Spaces:
Sleeping
Sleeping
File size: 2,891 Bytes
234eac0 cc17218 234eac0 cc17218 234eac0 cc17218 234eac0 cc17218 234eac0 cc17218 234eac0 cc17218 234eac0 cc17218 234eac0 cc17218 234eac0 cc17218 234eac0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 |
import os
from typing import List
import fitz # PyMuPDF
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()
elif os.path.isfile(self.path):
if self.path.endswith(".txt"):
self.load_file()
elif self.path.endswith(".pdf"):
self.load_pdf()
else:
raise ValueError("Unsupported file type. Only .txt and .pdf files are supported.")
else:
raise ValueError("Provided path is neither a valid directory nor a file.")
def load_file(self):
with open(self.path, "r", encoding=self.encoding) as f:
self.documents.append(f.read())
def load_pdf(self):
with fitz.open(self.path) as doc:
text = ""
for page in doc:
text += page.get_text("text")
self.documents.append(text)
def load_directory(self):
for root, _, files in os.walk(self.path):
for file in files:
file_path = os.path.join(root, file)
if file.endswith(".txt"):
with open(file_path, "r", encoding=self.encoding) as f:
self.documents.append(f.read())
elif file.endswith(".pdf"):
with fitz.open(file_path) as doc:
text = ""
for page in doc:
text += page.get_text("text")
self.documents.append(text)
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__":
# Example usage with a PDF file
loader = TextFileLoader("data/sample.pdf")
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])
|