Expose pdfium functionality for N-up mojo service.

Added two new functions to expose pdfium functionality to the
to-be-created N-up conversion mojo service.

ConvertPdfPagesToNupPdf will take multiple PDF pages and import them
into a N-up PDF.

ConvertPdfDocumentToNupPdf will take an entire PDF document and convert
it to a N-up PDF document.

In printing, 2-up, 3-up, or more generally N-up refers to a page
layout strategy in which multiple pages are composited onto a
single page.

Bug: 775999
Change-Id: I11edc90ee717fcb295a35e3784f4ed4e72ae8117
Reviewed-on: https://chromium-review.googlesource.com/1134484
Commit-Queue: Shirleen Lou <xlou@chromium.org>
Reviewed-by: Lei Zhang <thestig@chromium.org>
Cr-Commit-Position: refs/heads/master@{#577052}

pdf/pdf.cc

@@ -6,6 +6,8 @@
 
 #include <stdint.h>
 
+#include <utility>
+
 #if defined(OS_WIN)
 #include <windows.h>
 #endif
@@ -143,4 +145,37 @@ bool RenderPDFPageToBitmap(const void* pdf_buffer,
       pdf_buffer, pdf_buffer_size, page_number, settings, bitmap_buffer);
 }
 
+bool ConvertPdfPagesToNupPdf(
+    std::vector<base::span<const uint8_t>> input_buffers,
+    size_t pages_per_sheet,
+    size_t page_size_width,
+    size_t page_size_height,
+    void** dest_pdf_buffer,
+    size_t* dest_pdf_buffer_size) {
+  ScopedSdkInitializer scoped_sdk_initializer;
+  if (!scoped_sdk_initializer.Init())
+    return false;
+
+  PDFEngineExports* engine_exports = PDFEngineExports::Get();
+  return engine_exports->ConvertPdfPagesToNupPdf(
+      std::move(input_buffers), pages_per_sheet, page_size_width,
+      page_size_height, dest_pdf_buffer, dest_pdf_buffer_size);
+}
+
+bool ConvertPdfDocumentToNupPdf(base::span<const uint8_t> input_buffer,
+                                size_t pages_per_sheet,
+                                size_t page_size_width,
+                                size_t page_size_height,
+                                void** dest_pdf_buffer,
+                                size_t* dest_pdf_buffer_size) {
+  ScopedSdkInitializer scoped_sdk_initializer;
+  if (!scoped_sdk_initializer.Init())
+    return false;
+
+  PDFEngineExports* engine_exports = PDFEngineExports::Get();
+  return engine_exports->ConvertPdfDocumentToNupPdf(
+      input_buffer, pages_per_sheet, page_size_width, page_size_height,
+      dest_pdf_buffer, dest_pdf_buffer_size);
+}
+
 }  // namespace chrome_pdf

pdf/pdf.h

@@ -5,6 +5,9 @@
 #ifndef PDF_PDF_H_
 #define PDF_PDF_H_
 
+#include <vector>
+
+#include "base/containers/span.h"
 #include "build/build_config.h"
 
 #if defined(OS_WIN)
@@ -126,6 +129,59 @@ bool RenderPDFPageToBitmap(const void* pdf_buffer,
                            bool autorotate,
                            bool use_color);
 
+// Convert multiple PDF pages into a N-up PDF.
+// |input_buffers| is the vector of buffers with each buffer contains a PDF.
+//     If any of the PDFs contains multiple pages, only the first page of the
+//     document is used.
+// |pages_per_sheet| is the number of pages to put on one sheet.
+// |page_size_width| is the width of the output page size, measured in PDF
+//     "user space" units.
+// |page_size_height| is the height of the output page size, measured in PDF
+//     "user space" units.
+// |dest_pdf_buffer| is the output N-up PDF page.  Caller takes ownership, and
+//     needs to free the memory.
+// |dest_pdf_buffer_size| is the size of output N-up PDF page.
+//
+// |page_size_width| and |page_size_height| are the print media size.  The page
+// size of the output N-up PDF is determined by the |pages_per_sheet|, the
+// orientation of the PDF pages contained in the |input_buffers|, and the media
+// page size |page_size_width| and |page_size_height|.  For example, when
+// |page_size_width| = 512, |page_size_height| = 792, |pages_per_sheet| = 2, and
+// the orientation of |input_buffers| = portrait, the output N-up PDF will have
+// |page_size_width| = 792, and |page_size_height| = 512.
+// See printing::NupParameters for more details on how the output page
+// orientation is determined, to understand why |page_size_width| and
+// |page_size_height| may be swapped in some cases.
+bool ConvertPdfPagesToNupPdf(
+    std::vector<base::span<const uint8_t>> input_buffers,
+    size_t pages_per_sheet,
+    size_t page_size_width,
+    size_t page_size_height,
+    void** dest_pdf_buffer,
+    size_t* dest_pdf_buffer_size);
+
+// Convert a PDF document to a N-up PDF document.
+// |input_buffer| is the buffer that contains the entire PDF document to be
+//     converted to a N-up PDF document.
+// |pages_per_sheet| is the number of pages to put on one sheet.
+// |page_size_width| is the width of the media page size, measured in PDF
+//     "user space" units.
+// |page_size_height| is the height of the media page size, measured in PDF
+//     "user space" units.
+// |dest_pdf_buffer| is the output N-up PDF page.  Caller takes ownership, and
+//     needs to free the memory.
+// |dest_pdf_buffer_size| is the size of output N-up PDF document.
+//
+// Refer to the description of ConvertPdfPagesToNupPdf to understand how the
+// output page size |page_size_width| and |page_size_height| will be calculated.
+// The algorithm used to determine the output page size is the same.
+bool ConvertPdfDocumentToNupPdf(base::span<const uint8_t> input_buffer,
+                                size_t pages_per_sheet,
+                                size_t page_size_width,
+                                size_t page_size_height,
+                                void** dest_pdf_buffer,
+                                size_t* dest_pdf_buffer_size);
+
 }  // namespace chrome_pdf
 
 #endif  // PDF_PDF_H_

pdf/pdf_engine.h

@@ -18,6 +18,7 @@
 #include <string>
 #include <vector>
 
+#include "base/containers/span.h"
 #include "base/optional.h"
 #include "base/strings/string16.h"
 #include "base/time/time.h"
@@ -464,6 +465,24 @@ class PDFEngineExports {
                                      const RenderingSettings& settings,
                                      void* bitmap_buffer) = 0;
 
+  // See the definition of ConvertPdfPagesToNupPdf in pdf.cc for details.
+  virtual bool ConvertPdfPagesToNupPdf(
+      std::vector<base::span<const uint8_t>> input_buffers,
+      size_t pages_per_sheet,
+      size_t page_size_width,
+      size_t page_size_height,
+      void** dest_pdf_buffer,
+      size_t* dest_pdf_buffer_size) = 0;
+
+  // See the definition of ConvertPdfDocumentToNupPdf in pdf.cc for details.
+  virtual bool ConvertPdfDocumentToNupPdf(
+      base::span<const uint8_t> input_buffer,
+      size_t pages_per_sheet,
+      size_t page_size_width,
+      size_t page_size_height,
+      void** dest_pdf_buffer,
+      size_t* dest_pdf_buffer_size) = 0;
+
   virtual bool GetPDFDocInfo(const void* pdf_buffer,
                              int buffer_size,
                              int* page_count,

pdf/pdfium/pdfium_engine_exports.cc

@@ -8,8 +8,13 @@
 #include <utility>
 
 #include "base/no_destructor.h"
+#include "base/numerics/safe_conversions.h"
+#include "pdf/pdfium/pdfium_mem_buffer_file_write.h"
+#include "pdf/pdfium/pdfium_print.h"
+#include "printing/nup_parameters.h"
 #include "printing/units.h"
 #include "third_party/pdfium/public/cpp/fpdf_scopers.h"
+#include "third_party/pdfium/public/fpdf_ppo.h"
 #include "third_party/pdfium/public/fpdfview.h"
 
 using printing::ConvertUnitDouble;
@@ -89,6 +94,66 @@ int CalculatePosition(FPDF_PAGE page,
   return rotate;
 }
 
+ScopedFPDFDocument LoadPdfData(base::span<const uint8_t> pdf_buffer) {
+  ScopedFPDFDocument doc;
+  if (base::IsValueInRangeForNumericType<int>(pdf_buffer.size())) {
+    doc.reset(
+        FPDF_LoadMemDocument(pdf_buffer.data(), pdf_buffer.size(), nullptr));
+  }
+  return doc;
+}
+
+ScopedFPDFDocument CreatePdfDoc(
+    std::vector<base::span<const uint8_t>> input_buffers) {
+  ScopedFPDFDocument doc(FPDF_CreateNewDocument());
+
+  size_t index = 0;
+  for (auto input_buffer : input_buffers) {
+    ScopedFPDFDocument single_page_doc = LoadPdfData(input_buffer);
+    if (!FPDF_ImportPages(doc.get(), single_page_doc.get(), "1", index++)) {
+      return nullptr;
+    }
+  }
+
+  return doc;
+}
+
+bool CreateNupPdfDocument(FPDF_DOCUMENT doc,
+                          size_t pages_per_sheet,
+                          size_t page_size_width,
+                          size_t page_size_height,
+                          void** dest_pdf_buffer,
+                          size_t* dest_pdf_buffer_size) {
+  if (!dest_pdf_buffer || !dest_pdf_buffer_size)
+    return false;
+
+  printing::NupParameters nup_params;
+  bool is_landscape = PDFiumPrint::IsSourcePdfLandscape(doc);
+  nup_params.SetParameters(pages_per_sheet, is_landscape);
+  bool paper_is_landscape = page_size_width > page_size_height;
+  if (nup_params.landscape() != paper_is_landscape)
+    std::swap(page_size_width, page_size_height);
+
+  ScopedFPDFDocument output_doc_nup(FPDF_ImportNPagesToOne(
+      doc, page_size_width, page_size_height, nup_params.num_pages_on_x_axis(),
+      nup_params.num_pages_on_y_axis()));
+
+  if (!output_doc_nup)
+    return false;
+
+  // Copy data to the |dest_pdf_buffer| here.
+  // TODO(thestig): Avoid this copy.
+  PDFiumMemBufferFileWrite output_file_write;
+  if (!FPDF_SaveAsCopy(output_doc_nup.get(), &output_file_write, 0)) {
+    return false;
+  }
+  *dest_pdf_buffer = malloc(output_file_write.size());
+  memcpy(*dest_pdf_buffer, output_file_write.buffer().c_str(),
+         output_file_write.size());
+  *dest_pdf_buffer_size = output_file_write.size();
+  return true;
+}
+
 }  // namespace
 
 PDFEngineExports::RenderingSettings::RenderingSettings(int dpi_x,
@@ -245,6 +310,38 @@ bool PDFiumEngineExports::RenderPDFPageToBitmap(
   return true;
 }
 
+bool PDFiumEngineExports::ConvertPdfPagesToNupPdf(
+    std::vector<base::span<const uint8_t>> input_buffers,
+    size_t pages_per_sheet,
+    size_t page_size_width,
+    size_t page_size_height,
+    void** dest_pdf_buffer,
+    size_t* dest_pdf_buffer_size) {
+  ScopedFPDFDocument doc = CreatePdfDoc(std::move(input_buffers));
+  if (!doc)
+    return false;
+
+  return CreateNupPdfDocument(doc.get(), pages_per_sheet, page_size_width,
+                              page_size_height, dest_pdf_buffer,
+                              dest_pdf_buffer_size);
+}
+
+bool PDFiumEngineExports::ConvertPdfDocumentToNupPdf(
+    base::span<const uint8_t> input_buffer,
+    size_t pages_per_sheet,
+    size_t page_size_width,
+    size_t page_size_height,
+    void** dest_pdf_buffer,
+    size_t* dest_pdf_buffer_size) {
+  ScopedFPDFDocument doc = LoadPdfData(input_buffer);
+  if (!doc)
+    return false;
+
+  return CreateNupPdfDocument(doc.get(), pages_per_sheet, page_size_width,
+                              page_size_height, dest_pdf_buffer,
+                              dest_pdf_buffer_size);
+}
+
 bool PDFiumEngineExports::GetPDFDocInfo(const void* pdf_buffer,
                                         int buffer_size,
                                         int* page_count,

pdf/pdfium/pdfium_engine_exports.h

@@ -8,6 +8,7 @@
 #include <stddef.h>
 #include <stdint.h>
 
+#include "base/containers/span.h"
 #include "build/build_config.h"
 #include "pdf/pdf_engine.h"
 
@@ -36,6 +37,19 @@ class PDFiumEngineExports : public PDFEngineExports {
                              int page_number,
                              const RenderingSettings& settings,
                              void* bitmap_buffer) override;
+  bool ConvertPdfPagesToNupPdf(
+      std::vector<base::span<const uint8_t>> input_buffers,
+      size_t pages_per_sheet,
+      size_t page_size_width,
+      size_t page_size_height,
+      void** dest_pdf_buffer,
+      size_t* dest_pdf_buffer_size) override;
+  bool ConvertPdfDocumentToNupPdf(base::span<const uint8_t> input_buffer,
+                                  size_t pages_per_sheet,
+                                  size_t page_size_width,
+                                  size_t page_size_height,
+                                  void** dest_pdf_buffer,
+                                  size_t* dest_pdf_buffer_size) override;
   bool GetPDFDocInfo(const void* pdf_buffer,
                      int buffer_size,
                      int* page_count,

pdf/pdfium/pdfium_engine_exports_unittest.cc

@@ -98,4 +98,74 @@ TEST_F(PDFiumEngineExportsTest, GetPDFPageSizeByIndex) {
   }
 }
 
+TEST_F(PDFiumEngineExportsTest, ConvertPdfPagesToNupPdf) {
+  base::FilePath pdf_path =
+      pdf_data_dir().Append(FILE_PATH_LITERAL("rectangles.pdf"));
+  std::string pdf_data;
+  ASSERT_TRUE(base::ReadFileToString(pdf_path, &pdf_data));
+
+  std::vector<base::span<const uint8_t>> pdf_buffers;
+
+  EXPECT_FALSE(
+      ConvertPdfPagesToNupPdf(pdf_buffers, 1, 512, 792, nullptr, nullptr));
+
+  pdf_buffers.push_back(base::as_bytes(base::make_span(pdf_data)));
+  pdf_buffers.push_back(base::as_bytes(base::make_span(pdf_data)));
+
+  void* output_pdf_buffer;
+  size_t output_pdf_buffer_size;
+  ASSERT_TRUE(ConvertPdfPagesToNupPdf(
+      pdf_buffers, 2, 512, 792, &output_pdf_buffer, &output_pdf_buffer_size));
+  ASSERT_GT(output_pdf_buffer_size, 0U);
+  ASSERT_NE(output_pdf_buffer, nullptr);
+  int page_count;
+  ASSERT_TRUE(GetPDFDocInfo(output_pdf_buffer, output_pdf_buffer_size,
+                            &page_count, nullptr));
+  ASSERT_EQ(1, page_count);
+
+  double width;
+  double height;
+  ASSERT_TRUE(GetPDFPageSizeByIndex(output_pdf_buffer, output_pdf_buffer_size,
+                                    0, &width, &height));
+  EXPECT_DOUBLE_EQ(792.0, width);
+  EXPECT_DOUBLE_EQ(512.0, height);
+
+  free(output_pdf_buffer);
+}
+
+TEST_F(PDFiumEngineExportsTest, ConvertPdfDocumentToNupPdf) {
+  base::FilePath pdf_path =
+      pdf_data_dir().Append(FILE_PATH_LITERAL("rectangles_multi_pages.pdf"));
+  std::string pdf_data;
+  ASSERT_TRUE(base::ReadFileToString(pdf_path, &pdf_data));
+
+  base::span<const uint8_t> pdf_buffer;
+
+  EXPECT_FALSE(
+      ConvertPdfDocumentToNupPdf(pdf_buffer, 1, 512, 792, nullptr, nullptr));
+
+  pdf_buffer = base::as_bytes(base::make_span(pdf_data));
+
+  void* output_pdf_buffer;
+  size_t output_pdf_buffer_size;
+  ASSERT_TRUE(ConvertPdfDocumentToNupPdf(
+      pdf_buffer, 4, 512, 792, &output_pdf_buffer, &output_pdf_buffer_size));
+  ASSERT_GT(output_pdf_buffer_size, 0U);
+  ASSERT_NE(output_pdf_buffer, nullptr);
+  int page_count;
+  ASSERT_TRUE(GetPDFDocInfo(output_pdf_buffer, output_pdf_buffer_size,
+                            &page_count, nullptr));
+  ASSERT_EQ(2, page_count);
+  for (int page_number = 0; page_number < page_count; ++page_number) {
+    double width;
+    double height;
+    ASSERT_TRUE(GetPDFPageSizeByIndex(output_pdf_buffer, output_pdf_buffer_size,
+                                      page_number, &width, &height));
+    EXPECT_DOUBLE_EQ(512.0, width);
+    EXPECT_DOUBLE_EQ(792.0, height);
+  }
+
+  free(output_pdf_buffer);
+}
+
 }  // namespace chrome_pdf

pdf/pdfium/pdfium_print.cc

@@ -37,24 +37,6 @@ bool ShouldDoNup(int pages_per_sheet) {
   return pages_per_sheet > 1;
 }
 
-// Check the source doc orientation.  Returns true if the doc is landscape.
-// For now the orientation of the doc is determined by its first page's
-// orientation.  Improvement can be added in the future to better determine the
-// orientation of the source docs that have mixed orientation.
-// TODO(xlou): rotate pages if the source doc has mixed orientation.  So that
-// the orientation of all pages of the doc are uniform.  Pages of square size
-// will not be rotated.
-bool IsSourcePdfLandscape(FPDF_DOCUMENT doc) {
-  DCHECK(doc);
-
-  ScopedFPDFPage pdf_page(FPDF_LoadPage(doc, 0));
-  DCHECK(pdf_page);
-
-  bool is_source_landscape =
-      FPDF_GetPageWidth(pdf_page.get()) > FPDF_GetPageHeight(pdf_page.get());
-  return is_source_landscape;
-}
-
 // Set the destination page size and content area in points based on source
 // page rotation and orientation.
 //
@@ -235,6 +217,17 @@ std::vector<uint32_t> PDFiumPrint::GetPageNumbersFromPrintPageNumberRange(
   return page_numbers;
 }
 
+bool PDFiumPrint::IsSourcePdfLandscape(FPDF_DOCUMENT doc) {
+  DCHECK(doc);
+
+  ScopedFPDFPage pdf_page(FPDF_LoadPage(doc, 0));
+  DCHECK(pdf_page);
+
+  bool is_source_landscape =
+      FPDF_GetPageWidth(pdf_page.get()) > FPDF_GetPageHeight(pdf_page.get());
+  return is_source_landscape;
+}
+
 pp::Buffer_Dev PDFiumPrint::PrintPagesAsRasterPDF(
     const PP_PrintPageNumberRange_Dev* page_ranges,
     uint32_t page_range_count,

pdf/pdfium/pdfium_print.h

@@ -40,6 +40,15 @@ class PDFiumPrint {
       const PP_PrintSettings_Dev& print_settings,
       const PP_PdfPrintSettings_Dev& pdf_print_settings);
 
+  // Check the source doc orientation.  Returns true if the doc is landscape.
+  // For now the orientation of the doc is determined by its first page's
+  // orientation.  Improvement can be added in the future to better determine
+  // the orientation of the source docs that have mixed orientation.
+  // TODO(xlou): rotate pages if the source doc has mixed orientation.  So that
+  // the orientation of all pages of the doc are uniform.  Pages of square size
+  // will not be rotated.
+  static bool IsSourcePdfLandscape(FPDF_DOCUMENT doc);
+
  private:
   FPDF_DOCUMENT CreateSinglePageRasterPdf(
       double source_page_width,

pdf/test/data/rectangles.pdf

@@ -0,0 +1,50 @@
+%PDF-1.7
+%<25><><EFBFBD><EFBFBD>
+1 0 obj <<
+  /Type /Catalog
+  /Pages 2 0 R
+>>
+endobj
+2 0 obj <<
+  /Type /Pages
+  /MediaBox [ 0 0 200 300 ]
+  /Count 1
+  /Kids [ 3 0 R ]
+>>
+endobj
+3 0 obj <<
+  /Type /Page
+  /Parent 2 0 R
+  /Contents 4 0 R
+>>
+endobj
+4 0 obj <<
+>>
+stream
+q
+0 0 0 rg
+0 290 10 10 re B*
+10 150 50 30 re B*
+0 0 1 rg
+190 290 10 10 re B*
+70 232 50 30 re B*
+0 1 0 rg
+190 0 10 10 re B*
+130 150 50 30 re B*
+1 0 0 rg
+0 0 10 10 re B*
+70 67 50 30 re B*
+Q
+endstream
+endobj
+xref
+0 5
+0000000000 65535 f 
+0000000015 00000 n 
+0000000068 00000 n 
+0000000161 00000 n 
+0000000230 00000 n 
+trailer<< /Root 1 0 R /Size 5 >>
+startxref
+456
+%%EOF

pdf/test/data/rectangles_multi_pages.pdf

@@ -0,0 +1,122 @@
+%PDF-1.7
+%<25><><EFBFBD><EFBFBD>
+1 0 obj <<
+  /Type /Catalog
+  /Pages 2 0 R
+>>
+endobj
+2 0 obj <<
+  /Type /Pages
+  /MediaBox [ 0 0 200 250 ]
+  /Count 5
+  /Kids [ 3 0 R 5 0 R 7 0 R 9 0 R 11 0 R ]
+>>
+endobj
+3 0 obj <<
+  /Type /Page
+  /Parent 2 0 R
+  /Contents 4 0 R
+>>
+endobj
+4 0 obj <<
+  /Length 49
+>>
+stream
+q
+1 1 0 rg
+100 0 30 50 re B*
+70 67 50 30 re B*
+Q
+endstream
+endobj
+5 0 obj <<
+  /Type /Page
+  /Parent 2 0 R
+  /Rotate 90
+  /Contents 6 0 R
+>>
+endobj
+6 0 obj <<
+  /Length 49
+>>
+stream
+q
+0 1 1 rg
+100 0 30 50 re B*
+70 67 50 30 re B*
+Q
+endstream
+endobj
+7 0 obj <<
+  /Type /Page
+  /Parent 2 0 R
+  /Contents 8 0 R
+>>
+endobj
+8 0 obj <<
+  /Length 49
+>>
+stream
+q
+1 0 0 rg
+100 0 30 50 re B*
+70 67 50 30 re B*
+Q
+endstream
+endobj
+9 0 obj <<
+  /Type /Page
+  /Parent 2 0 R
+  /Contents 10 0 R
+>>
+endobj
+10 0 obj <<
+  /Length 51
+>>
+stream
+q
+0 1 0 rg
+100 0 30 50 re B*
+100 150 50 30 re B*
+Q
+endstream
+endobj
+11 0 obj <<
+  /Type /Page
+  /Parent 2 0 R
+  /Contents 12 0 R
+>>
+endobj
+12 0 obj <<
+  /Length 50
+>>
+stream
+q
+0 0 0 rg
+0 90 80 60 re B*
+100 150 50 30 re B*
+Q
+endstream
+endobj
+xref
+0 13
+0000000000 65535 f 
+0000000015 00000 n 
+0000000068 00000 n 
+0000000186 00000 n 
+0000000255 00000 n 
+0000000355 00000 n 
+0000000437 00000 n 
+0000000537 00000 n 
+0000000606 00000 n 
+0000000706 00000 n 
+0000000776 00000 n 
+0000000879 00000 n 
+0000000950 00000 n 
+trailer <<
+  /Root 1 0 R
+  /Size 13
+>>
+startxref
+1052
+%%EOF