tests/f

bundle2: implement consume() API on unbundlepart

We want bundle parts to not be seekable by default. That means
eliminating the generic seek() method.

A common pattern in bundle2.py is to seek to the end of the part
data. This is mainly used by the part iteration code to ensure
the underlying stream is advanced to the next bundle part.

In this commit, we establish a dedicated API for consuming a
bundle2 part data. We switch users of seek() to it.

The old implementation of seek(0, os.SEEK_END) would effectively
call self.read(). The new implementation calls self.read(32768)
in a loop. The old implementation would therefore assemble a
buffer to hold all remaining data being seeked over. For seeking
over large bundle parts, this would involve a large allocation and
a lot of overhead to collect intermediate data! This overhead can
be seen in the results for `hg perfbundleread`:

! bundle2 iterparts()
! wall 10.891305 comb 10.820000 user 7.990000 sys 2.830000 (best of 3)
! wall 8.070791 comb 8.060000 user 7.180000 sys 0.880000 (best of 3)
! bundle2 part seek()
! wall 12.991478 comb 10.390000 user 7.720000 sys 2.670000 (best of 3)
! wall 10.370142 comb 10.350000 user 7.430000 sys 2.920000 (best of 3)

Of course, skipping over large payload data isn't likely very common.
So I doubt the performance wins will be observed in the wild.

Differential Revision: https://phab.mercurial-scm.org/D1388

#!/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

# Python 3 adapters
ispy3 = (sys.version_info[0] >= 3)
if ispy3:
    def iterbytes(s):
        for i in range(len(s)):
            yield s[i:i + 1]
else:
    iterbytes = iter

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('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 = getattr(sys.stdin, 'buffer', 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(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("-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))