def extract_text_from_file()

in services/file.py [0:0]

• 33 lines of code
• 15 McCabe index (conditional complexity)

def extract_text_from_file(file: BufferedReader, mimetype: str) -> str:
    if mimetype == "application/pdf":
        # Extract text from pdf using PyPDF2
        reader = PdfReader(file)
        extracted_text = " ".join([page.extract_text() for page in reader.pages])
    elif mimetype == "text/plain" or mimetype == "text/markdown":
        # Read text from plain text file
        extracted_text = file.read().decode("utf-8")
    elif (
        mimetype
        == "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
    ):
        # Extract text from docx using docx2txt
        extracted_text = docx2txt.process(file)
    elif mimetype == "text/csv":
        # Extract text from csv using csv module
        extracted_text = ""
        decoded_buffer = (line.decode("utf-8") for line in file)
        reader = csv.reader(decoded_buffer)
        for row in reader:
            extracted_text += " ".join(row) + "\n"
    elif (
        mimetype
        == "application/vnd.openxmlformats-officedocument.presentationml.presentation"
    ):
        # Extract text from pptx using python-pptx
        extracted_text = ""
        presentation = pptx.Presentation(file)
        for slide in presentation.slides:
            for shape in slide.shapes:
                if shape.has_text_frame:
                    for paragraph in shape.text_frame.paragraphs:
                        for run in paragraph.runs:
                            extracted_text += run.text + " "
                    extracted_text += "\n"
    else:
        # Unsupported file type
        raise ValueError("Unsupported file type: {}".format(mimetype))

    return extracted_text