Use CFX_WideString in CPDF_NameTree functions to strip BOMchromium/3162

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 <dsinclair@chromium.org>
Commit-Queue: Jane Liu <janeliulwq@google.com>

4 files changed, 8 insertions, 9 deletions

diff --git a/fpdfsdk/cpdfsdk_formfillenvironment.cpp b/fpdfsdk/cpdfsdk_formfillenvironment.cpp
index b0ee903ead..de7947556d 100644
--- a/fpdfsdk/cpdfsdk_formfillenvironment.cpp
+++ b/fpdfsdk/cpdfsdk_formfillenvironment.cpp
@@ -603,10 +603,9 @@ void CPDFSDK_FormFillEnvironment::ProcJavascriptFun() {
   CPDF_DocJSActions docJS(pPDFDoc);
   int iCount = docJS.CountJSActions();
   for (int i = 0; i < iCount; i++) {
-    CFX_ByteString csJSName;
+    CFX_WideString csJSName;
     CPDF_Action jsAction = docJS.GetJSActionAndName(i, &csJSName);
-    GetActionHandler()->DoAction_JavaScript(
-        jsAction, CFX_WideString::FromLocal(csJSName.AsStringC()), this);
+    GetActionHandler()->DoAction_JavaScript(jsAction, csJSName, this);
   }
 }
 
diff --git a/fpdfsdk/fpdfattachment.cpp b/fpdfsdk/fpdfattachment.cpp
index 337ab35e0f..7d8cce736b 100644
--- a/fpdfsdk/fpdfattachment.cpp
+++ b/fpdfsdk/fpdfattachment.cpp
@@ -30,7 +30,7 @@ DLLEXPORT FPDF_ATTACHMENT STDCALL FPDFDoc_GetAttachment(FPDF_DOCUMENT document,
   if (static_cast<size_t>(index) >= nameTree.GetCount())
     return nullptr;
 
-  CFX_ByteString csName;
+  CFX_WideString csName;
   return nameTree.LookupValueAndName(index, &csName);
 }
 
diff --git a/fpdfsdk/fpdfview.cpp b/fpdfsdk/fpdfview.cpp
index 06e72b3a71..7dbaf7f9e7 100644
--- a/fpdfsdk/fpdfview.cpp
+++ b/fpdfsdk/fpdfview.cpp
@@ -1322,7 +1322,7 @@ DLLEXPORT FPDF_DEST STDCALL FPDF_GetNamedDestByName(FPDF_DOCUMENT document,
     return nullptr;
 
   CPDF_NameTree name_tree(pDoc, "Dests");
-  return name_tree.LookupNamedDest(pDoc, name);
+  return name_tree.LookupNamedDest(pDoc, PDF_DecodeText(CFX_ByteString(name)));
 }
 
 #ifdef PDF_ENABLE_XFA
@@ -1398,6 +1398,7 @@ DLLEXPORT FPDF_DEST STDCALL FPDF_GetNamedDest(FPDF_DOCUMENT document,
 
   CPDF_Object* pDestObj = nullptr;
   CFX_ByteString bsName;
+  CFX_WideString wsName;
   CPDF_NameTree nameTree(pDoc, "Dests");
   int count = nameTree.GetCount();
   if (index >= count) {
@@ -1421,8 +1422,9 @@ DLLEXPORT FPDF_DEST STDCALL FPDF_GetNamedDest(FPDF_DOCUMENT document,
         break;
       i++;
     }
+    wsName = PDF_DecodeText(bsName);
   } else {
-    pDestObj = nameTree.LookupValueAndName(index, &bsName);
+    pDestObj = nameTree.LookupValueAndName(index, &wsName);
   }
   if (!pDestObj)
     return nullptr;
@@ -1434,7 +1436,6 @@ DLLEXPORT FPDF_DEST STDCALL FPDF_GetNamedDest(FPDF_DOCUMENT document,
   if (!pDestObj->IsArray())
     return nullptr;
 
-  CFX_WideString wsName = PDF_DecodeText(bsName);
   CFX_ByteString utf16Name = wsName.UTF16LE_Encode();
   int len = utf16Name.GetLength();
   if (!buffer) {
diff --git a/fpdfsdk/javascript/Document.cpp b/fpdfsdk/javascript/Document.cpp
index d5b075da62..ba4b2ae622 100644
--- a/fpdfsdk/javascript/Document.cpp
+++ b/fpdfsdk/javascript/Document.cpp
@@ -1594,13 +1594,12 @@ bool Document::gotoNamedDest(CJS_Runtime* pRuntime,
     return false;
   }
   CFX_WideString wideName = params[0].ToCFXWideString(pRuntime);
-  CFX_ByteString utf8Name = wideName.UTF8Encode();
   CPDF_Document* pDocument = m_pFormFillEnv->GetPDFDocument();
   if (!pDocument)
     return false;
 
   CPDF_NameTree nameTree(pDocument, "Dests");
-  CPDF_Array* destArray = nameTree.LookupNamedDest(pDocument, utf8Name);
+  CPDF_Array* destArray = nameTree.LookupNamedDest(pDocument, wideName);
   if (!destArray)
     return false;