Update docs, distinguish truncated/invalid

elixir-lang · Jan 18, 2024 · f14bcdc · f14bcdc
1 parent 1a36b68
commit f14bcdc
Show file tree

Hide file tree

Showing 2 changed files with 11 additions and 6 deletions.
diff --git a/lib/elixir/lib/string.ex b/lib/elixir/lib/string.ex
@@ -2586,27 +2586,29 @@ defmodule String do
     byte = :binary.at(string, last)
 
     cond do
-      # This byte is valid, discard all truncated entries
+      # ASCII byte, discard all truncated entries
       byte <= 127 ->
         last + 1
 
+      # In the middle of a codepoint
       byte <= 191 ->
         invalid_suffix(string, last - 1, truncated + 1)
 
-      # 2 bytes
+      # 2 bytes codepoint start
       byte <= 223 ->
         if truncated == 1, do: last + truncated + 1, else: last
 
-      # 3 bytes
+      # 3 bytes codepoint start
       byte <= 239 ->
         if truncated == 2, do: last + truncated + 1, else: last
 
-      # 3 bytes
+      # 4 bytes codepoint start
       byte <= 247 ->
         if truncated == 3, do: last + truncated + 1, else: last
 
+      # Invalid codepoint, discard it, stop checking
       true ->
-        last
+        last + 1
     end
   end
 

diff --git a/lib/elixir/test/elixir/string_test.exs b/lib/elixir/test/elixir/string_test.exs
@@ -845,8 +845,11 @@ defmodule StringTest do
     assert String.byte_slice("h😍ll😍", 2, 5) == "ll"
     assert String.byte_slice("h😍ll😍", 2, 6) == "ll😍"
 
-    # Already invalid
+    # Already truncated
     assert String.byte_slice(<<178, "ll", 178>>, 0, 10) == "ll"
+
+    # Already invalid
+    assert String.byte_slice(<<255, "ll", 255>>, 0, 10) == <<255, "ll", 255>>
   end
 
   test "valid?/1" do