Fixed prefix extraction during normalization

iscc · Jan 24, 2024 · 33f36ff · 33f36ff
1 parent abdcfcd
commit 33f36ff
Show file tree

Hide file tree

Showing 4 changed files with 8 additions and 1 deletion.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,6 +2,7 @@
 
 ## [1.0.8] - Unreleased
 - Import from pydantic v2 lib first
+- Fixed prefix extraction during normalization
 
 ## [1.0.7] - 2024-01-07
 - Support pydantic v1 & v2

diff --git a/docs/changelog.md b/docs/changelog.md
@@ -2,6 +2,7 @@
 
 ## [1.0.8] - Unreleased
 - Import from pydantic v2 lib first
+- Fixed prefix extraction during normalization
 
 ## [1.0.7] - 2024-01-07
 - Support pydantic v1 & v2

diff --git a/iscc_core/codec.py b/iscc_core/codec.py
@@ -418,7 +418,7 @@ def iscc_normalize(iscc_code):
             raise ValueError(f"Malformed multiformat codec: {decoded[:2]}")
         iscc_code = encode_base32(decoded[2:])
     else:
-        prefix = iscc_code.lstrip("ISCC:").lstrip("iscc:")[:2].upper()
+        prefix = iscc_code.upper().replace("ISCC:", "")[:2]
         if prefix not in PREFIXES:
             raise ValueError(f"ISCC starts with invalid prefix {prefix}")
 

diff --git a/tests/test_codec.py b/tests/test_codec.py
@@ -298,6 +298,11 @@ def test_Code_rnd():
     assert ic.Code.rnd(ic.MT.DATA).maintype == ic.MT.DATA
 
 
+def test_nomralize_roundtrip():
+    code = "ISCC:IABTRD3EMDL2W74Z4ROZTOJTT3BDY"
+    assert ic.iscc_normalize(code) == code
+
+
 def test_noramlize_bad_prefix():
     with pytest.raises(ValueError):
         ic.iscc_normalize("ISCC:LA22222222")