refactor: 抽取 BaseStorage 存储抽象，支持 JSON 原始文本数据加载

- 新增 astrai/dataset/storage.py：BaseStorage/H5Storage/JSONStorage + Fetchers + 序列化函数
- BaseDataset.load() 接入存储抽象，自动检测 HDF5/JSON 格式
- JSON 支持原始文本 + tokenizer callable 加载时 tokenize
- 新增 BaseDataset.count / keys 属性进行长度观测
- serialization.py 精简为只保留 Checkpoint 类
- 函数放前、类放后，删除分隔注释

tests/data/test_dataset.py

@@ -1,8 +1,11 @@
+import json
+import os
+
 import numpy as np
 import torch
 
 from astrai.dataset.dataset import DatasetFactory
-from astrai.serialization import save_h5
+from astrai.dataset.storage import save_h5
 
 
 def test_dataset_loader_random_paths(base_test_env):
@@ -64,7 +67,7 @@ def test_dpo_strategy_with_random_data(base_test_env):
     )
 
     assert dpo_dataset is not None
-    assert hasattr(dpo_dataset, "fetcher")
+    assert dpo_dataset.storage is not None
     assert len(dpo_dataset) > 0
 
     # Test that we can get DPO items without errors
@@ -100,7 +103,7 @@ def test_sft_dataset_with_random_data(base_test_env):
     )
 
     assert sft_dataset is not None
-    assert hasattr(sft_dataset, "fetcher")
+    assert sft_dataset.storage is not None
     assert len(sft_dataset) > 0
 
     # Test that we can get SFT items without errors
@@ -143,3 +146,139 @@ def test_dataset_with_custom_stride(base_test_env):
     )
 
     assert len(dataset) > len(default_stride_dataset)
+
+
+# ============== JSON Storage Tests (raw text + tokenizer) ==============
+
+
+def _make_tokenizer_fn(tokenizer):
+    """Wrap tokenizer.encode() as a str -> List[int] callable."""
+    return lambda text: tokenizer.encode(text, add_special_tokens=False)
+
+
+def test_seq_dataset_from_json_text(base_test_env):
+    """Test loading SEQ dataset from raw-text JSON with tokenizer"""
+    tokenizer = base_test_env["tokenizer"]
+    tokenizer_fn = _make_tokenizer_fn(tokenizer)
+    test_dir = base_test_env["test_dir"]
+    data_dir = os.path.join(test_dir, "json_text")
+    os.makedirs(data_dir, exist_ok=True)
+
+    texts = [
+        "hello world this is a test sentence for tokenizer",
+        "another sentence with different words and tokens",
+        "machine learning is fascinating and powerful",
+    ]
+
+    json_path = os.path.join(data_dir, "seq_data.json")
+    with open(json_path, "w", encoding="utf-8") as f:
+        json.dump({"sequence": texts}, f, ensure_ascii=False)
+
+    dataset = DatasetFactory.load(
+        train_type="seq",
+        load_path=data_dir,
+        window_size=16,
+        tokenizer=tokenizer_fn,
+    )
+    assert dataset is not None
+    assert len(dataset) > 0
+    assert dataset.count > 0
+    assert "sequence" in dataset.keys
+
+    item = dataset[0]
+    assert "input_ids" in item
+    assert "target_ids" in item
+    assert item["input_ids"].shape[0] == 16
+
+
+def test_sft_dataset_from_json_text(base_test_env):
+    """Test loading SFT dataset from raw-text JSON with tokenizer"""
+    tokenizer = base_test_env["tokenizer"]
+    tokenizer_fn = _make_tokenizer_fn(tokenizer)
+    test_dir = base_test_env["test_dir"]
+    data_dir = os.path.join(test_dir, "json_sft")
+    os.makedirs(data_dir, exist_ok=True)
+
+    texts = [
+        "user asks a question about the weather",
+        "assistant provides a helpful response to the user",
+    ]
+
+    json_path = os.path.join(data_dir, "sft_data.json")
+    with open(json_path, "w", encoding="utf-8") as f:
+        json.dump(
+            {"sequence": texts, "loss_mask": texts},
+            f,
+            ensure_ascii=False,
+        )
+
+    dataset = DatasetFactory.load(
+        train_type="sft",
+        load_path=data_dir,
+        window_size=16,
+        tokenizer=tokenizer_fn,
+    )
+    assert dataset is not None
+    assert len(dataset) > 0
+
+    item = dataset[0]
+    assert "loss_mask" in item
+
+
+def test_json_storage_explicit_tokenizer(base_test_env):
+    """Test explicit JSON storage with tokenizer"""
+    tokenizer = base_test_env["tokenizer"]
+    tokenizer_fn = _make_tokenizer_fn(tokenizer)
+    test_dir = base_test_env["test_dir"]
+    data_dir = os.path.join(test_dir, "json_explicit")
+    os.makedirs(data_dir, exist_ok=True)
+
+    texts = ["abcdefghijklmnopqrstuvwxyz" * 10]
+
+    json_path = os.path.join(data_dir, "data.json")
+    with open(json_path, "w", encoding="utf-8") as f:
+        json.dump({"sequence": texts}, f, ensure_ascii=False)
+
+    token_count = len(tokenizer_fn(texts[0]))
+
+    dataset = DatasetFactory.load(
+        train_type="seq",
+        load_path=data_dir,
+        window_size=32,
+        storage_type="json",
+        tokenizer=tokenizer_fn,
+    )
+    assert dataset is not None
+    assert len(dataset) > 0
+    assert dataset.count == token_count
+
+
+def test_dataset_count_property(base_test_env):
+    """Test the count property returns correct raw token count"""
+    test_dir = base_test_env["test_dir"]
+
+    seq_length = 200
+    dummy_data = {
+        "sequence": [torch.randint(0, 1000, (seq_length,), dtype=torch.int64)],
+    }
+
+    save_h5(test_dir, "count_test_data", dummy_data)
+
+    dataset = DatasetFactory.load(
+        train_type="seq",
+        load_path=test_dir,
+        window_size=64,
+    )
+
+    assert dataset.count == seq_length
+    assert dataset.count > len(dataset)  # raw tokens > windows
+    assert len(dataset) == (seq_length - 1 - 64) // 64 + 1
+
+
+def test_empty_dataset_count(base_test_env):
+    """Test count returns 0 when no data is loaded"""
+    from astrai.dataset.dataset import SEQDataset
+
+    dataset = SEQDataset(window_size=64, stride=32)
+    assert dataset.count == 0
+    assert dataset.keys == []