invert images example

git-svn-id: svn+q:///qpdf/trunk@1001 71b93d88-0707-0410-a8cf-f5a4172ac649

invert images example
git-svn-id: svn+q:///qpdf/trunk@1001 71b93d88-0707-0410-a8cf-f5a4172ac649
Jay Berkenbilt
1 parent b6c7a809
Showing 7 changed files with 215 additions and 13 deletions
ChangeLog
TODO
examples/build.mk
examples/pdf-invert-images.cc
examples/qtest/invert-images.test
examples/qtest/invert-images/in.pdf
examples/qtest/invert-images/out.pdf
@@ -2,13 +2,13 @@
  
 	* Add QPDFObjectHandle::addPageContents, a convenience routine for
 	appending or prepending new streams to a page's content streams.
-	The "double-page-size" example illustrates its use.
+	The "pdf-double-page-size" example illustrates its use.
  
 	* Add new methods to QPDFObjectHandle: replaceStreamData and
 	newStream.  These methods allow users of the qpdf library to add
 	new streams and to replace data of existing streams.  The
-	"double-page-size" and "tweak-images" examples illustrate their
-	use.
+	"pdf-double-page-size" and "pdf-invert-images" examples illustrate
+	their use.
  
 2010-06-06  Jay Berkenbilt  <ejb@ql.org>
  
@@ -5,20 +5,13 @@ Next
  
  * Find messages exchanged with Stefan Heinsen <stefan.heinsen@gmx.de>
    in August, 2009.  He seems to like to send encrypted mail (key
-   01FCC336).  Tell him about newStream and replaceStreamData.
+   01FCC336).  Tell him about newStream, replaceStreamData, and the
+   invert-images example.
  
  * Tell stronghorse@tom.com about QPDFObjectHandle::addPageContents
    and double-page-size example.  See message from stronghorse@tom.com
    ("Suggestion for qpdf") from 2010-06-09 and my response.
  
-2.2
-===
-
- * Create an example (tweak-images) that does some kind of
-   manipulation on every image.  Use QPDF::getAllPages and
-   QPDFObjectHandle::getPageImages along with new stream data and
-   dictionary manipulation.
-
  
 General
 =======
-BINS_examples = pdf-bookmarks pdf-mod-info pdf-npages double-page-size
+BINS_examples = \
+	pdf-bookmarks \
+	pdf-mod-info \
+	pdf-npages \
+	pdf-double-page-size \
+	pdf-invert-images
 CBINS_examples = pdf-linearize
  
 TARGETS_examples = $(foreach B,$(BINS_examples) $(CBINS_examples),examples/$(OUTPUT_DIR)/$(call binname,$(B)))
+#include <iostream>
+#include <string.h>
+#include <stdlib.h>
+#include <qpdf/QPDF.hh>
+#include <qpdf/QUtil.hh>
+#include <qpdf/Buffer.hh>
+#include <qpdf/QPDFWriter.hh>
+
+static char const* whoami = 0;
+
+void usage()
+{
+    std::cerr << "Usage: " << whoami << " infile.pdf outfile.pdf [in-password]"
+	      << std::endl
+	      << "Invert some images in infile.pdf;"
+	      << " write output to outfile.pdf" << std::endl;
+    exit(2);
+}
+
+// Derive a class from StreamDataProvider to provide updated stream
+// data.  The main purpose of using this object is to avoid having to
+// allocate memory up front for the objects.  A real application might
+// use temporary files in order to avoid having to allocate all the
+// memory.  Here, we're not going to worry about that since the goal
+// is really to show how to use this facility rather than to show the
+// best possible way to write an image inverter.  This class still
+// illustrates dynamic creation of the new stream data.
+class ImageInverter: public QPDFObjectHandle::StreamDataProvider
+{
+  public:
+    virtual ~ImageInverter()
+    {
+    }
+    virtual void provideStreamData(int objid, int generation,
+				   Pipeline* pipeline);
+
+    // Map [obj][gen] = image object
+    std::map<int, std::map<int, QPDFObjectHandle> > image_objects;
+    // Map [obj][gen] = image data
+    std::map<int, std::map<int, PointerHolder<Buffer> > > image_data;
+};
+
+void
+ImageInverter::provideStreamData(int objid, int generation,
+				 Pipeline* pipeline)
+{
+    // Use the object and generation number supplied to look up the
+    // image data.  Then invert the image data and write the inverted
+    // data to the pipeline.
+    PointerHolder<Buffer> data = this->image_data[objid][generation];
+    size_t size = data.getPointer()->getSize();
+    unsigned char* buf = data.getPointer()->getBuffer();
+    unsigned char ch;
+    for (size_t i = 0; i < size; ++i)
+    {
+	ch = (unsigned char)0xff - buf[i];
+	pipeline->write(&ch, 1);
+    }
+    pipeline->finish();
+}
+
+int main(int argc, char* argv[])
+{
+    whoami = QUtil::getWhoami(argv[0]);
+
+    // For libtool's sake....
+    if (strncmp(whoami, "lt-", 3) == 0)
+    {
+	whoami += 3;
+    }
+
+    if (! ((argc == 3) || (argc == 4)))
+    {
+	usage();
+    }
+
+    char const* infilename = argv[1];
+    char const* outfilename = argv[2];
+    char const* password = (argc == 4) ? argv[3] : "";
+
+    try
+    {
+	QPDF qpdf;
+	qpdf.processFile(infilename, password);
+
+	ImageInverter* inv = new ImageInverter;
+	PointerHolder<QPDFObjectHandle::StreamDataProvider> p = inv;
+
+	// For each page...
+	std::vector<QPDFObjectHandle> pages = qpdf.getAllPages();
+	for (std::vector<QPDFObjectHandle>::iterator iter = pages.begin();
+	     iter != pages.end(); ++iter)
+	{
+	    QPDFObjectHandle& page = *iter;
+	    // Get all images on the page.
+	    std::map<std::string, QPDFObjectHandle> images =
+		page.getPageImages();
+	    for (std::map<std::string, QPDFObjectHandle>::iterator iter =
+		     images.begin();
+		 iter != images.end(); ++iter)
+	    {
+		QPDFObjectHandle& image = (*iter).second;
+		QPDFObjectHandle image_dict = image.getDict();
+		QPDFObjectHandle color_space =
+		    image_dict.getKey("/ColorSpace");
+		QPDFObjectHandle bits_per_component =
+		    image_dict.getKey("/BitsPerComponent");
+
+		// For our example, we can only work with images 8-bit
+		// grayscale images that we can fully decode.  Use
+		// pipeStreamData with a null pipeline to determine
+		// whether the image is filterable.  Directly inspect
+		// keys to determine the image type.
+		if (image.pipeStreamData(0, true, false, false) &&
+		    color_space.isName() &&
+		    bits_per_component.isInteger() &&
+		    (color_space.getName() == "/DeviceGray") &&
+		    (bits_per_component.getIntValue() == 8))
+		{
+		    // Store information about the images based on the
+		    // object and generation number.  Recall that a single
+		    // image object may be used more than once.
+		    int objid = image.getObjectID();
+		    int gen = image.getGeneration();
+		    if (inv->image_objects[objid].count(gen) == 0)
+		    {
+			inv->image_objects[objid][gen] = image;
+			inv->image_data[objid][gen] = image.getStreamData();
+
+			// Register our stream data provider for this
+			// stream.  Future calls to getStreamData or
+			// pipeStreamData will use the new
+			// information.  Provide null for both filter
+			// and decode parameters.  Note that this does
+			// not mean the image data will be
+			// uncompressed when we write the file.  By
+			// default, QPDFWriter will use /FlateDecode
+			// for anything that is uncompressed or
+			// filterable in the input QPDF object, so we
+			// don't have to deal with it explicitly here.
+			image.replaceStreamData(
+			    p,
+			    QPDFObjectHandle::newNull(),
+			    QPDFObjectHandle::newNull(),
+			    inv->image_data[objid][gen].getPointer()->
+			        getSize());
+		    }
+		}
+	    }
+	}
+
+	// Write out a new file
+	QPDFWriter w(qpdf, outfilename);
+	if (QUtil::get_env("IN_TESTSUITE"))
+	{
+	    // For the test suite, uncompress streams and use static
+	    // IDs.
+	    w.setStaticID(true);
+	}
+	w.write();
+	std::cout << whoami << ": new file written to " << outfilename
+		  << std::endl;
+    }
+    catch (std::exception &e)
+    {
+	std::cerr << whoami << " processing file " << infilename << ": "
+		  << e.what() << std::endl;
+	exit(2);
+    }
+
+    return 0;
+}
+#!/usr/bin/env perl
+require 5.008;
+BEGIN { $^W = 1; }
+use strict;
+
+chdir("invert-images") or die "chdir testdir failed: $!\n";
+
+require TestDriver;
+
+my $td = new TestDriver('invert-images');
+
+cleanup();
+
+$td->runtest("double page size",
+	     {$td->COMMAND => "pdf-invert-images in.pdf a.pdf"},
+	     {$td->STRING =>
+		  "pdf-invert-images: new file written to a.pdf\n",
+	      $td->EXIT_STATUS => 0},
+	     $td->NORMALIZE_NEWLINES);
+
+$td->runtest("check output",
+	     {$td->FILE => "a.pdf"},
+	     {$td->FILE => "out.pdf"});
+
+cleanup();
+
+$td->report(2);
+
+sub cleanup
+{
+    unlink 'a.pdf';
+}