- Olena-patches

olena-2.0-103-g766aeea Fix inclusion paths.
by Roland Levillain 04 Mar '13

04 Mar '13

* common.mk (AM_CPPFLAGS): Add paths to scribo/ dirs instead of top-level dirs. --- scribo/ChangeLog | 7 +++++++ scribo/common.mk | 7 ++++--- 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/scribo/ChangeLog b/scribo/ChangeLog index d7f779c..cd207a3 100644 --- a/scribo/ChangeLog +++ b/scribo/ChangeLog @@ -1,3 +1,10 @@ +2013-03-04 Roland Levillain <roland(a)lrde.epita.fr> + + Fix inclusion paths. + + * common.mk (AM_CPPFLAGS): Add paths to scribo/ dirs instead of + top-level dirs. + 2013-02-13 Roland Levillain <roland(a)lrde.epita.fr> Simplify more Scribo Makefiles thanks to AM_DEFAULT_SOURCE_EXT. diff --git a/scribo/common.mk b/scribo/common.mk index ef59d88..a0dee7c 100644 --- a/scribo/common.mk +++ b/scribo/common.mk @@ -2,7 +2,7 @@ ## Common Automake parameters. -## Copyright (C) 2010 EPITA Research and Development Laboratory (LRDE). +## Copyright (C) 2010, 2013 EPITA Research and Development Laboratory (LRDE). ## ## This file is part of Olena. ## @@ -21,6 +21,7 @@ # C++ sources. AM_DEFAULT_SOURCE_EXT = .cc -# Add paths to Scribo's headers. -AM_CPPFLAGS = -I$(top_srcdir)/ -I$(top_builddir)/ \ +# Add paths to Scribo's and Milena's headers. +AM_CPPFLAGS = \ + -I$(top_srcdir)/scribo -I$(top_builddir)/scribo \ -I$(top_srcdir)/milena -I$(top_builddir)/milena -- 1.7.2.5

1 0

branch icdar/bsec2013 created: olena-2.0-229-g115049c
by git＠lrde.epita.fr 01 Mar '13

01 Mar '13

This is an automated email from the git hooks/post-receive script. It was generated because a ref change was pushed to the repository containing the project "Olena, a generic and efficient image processing platform". The branch icdar/bsec2013 has been created at 115049c77493d553961bdacfa5e80c2f276d1bb6 (commit) - Log ----------------------------------------------------------------- 115049c src/contest/bsec2013/process_toc_page.cc: New. ----------------------------------------------------------------------- hooks/post-receive -- Olena, a generic and efficient image processing platform

1 0

branch unstable/scribo updated: olena-2.0-229-g7e065e0
by git＠lrde.epita.fr 01 Mar '13

01 Mar '13

This is an automated email from the git hooks/post-receive script. It was generated because a ref change was pushed to the repository containing the project "Olena, a generic and efficient image processing platform". The branch unstable/scribo has been updated via 7e065e0e5f6be35574c5ea8c1260be79f5be1c49 (commit) from da8955a22c1dcb7945d813a802bceee05c129594 (commit) Those revisions listed above that are new to this repository have not appeared on any other notification email; so we list those revisions in full, below. - Log ----------------------------------------------------------------- 7e065e0 mln/io/pdf/load.hh: Check if the PDF can be rendered. ----------------------------------------------------------------------- Summary of changes: milena/ChangeLog | 4 ++++ milena/mln/io/pdf/load.hh | 6 ++++++ 2 files changed, 10 insertions(+), 0 deletions(-) hooks/post-receive -- Olena, a generic and efficient image processing platform

1 0

olena-2.0-229-g7e065e0 mln/io/pdf/load.hh: Check if the PDF can be rendered.
by Guillaume Lazzara 01 Mar '13

01 Mar '13

--- milena/ChangeLog | 4 ++++ milena/mln/io/pdf/load.hh | 6 ++++++ 2 files changed, 10 insertions(+), 0 deletions(-) diff --git a/milena/ChangeLog b/milena/ChangeLog index a14bc8a..86b2a92 100644 --- a/milena/ChangeLog +++ b/milena/ChangeLog @@ -1,5 +1,9 @@ 2013-03-01 Guillaume Lazzara <z(a)lrde.epita.fr> + * mln/io/pdf/load.hh: Check if the PDF can be rendered. + +2013-03-01 Guillaume Lazzara <z(a)lrde.epita.fr> + Add test images. * tests/img/example-0.ppm, diff --git a/milena/mln/io/pdf/load.hh b/milena/mln/io/pdf/load.hh index 513a61d..ee68c8a 100644 --- a/milena/mln/io/pdf/load.hh +++ b/milena/mln/io/pdf/load.hh @@ -198,6 +198,12 @@ namespace mln // Render Page poppler::page_renderer pr; + if (! pr.can_render()) + { + std::cout << "PDF cannot be rendered! Make sure libpoppler is " + << "compiled with a render backend." << std::endl; + abort(); + } poppler::image pima = pr.render_page(p, dpi, dpi); // Prepare MLN image. -- 1.7.2.5

1 0

olena-2.0-229-g115049c src/contest/bsec2013/process_toc_page.cc: New.
by Guillaume Lazzara 01 Mar '13

01 Mar '13

--- scribo/ChangeLog | 4 + scribo/src/contest/bsec2013/process_toc_page.cc | 190 +++++++++++++++++++++++ 2 files changed, 194 insertions(+), 0 deletions(-) create mode 100644 scribo/src/contest/bsec2013/process_toc_page.cc diff --git a/scribo/ChangeLog b/scribo/ChangeLog index c4bdcfc..e44574a 100644 --- a/scribo/ChangeLog +++ b/scribo/ChangeLog @@ -1,3 +1,7 @@ +2013-03-01 Guillaume Lazzara <z(a)lrde.epita.fr> + + * src/contest/bsec2013/process_toc_page.cc: New. + 2013-02-26 Guillaume Lazzara <z(a)lrde.epita.fr> * tests/unit_test/unit-tests.mk: Update. diff --git a/scribo/src/contest/bsec2013/process_toc_page.cc b/scribo/src/contest/bsec2013/process_toc_page.cc new file mode 100644 index 0000000..f261e2c --- /dev/null +++ b/scribo/src/contest/bsec2013/process_toc_page.cc @@ -0,0 +1,190 @@ +#include <iostream> +#include <mln/core/image/image2d.hh> +#include <mln/value/rgba.hh> +#include <mln/value/rgb8.hh> +#include <mln/value/qt/rgb32.hh> +#include <mln/io/ppm/save.hh> +#include <mln/io/pdf/load.hh> +#include <mln/io/pdf/get_header.hh> +#include <mln/data/convert.hh> +#include <poppler/cpp/poppler-document.h> +#include <poppler/cpp/poppler-page.h> +#include <poppler/cpp/poppler-page-renderer.h> +#include <mln/debug/filename.hh> +#include <QString> +#include <QStringList> +#include <QDebug> + +int main(int argc, char *argv[]) +{ + if (argc != 3) + { + std::cout << "Usage: " << argv[0] << " <doc.pdf> <page>" << std::endl; + return 1; + } + + using namespace poppler; + using namespace mln; + + // Load document + poppler::document *pdf = poppler::document::load_from_file(argv[1]); + if (pdf == 0) + { + std::cerr << "Error: Cannot load PDF " << argv[1] << std::endl; + abort(); + } + + + + // Read page + poppler::page* p = pdf->create_page(atoi(argv[2])); + std::vector<char> byte_array = p->text().to_utf8(); + if (byte_array.size() > 0) + { + QString text = QString::fromUtf8((const char *)&byte_array[0]); + + // Remove '.' and '-' (usually used in table of contents between + // title and page number. + text = text.replace('.', ' '); + text = text.replace('-', ' '); + text = text.replace('*', ' '); + + QStringList entries = text.split('\n'); + + qDebug() << entries; + + qDebug(); + + + // PASS 1 - Remove useless spaces. + for (int i = 0; i < entries.size(); ++i) + entries[i] = entries[i].simplified(); + + + // PASS 2 - Merge lines. + for (int i = 0; i < entries.size();) + { + bool removed = false; + QString& entry = entries[i]; + + // Skip Table of Contents title. + if (entry.contains("table of contents", Qt::CaseInsensitive)) + { + ++i; + continue; + } + + // Remove empty lines + if (entry.isEmpty() || entry == "") // FIXME: There is a bug! + // Some empty strings seems + // to pass this test! + // (100_book_subset/pdfs/aidstothebible01popeuoft.pdf + // page10) + { + entries.removeAt(i); + continue; + } + + // Move single numbers to previous lines. + qDebug() << "Checking " << entry; + if (entry.contains(QRegExp("^[0-9mcxilv]+$", Qt::CaseInsensitive))) + { + if ((i - 1) > 0) + { + //qDebug() << "MERGING BACK " << entry << " TO " << entries[i - 1]; + + entries[i - 1].append(" " + entry); + entries.removeAt(i); + removed = true; + } + } + // Trying to merge lines corresponding to entries on several + // lines. + else if (! entry.contains(QRegExp(" [0-9mcxilv]+$", Qt::CaseInsensitive))) + if ((i + 1) < entries.size()) + { + //qDebug() << "MERGING FORWARD " << entries[i + 1] << " TO " << entry; + entry.append(" " + entries[i + 1].simplified()); + entries.removeAt(i + 1); + removed = true; + //entries[i + 1].clear(); + } + + if (!removed) + ++i; + } + + // PASS 3 - Grouping page numbers if there is space in between. + // Remove multiple invalid page numbers like "14 VI". + for (int i = 0; i < entries.size(); ++i) + { + QString& entry = entries[i]; + + // Garbage page numbers. Keep the first one. + if (entry.contains(QRegExp(" [0-9]+ [mcxilv]+$", Qt::CaseInsensitive)) + || entry.contains(QRegExp(" [mcxilv]+ [0-9]+$", Qt::CaseInsensitive))) + { + QStringList words = entry.split(' '); + QString new_entry = ""; + for (int j = 0; j < words.size() - 2; ++j) + new_entry += words[j] + " "; + new_entry += words[words.size() - 1]; + entry = new_entry; + } + else if (entry.contains(QRegExp(" [mcxilv]+ [mcxilv]+$", Qt::CaseInsensitive))) + { + QStringList words = entry.split(' '); + QString new_entry = ""; + for (int j = 0; j < words.size() - 2; ++j) + new_entry += words[j] + " "; + new_entry += words[words.size() - 2] + words[words.size() - 1]; + entry = new_entry; + } + else if (entry.contains(QRegExp(" [0-9]+ [0-9]+$", Qt::CaseInsensitive))) + { // Same case as previous one except that we check if the page number exists! + QStringList words = entry.split(' '); + QString new_entry = ""; + for (int j = 0; j < words.size() - 2; ++j) + new_entry += words[j] + " "; + + int page = QString(words[words.size() - 2] + words[words.size() - 1]).toInt(); + + if (page > pdf->pages()) + new_entry += words[words.size() - 2]; // Keep first page number + else + new_entry += words[words.size() - 2] + words[words.size() - 1]; // Merging both. + entry = new_entry; + } + + } + + qDebug() << entries; + } + + + // io::pdf::pdf_header header = + // io::pdf::get_header(argv[1]); + + // std::cout << header.page_count << std::endl; + // util::array<image2d<value::rgb8> > arr; + // io::pdf::load(arr, argv[1], 0, 10); + + // for (unsigned i = 0; i < arr.size(); ++i) + // io::ppm::save(arr[i], mln::debug::filename("page.ppm")); + + // util::array<int> pages; + // pages.append(1); + // pages.append(9); + + // arr.clear(); + // io::pdf::load(arr, argv[1], pages); + + // for (unsigned i = 0; i < arr.size(); ++i) + // io::ppm::save(arr[i], mln::debug::filename("pages.ppm")); + + + //pima.save("page.png", "PNG", 300); + + + +} -- 1.7.2.5

1 0

branch papers/lazzara.13.ijdar updated: olena-2.0-138-g9d6aa0a
by git＠lrde.epita.fr 01 Mar '13

01 Mar '13

This is an automated email from the git hooks/post-receive script. It was generated because a ref change was pushed to the repository containing the project "Olena, a generic and efficient image processing platform". The branch papers/lazzara.13.ijdar has been updated via 9d6aa0aed479c79c07ce250cc0f37b8787b416b8 (commit) from b05f4e5c24d32b2d704badd28fd16dfa4a235bc6 (commit) Those revisions listed above that are new to this repository have not appeared on any other notification email; so we list those revisions in full, below. - Log ----------------------------------------------------------------- 9d6aa0a scribo/text/recognition.hh: Fix tesseract includes. ----------------------------------------------------------------------- Summary of changes: scribo/ChangeLog | 4 ++++ scribo/scribo/text/recognition.hh | 1 - 2 files changed, 4 insertions(+), 1 deletions(-) hooks/post-receive -- Olena, a generic and efficient image processing platform

1 0

olena-2.0-138-g9d6aa0a scribo/text/recognition.hh: Fix tesseract includes.
by Guillaume Lazzara 01 Mar '13

01 Mar '13

--- scribo/ChangeLog | 4 ++++ scribo/scribo/text/recognition.hh | 1 - 2 files changed, 4 insertions(+), 1 deletions(-) diff --git a/scribo/ChangeLog b/scribo/ChangeLog index 687f107..2a4ea62 100644 --- a/scribo/ChangeLog +++ b/scribo/ChangeLog @@ -1,3 +1,7 @@ +2013-03-01 Guillaume Lazzara <z(a)lrde.epita.fr> + + * scribo/text/recognition.hh: Fix tesseract includes. + 2013-01-28 Guillaume Lazzara <z(a)lrde.epita.fr> Use io::magick to save output. diff --git a/scribo/scribo/text/recognition.hh b/scribo/scribo/text/recognition.hh index 2b9d5a1..bf3ae9b 100644 --- a/scribo/scribo/text/recognition.hh +++ b/scribo/scribo/text/recognition.hh @@ -66,7 +66,6 @@ # include <tesseract/baseapi.h> # if defined HAVE_TESSERACT_3 -# include <tesseract/ocrclass.h> # include <tesseract/resultiterator.h> # endif // ! HAVE_TESSERACT_3 -- 1.7.2.5

1 0

branch unstable/scribo updated: olena-2.0-228-gda8955a
by git＠lrde.epita.fr 01 Mar '13

01 Mar '13

This is an automated email from the git hooks/post-receive script. It was generated because a ref change was pushed to the repository containing the project "Olena, a generic and efficient image processing platform". The branch unstable/scribo has been updated via da8955a22c1dcb7945d813a802bceee05c129594 (commit) from c37c7275749e5e85303ad4d19db9de5a533cbb01 (commit) Those revisions listed above that are new to this repository have not appeared on any other notification email; so we list those revisions in full, below. - Log ----------------------------------------------------------------- da8955a Add test images. ----------------------------------------------------------------------- Summary of changes: milena/ChangeLog | 10 ++++++++++ milena/tests/img/example-0.ppm | 6 ++++++ milena/tests/img/example-1.ppm | 6 ++++++ milena/tests/img/example-2.ppm | 6 ++++++ milena/tests/img/example-3.ppm | 6 ++++++ milena/tests/img/example.pdf | Bin 0 -> 202744 bytes 6 files changed, 34 insertions(+), 0 deletions(-) create mode 100644 milena/tests/img/example-0.ppm create mode 100644 milena/tests/img/example-1.ppm create mode 100644 milena/tests/img/example-2.ppm create mode 100644 milena/tests/img/example-3.ppm create mode 100644 milena/tests/img/example.pdf hooks/post-receive -- Olena, a generic and efficient image processing platform

1 0

branch unstable/scribo updated: olena-2.0-227-gc37c727
by git＠lrde.epita.fr 28 Feb '13

28 Feb '13

This is an automated email from the git hooks/post-receive script. It was generated because a ref change was pushed to the repository containing the project "Olena, a generic and efficient image processing platform". The branch unstable/scribo has been updated via c37c7275749e5e85303ad4d19db9de5a533cbb01 (commit) via b703a0846caa205810f7bb044f6af5a1dc881472 (commit) from b460ca006fc7f6d667402ef56cd474e422ab61d2 (commit) Those revisions listed above that are new to this repository have not appeared on any other notification email; so we list those revisions in full, below. - Log ----------------------------------------------------------------- c37c727 configure.ac: Check for libpoppler dependency and configure pdf::load test directory. b703a08 Add support for loading multiple pages PDF files using libpoppler. ----------------------------------------------------------------------- Summary of changes: ChangeLog | 5 + configure.ac | 9 + milena/ChangeLog | 11 + milena/mln/io/{dicom => pdf}/get_header.hh | 85 ++++--- milena/mln/io/pdf/load.hh | 335 ++++++++++++++++++++++++++++ milena/tests/io/Makefile.am | 6 +- milena/tests/io/{pbms => pdf}/Makefile.am | 9 +- milena/tests/io/pdf/load.cc | 88 ++++++++ 8 files changed, 505 insertions(+), 43 deletions(-) copy milena/mln/io/{dicom => pdf}/get_header.hh (53%) create mode 100644 milena/mln/io/pdf/load.hh copy milena/tests/io/{pbms => pdf}/Makefile.am (82%) create mode 100644 milena/tests/io/pdf/load.cc hooks/post-receive -- Olena, a generic and efficient image processing platform

1 0

olena-2.0-226-gb703a08 Add support for loading multiple pages PDF files using libpoppler.
by Guillaume Lazzara 28 Feb '13

28 Feb '13

* mln/io/pdf/get_header.hh, * mln/io/pdf/load.hh, * mln/tests/io/pdf/Makefile.am, * mln/tests/io/pdf/load.cc: New. * mln/tests/io/Makefile.am: Add pdf/ subdir. --- milena/ChangeLog | 11 + milena/mln/io/{dicom => pdf}/get_header.hh | 85 ++++--- milena/mln/io/pdf/load.hh | 335 ++++++++++++++++++++++++++++ milena/tests/io/Makefile.am | 6 +- milena/tests/io/{pbms => pdf}/Makefile.am | 9 +- milena/tests/io/pdf/load.cc | 88 ++++++++ 6 files changed, 491 insertions(+), 43 deletions(-) copy milena/mln/io/{dicom => pdf}/get_header.hh (53%) create mode 100644 milena/mln/io/pdf/load.hh copy milena/tests/io/{pbms => pdf}/Makefile.am (82%) create mode 100644 milena/tests/io/pdf/load.cc diff --git a/milena/ChangeLog b/milena/ChangeLog index 4d53dd4..2b19aec 100644 --- a/milena/ChangeLog +++ b/milena/ChangeLog @@ -1,3 +1,14 @@ +2013-02-28 Guillaume Lazzara <z(a)lrde.epita.fr> + + Add support for loading multiple pages PDF files using libpoppler. + + * mln/io/pdf/get_header.hh, + * mln/io/pdf/load.hh, + * mln/tests/io/pdf/Makefile.am, + * mln/tests/io/pdf/load.cc: New. + + * mln/tests/io/Makefile.am: Add pdf/ subdir. + 2013-02-26 Guillaume Lazzara <z(a)lrde.epita.fr> * tests/unit_test/unit-tests.mk: Update. diff --git a/milena/mln/io/dicom/get_header.hh b/milena/mln/io/pdf/get_header.hh similarity index 53% copy from milena/mln/io/dicom/get_header.hh copy to milena/mln/io/pdf/get_header.hh index 8ebe375..1969689 100644 --- a/milena/mln/io/dicom/get_header.hh +++ b/milena/mln/io/pdf/get_header.hh @@ -1,4 +1,4 @@ -// Copyright (C) 2010 EPITA Research and Development Laboratory (LRDE) +// Copyright (C) 2013 EPITA Research and Development Laboratory (LRDE) // // This file is part of Olena. // @@ -23,22 +23,16 @@ // exception does not however invalidate any other reasons why the // executable file might be covered by the GNU General Public License. -#ifndef MLN_IO_DICOM_GET_HEADER_HH -# define MLN_IO_DICOM_GET_HEADER_HH +#ifndef MLN_IO_PDF_GET_HEADER_HH +# define MLN_IO_PDF_GET_HEADER_HH /// \file /// -/// Load a DICOM file header. +/// Load PDF header. # include <iostream> # include <fstream> -# include <gdcm-2.0/gdcmReader.h> -# include <gdcm-2.0/gdcmImageReader.h> -# include <gdcm-2.0/gdcmWriter.h> -# include <gdcm-2.0/gdcmDataSet.h> -# include <gdcm-2.0/gdcmAttribute.h> - # include <mln/core/concept/image.hh> # include <mln/core/routine/initialize.hh> # include <mln/core/box_runstart_piter.hh> @@ -52,63 +46,78 @@ namespace mln namespace io { - namespace dicom + namespace pdf { - /// Store dicom file header. - struct dicom_header + /// Store pdf file header. + struct pdf_header { - // The number of dimensions. - unsigned dim; - - // The size in each dimension. - util::array<unsigned> size; + pdf_header(const poppler::document *doc); + + int page_count; + int pdf_version_major; + int pdf_version_minor; + bool is_encrypted; + bool is_linearized; + bool is_locked; + std::string metadata; }; - /// Retrieve header in a dicom file. - dicom_header get_header(const std::string& filename); + /// Retrieve header in a pdf file. + pdf_header get_header(const std::string& filename); # ifndef MLN_INCLUDE_ONLY + // Begin of pdf_header implementation. - dicom_header get_header(const std::string& filename) + pdf_header::pdf_header(const poppler::document *doc) { - trace::entering("mln::io::dicom::get_header"); + page_count = doc->pages(); + doc->get_pdf_version(&pdf_version_major, 0); + doc->get_pdf_version(0, &pdf_version_minor); + is_encrypted = doc->is_encrypted(); + is_linearized = doc->is_linearized(); + is_locked = doc->is_locked(); + metadata = doc->metadata().to_latin1(); + } + + // End of pdf_header implementation. - dicom_header header; - gdcm::ImageReader r; - r.SetFileName(filename.c_str()); - if (!r.Read()) + + inline + pdf_header get_header(const std::string& filename) + { + trace::entering("mln::io::pdf::get_header"); + + // Load document + poppler::document *pdf = poppler::document::load_from_file(filename); + if (pdf == 0) { - std::cerr << "error: cannot open file '" << filename << "'!"; + std::cerr << "Error: Cannot load PDF " << filename << std::endl; abort(); } - gdcm::Image& image = r.GetImage(); - - header.dim = image.GetNumberOfDimensions(); - const unsigned int* dims = image.GetDimensions(); + // Initialize structure with pdf information. + pdf_header header(pdf); - for (unsigned i = 2; i < header.dim; ++i) - header.size.append(dims[i]); // sli, ... - for (unsigned i = 0; i < 2; ++i) - header.size.append(dims[i]); // row, col + // Clear pdf document. + delete pdf; - trace::exiting("mln::io::dicom::get_header"); + trace::exiting("mln::io::pdf::get_header"); return header; } # endif // ! MLN_INCLUDE_ONLY - } // end of namespace mln::io::dicom + } // end of namespace mln::io::pdf } // end of namespace mln::io } // end of namespace mln -#endif // ! MLN_IO_DICOM_GET_HEADER_HH +#endif // ! MLN_IO_PDF_GET_HEADER_HH diff --git a/milena/mln/io/pdf/load.hh b/milena/mln/io/pdf/load.hh new file mode 100644 index 0000000..513a61d --- /dev/null +++ b/milena/mln/io/pdf/load.hh @@ -0,0 +1,335 @@ +// Copyright (C) 2013 EPITA Research and Development Laboratory (LRDE) +// +// This file is part of Olena. +// +// Olena is free software: you can redistribute it and/or modify it under +// the terms of the GNU General Public License as published by the Free +// Software Foundation, version 2 of the License. +// +// Olena is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +// General Public License for more details. +// +// You should have received a copy of the GNU General Public License +// along with Olena. If not, see <http://www.gnu.org/licenses/>. +// +// As a special exception, you may use this file as part of a free +// software project without restriction. Specifically, if other files +// instantiate templates or use macros or inline functions from this +// file, or you compile this file and link it with other files to produce +// an executable, this file does not by itself cause the resulting +// executable to be covered by the GNU General Public License. This +// exception does not however invalidate any other reasons why the +// executable file might be covered by the GNU General Public License. + +#ifndef MLN_IO_PDF_LOAD_HH +# define MLN_IO_PDF_LOAD_HH + +/// \file +/// +/// \brief Load a multiple page PDF document using libpoppler. + +#include <iostream> +#include <mln/core/image/image2d.hh> +#include <poppler/cpp/poppler-document.h> +#include <poppler/cpp/poppler-page-renderer.h> + + +namespace mln +{ + + namespace io + { + + namespace pdf + { + + /**! Load a multiple page PDF document using libpoppler. + + \param[out] arr An array of images. + \param[in] filename The name of the input file. + \param[in] dpi Document resolution. + + Page numbering starts from 0. + */ + template <typename I> + void load(util::array& arr, const std::string& filename, + float dpi); + + /**! Load a range of pages from a PDF document using libpoppler. + + \param[out] arr An array of images. + \param[in] filename The name of the input file. + \param[in] first_page First page number. + \param[in] last_page Last page number. + \param[in] dpi Document resolution. + + Page numbering starts from 0. + */ + template <typename I> + void load(util::array& arr, const std::string& filename, + int first_page, int last_page, float dpi); + + + /**! Load specific pages from a PDF document using libpoppler. + + \param[out] arr An array of images. + \param[in] filename The name of the input file. + \param[in] pages An array of pages numbers. + \param[in] dpi Document resolution. + + Page numbering starts from 0. + */ + template <typename I> + void load(util::array& arr, const std::string& filename, + util::array<int> pages, float dpi); + + /**! Load a specific page from a PDF document using libpoppler. + + \param[out] ima An image. + \param[in] filename The name of the input file. + \param[in] page The page number. + \param[in] dpi Document resolution. + + Page numbering starts from 0. + */ + template <typename I> + void load(Image& ima, const std::string& filename, + int page, float dpi); + + + /**! \overload Load a multiple page PDF document using libpoppler. + + \param[out] arr An array of images. + \param[in] filename The name of the input file. + + DPI resolution is set to 300. + Page numbering starts from 0. + */ + template <typename I> + void load(util::array& arr, const std::string& filename); + + /**! \overload Load specific pages from a PDF document using + libpoppler. + + \param[out] arr An array of images. + \param[in] filename The name of the input file. + \param[in] pages An array of pages numbers. + + DPI resolution is set to 300. + Page numbering starts from 0. + */ + template <typename I> + void load(util::array& arr, const std::string& filename, + util::array<int> pages); + + +# ifndef MLN_INCLUDE_ONLY + + namespace internal + { + + template <typename I> + void copy_data_argb32(I& ima, const poppler::image& pima) + { + mln_value(I) *vima = &ima(ima.domain().pmin()); + const unsigned char * + nsites = (unsigned char *)pima.const_data() + + pima.width() * pima.height() * 4; + + unsigned next = 4; + for (const unsigned char *v = (unsigned char *)pima.const_data(); + v < nsites; v += next, ++vima) + { + vima->red() = *(v + 2); + vima->green() = *(v + 1); + vima->blue() = *v; + } + } + + template <typename I> + void copy_data_rgb24(I& ima, const poppler::image& pima) + { + mln_value(I) *vima = &ima(ima.domain().pmin()); + const unsigned char * + nsites = (unsigned char *)pima.const_data() + + pima.width() * pima.height() * 3; + + unsigned next = 3; + for (const unsigned char *v = (unsigned char *)pima.const_data(); + v < nsites; v += next, ++vima) + { + vima->red() = *v; + vima->green() = *(v + 1); + vima->blue() = *(v + 2); + } + } + + + template <typename I> + void copy_data(I& ima, const poppler::image& pima) + { + mln_precondition(ima.is_valid()); + + switch(pima.format()) + { + case poppler::image::format_invalid: + case poppler::image::format_mono: + std::cout << "Loading black and white pdf is not implemented!"; + abort(); + break; + case poppler::image::format_rgb24: + copy_data_rgb24(ima, pima); + break; + case poppler::image::format_argb32: + copy_data_argb32(ima, pima); + break; + } + } + + + template <typename I> + void extract_page(const poppler::document* pdf, int i, + util::array& arr, float dpi) + { + // Read page + poppler::page* p = pdf->create_page(i); + + // Render Page + poppler::page_renderer pr; + poppler::image pima = pr.render_page(p, dpi, dpi); + + // Prepare MLN image. + I ima(make::box2d(pima.height(), pima.width()), 0); + mln_assertion(ima.is_valid()); + + // Copy data + internal::copy_data(ima, pima); + + // Append result + arr.append(ima); + } + + } // end of namespace mln::io::pdf::internal + + + template <typename I> + void load(util::array& arr, const std::string& filename, float dpi) + { + trace::entering("mln::io::pdf::load"); + + // Load document + poppler::document *pdf = poppler::document::load_from_file(filename); + if (pdf == 0) + { + std::cerr << "Error: Cannot load pdf " << filename << std::endl; + abort(); + } + + for (int i = 0; i < pdf->pages(); ++i) + internal::extract_page(pdf, i, arr, dpi); + + delete pdf; + + trace::exiting("mln::io::pdf::load"); + } + + template <typename I> + void load(util::array& arr, const std::string& filename, + int first_page, int last_page, float dpi) + { + trace::entering("mln::io::pdf::load"); + + // Load document + poppler::document *pdf = poppler::document::load_from_file(filename); + if (pdf == 0) + { + std::cerr << "Error: Cannot load PDF " << filename << std::endl; + abort(); + } + + if (first_page < 0 || first_page > (pdf->pages() - 1) + || last_page < 0 || last_page > (pdf->pages() - 1)) + { + std::cout << "Error while loading PDF: page range is not correct!" + << std::endl; + abort(); + } + + for (int i = first_page; i <= last_page; ++i) + internal::extract_page(pdf, i, arr, dpi); + + delete pdf; + + trace::exiting("mln::io::pdf::load"); + } + + + template <typename I> + void load(util::array& arr, const std::string& filename, + util::array<int> pages, float dpi) + { + trace::entering("mln::io::pdf::load"); + + // Load document + poppler::document *pdf = poppler::document::load_from_file(filename); + if (pdf == 0) + { + std::cerr << "Error: Cannot load PDF " << filename << std::endl; + abort(); + } + + for (unsigned i = 0; i < pages.size(); ++i) + { + if (pages[i] < 0 || pages[i] > pdf->pages() - 1) + { + std::cout << "Error while loading PDF: selected page " + << pages[i] << " does not exist!" << std::endl; + abort(); + } + + internal::extract_page(pdf, pages[i], arr, dpi); + } + + delete pdf; + + trace::exiting("mln::io::pdf::load"); + } + + + template <typename I> + void load(Image& ima, const std::string& filename, + int page, float dpi) + { + util::array arr; + load(arr, filename, page, page, dpi); + mln_assertion(arr.size() == 1); + exact(ima) = arr[0]; + } + + template <typename I> + void load(util::array& arr, const std::string& filename) + { + load(arr, filename, 300); + } + + + template <typename I> + void load(util::array& arr, const std::string& filename, + util::array<int> pages) + { + load(arr, filename, pages, 300); + } + + +# endif // ! MLN_INCLUDE_ONLY + + } // end of namespace mln::io::pdf + + } // end of namespace mln::io + +} // end of namespace mln + + +#endif // ! MLN_IO_PDF_LOAD_HH diff --git a/milena/tests/io/Makefile.am b/milena/tests/io/Makefile.am index bd6c0a4..1859b6a 100644 --- a/milena/tests/io/Makefile.am +++ b/milena/tests/io/Makefile.am @@ -1,4 +1,4 @@ -# Copyright (C) 2007, 2008, 2009 EPITA Research and Development +# Copyright (C) 2007, 2008, 2009, 2013 EPITA Research and Development # Laboratory (LRDE). # # This file is part of Olena. @@ -53,3 +53,7 @@ endif HAVE_MAGICKXX if HAVE_TIFF SUBDIRS += tiff endif HAVE_TIFF + +if HAVE_POPPLER + SUBDIRS += pdf +endif HAVE_POPPLER \ No newline at end of file diff --git a/milena/tests/io/pbms/Makefile.am b/milena/tests/io/pdf/Makefile.am similarity index 82% copy from milena/tests/io/pbms/Makefile.am copy to milena/tests/io/pdf/Makefile.am index 4d54371..0144098 100644 --- a/milena/tests/io/pbms/Makefile.am +++ b/milena/tests/io/pdf/Makefile.am @@ -1,4 +1,4 @@ -# Copyright (C) 2009, 2010 EPITA Research and Development Laboratory (LRDE). +# Copyright (C) 2013 EPITA Research and Development Laboratory (LRDE). # # This file is part of Olena. # @@ -16,10 +16,11 @@ include $(top_srcdir)/milena/tests/tests.mk +AM_CPPFLAGS += $(POPPLER_CPPFLAGS) +AM_LDFLAGS = $(POPPLER_LDFLAGS) + check_PROGRAMS = \ - load + load TESTS = $(check_PROGRAMS) - -MOSTLYCLEANFILES = pbms-out.pbm diff --git a/milena/tests/io/pdf/load.cc b/milena/tests/io/pdf/load.cc new file mode 100644 index 0000000..c517784 --- /dev/null +++ b/milena/tests/io/pdf/load.cc @@ -0,0 +1,88 @@ +// Copyright (C) 2013 EPITA Research and Development Laboratory (LRDE) +// +// This file is part of Olena. +// +// Olena is free software: you can redistribute it and/or modify it under +// the terms of the GNU General Public License as published by the Free +// Software Foundation, version 2 of the License. +// +// Olena is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +// General Public License for more details. +// +// You should have received a copy of the GNU General Public License +// along with Olena. If not, see <http://www.gnu.org/licenses/>. +// +// As a special exception, you may use this file as part of a free +// software project without restriction. Specifically, if other files +// instantiate templates or use macros or inline functions from this +// file, or you compile this file and link it with other files to produce +// an executable, this file does not by itself cause the resulting +// executable to be covered by the GNU General Public License. This +// exception does not however invalidate any other reasons why the +// executable file might be covered by the GNU General Public License. + +#include <mln/core/image/image2d.hh> +#include <mln/data/compare.hh> +#include <mln/value/rgb8.hh> +#include <mln/io/ppm/load.hh> +#include <mln/io/pdf/load.hh> +#include "tests/data.hh" + +int main() +{ + using namespace mln; + + image2d<value::rgb8> page0, page1, page2, page3; + + io::ppm::load(page0, MLN_TESTS_IMG_DIR "/example-0.ppm"); + io::ppm::load(page1, MLN_TESTS_IMG_DIR "/example-1.ppm"); + io::ppm::load(page2, MLN_TESTS_IMG_DIR "/example-2.ppm"); + io::ppm::load(page3, MLN_TESTS_IMG_DIR "/example-3.ppm"); + + // Loading full PDF. + { + util::array<image2d<value::rgb8> > arr; + io::pdf::load(arr, MLN_TESTS_IMG_DIR "/example.pdf", 75); + + mln_assertion(arr.size() == 4); + mln_assertion(arr[0] == page0); + mln_assertion(arr[1] == page1); + mln_assertion(arr[2] == page2); + mln_assertion(arr[3] == page3); + } + + // Loading a page range + { + util::array<image2d<value::rgb8> > arr; + io::pdf::load(arr, MLN_TESTS_IMG_DIR "/example.pdf", 1, 2, 75); + + mln_assertion(arr.size() == 2); + mln_assertion(arr[0] == page1); + mln_assertion(arr[1] == page2); + } + + // Loading specific pages. + { + util::array<int> pages; + pages.append(1); + pages.append(3); + util::array<image2d<value::rgb8> > arr; + io::pdf::load(arr, MLN_TESTS_IMG_DIR "/example.pdf", pages, 75); + + mln_assertion(arr.size() == 2); + mln_assertion(arr[0] == page1); + mln_assertion(arr[1] == page3); + } + + // Loading a specific page. + { + image2d<value::rgb8> ima; + io::pdf::load(ima, MLN_TESTS_IMG_DIR "/example.pdf", 3, 75); + + mln_assertion(ima.is_valid()); + mln_assertion(ima == page3); + } + +} -- 1.7.2.5

1 0