view mercurial/revlogutils/flagutil.py @ 43254:181d28ba05da

copies: avoid instancing more changectx to access parent revisions We just need to know the revision numbers of the parents, creating full context is needlessly expensive. This provide a small, but noticeable performance boost. revision: large amount; added files: large amount; rename small amount; c3b14617fbd7 9ba6ab77fd29 before: ! wall 2.885636 comb 2.900000 user 2.870000 sys 0.030000 (median of 10) after: ! wall 2.702270 comb 2.710000 user 2.690000 sys 0.020000 (median of 10) revision: large amount; added files: small amount; rename small amount; c3b14617fbd7 f650a9b140d2 before: ! wall 4.298271 comb 4.290000 user 4.240000 sys 0.050000 (median of 10) after: ! wall 3.976610 comb 3.970000 user 3.920000 sys 0.050000 (median of 10) revision: large amount; added files: large amount; rename large amount; 08ea3258278e d9fa043f30c0 before: ! wall 0.773397 comb 0.770000 user 0.770000 sys 0.000000 (median of 11) after: ! wall 0.701634 comb 0.700000 user 0.700000 sys 0.000000 (median of 13) revision: small amount; added files: large amount; rename large amount; df6f7a526b60 a83dc6a2d56f before: ! wall 0.013585 comb 0.010000 user 0.010000 sys 0.000000 (median of 217) after: ! wall 0.013550 comb 0.010000 user 0.010000 sys 0.000000 (median of 218) revision: small amount; added files: large amount; rename small amount; 4aa4e1f8e19a 169138063d63 before: ! wall 0.003202 comb 0.000000 user 0.000000 sys 0.000000 (median of 929) after: ! wall 0.002993 comb 0.010000 user 0.010000 sys 0.000000 (median of 992) revision: small amount; added files: small amount; rename small amount; 4bc173b045a6 964879152e2e before: ! wall 0.000077 comb 0.000000 user 0.000000 sys 0.000000 (median of 12060) after: ! wall 0.000072 comb 0.000000 user 0.000000 sys 0.000000 (median of 12804) revision: medium amount; added files: large amount; rename medium amount; c95f1ced15f2 2c68e87c3efe before: ! wall 0.510614 comb 0.500000 user 0.500000 sys 0.000000 (median of 18) after: ! wall 0.473681 comb 0.470000 user 0.470000 sys 0.000000 (median of 20) revision: medium amount; added files: medium amount; rename small amount; d343da0c55a8 d7746d32bf9d before: ! wall 0.126552 comb 0.130000 user 0.130000 sys 0.000000 (median of 77) after: ! wall 0.115240 comb 0.110000 user 0.110000 sys 0.000000 (median of 85) Differential Revision: https://phab.mercurial-scm.org/D7122
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Wed, 16 Oct 2019 17:49:30 +0200
parents 687b865b95ad
children 2d6aea053153
line wrap: on
line source

# flagutils.py - code to deal with revlog flags and their processors
#
# Copyright 2016 Remi Chaintron <remi@fb.com>
# Copyright 2016-2019 Pierre-Yves David <pierre-yves.david@ens-lyon.org>
#
# 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

from ..i18n import _

from .constants import (
    REVIDX_DEFAULT_FLAGS,
    REVIDX_ELLIPSIS,
    REVIDX_EXTSTORED,
    REVIDX_FLAGS_ORDER,
    REVIDX_ISCENSORED,
    REVIDX_RAWTEXT_CHANGING_FLAGS,
    REVIDX_SIDEDATA,
)

from .. import error, util

# blanked usage of all the name to prevent pyflakes constraints
# We need these name available in the module for extensions.
REVIDX_ISCENSORED
REVIDX_ELLIPSIS
REVIDX_EXTSTORED
REVIDX_SIDEDATA
REVIDX_DEFAULT_FLAGS
REVIDX_FLAGS_ORDER
REVIDX_RAWTEXT_CHANGING_FLAGS

REVIDX_KNOWN_FLAGS = util.bitsfrom(REVIDX_FLAGS_ORDER)

# Store flag processors (cf. 'addflagprocessor()' to register)
flagprocessors = {
    REVIDX_ISCENSORED: None,
}


def addflagprocessor(flag, processor):
    """Register a flag processor on a revision data flag.

    Invariant:
    - Flags need to be defined in REVIDX_KNOWN_FLAGS and REVIDX_FLAGS_ORDER,
      and REVIDX_RAWTEXT_CHANGING_FLAGS if they can alter rawtext.
    - Only one flag processor can be registered on a specific flag.
    - flagprocessors must be 3-tuples of functions (read, write, raw) with the
      following signatures:
          - (read)  f(self, rawtext) -> text, bool
          - (write) f(self, text) -> rawtext, bool
          - (raw)   f(self, rawtext) -> bool
      "text" is presented to the user. "rawtext" is stored in revlog data, not
      directly visible to the user.
      The boolean returned by these transforms is used to determine whether
      the returned text can be used for hash integrity checking. For example,
      if "write" returns False, then "text" is used to generate hash. If
      "write" returns True, that basically means "rawtext" returned by "write"
      should be used to generate hash. Usually, "write" and "read" return
      different booleans. And "raw" returns a same boolean as "write".

      Note: The 'raw' transform is used for changegroup generation and in some
      debug commands. In this case the transform only indicates whether the
      contents can be used for hash integrity checks.
    """
    insertflagprocessor(flag, processor, flagprocessors)


def insertflagprocessor(flag, processor, flagprocessors):
    if not flag & REVIDX_KNOWN_FLAGS:
        msg = _(b"cannot register processor on unknown flag '%#x'.") % flag
        raise error.ProgrammingError(msg)
    if flag not in REVIDX_FLAGS_ORDER:
        msg = _(b"flag '%#x' undefined in REVIDX_FLAGS_ORDER.") % flag
        raise error.ProgrammingError(msg)
    if flag in flagprocessors:
        msg = _(b"cannot register multiple processors on flag '%#x'.") % flag
        raise error.Abort(msg)
    flagprocessors[flag] = processor


def processflagswrite(revlog, text, flags, sidedata):
    """Inspect revision data flags and applies write transformations defined
    by registered flag processors.

    ``text`` - the revision data to process
    ``flags`` - the revision flags

    This method processes the flags in the order (or reverse order if
    ``operation`` is 'write') defined by REVIDX_FLAGS_ORDER, applying the
    flag processors registered for present flags. The order of flags defined
    in REVIDX_FLAGS_ORDER needs to be stable to allow non-commutativity.

    Returns a 2-tuple of ``(text, validatehash)`` where ``text`` is the
    processed text and ``validatehash`` is a bool indicating whether the
    returned text should be checked for hash integrity.
    """
    return _processflagsfunc(revlog, text, flags, b'write', sidedata=sidedata)[
        :2
    ]


def processflagsread(revlog, text, flags):
    """Inspect revision data flags and applies read transformations defined
    by registered flag processors.

    ``text`` - the revision data to process
    ``flags`` - the revision flags
    ``raw`` - an optional argument describing if the raw transform should be
    applied.

    This method processes the flags in the order (or reverse order if
    ``operation`` is 'write') defined by REVIDX_FLAGS_ORDER, applying the
    flag processors registered for present flags. The order of flags defined
    in REVIDX_FLAGS_ORDER needs to be stable to allow non-commutativity.

    Returns a 2-tuple of ``(text, validatehash)`` where ``text`` is the
    processed text and ``validatehash`` is a bool indicating whether the
    returned text should be checked for hash integrity.
    """
    return _processflagsfunc(revlog, text, flags, b'read')


def processflagsraw(revlog, text, flags):
    """Inspect revision data flags to check is the content hash should be
    validated.

    ``text`` - the revision data to process
    ``flags`` - the revision flags

    This method processes the flags in the order (or reverse order if
    ``operation`` is 'write') defined by REVIDX_FLAGS_ORDER, applying the
    flag processors registered for present flags. The order of flags defined
    in REVIDX_FLAGS_ORDER needs to be stable to allow non-commutativity.

    Returns a 2-tuple of ``(text, validatehash)`` where ``text`` is the
    processed text and ``validatehash`` is a bool indicating whether the
    returned text should be checked for hash integrity.
    """
    return _processflagsfunc(revlog, text, flags, b'raw')[1]


def _processflagsfunc(revlog, text, flags, operation, sidedata=None):
    """internal function to process flag on a revlog

    This function is private to this module, code should never needs to call it
    directly."""
    # fast path: no flag processors will run
    if flags == 0:
        return text, True, {}
    if operation not in (b'read', b'write', b'raw'):
        raise error.ProgrammingError(_(b"invalid '%s' operation") % operation)
    # Check all flags are known.
    if flags & ~REVIDX_KNOWN_FLAGS:
        raise revlog._flagserrorclass(
            _(b"incompatible revision flag '%#x'")
            % (flags & ~REVIDX_KNOWN_FLAGS)
        )
    validatehash = True
    # Depending on the operation (read or write), the order might be
    # reversed due to non-commutative transforms.
    orderedflags = REVIDX_FLAGS_ORDER
    if operation == b'write':
        orderedflags = reversed(orderedflags)

    outsidedata = {}
    for flag in orderedflags:
        # If a flagprocessor has been registered for a known flag, apply the
        # related operation transform and update result tuple.
        if flag & flags:
            vhash = True

            if flag not in revlog._flagprocessors:
                message = _(b"missing processor for flag '%#x'") % flag
                raise revlog._flagserrorclass(message)

            processor = revlog._flagprocessors[flag]
            if processor is not None:
                readtransform, writetransform, rawtransform = processor

                if operation == b'raw':
                    vhash = rawtransform(revlog, text)
                elif operation == b'read':
                    text, vhash, s = readtransform(revlog, text)
                    outsidedata.update(s)
                else:  # write operation
                    text, vhash = writetransform(revlog, text, sidedata)
            validatehash = validatehash and vhash

    return text, validatehash, outsidedata