From 0cef727e59d7b0c34756c09f64cbfe4490dcc3e7 Mon Sep 17 00:00:00 2001
From: Ryan Liptak <squeek502@hotmail.com>
Date: Tue, 11 Jun 2024 22:13:22 -0700
Subject: [PATCH] More precise error message for unencodable `\u` escapes

The surrogate code points U+D800 to U+DFFF are valid code points but are not Unicode scalar values. This commit makes the error message more accurately reflect what is actually allowed in `\u` escape sequences.

From https://www.unicode.org/versions/Unicode15.0.0/ch03.pdf:

> D71 High-surrogate code point: A Unicode code point in the range U+D800 to U+DBFF.
> D73 Low-surrogate code point: A Unicode code point in the range U+DC00 to U+DFFF.
>
> 3.9 Unicode Encoding Forms
> D76 Unicode scalar value: Any Unicode code point except high-surrogate and low-surrogate code points.

Related: #20270
---
 doc/langref.html.in      | 4 ++--
 lib/std/zig/AstGen.zig   | 2 +-
 src/Package/Manifest.zig | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/doc/langref.html.in b/doc/langref.html.in
index 42aebdcac2..9ef3691991 100644
--- a/doc/langref.html.in
+++ b/doc/langref.html.in
@@ -728,12 +728,12 @@
         </tr>
         <tr>
             <th scope="row"><code>\u{NNNNNN}</code></th>
-          <td>hexadecimal Unicode code point UTF-8 encoded (1 or more digits)</td>
+          <td>hexadecimal Unicode scalar value UTF-8 encoded (1 or more digits)</td>
         </tr>
         </tbody>
       </table>
       </div>
-      <p>Note that the maximum valid Unicode point is {#syntax#}0x10ffff{#endsyntax#}.</p>
+      <p>Note that the maximum valid Unicode scalar value is {#syntax#}0x10ffff{#endsyntax#}.</p>
       {#header_close#}
       {#header_open|Multiline String Literals#}
       <p>
diff --git a/lib/std/zig/AstGen.zig b/lib/std/zig/AstGen.zig
index 9c068eb597..f02dcaa2db 100644
--- a/lib/std/zig/AstGen.zig
+++ b/lib/std/zig/AstGen.zig
@@ -11306,7 +11306,7 @@ fn failWithStrLitError(astgen: *AstGen, err: std.zig.string_literal.Error, token
             return astgen.failOff(
                 token,
                 offset + @as(u32, @intCast(bad_index)),
-                "unicode escape does not correspond to a valid codepoint",
+                "unicode escape does not correspond to a valid unicode scalar value",
                 .{},
             );
         },
diff --git a/src/Package/Manifest.zig b/src/Package/Manifest.zig
index 589be91357..3bcb4a7958 100644
--- a/src/Package/Manifest.zig
+++ b/src/Package/Manifest.zig
@@ -522,7 +522,7 @@ const Parse = struct {
                 try p.appendErrorOff(
                     token,
                     offset + @as(u32, @intCast(bad_index)),
-                    "unicode escape does not correspond to a valid codepoint",
+                    "unicode escape does not correspond to a valid unicode scalar value",
                     .{},
                 );
             },