"""Module/script to byte-compile all .py files to .pyc files.
When called as a script with arguments, this compiles the directories
given as arguments recursively; the -l option prevents it from
recursing into directories.
Without arguments, if compiles all modules on sys.path, without
recursing into subdirectories. (Even though it should do so for
packages -- for now, you'll have to deal with packages separately.)
See module py_compile for details of the actual byte-compilation.
from functools import partial
__all__ = ["compile_dir","compile_file","compile_path"]
def _walk_dir(dir, maxlevels, quiet=0):
if quiet < 2 and isinstance(dir, os.PathLike):
print('Listing {!r}...'.format(dir))
print("Can't list {!r}".format(dir))
if name == '__pycache__':
fullname = os.path.join(dir, name)
if not os.path.isdir(fullname):
elif (maxlevels > 0 and name != os.curdir and name != os.pardir and
os.path.isdir(fullname) and not os.path.islink(fullname)):
yield from _walk_dir(fullname, maxlevels=maxlevels - 1,
def compile_dir(dir, maxlevels=None, ddir=None, force=False,
rx=None, quiet=0, legacy=False, optimize=-1, workers=1,
invalidation_mode=None, *, stripdir=None,
prependdir=None, limit_sl_dest=None, hardlink_dupes=False):
"""Byte-compile all modules in the given directory tree.
Arguments (only dir is required):
dir: the directory to byte-compile
maxlevels: maximum recursion level (default `sys.getrecursionlimit()`)
ddir: the directory that will be prepended to the path to the
file as it is compiled into each byte-code file.
force: if True, force compilation, even if timestamps are up-to-date
quiet: full output with False or 0, errors only with 1,
legacy: if True, produce legacy pyc paths instead of PEP 3147 paths
optimize: int or list of optimization levels or -1 for level of
the interpreter. Multiple levels leads to multiple compiled
files each with one optimization level.
workers: maximum number of parallel workers
invalidation_mode: how the up-to-dateness of the pyc will be checked
stripdir: part of path to left-strip from source file path
prependdir: path to prepend to beginning of original file path, applied
limit_sl_dest: ignore symlinks if they are pointing outside of
hardlink_dupes: hardlink duplicated pyc files
ProcessPoolExecutor = None
if ddir is not None and (stripdir is not None or prependdir is not None):
raise ValueError(("Destination dir (ddir) cannot be used "
"in combination with stripdir or prependdir"))
raise ValueError('workers must be greater or equal to 0')
# Only import when needed, as low resource platforms may
from concurrent.futures import ProcessPoolExecutor
maxlevels = sys.getrecursionlimit()
files = _walk_dir(dir, quiet=quiet, maxlevels=maxlevels)
if workers != 1 and ProcessPoolExecutor is not None:
# If workers == 0, let ProcessPoolExecutor choose
workers = workers or None
with ProcessPoolExecutor(max_workers=workers) as executor:
results = executor.map(partial(compile_file,
invalidation_mode=invalidation_mode,
limit_sl_dest=limit_sl_dest,
hardlink_dupes=hardlink_dupes),
success = min(results, default=True)
if not compile_file(file, ddir, force, rx, quiet,
legacy, optimize, invalidation_mode,
stripdir=stripdir, prependdir=prependdir,
limit_sl_dest=limit_sl_dest,
hardlink_dupes=hardlink_dupes):
def compile_file(fullname, ddir=None, force=False, rx=None, quiet=0,
legacy=False, optimize=-1,
invalidation_mode=None, *, stripdir=None, prependdir=None,
limit_sl_dest=None, hardlink_dupes=False):
"""Byte-compile one file.
Arguments (only fullname is required):
fullname: the file to byte-compile
ddir: if given, the directory name compiled in to the
force: if True, force compilation, even if timestamps are up-to-date
quiet: full output with False or 0, errors only with 1,
legacy: if True, produce legacy pyc paths instead of PEP 3147 paths
optimize: int or list of optimization levels or -1 for level of
the interpreter. Multiple levels leads to multiple compiled
files each with one optimization level.
invalidation_mode: how the up-to-dateness of the pyc will be checked
stripdir: part of path to left-strip from source file path
prependdir: path to prepend to beginning of original file path, applied
limit_sl_dest: ignore symlinks if they are pointing outside of
hardlink_dupes: hardlink duplicated pyc files
if ddir is not None and (stripdir is not None or prependdir is not None):
raise ValueError(("Destination dir (ddir) cannot be used "
"in combination with stripdir or prependdir"))
if quiet < 2 and isinstance(fullname, os.PathLike):
fullname = os.fspath(fullname)
name = os.path.basename(fullname)
dfile = os.path.join(ddir, name)
fullname_parts = fullname.split(os.path.sep)
stripdir_parts = stripdir.split(os.path.sep)
ddir_parts = list(fullname_parts)
for spart, opart in zip(stripdir_parts, fullname_parts):
dfile = os.path.join(*ddir_parts)
if prependdir is not None:
dfile = os.path.join(prependdir, fullname)
dfile = os.path.join(prependdir, dfile)
if isinstance(optimize, int):
# Use set() to remove duplicates.
# Use sorted() to create pyc files in a deterministic order.
optimize = sorted(set(optimize))
if hardlink_dupes and len(optimize) < 2:
raise ValueError("Hardlinking of duplicated bytecode makes sense "
"only for more than one optimization level")
if limit_sl_dest is not None and os.path.islink(fullname):
if Path(limit_sl_dest).resolve() not in Path(fullname).resolve().parents:
if os.path.isfile(fullname):
for opt_level in optimize:
opt_cfiles[opt_level] = fullname + 'c'
opt = opt_level if opt_level >= 1 else ''
cfile = (importlib.util.cache_from_source(
fullname, optimization=opt))
opt_cfiles[opt_level] = cfile
cfile = importlib.util.cache_from_source(fullname)
opt_cfiles[opt_level] = cfile
head, tail = name[:-3], name[-3:]
mtime = int(os.stat(fullname).st_mtime)
expect = struct.pack('<4sLL', importlib.util.MAGIC_NUMBER,
for cfile in opt_cfiles.values():
with open(cfile, 'rb') as chandle:
actual = chandle.read(12)
print('Compiling {!r}...'.format(fullname))
for index, opt_level in enumerate(optimize):
cfile = opt_cfiles[opt_level]
ok = py_compile.compile(fullname, cfile, dfile, True,
invalidation_mode=invalidation_mode)
if index > 0 and hardlink_dupes:
previous_cfile = opt_cfiles[optimize[index - 1]]
if filecmp.cmp(cfile, previous_cfile, shallow=False):
os.link(previous_cfile, cfile)
except py_compile.PyCompileError as err:
print('*** Error compiling {!r}...'.format(fullname))
# escape non-printable characters in msg
encoding = sys.stdout.encoding or sys.getdefaultencoding()
msg = err.msg.encode(encoding, errors='backslashreplace').decode(encoding)
except (SyntaxError, UnicodeError, OSError) as e:
print('*** Error compiling {!r}...'.format(fullname))
print(e.__class__.__name__ + ':', e)
def compile_path(skip_curdir=1, maxlevels=0, force=False, quiet=0,
legacy=False, optimize=-1,
"""Byte-compile all module on sys.path.
Arguments (all optional):
skip_curdir: if true, skip current directory (default True)
maxlevels: max recursion level (default 0)
force: as for compile_dir() (default False)
quiet: as for compile_dir() (default 0)
legacy: as for compile_dir() (default False)
optimize: as for compile_dir() (default -1)
invalidation_mode: as for compiler_dir()
if (not dir or dir == os.curdir) and skip_curdir:
print('Skipping current directory')
success = success and compile_dir(
invalidation_mode=invalidation_mode,
"""Script main program."""
parser = argparse.ArgumentParser(
description='Utilities to support installing Python libraries.')
parser.add_argument('-l', action='store_const', const=0,
default=None, dest='maxlevels',
help="don't recurse into subdirectories")
parser.add_argument('-r', type=int, dest='recursion',
help=('control the maximum recursion level. '
'if `-l` and `-r` options are specified, '
'then `-r` takes precedence.'))
parser.add_argument('-f', action='store_true', dest='force',
help='force rebuild even if timestamps are up to date')
parser.add_argument('-q', action='count', dest='quiet', default=0,
help='output only error messages; -qq will suppress '
'the error messages as well.')
parser.add_argument('-b', action='store_true', dest='legacy',
help='use legacy (pre-PEP3147) compiled file locations')
parser.add_argument('-d', metavar='DESTDIR', dest='ddir', default=None,
help=('directory to prepend to file paths for use in '
'compile-time tracebacks and in runtime '
'tracebacks in cases where the source file is '
parser.add_argument('-s', metavar='STRIPDIR', dest='stripdir',
help=('part of path to left-strip from path '
'to source file - for example buildroot. '
'`-d` and `-s` options cannot be '
parser.add_argument('-p', metavar='PREPENDDIR', dest='prependdir',
help=('path to add as prefix to path '
'to source file - for example / to make '
'it absolute when some part is removed '
'`-d` and `-p` options cannot be '
parser.add_argument('-x', metavar='REGEXP', dest='rx', default=None,
help=('skip files matching the regular expression; '
'the regexp is searched for in the full path '
'of each file considered for compilation'))
parser.add_argument('-i', metavar='FILE', dest='flist',
help=('add all the files and directories listed in '
'FILE to the list considered for compilation; '
'if "-", names are read from stdin'))
parser.add_argument('compile_dest', metavar='FILE|DIR', nargs='*',
help=('zero or more file and directory names '
'to compile; if no arguments given, defaults '
'to the equivalent of -l sys.path'))
parser.add_argument('-j', '--workers', default=1,
type=int, help='Run compileall concurrently')
invalidation_modes = [mode.name.lower().replace('_', '-')
for mode in py_compile.PycInvalidationMode]
parser.add_argument('--invalidation-mode',
choices=sorted(invalidation_modes),
help=('set .pyc invalidation mode; defaults to '
'"checked-hash" if the SOURCE_DATE_EPOCH '
'environment variable is set, and '
'"timestamp" otherwise.'))
parser.add_argument('-o', action='append', type=int, dest='opt_levels',
help=('Optimization levels to run compilation with.'
'Default is -1 which uses optimization level of'
'Python interpreter itself (specified by -O).'))
parser.add_argument('-e', metavar='DIR', dest='limit_sl_dest',
help='Ignore symlinks pointing outsite of the DIR')
parser.add_argument('--hardlink-dupes', action='store_true',
help='Hardlink duplicated pyc files')
args = parser.parse_args()
compile_dests = args.compile_dest
args.rx = re.compile(args.rx)
if args.limit_sl_dest == "":
args.limit_sl_dest = None
if args.recursion is not None:
maxlevels = args.recursion
maxlevels = args.maxlevels
if args.opt_levels is None:
if len(args.opt_levels) == 1 and args.hardlink_dupes:
parser.error(("Hardlinking of duplicated bytecode makes sense "
"only for more than one optimization level."))
if args.ddir is not None and (
args.stripdir is not None or args.prependdir is not None
parser.error("-d cannot be used in combination with -s or -p")
# if flist is provided then load it
with (sys.stdin if args.flist=='-' else open(args.flist)) as f:
compile_dests.append(line.strip())
print("Error reading file list {}".format(args.flist))
if args.invalidation_mode:
ivl_mode = args.invalidation_mode.replace('-', '_').upper()
invalidation_mode = py_compile.PycInvalidationMode[ivl_mode]
for dest in compile_dests:
if not compile_file(dest, args.ddir, args.force, args.rx,
invalidation_mode=invalidation_mode,
prependdir=args.prependdir,
optimize=args.opt_levels,
limit_sl_dest=args.limit_sl_dest,
hardlink_dupes=args.hardlink_dupes):
if not compile_dir(dest, maxlevels, args.ddir,
args.force, args.rx, args.quiet,
args.legacy, workers=args.workers,
invalidation_mode=invalidation_mode,
prependdir=args.prependdir,
optimize=args.opt_levels,
limit_sl_dest=args.limit_sl_dest,
hardlink_dupes=args.hardlink_dupes):
return compile_path(legacy=args.legacy, force=args.force,
invalidation_mode=invalidation_mode)
except KeyboardInterrupt:
if __name__ == '__main__':
exit_status = int(not main())