tests/f
author Pierre-Yves David <pierre-yves.david@octobus.net>
Wed, 21 Feb 2024 10:41:09 +0100
changeset 51409 2f39c7aeb549
parent 49873 e9d06ed64161
permissions -rwxr-xr-x
phases: large rewrite on retract boundary The new code is still pure Python, so we still have room to going significantly faster. However its complexity of the complex part is `O(|[min_new_draft, tip]|)` instead of `O(|[min_draft, tip]|` which should help tremendously one repository with old draft (like mercurial-devel or mozilla-try). This is especially useful as the most common "retract boundary" operation happens when we commit/rewrite new drafts or when we push new draft to a non-publishing server. In this case, the smallest new_revs is very close to the tip and there is very few work to do. A few smaller optimisation could be done for these cases and will be introduced in later changesets. We still have iterate over large sets of roots, but this is already a great improvement for a very small amount of work. We gather information on the affected changeset as we go as we can put it to use in the next changesets. This extra data collection might slowdown the `register_new` case a bit, however for register_new, it should not really matters. The set of new nodes is either small, so the impact is negligible, or the set of new nodes is large, and the amount of work to do to had them will dominate the overhead the collecting information in `changed_revs`. As this new code compute the changes on the fly, it unlock other interesting improvement to be done in later changeset.

#!/usr/bin/env python3

"""
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
"""


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


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


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')
            needs_reading = (
                opts.hexdump,
                opts.dump,
                opts.md5,
                opts.sha1,
                opts.raw_sha1,
                opts.sha256,
            )

            if any(needs_reading):
                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.raw_sha1 and content is not None:
            h = hashlib.sha1(content)
            facts.append(b'raw-sha1=%s' % 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(
        "",
        "--raw-sha1",
        action="store_true",
        help="show raw bytes of the 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))