summaryrefslogtreecommitdiff
path: root/src/plugins/html
diff options
context:
space:
mode:
Diffstat (limited to 'src/plugins/html')
-rw-r--r--src/plugins/html/DemoOutput.cpp187
-rw-r--r--src/plugins/html/DemoOutput.hpp85
2 files changed, 272 insertions, 0 deletions
diff --git a/src/plugins/html/DemoOutput.cpp b/src/plugins/html/DemoOutput.cpp
new file mode 100644
index 0000000..6b9b3a4
--- /dev/null
+++ b/src/plugins/html/DemoOutput.cpp
@@ -0,0 +1,187 @@
+/*
+ Ousía
+ Copyright (C) 2014 Benjamin Paaßen, Andreas Stöckel
+
+ This program 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, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program 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 this program. If not, see <http://www.gnu.org/licenses/>.
+*/
+
+#include <core/common/Exceptions.hpp>
+#include <core/common/Rtti.hpp>
+
+#include "DemoOutput.hpp"
+
+namespace ousia {
+namespace html {
+
+void DemoHTMLTransformer::writeHTML(Handle<model::Document> doc,
+ std::ostream &out)
+{
+ // write preamble
+ out << "<?xml version=\" 1.0 \"?>\n";
+ out << "<html>\n";
+ out << "\t<head>\n";
+ out << "\t\t<title>Test HTML Output for" << doc->getName() << "</title>\n";
+ out << "\t</head>\n";
+ out << "\t<body>\n";
+
+ // look for the book root node.
+ Rooted<model::StructuredEntity> root = doc->getRoot();
+ if (root->getDescriptor()->getName() != "book") {
+ throw OusiaException("The given documents root is no book node!");
+ }
+ // write it to HTML.
+ writeSection(root, out);
+ // write end
+ out << "\t</body>\n";
+ out << "</html>\n";
+}
+
+/**
+ * This is just for easier internal handling.
+ */
+enum class SectionType { BOOK, CHAPTER, SECTION, SUBSECTION, NONE };
+
+SectionType getSectionType(const std::string &name)
+{
+ if (name == "book") {
+ return SectionType::BOOK;
+ } else if (name == "chapter") {
+ return SectionType::CHAPTER;
+ } else if (name == "section") {
+ return SectionType::SECTION;
+ } else if (name == "subsection") {
+ return SectionType::SUBSECTION;
+ } else {
+ return SectionType::NONE;
+ }
+}
+
+void DemoHTMLTransformer::writeSection(Handle<model::StructuredEntity> sec,
+ std::ostream &out)
+{
+ // check the section type.
+ SectionType type = getSectionType(sec->getDescriptor()->getName());
+ if (type == SectionType::NONE) {
+ // if the input node is no section, we ignore it.
+ return;
+ }
+ // get the fields.
+ std::vector<NodeVector<model::StructuredEntity>> &fields = sec->getFields();
+ // check if we have a heading.
+ if (fields.size() > 1 && fields[1].size() > 0) {
+ out << "\t\t";
+ switch (type) {
+ case SectionType::BOOK:
+ out << "<h1>";
+ break;
+ case SectionType::CHAPTER:
+ out << "<h2>";
+ break;
+ case SectionType::SECTION:
+ out << "<h3>";
+ break;
+ case SectionType::SUBSECTION:
+ out << "<h4>";
+ break;
+ case SectionType::NONE:
+ // this can not happen;
+ break;
+ }
+ // the second field marks the heading. So let's write it.
+ writeParagraph(fields[1][0], out, false);
+ // close the heading tag.
+ switch (type) {
+ case SectionType::BOOK:
+ out << "</h1>";
+ break;
+ case SectionType::CHAPTER:
+ out << "</h2>";
+ break;
+ case SectionType::SECTION:
+ out << "</h3>";
+ break;
+ case SectionType::SUBSECTION:
+ out << "</h4>";
+ break;
+ case SectionType::NONE:
+ // this can not happen;
+ break;
+ }
+ out << "\n";
+ }
+
+ // then write the section content recursively.
+ for (auto &n : fields[0]) {
+ /*
+ * Strictly speaking this is the wrong mechanism, because we would have
+ * to make an "isa" call here because we can not rely on our knowledge
+ * that paragraphs can only be paragraphs or lists. There would have
+ * to be a listener structure of transformations that check if they can
+ * transform this specific node.
+ */
+ std::string childDescriptorName = n->getDescriptor()->getName();
+ if (childDescriptorName == "paragraph") {
+ writeParagraph(n, out);
+ // TODO: Implement
+ // } else if(childDescriptorName == "ul"){
+ // writeList(n, out);
+ } else {
+ writeSection(n, out);
+ }
+ }
+}
+
+void DemoHTMLTransformer::writeParagraph(Handle<model::StructuredEntity> par,
+ std::ostream &out, bool writePTags)
+{
+ // validate descriptor.
+ if (par->getDescriptor()->getName() != "paragraph") {
+ throw OusiaException("Expected paragraph!");
+ }
+ // get the fields.
+ std::vector<NodeVector<model::StructuredEntity>> &fields = par->getFields();
+ // write heading if its there.
+ // check if we have a heading.
+ if (fields.size() > 1 && fields[1].size() > 0) {
+ // start the heading tag
+ out << "\t\t<h5>";
+ // the second field marks the heading. So let's write it.
+ writeParagraph(fields[1][0], out, false);
+ // close the heading tag.
+ out << "</h5>\n";
+ }
+ // write start tag
+ if (writePTags) {
+ out << "\t\t<p>";
+ }
+ // write content
+ // TODO: What about emphasis?
+ for (auto &text : fields[0]) {
+ if (text->getDescriptor()->getName() != "text") {
+ throw OusiaException("Expected text!");
+ }
+ Handle<model::DocumentPrimitive> primitive =
+ text->getFields()[0][0].cast<model::DocumentPrimitive>();
+ if (primitive == nullptr) {
+ throw OusiaException("Text field is not primitive!");
+ }
+ out << primitive->getContent().asString();
+ }
+ // write end tag
+ if (writePTags) {
+ out << "</p>\n";
+ }
+}
+}
+}
diff --git a/src/plugins/html/DemoOutput.hpp b/src/plugins/html/DemoOutput.hpp
new file mode 100644
index 0000000..ca9bcd2
--- /dev/null
+++ b/src/plugins/html/DemoOutput.hpp
@@ -0,0 +1,85 @@
+/*
+ Ousía
+ Copyright (C) 2014 Benjamin Paaßen, Andreas Stöckel
+
+ This program 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, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program 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 this program. If not, see <http://www.gnu.org/licenses/>.
+*/
+
+/**
+ * @file DemoOutput.hpp
+ *
+ * This implements a Demo HTML output for the following domains:
+ * * book
+ * * headings
+ * * emphasis
+ * * lists
+ *
+ * @author Benjamin Paassen - bpaassen@techfak.uni-bielefeld.de
+ */
+#ifndef _OUSIA_HTML_DEMO_OUTPUT_HPP_
+#define _OUSIA_HTML_DEMO_OUTPUT_HPP_
+
+#include <ostream>
+
+#include <core/model/Document.hpp>
+
+namespace ousia {
+namespace html {
+
+class DemoHTMLTransformer {
+private:
+ /**
+ * This method is to be called recursively to write a chapter, section or
+ * subsection to HTML.
+ */
+ void writeSection(Handle<model::StructuredEntity> sec, std::ostream& out);
+ /**
+ * This method is to be called recursively to write a paragraph to HTML.
+ */
+ void writeParagraph(Handle<model::StructuredEntity> par, std::ostream& out,
+ bool writePTags = true);
+ /**
+ * This method is to be called recursively to write a list to HTML.
+ * TODO: Implement
+ */
+// void writeList(Handle<StructuredEntity> sec, std::ostream& out,
+// int tabdepth);
+
+ //TODO: Implement emphasis.
+
+public:
+ /**
+ * This writes a HTML representation of the given document to the given
+ * output stream. Note that this method lacks the generality of our Ousia
+ * approach with respect to two important points:
+ * 1.) It hardcodes the dependency to a certain set of domains in the C++
+ * code.
+ * 2.) It does not use the proposed pipeline of first copying the document
+ * graph, then attaching style attributes and then transforming it to a
+ * specific output format but does all of these steps at once.
+ * 3.) It does not use different transformers for the different domains but
+ * does all transformations at once.
+ * Therefore this is not an adequate model of our algorithms but only a
+ * Demo.
+ *
+ * @param doc is a Document using concepts of the book, headings, emphasis
+ * and lists domains but no other.
+ * @param out is the output stream the data shall be written to.
+ */
+ void writeHTML(Handle<model::Document> doc, std::ostream& out);
+};
+}
+}
+
+#endif
generated by cgit v1.2.3 (git 2.39.1) at 2025-05-01 00:17:40 +0000