Crafter.Build/implementations/Crafter.Build-Platform.cpp

// SPDX-License-Identifier: LGPL-3.0-only
// SPDX-FileCopyrightText: Copyright (C) 2026 Catcrafts®

module;
#include <stdio.h>
#include <stdlib.h>
#include <limits.h>
#include <unistd.h>
#include <dlfcn.h>
#include <sys/wait.h>
#include <sys/file.h>
#include <fcntl.h>
#include <errno.h>
module Crafter.Build:Platform_impl;
import std;
import :Platform;
import :Toolchain;
import :Clang;
import :Interface;
import :External;
import :Progress;
namespace fs = std::filesystem;
using namespace Crafter;

namespace {
    // Exclusive advisory lock over one PCM cache dir (`<cache>/<target>-<march>/`),
    // held for the duration of a (re)build. Concurrent crafter-build invocations —
    // and the worker threads inside a single invocation — that share a cache
    // serialize their builds through it: the first builder to acquire the lock
    // precompiles std.pcm / the Crafter.Build-*.pcm modules while everyone else
    // blocks, then re-checks freshness and reuses the finished file instead of
    // re-running clang and racing to overwrite the same path. Each builder must
    // pass through the lock before it reaches the compile steps that *read* those
    // PCMs, so a reader never observes a half-written file.
    //
    // A FileLock on a `.lock` file in the cache dir.
    struct CacheLock {
        FileLock lock;
        explicit CacheLock(const fs::path& cacheDir) : lock(cacheDir / ".lock") {}
    };

    // The cached Crafter.Build PCMs are keyed by `<target>-<march>` alone, so
    // every crafter-build on the machine writes to the same files regardless of
    // which share/crafter-build its module sources came from. Freshness used to
    // be a per-file mtime comparison, which cannot distinguish "this PCM is
    // newer than my source" from "this PCM was built from *different* sources
    // that happen to be newer" — so a second install or checkout silently
    // compiled its project against the other's declarations. Same failure shape
    // as issue #27: no error, a binary built against a layout nobody linked.
    //
    // A stamp over the bytes of every module source answers what the mtime
    // can't. It covers the whole set rather than one file at a time because the
    // PCMs import each other: a change to :Interface invalidates :Clang's PCM
    // even though Crafter.Build-Clang.cppm is untouched.
    std::string CrafterBuildSourceStamp(const fs::path& sourceDir, std::span<const std::string_view> moduleNames) {
        std::string all;
        auto append = [&all, &sourceDir](const fs::path& relative) {
            std::ifstream in(sourceDir / relative, std::ios::binary);
            std::ostringstream buffer;
            buffer << in.rdbuf();
            all += relative.string();
            all += '\0';
            all += buffer.str();
            all += '\0';
        };
        for (std::string_view name : moduleNames) {
            append(fs::path(std::format("{}.cppm", name)));
        }
        return std::format("{:016x}", std::hash<std::string>{}(all));
    }

    fs::path CacheStampPath(const fs::path& cacheDir) {
        return cacheDir / "crafter-build-sources.stamp";
    }

    // A stamp is a one-line content hash kept next to the artifact it
    // describes. Written last, after the artifact, so an interrupted build
    // leaves a stamp that disagrees and the next run starts over.
    std::string ReadStamp(const fs::path& file) {
        std::ifstream in(file, std::ios::binary);
        std::string stamp;
        std::getline(in, stamp);
        return stamp;
    }

    void WriteStamp(const fs::path& file, std::string_view stamp) {
        std::ofstream(file, std::ios::binary | std::ios::trunc) << stamp << '\n';
    }

    fs::path StampPath(const fs::path& artifact) {
        fs::path stamp = artifact;
        stamp += ".stamp";
        return stamp;
    }

    std::string HashStamp(std::string_view content) {
        return std::format("{:016x}", std::hash<std::string_view>{}(content));
    }

    std::string FileBytes(const fs::path& file) {
        std::ifstream in(file, std::ios::binary);
        std::ostringstream buffer;
        buffer << in.rdbuf();
        return buffer.str();
    }

    // The string value of `"key": "..."` in `object`, if it has one.
    std::optional<std::string> JsonString(std::string_view object, std::string_view key) {
        const std::string quoted = std::format("\"{}\"", key);
        std::size_t at = object.find(quoted);
        if (at == std::string_view::npos) return std::nullopt;
        at = object.find_first_not_of(" \t\r\n", at + quoted.size());
        if (at == std::string_view::npos || object[at] != ':') return std::nullopt;
        at = object.find_first_not_of(" \t\r\n", at + 1);
        if (at == std::string_view::npos || object[at] != '"') return std::nullopt;
        std::string value;
        for (std::size_t i = at + 1; i < object.size(); ++i) {
            if (object[i] == '"') return value;
            if (object[i] == '\\' && i + 1 < object.size()) ++i;
            value += object[i];
        }
        return std::nullopt;
    }

    // The std module's "source-path" in a libstdc++.modules.json: the object
    // in its "modules" array whose "logical-name" is "std". The manifest is
    // a flat list of such objects, so each one is the text between its
    // braces.
    std::optional<std::string> StdModuleSourcePath(std::string_view manifest) {
        for (std::size_t open = manifest.find('{', manifest.find("\"modules\"")); open != std::string_view::npos; open = manifest.find('{', open + 1)) {
            const std::size_t close = manifest.find('}', open);
            if (close == std::string_view::npos) break;
            const std::string_view object = manifest.substr(open, close - open);
            if (JsonString(object, "logical-name") == "std") return JsonString(object, "source-path");
        }
        return std::nullopt;
    }
}

Crafter::FileLock::FileLock(const fs::path& path) {
    fd = ::open(path.c_str(), O_RDWR | O_CREAT | O_CLOEXEC, 0644);
    if (fd >= 0) {
        while (::flock(fd, LOCK_EX) != 0 && errno == EINTR) {}
    }
}

Crafter::FileLock::~FileLock() {
    if (fd >= 0) {
        ::close(fd);  // closing the descriptor drops the flock
    }
}

fs::path Crafter::GetCrafterBuildHome() {
    if (const char* envHome = std::getenv("CRAFTER_BUILD_HOME")) {
        return fs::path(envHome);
    }
    fs::path hostExe = fs::read_symlink("/proc/self/exe");

    // Walk up from the exe's directory looking for share/crafter-build with
    // a known module source present as a sentinel. Handles:
    //   <prefix>/bin/crafter-build      -> <prefix>/share/crafter-build  (FHS install)
    //   <repo>/bin/crafter-build        -> <repo>/share/crafter-build    (build.sh)
    //   <repo>/bin/<arch>/crafter-build -> <repo>/share/crafter-build    (self-host)
    fs::path dir = hostExe.parent_path();
    std::vector<fs::path> tried;
    for (;;) {
        fs::path candidate = dir / "share" / "crafter-build";
        tried.push_back(candidate);
        std::error_code ec;
        if (fs::exists(candidate / "Crafter.Build.cppm", ec)) {
            return candidate;
        }
        fs::path parent = dir.parent_path();
        if (parent == dir) break;
        dir = parent;
    }
    std::string msg = std::format("could not locate crafter-build runtime assets relative to {} (set CRAFTER_BUILD_HOME). Tried:", hostExe.string());
    for (const auto& p : tried) {
        msg += std::format("\n  {}", p.string());
    }
    throw std::runtime_error(msg);
}

fs::file_time_type Crafter::NewestPrerequisite(const fs::path& depFile) {
    std::ifstream in(depFile, std::ios::binary);
    if (!in) return fs::file_time_type::max();
    std::ostringstream buffer;
    buffer << in.rdbuf();
    const std::string text = std::move(buffer).str();

    // Make-rule tokenizing, as clang writes it: `target: prereq prereq`, with a
    // trailing '\' continuing the rule onto the next line (clang wraps at ~80
    // columns, so any real depfile has several), '\ ' and '\#' escaping a
    // character into a filename, and '$$' standing for a literal '$'. A
    // backslash that is none of those is a Windows path separator and stays.
    std::vector<std::string> tokens;
    std::string token;
    auto flush = [&tokens, &token]() {
        if (!token.empty()) {
            tokens.push_back(token);
            token.clear();
        }
    };
    for (std::size_t i = 0; i < text.size(); ++i) {
        const char c = text[i];
        const char next = i + 1 < text.size() ? text[i + 1] : '\0';
        if (c == '\\' && (next == '\n' || next == '\r')) {
            flush();
            ++i;
        } else if (c == '\\' && (next == ' ' || next == '\t' || next == '#')) {
            token += next;
            ++i;
        } else if (c == '$' && next == '$') {
            token += '$';
            ++i;
        } else if (c == ' ' || c == '\t' || c == '\n' || c == '\r') {
            flush();
        } else {
            token += c;
        }
    }
    flush();

    // A token ending in ':' names a rule target, not an input. The first one
    // closes the target list (and a Windows `C:\build\x.o:` still ends in ':',
    // where splitting on the first colon would not); a later one opens another
    // rule, as `-MP` phony targets do, whose name is not a file to stat.
    bool sawTarget = false;
    fs::file_time_type newest = fs::file_time_type::min();
    for (const std::string& prerequisite : tokens) {
        if (prerequisite.ends_with(':')) {
            sawTarget = true;
            continue;
        }
        if (!sawTarget) continue;
        std::error_code ec;
        const fs::file_time_type stamp = fs::last_write_time(prerequisite, ec);
        // A prerequisite that has since been deleted makes the recorded set
        // unusable as evidence — the source that included it must have changed
        // too, and rebuilding is what writes a depfile that no longer names it.
        if (ec) return fs::file_time_type::max();
        if (stamp > newest) newest = stamp;
    }
    // No rule at all: a truncated or empty depfile proves nothing.
    if (!sawTarget) return fs::file_time_type::max();
    return newest;
}

bool Crafter::MatchGlob(std::string_view glob, std::string_view name) {
    std::size_t gi = 0;
    std::size_t ni = 0;
    std::size_t star = std::string_view::npos;
    std::size_t mark = 0;
    while (ni < name.size()) {
        if (gi < glob.size() && (glob[gi] == '?' || glob[gi] == name[ni])) {
            ++gi; ++ni;
        } else if (gi < glob.size() && glob[gi] == '*') {
            star = gi++;
            mark = ni;
        } else if (star != std::string_view::npos) {
            gi = star + 1;
            ni = ++mark;
        } else {
            return false;
        }
    }
    while (gi < glob.size() && glob[gi] == '*') ++gi;
    return gi == glob.size();
}

bool Crafter::MatchAny(std::span<const std::string> globs, std::string_view name) {
    if (globs.empty()) return true;
    for (const auto& g : globs) {
        if (MatchGlob(g, name)) return true;
    }
    return false;
}

// See the declaration in Crafter.Build-Platform.cppm for why this branches on
// the exit code rather than on whether the command said anything.
std::string Crafter::RunBuildCommand(std::string_view cmd) {
    Progress::EchoCommand(cmd);
    CommandResult r = RunCommandChecked(cmd);

    if (r.exitCode == 0) {
        // Warnings from a step that succeeded. Show them — until now they were
        // invisible on an incremental build and fatal on a cold one.
        if (!r.output.empty()) Progress::Diagnostic(r.output);
        return "";
    }

    // A compiler killed outright (the OOM killer is the common one) prints
    // nothing, so the old "output means failure" rule read it as success and
    // let the build carry on with a missing object. Say what happened instead.
    if (r.output.empty()) {
        return r.crashed
            ? std::format("terminated by signal {}: {}", r.signal, cmd)
            : std::format("exited with code {}: {}", r.exitCode, cmd);
    }
    if (r.crashed) {
        return std::format("{}\nterminated by signal {}", r.output, r.signal);
    }
    return r.output;
}

// --- Dependencies of project.cpp itself -------------------------------------
//
//   #pragma crafter dependency "<source>" [branch "<b>" | commit "<sha>"] [project "<file>"]
//
// names a sibling crafter-build project that project.cpp imports a module
// from. Anything a file needs before it can compile cannot be C++ inside that
// file, so this is a directive next to the `import` it enables — where
// `#include` lives. Each one is fetched, built for the host, and put on
// project.so's module path and link line before project.cpp is compiled. The
// dependency's own project.cpp goes through LoadProject, so its pragmas
// resolve recursively.
namespace {
    struct PragmaDependency {
        std::string source;
        std::string branch;
        std::string commit;
        std::string project;
        std::size_t line = 0;
    };

    [[noreturn]] void PragmaError(const fs::path& file, std::size_t line, std::string_view message) {
        throw std::runtime_error(std::format("{}:{}: {}", file.string(), line, message));
    }

    // The tokens of one directive: bare words and double-quoted strings (no
    // escapes — a path or URL never needs one). Reading stops at `//`.
    class PragmaCursor {
    public:
        PragmaCursor(std::string_view text, const fs::path& file, std::size_t line) : text_(text), file_(file), line_(line) {}

        bool AtEnd() {
            SkipSpace();
            return pos_ >= text_.size() || text_.substr(pos_).starts_with("//");
        }

        bool Take(char c) {
            SkipSpace();
            if (pos_ >= text_.size() || text_[pos_] != c) return false;
            ++pos_;
            return true;
        }

        std::string_view Word() {
            SkipSpace();
            const std::size_t start = pos_;
            while (pos_ < text_.size() && IsWordChar(text_[pos_])) ++pos_;
            return text_.substr(start, pos_ - start);
        }

        std::optional<std::string_view> Quoted() {
            SkipSpace();
            if (pos_ >= text_.size() || text_[pos_] != '"') return std::nullopt;
            const std::size_t close = text_.find('"', pos_ + 1);
            if (close == std::string_view::npos) Fail("unterminated string");
            const std::string_view inner = text_.substr(pos_ + 1, close - pos_ - 1);
            pos_ = close + 1;
            return inner;
        }

        [[noreturn]] void Fail(std::string_view message) const { PragmaError(file_, line_, message); }

    private:
        static bool IsWordChar(char c) { return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9') || c == '_'; }

        void SkipSpace() {
            while (pos_ < text_.size() && (text_[pos_] == ' ' || text_[pos_] == '\t' || text_[pos_] == '\r')) ++pos_;
        }

        std::string_view text_;
        const fs::path& file_;
        std::size_t line_;
        std::size_t pos_ = 0;
    };

    // One directive per line, anywhere in the file. Comments aren't parsed:
    // a directive inside a block comment is honoured, and `//` lines fall out
    // because they don't start with `#`.
    std::vector<PragmaDependency> ScanProjectFilePragmas(const fs::path& absProject) {
        std::vector<PragmaDependency> found;
        std::ifstream in(absProject);
        std::string raw;
        for (std::size_t lineNo = 1; std::getline(in, raw); ++lineNo) {
            PragmaCursor cur(raw, absProject, lineNo);
            if (!cur.Take('#') || cur.Word() != "pragma" || cur.Word() != "crafter") continue;
            const std::string_view verb = cur.Word();
            if (verb != "dependency") cur.Fail(std::format("unknown crafter pragma '{}'", verb));

            PragmaDependency dep;
            dep.line = lineNo;
            const std::optional<std::string_view> source = cur.Quoted();
            if (!source) cur.Fail("expected a quoted source after 'dependency'");
            dep.source = *source;
            while (!cur.AtEnd()) {
                const std::string_view key = cur.Word();
                std::string* field = key == "branch" ? &dep.branch : key == "commit" ? &dep.commit : key == "project" ? &dep.project : nullptr;
                if (!field) cur.Fail(key.empty() ? "unexpected text after the source" : std::format("unknown keyword '{}' (expected branch, commit or project)", key));
                if (!field->empty()) cur.Fail(std::format("'{}' given twice", key));
                const std::optional<std::string_view> value = cur.Quoted();
                if (!value || value->empty()) cur.Fail(std::format("expected a quoted value after '{}'", key));
                *field = *value;
            }
            if (dep.source.empty()) cur.Fail("the source is empty");
            if (!dep.branch.empty() && !dep.commit.empty()) cur.Fail("'branch' and 'commit' are mutually exclusive");
            found.push_back(std::move(dep));
        }
        return found;
    }

    struct ProjectFileFrame {
        fs::path project;
        std::vector<Configuration*> dependencies;
    };

    // LoadProject nests: a dependency's project.cpp loads inside its
    // consumer's pre-pass, and GitProject inside CrafterBuildProject nests
    // again. Several threads may also load at once (ConcurrentCacheRace), so
    // the stack is per thread. ProjectDependency() reads the top frame.
    thread_local std::vector<ProjectFileFrame> LoadingFrames;

    // Held for the whole of one LoadProject call. Pushing a file that is
    // already on the stack is a cycle, which used to recurse forever.
    class ProjectFileGuard {
    public:
        explicit ProjectFileGuard(const fs::path& absProject) {
            for (const ProjectFileFrame& frame : LoadingFrames) {
                if (frame.project != absProject) continue;
                std::string chain;
                for (const ProjectFileFrame& f : LoadingFrames) chain += std::format("{} -> ", f.project.string());
                throw std::runtime_error(std::format("circular project dependency: {}{}", chain, absProject.string()));
            }
            index_ = LoadingFrames.size();
            LoadingFrames.push_back({ absProject, {} });
        }
        ~ProjectFileGuard() { LoadingFrames.pop_back(); }
        ProjectFileGuard(const ProjectFileGuard&) = delete;
        ProjectFileGuard& operator=(const ProjectFileGuard&) = delete;

        ProjectFileFrame& Frame() { return LoadingFrames[index_]; }

    private:
        std::size_t index_ = 0;
    };

    // A pre-dependency is host tooling: project.so is loaded into the running
    // crafter-build, so the dependency is built for the host and against the
    // same PCM cache LoadProject populates — the hostConfig LoadProject itself
    // compiles project.so with, so the dependency's std/Crafter.Build PCMs
    // land in the cache dir project.so is built against. Recursive, because
    // the dependency's project.cpp forwards no arguments but still reads
    // CRAFTER_BUILD_MARCH from the environment for its own deps.
    void ForceHostTooling(Configuration& cfg, const Configuration& host, std::unordered_set<Configuration*>& seen) {
        if (!seen.insert(&cfg).second) return;
        cfg.target = host.target;
        cfg.march = host.march;
        cfg.mtune = host.mtune;
        cfg.debug = false;
        // project.so is a shared object, so the archive it links has to be
        // position-independent; static libraries aren't by default. Part of
        // VariantId, so this build never shares a bin dir with a normal one.
        // Checked before pushing: the same Configuration comes back from the
        // project cache for every consumer in this process. Linux hosts only,
        // glibc or musl: Windows targets have no use for the flag.
        const bool linuxHost = host.target.ends_with("-linux-gnu") || host.target.ends_with("-linux-musl");
        if (linuxHost && !std::ranges::contains(cfg.compileFlags, "-fPIC")) {
            cfg.compileFlags.emplace_back("-fPIC");
        }
        for (Configuration* dep : cfg.dependencies) ForceHostTooling(*dep, host, seen);
    }

    struct ProjectFileDependencies {
        std::vector<Configuration*> configs;
        std::string compileFlags;   // " -fprebuilt-module-path=…" for each dependency and its transitive deps
        std::string linkFlags;      // every dependency's BuildResult.libs, verbatim
        fs::file_time_type newestArtifact = fs::file_time_type::min();
    };

    bool IsGitSource(std::string_view source) {
        return source.contains("://") || source.starts_with("git@");
    }

    ProjectFileDependencies ResolveProjectFileDependencies(const fs::path& absProject, const Configuration& host) {
        ProjectFileDependencies out;
        const std::vector<PragmaDependency> pragmas = ScanProjectFilePragmas(absProject);
        if (pragmas.empty()) return out;

        std::unordered_map<fs::path, std::shared_future<BuildResult>> depResults;
        std::mutex depMutex;
        std::unordered_set<Configuration*> forced;
        std::unordered_set<Configuration*> walked;
        std::set<std::string> libs;

        for (const PragmaDependency& pragma : pragmas) {
            Configuration* cfg = nullptr;
            if (IsGitSource(pragma.source)) {
                GitProjectSpec spec;
                spec.source = { pragma.source, pragma.branch, pragma.commit };
                if (!pragma.project.empty()) spec.projectFile = pragma.project;
                cfg = GitProject(spec);
            } else {
                if (!pragma.branch.empty() || !pragma.commit.empty()) PragmaError(absProject, pragma.line, "'branch' and 'commit' only apply to a git source");
                // Relative to the project file, not the cwd: LoadProject runs
                // from wherever the consumer was invoked.
                fs::path local = (absProject.parent_path() / pragma.source).lexically_normal();
                if (fs::is_directory(local)) {
                    local /= pragma.project.empty() ? fs::path("project.cpp") : fs::path(pragma.project);
                } else if (!pragma.project.empty()) {
                    PragmaError(absProject, pragma.line, "'project' only applies to a directory source");
                }
                if (!fs::exists(local)) PragmaError(absProject, pragma.line, std::format("no such project file: {}", local.string()));
                cfg = LocalProject({ .projectFile = local });
            }
            if (std::ranges::contains(out.configs, cfg)) continue;

            ForceHostTooling(*cfg, host, forced);
            BuildResult built;
            {
                Progress::Task task(std::format("Building project dependency {}", cfg->name));
                built = Build(*cfg, depResults, depMutex);
            }
            if (!built.result.empty()) PragmaError(absProject, pragma.line, std::format("project dependency '{}' failed to build: {}", cfg->name, built.result));
            out.configs.push_back(cfg);
            libs.insert(built.libs.begin(), built.libs.end());

            // The module path needs the dependency and everything it depends
            // on, same as GetCompileCommand does for a consumer; the newest
            // artifact over the same set is what project.so is stale against.
            std::function<void(Configuration*)> walk = [&](Configuration* c) {
                if (!walked.insert(c).second) return;
                out.compileFlags += std::format(" -fprebuilt-module-path={}", c->PcmDir().string());
                std::error_code ec;
                const fs::file_time_type t = fs::last_write_time(ExpectedOutput(*c), ec);
                if (!ec && t > out.newestArtifact) out.newestArtifact = t;
                for (Configuration* sub : c->dependencies) walk(sub);
            };
            walk(cfg);
        }
        for (const std::string& lib : libs) out.linkFlags += std::format(" {}", lib);
        return out;
    }

    // project.so is stale when its stamp (crafter-build version, toolchain,
    // module sources and compile command) disagrees, or when it predates its
    // source or a pre-dependency artifact. The executable's mtime is not an
    // input any more: an OSTree deployment dates every installed file at the
    // epoch, so a comparison against it never fired after an update and the
    // old project.so was loaded into a binary it did not match.
    bool ProjectFileStale(const fs::path& artifact, const fs::path& project, std::string_view stamp, const ProjectFileDependencies& deps) {
        if (!fs::exists(artifact)) return true;
        if (ReadStamp(StampPath(artifact)) != stamp) return true;
        const fs::file_time_type built = fs::last_write_time(artifact);
        return built < fs::last_write_time(project) || built < deps.newestArtifact;
    }
}

Configuration* Crafter::ProjectDependency(std::string_view name) {
    if (LoadingFrames.empty()) throw std::runtime_error(std::format("ProjectDependency('{}'): called outside a project file", name));
    const ProjectFileFrame& frame = LoadingFrames.back();
    for (Configuration* cfg : frame.dependencies) {
        if (cfg->name == name) return cfg;
        for (const std::unique_ptr<Module>& iface : cfg->interfaces) {
            if (iface->name == name) return cfg;
        }
    }
    std::string declared;
    for (Configuration* cfg : frame.dependencies) {
        if (!declared.empty()) declared += ", ";
        declared += cfg->name;
    }
    throw std::runtime_error(std::format("ProjectDependency('{}'): not declared by {} (declared: {})", name, frame.project.string(), declared.empty() ? "none" : declared));
}

bool Crafter::IsTopLevelProject() {
    // One frame is the project file crafter-build was pointed at; a second
    // is only ever pushed for a dependency's project file.
    return LoadingFrames.size() <= 1;
}

namespace {
    // The one reading of a wait status (pclose, system) for every helper
    // that runs a command: a signal death is reported the way a shell
    // reports it, as 128+signal.
    void DecodeWaitStatus(std::int32_t status, CommandResult& result) {
        if (WIFEXITED(status)) {
            result.exitCode = WEXITSTATUS(status);
        } else if (WIFSIGNALED(status)) {
            result.signal = WTERMSIG(status);
            result.exitCode = 128 + result.signal;
            result.crashed = true;
        } else {
            result.exitCode = -1;
        }
    }
}

std::string Crafter::ShellQuote(std::string_view s) {
    std::string out;
    out.reserve(s.size() + 2);
    out.push_back('\'');
    for (char c : s) {
        if (c == '\'') out += "'\\''";
        else out.push_back(c);
    }
    out.push_back('\'');
    return out;
}

CommandResult Crafter::RunCommandChecked(std::string_view cmd) {
    std::array<char, 128> buffer;
    CommandResult result{};

    std::string with = std::format("{} 2>&1", cmd);
    FILE* pipe = popen(with.c_str(), "r");
    if (!pipe) throw std::runtime_error("popen() failed!");

    while (fgets(buffer.data(), buffer.size(), pipe) != nullptr) {
        result.output += buffer.data();
    }

    DecodeWaitStatus(pclose(pipe), result);
    return result;
}

std::int32_t Crafter::RunCommandAttached(std::string_view cmd) {
    // The child writes straight to the terminal. Anything of ours that is
    // still pending — the in-place status line, buffered stdout when it is
    // a pipe — has to be out before the child's first byte, or it lands in
    // the middle of the child's output or after it.
    Progress::Clear();
    std::fflush(stdout);
    std::fflush(stderr);

    const std::string command(cmd);
    const std::int32_t status = std::system(command.c_str());
    if (status == -1) throw std::runtime_error(std::format("could not start a shell for: {}", cmd));
    CommandResult result{};
    DecodeWaitStatus(status, result);
    return result.exitCode;
}

CommandResult Crafter::RunCommandWithTimeout(std::string_view cmd, std::chrono::seconds timeout) {
    std::array<char, 128> buffer;
    CommandResult result{};

    // -k (not --kill-after=): the short form is what GNU coreutils and busybox
    // (Alpine) have in common.
    std::string wrapped = std::format("timeout -k 2 {} {} 2>&1", timeout.count(), cmd);

    FILE* pipe = popen(wrapped.c_str(), "r");
    if (!pipe) throw std::runtime_error("popen() failed!");

    while (fgets(buffer.data(), buffer.size(), pipe) != nullptr) {
        result.output += buffer.data();
    }

    DecodeWaitStatus(pclose(pipe), result);
    // What comes back is `timeout`'s own exit, and it speaks through the
    // code: 124 for a command it had to stop, 128+signal for one that died.
    if (!result.crashed) {
        if (result.exitCode == 124) {
            result.timedOut = true;
        } else if (result.exitCode >= 128) {
            result.signal = result.exitCode - 128;
            result.crashed = true;
        }
    }
    return result;
}

std::string Crafter::BuildStdPcm(const Configuration& config, fs::path stdPcm) {
    CacheLock lock(stdPcm.parent_path());
    if(config.target == "x86_64-w64-mingw32") {
        // libstdc++ 15 and newer install libstdc++.modules.json beside the
        // library, naming the std module's source relative to itself. It is
        // looked for in the library directories the compiler searches for
        // this target, as it would look for libstdc++ itself, but only in
        // those that belong to the mingw toolchain: the list also has the
        // generic <prefix>/lib, where the host's own (Linux) libstdc++ keeps
        // its manifest. A toolchain that isn't there is a build error, not
        // an exception: Build() runs this with its worker threads started.
        const Toolchain& tc = GetToolchain();
        const std::string where = tc.mingwSysroot.empty()
            ? std::string("where clang finds it by the x86_64-w64-mingw32 gcc on PATH")
            : std::format("under {}", tc.mingwSysroot.string());
        const std::string missing = std::format("no mingw-w64 libstdc++ with the std module (libstdc++ 15 or newer) {}. Install mingw-w64, or point CRAFTER_MINGW_DIR at its prefix, the directory holding x86_64-w64-mingw32/ and lib/gcc/", where);
        // Asked once a run for each compiler and target: every mingw
        // configuration comes through here, up to date or not, and the answer
        // costs a clang.
        static std::mutex probeMutex;
        static std::unordered_map<std::string, CommandResult> probes;
        const std::string probe = std::format("{} --target={} -print-search-dirs", GetBaseCommand(config), config.target);
        CommandResult dirs;
        {
            std::lock_guard guard(probeMutex);
            auto found = probes.find(probe);
            if (found == probes.end()) found = probes.emplace(probe, RunCommandChecked(probe)).first;
            dirs = found->second;
        }
        if (dirs.exitCode != 0) return std::format("{}: {}", missing, dirs.output);
        fs::path manifestPath;
        constexpr std::string_view librariesLine = "libraries: =";
        if (const std::size_t at = dirs.output.find(librariesLine); at != std::string::npos) {
            const std::size_t end = dirs.output.find('\n', at);
            const std::string list = dirs.output.substr(at + librariesLine.size(), end == std::string::npos ? std::string::npos : end - at - librariesLine.size());
            for (const auto part : std::views::split(list, ':')) {
                const fs::path dir(std::string_view(part.begin(), part.end()));
                const bool mingwOwn = std::ranges::contains(dir, fs::path("x86_64-w64-mingw32"));
                if (mingwOwn && fs::exists(dir / "libstdc++.modules.json")) {
                    manifestPath = dir / "libstdc++.modules.json";
                    break;
                }
            }
        }
        if (manifestPath.empty()) return missing;
        const std::optional<std::string> source = StdModuleSourcePath(FileBytes(manifestPath));
        if (!source) return std::format("{} names no std module", manifestPath.string());
        const fs::path stdCc = (manifestPath.parent_path() / *source).lexically_normal();
        if (!fs::exists(stdCc)) return std::format("{}, which {} names as the std module, is missing", stdCc.string(), manifestPath.string());

        // -femulated-tls keeps PCM TLS access matching libstdc++'s emutls
        // definitions; mismatch surfaces as undefined std::__once_callable.
        // The std.cc → std.cppm copy uses a plain filename: held under the
        // cache lock, no other builder writes this path concurrently.
        fs::path stdCppm = stdPcm.parent_path() / "std.cppm";
        std::string command = std::format("{} --target={} -march={} -mtune={} -femulated-tls -O3 -std=c++26 -Wno-reserved-identifier -Wno-reserved-module-identifier --precompile {} -o {}", GetBaseCommand(config), config.target, config.march, config.mtune, stdCppm.string(), stdPcm.string());
        std::string stamp = HashStamp(command + '\0' + FileBytes(stdCc));
        if (fs::exists(stdPcm) && ReadStamp(StampPath(stdPcm)) == stamp) return "";
        std::error_code copyEc;
        fs::copy_file(stdCc, stdCppm, fs::copy_options::overwrite_existing, copyEc);
        if (copyEc) {
            return std::format("copy {} -> {}: {}", stdCc.string(), stdCppm.string(), copyEc.message());
        }
        std::string result = RunBuildCommand(command);
        if (result.empty()) WriteStamp(StampPath(stdPcm), stamp);
        return result;
    } else {
        const bool isWasm = config.target.starts_with("wasm32");
        // wasi-sdk drops std.cppm at <sysroot>/share/libc++/v1/, the rest of
        // the libc++ ecosystem (e.g. /opt/aarch64-rootfs) follows FHS at
        // <sysroot>/usr/share/libc++/v1/.
        std::string stdCppm;
        if (isWasm) {
            stdCppm = std::format("{}/share/libc++/v1/std.cppm", config.sysroot);
        } else if (config.sysroot.empty()) {
            stdCppm = GetToolchain().stdCppm.string();
        } else {
            // The source has to belong to the libc++ release whose headers
            // the sysroot carries. Handing clang the toolchain's own copy
            // regardless used to end in a page of "no member named ... in
            // namespace 'std'" once the two releases differed.
            StdModuleSource source = SysrootStdModule(GetToolchain(), config.sysroot);
            if (!source.error.empty()) return source.error;
            stdCppm = source.stdCppm.string();
        }
        std::string sysrootFlag = config.sysroot.empty()
            ? std::string()
            : std::format(" --sysroot={}", config.sysroot);
        // wasm32 rejects -march. wasi-libc++ headers require these baselines
        // to compile: setjmp.h needs -mllvm -wasm-enable-sjlj (lowered to wasm
        // EH); signal.h requires the emulation define; and EH itself isn't
        // wired up so -fno-exceptions stays.
        std::string archFlags = isWasm
            ? std::string(" -fno-exceptions -msimd128 -fno-c++-static-destructors -mllvm -wasm-enable-sjlj -D_WASI_EMULATED_SIGNAL")
            : std::format(" -march={} -mtune={}", config.march, config.mtune);
        // Match the variant codegen flags the consuming TUs are built with
        // (e.g. -mrelaxed-simd) so the std BMI is feature-compatible. wasm only;
        // wasmVariantFlags is empty on every other path.
        if (isWasm) {
            for (const std::string& f : config.wasmVariantFlags) archFlags += std::format(" {}", f);
        }
        // non-wasm cross builds: the driver ranks the host toolchain's own
        // libc++ headers (<install>/../include/c++/v1) above --sysroot, so
        // the PCM would mix host libc++ with the foreign libc — force the
        // sysroot's copy.
        if (!isWasm && !config.sysroot.empty()) {
            archFlags += std::format(" -nostdinc++ -isystem {}/usr/include/c++/v1", config.sysroot);
        }
        // Keyed on the command and the module source's bytes, never on
        // mtimes: an installed std.cppm can be dated at the epoch (OSTree),
        // and a libc++ update under the same clang changes the bytes but
        // not the path.
        std::string command = std::format("{} --target={} -std=c++26{}{} -O3 -Wno-reserved-identifier -Wno-reserved-module-identifier --precompile {} -o {}", GetBaseCommand(config), config.target, sysrootFlag, archFlags, stdCppm, stdPcm.string());
        std::string stamp = HashStamp(command + '\0' + FileBytes(stdCppm));
        if (fs::exists(stdPcm) && ReadStamp(StampPath(stdPcm)) == stamp) return "";
        std::string result = RunBuildCommand(command);
        if (result.empty()) WriteStamp(StampPath(stdPcm), stamp);
        return result;
    }
}

fs::path Crafter::GetCacheDir() {
    if (const char* xdg = std::getenv("XDG_CACHE_HOME"); xdg && *xdg) {
        return fs::path(xdg) / "crafter.build";
    }

    if (const char* home = std::getenv("HOME")) {
        return fs::path(home) / ".cache" / "crafter.build";
    }

    throw std::runtime_error("Neither XDG_CACHE_HOME nor HOME set");
}

std::string Crafter::GetBaseCommand(const Configuration& config) {
    const Toolchain& tc = GetToolchain();
    std::string command = tc.clangxx.string();
    if (config.target == "x86_64-w64-mingw32") {
        // libstdc++ from the mingw toolchain, said outright: a clang built to
        // default to libc++ (the Flatpak's) would otherwise reach for that.
        // Found by clang's own mingw discovery unless there is a sysroot.
        command += " -stdlib=libstdc++";
        if (!tc.mingwSysroot.empty()) command += std::format(" --sysroot={}", tc.mingwSysroot.string());
        return command;
    }
    command += " -stdlib=libc++";
    // A sysroot build (wasm, a cross rootfs) takes libc++ from the sysroot;
    // only host builds can be pointed at an explicit libc++ install.
    if (config.sysroot.empty()) command += tc.LibcxxCompileFlags();
    return command;
}

namespace {
    constexpr std::array<std::string_view, 13> CrafterBuildModules = {
        "Crafter.Build-Toolchain",
        "Crafter.Build-Shader",
        "Crafter.Build-Platform",
        "Crafter.Build-Interface",
        "Crafter.Build-Implementation",
        "Crafter.Build-External",
        "Crafter.Build-Clang",
        "Crafter.Build-Test",
        "Crafter.Build-Lint",
        "Crafter.Build-Script",
        "Crafter.Build-Progress",
        "Crafter.Build-Asset",
        "Crafter.Build",
    };

    // Returns the stamp of the module sources the cache was built from; it is
    // one of project.so's inputs.
    std::string EnsureCrafterBuildPcms(const fs::path& sourceDir, const fs::path& cacheDir, const Configuration& host) {
        CacheLock lock(cacheDir);
        // Re-derived under the lock: another builder may have refreshed the
        // cache from its own sources while we waited.
        // The std PCM is an input to every module PCM: its stamp is folded in
        // so a rebuilt std.pcm (a libc++ update under the same clang) rebuilds
        // them too, instead of leaving PCMs that import a std.pcm that is gone.
        std::string stamp = HashStamp(CrafterBuildSourceStamp(sourceDir, CrafterBuildModules) + '\0' + ReadStamp(StampPath(cacheDir / "std.pcm")));
        const bool upToDate = ReadStamp(CacheStampPath(cacheDir)) == stamp;
        for (std::string_view name : CrafterBuildModules) {
            fs::path cppmPath = sourceDir / std::format("{}.cppm", name);
            fs::path pcmPath = cacheDir / std::format("{}.pcm", name);
            if (!fs::exists(cppmPath)) {
                throw std::runtime_error(std::format("module source {} not found in {} (set CRAFTER_BUILD_HOME)", name, sourceDir.string()));
            }
            if (upToDate && fs::exists(pcmPath)) {
                continue;
            }
            std::string cmd = std::format(
                "{} --target={} -march=native -mtune=native "
                "-std=c++26 -O3 "
                "-Wno-reserved-identifier -Wno-reserved-module-identifier "
                "-fprebuilt-module-path={} "
                "--precompile {} -o {}",
                GetBaseCommand(host), host.target, cacheDir.string(), cppmPath.string(), pcmPath.string());
            CommandResult r = Crafter::RunCommandChecked(cmd);
            if (r.exitCode != 0) {
                throw std::runtime_error(std::format("Failed to precompile {} (exit {}): {}", name, r.exitCode, r.output));
            }
        }
        // Last, so an interrupted rebuild leaves the stamp disagreeing with the
        // sources and the next run starts over rather than trusting a half-built
        // set of PCMs.
        if (!upToDate) WriteStamp(CacheStampPath(cacheDir), stamp);
        return stamp;
    }
}

Configuration Crafter::LoadProject(const fs::path& projectFile, std::span<const std::string_view> args) {
    RequireToolchain();
    fs::path absProject = fs::canonical(projectFile);
    ProjectFileGuard guard(absProject);
    fs::path buildDir = absProject.parent_path() / "build";
    if (!fs::exists(buildDir)) {
        fs::create_directories(buildDir);
    }
    fs::path soPath = buildDir / std::format("{}.so", absProject.stem().string());

    fs::path sourceDir = Crafter::GetCrafterBuildHome();

    // The host toolchain's own triple (x86_64-pc-linux-gnu on glibc distros,
    // x86_64-alpine-linux-musl on Alpine): project.cpp and the module PCMs
    // it imports must be built for the libc crafter-build itself runs on.
    Configuration hostConfig;
    hostConfig.target = HostTarget();
    hostConfig.march = "native";
    hostConfig.mtune = "native";
    // The same directory Build() resolves the std PCM from, toolchain key
    // included (see StdPcmDir).
    fs::path cacheDir = StdPcmDir(hostConfig);
    if (!fs::exists(cacheDir)) fs::create_directories(cacheDir);

    std::string stdResult = BuildStdPcm(hostConfig, cacheDir / "std.pcm");
    if (!stdResult.empty()) {
        throw std::runtime_error(std::format("Failed to build std.pcm: {}", stdResult));
    }

    const std::string sourcesStamp = EnsureCrafterBuildPcms(sourceDir, cacheDir, hostConfig);

    // After the host PCMs exist (a dependency's build imports Crafter.Build
    // from that cache) and before the staleness check (its artifacts are
    // inputs to project.so). Built on every load, fresh or not: a dependency
    // BMI whose own imports were rebuilt underneath it doesn't fail cleanly,
    // clang crashes on it.
    ProjectFileDependencies preDeps = ResolveProjectFileDependencies(absProject, hostConfig);

    // -fuse-ld=lld like every other link the tool performs: lld is a hard
    // dependency, binutils' ld is not (Alpine's clang would default to it),
    // and a dependency archive built in release holds ThinLTO bitcode,
    // which GNU ld can't read.
    std::string compileCmd = std::format(
        "{} --target={} -march=native -mtune=native "
        "-std=c++26 -shared -fPIC -O3 -fuse-ld=lld "
        "-Wno-return-type-c-linkage "
        "-fprebuilt-module-path={}{} "
        "{} -o {}{}{}",
        GetBaseCommand(hostConfig), hostConfig.target, cacheDir.string(), preDeps.compileFlags,
        absProject.string(), soPath.string(), preDeps.linkFlags, GetToolchain().LibcxxLinkFlags());
    // What project.so was compiled against. The module source stamp stands
    // in for the executable: project.so resolves Crafter:: symbols from the
    // running binary, so only the declarations (the .cppm files) matter,
    // and an implementation-only rebuild of crafter-build leaves it valid.
    // The separators are appended, not written into a format string: a
    // format string is read as a C string, so one with "\0" in it ends at the
    // first NUL and everything after the version silently dropped out of the
    // stamp. A project.so compiled against other declarations (a Shader with
    // a different layout, say) was then loaded as current and corrupted the
    // heap.
    std::string projectStampInput(CrafterBuildVersion());
    for (std::string_view part : {std::string_view(GetToolchain().Key()), std::string_view(sourcesStamp), std::string_view(compileCmd)}) {
        projectStampInput += '\0';
        projectStampInput += part;
    }
    const std::string projectStamp = HashStamp(projectStampInput);

    if (ProjectFileStale(soPath, absProject, projectStamp, preDeps)) {
        std::string result = RunBuildCommand(compileCmd);
        if (!result.empty()) {
            throw std::runtime_error(std::format("Failed to compile project {}: {}", absProject.string(), result));
        }
        WriteStamp(StampPath(soPath), projectStamp);
    }

    void* handle = dlopen(soPath.c_str(), RTLD_NOW | RTLD_GLOBAL);
    if (!handle) {
        throw std::runtime_error(std::format("Failed to load project {}: {}", soPath.string(), dlerror()));
    }

    using ProjectFn = Configuration (*)(std::span<const std::string_view>);
    dlerror();
    auto fn = reinterpret_cast<ProjectFn>(dlsym(handle, "CrafterBuildProject"));
    if (const char* err = dlerror()) {
        throw std::runtime_error(std::format("CrafterBuildProject not found in {}: {}", soPath.string(), err));
    }

    guard.Frame().dependencies = std::move(preDeps.configs);
    return fn(args);
}