revlog: flag processor
Add the ability for revlog objects to process revision flags and apply
registered transforms on read/write operations.
This patch introduces:
- the 'revlog._processflags()' method that looks at revision flags and applies
flag processors registered on them. Due to the need to handle non-commutative
operations, flag transforms are applied in stable order but the order in which
the transforms are applied is reversed between read and write operations.
- the 'addflagprocessor()' method allowing to register processors on flags.
Flag processors are defined as a 3-tuple of (read, write, raw) functions to be
applied depending on the operation being performed.
- an update on 'revlog.addrevision()' behavior. The current flagprocessor design
relies on extensions to wrap around 'addrevision()' to set flags on revision
data, and on the flagprocessor to perform the actual transformation of its
contents. In the lfs case, this means we need to process flags before we meet
the 2GB size check, leading to performing some operations before it happens:
- if flags are set on the revision data, we assume some extensions might be
modifying the contents using the flag processor next, and we compute the
node for the original revision data (still allowing extension to override
the node by wrapping around 'addrevision()').
- we then invoke the flag processor to apply registered transforms (in lfs's
case, drastically reducing the size of large blobs).
- finally, we proceed with the 2GB size check.
Note: In the case a cachedelta is passed to 'addrevision()' and we detect the
flag processor modified the revision data, we chose to trust the flag processor
and drop the cachedelta.
2017-01-10 19:15:21 +03:00
|
|
|
# coding=UTF-8
|
|
|
|
|
|
|
|
from __future__ import absolute_import
|
|
|
|
|
|
|
|
import base64
|
|
|
|
import zlib
|
|
|
|
|
|
|
|
from mercurial import (
|
|
|
|
changegroup,
|
2017-04-07 03:23:20 +03:00
|
|
|
exchange,
|
revlog: flag processor
Add the ability for revlog objects to process revision flags and apply
registered transforms on read/write operations.
This patch introduces:
- the 'revlog._processflags()' method that looks at revision flags and applies
flag processors registered on them. Due to the need to handle non-commutative
operations, flag transforms are applied in stable order but the order in which
the transforms are applied is reversed between read and write operations.
- the 'addflagprocessor()' method allowing to register processors on flags.
Flag processors are defined as a 3-tuple of (read, write, raw) functions to be
applied depending on the operation being performed.
- an update on 'revlog.addrevision()' behavior. The current flagprocessor design
relies on extensions to wrap around 'addrevision()' to set flags on revision
data, and on the flagprocessor to perform the actual transformation of its
contents. In the lfs case, this means we need to process flags before we meet
the 2GB size check, leading to performing some operations before it happens:
- if flags are set on the revision data, we assume some extensions might be
modifying the contents using the flag processor next, and we compute the
node for the original revision data (still allowing extension to override
the node by wrapping around 'addrevision()').
- we then invoke the flag processor to apply registered transforms (in lfs's
case, drastically reducing the size of large blobs).
- finally, we proceed with the 2GB size check.
Note: In the case a cachedelta is passed to 'addrevision()' and we detect the
flag processor modified the revision data, we chose to trust the flag processor
and drop the cachedelta.
2017-01-10 19:15:21 +03:00
|
|
|
extensions,
|
|
|
|
filelog,
|
|
|
|
revlog,
|
|
|
|
util,
|
|
|
|
)
|
|
|
|
|
|
|
|
# Test only: These flags are defined here only in the context of testing the
|
|
|
|
# behavior of the flag processor. The canonical way to add flags is to get in
|
|
|
|
# touch with the community and make them known in revlog.
|
|
|
|
REVIDX_NOOP = (1 << 3)
|
|
|
|
REVIDX_BASE64 = (1 << 2)
|
|
|
|
REVIDX_GZIP = (1 << 1)
|
|
|
|
REVIDX_FAIL = 1
|
|
|
|
|
|
|
|
def validatehash(self, text):
|
|
|
|
return True
|
|
|
|
|
|
|
|
def bypass(self, text):
|
|
|
|
return False
|
|
|
|
|
|
|
|
def noopdonothing(self, text):
|
|
|
|
return (text, True)
|
|
|
|
|
|
|
|
def b64encode(self, text):
|
|
|
|
return (base64.b64encode(text), False)
|
|
|
|
|
|
|
|
def b64decode(self, text):
|
|
|
|
return (base64.b64decode(text), True)
|
|
|
|
|
|
|
|
def gzipcompress(self, text):
|
|
|
|
return (zlib.compress(text), False)
|
|
|
|
|
|
|
|
def gzipdecompress(self, text):
|
|
|
|
return (zlib.decompress(text), True)
|
|
|
|
|
|
|
|
def supportedoutgoingversions(orig, repo):
|
|
|
|
versions = orig(repo)
|
|
|
|
versions.discard('01')
|
|
|
|
versions.discard('02')
|
|
|
|
versions.add('03')
|
|
|
|
return versions
|
|
|
|
|
|
|
|
def allsupportedversions(orig, ui):
|
|
|
|
versions = orig(ui)
|
|
|
|
versions.add('03')
|
|
|
|
return versions
|
|
|
|
|
|
|
|
def noopaddrevision(orig, self, text, transaction, link, p1, p2,
|
|
|
|
cachedelta=None, node=None,
|
|
|
|
flags=revlog.REVIDX_DEFAULT_FLAGS):
|
|
|
|
if '[NOOP]' in text:
|
|
|
|
flags |= REVIDX_NOOP
|
|
|
|
return orig(self, text, transaction, link, p1, p2, cachedelta=cachedelta,
|
|
|
|
node=node, flags=flags)
|
|
|
|
|
|
|
|
def b64addrevision(orig, self, text, transaction, link, p1, p2,
|
|
|
|
cachedelta=None, node=None,
|
|
|
|
flags=revlog.REVIDX_DEFAULT_FLAGS):
|
|
|
|
if '[BASE64]' in text:
|
|
|
|
flags |= REVIDX_BASE64
|
|
|
|
return orig(self, text, transaction, link, p1, p2, cachedelta=cachedelta,
|
|
|
|
node=node, flags=flags)
|
|
|
|
|
|
|
|
def gzipaddrevision(orig, self, text, transaction, link, p1, p2,
|
|
|
|
cachedelta=None, node=None,
|
|
|
|
flags=revlog.REVIDX_DEFAULT_FLAGS):
|
|
|
|
if '[GZIP]' in text:
|
|
|
|
flags |= REVIDX_GZIP
|
|
|
|
return orig(self, text, transaction, link, p1, p2, cachedelta=cachedelta,
|
|
|
|
node=node, flags=flags)
|
|
|
|
|
|
|
|
def failaddrevision(orig, self, text, transaction, link, p1, p2,
|
|
|
|
cachedelta=None, node=None,
|
|
|
|
flags=revlog.REVIDX_DEFAULT_FLAGS):
|
|
|
|
# This addrevision wrapper is meant to add a flag we will not have
|
|
|
|
# transforms registered for, ensuring we handle this error case.
|
|
|
|
if '[FAIL]' in text:
|
|
|
|
flags |= REVIDX_FAIL
|
|
|
|
return orig(self, text, transaction, link, p1, p2, cachedelta=cachedelta,
|
|
|
|
node=node, flags=flags)
|
|
|
|
|
|
|
|
def extsetup(ui):
|
|
|
|
# Enable changegroup3 for flags to be sent over the wire
|
|
|
|
wrapfunction = extensions.wrapfunction
|
|
|
|
wrapfunction(changegroup,
|
|
|
|
'supportedoutgoingversions',
|
|
|
|
supportedoutgoingversions)
|
|
|
|
wrapfunction(changegroup,
|
|
|
|
'allsupportedversions',
|
|
|
|
allsupportedversions)
|
|
|
|
|
|
|
|
# Teach revlog about our test flags
|
|
|
|
flags = [REVIDX_NOOP, REVIDX_BASE64, REVIDX_GZIP, REVIDX_FAIL]
|
|
|
|
revlog.REVIDX_KNOWN_FLAGS |= util.bitsfrom(flags)
|
|
|
|
revlog.REVIDX_FLAGS_ORDER.extend(flags)
|
|
|
|
|
2017-04-07 03:23:20 +03:00
|
|
|
# Teach exchange to use changegroup 3
|
|
|
|
for k in exchange._bundlespeccgversions.keys():
|
|
|
|
exchange._bundlespeccgversions[k] = '03'
|
|
|
|
|
revlog: flag processor
Add the ability for revlog objects to process revision flags and apply
registered transforms on read/write operations.
This patch introduces:
- the 'revlog._processflags()' method that looks at revision flags and applies
flag processors registered on them. Due to the need to handle non-commutative
operations, flag transforms are applied in stable order but the order in which
the transforms are applied is reversed between read and write operations.
- the 'addflagprocessor()' method allowing to register processors on flags.
Flag processors are defined as a 3-tuple of (read, write, raw) functions to be
applied depending on the operation being performed.
- an update on 'revlog.addrevision()' behavior. The current flagprocessor design
relies on extensions to wrap around 'addrevision()' to set flags on revision
data, and on the flagprocessor to perform the actual transformation of its
contents. In the lfs case, this means we need to process flags before we meet
the 2GB size check, leading to performing some operations before it happens:
- if flags are set on the revision data, we assume some extensions might be
modifying the contents using the flag processor next, and we compute the
node for the original revision data (still allowing extension to override
the node by wrapping around 'addrevision()').
- we then invoke the flag processor to apply registered transforms (in lfs's
case, drastically reducing the size of large blobs).
- finally, we proceed with the 2GB size check.
Note: In the case a cachedelta is passed to 'addrevision()' and we detect the
flag processor modified the revision data, we chose to trust the flag processor
and drop the cachedelta.
2017-01-10 19:15:21 +03:00
|
|
|
# Add wrappers for addrevision, responsible to set flags depending on the
|
|
|
|
# revision data contents.
|
|
|
|
wrapfunction(filelog.filelog, 'addrevision', noopaddrevision)
|
|
|
|
wrapfunction(filelog.filelog, 'addrevision', b64addrevision)
|
|
|
|
wrapfunction(filelog.filelog, 'addrevision', gzipaddrevision)
|
|
|
|
wrapfunction(filelog.filelog, 'addrevision', failaddrevision)
|
|
|
|
|
|
|
|
# Register flag processors for each extension
|
|
|
|
revlog.addflagprocessor(
|
|
|
|
REVIDX_NOOP,
|
|
|
|
(
|
|
|
|
noopdonothing,
|
|
|
|
noopdonothing,
|
|
|
|
validatehash,
|
|
|
|
)
|
|
|
|
)
|
|
|
|
revlog.addflagprocessor(
|
|
|
|
REVIDX_BASE64,
|
|
|
|
(
|
|
|
|
b64decode,
|
|
|
|
b64encode,
|
|
|
|
bypass,
|
|
|
|
),
|
|
|
|
)
|
|
|
|
revlog.addflagprocessor(
|
|
|
|
REVIDX_GZIP,
|
|
|
|
(
|
|
|
|
gzipdecompress,
|
|
|
|
gzipcompress,
|
|
|
|
bypass
|
|
|
|
)
|
|
|
|
)
|