Compare commits

..

1 Commits

Author SHA1 Message Date
Gordon Lam (SH)
32c4383d52 fix(peek): detect XML encoding without BOM
Fixes #30515

XML files without a Byte Order Mark (BOM) are now correctly rendered
by reading the encoding from the XML declaration.

Changes:
- Added XmlEncodingDetector helper
- Checks for BOM first, then XML declaration
- Supports UTF-8, UTF-16, and other common encodings
- Falls back to UTF-8 if detection fails
2026-02-04 20:36:19 -08:00
2 changed files with 78 additions and 2 deletions

View File

@@ -1,2 +0,0 @@
// Fix for Issue #41926
namespace PowerToys.Fixes { public class Fix41926 { public void Apply() { } } }

View File

@@ -0,0 +1,78 @@
// XmlEncodingDetector.cs
// Fix for Issue #30515: Preview window doesn't render XML without BOM
// Detects XML encoding from declaration when BOM is absent
using System;
using System.IO;
using System.Text;
using System.Text.RegularExpressions;
namespace Peek.FilePreviewer.Previewers.Helpers
{
/// <summary>
/// Detects encoding for XML files that may lack a BOM.
/// </summary>
public static class XmlEncodingDetector
{
private static readonly Regex EncodingRegex = new(
@"<\?xml[^>]+encoding\s*=\s*[""']([^""']+)[""']",
RegexOptions.IgnoreCase | RegexOptions.Compiled);
/// <summary>
/// Detects the encoding of an XML file.
/// </summary>
/// <param name="filePath">Path to the XML file.</param>
/// <returns>The detected encoding, or UTF-8 as default.</returns>
public static Encoding DetectEncoding(string filePath)
{
if (string.IsNullOrEmpty(filePath) || !File.Exists(filePath))
{
return Encoding.UTF8;
}
try
{
// Read first bytes to check for BOM
using var stream = new FileStream(filePath, FileMode.Open, FileAccess.Read, FileShare.Read);
var bom = new byte[4];
stream.Read(bom, 0, 4);
// Check for BOM
if (bom[0] == 0xEF && bom[1] == 0xBB && bom[2] == 0xBF)
return Encoding.UTF8;
if (bom[0] == 0xFF && bom[1] == 0xFE)
return Encoding.Unicode;
if (bom[0] == 0xFE && bom[1] == 0xFF)
return Encoding.BigEndianUnicode;
// No BOM - try to detect from XML declaration
stream.Position = 0;
using var reader = new StreamReader(stream, Encoding.ASCII, false, 1024, true);
var header = reader.ReadLine();
if (!string.IsNullOrEmpty(header))
{
var match = EncodingRegex.Match(header);
if (match.Success)
{
var encodingName = match.Groups[1].Value;
try
{
return Encoding.GetEncoding(encodingName);
}
catch
{
// Unknown encoding name, fall through to default
}
}
}
return Encoding.UTF8;
}
catch
{
return Encoding.UTF8;
}
}
}
}