pdf'):
            file_path = os.path.join(folder_path, filename)
            with open(file_path, 'rb') as pdf_file:
                pdf_reader = PyPDF2.PdfReader(pdf_file)
                text = ''
                for page in pdf_reader.pages:
                    try:
                        text += page.extract_text()
                    except UnicodeDecodeError as e:
                        print(e)
                for c in text:
                    if c in ["ä", "Ä"]:
                        text = text[:text.index(c)] + "ae" + text[text.index(c)+1:]
                    if c in ["ö", "Ö"]:
                        text = text[:text.index(c)] + "oe" + text[text.index(c)+1:]
                    if c in ["ü", "Ü"]:
                        text = text[:text.index(c)] + "ue" + text[text.index(c)+1:]
                    if c in [",", ";", "\\", '"']:
                        text = text[:text.index(c)] + "_" + text[text.index(c)+1:]
                    if c in ["/n", "\n"]:
                        text = text[:text.index(c)] + "<newline>" + text[text.index(c) + 1:]
                pdf_texts[filename] = text
    return pdf_texts


def read_csv_lines_as_strings(filename):
    """
    Opens a CSV file and returns each line as a string in a list.

    Parameters:
    - filename: The path to the CSV file.

    Returns:
    - A list of strings, each representing a line from the CSV file.
    """
    lines_as_strings = []
    with open(filename, newline='') as csvfile:
        try:
            reader = csv.reader(csvfile)
            for row in reader:
                # Convert the row (a list of values) back into a comma-separated string
                line_as_string = ','.join(row)
                lines_as_strings.append(line_as_string)
        except UnicodeDecodeError as e:
            print(e)
    return lines_as_strings


# Function to load data from JSON files
def load_data(filename):
    with open(filename, 'r') as file:
        try:
            return json.load(file)
        except UnicodeDecodeError as err:
            print(err)
            return {}


def find_and_open_file(filename, start_directory):
    """
    Attempts to open a file with the given filename starting from the specified directory.
    If the file is not found, searches recursively in all subfolders. Works across macOS, Linux, and Windows.
    """
    for root, dirs, files in os.walk(start_directory):
        if filename in files:
            filepath = os.path.join(root, filename)
            print(f"File found: {filepath}")
            return filepath
    print(f"File {filename} not found.")
    return None


def open_file(filepath):
    """
    Opens the file with the default application, based on the operating system.
    """
    if os.path.exists(filepath):
        if os.name == 'posix':  # Linux, macOS, etc.
            subprocess.call(('open', filepath))
        elif os.name == 'nt':  # Windows
            os.startfile(filepath)
        else:
            print(f"Cannot open file on this operating system: {filepath}")
    else:
        print(f"File does not exist: {filepath}")


def list_folders_files_recursive(path, depth=0):
    """
    Recursively lists all folders and files within the specified path, including subfolders.

    Parameters:
    - path: The directory path to list contents from.
    - depth: The current depth of recursion (used for indentation in print statements).

    Returns:
    - None
    """
    # Ensure the provided path is a directory
    if not os.path.isdir(path):
        print(f"The provided path '{path}' is not a valid directory.")
        return

    indent = '  ' * depth  # Indentation based on recursion depth
    folders, files = [], []

    # List all entries in the directory
    for entry in os.listdir(path):
        full_path = os.path.join(path, entry)
        if os.path.isdir(full_path):
            folders.append(entry)
            print(f"{indent}Folder: {entry}")
            # Recursively list subfolders and files
            list_folders_files_recursive(full_path, depth + 1)
        elif os.path.isfile(full_path):
            files.append(entry)

    for f in files:
        print(f"{indent}File: {f}")


def list_folders_files(path):
    """
    Lists all folders and files within the specified path.

    Parameters:
    - path: The directory path to list contents from.

    Returns:
    - A tuple of two lists: (folders, files).
    """
    folders = []
    files = []

    # Ensure the provided path is a directory
    if not os.path.isdir(path):
        print(f"The provided path '{path}' is not a valid directory.")
        return folders, files

    # List all entries in the directory
    for entry in os.listdir(path):
        full_path = os.path.join(path, entry)
        if os.path.isdir(full_path):
            folders.append(entry)
        elif os.path.isfile(full_path):
            files.append(entry)

    return folders, files


if __name__ == "__main__":
    print("here are all functions that read files")