view tests/f @ 30561:7c0c722d568d

bdiff: early pruning of common prefix before doing expensive computations

It seems quite common that files don't change completely. New lines are often
pretty much appended, and modifications will often only change a small section
of the file which on average will be in the middle.

There can thus be a big win by pruning a common prefix before starting the more
expensive search for longest common substrings.

Worst case, it will scan through a long sequence of similar bytes without
encountering a newline. Splitlines will then have to do the same again ...
twice for each side. If similar lines are found, splitlines will save the
double iteration and hashing of the lines ... plus there will be less lines to
find common substrings in.

This change might in some cases make the algorith pick shorter or less optimal
common substrings. We can't have the cake and eat it.

This make hg --time bundle --base null -r 4.0 go from 14.5 to 15 s - a 3%
increase.

On mozilla-unified:
perfbdiff -m 3041e4d59df2
! wall 0.053088 comb 0.060000 user 0.060000 sys 0.000000 (best of 100) to
! wall 0.024618 comb 0.020000 user 0.020000 sys 0.000000 (best of 116)
perfbdiff 0e9928989e9c --alldata --count 10
! wall 0.702075 comb 0.700000 user 0.700000 sys 0.000000 (best of 15) to
! wall 0.579235 comb 0.580000 user 0.580000 sys 0.000000 (best of 18)

#!/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 = file(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)