view tests/common-pattern.py @ 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

# common patterns in test at can safely be replaced
from __future__ import absolute_import

import os

substitutions = [
    # list of possible compressions
    (br'(zstd,)?zlib,none,bzip2', br'$USUAL_COMPRESSIONS$'),
    (br'=(zstd,)?zlib', br'=$BUNDLE2_COMPRESSIONS$'),
    # capabilities sent through http
    (
        br'bundlecaps=HG20%2Cbundle2%3DHG20%250A'
        br'bookmarks%250A'
        br'changegroup%253D01%252C02%250A'
        br'digests%253Dmd5%252Csha1%252Csha512%250A'
        br'error%253Dabort%252Cunsupportedcontent%252Cpushraced%252Cpushkey%250A'
        br'hgtagsfnodes%250A'
        br'listkeys%250A'
        br'phases%253Dheads%250A'
        br'pushkey%250A'
        br'remote-changegroup%253Dhttp%252Chttps%250A'
        br'rev-branch-cache%250A'
        br'stream%253Dv2',
        # (the replacement patterns)
        br'$USUAL_BUNDLE_CAPS$',
    ),
    (
        br'bundlecaps=HG20%2Cbundle2%3DHG20%250A'
        br'bookmarks%250A'
        br'changegroup%253D01%252C02%250A'
        br'digests%253Dmd5%252Csha1%252Csha512%250A'
        br'error%253Dabort%252Cunsupportedcontent%252Cpushraced%252Cpushkey%250A'
        br'hgtagsfnodes%250A'
        br'listkeys%250A'
        br'phases%253Dheads%250A'
        br'pushkey%250A'
        br'remote-changegroup%253Dhttp%252Chttps',
        # (the replacement patterns)
        br'$USUAL_BUNDLE_CAPS_SERVER$',
    ),
    # bundle2 capabilities sent through ssh
    (
        br'bundle2=HG20%0A'
        br'bookmarks%0A'
        br'changegroup%3D01%2C02%0A'
        br'digests%3Dmd5%2Csha1%2Csha512%0A'
        br'error%3Dabort%2Cunsupportedcontent%2Cpushraced%2Cpushkey%0A'
        br'hgtagsfnodes%0A'
        br'listkeys%0A'
        br'phases%3Dheads%0A'
        br'pushkey%0A'
        br'remote-changegroup%3Dhttp%2Chttps%0A'
        br'rev-branch-cache%0A'
        br'stream%3Dv2',
        # (replacement patterns)
        br'$USUAL_BUNDLE2_CAPS$',
    ),
    # bundle2 capabilities advertised by the server
    (
        br'bundle2=HG20%0A'
        br'bookmarks%0A'
        br'changegroup%3D01%2C02%0A'
        br'digests%3Dmd5%2Csha1%2Csha512%0A'
        br'error%3Dabort%2Cunsupportedcontent%2Cpushraced%2Cpushkey%0A'
        br'hgtagsfnodes%0A'
        br'listkeys%0A'
        br'phases%3Dheads%0A'
        br'pushkey%0A'
        br'remote-changegroup%3Dhttp%2Chttps%0A'
        br'rev-branch-cache',
        # (replacement patterns)
        br'$USUAL_BUNDLE2_CAPS_SERVER$',
    ),
    (
        br'bundle2=HG20%0A'
        br'bookmarks%0A'
        br'changegroup%3D01%2C02%0A'
        br'digests%3Dmd5%2Csha1%2Csha512%0A'
        br'error%3Dabort%2Cunsupportedcontent%2Cpushraced%2Cpushkey%0A'
        br'hgtagsfnodes%0A'
        br'listkeys%0A'
        br'pushkey%0A'
        br'remote-changegroup%3Dhttp%2Chttps%0A'
        br'rev-branch-cache%0A'
        br'stream%3Dv2',
        # (replacement patterns)
        br'$USUAL_BUNDLE2_CAPS_NO_PHASES$',
    ),
    # HTTP access log dates
    (
        br' - - \[\d\d/.../2\d\d\d \d\d:\d\d:\d\d] "(GET|PUT|POST)',
        lambda m: br' - - [$LOGDATE$] "' + m.group(1),
    ),
    # HTTP error log dates
    (
        br' - - \[\d\d/.../2\d\d\d \d\d:\d\d:\d\d] (HG error:|Exception)',
        lambda m: br' - - [$ERRDATE$] ' + m.group(1),
    ),
    # HTTP header dates- RFC 1123
    (
        br'([Dd]ate): [A-Za-z]{3}, \d\d [A-Za-z]{3} \d{4} \d\d:\d\d:\d\d GMT',
        lambda m: br'%s: $HTTP_DATE$' % m.group(1),
    ),
    # LFS expiration value
    (
        br'"expires_at": "\d{4}-\d\d-\d\dT\d\d:\d\d:\d\dZ"',
        br'"expires_at": "$ISO_8601_DATE_TIME$"',
    ),
    # Windows has an extra '/' in the following lines that get globbed away:
    #   pushing to file:/*/$TESTTMP/r2 (glob)
    #   comparing with file:/*/$TESTTMP/r2 (glob)
    #   sub/maybelarge.dat: largefile 34..9c not available from
    #       file:/*/$TESTTMP/largefiles-repo (glob)
    (
        br'(.*file:/)/?(/\$TESTTMP.*)',
        lambda m: m.group(1) + b'*' + m.group(2) + b' (glob)',
    ),
]

# Various platform error strings, keyed on a common replacement string
_errors = {
    br'$ENOENT$': (
        # IOError in Python does not have the same error message
        # than in Rust, and automatic conversion is not possible
        # because of module member privacy.
        br'No such file or directory \(os error 2\)',
        # strerror()
        br'No such file or directory',
        # FormatMessage(ERROR_FILE_NOT_FOUND)
        br'The system cannot find the file specified',
    ),
    br'$ENOTDIR$': (
        # strerror()
        br'Not a directory',
        # FormatMessage(ERROR_PATH_NOT_FOUND)
        br'The system cannot find the path specified',
    ),
    br'$ECONNRESET$': (
        # strerror()
        br'Connection reset by peer',
        # FormatMessage(WSAECONNRESET)
        br'An existing connection was forcibly closed by the remote host',
    ),
    br'$EADDRINUSE$': (
        # strerror()
        br'Address already in use',
        # FormatMessage(WSAEADDRINUSE)
        br'Only one usage of each socket address'
        br' \(protocol/network address/port\) is normally permitted',
    ),
    br'$EADDRNOTAVAIL$': (
        # strerror()
        br'Cannot assign requested address',
        # FormatMessage(WSAEADDRNOTAVAIL)
    ),
}

for replace, msgs in _errors.items():
    substitutions.extend((m, replace) for m in msgs)

# Output lines on Windows that can be autocorrected for '\' vs '/' path
# differences.
_winpathfixes = [
    # cloning subrepo s\ss from $TESTTMP/t/s/ss
    # cloning subrepo foo\bar from http://localhost:$HGPORT/foo/bar
    br'(?m)^cloning subrepo \S+\\.*',
    # pulling from $TESTTMP\issue1852a
    br'(?m)^pulling from \$TESTTMP\\.*',
    # pushing to $TESTTMP\a
    br'(?m)^pushing to \$TESTTMP\\.*',
    # pushing subrepo s\ss to $TESTTMP/t/s/ss
    br'(?m)^pushing subrepo \S+\\\S+ to.*',
    # moving d1\d11\a1 to d3/d11/a1
    br'(?m)^moving \S+\\.*',
    # d1\a: not recording move - dummy does not exist
    br'\S+\\\S+: not recording move .+',
    # reverting s\a
    br'(?m)^reverting (?!subrepo ).*\\.*',
    # saved backup bundle to
    #     $TESTTMP\test\.hg\strip-backup/443431ffac4f-2fc5398a-backup.hg
    br'(?m)^saved backup bundle to \$TESTTMP.*\.hg',
    # no changes made to subrepo s\ss since last push to ../tcc/s/ss
    br'(?m)^no changes made to subrepo \S+\\\S+ since.*',
    # changeset 5:9cc5aa7204f0: stuff/maybelarge.dat references missing
    #     $TESTTMP\largefiles-repo-hg\.hg\largefiles\76..38
    br'(?m)^changeset .* references (corrupted|missing) \$TESTTMP\\.*',
    # stuff/maybelarge.dat: largefile 76..38 not available from
    #     file:/*/$TESTTMP\largefiles-repo (glob)
    br'.*: largefile \S+ not available from file:/\*/.+',
]

if os.name == 'nt':
    substitutions.extend(
        [
            (s, lambda match: match.group().replace(b'\\', b'/'))
            for s in _winpathfixes
        ]
    )