fix(esg): honor the declared response charset in ReadBodyBoundedAsync with UTF-8 fallback (plan R2-06 T4)

This commit is contained in:
Joseph Doherty
2026-07-13 09:53:00 -04:00
parent cc94b3a68c
commit b41b3b1b31
2 changed files with 87 additions and 1 deletions
@@ -466,6 +466,12 @@ public class ExternalSystemClient : IExternalSystemClient
/// into store-and-forward would defeat the cap. Cancellation /// into store-and-forward would defeat the cap. Cancellation
/// (<see cref="OperationCanceledException"/>) is allowed to propagate so the /// (<see cref="OperationCanceledException"/>) is allowed to propagate so the
/// caller's ordered timeout/cancellation catch filters classify it. /// caller's ordered timeout/cancellation catch filters classify it.
/// <para>
/// N4: the accumulated bytes are decoded using the response's declared charset
/// (<c>Content-Type: …; charset=…</c>) via <see cref="ResolveEncoding"/> — parity
/// with the pre-bounded-read <c>ReadAsStringAsync</c>. A null, empty, or
/// unrecognized charset falls back to UTF-8.
/// </para>
/// </summary> /// </summary>
private static async Task<string> ReadBodyBoundedAsync( private static async Task<string> ReadBodyBoundedAsync(
HttpContent content, string systemName, long maxBytes, CancellationToken token) HttpContent content, string systemName, long maxBytes, CancellationToken token)
@@ -498,7 +504,33 @@ public class ExternalSystemClient : IExternalSystemClient
} }
} }
return Encoding.UTF8.GetString(buffer.GetBuffer(), 0, (int)buffer.Length); // N4: honor the response's declared charset (parity with the pre-bounded-read
// ReadAsStringAsync). Unknown/invalid charset → UTF-8 fallback: mojibake beats
// failing the call over a cosmetic header.
return ResolveEncoding(content.Headers.ContentType?.CharSet)
.GetString(buffer.GetBuffer(), 0, (int)buffer.Length);
}
/// <summary>
/// Resolves the declared response charset to an <see cref="Encoding"/>, tolerating
/// the quoted form some servers emit (<c>charset="iso-8859-1"</c>). Null, empty,
/// or unrecognized values fall back to UTF-8.
/// </summary>
private static Encoding ResolveEncoding(string? charset)
{
if (string.IsNullOrWhiteSpace(charset))
{
return Encoding.UTF8;
}
try
{
return Encoding.GetEncoding(charset.Trim().Trim('"'));
}
catch (ArgumentException)
{
return Encoding.UTF8;
}
} }
private static string Truncate(string value, int maxChars) private static string Truncate(string value, int maxChars)
@@ -1,5 +1,6 @@
using System.Net; using System.Net;
using System.Net.Http.Headers; using System.Net.Http.Headers;
using System.Text;
using Microsoft.Data.Sqlite; using Microsoft.Data.Sqlite;
using Microsoft.Extensions.Logging; using Microsoft.Extensions.Logging;
using Microsoft.Extensions.Logging.Abstractions; using Microsoft.Extensions.Logging.Abstractions;
@@ -1377,4 +1378,57 @@ public class ExternalSystemClientTests
Assert.False(delivered); Assert.False(delivered);
} }
[Fact]
public async Task Call_Latin1Charset_DecodesUsingDeclaredCharset()
{
// Arch-review R2 N4: the bounded read must honor the declared charset —
// UTF-8-decoding an iso-8859-1 body turns every non-ASCII byte into U+FFFD.
var system = new ExternalSystemDefinition("TestAPI", "https://api.example.com", "none") { Id = 1 };
var method = new ExternalSystemMethod("getData", "GET", "/data") { Id = 1, ExternalSystemDefinitionId = 1 };
StubResolution(system, method);
var handler = new ByteBodyHandler(
HttpStatusCode.OK,
Encoding.Latin1.GetBytes("température 25°C"),
"text/plain; charset=iso-8859-1");
_httpClientFactory.CreateClient(Arg.Any<string>()).Returns(new HttpClient(handler));
var client = new ExternalSystemClient(
_httpClientFactory, _repository, NullLogger<ExternalSystemClient>.Instance);
var result = await client.CallAsync("TestAPI", "getData");
Assert.True(result.Success);
Assert.Contains("température 25°C", result.ResponseJson);
}
[Fact]
public async Task Call_UnknownCharset_FallsBackToUtf8()
{
var system = new ExternalSystemDefinition("TestAPI", "https://api.example.com", "none") { Id = 1 };
var method = new ExternalSystemMethod("getData", "GET", "/data") { Id = 1, ExternalSystemDefinitionId = 1 };
StubResolution(system, method);
var handler = new ByteBodyHandler(
HttpStatusCode.OK, Encoding.UTF8.GetBytes("ok"), "text/plain; charset=not-a-charset");
_httpClientFactory.CreateClient(Arg.Any<string>()).Returns(new HttpClient(handler));
var client = new ExternalSystemClient(
_httpClientFactory, _repository, NullLogger<ExternalSystemClient>.Instance);
var result = await client.CallAsync("TestAPI", "getData");
Assert.True(result.Success);
Assert.Contains("ok", result.ResponseJson);
}
/// <summary>Test helper: returns a fixed byte body with an explicit Content-Type.</summary>
private sealed class ByteBodyHandler(
HttpStatusCode statusCode, byte[] body, string contentType) : HttpMessageHandler
{
protected override Task<HttpResponseMessage> SendAsync(
HttpRequestMessage request, CancellationToken cancellationToken)
{
var response = new HttpResponseMessage(statusCode) { Content = new ByteArrayContent(body) };
response.Content.Headers.ContentType = MediaTypeHeaderValue.Parse(contentType);
return Task.FromResult(response);
}
}
} }