Skip to content

aws

AWS Cloud Utility API

This module provides utility functions to interact with AWS services.

Functions:

Functions

download_s3_file 

download_s3_file(key: str, dst: Path, bucket: str, client: boto3.client = None, checksum: str = 'size', config: Config | None = Config(signature_version=UNSIGNED)) -> bool

Download a file from S3

Parameters:

  • key

    (str) –

    Object key

  • dst

    (Path) –

    Destination path

  • bucket

    (str) –

    Bucket name

  • client

    (client, default: None ) –

    S3 client

  • checksum

    (str, default: 'size' ) –

    Checksum type. Defaults to "size".

  • config

    (Config, default: Config(signature_version=UNSIGNED) ) –

    Boto3 config. Defaults to Config(signature_version=UNSIGNED).

Returns:

  • bool ( bool ) –

    True if file was downloaded, False if already exists

Source code in helia_edge/utils/aws.py 
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
def download_s3_file(
    key: str,
    dst: Path,
    bucket: str,
    client: boto3.client = None,
    checksum: str = "size",
    config: Config | None = Config(signature_version=UNSIGNED),
) -> bool:
    """Download a file from S3

    Args:
        key (str): Object key
        dst (Path): Destination path
        bucket (str): Bucket name
        client (boto3.client): S3 client
        checksum (str, optional): Checksum type. Defaults to "size".
        config (Config, optional): Boto3 config. Defaults to Config(signature_version=UNSIGNED).

    Returns:
        bool: True if file was downloaded, False if already exists
    """

    if client is None:
        client = _get_s3_client(config)

    if not dst.is_file():
        pass
    elif checksum == "size":
        obj = client.head_object(Bucket=bucket, Key=key)
        if dst.stat().st_size == obj["ContentLength"]:
            return False
    elif checksum == "md5":
        obj = client.head_object(Bucket=bucket, Key=key)
        etag = obj["ETag"]
        checksum_type = obj.get("ChecksumAlgorithm", ["md5"])[0]
        calculated_checksum = compute_checksum(dst, checksum)
        if etag == calculated_checksum and checksum_type.lower() == "md5":
            return False
    # END IF

    client.download_file(
        Bucket=bucket,
        Key=key,
        Filename=str(dst),
    )

    return True

download_s3_object 

download_s3_object(item: dict[str, str], dst: Path, bucket: str, client: boto3.client = None, checksum: str = 'size', config: Config | None = Config(signature_version=UNSIGNED)) -> bool

Download an object from S3

Parameters:

  • item

    (dict[str, str]) –

    Object metadata

  • dst

    (Path) –

    Destination path

  • bucket

    (str) –

    Bucket name

  • client

    (client, default: None ) –

    S3 client

  • checksum

    (str, default: 'size' ) –

    Checksum type. Defaults to "size".

  • config

    (Config, default: Config(signature_version=UNSIGNED) ) –

    Boto3 config. Defaults to Config(signature_version=UNSIGNED).

Returns:

  • bool ( bool ) –

    True if file was downloaded, False if already exists

Source code in helia_edge/utils/aws.py 
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
def download_s3_object(
    item: dict[str, str],
    dst: Path,
    bucket: str,
    client: boto3.client = None,
    checksum: str = "size",
    config: Config | None = Config(signature_version=UNSIGNED),
) -> bool:
    """Download an object from S3

    Args:
        item (dict[str, str]): Object metadata
        dst (Path): Destination path
        bucket (str): Bucket name
        client (boto3.client): S3 client
        checksum (str, optional): Checksum type. Defaults to "size".
        config (Config, optional): Boto3 config. Defaults to Config(signature_version=UNSIGNED).

    Returns:
        bool: True if file was downloaded, False if already exists
    """

    # Is a directory, skip
    if item["Key"].endswith("/"):
        os.makedirs(dst, exist_ok=True)
        return False

    if not dst.is_file():
        pass
    elif checksum == "size":
        if dst.stat().st_size == item["Size"]:
            return False
    elif checksum == "md5":
        etag = item["ETag"]
        checksum_type = item.get("ChecksumAlgorithm", ["md5"])[0]
        calculated_checksum = compute_checksum(dst, checksum)
        if etag == calculated_checksum and checksum_type.lower() == "md5":
            return False
    # END IF

    if client is None:
        client = _get_s3_client()

    os.makedirs(dst.parent, exist_ok=True)

    client.download_file(
        Bucket=bucket,
        Key=item["Key"],
        Filename=str(dst),
    )

    return True

download_s3_objects 

download_s3_objects(bucket: str, prefix: str, dst: Path, checksum: str = 'size', progress: bool = True, num_workers: int | None = None, config: Config | None = Config(signature_version=UNSIGNED))

Download all objects in a S3 bucket with a given prefix.

.. deprecated:: Use :func:download_s3_prefix instead. This function preserves the full S3 key (including the prefix) when building local paths, which causes files to be nested one level too deep when dst already contains the prefix directory. The replacement strips the prefix so that dst is always the root of the downloaded tree.

Parameters:

  • bucket

    (str) –

    Bucket name

  • prefix

    (str) –

    Prefix to filter objects

  • dst

    (Path) –

    Destination directory

  • checksum

    (str, default: 'size' ) –

    Checksum type. Defaults to "size".

  • progress

    (bool, default: True ) –

    Show progress bar. Defaults to True.

  • num_workers

    (int | None, default: None ) –

    Number of workers. Defaults to None.

  • config

    (Config | None, default: Config(signature_version=UNSIGNED) ) –

    Boto3 config. Defaults to Config(signature_version=UNSIGNED).

Source code in helia_edge/utils/aws.py 
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
def download_s3_objects(
    bucket: str,
    prefix: str,
    dst: Path,
    checksum: str = "size",
    progress: bool = True,
    num_workers: int | None = None,
    config: Config | None = Config(signature_version=UNSIGNED),
):
    """Download all objects in a S3 bucket with a given prefix.

    .. deprecated::
        Use :func:`download_s3_prefix` instead.  This function preserves the
        full S3 key (including the prefix) when building local paths, which
        causes files to be nested one level too deep when ``dst`` already
        contains the prefix directory.  The replacement strips the prefix so
        that ``dst`` is always the root of the downloaded tree.

    Args:
        bucket (str): Bucket name
        prefix (str): Prefix to filter objects
        dst (Path): Destination directory
        checksum (str, optional): Checksum type. Defaults to "size".
        progress (bool, optional): Show progress bar. Defaults to True.
        num_workers (int | None, optional): Number of workers. Defaults to None.
        config (Config | None, optional): Boto3 config. Defaults to Config(signature_version=UNSIGNED).

    """

    warnings.warn(
        "download_s3_objects is deprecated and has a known path-nesting bug. "
        "Use download_s3_prefix instead.",
        DeprecationWarning,
        stacklevel=2,
    )

    client = _get_s3_client(config)

    # Fetch all objects in the bucket with the given prefix
    items = []
    fetching = True
    next_token = None
    while fetching:
        if next_token is None:
            response = client.list_objects_v2(Bucket=bucket, Prefix=prefix)
        else:
            response = client.list_objects_v2(Bucket=bucket, Prefix=prefix, ContinuationToken=next_token)
        items.extend(response["Contents"])
        next_token = response.get("NextContinuationToken", None)
        fetching = next_token is not None
    # END WHILE

    logger.debug(f"Found {len(items)} objects in {bucket}/{prefix}")

    os.makedirs(dst, exist_ok=True)

    func = functools.partial(download_s3_object, bucket=bucket, client=client, checksum=checksum)

    pbar = tqdm(total=len(items), unit="objects") if progress else None

    with ThreadPoolExecutor(max_workers=num_workers) as executor:
        futures = (
            executor.submit(
                func,
                item,
                dst / item["Key"],
            )
            for item in items
        )
        for future in as_completed(futures):
            err = future.exception()
            if err:
                logger.exception("Failed on file")
            if pbar:
                pbar.update(1)

download_s3_prefix 

download_s3_prefix(bucket: str, prefix: str, dst: Path, checksum: str = 'size', progress: bool = True, num_workers: int | None = None, config: Config | None = Config(signature_version=UNSIGNED)) -> int

Download all objects under an S3 prefix into a local directory.

Unlike :func:download_s3_objects, this function strips the prefix from each object key before joining it with dst, so that dst becomes the root of the downloaded tree.

Example::

# S3 objects:  s3://my-bucket/datasets/ptbxl/00001.h5
#              s3://my-bucket/datasets/ptbxl/00002.h5
download_s3_prefix(
    bucket="my-bucket",
    prefix="datasets/ptbxl",
    dst=Path("./data/ptbxl"),
)
# Results in: ./data/ptbxl/00001.h5
#             ./data/ptbxl/00002.h5

Parameters:

  • bucket

    (str) –

    Bucket name.

  • prefix

    (str) –

    Key prefix to filter objects. A trailing / is added automatically if missing.

  • dst

    (Path) –

    Local directory that will mirror the contents found under prefix.

  • checksum

    (str, default: 'size' ) –

    Checksum strategy ("size" or "md5"). Defaults to "size".

  • progress

    (bool, default: True ) –

    Show a tqdm progress bar. Defaults to True.

  • num_workers

    (int | None, default: None ) –

    Thread-pool size. None uses the :class:~concurrent.futures.ThreadPoolExecutor default.

  • config

    (Config | None, default: Config(signature_version=UNSIGNED) ) –

    Boto3 client config. Defaults to unsigned requests.

Returns:

  • int ( int ) –

    Number of objects downloaded (excludes skipped / up-to-date).

Source code in helia_edge/utils/aws.py 
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
def download_s3_prefix(
    bucket: str,
    prefix: str,
    dst: Path,
    checksum: str = "size",
    progress: bool = True,
    num_workers: int | None = None,
    config: Config | None = Config(signature_version=UNSIGNED),
) -> int:
    """Download all objects under an S3 prefix into a local directory.

    Unlike :func:`download_s3_objects`, this function **strips the prefix**
    from each object key before joining it with *dst*, so that *dst* becomes
    the root of the downloaded tree.

    Example::

        # S3 objects:  s3://my-bucket/datasets/ptbxl/00001.h5
        #              s3://my-bucket/datasets/ptbxl/00002.h5
        download_s3_prefix(
            bucket="my-bucket",
            prefix="datasets/ptbxl",
            dst=Path("./data/ptbxl"),
        )
        # Results in: ./data/ptbxl/00001.h5
        #             ./data/ptbxl/00002.h5

    Args:
        bucket (str): Bucket name.
        prefix (str): Key prefix to filter objects.  A trailing ``/`` is
            added automatically if missing.
        dst (Path): Local directory that will mirror the contents found
            under *prefix*.
        checksum (str, optional): Checksum strategy (``"size"`` or
            ``"md5"``). Defaults to ``"size"``.
        progress (bool, optional): Show a ``tqdm`` progress bar.
            Defaults to ``True``.
        num_workers (int | None, optional): Thread-pool size.  ``None``
            uses the :class:`~concurrent.futures.ThreadPoolExecutor`
            default.
        config (Config | None, optional): Boto3 client config.
            Defaults to unsigned requests.

    Returns:
        int: Number of objects downloaded (excludes skipped / up-to-date).
    """

    # Normalise prefix so stripping is reliable.
    norm_prefix = prefix.rstrip("/") + "/" if prefix and not prefix.endswith("/") else prefix

    client = _get_s3_client(config)
    items = _list_s3_objects(client, bucket, norm_prefix)

    logger.debug(f"Found {len(items)} objects in s3://{bucket}/{norm_prefix}")

    os.makedirs(dst, exist_ok=True)

    func = functools.partial(download_s3_object, bucket=bucket, client=client, checksum=checksum)
    downloaded = 0

    pbar = tqdm(total=len(items), unit="files") if progress else None

    def _local_path(key: str) -> Path:
        """Strip the prefix and join onto *dst*."""
        relative = key[len(norm_prefix):] if key.startswith(norm_prefix) else key
        return dst / PurePosixPath(relative)

    with ThreadPoolExecutor(max_workers=num_workers) as executor:
        futures = {
            executor.submit(func, item, _local_path(item["Key"])): item
            for item in items
        }
        for future in as_completed(futures):
            err = future.exception()
            if err:
                item = futures[future]
                logger.exception("Failed downloading %s", item["Key"])
            else:
                if future.result():
                    downloaded += 1
            if pbar:
                pbar.update(1)
        # END FOR
    # END WITH

    if pbar:
        pbar.close()

    return downloaded