Crafter.Build/implementations/Crafter.Build-External.cpp

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

module Crafter.Build:External_impl;
import std;
import :External;
import :Toolchain;
import :Platform;
import :Progress;
import :Clang;
namespace fs = std::filesystem;
using namespace Crafter;

namespace {

std::string DeriveName(const GitSource& source) {
    std::string url = source.url;
    while (!url.empty() && (url.back() == '/' || url.back() == '\\')) url.pop_back();
    if (url.ends_with(".git")) url.resize(url.size() - 4);
    auto slash = url.find_last_of("/\\");
    return slash == std::string::npos ? url : url.substr(slash + 1);
}

std::string JoinOptions(std::span<const std::string> options) {
    std::string out;
    for (const std::string& opt : options) {
        if (!out.empty()) out += ' ';
        out += ShellQuote(opt);
    }
    return out;
}

std::string FetchGit(const GitSource& source, const fs::path& cloneDir) {
    auto runGit = [](std::string_view cmd) -> std::optional<std::string> {
        CommandResult r = RunCommandChecked(cmd);
        if (r.exitCode != 0) return std::format("`{}` failed (exit {}): {}", cmd, r.exitCode, r.output);
        return std::nullopt;
    };
    // Submodules follow the checkout only when asked to: after every clone,
    // switch, checkout or pull, so they match the revision that was fetched
    // instead of whichever one was checked out before, from the URLs that
    // revision's .gitmodules gives (sync). A no-op, and offline, when they
    // already match, which puts back submodules moved by hand; and no git at
    // all without any.
    auto updateSubmodules = [&runGit](const fs::path& dir) -> std::optional<std::string> {
        if (!fs::exists(dir / ".gitmodules")) return std::nullopt;
        const std::string quoted = ShellQuote(dir.string());
        if (auto err = runGit(std::format("git -C {} submodule sync --recursive", quoted))) return err;
        return runGit(std::format("git -C {} submodule update --init --recursive", quoted));
    };

    if (fs::exists(cloneDir)) {
        CommandResult remote = RunCommandChecked(std::format("git -C {} remote get-url origin", ShellQuote(cloneDir.string())));
        std::string currentUrl = remote.output;
        while (!currentUrl.empty() && (currentUrl.back() == '\n' || currentUrl.back() == '\r')) currentUrl.pop_back();
        if (remote.exitCode != 0 || currentUrl != source.url) {
            fs::remove_all(cloneDir);
        } else if (!source.commit.empty()) {
            CommandResult head = RunCommandChecked(std::format("git -C {} rev-parse HEAD", ShellQuote(cloneDir.string())));
            std::string currentHead = head.output;
            while (!currentHead.empty() && (currentHead.back() == '\n' || currentHead.back() == '\r')) currentHead.pop_back();
            if (head.exitCode == 0 && currentHead != source.commit) {
                if (auto err = runGit(std::format("git -C {} fetch origin", ShellQuote(cloneDir.string())))) return *err;
                if (auto err = runGit(std::format("git -C {} checkout {}", ShellQuote(cloneDir.string()), ShellQuote(source.commit)))) return *err;
            }
            // Also when the commit already matched: a clone made before
            // submodules were updated has them at the default branch's.
            if (auto err = updateSubmodules(cloneDir)) return *err;
            return "";
        } else {
            // No commit pinned — pull latest. The user opted into "track latest"
            // by not pinning; the cost is one network round-trip per build.
            // Pin source.commit to a SHA for reproducible, offline-capable builds.
            if (!source.branch.empty()) {
                if (auto err = runGit(std::format("git -C {} pull origin {}", ShellQuote(cloneDir.string()), ShellQuote(source.branch)))) return *err;
            } else {
                if (auto err = runGit(std::format("git -C {} pull", ShellQuote(cloneDir.string())))) return *err;
            }
            if (auto err = updateSubmodules(cloneDir)) return *err;
            return "";
        }
    }

    // Random per-invocation tmp suffix so concurrent crafter-build processes
    // resolving to the same cache key don't share an in-flight `.tmp`
    // directory — git's pack tempfiles would get yanked when one process
    // removes or renames the dir out from under the other.
    std::random_device rd;
    fs::path tmpDir = cloneDir;
    tmpDir += std::format(".tmp.{:08x}{:08x}", rd(), rd());

    // Not --recursive: that checks out the default branch's submodules, and
    // the requested revision's come once it is checked out.
    if (auto err = runGit(std::format("git clone {} {}", ShellQuote(source.url), ShellQuote(tmpDir.string())))) {
        if (fs::exists(tmpDir)) fs::remove_all(tmpDir);
        return *err;
    }
    if (!source.branch.empty()) {
        if (auto err = runGit(std::format("git -C {} switch {}", ShellQuote(tmpDir.string()), ShellQuote(source.branch)))) {
            fs::remove_all(tmpDir);
            return *err;
        }
    }
    if (!source.commit.empty()) {
        if (auto err = runGit(std::format("git -C {} checkout {}", ShellQuote(tmpDir.string()), ShellQuote(source.commit)))) {
            fs::remove_all(tmpDir);
            return *err;
        }
    }
    if (auto err = updateSubmodules(tmpDir)) {
        fs::remove_all(tmpDir);
        return *err;
    }

    std::error_code ec;
    fs::rename(tmpDir, cloneDir, ec);
    if (ec) {
        fs::remove_all(tmpDir);
        // If a concurrent build won the race, cloneDir now exists with the
        // same source revision (cache key includes url+branch+commit), so
        // discard our clone and reuse theirs.
        if (fs::exists(cloneDir)) return "";
        return std::format("rename {} -> {} failed: {}", tmpDir.string(), cloneDir.string(), ec.message());
    }
    return "";
}

std::string BuildInjectedCMakeFlags(const fs::path& cmakeBuildDir, std::string_view target) {
    std::string out;
    // Without an explicit build type, some packages (glslang) append a 'd'
    // suffix to library names assuming a debug build, breaking -l<name>
    // linking. Pin to Release.
    out += " -DCMAKE_BUILD_TYPE=Release";
    const Toolchain& tc = GetToolchain();
    out += std::format(" -DCMAKE_C_COMPILER={}", ShellQuote(tc.clang.string()));
    out += std::format(" -DCMAKE_CXX_COMPILER={}", ShellQuote(tc.clangxx.string()));
    // Stdlib choice: libc++ for Linux targets (matches how crafter-build
    // itself is built with -stdlib=libc++); the mingw cross-compile uses the
    // libstdc++ shipped by the mingw-w64 toolchain, so it keeps the default.
    if (target.ends_with("-linux-gnu") || target.ends_with("-linux-musl")) {
        out += std::format(" -DCMAKE_CXX_FLAGS={}", ShellQuote(std::format("-stdlib=libc++{}", tc.LibcxxCompileFlags())));
        out += std::format(" -DCMAKE_EXE_LINKER_FLAGS={}", ShellQuote(std::format("-stdlib=libc++{}", tc.LibcxxLinkFlags())));
        out += std::format(" -DCMAKE_SHARED_LINKER_FLAGS={}", ShellQuote(std::format("-stdlib=libc++{}", tc.LibcxxLinkFlags())));
    }
    if (target == "x86_64-w64-mingw32") {
        out += " -DCMAKE_SYSTEM_NAME=Windows";
        out += std::format(" -DCMAKE_C_COMPILER_TARGET={}", target);
        out += std::format(" -DCMAKE_CXX_COMPILER_TARGET={}", target);
        // The libstdc++ and the mingw-w64 install the project's own compiles
        // use (GetBaseCommand).
        out += " -DCMAKE_CXX_FLAGS=-stdlib=libstdc++";
        if (const fs::path& sysroot = MingwSysroot(); !sysroot.empty()) out += std::format(" -DCMAKE_SYSROOT={}", ShellQuote(sysroot.string()));
    }
    fs::path absBuildDir = fs::absolute(cmakeBuildDir);
    out += std::format(" -DCMAKE_ARCHIVE_OUTPUT_DIRECTORY={}", ShellQuote(absBuildDir.string()));
    out += std::format(" -DCMAKE_LIBRARY_OUTPUT_DIRECTORY={}", ShellQuote(absBuildDir.string()));
    return out;
}

std::string ConfigureCMake(const fs::path& cloneDir, const fs::path& cmakeBuildDir, std::span<const std::string> options, std::string_view target) {
    fs::path optionsFile = cmakeBuildDir / ".crafter-options";
    std::string optionsKey = JoinOptions(options);
    // The injected flags are inputs too: a different compiler or libc++
    // must reconfigure rather than reuse a CMakeCache made with the old one.
    const std::string injected = BuildInjectedCMakeFlags(cmakeBuildDir, target);
    const std::string configureKey = injected + '\n' + optionsKey;

    bool needsConfigure = !fs::exists(cmakeBuildDir / "CMakeCache.txt");
    if (!needsConfigure) {
        std::ifstream existing(optionsFile);
        if (!existing) {
            needsConfigure = true;
        } else {
            std::stringstream buf;
            buf << existing.rdbuf();
            if (buf.str() != configureKey) needsConfigure = true;
        }
    }

    if (!needsConfigure) return "";

    if (!fs::exists(cmakeBuildDir)) fs::create_directories(cmakeBuildDir);

    std::string cmd = std::format("cmake -S {} -B {}{}", ShellQuote(fs::absolute(cloneDir).string()), ShellQuote(fs::absolute(cmakeBuildDir).string()), injected);
    if (!options.empty()) {
        cmd += " ";
        cmd += optionsKey;
    }

    CommandResult r = RunCommandChecked(cmd);
    if (r.exitCode != 0) {
        return std::format("cmake configure failed (exit {}): {}", r.exitCode, r.output);
    }

    std::ofstream(optionsFile) << configureKey;
    return "";
}

std::string BuildCMake(const fs::path& cmakeBuildDir) {
    // Without --parallel, the Unix Makefiles generator builds one translation
    // unit at a time, leaving every core but one idle. Pass an explicit job
    // count (a bare --parallel maps to an unbounded `make -j` fork bomb on the
    // Makefiles generator) so deps like DPP/msquic/glslang compile ~N× faster.
    std::uint32_t jobs = std::max(1u, std::thread::hardware_concurrency());
    std::string cmd = std::format("cmake --build {} --parallel {}", ShellQuote(fs::absolute(cmakeBuildDir).string()), jobs);
    CommandResult r = RunCommandChecked(cmd);
    if (r.exitCode != 0) {
        return std::format("cmake --build failed (exit {}): {}", r.exitCode, r.output);
    }
    return "";
}

}  // namespace

fs::path Crafter::ExternalCloneDir(const ExternalDependency& dep, std::string_view target) {
    std::string name = dep.name.empty() ? DeriveName(dep.source) : dep.name;
    if (name.empty()) return {};
    std::string keyMaterial = std::format("{}|{}|{}|{}|{}", dep.source.url, dep.source.branch, dep.source.commit, JoinOptions(dep.options), target);
    std::size_t key = std::hash<std::string>{}(keyMaterial);
    return GetCacheDir() / "external" / std::format("{}-{:016x}", name, key);
}

std::vector<std::string> Crafter::ExternalIncludeFlags(const ExternalDependency& dep, std::string_view target) {
    std::vector<std::string> flags;
    fs::path cloneDir = ExternalCloneDir(dep, target);
    if (cloneDir.empty()) return flags;
    for (const fs::path& include : dep.includeDirs) {
        fs::path full = include.empty() ? cloneDir : cloneDir / include;
        flags.push_back(std::format("-I{}", fs::absolute(full).string()));
    }
    return flags;
}

fs::path Crafter::ExternalBuildDir(const ExternalDependency& dep, std::string_view target) {
    fs::path cloneDir = ExternalCloneDir(dep, target);
    if (cloneDir.empty() || dep.builder != ExternalBuilder::CMake) return cloneDir;
    return cloneDir / "build";
}

std::string Crafter::BuildExternal(const ExternalDependency& dep, std::string_view target) {
    std::string name = dep.name.empty() ? DeriveName(dep.source) : dep.name;
    if (name.empty()) {
        return std::format("Could not derive name for external dependency from URL '{}'", dep.source.url);
    }

    fs::path externalRoot = GetCacheDir() / "external";
    if (!fs::exists(externalRoot)) {
        std::error_code ec;
        fs::create_directories(externalRoot, ec);
        if (ec) {
            return std::format("Failed to create {}: {}", externalRoot.string(), ec.message());
        }
    }

    fs::path cloneDir = ExternalCloneDir(dep, target);
    // Build() makes one call for all the configurations of a pass, but two
    // crafter-builds, or two passes, can still reach the same clone at once,
    // and two pulls in one clone race on its .git/FETCH_HEAD.
    FileLock lock(fs::path(std::format("{}.lock", cloneDir.string())));

    if (std::string err = FetchGit(dep.source, cloneDir); !err.empty()) {
        return std::format("git fetch for '{}': {}", name, err);
    }
    if (dep.builder != ExternalBuilder::CMake) return "";

    const fs::path cmakeBuildDir = ExternalBuildDir(dep, target);
    if (std::string err = ConfigureCMake(cloneDir, cmakeBuildDir, dep.options, target); !err.empty()) {
        return std::format("cmake configure for '{}': {}", name, err);
    }
    if (std::string err = BuildCMake(cmakeBuildDir); !err.empty()) {
        return std::format("cmake build for '{}': {}", name, err);
    }
    return "";
}

ExternalBuildResult Crafter::ExternalOutputs(const ExternalDependency& dep, std::string_view target) {
    ExternalBuildResult result;
    result.compileFlags = ExternalIncludeFlags(dep, target);

    const fs::path cmakeBuildDir = ExternalBuildDir(dep, target);
    if (dep.builder != ExternalBuilder::CMake || cmakeBuildDir.empty()) return result;

    // Each search path gets both a -L (link-time) and a -Wl,-rpath
    // (runtime-loader). The rpath stays embedded in the produced
    // binary so it picks up shared deps from the cache without any
    // LD_LIBRARY_PATH gymnastics. Static deps (.a) ignore the rpath
    // harmlessly. The PE/COFF target (mingw) resolves DLLs via PATH or
    // adjacency rather than rpath, so lld warns if we pass it.
    const bool isPe = target == "x86_64-w64-mingw32";
    std::string buildDirAbs = fs::absolute(cmakeBuildDir).string();
    result.linkFlags.push_back(std::format("-L{}", buildDirAbs));
    if (!isPe) result.linkFlags.push_back(std::format("-Wl,-rpath,{}", buildDirAbs));
    for (const fs::path& libDir : dep.libDirs) {
        fs::path full = libDir.is_absolute() ? libDir : cmakeBuildDir / libDir;
        std::string fullAbs = fs::absolute(full).string();
        result.linkFlags.push_back(std::format("-L{}", fullAbs));
        if (!isPe) result.linkFlags.push_back(std::format("-Wl,-rpath,{}", fullAbs));
    }
    for (const std::string& lib : dep.libs) {
        result.linkFlags.push_back(std::format("-l{}", lib));
    }

    // The newest library in every directory the link searches: the build
    // directory and the libDirs, where projects like msquic put theirs,
    // versioned names (libmsquic.so.2) included.
    auto isLibrary = [](const std::string& name) {
        return name.ends_with(".a") || name.ends_with(".so") || name.contains(".so.") || name.ends_with(".dll");
    };
    std::vector<fs::path> searched = { cmakeBuildDir };
    for (const fs::path& libDir : dep.libDirs) searched.push_back(libDir.is_absolute() ? libDir : cmakeBuildDir / libDir);
    for (const fs::path& dir : searched) {
        std::error_code listEc;
        for (fs::directory_iterator it(dir, listEc), end; !listEc && it != end; it.increment(listEc)) {
            std::error_code ec;
            if (!it->is_regular_file(ec) || !isLibrary(it->path().filename().string())) continue;
            fs::file_time_type t = it->last_write_time(ec);
            if (!ec && t > result.latestArtifact) result.latestArtifact = t;
        }
    }

    return result;
}

namespace {
    std::mutex ProjectCacheMutex;
    std::unordered_map<std::string, std::unique_ptr<Configuration>> ProjectCache;
    // Keyed by the Configurations ProjectCache owns, which live as long as
    // the process does, so the pointers never dangle. Guarded by
    // ProjectCacheMutex as well.
    std::unordered_map<const Configuration*, LoadedProject> LoadedProjects;

    // Run the dep's project.cpp from its own directory so its relative paths
    // (cfg.path = "./", interfaces/, lib/, ...) resolve against the dep
    // root, then rebase cfg.path and all other relative path collections to
    // absolute so Build() can run from any cwd without misresolving them.
    // The mutex is NOT held across LoadProject — the dep may itself call
    // GitProject/LocalProject, and a non-recursive lock would deadlock.
    Configuration LoadProjectFromRoot(const fs::path& projectPath, const fs::path& depRoot, std::span<const std::string_view> args) {
        fs::path savedCwd = fs::current_path();
        Configuration cfg;
        fs::current_path(depRoot);
        try {
            cfg = LoadProject(projectPath, args);
        } catch (...) {
            fs::current_path(savedCwd);
            throw;
        }
        fs::current_path(savedCwd);
        cfg.path = fs::absolute(depRoot / cfg.path).lexically_normal();
        auto abs = [&](const fs::path& p) -> fs::path {
            return p.is_absolute() ? p : fs::absolute(depRoot / p).lexically_normal();
        };
        for (fs::path& p : cfg.cFiles)  p = abs(p);
        for (fs::path& p : cfg.cuda)    p = abs(p);
        for (fs::path& p : cfg.files)   p = abs(p);
        for (fs::path& p : cfg.buildFiles) p = abs(p);
        for (Shader& s : cfg.shaders)   s.path = abs(s.path);
        return cfg;
    }

    // Into ProjectCache under `fullHash`, with `loaded` recorded beside it.
    // When another thread stored the same spec first, its Configuration
    // wins and `cfg` is dropped.
    Configuration* StoreProject(std::string fullHash, Configuration cfg, LoadedProject loaded) {
        std::lock_guard lock(ProjectCacheMutex);
        if (auto it = ProjectCache.find(fullHash); it != ProjectCache.end()) {
            return it->second.get();
        }
        auto stored = std::make_unique<Configuration>(std::move(cfg));
        Configuration* ptr = stored.get();
        ProjectCache.emplace(std::move(fullHash), std::move(stored));
        LoadedProjects.emplace(ptr, std::move(loaded));
        return ptr;
    }

    // `url` as it names a repository: without user info, which is where a
    // token goes, and without trailing slashes or ".git", so specs that only
    // spell the repository differently name the same one.
    std::string RepositoryKey(std::string_view url) {
        std::string key(url);
        if (const std::size_t scheme = key.find("://"); scheme != std::string::npos) {
            const std::size_t host = scheme + 3;
            const std::size_t at = key.rfind('@', key.find('/', host));
            if (at != std::string::npos && at >= host) key.erase(host, at + 1 - host);
        }
        while (key.ends_with('/')) key.pop_back();
        if (key.ends_with(".git")) key.resize(key.size() - 4);
        return key;
    }
}

Configuration* Crafter::GitProject(const GitProjectSpec& spec) {
    // Two hashes: the clone is shared across specs that point at the same
    // source revision (forwarded args don't change what gets cloned, just
    // how the dep's project.cpp interprets them at runtime), while the
    // in-memory Configuration is keyed by the full spec so each (args)
    // permutation gets its own Configuration object, and host tooling one
    // apart from the target's even for the same args.
    std::string srcKey = std::format("git|{}|{}|{}|{}", spec.source.url, spec.source.branch, spec.source.commit, spec.projectFile.string());
    std::string srcHash = std::format("{:016x}", std::hash<std::string>{}(srcKey));

    std::string fullKey = std::format("{}{}", LoadingHostTooling() ? "host|" : "", srcKey);
    for (const std::string& a : spec.args) {
        fullKey += '|';
        fullKey += a;
    }
    std::string fullHash = std::format("{:016x}", std::hash<std::string>{}(fullKey));

    {
        std::lock_guard lock(ProjectCacheMutex);
        if (auto it = ProjectCache.find(fullHash); it != ProjectCache.end()) {
            return it->second.get();
        }
    }

    std::string name = DeriveName(spec.source);
    if (name.empty()) {
        throw std::runtime_error(std::format("GitProject: could not derive name from URL '{}'", spec.source.url));
    }

    fs::path externalRoot = GetCacheDir() / "external";
    fs::create_directories(externalRoot);
    fs::path cloneDir = externalRoot / std::format("{}-{}", name, srcHash);

    {
        // One fetch of a clone at a time, as in BuildExternal.
        FileLock lock(fs::path(std::format("{}.lock", cloneDir.string())));
        const bool exists = fs::exists(cloneDir);
        Progress::Task task(std::format("{} {}", exists ? "Updating" : "Cloning", name));
        if (std::string err = FetchGit(spec.source, cloneDir); !err.empty()) {
            throw std::runtime_error(std::format("GitProject({}): {}", spec.source.url, err));
        }
    }

    fs::path projectPath = cloneDir / spec.projectFile;
    if (!fs::exists(projectPath)) {
        throw std::runtime_error(std::format("GitProject({}): {} not found in clone", spec.source.url, spec.projectFile.string()));
    }

    std::vector<std::string_view> argViews(spec.args.begin(), spec.args.end());
    Configuration cfg = LoadProjectFromRoot(projectPath, cloneDir, argViews);

    const fs::path projectInRepo = spec.projectFile.lexically_normal();
    const fs::path below = projectInRepo.parent_path();
    return StoreProject(std::move(fullHash), std::move(cfg), {
        .projectFile = projectPath.lexically_normal(),
        .name = below.empty() ? name : std::format("{}/{}", name, below.generic_string()),
        .identity = std::format("git|{}|{}", RepositoryKey(spec.source.url), projectInRepo.generic_string()),
    });
}

fs::path Crafter::GitFetch(const GitSource& source) {
    std::string name = DeriveName(source);
    if (name.empty()) {
        throw std::runtime_error(std::format("GitFetch: could not derive name from URL '{}'", source.url));
    }
    fs::path externalRoot = GetCacheDir() / "external";
    std::error_code ec;
    fs::create_directories(externalRoot, ec);
    if (ec) {
        throw std::runtime_error(std::format("GitFetch: failed to create {}: {}", externalRoot.string(), ec.message()));
    }
    std::string keyMaterial = std::format("git|{}|{}|{}", source.url, source.branch, source.commit);
    std::size_t key = std::hash<std::string>{}(keyMaterial);
    fs::path cloneDir = externalRoot / std::format("{}-{:016x}", name, key);

    {
        // One fetch of a clone at a time, as in BuildExternal.
        FileLock lock(fs::path(std::format("{}.lock", cloneDir.string())));
        const bool exists = fs::exists(cloneDir);
        Progress::Task task(std::format("{} {}", exists ? "Updating" : "Cloning", name));
        if (std::string err = FetchGit(source, cloneDir); !err.empty()) {
            throw std::runtime_error(std::format("GitFetch({}): {}", source.url, err));
        }
    }
    return cloneDir;
}

Configuration* Crafter::LocalProject(const LocalProjectSpec& spec) {
    fs::path projectPath = fs::absolute(spec.projectFile).lexically_normal();
    if (!fs::exists(projectPath)) {
        throw std::runtime_error(std::format("LocalProject: {} not found", projectPath.string()));
    }
    fs::path canonical = fs::canonical(projectPath);

    std::string fullKey = std::format("{}local|{}", LoadingHostTooling() ? "host|" : "", canonical.string());
    for (const std::string& a : spec.args) {
        fullKey += '|';
        fullKey += a;
    }
    std::string fullHash = std::format("{:016x}", std::hash<std::string>{}(fullKey));

    {
        std::lock_guard lock(ProjectCacheMutex);
        if (auto it = ProjectCache.find(fullHash); it != ProjectCache.end()) {
            return it->second.get();
        }
    }

    fs::path depRoot = canonical.parent_path();
    std::vector<std::string_view> argViews(spec.args.begin(), spec.args.end());
    Configuration cfg = LoadProjectFromRoot(canonical, depRoot, argViews);

    return StoreProject(std::move(fullHash), std::move(cfg), {
        .projectFile = canonical,
        .name = depRoot.filename().string(),
        .identity = std::format("local|{}", canonical.string()),
    });
}

std::optional<LoadedProject> Crafter::LoadedProjectOf(const Configuration& cfg) {
    std::lock_guard lock(ProjectCacheMutex);
    if (auto it = LoadedProjects.find(&cfg); it != LoadedProjects.end()) return it->second;
    return std::nullopt;
}