⚡ Benchmark using the default blake hash

data61 · Apr 24, 2023 · b5b169c · b5b169c
1 parent 188bb18
commit b5b169c
Show file tree

Hide file tree

Showing 3 changed files with 77 additions and 3 deletions.
diff --git a/clkhash/data/randomnames-schema-v2.json b/clkhash/data/randomnames-schema-v2.json
@@ -0,0 +1,74 @@
+{
+  "version": 3,
+  "clkConfig": {
+    "l": 1024,
+    "kdf": {
+      "type": "HKDF",
+      "hash": "SHA256",
+      "salt": "SCbL2zHNnmsckfzchsNkZY9XoHk96P/G5nUBrM7ybymlEFsMV6PAeDZCNp3rfNUPCtLDMOGQHG4pCQpfhiHCyA==",
+      "info": "c2NoZW1hX2V4YW1wbGU=",
+      "keySize": 64
+    }
+  },
+  "features": [
+    {
+      "identifier": "INDEX",
+      "ignored": true
+    },
+    {
+      "identifier": "NAME freetext",
+      "format": {
+        "type": "string",
+        "encoding": "utf-8",
+        "case": "mixed",
+        "minLength": 3
+      },
+      "hashing": {
+        "comparison": {
+          "type": "ngram",
+          "n": 2
+        },
+        "strategy": {
+          "bitsPerToken": 15
+        },
+        "hash": {"type": "blakeHash"}
+      }
+    },
+    {
+      "identifier": "DOB YYYY/MM/DD",
+      "format": {
+        "type": "date",
+        "description": "Numbers separated by slashes, in the year, month, day order",
+        "format": "%Y/%m/%d"
+      },
+      "hashing": {
+        "comparison": {
+          "type": "ngram",
+          "n": 1,
+          "positional": true
+        },
+        "strategy": {
+          "bitsPerToken": 30
+        },
+        "hash": {"type": "blakeHash"}
+      }
+    },
+    {
+      "identifier": "GENDER M or F",
+      "format": {
+        "type": "enum",
+        "values": ["M", "F"]
+      },
+      "hashing": {
+        "comparison": {
+          "type": "ngram",
+          "n": 1
+        },
+        "strategy": {
+          "bitsPerToken": 60
+        },
+        "hash": {"type": "blakeHash"}
+      }
+    }
+  ]
+}
diff --git a/clkhash/randomnames.py b/clkhash/randomnames.py
@@ -108,7 +108,7 @@ class NameList:
     """ Randomly generated PII records.
     """
 
-    randomname_schema_bytes = pkgutil.get_data('clkhash', 'data/randomnames-schema.json')
+    randomname_schema_bytes = pkgutil.get_data('clkhash', 'data/randomnames-schema-v2.json')
     if randomname_schema_bytes is None:
         raise Exception("Couldn't locate package data. Please file a bug report.")
     randomname_schema = json.loads(randomname_schema_bytes.decode())

diff --git a/tests/test_e2e_hashing.py b/tests/test_e2e_hashing.py
@@ -38,15 +38,15 @@ class TestV2(unittest.TestCase):
     def test_compare_v1_v2_and_v3(self):
         pii = randomnames.NameList(100).names
         schema_v3 = randomnames.NameList.SCHEMA
-        # this v2 schema should be equivalent to the above v3 schema
+        # this v2 schema is no longer equivalent to the v3 schema as the hash type changed to blakeHash
         schema_v2 = _test_schema('randomnames-schema-v2.json')
         schema_v1 = _test_schema('randomnames-schema-v1.json')
         secret = 'secret'
         for clkv1, clkv2, clkv3 in zip(clk.generate_clks(pii, schema_v1, secret),
                                        clk.generate_clks(pii, schema_v2, secret),
                                        clk.generate_clks(pii, schema_v3, secret)):
             self.assertEqual(clkv1, clkv2)
-            self.assertEqual(clkv1, clkv3)
+            self.assertNotEqual(clkv1, clkv3)
 
     def test_compare_strategies(self):
         def mkSchema(hashing_properties):