Source code for langchain_community.document_loaders.conllu

import csv
from pathlib import Path
from typing import List, Union

from langchain_core.documents import Document

from langchain_community.document_loaders.base import BaseLoader


[docs]class CoNLLULoader(BaseLoader): """Load `CoNLL-U` files."""
[docs] def __init__(self, file_path: Union[str, Path]): """Initialize with a file path.""" self.file_path = file_path
[docs] def load(self) -> List[Document]: """Load from a file path.""" with open(self.file_path, encoding="utf8") as f: tsv = list(csv.reader(f, delimiter="\t")) # If len(line) > 1, the line is not a comment lines = [line for line in tsv if len(line) > 1] text = "" for i, line in enumerate(lines): # Do not add a space after a punctuation mark or at the end of the sentence if line[9] == "SpaceAfter=No" or i == len(lines) - 1: text += line[1] else: text += line[1] + " " metadata = {"source": str(self.file_path)} return [Document(page_content=text, metadata=metadata)]