aimakerspace/text_utils.py

import os
import re
from typing import List
import PyPDF2


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

    def load(self):
        if os.path.isdir(self.path):
            self.load_directory()
        else:
            self.load_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(".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


class PDFLoader:
    def __init__(self, path: str):
        self.documents = []
        self.path = path
        print(f"PDFLoader initialized with path: {self.path}")

    def load(self):
        print(f"Loading PDF from path: {self.path}")
        print(f"Path exists: {os.path.exists(self.path)}")
        print(f"Is file: {os.path.isfile(self.path)}")
        print(f"Is directory: {os.path.isdir(self.path)}")
        print(f"File permissions: {oct(os.stat(self.path).st_mode)[-3:]}")
        
        try:
            # Try to open the file first to verify access
            with open(self.path, 'rb') as test_file:
                pass
            
            # If we can open it, proceed with loading
            if os.path.isdir(self.path):
                self.load_directory()
            else:
                self.load_file()
            
        except IOError as e:
            raise ValueError(f"Cannot access file at '{self.path}': {str(e)}")
        except Exception as e:
            raise ValueError(f"Error processing file at '{self.path}': {str(e)}")

    def load_file(self):
        with open(self.path, 'rb') as file:
            # Create PDF reader object
            pdf_reader = PyPDF2.PdfReader(file)
            
            # Extract text from each page separately
            self.documents = []  # Clear existing documents
            for page_num, page in enumerate(pdf_reader.pages):
                page_text = page.extract_text() or ""  # Handle None returns
                if page_text.strip():  # Only add non-empty pages
                    self.documents.append(page_text)
                else:
                    print(f"Warning: Page {page_num + 1} is empty in {os.path.basename(self.path)}")

            print(f"Loaded {len(self.documents)} pages from {os.path.basename(self.path)}")

    def load_directory(self):
        self.documents = []  # Clear existing documents
        for root, _, files in os.walk(self.path):
            for file in files:
                if file.lower().endswith('.pdf'):
                    file_path = os.path.join(root, file)
                    try:
                        with open(file_path, 'rb') as f:
                            pdf_reader = PyPDF2.PdfReader(f)
                            
                            # Extract text from each page separately
                            for page_num, page in enumerate(pdf_reader.pages):
                                page_text = page.extract_text() or ""
                                if page_text.strip():
                                    self.documents.append(page_text)
                                else:
                                    print(f"Warning: Page {page_num + 1} is empty in {file}")
                    except Exception as e:
                        print(f"Error processing {file}: {str(e)}")

    def load_documents(self):
        if not self.documents:  # Only load if not already loaded
            self.load()
        return self.documents


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])