Classify broken document and presentation packages

This commit is contained in:
Thorsten Sommer committed 2026-09-09 15:57:22 +02:00
1 parent ec1d321598
commit 2a79f5f3b7
7 files changed
+103 -9

No files matched your search

@@ -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."),