xcescommon.cpp

/*
    Copyright (C) 2010 Tomasz Śniatowski, Adam Radziszewski
    Part of the libcorpus2 project

    This program is free software; you can redistribute it and/or modify it
under the terms of the GNU Lesser 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 LICENSE.CORPUS2, LICENSE.POLIQARP, COPYING.LESSER and COPYING files for more details.
*/

#include <libcorpus2/io/xcescommon.h>
#include <boost/foreach.hpp>
#include <sstream>

namespace Corpus2 {

namespace {
	std::ostream& osi(std::ostream& os, int indent) {
		for (int i = 0; i < indent; ++i) {
			os << " ";
		}
		return os;
	}

	inline void lexeme_as_xces_xml(std::ostream& os, const Tagset& tagset,
			const Lexeme& l, bool output_disamb)
	{
		if (output_disamb && l.is_disamb()) {
			os << "<lex disamb=\"1\">";
		} else {
			os << "<lex>";
		}
		os << "<base>";
		encode_xml_entities_into(os, l.lemma_utf8());
		os << "</base>";
		os << "<ctag>";
		encode_xml_entities_into(os, tagset.tag_to_string(l.tag()));
		os << "</ctag>";
		os << "</lex>\n";
	}
}

void token_as_xces_xml_head(std::ostream& os,
		const Token& t, int indent, bool whitespace_info /* false */)
{
	if (t.wa() == PwrNlp::Whitespace::None) {
		osi(os, indent) << "<ns/>\n";
	}
	if (!whitespace_info) {
		osi(os, indent) << "<tok>\n";
	} else {
		osi(os, indent) << "<tok ws=\""
			<< PwrNlp::Whitespace::to_string(t.wa()) << "\">\n";
	}
}

void token_as_xces_xml_body(std::ostream& os, const Tagset& tagset,
		const Token& t, int indent, bool output_disamb /* = false */,
		bool sort /* = false */)
{
	osi(os, indent) << "<orth>";
	encode_xml_entities_into(os, t.orth_utf8());
	os << "</orth>\n";
	if (!sort) {