mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-03 18:46:54 +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.
63 lines
1.8 KiB
Python
63 lines
1.8 KiB
Python
from pathlib import Path
|
|
from unittest.mock import mock_open, patch
|
|
|
|
import pytest
|
|
|
|
from docsgpt.parser.file.markdown_parser import MarkdownParser
|
|
from docsgpt import utils
|
|
|
|
|
|
class _Enc:
|
|
def encode(self, s: str):
|
|
return list(s)
|
|
|
|
def encode_ordinary(self, s: str):
|
|
return list(s)
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _patch_tokenizer(monkeypatch):
|
|
monkeypatch.setattr(utils, "get_encoding", lambda: _Enc())
|
|
|
|
def test_markdown_init_parser():
|
|
parser = MarkdownParser()
|
|
assert isinstance(parser._init_parser(), dict)
|
|
assert not parser.parser_config_set
|
|
parser.init_parser()
|
|
assert parser.parser_config_set
|
|
|
|
|
|
def test_markdown_parse_file_basic_structure():
|
|
content = "# Title\npara1\npara2\n## Sub\ntext\n"
|
|
parser = MarkdownParser()
|
|
with patch("builtins.open", mock_open(read_data=content)):
|
|
result = parser.parse_file(Path("doc.md"))
|
|
assert isinstance(result, list) and len(result) >= 2
|
|
|
|
assert "Title" in result[0]
|
|
assert "para1" in result[0] and "para2" in result[0]
|
|
assert "Sub" in result[1]
|
|
assert "text" in result[1]
|
|
|
|
|
|
def test_markdown_removes_links_and_images_in_parse():
|
|
content = "# T\nSee [link](http://x) and ![[img.png]] here.\n"
|
|
parser = MarkdownParser()
|
|
with patch("builtins.open", mock_open(read_data=content)):
|
|
result = parser.parse_file(Path("doc.md"))
|
|
joined = "\n".join(result)
|
|
assert "(http://x)" not in joined
|
|
assert "![[img.png]]" not in joined
|
|
assert "link" in joined
|
|
|
|
|
|
def test_markdown_token_chunking_via_max_tokens():
|
|
|
|
raw = "abcdefghij" # 10 chars
|
|
parser = MarkdownParser(max_tokens=4)
|
|
with patch("builtins.open", mock_open(read_data=raw)):
|
|
tups = parser.parse_tups(Path("doc.md"))
|
|
assert len(tups) > 1
|
|
for _hdr, chunk in tups:
|
|
assert len(chunk) <= 4
|