From 67ccef73bf664b7cdb4c6eed7acbaa4163c22a80 Mon Sep 17 00:00:00 2001 From: Jane Liu Date: Wed, 19 Jul 2017 13:10:50 -0400 Subject: Use CFX_WideString in CPDF_NameTree functions to strip BOM PDFium doesn't strip BOMs during parsing, but we should strip BOMs when retrieving parsed strings in CPDF_NameTree to ensure consistency and appropriate function behavior. See the bug for more info. As outlined in Bug=pdfium:593, the solution is to call GetUnicodeText() instead of GetString(). I added a GetUnicodeTextAt() function in CPDF_Array, which is symmetrical to GetUnicodeTextFor() in CPDF_Dictionary. I then changed the input variable types to CPDF_NameTree functions to be CFX_WideString instead of CFX_ByteString, and modified all the calls to them. I also added a unit test for nametree, which would fail prior to this change. Nametrees with non-unicode names are already tested by embedder tests. Bug=pdfium:820 Change-Id: Id69d7343632f83d1f5180348c0eea290f478183f Reviewed-on: https://pdfium-review.googlesource.com/8091 Reviewed-by: dsinclair Commit-Queue: Jane Liu --- core/fpdfdoc/cpdf_action.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'core/fpdfdoc/cpdf_action.cpp') diff --git a/core/fpdfdoc/cpdf_action.cpp b/core/fpdfdoc/cpdf_action.cpp index 88d0781e80..2357580548 100644 --- a/core/fpdfdoc/cpdf_action.cpp +++ b/core/fpdfdoc/cpdf_action.cpp @@ -42,7 +42,7 @@ CPDF_Dest CPDF_Action::GetDest(CPDF_Document* pDoc) const { return CPDF_Dest(); if (pDest->IsString() || pDest->IsName()) { CPDF_NameTree name_tree(pDoc, "Dests"); - return CPDF_Dest(name_tree.LookupNamedDest(pDoc, pDest->GetString())); + return CPDF_Dest(name_tree.LookupNamedDest(pDoc, pDest->GetUnicodeText())); } if (CPDF_Array* pArray = pDest->AsArray()) return CPDF_Dest(pArray); -- cgit v1.2.3