view tests/f @ 39842:97986c9c69d3

verify: start to abstract file verification

Currently, the file storage interface has a handful of attributes
that are exclusively or near-exclusively used by repo verification
code. In order to support verification on non-revlog/alternate
storage backends, we'll need to abstract verification so it can
be performed in a storage-agnostic way.

This commit starts that process.

We establish a new verifyintegrity() method on revlogs and expose
it to the file storage interface. Most of verify.verifier.checklog()
has been ported to this new method.

We need a way to represent verification problems. So we invent an
interface to represent a verification problem, invent a revlog type
to implement that interface, and use it.

The arguments to verifyintegrity() will almost certainly change in
the future, once more functionality is ported from the verify code.
And the "revlogv1" version check is very hacky. (The code in verify
is actually buggy because it is comparing the full 32-bit header
integer instead of just the revlog version short. I'll likely fix
this in a subsequent commit.)

Differential Revision: https://phab.mercurial-scm.org/D4701

#!/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)
        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)
                else:
                    facts.append(b'older than %s' % opts.newer)
        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))