view tests/flagprocessorext.py @ 33388:0823f0983eaa

convert: transcode CVS log messages by specified encoding (issue5597) Converting from CVS to Mercurial assumes that CVS log messages in "cvs rlog" output are encoded in UTF-8 (or basic Latin-1). But cvs itself is usually unaware of encoding of log messages, in practice. Therefore, if there are commits, of which log message is encoded in other than UTF-8, log message of corresponded revisions in the converted repository will be broken. To avoid such broken log messages, this patch transcodes CVS log messages by encoding specified via "convert.cvsps.logencoding" configuration. This patch accepts multiple encoding for convenience, because "multiple encoding mixed in a repository" easily occurs. For example, UTF-8 (recent POSIX), cp932 (Windows), and EUC-JP (legacy POSIX) are well known encoding for Japanese.
author FUJIWARA Katsunori <foozy@lares.dti.ne.jp>
date Tue, 11 Jul 2017 02:10:04 +0900
parents 77f746e5383a
children 3e3f4c03876b
line wrap: on
line source

# coding=UTF-8

from __future__ import absolute_import

import base64
import zlib

from mercurial import (
    changegroup,
    exchange,
    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)

    # Teach exchange to use changegroup 3
    for k in exchange._bundlespeccgversions.keys():
        exchange._bundlespeccgversions[k] = '03'

    # 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
        )
    )