Test Case: python-instruct-1659

  1import subprocess  2import re  3from collections import Counter  4import argparse  5​  6def extract_text_from_pdf(pdf_path):  7    """  8    Extracts text from a PDF file using pdftotext.  9​ 10    Args: 11        pdf_path (str): The path to the PDF file. 12​ 13    Returns: 14        str: The extracted text. 15    """ 16    try: 17        result = subprocess.run(['pdftotext', pdf_path, '-'], capture_output=True, text=True, check=True) 18        return result.stdout 19    except subprocess.CalledProcessError as e: 20        print(f"Error extracting text: {e}") 21        return None 22​ 23def tokenize_text(text): 24    """ 25    Tokenizes the text by removing punctuation and converting to lowercase. 26​ 27    Args: 28        text (str): The text to tokenize. 29​ 30    Returns: 31        list: A list of tokens. 32    """ 33    text = re.sub(r'[^\w\s]', '', text)  # Remove punctuation 34    text = text.lower()  # Convert to lowercase 35    tokens = text.split()  # Split into words 36    return tokens 37​ 38def create_bag_of_words(tokens): 39    """ 40    Creates a bag-of-words representation from a list of tokens. 41​ 42    Args: 43        tokens (list): A list of tokens. 44​ 45    Returns: 46        Counter: A Counter object representing the bag-of-words. 47    """ 48    return Counter(tokens) 49​ 50def write_bag_of_words_to_file(bag_of_words, output_file): 51    """ 52    Writes the bag-of-words to a file in a format suitable for machine learning. 53​ 54    Args: 55        bag_of_words (Counter): The bag-of-words representation. 56        output_file (str): The path to the output file. 57    """ 58    with open(output_file, 'w') as f: 59        for word, count in bag_of_words.items(): 60            f.write(f"{word}:{count}\n") 61​ 62def main(): 63    """ 64    Main function to process the PDF and create the bag-of-words file. 65    """ 66    parser = argparse.ArgumentParser(description='Extract text from PDF, tokenize, and create bag-of-words.') 67    parser.add_argument('pdf_file', help='Path to the PDF file') 68    parser.add_argument('output_file', help='Path to the output file for bag-of-words') 69​ 70    args = parser.parse_args() 71​ 72    pdf_file = args.pdf_file 73    output_file = args.output_file 74​ 75    text = extract_text_from_pdf(pdf_file) 76​ 77    if text: 78        tokens = tokenize_text(text) 79        bag_of_words = create_bag_of_words(tokens) 80        write_bag_of_words_to_file(bag_of_words, output_file) 81        print(f"Bag-of-words written to {output_file}") 82    else: 83        print("Failed to extract text from PDF.") 84​ 85if __name__ == "__main__": 86    main()

None

  1import os  2import subprocess  3import re  4from collections import Counter  5import shlex  6​  7def extract_text_from_pdf(pdf_path):  8    """  9    Extracts text from a PDF file using pdftotext via subprocess. 10​ 11    Args: 12        pdf_path (str): The path to the PDF file. 13​ 14    Returns: 15        str: The extracted text from the PDF, or None if an error occurred. 16    """ 17    try: 18        # Use shlex.quote to properly escape the PDF path for the shell 19        command = ['pdftotext', '-layout', shlex.quote(pdf_path), '-'] 20        process = subprocess.run(command, capture_output=True, text=True, check=True, shell=False, timeout=60)  # Added timeout 21        return process.stdout 22    except subprocess.CalledProcessError as e: 23        print(f"Error extracting text from PDF: {e}") 24        return None 25    except FileNotFoundError: 26        print("Error: pdftotext not found. Please ensure it is installed and in your PATH.") 27        return None 28    except subprocess.TimeoutExpired: 29        print("Error: pdftotext timed out.") 30        return None 31​ 32​ 33def tokenize_text(text): 34    """ 35    Tokenizes the input text by removing punctuation and converting to lowercase. 36​ 37    Args: 38        text (str): The input text. 39​ 40    Returns: 41        list: A list of tokens. 42    """ 43    if text is None: 44        return [] 45    text = re.sub(r'[^\w\s]', '', text)  # Remove punctuation 46    text = text.lower()  # Convert to lowercase 47    tokens = text.split()  # Split into words 48    return tokens 49​ 50​ 51def create_bag_of_words(tokens): 52    """ 53    Creates a bag-of-words representation from a list of tokens. 54​ 55    Args: 56        tokens (list): A list of tokens. 57​ 58    Returns: 59        Counter: A Counter object representing the bag-of-words. 60    """ 61    return Counter(tokens) 62​ 63​ 64def write_bag_of_words_to_file(bag_of_words, output_file_path): 65    """ 66    Writes the bag-of-words representation to a file. 67​ 68    Args: 69        bag_of_words (Counter): A Counter object representing the bag-of-words. 70        output_file_path (str): The path to the output file. 71    """ 72    try: 73        with open(output_file_path, 'w') as f: 74            for word, count in bag_of_words.items(): 75                f.write(f"{word}:{count}\n") 76    except OSError as e: 77        print(f"Error writing to file: {e}") 78​ 79​ 80def main(pdf_path, output_file_path): 81    """ 82    Main function to extract text from a PDF, tokenize it, create a bag-of-words, 83    and write the bag-of-words to a file. 84​ 85    Args: 86        pdf_path (str): The path to the PDF file. 87        output_file_path (str): The path to the output file. 88    """ 89    if not os.path.isfile(pdf_path): 90        print(f"Error: PDF file not found at {pdf_path}") 91        return 92​ 93    extracted_text = extract_text_from_pdf(pdf_path) 94​ 95    if extracted_text is None: 96        print("Error: Could not extract text from PDF.") 97        return 98​ 99    tokens = tokenize_text(extracted_text)100    bag_of_words = create_bag_of_words(tokens)101    write_bag_of_words_to_file(bag_of_words, output_file_path)102​103    print(f"Bag-of-words representation written to {output_file_path}")104​105​106if __name__ == "__main__":107    import argparse108​109    parser = argparse.ArgumentParser(description="Extract text from PDF, create bag-of-words, and write to file.")110    parser.add_argument("pdf_path", help="Path to the PDF file")111    parser.add_argument("output_file_path", help="Path to the output file")112​113    args = parser.parse_args()114​115    pdf_path = args.pdf_path116    output_file_path = args.output_file_path117​118    main(pdf_path, output_file_path)

None