Skip to content

We have extra and unnecessary checks. #53

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
lemire merged 1 commit into from
May 5, 2026
+15 −7
Merged

We have extra and unnecessary checks. #53

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 8 additions & 4 deletions src/UTF8.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -124,7 +124,8 @@ private static (int utfAdjust, int scalarAdjust) GetFinalScalarUtfAdjustments(by
} // Too short
// range check
codePoint = (uint)(firstByte & 0b00011111) << 6 | (uint)(buf[pos + 1] & 0b00111111);
if ((codePoint < 0x80) || (0x7ff < codePoint))
// codePoint is necessarily <= 0x7ff
if (codePoint < 0x80)
{
return buf + pos;
} // Overlong
Expand All @@ -141,7 +142,8 @@ private static (int utfAdjust, int scalarAdjust) GetFinalScalarUtfAdjustments(by
(uint)(buf[pos + 1] & 0b00111111) << 6 |
(uint)(buf[pos + 2] & 0b00111111);
// Either overlong or too large:
if ((codePoint < 0x800) || (0xffff < codePoint) ||
// codePoint is necessarily <= 0xffff
if ((codePoint < 0x800) ||
(0xd7ff < codePoint && codePoint < 0xe000))
{
return buf + pos;
Expand Down Expand Up @@ -238,7 +240,8 @@ private static (int utfAdjust, int scalarAdjust) GetFinalScalarUtfAdjustments(by
} // Too short
// range check
codePoint = (uint)(firstByte & 0b00011111) << 6 | (uint)(pInputBuffer[pos + 1] & 0b00111111);
if ((codePoint < 0x80) || (0x7ff < codePoint))
// codePoint is necessarily <= 0x7ff
if (codePoint < 0x80)
{
utf16CodeUnitCountAdjustment = TempUtf16CodeUnitCountAdjustment;
scalarCountAdjustment = TempScalarCountAdjustment;
Expand All @@ -261,7 +264,8 @@ private static (int utfAdjust, int scalarAdjust) GetFinalScalarUtfAdjustments(by
(uint)(pInputBuffer[pos + 1] & 0b00111111) << 6 |
(uint)(pInputBuffer[pos + 2] & 0b00111111);
// Either overlong or too large:
if ((codePoint < 0x800) || (0xffff < codePoint) ||
// codePoint is necessarily <= 0xffff
if ((codePoint < 0x800) ||
(0xd7ff < codePoint && codePoint < 0xe000))
{
utf16CodeUnitCountAdjustment = TempUtf16CodeUnitCountAdjustment;
Expand Down
3 changes: 2 additions & 1 deletion test/AsciiTest.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
namespace tests;
namespace tests;

using System.Text;
using SimdUnicode;

Expand Down
6 changes: 4 additions & 2 deletions test/UTF8ValidationTests.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
namespace tests;

using System.Text;
using SimdUnicode;
using System.Diagnostics;
Expand Down Expand Up @@ -1245,7 +1246,8 @@ public static bool ValidateUtf8Fuschia(byte[] data)
if ((data[pos + 1] & 0b11000000) != 0b10000000) return false;

codePoint = (uint)((byte1 & 0b00011111) << 6 | (data[pos + 1] & 0b00111111));
if (codePoint < 0x80 || 0x7ff < codePoint) return false;
// codePoint is necessarily <= 0x7ff
if (codePoint < 0x80) return false;
pos += 2;
}
else if ((byte1 & 0b11110000) == 0b11100000)
Expand All @@ -1255,7 +1257,7 @@ public static bool ValidateUtf8Fuschia(byte[] data)
if ((data[pos + 2] & 0b11000000) != 0b10000000) return false;

codePoint = (uint)((byte1 & 0b00001111) << 12 | (data[pos + 1] & 0b00111111) << 6 | (data[pos + 2] & 0b00111111));
if (codePoint < 0x800 || 0xffff < codePoint || (0xd7ff < codePoint && codePoint < 0xe000)) return false;
if (codePoint < 0x800 || (0xd7ff < codePoint && codePoint < 0xe000)) return false;
pos += 3;
}
else if ((byte1 & 0b11111000) == 0b11110000)
Expand Down
1 change: 1 addition & 0 deletions test/helpers/randomutf8.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
namespace tests;

using System;
using System.Collections.Generic;
using System.Linq;
Expand Down
Loading