view tests/test-fastannotate-revmap.py @ 39270:37e56607cbb9

lfs: add a progress bar when searching for blobs to upload

The search itself can take an extreme amount of time if there are a lot of
revisions involved.  I've got a local repo that took 6 minutes to push 1850
commits, and 60% of that time was spent here (there are ~70K files):

     \ 58.1%  wrapper.py:     extractpointers      line 297:  pointers = extractpointers(...
       | 57.7%  wrapper.py:     pointersfromctx    line 352:  for p in pointersfromctx(ct...
       | 57.4%  wrapper.py:     pointerfromctx     line 397:  p = pointerfromctx(ctx, f, ...
         \ 38.7%  context.py:     __contains__     line 368:  if f not in ctx:
           | 38.7%  util.py:        __get__        line 82:  return key in self._manifest
           | 38.7%  context.py:     _manifest      line 1416:  result = self.func(obj)
           | 38.7%  manifest.py:    read           line 472:  return self._manifestctx.re...
             \ 25.6%  revlog.py:      revision     line 1562:  text = rl.revision(self._node)
               \ 12.8%  revlog.py:      _chunks    line 2217:  bins = self._chunks(chain, ...
                 | 12.0%  revlog.py:      decompressline 2112:  ladd(decomp(buffer(data, ch...
               \  7.8%  revlog.py:      checkhash  line 2232:  self.checkhash(text, node, ...
                 |  7.8%  revlog.py:      hash     line 2315:  if node != self.hash(text, ...
                 |  7.8%  revlog.py:      hash     line 2242:  return hash(text, p1, p2)
             \ 12.0%  manifest.py:    __init__     line 1565:  self._data = manifestdict(t...
         \ 16.8%  context.py:     filenode         line 378:  if not _islfs(fctx.filelog(...
           | 15.7%  util.py:        __get__        line 706:  return self._filelog
           | 14.8%  context.py:     _filelog       line 1416:  result = self.func(obj)
           | 14.8%  localrepo.py:   file           line 629:  return self._repo.file(self...
           | 14.8%  filelog.py:     __init__       line 1134:  return filelog.filelog(self...
           | 14.5%  revlog.py:      __init__       line 24:  censorable=True)

from __future__ import absolute_import, print_function

import os
import tempfile

from mercurial import util
from hgext.fastannotate import error, revmap

def genhsh(i):
    return chr(i) + b'\0' * 19

def gettemppath():
    fd, path = tempfile.mkstemp()
    os.close(fd)
    os.unlink(path)
    return path

def ensure(condition):
    if not condition:
        raise RuntimeError('Unexpected')

def testbasicreadwrite():
    path = gettemppath()

    rm = revmap.revmap(path)
    ensure(rm.maxrev == 0)
    for i in xrange(5):
        ensure(rm.rev2hsh(i) is None)
    ensure(rm.hsh2rev(b'\0' * 20) is None)

    paths = ['', 'a', None, 'b', 'b', 'c', 'c', None, 'a', 'b', 'a', 'a']
    for i in xrange(1, 5):
        ensure(rm.append(genhsh(i), sidebranch=(i & 1), path=paths[i]) == i)

    ensure(rm.maxrev == 4)
    for i in xrange(1, 5):
        ensure(rm.hsh2rev(genhsh(i)) == i)
        ensure(rm.rev2hsh(i) == genhsh(i))

    # re-load and verify
    rm.flush()
    rm = revmap.revmap(path)
    ensure(rm.maxrev == 4)
    for i in xrange(1, 5):
        ensure(rm.hsh2rev(genhsh(i)) == i)
        ensure(rm.rev2hsh(i) == genhsh(i))
        ensure(bool(rm.rev2flag(i) & revmap.sidebranchflag) == bool(i & 1))

    # append without calling save() explicitly
    for i in xrange(5, 12):
        ensure(rm.append(genhsh(i), sidebranch=(i & 1), path=paths[i],
                         flush=True) == i)

    # re-load and verify
    rm = revmap.revmap(path)
    ensure(rm.maxrev == 11)
    for i in xrange(1, 12):
        ensure(rm.hsh2rev(genhsh(i)) == i)
        ensure(rm.rev2hsh(i) == genhsh(i))
        ensure(rm.rev2path(i) == paths[i] or paths[i - 1])
        ensure(bool(rm.rev2flag(i) & revmap.sidebranchflag) == bool(i & 1))

    os.unlink(path)

    # missing keys
    ensure(rm.rev2hsh(12) is None)
    ensure(rm.rev2hsh(0) is None)
    ensure(rm.rev2hsh(-1) is None)
    ensure(rm.rev2flag(12) is None)
    ensure(rm.rev2path(12) is None)
    ensure(rm.hsh2rev(b'\1' * 20) is None)

    # illformed hash (not 20 bytes)
    try:
        rm.append(b'\0')
        ensure(False)
    except Exception:
        pass

def testcorruptformat():
    path = gettemppath()

    # incorrect header
    with open(path, 'w') as f:
        f.write(b'NOT A VALID HEADER')
    try:
        revmap.revmap(path)
        ensure(False)
    except error.CorruptedFileError:
        pass

    # rewrite the file
    os.unlink(path)
    rm = revmap.revmap(path)
    rm.append(genhsh(0), flush=True)

    rm = revmap.revmap(path)
    ensure(rm.maxrev == 1)

    # corrupt the file by appending a byte
    size = os.stat(path).st_size
    with open(path, 'a') as f:
        f.write('\xff')
    try:
        revmap.revmap(path)
        ensure(False)
    except error.CorruptedFileError:
        pass

    # corrupt the file by removing the last byte
    ensure(size > 0)
    with open(path, 'w') as f:
        f.truncate(size - 1)
    try:
        revmap.revmap(path)
        ensure(False)
    except error.CorruptedFileError:
        pass

    os.unlink(path)

def testcopyfrom():
    path = gettemppath()
    rm = revmap.revmap(path)
    for i in xrange(1, 10):
        ensure(rm.append(genhsh(i), sidebranch=(i & 1), path=str(i // 3)) == i)
    rm.flush()

    # copy rm to rm2
    rm2 = revmap.revmap()
    rm2.copyfrom(rm)
    path2 = gettemppath()
    rm2.path = path2
    rm2.flush()

    # two files should be the same
    ensure(len(set(util.readfile(p) for p in [path, path2])) == 1)

    os.unlink(path)
    os.unlink(path2)

class fakefctx(object):
    def __init__(self, node, path=None):
        self._node = node
        self._path = path

    def node(self):
        return self._node

    def path(self):
        return self._path

def testcontains():
    path = gettemppath()

    rm = revmap.revmap(path)
    for i in xrange(1, 5):
        ensure(rm.append(genhsh(i), sidebranch=(i & 1)) == i)

    for i in xrange(1, 5):
        ensure(((genhsh(i), None) in rm) == ((i & 1) == 0))
        ensure((fakefctx(genhsh(i)) in rm) == ((i & 1) == 0))
    for i in xrange(5, 10):
        ensure(fakefctx(genhsh(i)) not in rm)
        ensure((genhsh(i), None) not in rm)

    # "contains" checks paths
    rm = revmap.revmap()
    for i in xrange(1, 5):
        ensure(rm.append(genhsh(i), path=str(i // 2)) == i)
    for i in xrange(1, 5):
        ensure(fakefctx(genhsh(i), path=str(i // 2)) in rm)
        ensure(fakefctx(genhsh(i), path='a') not in rm)

def testlastnode():
    path = gettemppath()
    ensure(revmap.getlastnode(path) is None)
    rm = revmap.revmap(path)
    ensure(revmap.getlastnode(path) is None)
    for i in xrange(1, 10):
        hsh = genhsh(i)
        rm.append(hsh, path=str(i // 2), flush=True)
        ensure(revmap.getlastnode(path) == hsh)
        rm2 = revmap.revmap(path)
        ensure(rm2.rev2hsh(rm2.maxrev) == hsh)

testbasicreadwrite()
testcorruptformat()
testcopyfrom()
testcontains()
testlastnode()