Bootstrap GnuPG and `file` on Windows (#41810)

Spack can now bootstrap two new dependencies on Windows: GnuPG, and file. 

These dependencies are modeled as a separate package, and they install a cross-compiled binary.
Details on how they binaries are built are in https://github.com/spack/windows-bootstrap-resources

8 files changed, 130 insertions, 83 deletions

diff --git a/lib/spack/llnl/util/filesystem.py b/lib/spack/llnl/util/filesystem.py
index 308c6154e1..54ace7d42f 100644
--- a/lib/spack/llnl/util/filesystem.py
+++ b/lib/spack/llnl/util/filesystem.py
@@ -27,8 +27,6 @@ from llnl.util import tty
 from llnl.util.lang import dedupe, memoized
 from llnl.util.symlink import islink, readlink, resolve_link_target_relative_to_the_link, symlink
 
-from spack.util.executable import Executable, which
-
 from ..path import path_to_os_path, system_path_filter
 
 if sys.platform != "win32":
@@ -53,7 +51,6 @@ __all__ = [
     "find_all_headers",
     "find_libraries",
     "find_system_libraries",
-    "fix_darwin_install_name",
     "force_remove",
     "force_symlink",
     "getuid",
@@ -248,42 +245,6 @@ def path_contains_subdirectory(path, root):
     return norm_path.startswith(norm_root)
 
 
-@memoized
-def file_command(*args):
-    """Creates entry point to `file` system command with provided arguments"""
-    file_cmd = which("file", required=True)
-    for arg in args:
-        file_cmd.add_default_arg(arg)
-    return file_cmd
-
-
-@memoized
-def _get_mime_type():
-    """Generate method to call `file` system command to aquire mime type
-    for a specified path
-    """
-    if sys.platform == "win32":
-        # -h option (no-dereference) does not exist in Windows
-        return file_command("-b", "--mime-type")
-    else:
-        return file_command("-b", "-h", "--mime-type")
-
-
-def mime_type(filename):
-    """Returns the mime type and subtype of a file.
-
-    Args:
-        filename: file to be analyzed
-
-    Returns:
-        Tuple containing the MIME type and subtype
-    """
-    output = _get_mime_type()(filename, output=str, error=str).strip()
-    tty.debug("==> " + output)
-    type, _, subtype = output.partition("/")
-    return type, subtype
-
-
 #: This generates the library filenames that may appear on any OS.
 library_extensions = ["a", "la", "so", "tbd", "dylib"]
 
@@ -1679,41 +1640,6 @@ def safe_remove(*files_or_dirs):
         raise
 
 
-@system_path_filter
-def fix_darwin_install_name(path):
-    """Fix install name of dynamic libraries on Darwin to have full path.
-
-    There are two parts of this task:
-
-    1. Use ``install_name('-id', ...)`` to change install name of a single lib
-    2. Use ``install_name('-change', ...)`` to change the cross linking between
-       libs. The function assumes that all libraries are in one folder and
-       currently won't follow subfolders.
-
-    Parameters:
-        path (str): directory in which .dylib files are located
-    """
-    libs = glob.glob(join_path(path, "*.dylib"))
-    for lib in libs:
-        # fix install name first:
-        install_name_tool = Executable("install_name_tool")
-        install_name_tool("-id", lib, lib)
-        otool = Executable("otool")
-        long_deps = otool("-L", lib, output=str).split("\n")
-        deps = [dep.partition(" ")[0][1::] for dep in long_deps[2:-1]]
-        # fix all dependencies:
-        for dep in deps:
-            for loc in libs:
-                # We really want to check for either
-                #     dep == os.path.basename(loc)   or
-                #     dep == join_path(builddir, os.path.basename(loc)),
-                # but we don't know builddir (nor how symbolic links look
-                # in builddir). We thus only compare the basenames.
-                if os.path.basename(dep) == os.path.basename(loc):
-                    install_name_tool("-change", dep, loc, lib)
-                    break
-
-
 def find_first(root: str, files: Union[Iterable[str], str], bfs_depth: int = 2) -> Optional[str]:
     """Find the first file matching a pattern.
 
diff --git a/lib/spack/spack/binary_distribution.py b/lib/spack/spack/binary_distribution.py
index 8d3c3cfb7a..15189f9d43 100644
--- a/lib/spack/spack/binary_distribution.py
+++ b/lib/spack/spack/binary_distribution.py
@@ -54,6 +54,7 @@ import spack.user_environment
 import spack.util.archive
 import spack.util.crypto
 import spack.util.file_cache as file_cache
+import spack.util.filesystem as ssys
 import spack.util.gpg
 import spack.util.parallel
 import spack.util.path
@@ -687,7 +688,7 @@ def get_buildfile_manifest(spec):
     # Non-symlinks.
     for rel_path in visitor.files:
         abs_path = os.path.join(root, rel_path)
-        m_type, m_subtype = fsys.mime_type(abs_path)
+        m_type, m_subtype = ssys.mime_type(abs_path)
 
         if relocate.needs_binary_relocation(m_type, m_subtype):
             # Why is this branch not part of needs_binary_relocation? :(
diff --git a/lib/spack/spack/bootstrap/__init__.py b/lib/spack/spack/bootstrap/__init__.py
index 85935cd0e0..d710caee68 100644
--- a/lib/spack/spack/bootstrap/__init__.py
+++ b/lib/spack/spack/bootstrap/__init__.py
@@ -9,6 +9,7 @@ from .core import (
     all_core_root_specs,
     ensure_clingo_importable_or_raise,
     ensure_core_dependencies,
+    ensure_file_in_path_or_raise,
     ensure_gpg_in_path_or_raise,
     ensure_patchelf_in_path_or_raise,
 )
@@ -19,6 +20,7 @@ __all__ = [
     "is_bootstrapping",
     "ensure_bootstrap_configuration",
     "ensure_core_dependencies",
+    "ensure_file_in_path_or_raise",
     "ensure_gpg_in_path_or_raise",
     "ensure_clingo_importable_or_raise",
     "ensure_patchelf_in_path_or_raise",
diff --git a/lib/spack/spack/bootstrap/core.py b/lib/spack/spack/bootstrap/core.py
index 62b6b86570..02909cbdf7 100644
--- a/lib/spack/spack/bootstrap/core.py
+++ b/lib/spack/spack/bootstrap/core.py
@@ -472,7 +472,8 @@ def ensure_clingo_importable_or_raise() -> None:
 
 def gnupg_root_spec() -> str:
     """Return the root spec used to bootstrap GnuPG"""
-    return _root_spec("gnupg@2.3:")
+    root_spec_name = "win-gpg" if IS_WINDOWS else "gnupg"
+    return _root_spec(f"{root_spec_name}@2.3:")
 
 
 def ensure_gpg_in_path_or_raise() -> None:
@@ -482,6 +483,19 @@ def ensure_gpg_in_path_or_raise() -> None:
     )
 
 
+def file_root_spec() -> str:
+    """Return the root spec used to bootstrap file"""
+    root_spec_name = "win-file" if IS_WINDOWS else "file"
+    return _root_spec(root_spec_name)
+
+
+def ensure_file_in_path_or_raise() -> None:
+    """Ensure file is in the PATH or raise"""
+    return ensure_executables_in_path_or_raise(
+        executables=["file"], abstract_spec=file_root_spec()
+    )
+
+
 def patchelf_root_spec() -> str:
     """Return the root spec used to bootstrap patchelf"""
     # 0.13.1 is the last version not to require C++17.
@@ -565,14 +579,15 @@ def ensure_core_dependencies() -> None:
     """Ensure the presence of all the core dependencies."""
     if sys.platform.lower() == "linux":
         ensure_patchelf_in_path_or_raise()
-    if not IS_WINDOWS:
-        ensure_gpg_in_path_or_raise()
+    elif sys.platform == "win32":
+        ensure_file_in_path_or_raise()
+    ensure_gpg_in_path_or_raise()
     ensure_clingo_importable_or_raise()
 
 
 def all_core_root_specs() -> List[str]:
     """Return a list of all the core root specs that may be used to bootstrap Spack"""
-    return [clingo_root_spec(), gnupg_root_spec(), patchelf_root_spec()]
+    return [clingo_root_spec(), gnupg_root_spec(), patchelf_root_spec(), file_root_spec()]
 
 
 def bootstrapping_sources(scope: Optional[str] = None):
diff --git a/lib/spack/spack/bootstrap/status.py b/lib/spack/spack/bootstrap/status.py
index 582927af6e..6d3270b42c 100644
--- a/lib/spack/spack/bootstrap/status.py
+++ b/lib/spack/spack/bootstrap/status.py
@@ -88,7 +88,7 @@ def _core_requirements() -> List[RequiredResponseType]:
 
 def _buildcache_requirements() -> List[RequiredResponseType]:
     _buildcache_exes = {
-        "file": _missing("file", "required to analyze files for buildcaches"),
+        "file": _missing("file", "required to analyze files for buildcaches", system_only=False),
         ("gpg2", "gpg"): _missing("gpg2", "required to sign/verify buildcaches", False),
     }
     if platform.system().lower() == "darwin":
diff --git a/lib/spack/spack/package.py b/lib/spack/spack/package.py
index d0b7beda1d..99135b4834 100644
--- a/lib/spack/spack/package.py
+++ b/lib/spack/spack/package.py
@@ -104,6 +104,7 @@ from spack.package_base import (
 from spack.spec import InvalidSpecDetected, Spec
 from spack.util.cpus import determine_number_of_jobs
 from spack.util.executable import *
+from spack.util.filesystem import file_command, fix_darwin_install_name, mime_type
 from spack.variant import (
     any_combination_of,
     auto_or_any_combination_of,
diff --git a/lib/spack/spack/relocate.py b/lib/spack/spack/relocate.py
index 357dd92f84..364e72f7c3 100644
--- a/lib/spack/spack/relocate.py
+++ b/lib/spack/spack/relocate.py
@@ -12,7 +12,6 @@ from typing import List, Optional
 import macholib.mach_o
 import macholib.MachO
 
-import llnl.util.filesystem as fs
 import llnl.util.lang
 import llnl.util.tty as tty
 from llnl.util.lang import memoized
@@ -25,6 +24,7 @@ import spack.spec
 import spack.store
 import spack.util.elf as elf
 import spack.util.executable as executable
+import spack.util.filesystem as ssys
 import spack.util.path
 
 from .relocate_text import BinaryFilePrefixReplacer, TextFilePrefixReplacer
@@ -664,7 +664,7 @@ def is_binary(filename):
     Returns:
         True or False
     """
-    m_type, _ = fs.mime_type(filename)
+    m_type, _ = ssys.mime_type(filename)
 
     msg = "[{0}] -> ".format(filename)
     if m_type == "application":
@@ -692,7 +692,7 @@ def fixup_macos_rpath(root, filename):
         True if fixups were applied, else False
     """
     abspath = os.path.join(root, filename)
-    if fs.mime_type(abspath) != ("application", "x-mach-binary"):
+    if ssys.mime_type(abspath) != ("application", "x-mach-binary"):
         return False
 
     # Get Mach-O header commands
diff --git a/lib/spack/spack/util/filesystem.py b/lib/spack/spack/util/filesystem.py
new file mode 100644
index 0000000000..b296438fe8
--- /dev/null
+++ b/lib/spack/spack/util/filesystem.py
@@ -0,0 +1,102 @@
+# Copyright 2013-2024 Lawrence Livermore National Security, LLC and other
+# Spack Project Developers. See the top-level COPYRIGHT file for details.
+#
+# SPDX-License-Identifier: (Apache-2.0 OR MIT)
+
+"""
+Utilities for interacting with files,
+like those in llnl.util.filesystem, but which require logic from spack.util
+"""
+
+import glob
+import os
+import sys
+
+from llnl.util import tty
+from llnl.util.filesystem import join_path
+from llnl.util.lang import memoized
+
+from spack.util.executable import Executable, which
+
+
+def _ensure_file_on_win():
+    """Ensures the file command is available on Windows
+    If not, it is bootstrapped.
+    No-op on all other platforms"""
+    if sys.platform != "win32":
+        return
+    import spack.bootstrap
+
+    with spack.bootstrap.ensure_bootstrap_configuration():
+        spack.bootstrap.ensure_file_in_path_or_raise()
+
+
+@memoized
+def file_command(*args):
+    """Creates entry point to `file` system command with provided arguments"""
+    _ensure_file_on_win()
+    file_cmd = which("file", required=True)
+    for arg in args:
+        file_cmd.add_default_arg(arg)
+    return file_cmd
+
+
+@memoized
+def _get_mime_type():
+    """Generate method to call `file` system command to aquire mime type
+    for a specified path
+    """
+    if sys.platform == "win32":
+        # -h option (no-dereference) does not exist in Windows
+        return file_command("-b", "--mime-type")
+    else:
+        return file_command("-b", "-h", "--mime-type")
+
+
+def mime_type(filename):
+    """Returns the mime type and subtype of a file.
+
+    Args:
+        filename: file to be analyzed
+
+    Returns:
+        Tuple containing the MIME type and subtype
+    """
+    output = _get_mime_type()(filename, output=str, error=str).strip()
+    tty.debug("==> " + output)
+    type, _, subtype = output.partition("/")
+    return type, subtype
+
+
+def fix_darwin_install_name(path):
+    """Fix install name of dynamic libraries on Darwin to have full path.
+
+    There are two parts of this task:
+
+    1. Use ``install_name('-id', ...)`` to change install name of a single lib
+    2. Use ``install_name('-change', ...)`` to change the cross linking between
+       libs. The function assumes that all libraries are in one folder and
+       currently won't follow subfolders.
+
+    Parameters:
+        path (str): directory in which .dylib files are located
+    """
+    libs = glob.glob(join_path(path, "*.dylib"))
+    for lib in libs:
+        # fix install name first:
+        install_name_tool = Executable("install_name_tool")
+        install_name_tool("-id", lib, lib)
+        otool = Executable("otool")
+        long_deps = otool("-L", lib, output=str).split("\n")
+        deps = [dep.partition(" ")[0][1::] for dep in long_deps[2:-1]]
+        # fix all dependencies:
+        for dep in deps:
+            for loc in libs:
+                # We really want to check for either
+                #     dep == os.path.basename(loc)   or
+                #     dep == join_path(builddir, os.path.basename(loc)),
+                # but we don't know builddir (nor how symbolic links look
+                # in builddir). We thus only compare the basenames.
+                if os.path.basename(dep) == os.path.basename(loc):
+                    install_name_tool("-change", dep, loc, lib)
+                    break