Merge pull request #47 from brain-bican/add_cli_library_generation

Add functionality to parse data catalog's large file metadata manifest

bkbit/cli.py

@@ -1,8 +1,9 @@
 import click
 from bkbit.model_converters.sheets_converter import schema2model
-from bkbit.data_translators.library_generation_translator import specimen2jsonld
 from bkbit.model_converters.yaml2sheet_converter import yaml2cvs
+from bkbit.data_translators.library_generation_translator import specimen2jsonld
 from bkbit.data_translators.file_manifest_translator import filemanifest2jsonld
+from bkbit.data_translators.specimen_metadata_translator import list_library_aliquot
 from bkbit.data_translators.genome_annotation_translator import gff2jsonld
 from bkbit.utils.get_ncbi_taxonomy import download_ncbi_taxonomy
 from bkbit.model_editors.linkml_trimmer import linkml_trimmer
@@ -14,9 +15,10 @@ def cli():
 
 # Add commands to the CLI group
 cli.add_command(schema2model)
-cli.add_command(specimen2jsonld)
 cli.add_command(yaml2cvs)
+cli.add_command(specimen2jsonld)
 cli.add_command(filemanifest2jsonld)
+cli.add_command(list_library_aliquot)
 cli.add_command(gff2jsonld)
 cli.add_command(download_ncbi_taxonomy)
 cli.add_command(linkml_trimmer)

bkbit/data_translators/file_manifest_translator.py

@@ -69,9 +69,17 @@ def serialize_to_jsonld(objects):
 
 ##OPTIONS##
 # Option #1: List all library aliquots in the file manifest.
-@click.option('--list_library_aliquots', is_flag=True, help='List all library aliquots in the file manifest.')  
+@click.option('-l', '--list_library_aliquots', is_flag=True, help='List all library aliquots in the file manifest.')  
 
 def filemanifest2jsonld(file_manifest_path: str, list_library_aliquots: bool):
+    """
+    Generates a JSON-LD representation of the digital objects and checksums in the given file manifest.
+
+    Args:
+        file_manifest_path (str): The path to the file manifest CSV file.
+        list_library_aliquots (bool): List all library aliquots in the file manifest.
+    """
+
     digital_and_checksum_objects, specimen_ids = process_csv(file_manifest_path)
     if list_library_aliquots:
         with open('file_manifest_library_aliquots.txt', 'w') as f:

bkbit/data_translators/specimen_metadata_translator.py

@@ -0,0 +1,37 @@
+import csv
+import click
+
+def extract_specimen_ids(csv_file_path):
+    """
+    Reads a CSV file and prints the 'Specimen ID' column to the command line.
+
+    Parameters:
+    - csv_file_path: str, path to the input CSV file.
+    """
+    with open(csv_file_path, 'r', encoding='utf-8') as csv_file:
+        reader = csv.DictReader(csv_file)
+
+        # Ensure 'Specimen ID' column exists in the CSV
+        if 'Specimen ID' not in reader.fieldnames:
+            raise ValueError("The CSV file does not contain the 'Specimen ID' column.")
+
+        # Print 'Specimen ID' values to the command line
+        for row in reader:
+            specimen_id = row['Specimen ID']
+            if specimen_id.startswith("LA"):
+                print(specimen_id)
+
+@click.command
+@click.argument('specimen_metadata_file_path')
+
+def list_library_aliquot(specimen_metadata_file_path):
+    """
+    Extracts and prints all the Library Aliquot NHash IDs from Data Catalog's specimen metadata file.
+
+    Args:
+        specimen_metadata_file_path (str): Path to the specimen metadata file.
+    """
+    extract_specimen_ids(specimen_metadata_file_path)
+
+if __name__ == '__main__':  
+    list_library_aliquot()