cpython/Tools/wasm/emscripten/__main__.py
Hood Chatham ecb3f23b94
gh-136976: Emscripten: Add _decimal and libmpdec (#136997)
Adds tooling to build mpdec (and thus _decimal) as part of an Emscripten build.
2025-07-24 06:31:30 +00:00

467 lines
15 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

#!/usr/bin/env python3
import argparse
import contextlib
import functools
import os
import shutil
import subprocess
import sys
import sysconfig
import hashlib
import tempfile
from urllib.request import urlopen
from pathlib import Path
from textwrap import dedent
try:
from os import process_cpu_count as cpu_count
except ImportError:
from os import cpu_count
EMSCRIPTEN_DIR = Path(__file__).parent
CHECKOUT = EMSCRIPTEN_DIR.parent.parent.parent
CROSS_BUILD_DIR = CHECKOUT / "cross-build"
NATIVE_BUILD_DIR = CROSS_BUILD_DIR / "build"
HOST_TRIPLE = "wasm32-emscripten"
DOWNLOAD_DIR = CROSS_BUILD_DIR / HOST_TRIPLE / "build"
HOST_BUILD_DIR = CROSS_BUILD_DIR / HOST_TRIPLE / "build"
HOST_DIR = HOST_BUILD_DIR / "python"
PREFIX_DIR = CROSS_BUILD_DIR / HOST_TRIPLE / "prefix"
LOCAL_SETUP = CHECKOUT / "Modules" / "Setup.local"
LOCAL_SETUP_MARKER = "# Generated by Tools/wasm/emscripten.py\n".encode("utf-8")
def updated_env(updates={}):
"""Create a new dict representing the environment to use.
The changes made to the execution environment are printed out.
"""
env_defaults = {}
# https://reproducible-builds.org/docs/source-date-epoch/
git_epoch_cmd = ["git", "log", "-1", "--pretty=%ct"]
try:
epoch = subprocess.check_output(git_epoch_cmd, encoding="utf-8").strip()
env_defaults["SOURCE_DATE_EPOCH"] = epoch
except subprocess.CalledProcessError:
pass # Might be building from a tarball.
# This layering lets SOURCE_DATE_EPOCH from os.environ takes precedence.
environment = env_defaults | os.environ | updates
env_diff = {}
for key, value in environment.items():
if os.environ.get(key) != value:
env_diff[key] = value
print("๐ŸŒŽ Environment changes:")
for key in sorted(env_diff.keys()):
print(f" {key}={env_diff[key]}")
return environment
def subdir(working_dir, *, clean_ok=False):
"""Decorator to change to a working directory."""
def decorator(func):
@functools.wraps(func)
def wrapper(context):
try:
tput_output = subprocess.check_output(
["tput", "cols"], encoding="utf-8"
)
terminal_width = int(tput_output.strip())
except subprocess.CalledProcessError:
terminal_width = 80
print("โŽฏ" * terminal_width)
print("๐Ÿ“", working_dir)
if clean_ok and getattr(context, "clean", False) and working_dir.exists():
print("๐Ÿšฎ Deleting directory (--clean)...")
shutil.rmtree(working_dir)
working_dir.mkdir(parents=True, exist_ok=True)
with contextlib.chdir(working_dir):
return func(context, working_dir)
return wrapper
return decorator
def call(command, *, quiet, **kwargs):
"""Execute a command.
If 'quiet' is true, then redirect stdout and stderr to a temporary file.
"""
print("โฏ", " ".join(map(str, command)))
if not quiet:
stdout = None
stderr = None
else:
stdout = tempfile.NamedTemporaryFile(
"w",
encoding="utf-8",
delete=False,
prefix="cpython-emscripten-",
suffix=".log",
)
stderr = subprocess.STDOUT
print(f"๐Ÿ“ Logging output to {stdout.name} (--quiet)...")
subprocess.check_call(command, **kwargs, stdout=stdout, stderr=stderr)
def build_platform():
"""The name of the build/host platform."""
# Can also be found via `config.guess`.`
return sysconfig.get_config_var("BUILD_GNU_TYPE")
def build_python_path():
"""The path to the build Python binary."""
binary = NATIVE_BUILD_DIR / "python"
if not binary.is_file():
binary = binary.with_suffix(".exe")
if not binary.is_file():
raise FileNotFoundError("Unable to find `python(.exe)` in " f"{NATIVE_BUILD_DIR}")
return binary
@subdir(NATIVE_BUILD_DIR, clean_ok=True)
def configure_build_python(context, working_dir):
"""Configure the build/host Python."""
if LOCAL_SETUP.exists():
print(f"๐Ÿ‘ {LOCAL_SETUP} exists ...")
else:
print(f"๐Ÿ“ Touching {LOCAL_SETUP} ...")
LOCAL_SETUP.write_bytes(LOCAL_SETUP_MARKER)
configure = [os.path.relpath(CHECKOUT / "configure", working_dir)]
if context.args:
configure.extend(context.args)
call(configure, quiet=context.quiet)
@subdir(NATIVE_BUILD_DIR)
def make_build_python(context, working_dir):
"""Make/build the build Python."""
call(["make", "--jobs", str(cpu_count()), "all"], quiet=context.quiet)
binary = build_python_path()
cmd = [
binary,
"-c",
"import sys; " "print(f'{sys.version_info.major}.{sys.version_info.minor}')",
]
version = subprocess.check_output(cmd, encoding="utf-8").strip()
print(f"๐ŸŽ‰ {binary} {version}")
def check_shasum(file: str, expected_shasum: str):
with open(file, "rb") as f:
digest = hashlib.file_digest(f, "sha256")
if digest.hexdigest() != expected_shasum:
raise RuntimeError(f"Unexpected shasum for {file}")
def download_and_unpack(working_dir: Path, url: str, expected_shasum: str):
with tempfile.NamedTemporaryFile(suffix=".tar.gz", delete_on_close=False) as tmp_file:
with urlopen(url) as response:
shutil.copyfileobj(response, tmp_file)
tmp_file.close()
check_shasum(tmp_file.name, expected_shasum)
shutil.unpack_archive(tmp_file.name, working_dir)
@subdir(HOST_BUILD_DIR, clean_ok=True)
def make_emscripten_libffi(context, working_dir):
ver = "3.4.6"
libffi_dir = working_dir / f"libffi-{ver}"
shutil.rmtree(libffi_dir, ignore_errors=True)
download_and_unpack(working_dir, f"https://github.com/libffi/libffi/releases/download/v{ver}/libffi-{ver}.tar.gz", "b0dea9df23c863a7a50e825440f3ebffabd65df1497108e5d437747843895a4e")
call(
[EMSCRIPTEN_DIR / "make_libffi.sh"],
env=updated_env({"PREFIX": PREFIX_DIR}),
cwd=libffi_dir,
quiet=context.quiet,
)
@subdir(HOST_BUILD_DIR, clean_ok=True)
def make_mpdec(context, working_dir):
ver = "4.0.1"
mpdec_dir = working_dir / f"mpdecimal-{ver}"
shutil.rmtree(mpdec_dir, ignore_errors=True)
download_and_unpack(working_dir, f"https://www.bytereef.org/software/mpdecimal/releases/mpdecimal-{ver}.tar.gz", "96d33abb4bb0070c7be0fed4246cd38416188325f820468214471938545b1ac8")
call(
[
"emconfigure",
mpdec_dir / "configure",
"CFLAGS=-fPIC",
"--prefix",
PREFIX_DIR,
"--disable-shared",
],
cwd=mpdec_dir,
quiet=context.quiet,
)
call(
[
"make",
"install"
],
cwd=mpdec_dir,
quiet=context.quiet,
)
@subdir(HOST_DIR, clean_ok=True)
def configure_emscripten_python(context, working_dir):
"""Configure the emscripten/host build."""
config_site = os.fsdecode(
EMSCRIPTEN_DIR / "config.site-wasm32-emscripten"
)
emscripten_build_dir = working_dir.relative_to(CHECKOUT)
python_build_dir = NATIVE_BUILD_DIR / "build"
lib_dirs = list(python_build_dir.glob("lib.*"))
assert (
len(lib_dirs) == 1
), f"Expected a single lib.* directory in {python_build_dir}"
lib_dir = os.fsdecode(lib_dirs[0])
pydebug = lib_dir.endswith("-pydebug")
python_version = lib_dir.removesuffix("-pydebug").rpartition("-")[-1]
sysconfig_data = (
f"{emscripten_build_dir}/build/lib.emscripten-wasm32-{python_version}"
)
if pydebug:
sysconfig_data += "-pydebug"
host_runner = context.host_runner
if node_version := os.environ.get("PYTHON_NODE_VERSION", None):
res = subprocess.run(
[
"bash",
"-c",
f"source ~/.nvm/nvm.sh && nvm which {node_version}",
],
text=True,
capture_output=True,
)
host_runner = res.stdout.strip()
pkg_config_path_dir = (PREFIX_DIR / "lib/pkgconfig/").resolve()
env_additions = {
"CONFIG_SITE": config_site,
"HOSTRUNNER": host_runner,
"EM_PKG_CONFIG_PATH": str(pkg_config_path_dir),
}
build_python = os.fsdecode(build_python_path())
configure = [
"emconfigure",
os.path.relpath(CHECKOUT / "configure", working_dir),
"CFLAGS=-DPY_CALL_TRAMPOLINE -sUSE_BZIP2",
"PKG_CONFIG=pkg-config",
f"--host={HOST_TRIPLE}",
f"--build={build_platform()}",
f"--with-build-python={build_python}",
"--without-pymalloc",
"--disable-shared",
"--disable-ipv6",
"--enable-big-digits=30",
"--enable-wasm-dynamic-linking",
f"--prefix={PREFIX_DIR}",
]
if pydebug:
configure.append("--with-pydebug")
if context.args:
configure.extend(context.args)
call(
configure,
env=updated_env(env_additions),
quiet=context.quiet,
)
shutil.copy(EMSCRIPTEN_DIR / "node_entry.mjs", working_dir / "node_entry.mjs")
node_entry = working_dir / "node_entry.mjs"
exec_script = working_dir / "python.sh"
exec_script.write_text(
dedent(
f"""\
#!/bin/sh
# Macs come with FreeBSD coreutils which doesn't have the -s option
# so feature detect and work around it.
if which grealpath > /dev/null 2>&1; then
# It has brew installed gnu core utils, use that
REALPATH="grealpath -s"
elif which realpath > /dev/null 2>&1 && realpath --version > /dev/null 2>&1 && realpath --version | grep GNU > /dev/null 2>&1; then
# realpath points to GNU realpath so use it.
REALPATH="realpath -s"
else
# Shim for macs without GNU coreutils
abs_path () {{
echo "$(cd "$(dirname "$1")" || exit; pwd)/$(basename "$1")"
}}
REALPATH=abs_path
fi
# Before node 24, --experimental-wasm-jspi uses different API,
# After node 24 JSPI is on by default.
ARGS=$({host_runner} -e "$(cat <<"EOF"
const major_version = Number(process.version.split(".")[0].slice(1));
if (major_version === 24) {{
process.stdout.write("--experimental-wasm-jspi");
}}
EOF
)")
# We compute our own path, not following symlinks and pass it in so that
# node_entry.mjs can set sys.executable correctly.
# Intentionally allow word splitting on NODEFLAGS.
exec {host_runner} $NODEFLAGS $ARGS {node_entry} --this-program="$($REALPATH "$0")" "$@"
"""
)
)
exec_script.chmod(0o755)
print(f"๐Ÿƒโ€โ™€๏ธ Created {exec_script} ... ")
sys.stdout.flush()
@subdir(HOST_DIR)
def make_emscripten_python(context, working_dir):
"""Run `make` for the emscripten/host build."""
call(
["make", "--jobs", str(cpu_count()), "all"],
env=updated_env(),
quiet=context.quiet,
)
exec_script = working_dir / "python.sh"
subprocess.check_call([exec_script, "--version"])
def build_all(context):
"""Build everything."""
steps = [
configure_build_python,
make_build_python,
make_emscripten_libffi,
make_mpdec,
configure_emscripten_python,
make_emscripten_python,
]
for step in steps:
step(context)
def clean_contents(context):
"""Delete all files created by this script."""
if CROSS_BUILD_DIR.exists():
print(f"๐Ÿงน Deleting {CROSS_BUILD_DIR} ...")
shutil.rmtree(CROSS_BUILD_DIR)
if LOCAL_SETUP.exists():
with LOCAL_SETUP.open("rb") as file:
if file.read(len(LOCAL_SETUP_MARKER)) == LOCAL_SETUP_MARKER:
print(f"๐Ÿงน Deleting generated {LOCAL_SETUP} ...")
def main():
default_host_runner = "node"
parser = argparse.ArgumentParser()
subcommands = parser.add_subparsers(dest="subcommand")
build = subcommands.add_parser("build", help="Build everything")
configure_build = subcommands.add_parser(
"configure-build-python", help="Run `configure` for the " "build Python"
)
make_mpdec_cmd = subcommands.add_parser(
"make-mpdec", help="Clone mpdec repo, configure and build it for emscripten"
)
make_libffi_cmd = subcommands.add_parser(
"make-libffi", help="Clone libffi repo, configure and build it for emscripten"
)
make_build = subcommands.add_parser(
"make-build-python", help="Run `make` for the build Python"
)
configure_host = subcommands.add_parser(
"configure-host",
help="Run `configure` for the host/emscripten (pydebug builds are inferred from the build Python)",
)
make_host = subcommands.add_parser(
"make-host", help="Run `make` for the host/emscripten"
)
clean = subcommands.add_parser(
"clean", help="Delete files and directories created by this script"
)
for subcommand in (
build,
configure_build,
make_libffi_cmd,
make_mpdec_cmd,
make_build,
configure_host,
make_host,
):
subcommand.add_argument(
"--quiet",
action="store_true",
default=False,
dest="quiet",
help="Redirect output from subprocesses to a log file",
)
for subcommand in configure_build, configure_host:
subcommand.add_argument(
"--clean",
action="store_true",
default=False,
dest="clean",
help="Delete any relevant directories before building",
)
for subcommand in build, configure_build, configure_host:
subcommand.add_argument(
"args", nargs="*", help="Extra arguments to pass to `configure`"
)
for subcommand in build, configure_host:
subcommand.add_argument(
"--host-runner",
action="store",
default=default_host_runner,
dest="host_runner",
help="Command template for running the emscripten host"
f"`{default_host_runner}`)",
)
context = parser.parse_args()
dispatch = {
"make-libffi": make_emscripten_libffi,
"make-mpdec": make_mpdec,
"configure-build-python": configure_build_python,
"make-build-python": make_build_python,
"configure-host": configure_emscripten_python,
"make-host": make_emscripten_python,
"build": build_all,
"clean": clean_contents,
}
if not context.subcommand:
# No command provided, display help and exit
print("Expected one of", ", ".join(sorted(dispatch.keys())), file=sys.stderr)
parser.print_help(sys.stderr)
sys.exit(1)
dispatch[context.subcommand](context)
if __name__ == "__main__":
main()