qswiki/parser.cpp

/* Copyright (c) 2018 Albert S.

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
*/
#include <regex>
#include <iostream>
#include <regex>
#include <vector>
#include <algorithm>
#include <iterator>
#include "parser.h"
#include "utils.h"
#include "htmllink.h"
std::vector<Headline> Parser::extractHeadlines(const std::string &content) const
{
	std::vector<Headline> result;

	std::string reg = R"(\[h(1|2|3)\](\[.*?\])*(.*?)(\[.*?\])*\[\/h\1\])";
	std::regex headerfinder(reg);
	auto begin = std::sregex_iterator(content.begin(), content.end(), headerfinder);
	auto end = std::sregex_iterator();

	for(auto it = begin; it != end; it++)
	{
		auto smatch = *it;
		Headline h;
		h.level = utils::toUInt(smatch.str(1));
		h.title = smatch.str(3);
		result.push_back(h);
	}
	return result;
}

std::vector<std::string> Parser::extractCategories(const std::string &content) const
{
	std::vector<std::string> result;
	std::string reg = R"(\[category\](.*?)\[/category\])";
	std::regex headerfinder(reg);
	auto begin = std::sregex_iterator(content.begin(), content.end(), headerfinder);
	auto end = std::sregex_iterator();

	for(auto it = begin; it != end; it++)
	{
		auto smatch = *it;
		result.emplace_back(smatch.str(1));
	}
	return result;
}

std::string Parser::extractFirstTag(std::string tagname, const std::string &content) const
{
	std::string cmd = "[" + tagname + "]";
	std::string cmdend = "[/" + tagname + "]";
	std::string_view view = content;
	size_t pos = 0;
	if((pos = view.find(cmd)) != std::string::npos)
	{
		view.remove_prefix(pos);
		view.remove_prefix(cmd.size());
		if((pos = view.find(cmdend)) != std::string::npos)
		{
			auto result = view.substr(0, pos);
			return std::string{result};
		}
	}
	return "";
}

std::string Parser::extractCommand(std::string cmdname, const std::string &content) const
{

	return extractFirstTag("cmd:" + cmdname, content);
}

std::vector<std::string> Parser::extractCommands(std::string cmdname, const std::string &content) const
{
	std::vector<std::string> result;

	std::string cmd = "[cmd:" + cmdname + "]";
	std::string cmdend = "[/cmd:" + cmdname + "]";

	std::string_view view = content;
	size_t pos = 0;
	while((pos = view.find(cmd)) != std::string::npos)
	{
		view.remove_prefix(pos);
		view.remove_prefix(cmd.size());
		if((pos = view.find(cmdend)) != std::string::npos)
		{
			result.emplace_back(view.substr(0, pos));
		}
	}
	return result;
}

std::string Parser::processLink(const PageDao &pageDao, UrlProvider &urlProvider, std::smatch &match) const
{
	std::string linktag = match.str(1);
	std::string inside = match.str(2);

	std::vector<std::string> splitted = utils::split(inside, '|');
	HtmlLink htmllink;
	if(splitted.size() == 2)
	{
		htmllink.innervalue = splitted[1];
		htmllink.href = splitted[0];
	}
	else
	{
		htmllink.innervalue = inside;
		htmllink.href = inside;
	}

	if(linktag == "wikilink")
	{
		if(pageDao.exists(htmllink.href))
		{
			htmllink.cssclass = "exists";
		}
		else
		{
			htmllink.cssclass = "notexists";
		}

		htmllink.href = urlProvider.page(htmllink.href);
	}

	return htmllink.render();
}

std::string Parser::processImage(std::smatch &match) const
{
	std::string tag = match.str(1);
	std::string inside = match.str(2);
	std::vector<std::string> splitted = utils::split(inside, '|');
	std::string width;
	std::string height;
	std::string src;
	if(splitted.size() == 3)
	{
		width = splitted[0];
		height = splitted[1];
		src = splitted[2];
	}
	else
	{
		src = splitted[0];
	}
	if(!width.empty() && !height.empty())
	{
		return "<img src=\"" + src + "\" width=\"" + width + "\" height=\"" + height + "\"/>";
	}
	return "<img src=\"" + src + "\"/>";
}

std::string Parser::parse(const PageDao &pagedao, UrlProvider &provider, const std::string &content,
						  const std::function<std::string(std::string_view, std::string_view)> &callback) const
{
	std::string result;
	// we don't care about commands, but we nevertheless replace them with empty strings
	std::regex tagfinder(
		R"(\[(b|i|u|s|li|p|br|ul|ol|code|blockquote|img|link|wikilink|h\d|cmd:visible|cmd:listed|cmd:feedlisted|cmd:rename|cmd:redirect|cmd:pagetitle|cmd:allowinclude|cmd:permissions|cmd:parentpage|content|category|dynamic:postlist|dynamic:includepage|dynamic:getvar|dynamic:setvar)*?\]((\s|\S)*?)\[/\1](\r\n)*)");

	const std::string justreplace[] = {"b", "i", "u", "p", "br", "ul", "li", "ol"};

	result = utils::regex_callback_replacer(
		tagfinder, content,
		[&](std::smatch &match)
		{
			std::string tag = match.str(1);
			std::string content = match.str(2);

			std::string newlines = match.str(4);
			if(newlines == "\r\n")
			{
				newlines = "<br>";
			}
			if(tag == "br")
			{
				return std::string("<br>");
			}
			if(tag != "code" && tag != "blockquote")
			{
				content = parse(pagedao, provider, content, callback);
			}
			/* [content] just helps extracting the actual content of a page, pretty much noop otherwise */
			if(tag == "content")
			{
				return parse(pagedao, provider, content, callback);
			}
			if(std::find(std::begin(justreplace), std::end(justreplace), tag) != std::end(justreplace))
			{
				if(tag == "p" || tag == "br")
				{
					newlines = "";
				}
				return "<" + tag + ">" + content + "</" + tag + ">" + newlines;
			}
			if(tag == "link" || tag == "wikilink")
			{
				return this->processLink(pagedao, provider,
										 match) +
					   newlines; // TODO: recreate this so we don't check inside the function stuff again
			}
			if(tag == "img")
			{
				return this->processImage(match);
			}
			if(tag[0] == 'h')
			{
				return "<" + tag + " id='" + utils::strreplace(content, " ", "") + "'>" + content + "</" + tag + ">";
			}
			if(tag == "code" || tag == "blockquote")
			{
				return "<pre><" + tag + ">" + utils::strreplace(content, "\r\n", "\n") + "</" + tag + "></pre>";
			}
			return callback(tag, content);
		});
	result = utils::strreplace(result, "\r\n", "<br>");
	return result;
}

std::string Parser::parseDynamics(const std::string &content,
								  const std::function<std::string(std::string_view, std::string_view)> &callback) const
{
	std::regex tagfinder(R"(\[(dynamic:\w+)*?\]((\s|\S)*?)\[/\1])");
	return utils::regex_callback_replacer(tagfinder, content,
										  [&](std::smatch &match) { return callback(match.str(1), match.str(2)); });
}