From 9465f6e46335ae3eea3be790f73026558c3c4cda Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon.koehn@dbsse.ethz.ch>
Date: Fri, 20 Dec 2024 14:02:49 +0100
Subject: [PATCH] add metadata to vpipe module

---
 .gitignore                    |  3 +++
 scripts/vp_transformer.py     | 26 +-------------------------
 src/sr2silo/__init__.py       |  4 ++++
 src/sr2silo/vpipe/__init__.py |  4 ++++
 src/sr2silo/vpipe/metadata.py | 28 ++++++++++++++++++++++++++++
 tests/vpipe/test_metadata.py  | 18 ++++++++++++++++++
 6 files changed, 58 insertions(+), 25 deletions(-)
 create mode 100644 src/sr2silo/vpipe/__init__.py
 create mode 100644 src/sr2silo/vpipe/metadata.py
 create mode 100644 tests/vpipe/test_metadata.py

diff --git a/.gitignore b/.gitignore
index 1faa6fe..1691913 100644
--- a/.gitignore
+++ b/.gitignore
@@ -136,3 +136,6 @@ poetry.lock
 
 # Output folder
 output
+
+# Secret files
+secrets
diff --git a/scripts/vp_transformer.py b/scripts/vp_transformer.py
index 88c395f..ae3b039 100644
--- a/scripts/vp_transformer.py
+++ b/scripts/vp_transformer.py
@@ -18,6 +18,7 @@
 from sr2silo.process import pair_normalize_reads
 from sr2silo.s3 import compress_bz2, upload_file_to_s3
 from sr2silo.translation import translate
+from sr2silo.vpipe.metadata import sample_id_decoder
 
 logging.basicConfig(
     level=logging.DEBUG, format="%(asctime)s - %(levelname)s - %(message)s"
@@ -37,31 +38,6 @@ def load_config(config_file: Path) -> dict:
         raise
 
 
-def sample_id_decoder(sample_id: str) -> dict:
-    """Decode the sample ID into individual components.
-
-    Args:
-        sample_id (str): The sample ID to decode.
-
-    Returns:
-        dict: A dictionary containing the decoded components.
-              containing the following keys:
-                - sequencing_well_position (str : sequencing well position)
-                - location_code (int : code of the location)
-                - sampling_date (str : date of the sampling)
-    """
-    components = sample_id.split("_")
-    # Assign components to meaningful variable names
-    well_position = components[0]  # A1
-    location_code = components[1]  # 10
-    sampling_date = f"{components[2]}-{components[3]}-{components[4]}"  # 2024-09-30
-    return {
-        "sequencing_well_position": well_position,
-        "location_code": location_code,
-        "sampling_date": sampling_date,
-    }
-
-
 def batch_id_decoder(batch_id: str) -> dict:
     """Decode the batch ID into individual components.
 
diff --git a/src/sr2silo/__init__.py b/src/sr2silo/__init__.py
index 775d0ba..bbab54f 100644
--- a/src/sr2silo/__init__.py
+++ b/src/sr2silo/__init__.py
@@ -5,4 +5,8 @@
 """sr2silo connects pairs, normalizes reads, and converts BAM to SAM files."""
 from __future__ import annotations
 
+import sr2silo.vpipe as vpipe
+
 __version__ = "0.0.2"
+
+__all__ = ["vpipe"]
diff --git a/src/sr2silo/vpipe/__init__.py b/src/sr2silo/vpipe/__init__.py
new file mode 100644
index 0000000..397901f
--- /dev/null
+++ b/src/sr2silo/vpipe/__init__.py
@@ -0,0 +1,4 @@
+"""Implements V-Pipe specific utilities.
+
+  i.e. extracting metadata from V-Pipe Filenaming Conventions.
+  """
diff --git a/src/sr2silo/vpipe/metadata.py b/src/sr2silo/vpipe/metadata.py
new file mode 100644
index 0000000..8dee106
--- /dev/null
+++ b/src/sr2silo/vpipe/metadata.py
@@ -0,0 +1,28 @@
+"""Extract metadata from V-Pipe Filenaming Conventions."""
+
+from __future__ import annotations
+
+
+def sample_id_decoder(sample_id: str) -> dict:
+    """Decode the sample ID into individual components.
+
+    Args:
+        sample_id (str): The sample ID to decode.
+
+    Returns:
+        dict: A dictionary containing the decoded components.
+              containing the following keys:
+                - sequencing_well_position (str : sequencing well position)
+                - location_code (int : code of the location)
+                - sampling_date (str : date of the sampling)
+    """
+    components = sample_id.split("_")
+    # Assign components to meaningful variable names
+    well_position = components[0]  # A1
+    location_code = components[1]  # 10
+    sampling_date = f"{components[2]}-{components[3]}-{components[4]}"  # 2024-09-30
+    return {
+        "sequencing_well_position": well_position,
+        "location_code": location_code,
+        "sampling_date": sampling_date,
+    }
diff --git a/tests/vpipe/test_metadata.py b/tests/vpipe/test_metadata.py
new file mode 100644
index 0000000..156c287
--- /dev/null
+++ b/tests/vpipe/test_metadata.py
@@ -0,0 +1,18 @@
+"""Implement tests for the metadata extraction functions."""
+
+
+from __future__ import annotations
+
+from sr2silo.vpipe.metadata import sample_id_decoder
+
+
+def test_sample_id_decoder():
+    """Test the sample_id_decoder function."""
+    sample_id = "A1_10_2024_09_30"
+    result = sample_id_decoder(sample_id)
+    expected = {
+        "sequencing_well_position": "A1",
+        "location_code": "10",
+        "sampling_date": "2024-09-30",
+    }
+    assert result == expected