aimakerspace/text_utils.py

import os
from typing import List
from pypdf import PdfReader


class TextFileLoader:
    def __init__(self, path: str, encoding: str = "utf-8"):
        self.documents = []
        self.path = path
        self.encoding = encoding

    # transform pdf to text and return text

    def load_pdf_file(self):
        # read from path
        read_pdf = PdfReader(self.path)

        # extract text for all the pages
        text_list = [i.extract_text() for i in read_pdf.pages]
        txt_document = "\n\n".join(text_list)

        # name the file
        output_name = "{}.txt".format(self.path[:-4])

        # write file
        f = open(output_name, "w")
        f.write(txt_document)
        f.close()

        return output_name

    def load(self):
        if self.path.endswith((".pdf","")):
                self.path=self.load_pdf_file()

        if os.path.isdir(self.path):
            self.load_directory()
        elif os.path.isfile(self.path) and self.path.endswith(".txt"):
            self.load_file()
            self.load_file()
        else:
            raise ValueError(
                "Provided path is neither a valid directory nor a .txt file."
            )

    def load_file(self):
        with open(self.path, "r", encoding=self.encoding) as f:
            self.documents.append(f.read())

    def load_directory(self):
        for root, _, files in os.walk(self.path):
            for file in files:
                if file.endswith(".pdf"):
                        file=self.load_pdf_file()

                if file.endswith(".txt"):
                    with open(
                        os.path.join(root, file), "r", encoding=self.encoding
                    ) as f:
                        self.documents.append(f.read())

    def load_documents(self):
        self.load()
        return self.documents


class CharacterTextSplitter:
    def __init__(
        self,
        chunk_size: int = 1000,
        chunk_overlap: int = 200,
    ):
        assert (
            chunk_size > chunk_overlap
        ), "Chunk size must be greater than chunk overlap"

        self.chunk_size = chunk_size
        self.chunk_overlap = chunk_overlap

    def split(self, text: str) -> List[str]:
        chunks = []
        for i in range(0, len(text), self.chunk_size - self.chunk_overlap):
            chunks.append(text[i : i + self.chunk_size])
        return chunks

    def split_texts(self, texts: List[str]) -> List[str]:
        chunks = []
        for text in texts:
            chunks.extend(self.split(text))
        return chunks


if __name__ == "__main__":
    loader = TextFileLoader("data/KingLear.txt")
    loader.load()
    splitter = CharacterTextSplitter()
    chunks = splitter.split_texts(loader.documents)
    print(len(chunks))
    print(chunks[0])
    print("--------")
    print(chunks[1])
    print("--------")
    print(chunks[-2])
    print("--------")
    print(chunks[-1])