mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-03 17:11:24 +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.
64 lines
1.8 KiB
Python
64 lines
1.8 KiB
Python
import pytest
|
|
from pathlib import Path
|
|
from unittest.mock import patch
|
|
|
|
from docsgpt.parser.file.pptx_parser import PPTXParser
|
|
|
|
|
|
def test_pptx_init_parser():
|
|
parser = PPTXParser()
|
|
assert isinstance(parser._init_parser(), dict)
|
|
assert not parser.parser_config_set
|
|
parser.init_parser()
|
|
assert parser.parser_config_set
|
|
|
|
|
|
def _fake_presentation_with(slides_shapes_texts):
|
|
class Shape:
|
|
def __init__(self, text=None):
|
|
if text is not None:
|
|
self.text = text
|
|
class Slide:
|
|
def __init__(self, texts):
|
|
self.shapes = [Shape(t) for t in texts]
|
|
class Pres:
|
|
def __init__(self, _file):
|
|
self.slides = [Slide(texts) for texts in slides_shapes_texts]
|
|
return Pres
|
|
|
|
|
|
def test_pptx_parser_concat_true():
|
|
slides = [["Hello ", "World"], ["Slide2"]]
|
|
FakePres = _fake_presentation_with(slides)
|
|
import sys
|
|
import types
|
|
fake_pptx = types.ModuleType("pptx")
|
|
fake_pptx.Presentation = FakePres
|
|
parser = PPTXParser()
|
|
with patch.dict(sys.modules, {"pptx": fake_pptx}):
|
|
result = parser.parse_file(Path("deck.pptx"))
|
|
assert result == "Hello World\nSlide2"
|
|
|
|
|
|
def test_pptx_parser_list_mode():
|
|
slides = [[" A ", "B"], [" C "]]
|
|
FakePres = _fake_presentation_with(slides)
|
|
import sys
|
|
import types
|
|
fake_pptx = types.ModuleType("pptx")
|
|
fake_pptx.Presentation = FakePres
|
|
parser = PPTXParser()
|
|
parser._concat_slides = False
|
|
with patch.dict(sys.modules, {"pptx": fake_pptx}):
|
|
result = parser.parse_file(Path("deck.pptx"))
|
|
assert result == ["A B", "C"]
|
|
|
|
|
|
def test_pptx_parser_import_error():
|
|
parser = PPTXParser()
|
|
import sys
|
|
with patch.dict(sys.modules, {"pptx": None}):
|
|
with pytest.raises(ImportError, match="pptx module is required to read .PPTX files"):
|
|
parser.parse_file(Path("missing.pptx"))
|
|
|