Cleanup

- Remove circular dependency of mapping by moving all to `mappings.py`
- Constants moved to `constants.py`

Author: pbashyal-nmdp

pyard/__init__.py

@@ -23,7 +23,7 @@
 #
 from .blender import blender as dr_blender
 from .broad_splits import find_splits as find_broad_splits
-from .misc import DEFAULT_CACHE_SIZE
+from .constants import DEFAULT_CACHE_SIZE
 from .misc import get_imgt_db_versions as db_versions
 
 __author__ = """NMDP Bioinformatics"""

pyard/ard.py

@@ -33,11 +33,13 @@
 from .misc import (
     get_n_field_allele,
     get_2field_allele,
-    expression_chars,
-    DEFAULT_CACHE_SIZE,
+    validate_reduction_type,
+)
+from .constants import (
     HLA_regex,
     VALID_REDUCTION_TYPES,
-    validate_reduction_type,
+    expression_chars,
+    DEFAULT_CACHE_SIZE,
 )
 from .smart_sort import smart_sort_comparator
 

pyard/constants.py

@@ -0,0 +1,10 @@
+import re
+
+DEFAULT_CACHE_SIZE = 1_000
+
+HLA_regex = re.compile("^HLA-")
+
+VALID_REDUCTION_TYPES = ["G", "P", "lg", "lgx", "W", "exon", "U2"]
+expression_chars = ["N", "Q", "L", "S"]
+# List of P and G characters
+PandG_chars = ["P", "G"]

pyard/data_repository.py

@@ -23,7 +23,6 @@
 import copy
 import functools
 import sqlite3
-from collections import namedtuple
 
 import pandas as pd
 
@@ -37,32 +36,15 @@
     load_serology_mappings,
     load_latest_version,
 )
-from .misc import expression_chars
+from .constants import expression_chars
+from .mappings import ars_mapping_tables, ARSMapping, code_mapping_tables
 from .misc import (
     get_2field_allele,
     get_3field_allele,
     number_of_fields,
     get_1field_allele,
 )
 
-ars_mapping_tables = [
-    "dup_g",
-    "dup_lgx",
-    "g_group",
-    "p_group",
-    "lgx_group",
-    "exon_group",
-    "p_not_g",
-]
-ARSMapping = namedtuple("ARSMapping", ars_mapping_tables)
-
-code_mapping_tables = [
-    "alleles",
-    "xx_codes",
-    "who_alleles",
-    "who_group",
-]
-
 
 def expression_reduce(df):
     """

pyard/db.py

@@ -24,7 +24,7 @@
 import sqlite3
 from typing import Tuple, Dict, Set, List
 
-from .data_repository import ARSMapping
+from .mappings import ARSMapping
 from .misc import get_imgt_db_versions, get_default_db_directory
 
 

pyard/mappings.py

@@ -0,0 +1,20 @@
+from collections import namedtuple
+
+ars_mapping_tables = [
+    "dup_g",
+    "dup_lgx",
+    "g_group",
+    "p_group",
+    "lgx_group",
+    "exon_group",
+    "p_not_g",
+]
+code_mapping_tables = [
+    "alleles",
+    "exp_alleles",
+    "xx_codes",
+    "who_alleles",
+    "who_group",
+]
+
+ARSMapping = namedtuple("ARSMapping", ars_mapping_tables)

pyard/misc.py

@@ -1,17 +1,9 @@
 # List of expression characters
 import pathlib
-import re
 import tempfile
 from typing import List
 
-HLA_regex = re.compile("^HLA-")
-
-VALID_REDUCTION_TYPES = ["G", "P", "lg", "lgx", "W", "exon", "U2"]
-expression_chars = ["N", "Q", "L", "S"]
-# List of P and G characters
-PandG_chars = ["P", "G"]
-
-DEFAULT_CACHE_SIZE = 1_000
+from pyard.constants import VALID_REDUCTION_TYPES, expression_chars, PandG_chars
 
 
 def get_n_field_allele(allele: str, n: int, preserve_expression=False) -> str:

scripts/pyard

@@ -24,6 +24,7 @@
 import argparse
 import sys
 
+from pyard.constants import VALID_REDUCTION_TYPES
 import pyard.misc
 from pyard.exceptions import InvalidAlleleError
 from pyard.misc import get_data_dir, get_imgt_version
@@ -57,7 +58,7 @@ if __name__ == "__main__":
     parser.add_argument(
         "-r",
         "--redux-type",
-        choices=pyard.misc.VALID_REDUCTION_TYPES,
+        choices=VALID_REDUCTION_TYPES,
         dest="redux_type",
         help="Reduction Method",
     )
@@ -85,11 +86,12 @@ if __name__ == "__main__":
         if args.redux_type:
             print(ard.redux(args.gl_string, args.redux_type))
         else:
-            for redux_type in pyard.misc.VALID_REDUCTION_TYPES:
+            for redux_type in VALID_REDUCTION_TYPES:
                 redux_type_info = f"Reduction Method: {redux_type}"
                 print(redux_type_info)
                 print("-" * len(redux_type_info))
                 print(ard.redux(args.gl_string, redux_type))
+                print()
     except InvalidAlleleError as e:
         print("Error:", e)
 

scripts/pyard-status

@@ -26,6 +26,7 @@ import os
 import re
 
 import pyard
+import pyard.mappings
 from pyard import db, data_repository
 from pyard.misc import get_data_dir
 
@@ -93,8 +94,8 @@ if __name__ == "__main__":
             print(f"|{'Table Name':20}|{'Rows':20}|")
             print(f"|{'-' * 41}|")
             for table in (
-                data_repository.ars_mapping_tables
-                + data_repository.code_mapping_tables
+                pyard.mappings.ars_mapping_tables
+                + pyard.mappings.code_mapping_tables
                 + ["mac_codes"]
             ):
                 if db.table_exists(db_connection, table):

tests/test_pyard.py

@@ -33,6 +33,7 @@
 import unittest
 
 import pyard
+from pyard.constants import DEFAULT_CACHE_SIZE
 from pyard.exceptions import InvalidAlleleError, InvalidMACError, InvalidTypingError
 from pyard.misc import validate_reduction_type
 
@@ -170,11 +171,9 @@ def test_xx_codes_broad_split(self):
     def test_cache_info(self):
         # validate the default cache size
         self.assertEqual(
-            self.ard._redux_allele.cache_info().maxsize, pyard.misc.DEFAULT_CACHE_SIZE
-        )
-        self.assertEqual(
-            self.ard.redux.cache_info().maxsize, pyard.misc.DEFAULT_CACHE_SIZE
+            self.ard._redux_allele.cache_info().maxsize, DEFAULT_CACHE_SIZE
         )
+        self.assertEqual(self.ard.redux.cache_info().maxsize, DEFAULT_CACHE_SIZE)
         # validate you can change the cache size
         higher_cache_size = 5_000_000
         another_ard = pyard.init(