mirror of
https://github.com/hwchase17/langchain
synced 2024-11-18 09:25:54 +00:00
f7a1fd91b8
So this arose from the https://github.com/langchain-ai/langchain/pull/18397 problem of document loaders not supporting `pathlib.Path`. This pull request provides more uniform support for Path as an argument. The core ideas for this upgrade: - if there is a local file path used as an argument, it should be supported as `pathlib.Path` - if there are some external calls that may or may not support Pathlib, the argument is immidiately converted to `str` - if there `self.file_path` is used in a way that it allows for it to stay pathlib without conversion, is is only converted for the metadata. Twitter handle: https://twitter.com/mwmajewsk
35 lines
1.1 KiB
Python
35 lines
1.1 KiB
Python
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
|
|
|
|
|
|
class CoNLLULoader(BaseLoader):
|
|
"""Load `CoNLL-U` files."""
|
|
|
|
def __init__(self, file_path: Union[str, Path]):
|
|
"""Initialize with a file path."""
|
|
self.file_path = file_path
|
|
|
|
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)]
|