def read_documents()

in hugegraph-llm/src/hugegraph_llm/utils/vector_index_utils.py [0:0]

• 24 lines of code
• 8 McCabe index (conditional complexity)

def read_documents(input_file, input_text):
    if input_text:
        texts = [input_text]
    elif input_file:
        texts = []
        for file in input_file:
            full_path = file.name
            if full_path.endswith(".txt"):
                with open(full_path, "r", encoding="utf-8") as f:
                    texts.append(f.read())
            elif full_path.endswith(".docx"):
                text = ""
                doc = docx.Document(full_path)
                for para in doc.paragraphs:
                    text += para.text
                    text += "\n"
                texts.append(text)
            elif full_path.endswith(".pdf"):
                # TODO: support PDF file
                raise gr.Error("PDF will be supported later! Try to upload text/docx now")
            else:
                raise gr.Error("Please input txt or docx file.")
    else:
        raise gr.Error("Please input text or upload file.")
    return texts