mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-03 22:13:01 +00:00
Alex
574f96341e
The backend import package is now docsgpt, the name it will carry on PyPI; application was far too generic to install into anyone's site-packages. git mv plus a mechanical rewrite of every import, dotted string and path reference: 734 Python files, the compose files, Dockerfile, workflows, docs, setup scripts, devcontainer, k8s manifests, vscode config, pytest and coverage config, .gitignore. Behaviour is unchanged. Kept for one release: - A top-level application package whose meta-path finder resolves application.x.y to the already-imported docsgpt.x.y object, so old imports and entry points (celery -A application.app.celery, uvicorn application.asgi:asgi_app) keep working with a FutureWarning. - Celery registers every application.* task name as an alias of its docsgpt.* task on start-up, so messages queued by the previous release still run. The redbeat key prefix moves to redbeat:docsgpt:v2: so schedule entries the previous release wrote are left unread instead of firing twice. The backend image builds from the repository root (docker build -f docsgpt/Dockerfile .) so it can ship the alias package; a root .dockerignore allow-lists docsgpt/ and application/ and keeps caches, local data, .env files, the sample index files and the Dockerfile out. Compose and the image workflows point at the new context.
58 lines
1.7 KiB
Python
58 lines
1.7 KiB
Python
import json
|
|
from typing import Any, Dict, List, Union
|
|
from pathlib import Path
|
|
|
|
from docsgpt.parser.file.base_parser import BaseParser
|
|
|
|
class JSONParser(BaseParser):
|
|
r"""JSON (.json) parser.
|
|
|
|
Parses JSON files into a list of strings or a concatenated document.
|
|
It handles both JSON objects (dictionaries) and arrays (lists).
|
|
|
|
Args:
|
|
concat_rows (bool): Whether to concatenate all rows into one document.
|
|
If set to False, a Document will be created for each item in the JSON.
|
|
True by default.
|
|
|
|
row_joiner (str): Separator to use for joining each row.
|
|
Only used when `concat_rows=True`.
|
|
Set to "\n" by default.
|
|
|
|
json_config (dict): Options for parsing JSON. Can be used to specify options like
|
|
custom decoding or formatting. Set to empty dict by default.
|
|
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
*args: Any,
|
|
concat_rows: bool = True,
|
|
row_joiner: str = "\n",
|
|
json_config: dict = {},
|
|
**kwargs: Any
|
|
) -> None:
|
|
"""Init params."""
|
|
super().__init__(*args, **kwargs)
|
|
self._concat_rows = concat_rows
|
|
self._row_joiner = row_joiner
|
|
self._json_config = json_config
|
|
|
|
def _init_parser(self) -> Dict:
|
|
"""Init parser."""
|
|
return {}
|
|
|
|
def parse_file(self, file: Path, errors: str = "ignore") -> Union[str, List[str]]:
|
|
"""Parse JSON file."""
|
|
|
|
with open(file, 'r', encoding='utf-8') as f:
|
|
data = json.load(f, **self._json_config)
|
|
|
|
if isinstance(data, dict):
|
|
data = [data]
|
|
|
|
if self._concat_rows:
|
|
return self._row_joiner.join([str(item) for item in data])
|
|
else:
|
|
return data
|