Stefan/Fuchs_Intranet
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix invoice-image code-review findings: aspect ratio, whitelist config, stale refs

Browse Source 
- MigraDocExtensions: fix a bug where capping an oversized explicit
  width+height image re-derived the other dimension from the image's
  native pixel ratio instead of scaling both sides uniformly, silently
  distorting a deliberately non-native-ratio (e.g. stretched) image.
- InvoiceService: derive the mfr-portal image whitelist prefix from the
  existing Fds:MFR_host config setting (via MFRClientConfig.RestRoot)
  instead of a second hardcoded literal, so it can't drift from the
  actual configured host; parse <img> sources with HtmlAgilityPack
  (already used by the PDF's own HTML converter) instead of a regex, so
  a decoy attribute like data-src can't be picked up in place of the
  real src; dedup fetch URLs with a HashSet instead of O(n^2) List
  scanning; reuse FuchsPdf.MigraDocFilenameFromByteArray instead of
  re-spelling the "base64:" prefix.
- Fix a stale log message and comment left over from the
  GenerateInvoicePdf -> GenerateInvoicePdfAsync rename, and update
  INVOICE_LIFECYCLE.md's references to the old sync method name.
- Add tests for the config-derived whitelist, a decoy-attribute src,
  and the 20-image-per-invoice fetch cap boundary.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
Stefan
2026-09-10 21:03:09 +02:00
co-authored by Claude Sonnet 5
parent c182d4fd69
commit 406c6f2860
6 changed files with 146 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Fuchs/Services/InvoiceService.cs
+33 -20
View File
@@ -1,10 +1,12 @@
using System.Data;
using System.Diagnostics;
using System.Text.RegularExpressions;
using Fuchs.intranet;
using Fuchs.Notifications;
using Fuchs.Observability;
using HtmlAgilityPack;
using MFR_RESTClient;
using Microsoft.Data.SqlClient;
using Microsoft.Extensions.Configuration;
using Microsoft.Extensions.Logging;
using MigraDoc.DocumentObjectModel;
using Newtonsoft.Json.Linq;
@@ -26,19 +28,9 @@ public class InvoiceService : IInvoiceService
/// <summary>Named <see cref="IHttpClientFactory"/> client used to fetch invoice-text images.</summary>
public const string InlineImageHttpClientName = "InvoiceInlineImages";
/// <summary>
/// The only origin invoice-text &lt;img&gt; sources are fetched from for inline PDF rendering
/// (ADR 0018) — the mfr portal picture links the invoice editor already displays. Any other
/// src (including other remote hosts) is left unrendered, exactly as before this feature.
/// </summary>
internal const string AllowedInlineImagePrefix = "https://portal.mobilefieldreport.com/mfr/";
private const int MaxInlineImageBytes = 5 * 1024 * 1024;
private const int MaxInlineImagesPerInvoice = 20;
private static readonly Regex ImgSrcRegex =
new(@"<img[^>]+src\s*=\s*[""']([^""']+)[""']", RegexOptions.IgnoreCase | RegexOptions.Compiled);
private readonly Fuchs_intranet _intranet;
private readonly IPdfService _pdf;
private readonly IBlobStorageService _blobStorage;
@@ -47,9 +39,19 @@ public class InvoiceService : IInvoiceService
private readonly IHttpClientFactory _httpClientFactory;
private readonly ILogger<InvoiceService> _logger;
/// <summary>
/// The only origin invoice-text &lt;img&gt; sources are fetched from for inline PDF rendering
/// (ADR 0018) — the mfr portal picture links the invoice editor already displays. Any other
/// src (including other remote hosts) is left unrendered, exactly as before this feature.
/// Derived from the same <c>Fds:MFR_host</c> setting the MFR REST client itself uses (via
/// <see cref="MFRClientConfig.RestRoot"/>), not a separately-hardcoded host, so it can't drift
/// from the actual configured mfr portal.
/// </summary>
internal readonly string AllowedInlineImagePrefix;
public InvoiceService(Fuchs_intranet intranet, IPdfService pdf, IBlobStorageService blobStorage,
IEventService events, IERechnungService erechnung, IHttpClientFactory httpClientFactory,
ILogger<InvoiceService> logger)
IConfiguration configuration, ILogger<InvoiceService> logger)
{
_intranet = intranet;
_pdf = pdf;
@@ -58,6 +60,11 @@ public class InvoiceService : IInvoiceService
_erechnung = erechnung;
_httpClientFactory = httpClientFactory;
_logger = logger;
string? mfrHost = configuration["Fds:MFR_host"];
AllowedInlineImagePrefix = string.IsNullOrWhiteSpace(mfrHost)
? MFRClientConfig.DefaultHost + "/mfr/"
: new MFRClientConfig(mfrHost).RestRoot;
}
private string Conn => _intranet.Intranet__SQLConnectionString;
@@ -284,7 +291,7 @@ public class InvoiceService : IInvoiceService
using var act = FuchsTelemetry.StartActivity("invoice.render");
act?.SetTag("fuchs.invoice.id", invoice.Id);
act?.SetTag("fuchs.invoice.draft", draft);
_logger.LogDebug("GenerateInvoicePdf id={Id} draft={Draft}", invoice.Id, draft);
_logger.LogDebug("GenerateInvoicePdfAsync id={Id} draft={Draft}", invoice.Id, draft);
var reg = invoice.InvoiceRegistration;
var tb = new FuchsPdf.FdsTextBlocks
{
@@ -297,7 +304,6 @@ public class InvoiceService : IInvoiceService
AdminDatumValue = reg?.getString("DateCreated") is { Length: > 0 } dc ? DateTime.Parse(dc) : DateTime.Now
};
var inlineImages = await ResolveInlineImagesAsync(invoice);
// WriteLetter is effectively synchronous; no Task.Run thread-hop (safe: no sync context in ASP.NET Core).
var doc = await _pdf.WriteLetterAsync(tb, draft);
doc.Info.Title = reg?.getString("InvoiceTitle") ?? "";
_pdf.ApplyInvoice(doc, tb, invoice, draft, inlineImages);
@@ -315,17 +321,24 @@ public class InvoiceService : IInvoiceService
internal async Task<Dictionary<string, string>> ResolveInlineImagesAsync(FdsInvoiceData invoice)
{
var result = new Dictionary<string, string>();
var urls = new List<string>();
// Parsed with HtmlAgilityPack (already a project dependency, and what the PDF's own HTML
// converter parses this same text with) rather than a regex, so a decoy attribute like
// data-src="..." next to the real src can never be picked up in its place.
var urls = new HashSet<string>();
foreach (var block in invoice.InvoiceBlocks)
foreach (var item in block.Items)
{
string desc = item.nz("desc", "");
if (desc.Length == 0) continue;
foreach (Match m in ImgSrcRegex.Matches(desc))
var doc = new HtmlDocument();
doc.LoadHtml(desc);
var imgNodes = doc.DocumentNode.SelectNodes("//img");
if (imgNodes == null) continue;
foreach (var node in imgNodes)
{
string src = m.Groups[1].Value;
if (src.StartsWith(AllowedInlineImagePrefix, StringComparison.Ordinal)
&& !urls.Contains(src) && urls.Count < MaxInlineImagesPerInvoice)
string src = node.GetAttributeValue("src", "");
if (src.Length > 0 && src.StartsWith(AllowedInlineImagePrefix, StringComparison.Ordinal)
&& urls.Count < MaxInlineImagesPerInvoice)
urls.Add(src);
}
}
@@ -354,7 +367,7 @@ public class InvoiceService : IInvoiceService
_logger.LogWarning("ResolveInlineImagesAsync: {Url} image size {Size} out of bounds", url, bytes.Length);
continue;
}
result[url] = "base64:" + Convert.ToBase64String(bytes);
result[url] = FuchsPdf.MigraDocFilenameFromByteArray(bytes);
}
catch (Exception ex)
{