feat: 添加 FileTracker — 基于 SHA256 的文件变更追踪

tests/test_file_tracker.py

@@ -0,0 +1,104 @@
+"""文件变更追踪器测试."""
+import hashlib
+from pathlib import Path
+
+from src.core.file_tracker import FileTracker
+
+
+def test_compute_file_hash(tmp_path: Path):
+    """计算文件 SHA256 哈希."""
+    file = tmp_path / "test.md"
+    file.write_text("hello world", encoding="utf-8")
+    result = FileTracker.compute_hash(str(file))
+    expected = hashlib.sha256(b"hello world").hexdigest()
+    assert result == expected
+
+
+def test_compute_hash_deterministic(tmp_path: Path):
+    """同一文件内容产生相同哈希."""
+    file = tmp_path / "a.md"
+    file.write_text("same content", encoding="utf-8")
+    assert FileTracker.compute_hash(str(file)) == FileTracker.compute_hash(str(file))
+
+
+def test_hash_changes_with_content(tmp_path: Path):
+    """内容变更导致哈希不同."""
+    file = tmp_path / "b.md"
+    file.write_text("v1", encoding="utf-8")
+    h1 = FileTracker.compute_hash(str(file))
+    file.write_text("v2", encoding="utf-8")
+    h2 = FileTracker.compute_hash(str(file))
+    assert h1 != h2
+
+
+def test_is_stale_new_file(tmp_path: Path):
+    """新文件（无记录）视为过期."""
+    file = tmp_path / "new.md"
+    file.write_text("content", encoding="utf-8")
+    tracker = FileTracker(tmp_path / "tracker.json")
+    record = tracker.get_record(str(file))
+    assert record is None
+    assert tracker.is_stale(str(file)) is True
+
+
+def test_is_stale_unchanged_file(tmp_path: Path):
+    """未修改文件视为未过期."""
+    file = tmp_path / "unchanged.md"
+    file.write_text("stable", encoding="utf-8")
+    tracker = FileTracker(tmp_path / "tracker.json")
+    tracker.mark_ingested(str(file))
+    assert tracker.is_stale(str(file)) is False
+
+
+def test_is_stale_modified_file(tmp_path: Path):
+    """修改后文件视为过期."""
+    file = tmp_path / "modified.md"
+    file.write_text("v1", encoding="utf-8")
+    tracker = FileTracker(tmp_path / "tracker.json")
+    tracker.mark_ingested(str(file))
+    file.write_text("v2", encoding="utf-8")
+    assert tracker.is_stale(str(file)) is True
+
+
+def test_mark_ingested_updates_record(tmp_path: Path):
+    """mark_ingested 创建/更新记录."""
+    file = tmp_path / "x.md"
+    file.write_text("hello", encoding="utf-8")
+    tracker = FileTracker(tmp_path / "tracker.json")
+    tracker.mark_ingested(str(file))
+    record = tracker.get_record(str(file))
+    assert record is not None
+    assert record["hash"] == FileTracker.compute_hash(str(file))
+    assert "ingested_at" in record
+
+
+def test_persistence_across_instances(tmp_path: Path):
+    """tracker 数据持久化到 JSON，跨实例可读."""
+    file = tmp_path / "p.md"
+    file.write_text("persist me", encoding="utf-8")
+    db_path = tmp_path / "tracker.json"
+
+    t1 = FileTracker(db_path)
+    t1.mark_ingested(str(file))
+
+    t2 = FileTracker(db_path)
+    assert t2.is_stale(str(file)) is False
+
+
+def test_file_deleted_considered_stale(tmp_path: Path):
+    """文件被删除后视为过期."""
+    file = tmp_path / "tmp.md"
+    file.write_text("temp", encoding="utf-8")
+    tracker = FileTracker(tmp_path / "tracker.json")
+    tracker.mark_ingested(str(file))
+    file.unlink()
+    assert tracker.is_stale(str(file)) is True
+
+
+def test_binary_file_hash(tmp_path: Path):
+    """二进制文件也能正确计算哈希（如 PDF）."""
+    file = tmp_path / "doc.pdf"
+    file.write_bytes(b"\x00\x01\x02\x03")
+    h = FileTracker.compute_hash(str(file))
+    assert len(h) == 64
+    assert h == hashlib.sha256(b"\x00\x01\x02\x03").hexdigest()