* arthur/xml_transform/README * arthur/xml_transform/loader.cc * arthur/xml_transform/loader.hh * arthur/xml_transform/main.cc * arthur/xml_transform/xml_transform.cc * arthur/xml_transform/xml_transform.hh * arthur/xml_transform/templates/pdf/regions_svg.xsl, * arthur/xml_transform/templates/pdf/svg_generator.sh: New. --- scribo/sandbox/ChangeLog | 15 +++ scribo/sandbox/arthur/xml_transform/README | 25 ++++-- scribo/sandbox/arthur/xml_transform/loader.cc | 15 +++ scribo/sandbox/arthur/xml_transform/loader.hh | 1 + scribo/sandbox/arthur/xml_transform/main.cc | 41 ++++++--- .../xml_transform/templates/pdf/regions_svg.xsl | 98 ++++++++++++++++++++ .../xml_transform/templates/pdf/svg_generator.sh | 3 + .../sandbox/arthur/xml_transform/xml_transform.cc | 10 ++ .../sandbox/arthur/xml_transform/xml_transform.hh | 1 + 9 files changed, 188 insertions(+), 21 deletions(-) create mode 100644 scribo/sandbox/arthur/xml_transform/templates/pdf/regions_svg.xsl create mode 100644 scribo/sandbox/arthur/xml_transform/templates/pdf/svg_generator.sh diff --git a/scribo/sandbox/ChangeLog b/scribo/sandbox/ChangeLog index 8d7b3e9..7c53037 100644 --- a/scribo/sandbox/ChangeLog +++ b/scribo/sandbox/ChangeLog @@ -1,3 +1,18 @@ +2010-07-22 Arthur Crepin-Leblond <crepin@ptaouchnok.lrde.epita.fr> + + SVG output. + + * arthur/xml_transform/README + * arthur/xml_transform/loader.cc + * arthur/xml_transform/loader.hh + * arthur/xml_transform/main.cc + * arthur/xml_transform/xml_transform.cc + * arthur/xml_transform/xml_transform.hh + + * arthur/xml_transform/templates/pdf/regions_svg.xsl, + * arthur/xml_transform/templates/pdf/svg_generator.sh: New. + + 2010-07-15 Arthur Crepin-Leblond <crepin@stockholm.lrde.epita.fr> XML Tranform. diff --git a/scribo/sandbox/arthur/xml_transform/README b/scribo/sandbox/arthur/xml_transform/README index aedf220..4e98a76 100644 --- a/scribo/sandbox/arthur/xml_transform/README +++ b/scribo/sandbox/arthur/xml_transform/README @@ -1,23 +1,29 @@ xml_transform - OPTIONS: HTML output: - --html <xml> <ppm> <out_dir> : HTML output with non-text regions croped into many png files. + --html <xml> <ppm> <out_dir> : HTML output with non-text regions cropped into many png files. --html-base64 <xml> <out_dir> : HTML output from a container XML file. PDF output: - --pdf <xml> <ppm> <out_dir> : PDF output with non-text regions croped into many png files. + --pdf <xml> <ppm> <out_dir> : PDF output with non-text regions cropped into many png files. --pdf-no-crop <xml> <ppm> <out_dir>: PDF output with the entire picture displayed over the text. --pdf-base64 <xml> <out_dir> : PDF output from a container XML file. - --pdf-base64-no-crop <xml> <ppm> <out_dir> : PDF with the entire picture displayed over the text, - the picture is loaded from a container XML file. + --pdf-base64-no-crop <xml> <ppm> <out_dir> : PDF with the entire picture displayed over the text, the picture is loaded from a container XML file. + +SVG output: + --svg <xml> <out_dir> : SVG output (works only with base 64 xml encoded. Base 64 operations: - --to-base64 <xml> <ppm> <out_xml> : Produces a container XML file by converting croped pictures into base 64 format. + --to-base64 <xml> <ppm> <out_xml> : Produces a container XML file by converting cropped pictures into base 64 format. --to-base64-no-crop <xml> <ppm> <out_xml> : Same as to-base64 but only the picture is converted in base 64. --from-base64 <xml> <out_dir> : Decodes a XML container file to produce original image files. +For PDF/HTML/SVG output, Bourne shell scripts are provided to produce the outputs, just run sh *_generator.sh +Requirements: +PDF : fop >= 0.95 +HTML : xsltproc +SVG : trunk version of fop BUILD: @@ -25,5 +31,10 @@ Chnage the environment variable QMAKE_CXXFLAGS in xml_transfrom.pro then mkdir _build cd _build +cp -r ../templates . qmake ../xml_transfrom.pro -make \ No newline at end of file +make + +/!\ IMPORTANT NOTE /!\ + +xml_transfrom uses a templates directory, binary and this folder should be in the same place. \ No newline at end of file diff --git a/scribo/sandbox/arthur/xml_transform/loader.cc b/scribo/sandbox/arthur/xml_transform/loader.cc index 2b64337..1698899 100644 --- a/scribo/sandbox/arthur/xml_transform/loader.cc +++ b/scribo/sandbox/arthur/xml_transform/loader.cc @@ -126,6 +126,21 @@ void Loader::add_pdf_templates(bool crop, bool base64, QString output) } } +void Loader::add_svg_templates(QString output) +{ + QFile regions("templates/pdf/regions_svg.xsl"); + regions.copy(output + "regions.xsl"); + + QFile gen("templates/pdf/svg_generator.sh"); + gen.copy(output + "svg_generator.sh"); + + QFile line("templates/pdf/line.xsl"); + line.copy(output + "line.xsl"); + + QFile xsl("templates/pdf/main_crop.xsl"); + xsl.copy(output + "main.xsl"); +} + bool Loader::xml_output(QString xml_file, bool html, QString output) { QFile file(xml_file); diff --git a/scribo/sandbox/arthur/xml_transform/loader.hh b/scribo/sandbox/arthur/xml_transform/loader.hh index fadceed..3cbae5c 100644 --- a/scribo/sandbox/arthur/xml_transform/loader.hh +++ b/scribo/sandbox/arthur/xml_transform/loader.hh @@ -42,6 +42,7 @@ class Loader : public QObject QDomDocument* xml_to_dom(QString xml_file); bool set_output(QString& output); void add_pdf_templates(bool crop, bool base64, QString output); + void add_svg_templates(QString output); void add_html_templates(bool base64, QString output); }; diff --git a/scribo/sandbox/arthur/xml_transform/main.cc b/scribo/sandbox/arthur/xml_transform/main.cc index c259c76..d1c789d 100644 --- a/scribo/sandbox/arthur/xml_transform/main.cc +++ b/scribo/sandbox/arthur/xml_transform/main.cc @@ -6,20 +6,27 @@ int main(int argc, char **argv) { std::string man; - man = "xml_transform\n"; - man += "OPTIONS:\n\n"; - man += "HTML output:\n"; - man += "\t--html <xml> <ppm> <out_dir> : HTML output with non-text regions cropped into many png files.\n"; - man += "\t--html-base64 <xml> <out_dir> : HTML output from a container XML file.\n\n"; - man += "PDF output:\n"; - man += "\t--pdf <xml> <ppm> <out_dir> : PDF output with non-text regions cropped into many png files.\n"; - man += "\t--pdf-no-crop <xml> <ppm> <out_dir>: PDF output with the entire picture displayed over the text.\n"; - man += "\t--pdf-base64 <xml> <out_dir> : PDF output from a container XML file.\n"; - man += "\t--pdf-base64-no-crop <xml> <ppm> <out_dir> : PDF with the entire picture displayed over the text, the picture is loaded from a container XML file.\n\n"; - man += "Base 64 operations:\n"; - man += "\t--to-base64 <xml> <ppm> <out_xml> : Produces a container XML file by converting cropped pictures into base 64 format.\n"; - man += "\t--to-base64-no-crop <xml> <ppm> <out_xml> : Same as to-base64 but only the picture is converted in base 64.\n"; - man += "\t--from-base64 <xml> <out_dir> : Decodes a XML container file to produce original image files.\n"; + man = "xml_transform\n" + "OPTIONS:\n\n" + "HTML output:\n" + "\t--html <xml> <ppm> <out_dir> : HTML output with non-text regions cropped into many png files.\n" + "\t--html-base64 <xml> <out_dir> : HTML output from a container XML file.\n\n" + "PDF output:\n" + "\t--pdf <xml> <ppm> <out_dir> : PDF output with non-text regions cropped into many png files.\n" + "\t--pdf-no-crop <xml> <ppm> <out_dir>: PDF output with the entire picture displayed over the text.\n" + "\t--pdf-base64 <xml> <out_dir> : PDF output from a container XML file.\n" + "\t--pdf-base64-no-crop <xml> <ppm> <out_dir> : PDF with the entire picture displayed over the text, the picture is loaded from a container XML file.\n\n" + "SVG output:\n" + "\t--svg <xml> <out_dir> : SVG output (works only with base 64 xml encoded.\n\n" + "Base 64 operations:\n" + "\t--to-base64 <xml> <ppm> <out_xml> : Produces a container XML file by converting cropped pictures into base 64 format.\n" + "\t--to-base64-no-crop <xml> <ppm> <out_xml> : Same as to-base64 but only the picture is converted in base 64.\n" + "\t--from-base64 <xml> <out_dir> : Decodes a XML container file to produce original image files.\n\n" + "For PDF/HTML/SVG output, Bourne shell scripts are provided to produce the outputs, just run sh *_generator.sh \n" + "Requirements:\n" + "PDF : fop >= 0.95\n" + "HTML : xsltproc\n" + "SVG : trunk version of fop\n"; if (argc > 4) { @@ -60,6 +67,7 @@ int main(int argc, char **argv) else if (argc > 3) { std::string pdfbase64 = "--pdf-base64"; + std::string svg = "--svg"; std::string pdfbase64nocrop = "--pdf-base64-no-crop"; std::string htmlbase64 = "--html-base64"; std::string from_base64 = "--from-base64"; @@ -69,6 +77,11 @@ int main(int argc, char **argv) XmlTransform xmlt(argv[2], QString::Null(), argv[3]); xmlt.createPDF(true, true); } + else if (svg.compare(argv[1]) == 0) + { + XmlTransform xmlt(argv[2], QString::Null(), argv[3]); + xmlt.createSVG(); + } else if (pdfbase64nocrop.compare(argv[1]) == 0) { XmlTransform xmlt(argv[2], QString::Null(), argv[3]); diff --git a/scribo/sandbox/arthur/xml_transform/templates/pdf/regions_svg.xsl b/scribo/sandbox/arthur/xml_transform/templates/pdf/regions_svg.xsl new file mode 100644 index 0000000..86b5f51 --- /dev/null +++ b/scribo/sandbox/arthur/xml_transform/templates/pdf/regions_svg.xsl @@ -0,0 +1,98 @@ +<?xml version="1.0"?> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:fo="http://www.w3.org/1999/XSL/Format" version="1.0"> + + <!-- FILE: regions.xsl + DESCRIPTION: Match all regions that are not text to display them --> + + <xsl:template match="pcGts/page/image_region| + pcGts/page/graphic_region| + pcGts/page/chart_region| + pcGts/page/table_region| + pcGts/page/separator_region"> + + <!-- ID of the region, used to display id.png --> + <xsl:variable name="data"> + <xsl:value-of select="container/data" /> + </xsl:variable> + + <!-- Regions coordinates --> + <xsl:variable name="y1"> + <xsl:for-each select="coords/point"> + <xsl:sort select="@y" order="ascending" data-type="number"/> + <xsl:if test="position() = 1"> + <xsl:value-of select="@y" /> + </xsl:if> + </xsl:for-each> + </xsl:variable> + + <xsl:variable name="x1"> + <xsl:for-each select="coords/point"> + <xsl:sort select="@x" order="ascending" data-type="number"/> + <xsl:if test="position() = 1"> + <xsl:value-of select="@x" /> + </xsl:if> + </xsl:for-each> + </xsl:variable> + + <xsl:variable name="y2"> + <xsl:for-each select="coords/point"> + <xsl:sort select="@y" order="descending" data-type="number"/> + <xsl:if test="position() = 1"> + <xsl:value-of select="@y" /> + </xsl:if> + </xsl:for-each> + </xsl:variable> + + <xsl:variable name="x2"> + <xsl:for-each select="coords/point"> + <xsl:sort select="@x" order="descending" data-type="number"/> + <xsl:if test="position() = 1"> + <xsl:value-of select="@x" /> + </xsl:if> + </xsl:for-each> + </xsl:variable> + <!-- END OF regions coordinates --> + + <fo:block-container> + + <fo:block> + <fo:instream-foreign-object> + <svg:svg xmlns:svg="http://www.w3.org/2000/svg" + xmlns:xlink="http://www.w3.org/1999/xlink" + Version="1.1"> + + <xsl:attribute name="viewBox"> + <xsl:value-of select="$x1" /> <xsl:value-of select="$y1" /> <xsl:value-of select="$x2" /> <xsl:value-of select="$y2" /> + </xsl:attribute> + + <svg:image position="absolute"> + + <xsl:attribute name="y"> + <xsl:value-of select="$y1" /> + </xsl:attribute> + + <xsl:attribute name="x"> + <xsl:value-of select="$x1" /> + </xsl:attribute> + + <xsl:attribute name="width"> + <xsl:value-of select="$x2 - $x1" /> + </xsl:attribute> + + <xsl:attribute name="height"> + <xsl:value-of select="$y2 - $y1" /> + </xsl:attribute> + + <xsl:attribute name="xlink:href">data:image/png;base64,<xsl:value-of select="$data" /></xsl:attribute> + </svg:image> + + </svg:svg> + + </fo:instream-foreign-object> + + </fo:block> + </fo:block-container> + + </xsl:template> + +</xsl:stylesheet> diff --git a/scribo/sandbox/arthur/xml_transform/templates/pdf/svg_generator.sh b/scribo/sandbox/arthur/xml_transform/templates/pdf/svg_generator.sh new file mode 100644 index 0000000..0d4907c --- /dev/null +++ b/scribo/sandbox/arthur/xml_transform/templates/pdf/svg_generator.sh @@ -0,0 +1,3 @@ +#!/bin/sh + +fop -xsl main.xsl -xml output.xml -svg output.svg \ No newline at end of file diff --git a/scribo/sandbox/arthur/xml_transform/xml_transform.cc b/scribo/sandbox/arthur/xml_transform/xml_transform.cc index ebfbed8..c40366a 100644 --- a/scribo/sandbox/arthur/xml_transform/xml_transform.cc +++ b/scribo/sandbox/arthur/xml_transform/xml_transform.cc @@ -117,6 +117,16 @@ void XmlTransform::createPDF (bool crop, bool base64) abort(); } +void XmlTransform::createSVG () +{ + if (loader_->xml_output(xml_file_, false, output_dir_)) + { + loader_->add_svg_templates(output_dir_); + } + else + abort(); +} + void XmlTransform::createHTML(bool base64) { if (loader_->xml_output(xml_file_, true, output_dir_)) diff --git a/scribo/sandbox/arthur/xml_transform/xml_transform.hh b/scribo/sandbox/arthur/xml_transform/xml_transform.hh index 172bddb..30d5c6c 100644 --- a/scribo/sandbox/arthur/xml_transform/xml_transform.hh +++ b/scribo/sandbox/arthur/xml_transform/xml_transform.hh @@ -42,6 +42,7 @@ class XmlTransform : public QObject void createHTML(bool base64); void createPDF(bool crop, bool base64); + void createSVG(); void toBase64(bool crop); void fromBase64(); -- 1.5.6.5