tests/generate-working-copy-states.py
author Georges Racinet <georges.racinet@octobus.net>
Fri, 27 Oct 2023 22:11:05 +0200
changeset 51239 7eea2e4109ae
parent 48875 6000f5b25c9b
child 51690 493034cc3265
permissions -rw-r--r--
rust-index: using the `hg::index::Index` in ancestors iterator and lazy set Since there is no Rust implementation for REVLOGV2/CHANGELOGv2, we declare them to be incompatible with Rust, hence indexes in these formats will use the implementations from Python `mercurial.ancestor`. If this is an unacceptable performance hit for current users of these formats, we can later on add Rust implementations based on the C index for them or implement these formats for the Rust indexes. Among the challenges that we had to meet, we wanted to avoid taking the GIL each time the inner (vcsgraph) iterator has to call the parents function. This would probably still be acceptable in terms of performance with `AncestorsIterator`, but not with `LazyAncestors` nor for the upcoming change in `MissingAncestors`. Hence we enclose the reference to the index in a `PySharedRef`, leading to more rigourous checking of mutations, which does pass now that there no logically immutable methods of `hg::index::Index` that take a mutable reference as input.

# 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)