Werkzeugkasten: PDF-Text aus Anhaengen und Dateien (#692)

- DocumentText reads PDF with PdfPig 0.1.16 (managed, Apache-2.0): page by
  page in reading order, at most 300 pages; a PDF without a text layer is
  named as probably scanned; broken and protected files are named.
- Mail read_attachment and FileRW read/read_many take PDF like Word/Excel.
- nuget.config maps exactly "PdfPig" - "UglyToad.PdfPig" is a package of a
  different account and stays out.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

src/ClawdDotNet.Core/ClawdDotNet.Core.csproj

@@ -23,6 +23,11 @@
     <PackageReference Include="System.Security.Cryptography.ProtectedData" Version="10.0.0" />
     <PackageReference Include="Microsoft.Extensions.Logging" Version="10.0.8" />
     <PackageReference Include="Microsoft.Extensions.Logging.Abstractions" Version="10.0.8" />
+
+    <!-- #692: PDF text, managed code only, Apache-2.0. Das Paket heisst "PdfPig" (Eigentuemer
+         EliotJones/BobLd, github.com/UglyToad/PdfPig) - NICHT "UglyToad.PdfPig": unter diesem
+         Namen liegt eine fremde Vorabversion eines anderen Kontos. -->
+    <PackageReference Include="PdfPig" Version="0.1.16" />
   </ItemGroup>
 
 </Project>

src/ClawdDotNet.Core/Documents/DocumentText.cs

@@ -22,8 +22,8 @@ public sealed record DocumentExtraction(bool Ok, string Text, string Kind, bool
 /// <para><b>Bounded.</b> Office files are zip archives, and a zip can unpack to anything. Every
 /// part is read up to <see cref="MaxPartBytes"/>, the whole up to the caller's character limit.</para>
 ///
-/// <para>PDF is not read here yet: a reliable PDF text extractor is a library decision, not a
-/// hundred lines of code — fonts with their own encodings come out as garbage otherwise.</para>
+/// <para><b>PDF</b> is read with PdfPig (managed code only): the text of each page in reading
+/// order. A scanned PDF has no text layer and is named as such — reading it would need OCR.</para>
 /// </summary>
 public static class DocumentText
 {
@@ -40,7 +40,10 @@ public static class DocumentText
 
     /// <summary>Whether the file is a document whose text needs extracting (not plain text).</summary>
     public static bool IsOfficeDocument(string fileName)
-        => Path.GetExtension(fileName).ToLowerInvariant() is ".docx" or ".xlsx";
+        => Path.GetExtension(fileName).ToLowerInvariant() is ".docx" or ".xlsx" or ".pdf";
+
+    /// <summary>Pages read from one PDF — an invoice has a few, a catalogue is not read whole.</summary>
+    public const int MaxPdfPages = 300;
 
     public static DocumentExtraction Extract(byte[] content, string fileName, int maxChars)
     {
@@ -51,7 +54,7 @@ public static class DocumentText
             {
                 ".docx" => Bounded(Docx(content), "Word document", maxChars),
                 ".xlsx" => Bounded(Xlsx(content), "spreadsheet", maxChars),
-                ".pdf" => DocumentExtraction.Fail("PDF", "PDF text cannot be read in this version yet."),
+                ".pdf" => Pdf(content, maxChars),
                 _ when PlainText.Contains(ext) => Bounded(Decode(content), "text", maxChars),
                 _ => DocumentExtraction.Fail(ext.TrimStart('.'), $"'{ext}' files cannot be read as text.")
             };
@@ -62,6 +65,44 @@ public static class DocumentText
         }
     }
 
+    // ─── PDF ───
+
+    private static DocumentExtraction Pdf(byte[] content, int maxChars)
+    {
+        try
+        {
+            using var document = UglyToad.PdfPig.PdfDocument.Open(content, new UglyToad.PdfPig.ParsingOptions { UseLenientParsing = true });
+            var sb = new StringBuilder();
+            var pages = document.NumberOfPages;
+            var read = 0;
+            foreach (var page in document.GetPages())
+            {
+                if (read >= MaxPdfPages || sb.Length > maxChars)
+                    break;
+                read++;
+                var text = UglyToad.PdfPig.DocumentLayoutAnalysis.TextExtractor.ContentOrderTextExtractor.GetText(page).Trim();
+                if (pages > 1)
+                    sb.AppendLine($"## Page {page.Number}");
+                sb.AppendLine(text).AppendLine();
+            }
+
+            var all = sb.ToString().Trim();
+            if (all.Replace("## Page", "").All(c => char.IsWhiteSpace(c) || char.IsDigit(c)))
+                return DocumentExtraction.Fail("PDF", "The PDF has no text layer — it is probably scanned, and reading it would need OCR.");
+            if (read < pages)
+                all += $"\n\n(Read {read} of {pages} pages.)";
+            var bounded = Bounded(all, "PDF", maxChars);
+            return bounded with { Truncated = bounded.Truncated || read < pages };
+        }
+        catch (Exception ex) when (ex is not OutOfMemoryException)
+        {
+            // PdfPig throws its own exceptions for broken and encrypted files.
+            return DocumentExtraction.Fail("PDF", ex.Message.Contains("password", StringComparison.OrdinalIgnoreCase) || ex.Message.Contains("encrypt", StringComparison.OrdinalIgnoreCase)
+                ? "The PDF is protected by a password."
+                : $"The PDF could not be read: {ex.Message}");
+        }
+    }
+
     private static DocumentExtraction Bounded(string text, string kind, int maxChars)
     {
         var limit = Math.Max(1, maxChars);