Merge pull request #8 from wtsi-npg/devel

Pull from devel to master to create release 1.0.1

CHANGELOG.md

@@ -0,0 +1,18 @@
+# Changelog
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [1.0.1]
+
+### Changed
+
+ - Add tags argument to generate_pac_bio_id
+ - Sort tags on creation of PacBioEntity object
+
+## [1.0.0]
+
+### Added
+
+ - Ability to generate a product id for a PacBio well

bin/generate_pac_bio_id

@@ -31,12 +31,19 @@ parser.add_argument(
 
 parser.add_argument("well_label", type=str, help="The well label")
 
+parser.add_argument(
+    "--tags",
+    type=str,
+    required=False,
+    help="A comma separated list of tag sequences to include in id generation",
+)
+
 args = parser.parse_args()
 
 
 def main():
     print(
-        f"{PacBioEntity(run_name=args.run_name, well_label=args.well_label).hash_product_id()}\n"
+        f"{PacBioEntity(run_name=args.run_name, well_label=args.well_label, tags=args.tags).hash_product_id()}\n"
     )
 
 

npg_id_generation/pac_bio.py

@@ -45,6 +45,14 @@ def attributes_are_non_empty_strings(cls, v):
             raise ValueError("Cannot be an empty string")
         return v
 
+    @validator("tags")
+    def sort_tags(cls, v):
+        if v is None:
+            return v
+        tags = v.split(",")
+        tags.sort()
+        return ",".join(tags)
+
     def hash_product_id(self):
         """Generate a sha256sum for the PacBio Entity"""
 

tests/test_hashing.py

@@ -136,3 +136,27 @@ def test_expected_hashes():
             PacBioEntity.parse_raw(json_str, content_type="json").hash_product_id()
             == expected_hash
         )
+
+
+def test_tags_sorted():
+    """Test that tags are automatically sorted alphabetically before id generation"""
+
+    pb_entity_1 = PacBioEntity(
+        run_name="MARATHON", well_label="A1", tags="TCGA,ACGT,TGAC,AACG"
+    )
+    assert pb_entity_1.tags == "AACG,ACGT,TCGA,TGAC"
+
+    pb_entity_2 = PacBioEntity(
+        run_name="MARATHON", well_label="A1", tags="ACGT,AACG,TGAC,TCGA"
+    )
+
+    pb_entity_3 = PacBioEntity.parse_raw(
+        '{"run_name": "MARATHON", "well_label": "A1", "tags": "TGAC,TCGA,AACG,ACGT"}'
+    )
+
+    assert pb_entity_1.tags == pb_entity_2.tags == pb_entity_3.tags
+    assert (
+        pb_entity_3.hash_product_id()
+        == pb_entity_2.hash_product_id()
+        == pb_entity_3.hash_product_id()
+    )