##// END OF EJS Templates
nodemap: gate the feature behind a new requirement...
nodemap: gate the feature behind a new requirement Now that the feature is working smoothly, a question was still open, should we gate the feature behind a new requirement or just treat it as a cache to be warmed by those who can and ignored by other. The advantage of using the cache approach is a transparent upgrade/downgrade story, making the feature easier to move to. However having out of date cache can come with a significant performance hit for process who expect an up to date cache but found none. In this case the file needs to be stored under `.hg/cache`. The "requirement" approach guarantee that the persistent nodemap is up to date. However, it comes with a less flexible activation story since an explicite upgrade is required. In this case the file can be stored in `.hg/store`. This wiki page is relevant to this questions: https://www.mercurial-scm.org/wiki/ComputedIndexPlan So which one should we take? Another element came into plan, the persistent nodemap use the `add` method of the transaction, it is used to keep track of a file content before a transaction in case we need to rollback it back. It turns out that the `transaction.add` API does not support file stored anywhere than `.hg/store`. Making it support file stored elsewhere is possible, require a change in on disk transaction format. Updating on disk file requires… introducing a new requirements. As a result, we pick the second option "gating the persistent nodemap behind a new requirements". Differential Revision: https://phab.mercurial-scm.org/D8417

File last commit:

r43347:687b865b default
r45295:b81486b6 default
Show More
flagutil.py
192 lines | 7.3 KiB | text/x-python | PythonLexer
# 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