added extension_match, _fullmatch

pymrio/core/mriosystem.py

@@ -2164,8 +2164,95 @@ def get_extensions(self, data=False):
             else:
                 yield key
 
+    def extension_fullmatch(self, extensions=None, find_all=None, **kwargs):
+        """Get a dict of extension index dicts with full match of a search pattern.
+
+        This calls the extension.fullmatch for all extensions.
+
+        Similar to pandas str.fullmatch, thus the start of the index string must match.
+
+        Note
+        -----
+        Arguments are set to case=True, flags=0, na=False, regex=True.
+        For case insensitive matching, use (?i) at the beginning of the pattern.
+
+        See the pandas/python.re documentation for more details.
+
+
+        Parameters
+        ----------
+        extensions: str, list of str, list of extensions, None
+            Which extensions to consider, default (None): all extensions
+        find_all : None or str
+            If str (regex pattern) search in all index levels.
+            All matching rows are returned. The remaining kwargs are ignored.
+        kwargs : dict
+            The regex which should be contained. The keys are the index names,
+            the values are the regex.
+            If the entry is not in index name, it is ignored silently.
+
+        Returns
+        -------
+        dict
+            A dict with the extension names as keys and an Index/MultiIndex of
+            the matched rows as values
+        """
+        return self._apply_extension_method(
+            extensions, method="match", find_all=find_all, **kwargs
+        )
+
+    def extension_match(self, extensions=None, find_all=None, **kwargs):
+        """Get a dict of extension index dicts which match a search pattern
+
+        This calls the extension.match for all extensions.
+
+        Similar to pandas str.match, thus the start of the index string must match.
+
+        Note
+        -----
+        Arguments are set to case=True, flags=0, na=False, regex=True.
+        For case insensitive matching, use (?i) at the beginning of the pattern.
+
+        See the pandas/python.re documentation for more details.
+
+
+        Parameters
+        ----------
+        extensions: str, list of str, list of extensions, None
+            Which extensions to consider, default (None): all extensions
+        find_all : None or str
+            If str (regex pattern) search in all index levels.
+            All matching rows are returned. The remaining kwargs are ignored.
+        kwargs : dict
+            The regex which should be contained. The keys are the index names,
+            the values are the regex.
+            If the entry is not in index name, it is ignored silently.
+
+        Returns
+        -------
+        dict
+            A dict with the extension names as keys and an Index/MultiIndex of
+            the matched rows as values
+        """
+        return self._apply_extension_method(
+            extensions, method="match", find_all=find_all, **kwargs
+        )
+
     def extension_contains(self, extensions=None, find_all=None, **kwargs):
-        """Get a dict of extension index dicts
+        """Get a dict of extension index dicts which contains a search pattern
+
+        This calls the extension.contains for all extensions.
+
+        Similar to pandas str.contains, thus the index
+        string must contain the regex pattern.
+
+        Note
+        -----
+        Arguments are set to case=True, flags=0, na=False, regex=True.
+        For case insensitive matching, use (?i) at the beginning of the pattern.
+
+        See the pandas/python.re documentation for more details.
+
 
         Parameters
         ----------
@@ -2178,13 +2265,17 @@ def extension_contains(self, extensions=None, find_all=None, **kwargs):
             The regex which should be contained. The keys are the index names,
             the values are the regex.
             If the entry is not in index name, it is ignored silently.
+
+        Returns
+        -------
+        dict
+            A dict with the extension names as keys and an Index/MultiIndex of
+            the matched rows as values
         """
-        method = "contains"
         return self._apply_extension_method(
-            extensions, method, find_all=find_all, **kwargs
+            extensions, method="contains", find_all=find_all, **kwargs
         )
 
-    # TODO: CONT: added methods for match, fullmatch
     # TODO: CONT: add method for extract extension
 
     def _apply_extension_method(self, extensions, method, *args, **kwargs):

tests/test_core.py

@@ -554,6 +554,33 @@ def test_contain_match_matchall(fix_testmrio):
     assert all(ext_all_comp == tt.emissions.F.index)
 
 
+def test_extension_match_contain(fix_testmrio):
+    tt = fix_testmrio.testmrio
+    match_air = tt.extension_match(find_all="air")
+    assert len(match_air["factor_inputs"]) == 0
+    assert len(match_air["emissions"]) == 1
+
+    contain_value_added = tt.extension_contains(inputtype="dded")
+    assert len(contain_value_added["factor_inputs"]) == 1
+    assert len(contain_value_added["emissions"]) == 0
+
+    fullmatch_0 = tt.extension_fullmatch(emissions="dded")
+    assert len(fullmatch_0["factor_inputs"]) == 0
+    assert len(fullmatch_0["emissions"]) == 0
+    fullmatch_1 = tt.extension_fullmatch(stressor="emission_type.*")
+    assert len(fullmatch_1["factor_inputs"]) == 0
+    assert len(fullmatch_1["emissions"]) == 2
+
+    # dual match
+    dual_match1 = tt.extension_match(stressor="emission_type.*", compartment="air")
+    assert len(dual_match1["factor_inputs"]) == 0
+    assert len(dual_match1["emissions"]) == 1
+
+    dual_match2 = tt.extension_contains(stressor="1", inputtype="alue")
+    assert len(dual_match2["factor_inputs"]) == 1
+    assert len(dual_match2["emissions"]) == 1
+
+
 def test_direct_account_calc(fix_testmrio):
     orig = fix_testmrio.testmrio
     orig.calc_all()