Add IntegerSum transformation function (#50)

* Add IntegerSum transformation function

* Bump version

* Update README

README.md

@@ -62,21 +62,21 @@ We recommend using the provided Docker container.
 
 A pre-build version is available at [docker hub](https://hub.docker.com/repository/docker/ghga/metldata):
 ```bash
-docker pull ghga/metldata:0.4.3
+docker pull ghga/metldata:0.4.4
 ```
 
 Or you can build the container yourself from the [`./Dockerfile`](./Dockerfile):
 ```bash
 # Execute in the repo's root dir:
-docker build -t ghga/metldata:0.4.3 .
+docker build -t ghga/metldata:0.4.4 .
 ```
 
 For production-ready deployment, we recommend using Kubernetes, however,
 for simple use cases, you could execute the service using docker
 on a single server:
 ```bash
 # The entrypoint is preconfigured:
-docker run -p 8080:8080 ghga/metldata:0.4.3 --help
+docker run -p 8080:8080 ghga/metldata:0.4.4 --help
 ```
 
 If you prefer not to use containers, you may install the service from source:

metldata/__init__.py

@@ -15,4 +15,4 @@
 
 """Short description of package"""  # Please adapt to package
 
-__version__ = "0.4.3"
+__version__ = "0.4.4"

metldata/builtin_transformations/aggregate/func.py

@@ -126,6 +126,20 @@ def func(cls, data: Iterable[Any]) -> int:
         return sum(1 for _ in data)
 
 
+@register_function
+class IntegerSumAggregation(AggregationFunction):
+    """Transformation that returns the sum for a given sequence of integer
+    values."""
+
+    result_range_name = "integer"
+    result_range_cls_def = None
+    result_multivalued = False
+
+    @classmethod
+    def func(cls, data: Iterable[int]) -> int:
+        return sum(data)
+
+
 class ElementCountAggregation(AggregationFunction, ABC):
     """Aggregation that returns the counts of unique elements in the given data."""
 

tests/fixtures/transformations/aggregate/default/config.yaml

@@ -99,3 +99,10 @@ aggregations:
           - study_files.format
           - analysis_process_output_files.format
         function: StringElementCount
+      - output_path: file_summary.stats.total_size
+        input_paths:
+          - sequencing_process_files.size
+          - sample_files.size
+          - study_files.size
+          - analysis_process_output_files.size
+        function: IntegerSum

tests/fixtures/transformations/aggregate/default/transformed_metadata.yaml

@@ -35,6 +35,7 @@ dataset_stats:
             count: 4
           - value: VCF
             count: 3
+        total_size: 753721
     accession: GHGAD03742971815534
   - title: The B dataset
     types:
@@ -71,4 +72,5 @@ dataset_stats:
             count: 6
           - value: VCF
             count: 6
+        total_size: 1663486
     accession: GHGAD97673713575489

tests/fixtures/transformations/aggregate/default/transformed_model.yaml

@@ -240,6 +240,9 @@ slots:
   value:
     name: value
     from_schema: https://w3id.org/GHGA-Submission-Metadata-Schema
+  total_size:
+    name: total_size
+    from_schema: https://w3id.org/GHGA-Submission-Metadata-Schema
   dataset_stats:
     name: dataset_stats
     from_schema: https://w3id.org/GHGA-Submission-Metadata-Schema
@@ -427,6 +430,7 @@ classes:
     from_schema: https://w3id.org/GHGA-Submission-Metadata-Schema
     slots:
       - format
+      - total_size
     slot_usage:
       format:
         name: format
@@ -436,6 +440,12 @@ classes:
         range: StringValueCount
         inlined: true
         inlined_as_list: true
+      total_size:
+        name: total_size
+        multivalued: false
+        domain_of:
+          - AutoGeneratedClass3
+        range: integer
   AutoGeneratedClass4:
     name: AutoGeneratedClass4
     from_schema: https://w3id.org/GHGA-Submission-Metadata-Schema