Merge pull request #16 from meero-com/chore/add-license

License the project and correct wording

LICENSE

@@ -0,0 +1,22 @@
+MIT License
+
+Copyright (c) 2024 Meero
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+

README.md

@@ -1,4 +1,6 @@
-# Media Archiver
+# Archiver
+
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
 [![Quality analysis](https://github.com/meero-com/archiver/actions/workflows/quality.yaml/badge.svg)](https://github.com/meero-com/archiver/actions/workflows/quality.yaml) [![CICD](https://github.com/meero-com/archiver/actions/workflows/ci.yaml/badge.svg)](https://github.com/meero-com/archiver/actions/workflows/ci.yaml)
 
@@ -7,7 +9,7 @@ Create a zip archive of several S3 files and upload it to an S3 bucket.
 ## Features
 
 - Retrieve payloads from an SQS Queue.
-- Create a Zip archive from a list of media.
+- Create a Zip archive from a list of files.
 - Optionally create a directory structure inside the zip.
 - Upload the zip file to an S3 bucket.
 - Notify a consumer once the archive is ready to be downloaded.
@@ -48,7 +50,7 @@ Below is a table with each required and optional environment variables:
 | `SQS_DESTINATION_QUEUE` | SQS Queue to send message to downstream consumer. | `None` |
 | `SQS_SOURCE_QUEUE` | SQS Queue to retrieve payloads from. | `None` |
 | `S3_DESTINATION_BUCKET` | Target S3 bucket to store the archive files. | `None` |
-| `S3_SOURCE_BUCKET` | Source S3 bucket that contains the media used to create the archive by default. | `None` |
+| `S3_SOURCE_BUCKET` | Source S3 bucket that contains the files used to create the archive by default. | `None` |
 | `S3_FILE_PREFIX` | The prefix that will be added to each archive created. | `download` |
 | `APP_DEBUG` | Enable debug log level. | `0` |
 | `DEV_MODE` | Use console rendering for logs instead of JSON rendering. | `0` |
@@ -59,7 +61,7 @@ This project is intended to be deployed as an ECS Service inside AWS.
 It requires the following permissions:
 
 - Interact with an SQS Queue.
-- Read from the source S3 bucket (media files).
+- Read from the source S3 bucket (S3 objects).
 - Write to the destination S3 bucket (zip archives).
 
 It should be able to scale based on the SQS Queue's number of message.

src/archiver/main.py

@@ -9,7 +9,7 @@
 
 Each processed message will trigger the following processing:
     - Create an in-memory file-like object based ZipFile.
-    - Download each media and write it to the archive.
+    - Download each file and write it to the archive.
     - Upload the archive to the S3_DESTINATION_BUCKET.
     - Send SQS message to downstream consumers.
 """
@@ -40,7 +40,7 @@
     process_file,
     generate_s3_source_infos_from_payload
 )
-from archiver.payload import MediaSpec, PayloadSpec
+from archiver.payload import FileSpec, PayloadSpec
 from archiver.logs import bootstrap_logging
 
 
@@ -91,7 +91,7 @@ def process_archive(s3_client, sqs_client, sqs_response, logger):
     )
     archive_s3_path = generate_s3_destination_path(datetime.now())
 
-    source_files = [MediaSpec(**item) for item in content['files']]
+    source_files = [FileSpec(**item) for item in content['files']]
 
     logger.info(
         "processing message for archive %s",

src/archiver/payload.py

@@ -5,8 +5,8 @@
 from pydantic import BaseModel
 
 
-class MediaSpec(BaseModel):
-    """Media definition spec.
+class FileSpec(BaseModel):
+    """File definition spec.
     The `source` attribute represents an S3 prefix or a full s3 path.
     The optional `destination` attribute sets the directory and
     file name in the created Zip archive.
@@ -17,7 +17,7 @@ class MediaSpec(BaseModel):
 
 class PayloadSpec(BaseModel):
     """Archiver payload spec."""
-    files: List[MediaSpec]
+    files: List[FileSpec]
     metadata: Optional[Dict[str, Any]] = None
 
 

src/archiver/utils.py

@@ -8,7 +8,7 @@
 import re
 
 from archiver.config import S3_SOURCE_BUCKET, S3_FILE_PREFIX
-from archiver.payload import MediaSpec
+from archiver.payload import FileSpec
 
 
 def process_file(s3_client, zip_file, file, s3_bucket, s3_key):
@@ -29,19 +29,19 @@ def process_file(s3_client, zip_file, file, s3_bucket, s3_key):
     return data
 
 
-def _forge_zip_path(file: MediaSpec):
+def _forge_zip_path(file: FileSpec):
     """Return the path of the file used inside the Zip archive.
 
     This function covers the following scenarios:
     - `destination` has no value: path is `source`;
     - `destination` has no extension: put `source` in `destination` directory;
     - `destination` has an extension: `destination` is file location.
 
-    >>> _forge_zip_path(MediaSpec("abc/def/file.jpg", None))
+    >>> _forge_zip_path(FileSpec("abc/def/file.jpg", None))
     'file.jpg'
-    >>> _forge_zip_path(MediaSpec("file.jpg", "directory"))
+    >>> _forge_zip_path(FileSpec("file.jpg", "directory"))
     'directory/file.jpg'
-    >>> _forge_zip_path(MediaSpec("file.jpg", "directory/pretty name.jpg"))
+    >>> _forge_zip_path(FileSpec("file.jpg", "directory/pretty name.jpg"))
     'directory/pretty name.jpg'
     """
     _, filename = path.split(file.source)
@@ -81,7 +81,7 @@ def generate_s3_destination_path(creation_date: datetime) -> str:
     archive_path = f"{digest}/{file_prefix}-{filename}.zip"
     return archive_path
 
-def generate_s3_source_infos_from_payload(file: MediaSpec):
+def generate_s3_source_infos_from_payload(file: FileSpec):
     """Extract s3 source informations from the payload
 
     The source can be just an s3 key in the S3_SOURCE_BUCKET or a

tests/test_utils.py

@@ -15,9 +15,9 @@
 )
 def test_forge_zip_path(source, destination, expected_path):
     import archiver.utils
-    from archiver.payload import MediaSpec
-    media_spec = MediaSpec(source=source, destination=destination)
-    assert archiver.utils._forge_zip_path(media_spec) == expected_path
+    from archiver.payload import FileSpec
+    file_spec = FileSpec(source=source, destination=destination)
+    assert archiver.utils._forge_zip_path(file_spec) == expected_path
 
 
 def test_generate_destination_path():
@@ -36,13 +36,13 @@ def test_generate_destination_path():
 )
 def test_generate_s3_source_with_no_s3_uri(source, destination):
     from archiver.utils import generate_s3_source_infos_from_payload
-    from archiver.payload import MediaSpec
+    from archiver.payload import FileSpec
     from archiver.config import S3_SOURCE_BUCKET
 
-    media_spec = MediaSpec(source=source, destination=destination)
-    s3_bucket, s3_key = generate_s3_source_infos_from_payload(media_spec)
+    file_spec = FileSpec(source=source, destination=destination)
+    s3_bucket, s3_key = generate_s3_source_infos_from_payload(file_spec)
     assert s3_bucket == S3_SOURCE_BUCKET
-    assert s3_key == media_spec.source
+    assert s3_key == file_spec.source
 
 @pytest.mark.parametrize(
     'source,destination',
@@ -52,10 +52,10 @@ def test_generate_s3_source_with_no_s3_uri(source, destination):
 )
 def test_generate_s3_source_with_s3_uri(source, destination):
     from archiver.utils import generate_s3_source_infos_from_payload
-    from archiver.payload import MediaSpec
+    from archiver.payload import FileSpec
     from archiver.config import S3_SOURCE_BUCKET
 
-    media_spec = MediaSpec(source=source, destination=destination)
-    s3_bucket, s3_key = generate_s3_source_infos_from_payload(media_spec)
+    file_spec = FileSpec(source=source, destination=destination)
+    s3_bucket, s3_key = generate_s3_source_infos_from_payload(file_spec)
     assert s3_bucket == "bucket_name"
     assert s3_key == "abc/def/file.jpg"