Move UtfCodepoint functionality into string module

Author: tomwhatmore

src/gleam/string.gleam

@@ -10,6 +10,10 @@ import gleam/result
 pub type String =
   String
 
+/// A UtfCodepoint is the integer representation of a valid UTF codepoint
+pub type UtfCodepoint =
+  UtfCodepoint
+
 /// Determine if a string is empty.
 ///
 /// ## Examples
@@ -451,3 +455,20 @@ pub fn to_graphemes(string: String) -> List(String) {
     _ -> []
   }
 }
+
+external fn int_to_utf_codepoint(Int) -> UtfCodepoint =
+  "gleam_stdlib" "identity"
+
+/// Convert an integer to a UtfCodepoint
+///
+/// Returns an error if the integer does not represent a valid UTF codepoint.
+///
+pub fn utf_codepoint(value: Int) -> Result(UtfCodepoint, Nil) {
+  case value {
+    i if i > 1114111 -> Error(Nil)
+    i if i == 65534 -> Error(Nil)
+    i if i == 65535 -> Error(Nil)
+    i if i >= 55296 && i <= 57343 -> Error(Nil)
+    i -> Ok(int_to_utf_codepoint(i))
+  }
+}

src/gleam/utf_codepoint.gleam

@@ -295,3 +295,17 @@ pub fn to_graphemes_test() {
   |> string.to_graphemes()
   |> should.equal([])
 }
+
+pub fn utf_codepoint_test() {
+  string.utf_codepoint(1114444)
+  |> should.be_error
+
+  string.utf_codepoint(65534)
+  |> should.be_error
+
+  string.utf_codepoint(55296)
+  |> should.be_error
+
+  assert Ok(snake) = string.utf_codepoint(128013)
+  should.equal(<<snake:utf8_codepoint>>, <<"🐍":utf8>>)
+}