Merge to XFA: Add test for StringToCode and StringToWideString

This CL adds a test case for the StringToCode and
StringToWideString methods in fpdf_font.cpp. In order
to do so, it moves the methods to be private methods of CPDF_ToUnicodeMap and
make the tests friends of the class.

TBR=tsepez@chromium.org

Review URL: https://codereview.chromium.org/1428593005 .

(cherry picked from commit 52b0b525dca3d982a04b77fa6d0913aff1e5fd9c)

Review URL: https://codereview.chromium.org/1425233004 .

5 files changed, 57 insertions, 11 deletions

diff --git a/BUILD.gn b/BUILD.gn
index dcc55bcf65..199d115d9e 100644
--- a/BUILD.gn
+++ b/BUILD.gn
@@ -1473,6 +1473,7 @@ static_library("xfa") {
 
 test("pdfium_unittests") {
   sources = [
+    "core/src/fpdfapi/fpdf_font/fpdf_font_unittest.cpp",
     "core/src/fxcodec/codec/fx_codec_jpx_unittest.cpp",
     "core/src/fxcrt/fx_basic_bstring_unittest.cpp",
     "core/src/fxcrt/fx_basic_memmgr_unittest.cpp",
diff --git a/core/src/fpdfapi/fpdf_font/font_int.h b/core/src/fpdfapi/fpdf_font/font_int.h
index 48e58d6345..559027b283 100644
--- a/core/src/fpdfapi/fpdf_font/font_int.h
+++ b/core/src/fpdfapi/fpdf_font/font_int.h
@@ -174,6 +174,13 @@ class CPDF_ToUnicodeMap {
   std::map<FX_DWORD, FX_DWORD> m_Map;
   CPDF_CID2UnicodeMap* m_pBaseMap;
   CFX_WideTextBuf m_MultiCharBuf;
+
+ private:
+  friend class fpdf_font_StringToCode_Test;
+  friend class fpdf_font_StringToWideString_Test;
+
+  static FX_DWORD StringToCode(const CFX_ByteStringC& str);
+  static CFX_WideString StringToWideString(const CFX_ByteStringC& str);
 };
 class CPDF_FontCharMap : public CFX_CharMap {
  public:
diff --git a/core/src/fpdfapi/fpdf_font/fpdf_font.cpp b/core/src/fpdfapi/fpdf_font/fpdf_font.cpp
index 543816b03a..0529d3d35b 100644
--- a/core/src/fpdfapi/fpdf_font/fpdf_font.cpp
+++ b/core/src/fpdfapi/fpdf_font/fpdf_font.cpp
@@ -508,7 +508,9 @@ FX_DWORD CPDF_ToUnicodeMap::ReverseLookup(FX_WCHAR unicode) {
   }
   return 0;
 }
-static FX_DWORD _StringToCode(const CFX_ByteStringC& str) {
+
+// Static.
+FX_DWORD CPDF_ToUnicodeMap::StringToCode(const CFX_ByteStringC& str) {
   const FX_CHAR* buf = str.GetCStr();
   int len = str.GetLength();
   if (len == 0) {
@@ -539,7 +541,7 @@ static FX_DWORD _StringToCode(const CFX_ByteStringC& str) {
   }
   return result;
 }
-static CFX_WideString _StringDataAdd(CFX_WideString str) {
+static CFX_WideString StringDataAdd(CFX_WideString str) {
   CFX_WideString ret;
   int len = str.GetLength();
   FX_WCHAR value = 1;
@@ -557,7 +559,10 @@ static CFX_WideString _StringDataAdd(CFX_WideString str) {
   }
   return ret;
 }
-static CFX_WideString _StringToWideString(const CFX_ByteStringC& str) {
+
+// Static.
+CFX_WideString CPDF_ToUnicodeMap::StringToWideString(
+    const CFX_ByteStringC& str) {
   const FX_CHAR* buf = str.GetCStr();
   int len = str.GetLength();
   if (len == 0) {
@@ -579,6 +584,7 @@ static CFX_WideString _StringToWideString(const CFX_ByteStringC& str) {
         break;
       }
       ch = ch * 16 + digit;
+
       byte_pos++;
       if (byte_pos == 4) {
         result += ch;
@@ -608,9 +614,9 @@ void CPDF_ToUnicodeMap::Load(CPDF_Stream* pStream) {
         if (word.IsEmpty() || word == FX_BSTRC("endbfchar")) {
           break;
         }
-        FX_DWORD srccode = _StringToCode(word);
+        FX_DWORD srccode = StringToCode(word);
         word = parser.GetWord();
-        CFX_WideString destcode = _StringToWideString(word);
+        CFX_WideString destcode = StringToWideString(word);
         int len = destcode.GetLength();
         if (len == 0) {
           continue;
@@ -631,9 +637,9 @@ void CPDF_ToUnicodeMap::Load(CPDF_Stream* pStream) {
           break;
         }
         high = parser.GetWord();
-        FX_DWORD lowcode = _StringToCode(low);
+        FX_DWORD lowcode = StringToCode(low);
         FX_DWORD highcode =
-            (lowcode & 0xffffff00) | (_StringToCode(high) & 0xff);
+            (lowcode & 0xffffff00) | (StringToCode(high) & 0xff);
         if (highcode == (FX_DWORD)-1) {
           break;
         }
@@ -641,7 +647,7 @@ void CPDF_ToUnicodeMap::Load(CPDF_Stream* pStream) {
         if (start == FX_BSTRC("[")) {
           for (FX_DWORD code = lowcode; code <= highcode; code++) {
             CFX_ByteString dest = parser.GetWord();
-            CFX_WideString destcode = _StringToWideString(dest);
+            CFX_WideString destcode = StringToWideString(dest);
             int len = destcode.GetLength();
             if (len == 0) {
               continue;
@@ -656,11 +662,11 @@ void CPDF_ToUnicodeMap::Load(CPDF_Stream* pStream) {
           }
           parser.GetWord();
         } else {
-          CFX_WideString destcode = _StringToWideString(start);
+          CFX_WideString destcode = StringToWideString(start);
           int len = destcode.GetLength();
           FX_DWORD value = 0;
           if (len == 1) {
-            value = _StringToCode(start);
+            value = StringToCode(start);
             for (FX_DWORD code = lowcode; code <= highcode; code++) {
               m_Map[code] = value++;
             }
@@ -670,7 +676,7 @@ void CPDF_ToUnicodeMap::Load(CPDF_Stream* pStream) {
               if (code == lowcode) {
                 retcode = destcode;
               } else {
-                retcode = _StringDataAdd(destcode);
+                retcode = StringDataAdd(destcode);
               }
               m_Map[code] = m_MultiCharBuf.GetLength() * 0x10000 + 0xffff;
               m_MultiCharBuf.AppendChar(retcode.GetLength());
diff --git a/core/src/fpdfapi/fpdf_font/fpdf_font_unittest.cpp b/core/src/fpdfapi/fpdf_font/fpdf_font_unittest.cpp
new file mode 100644
index 0000000000..9cc529c3df
--- /dev/null
+++ b/core/src/fpdfapi/fpdf_font/fpdf_font_unittest.cpp
@@ -0,0 +1,31 @@
+// Copyright 2015 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 "testing/gtest/include/gtest/gtest.h"
+
+#include "font_int.h"
+
+TEST(fpdf_font, StringToCode) {
+  EXPECT_EQ(0, CPDF_ToUnicodeMap::StringToCode(""));
+  EXPECT_EQ(194, CPDF_ToUnicodeMap::StringToCode("<c2"));
+  EXPECT_EQ(162, CPDF_ToUnicodeMap::StringToCode("<A2"));
+  EXPECT_EQ(2802, CPDF_ToUnicodeMap::StringToCode("<Af2"));
+  EXPECT_EQ(12, CPDF_ToUnicodeMap::StringToCode("12"));
+  EXPECT_EQ(128, CPDF_ToUnicodeMap::StringToCode("128"));
+}
+
+TEST(fpdf_font, StringToWideString) {
+  EXPECT_EQ(L"", CPDF_ToUnicodeMap::StringToWideString(""));
+  EXPECT_EQ(L"", CPDF_ToUnicodeMap::StringToWideString("1234"));
+
+  EXPECT_EQ(L"", CPDF_ToUnicodeMap::StringToWideString("<c2"));
+
+  CFX_WideString res = L"\xc2ab";
+  EXPECT_EQ(res, CPDF_ToUnicodeMap::StringToWideString("<c2ab"));
+  EXPECT_EQ(res, CPDF_ToUnicodeMap::StringToWideString("<c2abab"));
+  EXPECT_EQ(res, CPDF_ToUnicodeMap::StringToWideString("<c2ab 1234"));
+
+  res += L"\xfaab";
+  EXPECT_EQ(res, CPDF_ToUnicodeMap::StringToWideString("<c2abFaAb"));
+}
diff --git a/pdfium.gyp b/pdfium.gyp
index 48ed36de42..44a7611740 100644
--- a/pdfium.gyp
+++ b/pdfium.gyp
@@ -748,6 +748,7 @@
         '<(DEPTH)'
       ],
       'sources': [
+        'core/src/fpdfapi/fpdf_font/fpdf_font_unittest.cpp',
         'core/src/fxcodec/codec/fx_codec_jpx_unittest.cpp',
         'core/src/fxcrt/fx_basic_bstring_unittest.cpp',
         'core/src/fxcrt/fx_basic_memmgr_unittest.cpp',