acb / src /document_processor.py
Kagan Tek
Cleaner comments
f5e4ae6
Raw
History Blame Contribute Delete
3.64 kB
import os
import tempfile
from typing import List, Dict, Any, BinaryIO
import pdfplumber
from langchain_text_splitters import RecursiveCharacterTextSplitter
from config import CHUNK_SIZE, CHUNK_OVERLAP
"""
Methods:
extract_uploaded_pdf_pages -> Takes in a file_obj in the form of BinaryIO and a filename as string. Extracts text from PDF file, page by page.
extract_pdf_from_path -> Extract text from PDF file path directly for
chunk_text -> Split text into chunks with metadata.
process_documents -> Process extracted pages into chunks.
chunks_to_store_format -> Convert chunks to vector store add_documents format.
"""
def extract_pdf_pages(file_obj: BinaryIO, filename: str = "document.pdf") -> List[Dict[str, Any]]:
pages = []
with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp:
tmp.write(file_obj.read())
tmp_path = tmp.name
try:
with pdfplumber.open(tmp_path) as pdf:
for i, page in enumerate(pdf.pages, 1):
text = page.extract_text() or ""
if text.strip():
pages.append({
"text": text,
"page_number": i,
"source": filename
})
finally:
os.unlink(tmp_path)
return pages
def extract_pdf_from_path(pdf_path: str, filename: str = None) -> List[Dict[str, Any]]:
pages = []
if filename is None:
filename = os.path.basename(pdf_path)
try:
with pdfplumber.open(pdf_path) as pdf:
for i, page in enumerate(pdf.pages, 1):
text = page.extract_text() or ""
if text.strip():
pages.append({
"text": text,
"page_number": i,
"source": filename
})
except Exception:
pass
return pages
def chunk_text(text: str, source: str, page_number: int, chunk_size: int = CHUNK_SIZE, chunk_overlap: int = CHUNK_OVERLAP) -> List[Dict[str, Any]]:
splitter = RecursiveCharacterTextSplitter(
chunk_size=chunk_size,
chunk_overlap=chunk_overlap,
separators=["\n\n", "\n", ".", " ", ""]
)
chunks = splitter.split_text(text)
result = []
for i, chunk in enumerate(chunks):
result.append({
"text": chunk,
"metadata": {
"source": source,
"page_number": page_number,
"chunk_index": i
}
})
return result
def process_documents(pages: List[Dict[str, Any]], chunk_size: int = CHUNK_SIZE, chunk_overlap: int = CHUNK_OVERLAP) -> List[Dict[str, Any]]:
all_chunks = []
for page in pages:
chunks = chunk_text(
text=page["text"],
source=page["source"],
page_number=page["page_number"],
chunk_size=chunk_size,
chunk_overlap=chunk_overlap
)
all_chunks.extend(chunks)
return all_chunks
def chunks_to_store_format(chunks: List[Dict[str, Any]]) -> tuple:
texts = [c["text"] for c in chunks]
metadatas = [c["metadata"] for c in chunks]
return texts, metadatas
if __name__ == "__main__":
test_text = """This is a test document.
It has multiple paragraphs. Each paragraph contains some text.
This is the third paragraph with more content."""
chunks = chunk_text(test_text, "test.pdf", 1)
print(f"Created {len(chunks)} chunks")
for c in chunks:
print(f" - {c['metadata']}: {c['text'][:50]}...")