zotero-kb/tests/test_projects.py
Saberlve aaafa78883 feat: Add multilingual support for project cards and attachments
- Introduced `card_language` attribute in ProjectRecord and Workspace classes to handle multiple languages for project cards.
- Updated project creation and renaming methods to accept and store the card language.
- Enhanced ZoteroReader to read and return attachment metadata, including language-specific summaries and claims.
- Modified LLM client to generate card content based on the specified language, supporting both English and Chinese.
- Updated tests to cover new functionality, ensuring correct handling of multilingual card generation and retrieval.
- Adjusted UI tests to verify the presence of language selection options and proper rendering of multilingual content.
2026-04-22 10:21:03 +08:00

230 lines
8.9 KiB
Python

import json
from pathlib import Path
from zotero_kb.cards import CardBuilder
from zotero_kb.config import AppConfig
from zotero_kb.projects import ProjectService
from zotero_kb.workspace import Workspace
from zotero_kb.zotero_reader import ZoteroItemRecord
class FakeLlmClient:
def generate_card(self, source_bundle: dict[str, object]) -> dict[str, object]:
title = str(source_bundle["title"])
language = str(source_bundle.get("card_language", "en"))
if "Scoped" in title:
summary = "项目范围检索能改善写作。" if language == "zh" else "Project-scoped retrieval improves drafting."
claims = ["项目范围限定能提升引文精度。"] if language == "zh" else ["Project scoping improves citation precision."]
else:
summary = "无关检索基线。" if language == "zh" else "Unrelated retrieval baseline."
claims = ["基线检索范围较宽。"] if language == "zh" else ["Baseline retrieval is broad."]
return {
"summary": summary,
"core_claims": claims,
"methods": ["Method details."],
"evidence": ["Evidence details."],
"quotable_passages": claims,
"writing_hints": [summary],
"keywords": ["retrieval"],
}
def _build_item(item_key: str, title: str) -> ZoteroItemRecord:
return ZoteroItemRecord(
item_key=item_key,
title=title,
creators=["Alice Smith"],
year="2024",
item_type="journalArticle",
abstract=title,
tags=["retrieval"],
collection_paths=[["Theory", "Drafting"]],
notes=[title],
attachments=[],
attachment_texts=[title],
)
def test_add_item_to_project_updates_selected_items_and_project_index(tmp_path: Path) -> None:
config = AppConfig(workspace_dir=tmp_path / "workspace", zotero_data_dir=tmp_path / "zotero")
workspace = Workspace(config)
workspace.create_project("thesis-ch2", "Thesis Chapter 2", "openai", "gpt-5-mini", "en")
builder = CardBuilder(config.workspace_dir, FakeLlmClient())
builder.build_or_update(_build_item("PAPER0001", "Scoped Retrieval for Drafting"))
service = ProjectService(config.workspace_dir)
payload = service.add_items("thesis-ch2", ["PAPER0001"])
assert payload["selected_items"] == ["PAPER0001"]
assert payload["cards"][0]["item_key"] == "PAPER0001"
selected_items = json.loads(
(config.workspace_dir / "projects" / "thesis-ch2" / "selected-items.json").read_text(encoding="utf-8")
)
assert selected_items == ["PAPER0001"]
def test_remove_item_from_project_updates_selected_items(tmp_path: Path) -> None:
config = AppConfig(workspace_dir=tmp_path / "workspace", zotero_data_dir=tmp_path / "zotero")
workspace = Workspace(config)
workspace.create_project("thesis-ch2", "Thesis Chapter 2", "openai", "gpt-5-mini", "en")
builder = CardBuilder(config.workspace_dir, FakeLlmClient())
builder.build_or_update(_build_item("PAPER0001", "Scoped Retrieval for Drafting"))
service = ProjectService(config.workspace_dir)
service.add_items("thesis-ch2", ["PAPER0001"])
payload = service.remove_item("thesis-ch2", "PAPER0001")
assert payload["selected_items"] == []
def test_add_item_to_project_returns_pending_item_when_card_not_generated(tmp_path: Path) -> None:
config = AppConfig(workspace_dir=tmp_path / "workspace", zotero_data_dir=tmp_path / "zotero")
workspace = Workspace(config)
workspace.create_project("thesis-ch2", "Thesis Chapter 2", "openai", "gpt-5-mini", "zh")
items_index_path = config.workspace_dir / "library" / "index" / "items.json"
items_index_path.parent.mkdir(parents=True, exist_ok=True)
items_index_path.write_text(
json.dumps(
{
"PAPER0001": {
"item_key": "PAPER0001",
"title": "Pending Item",
"creators": ["Alice Smith"],
"year": "2024",
"item_type": "journalArticle",
}
},
ensure_ascii=False,
),
encoding="utf-8",
)
service = ProjectService(config.workspace_dir)
payload = service.add_items("thesis-ch2", ["PAPER0001"])
assert payload["selected_items"] == ["PAPER0001"]
assert len(payload["items"]) == 1
assert payload["items"][0]["item_key"] == "PAPER0001"
assert payload["items"][0]["card_status"] == "pending"
def test_project_view_treats_legacy_cards_as_english_only(tmp_path: Path) -> None:
config = AppConfig(workspace_dir=tmp_path / "workspace", zotero_data_dir=tmp_path / "zotero")
workspace = Workspace(config)
workspace.create_project("thesis-ch2", "Thesis Chapter 2", "openai", "gpt-5-mini", "zh")
cards_index_path = config.workspace_dir / "library" / "index" / "cards.json"
cards_index_path.parent.mkdir(parents=True, exist_ok=True)
cards_index_path.write_text(
json.dumps(
{
"PAPER0001": {
"item_key": "PAPER0001",
"title": "Legacy Card",
"summary": "English legacy summary",
"claims": ["Legacy claim"],
"citations": [],
"quotable_spans": [],
"writing_hints": [],
"attachments": [],
}
},
ensure_ascii=False,
),
encoding="utf-8",
)
items_index_path = config.workspace_dir / "library" / "index" / "items.json"
items_index_path.write_text(
json.dumps(
{
"PAPER0001": {
"item_key": "PAPER0001",
"title": "Legacy Card",
"creators": ["Alice Smith"],
"year": "2024",
"item_type": "journalArticle",
}
},
ensure_ascii=False,
),
encoding="utf-8",
)
service = ProjectService(config.workspace_dir)
payload = service.add_items("thesis-ch2", ["PAPER0001"])
assert payload["items"][0]["card_status"] == "pending"
workspace.rename_project("thesis-ch2", "Thesis Chapter 2", "en")
english_view = service.get_project_view("thesis-ch2")
assert english_view["items"][0]["card_status"] == "done"
assert english_view["items"][0]["summary"] == "English legacy summary"
def test_project_view_reads_only_current_language_card_variant(tmp_path: Path) -> None:
config = AppConfig(workspace_dir=tmp_path / "workspace", zotero_data_dir=tmp_path / "zotero")
workspace = Workspace(config)
workspace.create_project("thesis-ch2", "Thesis Chapter 2", "openai", "gpt-5-mini", "zh")
cards_index_path = config.workspace_dir / "library" / "index" / "cards.json"
cards_index_path.parent.mkdir(parents=True, exist_ok=True)
cards_index_path.write_text(
json.dumps(
{
"PAPER0001": {
"zh": {
"item_key": "PAPER0001",
"language": "zh",
"title": "Bilingual Card",
"summary": "中文摘要",
"claims": ["中文 claim"],
"citations": [],
"quotable_spans": [],
"writing_hints": [],
"attachments": [],
},
"en": {
"item_key": "PAPER0001",
"language": "en",
"title": "Bilingual Card",
"summary": "English summary",
"claims": ["English claim"],
"citations": [],
"quotable_spans": [],
"writing_hints": [],
"attachments": [],
},
}
},
ensure_ascii=False,
),
encoding="utf-8",
)
items_index_path = config.workspace_dir / "library" / "index" / "items.json"
items_index_path.write_text(
json.dumps(
{
"PAPER0001": {
"item_key": "PAPER0001",
"title": "Bilingual Card",
"creators": ["Alice Smith"],
"year": "2024",
"item_type": "journalArticle",
}
},
ensure_ascii=False,
),
encoding="utf-8",
)
service = ProjectService(config.workspace_dir)
zh_view = service.add_items("thesis-ch2", ["PAPER0001"])
assert zh_view["items"][0]["summary"] == "中文摘要"
assert zh_view["cards"][0]["language"] == "zh"
workspace.rename_project("thesis-ch2", "Thesis Chapter 2", "en")
en_view = service.get_project_view("thesis-ch2")
assert en_view["items"][0]["summary"] == "English summary"
assert en_view["cards"][0]["language"] == "en"