Add function for handling a bad prefix map

Motivated by mapping-commons/sssom-py#485

docs/source/tutorial.rst

@@ -92,6 +92,10 @@ This function also accepts a string with a HTTP, HTTPS, or FTP path to a remote
     structure for situations when there can be CURIE synonyms or even URI prefix synonyms is
     the *extended prefix map* (see below).
 
+    If you're not in a position where you can fix data issues upstream, you can try using the
+    :func:`curies.clean_prefix_map` to extract a canonical extended prefix map from a non-bijective
+    prefix map.
+
 Loading Extended Prefix Maps
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 Extended prefix maps (EPMs) address the issues with prefix maps by including explicit

src/curies/api.py

@@ -2191,3 +2191,15 @@ def _get_shacl_line(prefix: str, uri_prefix: str, pattern: Optional[str] = None)
         pattern = pattern.replace("\\", "\\\\")
         line += f'; sh:pattern "{pattern}"'
     return line + " ]"
+
+
+def clean_prefix_map(prefix_map: Mapping[str, str]) -> List[Record]:
+    """Convert a problematic prefix map (i.e., not bijective) into a list of records."""
+    dd = defaultdict(list)
+    for curie_prefix, uri_prefix in prefix_map.items():
+        dd[uri_prefix].append(curie_prefix)
+    xx = {uri_prefix: sorted(curie_prefixes) for uri_prefix, curie_prefixes in dd.items()}
+    return [
+        Record(prefix=prefix, prefix_synonyms=prefix_synonyms, uri_prefix=uri_prefix)
+        for uri_prefix, (prefix, *prefix_synonyms) in sorted(xx.items())
+    ]

tests/test_api.py

@@ -25,6 +25,7 @@
     ReferenceTuple,
     URIStandardizationError,
     chain,
+    clean_prefix_map,
 )
 from curies.sources import (
     BIOREGISTRY_CONTEXTS,
@@ -860,3 +861,14 @@ def test_version_type(self):
         """
         version = get_version()
         self.assertIsInstance(version, str)
+
+
+class TestUtils(unittest.TestCase):
+    """Test utility functions."""
+
+    def test_clean(self):
+        """Test clean."""
+        prefix_map = {"a": "https://example.com/", "b": "https://example.com/"}
+        records = clean_prefix_map(prefix_map)
+        self.assertEqual(1, len(records))
+        self.assertEqual("a", records[0].prefix)