metameq 2026.1.2__py3-none-any.whl → 2026.2.1__py3-none-any.whl

metameq/_version.py

@@ -8,11 +8,11 @@ import json
 
 version_json = '''
 {
- "date": "2026-01-31T12:28:01-0800",
+ "date": "2026-02-01T21:32:06-0800",
  "dirty": false,
  "error": null,
- "full-revisionid": "889941fbd7d28889867e3f4b6edba2d50dbc5956",
- "version": "2026.01.2"
+ "full-revisionid": "87171fd73f555e2c03a15fa36ed9b5a912b824e9",
+ "version": "2026.02.1"
 }
 '''  # END VERSION_JSON
 

metameq/config/config.yml

@@ -1,3 +1,7 @@
 "default": "not applicable"
 "leave_requireds_blank": false
-"overwrite_non_nans": false
+"overwrite_non_nans": false
+"hosttype_column_options":
+  - "host_common_name"
+"sampletype_column_options":
+  - "sample_type"

metameq/src/metadata_extender.py

@@ -15,7 +15,8 @@ from metameq.src.util import extract_config_dict, \
     LEAVE_BLANK_VAL, SAMPLE_NAME_KEY, \
     ALLOWED_KEY, TYPE_KEY, LEAVE_REQUIREDS_BLANK_KEY, OVERWRITE_NON_NANS_KEY, \
     METADATA_TRANSFORMERS_KEY, PRE_TRANSFORMERS_KEY, POST_TRANSFORMERS_KEY, \
-    SOURCES_KEY, FUNCTION_KEY, REQUIRED_RAW_METADATA_FIELDS
+    SOURCES_KEY, FUNCTION_KEY, REQUIRED_RAW_METADATA_FIELDS, \
+    HOSTTYPE_COL_OPTIONS_KEY, SAMPLETYPE_COL_OPTIONS_KEY
 from metameq.src.metadata_configurator import update_wip_metadata_dict, \
     build_full_flat_config_dict
 from metameq.src.metadata_validator import validate_metadata_df, \
@@ -447,13 +448,22 @@ def extend_metadata_df(
     ValueError
         If required columns are missing from the metadata.
     """
+    full_flat_config_dict = build_full_flat_config_dict(
+        study_specific_config_dict, software_config_dict, stds_fp)
+
+    needed_cols = [(HOSTTYPE_SHORTHAND_KEY, HOSTTYPE_COL_OPTIONS_KEY), 
+                   (SAMPLETYPE_SHORTHAND_KEY, SAMPLETYPE_COL_OPTIONS_KEY)]
+    for curr_key, curr_options_key in needed_cols:
+        if curr_key not in raw_metadata_df.columns:
+            specified_name = _get_specified_column_name(
+                curr_options_key, raw_metadata_df, full_flat_config_dict)
+            if specified_name:
+                raw_metadata_df[curr_key] = raw_metadata_df[specified_name]
+
     validate_required_columns_exist(
         raw_metadata_df, REQUIRED_RAW_METADATA_FIELDS,
         "metadata missing required columns")
 
-    full_flat_config_dict = build_full_flat_config_dict(
-        study_specific_config_dict, software_config_dict, stds_fp)
-
     metadata_df, validation_msgs_df = _populate_metadata_df(
         raw_metadata_df, full_flat_config_dict,
         study_specific_transformers_dict)
@@ -461,6 +471,40 @@ def extend_metadata_df(
     return metadata_df, validation_msgs_df
 
 
+def _get_specified_column_name(
+        col_options_key: str,
+        raw_metadata_df: pandas.DataFrame,
+        config_dict: Dict[str, Any] = None) -> Optional[str]:
+    """Get the specified type of column name from the metadata DataFrame based on possible options.
+
+    Parameters
+    ----------
+    col_options_key : str
+        Key in the config dict that holds the list of possible column names to check.
+    raw_metadata_df : pandas.DataFrame
+        The metadata DataFrame to check.
+    config_dict : Dict[str, Any], default=None
+        Configuration dictionary. If provided, may contain a list of possible
+        column names under the key specified by col_options_key. 
+        If None, defaults to values from the main config.yml file.
+    Returns
+    -------
+    Optional[str]
+        The specified column name found in the DataFrame, or None if not found.
+    """
+    found_name = None
+
+    if not config_dict:
+        config_dict = extract_config_dict(None)
+    col_options = config_dict.get(col_options_key)
+    if col_options:
+        for col_name in col_options:
+            if col_name in raw_metadata_df.columns:
+                found_name = col_name
+                break
+
+    return found_name 
+
 def write_metadata_results(
         metadata_df: pandas.DataFrame,
         validation_msgs_df: pandas.DataFrame,

metameq/src/util.py

@@ -27,6 +27,8 @@ SOURCES_KEY = "sources"
 FUNCTION_KEY = "function"
 LEAVE_REQUIREDS_BLANK_KEY = "leave_requireds_blank"
 OVERWRITE_NON_NANS_KEY = "overwrite_non_nans"
+HOSTTYPE_COL_OPTIONS_KEY = "hosttype_column_options"
+SAMPLETYPE_COL_OPTIONS_KEY = "sampletype_column_options"
 
 # internal code keys
 HOSTTYPE_SHORTHAND_KEY = "hosttype_shorthand"

metameq/tests/test_metadata_configurator.py

@@ -5,7 +5,8 @@ from metameq.src.util import \
     SAMPLE_TYPE_SPECIFIC_METADATA_KEY, DEFAULT_KEY, \
     ALIAS_KEY, BASE_TYPE_KEY, ALLOWED_KEY, ANYOF_KEY, TYPE_KEY, \
     STUDY_SPECIFIC_METADATA_KEY, LEAVE_REQUIREDS_BLANK_KEY, \
-    OVERWRITE_NON_NANS_KEY, REQUIRED_KEY, SAMPLE_TYPE_KEY, QIITA_SAMPLE_TYPE
+    OVERWRITE_NON_NANS_KEY, REQUIRED_KEY, SAMPLE_TYPE_KEY, QIITA_SAMPLE_TYPE, \
+    HOSTTYPE_COL_OPTIONS_KEY, SAMPLETYPE_COL_OPTIONS_KEY
 from metameq.src.metadata_configurator import \
     combine_stds_and_study_config, \
     _make_combined_stds_and_study_host_type_dicts, \
@@ -4643,6 +4644,8 @@ class TestMetadataConfigurator(TestCase):
             DEFAULT_KEY: "not applicable",
             LEAVE_REQUIREDS_BLANK_KEY: False,
             OVERWRITE_NON_NANS_KEY: False,
+            HOSTTYPE_COL_OPTIONS_KEY: ["host_common_name"],
+            SAMPLETYPE_COL_OPTIONS_KEY: ["sample_type"],
             # Flattened host types
             HOST_TYPE_SPECIFIC_METADATA_KEY: {
                 "base": {

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):
@@ -3189,6 +3190,63 @@ 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):
@@ -4145,3 +4203,83 @@ 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

{metameq-2026.1.2.dist-info → metameq-2026.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: metameq
-Version: 2026.1.2
+Version: 2026.2.1
 Summary: Qiita-compliant metadata generation and validation tool
 Home-page: https://github.com/AmandaBirmingham/metameq
 Author: Amanda Birmingham

{metameq-2026.1.2.dist-info → metameq-2026.2.1.dist-info}/RECORD

@@ -1,27 +1,27 @@
 metameq/__init__.py,sha256=6mwG4ULHzMyPm5V16BSJwTMBsqsugFe2yRp5oA-IVHo,2461
-metameq/_version.py,sha256=5-CGLD5PYBqdyo9o8UYmWnOuu45AAgnXxC4kUHGFqm8,501
+metameq/_version.py,sha256=CWCggc3pJMv268vpQwqYr3laum4cOXHQPgqjMq3Mbxw,501
 metameq/config/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-metameq/config/config.yml,sha256=0FIJYepFxR3w0GVhMNGrNQLz0HQOBcrGDkcFjzQdRlc,86
+metameq/config/config.yml,sha256=63tBG-SeNdysvRc9DNofqitvTPWtUCT1FbTdrn3KpBs,183
 metameq/config/standards.yml,sha256=tY3G4jL0GlxcpW8I6xoOmzdtoH6Pn5hZ_9BR_tL9lxo,73783
 metameq/src/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 metameq/src/__main__.py,sha256=KJtslcriLKqYA9FcFH02i8TXMsCeB-14b8L9SBP18qw,1379
 metameq/src/metadata_configurator.py,sha256=tPTODu4y-Oe1uMNOQ86BYsPjNnc66iNfF2EiM9hQCAE,28176
-metameq/src/metadata_extender.py,sha256=DQ9ZfWkMNerHBg2NGga3No_oliyteZ2J456BiuYGhm8,48489
+metameq/src/metadata_extender.py,sha256=FvathKmnDDf5Ax68dKTaLzh93a8L_TkH0uHhA6ClmKM,50256
 metameq/src/metadata_merger.py,sha256=aZo3NdYAsbz34rjLEZXvRRCtFm25p8BUNW79kW9y55Y,13067
 metameq/src/metadata_transformers.py,sha256=kBGB2zbyRTpu-M9nIZBGhlCIDnWxnPPZPylfvxfX5YU,9354
 metameq/src/metadata_validator.py,sha256=pvyPACr4epJv9zkJdS6bS0JzRXTPj6rxVl_n8p0RQxs,14351
-metameq/src/util.py,sha256=A2J2oyRPz8XTaq68AgJuGPuvMh6x0HUtQ684pZoXSMM,8958
+metameq/src/util.py,sha256=8tPBLedQRedaD9Ddbh3rgYKgs6voeVGuUeFBsD_h2SU,9068
 metameq/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-metameq/tests/test_metadata_configurator.py,sha256=3g19YpK3R7HRxFwAwTXQ23x31XynX4V81CMIlGbmm3Q,208301
-metameq/tests/test_metadata_extender.py,sha256=LfP2LERL6IggReY1dvEEqizLZPZAuM05J60y-mFSshs,173734
+metameq/tests/test_metadata_configurator.py,sha256=yVDgOUsQyOsoXUFJUq32CUZvE5fSFV742AGA8b3TdEY,208478
+metameq/tests/test_metadata_extender.py,sha256=Q4bfcnAPfLioqexmKy0Nu3CsJG6tp3nRjE5lMKTykKM,179546
 metameq/tests/test_metadata_merger.py,sha256=U1FqGhkZVSyeX37kSk4QpD0N9HzWGcpsCR38Xc0Lz-g,22992
 metameq/tests/test_metadata_transformers.py,sha256=O80Qzka_7CeyMZz5RO8YQ-AR12sK64ArevWbkt7NVZU,11857
 metameq/tests/test_metadata_validator.py,sha256=Ux9EDsmYJdUFeKKey4QstnW3sgWKFuNneFyYZ8dWPHc,39814
 metameq/tests/test_util.py,sha256=x26gcYxNDPCPS7OPKftEcl-ezFnka-pyMA-SVSMK_dQ,17161
 metameq/tests/data/invalid.yml,sha256=ZjyPB2QELgjhhTx8lHgaVXWoIIbfmU_YcMxebHWda78,27
 metameq/tests/data/test_config.yml,sha256=KKvu_ILmcN7822r1BwWQ9s14AW6vVSePmjmoSx8B1zM,180
-metameq-2026.1.2.dist-info/METADATA,sha256=wQCw216MuuYGaw_EQEIAqZX7Uw3J8ot_xlm48hZNe8U,658
-metameq-2026.1.2.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-metameq-2026.1.2.dist-info/entry_points.txt,sha256=DJsXx2sh4afJZw4KGcYrz9v4L86LrMKrJYYuDRV7edQ,54
-metameq-2026.1.2.dist-info/top_level.txt,sha256=UKD6LtyBhlRDgKBfaPUuQGp_ekTsmOXucSwuDoUO1Fw,8
-metameq-2026.1.2.dist-info/RECORD,,
+metameq-2026.2.1.dist-info/METADATA,sha256=w9eJP5RAZJJBS65vU_nXMFv3wU1gU1Chu26Cl6Now6g,658
+metameq-2026.2.1.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+metameq-2026.2.1.dist-info/entry_points.txt,sha256=DJsXx2sh4afJZw4KGcYrz9v4L86LrMKrJYYuDRV7edQ,54
+metameq-2026.2.1.dist-info/top_level.txt,sha256=UKD6LtyBhlRDgKBfaPUuQGp_ekTsmOXucSwuDoUO1Fw,8
+metameq-2026.2.1.dist-info/RECORD,,