view tests/f @ 44118:f81c17ec303c

hgdemandimport: apply lazy module loading to sys.meta_path finders

Python's `sys.meta_path` finders are the primary objects whose job it
is to find a module at import time. When `import` is called, Python
iterates objects in this list and calls `o.find_spec(...)` to find
a `ModuleSpec` (or None if the module couldn't be found by that
finder). If no meta path finder can find a module, import fails.

One of the default meta path finders is `PathFinder`. Its job is to
import modules from the filesystem and is probably the most important
importer. This finder looks at `sys.path` and `sys.path_hooks` to do
its job.

The `ModuleSpec` returned by `MetaPathImporter.find_spec()` has a
`loader` attribute, which defines the concrete module loader to use.
`sys.path_hooks` is a hook point for teaching `PathFinder` to
instantiate custom loader types.

Previously, we injected a custom `sys.path_hook` that told `PathFinder`
to wrap the default loaders with a loader that creates a module object
that is lazy.

This approach worked. But its main limitation was that it only applied
to the `PathFinder` meta path importer. There are other meta path
importers that are registered. And in the case of PyOxidizer loading
modules from memory, `PathFinder` doesn't come into play since
PyOxidizer's own meta path importer was handling all imports.

This commit changes our approach to lazy module loading by proxying
all meta path importers. Specifically, we overload the `find_spec()`
method to swap in a wrapped loader on the `ModuleSpec` before it
is returned. The end result of this is all meta path importers should
be lazy.

As much as I would have loved to utilize .__class__ manipulation to
achieve this, some meta path importers are implemented in C/Rust
in such a way that they cannot be monkeypatched. This is why we
use __getattribute__ to define a proxy.

Also, this change could theoretically open us up to regressions in
meta path importers whose loader is creating module objects which
can't be monkeypatched. But I'm not aware of any of these in the
wild. So I think we'll be safe.

According to hyperfine, this change yields a decent startup time win of
5-6ms:

```
Benchmark #1: ~/.pyenv/versions/3.6.10/bin/python ./hg version
  Time (mean ± σ):      86.8 ms ±   0.5 ms    [User: 78.0 ms, System: 8.7 ms]
  Range (min … max):    86.0 ms …  89.1 ms    50 runs

  Time (mean ± σ):      81.1 ms ±   2.7 ms    [User: 74.5 ms, System: 6.5 ms]
  Range (min … max):    77.8 ms …  90.5 ms    50 runs

Benchmark #2: ~/.pyenv/versions/3.7.6/bin/python ./hg version
  Time (mean ± σ):      78.9 ms ±   0.6 ms    [User: 70.2 ms, System: 8.7 ms]
  Range (min … max):    78.1 ms …  81.2 ms    50 runs

  Time (mean ± σ):      73.4 ms ±   0.6 ms    [User: 65.3 ms, System: 8.0 ms]
  Range (min … max):    72.4 ms …  75.7 ms    50 runs

Benchmark #3: ~/.pyenv/versions/3.8.1/bin/python ./hg version
  Time (mean ± σ):      78.1 ms ±   0.6 ms    [User: 70.2 ms, System: 7.9 ms]
  Range (min … max):    77.4 ms …  80.9 ms    50 runs

  Time (mean ± σ):      72.1 ms ±   0.4 ms    [User: 64.4 ms, System: 7.6 ms]
  Range (min … max):    71.4 ms …  74.1 ms    50 runs
```

Differential Revision: https://phab.mercurial-scm.org/D7954

#!/usr/bin/env python

"""
Utility for inspecting files in various ways.

This tool is like the collection of tools found in a unix environment but are
cross platform and stable and suitable for our needs in the test suite.

This can be used instead of tools like:
  [
  dd
  find
  head
  hexdump
  ls
  md5sum
  readlink
  sha1sum
  stat
  tail
  test
  readlink.py
  md5sum.py
"""

from __future__ import absolute_import

import binascii
import glob
import hashlib
import optparse
import os
import re
import sys

# Python 3 adapters
ispy3 = sys.version_info[0] >= 3
if ispy3:

    def iterbytes(s):
        for i in range(len(s)):
            yield s[i : i + 1]


else:
    iterbytes = iter


def visit(opts, filenames, outfile):
    """Process filenames in the way specified in opts, writing output to
    outfile."""
    for f in sorted(filenames):
        isstdin = f == '-'
        if not isstdin and not os.path.lexists(f):
            outfile.write(b'%s: file not found\n' % f.encode('utf-8'))
            continue
        quiet = opts.quiet and not opts.recurse or isstdin
        isdir = os.path.isdir(f)
        islink = os.path.islink(f)
        isfile = os.path.isfile(f) and not islink
        dirfiles = None
        content = None
        facts = []
        if isfile:
            if opts.type:
                facts.append(b'file')
            if any((opts.hexdump, opts.dump, opts.md5, opts.sha1, opts.sha256)):
                with open(f, 'rb') as fobj:
                    content = fobj.read()
        elif islink:
            if opts.type:
                facts.append(b'link')
            content = os.readlink(f).encode('utf8')
        elif isstdin:
            content = getattr(sys.stdin, 'buffer', sys.stdin).read()
            if opts.size:
                facts.append(b'size=%d' % len(content))
        elif isdir:
            if opts.recurse or opts.type:
                dirfiles = glob.glob(f + '/*')
                facts.append(b'directory with %d files' % len(dirfiles))
        elif opts.type:
            facts.append(b'type unknown')
        if not isstdin:
            stat = os.lstat(f)
            if opts.size and not isdir:
                facts.append(b'size=%d' % stat.st_size)
            if opts.mode and not islink:
                facts.append(b'mode=%o' % (stat.st_mode & 0o777))
            if opts.links:
                facts.append(b'links=%d' % stat.st_nlink)
            if opts.newer:
                # mtime might be in whole seconds so newer file might be same
                if stat.st_mtime >= os.stat(opts.newer).st_mtime:
                    facts.append(
                        b'newer than %s' % opts.newer.encode('utf8', 'replace')
                    )
                else:
                    facts.append(
                        b'older than %s' % opts.newer.encode('utf8', 'replace')
                    )
        if opts.md5 and content is not None:
            h = hashlib.md5(content)
            facts.append(b'md5=%s' % binascii.hexlify(h.digest())[: opts.bytes])
        if opts.sha1 and content is not None:
            h = hashlib.sha1(content)
            facts.append(
                b'sha1=%s' % binascii.hexlify(h.digest())[: opts.bytes]
            )
        if opts.sha256 and content is not None:
            h = hashlib.sha256(content)
            facts.append(
                b'sha256=%s' % binascii.hexlify(h.digest())[: opts.bytes]
            )
        if isstdin:
            outfile.write(b', '.join(facts) + b'\n')
        elif facts:
            outfile.write(b'%s: %s\n' % (f.encode('utf-8'), b', '.join(facts)))
        elif not quiet:
            outfile.write(b'%s:\n' % f.encode('utf-8'))
        if content is not None:
            chunk = content
            if not islink:
                if opts.lines:
                    if opts.lines >= 0:
                        chunk = b''.join(chunk.splitlines(True)[: opts.lines])
                    else:
                        chunk = b''.join(chunk.splitlines(True)[opts.lines :])
                if opts.bytes:
                    if opts.bytes >= 0:
                        chunk = chunk[: opts.bytes]
                    else:
                        chunk = chunk[opts.bytes :]
            if opts.hexdump:
                for i in range(0, len(chunk), 16):
                    s = chunk[i : i + 16]
                    outfile.write(
                        b'%04x: %-47s |%s|\n'
                        % (
                            i,
                            b' '.join(b'%02x' % ord(c) for c in iterbytes(s)),
                            re.sub(b'[^ -~]', b'.', s),
                        )
                    )
            if opts.dump:
                if not quiet:
                    outfile.write(b'>>>\n')
                outfile.write(chunk)
                if not quiet:
                    if chunk.endswith(b'\n'):
                        outfile.write(b'<<<\n')
                    else:
                        outfile.write(b'\n<<< no trailing newline\n')
        if opts.recurse and dirfiles:
            assert not isstdin
            visit(opts, dirfiles, outfile)


if __name__ == "__main__":
    parser = optparse.OptionParser("%prog [options] [filenames]")
    parser.add_option(
        "-t",
        "--type",
        action="store_true",
        help="show file type (file or directory)",
    )
    parser.add_option(
        "-m", "--mode", action="store_true", help="show file mode"
    )
    parser.add_option(
        "-l", "--links", action="store_true", help="show number of links"
    )
    parser.add_option(
        "-s", "--size", action="store_true", help="show size of file"
    )
    parser.add_option(
        "-n", "--newer", action="store", help="check if file is newer (or same)"
    )
    parser.add_option(
        "-r", "--recurse", action="store_true", help="recurse into directories"
    )
    parser.add_option(
        "-S",
        "--sha1",
        action="store_true",
        help="show sha1 hash of the content",
    )
    parser.add_option(
        "",
        "--sha256",
        action="store_true",
        help="show sha256 hash of the content",
    )
    parser.add_option(
        "-M", "--md5", action="store_true", help="show md5 hash of the content"
    )
    parser.add_option(
        "-D", "--dump", action="store_true", help="dump file content"
    )
    parser.add_option(
        "-H", "--hexdump", action="store_true", help="hexdump file content"
    )
    parser.add_option(
        "-B", "--bytes", type="int", help="number of characters to dump"
    )
    parser.add_option(
        "-L", "--lines", type="int", help="number of lines to dump"
    )
    parser.add_option(
        "-q", "--quiet", action="store_true", help="no default output"
    )
    (opts, filenames) = parser.parse_args(sys.argv[1:])
    if not filenames:
        filenames = ['-']

    visit(opts, filenames, getattr(sys.stdout, 'buffer', sys.stdout))