Use ToUnicode mapping even when unicode is 0.

CPDF_Font::UnicodeFromCharcode returns 0 only if ToUnicode map maps the
charcode to 0. CPDF_SimpleFont::UnicodeFromCharcode and CPDF_CID_Font::
UnicodeFromCharCode return 0 only if the call to CPDF_Font returns 0.
In other cases, these methods return an empty string. So when
processing text, a 0 return from the method should not be replaced
with the charcode.

BUG=pdfium:583

Review-Url: https://codereview.chromium.org/2342073002

1 files changed, 15 insertions, 0 deletions

diff --git a/fpdfsdk/fpdftext_embeddertest.cpp b/fpdfsdk/fpdftext_embeddertest.cpp
index 3070c30771..957e813f64 100644
--- a/fpdfsdk/fpdftext_embeddertest.cpp
+++ b/fpdfsdk/fpdftext_embeddertest.cpp
@@ -388,3 +388,18 @@ TEST_F(FPDFTextEmbeddertest, GetFontSize) {
   FPDFText_ClosePage(textpage);
   UnloadPage(page);
 }
+
+TEST_F(FPDFTextEmbeddertest, ToUnicode) {
+  EXPECT_TRUE(OpenDocument("bug_583.pdf"));
+  FPDF_PAGE page = LoadPage(0);
+  EXPECT_TRUE(page);
+
+  FPDF_TEXTPAGE textpage = FPDFText_LoadPage(page);
+  EXPECT_TRUE(textpage);
+
+  ASSERT_EQ(1, FPDFText_CountChars(textpage));
+  EXPECT_EQ(static_cast<unsigned int>(0), FPDFText_GetUnicode(textpage, 0));
+
+  FPDFText_ClosePage(textpage);
+  UnloadPage(page);
+}