Example: fast split into single pages

This is faster than using qpdf --pages to do it.

Example: fast split into single pages
This is faster than using qpdf --pages to do it.
Jay Berkenbilt
1 parent 9f8aba1d
Showing 7 changed files with 195 additions and 1 deletions
ChangeLog
examples/build.mk
examples/pdf-split-pages.cc
examples/qtest/pdf-split-pages.test
examples/qtest/pdf-split-pages/exp1.pdf
examples/qtest/pdf-split-pages/exp2.pdf
examples/qtest/pdf-split-pages/in.pdf
 2014-06-07  Jay Berkenbilt  <ejb@ql.org>
+	* New example program: pdf-split-pages: efficiently split PDF
+	files into individual pages.
+
 	* Bug fix: don't fail on files that contain streams where /Filter
 	or /DecodeParms references a stream. Before, qpdf would try to
 	convert these to direct objects, which would fail because of the
@@ -5,7 +5,8 @@ BINS_examples = \
 	pdf-double-page-size \
 	pdf-invert-images \
 	pdf-create \
-	pdf-parse-content
+	pdf-parse-content \
+	pdf-split-pages
 CBINS_examples = pdf-linearize
 TARGETS_examples = $(foreach B,$(BINS_examples) $(CBINS_examples),examples/$(OUTPUT_DIR)/$(call binname,$(B)))
+//
+// This is a stand-alone example of splitting a PDF into individual
+// pages. It is much faster than using the qpdf command-line tool to
+// split into separate files per page.
+//
+
+#include <qpdf/QPDF.hh>
+#include <qpdf/QPDFWriter.hh>
+#include <qpdf/QUtil.hh>
+#include <string>
+#include <iostream>
+#include <cstdlib>
+
+static bool static_id = false;
+
+static void process(char const* whoami,
+                    char const* infile,
+                    std::string outprefix)
+{
+    QPDF inpdf;
+    inpdf.processFile(infile);
+    std::vector<QPDFObjectHandle> const& pages = inpdf.getAllPages();
+    int pageno_len = QUtil::int_to_string(pages.size()).length();
+    int pageno = 0;
+    for (std::vector<QPDFObjectHandle>::const_iterator iter = pages.begin();
+         iter != pages.end(); ++iter)
+    {
+        QPDFObjectHandle page = *iter;
+        std::string outfile =
+            outprefix + QUtil::int_to_string(++pageno, pageno_len) + ".pdf";
+        QPDF outpdf;
+        outpdf.emptyPDF();
+        outpdf.addPage(page, false);
+        QPDFWriter outpdfw(outpdf, outfile.c_str());
+	if (static_id)
+	{
+	    // For the test suite, uncompress streams and use static
+	    // IDs.
+	    outpdfw.setStaticID(true);
+	    outpdfw.setStreamDataMode(qpdf_s_uncompress);
+	}
+        outpdfw.write();
+    }
+}
+
+int main(int argc, char* argv[])
+{
+    char* whoami = QUtil::getWhoami(argv[0]);
+
+    // For libtool's sake....
+    if (strncmp(whoami, "lt-", 3) == 0)
+    {
+	whoami += 3;
+    }
+    // For test suite
+    if ((argc > 1) && (strcmp(argv[1], " --static-id") == 0))
+    {
+        static_id = true;
+        --argc;
+        ++argv;
+    }
+
+    if (argc != 3)
+    {
+        std::cerr << "Usage: " << whoami << " infile outprefix" << std::endl;
+    }
+    try
+    {
+        process(whoami, argv[1], argv[2]);
+    }
+    catch (std::exception e)
+    {
+        std::cerr << whoami << ": exception: " << e.what() << std::endl;
+        return 2;
+    }
+    return 0;
+}
+#!/usr/bin/env perl
+require 5.008;
+use warnings;
+use strict;
+
+chdir("pdf-split-pages");
+
+require TestDriver;
+
+my $td = new TestDriver('pdf-split-pages');
+
+cleanup();
+
+$td->runtest("split",
+	     {$td->COMMAND => "pdf-split-pages ' --static-id' in.pdf out"},
+	     {$td->STRING => "", $td->EXIT_STATUS => 0});
+
+$td->runtest("check page 1",
+	     {$td->FILE => "out1.pdf"},
+	     {$td->FILE => "exp1.pdf"});
+
+$td->runtest("check page 2",
+	     {$td->FILE => "out2.pdf"},
+	     {$td->FILE => "exp2.pdf"});
+
+cleanup();
+
+$td->report(3);
+
+sub cleanup
+{
+    unlink (<out?.pdf>);
+}
+%PDF-1.3
+%¿÷¢þ
+1 0 obj
+<< /Pages 2 0 R /Type /Catalog >>
+endobj
+2 0 obj
+<< /Count 1 /Kids [ 3 0 R ] /Type /Pages >>
+endobj
+3 0 obj
+<< /Contents 4 0 R /MediaBox [ 0 0 612 792 ] /Parent 2 0 R /Resources << /Font << /F1 5 0 R >> /ProcSet 6 0 R >> /Type /Page >>
+endobj
+4 0 obj
+<< /Length 44 >>
+stream
+BT
+  /F1 24 Tf
+  72 720 Td
+  (Page 1) Tj
+ET
+endstream
+endobj
+5 0 obj
+<< /BaseFont /Helvetica /Encoding /WinAnsiEncoding /Name /F1 /Subtype /Type1 /Type /Font >>
+endobj
+6 0 obj
+[ /PDF /Text ]
+endobj
+xref
+0 7
+0000000000 65535 f 
+0000000015 00000 n 
+0000000064 00000 n 
+0000000123 00000 n 
+0000000266 00000 n 
+0000000359 00000 n 
+0000000466 00000 n 
+trailer << /Root 1 0 R /Size 7 /ID [<31415926535897932384626433832795><31415926535897932384626433832795>] >>
+startxref
+496
+%%EOF
+%PDF-1.3
+%¿÷¢þ
+1 0 obj
+<< /Pages 2 0 R /Type /Catalog >>
+endobj
+2 0 obj
+<< /Count 1 /Kids [ 3 0 R ] /Type /Pages >>
+endobj
+3 0 obj
+<< /Contents 4 0 R /MediaBox [ 0 0 612 792 ] /Parent 2 0 R /Resources << /Font << /F1 5 0 R >> /ProcSet 6 0 R >> /Type /Page >>
+endobj
+4 0 obj
+<< /Length 44 >>
+stream
+BT
+  /F1 24 Tf
+  72 720 Td
+  (Page 2) Tj
+ET
+endstream
+endobj
+5 0 obj
+<< /BaseFont /Helvetica /Encoding /WinAnsiEncoding /Name /F1 /Subtype /Type1 /Type /Font >>
+endobj
+6 0 obj
+[ /PDF /Text ]
+endobj
+xref
+0 7
+0000000000 65535 f 
+0000000015 00000 n 
+0000000064 00000 n 
+0000000123 00000 n 
+0000000266 00000 n 
+0000000359 00000 n 
+0000000466 00000 n 
+trailer << /Root 1 0 R /Size 7 /ID [<31415926535897932384626433832795><31415926535897932384626433832795>] >>
+startxref
+496
+%%EOF