klammertext/sks/document/document_class.cpp

#include "util.h"
#include "machine.h"
#include "error.h"
#include "kutil.h"
#include "html_util.h"
#include "latex_util.h"
#include "locator.h"
// #include "state.h"
#include "document_class.h"
#include "show.h"
#include "log.h"
#include "file.h"

bool strbool(const std::string& s, const Locator& loc)
{
    std::vector<std::string> values = {"false", "False", "0", "true", "True", "1"};
    if (is_not_in(s, values)) {
        std::stringstream ss {};
        ss << "The value \"" << s << "\" is not a Boolean value. Possible values are:\n  "
           << join(values, ", ");
        throw Argument_error(ss.str(), loc);
    }
    bool result = (find(values.begin(), values.end(), s) - values.begin()) > 2;
    return result;
}


Document_class::Document_class(Machine& machine) : Klammer_base(machine)
{
    (void)K::log(3);
    // show("document in main SKS");
    m_machine = machine;
    sloc = get("K_loc");
    // The klammer's own position, so an argument error points at the
    // @document application rather than at document_class.cpp: a
    // default-constructed Locator captures the C++ source location.
    loc = Locator::from_string(sloc);
    m_title = get("title");
    m_subtitle = get("subtitle");
    m_page_title = get("page_title");
    m_author = get("author");
    m_date = get("date");

    // m_nav = strbool(get("nav"), loc);
    // m_toc = strbool(get("toc"), loc);

    m_structure = docstruct(get("structure"));

    m_date = get("date");
    m_version = get("version");
    m_logo = get("logo");

    m_text = get("text");
    // Filename lists: standalone-"/" separation, existence rescue for
    // spaces, ~ expansion (resolve_filename_list in mac/file.cpp); the
    // existence checks resolve relative names against the input directory,
    // as parse_input_filename() will.
    // Filename-bearing values arrive ESCAPED for the target (the state
    // stores escaped values so they flow correctly into output); a filename
    // is programmatic use, so decode the markers first -- the C++ mirror of
    // the Python-side unescape_ktesc() rule.  Found 2026-08-22: under tex,
    // ":files my_chapter" searched for "myKTESC005fKTESCchapter".
    m_files = resolve_filename_list(ktesc_resolve(get("files")), get("K_input_dir"));

    m_css_text = get("css_text");
    m_css_filenames = resolve_filename_list(ktesc_resolve(get("css_files")), get("K_input_dir"));
    m_include_sks_css = strbool(get("include_sks_css"), loc);
    frame_background_color = get("frame_background_color");
    frame_text_color = get("frame_text_color");
    nav_background_color = get("nav_background_color");
    nav_text_color = get("nav_text_color");

    js_text = get("js_text");
    m_js_filenames = resolve_filename_list(ktesc_resolve(get("js_files")), get("K_input_dir"));
    m_include_sks_js = strbool(get("include_sks_js"), loc);

    // font_dirs = word_split(get("font_dirs"));

    auto strip_quotes = [](std::string s) {
        if (s.size() >= 2 && s.front() == '"' && s.back() == '"')
            s = s.substr(1, s.size() - 2);
        return s;
    };
    m_serif_typeface = strip_quotes(get("serif_typeface"));
    m_sans_typeface = strip_quotes(get("sans_typeface"));
    m_mono_typeface = strip_quotes(get("mono_typeface"));
    m_text_scale = stof(get("text_scale"));

    if (!m_serif_typeface.empty())
        m_resolved_serif = resolve_font(m_serif_typeface, loc);
    if (!m_sans_typeface.empty())
        m_resolved_sans = resolve_font(m_sans_typeface, loc);
    if (!m_mono_typeface.empty())
        m_resolved_mono = resolve_font(m_mono_typeface, loc);
    paper_size = get("paper_size");
    landscape = strbool(get("landscape"), loc);
    leading = stof(get("leading"));
    point_size = stoi(get("point_size"));
    ragged_right = strbool(get("ragged_right"), loc);
    cover = get("cover");
    prolog = get("prolog");
    m_two_column = strbool(get("two_column"), loc);

    m_copyright = get("copyright");
    m_bottom = get("bottom");

    create_output_directory = strbool(get("create_output_directory"), loc);
    output_directory_name = get("output_directory_name");

    resources_in_file = strbool(get("resources_in_file"), loc);

    //use_pages_dir = strbool(get("use_pages_dir"), loc);

    // m_toc_only = strbool(get("K_toc_only"), loc);
    m_kt_root_filename = get("K_input_filename");

    m_no_cache = !strbool(get("cache"), loc);

    write_files = !strbool(get("K_stdout_only"), loc);
    m_input_dir = get("K_input_dir");

    if (m_text.size() == 0 and m_files.size() == 0) {
        throw Argument_error(
            "Neither the :text or :files options have values"); //,
        //get("K_loc"));
    }
    /*
    for (std::string file : m_files) {
        sources.push_back(string_from_file(find_kt_file(file)));
    }
    */
    // std::cout << "IN DOCUMENT CLASS:\n" << m_state << "\n";
}


void Document_class::save_string_input_as_file()
{
    if (!m_text.empty()) {
        std::string input_text_filename = m_cache_dir + "/_text.kt";
        // msg() << "Write string input to cache file: "
        //      << input_text_filename << "\n";
        string_to_file(input_text_filename, m_text);
        m_files.insert(m_files.begin(), input_text_filename);
    }
}


fs::path parse_input_filename(const std::string& s, const std::string& input_dir)
{
    // The two-class rule (2026-08-22), replacing a three-stage search whose
    // second stage could quietly shadow a file beside the document:
    //
    //   * a BARE WORD -- no directory separator, no extension -- is the kt/
    //     SHORTCUT: ":files X" MEANS kt/X.kt in the root file's directory,
    //     and nothing else.  Missing is an immediate error whose message
    //     teaches the convention, not a fallback.  The kt/ directory is the
    //     conventional home for a document's input files, and putting the
    //     meaning entirely in the name lets several root documents share it.
    //
    //   * anything else is a real PATHNAME, absolute or resolved against the
    //     input file's directory (K_input_dir), so a document renders
    //     identically wherever ktext is run from.
    //
    // Which file a name landed on is a DERIVED value, so "-v 1" reports it.
    fs::path p(s);
    bool bare = s.find('/') == std::string::npos && p.extension().empty();
    if (bare) {
        fs::path in_kt = fs::path(input_dir) / "kt" / (s + ".kt");
        if (!file_exists(in_kt.string())) {
            throw Argument_error(
                "The \":files\" name \"" + s + "\" is a bare word, which by "
                "convention means the file kt/" + s + ".kt in the root "
                "document's directory:\n"
                "  " + in_kt.string() + "\n"
                "That file does not exist. Create it there, or write a real "
                "pathname (a name with a directory or the \".kt\" extension) "
                "to use a file elsewhere.",
                Locator::none());
        }
        // The resolved path itself shows kt/ -- no label needed.
        (void)K::log(1, "Input file \"" + s + "\": " + in_kt.string());
        return in_kt;
    }
    if (p.extension() != ".kt") {
        p += ".kt";
    }
    if (p.is_absolute()) {
        return p;
    }
    fs::path in_input_dir = fs::path(input_dir) / p;
    (void)K::log(1, "Input file \"" + s + "\": " + in_input_dir.string());
    return in_input_dir;
}

void Document_class::write(const std::string& filename, const std::string& contents)
{
    write_file(filename, contents, write_files);
}


void write_file(const std::string& filename, const std::string& contents, bool write_p)
{
    if (write_p) {
        string_to_file(filename, contents);
    } else {
        // Not writing: name the file that would have been written.  A
        // derived value, so "-v 1" -- and never on stdout, which carries
        // the document itself.
        (void)K::log(1, "Output filename:", filename);
    }
}


// ---------------------------------------------------------------------
// Typeface markers (@typeface; see the marker note in sks/font/font.py)
//
// Hand-rolled scanning, no std::regex: these run over the whole assembled
// document and libstdc++'s regex executor recurses per character (the
// documented SIGSEGV hazard).
// ---------------------------------------------------------------------

namespace {

const std::string typeface_tag { "__TYPEFACE__" };

// The next marker at or after `from`.  Returns false when there is none.
// A marker is __TYPEFACE__<name>__<scale>__ : the two fields are taken up
// to the next "__", so neither may contain one (a typeface name with a
// double underscore is not a thing, and the scale is a number).
bool next_typeface_marker(const std::string& text, size_t from,
                          size_t& start, size_t& end,
                          std::string& name, std::string& scale)
{
    start = text.find(typeface_tag, from);
    if (start == std::string::npos) return false;
    size_t name_at = start + typeface_tag.size();
    size_t name_end = text.find("__", name_at);
    if (name_end == std::string::npos) return false;
    size_t scale_at = name_end + 2;
    size_t scale_end = text.find("__", scale_at);
    if (scale_end == std::string::npos) return false;
    name = text.substr(name_at, name_end - name_at);
    scale = text.substr(scale_at, scale_end - scale_at);
    end = scale_end + 2;
    return true;
}

// The fontspec command name for the nth distinct (typeface, scale) pair.
// A TeX command name may hold only letters, and a typeface name may hold
// anything -- so the pairs are NUMBERED rather than transliterated, and
// the number is turned into letters.  Nothing outside this file needs to
// know the rule: the klammer leaves a marker and this replaces it, so
// there is no second implementation to keep in step.
std::string typeface_command(size_t index)
{
    std::string suffix {};
    do {
        suffix = char('a' + (index % 26)) + suffix;
        index /= 26;
    } while (index > 0);
    return "\\ktface" + suffix;
}

} // namespace

void Document_class::collect_typefaces(const std::string& text)
{
    size_t pos = 0, start = 0, end = 0;
    std::string name {}, scale {};
    while (next_typeface_marker(text, pos, start, end, name, scale)) {
        std::pair<std::string, std::string> entry { name, scale };
        if (std::find(m_extra_typefaces.begin(), m_extra_typefaces.end(), entry)
            == m_extra_typefaces.end()) {
            m_extra_typefaces.push_back(entry);
            // Resolve ONCE per distinct typeface: resolve_font() throws a
            // located error naming the available typefaces if the store
            // does not have it, which is the whole error path for a
            // misspelled or uninstalled typeface.
            // Compared by directory name: a @typeface may write either
            // the family name or the store's directory name, and both
            // resolve to the same directory.
            bool seen = false;
            for (const auto& rf : m_resolved_extra)
                if (rf.dir_name == name_to_dirname(name)) seen = true;
            if (!seen) {
                // What a @typeface klammer asked for, and what the store
                // resolved it to: a decision the user cannot read off
                // their own input, so "-v 1".
                Resolved_font rf = resolve_font(name, loc);
                (void)K::log(1, "Typeface \"" + name + "\" resolved to:",
                             rf.font_dir);
                m_resolved_extra.push_back(rf);
            }
        }
        pos = end;
    }
}

const Resolved_font& Document_class::resolved_typeface(const std::string& name) const
{
    for (const auto& rf : m_resolved_extra)
        if (rf.dir_name == name_to_dirname(name)) return rf;
    // collect_typefaces() resolves every marker before this is asked.
    throw Internal_error("Typeface \"" + name + "\" was not resolved");
}

std::string Document_class::resolve_typeface_families(const std::string& text)
{
    std::string result {};
    size_t pos = 0, start = 0, end = 0;
    std::string name {}, scale {};
    while (next_typeface_marker(text, pos, start, end, name, scale)) {
        result += text.substr(pos, start - pos);
        result += resolved_typeface(name).family_name;
        pos = end;
    }
    result += text.substr(pos);
    return result;
}

std::string Document_class::resolve_typeface_markers(const std::string& text)
{
    std::string result {};
    size_t pos = 0, start = 0, end = 0;
    std::string name {}, scale {};
    while (next_typeface_marker(text, pos, start, end, name, scale)) {
        result += text.substr(pos, start - pos);
        auto entry = std::make_pair(name, scale);
        auto it = std::find(m_extra_typefaces.begin(), m_extra_typefaces.end(), entry);
        if (it != m_extra_typefaces.end())
            result += typeface_command(it - m_extra_typefaces.begin());
        pos = end;
    }
    result += text.substr(pos);
    return result;
}

std::string Document_class::typeface_preamble()
{
    std::stringstream ss {};
    for (size_t i = 0; i < m_extra_typefaces.size(); i++) {
        const auto& [name, scale] = m_extra_typefaces[i];
        // Compared by directory name, as collect_typefaces() compares: a
        // @typeface may write the family name or the store's directory
        // name, and family_name holds what the css declares (2026-09-12),
        // so a name-for-name comparison missed the directory spelling and
        // left \ktface<n> undefined in the .tex (found 2026-09-17).
        const Resolved_font* rf = nullptr;
        for (const auto& f : m_resolved_extra)
            if (f.dir_name == name_to_dirname(name)) rf = &f;
        if (!rf) continue;
        // \newfontfamily declares a switch command, unlike \setmainfont,
        // which changes the document's font permanently.
        ss << latex::font_command("newfontfamily" + typeface_command(i),
                                  *rf, stof(scale));
    }
    return ss.str();
}