klammertext/mac/command.cpp

#ifdef _WIN32
#define WIN32_LEAN_AND_MEAN
#define NOMINMAX
#include <windows.h>
#include <fcntl.h>
#include <io.h>
#endif
#include <cstdlib>
#include <tuple>

#include "argv.h"
#include "file.h"
#include "log.h"
#include "machine.h"

using namespace std::string_literals;

fs::path construct_command_pathname(char* command)
{
    // The pseudo source file for command-line string input (-s, kdiag's
    // input): a file IN THE CWD named after the command, so that a relative
    // @read in string input resolves against the directory the user ran the
    // command from -- the string-input analog of "a document's relative
    // names resolve against the document".  The basename matters: the
    // former "<cwd>/<argv[0]>" string concatenation anchored resolution at
    // the BINARY's directory whenever argv[0] was absolute
    // (/usr/local/bin/ktext, a wrapper script), so every relative @read in
    // -s input searched bin/ instead of the cwd.
    return fs::current_path() / fs::path(command).filename();
}

void set_command_identity(const std::string& name, const std::string& pathname)
{
    command_name = name;
    command_pathname = pathname;
}

void set_verbose_level(int argc, char* argv[])
{
#ifdef _WIN32
    // Klammertext writes LF on every system: a document a Windows user pipes
    // or redirects must not gain CR, and the suites read the streams byte for
    // byte. The C runtime's text mode would append it to every line.
    _setmode(_fileno(stdout), _O_BINARY);
    _setmode(_fileno(stderr), _O_BINARY);
    // A console decodes what a program writes in the CONSOLE's output code
    // page, which on a localized Windows is an OEM page (850 on a German one)
    // and never UTF-8, whatever the process's own code page (the manifest
    // makes that UTF-8). The commands write UTF-8 -- kdesc --katoms's
    // ⟨name⟩, an error report's ⟨katom⟩ -- so a console showed three cp850
    // characters per symbol while a file or a pipe received the right bytes
    // (which is why no suite saw it; Andy did, 2026-09-25). Switch the
    // console to UTF-8 while a command runs, when a stream is a console, and
    // put it back at exit: the page belongs to the console, not the process,
    // and would outlive it.
    static UINT console_output_cp = 0;
    static UINT console_output_cp_now = 0;
    if (_isatty(_fileno(stdout)) || _isatty(_fileno(stderr))) {
        console_output_cp = GetConsoleOutputCP();
        if (console_output_cp != 0 && console_output_cp != CP_UTF8) {
            SetConsoleOutputCP(CP_UTF8);
            console_output_cp_now = GetConsoleOutputCP();
            std::atexit([] { SetConsoleOutputCP(console_output_cp); });
        }
    }
#endif
    //command_name = absolute_pathname(argv[0]);
    command_name = fs::path(argv[0]).generic_string();
    command_pathname = construct_command_pathname(argv[0]).generic_string();
    //std::cout << "set_verbose_level: " << command_pathname << "\n";

    Argv args {};
    args.opt("v", "'verbosity'", "level", "0", "'verbosity'");
    args.parse(argc, argv, false);
    verbose_level = args.as_verbosity("v");
#ifdef _WIN32
    if (console_output_cp != 0 && console_output_cp != CP_UTF8) {
        K::log(1, "Console output code page set to UTF-8 for this run (was "
                  + std::to_string(console_output_cp) + ", now "
                  + std::to_string(console_output_cp_now) + ")");
    }
#endif
}

bool show_usage(int argc, char* argv[])
{
    return argc == 1 || (argc == 3 && std::string(argv[1]) == "-v"s);
}

std::string construct_output_filename(
    const std::string& output_dir, const std::string& output_basename, const std::string& target)
{
    std::string result {};
    if (target == "html") {
        result = output_dir + "/" + output_basename + "/index.html";
    } else {
        result = output_dir + "/" + output_basename + "." + target;
    }
    return result;
}

bool only_definitions(std::vector<std::string> filenames)
{
    if (filenames.empty()) return false;
    bool result = true;
    for (auto f : filenames) {
        if (fs::path(f).extension() != ".k") {
            result = false;
            break;
        }
    }
    return result;
}

std::tuple<std::string, std::string, std::string, std::string, bool, bool>
parse_args(
    const std::vector<std::string>& input_filenames, std::string target, std::string output_basename, bool display_only)
{
    // output_dir
    std::string output_target = target;
    std::string output_dir = "";
    std::string ext = extension(output_basename);
    // std::string output_filename = "";
    bool write_files = true;
    if (target.empty() && output_basename.empty()) {
        output_target = "any";
    }
    if (output_basename == "-") {
        write_files = false;
    } else if (!output_basename.empty()) {
        output_dir = file_directory(output_basename);
        output_basename = file_basename(output_basename);
    } else if (!input_filenames.empty()) {
        // No -o: output goes next to the input file ("" -- an input with no
        // directory component -- resolves to cwd below).
        output_dir = file_directory(input_filenames[0]);
        output_basename = file_basename(input_filenames[0]);
    }
    output_dir = absolute_pathname(output_dir);
        
    if (output_target.empty()) {
        target = ext;
    }

    std::string output_filename =
        construct_output_filename(output_dir, output_basename, target);

    if (output_basename.empty() && input_filenames.empty()) {
        display_only = true;
    } else if (only_definitions(input_filenames)) {
        display_only = true;
    }

    std::vector<std::pair<std::string,std::string>> vars = {
        {"Output target", output_target},
        {"Output directory", output_dir},
        {"Output basename", output_basename},
        {"Output filename", output_filename},
        {"Write file", write_files ? "true" : "false"}};

    int verbose = 1;
    for (auto [label, value] : vars) {
        if (label == "Output filename") {
            //verbose = 2;
        }
        (void)K::log(int(verbose), label + ":", value);
    }
    return {output_target, output_dir, output_basename, output_filename, write_files, display_only};
}


void set_command_state(
    Machine& machine, const std::string& frame_name, const std::string& target,
    const std::vector<std::string>& input_filenames, const std::string& output_dir,
    const std::string& output_basename, bool display_only)
{
    State& S = machine.m_state;
    S.open_frame(frame_name);
    S.set("K_target", target);
    S.set("K_output_dir", output_dir);
    S.set("K_output_basename", output_basename);
    S.set("K_stdout_only", display_only ? "true" : "false");
    // The list form uses the standalone-"/" separator (filenames may
    // contain spaces); K_input_filename is the single root input file.
    S.set("K_input_filenames", join(input_filenames, " / "));
    S.set("K_input_filename", input_filenames.empty() ? "" : input_filenames[0]);
    S.set("K_verbose_level", std::to_string(verbose_level));
    if (!input_filenames.empty()) {
        S.set("K_input_dir", absolute_pathname(file_directory(input_filenames[0])));
    } else {
        S.set("K_input_dir", fs::current_path().generic_string());
    }
}

void load_klammersets(Machine& machine, const strings_t& symbols)
{
    // "none" is the absence of a klammerset, not the name of one, so it says
    // nothing about what should be loaded ALONGSIDE it: written first it would
    // silently discard the rest of the list, written last it would be looked up
    // as a symbol and reported missing.  Both readings are wrong, so neither is
    // guessed at -- "none" is accepted only alone.
    if (is_in("none"s, symbols) && symbols.size() > 1) {
        throw Klammerset_error(
            "The klammerset \"none\" cannot be combined with other klammersets: "
            "it means that none is loaded. Give \"none\" alone, or name only the "
            "klammersets to load.",
            Locator::none());
    }
    if (symbols.empty()) {
        // Which klammerset was loaded, and from where, is a DERIVED value: the
        // user wrote no --klammersets at all and got the SKS from
        // $KLAMMERTEXT_HOME.  Only the symbol branch below reported its
        // resolution, so the commonest case -- the default -- said nothing.
        std::string sks = machine.m_state.value("KLAMMERTEXT_HOME") + "/sks/sks.k";
        (void)K::log(1, "Klammerset (default): " + sks);
        machine.read(fs::path(sks));
    } else if (symbols[0] == "none") {
        (void)K::log(1, "Klammersets: none");
    } else {
        // The whitespace-delimited words in symbols must be klammerset symbols:
        for (const auto& symbol : symbols) {
            // Same guard as ":requires" (Machine::load_klammerset_files): a set
            // named twice on the command line is loaded once.
            if (machine.m_klammersets.has(symbol)) {
                (void)K::log(1, "Klammerset \"" + symbol + "\": already loaded, skipped");
                continue;
            }
            std::string klammerset_filename = resolve_klammerset_symbol(
                symbol, machine.m_state.value("K_input_dir"), Locator::none()).generic_string();
            // Symbol -> file is the search path's answer, and the search
            // path has three stages with shadowing: the file it landed on is
            // exactly what a user cannot read off "--klammersets x".
            (void)K::log(1, "Klammerset \"" + symbol + "\": " + klammerset_filename);
            machine.read(fs::path(klammerset_filename));
        }
    }
}