Mercurial > hg
view tests/f @ 33289:abd7dedbaa36
sparse: vendor Facebook-developed extension
Facebook has developed an extension to enable "sparse" checkouts -
a working directory with a subset of files. This feature is a critical
component in enabling repositories to scale to infinite number of
files while retaining reasonable performance. It's worth noting
that sparse checkout is only one possible solution to this problem:
another is virtual filesystems that realize files on first access.
But given that virtual filesystems may not be accessible to all
users, sparse checkout is necessary as a fallback.
Per mailing list discussion at
https://www.mercurial-scm.org/pipermail/mercurial-devel/2017-March/095868.html
we want to add sparse checkout to the Mercurial distribution via
roughly the following mechanism:
1. Vendor extension as-is with minimal modifications (this patch)
2. Refactor extension so it is more clearly experimental and inline
with Mercurial practices
3. Move code from extension into core where possible
4. Drop experimental labeling and/or move feature into core
after sign-off from narrow clone feature owners
This commit essentially copies the sparse extension and tests
from revision 71e0a2aeca92a4078fe1b8c76e32c88ff1929737 of the
https://bitbucket.org/facebook/hg-experimental repository.
A list of modifications made as part of vendoring is as follows:
* "EXPERIMENTAL" added to module docstring
* Imports were changed to match Mercurial style conventions
* "testedwith" value was updated to core Mercurial special value and
comment boilerplate was inserted
* A "clone_sparse" function was renamed to "clonesparse" to appease
the style checker
* Paths to the sparse extension in tests reflect built-in location
* test-sparse-extensions.t was renamed to test-sparse-fsmonitor.t
and references to "simplecache" were removed. The test always skips
because it isn't trivial to run it given the way we currently run
fsmonitor tests
* A double empty line was removed from test-sparse-profiles.t
There are aspects of the added code that are obviously not ideal.
The goal is to make a minimal number of modifications as part of
the vendoring to make it easier to track changes from the original
implementation. Refactoring will occur in subsequent patches.
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Sat, 01 Jul 2017 10:43:29 -0700 |
parents | c425b678df7c |
children | 3db2365d43e4 |
line wrap: on
line source
#!/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 glob import hashlib import optparse import os import re import sys 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('%s: file not found\n' % f) 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('file') if opts.hexdump or opts.dump or opts.md5: content = open(f, 'rb').read() elif islink: if opts.type: facts.append('link') content = os.readlink(f) elif isstdin: content = sys.stdin.read() if opts.size: facts.append('size=%s' % len(content)) elif isdir: if opts.recurse or opts.type: dirfiles = glob.glob(f + '/*') facts.append('directory with %s files' % len(dirfiles)) elif opts.type: facts.append('type unknown') if not isstdin: stat = os.lstat(f) if opts.size and not isdir: facts.append('size=%s' % stat.st_size) if opts.mode and not islink: facts.append('mode=%o' % (stat.st_mode & 0o777)) if opts.links: facts.append('links=%s' % 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('newer than %s' % opts.newer) else: facts.append('older than %s' % opts.newer) if opts.md5 and content is not None: h = hashlib.md5(content) facts.append('md5=%s' % h.hexdigest()[:opts.bytes]) if opts.sha1 and content is not None: h = hashlib.sha1(content) facts.append('sha1=%s' % h.hexdigest()[:opts.bytes]) if isstdin: outfile.write(', '.join(facts) + '\n') elif facts: outfile.write('%s: %s\n' % (f, ', '.join(facts))) elif not quiet: outfile.write('%s:\n' % f) if content is not None: chunk = content if not islink: if opts.lines: if opts.lines >= 0: chunk = ''.join(chunk.splitlines(True)[:opts.lines]) else: chunk = ''.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('%04x: %-47s |%s|\n' % (i, ' '.join('%02x' % ord(c) for c in s), re.sub('[^ -~]', '.', s))) if opts.dump: if not quiet: outfile.write('>>>\n') outfile.write(chunk) if not quiet: if chunk.endswith('\n'): outfile.write('<<<\n') else: outfile.write('\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("-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, sys.stdout)