metameq 2026.1.2__py3-none-any.whl → 2026.2.2__py3-none-any.whl

metameq/tests/test_metadata_extender.py

@@ -14,7 +14,8 @@ from metameq.src.util import \
     OVERWRITE_NON_NANS_KEY, LEAVE_REQUIREDS_BLANK_KEY, LEAVE_BLANK_VAL, \
     HOST_TYPE_SPECIFIC_METADATA_KEY, METADATA_TRANSFORMERS_KEY, \
     SOURCES_KEY, FUNCTION_KEY, PRE_TRANSFORMERS_KEY, POST_TRANSFORMERS_KEY, \
-    STUDY_SPECIFIC_METADATA_KEY
+    STUDY_SPECIFIC_METADATA_KEY, HOSTTYPE_COL_OPTIONS_KEY, \
+    SAMPLETYPE_COL_OPTIONS_KEY
 from metameq.src.metadata_extender import \
     id_missing_cols, get_qc_failures, get_reserved_cols, find_standard_cols, \
     find_nonstandard_cols, write_metadata_results, \
@@ -26,7 +27,7 @@ from metameq.src.metadata_extender import \
     _generate_metadata_for_a_host_type, _generate_metadata_for_host_types, \
     _transform_metadata, _populate_metadata_df, extend_metadata_df, \
     _get_study_specific_config, _output_metadata_df_to_files, \
-    INTERNAL_COL_KEYS, REQ_PLACEHOLDER
+    _get_specified_column_name, INTERNAL_COL_KEYS, REQ_PLACEHOLDER
 
 
 class TestMetadataExtender(TestCase):
@@ -747,16 +748,15 @@ class TestMetadataExtender(TestCase):
 
     # Tests for _fill_na_if_default
 
-    def test__fill_na_if_default_specific_overrides_settings(self):
+    def test__fill_na_if_default_has_default_in_settings(self):
         """Test that specific_dict default takes precedence over settings_dict."""
         input_df = pandas.DataFrame({
             "field1": ["value1", np.nan, "value3"],
             "field2": [np.nan, "value2", np.nan]
         })
-        specific_dict = {DEFAULT_KEY: "filled"}
-        settings_dict = {DEFAULT_KEY: "unused"}
+        settings_dict = {DEFAULT_KEY: "filled"}
 
-        result = _fill_na_if_default(input_df, specific_dict, settings_dict)
+        result = _fill_na_if_default(input_df, settings_dict)
 
         expected = pandas.DataFrame({
             "field1": ["value1", "filled", "value3"],
@@ -764,18 +764,19 @@ class TestMetadataExtender(TestCase):
         })
         assert_frame_equal(expected, result)
 
-    def test__fill_na_if_default_uses_settings_when_specific_missing(self):
-        """Test that settings_dict default is used when specific_dict has no default."""
+    def test__fill_na_if_default_no_default_in_settings(self):
+        """Test that NaN values are unchanged when no default is in settings."""
         input_df = pandas.DataFrame({
-            "field1": [np.nan]
+            "field1": ["value1", np.nan, "value3"],
+            "field2": [np.nan, "value2", np.nan]
         })
-        specific_dict = {}
-        settings_dict = {DEFAULT_KEY: "settings_default"}
+        settings_dict = {}
 
-        result = _fill_na_if_default(input_df, specific_dict, settings_dict)
+        result = _fill_na_if_default(input_df, settings_dict)
 
         expected = pandas.DataFrame({
-            "field1": ["settings_default"]
+            "field1": ["value1", np.nan, "value3"],
+            "field2": [np.nan, "value2", np.nan]
         })
         assert_frame_equal(expected, result)
 
@@ -1272,14 +1273,13 @@ class TestMetadataExtender(TestCase):
             SAMPLETYPE_SHORTHAND_KEY: ["stool", "stool"],
             QC_NOTE_KEY: ["", ""]
         })
-        global_plus_host_settings_dict = {
-            OVERWRITE_NON_NANS_KEY: False,
-            LEAVE_REQUIREDS_BLANK_KEY: False,
-            DEFAULT_KEY: "not provided"
-        }
+
         # Config is pre-resolved: sample type's metadata_fields already includes
         # host fields merged in, plus sample_type and qiita_sample_type
         host_type_config_dict = {
+            OVERWRITE_NON_NANS_KEY: False,
+            LEAVE_REQUIREDS_BLANK_KEY: False,
+            DEFAULT_KEY: "not provided",
             METADATA_FIELDS_KEY: {
                 "host_field": {
                     DEFAULT_KEY: "host_default",
@@ -1313,7 +1313,7 @@ class TestMetadataExtender(TestCase):
         }
 
         result_df, validation_msgs = _generate_metadata_for_a_sample_type_in_a_host_type(
-            input_df, "stool", global_plus_host_settings_dict, host_type_config_dict)
+            input_df, "stool", host_type_config_dict)
 
         expected_df = pandas.DataFrame({
             SAMPLE_NAME_KEY: ["sample1", "sample2"],
@@ -1336,12 +1336,11 @@ class TestMetadataExtender(TestCase):
             SAMPLETYPE_SHORTHAND_KEY: ["unknown_type"],
             QC_NOTE_KEY: [""]
         })
-        global_plus_host_settings_dict = {
+
+        host_type_config_dict = {
             OVERWRITE_NON_NANS_KEY: False,
             LEAVE_REQUIREDS_BLANK_KEY: False,
-            DEFAULT_KEY: "not provided"
-        }
-        host_type_config_dict = {
+            DEFAULT_KEY: "not provided",
             METADATA_FIELDS_KEY: {},
             SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {
                 "stool": {
@@ -1351,7 +1350,7 @@ class TestMetadataExtender(TestCase):
         }
 
         result_df, validation_msgs = _generate_metadata_for_a_sample_type_in_a_host_type(
-            input_df, "unknown_type", global_plus_host_settings_dict, host_type_config_dict)
+            input_df, "unknown_type", host_type_config_dict)
 
         expected_df = pandas.DataFrame({
             SAMPLE_NAME_KEY: ["sample1"],
@@ -1370,12 +1369,11 @@ class TestMetadataExtender(TestCase):
             SAMPLETYPE_SHORTHAND_KEY: ["stool", "blood", "stool"],
             QC_NOTE_KEY: ["", "", ""]
         })
-        global_plus_host_settings_dict = {
+
+        host_type_config_dict = {
             OVERWRITE_NON_NANS_KEY: False,
             LEAVE_REQUIREDS_BLANK_KEY: False,
-            DEFAULT_KEY: "not provided"
-        }
-        host_type_config_dict = {
+            DEFAULT_KEY: "not provided",
             METADATA_FIELDS_KEY: {},
             SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {
                 "stool": {
@@ -1393,7 +1391,7 @@ class TestMetadataExtender(TestCase):
         }
 
         result_df, validation_msgs = _generate_metadata_for_a_sample_type_in_a_host_type(
-            input_df, "stool", global_plus_host_settings_dict, host_type_config_dict)
+            input_df, "stool", host_type_config_dict)
 
         # Should only have the two stool samples
         self.assertEqual(2, len(result_df))
@@ -1408,12 +1406,11 @@ class TestMetadataExtender(TestCase):
             SAMPLETYPE_SHORTHAND_KEY: ["stool"],
             QC_NOTE_KEY: [""]
         })
-        global_plus_host_settings_dict = {
+
+        host_type_config_dict = {
             OVERWRITE_NON_NANS_KEY: False,
             LEAVE_REQUIREDS_BLANK_KEY: True,
-            DEFAULT_KEY: "not provided"
-        }
-        host_type_config_dict = {
+            DEFAULT_KEY: "not provided",
             METADATA_FIELDS_KEY: {},
             SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {
                 "stool": {
@@ -1428,7 +1425,7 @@ class TestMetadataExtender(TestCase):
         }
 
         result_df, validation_msgs = _generate_metadata_for_a_sample_type_in_a_host_type(
-            input_df, "stool", global_plus_host_settings_dict, host_type_config_dict)
+            input_df, "stool", host_type_config_dict)
 
         self.assertEqual(LEAVE_BLANK_VAL, result_df["required_field"].iloc[0])
 
@@ -1440,12 +1437,11 @@ class TestMetadataExtender(TestCase):
             SAMPLETYPE_SHORTHAND_KEY: ["stool"],
             QC_NOTE_KEY: [""]
         })
-        global_plus_host_settings_dict = {
+
+        host_type_config_dict = {
             OVERWRITE_NON_NANS_KEY: False,
             LEAVE_REQUIREDS_BLANK_KEY: False,
-            DEFAULT_KEY: "global_default"
-        }
-        host_type_config_dict = {
+            DEFAULT_KEY: "global_default",
             METADATA_FIELDS_KEY: {},
             SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {
                 "stool": {
@@ -1460,7 +1456,7 @@ class TestMetadataExtender(TestCase):
         }
 
         result_df, validation_msgs = _generate_metadata_for_a_sample_type_in_a_host_type(
-            input_df, "stool", global_plus_host_settings_dict, host_type_config_dict)
+            input_df, "stool", host_type_config_dict)
 
         # When leave_requireds_blank is False, NaN values get filled with global default
         self.assertEqual("global_default", result_df["required_field"].iloc[0])
@@ -1474,12 +1470,11 @@ class TestMetadataExtender(TestCase):
             QC_NOTE_KEY: [""],
             "existing_field": ["original_value"]
         })
-        global_plus_host_settings_dict = {
+
+        host_type_config_dict = {
             OVERWRITE_NON_NANS_KEY: True,
             LEAVE_REQUIREDS_BLANK_KEY: False,
-            DEFAULT_KEY: "not provided"
-        }
-        host_type_config_dict = {
+            DEFAULT_KEY: "not provided",
             METADATA_FIELDS_KEY: {},
             SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {
                 "stool": {
@@ -1494,7 +1489,7 @@ class TestMetadataExtender(TestCase):
         }
 
         result_df, validation_msgs = _generate_metadata_for_a_sample_type_in_a_host_type(
-            input_df, "stool", global_plus_host_settings_dict, host_type_config_dict)
+            input_df, "stool", host_type_config_dict)
 
         self.assertEqual("new_value", result_df["existing_field"].iloc[0])
 
@@ -1507,12 +1502,11 @@ class TestMetadataExtender(TestCase):
             QC_NOTE_KEY: [""],
             "existing_field": ["original_value"]
         })
-        global_plus_host_settings_dict = {
+
+        host_type_config_dict = {
             OVERWRITE_NON_NANS_KEY: False,
             LEAVE_REQUIREDS_BLANK_KEY: False,
-            DEFAULT_KEY: "not provided"
-        }
-        host_type_config_dict = {
+            DEFAULT_KEY: "not provided",
             METADATA_FIELDS_KEY: {},
             SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {
                 "stool": {
@@ -1527,7 +1521,7 @@ class TestMetadataExtender(TestCase):
         }
 
         result_df, validation_msgs = _generate_metadata_for_a_sample_type_in_a_host_type(
-            input_df, "stool", global_plus_host_settings_dict, host_type_config_dict)
+            input_df, "stool", host_type_config_dict)
 
         self.assertEqual("original_value", result_df["existing_field"].iloc[0])
 
@@ -1539,14 +1533,13 @@ class TestMetadataExtender(TestCase):
             SAMPLETYPE_SHORTHAND_KEY: ["feces"],
             QC_NOTE_KEY: [""]
         })
-        global_plus_host_settings_dict = {
-            OVERWRITE_NON_NANS_KEY: False,
-            LEAVE_REQUIREDS_BLANK_KEY: False,
-            DEFAULT_KEY: "not provided"
-        }
+
         # Config is pre-resolved: alias "feces" has its own metadata_fields
         # that is a copy of "stool"'s resolved fields with sample_type="stool"
         host_type_config_dict = {
+            OVERWRITE_NON_NANS_KEY: False,
+            LEAVE_REQUIREDS_BLANK_KEY: False,
+            DEFAULT_KEY: "not provided",
             METADATA_FIELDS_KEY: {},
             SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {
                 "feces": {
@@ -1589,7 +1582,7 @@ class TestMetadataExtender(TestCase):
         }
 
         result_df, validation_msgs = _generate_metadata_for_a_sample_type_in_a_host_type(
-            input_df, "feces", global_plus_host_settings_dict, host_type_config_dict)
+            input_df, "feces", host_type_config_dict)
 
         self.assertEqual("stool_value", result_df["stool_field"].iloc[0])
         # sample_type should be set to the resolved type "stool"
@@ -1605,17 +1598,15 @@ class TestMetadataExtender(TestCase):
             SAMPLETYPE_SHORTHAND_KEY: ["stool", "stool"],
             QC_NOTE_KEY: ["", ""]
         })
-        settings_dict = {
-            OVERWRITE_NON_NANS_KEY: False,
-            LEAVE_REQUIREDS_BLANK_KEY: False,
-            DEFAULT_KEY: "global_default"
-        }
+
         # Config is pre-resolved: sample type's metadata_fields includes
         # host fields merged in, plus sample_type and qiita_sample_type
         full_flat_config_dict = {
             HOST_TYPE_SPECIFIC_METADATA_KEY: {
                 "human": {
                     DEFAULT_KEY: "human_default",
+                    OVERWRITE_NON_NANS_KEY: False,
+                    LEAVE_REQUIREDS_BLANK_KEY: False,
                     METADATA_FIELDS_KEY: {
                         "host_field": {
                             DEFAULT_KEY: "host_value",
@@ -1651,7 +1642,7 @@ class TestMetadataExtender(TestCase):
         }
 
         result_df, validation_msgs = _generate_metadata_for_a_host_type(
-            input_df, "human", settings_dict, full_flat_config_dict)
+            input_df, "human", full_flat_config_dict)
 
         expected_df = pandas.DataFrame({
             SAMPLE_NAME_KEY: ["sample1", "sample2"],
@@ -1674,14 +1665,13 @@ class TestMetadataExtender(TestCase):
             SAMPLETYPE_SHORTHAND_KEY: ["stool"],
             QC_NOTE_KEY: [""]
         })
-        settings_dict = {
-            OVERWRITE_NON_NANS_KEY: False,
-            LEAVE_REQUIREDS_BLANK_KEY: False,
-            DEFAULT_KEY: "global_default"
-        }
+
         full_flat_config_dict = {
             HOST_TYPE_SPECIFIC_METADATA_KEY: {
                 "human": {
+                    OVERWRITE_NON_NANS_KEY: False,
+                    LEAVE_REQUIREDS_BLANK_KEY: False,
+                    DEFAULT_KEY: "global_default",
                     METADATA_FIELDS_KEY: {},
                     SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {}
                 }
@@ -1689,7 +1679,7 @@ class TestMetadataExtender(TestCase):
         }
 
         result_df, validation_msgs = _generate_metadata_for_a_host_type(
-            input_df, "unknown_host", settings_dict, full_flat_config_dict)
+            input_df, "unknown_host", full_flat_config_dict)
 
         expected_df = pandas.DataFrame({
             SAMPLE_NAME_KEY: ["sample1"],
@@ -1708,14 +1698,13 @@ class TestMetadataExtender(TestCase):
             SAMPLETYPE_SHORTHAND_KEY: ["unknown_sample"],
             QC_NOTE_KEY: [""]
         })
-        settings_dict = {
-            OVERWRITE_NON_NANS_KEY: False,
-            LEAVE_REQUIREDS_BLANK_KEY: False,
-            DEFAULT_KEY: "global_default"
-        }
+
         full_flat_config_dict = {
             HOST_TYPE_SPECIFIC_METADATA_KEY: {
                 "human": {
+                    OVERWRITE_NON_NANS_KEY: False,
+                    LEAVE_REQUIREDS_BLANK_KEY: False,
+                    DEFAULT_KEY: "global_default",
                     METADATA_FIELDS_KEY: {},
                     SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {
                         "stool": {
@@ -1727,7 +1716,7 @@ class TestMetadataExtender(TestCase):
         }
 
         result_df, validation_msgs = _generate_metadata_for_a_host_type(
-            input_df, "human", settings_dict, full_flat_config_dict)
+            input_df, "human", full_flat_config_dict)
 
         expected_df = pandas.DataFrame({
             SAMPLE_NAME_KEY: ["sample1"],
@@ -1746,16 +1735,15 @@ class TestMetadataExtender(TestCase):
             SAMPLETYPE_SHORTHAND_KEY: ["stool", "stool", "stool"],
             QC_NOTE_KEY: ["", "", ""]
         })
-        settings_dict = {
-            OVERWRITE_NON_NANS_KEY: False,
-            LEAVE_REQUIREDS_BLANK_KEY: False,
-            DEFAULT_KEY: "global_default"
-        }
+
         # Config is pre-resolved: sample type's metadata_fields includes
         # host fields merged in, plus sample_type and qiita_sample_type
         full_flat_config_dict = {
             HOST_TYPE_SPECIFIC_METADATA_KEY: {
                 "human": {
+                    OVERWRITE_NON_NANS_KEY: False,
+                    LEAVE_REQUIREDS_BLANK_KEY: False,
+                    DEFAULT_KEY: "global_default",
                     METADATA_FIELDS_KEY: {
                         "human_field": {
                             DEFAULT_KEY: "human_value",
@@ -1784,6 +1772,9 @@ class TestMetadataExtender(TestCase):
                     }
                 },
                 "mouse": {
+                    OVERWRITE_NON_NANS_KEY: False,
+                    LEAVE_REQUIREDS_BLANK_KEY: False,
+                    DEFAULT_KEY: "global_default",
                     METADATA_FIELDS_KEY: {},
                     SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {}
                 }
@@ -1791,7 +1782,7 @@ class TestMetadataExtender(TestCase):
         }
 
         result_df, validation_msgs = _generate_metadata_for_a_host_type(
-            input_df, "human", settings_dict, full_flat_config_dict)
+            input_df, "human", full_flat_config_dict)
 
         expected_df = pandas.DataFrame({
             SAMPLE_NAME_KEY: ["sample1", "sample3"],
@@ -1812,17 +1803,15 @@ class TestMetadataExtender(TestCase):
             SAMPLETYPE_SHORTHAND_KEY: ["stool"],
             QC_NOTE_KEY: [""]
         })
-        settings_dict = {
-            OVERWRITE_NON_NANS_KEY: False,
-            LEAVE_REQUIREDS_BLANK_KEY: False,
-            DEFAULT_KEY: "global_default"
-        }
+
         # Config is pre-resolved: sample type's metadata_fields includes
         # host fields merged in, plus sample_type and qiita_sample_type
         full_flat_config_dict = {
             HOST_TYPE_SPECIFIC_METADATA_KEY: {
                 "human": {
                     DEFAULT_KEY: "human_specific_default",
+                    OVERWRITE_NON_NANS_KEY: False,
+                    LEAVE_REQUIREDS_BLANK_KEY: False,
                     METADATA_FIELDS_KEY: {},
                     SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {
                         "stool": {
@@ -1849,7 +1838,7 @@ class TestMetadataExtender(TestCase):
         }
 
         result_df, validation_msgs = _generate_metadata_for_a_host_type(
-            input_df, "human", settings_dict, full_flat_config_dict)
+            input_df, "human", full_flat_config_dict)
 
         expected_df = pandas.DataFrame({
             SAMPLE_NAME_KEY: ["sample1"],
@@ -1870,17 +1859,14 @@ class TestMetadataExtender(TestCase):
             SAMPLETYPE_SHORTHAND_KEY: ["stool"],
             QC_NOTE_KEY: [""]
         })
-        settings_dict = {
-            OVERWRITE_NON_NANS_KEY: False,
-            LEAVE_REQUIREDS_BLANK_KEY: False,
-            DEFAULT_KEY: "global_default"
-        }
         # Config is pre-resolved: sample type's metadata_fields includes
         # host fields merged in, plus sample_type and qiita_sample_type
         full_flat_config_dict = {
             HOST_TYPE_SPECIFIC_METADATA_KEY: {
                 "human": {
-                    # No DEFAULT_KEY here
+                    OVERWRITE_NON_NANS_KEY: False,
+                    LEAVE_REQUIREDS_BLANK_KEY: False,
+                    DEFAULT_KEY: "global_default",
                     METADATA_FIELDS_KEY: {},
                     SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {
                         "stool": {
@@ -1907,7 +1893,7 @@ class TestMetadataExtender(TestCase):
         }
 
         result_df, validation_msgs = _generate_metadata_for_a_host_type(
-            input_df, "human", settings_dict, full_flat_config_dict)
+            input_df, "human", full_flat_config_dict)
 
         expected_df = pandas.DataFrame({
             SAMPLE_NAME_KEY: ["sample1"],
@@ -1938,6 +1924,9 @@ class TestMetadataExtender(TestCase):
             OVERWRITE_NON_NANS_KEY: False,
             HOST_TYPE_SPECIFIC_METADATA_KEY: {
                 "human": {
+                    DEFAULT_KEY: "global_default",
+                    LEAVE_REQUIREDS_BLANK_KEY: False,
+                    OVERWRITE_NON_NANS_KEY: False,
                     METADATA_FIELDS_KEY: {
                         "host_field": {
                             DEFAULT_KEY: "host_value",
@@ -2004,6 +1993,9 @@ class TestMetadataExtender(TestCase):
             OVERWRITE_NON_NANS_KEY: False,
             HOST_TYPE_SPECIFIC_METADATA_KEY: {
                 "human": {
+                    DEFAULT_KEY: "global_default",
+                    LEAVE_REQUIREDS_BLANK_KEY: False,
+                    OVERWRITE_NON_NANS_KEY: False,
                     METADATA_FIELDS_KEY: {
                         "human_field": {
                             DEFAULT_KEY: "human_value",
@@ -2050,6 +2042,9 @@ class TestMetadataExtender(TestCase):
                     }
                 },
                 "mouse": {
+                    DEFAULT_KEY: "global_default",
+                    LEAVE_REQUIREDS_BLANK_KEY: False,
+                    OVERWRITE_NON_NANS_KEY: False,
                     METADATA_FIELDS_KEY: {
                         "mouse_field": {
                             DEFAULT_KEY: "mouse_value",
@@ -2181,6 +2176,9 @@ class TestMetadataExtender(TestCase):
             OVERWRITE_NON_NANS_KEY: False,
             HOST_TYPE_SPECIFIC_METADATA_KEY: {
                 "human": {
+                    DEFAULT_KEY: "global_default",
+                    LEAVE_REQUIREDS_BLANK_KEY: True,  # This causes required fields to get LEAVE_BLANK_VAL
+                    OVERWRITE_NON_NANS_KEY: False,
                     METADATA_FIELDS_KEY: {},
                     SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {
                         "stool": {
@@ -2505,6 +2503,9 @@ class TestMetadataExtender(TestCase):
             OVERWRITE_NON_NANS_KEY: False,
             HOST_TYPE_SPECIFIC_METADATA_KEY: {
                 "human": {
+                    DEFAULT_KEY: "not provided",
+                    LEAVE_REQUIREDS_BLANK_KEY: False,
+                    OVERWRITE_NON_NANS_KEY: False,
                     METADATA_FIELDS_KEY: {
                         "host_field": {
                             DEFAULT_KEY: "host_value",
@@ -2579,6 +2580,9 @@ class TestMetadataExtender(TestCase):
             },
             HOST_TYPE_SPECIFIC_METADATA_KEY: {
                 "human": {
+                    DEFAULT_KEY: "not provided",
+                    LEAVE_REQUIREDS_BLANK_KEY: False,
+                    OVERWRITE_NON_NANS_KEY: False,
                     METADATA_FIELDS_KEY: {},
                     SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {
                         "stool": {
@@ -2638,6 +2642,9 @@ class TestMetadataExtender(TestCase):
             },
             HOST_TYPE_SPECIFIC_METADATA_KEY: {
                 "human": {
+                    DEFAULT_KEY: "not provided",
+                    LEAVE_REQUIREDS_BLANK_KEY: False,
+                    OVERWRITE_NON_NANS_KEY: False,
                     METADATA_FIELDS_KEY: {},
                     SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {
                         "stool": {
@@ -2686,6 +2693,9 @@ class TestMetadataExtender(TestCase):
             OVERWRITE_NON_NANS_KEY: False,
             HOST_TYPE_SPECIFIC_METADATA_KEY: {
                 "human": {
+                    DEFAULT_KEY: "not provided",
+                    LEAVE_REQUIREDS_BLANK_KEY: False,
+                    OVERWRITE_NON_NANS_KEY: False,
                     METADATA_FIELDS_KEY: {},
                     SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {}
                 }
@@ -2720,6 +2730,9 @@ class TestMetadataExtender(TestCase):
             OVERWRITE_NON_NANS_KEY: False,
             HOST_TYPE_SPECIFIC_METADATA_KEY: {
                 "human": {
+                    DEFAULT_KEY: "not provided",
+                    LEAVE_REQUIREDS_BLANK_KEY: False,
+                    OVERWRITE_NON_NANS_KEY: False,
                     METADATA_FIELDS_KEY: {},
                     SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {
                         "stool": {
@@ -2780,6 +2793,9 @@ class TestMetadataExtender(TestCase):
             },
             HOST_TYPE_SPECIFIC_METADATA_KEY: {
                 "human": {
+                    DEFAULT_KEY: "not provided",
+                    LEAVE_REQUIREDS_BLANK_KEY: False,
+                    OVERWRITE_NON_NANS_KEY: False,
                     METADATA_FIELDS_KEY: {},
                     SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {
                         "stool": {
@@ -3189,6 +3205,63 @@ class TestMetadataExtender(TestCase):
         })
         assert_frame_equal(expected_df, result_df)
 
+    def test_extend_metadata_df_with_alternate_column_names(self):
+        """Test metadata extension with alternate hosttype and sampletype column names."""
+        # Use alternate column names instead of hosttype_shorthand and sampletype_shorthand
+        input_df = pandas.DataFrame({
+            SAMPLE_NAME_KEY: ["sample1", "sample2"],
+            "host_type": ["human", "human"],
+            "sample": ["stool", "stool"]
+        })
+        study_config = {
+            DEFAULT_KEY: "not provided",
+            LEAVE_REQUIREDS_BLANK_KEY: True,
+            OVERWRITE_NON_NANS_KEY: False,
+            STUDY_SPECIFIC_METADATA_KEY: {
+                HOST_TYPE_SPECIFIC_METADATA_KEY: {
+                    "human": {
+                        METADATA_FIELDS_KEY: {},
+                        SAMPLE_TYPE_SPECIFIC_METADATA_KEY: {
+                            "stool": {
+                                METADATA_FIELDS_KEY: {}
+                            }
+                        }
+                    }
+                }
+            }
+        }
+        # Software config specifies alternate column names
+        software_config = {
+            DEFAULT_KEY: "not provided",
+            LEAVE_REQUIREDS_BLANK_KEY: True,
+            OVERWRITE_NON_NANS_KEY: False,
+            HOSTTYPE_COL_OPTIONS_KEY: ["host_type"],
+            SAMPLETYPE_COL_OPTIONS_KEY: ["sample"]
+        }
+
+        result_df, validation_msgs_df = extend_metadata_df(
+            input_df, study_config, None, software_config, self.TEST_STDS_FP)
+
+        expected_df = pandas.DataFrame({
+            SAMPLE_NAME_KEY: ["sample1", "sample2"],
+            "body_product": ["UBERON:feces", "UBERON:feces"],
+            "body_site": ["gut", "gut"],
+            "description": ["human sample", "human sample"],
+            "host_common_name": ["human", "human"],
+            # Alternate column names from input are preserved
+            "host_type": ["human", "human"],
+            QIITA_SAMPLE_TYPE: ["stool", "stool"],
+            # Alternate column names from input are preserved
+            "sample": ["stool", "stool"],
+            SAMPLE_TYPE_KEY: ["stool", "stool"],
+            # Standard internal columns added at end (in order of INTERNAL_COL_KEYS)
+            HOSTTYPE_SHORTHAND_KEY: ["human", "human"],
+            SAMPLETYPE_SHORTHAND_KEY: ["stool", "stool"],
+            QC_NOTE_KEY: ["", ""]
+        })
+        assert_frame_equal(expected_df, result_df)
+        self.assertTrue(validation_msgs_df.empty)
+
     # Tests for _get_study_specific_config
 
     def test__get_study_specific_config_with_valid_file(self):
@@ -4084,6 +4157,7 @@ class TestMetadataExtender(TestCase):
         TEST_DIR, "data/test_project1_output_metadata.txt")
     TEST_PROJECT1_EXPECTED_FAILS_FP = path.join(
         TEST_DIR, "data/test_project1_output_fails.csv")
+
     def test_write_extended_metadata_from_df_project1_integration(self):
         """Integration test using project1 test data files."""
 
@@ -4095,7 +4169,6 @@ class TestMetadataExtender(TestCase):
             with open(path.join(debug_dir, f"UNMATCHED_2_{file_name}"), 'w') as debug_actual_file:
                 debug_actual_file.write(actual_content)
 
-
         # Load input metadata CSV
         input_df = pandas.read_csv(self.TEST_PROJECT1_METADATA_FP, dtype=str)
         # for the columns "plating_notes" and "notes", fill NaN with empty string
@@ -4145,3 +4218,83 @@ class TestMetadataExtender(TestCase):
                 os.path.join(tmpdir, "*_test_output_validation_errors.csv"))
             self.assertEqual(1, len(validation_files))
             self.assertEqual(0, os.path.getsize(validation_files[0]))
+
+    # Tests for _get_specified_column_name
+
+    def test__get_specified_column_name_finds_column(self):
+        """Test that _get_specified_column_name finds a column that exists."""
+        input_df = pandas.DataFrame({
+            "sample_name": ["s1"],
+            "host_type": ["human"]
+        })
+        config_dict = {
+            HOSTTYPE_COL_OPTIONS_KEY: ["host_type", "host_common_name"]
+        }
+        result = _get_specified_column_name(
+            HOSTTYPE_COL_OPTIONS_KEY, input_df, config_dict)
+        self.assertEqual("host_type", result)
+
+    def test__get_specified_column_name_returns_first_match(self):
+        """Test that _get_specified_column_name returns the first match when multiple options exist."""
+        input_df = pandas.DataFrame({
+            "sample_name": ["s1"],
+            "host_type": ["human"],
+            "host_common_name": ["human"]
+        })
+        config_dict = {
+            HOSTTYPE_COL_OPTIONS_KEY: ["host_type", "host_common_name"]
+        }
+        result = _get_specified_column_name(
+            HOSTTYPE_COL_OPTIONS_KEY, input_df, config_dict)
+        self.assertEqual("host_type", result)
+
+    def test__get_specified_column_name_returns_none_when_no_match(self):
+        """Test that _get_specified_column_name returns None when no options match."""
+        input_df = pandas.DataFrame({
+            "sample_name": ["s1"],
+            "other_column": ["value"]
+        })
+        config_dict = {
+            HOSTTYPE_COL_OPTIONS_KEY: ["host_type", "host_common_name"]
+        }
+        result = _get_specified_column_name(
+            HOSTTYPE_COL_OPTIONS_KEY, input_df, config_dict)
+        self.assertIsNone(result)
+
+    def test__get_specified_column_name_returns_none_when_key_missing(self):
+        """Test that _get_specified_column_name returns None when col_options_key is not in config."""
+        input_df = pandas.DataFrame({
+            "sample_name": ["s1"],
+            "host_type": ["human"]
+        })
+        config_dict = {}
+        result = _get_specified_column_name(
+            HOSTTYPE_COL_OPTIONS_KEY, input_df, config_dict)
+        self.assertIsNone(result)
+
+    def test__get_specified_column_name_returns_none_when_options_empty(self):
+        """Test that _get_specified_column_name returns None when col_options is empty list."""
+        input_df = pandas.DataFrame({
+            "sample_name": ["s1"],
+            "host_type": ["human"]
+        })
+        config_dict = {
+            HOSTTYPE_COL_OPTIONS_KEY: []
+        }
+        result = _get_specified_column_name(
+            HOSTTYPE_COL_OPTIONS_KEY, input_df, config_dict)
+        self.assertIsNone(result)
+
+    def test__get_specified_column_name_with_sampletype_key(self):
+        """Test that _get_specified_column_name works with sampletype column options."""
+        input_df = pandas.DataFrame({
+            "sample_name": ["s1"],
+            "sample_type": ["stool"]
+        })
+        config_dict = {
+            SAMPLETYPE_COL_OPTIONS_KEY: ["sample_type", "sampletype"]
+        }
+        result = _get_specified_column_name(
+            SAMPLETYPE_COL_OPTIONS_KEY, input_df, config_dict)
+        self.assertEqual("sample_type", result)
+    # endregion _get_specified_column_name tests