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/fpdfapi/parser/cpdf_array.cpp | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'core/fpdfapi/parser/cpdf_array.cpp') diff --git a/core/fpdfapi/parser/cpdf_array.cpp b/core/fpdfapi/parser/cpdf_array.cpp index ea4ca7eaeb..1f2740ea9c 100644 --- a/core/fpdfapi/parser/cpdf_array.cpp +++ b/core/fpdfapi/parser/cpdf_array.cpp @@ -105,6 +105,12 @@ CFX_ByteString CPDF_Array::GetStringAt(size_t i) const { return m_Objects[i]->GetString(); } +CFX_WideString CPDF_Array::GetUnicodeTextAt(size_t i) const { + if (i >= m_Objects.size()) + return CFX_WideString(); + return m_Objects[i]->GetUnicodeText(); +} + int CPDF_Array::GetIntegerAt(size_t i) const { if (i >= m_Objects.size()) return 0; -- cgit v1.2.3