Add coverage for combining characters and precomposed characters

Author: gibson042

tests/unicode.json

@@ -38,49 +38,78 @@
     {
         "given": {},
         "cases": [
-            {   
+            {
+                "expression": "'é' == 'e\u0301'",
+                "result": false
+            }
+        ]
+    },
+    {
+        "given": {},
+        "cases": [
+            {
                 "expression": "length('𝌆')",
                 "result": 1
+            },
+            {
+                "expression": "length('é')",
+                "result": 1
+            },
+            {
+                "expression": "length('e\u0301')",
+                "result": 2
             }
         ]
     },
     {
         "given": {},
         "cases": [
-            {   
+            {
                 "expression": "reverse('a𝌆b')",
                 "result": "b𝌆a"
+            },
+            {
+                "expression": "reverse('aéb')",
+                "result": "béa"
+            },
+            {
+                "expression": "reverse('xe\u0303y')",
+                "result": "y\u0303ex"
             }
         ]
     },
     {
         "given": {
-            "strings": ["𝌆", "st", "style", "ffi"]
+            "strings": ["é", "e\u0301", "𝌆", "st", "style", "ffi"]
         },
         "cases": [
             {
                 "expression": "sort(strings)",
-                "result": ["ffi", "st", "style", "𝌆"]
+                "result": ["e\u0301", "é", "ffi", "st", "style", "𝌆"]
             }
         ]
     },
     {
         "given": {
-            "characters": [
-                {"character": "𝌆", "codePoint": 119558, "name": "TETRAGRAM FOR CENTRE"},
-                {"character": "st", "codePoint": 64262, "name": "LATIN SMALL LIGATURE ST"},
-                {"character": "ff", "codePoint": 64256, "name": "LATIN SMALL LIGATURE FF"},
-                {"character": "ffi", "codePoint": 64259, "name": "LATIN SMALL LIGATURE FFI"}
+            "graphemeClusters": [
+                {"string": "é", "codePoints": 233, "name": "LATIN SMALL LETTER E WITH ACUTE"},
+                {"string": "é", "codePoints": [101, 769], "name": "LATIN SMALL LETTER E + COMBINING ACUTE ACCENT"},
+                {"string": "𝌆", "codePoints": 119558, "name": "TETRAGRAM FOR CENTRE"},
+                {"string": "st", "codePoints": 64262, "name": "LATIN SMALL LIGATURE ST"},
+                {"string": "ff", "codePoints": 64256, "name": "LATIN SMALL LIGATURE FF"},
+                {"string": "ffi", "codePoints": 64259, "name": "LATIN SMALL LIGATURE FFI"}
             ]
         },
         "cases": [
             {
-                "expression": "sort_by(characters, &character)",
+                "expression": "sort_by(graphemeClusters, &string)",
                 "result": [
-                    {"character": "ff", "codePoint": 64256, "name": "LATIN SMALL LIGATURE FF"},
-                    {"character": "ffi", "codePoint": 64259, "name": "LATIN SMALL LIGATURE FFI"},
-                    {"character": "st", "codePoint": 64262, "name": "LATIN SMALL LIGATURE ST"},
-                    {"character": "𝌆", "codePoint": 119558, "name": "TETRAGRAM FOR CENTRE"}
+                    {"string": "é", "codePoints": [101, 769], "name": "LATIN SMALL LETTER E + COMBINING ACUTE ACCENT"},
+                    {"string": "é", "codePoints": 233, "name": "LATIN SMALL LETTER E WITH ACUTE"},
+                    {"string": "ff", "codePoints": 64256, "name": "LATIN SMALL LIGATURE FF"},
+                    {"string": "ffi", "codePoints": 64259, "name": "LATIN SMALL LIGATURE FFI"},
+                    {"string": "st", "codePoints": 64262, "name": "LATIN SMALL LIGATURE ST"},
+                    {"string": "𝌆", "codePoints": 119558, "name": "TETRAGRAM FOR CENTRE"}
                 ]
             }
         ]