Classify broken document and presentation packages

app/MindWork AI Studio/Tools/FileExtractionErrorCode.cs

@@ -32,6 +32,13 @@ public enum FileExtractionErrorCode
     FORMAT_DETECTION_FAILED,
     NOT_A_VALID_PDF,
     NOT_A_VALID_SPREADSHEET,
+
+    /// <summary>
+    /// The package of a Word, OpenDocument, or presentation file is broken, e.g. a damaged
+    /// archive or a missing part inside it.
+    /// </summary>
+    NOT_A_VALID_DOCUMENT,
+
     PDFIUM_UNAVAILABLE,
     PDF_ENCRYPTED,
     PAGE_EXTRACTION_FAILED,

app/MindWork AI Studio/Tools/FileExtractionErrorCodeExtensions.cs

@@ -32,6 +32,7 @@ internal static class FileExtractionErrorCodeExtensions
         FileExtractionErrorCode.NOT_TEXT_CONTENT => true,
         FileExtractionErrorCode.NOT_A_VALID_PDF => true,
         FileExtractionErrorCode.NOT_A_VALID_SPREADSHEET => true,
+        FileExtractionErrorCode.NOT_A_VALID_DOCUMENT => true,
         FileExtractionErrorCode.PDF_ENCRYPTED => true,
         FileExtractionErrorCode.FORMAT_DETECTION_FAILED => true,
         FileExtractionErrorCode.EXECUTABLE_REJECTED => true,
@@ -65,6 +66,7 @@ internal static class FileExtractionErrorCodeExtensions
         FileExtractionErrorCode.NOT_TEXT_CONTENT => TB("Not a text file"),
         FileExtractionErrorCode.NOT_A_VALID_PDF => TB("Not a readable PDF"),
         FileExtractionErrorCode.NOT_A_VALID_SPREADSHEET => TB("Not a readable spreadsheet"),
+        FileExtractionErrorCode.NOT_A_VALID_DOCUMENT => TB("Not a readable document"),
         FileExtractionErrorCode.PDF_ENCRYPTED => TB("Protected PDF"),
         FileExtractionErrorCode.FORMAT_DETECTION_FAILED => TB("Unknown file type"),
         FileExtractionErrorCode.EXECUTABLE_REJECTED => TB("Executable program"),
@@ -115,6 +117,7 @@ internal static class FileExtractionErrorCodeExtensions
         FileExtractionErrorCode.NOT_TEXT_CONTENT => TB("The file '{0}' is not a text file, so it was not indexed. Its content could not be read as text, which means it might have a wrong file extension. AI Studio reads it again as soon as the file changes."),
         FileExtractionErrorCode.NOT_A_VALID_PDF => TB("The file '{0}' is not a readable PDF, so it was not indexed. It might be damaged or transferred incompletely. AI Studio reads it again as soon as the file changes."),
         FileExtractionErrorCode.NOT_A_VALID_SPREADSHEET => TB("The file '{0}' is not a readable spreadsheet, so it was not indexed. It might be damaged or transferred incompletely. AI Studio reads it again as soon as the file changes."),
+        FileExtractionErrorCode.NOT_A_VALID_DOCUMENT => TB("The file '{0}' is not a readable document, so it was not indexed. It might be damaged or transferred incompletely. AI Studio reads it again as soon as the file changes."),
         FileExtractionErrorCode.PDF_ENCRYPTED => TB("The file '{0}' is protected and could not be opened, so it was not indexed. AI Studio reads it again as soon as the file changes."),
         FileExtractionErrorCode.FORMAT_DETECTION_FAILED => TB("The file type of '{0}' could not be determined, so the file was not indexed. AI Studio reads it again as soon as the file changes."),
         FileExtractionErrorCode.EXECUTABLE_REJECTED => TB("The file '{0}' is an executable program and was not indexed, regardless of its file extension."),

app/MindWork AI Studio/Tools/FileExtractionResultExtensions.cs

@@ -78,6 +78,7 @@ internal static class FileExtractionResultExtensions
         FileExtractionErrorCode.TIMEOUT => TB("Reading the file '{0}' took too long and was stopped, so the file was not sent. When the file is stored on a network drive, the connection might be slow or interrupted."),
         FileExtractionErrorCode.NOT_A_VALID_PDF => TB("The file '{0}' is not a readable PDF and was not sent. It might be damaged or transferred incompletely."),
         FileExtractionErrorCode.NOT_A_VALID_SPREADSHEET => TB("The file '{0}' is not a readable spreadsheet and was not sent. It might be damaged or transferred incompletely."),
+        FileExtractionErrorCode.NOT_A_VALID_DOCUMENT => TB("The file '{0}' is not a readable document and was not sent. It might be damaged or transferred incompletely."),
         FileExtractionErrorCode.PDF_ENCRYPTED => TB("The file '{0}' is protected and could not be opened, so it was not sent."),
         FileExtractionErrorCode.PDFIUM_UNAVAILABLE => TB("AI Studio was not able to start its PDF engine, so the file '{0}' was not sent."),
         FileExtractionErrorCode.PANDOC_UNAVAILABLE => TB("Reading the file '{0}' needs Pandoc, which is not available, so the file was not sent."),