view mercurial/py3kcompat.py @ 28203:7297e9e13a8a

verify: check directory manifests

In repos with treemanifests, there is no specific verification of
directory manifest revlogs. It simply collects all file nodes by
reading each manifest delta. With treemanifests, that's means calling
the manifest._slowreaddelta(). If there are missing revlog entries in
a subdirectory revlog, 'hg verify' will simply report the exception
that occurred while trying to read the root manifest:


  manifest@0: reading delta 1700e2e92882: meta/b/00manifest.i@67688a370455: no node

This patch changes the verify code to load only the root manifest at
first and verify all revisions of it, then verify all revisions of
each direct subdirectory, and so on, recursively. The above message
becomes

  b/@0: parent-directory manifest refers to unknown revision 67688a370455

Since the new algorithm reads a single revlog at a time and in order,
'hg verify' on a treemanifest version of the hg core repo goes from
~50s to ~14s. As expected, there is no significant difference on a
repo with flat manifests.

# py3kcompat.py - compatibility definitions for running hg in py3k
#
# Copyright 2010 Renato Cunha <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import builtins
import numbers

Number = numbers.Number

def bytesformatter(format, args):
    '''Custom implementation of a formatter for bytestrings.

    This function currently relies on the string formatter to do the
    formatting and always returns bytes objects.

    >>> bytesformatter(20, 10)
    0
    >>> bytesformatter('unicode %s, %s!', ('string', 'foo'))
    b'unicode string, foo!'
    >>> bytesformatter(b'test %s', 'me')
    b'test me'
    >>> bytesformatter('test %s', 'me')
    b'test me'
    >>> bytesformatter(b'test %s', b'me')
    b'test me'
    >>> bytesformatter('test %s', b'me')
    b'test me'
    >>> bytesformatter('test %d: %s', (1, b'result'))
    b'test 1: result'
    '''
    # The current implementation just converts from bytes to unicode, do
    # what's needed and then convert the results back to bytes.
    # Another alternative is to use the Python C API implementation.
    if isinstance(format, Number):
        # If the fixer erroneously passes a number remainder operation to
        # bytesformatter, we just return the correct operation
        return format % args
    if isinstance(format, bytes):
        format = format.decode('utf-8', 'surrogateescape')
    if isinstance(args, bytes):
        args = args.decode('utf-8', 'surrogateescape')
    if isinstance(args, tuple):
        newargs = []
        for arg in args:
            if isinstance(arg, bytes):
                arg = arg.decode('utf-8', 'surrogateescape')
            newargs.append(arg)
        args = tuple(newargs)
    ret = format % args
    return ret.encode('utf-8', 'surrogateescape')
builtins.bytesformatter = bytesformatter

origord = builtins.ord
def fakeord(char):
    if isinstance(char, int):
        return char
    return origord(char)
builtins.ord = fakeord

if __name__ == '__main__':
    import doctest
    doctest.testmod()