Allow zero length streams when parsing.chromium/3130

It's possible to create a stream of length 0 in a PDF document.
Currently the code will early exit and return a nullptr. This causes
issues when you want to print the given PDF as the FPDF_ImportPages code
ends up only generating up to the zero length object.

This CL allows creating streams with length 0 and updates the PDF saving
code to output a blank stream.

Bug: chromium:732380
Change-Id: I44182ba4aaac7c51284b002ba01bbc34b6bcf9e0
Reviewed-on: https://pdfium-review.googlesource.com/6490
Reviewed-by: Lei Zhang <thestig@chromium.org>
Commit-Queue: dsinclair <dsinclair@chromium.org>

4 files changed, 153 insertions, 4 deletions

diff --git a/testing/embedder_test.cpp b/testing/embedder_test.cpp
index bf00c11607..6cea598400 100644
--- a/testing/embedder_test.cpp
+++ b/testing/embedder_test.cpp
@@ -326,6 +326,15 @@ FPDF_PAGE EmbedderTest::GetPageTrampoline(FPDF_FORMFILLINFO* info,
                                                               page_index);
 }
 
+std::string EmbedderTest::HashBitmap(FPDF_BITMAP bitmap,
+                                     int expected_width,
+                                     int expected_height) {
+  uint8_t digest[16];
+  CRYPT_MD5Generate(static_cast<uint8_t*>(FPDFBitmap_GetBuffer(bitmap)),
+                    expected_width * 4 * expected_height, digest);
+  return CryptToBase16(digest);
+}
+
 // static
 void EmbedderTest::CompareBitmap(FPDF_BITMAP bitmap,
                                  int expected_width,
@@ -339,10 +348,8 @@ void EmbedderTest::CompareBitmap(FPDF_BITMAP bitmap,
   if (!expected_md5sum)
     return;
 
-  uint8_t digest[16];
-  CRYPT_MD5Generate(static_cast<uint8_t*>(FPDFBitmap_GetBuffer(bitmap)),
-                    expected_stride * expected_height, digest);
-  EXPECT_EQ(expected_md5sum, CryptToBase16(digest));
+  EXPECT_EQ(expected_md5sum,
+            HashBitmap(bitmap, expected_width, expected_height));
 }
 
 // Can't use gtest-provided main since we need to stash the path to the
diff --git a/testing/embedder_test.h b/testing/embedder_test.h
index 619fc5d699..2bb796d905 100644
--- a/testing/embedder_test.h
+++ b/testing/embedder_test.h
@@ -108,6 +108,11 @@ class EmbedderTest : public ::testing::Test,
  protected:
   void SetupFormFillEnvironment();
 
+  // Return the hash of |bitmap|.
+  static std::string HashBitmap(FPDF_BITMAP bitmap,
+                                int expected_width,
+                                int expected_height);
+
   // Check |bitmap| to make sure it has the right dimensions and content.
   static void CompareBitmap(FPDF_BITMAP bitmap,
                             int expected_width,
diff --git a/testing/resources/zero_length_stream.in b/testing/resources/zero_length_stream.in
new file mode 100644
index 0000000000..5b258d4d74
--- /dev/null
+++ b/testing/resources/zero_length_stream.in
@@ -0,0 +1,63 @@
+{{header}}
+{{object 1 0}} <<
+  /Type /Catalog
+  /Pages 2 0 R
+>>
+{{object 2 0}} <<
+  /Type /Pages
+  /MediaBox [ 0 0 200 200 ]
+  /Count 1
+  /Kids [ 3 0 R ]
+>>
+endobj
+{{object 3 0}} <<
+  /Type /Page
+  /Parent 2 0 R
+  /Resources <<
+    /Font <<
+      /F1 4 0 R
+      /F2 5 0 R
+    >>
+  >>
+  /Contents [6 0 R 7 0 R]
+>>
+endobj
+{{object 4 0}} <<
+  /Type /Font
+  /Subtype /Type1
+  /BaseFont /Times-Roman
+>>
+endobj
+{{object 5 0}} <<
+  /Type /Font
+  /Subtype /Type1
+  /BaseFont /Helvetica
+>>
+endobj
+{{object 6 0}} <<
+  /Filter /FlateDecode
+  /Length 0
+>>
+stream
+endstream
+endobj
+{{object 7 0}} <<
+>>
+stream
+BT
+20 50 Td
+/F1 12 Tf
+(Hello, world!) Tj
+0 50 Td
+/F2 16 Tf
+(Goodbye, world!) Tj
+ET
+endstream
+endobj
+{{xref}}
+trailer <<
+  /Size 6
+  /Root 1 0 R
+>>
+{{startxref}}
+%%EOF
diff --git a/testing/resources/zero_length_stream.pdf b/testing/resources/zero_length_stream.pdf
new file mode 100644
index 0000000000..90fae5be7f
--- /dev/null
+++ b/testing/resources/zero_length_stream.pdf
@@ -0,0 +1,74 @@
+%PDF-1.7
+% ò¤ô
+1 0 obj <<
+  /Type /Catalog
+  /Pages 2 0 R
+>>
+2 0 obj <<
+  /Type /Pages
+  /MediaBox [ 0 0 200 200 ]
+  /Count 1
+  /Kids [ 3 0 R ]
+>>
+endobj
+3 0 obj <<
+  /Type /Page
+  /Parent 2 0 R
+  /Resources <<
+    /Font <<
+      /F1 4 0 R
+      /F2 5 0 R
+    >>
+  >>
+  /Contents [6 0 R 7 0 R]
+>>
+endobj
+4 0 obj <<
+  /Type /Font
+  /Subtype /Type1
+  /BaseFont /Times-Roman
+>>
+endobj
+5 0 obj <<
+  /Type /Font
+  /Subtype /Type1
+  /BaseFont /Helvetica
+>>
+endobj
+6 0 obj <<
+  /Filter /FlateDecode
+  /Length 0
+>>
+stream
+endstream
+endobj
+7 0 obj <<
+>>
+stream
+BT
+20 50 Td
+/F1 12 Tf
+(Hello, world!) Tj
+0 50 Td
+/F2 16 Tf
+(Goodbye, world!) Tj
+ET
+endstream
+endobj
+xref
+0 8
+0000000000 65535 f 
+0000000015 00000 n 
+0000000061 00000 n 
+0000000154 00000 n 
+0000000304 00000 n 
+0000000382 00000 n 
+0000000458 00000 n 
+0000000531 00000 n 
+trailer <<
+  /Size 6
+  /Root 1 0 R
+>>
+startxref
+652
+%%EOF