Classify broken document and presentation packages

2026-10-08 19:29:40 +00:00 · 2026-09-09 15:57:22 +02:00
1 parent ec1d321598
commit 2a79f5f3b7
@@ -10723,6 +10723,9 @@ UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T1465212038
 -- The file '{0}' does not exist anymore and was not indexed.
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T1553912802"] = "The file '{0}' does not exist anymore and was not indexed."

+-- Not a readable document
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T1671731444"] = "Not a readable document"
+
 -- No text could be read from the file '{0}', so it was not indexed. It might contain images only, such as a scanned PDF without a text layer. AI Studio reads it again as soon as the file changes.
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T1675617688"] = "No text could be read from the file '{0}', so it was not indexed. It might contain images only, such as a scanned PDF without a text layer. AI Studio reads it again as soon as the file changes."

@@ -10804,6 +10807,9 @@ UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T4041351522
 -- File is open elsewhere
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T4201096587"] = "File is open elsewhere"

+-- 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.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T564482210"] = "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."
+
 -- PDF system unavailable
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T800475300"] = "PDF system unavailable"

@@ -10876,6 +10882,9 @@ UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONRESULTEXTENSIONS::T4291141931"]
 -- Reading the file '{0}' needs Pandoc, which is not available, so the file was not sent.
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONRESULTEXTENSIONS::T594894810"] = "Reading the file '{0}' needs Pandoc, which is not available, so the file was not sent."

+-- The file '{0}' is not a readable document and was not sent. It might be damaged or transferred incompletely.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONRESULTEXTENSIONS::T985448614"] = "The file '{0}' is not a readable document and was not sent. It might be damaged or transferred incompletely."
+
 -- AI Studio couldn't install Pandoc because the archive was not found.
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::PANDOC::T1059477764"] = "AI Studio couldn't install Pandoc because the archive was not found."

@@ -10725,6 +10725,9 @@ UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T1465212038
 -- The file '{0}' does not exist anymore and was not indexed.
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T1553912802"] = "Die Datei „{0}“ existiert nicht mehr und wurde nicht indexiert."

+-- Not a readable document
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T1671731444"] = "Kein lesbares Dokument"
+
 -- No text could be read from the file '{0}', so it was not indexed. It might contain images only, such as a scanned PDF without a text layer. AI Studio reads it again as soon as the file changes.
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T1675617688"] = "Aus der Datei „{0}“ konnte kein Text gelesen werden, daher wurde sie nicht indexiert. Möglicherweise enthält sie nur Bilder, etwa ein gescanntes PDF ohne Textebene. AI Studio liest sie erneut ein, sobald sich die Datei ändert."

@@ -10806,6 +10809,9 @@ UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T4041351522
 -- File is open elsewhere
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T4201096587"] = "Die Datei ist an anderer Stelle geöffnet."

+-- 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.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T564482210"] = "Die Datei „{0}“ ist kein lesbares Dokument und wurde nicht indexiert. Möglicherweise ist sie beschädigt oder unvollständig übertragen worden. AI Studio liest sie erneut ein, sobald sich die Datei ändert."
+
 -- PDF system unavailable
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T800475300"] = "PDF-System nicht verfügbar"

@@ -10878,6 +10884,9 @@ UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONRESULTEXTENSIONS::T4291141931"]
 -- Reading the file '{0}' needs Pandoc, which is not available, so the file was not sent.
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONRESULTEXTENSIONS::T594894810"] = "Zum Lesen der Datei „{0}“ wird Pandoc benötigt. Da Pandoc nicht verfügbar ist, wurde die Datei nicht gesendet."

+-- The file '{0}' is not a readable document and was not sent. It might be damaged or transferred incompletely.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONRESULTEXTENSIONS::T985448614"] = "Die Datei „{0}“ ist kein lesbares Dokument und wurde nicht gesendet. Möglicherweise ist sie beschädigt oder unvollständig übertragen worden."
+
 -- AI Studio couldn't install Pandoc because the archive was not found.
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::PANDOC::T1059477764"] = "AI Studio konnte Pandoc nicht installieren, da das Archiv nicht gefunden wurde."

@@ -10725,6 +10725,9 @@ UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T1465212038
 -- The file '{0}' does not exist anymore and was not indexed.
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T1553912802"] = "The file '{0}' does not exist anymore and was not indexed."

+-- Not a readable document
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T1671731444"] = "Not a readable document"
+
 -- No text could be read from the file '{0}', so it was not indexed. It might contain images only, such as a scanned PDF without a text layer. AI Studio reads it again as soon as the file changes.
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T1675617688"] = "No text could be read from the file '{0}', so it was not indexed. It might contain images only, such as a scanned PDF without a text layer. AI Studio reads it again as soon as the file changes."

@@ -10806,6 +10809,9 @@ UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T4041351522
 -- File is open elsewhere
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T4201096587"] = "File is open elsewhere"

+-- 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.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T564482210"] = "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."
+
 -- PDF system unavailable
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONERRORCODEEXTENSIONS::T800475300"] = "PDF system unavailable"

@@ -10878,6 +10884,9 @@ UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONRESULTEXTENSIONS::T4291141931"]
 -- Reading the file '{0}' needs Pandoc, which is not available, so the file was not sent.
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONRESULTEXTENSIONS::T594894810"] = "Reading the file '{0}' needs Pandoc, which is not available, so the file was not sent."

+-- The file '{0}' is not a readable document and was not sent. It might be damaged or transferred incompletely.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::FILEEXTRACTIONRESULTEXTENSIONS::T985448614"] = "The file '{0}' is not a readable document and was not sent. It might be damaged or transferred incompletely."
+
 -- AI Studio couldn't install Pandoc because the archive was not found.
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::PANDOC::T1059477764"] = "AI Studio couldn't install Pandoc because the archive was not found."

@@ -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,
@@ -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."),
@@ -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."),