| author |  Ryan Liptak <squeek502@hotmail.com> 2024-06-11 22:13:22-07:00 |
| committer |  Andrew Kelley <andrew@ziglang.org> 2024-06-12 16:49:00-04:00 |
| log | 0cef727e59d7b0c34756c09f64cbfe4490dcc3e7 |
| tree | 4cecb36f3903d8c97a9205dd33e7374cdc9b192f |
| parent | 44f4abf3805eb457525a474f243b71373b5c3824 |
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: #202703 files changed, 4 insertions(+), 4 deletions(-)
lib- std
- zig
- src
- Package
doc/langref.html.in+2-2
| ... | @@ -728,12 +728,12 @@ | ... | @@ -728,12 +728,12 @@ |
| 728 | </tr> | 728 | </tr> |
| 729 | <tr> | 729 | <tr> |
| 730 | <th scope="row"><code>\u{NNNNNN}</code></th> | 730 | <th scope="row"><code>\u{NNNNNN}</code></th> |
| 731 | <td>hexadecimal Unicode code point UTF-8 encoded (1 or more digits)</td> | 731 | <td>hexadecimal Unicode scalar value UTF-8 encoded (1 or more digits)</td> |
| 732 | </tr> | 732 | </tr> |
| 733 | </tbody> | 733 | </tbody> |
| 734 | </table> | 734 | </table> |
| 735 | </div> | 735 | </div> |
| 736 | <p>Note that the maximum valid Unicode point is {#syntax#}0x10ffff{#endsyntax#}.</p> | 736 | <p>Note that the maximum valid Unicode scalar value is {#syntax#}0x10ffff{#endsyntax#}.</p> |
| 737 | {#header_close#} | 737 | {#header_close#} |
| 738 | {#header_open|Multiline String Literals#} | 738 | {#header_open|Multiline String Literals#} |
| 739 | <p> | 739 | <p> |
lib/std/zig/AstGen.zig+1-1
| ... | @@ -11306,7 +11306,7 @@ fn failWithStrLitError(astgen: *AstGen, err: std.zig.string_literal.Error, token | ... | @@ -11306,7 +11306,7 @@ fn failWithStrLitError(astgen: *AstGen, err: std.zig.string_literal.Error, token |
| 11306 | return astgen.failOff( | 11306 | return astgen.failOff( |
| 11307 | token, | 11307 | token, |
| 11308 | offset + @as(u32, @intCast(bad_index)), | 11308 | offset + @as(u32, @intCast(bad_index)), |
| 11309 | "unicode escape does not correspond to a valid codepoint", | 11309 | "unicode escape does not correspond to a valid unicode scalar value", |
| 11310 | .{}, | 11310 | .{}, |
| 11311 | ); | 11311 | ); |
| 11312 | }, | 11312 | }, |
src/Package/Manifest.zig+1-1
| ... | @@ -522,7 +522,7 @@ const Parse = struct { | ... | @@ -522,7 +522,7 @@ const Parse = struct { |
| 522 | try p.appendErrorOff( | 522 | try p.appendErrorOff( |
| 523 | token, | 523 | token, |
| 524 | offset + @as(u32, @intCast(bad_index)), | 524 | offset + @as(u32, @intCast(bad_index)), |
| 525 | "unicode escape does not correspond to a valid codepoint", | 525 | "unicode escape does not correspond to a valid unicode scalar value", |
| 526 | .{}, | 526 | .{}, |
| 527 | ); | 527 | ); |
| 528 | }, | 528 | }, |