mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-03 15:11:30 +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.
108 lines
3.6 KiB
Python
108 lines
3.6 KiB
Python
import pytest
|
|
|
|
from docsgpt.parser.schema.schema import BaseDocument
|
|
|
|
|
|
class ConcreteDoc(BaseDocument):
|
|
@classmethod
|
|
def get_type(cls) -> str:
|
|
return "test"
|
|
|
|
|
|
@pytest.mark.unit
|
|
class TestBaseDocument:
|
|
|
|
def test_get_text(self):
|
|
doc = ConcreteDoc(text="hello")
|
|
assert doc.get_text() == "hello"
|
|
|
|
def test_get_text_raises_when_none(self):
|
|
doc = ConcreteDoc()
|
|
with pytest.raises(ValueError, match="text field not set"):
|
|
doc.get_text()
|
|
|
|
def test_get_doc_id(self):
|
|
doc = ConcreteDoc(text="x", doc_id="doc1")
|
|
assert doc.get_doc_id() == "doc1"
|
|
|
|
def test_get_doc_id_raises_when_none(self):
|
|
doc = ConcreteDoc(text="x")
|
|
with pytest.raises(ValueError, match="doc_id not set"):
|
|
doc.get_doc_id()
|
|
|
|
def test_is_doc_id_none(self):
|
|
doc = ConcreteDoc(text="x")
|
|
assert doc.is_doc_id_none is True
|
|
|
|
def test_is_doc_id_not_none(self):
|
|
doc = ConcreteDoc(text="x", doc_id="y")
|
|
assert doc.is_doc_id_none is False
|
|
|
|
def test_get_embedding(self):
|
|
doc = ConcreteDoc(text="x", embedding=[1.0, 2.0])
|
|
assert doc.get_embedding() == [1.0, 2.0]
|
|
|
|
def test_get_embedding_raises_when_none(self):
|
|
doc = ConcreteDoc(text="x")
|
|
with pytest.raises(ValueError, match="embedding not set"):
|
|
doc.get_embedding()
|
|
|
|
def test_extra_info_str(self):
|
|
doc = ConcreteDoc(text="x", extra_info={"key": "value", "num": 42})
|
|
result = doc.extra_info_str
|
|
assert "key: value" in result
|
|
assert "num: 42" in result
|
|
|
|
def test_extra_info_str_none(self):
|
|
doc = ConcreteDoc(text="x")
|
|
assert doc.extra_info_str is None
|
|
|
|
|
|
# =====================================================================
|
|
# Coverage gap tests for docsgpt/parser/schema/base.py (lines 19, 27, 34)
|
|
# =====================================================================
|
|
|
|
|
|
@pytest.mark.unit
|
|
class TestDocumentBase:
|
|
|
|
def test_document_post_init_raises_on_none_text(self):
|
|
"""Cover line 19: Document.__post_init__ raises ValueError for None text."""
|
|
from docsgpt.parser.schema.base import Document
|
|
|
|
with pytest.raises(ValueError, match="text field not set"):
|
|
Document(text=None)
|
|
|
|
def test_document_to_vector_format(self):
|
|
"""Cover line 27: Document.to_vector_format converts correctly."""
|
|
from docsgpt.parser.schema.base import Document
|
|
|
|
doc = Document(text="hello world", extra_info={"source": "test"})
|
|
lc_doc = doc.to_vector_format()
|
|
assert lc_doc.page_content == "hello world"
|
|
assert lc_doc.metadata == {"source": "test"}
|
|
|
|
def test_document_to_vector_format_no_extra_info(self):
|
|
"""Cover: to_vector_format with no extra_info uses empty dict."""
|
|
from docsgpt.parser.schema.base import Document
|
|
|
|
doc = Document(text="hello")
|
|
lc_doc = doc.to_vector_format()
|
|
assert lc_doc.metadata == {}
|
|
|
|
def test_document_from_vector_format(self):
|
|
"""Cover line 34: Document.from_vector_format creates Document."""
|
|
from docsgpt.parser.schema.base import Document
|
|
from docsgpt.vectorstore.document_class import Document as LCDocument
|
|
|
|
lc_doc = LCDocument(page_content="test content", metadata={"key": "val"})
|
|
doc = Document.from_vector_format(lc_doc)
|
|
assert doc.text == "test content"
|
|
assert doc.extra_info == {"key": "val"}
|
|
|
|
def test_document_get_type(self):
|
|
"""Cover line 24: Document.get_type returns 'Document'."""
|
|
from docsgpt.parser.schema.base import Document
|
|
|
|
assert Document.get_type() == "Document"
|