annotate tests/test-filecache.py @ 37048:fc5e261915b9

wireproto: require POST for all HTTPv2 requests

Wire protocol version 1 transfers argument data via request
headers by default. This has historically caused problems because
servers institute limits on the length of individual HTTP headers
as well as the total size of all request headers. Mercurial servers
can advertise the maximum length of an individual header. But
there's no guarantee any intermediate HTTP agents will accept
headers up to that length.

In the existing wire protocol, server operators typically also
key off the HTTP request method to implement authentication.
For example, GET requests translate to read-only requests and
can be allowed. But read-write commands must use POST and require
authentication. This has typically worked because the only wire
protocol commands that use POST modify the repo (e.g. the
"unbundle" command).

There is an experimental feature to enable clients to transmit
argument data via POST request bodies. This is technically a
better and more robust solution. But we can't enable it by default
because of servers assuming POST means write access.

In version 2 of the wire protocol, the permissions of a request
are encoded in the URL. And with it being a new protocol in a new
URL space, we're not constrained by backwards compatibility
requirements.

This commit adopts the technically superior mechanism of using
HTTP request bodies to send argument data by requiring POST for
all commands. Strictly speaking, it may be possible to send
request bodies on GET requests. But my experience is that not all
HTTP stacks support this. POST pretty much always works. Using POST
for read-only operations does sacrifice some RESTful design
purity. But this API cares about practicality, not about being
in Roy T. Fielding's REST ivory tower.

There's a chance we may relax this restriction in the future. But
for now, I want to see how far we can get with a POST only API.

Differential Revision: https://phab.mercurial-scm.org/D2837

from __future__ import absolute_import, print_function
import os
import stat
import subprocess
import sys

if subprocess.call(['python', '%s/hghave' % os.environ['TESTDIR'],
                    'cacheable']):
    sys.exit(80)

from mercurial import (
    extensions,
    hg,
    localrepo,
    pycompat,
    ui as uimod,
    util,
    vfs as vfsmod,
)

if pycompat.ispy3:
    xrange = range

class fakerepo(object):
    def __init__(self):
        self._filecache = {}

    class fakevfs(object):

        def join(self, p):
            return p

    vfs = fakevfs()

    def unfiltered(self):
        return self

    def sjoin(self, p):
        return p

    @localrepo.repofilecache('x', 'y')
    def cached(self):
        print('creating')
        return 'string from function'

    def invalidate(self):
        for k in self._filecache:
            try:
                delattr(self, k)
            except AttributeError:
                pass

def basic(repo):
    print("* neither file exists")
    # calls function
    repo.cached

    repo.invalidate()
    print("* neither file still exists")
    # uses cache
    repo.cached

    # create empty file
    f = open('x', 'w')
    f.close()
    repo.invalidate()
    print("* empty file x created")
    # should recreate the object
    repo.cached

    f = open('x', 'w')
    f.write('a')
    f.close()
    repo.invalidate()
    print("* file x changed size")
    # should recreate the object
    repo.cached

    repo.invalidate()
    print("* nothing changed with either file")
    # stats file again, reuses object
    repo.cached

    # atomic replace file, size doesn't change
    # hopefully st_mtime doesn't change as well so this doesn't use the cache
    # because of inode change
    f = vfsmod.vfs('.')('x', 'w', atomictemp=True)
    f.write('b')
    f.close()

    repo.invalidate()
    print("* file x changed inode")
    repo.cached

    # create empty file y
    f = open('y', 'w')
    f.close()
    repo.invalidate()
    print("* empty file y created")
    # should recreate the object
    repo.cached

    f = open('y', 'w')
    f.write('A')
    f.close()
    repo.invalidate()
    print("* file y changed size")
    # should recreate the object
    repo.cached

    f = vfsmod.vfs('.')('y', 'w', atomictemp=True)
    f.write('B')
    f.close()

    repo.invalidate()
    print("* file y changed inode")
    repo.cached

    f = vfsmod.vfs('.')('x', 'w', atomictemp=True)
    f.write('c')
    f.close()
    f = vfsmod.vfs('.')('y', 'w', atomictemp=True)
    f.write('C')
    f.close()

    repo.invalidate()
    print("* both files changed inode")
    repo.cached

def fakeuncacheable():
    def wrapcacheable(orig, *args, **kwargs):
        return False

    def wrapinit(orig, *args, **kwargs):
        pass

    originit = extensions.wrapfunction(util.cachestat, '__init__', wrapinit)
    origcacheable = extensions.wrapfunction(util.cachestat, 'cacheable',
                                            wrapcacheable)

    for fn in ['x', 'y']:
        try:
            os.remove(fn)
        except OSError:
            pass

    basic(fakerepo())

    util.cachestat.cacheable = origcacheable
    util.cachestat.__init__ = originit

def test_filecache_synced():
    # test old behavior that caused filecached properties to go out of sync
    os.system('hg init && echo a >> a && hg ci -qAm.')
    repo = hg.repository(uimod.ui.load())
    # first rollback clears the filecache, but changelog to stays in __dict__
    repo.rollback()
    repo.commit('.')
    # second rollback comes along and touches the changelog externally
    # (file is moved)
    repo.rollback()
    # but since changelog isn't under the filecache control anymore, we don't
    # see that it changed, and return the old changelog without reconstructing
    # it
    repo.commit('.')

def setbeforeget(repo):
    os.remove('x')
    os.remove('y')
    repo.cached = 'string set externally'
    repo.invalidate()
    print("* neither file exists")
    print(repo.cached)
    repo.invalidate()
    f = open('x', 'w')
    f.write('a')
    f.close()
    print("* file x created")
    print(repo.cached)

    repo.cached = 'string 2 set externally'
    repo.invalidate()
    print("* string set externally again")
    print(repo.cached)

    repo.invalidate()
    f = open('y', 'w')
    f.write('b')
    f.close()
    print("* file y created")
    print(repo.cached)

def antiambiguity():
    filename = 'ambigcheck'

    # try some times, because reproduction of ambiguity depends on
    # "filesystem time"
    for i in xrange(5):
        fp = open(filename, 'w')
        fp.write('FOO')
        fp.close()

        oldstat = os.stat(filename)
        if oldstat[stat.ST_CTIME] != oldstat[stat.ST_MTIME]:
            # subsequent changing never causes ambiguity
            continue

        repetition = 3

        # repeat changing via checkambigatclosing, to examine whether
        # st_mtime is advanced multiple times as expected
        for i in xrange(repetition):
            # explicit closing
            fp = vfsmod.checkambigatclosing(open(filename, 'a'))
            fp.write('FOO')
            fp.close()

            # implicit closing by "with" statement
            with vfsmod.checkambigatclosing(open(filename, 'a')) as fp:
                fp.write('BAR')

        newstat = os.stat(filename)
        if oldstat[stat.ST_CTIME] != newstat[stat.ST_CTIME]:
            # timestamp ambiguity was naturally avoided while repetition
            continue

        # st_mtime should be advanced "repetition * 2" times, because
        # all changes occurred at same time (in sec)
        expected = (oldstat[stat.ST_MTIME] + repetition * 2) & 0x7fffffff
        if newstat[stat.ST_MTIME] != expected:
            print("'newstat[stat.ST_MTIME] %s is not %s (as %s + %s * 2)" %
                  (newstat[stat.ST_MTIME], expected,
                   oldstat[stat.ST_MTIME], repetition))

        # no more examination is needed regardless of result
        break
    else:
        # This platform seems too slow to examine anti-ambiguity
        # of file timestamp (or test happened to be executed at
        # bad timing). Exit silently in this case, because running
        # on other faster platforms can detect problems
        pass

print('basic:')
print()
basic(fakerepo())
print()
print('fakeuncacheable:')
print()
fakeuncacheable()
test_filecache_synced()
print()
print('setbeforeget:')
print()
setbeforeget(fakerepo())
print()
print('antiambiguity:')
print()
antiambiguity()