refactor: remove H5 storage backend in favor of mmap bin

- Remove H5Store, H5Writer, save_h5/load_h5 and h5py dependency
- MmapStore (bin) is the sole pre-tokenized storage backend
- Move setup_logging after imports to fix E402 in __init__.py
- Clean up unused imports across test files
- Move inline test imports to file top

astrai/preprocessing/pipeline.py

@@ -1,7 +1,7 @@
 """Config-driven JSONL preprocessing pipeline.
 
 Composes a :class:`BaseMaskBuilder` (selected by ``input.type``) with
-sharding and flush to ``.h5`` / ``.bin`` storage.  Packing, position-id
+sharding and flush to ``.bin`` storage.  Packing, position-id
 generation and storage writing are each delegated to pluggable strategies,
 dispatched by configuration keys.
 

astrai/preprocessing/writer.py

@@ -1,7 +1,7 @@
 """Storage writer strategies for pipeline output.
 
 The :class:`StoreWriter` abstraction decouples the pipeline from the
-concrete storage format (bin / h5).  The pipeline builds a ``{key:
+concrete storage format (bin).  The pipeline builds a ``{key:
 List[Tensor]}`` dict and delegates the write to the writer selected
 by ``output.storage_format``.
 """
@@ -15,7 +15,7 @@ from typing import Dict, List
 import torch
 
 from astrai.factory import BaseFactory
-from astrai.serialization import save_bin, save_h5
+from astrai.serialization import save_bin
 
 logger = logging.getLogger(__name__)
 
@@ -54,22 +54,3 @@ class BinWriter(StoreWriter):
                 exc_info=True,
             )
             raise
-
-
-@StoreWriterFactory.register("h5")
-class H5Writer(StoreWriter):
-    def save(self, output_dir, domain, shard_idx, tensors):
-        chunk_dir = os.path.join(output_dir, domain)
-        file_path = os.path.join(chunk_dir, f"data_{shard_idx:04d}.h5")
-        try:
-            save_h5(chunk_dir, f"data_{shard_idx:04d}", tensors)
-        except Exception:
-            if os.path.exists(file_path):
-                os.remove(file_path)
-            logger.error(
-                "Failed to write shard %s/data_%04d.h5, cleaned up partial output",
-                domain,
-                shard_idx,
-                exc_info=True,
-            )
-            raise