klammertext/com/kdiag.cpp

#include <iostream>
#include <limits>
#include <map>

#include "util.h"
#include "check.h"
#include "argument_set.h"
#include "argv.h"
#include "argument.h"
#include "command.h"
#include "error.h"
#include "file.h"
#include "katom.h"
#include "log.h"
#include "show.h"

int main(int argc, char* argv[])
{
    try {
        set_verbose_level(argc, argv);

        Argv args {};
        // Optional: "kdiag --machine" with no input shows the Machine's initial
        // state, which is a question about the machine rather than about any
        // document -- and the one thing a programmer wants before feeding it
        // anything.
        args.req("input",    "Klammertext input text", "'text'", false);
        args.flag("type",    "Show katom types in subscript");
        args.flag("index",   "Show the list index of the katom");
        args.flag("text",    "Show text katoms with selected attributes");
        args.flag("replaced","Show replaced katoms");
        args.flag("ignored", "Show ignored katoms");
        args.flag("all",     "Show all katoms, including katoms replaced or ignored"); // in brackets with selected attributes");
        args.flag("spans",   "Show the beginning and ending katoms of spans");
        args.flag("rewrite", "Show applied rewrite rules");
        args.flag("args",    "Show how the text would be parsed as klammer arguments");
        args.opt("pos",      "Number of positional arguments to parse for --args", "count", "-1", R"(([^\s]+))");
        args.flag("read",    "Process read: @read <filename> @");
        args.flag("eval",    "Process eval: @eval <expression> @");
        args.flag("cond",    "Process cond: @cond <condition> | <if-true> | <if_false> @");
        args.flag("nonascii","Process encoded characters (not ASCII): ^... or ^...^");
        args.flag("literal", "Process literal: ^'...'^");
        args.flag("ignore",  "Process ignored: #, ##, #[...]#");
        args.flag("ws",      "Process whitespace: #-, #+, #/");
        args.flag("klammer", "Register klammer definitions: @@<name> ... @@.  Their katoms "
                             "are consumed, so they appear only with --replaced.");
        args.flag("system",  "Register machine definitions: @@@target, @@@argtype, @@@state, "
                             "@@@klammerset.  Their katoms are consumed, so they appear only "
                             "with --replaced.  The two tiers are ORDERED: a klammer names a "
                             "target, so --klammer alone cannot register a klammer whose "
                             "target the input itself declares.  That is not an error here: "
                             "the definition is skipped and its katoms stay visible, which is "
                             "the report.");
        args.flag("process", "Process all, both tiers of definition included");
        args.flag("check",   "Check every klammer application in the input and in the "
                             "body of every defined klammer");
        args.flag("machine", "Show the state of the Klammermachine after all processing");
        args.opt("v",        "'verbosity'", "degree", "0", "'verbosity'");

        if (show_usage(argc, argv)) {
            // A bare command is a REQUEST for information, not a failure:
            // usage goes to stdout (it is the result being asked for) and the
            // exit status is 0, so "kdiag && echo ok" reports what happened.
            args.usage(file_basename(argv[0]));
            exit(0);
        }
        auto p = [&](const std::string& name) { return args.get(name) == "true"; };

        args.parse(argc, argv);
        verbose_level = args.as_int("v");
        if (verbose_level > 0) {
            args.describe();
        }

        if (p("rewrite")) {
            show_rewrite_rules = true;
        }

        // kdiag deliberately has no --klammersets: a klammerset is reached here
        // the way the input reaches anything else, with "@read sks/sks.k @".
        // The symbol mechanism is a higher-level convenience, and a debugger
        // must not depend on the machinery it debugs -- if symbol resolution
        // breaks, kdiag must still run, and the two paths to the same file can
        // then be compared.
        Machine machine;
        // kdiag has no target argument, and evaluating needs one: Eval::eval
        // re-reads its result under K_target, so with the variable unset every
        // @eval died with "Variable "K_target" not defined" -- an error naming
        // something the user never wrote.  A command that does not specify a
        // target evaluates under the GENERAL target (Andy, 2026-08-15), which
        // is also what kdiag means: it loads no klammerset, so nothing
        // target-specific is in scope to begin with.
        machine.m_state.set("K_target", Target_registry::general_name);
        machine.m_state.set("K_input_dir", fs::current_path().string());
        std::string input = args.as_string("input");
        std::string command = construct_command_pathname(argv[0]);
        // ONE authoritative katom list.  process() returns the katoms but
        // registers nothing -- read() is what appends to m_katoms and extracts
        // the definitions -- so kdiag does that itself, in the order read()
        // uses, and then displays m_katoms.  Displaying its own copy instead
        // would show the definition katoms unconsumed, because extraction
        // marks them "replaced" in the Machine's list, not in a copy.
        bool all = p("process");
        katom_list processed = all
            ? machine.process(input, command)
            : machine.process(input, command,
                              p("nonascii"), p("literal"), p("ignore"), p("ws"),
                              p("klammer"), p("eval"), p("cond"), p("read"));
        machine.m_katoms.insert(
            machine.m_katoms.end(), processed.begin(), processed.end());
        // Machine definitions first: a klammer definition names a target, so
        // the target must be registered before the klammer that uses it.
        // Tolerant: a definition that cannot be registered because the other
        // tier was not run is skipped, not fatal -- its katoms stay visible.
        // kdiag dissects structure and typing, which means allowing modes of
        // processing that would be errors in ktext.
        if (all || p("system")) machine.extract_machine_definitions(true);
        if (all || p("klammer")) machine.extract_klammer_definitions(true);
        katom_list& katoms = machine.m_katoms;

        if (p("spans")) {
            describe_spans(katoms);
        } else {
            if (p("ignored")) std::cout << kignored;
            if (p("type")) std::cout << ktype;
            if (p("index")) std::cout << kindex;
            if (p("text")) std::cout << kall;
            if (p("all")) std::cout << kall << kreplaced << kignored;
            if (p("replaced")) std::cout << kreplaced;
            if (!p("check")) {
                std::cout << katoms << "\n";
            }
        }

        if (p("args")) {
            int req_count = args.as_int("pos");
            bool limit_req = req_count != -1;
            if (req_count == -1) {
                req_count = std::numeric_limits<int>::max();
            }
            auto [required, optional, rest] =
                argument_split(katoms.begin(), katoms.end(), req_count);
            std::stringstream ss {};
            ss << "required";
            if (limit_req) {
                ss << " (" << req_count << ")";
            }
            ss << ":";
            std::string req_label = ss.str();
            auto label_width = req_label.size() + 2;
            std::cout << std::setfill(' ')
                      << std::right << std::setw(label_width) << req_label << "  " << required << "\n"
                      << std::right << std::setw(label_width) << "optional:" << "  " << optional << "\n";
            if (limit_req) {
                std::cout << std::right << std::setw(label_width) << "rest:" << "  " << rest << "\n";
            }
        }
        int check_errors = 0;
        if (p("check")) {
            check_errors = report_diagnostics(check_machine(machine, katoms, "*"), std::cout);
            // The commonest cause of a wall of "not defined" is that nothing
            // was registered.  The advice belongs here rather than in the
            // catch block: --check REPORTS, it does not throw, so an exception
            // handler never sees this case.  The condition is the CAUSE, not a
            // proxy for it.
            if (check_errors > 0 && machine.m_klammers.m_klammers.empty()) {
                std::cout << "\nNo klammers are registered, so every application is "
                             "undefined.\nkdiag loads no klammerset: read one in the input, "
                             "as \"@read sks/sks.k @\",\nand add --process (or --system "
                             "--klammer --read) to register what it defines.\n";
            }
        }
        // Last, and after everything else: the state shown is the result of
        // whatever the other arguments did.  This is why --check defers its
        // exit status rather than returning as soon as it finds errors.
        if (p("machine")) {
            std::cout << machine;
        }
        if (check_errors > 0) {
            std::cout << black;
            return 1;
        }

    }
    catch (Error& e) {
        // The advice must name a way in that kdiag actually has.  It named
        // "--klammersets sks" until 2026-08-15, a flag the 2026-08-14 redesign
        // deliberately removed from this command -- a debugger must not depend
        // on the machinery it debugs -- so the one remedy offered was one that
        // errors.  Same wording as the --check hint above, for the same reason.
        std::string advice = "";
        if (e.m_type == "target" || e.m_type == "definition") {
            advice = "kdiag loads no klammerset: read one in the input, as "
                     "\"@read sks/sks.k @\", and add --process to register what it "
                     "defines.";
        }
        e.print_message(advice);
        // Nonzero, as ktext does: a command that prints an error and exits 0
        // reports success, and a script cannot tell the difference.
        std::cout << black;
        return 1;
    }
    std::cout << black;
    return 0;
}