Fix CData parsing in CFDE_XMLSyntaxParser.

xfa/fde/xml/fde_xml_imp_unittest.cpp

Index: xfa/fde/xml/fde_xml_imp_unittest.cpp
diff --git a/xfa/fde/xml/fde_xml_imp_unittest.cpp b/xfa/fde/xml/fde_xml_imp_unittest.cpp
new file mode 100644
index 0000000000000000000000000000000000000000..75dc4dd4bf7476bd45ea818d1196bb43d2c7b3a4
--- /dev/null
+++ b/xfa/fde/xml/fde_xml_imp_unittest.cpp
@@ -0,0 +1,64 @@
+// Copyright 2016 PDFium Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file.
+
+#include "xfa/fde/xml/fde_xml_imp.h"
+
+#include "xfa/fgas/crt/fgas_stream.h"
+#include "testing/gtest/include/gtest/gtest.h"
+
+TEST(CFDE_XMLSyntaxParser, CData) {
+  const FX_WCHAR* input =
+      L"<script contentType=\"application/x-javascript\">\n"
+      "  <![CDATA[\n"

[Tom Sepez, 2016/03/30 16:55:30]

I'd like to see some variations on this as in
<!>
<![>
<![CDATA>
<![CDATA[]>
etc.

[dsinclair, 2016/03/30 17:32:13]

Added a bunch of tests. Any more? (And a bunch of todo's where the result seemed
weird.)

+      "    if (a[1] < 3)\n"
+      "      app.alert(\"Tclams\");\n"

[Tom Sepez, 2016/03/30 16:55:30]

Since were'e in cdata, we should test having an embedded </script> tag in the
section which should be ignored.

[dsinclair, 2016/03/30 17:32:13]

Done.

+      "  ]]>\n"
+      "</script>";
+
+  const FX_WCHAR* cdata =
+      L"\n"
+      "    if (a[1] < 3)\n"
+      "      app.alert(\"Tclams\");\n"
+      "  ";
+
+  // We *2 because we pass in the uint8_t, not the FX_WCHAR.
+  size_t len = FXSYS_wcslen(input) * 2;

[Tom Sepez, 2016/03/30 16:55:30]

Needs to be sizeof(FX_WCHAR) (2 vs. 4 depending on platform).

[dsinclair, 2016/03/30 17:32:13]

Done.

+  std::unique_ptr<IFX_Stream> stream = std::unique_ptr<IFX_Stream>(

[Tom Sepez, 2016/03/30 16:55:30]

Just std::unique_ptr<IFX_Stream> stream(FX_Stream::CreateStream((uint8_t*)input,
len, 0));
also reinterpret_cast<uint8_t*>

[dsinclair, 2016/03/30 17:32:13]

Done.

+      IFX_Stream::CreateStream((uint8_t*)input, len, 0));
+  CFDE_XMLSyntaxParser parser;
+  parser.Init(stream.get(), 256);

[Tom Sepez, 2016/03/30 16:55:30]

why 256?

[dsinclair, 2016/03/30 17:32:13]

No particular reason. Has to be > 0, and at 256 it's longer then my string
length so I think the parser should consume it in one go.

+
+  CFX_WideString data;
+
+  EXPECT_EQ(FDE_XMLSYNTAXSTATUS_ElementOpen, parser.DoSyntaxParse());
+  EXPECT_EQ(FDE_XMLSYNTAXSTATUS_TagName, parser.DoSyntaxParse());
+  parser.GetTagName(data);
+  EXPECT_EQ(L"script", data);
+
+  EXPECT_EQ(FDE_XMLSYNTAXSTATUS_AttriName, parser.DoSyntaxParse());
+  parser.GetAttributeName(data);
+  EXPECT_EQ(L"contentType", data);
+  EXPECT_EQ(FDE_XMLSYNTAXSTATUS_AttriValue, parser.DoSyntaxParse());
+  parser.GetAttributeValue(data);
+  EXPECT_EQ(L"application/x-javascript", data);
+
+  EXPECT_EQ(FDE_XMLSYNTAXSTATUS_ElementBreak, parser.DoSyntaxParse());
+  EXPECT_EQ(FDE_XMLSYNTAXSTATUS_Text, parser.DoSyntaxParse());
+  parser.GetTextData(data);
+  EXPECT_EQ(L"\n  ", data);
+
+  EXPECT_EQ(FDE_XMLSYNTAXSTATUS_CData, parser.DoSyntaxParse());
+  parser.GetTextData(data);
+  EXPECT_EQ(cdata, data);
+
+  EXPECT_EQ(FDE_XMLSYNTAXSTATUS_Text, parser.DoSyntaxParse());
+  parser.GetTextData(data);
+  EXPECT_EQ(L"\n", data);
+
+  EXPECT_EQ(FDE_XMLSYNTAXSTATUS_ElementClose, parser.DoSyntaxParse());
+  parser.GetTagName(data);
+  EXPECT_EQ(L"script", data);
+
+  EXPECT_EQ(FDE_XMLSYNTAXSTATUS_EOS, parser.DoSyntaxParse());
+}