mirror of
https://github.com/hwchase17/langchain
synced 2024-11-02 09:40:22 +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
126 lines
4.5 KiB
Python
126 lines
4.5 KiB
Python
"""Loads word documents."""
|
|
import os
|
|
import tempfile
|
|
from abc import ABC
|
|
from pathlib import Path
|
|
from typing import List, Union
|
|
from urllib.parse import urlparse
|
|
|
|
import requests
|
|
from langchain_core.documents import Document
|
|
|
|
from langchain_community.document_loaders.base import BaseLoader
|
|
from langchain_community.document_loaders.unstructured import UnstructuredFileLoader
|
|
|
|
|
|
class Docx2txtLoader(BaseLoader, ABC):
|
|
"""Load `DOCX` file using `docx2txt` and chunks at character level.
|
|
|
|
Defaults to check for local file, but if the file is a web path, it will download it
|
|
to a temporary file, and use that, then clean up the temporary file after completion
|
|
"""
|
|
|
|
def __init__(self, file_path: Union[str, Path]):
|
|
"""Initialize with file path."""
|
|
self.file_path = str(file_path)
|
|
if "~" in self.file_path:
|
|
self.file_path = os.path.expanduser(self.file_path)
|
|
|
|
# If the file is a web path, download it to a temporary file, and use that
|
|
if not os.path.isfile(self.file_path) and self._is_valid_url(self.file_path):
|
|
r = requests.get(self.file_path)
|
|
|
|
if r.status_code != 200:
|
|
raise ValueError(
|
|
"Check the url of your file; returned status code %s"
|
|
% r.status_code
|
|
)
|
|
|
|
self.web_path = self.file_path
|
|
self.temp_file = tempfile.NamedTemporaryFile()
|
|
self.temp_file.write(r.content)
|
|
self.file_path = self.temp_file.name
|
|
elif not os.path.isfile(self.file_path):
|
|
raise ValueError("File path %s is not a valid file or url" % self.file_path)
|
|
|
|
def __del__(self) -> None:
|
|
if hasattr(self, "temp_file"):
|
|
self.temp_file.close()
|
|
|
|
def load(self) -> List[Document]:
|
|
"""Load given path as single page."""
|
|
import docx2txt
|
|
|
|
return [
|
|
Document(
|
|
page_content=docx2txt.process(self.file_path),
|
|
metadata={"source": self.file_path},
|
|
)
|
|
]
|
|
|
|
@staticmethod
|
|
def _is_valid_url(url: str) -> bool:
|
|
"""Check if the url is valid."""
|
|
parsed = urlparse(url)
|
|
return bool(parsed.netloc) and bool(parsed.scheme)
|
|
|
|
|
|
class UnstructuredWordDocumentLoader(UnstructuredFileLoader):
|
|
"""Load `Microsoft Word` file using `Unstructured`.
|
|
|
|
Works with both .docx and .doc files.
|
|
You can run the loader in one of two modes: "single" and "elements".
|
|
If you use "single" mode, the document will be returned as a single
|
|
langchain Document object. If you use "elements" mode, the unstructured
|
|
library will split the document into elements such as Title and NarrativeText.
|
|
You can pass in additional unstructured kwargs after mode to apply
|
|
different unstructured settings.
|
|
|
|
Examples
|
|
--------
|
|
from langchain_community.document_loaders import UnstructuredWordDocumentLoader
|
|
|
|
loader = UnstructuredWordDocumentLoader(
|
|
"example.docx", mode="elements", strategy="fast",
|
|
)
|
|
docs = loader.load()
|
|
|
|
References
|
|
----------
|
|
https://unstructured-io.github.io/unstructured/bricks.html#partition-docx
|
|
"""
|
|
|
|
def _get_elements(self) -> List:
|
|
from unstructured.__version__ import __version__ as __unstructured_version__
|
|
from unstructured.file_utils.filetype import FileType, detect_filetype
|
|
|
|
unstructured_version = tuple(
|
|
[int(x) for x in __unstructured_version__.split(".")]
|
|
)
|
|
# NOTE(MthwRobinson) - magic will raise an import error if the libmagic
|
|
# system dependency isn't installed. If it's not installed, we'll just
|
|
# check the file extension
|
|
try:
|
|
import magic # noqa: F401
|
|
|
|
is_doc = detect_filetype(self.file_path) == FileType.DOC
|
|
except ImportError:
|
|
_, extension = os.path.splitext(str(self.file_path))
|
|
is_doc = extension == ".doc"
|
|
|
|
if is_doc and unstructured_version < (0, 4, 11):
|
|
raise ValueError(
|
|
f"You are on unstructured version {__unstructured_version__}. "
|
|
"Partitioning .doc files is only supported in unstructured>=0.4.11. "
|
|
"Please upgrade the unstructured package and try again."
|
|
)
|
|
|
|
if is_doc:
|
|
from unstructured.partition.doc import partition_doc
|
|
|
|
return partition_doc(filename=self.file_path, **self.unstructured_kwargs)
|
|
else:
|
|
from unstructured.partition.docx import partition_docx
|
|
|
|
return partition_docx(filename=self.file_path, **self.unstructured_kwargs)
|