bpo-40495: compileall option to hardlink duplicate pyc files (GH-19901)

compileall is now able to use hardlinks to prevent duplicates in a
case when .pyc files for different optimization levels have the same content.

Co-authored-by: Miro Hrončok <[email protected]>
Co-authored-by: Victor Stinner <[email protected]>

Author: 3 people

Doc/library/compileall.rst

@@ -113,6 +113,11 @@ compile Python sources.
 
    Ignore symlinks pointing outside the given directory.
 
+.. cmdoption:: --hardlink-dupes
+
+   If two ``.pyc`` files with different optimization level have
+   the same content, use hard links to consolidate duplicate files.
+
 .. versionchanged:: 3.2
    Added the ``-i``, ``-b`` and ``-h`` options.
 
@@ -125,7 +130,7 @@ compile Python sources.
    Added the ``--invalidation-mode`` option.
 
 .. versionchanged:: 3.9
-   Added the ``-s``, ``-p``, ``-e`` options.
+   Added the ``-s``, ``-p``, ``-e`` and ``--hardlink-dupes`` options.
    Raised the default recursion limit from 10 to
    :py:func:`sys.getrecursionlimit()`.
    Added the possibility to specify the ``-o`` option multiple times.
@@ -143,7 +148,7 @@ runtime.
 Public functions
 ----------------
 
-.. function:: compile_dir(dir, maxlevels=sys.getrecursionlimit(), 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)
+.. function:: compile_dir(dir, maxlevels=sys.getrecursionlimit(), 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)
 
    Recursively descend the directory tree named by *dir*, compiling all :file:`.py`
    files along the way. Return a true value if all the files compiled successfully,
@@ -193,6 +198,9 @@ Public functions
    the ``-s``, ``-p`` and ``-e`` options described above.
    They may be specified as ``str``, ``bytes`` or :py:class:`os.PathLike`.
 
+   If *hardlink_dupes* is true and two ``.pyc`` files with different optimization
+   level have the same content, use hard links to consolidate duplicate files.
+
    .. versionchanged:: 3.2
       Added the *legacy* and *optimize* parameter.
 
@@ -219,9 +227,9 @@ Public functions
       Setting *workers* to 0 now chooses the optimal number of cores.
 
    .. versionchanged:: 3.9
-      Added *stripdir*, *prependdir* and *limit_sl_dest* arguments.
+      Added *stripdir*, *prependdir*, *limit_sl_dest* and *hardlink_dupes* arguments.
 
-.. function:: 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)
+.. function:: 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)
 
    Compile the file with path *fullname*. Return a true value if the file
    compiled successfully, and a false value otherwise.
@@ -257,6 +265,9 @@ Public functions
    the ``-s``, ``-p`` and ``-e`` options described above.
    They may be specified as ``str``, ``bytes`` or :py:class:`os.PathLike`.
 
+   If *hardlink_dupes* is true and two ``.pyc`` files with different optimization
+   level have the same content, use hard links to consolidate duplicate files.
+
    .. versionadded:: 3.2
 
    .. versionchanged:: 3.5
@@ -273,7 +284,7 @@ Public functions
       The *invalidation_mode* parameter's default value is updated to None.
 
    .. versionchanged:: 3.9
-      Added *stripdir*, *prependdir* and *limit_sl_dest* arguments.
+      Added *stripdir*, *prependdir*, *limit_sl_dest* and *hardlink_dupes* arguments.
 
 .. function:: compile_path(skip_curdir=True, maxlevels=0, force=False, quiet=0, legacy=False, optimize=-1, invalidation_mode=None)
 

Doc/whatsnew/3.9.rst

@@ -245,6 +245,16 @@ that schedules a shutdown for the default executor that waits on the
 Added :class:`asyncio.PidfdChildWatcher`, a Linux-specific child watcher
 implementation that polls process file descriptors. (:issue:`38692`)
 
+compileall
+----------
+
+Added new possibility to use hardlinks for duplicated ``.pyc`` files: *hardlink_dupes* parameter and --hardlink-dupes command line option.
+(Contributed by  Lumír 'Frenzy' Balhar in :issue:`40495`.)
+
+Added new options for path manipulation in resulting ``.pyc`` files: *stripdir*, *prependdir*, *limit_sl_dest* parameters and -s, -p, -e command line options.
+Added the possibility to specify the option for an optimization level multiple times.
+(Contributed by Lumír 'Frenzy' Balhar in :issue:`38112`.)
+
 concurrent.futures
 ------------------
 

Lib/compileall.py

@@ -15,6 +15,7 @@
 import importlib.util
 import py_compile
 import struct
+import filecmp
 
 from functools import partial
 from pathlib import Path
@@ -47,7 +48,7 @@ def _walk_dir(dir, maxlevels, quiet=0):
 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):
+                prependdir=None, limit_sl_dest=None, hardlink_dupes=False):
     """Byte-compile all modules in the given directory tree.
 
     Arguments (only dir is required):
@@ -70,6 +71,7 @@ def compile_dir(dir, maxlevels=None, ddir=None, force=False,
                after stripdir
     limit_sl_dest: ignore symlinks if they are pointing outside of
                    the defined path
+    hardlink_dupes: hardlink duplicated pyc files
     """
     ProcessPoolExecutor = None
     if ddir is not None and (stripdir is not None or prependdir is not None):
@@ -104,22 +106,24 @@ def compile_dir(dir, maxlevels=None, ddir=None, force=False,
                                            invalidation_mode=invalidation_mode,
                                            stripdir=stripdir,
                                            prependdir=prependdir,
-                                           limit_sl_dest=limit_sl_dest),
+                                           limit_sl_dest=limit_sl_dest,
+                                           hardlink_dupes=hardlink_dupes),
                                    files)
             success = min(results, default=True)
     else:
         for file in files:
             if not compile_file(file, ddir, force, rx, quiet,
                                 legacy, optimize, invalidation_mode,
                                 stripdir=stripdir, prependdir=prependdir,
-                                limit_sl_dest=limit_sl_dest):
+                                limit_sl_dest=limit_sl_dest,
+                                hardlink_dupes=hardlink_dupes):
                 success = False
     return success
 
 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):
+                 limit_sl_dest=None, hardlink_dupes=False):
     """Byte-compile one file.
 
     Arguments (only fullname is required):
@@ -140,6 +144,7 @@ def compile_file(fullname, ddir=None, force=False, rx=None, quiet=0,
                after stripdir
     limit_sl_dest: ignore symlinks if they are pointing outside of
                    the defined path.
+    hardlink_dupes: hardlink duplicated pyc files
     """
 
     if ddir is not None and (stripdir is not None or prependdir is not None):
@@ -176,6 +181,14 @@ def compile_file(fullname, ddir=None, force=False, rx=None, quiet=0,
     if isinstance(optimize, int):
         optimize = [optimize]
 
+    # 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 rx is not None:
         mo = rx.search(fullname)
         if mo:
@@ -220,10 +233,16 @@ def compile_file(fullname, ddir=None, force=False, rx=None, quiet=0,
             if not quiet:
                 print('Compiling {!r}...'.format(fullname))
             try:
-                for opt_level, cfile in opt_cfiles.items():
+                for index, opt_level in enumerate(optimize):
+                    cfile = opt_cfiles[opt_level]
                     ok = py_compile.compile(fullname, cfile, dfile, True,
                                             optimize=opt_level,
                                             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.unlink(cfile)
+                            os.link(previous_cfile, cfile)
             except py_compile.PyCompileError as err:
                 success = False
                 if quiet >= 2:
@@ -352,6 +371,9 @@ def main():
                               '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',
+                        dest='hardlink_dupes',
+                        help='Hardlink duplicated pyc files')
 
     args = parser.parse_args()
     compile_dests = args.compile_dest
@@ -371,6 +393,10 @@ def main():
     if args.opt_levels is None:
         args.opt_levels = [-1]
 
+    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
     ):
@@ -404,7 +430,8 @@ def main():
                                         stripdir=args.stripdir,
                                         prependdir=args.prependdir,
                                         optimize=args.opt_levels,
-                                        limit_sl_dest=args.limit_sl_dest):
+                                        limit_sl_dest=args.limit_sl_dest,
+                                        hardlink_dupes=args.hardlink_dupes):
                         success = False
                 else:
                     if not compile_dir(dest, maxlevels, args.ddir,
@@ -414,7 +441,8 @@ def main():
                                        stripdir=args.stripdir,
                                        prependdir=args.prependdir,
                                        optimize=args.opt_levels,
-                                       limit_sl_dest=args.limit_sl_dest):
+                                       limit_sl_dest=args.limit_sl_dest,
+                                       hardlink_dupes=args.hardlink_dupes):
                         success = False
             return success
         else: