From 93062e2b7802a001226ec87f9fd3506dc07bc720 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Julian=20Offenh=C3=A4user?= Date: Tue, 21 Feb 2023 23:56:49 +0100 Subject: [PATCH] LibPDF: Be more cautious of errors when looking for linearization dict We would previously assume that, following the header, there must be a valid PDF object that could be a linearization dict. However, if the file is not linearized, this is not necessarily true. We now try to detect if there even is an object, and don't treat parsing errors as fatal. --- Userland/Libraries/LibPDF/DocumentParser.cpp | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/Userland/Libraries/LibPDF/DocumentParser.cpp b/Userland/Libraries/LibPDF/DocumentParser.cpp index b070c30a566..e2c1538e6eb 100644 --- a/Userland/Libraries/LibPDF/DocumentParser.cpp +++ b/Userland/Libraries/LibPDF/DocumentParser.cpp @@ -111,8 +111,21 @@ PDFErrorOr DocumentParser::parse_header() PDFErrorOr DocumentParser::initialize_linearization_dict() { - // parse_header() is called immediately before this, so we are at the right location - auto indirect_value = Value(*TRY(parse_indirect_value())); + // parse_header() is called immediately before this, so we are at the right location. + // There may not actually be a linearization dict, or even a valid PDF object here. + // If that is the case, this file may be completely valid but not linearized. + + // If there is indeed a linearization dict, there should be an object number here. + if (!m_reader.matches_number()) + return LinearizationResult::NotLinearized; + + // At this point, we still don't know for sure if we are dealing with a valid object. + auto indirect_value_or_error = parse_indirect_value(); + if (indirect_value_or_error.is_error()) + return LinearizationResult::NotLinearized; + + auto indirect_value = indirect_value_or_error.value(); + auto dict_value = TRY(m_document->resolve(indirect_value)); if (!dict_value.has>()) return error("Expected linearization object to be a dictionary");