backend/src/generators/rss.cpp

/*  This file is part of FediBlock-backend.
 *  Copyright © 2020 tastytea <tastytea@tastytea.de>
 *
 *  This program is free software: you can redistribute it and/or modify
 *  it under the terms of the GNU Affero General Public License as published by
 *  the Free Software Foundation, version 3.
 *
 *  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 Affero General Public License for more details.
 *
 *  You should have received a copy of the GNU Affero General Public License
 *  along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#include "rss.hpp"
#include "cgi.hpp"
#include "files.hpp"
#include "git.hpp"
#include "time.hpp"

#include <fmt/format.h>
#include <pugixml.hpp>

#include <algorithm>
#include <chrono>
#include <cstdint>
#include <cstdlib>
#include <exception>
#include <iostream>
#include <ostream>
#include <stdexcept>
#include <string>
#include <string_view>
#include <vector>

namespace FediBlock::rss
{

using fmt::format;
using std::find;
using std::getenv;
using std::none_of;
using std::ostream;
using std::string;
using std::string_view;
using std::uint8_t;
using std::chrono::system_clock;

void write_rss(ostream &out, const vector<entry_type> &entries,
               const vector<string> &tags)
{
    string selfurl;
    char *env{getenv("HTTPS")};
    if (env == nullptr || string(env) != "on")
    {
        selfurl = "http://";
    }
    else
    {
        selfurl = "https://";
    }
    env = getenv("SERVER_NAME");
    if (env != nullptr)
    {
        selfurl += env;
    }
    const string baseurl{selfurl + "/blocklist/"};
    env = getenv("REQUEST_URI");
    if (env != nullptr)
    {
        selfurl += env;
    }

    constexpr string_view rss_time_format{"%a, %d %b %Y %T %z"};

    pugi::xml_document doc;
    auto rss{doc.append_child("rss")};
    rss.append_attribute("version") = "2.0";
    rss.append_attribute("xmlns:atom") = "http://www.w3.org/2005/Atom";

    auto channel{rss.append_child("channel")};
    string tmp_title{"FediBlock: "};
    string tmp_description{"The newest FediBlock entries. "};
    if (tags.empty())
    {
        tmp_title += "All tags";
        tmp_description += "All tags";
    }
    else
    {
        tmp_description += "Tags: ";
    }
    for (const auto &tag : tags)
    {
        if (tag != *tags.begin())
        {
            tmp_title += ", ";
            tmp_description += ", ";
        }
        tmp_title += tag;
        tmp_description += tag;
    }
    tmp_description += ".";
    auto title{channel.append_child("title")};
    title.text() = tmp_title.c_str();
    auto link{channel.append_child("link")};
    link.text() = baseurl.c_str();
    auto description{channel.append_child("description")};
    description.text() = tmp_description.c_str();
    auto lastBuildDate{channel.append_child("lastBuildDate")};
    lastBuildDate.text() = time::to_string(system_clock::now(), rss_time_format)
                               .c_str();

    for (const auto &entry : entries)
    {
        // If tags are specified and none of them match, go to the next entry.
        if (!tags.empty())
        {
            // clang-format off
            if (none_of(entry.tags.begin(), entry.tags.end(),
                        [&tags](const auto &tag)
                        {
                            return find(tags.begin(), tags.end(), tag)
                                   != tags.end();
                        }))
            {
                continue;
            }
            // clang-format on
        }

        auto item{channel.append_child("item")};
        auto item_title{item.append_child("title")};
        item_title.text() = entry.instance.c_str();
        auto item_guid{item.append_child("guid")};
        item_guid.append_attribute("isPermaLink") = "false";
        item_guid.text() = format("FediBlock: {:s} {:s}", entry.report_time,
                                  entry.instance)
                               .c_str();
        auto item_pubDate{item.append_child("pubDate")};
        item_pubDate.text() = time::to_string(entry.report_time,
                                              rss_time_format)
                                  .c_str();
        auto item_link{item.append_child("link")};
        item_link.text() = format("{:s}#{:s}", baseurl, entry.instance).c_str();

        string tmp_item_description{format("<p>{:s}</p>"
                                           "<p><strong>Tags:</strong> ",
                                           cgi::text2html(entry.description))};
        for (const auto &tag : entry.tags)
        {
            if (tag != *entry.tags.begin())
            {
                tmp_item_description += ", ";
            }
            tmp_item_description += tag;
        }
        tmp_item_description += "</p><strong>Receipts:</strong><ul>";
        for (const auto &receipt : entry.receipts)
        {
            tmp_item_description += format(
                "<li><a href=\"{0:s}\">{0:s}</a></li>", receipt);
        }
        tmp_item_description += "</ul>";
        if (!entry.screenshot_filepath.empty())
        {
            tmp_item_description += "<p><strong>Screenshot:</strong><br>";
            tmp_item_description += format(
                "<a href=\"{0:s}{1:s}\"><img "
                "src=\"{0:s}{1:s}\" height=\"200\"></a></p>\n",
                baseurl, entry.screenshot_filepath);
        }
        auto item_description{item.append_child("description")};
        item_description.append_child(pugi::node_cdata)
            .set_value(tmp_item_description.c_str());
    }

    doc.print(out);
}

} // namespace FediBlock::rss

using std::cerr;
using std::cout;
using std::exception;
using std::runtime_error;
using std::vector;

using namespace FediBlock;
using namespace FediBlock::rss;

int main(int argc, char *argv[])
{
    const vector<string_view> args(argv, argv + argc);

    git::init(true);

    bool remove_lockfile{false};
    try
    {
        try
        {
            git::update_cached_repo();
            remove_lockfile = true;
        }
        catch (const runtime_error &)
        {
            // Ignore, use old version of repo.
        }
        const auto entries{files::read_json_files(true)};
        cout << "Content-Type: application/rss+xml\r\n\r\n";
        write_rss(cout, entries, cgi::get_tags());
    }
    catch (const exception &e)
    {
        cerr << "Error: " << e.what() << '\n';
    }

    git::cleanup(remove_lockfile);

    return 0;
}