tests/generate-working-copy-states.py
author Pierre-Yves David <pierre-yves.david@octobus.net>
Sun, 14 Apr 2024 02:33:36 +0200
changeset 51587 8cd317c033b8
parent 48875 6000f5b25c9b
permissions -rw-r--r--
stream-clone: disable gc for the entry listing section for the v2 format This is similar to the change we did for the v3 format in 6e4c8366c5ce. The benchmark bellow show this gives us a notable gains, especially on larger repositories. ### benchmark.name = hg.perf.stream-locked-section # benchmark.name = hg.perf.stream-locked-section # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.version = v2 ## data-env-vars.name = pypy-2018-08-01-zstd-sparse-revlog 5e931bf8707c: 0.503820 ~~~~~ 1106d1bf695e: 0.470078 (-6.70%, -0.03) ## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog 5e931bf8707c: 0.535756 ~~~~~ 1106d1bf695e: 0.490249 (-8.49%, -0.05) ## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog 5e931bf8707c: 1.327041 ~~~~~ 1106d1bf695e: 1.174636 (-11.48%, -0.15) ## data-env-vars.name = netbeans-2018-08-01-zstd-sparse-revlog 5e931bf8707c: 2.439158 ~~~~~ 1106d1bf695e: 2.220515 (-8.96%, -0.22) ## data-env-vars.name = netbeans-2019-11-07-zstd-sparse-revlog 5e931bf8707c: 2.630794 ~~~~~ 1106d1bf695e: 2.261473 (-14.04%, -0.37) ## data-env-vars.name = mozilla-central-2018-08-01-zstd-sparse-revlog 5e931bf8707c: 5.769002 ~~~~~ 1106d1bf695e: 5.062000 (-12.26%, -0.71) ## data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog 5e931bf8707c: 13.351750 ~~~~~ 1106d1bf695e: 12.346655 (-7.53%, -1.01) ## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog 5e931bf8707c: 10.772939 ~~~~~ 1106d1bf695e: 9.495407 (-11.86%, -1.28) ## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog 5e931bf8707c: 10.864297 ~~~~~ 1106d1bf695e: 9.475597 (-12.78%, -1.39) ## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog 5e931bf8707c: 17.448335 ~~~~~ 1106d1bf695e: 16.027474 (-8.14%, -1.42)

# Helper script used for generating history and working copy files and content.
# The file's name corresponds to its history. The number of changesets can
# be specified on the command line. With 2 changesets, files with names like
# content1_content2_content1-untracked are generated. The first two filename
# segments describe the contents in the two changesets. The third segment
# ("content1-untracked") describes the state in the working copy, i.e.
# the file has content "content1" and is untracked (since it was previously
# tracked, it has been forgotten).
#
# This script generates the filenames and their content, but it's up to the
# caller to tell hg about the state.
#
# There are two subcommands:
#   filelist <numchangesets>
#   state <numchangesets> (<changeset>|wc)
#
# Typical usage:
#
# $ python $TESTDIR/generate-working-copy-states.py state 2 1
# $ hg addremove --similarity 0
# $ hg commit -m 'first'
#
# $ python $TESTDIR/generate-working-copy-states.py state 2 1
# $ hg addremove --similarity 0
# $ hg commit -m 'second'
#
# $ python $TESTDIR/generate-working-copy-states.py state 2 wc
# $ hg addremove --similarity 0
# $ hg forget *_*_*-untracked
# $ rm *_*_missing-*


import os
import sys

# Generates pairs of (filename, contents), where 'contents' is a list
# describing the file's content at each revision (or in the working copy).
# At each revision, it is either None or the file's actual content. When not
# None, it may be either new content or the same content as an earlier
# revisions, so all of (modified,clean,added,removed) can be tested.
def generatestates(maxchangesets, parentcontents):
    depth = len(parentcontents)
    if depth == maxchangesets + 1:
        for tracked in (b'untracked', b'tracked'):
            filename = (
                b"_".join(
                    [
                        (content is None and b'missing' or content)
                        for content in parentcontents
                    ]
                )
                + b"-"
                + tracked
            )
            yield (filename, parentcontents)
    else:
        for content in {None, b'content' + (b"%d" % (depth + 1))} | set(
            parentcontents
        ):
            for combination in generatestates(
                maxchangesets, parentcontents + [content]
            ):
                yield combination


# retrieve the command line arguments
target = sys.argv[1]
maxchangesets = int(sys.argv[2])
if target == 'state':
    depth = sys.argv[3]

# sort to make sure we have stable output
combinations = sorted(generatestates(maxchangesets, []))

# compute file content
content = []
for filename, states in combinations:
    if target == 'filelist':
        print(filename.decode('ascii'))
    elif target == 'state':
        if depth == 'wc':
            # Make sure there is content so the file gets written and can be
            # tracked. It will be deleted outside of this script.
            content.append((filename, states[maxchangesets] or b'TOBEDELETED'))
        else:
            content.append((filename, states[int(depth) - 1]))
    else:
        print("unknown target:", target, file=sys.stderr)
        sys.exit(1)

# write actual content
for filename, data in content:
    if data is not None:
        f = open(filename, 'wb')
        f.write(data + b'\n')
        f.close()
    elif os.path.exists(filename):
        os.remove(filename)