view tests/f @ 42619:20d0e59be79b

tests: show the files fields of changelogs for many merges

I don't think there's coverage for many of the subtle cases, and I
found it hard to understand what the code is doing by reading it.  The
test takes 40s to run on a laptop, or 9s with --chg.

I have yet to find a description of what the files field is supposed
to be for merges. I thought it could be one of:
1. the files added/modified/removed relative to p1 (wouldn't seem
  useful, but `hg diff -c -r mergerev` has this behavior)
2. the files with filelog nodes not in either parent (i.e., what is
needed to create a bundle out of a commit)
3. the files added/removed/modified files by merge itself [1]

It's clearly not 1, because file contents merges are symmetric. It's
clearly not 2 because removed files and exec bit changes are
listed. It's also not 3 but I think it's intended to be 3 and the
differences are bugs.

Assuming 3, the test shows that, for merges, the list of files both
overapproximates and underapproximates. All the cases involve file
changes not in the filelog but in the manifest (existence of file
at revision, exec bit and file vs symlink).

I didn't look at all underapproximations, but they looked minor. The
two overapproximations are problematic though because they both cause
potentially long lists of files when merging cleanly.


[1] even what it means for the merge commit itself to change a file is
not completely trivial. A file in the merge being the same as in one
of the parent is too lax as it would consider that merges change
nothing when they revert all the changes done on one side. The
criteria used in the test and in the next commit for "merge didn't
touch a file" is:
- the parents and the merge all have the same file
- or, one parent didn't touch the file and the other parent contains
  the same file as the merge

Differential Revision: https://phab.mercurial-scm.org/D6612

#!/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 binascii
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(b'file')
            if any((opts.hexdump, opts.dump, opts.md5, opts.sha1, opts.sha256)):
                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.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("", "--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))