forked from Archives/langchain
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
74 lines
2.5 KiB
Python
74 lines
2.5 KiB
Python
"""Loader that loads acreom vault from a directory."""
|
|
import re
|
|
from pathlib import Path
|
|
from typing import Iterator, List
|
|
|
|
from langchain.docstore.document import Document
|
|
from langchain.document_loaders.base import BaseLoader
|
|
|
|
|
|
class AcreomLoader(BaseLoader):
|
|
FRONT_MATTER_REGEX = re.compile(r"^---\n(.*?)\n---\n", re.MULTILINE | re.DOTALL)
|
|
|
|
def __init__(
|
|
self, path: str, encoding: str = "UTF-8", collect_metadata: bool = True
|
|
):
|
|
"""Initialize with path."""
|
|
self.file_path = path
|
|
self.encoding = encoding
|
|
self.collect_metadata = collect_metadata
|
|
|
|
def _parse_front_matter(self, content: str) -> dict:
|
|
"""Parse front matter metadata from the content and return it as a dict."""
|
|
if not self.collect_metadata:
|
|
return {}
|
|
match = self.FRONT_MATTER_REGEX.search(content)
|
|
front_matter = {}
|
|
if match:
|
|
lines = match.group(1).split("\n")
|
|
for line in lines:
|
|
if ":" in line:
|
|
key, value = line.split(":", 1)
|
|
front_matter[key.strip()] = value.strip()
|
|
else:
|
|
# Skip lines without a colon
|
|
continue
|
|
return front_matter
|
|
|
|
def _remove_front_matter(self, content: str) -> str:
|
|
"""Remove front matter metadata from the given content."""
|
|
if not self.collect_metadata:
|
|
return content
|
|
return self.FRONT_MATTER_REGEX.sub("", content)
|
|
|
|
def _process_acreom_content(self, content: str) -> str:
|
|
# remove acreom specific elements from content that
|
|
# do not contribute to the context of current document
|
|
content = re.sub("\s*-\s\[\s\]\s.*|\s*\[\s\]\s.*", "", content) # rm tasks
|
|
content = re.sub("#", "", content) # rm hashtags
|
|
content = re.sub("\[\[.*?\]\]", "", content) # rm doclinks
|
|
return content
|
|
|
|
def lazy_load(self) -> Iterator[Document]:
|
|
ps = list(Path(self.file_path).glob("**/*.md"))
|
|
|
|
for p in ps:
|
|
with open(p, encoding=self.encoding) as f:
|
|
text = f.read()
|
|
|
|
front_matter = self._parse_front_matter(text)
|
|
text = self._remove_front_matter(text)
|
|
|
|
text = self._process_acreom_content(text)
|
|
|
|
metadata = {
|
|
"source": str(p.name),
|
|
"path": str(p),
|
|
**front_matter,
|
|
}
|
|
|
|
yield Document(page_content=text, metadata=metadata)
|
|
|
|
def load(self) -> List[Document]:
|
|
return list(self.lazy_load())
|