feat: implement "append_from_file"

google/cloud/storage/_experimental/asyncio/async_appendable_object_writer.py

@@ -21,6 +21,7 @@
 if you want to use these Rapid Storage APIs.
 
 """
+from io import BufferedReader
 from typing import Optional, Union
 
 from google_crc32c import Checksum
@@ -36,7 +37,7 @@
 
 
 _MAX_CHUNK_SIZE_BYTES = 2 * 1024 * 1024  # 2 MiB
-_MAX_BUFFER_SIZE_BYTES = 16 * 1024 * 1024  # 16 MiB
+_DEFAULT_FLUSH_INTERVAL_BYTES = 16 * 1024 * 1024  # 16 MiB
 
 
 class AsyncAppendableObjectWriter:
@@ -49,6 +50,7 @@ def __init__(
         object_name: str,
         generation=None,
         write_handle=None,
+        writer_options: Optional[dict] = None,
     ):
         """
         Class for appending data to a GCS Appendable Object.
@@ -125,6 +127,21 @@ def __init__(
         # Please note: `offset` and `persisted_size` are same when the stream is
         # opened.
         self.persisted_size: Optional[int] = None
+        if writer_options is None:
+            writer_options = {}
+        self.flush_interval = writer_options.get(
+            "FLUSH_INTERVAL_BYTES", _DEFAULT_FLUSH_INTERVAL_BYTES
+        )
+        # TODO: add test case for this.
+        if self.flush_interval < _MAX_CHUNK_SIZE_BYTES:
+            raise exceptions.OutOfRange(
+                f"flush_interval must be >= {_MAX_CHUNK_SIZE_BYTES} , but provided {self.flush_interval}"
+            )
+        if self.flush_interval % _MAX_CHUNK_SIZE_BYTES != 0:
+            raise exceptions.OutOfRange(
+                f"flush_interval must be a multiple of {_MAX_CHUNK_SIZE_BYTES}, but provided {self.flush_interval}"
+            )
+        self.bytes_appended_since_last_flush = 0
 
     async def state_lookup(self) -> int:
         """Returns the persisted_size
@@ -193,7 +210,6 @@ async def append(self, data: bytes) -> None:
             self.offset = self.persisted_size
 
         start_idx = 0
-        bytes_to_flush = 0
         while start_idx < total_bytes:
             end_idx = min(start_idx + _MAX_CHUNK_SIZE_BYTES, total_bytes)
             data_chunk = data[start_idx:end_idx]
@@ -208,10 +224,10 @@ async def append(self, data: bytes) -> None:
             )
             chunk_size = end_idx - start_idx
             self.offset += chunk_size
-            bytes_to_flush += chunk_size
-            if bytes_to_flush >= _MAX_BUFFER_SIZE_BYTES:
+            self.bytes_appended_since_last_flush += chunk_size
+            if self.bytes_appended_since_last_flush >= self.flush_interval:
                 await self.simple_flush()
-                bytes_to_flush = 0
+                self.bytes_appended_since_last_flush = 0
             start_idx = end_idx
 
     async def simple_flush(self) -> None:
@@ -323,6 +339,16 @@ async def append_from_stream(self, stream_obj):
         """
         raise NotImplementedError("append_from_stream is not implemented yet.")
 
-    async def append_from_file(self, file_path: str):
-        """Create a file object from `file_path` and call append_from_stream(file_obj)"""
-        raise NotImplementedError("append_from_file is not implemented yet.")
+    async def append_from_file(
+        self, file_obj: BufferedReader, block_size: int = _DEFAULT_FLUSH_INTERVAL_BYTES
+    ):
+        """
+        Appends data to an Appendable Object using file_handle which is opened
+        for reading in binary mode.
+
+        :type file_obj: file
+        :param file_obj: A file handle opened in binary mode for reading.
+
+        """
+        while block := file_obj.read(block_size):
+            await self.append(block)

tests/system/test_zonal.py

@@ -5,12 +5,15 @@
 from io import BytesIO
 
 # python additional imports
+import google_crc32c
+
 import pytest
 
 # current library imports
 from google.cloud.storage._experimental.asyncio.async_grpc_client import AsyncGrpcClient
 from google.cloud.storage._experimental.asyncio.async_appendable_object_writer import (
     AsyncAppendableObjectWriter,
+    _DEFAULT_FLUSH_INTERVAL_BYTES,
 )
 from google.cloud.storage._experimental.asyncio.async_multi_range_downloader import (
     AsyncMultiRangeDownloader,
@@ -28,6 +31,11 @@
 _BYTES_TO_UPLOAD = b"dummy_bytes_to_write_read_and_delete_appendable_object"
 
 
+def _get_equal_dist(a: int, b: int) -> tuple[int, int]:
+    step = (b - a) // 3
+    return a + step, a + 2 * step
+
+
 async def write_one_appendable_object(
     bucket_name: str,
     object_name: str,
@@ -59,11 +67,21 @@ def appendable_object(storage_client, blobs_to_delete):
 
 
 @pytest.mark.asyncio
+@pytest.mark.parametrize(
+    "object_size",
+    [
+        256,  # less than _chunk size
+        10 * 1024 * 1024,  # less than _MAX_BUFFER_SIZE_BYTES
+        20 * 1024 * 1024,  # greater than _MAX_BUFFER_SIZE
+    ],
+)
 @pytest.mark.parametrize(
     "attempt_direct_path",
     [True, False],
 )
-async def test_basic_wrd(storage_client, blobs_to_delete, attempt_direct_path):
+async def test_basic_wrd(
+    storage_client, blobs_to_delete, attempt_direct_path, object_size
+):
     object_name = f"test_basic_wrd-{str(uuid.uuid4())}"
 
     # Client instantiation; it cannot be part of fixture because.
@@ -74,22 +92,129 @@ async def test_basic_wrd(storage_client, blobs_to_delete, attempt_direct_path):
     # 2. we can keep the same event loop for entire module but that may
     #  create issues if tests are run in parallel and one test hogs the event
     #  loop slowing down other tests.
+    object_data = os.urandom(object_size)
+    object_checksum = google_crc32c.value(object_data)
     grpc_client = AsyncGrpcClient(attempt_direct_path=attempt_direct_path).grpc_client
 
     writer = AsyncAppendableObjectWriter(grpc_client, _ZONAL_BUCKET, object_name)
     await writer.open()
-    await writer.append(_BYTES_TO_UPLOAD)
+    await writer.append(object_data)
     object_metadata = await writer.close(finalize_on_close=True)
-    assert object_metadata.size == len(_BYTES_TO_UPLOAD)
+    assert object_metadata.size == object_size
+    assert int(object_metadata.checksums.crc32c) == object_checksum
 
     mrd = AsyncMultiRangeDownloader(grpc_client, _ZONAL_BUCKET, object_name)
     buffer = BytesIO()
     await mrd.open()
     # (0, 0) means read the whole object
     await mrd.download_ranges([(0, 0, buffer)])
     await mrd.close()
-    assert buffer.getvalue() == _BYTES_TO_UPLOAD
-    assert mrd.persisted_size == len(_BYTES_TO_UPLOAD)
+    assert buffer.getvalue() == object_data
+    assert mrd.persisted_size == object_size
+
+    # Clean up; use json client (i.e. `storage_client` fixture) to delete.
+    blobs_to_delete.append(storage_client.bucket(_ZONAL_BUCKET).blob(object_name))
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize(
+    "object_size",
+    [
+        20 * 1024 * 1024,  # greater than _MAX_BUFFER_SIZE
+    ],
+)
+@pytest.mark.parametrize(
+    "attempt_direct_path",
+    [True],
+)
+async def test_basic_wrd_in_slices(
+    storage_client, blobs_to_delete, attempt_direct_path, object_size
+):
+    object_name = f"test_basic_wrd-{str(uuid.uuid4())}"
+
+    # Client instantiation; it cannot be part of fixture because.
+    # grpc_client's event loop and event loop of coroutine running it
+    # (i.e. this test) must be same.
+    # Note:
+    # 1. @pytest.mark.asyncio ensures new event loop for each test.
+    # 2. we can keep the same event loop for entire module but that may
+    #  create issues if tests are run in parallel and one test hogs the event
+    #  loop slowing down other tests.
+    object_data = os.urandom(object_size)
+    object_checksum = google_crc32c.value(object_data)
+    grpc_client = AsyncGrpcClient(attempt_direct_path=attempt_direct_path).grpc_client
+
+    writer = AsyncAppendableObjectWriter(grpc_client, _ZONAL_BUCKET, object_name)
+    await writer.open()
+    mark1, mark2 = _get_equal_dist(0, object_size)
+    await writer.append(object_data[0:mark1])
+    await writer.append(object_data[mark1:mark2])
+    await writer.append(object_data[mark2:])
+    object_metadata = await writer.close(finalize_on_close=True)
+    assert object_metadata.size == object_size
+    assert int(object_metadata.checksums.crc32c) == object_checksum
+
+    mrd = AsyncMultiRangeDownloader(grpc_client, _ZONAL_BUCKET, object_name)
+    buffer = BytesIO()
+    await mrd.open()
+    # (0, 0) means read the whole object
+    await mrd.download_ranges([(0, 0, buffer)])
+    await mrd.close()
+    assert buffer.getvalue() == object_data
+    assert mrd.persisted_size == object_size
+
+    # Clean up; use json client (i.e. `storage_client` fixture) to delete.
+    blobs_to_delete.append(storage_client.bucket(_ZONAL_BUCKET).blob(object_name))
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize(
+    "flush_interval",
+    [2 * 1024 * 1024, 4 * 1024 * 1024, 8 * 1024 * 1024, _DEFAULT_FLUSH_INTERVAL_BYTES],
+)
+async def test_wrd_with_non_default_flush_interval(
+    storage_client,
+    blobs_to_delete,
+    flush_interval,
+):
+    object_name = f"test_basic_wrd-{str(uuid.uuid4())}"
+    object_size = 9 * 1024 * 1024
+
+    # Client instantiation; it cannot be part of fixture because.
+    # grpc_client's event loop and event loop of coroutine running it
+    # (i.e. this test) must be same.
+    # Note:
+    # 1. @pytest.mark.asyncio ensures new event loop for each test.
+    # 2. we can keep the same event loop for entire module but that may
+    #  create issues if tests are run in parallel and one test hogs the event
+    #  loop slowing down other tests.
+    object_data = os.urandom(object_size)
+    object_checksum = google_crc32c.value(object_data)
+    grpc_client = AsyncGrpcClient().grpc_client
+
+    writer = AsyncAppendableObjectWriter(
+        grpc_client,
+        _ZONAL_BUCKET,
+        object_name,
+        writer_options={"FLUSH_INTERVAL_BYTES": flush_interval},
+    )
+    await writer.open()
+    mark1, mark2 = _get_equal_dist(0, object_size)
+    await writer.append(object_data[0:mark1])
+    await writer.append(object_data[mark1:mark2])
+    await writer.append(object_data[mark2:])
+    object_metadata = await writer.close(finalize_on_close=True)
+    assert object_metadata.size == object_size
+    assert int(object_metadata.checksums.crc32c) == object_checksum
+
+    mrd = AsyncMultiRangeDownloader(grpc_client, _ZONAL_BUCKET, object_name)
+    buffer = BytesIO()
+    await mrd.open()
+    # (0, 0) means read the whole object
+    await mrd.download_ranges([(0, 0, buffer)])
+    await mrd.close()
+    assert buffer.getvalue() == object_data
+    assert mrd.persisted_size == object_size
 
     # Clean up; use json client (i.e. `storage_client` fixture) to delete.
     blobs_to_delete.append(storage_client.bucket(_ZONAL_BUCKET).blob(object_name))