merge with stable

contrib/heptapod-ci.yml

@@ -0,0 +1,75 b''
+image: octobus/ci-mercurial-core
+
+# The runner made a clone as root.
+# We make a new clone owned by user used to run the step.
+before_script:
+    - hg clone . /tmp/mercurial-ci/ --noupdate
+    - hg -R /tmp/mercurial-ci/ update `hg log --rev '.' --template '{node}'`
+    - cd /tmp/mercurial-ci/
+    - (cd tests; ls -1 test-check-*.*) > /tmp/check-tests.txt
+
+variables:
+    PYTHON: python
+
+.runtests_template: &runtests
+    script:
+        - cd tests/
+        - echo "python used, $PYTHON"
+        - echo "$RUNTEST_ARGS"
+        - $PYTHON run-tests.py --color=always $RUNTEST_ARGS
+
+checks-py2:
+    <<: *runtests
+    variables:
+        RUNTEST_ARGS: "--time --test-list /tmp/check-tests.txt"
+
+checks-py3:
+    <<: *runtests
+    variables:
+        RUNTEST_ARGS: "--time --test-list /tmp/check-tests.txt"
+        PYTHON: python3
+
+rust-cargo-test-py2: &rust_cargo_test
+    script:
+        - echo "python used, $PYTHON"
+        - make rust-tests
+
+rust-cargo-test-py3:
+    <<: *rust_cargo_test
+    variables:
+        PYTHON: python3
+
+test-py2:
+    <<: *runtests
+    variables:
+        RUNTEST_ARGS: "--blacklist /tmp/check-tests.txt"
+
+test-py3:
+    <<: *runtests
+    variables:
+        RUNTEST_ARGS: "--blacklist /tmp/check-tests.txt"
+        PYTHON: python3
+
+test-py2-pure:
+    <<: *runtests
+    variables:
+        RUNTEST_ARGS: "--pure --blacklist /tmp/check-tests.txt"
+
+test-py3-pure:
+    <<: *runtests
+    variables:
+        RUNTEST_ARGS: "--pure --blacklist /tmp/check-tests.txt"
+        PYTHON: python3
+
+test-py2-rust:
+    <<: *runtests
+    variables:
+        HGWITHRUSTEXT: cpython
+        RUNTEST_ARGS: "--blacklist /tmp/check-tests.txt"
+
+test-py3-rust:
+    <<: *runtests
+    variables:
+        HGWITHRUSTEXT: cpython
+        RUNTEST_ARGS: "--blacklist /tmp/check-tests.txt"
+        PYTHON: python3

contrib/packaging/hgpackaging/wix.py

@@ -1,497 +1,499 b''
 # wix.py - WiX installer functionality
 #
 # Copyright 2019 Gregory Szorc <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 # no-check-code because Python 3 native.
 
 import collections
 import os
 import pathlib
 import re
 import shutil
 import subprocess
 import typing
 import uuid
 import xml.dom.minidom
 
 from .downloads import download_entry
 from .py2exe import (
     build_py2exe,
     stage_install,
 )
 from .util import (
     extract_zip_to_directory,
     normalize_windows_version,
     process_install_rules,
     sign_with_signtool,
 )
 
 
 EXTRA_PACKAGES = {
     'dulwich',
     'distutils',
     'keyring',
     'pygments',
     'win32ctypes',
 }
 
 
 EXTRA_INSTALL_RULES = [
     ('contrib/packaging/wix/COPYING.rtf', 'COPYING.rtf'),
     ('contrib/win32/mercurial.ini', 'defaultrc/mercurial.rc'),
 ]
 
 STAGING_REMOVE_FILES = [
     # We use the RTF variant.
     'copying.txt',
 ]
 
 SHORTCUTS = {
     # hg.1.html'
     'hg.file.5d3e441c_28d9_5542_afd0_cdd4234f12d5': {
         'Name': 'Mercurial Command Reference',
     },
     # hgignore.5.html
     'hg.file.5757d8e0_f207_5e10_a2ec_3ba0a062f431': {
         'Name': 'Mercurial Ignore Files',
     },
     # hgrc.5.html
     'hg.file.92e605fd_1d1a_5dc6_9fc0_5d2998eb8f5e': {
         'Name': 'Mercurial Configuration Files',
     },
 }
 
 
 def find_version(source_dir: pathlib.Path):
     version_py = source_dir / 'mercurial' / '__version__.py'
 
     with version_py.open('r', encoding='utf-8') as fh:
         source = fh.read().strip()
 
     m = re.search('version = b"(.*)"', source)
     return m.group(1)
 
 
 def ensure_vc90_merge_modules(build_dir):
     x86 = (
         download_entry(
             'vc9-crt-x86-msm',
             build_dir,
             local_name='microsoft.vcxx.crt.x86_msm.msm',
         )[0],
         download_entry(
             'vc9-crt-x86-msm-policy',
             build_dir,
             local_name='policy.x.xx.microsoft.vcxx.crt.x86_msm.msm',
         )[0],
     )
 
     x64 = (
         download_entry(
             'vc9-crt-x64-msm',
             build_dir,
             local_name='microsoft.vcxx.crt.x64_msm.msm',
         )[0],
         download_entry(
             'vc9-crt-x64-msm-policy',
             build_dir,
             local_name='policy.x.xx.microsoft.vcxx.crt.x64_msm.msm',
         )[0],
     )
     return {
         'x86': x86,
         'x64': x64,
     }
 
 
 def run_candle(wix, cwd, wxs, source_dir, defines=None):
     args = [
         str(wix / 'candle.exe'),
         '-nologo',
         str(wxs),
         '-dSourceDir=%s' % source_dir,
     ]
 
     if defines:
         args.extend('-d%s=%s' % define for define in sorted(defines.items()))
 
     subprocess.run(args, cwd=str(cwd), check=True)
 
 
 def make_post_build_signing_fn(
     name,
     subject_name=None,
     cert_path=None,
     cert_password=None,
     timestamp_url=None,
 ):
     """Create a callable that will use signtool to sign hg.exe."""
 
     def post_build_sign(source_dir, build_dir, dist_dir, version):
         description = '%s %s' % (name, version)
 
         sign_with_signtool(
             dist_dir / 'hg.exe',
             description,
             subject_name=subject_name,
             cert_path=cert_path,
             cert_password=cert_password,
             timestamp_url=timestamp_url,
         )
 
     return post_build_sign
 
 
 def make_files_xml(staging_dir: pathlib.Path, is_x64) -> str:
     """Create XML string listing every file to be installed."""
 
     # We derive GUIDs from a deterministic file path identifier.
     # We shoehorn the name into something that looks like a URL because
     # the UUID namespaces are supposed to work that way (even though
     # the input data probably is never validated).
 
     doc = xml.dom.minidom.parseString(
         '<?xml version="1.0" encoding="utf-8"?>'
         '<Wix xmlns="http://schemas.microsoft.com/wix/2006/wi">'
         '</Wix>'
     )
 
     # Assemble the install layout by directory. This makes it easier to
     # emit XML, since each directory has separate entities.
     manifest = collections.defaultdict(dict)
 
     for root, dirs, files in os.walk(staging_dir):
         dirs.sort()
 
         root = pathlib.Path(root)
         rel_dir = root.relative_to(staging_dir)
 
         for i in range(len(rel_dir.parts)):
             parent = '/'.join(rel_dir.parts[0 : i + 1])
             manifest.setdefault(parent, {})
 
         for f in sorted(files):
             full = root / f
             manifest[str(rel_dir).replace('\\', '/')][full.name] = full
 
     component_groups = collections.defaultdict(list)
 
     # Now emit a <Fragment> for each directory.
     # Each directory is composed of a <DirectoryRef> pointing to its parent
     # and defines child <Directory>'s and a <Component> with all the files.
     for dir_name, entries in sorted(manifest.items()):
         # The directory id is derived from the path. But the root directory
         # is special.
         if dir_name == '.':
             parent_directory_id = 'INSTALLDIR'
         else:
             parent_directory_id = 'hg.dir.%s' % dir_name.replace('/', '.')
 
         fragment = doc.createElement('Fragment')
         directory_ref = doc.createElement('DirectoryRef')
         directory_ref.setAttribute('Id', parent_directory_id)
 
         # Add <Directory> entries for immediate children directories.
         for possible_child in sorted(manifest.keys()):
             if (
                 dir_name == '.'
                 and '/' not in possible_child
                 and possible_child != '.'
             ):
                 child_directory_id = 'hg.dir.%s' % possible_child
                 name = possible_child
             else:
                 if not possible_child.startswith('%s/' % dir_name):
                     continue
                 name = possible_child[len(dir_name) + 1 :]
                 if '/' in name:
                     continue
 
                 child_directory_id = 'hg.dir.%s' % possible_child.replace(
                     '/', '.'
                 )
 
             directory = doc.createElement('Directory')
             directory.setAttribute('Id', child_directory_id)
             directory.setAttribute('Name', name)
             directory_ref.appendChild(directory)
 
         # Add <Component>s for files in this directory.
         for rel, source_path in sorted(entries.items()):
             if dir_name == '.':
                 full_rel = rel
             else:
                 full_rel = '%s/%s' % (dir_name, rel)
 
             component_unique_id = (
                 'https://www.mercurial-scm.org/wix-installer/0/component/%s'
                 % full_rel
             )
             component_guid = uuid.uuid5(uuid.NAMESPACE_URL, component_unique_id)
             component_id = 'hg.component.%s' % str(component_guid).replace(
                 '-', '_'
             )
 
             component = doc.createElement('Component')
 
             component.setAttribute('Id', component_id)
             component.setAttribute('Guid', str(component_guid).upper())
             component.setAttribute('Win64', 'yes' if is_x64 else 'no')
 
             # Assign this component to a top-level group.
             if dir_name == '.':
                 component_groups['ROOT'].append(component_id)
             elif '/' in dir_name:
                 component_groups[dir_name[0 : dir_name.index('/')]].append(
                     component_id
                 )
             else:
                 component_groups[dir_name].append(component_id)
 
             unique_id = (
                 'https://www.mercurial-scm.org/wix-installer/0/%s' % full_rel
             )
             file_guid = uuid.uuid5(uuid.NAMESPACE_URL, unique_id)
 
             # IDs have length limits. So use GUID to derive them.
             file_guid_normalized = str(file_guid).replace('-', '_')
             file_id = 'hg.file.%s' % file_guid_normalized
 
             file_element = doc.createElement('File')
             file_element.setAttribute('Id', file_id)
             file_element.setAttribute('Source', str(source_path))
             file_element.setAttribute('KeyPath', 'yes')
             file_element.setAttribute('ReadOnly', 'yes')
 
             component.appendChild(file_element)
             directory_ref.appendChild(component)
 
         fragment.appendChild(directory_ref)
         doc.documentElement.appendChild(fragment)
 
     for group, component_ids in sorted(component_groups.items()):
         fragment = doc.createElement('Fragment')
         component_group = doc.createElement('ComponentGroup')
         component_group.setAttribute('Id', 'hg.group.%s' % group)
 
         for component_id in component_ids:
             component_ref = doc.createElement('ComponentRef')
             component_ref.setAttribute('Id', component_id)
             component_group.appendChild(component_ref)
 
         fragment.appendChild(component_group)
         doc.documentElement.appendChild(fragment)
 
     # Add <Shortcut> to files that have it defined.
     for file_id, metadata in sorted(SHORTCUTS.items()):
         els = doc.getElementsByTagName('File')
         els = [el for el in els if el.getAttribute('Id') == file_id]
 
         if not els:
             raise Exception('could not find File[Id=%s]' % file_id)
 
         for el in els:
             shortcut = doc.createElement('Shortcut')
             shortcut.setAttribute('Id', 'hg.shortcut.%s' % file_id)
             shortcut.setAttribute('Directory', 'ProgramMenuDir')
             shortcut.setAttribute('Icon', 'hgIcon.ico')
             shortcut.setAttribute('IconIndex', '0')
             shortcut.setAttribute('Advertise', 'yes')
             for k, v in sorted(metadata.items()):
                 shortcut.setAttribute(k, v)
 
             el.appendChild(shortcut)
 
     return doc.toprettyxml()
 
 
 def build_installer(
     source_dir: pathlib.Path,
     python_exe: pathlib.Path,
     msi_name='mercurial',
     version=None,
     post_build_fn=None,
     extra_packages_script=None,
     extra_wxs: typing.Optional[typing.Dict[str, str]] = None,
     extra_features: typing.Optional[typing.List[str]] = None,
 ):
     """Build a WiX MSI installer.
 
     ``source_dir`` is the path to the Mercurial source tree to use.
     ``arch`` is the target architecture. either ``x86`` or ``x64``.
     ``python_exe`` is the path to the Python executable to use/bundle.
     ``version`` is the Mercurial version string. If not defined,
     ``mercurial/__version__.py`` will be consulted.
     ``post_build_fn`` is a callable that will be called after building
     Mercurial but before invoking WiX. It can be used to e.g. facilitate
     signing. It is passed the paths to the Mercurial source, build, and
     dist directories and the resolved Mercurial version.
     ``extra_packages_script`` is a command to be run to inject extra packages
     into the py2exe binary. It should stage packages into the virtualenv and
     print a null byte followed by a newline-separated list of packages that
     should be included in the exe.
     ``extra_wxs`` is a dict of {wxs_name: working_dir_for_wxs_build}.
     ``extra_features`` is a list of additional named Features to include in
     the build. These must match Feature names in one of the wxs scripts.
     """
     arch = 'x64' if r'\x64' in os.environ.get('LIB', '') else 'x86'
 
     hg_build_dir = source_dir / 'build'
     dist_dir = source_dir / 'dist'
     wix_dir = source_dir / 'contrib' / 'packaging' / 'wix'
 
-    requirements_txt = 'requirements_win32.txt'
+    requirements_txt = (
+        source_dir / 'contrib' / 'packaging' / 'requirements_win32.txt'
+    )
 
     build_py2exe(
         source_dir,
         hg_build_dir,
         python_exe,
         'wix',
         requirements_txt,
         extra_packages=EXTRA_PACKAGES,
         extra_packages_script=extra_packages_script,
     )
 
     orig_version = version or find_version(source_dir)
     version = normalize_windows_version(orig_version)
     print('using version string: %s' % version)
     if version != orig_version:
         print('(normalized from: %s)' % orig_version)
 
     if post_build_fn:
         post_build_fn(source_dir, hg_build_dir, dist_dir, version)
 
     build_dir = hg_build_dir / ('wix-%s' % arch)
     staging_dir = build_dir / 'stage'
 
     build_dir.mkdir(exist_ok=True)
 
     # Purge the staging directory for every build so packaging is pristine.
     if staging_dir.exists():
         print('purging %s' % staging_dir)
         shutil.rmtree(staging_dir)
 
     stage_install(source_dir, staging_dir, lower_case=True)
 
     # We also install some extra files.
     process_install_rules(EXTRA_INSTALL_RULES, source_dir, staging_dir)
 
     # And remove some files we don't want.
     for f in STAGING_REMOVE_FILES:
         p = staging_dir / f
         if p.exists():
             print('removing %s' % p)
             p.unlink()
 
     wix_pkg, wix_entry = download_entry('wix', hg_build_dir)
     wix_path = hg_build_dir / ('wix-%s' % wix_entry['version'])
 
     if not wix_path.exists():
         extract_zip_to_directory(wix_pkg, wix_path)
 
     ensure_vc90_merge_modules(hg_build_dir)
 
     source_build_rel = pathlib.Path(os.path.relpath(source_dir, build_dir))
 
     defines = {'Platform': arch}
 
     # Derive a .wxs file with the staged files.
     manifest_wxs = build_dir / 'stage.wxs'
     with manifest_wxs.open('w', encoding='utf-8') as fh:
         fh.write(make_files_xml(staging_dir, is_x64=arch == 'x64'))
 
     run_candle(wix_path, build_dir, manifest_wxs, staging_dir, defines=defines)
 
     for source, rel_path in sorted((extra_wxs or {}).items()):
         run_candle(wix_path, build_dir, source, rel_path, defines=defines)
 
     source = wix_dir / 'mercurial.wxs'
     defines['Version'] = version
     defines['Comments'] = 'Installs Mercurial version %s' % version
     defines['VCRedistSrcDir'] = str(hg_build_dir)
     if extra_features:
         assert all(';' not in f for f in extra_features)
         defines['MercurialExtraFeatures'] = ';'.join(extra_features)
 
     run_candle(wix_path, build_dir, source, source_build_rel, defines=defines)
 
     msi_path = (
         source_dir / 'dist' / ('%s-%s-%s.msi' % (msi_name, orig_version, arch))
     )
 
     args = [
         str(wix_path / 'light.exe'),
         '-nologo',
         '-ext',
         'WixUIExtension',
         '-sw1076',
         '-spdb',
         '-o',
         str(msi_path),
     ]
 
     for source, rel_path in sorted((extra_wxs or {}).items()):
         assert source.endswith('.wxs')
         source = os.path.basename(source)
         args.append(str(build_dir / ('%s.wixobj' % source[:-4])))
 
     args.extend(
         [str(build_dir / 'stage.wixobj'), str(build_dir / 'mercurial.wixobj'),]
     )
 
     subprocess.run(args, cwd=str(source_dir), check=True)
 
     print('%s created' % msi_path)
 
     return {
         'msi_path': msi_path,
     }
 
 
 def build_signed_installer(
     source_dir: pathlib.Path,
     python_exe: pathlib.Path,
     name: str,
     version=None,
     subject_name=None,
     cert_path=None,
     cert_password=None,
     timestamp_url=None,
     extra_packages_script=None,
     extra_wxs=None,
     extra_features=None,
 ):
     """Build an installer with signed executables."""
 
     post_build_fn = make_post_build_signing_fn(
         name,
         subject_name=subject_name,
         cert_path=cert_path,
         cert_password=cert_password,
         timestamp_url=timestamp_url,
     )
 
     info = build_installer(
         source_dir,
         python_exe=python_exe,
         msi_name=name.lower(),
         version=version,
         post_build_fn=post_build_fn,
         extra_packages_script=extra_packages_script,
         extra_wxs=extra_wxs,
         extra_features=extra_features,
     )
 
     description = '%s %s' % (name, version)
 
     sign_with_signtool(
         info['msi_path'],
         description,
         subject_name=subject_name,
         cert_path=cert_path,
         cert_password=cert_password,
         timestamp_url=timestamp_url,
     )

hgext/zeroconf/__init__.py

@@ -1,241 +1,243 b''
 # zeroconf.py - zeroconf support for Mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 '''discover and advertise repositories on the local network
 
 The zeroconf extension will advertise :hg:`serve` instances over
 DNS-SD so that they can be discovered using the :hg:`paths` command
 without knowing the server's IP address.
 
 To allow other people to discover your repository using run
 :hg:`serve` in your repository::
 
   $ cd test
   $ hg serve
 
 You can discover Zeroconf-enabled repositories by running
 :hg:`paths`::
 
   $ hg paths
   zc-test = http://example.com:8000/test
 '''
 from __future__ import absolute_import
 
 import os
 import socket
 import time
 
 from . import Zeroconf
 from mercurial import (
     dispatch,
     encoding,
     extensions,
     hg,
     pycompat,
+    rcutil,
     ui as uimod,
 )
 from mercurial.hgweb import server as servermod
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = b'ships-with-hg-core'
 
 # publish
 
 server = None
 localip = None
 
 
 def getip():
     # finds external-facing interface without sending any packets (Linux)
     try:
         s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
         s.connect(('1.0.0.1', 0))
         ip = s.getsockname()[0]
         return ip
     except socket.error:
         pass
 
     # Generic method, sometimes gives useless results
     try:
         dumbip = socket.gethostbyaddr(socket.gethostname())[2][0]
         if ':' in dumbip:
             dumbip = '127.0.0.1'
         if not dumbip.startswith('127.'):
             return dumbip
     except (socket.gaierror, socket.herror):
         dumbip = '127.0.0.1'
 
     # works elsewhere, but actually sends a packet
     try:
         s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
         s.connect(('1.0.0.1', 1))
         ip = s.getsockname()[0]
         return ip
     except socket.error:
         pass
 
     return dumbip
 
 
 def publish(name, desc, path, port):
     global server, localip
     if not server:
         ip = getip()
         if ip.startswith('127.'):
             # if we have no internet connection, this can happen.
             return
         localip = socket.inet_aton(ip)
         server = Zeroconf.Zeroconf(ip)
 
     hostname = socket.gethostname().split('.')[0]
     host = hostname + ".local"
     name = "%s-%s" % (hostname, name)
 
     # advertise to browsers
     svc = Zeroconf.ServiceInfo(
         b'_http._tcp.local.',
         pycompat.bytestr(name + '._http._tcp.local.'),
         server=host,
         port=port,
         properties={b'description': desc, b'path': b"/" + path},
         address=localip,
         weight=0,
         priority=0,
     )
     server.registerService(svc)
 
     # advertise to Mercurial clients
     svc = Zeroconf.ServiceInfo(
         b'_hg._tcp.local.',
         pycompat.bytestr(name + '._hg._tcp.local.'),
         server=host,
         port=port,
         properties={b'description': desc, b'path': b"/" + path},
         address=localip,
         weight=0,
         priority=0,
     )
     server.registerService(svc)
 
 
 def zc_create_server(create_server, ui, app):
     httpd = create_server(ui, app)
     port = httpd.port
 
     try:
         repos = app.repos
     except AttributeError:
         # single repo
         with app._obtainrepo() as repo:
             name = app.reponame or os.path.basename(repo.root)
             path = repo.ui.config(b"web", b"prefix", b"").strip(b'/')
             desc = repo.ui.config(b"web", b"description")
             if not desc:
                 desc = name
         publish(name, desc, path, port)
     else:
         # webdir
         prefix = app.ui.config(b"web", b"prefix", b"").strip(b'/') + b'/'
         for repo, path in repos:
             u = app.ui.copy()
+            if rcutil.use_repo_hgrc():
             u.readconfig(os.path.join(path, b'.hg', b'hgrc'))
             name = os.path.basename(repo)
             path = (prefix + repo).strip(b'/')
             desc = u.config(b'web', b'description')
             if not desc:
                 desc = name
             publish(name, desc, path, port)
     return httpd
 
 
 # listen
 
 
 class listener(object):
     def __init__(self):
         self.found = {}
 
     def removeService(self, server, type, name):
         if repr(name) in self.found:
             del self.found[repr(name)]
 
     def addService(self, server, type, name):
         self.found[repr(name)] = server.getServiceInfo(type, name)
 
 
 def getzcpaths():
     ip = getip()
     if ip.startswith('127.'):
         return
     server = Zeroconf.Zeroconf(ip)
     l = listener()
     Zeroconf.ServiceBrowser(server, b"_hg._tcp.local.", l)
     time.sleep(1)
     server.close()
     for value in l.found.values():
         name = value.name[: value.name.index(b'.')]
         url = "http://%s:%s%s" % (
             socket.inet_ntoa(value.address),
             value.port,
             value.properties.get("path", "/"),
         )
         yield b"zc-" + name, pycompat.bytestr(url)
 
 
 def config(orig, self, section, key, *args, **kwargs):
     if section == b"paths" and key.startswith(b"zc-"):
         for name, path in getzcpaths():
             if name == key:
                 return path
     return orig(self, section, key, *args, **kwargs)
 
 
 def configitems(orig, self, section, *args, **kwargs):
     repos = orig(self, section, *args, **kwargs)
     if section == b"paths":
         repos += getzcpaths()
     return repos
 
 
 def configsuboptions(orig, self, section, name, *args, **kwargs):
     opt, sub = orig(self, section, name, *args, **kwargs)
     if section == b"paths" and name.startswith(b"zc-"):
         # We have to find the URL in the zeroconf paths.  We can't cons up any
         # suboptions, so we use any that we found in the original config.
         for zcname, zcurl in getzcpaths():
             if zcname == name:
                 return zcurl, sub
     return opt, sub
 
 
 def defaultdest(orig, source):
     for name, path in getzcpaths():
         if path == source:
             return name.encode(encoding.encoding)
     return orig(source)
 
 
 def cleanupafterdispatch(orig, ui, options, cmd, cmdfunc):
     try:
         return orig(ui, options, cmd, cmdfunc)
     finally:
         # we need to call close() on the server to notify() the various
         # threading Conditions and allow the background threads to exit
         global server
         if server:
             server.close()
 
 
 extensions.wrapfunction(dispatch, b'_runcommand', cleanupafterdispatch)
 
 extensions.wrapfunction(uimod.ui, b'config', config)
 extensions.wrapfunction(uimod.ui, b'configitems', configitems)
 extensions.wrapfunction(uimod.ui, b'configsuboptions', configsuboptions)
 extensions.wrapfunction(hg, b'defaultdest', defaultdest)
 extensions.wrapfunction(servermod, b'create_server', zc_create_server)

mercurial/bundle2.py

@@ -1,2578 +1,2578 b''
 # bundle2.py - generic container format to transmit arbitrary data.
 #
 # Copyright 2013 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 """Handling of the new bundle2 format
 
 The goal of bundle2 is to act as an atomically packet to transmit a set of
 payloads in an application agnostic way. It consist in a sequence of "parts"
 that will be handed to and processed by the application layer.
 
 
 General format architecture
 ===========================
 
 The format is architectured as follow
 
  - magic string
  - stream level parameters
  - payload parts (any number)
  - end of stream marker.
 
 the Binary format
 ============================
 
 All numbers are unsigned and big-endian.
 
 stream level parameters
 ------------------------
 
 Binary format is as follow
 
 :params size: int32
 
   The total number of Bytes used by the parameters
 
 :params value: arbitrary number of Bytes
 
   A blob of `params size` containing the serialized version of all stream level
   parameters.
 
   The blob contains a space separated list of parameters. Parameters with value
   are stored in the form `<name>=<value>`. Both name and value are urlquoted.
 
   Empty name are obviously forbidden.
 
   Name MUST start with a letter. If this first letter is lower case, the
   parameter is advisory and can be safely ignored. However when the first
   letter is capital, the parameter is mandatory and the bundling process MUST
   stop if he is not able to proceed it.
 
   Stream parameters use a simple textual format for two main reasons:
 
   - Stream level parameters should remain simple and we want to discourage any
     crazy usage.
   - Textual data allow easy human inspection of a bundle2 header in case of
     troubles.
 
   Any Applicative level options MUST go into a bundle2 part instead.
 
 Payload part
 ------------------------
 
 Binary format is as follow
 
 :header size: int32
 
   The total number of Bytes used by the part header. When the header is empty
   (size = 0) this is interpreted as the end of stream marker.
 
 :header:
 
     The header defines how to interpret the part. It contains two piece of
     data: the part type, and the part parameters.
 
     The part type is used to route an application level handler, that can
     interpret payload.
 
     Part parameters are passed to the application level handler.  They are
     meant to convey information that will help the application level object to
     interpret the part payload.
 
     The binary format of the header is has follow
 
     :typesize: (one byte)
 
     :parttype: alphanumerical part name (restricted to [a-zA-Z0-9_:-]*)
 
     :partid: A 32bits integer (unique in the bundle) that can be used to refer
              to this part.
 
     :parameters:
 
         Part's parameter may have arbitrary content, the binary structure is::
 
             <mandatory-count><advisory-count><param-sizes><param-data>
 
         :mandatory-count: 1 byte, number of mandatory parameters
 
         :advisory-count:  1 byte, number of advisory parameters
 
         :param-sizes:
 
             N couple of bytes, where N is the total number of parameters. Each
             couple contains (<size-of-key>, <size-of-value) for one parameter.
 
         :param-data:
 
             A blob of bytes from which each parameter key and value can be
             retrieved using the list of size couples stored in the previous
             field.
 
             Mandatory parameters comes first, then the advisory ones.
 
             Each parameter's key MUST be unique within the part.
 
 :payload:
 
     payload is a series of `<chunksize><chunkdata>`.
 
     `chunksize` is an int32, `chunkdata` are plain bytes (as much as
     `chunksize` says)` The payload part is concluded by a zero size chunk.
 
     The current implementation always produces either zero or one chunk.
     This is an implementation limitation that will ultimately be lifted.
 
     `chunksize` can be negative to trigger special case processing. No such
     processing is in place yet.
 
 Bundle processing
 ============================
 
 Each part is processed in order using a "part handler". Handler are registered
 for a certain part type.
 
 The matching of a part to its handler is case insensitive. The case of the
 part type is used to know if a part is mandatory or advisory. If the Part type
 contains any uppercase char it is considered mandatory. When no handler is
 known for a Mandatory part, the process is aborted and an exception is raised.
 If the part is advisory and no handler is known, the part is ignored. When the
 process is aborted, the full bundle is still read from the stream to keep the
 channel usable. But none of the part read from an abort are processed. In the
 future, dropping the stream may become an option for channel we do not care to
 preserve.
 """
 
 from __future__ import absolute_import, division
 
 import collections
 import errno
 import os
 import re
 import string
 import struct
 import sys
 
 from .i18n import _
 from . import (
     bookmarks,
     changegroup,
     encoding,
     error,
     node as nodemod,
     obsolete,
     phases,
     pushkey,
     pycompat,
     streamclone,
     tags,
     url,
     util,
 )
 from .utils import stringutil
 
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 _pack = struct.pack
 _unpack = struct.unpack
 
 _fstreamparamsize = b'>i'
 _fpartheadersize = b'>i'
 _fparttypesize = b'>B'
 _fpartid = b'>I'
 _fpayloadsize = b'>i'
 _fpartparamcount = b'>BB'
 
 preferedchunksize = 32768
 
 _parttypeforbidden = re.compile(b'[^a-zA-Z0-9_:-]')
 
 
 def outdebug(ui, message):
     """debug regarding output stream (bundling)"""
     if ui.configbool(b'devel', b'bundle2.debug'):
         ui.debug(b'bundle2-output: %s\n' % message)
 
 
 def indebug(ui, message):
     """debug on input stream (unbundling)"""
     if ui.configbool(b'devel', b'bundle2.debug'):
         ui.debug(b'bundle2-input: %s\n' % message)
 
 
 def validateparttype(parttype):
     """raise ValueError if a parttype contains invalid character"""
     if _parttypeforbidden.search(parttype):
         raise ValueError(parttype)
 
 
 def _makefpartparamsizes(nbparams):
     """return a struct format to read part parameter sizes
 
     The number parameters is variable so we need to build that format
     dynamically.
     """
     return b'>' + (b'BB' * nbparams)
 
 
 parthandlermapping = {}
 
 
 def parthandler(parttype, params=()):
     """decorator that register a function as a bundle2 part handler
 
     eg::
 
         @parthandler('myparttype', ('mandatory', 'param', 'handled'))
         def myparttypehandler(...):
             '''process a part of type "my part".'''
             ...
     """
     validateparttype(parttype)
 
     def _decorator(func):
         lparttype = parttype.lower()  # enforce lower case matching.
         assert lparttype not in parthandlermapping
         parthandlermapping[lparttype] = func
         func.params = frozenset(params)
         return func
 
     return _decorator
 
 
 class unbundlerecords(object):
     """keep record of what happens during and unbundle
 
     New records are added using `records.add('cat', obj)`. Where 'cat' is a
     category of record and obj is an arbitrary object.
 
     `records['cat']` will return all entries of this category 'cat'.
 
     Iterating on the object itself will yield `('category', obj)` tuples
     for all entries.
 
     All iterations happens in chronological order.
     """
 
     def __init__(self):
         self._categories = {}
         self._sequences = []
         self._replies = {}
 
     def add(self, category, entry, inreplyto=None):
         """add a new record of a given category.
 
         The entry can then be retrieved in the list returned by
         self['category']."""
         self._categories.setdefault(category, []).append(entry)
         self._sequences.append((category, entry))
         if inreplyto is not None:
             self.getreplies(inreplyto).add(category, entry)
 
     def getreplies(self, partid):
         """get the records that are replies to a specific part"""
         return self._replies.setdefault(partid, unbundlerecords())
 
     def __getitem__(self, cat):
         return tuple(self._categories.get(cat, ()))
 
     def __iter__(self):
         return iter(self._sequences)
 
     def __len__(self):
         return len(self._sequences)
 
     def __nonzero__(self):
         return bool(self._sequences)
 
     __bool__ = __nonzero__
 
 
 class bundleoperation(object):
     """an object that represents a single bundling process
 
     Its purpose is to carry unbundle-related objects and states.
 
     A new object should be created at the beginning of each bundle processing.
     The object is to be returned by the processing function.
 
     The object has very little content now it will ultimately contain:
     * an access to the repo the bundle is applied to,
     * a ui object,
     * a way to retrieve a transaction to add changes to the repo,
     * a way to record the result of processing each part,
     * a way to construct a bundle response when applicable.
     """
 
     def __init__(self, repo, transactiongetter, captureoutput=True, source=b''):
         self.repo = repo
         self.ui = repo.ui
         self.records = unbundlerecords()
         self.reply = None
         self.captureoutput = captureoutput
         self.hookargs = {}
         self._gettransaction = transactiongetter
         # carries value that can modify part behavior
         self.modes = {}
         self.source = source
 
     def gettransaction(self):
         transaction = self._gettransaction()
 
         if self.hookargs:
             # the ones added to the transaction supercede those added
             # to the operation.
             self.hookargs.update(transaction.hookargs)
             transaction.hookargs = self.hookargs
 
         # mark the hookargs as flushed.  further attempts to add to
         # hookargs will result in an abort.
         self.hookargs = None
 
         return transaction
 
     def addhookargs(self, hookargs):
         if self.hookargs is None:
             raise error.ProgrammingError(
                 b'attempted to add hookargs to '
                 b'operation after transaction started'
             )
         self.hookargs.update(hookargs)
 
 
 class TransactionUnavailable(RuntimeError):
     pass
 
 
 def _notransaction():
     """default method to get a transaction while processing a bundle
 
     Raise an exception to highlight the fact that no transaction was expected
     to be created"""
     raise TransactionUnavailable()
 
 
 def applybundle(repo, unbundler, tr, source, url=None, **kwargs):
     # transform me into unbundler.apply() as soon as the freeze is lifted
     if isinstance(unbundler, unbundle20):
         tr.hookargs[b'bundle2'] = b'1'
         if source is not None and b'source' not in tr.hookargs:
             tr.hookargs[b'source'] = source
         if url is not None and b'url' not in tr.hookargs:
             tr.hookargs[b'url'] = url
         return processbundle(repo, unbundler, lambda: tr, source=source)
     else:
         # the transactiongetter won't be used, but we might as well set it
         op = bundleoperation(repo, lambda: tr, source=source)
         _processchangegroup(op, unbundler, tr, source, url, **kwargs)
         return op
 
 
 class partiterator(object):
     def __init__(self, repo, op, unbundler):
         self.repo = repo
         self.op = op
         self.unbundler = unbundler
         self.iterator = None
         self.count = 0
         self.current = None
 
     def __enter__(self):
         def func():
             itr = enumerate(self.unbundler.iterparts(), 1)
             for count, p in itr:
                 self.count = count
                 self.current = p
                 yield p
                 p.consume()
                 self.current = None
 
         self.iterator = func()
         return self.iterator
 
     def __exit__(self, type, exc, tb):
         if not self.iterator:
             return
 
         # Only gracefully abort in a normal exception situation. User aborts
         # like Ctrl+C throw a KeyboardInterrupt which is not a base Exception,
         # and should not gracefully cleanup.
         if isinstance(exc, Exception):
             # Any exceptions seeking to the end of the bundle at this point are
             # almost certainly related to the underlying stream being bad.
             # And, chances are that the exception we're handling is related to
             # getting in that bad state. So, we swallow the seeking error and
             # re-raise the original error.
             seekerror = False
             try:
                 if self.current:
                     # consume the part content to not corrupt the stream.
                     self.current.consume()
 
                 for part in self.iterator:
                     # consume the bundle content
                     part.consume()
             except Exception:
                 seekerror = True
 
             # Small hack to let caller code distinguish exceptions from bundle2
             # processing from processing the old format. This is mostly needed
             # to handle different return codes to unbundle according to the type
             # of bundle. We should probably clean up or drop this return code
             # craziness in a future version.
             exc.duringunbundle2 = True
             salvaged = []
             replycaps = None
             if self.op.reply is not None:
                 salvaged = self.op.reply.salvageoutput()
                 replycaps = self.op.reply.capabilities
             exc._replycaps = replycaps
             exc._bundle2salvagedoutput = salvaged
 
             # Re-raising from a variable loses the original stack. So only use
             # that form if we need to.
             if seekerror:
                 raise exc
 
         self.repo.ui.debug(
             b'bundle2-input-bundle: %i parts total\n' % self.count
         )
 
 
 def processbundle(repo, unbundler, transactiongetter=None, op=None, source=b''):
     """This function process a bundle, apply effect to/from a repo
 
     It iterates over each part then searches for and uses the proper handling
     code to process the part. Parts are processed in order.
 
     Unknown Mandatory part will abort the process.
 
     It is temporarily possible to provide a prebuilt bundleoperation to the
     function. This is used to ensure output is properly propagated in case of
     an error during the unbundling. This output capturing part will likely be
     reworked and this ability will probably go away in the process.
     """
     if op is None:
         if transactiongetter is None:
             transactiongetter = _notransaction
         op = bundleoperation(repo, transactiongetter, source=source)
     # todo:
     # - replace this is a init function soon.
     # - exception catching
     unbundler.params
     if repo.ui.debugflag:
         msg = [b'bundle2-input-bundle:']
         if unbundler.params:
             msg.append(b' %i params' % len(unbundler.params))
         if op._gettransaction is None or op._gettransaction is _notransaction:
             msg.append(b' no-transaction')
         else:
             msg.append(b' with-transaction')
         msg.append(b'\n')
         repo.ui.debug(b''.join(msg))
 
     processparts(repo, op, unbundler)
 
     return op
 
 
 def processparts(repo, op, unbundler):
     with partiterator(repo, op, unbundler) as parts:
         for part in parts:
             _processpart(op, part)
 
 
 def _processchangegroup(op, cg, tr, source, url, **kwargs):
     ret = cg.apply(op.repo, tr, source, url, **kwargs)
     op.records.add(b'changegroup', {b'return': ret,})
     return ret
 
 
 def _gethandler(op, part):
     status = b'unknown'  # used by debug output
     try:
         handler = parthandlermapping.get(part.type)
         if handler is None:
             status = b'unsupported-type'
             raise error.BundleUnknownFeatureError(parttype=part.type)
         indebug(op.ui, b'found a handler for part %s' % part.type)
         unknownparams = part.mandatorykeys - handler.params
         if unknownparams:
             unknownparams = list(unknownparams)
             unknownparams.sort()
             status = b'unsupported-params (%s)' % b', '.join(unknownparams)
             raise error.BundleUnknownFeatureError(
                 parttype=part.type, params=unknownparams
             )
         status = b'supported'
     except error.BundleUnknownFeatureError as exc:
         if part.mandatory:  # mandatory parts
             raise
         indebug(op.ui, b'ignoring unsupported advisory part %s' % exc)
         return  # skip to part processing
     finally:
         if op.ui.debugflag:
             msg = [b'bundle2-input-part: "%s"' % part.type]
             if not part.mandatory:
                 msg.append(b' (advisory)')
             nbmp = len(part.mandatorykeys)
             nbap = len(part.params) - nbmp
             if nbmp or nbap:
                 msg.append(b' (params:')
                 if nbmp:
                     msg.append(b' %i mandatory' % nbmp)
                 if nbap:
                     msg.append(b' %i advisory' % nbmp)
                 msg.append(b')')
             msg.append(b' %s\n' % status)
             op.ui.debug(b''.join(msg))
 
     return handler
 
 
 def _processpart(op, part):
     """process a single part from a bundle
 
     The part is guaranteed to have been fully consumed when the function exits
     (even if an exception is raised)."""
     handler = _gethandler(op, part)
     if handler is None:
         return
 
     # handler is called outside the above try block so that we don't
     # risk catching KeyErrors from anything other than the
     # parthandlermapping lookup (any KeyError raised by handler()
     # itself represents a defect of a different variety).
     output = None
     if op.captureoutput and op.reply is not None:
         op.ui.pushbuffer(error=True, subproc=True)
         output = b''
     try:
         handler(op, part)
     finally:
         if output is not None:
             output = op.ui.popbuffer()
         if output:
             outpart = op.reply.newpart(b'output', data=output, mandatory=False)
             outpart.addparam(
                 b'in-reply-to', pycompat.bytestr(part.id), mandatory=False
             )
 
 
 def decodecaps(blob):
     """decode a bundle2 caps bytes blob into a dictionary
 
     The blob is a list of capabilities (one per line)
     Capabilities may have values using a line of the form::
 
         capability=value1,value2,value3
 
     The values are always a list."""
     caps = {}
     for line in blob.splitlines():
         if not line:
             continue
         if b'=' not in line:
             key, vals = line, ()
         else:
             key, vals = line.split(b'=', 1)
             vals = vals.split(b',')
         key = urlreq.unquote(key)
         vals = [urlreq.unquote(v) for v in vals]
         caps[key] = vals
     return caps
 
 
 def encodecaps(caps):
     """encode a bundle2 caps dictionary into a bytes blob"""
     chunks = []
     for ca in sorted(caps):
         vals = caps[ca]
         ca = urlreq.quote(ca)
         vals = [urlreq.quote(v) for v in vals]
         if vals:
             ca = b"%s=%s" % (ca, b','.join(vals))
         chunks.append(ca)
     return b'\n'.join(chunks)
 
 
 bundletypes = {
     b"": (b"", b'UN'),  # only when using unbundle on ssh and old http servers
     # since the unification ssh accepts a header but there
     # is no capability signaling it.
     b"HG20": (),  # special-cased below
     b"HG10UN": (b"HG10UN", b'UN'),
     b"HG10BZ": (b"HG10", b'BZ'),
     b"HG10GZ": (b"HG10GZ", b'GZ'),
 }
 
 # hgweb uses this list to communicate its preferred type
 bundlepriority = [b'HG10GZ', b'HG10BZ', b'HG10UN']
 
 
 class bundle20(object):
     """represent an outgoing bundle2 container
 
     Use the `addparam` method to add stream level parameter. and `newpart` to
     populate it. Then call `getchunks` to retrieve all the binary chunks of
     data that compose the bundle2 container."""
 
     _magicstring = b'HG20'
 
     def __init__(self, ui, capabilities=()):
         self.ui = ui
         self._params = []
         self._parts = []
         self.capabilities = dict(capabilities)
         self._compengine = util.compengines.forbundletype(b'UN')
         self._compopts = None
         # If compression is being handled by a consumer of the raw
         # data (e.g. the wire protocol), unsetting this flag tells
         # consumers that the bundle is best left uncompressed.
         self.prefercompressed = True
 
     def setcompression(self, alg, compopts=None):
         """setup core part compression to <alg>"""
         if alg in (None, b'UN'):
             return
         assert not any(n.lower() == b'compression' for n, v in self._params)
         self.addparam(b'Compression', alg)
         self._compengine = util.compengines.forbundletype(alg)
         self._compopts = compopts
 
     @property
     def nbparts(self):
         """total number of parts added to the bundler"""
         return len(self._parts)
 
     # methods used to defines the bundle2 content
     def addparam(self, name, value=None):
         """add a stream level parameter"""
         if not name:
             raise error.ProgrammingError(b'empty parameter name')
         if name[0:1] not in pycompat.bytestr(
             string.ascii_letters  # pytype: disable=wrong-arg-types
         ):
             raise error.ProgrammingError(
                 b'non letter first character: %s' % name
             )
         self._params.append((name, value))
 
     def addpart(self, part):
         """add a new part to the bundle2 container
 
         Parts contains the actual applicative payload."""
         assert part.id is None
         part.id = len(self._parts)  # very cheap counter
         self._parts.append(part)
 
     def newpart(self, typeid, *args, **kwargs):
         """create a new part and add it to the containers
 
         As the part is directly added to the containers. For now, this means
         that any failure to properly initialize the part after calling
         ``newpart`` should result in a failure of the whole bundling process.
 
         You can still fall back to manually create and add if you need better
         control."""
         part = bundlepart(typeid, *args, **kwargs)
         self.addpart(part)
         return part
 
     # methods used to generate the bundle2 stream
     def getchunks(self):
         if self.ui.debugflag:
             msg = [b'bundle2-output-bundle: "%s",' % self._magicstring]
             if self._params:
                 msg.append(b' (%i params)' % len(self._params))
             msg.append(b' %i parts total\n' % len(self._parts))
             self.ui.debug(b''.join(msg))
         outdebug(self.ui, b'start emission of %s stream' % self._magicstring)
         yield self._magicstring
         param = self._paramchunk()
         outdebug(self.ui, b'bundle parameter: %s' % param)
         yield _pack(_fstreamparamsize, len(param))
         if param:
             yield param
         for chunk in self._compengine.compressstream(
             self._getcorechunk(), self._compopts
         ):
             yield chunk
 
     def _paramchunk(self):
         """return a encoded version of all stream parameters"""
         blocks = []
         for par, value in self._params:
             par = urlreq.quote(par)
             if value is not None:
                 value = urlreq.quote(value)
                 par = b'%s=%s' % (par, value)
             blocks.append(par)
         return b' '.join(blocks)
 
     def _getcorechunk(self):
         """yield chunk for the core part of the bundle
 
         (all but headers and parameters)"""
         outdebug(self.ui, b'start of parts')
         for part in self._parts:
             outdebug(self.ui, b'bundle part: "%s"' % part.type)
             for chunk in part.getchunks(ui=self.ui):
                 yield chunk
         outdebug(self.ui, b'end of bundle')
         yield _pack(_fpartheadersize, 0)
 
     def salvageoutput(self):
         """return a list with a copy of all output parts in the bundle
 
         This is meant to be used during error handling to make sure we preserve
         server output"""
         salvaged = []
         for part in self._parts:
             if part.type.startswith(b'output'):
                 salvaged.append(part.copy())
         return salvaged
 
 
 class unpackermixin(object):
     """A mixin to extract bytes and struct data from a stream"""
 
     def __init__(self, fp):
         self._fp = fp
 
     def _unpack(self, format):
         """unpack this struct format from the stream
 
         This method is meant for internal usage by the bundle2 protocol only.
         They directly manipulate the low level stream including bundle2 level
         instruction.
 
         Do not use it to implement higher-level logic or methods."""
         data = self._readexact(struct.calcsize(format))
         return _unpack(format, data)
 
     def _readexact(self, size):
         """read exactly <size> bytes from the stream
 
         This method is meant for internal usage by the bundle2 protocol only.
         They directly manipulate the low level stream including bundle2 level
         instruction.
 
         Do not use it to implement higher-level logic or methods."""
         return changegroup.readexactly(self._fp, size)
 
 
 def getunbundler(ui, fp, magicstring=None):
     """return a valid unbundler object for a given magicstring"""
     if magicstring is None:
         magicstring = changegroup.readexactly(fp, 4)
     magic, version = magicstring[0:2], magicstring[2:4]
     if magic != b'HG':
         ui.debug(
             b"error: invalid magic: %r (version %r), should be 'HG'\n"
             % (magic, version)
         )
         raise error.Abort(_(b'not a Mercurial bundle'))
     unbundlerclass = formatmap.get(version)
     if unbundlerclass is None:
         raise error.Abort(_(b'unknown bundle version %s') % version)
     unbundler = unbundlerclass(ui, fp)
     indebug(ui, b'start processing of %s stream' % magicstring)
     return unbundler
 
 
 class unbundle20(unpackermixin):
     """interpret a bundle2 stream
 
     This class is fed with a binary stream and yields parts through its
     `iterparts` methods."""
 
     _magicstring = b'HG20'
 
     def __init__(self, ui, fp):
         """If header is specified, we do not read it out of the stream."""
         self.ui = ui
         self._compengine = util.compengines.forbundletype(b'UN')
         self._compressed = None
         super(unbundle20, self).__init__(fp)
 
     @util.propertycache
     def params(self):
         """dictionary of stream level parameters"""
         indebug(self.ui, b'reading bundle2 stream parameters')
         params = {}
         paramssize = self._unpack(_fstreamparamsize)[0]
         if paramssize < 0:
             raise error.BundleValueError(
                 b'negative bundle param size: %i' % paramssize
             )
         if paramssize:
             params = self._readexact(paramssize)
             params = self._processallparams(params)
         return params
 
     def _processallparams(self, paramsblock):
         """"""
         params = util.sortdict()
         for p in paramsblock.split(b' '):
             p = p.split(b'=', 1)
             p = [urlreq.unquote(i) for i in p]
             if len(p) < 2:
                 p.append(None)
             self._processparam(*p)
             params[p[0]] = p[1]
         return params
 
     def _processparam(self, name, value):
         """process a parameter, applying its effect if needed
 
         Parameter starting with a lower case letter are advisory and will be
         ignored when unknown.  Those starting with an upper case letter are
         mandatory and will this function will raise a KeyError when unknown.
 
         Note: no option are currently supported. Any input will be either
               ignored or failing.
         """
         if not name:
             raise ValueError('empty parameter name')
         if name[0:1] not in pycompat.bytestr(
             string.ascii_letters  # pytype: disable=wrong-arg-types
         ):
             raise ValueError('non letter first character: %s' % name)
         try:
             handler = b2streamparamsmap[name.lower()]
         except KeyError:
             if name[0:1].islower():
                 indebug(self.ui, b"ignoring unknown parameter %s" % name)
             else:
                 raise error.BundleUnknownFeatureError(params=(name,))
         else:
             handler(self, name, value)
 
     def _forwardchunks(self):
         """utility to transfer a bundle2 as binary
 
         This is made necessary by the fact the 'getbundle' command over 'ssh'
         have no way to know then the reply end, relying on the bundle to be
         interpreted to know its end. This is terrible and we are sorry, but we
         needed to move forward to get general delta enabled.
         """
         yield self._magicstring
         assert 'params' not in vars(self)
         paramssize = self._unpack(_fstreamparamsize)[0]
         if paramssize < 0:
             raise error.BundleValueError(
                 b'negative bundle param size: %i' % paramssize
             )
         if paramssize:
             params = self._readexact(paramssize)
             self._processallparams(params)
             # The payload itself is decompressed below, so drop
             # the compression parameter passed down to compensate.
             outparams = []
             for p in params.split(b' '):
                 k, v = p.split(b'=', 1)
                 if k.lower() != b'compression':
                     outparams.append(p)
             outparams = b' '.join(outparams)
             yield _pack(_fstreamparamsize, len(outparams))
             yield outparams
         else:
             yield _pack(_fstreamparamsize, paramssize)
         # From there, payload might need to be decompressed
         self._fp = self._compengine.decompressorreader(self._fp)
         emptycount = 0
         while emptycount < 2:
             # so we can brainlessly loop
             assert _fpartheadersize == _fpayloadsize
             size = self._unpack(_fpartheadersize)[0]
             yield _pack(_fpartheadersize, size)
             if size:
                 emptycount = 0
             else:
                 emptycount += 1
                 continue
             if size == flaginterrupt:
                 continue
             elif size < 0:
                 raise error.BundleValueError(b'negative chunk size: %i')
             yield self._readexact(size)
 
     def iterparts(self, seekable=False):
         """yield all parts contained in the stream"""
         cls = seekableunbundlepart if seekable else unbundlepart
         # make sure param have been loaded
         self.params
         # From there, payload need to be decompressed
         self._fp = self._compengine.decompressorreader(self._fp)
         indebug(self.ui, b'start extraction of bundle2 parts')
         headerblock = self._readpartheader()
         while headerblock is not None:
             part = cls(self.ui, headerblock, self._fp)
             yield part
             # Ensure part is fully consumed so we can start reading the next
             # part.
             part.consume()
 
             headerblock = self._readpartheader()
         indebug(self.ui, b'end of bundle2 stream')
 
     def _readpartheader(self):
         """reads a part header size and return the bytes blob
 
         returns None if empty"""
         headersize = self._unpack(_fpartheadersize)[0]
         if headersize < 0:
             raise error.BundleValueError(
                 b'negative part header size: %i' % headersize
             )
         indebug(self.ui, b'part header size: %i' % headersize)
         if headersize:
             return self._readexact(headersize)
         return None
 
     def compressed(self):
         self.params  # load params
         return self._compressed
 
     def close(self):
         """close underlying file"""
         if util.safehasattr(self._fp, 'close'):
             return self._fp.close()
 
 
 formatmap = {b'20': unbundle20}
 
 b2streamparamsmap = {}
 
 
 def b2streamparamhandler(name):
     """register a handler for a stream level parameter"""
 
     def decorator(func):
         assert name not in formatmap
         b2streamparamsmap[name] = func
         return func
 
     return decorator
 
 
 @b2streamparamhandler(b'compression')
 def processcompression(unbundler, param, value):
     """read compression parameter and install payload decompression"""
     if value not in util.compengines.supportedbundletypes:
         raise error.BundleUnknownFeatureError(params=(param,), values=(value,))
     unbundler._compengine = util.compengines.forbundletype(value)
     if value is not None:
         unbundler._compressed = True
 
 
 class bundlepart(object):
     """A bundle2 part contains application level payload
 
     The part `type` is used to route the part to the application level
     handler.
 
     The part payload is contained in ``part.data``. It could be raw bytes or a
     generator of byte chunks.
 
     You can add parameters to the part using the ``addparam`` method.
     Parameters can be either mandatory (default) or advisory. Remote side
     should be able to safely ignore the advisory ones.
 
     Both data and parameters cannot be modified after the generation has begun.
     """
 
     def __init__(
         self,
         parttype,
         mandatoryparams=(),
         advisoryparams=(),
         data=b'',
         mandatory=True,
     ):
         validateparttype(parttype)
         self.id = None
         self.type = parttype
         self._data = data
         self._mandatoryparams = list(mandatoryparams)
         self._advisoryparams = list(advisoryparams)
         # checking for duplicated entries
         self._seenparams = set()
         for pname, __ in self._mandatoryparams + self._advisoryparams:
             if pname in self._seenparams:
                 raise error.ProgrammingError(b'duplicated params: %s' % pname)
             self._seenparams.add(pname)
         # status of the part's generation:
         # - None: not started,
         # - False: currently generated,
         # - True: generation done.
         self._generated = None
         self.mandatory = mandatory
 
     def __repr__(self):
-        cls = b"%s.%s" % (self.__class__.__module__, self.__class__.__name__)
-        return b'<%s object at %x; id: %s; type: %s; mandatory: %s>' % (
+        cls = "%s.%s" % (self.__class__.__module__, self.__class__.__name__)
+        return '<%s object at %x; id: %s; type: %s; mandatory: %s>' % (
             cls,
             id(self),
             self.id,
             self.type,
             self.mandatory,
         )
 
     def copy(self):
         """return a copy of the part
 
         The new part have the very same content but no partid assigned yet.
         Parts with generated data cannot be copied."""
         assert not util.safehasattr(self.data, 'next')
         return self.__class__(
             self.type,
             self._mandatoryparams,
             self._advisoryparams,
             self._data,
             self.mandatory,
         )
 
     # methods used to defines the part content
     @property
     def data(self):
         return self._data
 
     @data.setter
     def data(self, data):
         if self._generated is not None:
             raise error.ReadOnlyPartError(b'part is being generated')
         self._data = data
 
     @property
     def mandatoryparams(self):
         # make it an immutable tuple to force people through ``addparam``
         return tuple(self._mandatoryparams)
 
     @property
     def advisoryparams(self):
         # make it an immutable tuple to force people through ``addparam``
         return tuple(self._advisoryparams)
 
     def addparam(self, name, value=b'', mandatory=True):
         """add a parameter to the part
 
         If 'mandatory' is set to True, the remote handler must claim support
         for this parameter or the unbundling will be aborted.
 
         The 'name' and 'value' cannot exceed 255 bytes each.
         """
         if self._generated is not None:
             raise error.ReadOnlyPartError(b'part is being generated')
         if name in self._seenparams:
             raise ValueError(b'duplicated params: %s' % name)
         self._seenparams.add(name)
         params = self._advisoryparams
         if mandatory:
             params = self._mandatoryparams
         params.append((name, value))
 
     # methods used to generates the bundle2 stream
     def getchunks(self, ui):
         if self._generated is not None:
             raise error.ProgrammingError(b'part can only be consumed once')
         self._generated = False
 
         if ui.debugflag:
             msg = [b'bundle2-output-part: "%s"' % self.type]
             if not self.mandatory:
                 msg.append(b' (advisory)')
             nbmp = len(self.mandatoryparams)
             nbap = len(self.advisoryparams)
             if nbmp or nbap:
                 msg.append(b' (params:')
                 if nbmp:
                     msg.append(b' %i mandatory' % nbmp)
                 if nbap:
                     msg.append(b' %i advisory' % nbmp)
                 msg.append(b')')
             if not self.data:
                 msg.append(b' empty payload')
             elif util.safehasattr(self.data, 'next') or util.safehasattr(
                 self.data, b'__next__'
             ):
                 msg.append(b' streamed payload')
             else:
                 msg.append(b' %i bytes payload' % len(self.data))
             msg.append(b'\n')
             ui.debug(b''.join(msg))
 
         #### header
         if self.mandatory:
             parttype = self.type.upper()
         else:
             parttype = self.type.lower()
         outdebug(ui, b'part %s: "%s"' % (pycompat.bytestr(self.id), parttype))
         ## parttype
         header = [
             _pack(_fparttypesize, len(parttype)),
             parttype,
             _pack(_fpartid, self.id),
         ]
         ## parameters
         # count
         manpar = self.mandatoryparams
         advpar = self.advisoryparams
         header.append(_pack(_fpartparamcount, len(manpar), len(advpar)))
         # size
         parsizes = []
         for key, value in manpar:
             parsizes.append(len(key))
             parsizes.append(len(value))
         for key, value in advpar:
             parsizes.append(len(key))
             parsizes.append(len(value))
         paramsizes = _pack(_makefpartparamsizes(len(parsizes) // 2), *parsizes)
         header.append(paramsizes)
         # key, value
         for key, value in manpar:
             header.append(key)
             header.append(value)
         for key, value in advpar:
             header.append(key)
             header.append(value)
         ## finalize header
         try:
             headerchunk = b''.join(header)
         except TypeError:
             raise TypeError(
                 'Found a non-bytes trying to '
                 'build bundle part header: %r' % header
             )
         outdebug(ui, b'header chunk size: %i' % len(headerchunk))
         yield _pack(_fpartheadersize, len(headerchunk))
         yield headerchunk
         ## payload
         try:
             for chunk in self._payloadchunks():
                 outdebug(ui, b'payload chunk size: %i' % len(chunk))
                 yield _pack(_fpayloadsize, len(chunk))
                 yield chunk
         except GeneratorExit:
             # GeneratorExit means that nobody is listening for our
             # results anyway, so just bail quickly rather than trying
             # to produce an error part.
             ui.debug(b'bundle2-generatorexit\n')
             raise
         except BaseException as exc:
             bexc = stringutil.forcebytestr(exc)
             # backup exception data for later
             ui.debug(
                 b'bundle2-input-stream-interrupt: encoding exception %s' % bexc
             )
             tb = sys.exc_info()[2]
             msg = b'unexpected error: %s' % bexc
             interpart = bundlepart(
                 b'error:abort', [(b'message', msg)], mandatory=False
             )
             interpart.id = 0
             yield _pack(_fpayloadsize, -1)
             for chunk in interpart.getchunks(ui=ui):
                 yield chunk
             outdebug(ui, b'closing payload chunk')
             # abort current part payload
             yield _pack(_fpayloadsize, 0)
             pycompat.raisewithtb(exc, tb)
         # end of payload
         outdebug(ui, b'closing payload chunk')
         yield _pack(_fpayloadsize, 0)
         self._generated = True
 
     def _payloadchunks(self):
         """yield chunks of a the part payload
 
         Exists to handle the different methods to provide data to a part."""
         # we only support fixed size data now.
         # This will be improved in the future.
         if util.safehasattr(self.data, 'next') or util.safehasattr(
             self.data, b'__next__'
         ):
             buff = util.chunkbuffer(self.data)
             chunk = buff.read(preferedchunksize)
             while chunk:
                 yield chunk
                 chunk = buff.read(preferedchunksize)
         elif len(self.data):
             yield self.data
 
 
 flaginterrupt = -1
 
 
 class interrupthandler(unpackermixin):
     """read one part and process it with restricted capability
 
     This allows to transmit exception raised on the producer size during part
     iteration while the consumer is reading a part.
 
     Part processed in this manner only have access to a ui object,"""
 
     def __init__(self, ui, fp):
         super(interrupthandler, self).__init__(fp)
         self.ui = ui
 
     def _readpartheader(self):
         """reads a part header size and return the bytes blob
 
         returns None if empty"""
         headersize = self._unpack(_fpartheadersize)[0]
         if headersize < 0:
             raise error.BundleValueError(
                 b'negative part header size: %i' % headersize
             )
         indebug(self.ui, b'part header size: %i\n' % headersize)
         if headersize:
             return self._readexact(headersize)
         return None
 
     def __call__(self):
 
         self.ui.debug(
             b'bundle2-input-stream-interrupt: opening out of band context\n'
         )
         indebug(self.ui, b'bundle2 stream interruption, looking for a part.')
         headerblock = self._readpartheader()
         if headerblock is None:
             indebug(self.ui, b'no part found during interruption.')
             return
         part = unbundlepart(self.ui, headerblock, self._fp)
         op = interruptoperation(self.ui)
         hardabort = False
         try:
             _processpart(op, part)
         except (SystemExit, KeyboardInterrupt):
             hardabort = True
             raise
         finally:
             if not hardabort:
                 part.consume()
         self.ui.debug(
             b'bundle2-input-stream-interrupt: closing out of band context\n'
         )
 
 
 class interruptoperation(object):
     """A limited operation to be use by part handler during interruption
 
     It only have access to an ui object.
     """
 
     def __init__(self, ui):
         self.ui = ui
         self.reply = None
         self.captureoutput = False
 
     @property
     def repo(self):
         raise error.ProgrammingError(b'no repo access from stream interruption')
 
     def gettransaction(self):
         raise TransactionUnavailable(b'no repo access from stream interruption')
 
 
 def decodepayloadchunks(ui, fh):
     """Reads bundle2 part payload data into chunks.
 
     Part payload data consists of framed chunks. This function takes
     a file handle and emits those chunks.
     """
     dolog = ui.configbool(b'devel', b'bundle2.debug')
     debug = ui.debug
 
     headerstruct = struct.Struct(_fpayloadsize)
     headersize = headerstruct.size
     unpack = headerstruct.unpack
 
     readexactly = changegroup.readexactly
     read = fh.read
 
     chunksize = unpack(readexactly(fh, headersize))[0]
     indebug(ui, b'payload chunk size: %i' % chunksize)
 
     # changegroup.readexactly() is inlined below for performance.
     while chunksize:
         if chunksize >= 0:
             s = read(chunksize)
             if len(s) < chunksize:
                 raise error.Abort(
                     _(
                         b'stream ended unexpectedly '
                         b' (got %d bytes, expected %d)'
                     )
                     % (len(s), chunksize)
                 )
 
             yield s
         elif chunksize == flaginterrupt:
             # Interrupt "signal" detected. The regular stream is interrupted
             # and a bundle2 part follows. Consume it.
             interrupthandler(ui, fh)()
         else:
             raise error.BundleValueError(
                 b'negative payload chunk size: %s' % chunksize
             )
 
         s = read(headersize)
         if len(s) < headersize:
             raise error.Abort(
                 _(b'stream ended unexpectedly  (got %d bytes, expected %d)')
                 % (len(s), chunksize)
             )
 
         chunksize = unpack(s)[0]
 
         # indebug() inlined for performance.
         if dolog:
             debug(b'bundle2-input: payload chunk size: %i\n' % chunksize)
 
 
 class unbundlepart(unpackermixin):
     """a bundle part read from a bundle"""
 
     def __init__(self, ui, header, fp):
         super(unbundlepart, self).__init__(fp)
         self._seekable = util.safehasattr(fp, 'seek') and util.safehasattr(
             fp, b'tell'
         )
         self.ui = ui
         # unbundle state attr
         self._headerdata = header
         self._headeroffset = 0
         self._initialized = False
         self.consumed = False
         # part data
         self.id = None
         self.type = None
         self.mandatoryparams = None
         self.advisoryparams = None
         self.params = None
         self.mandatorykeys = ()
         self._readheader()
         self._mandatory = None
         self._pos = 0
 
     def _fromheader(self, size):
         """return the next <size> byte from the header"""
         offset = self._headeroffset
         data = self._headerdata[offset : (offset + size)]
         self._headeroffset = offset + size
         return data
 
     def _unpackheader(self, format):
         """read given format from header
 
         This automatically compute the size of the format to read."""
         data = self._fromheader(struct.calcsize(format))
         return _unpack(format, data)
 
     def _initparams(self, mandatoryparams, advisoryparams):
         """internal function to setup all logic related parameters"""
         # make it read only to prevent people touching it by mistake.
         self.mandatoryparams = tuple(mandatoryparams)
         self.advisoryparams = tuple(advisoryparams)
         # user friendly UI
         self.params = util.sortdict(self.mandatoryparams)
         self.params.update(self.advisoryparams)
         self.mandatorykeys = frozenset(p[0] for p in mandatoryparams)
 
     def _readheader(self):
         """read the header and setup the object"""
         typesize = self._unpackheader(_fparttypesize)[0]
         self.type = self._fromheader(typesize)
         indebug(self.ui, b'part type: "%s"' % self.type)
         self.id = self._unpackheader(_fpartid)[0]
         indebug(self.ui, b'part id: "%s"' % pycompat.bytestr(self.id))
         # extract mandatory bit from type
         self.mandatory = self.type != self.type.lower()
         self.type = self.type.lower()
         ## reading parameters
         # param count
         mancount, advcount = self._unpackheader(_fpartparamcount)
         indebug(self.ui, b'part parameters: %i' % (mancount + advcount))
         # param size
         fparamsizes = _makefpartparamsizes(mancount + advcount)
         paramsizes = self._unpackheader(fparamsizes)
         # make it a list of couple again
         paramsizes = list(zip(paramsizes[::2], paramsizes[1::2]))
         # split mandatory from advisory
         mansizes = paramsizes[:mancount]
         advsizes = paramsizes[mancount:]
         # retrieve param value
         manparams = []
         for key, value in mansizes:
             manparams.append((self._fromheader(key), self._fromheader(value)))
         advparams = []
         for key, value in advsizes:
             advparams.append((self._fromheader(key), self._fromheader(value)))
         self._initparams(manparams, advparams)
         ## part payload
         self._payloadstream = util.chunkbuffer(self._payloadchunks())
         # we read the data, tell it
         self._initialized = True
 
     def _payloadchunks(self):
         """Generator of decoded chunks in the payload."""
         return decodepayloadchunks(self.ui, self._fp)
 
     def consume(self):
         """Read the part payload until completion.
 
         By consuming the part data, the underlying stream read offset will
         be advanced to the next part (or end of stream).
         """
         if self.consumed:
             return
 
         chunk = self.read(32768)
         while chunk:
             self._pos += len(chunk)
             chunk = self.read(32768)
 
     def read(self, size=None):
         """read payload data"""
         if not self._initialized:
             self._readheader()
         if size is None:
             data = self._payloadstream.read()
         else:
             data = self._payloadstream.read(size)
         self._pos += len(data)
         if size is None or len(data) < size:
             if not self.consumed and self._pos:
                 self.ui.debug(
                     b'bundle2-input-part: total payload size %i\n' % self._pos
                 )
             self.consumed = True
         return data
 
 
 class seekableunbundlepart(unbundlepart):
     """A bundle2 part in a bundle that is seekable.
 
     Regular ``unbundlepart`` instances can only be read once. This class
     extends ``unbundlepart`` to enable bi-directional seeking within the
     part.
 
     Bundle2 part data consists of framed chunks. Offsets when seeking
     refer to the decoded data, not the offsets in the underlying bundle2
     stream.
 
     To facilitate quickly seeking within the decoded data, instances of this
     class maintain a mapping between offsets in the underlying stream and
     the decoded payload. This mapping will consume memory in proportion
     to the number of chunks within the payload (which almost certainly
     increases in proportion with the size of the part).
     """
 
     def __init__(self, ui, header, fp):
         # (payload, file) offsets for chunk starts.
         self._chunkindex = []
 
         super(seekableunbundlepart, self).__init__(ui, header, fp)
 
     def _payloadchunks(self, chunknum=0):
         '''seek to specified chunk and start yielding data'''
         if len(self._chunkindex) == 0:
             assert chunknum == 0, b'Must start with chunk 0'
             self._chunkindex.append((0, self._tellfp()))
         else:
             assert chunknum < len(self._chunkindex), (
                 b'Unknown chunk %d' % chunknum
             )
             self._seekfp(self._chunkindex[chunknum][1])
 
         pos = self._chunkindex[chunknum][0]
 
         for chunk in decodepayloadchunks(self.ui, self._fp):
             chunknum += 1
             pos += len(chunk)
             if chunknum == len(self._chunkindex):
                 self._chunkindex.append((pos, self._tellfp()))
 
             yield chunk
 
     def _findchunk(self, pos):
         '''for a given payload position, return a chunk number and offset'''
         for chunk, (ppos, fpos) in enumerate(self._chunkindex):
             if ppos == pos:
                 return chunk, 0
             elif ppos > pos:
                 return chunk - 1, pos - self._chunkindex[chunk - 1][0]
         raise ValueError(b'Unknown chunk')
 
     def tell(self):
         return self._pos
 
     def seek(self, offset, whence=os.SEEK_SET):
         if whence == os.SEEK_SET:
             newpos = offset
         elif whence == os.SEEK_CUR:
             newpos = self._pos + offset
         elif whence == os.SEEK_END:
             if not self.consumed:
                 # Can't use self.consume() here because it advances self._pos.
                 chunk = self.read(32768)
                 while chunk:
                     chunk = self.read(32768)
             newpos = self._chunkindex[-1][0] - offset
         else:
             raise ValueError(b'Unknown whence value: %r' % (whence,))
 
         if newpos > self._chunkindex[-1][0] and not self.consumed:
             # Can't use self.consume() here because it advances self._pos.
             chunk = self.read(32768)
             while chunk:
                 chunk = self.read(32668)
 
         if not 0 <= newpos <= self._chunkindex[-1][0]:
             raise ValueError(b'Offset out of range')
 
         if self._pos != newpos:
             chunk, internaloffset = self._findchunk(newpos)
             self._payloadstream = util.chunkbuffer(self._payloadchunks(chunk))
             adjust = self.read(internaloffset)
             if len(adjust) != internaloffset:
                 raise error.Abort(_(b'Seek failed\n'))
             self._pos = newpos
 
     def _seekfp(self, offset, whence=0):
         """move the underlying file pointer
 
         This method is meant for internal usage by the bundle2 protocol only.
         They directly manipulate the low level stream including bundle2 level
         instruction.
 
         Do not use it to implement higher-level logic or methods."""
         if self._seekable:
             return self._fp.seek(offset, whence)
         else:
             raise NotImplementedError(_(b'File pointer is not seekable'))
 
     def _tellfp(self):
         """return the file offset, or None if file is not seekable
 
         This method is meant for internal usage by the bundle2 protocol only.
         They directly manipulate the low level stream including bundle2 level
         instruction.
 
         Do not use it to implement higher-level logic or methods."""
         if self._seekable:
             try:
                 return self._fp.tell()
             except IOError as e:
                 if e.errno == errno.ESPIPE:
                     self._seekable = False
                 else:
                     raise
         return None
 
 
 # These are only the static capabilities.
 # Check the 'getrepocaps' function for the rest.
 capabilities = {
     b'HG20': (),
     b'bookmarks': (),
     b'error': (b'abort', b'unsupportedcontent', b'pushraced', b'pushkey'),
     b'listkeys': (),
     b'pushkey': (),
     b'digests': tuple(sorted(util.DIGESTS.keys())),
     b'remote-changegroup': (b'http', b'https'),
     b'hgtagsfnodes': (),
     b'rev-branch-cache': (),
     b'phases': (b'heads',),
     b'stream': (b'v2',),
 }
 
 
 def getrepocaps(repo, allowpushback=False, role=None):
     """return the bundle2 capabilities for a given repo
 
     Exists to allow extensions (like evolution) to mutate the capabilities.
 
     The returned value is used for servers advertising their capabilities as
     well as clients advertising their capabilities to servers as part of
     bundle2 requests. The ``role`` argument specifies which is which.
     """
     if role not in (b'client', b'server'):
         raise error.ProgrammingError(b'role argument must be client or server')
 
     caps = capabilities.copy()
     caps[b'changegroup'] = tuple(
         sorted(changegroup.supportedincomingversions(repo))
     )
     if obsolete.isenabled(repo, obsolete.exchangeopt):
         supportedformat = tuple(b'V%i' % v for v in obsolete.formats)
         caps[b'obsmarkers'] = supportedformat
     if allowpushback:
         caps[b'pushback'] = ()
     cpmode = repo.ui.config(b'server', b'concurrent-push-mode')
     if cpmode == b'check-related':
         caps[b'checkheads'] = (b'related',)
     if b'phases' in repo.ui.configlist(b'devel', b'legacy.exchange'):
         caps.pop(b'phases')
 
     # Don't advertise stream clone support in server mode if not configured.
     if role == b'server':
         streamsupported = repo.ui.configbool(
             b'server', b'uncompressed', untrusted=True
         )
         featuresupported = repo.ui.configbool(b'server', b'bundle2.stream')
 
         if not streamsupported or not featuresupported:
             caps.pop(b'stream')
     # Else always advertise support on client, because payload support
     # should always be advertised.
 
     return caps
 
 
 def bundle2caps(remote):
     """return the bundle capabilities of a peer as dict"""
     raw = remote.capable(b'bundle2')
     if not raw and raw != b'':
         return {}
     capsblob = urlreq.unquote(remote.capable(b'bundle2'))
     return decodecaps(capsblob)
 
 
 def obsmarkersversion(caps):
     """extract the list of supported obsmarkers versions from a bundle2caps dict
     """
     obscaps = caps.get(b'obsmarkers', ())
     return [int(c[1:]) for c in obscaps if c.startswith(b'V')]
 
 
 def writenewbundle(
     ui,
     repo,
     source,
     filename,
     bundletype,
     outgoing,
     opts,
     vfs=None,
     compression=None,
     compopts=None,
 ):
     if bundletype.startswith(b'HG10'):
         cg = changegroup.makechangegroup(repo, outgoing, b'01', source)
         return writebundle(
             ui,
             cg,
             filename,
             bundletype,
             vfs=vfs,
             compression=compression,
             compopts=compopts,
         )
     elif not bundletype.startswith(b'HG20'):
         raise error.ProgrammingError(b'unknown bundle type: %s' % bundletype)
 
     caps = {}
     if b'obsolescence' in opts:
         caps[b'obsmarkers'] = (b'V1',)
     bundle = bundle20(ui, caps)
     bundle.setcompression(compression, compopts)
     _addpartsfromopts(ui, repo, bundle, source, outgoing, opts)
     chunkiter = bundle.getchunks()
 
     return changegroup.writechunks(ui, chunkiter, filename, vfs=vfs)
 
 
 def _addpartsfromopts(ui, repo, bundler, source, outgoing, opts):
     # We should eventually reconcile this logic with the one behind
     # 'exchange.getbundle2partsgenerator'.
     #
     # The type of input from 'getbundle' and 'writenewbundle' are a bit
     # different right now. So we keep them separated for now for the sake of
     # simplicity.
 
     # we might not always want a changegroup in such bundle, for example in
     # stream bundles
     if opts.get(b'changegroup', True):
         cgversion = opts.get(b'cg.version')
         if cgversion is None:
             cgversion = changegroup.safeversion(repo)
         cg = changegroup.makechangegroup(repo, outgoing, cgversion, source)
         part = bundler.newpart(b'changegroup', data=cg.getchunks())
         part.addparam(b'version', cg.version)
         if b'clcount' in cg.extras:
             part.addparam(
                 b'nbchanges', b'%d' % cg.extras[b'clcount'], mandatory=False
             )
         if opts.get(b'phases') and repo.revs(
             b'%ln and secret()', outgoing.missingheads
         ):
             part.addparam(
                 b'targetphase', b'%d' % phases.secret, mandatory=False
             )
         if b'exp-sidedata-flag' in repo.requirements:
             part.addparam(b'exp-sidedata', b'1')
 
     if opts.get(b'streamv2', False):
         addpartbundlestream2(bundler, repo, stream=True)
 
     if opts.get(b'tagsfnodescache', True):
         addparttagsfnodescache(repo, bundler, outgoing)
 
     if opts.get(b'revbranchcache', True):
         addpartrevbranchcache(repo, bundler, outgoing)
 
     if opts.get(b'obsolescence', False):
         obsmarkers = repo.obsstore.relevantmarkers(outgoing.missing)
         buildobsmarkerspart(bundler, obsmarkers)
 
     if opts.get(b'phases', False):
         headsbyphase = phases.subsetphaseheads(repo, outgoing.missing)
         phasedata = phases.binaryencode(headsbyphase)
         bundler.newpart(b'phase-heads', data=phasedata)
 
 
 def addparttagsfnodescache(repo, bundler, outgoing):
     # we include the tags fnode cache for the bundle changeset
     # (as an optional parts)
     cache = tags.hgtagsfnodescache(repo.unfiltered())
     chunks = []
 
     # .hgtags fnodes are only relevant for head changesets. While we could
     # transfer values for all known nodes, there will likely be little to
     # no benefit.
     #
     # We don't bother using a generator to produce output data because
     # a) we only have 40 bytes per head and even esoteric numbers of heads
     # consume little memory (1M heads is 40MB) b) we don't want to send the
     # part if we don't have entries and knowing if we have entries requires
     # cache lookups.
     for node in outgoing.missingheads:
         # Don't compute missing, as this may slow down serving.
         fnode = cache.getfnode(node, computemissing=False)
         if fnode is not None:
             chunks.extend([node, fnode])
 
     if chunks:
         bundler.newpart(b'hgtagsfnodes', data=b''.join(chunks))
 
 
 def addpartrevbranchcache(repo, bundler, outgoing):
     # we include the rev branch cache for the bundle changeset
     # (as an optional parts)
     cache = repo.revbranchcache()
     cl = repo.unfiltered().changelog
     branchesdata = collections.defaultdict(lambda: (set(), set()))
     for node in outgoing.missing:
         branch, close = cache.branchinfo(cl.rev(node))
         branchesdata[branch][close].add(node)
 
     def generate():
         for branch, (nodes, closed) in sorted(branchesdata.items()):
             utf8branch = encoding.fromlocal(branch)
             yield rbcstruct.pack(len(utf8branch), len(nodes), len(closed))
             yield utf8branch
             for n in sorted(nodes):
                 yield n
             for n in sorted(closed):
                 yield n
 
     bundler.newpart(b'cache:rev-branch-cache', data=generate(), mandatory=False)
 
 
 def _formatrequirementsspec(requirements):
     requirements = [req for req in requirements if req != b"shared"]
     return urlreq.quote(b','.join(sorted(requirements)))
 
 
 def _formatrequirementsparams(requirements):
     requirements = _formatrequirementsspec(requirements)
     params = b"%s%s" % (urlreq.quote(b"requirements="), requirements)
     return params
 
 
 def addpartbundlestream2(bundler, repo, **kwargs):
     if not kwargs.get('stream', False):
         return
 
     if not streamclone.allowservergeneration(repo):
         raise error.Abort(
             _(
                 b'stream data requested but server does not allow '
                 b'this feature'
             ),
             hint=_(
                 b'well-behaved clients should not be '
                 b'requesting stream data from servers not '
                 b'advertising it; the client may be buggy'
             ),
         )
 
     # Stream clones don't compress well. And compression undermines a
     # goal of stream clones, which is to be fast. Communicate the desire
     # to avoid compression to consumers of the bundle.
     bundler.prefercompressed = False
 
     # get the includes and excludes
     includepats = kwargs.get('includepats')
     excludepats = kwargs.get('excludepats')
 
     narrowstream = repo.ui.configbool(
         b'experimental', b'server.stream-narrow-clones'
     )
 
     if (includepats or excludepats) and not narrowstream:
         raise error.Abort(_(b'server does not support narrow stream clones'))
 
     includeobsmarkers = False
     if repo.obsstore:
         remoteversions = obsmarkersversion(bundler.capabilities)
         if not remoteversions:
             raise error.Abort(
                 _(
                     b'server has obsolescence markers, but client '
                     b'cannot receive them via stream clone'
                 )
             )
         elif repo.obsstore._version in remoteversions:
             includeobsmarkers = True
 
     filecount, bytecount, it = streamclone.generatev2(
         repo, includepats, excludepats, includeobsmarkers
     )
     requirements = _formatrequirementsspec(repo.requirements)
     part = bundler.newpart(b'stream2', data=it)
     part.addparam(b'bytecount', b'%d' % bytecount, mandatory=True)
     part.addparam(b'filecount', b'%d' % filecount, mandatory=True)
     part.addparam(b'requirements', requirements, mandatory=True)
 
 
 def buildobsmarkerspart(bundler, markers):
     """add an obsmarker part to the bundler with <markers>
 
     No part is created if markers is empty.
     Raises ValueError if the bundler doesn't support any known obsmarker format.
     """
     if not markers:
         return None
 
     remoteversions = obsmarkersversion(bundler.capabilities)
     version = obsolete.commonversion(remoteversions)
     if version is None:
         raise ValueError(b'bundler does not support common obsmarker format')
     stream = obsolete.encodemarkers(markers, True, version=version)
     return bundler.newpart(b'obsmarkers', data=stream)
 
 
 def writebundle(
     ui, cg, filename, bundletype, vfs=None, compression=None, compopts=None
 ):
     """Write a bundle file and return its filename.
 
     Existing files will not be overwritten.
     If no filename is specified, a temporary file is created.
     bz2 compression can be turned off.
     The bundle file will be deleted in case of errors.
     """
 
     if bundletype == b"HG20":
         bundle = bundle20(ui)
         bundle.setcompression(compression, compopts)
         part = bundle.newpart(b'changegroup', data=cg.getchunks())
         part.addparam(b'version', cg.version)
         if b'clcount' in cg.extras:
             part.addparam(
                 b'nbchanges', b'%d' % cg.extras[b'clcount'], mandatory=False
             )
         chunkiter = bundle.getchunks()
     else:
         # compression argument is only for the bundle2 case
         assert compression is None
         if cg.version != b'01':
             raise error.Abort(
                 _(b'old bundle types only supports v1 changegroups')
             )
         header, comp = bundletypes[bundletype]
         if comp not in util.compengines.supportedbundletypes:
             raise error.Abort(_(b'unknown stream compression type: %s') % comp)
         compengine = util.compengines.forbundletype(comp)
 
         def chunkiter():
             yield header
             for chunk in compengine.compressstream(cg.getchunks(), compopts):
                 yield chunk
 
         chunkiter = chunkiter()
 
     # parse the changegroup data, otherwise we will block
     # in case of sshrepo because we don't know the end of the stream
     return changegroup.writechunks(ui, chunkiter, filename, vfs=vfs)
 
 
 def combinechangegroupresults(op):
     """logic to combine 0 or more addchangegroup results into one"""
     results = [r.get(b'return', 0) for r in op.records[b'changegroup']]
     changedheads = 0
     result = 1
     for ret in results:
         # If any changegroup result is 0, return 0
         if ret == 0:
             result = 0
             break
         if ret < -1:
             changedheads += ret + 1
         elif ret > 1:
             changedheads += ret - 1
     if changedheads > 0:
         result = 1 + changedheads
     elif changedheads < 0:
         result = -1 + changedheads
     return result
 
 
 @parthandler(
     b'changegroup',
     (
         b'version',
         b'nbchanges',
         b'exp-sidedata',
         b'treemanifest',
         b'targetphase',
     ),
 )
 def handlechangegroup(op, inpart):
     """apply a changegroup part on the repo
 
     This is a very early implementation that will massive rework before being
     inflicted to any end-user.
     """
     from . import localrepo
 
     tr = op.gettransaction()
     unpackerversion = inpart.params.get(b'version', b'01')
     # We should raise an appropriate exception here
     cg = changegroup.getunbundler(unpackerversion, inpart, None)
     # the source and url passed here are overwritten by the one contained in
     # the transaction.hookargs argument. So 'bundle2' is a placeholder
     nbchangesets = None
     if b'nbchanges' in inpart.params:
         nbchangesets = int(inpart.params.get(b'nbchanges'))
     if (
         b'treemanifest' in inpart.params
         and b'treemanifest' not in op.repo.requirements
     ):
         if len(op.repo.changelog) != 0:
             raise error.Abort(
                 _(
                     b"bundle contains tree manifests, but local repo is "
                     b"non-empty and does not use tree manifests"
                 )
             )
         op.repo.requirements.add(b'treemanifest')
         op.repo.svfs.options = localrepo.resolvestorevfsoptions(
             op.repo.ui, op.repo.requirements, op.repo.features
         )
         op.repo._writerequirements()
 
     bundlesidedata = bool(b'exp-sidedata' in inpart.params)
     reposidedata = bool(b'exp-sidedata-flag' in op.repo.requirements)
     if reposidedata and not bundlesidedata:
         msg = b"repository is using sidedata but the bundle source do not"
         hint = b'this is currently unsupported'
         raise error.Abort(msg, hint=hint)
 
     extrakwargs = {}
     targetphase = inpart.params.get(b'targetphase')
     if targetphase is not None:
         extrakwargs['targetphase'] = int(targetphase)
     ret = _processchangegroup(
         op,
         cg,
         tr,
         b'bundle2',
         b'bundle2',
         expectedtotal=nbchangesets,
         **extrakwargs
     )
     if op.reply is not None:
         # This is definitely not the final form of this
         # return. But one need to start somewhere.
         part = op.reply.newpart(b'reply:changegroup', mandatory=False)
         part.addparam(
             b'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False
         )
         part.addparam(b'return', b'%i' % ret, mandatory=False)
     assert not inpart.read()
 
 
 _remotechangegroupparams = tuple(
     [b'url', b'size', b'digests']
     + [b'digest:%s' % k for k in util.DIGESTS.keys()]
 )
 
 
 @parthandler(b'remote-changegroup', _remotechangegroupparams)
 def handleremotechangegroup(op, inpart):
     """apply a bundle10 on the repo, given an url and validation information
 
     All the information about the remote bundle to import are given as
     parameters. The parameters include:
       - url: the url to the bundle10.
       - size: the bundle10 file size. It is used to validate what was
         retrieved by the client matches the server knowledge about the bundle.
       - digests: a space separated list of the digest types provided as
         parameters.
       - digest:<digest-type>: the hexadecimal representation of the digest with
         that name. Like the size, it is used to validate what was retrieved by
         the client matches what the server knows about the bundle.
 
     When multiple digest types are given, all of them are checked.
     """
     try:
         raw_url = inpart.params[b'url']
     except KeyError:
         raise error.Abort(_(b'remote-changegroup: missing "%s" param') % b'url')
     parsed_url = util.url(raw_url)
     if parsed_url.scheme not in capabilities[b'remote-changegroup']:
         raise error.Abort(
             _(b'remote-changegroup does not support %s urls')
             % parsed_url.scheme
         )
 
     try:
         size = int(inpart.params[b'size'])
     except ValueError:
         raise error.Abort(
             _(b'remote-changegroup: invalid value for param "%s"') % b'size'
         )
     except KeyError:
         raise error.Abort(
             _(b'remote-changegroup: missing "%s" param') % b'size'
         )
 
     digests = {}
     for typ in inpart.params.get(b'digests', b'').split():
         param = b'digest:%s' % typ
         try:
             value = inpart.params[param]
         except KeyError:
             raise error.Abort(
                 _(b'remote-changegroup: missing "%s" param') % param
             )
         digests[typ] = value
 
     real_part = util.digestchecker(url.open(op.ui, raw_url), size, digests)
 
     tr = op.gettransaction()
     from . import exchange
 
     cg = exchange.readbundle(op.repo.ui, real_part, raw_url)
     if not isinstance(cg, changegroup.cg1unpacker):
         raise error.Abort(
             _(b'%s: not a bundle version 1.0') % util.hidepassword(raw_url)
         )
     ret = _processchangegroup(op, cg, tr, b'bundle2', b'bundle2')
     if op.reply is not None:
         # This is definitely not the final form of this
         # return. But one need to start somewhere.
         part = op.reply.newpart(b'reply:changegroup')
         part.addparam(
             b'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False
         )
         part.addparam(b'return', b'%i' % ret, mandatory=False)
     try:
         real_part.validate()
     except error.Abort as e:
         raise error.Abort(
             _(b'bundle at %s is corrupted:\n%s')
             % (util.hidepassword(raw_url), bytes(e))
         )
     assert not inpart.read()
 
 
 @parthandler(b'reply:changegroup', (b'return', b'in-reply-to'))
 def handlereplychangegroup(op, inpart):
     ret = int(inpart.params[b'return'])
     replyto = int(inpart.params[b'in-reply-to'])
     op.records.add(b'changegroup', {b'return': ret}, replyto)
 
 
 @parthandler(b'check:bookmarks')
 def handlecheckbookmarks(op, inpart):
     """check location of bookmarks
 
     This part is to be used to detect push race regarding bookmark, it
     contains binary encoded (bookmark, node) tuple. If the local state does
     not marks the one in the part, a PushRaced exception is raised
     """
     bookdata = bookmarks.binarydecode(inpart)
 
     msgstandard = (
         b'remote repository changed while pushing - please try again '
         b'(bookmark "%s" move from %s to %s)'
     )
     msgmissing = (
         b'remote repository changed while pushing - please try again '
         b'(bookmark "%s" is missing, expected %s)'
     )
     msgexist = (
         b'remote repository changed while pushing - please try again '
         b'(bookmark "%s" set on %s, expected missing)'
     )
     for book, node in bookdata:
         currentnode = op.repo._bookmarks.get(book)
         if currentnode != node:
             if node is None:
                 finalmsg = msgexist % (book, nodemod.short(currentnode))
             elif currentnode is None:
                 finalmsg = msgmissing % (book, nodemod.short(node))
             else:
                 finalmsg = msgstandard % (
                     book,
                     nodemod.short(node),
                     nodemod.short(currentnode),
                 )
             raise error.PushRaced(finalmsg)
 
 
 @parthandler(b'check:heads')
 def handlecheckheads(op, inpart):
     """check that head of the repo did not change
 
     This is used to detect a push race when using unbundle.
     This replaces the "heads" argument of unbundle."""
     h = inpart.read(20)
     heads = []
     while len(h) == 20:
         heads.append(h)
         h = inpart.read(20)
     assert not h
     # Trigger a transaction so that we are guaranteed to have the lock now.
     if op.ui.configbool(b'experimental', b'bundle2lazylocking'):
         op.gettransaction()
     if sorted(heads) != sorted(op.repo.heads()):
         raise error.PushRaced(
             b'remote repository changed while pushing - please try again'
         )
 
 
 @parthandler(b'check:updated-heads')
 def handlecheckupdatedheads(op, inpart):
     """check for race on the heads touched by a push
 
     This is similar to 'check:heads' but focus on the heads actually updated
     during the push. If other activities happen on unrelated heads, it is
     ignored.
 
     This allow server with high traffic to avoid push contention as long as
     unrelated parts of the graph are involved."""
     h = inpart.read(20)
     heads = []
     while len(h) == 20:
         heads.append(h)
         h = inpart.read(20)
     assert not h
     # trigger a transaction so that we are guaranteed to have the lock now.
     if op.ui.configbool(b'experimental', b'bundle2lazylocking'):
         op.gettransaction()
 
     currentheads = set()
     for ls in op.repo.branchmap().iterheads():
         currentheads.update(ls)
 
     for h in heads:
         if h not in currentheads:
             raise error.PushRaced(
                 b'remote repository changed while pushing - '
                 b'please try again'
             )
 
 
 @parthandler(b'check:phases')
 def handlecheckphases(op, inpart):
     """check that phase boundaries of the repository did not change
 
     This is used to detect a push race.
     """
     phasetonodes = phases.binarydecode(inpart)
     unfi = op.repo.unfiltered()
     cl = unfi.changelog
     phasecache = unfi._phasecache
     msg = (
         b'remote repository changed while pushing - please try again '
         b'(%s is %s expected %s)'
     )
     for expectedphase, nodes in enumerate(phasetonodes):
         for n in nodes:
             actualphase = phasecache.phase(unfi, cl.rev(n))
             if actualphase != expectedphase:
                 finalmsg = msg % (
                     nodemod.short(n),
                     phases.phasenames[actualphase],
                     phases.phasenames[expectedphase],
                 )
                 raise error.PushRaced(finalmsg)
 
 
 @parthandler(b'output')
 def handleoutput(op, inpart):
     """forward output captured on the server to the client"""
     for line in inpart.read().splitlines():
         op.ui.status(_(b'remote: %s\n') % line)
 
 
 @parthandler(b'replycaps')
 def handlereplycaps(op, inpart):
     """Notify that a reply bundle should be created
 
     The payload contains the capabilities information for the reply"""
     caps = decodecaps(inpart.read())
     if op.reply is None:
         op.reply = bundle20(op.ui, caps)
 
 
 class AbortFromPart(error.Abort):
     """Sub-class of Abort that denotes an error from a bundle2 part."""
 
 
 @parthandler(b'error:abort', (b'message', b'hint'))
 def handleerrorabort(op, inpart):
     """Used to transmit abort error over the wire"""
     raise AbortFromPart(
         inpart.params[b'message'], hint=inpart.params.get(b'hint')
     )
 
 
 @parthandler(
     b'error:pushkey',
     (b'namespace', b'key', b'new', b'old', b'ret', b'in-reply-to'),
 )
 def handleerrorpushkey(op, inpart):
     """Used to transmit failure of a mandatory pushkey over the wire"""
     kwargs = {}
     for name in (b'namespace', b'key', b'new', b'old', b'ret'):
         value = inpart.params.get(name)
         if value is not None:
             kwargs[name] = value
     raise error.PushkeyFailed(
         inpart.params[b'in-reply-to'], **pycompat.strkwargs(kwargs)
     )
 
 
 @parthandler(b'error:unsupportedcontent', (b'parttype', b'params'))
 def handleerrorunsupportedcontent(op, inpart):
     """Used to transmit unknown content error over the wire"""
     kwargs = {}
     parttype = inpart.params.get(b'parttype')
     if parttype is not None:
         kwargs[b'parttype'] = parttype
     params = inpart.params.get(b'params')
     if params is not None:
         kwargs[b'params'] = params.split(b'\0')
 
     raise error.BundleUnknownFeatureError(**pycompat.strkwargs(kwargs))
 
 
 @parthandler(b'error:pushraced', (b'message',))
 def handleerrorpushraced(op, inpart):
     """Used to transmit push race error over the wire"""
     raise error.ResponseError(_(b'push failed:'), inpart.params[b'message'])
 
 
 @parthandler(b'listkeys', (b'namespace',))
 def handlelistkeys(op, inpart):
     """retrieve pushkey namespace content stored in a bundle2"""
     namespace = inpart.params[b'namespace']
     r = pushkey.decodekeys(inpart.read())
     op.records.add(b'listkeys', (namespace, r))
 
 
 @parthandler(b'pushkey', (b'namespace', b'key', b'old', b'new'))
 def handlepushkey(op, inpart):
     """process a pushkey request"""
     dec = pushkey.decode
     namespace = dec(inpart.params[b'namespace'])
     key = dec(inpart.params[b'key'])
     old = dec(inpart.params[b'old'])
     new = dec(inpart.params[b'new'])
     # Grab the transaction to ensure that we have the lock before performing the
     # pushkey.
     if op.ui.configbool(b'experimental', b'bundle2lazylocking'):
         op.gettransaction()
     ret = op.repo.pushkey(namespace, key, old, new)
     record = {b'namespace': namespace, b'key': key, b'old': old, b'new': new}
     op.records.add(b'pushkey', record)
     if op.reply is not None:
         rpart = op.reply.newpart(b'reply:pushkey')
         rpart.addparam(
             b'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False
         )
         rpart.addparam(b'return', b'%i' % ret, mandatory=False)
     if inpart.mandatory and not ret:
         kwargs = {}
         for key in (b'namespace', b'key', b'new', b'old', b'ret'):
             if key in inpart.params:
                 kwargs[key] = inpart.params[key]
         raise error.PushkeyFailed(
             partid=b'%d' % inpart.id, **pycompat.strkwargs(kwargs)
         )
 
 
 @parthandler(b'bookmarks')
 def handlebookmark(op, inpart):
     """transmit bookmark information
 
     The part contains binary encoded bookmark information.
 
     The exact behavior of this part can be controlled by the 'bookmarks' mode
     on the bundle operation.
 
     When mode is 'apply' (the default) the bookmark information is applied as
     is to the unbundling repository. Make sure a 'check:bookmarks' part is
     issued earlier to check for push races in such update. This behavior is
     suitable for pushing.
 
     When mode is 'records', the information is recorded into the 'bookmarks'
     records of the bundle operation. This behavior is suitable for pulling.
     """
     changes = bookmarks.binarydecode(inpart)
 
     pushkeycompat = op.repo.ui.configbool(
         b'server', b'bookmarks-pushkey-compat'
     )
     bookmarksmode = op.modes.get(b'bookmarks', b'apply')
 
     if bookmarksmode == b'apply':
         tr = op.gettransaction()
         bookstore = op.repo._bookmarks
         if pushkeycompat:
             allhooks = []
             for book, node in changes:
                 hookargs = tr.hookargs.copy()
                 hookargs[b'pushkeycompat'] = b'1'
                 hookargs[b'namespace'] = b'bookmarks'
                 hookargs[b'key'] = book
                 hookargs[b'old'] = nodemod.hex(bookstore.get(book, b''))
                 hookargs[b'new'] = nodemod.hex(
                     node if node is not None else b''
                 )
                 allhooks.append(hookargs)
 
             for hookargs in allhooks:
                 op.repo.hook(
                     b'prepushkey', throw=True, **pycompat.strkwargs(hookargs)
                 )
 
         bookstore.applychanges(op.repo, op.gettransaction(), changes)
 
         if pushkeycompat:
 
             def runhook(unused_success):
                 for hookargs in allhooks:
                     op.repo.hook(b'pushkey', **pycompat.strkwargs(hookargs))
 
             op.repo._afterlock(runhook)
 
     elif bookmarksmode == b'records':
         for book, node in changes:
             record = {b'bookmark': book, b'node': node}
             op.records.add(b'bookmarks', record)
     else:
         raise error.ProgrammingError(
             b'unkown bookmark mode: %s' % bookmarksmode
         )
 
 
 @parthandler(b'phase-heads')
 def handlephases(op, inpart):
     """apply phases from bundle part to repo"""
     headsbyphase = phases.binarydecode(inpart)
     phases.updatephases(op.repo.unfiltered(), op.gettransaction, headsbyphase)
 
 
 @parthandler(b'reply:pushkey', (b'return', b'in-reply-to'))
 def handlepushkeyreply(op, inpart):
     """retrieve the result of a pushkey request"""
     ret = int(inpart.params[b'return'])
     partid = int(inpart.params[b'in-reply-to'])
     op.records.add(b'pushkey', {b'return': ret}, partid)
 
 
 @parthandler(b'obsmarkers')
 def handleobsmarker(op, inpart):
     """add a stream of obsmarkers to the repo"""
     tr = op.gettransaction()
     markerdata = inpart.read()
     if op.ui.config(b'experimental', b'obsmarkers-exchange-debug'):
         op.ui.writenoi18n(
             b'obsmarker-exchange: %i bytes received\n' % len(markerdata)
         )
     # The mergemarkers call will crash if marker creation is not enabled.
     # we want to avoid this if the part is advisory.
     if not inpart.mandatory and op.repo.obsstore.readonly:
         op.repo.ui.debug(
             b'ignoring obsolescence markers, feature not enabled\n'
         )
         return
     new = op.repo.obsstore.mergemarkers(tr, markerdata)
     op.repo.invalidatevolatilesets()
     op.records.add(b'obsmarkers', {b'new': new})
     if op.reply is not None:
         rpart = op.reply.newpart(b'reply:obsmarkers')
         rpart.addparam(
             b'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False
         )
         rpart.addparam(b'new', b'%i' % new, mandatory=False)
 
 
 @parthandler(b'reply:obsmarkers', (b'new', b'in-reply-to'))
 def handleobsmarkerreply(op, inpart):
     """retrieve the result of a pushkey request"""
     ret = int(inpart.params[b'new'])
     partid = int(inpart.params[b'in-reply-to'])
     op.records.add(b'obsmarkers', {b'new': ret}, partid)
 
 
 @parthandler(b'hgtagsfnodes')
 def handlehgtagsfnodes(op, inpart):
     """Applies .hgtags fnodes cache entries to the local repo.
 
     Payload is pairs of 20 byte changeset nodes and filenodes.
     """
     # Grab the transaction so we ensure that we have the lock at this point.
     if op.ui.configbool(b'experimental', b'bundle2lazylocking'):
         op.gettransaction()
     cache = tags.hgtagsfnodescache(op.repo.unfiltered())
 
     count = 0
     while True:
         node = inpart.read(20)
         fnode = inpart.read(20)
         if len(node) < 20 or len(fnode) < 20:
             op.ui.debug(b'ignoring incomplete received .hgtags fnodes data\n')
             break
         cache.setfnode(node, fnode)
         count += 1
 
     cache.write()
     op.ui.debug(b'applied %i hgtags fnodes cache entries\n' % count)
 
 
 rbcstruct = struct.Struct(b'>III')
 
 
 @parthandler(b'cache:rev-branch-cache')
 def handlerbc(op, inpart):
     """receive a rev-branch-cache payload and update the local cache
 
     The payload is a series of data related to each branch
 
     1) branch name length
     2) number of open heads
     3) number of closed heads
     4) open heads nodes
     5) closed heads nodes
     """
     total = 0
     rawheader = inpart.read(rbcstruct.size)
     cache = op.repo.revbranchcache()
     cl = op.repo.unfiltered().changelog
     while rawheader:
         header = rbcstruct.unpack(rawheader)
         total += header[1] + header[2]
         utf8branch = inpart.read(header[0])
         branch = encoding.tolocal(utf8branch)
         for x in pycompat.xrange(header[1]):
             node = inpart.read(20)
             rev = cl.rev(node)
             cache.setdata(branch, rev, node, False)
         for x in pycompat.xrange(header[2]):
             node = inpart.read(20)
             rev = cl.rev(node)
             cache.setdata(branch, rev, node, True)
         rawheader = inpart.read(rbcstruct.size)
     cache.write()
 
 
 @parthandler(b'pushvars')
 def bundle2getvars(op, part):
     '''unbundle a bundle2 containing shellvars on the server'''
     # An option to disable unbundling on server-side for security reasons
     if op.ui.configbool(b'push', b'pushvars.server'):
         hookargs = {}
         for key, value in part.advisoryparams:
             key = key.upper()
             # We want pushed variables to have USERVAR_ prepended so we know
             # they came from the --pushvar flag.
             key = b"USERVAR_" + key
             hookargs[key] = value
         op.addhookargs(hookargs)
 
 
 @parthandler(b'stream2', (b'requirements', b'filecount', b'bytecount'))
 def handlestreamv2bundle(op, part):
 
     requirements = urlreq.unquote(part.params[b'requirements']).split(b',')
     filecount = int(part.params[b'filecount'])
     bytecount = int(part.params[b'bytecount'])
 
     repo = op.repo
     if len(repo):
         msg = _(b'cannot apply stream clone to non empty repository')
         raise error.Abort(msg)
 
     repo.ui.debug(b'applying stream bundle\n')
     streamclone.applybundlev2(repo, part, filecount, bytecount, requirements)
 
 
 def widen_bundle(
     bundler, repo, oldmatcher, newmatcher, common, known, cgversion, ellipses
 ):
     """generates bundle2 for widening a narrow clone
 
     bundler is the bundle to which data should be added
     repo is the localrepository instance
     oldmatcher matches what the client already has
     newmatcher matches what the client needs (including what it already has)
     common is set of common heads between server and client
     known is a set of revs known on the client side (used in ellipses)
     cgversion is the changegroup version to send
     ellipses is boolean value telling whether to send ellipses data or not
 
     returns bundle2 of the data required for extending
     """
     commonnodes = set()
     cl = repo.changelog
     for r in repo.revs(b"::%ln", common):
         commonnodes.add(cl.node(r))
     if commonnodes:
         # XXX: we should only send the filelogs (and treemanifest). user
         # already has the changelog and manifest
         packer = changegroup.getbundler(
             cgversion,
             repo,
             oldmatcher=oldmatcher,
             matcher=newmatcher,
             fullnodes=commonnodes,
         )
         cgdata = packer.generate(
             {nodemod.nullid},
             list(commonnodes),
             False,
             b'narrow_widen',
             changelog=False,
         )
 
         part = bundler.newpart(b'changegroup', data=cgdata)
         part.addparam(b'version', cgversion)
         if b'treemanifest' in repo.requirements:
             part.addparam(b'treemanifest', b'1')
         if b'exp-sidedata-flag' in repo.requirements:
             part.addparam(b'exp-sidedata', b'1')
 
     return bundler

mercurial/dispatch.py

@@ -1,1282 +1,1286 b''
 # dispatch.py - command dispatching for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # 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, print_function
 
 import difflib
 import errno
 import getopt
 import os
 import pdb
 import re
 import signal
 import sys
 import traceback
 
 
 from .i18n import _
 from .pycompat import getattr
 
 from hgdemandimport import tracing
 
 from . import (
     cmdutil,
     color,
     commands,
     demandimport,
     encoding,
     error,
     extensions,
     fancyopts,
     help,
     hg,
     hook,
     profiling,
     pycompat,
+    rcutil,
     registrar,
     scmutil,
     ui as uimod,
     util,
 )
 
 from .utils import (
     procutil,
     stringutil,
 )
 
 
 class request(object):
     def __init__(
         self,
         args,
         ui=None,
         repo=None,
         fin=None,
         fout=None,
         ferr=None,
         fmsg=None,
         prereposetups=None,
     ):
         self.args = args
         self.ui = ui
         self.repo = repo
 
         # input/output/error streams
         self.fin = fin
         self.fout = fout
         self.ferr = ferr
         # separate stream for status/error messages
         self.fmsg = fmsg
 
         # remember options pre-parsed by _earlyparseopts()
         self.earlyoptions = {}
 
         # reposetups which run before extensions, useful for chg to pre-fill
         # low-level repo state (for example, changelog) before extensions.
         self.prereposetups = prereposetups or []
 
         # store the parsed and canonical command
         self.canonical_command = None
 
     def _runexithandlers(self):
         exc = None
         handlers = self.ui._exithandlers
         try:
             while handlers:
                 func, args, kwargs = handlers.pop()
                 try:
                     func(*args, **kwargs)
                 except:  # re-raises below
                     if exc is None:
                         exc = sys.exc_info()[1]
                     self.ui.warnnoi18n(b'error in exit handlers:\n')
                     self.ui.traceback(force=True)
         finally:
             if exc is not None:
                 raise exc
 
 
 def run():
     """run the command in sys.argv"""
     initstdio()
     with tracing.log('parse args into request'):
         req = request(pycompat.sysargv[1:])
     err = None
     try:
         status = dispatch(req)
     except error.StdioError as e:
         err = e
         status = -1
 
     # In all cases we try to flush stdio streams.
     if util.safehasattr(req.ui, b'fout'):
         assert req.ui is not None  # help pytype
         assert req.ui.fout is not None  # help pytype
         try:
             req.ui.fout.flush()
         except IOError as e:
             err = e
             status = -1
 
     if util.safehasattr(req.ui, b'ferr'):
         assert req.ui is not None  # help pytype
         assert req.ui.ferr is not None  # help pytype
         try:
             if err is not None and err.errno != errno.EPIPE:
                 req.ui.ferr.write(
                     b'abort: %s\n' % encoding.strtolocal(err.strerror)
                 )
             req.ui.ferr.flush()
         # There's not much we can do about an I/O error here. So (possibly)
         # change the status code and move on.
         except IOError:
             status = -1
 
     _silencestdio()
     sys.exit(status & 255)
 
 
 if pycompat.ispy3:
 
     def initstdio():
         pass
 
     def _silencestdio():
         for fp in (sys.stdout, sys.stderr):
             # Check if the file is okay
             try:
                 fp.flush()
                 continue
             except IOError:
                 pass
             # Otherwise mark it as closed to silence "Exception ignored in"
             # message emitted by the interpreter finalizer. Be careful to
             # not close procutil.stdout, which may be a fdopen-ed file object
             # and its close() actually closes the underlying file descriptor.
             try:
                 fp.close()
             except IOError:
                 pass
 
 
 else:
 
     def initstdio():
         for fp in (sys.stdin, sys.stdout, sys.stderr):
             procutil.setbinary(fp)
 
     def _silencestdio():
         pass
 
 
 def _getsimilar(symbols, value):
     sim = lambda x: difflib.SequenceMatcher(None, value, x).ratio()
     # The cutoff for similarity here is pretty arbitrary. It should
     # probably be investigated and tweaked.
     return [s for s in symbols if sim(s) > 0.6]
 
 
 def _reportsimilar(write, similar):
     if len(similar) == 1:
         write(_(b"(did you mean %s?)\n") % similar[0])
     elif similar:
         ss = b", ".join(sorted(similar))
         write(_(b"(did you mean one of %s?)\n") % ss)
 
 
 def _formatparse(write, inst):
     similar = []
     if isinstance(inst, error.UnknownIdentifier):
         # make sure to check fileset first, as revset can invoke fileset
         similar = _getsimilar(inst.symbols, inst.function)
     if len(inst.args) > 1:
         write(
             _(b"hg: parse error at %s: %s\n")
             % (pycompat.bytestr(inst.args[1]), inst.args[0])
         )
         if inst.args[0].startswith(b' '):
             write(_(b"unexpected leading whitespace\n"))
     else:
         write(_(b"hg: parse error: %s\n") % inst.args[0])
         _reportsimilar(write, similar)
     if inst.hint:
         write(_(b"(%s)\n") % inst.hint)
 
 
 def _formatargs(args):
     return b' '.join(procutil.shellquote(a) for a in args)
 
 
 def dispatch(req):
     """run the command specified in req.args; returns an integer status code"""
     with tracing.log('dispatch.dispatch'):
         if req.ferr:
             ferr = req.ferr
         elif req.ui:
             ferr = req.ui.ferr
         else:
             ferr = procutil.stderr
 
         try:
             if not req.ui:
                 req.ui = uimod.ui.load()
             req.earlyoptions.update(_earlyparseopts(req.ui, req.args))
             if req.earlyoptions[b'traceback']:
                 req.ui.setconfig(b'ui', b'traceback', b'on', b'--traceback')
 
             # set ui streams from the request
             if req.fin:
                 req.ui.fin = req.fin
             if req.fout:
                 req.ui.fout = req.fout
             if req.ferr:
                 req.ui.ferr = req.ferr
             if req.fmsg:
                 req.ui.fmsg = req.fmsg
         except error.Abort as inst:
             ferr.write(_(b"abort: %s\n") % inst)
             if inst.hint:
                 ferr.write(_(b"(%s)\n") % inst.hint)
             return -1
         except error.ParseError as inst:
             _formatparse(ferr.write, inst)
             return -1
 
         msg = _formatargs(req.args)
         starttime = util.timer()
         ret = 1  # default of Python exit code on unhandled exception
         try:
             ret = _runcatch(req) or 0
         except error.ProgrammingError as inst:
             req.ui.error(_(b'** ProgrammingError: %s\n') % inst)
             if inst.hint:
                 req.ui.error(_(b'** (%s)\n') % inst.hint)
             raise
         except KeyboardInterrupt as inst:
             try:
                 if isinstance(inst, error.SignalInterrupt):
                     msg = _(b"killed!\n")
                 else:
                     msg = _(b"interrupted!\n")
                 req.ui.error(msg)
             except error.SignalInterrupt:
                 # maybe pager would quit without consuming all the output, and
                 # SIGPIPE was raised. we cannot print anything in this case.
                 pass
             except IOError as inst:
                 if inst.errno != errno.EPIPE:
                     raise
             ret = -1
         finally:
             duration = util.timer() - starttime
             req.ui.flush()
             if req.ui.logblockedtimes:
                 req.ui._blockedtimes[b'command_duration'] = duration * 1000
                 req.ui.log(
                     b'uiblocked',
                     b'ui blocked ms\n',
                     **pycompat.strkwargs(req.ui._blockedtimes)
                 )
             return_code = ret & 255
             req.ui.log(
                 b"commandfinish",
                 b"%s exited %d after %0.2f seconds\n",
                 msg,
                 return_code,
                 duration,
                 return_code=return_code,
                 duration=duration,
                 canonical_command=req.canonical_command,
             )
             try:
                 req._runexithandlers()
             except:  # exiting, so no re-raises
                 ret = ret or -1
         return ret
 
 
 def _runcatch(req):
     with tracing.log('dispatch._runcatch'):
 
         def catchterm(*args):
             raise error.SignalInterrupt
 
         ui = req.ui
         try:
             for name in b'SIGBREAK', b'SIGHUP', b'SIGTERM':
                 num = getattr(signal, name, None)
                 if num:
                     signal.signal(num, catchterm)
         except ValueError:
             pass  # happens if called in a thread
 
         def _runcatchfunc():
             realcmd = None
             try:
                 cmdargs = fancyopts.fancyopts(
                     req.args[:], commands.globalopts, {}
                 )
                 cmd = cmdargs[0]
                 aliases, entry = cmdutil.findcmd(cmd, commands.table, False)
                 realcmd = aliases[0]
             except (
                 error.UnknownCommand,
                 error.AmbiguousCommand,
                 IndexError,
                 getopt.GetoptError,
             ):
                 # Don't handle this here. We know the command is
                 # invalid, but all we're worried about for now is that
                 # it's not a command that server operators expect to
                 # be safe to offer to users in a sandbox.
                 pass
             if realcmd == b'serve' and b'--stdio' in cmdargs:
                 # We want to constrain 'hg serve --stdio' instances pretty
                 # closely, as many shared-ssh access tools want to grant
                 # access to run *only* 'hg -R $repo serve --stdio'. We
                 # restrict to exactly that set of arguments, and prohibit
                 # any repo name that starts with '--' to prevent
                 # shenanigans wherein a user does something like pass
                 # --debugger or --config=ui.debugger=1 as a repo
                 # name. This used to actually run the debugger.
                 if (
                     len(req.args) != 4
                     or req.args[0] != b'-R'
                     or req.args[1].startswith(b'--')
                     or req.args[2] != b'serve'
                     or req.args[3] != b'--stdio'
                 ):
                     raise error.Abort(
                         _(b'potentially unsafe serve --stdio invocation: %s')
                         % (stringutil.pprint(req.args),)
                     )
 
             try:
                 debugger = b'pdb'
                 debugtrace = {b'pdb': pdb.set_trace}
                 debugmortem = {b'pdb': pdb.post_mortem}
 
                 # read --config before doing anything else
                 # (e.g. to change trust settings for reading .hg/hgrc)
                 cfgs = _parseconfig(req.ui, req.earlyoptions[b'config'])
 
                 if req.repo:
                     # copy configs that were passed on the cmdline (--config) to
                     # the repo ui
                     for sec, name, val in cfgs:
                         req.repo.ui.setconfig(
                             sec, name, val, source=b'--config'
                         )
 
                 # developer config: ui.debugger
                 debugger = ui.config(b"ui", b"debugger")
                 debugmod = pdb
                 if not debugger or ui.plain():
                     # if we are in HGPLAIN mode, then disable custom debugging
                     debugger = b'pdb'
                 elif req.earlyoptions[b'debugger']:
                     # This import can be slow for fancy debuggers, so only
                     # do it when absolutely necessary, i.e. when actual
                     # debugging has been requested
                     with demandimport.deactivated():
                         try:
                             debugmod = __import__(debugger)
                         except ImportError:
                             pass  # Leave debugmod = pdb
 
                 debugtrace[debugger] = debugmod.set_trace
                 debugmortem[debugger] = debugmod.post_mortem
 
                 # enter the debugger before command execution
                 if req.earlyoptions[b'debugger']:
                     ui.warn(
                         _(
                             b"entering debugger - "
                             b"type c to continue starting hg or h for help\n"
                         )
                     )
 
                     if (
                         debugger != b'pdb'
                         and debugtrace[debugger] == debugtrace[b'pdb']
                     ):
                         ui.warn(
                             _(
                                 b"%s debugger specified "
                                 b"but its module was not found\n"
                             )
                             % debugger
                         )
                     with demandimport.deactivated():
                         debugtrace[debugger]()
                 try:
                     return _dispatch(req)
                 finally:
                     ui.flush()
             except:  # re-raises
                 # enter the debugger when we hit an exception
                 if req.earlyoptions[b'debugger']:
                     traceback.print_exc()
                     debugmortem[debugger](sys.exc_info()[2])
                 raise
 
         return _callcatch(ui, _runcatchfunc)
 
 
 def _callcatch(ui, func):
     """like scmutil.callcatch but handles more high-level exceptions about
     config parsing and commands. besides, use handlecommandexception to handle
     uncaught exceptions.
     """
     try:
         return scmutil.callcatch(ui, func)
     except error.AmbiguousCommand as inst:
         ui.warn(
             _(b"hg: command '%s' is ambiguous:\n    %s\n")
             % (inst.args[0], b" ".join(inst.args[1]))
         )
     except error.CommandError as inst:
         if inst.args[0]:
             ui.pager(b'help')
             msgbytes = pycompat.bytestr(inst.args[1])
             ui.warn(_(b"hg %s: %s\n") % (inst.args[0], msgbytes))
             commands.help_(ui, inst.args[0], full=False, command=True)
         else:
             ui.warn(_(b"hg: %s\n") % inst.args[1])
             ui.warn(_(b"(use 'hg help -v' for a list of global options)\n"))
     except error.ParseError as inst:
         _formatparse(ui.warn, inst)
         return -1
     except error.UnknownCommand as inst:
         nocmdmsg = _(b"hg: unknown command '%s'\n") % inst.args[0]
         try:
             # check if the command is in a disabled extension
             # (but don't check for extensions themselves)
             formatted = help.formattedhelp(
                 ui, commands, inst.args[0], unknowncmd=True
             )
             ui.warn(nocmdmsg)
             ui.write(formatted)
         except (error.UnknownCommand, error.Abort):
             suggested = False
             if len(inst.args) == 2:
                 sim = _getsimilar(inst.args[1], inst.args[0])
                 if sim:
                     ui.warn(nocmdmsg)
                     _reportsimilar(ui.warn, sim)
                     suggested = True
             if not suggested:
                 ui.warn(nocmdmsg)
                 ui.warn(_(b"(use 'hg help' for a list of commands)\n"))
     except IOError:
         raise
     except KeyboardInterrupt:
         raise
     except:  # probably re-raises
         if not handlecommandexception(ui):
             raise
 
     return -1
 
 
 def aliasargs(fn, givenargs):
     args = []
     # only care about alias 'args', ignore 'args' set by extensions.wrapfunction
     if not util.safehasattr(fn, b'_origfunc'):
         args = getattr(fn, 'args', args)
     if args:
         cmd = b' '.join(map(procutil.shellquote, args))
 
         nums = []
 
         def replacer(m):
             num = int(m.group(1)) - 1
             nums.append(num)
             if num < len(givenargs):
                 return givenargs[num]
             raise error.Abort(_(b'too few arguments for command alias'))
 
         cmd = re.sub(br'\$(\d+|\$)', replacer, cmd)
         givenargs = [x for i, x in enumerate(givenargs) if i not in nums]
         args = pycompat.shlexsplit(cmd)
     return args + givenargs
 
 
 def aliasinterpolate(name, args, cmd):
     '''interpolate args into cmd for shell aliases
 
     This also handles $0, $@ and "$@".
     '''
     # util.interpolate can't deal with "$@" (with quotes) because it's only
     # built to match prefix + patterns.
     replacemap = dict((b'$%d' % (i + 1), arg) for i, arg in enumerate(args))
     replacemap[b'$0'] = name
     replacemap[b'$$'] = b'$'
     replacemap[b'$@'] = b' '.join(args)
     # Typical Unix shells interpolate "$@" (with quotes) as all the positional
     # parameters, separated out into words. Emulate the same behavior here by
     # quoting the arguments individually. POSIX shells will then typically
     # tokenize each argument into exactly one word.
     replacemap[b'"$@"'] = b' '.join(procutil.shellquote(arg) for arg in args)
     # escape '\$' for regex
     regex = b'|'.join(replacemap.keys()).replace(b'$', br'\$')
     r = re.compile(regex)
     return r.sub(lambda x: replacemap[x.group()], cmd)
 
 
 class cmdalias(object):
     def __init__(self, ui, name, definition, cmdtable, source):
         self.name = self.cmd = name
         self.cmdname = b''
         self.definition = definition
         self.fn = None
         self.givenargs = []
         self.opts = []
         self.help = b''
         self.badalias = None
         self.unknowncmd = False
         self.source = source
 
         try:
             aliases, entry = cmdutil.findcmd(self.name, cmdtable)
             for alias, e in pycompat.iteritems(cmdtable):
                 if e is entry:
                     self.cmd = alias
                     break
             self.shadows = True
         except error.UnknownCommand:
             self.shadows = False
 
         if not self.definition:
             self.badalias = _(b"no definition for alias '%s'") % self.name
             return
 
         if self.definition.startswith(b'!'):
             shdef = self.definition[1:]
             self.shell = True
 
             def fn(ui, *args):
                 env = {b'HG_ARGS': b' '.join((self.name,) + args)}
 
                 def _checkvar(m):
                     if m.groups()[0] == b'$':
                         return m.group()
                     elif int(m.groups()[0]) <= len(args):
                         return m.group()
                     else:
                         ui.debug(
                             b"No argument found for substitution "
                             b"of %i variable in alias '%s' definition.\n"
                             % (int(m.groups()[0]), self.name)
                         )
                         return b''
 
                 cmd = re.sub(br'\$(\d+|\$)', _checkvar, shdef)
                 cmd = aliasinterpolate(self.name, args, cmd)
                 return ui.system(
                     cmd, environ=env, blockedtag=b'alias_%s' % self.name
                 )
 
             self.fn = fn
             self.alias = True
             self._populatehelp(ui, name, shdef, self.fn)
             return
 
         try:
             args = pycompat.shlexsplit(self.definition)
         except ValueError as inst:
             self.badalias = _(b"error in definition for alias '%s': %s") % (
                 self.name,
                 stringutil.forcebytestr(inst),
             )
             return
         earlyopts, args = _earlysplitopts(args)
         if earlyopts:
             self.badalias = _(
                 b"error in definition for alias '%s': %s may "
                 b"only be given on the command line"
             ) % (self.name, b'/'.join(pycompat.ziplist(*earlyopts)[0]))
             return
         self.cmdname = cmd = args.pop(0)
         self.givenargs = args
 
         try:
             tableentry = cmdutil.findcmd(cmd, cmdtable, False)[1]
             if len(tableentry) > 2:
                 self.fn, self.opts, cmdhelp = tableentry
             else:
                 self.fn, self.opts = tableentry
                 cmdhelp = None
 
             self.alias = True
             self._populatehelp(ui, name, cmd, self.fn, cmdhelp)
 
         except error.UnknownCommand:
             self.badalias = _(
                 b"alias '%s' resolves to unknown command '%s'"
             ) % (self.name, cmd,)
             self.unknowncmd = True
         except error.AmbiguousCommand:
             self.badalias = _(
                 b"alias '%s' resolves to ambiguous command '%s'"
             ) % (self.name, cmd)
 
     def _populatehelp(self, ui, name, cmd, fn, defaulthelp=None):
         # confine strings to be passed to i18n.gettext()
         cfg = {}
         for k in (b'doc', b'help', b'category'):
             v = ui.config(b'alias', b'%s:%s' % (name, k), None)
             if v is None:
                 continue
             if not encoding.isasciistr(v):
                 self.badalias = _(
                     b"non-ASCII character in alias definition '%s:%s'"
                 ) % (name, k)
                 return
             cfg[k] = v
 
         self.help = cfg.get(b'help', defaulthelp or b'')
         if self.help and self.help.startswith(b"hg " + cmd):
             # drop prefix in old-style help lines so hg shows the alias
             self.help = self.help[4 + len(cmd) :]
 
         self.owndoc = b'doc' in cfg
         doc = cfg.get(b'doc', pycompat.getdoc(fn))
         if doc is not None:
             doc = pycompat.sysstr(doc)
         self.__doc__ = doc
 
         self.helpcategory = cfg.get(
             b'category', registrar.command.CATEGORY_NONE
         )
 
     @property
     def args(self):
         args = pycompat.maplist(util.expandpath, self.givenargs)
         return aliasargs(self.fn, args)
 
     def __getattr__(self, name):
         adefaults = {
             'norepo': True,
             'intents': set(),
             'optionalrepo': False,
             'inferrepo': False,
         }
         if name not in adefaults:
             raise AttributeError(name)
         if self.badalias or util.safehasattr(self, b'shell'):
             return adefaults[name]
         return getattr(self.fn, name)
 
     def __call__(self, ui, *args, **opts):
         if self.badalias:
             hint = None
             if self.unknowncmd:
                 try:
                     # check if the command is in a disabled extension
                     cmd, ext = extensions.disabledcmd(ui, self.cmdname)[:2]
                     hint = _(b"'%s' is provided by '%s' extension") % (cmd, ext)
                 except error.UnknownCommand:
                     pass
             raise error.Abort(self.badalias, hint=hint)
         if self.shadows:
             ui.debug(
                 b"alias '%s' shadows command '%s'\n" % (self.name, self.cmdname)
             )
 
         ui.log(
             b'commandalias',
             b"alias '%s' expands to '%s'\n",
             self.name,
             self.definition,
         )
         if util.safehasattr(self, b'shell'):
             return self.fn(ui, *args, **opts)
         else:
             try:
                 return util.checksignature(self.fn)(ui, *args, **opts)
             except error.SignatureError:
                 args = b' '.join([self.cmdname] + self.args)
                 ui.debug(b"alias '%s' expands to '%s'\n" % (self.name, args))
                 raise
 
 
 class lazyaliasentry(object):
     """like a typical command entry (func, opts, help), but is lazy"""
 
     def __init__(self, ui, name, definition, cmdtable, source):
         self.ui = ui
         self.name = name
         self.definition = definition
         self.cmdtable = cmdtable.copy()
         self.source = source
         self.alias = True
 
     @util.propertycache
     def _aliasdef(self):
         return cmdalias(
             self.ui, self.name, self.definition, self.cmdtable, self.source
         )
 
     def __getitem__(self, n):
         aliasdef = self._aliasdef
         if n == 0:
             return aliasdef
         elif n == 1:
             return aliasdef.opts
         elif n == 2:
             return aliasdef.help
         else:
             raise IndexError
 
     def __iter__(self):
         for i in range(3):
             yield self[i]
 
     def __len__(self):
         return 3
 
 
 def addaliases(ui, cmdtable):
     # aliases are processed after extensions have been loaded, so they
     # may use extension commands. Aliases can also use other alias definitions,
     # but only if they have been defined prior to the current definition.
     for alias, definition in ui.configitems(b'alias', ignoresub=True):
         try:
             if cmdtable[alias].definition == definition:
                 continue
         except (KeyError, AttributeError):
             # definition might not exist or it might not be a cmdalias
             pass
 
         source = ui.configsource(b'alias', alias)
         entry = lazyaliasentry(ui, alias, definition, cmdtable, source)
         cmdtable[alias] = entry
 
 
 def _parse(ui, args):
     options = {}
     cmdoptions = {}
 
     try:
         args = fancyopts.fancyopts(args, commands.globalopts, options)
     except getopt.GetoptError as inst:
         raise error.CommandError(None, stringutil.forcebytestr(inst))
 
     if args:
         cmd, args = args[0], args[1:]
         aliases, entry = cmdutil.findcmd(
             cmd, commands.table, ui.configbool(b"ui", b"strict")
         )
         cmd = aliases[0]
         args = aliasargs(entry[0], args)
         defaults = ui.config(b"defaults", cmd)
         if defaults:
             args = (
                 pycompat.maplist(util.expandpath, pycompat.shlexsplit(defaults))
                 + args
             )
         c = list(entry[1])
     else:
         cmd = None
         c = []
 
     # combine global options into local
     for o in commands.globalopts:
         c.append((o[0], o[1], options[o[1]], o[3]))
 
     try:
         args = fancyopts.fancyopts(args, c, cmdoptions, gnu=True)
     except getopt.GetoptError as inst:
         raise error.CommandError(cmd, stringutil.forcebytestr(inst))
 
     # separate global options back out
     for o in commands.globalopts:
         n = o[1]
         options[n] = cmdoptions[n]
         del cmdoptions[n]
 
     return (cmd, cmd and entry[0] or None, args, options, cmdoptions)
 
 
 def _parseconfig(ui, config):
     """parse the --config options from the command line"""
     configs = []
 
     for cfg in config:
         try:
             name, value = [cfgelem.strip() for cfgelem in cfg.split(b'=', 1)]
             section, name = name.split(b'.', 1)
             if not section or not name:
                 raise IndexError
             ui.setconfig(section, name, value, b'--config')
             configs.append((section, name, value))
         except (IndexError, ValueError):
             raise error.Abort(
                 _(
                     b'malformed --config option: %r '
                     b'(use --config section.name=value)'
                 )
                 % pycompat.bytestr(cfg)
             )
 
     return configs
 
 
 def _earlyparseopts(ui, args):
     options = {}
     fancyopts.fancyopts(
         args,
         commands.globalopts,
         options,
         gnu=not ui.plain(b'strictflags'),
         early=True,
         optaliases={b'repository': [b'repo']},
     )
     return options
 
 
 def _earlysplitopts(args):
     """Split args into a list of possible early options and remainder args"""
     shortoptions = b'R:'
     # TODO: perhaps 'debugger' should be included
     longoptions = [b'cwd=', b'repository=', b'repo=', b'config=']
     return fancyopts.earlygetopt(
         args, shortoptions, longoptions, gnu=True, keepsep=True
     )
 
 
 def runcommand(lui, repo, cmd, fullargs, ui, options, d, cmdpats, cmdoptions):
     # run pre-hook, and abort if it fails
     hook.hook(
         lui,
         repo,
         b"pre-%s" % cmd,
         True,
         args=b" ".join(fullargs),
         pats=cmdpats,
         opts=cmdoptions,
     )
     try:
         ret = _runcommand(ui, options, cmd, d)
         # run post-hook, passing command result
         hook.hook(
             lui,
             repo,
             b"post-%s" % cmd,
             False,
             args=b" ".join(fullargs),
             result=ret,
             pats=cmdpats,
             opts=cmdoptions,
         )
     except Exception:
         # run failure hook and re-raise
         hook.hook(
             lui,
             repo,
             b"fail-%s" % cmd,
             False,
             args=b" ".join(fullargs),
             pats=cmdpats,
             opts=cmdoptions,
         )
         raise
     return ret
 
 
 def _getlocal(ui, rpath, wd=None):
     """Return (path, local ui object) for the given target path.
 
     Takes paths in [cwd]/.hg/hgrc into account."
     """
     if wd is None:
         try:
             wd = encoding.getcwd()
         except OSError as e:
             raise error.Abort(
                 _(b"error getting current working directory: %s")
                 % encoding.strtolocal(e.strerror)
             )
+
     path = cmdutil.findrepo(wd) or b""
     if not path:
         lui = ui
     else:
         lui = ui.copy()
+        if rcutil.use_repo_hgrc():
         lui.readconfig(os.path.join(path, b".hg", b"hgrc"), path)
 
     if rpath:
         path = lui.expandpath(rpath)
         lui = ui.copy()
+        if rcutil.use_repo_hgrc():
         lui.readconfig(os.path.join(path, b".hg", b"hgrc"), path)
 
     return path, lui
 
 
 def _checkshellalias(lui, ui, args):
     """Return the function to run the shell alias, if it is required"""
     options = {}
 
     try:
         args = fancyopts.fancyopts(args, commands.globalopts, options)
     except getopt.GetoptError:
         return
 
     if not args:
         return
 
     cmdtable = commands.table
 
     cmd = args[0]
     try:
         strict = ui.configbool(b"ui", b"strict")
         aliases, entry = cmdutil.findcmd(cmd, cmdtable, strict)
     except (error.AmbiguousCommand, error.UnknownCommand):
         return
 
     cmd = aliases[0]
     fn = entry[0]
 
     if cmd and util.safehasattr(fn, b'shell'):
         # shell alias shouldn't receive early options which are consumed by hg
         _earlyopts, args = _earlysplitopts(args)
         d = lambda: fn(ui, *args[1:])
         return lambda: runcommand(
             lui, None, cmd, args[:1], ui, options, d, [], {}
         )
 
 
 def _dispatch(req):
     args = req.args
     ui = req.ui
 
     # check for cwd
     cwd = req.earlyoptions[b'cwd']
     if cwd:
         os.chdir(cwd)
 
     rpath = req.earlyoptions[b'repository']
     path, lui = _getlocal(ui, rpath)
 
     uis = {ui, lui}
 
     if req.repo:
         uis.add(req.repo.ui)
 
     if (
         req.earlyoptions[b'verbose']
         or req.earlyoptions[b'debug']
         or req.earlyoptions[b'quiet']
     ):
         for opt in (b'verbose', b'debug', b'quiet'):
             val = pycompat.bytestr(bool(req.earlyoptions[opt]))
             for ui_ in uis:
                 ui_.setconfig(b'ui', opt, val, b'--' + opt)
 
     if req.earlyoptions[b'profile']:
         for ui_ in uis:
             ui_.setconfig(b'profiling', b'enabled', b'true', b'--profile')
 
     profile = lui.configbool(b'profiling', b'enabled')
     with profiling.profile(lui, enabled=profile) as profiler:
         # Configure extensions in phases: uisetup, extsetup, cmdtable, and
         # reposetup
         extensions.loadall(lui)
         # Propagate any changes to lui.__class__ by extensions
         ui.__class__ = lui.__class__
 
         # (uisetup and extsetup are handled in extensions.loadall)
 
         # (reposetup is handled in hg.repository)
 
         addaliases(lui, commands.table)
 
         # All aliases and commands are completely defined, now.
         # Check abbreviation/ambiguity of shell alias.
         shellaliasfn = _checkshellalias(lui, ui, args)
         if shellaliasfn:
             # no additional configs will be set, set up the ui instances
             for ui_ in uis:
                 extensions.populateui(ui_)
             return shellaliasfn()
 
         # check for fallback encoding
         fallback = lui.config(b'ui', b'fallbackencoding')
         if fallback:
             encoding.fallbackencoding = fallback
 
         fullargs = args
         cmd, func, args, options, cmdoptions = _parse(lui, args)
 
         # store the canonical command name in request object for later access
         req.canonical_command = cmd
 
         if options[b"config"] != req.earlyoptions[b"config"]:
             raise error.Abort(_(b"option --config may not be abbreviated!"))
         if options[b"cwd"] != req.earlyoptions[b"cwd"]:
             raise error.Abort(_(b"option --cwd may not be abbreviated!"))
         if options[b"repository"] != req.earlyoptions[b"repository"]:
             raise error.Abort(
                 _(
                     b"option -R has to be separated from other options (e.g. not "
                     b"-qR) and --repository may only be abbreviated as --repo!"
                 )
             )
         if options[b"debugger"] != req.earlyoptions[b"debugger"]:
             raise error.Abort(_(b"option --debugger may not be abbreviated!"))
         # don't validate --profile/--traceback, which can be enabled from now
 
         if options[b"encoding"]:
             encoding.encoding = options[b"encoding"]
         if options[b"encodingmode"]:
             encoding.encodingmode = options[b"encodingmode"]
         if options[b"time"]:
 
             def get_times():
                 t = os.times()
                 if t[4] == 0.0:
                     # Windows leaves this as zero, so use time.perf_counter()
                     t = (t[0], t[1], t[2], t[3], util.timer())
                 return t
 
             s = get_times()
 
             def print_time():
                 t = get_times()
                 ui.warn(
                     _(b"time: real %.3f secs (user %.3f+%.3f sys %.3f+%.3f)\n")
                     % (
                         t[4] - s[4],
                         t[0] - s[0],
                         t[2] - s[2],
                         t[1] - s[1],
                         t[3] - s[3],
                     )
                 )
 
             ui.atexit(print_time)
         if options[b"profile"]:
             profiler.start()
 
         # if abbreviated version of this were used, take them in account, now
         if options[b'verbose'] or options[b'debug'] or options[b'quiet']:
             for opt in (b'verbose', b'debug', b'quiet'):
                 if options[opt] == req.earlyoptions[opt]:
                     continue
                 val = pycompat.bytestr(bool(options[opt]))
                 for ui_ in uis:
                     ui_.setconfig(b'ui', opt, val, b'--' + opt)
 
         if options[b'traceback']:
             for ui_ in uis:
                 ui_.setconfig(b'ui', b'traceback', b'on', b'--traceback')
 
         if options[b'noninteractive']:
             for ui_ in uis:
                 ui_.setconfig(b'ui', b'interactive', b'off', b'-y')
 
         if cmdoptions.get(b'insecure', False):
             for ui_ in uis:
                 ui_.insecureconnections = True
 
         # setup color handling before pager, because setting up pager
         # might cause incorrect console information
         coloropt = options[b'color']
         for ui_ in uis:
             if coloropt:
                 ui_.setconfig(b'ui', b'color', coloropt, b'--color')
             color.setup(ui_)
 
         if stringutil.parsebool(options[b'pager']):
             # ui.pager() expects 'internal-always-' prefix in this case
             ui.pager(b'internal-always-' + cmd)
         elif options[b'pager'] != b'auto':
             for ui_ in uis:
                 ui_.disablepager()
 
         # configs are fully loaded, set up the ui instances
         for ui_ in uis:
             extensions.populateui(ui_)
 
         if options[b'version']:
             return commands.version_(ui)
         if options[b'help']:
             return commands.help_(ui, cmd, command=cmd is not None)
         elif not cmd:
             return commands.help_(ui, b'shortlist')
 
         repo = None
         cmdpats = args[:]
         assert func is not None  # help out pytype
         if not func.norepo:
             # use the repo from the request only if we don't have -R
             if not rpath and not cwd:
                 repo = req.repo
 
             if repo:
                 # set the descriptors of the repo ui to those of ui
                 repo.ui.fin = ui.fin
                 repo.ui.fout = ui.fout
                 repo.ui.ferr = ui.ferr
                 repo.ui.fmsg = ui.fmsg
             else:
                 try:
                     repo = hg.repository(
                         ui,
                         path=path,
                         presetupfuncs=req.prereposetups,
                         intents=func.intents,
                     )
                     if not repo.local():
                         raise error.Abort(
                             _(b"repository '%s' is not local") % path
                         )
                     repo.ui.setconfig(
                         b"bundle", b"mainreporoot", repo.root, b'repo'
                     )
                 except error.RequirementError:
                     raise
                 except error.RepoError:
                     if rpath:  # invalid -R path
                         raise
                     if not func.optionalrepo:
                         if func.inferrepo and args and not path:
                             # try to infer -R from command args
                             repos = pycompat.maplist(cmdutil.findrepo, args)
                             guess = repos[0]
                             if guess and repos.count(guess) == len(repos):
                                 req.args = [b'--repository', guess] + fullargs
                                 req.earlyoptions[b'repository'] = guess
                                 return _dispatch(req)
                         if not path:
                             raise error.RepoError(
                                 _(
                                     b"no repository found in"
                                     b" '%s' (.hg not found)"
                                 )
                                 % encoding.getcwd()
                             )
                         raise
             if repo:
                 ui = repo.ui
                 if options[b'hidden']:
                     repo = repo.unfiltered()
             args.insert(0, repo)
         elif rpath:
             ui.warn(_(b"warning: --repository ignored\n"))
 
         msg = _formatargs(fullargs)
         ui.log(b"command", b'%s\n', msg)
         strcmdopt = pycompat.strkwargs(cmdoptions)
         d = lambda: util.checksignature(func)(ui, *args, **strcmdopt)
         try:
             return runcommand(
                 lui, repo, cmd, fullargs, ui, options, d, cmdpats, cmdoptions
             )
         finally:
             if repo and repo != req.repo:
                 repo.close()
 
 
 def _runcommand(ui, options, cmd, cmdfunc):
     """Run a command function, possibly with profiling enabled."""
     try:
         with tracing.log("Running %s command" % cmd):
             return cmdfunc()
     except error.SignatureError:
         raise error.CommandError(cmd, _(b'invalid arguments'))
 
 
 def _exceptionwarning(ui):
     """Produce a warning message for the current active exception"""
 
     # For compatibility checking, we discard the portion of the hg
     # version after the + on the assumption that if a "normal
     # user" is running a build with a + in it the packager
     # probably built from fairly close to a tag and anyone with a
     # 'make local' copy of hg (where the version number can be out
     # of date) will be clueful enough to notice the implausible
     # version number and try updating.
     ct = util.versiontuple(n=2)
     worst = None, ct, b''
     if ui.config(b'ui', b'supportcontact') is None:
         for name, mod in extensions.extensions():
             # 'testedwith' should be bytes, but not all extensions are ported
             # to py3 and we don't want UnicodeException because of that.
             testedwith = stringutil.forcebytestr(
                 getattr(mod, 'testedwith', b'')
             )
             report = getattr(mod, 'buglink', _(b'the extension author.'))
             if not testedwith.strip():
                 # We found an untested extension. It's likely the culprit.
                 worst = name, b'unknown', report
                 break
 
             # Never blame on extensions bundled with Mercurial.
             if extensions.ismoduleinternal(mod):
                 continue
 
             tested = [util.versiontuple(t, 2) for t in testedwith.split()]
             if ct in tested:
                 continue
 
             lower = [t for t in tested if t < ct]
             nearest = max(lower or tested)
             if worst[0] is None or nearest < worst[1]:
                 worst = name, nearest, report
     if worst[0] is not None:
         name, testedwith, report = worst
         if not isinstance(testedwith, (bytes, str)):
             testedwith = b'.'.join(
                 [stringutil.forcebytestr(c) for c in testedwith]
             )
         warning = _(
             b'** Unknown exception encountered with '
             b'possibly-broken third-party extension %s\n'
             b'** which supports versions %s of Mercurial.\n'
             b'** Please disable %s and try your action again.\n'
             b'** If that fixes the bug please report it to %s\n'
         ) % (name, testedwith, name, stringutil.forcebytestr(report))
     else:
         bugtracker = ui.config(b'ui', b'supportcontact')
         if bugtracker is None:
             bugtracker = _(b"https://mercurial-scm.org/wiki/BugTracker")
         warning = (
             _(
                 b"** unknown exception encountered, "
                 b"please report by visiting\n** "
             )
             + bugtracker
             + b'\n'
         )
     sysversion = pycompat.sysbytes(sys.version).replace(b'\n', b'')
     warning += (
         (_(b"** Python %s\n") % sysversion)
         + (_(b"** Mercurial Distributed SCM (version %s)\n") % util.version())
         + (
             _(b"** Extensions loaded: %s\n")
             % b", ".join([x[0] for x in extensions.extensions()])
         )
     )
     return warning
 
 
 def handlecommandexception(ui):
     """Produce a warning message for broken commands
 
     Called when handling an exception; the exception is reraised if
     this function returns False, ignored otherwise.
     """
     warning = _exceptionwarning(ui)
     ui.log(
         b"commandexception",
         b"%s\n%s\n",
         warning,
         pycompat.sysbytes(traceback.format_exc()),
     )
     ui.warn(warning)
     return False  # re-raise the exception

mercurial/hgweb/hgwebdir_mod.py

@@ -1,579 +1,581 b''
 # hgweb/hgwebdir_mod.py - Web interface for a directory of repositories.
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 #
 # 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
 
 import gc
 import os
 import time
 
 from ..i18n import _
 
 from .common import (
     ErrorResponse,
     HTTP_SERVER_ERROR,
     cspvalues,
     get_contact,
     get_mtime,
     ismember,
     paritygen,
     staticfile,
     statusmessage,
 )
 
 from .. import (
     configitems,
     encoding,
     error,
     extensions,
     hg,
     pathutil,
     profiling,
     pycompat,
+    rcutil,
     registrar,
     scmutil,
     templater,
     templateutil,
     ui as uimod,
     util,
 )
 
 from . import (
     hgweb_mod,
     request as requestmod,
     webutil,
     wsgicgi,
 )
 from ..utils import dateutil
 
 
 def cleannames(items):
     return [(util.pconvert(name).strip(b'/'), path) for name, path in items]
 
 
 def findrepos(paths):
     repos = []
     for prefix, root in cleannames(paths):
         roothead, roottail = os.path.split(root)
         # "foo = /bar/*" or "foo = /bar/**" lets every repo /bar/N in or below
         # /bar/ be served as as foo/N .
         # '*' will not search inside dirs with .hg (except .hg/patches),
         # '**' will search inside dirs with .hg (and thus also find subrepos).
         try:
             recurse = {b'*': False, b'**': True}[roottail]
         except KeyError:
             repos.append((prefix, root))
             continue
         roothead = os.path.normpath(os.path.abspath(roothead))
         paths = scmutil.walkrepos(roothead, followsym=True, recurse=recurse)
         repos.extend(urlrepos(prefix, roothead, paths))
     return repos
 
 
 def urlrepos(prefix, roothead, paths):
     """yield url paths and filesystem paths from a list of repo paths
 
     >>> conv = lambda seq: [(v, util.pconvert(p)) for v,p in seq]
     >>> conv(urlrepos(b'hg', b'/opt', [b'/opt/r', b'/opt/r/r', b'/opt']))
     [('hg/r', '/opt/r'), ('hg/r/r', '/opt/r/r'), ('hg', '/opt')]
     >>> conv(urlrepos(b'', b'/opt', [b'/opt/r', b'/opt/r/r', b'/opt']))
     [('r', '/opt/r'), ('r/r', '/opt/r/r'), ('', '/opt')]
     """
     for path in paths:
         path = os.path.normpath(path)
         yield (
             prefix + b'/' + util.pconvert(path[len(roothead) :]).lstrip(b'/')
         ).strip(b'/'), path
 
 
 def readallowed(ui, req):
     """Check allow_read and deny_read config options of a repo's ui object
     to determine user permissions.  By default, with neither option set (or
     both empty), allow all users to read the repo.  There are two ways a
     user can be denied read access:  (1) deny_read is not empty, and the
     user is unauthenticated or deny_read contains user (or *), and (2)
     allow_read is not empty and the user is not in allow_read.  Return True
     if user is allowed to read the repo, else return False."""
 
     user = req.remoteuser
 
     deny_read = ui.configlist(b'web', b'deny_read', untrusted=True)
     if deny_read and (not user or ismember(ui, user, deny_read)):
         return False
 
     allow_read = ui.configlist(b'web', b'allow_read', untrusted=True)
     # by default, allow reading if no allow_read option has been set
     if not allow_read or ismember(ui, user, allow_read):
         return True
 
     return False
 
 
 def rawindexentries(ui, repos, req, subdir=b''):
     descend = ui.configbool(b'web', b'descend')
     collapse = ui.configbool(b'web', b'collapse')
     seenrepos = set()
     seendirs = set()
     for name, path in repos:
 
         if not name.startswith(subdir):
             continue
         name = name[len(subdir) :]
         directory = False
 
         if b'/' in name:
             if not descend:
                 continue
 
             nameparts = name.split(b'/')
             rootname = nameparts[0]
 
             if not collapse:
                 pass
             elif rootname in seendirs:
                 continue
             elif rootname in seenrepos:
                 pass
             else:
                 directory = True
                 name = rootname
 
                 # redefine the path to refer to the directory
                 discarded = b'/'.join(nameparts[1:])
 
                 # remove name parts plus accompanying slash
                 path = path[: -len(discarded) - 1]
 
                 try:
                     hg.repository(ui, path)
                     directory = False
                 except (IOError, error.RepoError):
                     pass
 
         parts = [
             req.apppath.strip(b'/'),
             subdir.strip(b'/'),
             name.strip(b'/'),
         ]
         url = b'/' + b'/'.join(p for p in parts if p) + b'/'
 
         # show either a directory entry or a repository
         if directory:
             # get the directory's time information
             try:
                 d = (get_mtime(path), dateutil.makedate()[1])
             except OSError:
                 continue
 
             # add '/' to the name to make it obvious that
             # the entry is a directory, not a regular repository
             row = {
                 b'contact': b"",
                 b'contact_sort': b"",
                 b'name': name + b'/',
                 b'name_sort': name,
                 b'url': url,
                 b'description': b"",
                 b'description_sort': b"",
                 b'lastchange': d,
                 b'lastchange_sort': d[1] - d[0],
                 b'archives': templateutil.mappinglist([]),
                 b'isdirectory': True,
                 b'labels': templateutil.hybridlist([], name=b'label'),
             }
 
             seendirs.add(name)
             yield row
             continue
 
         u = ui.copy()
+        if rcutil.use_repo_hgrc():
         try:
             u.readconfig(os.path.join(path, b'.hg', b'hgrc'))
         except Exception as e:
             u.warn(_(b'error reading %s/.hg/hgrc: %s\n') % (path, e))
             continue
 
         def get(section, name, default=uimod._unset):
             return u.config(section, name, default, untrusted=True)
 
         if u.configbool(b"web", b"hidden", untrusted=True):
             continue
 
         if not readallowed(u, req):
             continue
 
         # update time with local timezone
         try:
             r = hg.repository(ui, path)
         except IOError:
             u.warn(_(b'error accessing repository at %s\n') % path)
             continue
         except error.RepoError:
             u.warn(_(b'error accessing repository at %s\n') % path)
             continue
         try:
             d = (get_mtime(r.spath), dateutil.makedate()[1])
         except OSError:
             continue
 
         contact = get_contact(get)
         description = get(b"web", b"description")
         seenrepos.add(name)
         name = get(b"web", b"name", name)
         labels = u.configlist(b'web', b'labels', untrusted=True)
         row = {
             b'contact': contact or b"unknown",
             b'contact_sort': contact.upper() or b"unknown",
             b'name': name,
             b'name_sort': name,
             b'url': url,
             b'description': description or b"unknown",
             b'description_sort': description.upper() or b"unknown",
             b'lastchange': d,
             b'lastchange_sort': d[1] - d[0],
             b'archives': webutil.archivelist(u, b"tip", url),
             b'isdirectory': None,
             b'labels': templateutil.hybridlist(labels, name=b'label'),
         }
 
         yield row
 
 
 def _indexentriesgen(
     context, ui, repos, req, stripecount, sortcolumn, descending, subdir
 ):
     rows = rawindexentries(ui, repos, req, subdir=subdir)
 
     sortdefault = None, False
 
     if sortcolumn and sortdefault != (sortcolumn, descending):
         sortkey = b'%s_sort' % sortcolumn
         rows = sorted(rows, key=lambda x: x[sortkey], reverse=descending)
 
     for row, parity in zip(rows, paritygen(stripecount)):
         row[b'parity'] = parity
         yield row
 
 
 def indexentries(
     ui, repos, req, stripecount, sortcolumn=b'', descending=False, subdir=b''
 ):
     args = (ui, repos, req, stripecount, sortcolumn, descending, subdir)
     return templateutil.mappinggenerator(_indexentriesgen, args=args)
 
 
 class hgwebdir(object):
     """HTTP server for multiple repositories.
 
     Given a configuration, different repositories will be served depending
     on the request path.
 
     Instances are typically used as WSGI applications.
     """
 
     def __init__(self, conf, baseui=None):
         self.conf = conf
         self.baseui = baseui
         self.ui = None
         self.lastrefresh = 0
         self.motd = None
         self.refresh()
         if not baseui:
             # set up environment for new ui
             extensions.loadall(self.ui)
             extensions.populateui(self.ui)
 
     def refresh(self):
         if self.ui:
             refreshinterval = self.ui.configint(b'web', b'refreshinterval')
         else:
             item = configitems.coreitems[b'web'][b'refreshinterval']
             refreshinterval = item.default
 
         # refreshinterval <= 0 means to always refresh.
         if (
             refreshinterval > 0
             and self.lastrefresh + refreshinterval > time.time()
         ):
             return
 
         if self.baseui:
             u = self.baseui.copy()
         else:
             u = uimod.ui.load()
             u.setconfig(b'ui', b'report_untrusted', b'off', b'hgwebdir')
             u.setconfig(b'ui', b'nontty', b'true', b'hgwebdir')
             # displaying bundling progress bar while serving feels wrong and may
             # break some wsgi implementations.
             u.setconfig(b'progress', b'disable', b'true', b'hgweb')
 
         if not isinstance(self.conf, (dict, list, tuple)):
             map = {b'paths': b'hgweb-paths'}
             if not os.path.exists(self.conf):
                 raise error.Abort(_(b'config file %s not found!') % self.conf)
             u.readconfig(self.conf, remap=map, trust=True)
             paths = []
             for name, ignored in u.configitems(b'hgweb-paths'):
                 for path in u.configlist(b'hgweb-paths', name):
                     paths.append((name, path))
         elif isinstance(self.conf, (list, tuple)):
             paths = self.conf
         elif isinstance(self.conf, dict):
             paths = self.conf.items()
         extensions.populateui(u)
 
         repos = findrepos(paths)
         for prefix, root in u.configitems(b'collections'):
             prefix = util.pconvert(prefix)
             for path in scmutil.walkrepos(root, followsym=True):
                 repo = os.path.normpath(path)
                 name = util.pconvert(repo)
                 if name.startswith(prefix):
                     name = name[len(prefix) :]
                 repos.append((name.lstrip(b'/'), repo))
 
         self.repos = repos
         self.ui = u
         encoding.encoding = self.ui.config(b'web', b'encoding')
         self.style = self.ui.config(b'web', b'style')
         self.templatepath = self.ui.config(
             b'web', b'templates', untrusted=False
         )
         self.stripecount = self.ui.config(b'web', b'stripes')
         if self.stripecount:
             self.stripecount = int(self.stripecount)
         prefix = self.ui.config(b'web', b'prefix')
         if prefix.startswith(b'/'):
             prefix = prefix[1:]
         if prefix.endswith(b'/'):
             prefix = prefix[:-1]
         self.prefix = prefix
         self.lastrefresh = time.time()
 
     def run(self):
         if not encoding.environ.get(b'GATEWAY_INTERFACE', b'').startswith(
             b"CGI/1."
         ):
             raise RuntimeError(
                 b"This function is only intended to be "
                 b"called while running as a CGI script."
             )
         wsgicgi.launch(self)
 
     def __call__(self, env, respond):
         baseurl = self.ui.config(b'web', b'baseurl')
         req = requestmod.parserequestfromenv(env, altbaseurl=baseurl)
         res = requestmod.wsgiresponse(req, respond)
 
         return self.run_wsgi(req, res)
 
     def run_wsgi(self, req, res):
         profile = self.ui.configbool(b'profiling', b'enabled')
         with profiling.profile(self.ui, enabled=profile):
             try:
                 for r in self._runwsgi(req, res):
                     yield r
             finally:
                 # There are known cycles in localrepository that prevent
                 # those objects (and tons of held references) from being
                 # collected through normal refcounting. We mitigate those
                 # leaks by performing an explicit GC on every request.
                 # TODO remove this once leaks are fixed.
                 # TODO only run this on requests that create localrepository
                 # instances instead of every request.
                 gc.collect()
 
     def _runwsgi(self, req, res):
         try:
             self.refresh()
 
             csp, nonce = cspvalues(self.ui)
             if csp:
                 res.headers[b'Content-Security-Policy'] = csp
 
             virtual = req.dispatchpath.strip(b'/')
             tmpl = self.templater(req, nonce)
             ctype = tmpl.render(b'mimetype', {b'encoding': encoding.encoding})
 
             # Global defaults. These can be overridden by any handler.
             res.status = b'200 Script output follows'
             res.headers[b'Content-Type'] = ctype
 
             # a static file
             if virtual.startswith(b'static/') or b'static' in req.qsparams:
                 if virtual.startswith(b'static/'):
                     fname = virtual[7:]
                 else:
                     fname = req.qsparams[b'static']
                 static = self.ui.config(b"web", b"static", untrusted=False)
                 if not static:
                     tp = self.templatepath or templater.templatepaths()
                     if isinstance(tp, bytes):
                         tp = [tp]
                     static = [os.path.join(p, b'static') for p in tp]
 
                 staticfile(static, fname, res)
                 return res.sendresponse()
 
             # top-level index
 
             repos = dict(self.repos)
 
             if (not virtual or virtual == b'index') and virtual not in repos:
                 return self.makeindex(req, res, tmpl)
 
             # nested indexes and hgwebs
 
             if virtual.endswith(b'/index') and virtual not in repos:
                 subdir = virtual[: -len(b'index')]
                 if any(r.startswith(subdir) for r in repos):
                     return self.makeindex(req, res, tmpl, subdir)
 
             def _virtualdirs():
                 # Check the full virtual path, and each parent
                 yield virtual
                 for p in pathutil.finddirs(virtual):
                     yield p
 
             for virtualrepo in _virtualdirs():
                 real = repos.get(virtualrepo)
                 if real:
                     # Re-parse the WSGI environment to take into account our
                     # repository path component.
                     uenv = req.rawenv
                     if pycompat.ispy3:
                         uenv = {
                             k.decode('latin1'): v
                             for k, v in pycompat.iteritems(uenv)
                         }
                     req = requestmod.parserequestfromenv(
                         uenv,
                         reponame=virtualrepo,
                         altbaseurl=self.ui.config(b'web', b'baseurl'),
                         # Reuse wrapped body file object otherwise state
                         # tracking can get confused.
                         bodyfh=req.bodyfh,
                     )
                     try:
                         # ensure caller gets private copy of ui
                         repo = hg.repository(self.ui.copy(), real)
                         return hgweb_mod.hgweb(repo).run_wsgi(req, res)
                     except IOError as inst:
                         msg = encoding.strtolocal(inst.strerror)
                         raise ErrorResponse(HTTP_SERVER_ERROR, msg)
                     except error.RepoError as inst:
                         raise ErrorResponse(HTTP_SERVER_ERROR, bytes(inst))
 
             # browse subdirectories
             subdir = virtual + b'/'
             if [r for r in repos if r.startswith(subdir)]:
                 return self.makeindex(req, res, tmpl, subdir)
 
             # prefixes not found
             res.status = b'404 Not Found'
             res.setbodygen(tmpl.generate(b'notfound', {b'repo': virtual}))
             return res.sendresponse()
 
         except ErrorResponse as e:
             res.status = statusmessage(e.code, pycompat.bytestr(e))
             res.setbodygen(
                 tmpl.generate(b'error', {b'error': e.message or b''})
             )
             return res.sendresponse()
         finally:
             del tmpl
 
     def makeindex(self, req, res, tmpl, subdir=b""):
         self.refresh()
         sortable = [b"name", b"description", b"contact", b"lastchange"]
         sortcolumn, descending = None, False
         if b'sort' in req.qsparams:
             sortcolumn = req.qsparams[b'sort']
             descending = sortcolumn.startswith(b'-')
             if descending:
                 sortcolumn = sortcolumn[1:]
             if sortcolumn not in sortable:
                 sortcolumn = b""
 
         sort = [
             (
                 b"sort_%s" % column,
                 b"%s%s"
                 % (
                     (not descending and column == sortcolumn) and b"-" or b"",
                     column,
                 ),
             )
             for column in sortable
         ]
 
         self.refresh()
 
         entries = indexentries(
             self.ui,
             self.repos,
             req,
             self.stripecount,
             sortcolumn=sortcolumn,
             descending=descending,
             subdir=subdir,
         )
 
         mapping = {
             b'entries': entries,
             b'subdir': subdir,
             b'pathdef': hgweb_mod.makebreadcrumb(b'/' + subdir, self.prefix),
             b'sortcolumn': sortcolumn,
             b'descending': descending,
         }
         mapping.update(sort)
         res.setbodygen(tmpl.generate(b'index', mapping))
         return res.sendresponse()
 
     def templater(self, req, nonce):
         def config(section, name, default=uimod._unset, untrusted=True):
             return self.ui.config(section, name, default, untrusted)
 
         vars = {}
         styles, (style, mapfile) = hgweb_mod.getstyle(
             req, config, self.templatepath
         )
         if style == styles[0]:
             vars[b'style'] = style
 
         sessionvars = webutil.sessionvars(vars, b'?')
         logourl = config(b'web', b'logourl')
         logoimg = config(b'web', b'logoimg')
         staticurl = (
             config(b'web', b'staticurl')
             or req.apppath.rstrip(b'/') + b'/static/'
         )
         if not staticurl.endswith(b'/'):
             staticurl += b'/'
 
         defaults = {
             b"encoding": encoding.encoding,
             b"url": req.apppath + b'/',
             b"logourl": logourl,
             b"logoimg": logoimg,
             b"staticurl": staticurl,
             b"sessionvars": sessionvars,
             b"style": style,
             b"nonce": nonce,
         }
         templatekeyword = registrar.templatekeyword(defaults)
 
         @templatekeyword(b'motd', requires=())
         def motd(context, mapping):
             if self.motd is not None:
                 yield self.motd
             else:
                 yield config(b'web', b'motd')
 
         tmpl = templater.templater.frommapfile(mapfile, defaults=defaults)
         return tmpl

mercurial/linelog.py

@@ -1,467 +1,467 b''
 # linelog - efficient cache for annotate data
 #
 # Copyright 2018 Google LLC.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 """linelog is an efficient cache for annotate data inspired by SCCS Weaves.
 
 SCCS Weaves are an implementation of
 https://en.wikipedia.org/wiki/Interleaved_deltas. See
 mercurial/helptext/internals/linelog.txt for an exploration of SCCS weaves
 and how linelog works in detail.
 
 Here's a hacker's summary: a linelog is a program which is executed in
 the context of a revision. Executing the program emits information
 about lines, including the revision that introduced them and the line
 number in the file at the introducing revision. When an insertion or
 deletion is performed on the file, a jump instruction is used to patch
 in a new body of annotate information.
 """
 from __future__ import absolute_import, print_function
 
 import abc
 import struct
 
 from .thirdparty import attr
 from . import pycompat
 
 _llentry = struct.Struct(b'>II')
 
 
 class LineLogError(Exception):
     """Error raised when something bad happens internally in linelog."""
 
 
 @attr.s
 class lineinfo(object):
     # Introducing revision of this line.
     rev = attr.ib()
     # Line number for this line in its introducing revision.
     linenum = attr.ib()
     # Private. Offset in the linelog program of this line. Used internally.
     _offset = attr.ib()
 
 
 @attr.s
 class annotateresult(object):
     rev = attr.ib()
     lines = attr.ib()
     _eof = attr.ib()
 
     def __iter__(self):
         return iter(self.lines)
 
 
 class _llinstruction(object):  # pytype: disable=ignored-metaclass
 
     __metaclass__ = abc.ABCMeta
 
     @abc.abstractmethod
     def __init__(self, op1, op2):
         pass
 
     @abc.abstractmethod
     def __str__(self):
         pass
 
     def __repr__(self):
         return str(self)
 
     @abc.abstractmethod
     def __eq__(self, other):
         pass
 
     @abc.abstractmethod
     def encode(self):
         """Encode this instruction to the binary linelog format."""
 
     @abc.abstractmethod
     def execute(self, rev, pc, emit):
         """Execute this instruction.
 
         Args:
           rev: The revision we're annotating.
           pc: The current offset in the linelog program.
           emit: A function that accepts a single lineinfo object.
 
         Returns:
           The new value of pc. Returns None if exeuction should stop
           (that is, we've found the end of the file.)
         """
 
 
 class _jge(_llinstruction):
     """If the current rev is greater than or equal to op1, jump to op2."""
 
     def __init__(self, op1, op2):
         self._cmprev = op1
         self._target = op2
 
     def __str__(self):
         return 'JGE %d %d' % (self._cmprev, self._target)
 
     def __eq__(self, other):
         return (
             type(self) == type(other)
             and self._cmprev == other._cmprev
             and self._target == other._target
         )
 
     def encode(self):
         return _llentry.pack(self._cmprev << 2, self._target)
 
     def execute(self, rev, pc, emit):
         if rev >= self._cmprev:
             return self._target
         return pc + 1
 
 
 class _jump(_llinstruction):
     """Unconditional jumps are expressed as a JGE with op1 set to 0."""
 
     def __init__(self, op1, op2):
         if op1 != 0:
             raise LineLogError(b"malformed JUMP, op1 must be 0, got %d" % op1)
         self._target = op2
 
     def __str__(self):
         return 'JUMP %d' % (self._target)
 
     def __eq__(self, other):
         return type(self) == type(other) and self._target == other._target
 
     def encode(self):
         return _llentry.pack(0, self._target)
 
     def execute(self, rev, pc, emit):
         return self._target
 
 
 class _eof(_llinstruction):
     """EOF is expressed as a JGE that always jumps to 0."""
 
     def __init__(self, op1, op2):
         if op1 != 0:
             raise LineLogError(b"malformed EOF, op1 must be 0, got %d" % op1)
         if op2 != 0:
             raise LineLogError(b"malformed EOF, op2 must be 0, got %d" % op2)
 
     def __str__(self):
         return r'EOF'
 
     def __eq__(self, other):
         return type(self) == type(other)
 
     def encode(self):
         return _llentry.pack(0, 0)
 
     def execute(self, rev, pc, emit):
         return None
 
 
 class _jl(_llinstruction):
     """If the current rev is less than op1, jump to op2."""
 
     def __init__(self, op1, op2):
         self._cmprev = op1
         self._target = op2
 
     def __str__(self):
         return 'JL %d %d' % (self._cmprev, self._target)
 
     def __eq__(self, other):
         return (
             type(self) == type(other)
             and self._cmprev == other._cmprev
             and self._target == other._target
         )
 
     def encode(self):
         return _llentry.pack(1 | (self._cmprev << 2), self._target)
 
     def execute(self, rev, pc, emit):
         if rev < self._cmprev:
             return self._target
         return pc + 1
 
 
 class _line(_llinstruction):
     """Emit a line."""
 
     def __init__(self, op1, op2):
         # This line was introduced by this revision number.
         self._rev = op1
         # This line had the specified line number in the introducing revision.
         self._origlineno = op2
 
     def __str__(self):
         return 'LINE %d %d' % (self._rev, self._origlineno)
 
     def __eq__(self, other):
         return (
             type(self) == type(other)
             and self._rev == other._rev
             and self._origlineno == other._origlineno
         )
 
     def encode(self):
         return _llentry.pack(2 | (self._rev << 2), self._origlineno)
 
     def execute(self, rev, pc, emit):
         emit(lineinfo(self._rev, self._origlineno, pc))
         return pc + 1
 
 
 def _decodeone(data, offset):
     """Decode a single linelog instruction from an offset in a buffer."""
     try:
         op1, op2 = _llentry.unpack_from(data, offset)
     except struct.error as e:
         raise LineLogError(b'reading an instruction failed: %r' % e)
     opcode = op1 & 0b11
     op1 = op1 >> 2
     if opcode == 0:
         if op1 == 0:
             if op2 == 0:
                 return _eof(op1, op2)
             return _jump(op1, op2)
         return _jge(op1, op2)
     elif opcode == 1:
         return _jl(op1, op2)
     elif opcode == 2:
         return _line(op1, op2)
     raise NotImplementedError(b'Unimplemented opcode %r' % opcode)
 
 
 class linelog(object):
     """Efficient cache for per-line history information."""
 
     def __init__(self, program=None, maxrev=0):
         if program is None:
             # We pad the program with an extra leading EOF so that our
             # offsets will match the C code exactly. This means we can
             # interoperate with the C code.
             program = [_eof(0, 0), _eof(0, 0)]
         self._program = program
         self._lastannotate = None
         self._maxrev = maxrev
 
     def __eq__(self, other):
         return (
             type(self) == type(other)
             and self._program == other._program
             and self._maxrev == other._maxrev
         )
 
     def __repr__(self):
-        return b'<linelog at %s: maxrev=%d size=%d>' % (
+        return '<linelog at %s: maxrev=%d size=%d>' % (
             hex(id(self)),
             self._maxrev,
             len(self._program),
         )
 
     def debugstr(self):
         fmt = '%%%dd %%s' % len(str(len(self._program)))
         return pycompat.sysstr(b'\n').join(
             fmt % (idx, i) for idx, i in enumerate(self._program[1:], 1)
         )
 
     @classmethod
     def fromdata(cls, buf):
         if len(buf) % _llentry.size != 0:
             raise LineLogError(
                 b"invalid linelog buffer size %d (must be a multiple of %d)"
                 % (len(buf), _llentry.size)
             )
         expected = len(buf) / _llentry.size
         fakejge = _decodeone(buf, 0)
         if isinstance(fakejge, _jump):
             maxrev = 0
         elif isinstance(fakejge, (_jge, _jl)):
             maxrev = fakejge._cmprev
         else:
             raise LineLogError(
                 'Expected one of _jump, _jge, or _jl. Got %s.'
                 % type(fakejge).__name__
             )
         assert isinstance(fakejge, (_jump, _jge, _jl))  # help pytype
         numentries = fakejge._target
         if expected != numentries:
             raise LineLogError(
                 b"corrupt linelog data: claimed"
                 b" %d entries but given data for %d entries"
                 % (expected, numentries)
             )
         instructions = [_eof(0, 0)]
         for offset in pycompat.xrange(1, numentries):
             instructions.append(_decodeone(buf, offset * _llentry.size))
         return cls(instructions, maxrev=maxrev)
 
     def encode(self):
         hdr = _jge(self._maxrev, len(self._program)).encode()
         return hdr + b''.join(i.encode() for i in self._program[1:])
 
     def clear(self):
         self._program = []
         self._maxrev = 0
         self._lastannotate = None
 
     def replacelines_vec(self, rev, a1, a2, blines):
         return self.replacelines(
             rev, a1, a2, 0, len(blines), _internal_blines=blines
         )
 
     def replacelines(self, rev, a1, a2, b1, b2, _internal_blines=None):
         """Replace lines [a1, a2) with lines [b1, b2)."""
         if self._lastannotate:
             # TODO(augie): make replacelines() accept a revision at
             # which we're editing as well as a revision to mark
             # responsible for the edits. In hg-experimental it's
             # stateful like this, so we're doing the same thing to
             # retain compatibility with absorb until that's imported.
             ar = self._lastannotate
         else:
             ar = self.annotate(rev)
             #        ar = self.annotate(self._maxrev)
         if a1 > len(ar.lines):
             raise LineLogError(
                 b'%d contains %d lines, tried to access line %d'
                 % (rev, len(ar.lines), a1)
             )
         elif a1 == len(ar.lines):
             # Simulated EOF instruction since we're at EOF, which
             # doesn't have a "real" line.
             a1inst = _eof(0, 0)
             a1info = lineinfo(0, 0, ar._eof)
         else:
             a1info = ar.lines[a1]
             a1inst = self._program[a1info._offset]
         programlen = self._program.__len__
         oldproglen = programlen()
         appendinst = self._program.append
 
         # insert
         blineinfos = []
         bappend = blineinfos.append
         if b1 < b2:
             # Determine the jump target for the JGE at the start of
             # the new block.
             tgt = oldproglen + (b2 - b1 + 1)
             # Jump to skip the insert if we're at an older revision.
             appendinst(_jl(rev, tgt))
             for linenum in pycompat.xrange(b1, b2):
                 if _internal_blines is None:
                     bappend(lineinfo(rev, linenum, programlen()))
                     appendinst(_line(rev, linenum))
                 else:
                     newrev, newlinenum = _internal_blines[linenum]
                     bappend(lineinfo(newrev, newlinenum, programlen()))
                     appendinst(_line(newrev, newlinenum))
         # delete
         if a1 < a2:
             if a2 > len(ar.lines):
                 raise LineLogError(
                     b'%d contains %d lines, tried to access line %d'
                     % (rev, len(ar.lines), a2)
                 )
             elif a2 == len(ar.lines):
                 endaddr = ar._eof
             else:
                 endaddr = ar.lines[a2]._offset
             if a2 > 0 and rev < self._maxrev:
                 # If we're here, we're deleting a chunk of an old
                 # commit, so we need to be careful and not touch
                 # invisible lines between a2-1 and a2 (IOW, lines that
                 # are added later).
                 endaddr = ar.lines[a2 - 1]._offset + 1
             appendinst(_jge(rev, endaddr))
         # copy instruction from a1
         a1instpc = programlen()
         appendinst(a1inst)
         # if a1inst isn't a jump or EOF, then we need to add an unconditional
         # jump back into the program here.
         if not isinstance(a1inst, (_jump, _eof)):
             appendinst(_jump(0, a1info._offset + 1))
         # Patch instruction at a1, which makes our patch live.
         self._program[a1info._offset] = _jump(0, oldproglen)
 
         # Update self._lastannotate in place. This serves as a cache to avoid
         # expensive "self.annotate" in this function, when "replacelines" is
         # used continuously.
         if len(self._lastannotate.lines) > a1:
             self._lastannotate.lines[a1]._offset = a1instpc
         else:
             assert isinstance(a1inst, _eof)
             self._lastannotate._eof = a1instpc
         self._lastannotate.lines[a1:a2] = blineinfos
         self._lastannotate.rev = max(self._lastannotate.rev, rev)
 
         if rev > self._maxrev:
             self._maxrev = rev
 
     def annotate(self, rev):
         pc = 1
         lines = []
         executed = 0
         # Sanity check: if instructions executed exceeds len(program), we
         # hit an infinite loop in the linelog program somehow and we
         # should stop.
         while pc is not None and executed < len(self._program):
             inst = self._program[pc]
             lastpc = pc
             pc = inst.execute(rev, pc, lines.append)
             executed += 1
         if pc is not None:
             raise LineLogError(
                 r'Probably hit an infinite loop in linelog. Program:\n'
                 + self.debugstr()
             )
         ar = annotateresult(rev, lines, lastpc)
         self._lastannotate = ar
         return ar
 
     @property
     def maxrev(self):
         return self._maxrev
 
     # Stateful methods which depend on the value of the last
     # annotation run. This API is for compatiblity with the original
     # linelog, and we should probably consider refactoring it.
     @property
     def annotateresult(self):
         """Return the last annotation result. C linelog code exposed this."""
         return [(l.rev, l.linenum) for l in self._lastannotate.lines]
 
     def getoffset(self, line):
         return self._lastannotate.lines[line]._offset
 
     def getalllines(self, start=0, end=0):
         """Get all lines that ever occurred in [start, end).
 
         Passing start == end == 0 means "all lines ever".
 
         This works in terms of *internal* program offsets, not line numbers.
         """
         pc = start or 1
         lines = []
         # only take as many steps as there are instructions in the
         # program - if we don't find an EOF or our stop-line before
         # then, something is badly broken.
         for step in pycompat.xrange(len(self._program)):
             inst = self._program[pc]
             nextpc = pc + 1
             if isinstance(inst, _jump):
                 nextpc = inst._target
             elif isinstance(inst, _eof):
                 return lines
             elif isinstance(inst, (_jl, _jge)):
                 pass
             elif isinstance(inst, _line):
                 lines.append((inst._rev, inst._origlineno))
             else:
                 raise LineLogError(b"Illegal instruction %r" % inst)
             if nextpc == end:
                 return lines
             pc = nextpc
         raise LineLogError(b"Failed to perform getalllines")

mercurial/localrepo.py

@@ -1,3786 +1,3787 b''
 # localrepo.py - read/write repository class for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # 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
 
 import errno
 import os
 import random
 import sys
 import time
 import weakref
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
     short,
 )
 from .pycompat import (
     delattr,
     getattr,
 )
 from . import (
     bookmarks,
     branchmap,
     bundle2,
     changegroup,
     color,
     context,
     dirstate,
     dirstateguard,
     discovery,
     encoding,
     error,
     exchange,
     extensions,
     filelog,
     hook,
     lock as lockmod,
     match as matchmod,
     merge as mergemod,
     mergeutil,
     namespaces,
     narrowspec,
     obsolete,
     pathutil,
     phases,
     pushkey,
     pycompat,
+    rcutil,
     repoview,
     revset,
     revsetlang,
     scmutil,
     sparse,
     store as storemod,
     subrepoutil,
     tags as tagsmod,
     transaction,
     txnutil,
     util,
     vfs as vfsmod,
 )
 
 from .interfaces import (
     repository,
     util as interfaceutil,
 )
 
 from .utils import (
     hashutil,
     procutil,
     stringutil,
 )
 
 from .revlogutils import constants as revlogconst
 
 release = lockmod.release
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 # set of (path, vfs-location) tuples. vfs-location is:
 # - 'plain for vfs relative paths
 # - '' for svfs relative paths
 _cachedfiles = set()
 
 
 class _basefilecache(scmutil.filecache):
     """All filecache usage on repo are done for logic that should be unfiltered
     """
 
     def __get__(self, repo, type=None):
         if repo is None:
             return self
         # proxy to unfiltered __dict__ since filtered repo has no entry
         unfi = repo.unfiltered()
         try:
             return unfi.__dict__[self.sname]
         except KeyError:
             pass
         return super(_basefilecache, self).__get__(unfi, type)
 
     def set(self, repo, value):
         return super(_basefilecache, self).set(repo.unfiltered(), value)
 
 
 class repofilecache(_basefilecache):
     """filecache for files in .hg but outside of .hg/store"""
 
     def __init__(self, *paths):
         super(repofilecache, self).__init__(*paths)
         for path in paths:
             _cachedfiles.add((path, b'plain'))
 
     def join(self, obj, fname):
         return obj.vfs.join(fname)
 
 
 class storecache(_basefilecache):
     """filecache for files in the store"""
 
     def __init__(self, *paths):
         super(storecache, self).__init__(*paths)
         for path in paths:
             _cachedfiles.add((path, b''))
 
     def join(self, obj, fname):
         return obj.sjoin(fname)
 
 
 class mixedrepostorecache(_basefilecache):
     """filecache for a mix files in .hg/store and outside"""
 
     def __init__(self, *pathsandlocations):
         # scmutil.filecache only uses the path for passing back into our
         # join(), so we can safely pass a list of paths and locations
         super(mixedrepostorecache, self).__init__(*pathsandlocations)
         _cachedfiles.update(pathsandlocations)
 
     def join(self, obj, fnameandlocation):
         fname, location = fnameandlocation
         if location == b'plain':
             return obj.vfs.join(fname)
         else:
             if location != b'':
                 raise error.ProgrammingError(
                     b'unexpected location: %s' % location
                 )
             return obj.sjoin(fname)
 
 
 def isfilecached(repo, name):
     """check if a repo has already cached "name" filecache-ed property
 
     This returns (cachedobj-or-None, iscached) tuple.
     """
     cacheentry = repo.unfiltered()._filecache.get(name, None)
     if not cacheentry:
         return None, False
     return cacheentry.obj, True
 
 
 class unfilteredpropertycache(util.propertycache):
     """propertycache that apply to unfiltered repo only"""
 
     def __get__(self, repo, type=None):
         unfi = repo.unfiltered()
         if unfi is repo:
             return super(unfilteredpropertycache, self).__get__(unfi)
         return getattr(unfi, self.name)
 
 
 class filteredpropertycache(util.propertycache):
     """propertycache that must take filtering in account"""
 
     def cachevalue(self, obj, value):
         object.__setattr__(obj, self.name, value)
 
 
 def hasunfilteredcache(repo, name):
     """check if a repo has an unfilteredpropertycache value for <name>"""
     return name in vars(repo.unfiltered())
 
 
 def unfilteredmethod(orig):
     """decorate method that always need to be run on unfiltered version"""
 
     def wrapper(repo, *args, **kwargs):
         return orig(repo.unfiltered(), *args, **kwargs)
 
     return wrapper
 
 
 moderncaps = {
     b'lookup',
     b'branchmap',
     b'pushkey',
     b'known',
     b'getbundle',
     b'unbundle',
 }
 legacycaps = moderncaps.union({b'changegroupsubset'})
 
 
 @interfaceutil.implementer(repository.ipeercommandexecutor)
 class localcommandexecutor(object):
     def __init__(self, peer):
         self._peer = peer
         self._sent = False
         self._closed = False
 
     def __enter__(self):
         return self
 
     def __exit__(self, exctype, excvalue, exctb):
         self.close()
 
     def callcommand(self, command, args):
         if self._sent:
             raise error.ProgrammingError(
                 b'callcommand() cannot be used after sendcommands()'
             )
 
         if self._closed:
             raise error.ProgrammingError(
                 b'callcommand() cannot be used after close()'
             )
 
         # We don't need to support anything fancy. Just call the named
         # method on the peer and return a resolved future.
         fn = getattr(self._peer, pycompat.sysstr(command))
 
         f = pycompat.futures.Future()
 
         try:
             result = fn(**pycompat.strkwargs(args))
         except Exception:
             pycompat.future_set_exception_info(f, sys.exc_info()[1:])
         else:
             f.set_result(result)
 
         return f
 
     def sendcommands(self):
         self._sent = True
 
     def close(self):
         self._closed = True
 
 
 @interfaceutil.implementer(repository.ipeercommands)
 class localpeer(repository.peer):
     '''peer for a local repo; reflects only the most recent API'''
 
     def __init__(self, repo, caps=None):
         super(localpeer, self).__init__()
 
         if caps is None:
             caps = moderncaps.copy()
         self._repo = repo.filtered(b'served')
         self.ui = repo.ui
         self._caps = repo._restrictcapabilities(caps)
 
     # Begin of _basepeer interface.
 
     def url(self):
         return self._repo.url()
 
     def local(self):
         return self._repo
 
     def peer(self):
         return self
 
     def canpush(self):
         return True
 
     def close(self):
         self._repo.close()
 
     # End of _basepeer interface.
 
     # Begin of _basewirecommands interface.
 
     def branchmap(self):
         return self._repo.branchmap()
 
     def capabilities(self):
         return self._caps
 
     def clonebundles(self):
         return self._repo.tryread(b'clonebundles.manifest')
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         """Used to test argument passing over the wire"""
         return b"%s %s %s %s %s" % (
             one,
             two,
             pycompat.bytestr(three),
             pycompat.bytestr(four),
             pycompat.bytestr(five),
         )
 
     def getbundle(
         self, source, heads=None, common=None, bundlecaps=None, **kwargs
     ):
         chunks = exchange.getbundlechunks(
             self._repo,
             source,
             heads=heads,
             common=common,
             bundlecaps=bundlecaps,
             **kwargs
         )[1]
         cb = util.chunkbuffer(chunks)
 
         if exchange.bundle2requested(bundlecaps):
             # When requesting a bundle2, getbundle returns a stream to make the
             # wire level function happier. We need to build a proper object
             # from it in local peer.
             return bundle2.getunbundler(self.ui, cb)
         else:
             return changegroup.getunbundler(b'01', cb, None)
 
     def heads(self):
         return self._repo.heads()
 
     def known(self, nodes):
         return self._repo.known(nodes)
 
     def listkeys(self, namespace):
         return self._repo.listkeys(namespace)
 
     def lookup(self, key):
         return self._repo.lookup(key)
 
     def pushkey(self, namespace, key, old, new):
         return self._repo.pushkey(namespace, key, old, new)
 
     def stream_out(self):
         raise error.Abort(_(b'cannot perform stream clone against local peer'))
 
     def unbundle(self, bundle, heads, url):
         """apply a bundle on a repo
 
         This function handles the repo locking itself."""
         try:
             try:
                 bundle = exchange.readbundle(self.ui, bundle, None)
                 ret = exchange.unbundle(self._repo, bundle, heads, b'push', url)
                 if util.safehasattr(ret, b'getchunks'):
                     # This is a bundle20 object, turn it into an unbundler.
                     # This little dance should be dropped eventually when the
                     # API is finally improved.
                     stream = util.chunkbuffer(ret.getchunks())
                     ret = bundle2.getunbundler(self.ui, stream)
                 return ret
             except Exception as exc:
                 # If the exception contains output salvaged from a bundle2
                 # reply, we need to make sure it is printed before continuing
                 # to fail. So we build a bundle2 with such output and consume
                 # it directly.
                 #
                 # This is not very elegant but allows a "simple" solution for
                 # issue4594
                 output = getattr(exc, '_bundle2salvagedoutput', ())
                 if output:
                     bundler = bundle2.bundle20(self._repo.ui)
                     for out in output:
                         bundler.addpart(out)
                     stream = util.chunkbuffer(bundler.getchunks())
                     b = bundle2.getunbundler(self.ui, stream)
                     bundle2.processbundle(self._repo, b)
                 raise
         except error.PushRaced as exc:
             raise error.ResponseError(
                 _(b'push failed:'), stringutil.forcebytestr(exc)
             )
 
     # End of _basewirecommands interface.
 
     # Begin of peer interface.
 
     def commandexecutor(self):
         return localcommandexecutor(self)
 
     # End of peer interface.
 
 
 @interfaceutil.implementer(repository.ipeerlegacycommands)
 class locallegacypeer(localpeer):
     '''peer extension which implements legacy methods too; used for tests with
     restricted capabilities'''
 
     def __init__(self, repo):
         super(locallegacypeer, self).__init__(repo, caps=legacycaps)
 
     # Begin of baselegacywirecommands interface.
 
     def between(self, pairs):
         return self._repo.between(pairs)
 
     def branches(self, nodes):
         return self._repo.branches(nodes)
 
     def changegroup(self, nodes, source):
         outgoing = discovery.outgoing(
             self._repo, missingroots=nodes, missingheads=self._repo.heads()
         )
         return changegroup.makechangegroup(self._repo, outgoing, b'01', source)
 
     def changegroupsubset(self, bases, heads, source):
         outgoing = discovery.outgoing(
             self._repo, missingroots=bases, missingheads=heads
         )
         return changegroup.makechangegroup(self._repo, outgoing, b'01', source)
 
     # End of baselegacywirecommands interface.
 
 
 # Increment the sub-version when the revlog v2 format changes to lock out old
 # clients.
 REVLOGV2_REQUIREMENT = b'exp-revlogv2.1'
 
 # A repository with the sparserevlog feature will have delta chains that
 # can spread over a larger span. Sparse reading cuts these large spans into
 # pieces, so that each piece isn't too big.
 # Without the sparserevlog capability, reading from the repository could use
 # huge amounts of memory, because the whole span would be read at once,
 # including all the intermediate revisions that aren't pertinent for the chain.
 # This is why once a repository has enabled sparse-read, it becomes required.
 SPARSEREVLOG_REQUIREMENT = b'sparserevlog'
 
 # A repository with the sidedataflag requirement will allow to store extra
 # information for revision without altering their original hashes.
 SIDEDATA_REQUIREMENT = b'exp-sidedata-flag'
 
 # A repository with the the copies-sidedata-changeset requirement will store
 # copies related information in changeset's sidedata.
 COPIESSDC_REQUIREMENT = b'exp-copies-sidedata-changeset'
 
 # Functions receiving (ui, features) that extensions can register to impact
 # the ability to load repositories with custom requirements. Only
 # functions defined in loaded extensions are called.
 #
 # The function receives a set of requirement strings that the repository
 # is capable of opening. Functions will typically add elements to the
 # set to reflect that the extension knows how to handle that requirements.
 featuresetupfuncs = set()
 
 
 def makelocalrepository(baseui, path, intents=None):
     """Create a local repository object.
 
     Given arguments needed to construct a local repository, this function
     performs various early repository loading functionality (such as
     reading the ``.hg/requires`` and ``.hg/hgrc`` files), validates that
     the repository can be opened, derives a type suitable for representing
     that repository, and returns an instance of it.
 
     The returned object conforms to the ``repository.completelocalrepository``
     interface.
 
     The repository type is derived by calling a series of factory functions
     for each aspect/interface of the final repository. These are defined by
     ``REPO_INTERFACES``.
 
     Each factory function is called to produce a type implementing a specific
     interface. The cumulative list of returned types will be combined into a
     new type and that type will be instantiated to represent the local
     repository.
 
     The factory functions each receive various state that may be consulted
     as part of deriving a type.
 
     Extensions should wrap these factory functions to customize repository type
     creation. Note that an extension's wrapped function may be called even if
     that extension is not loaded for the repo being constructed. Extensions
     should check if their ``__name__`` appears in the
     ``extensionmodulenames`` set passed to the factory function and no-op if
     not.
     """
     ui = baseui.copy()
     # Prevent copying repo configuration.
     ui.copy = baseui.copy
 
     # Working directory VFS rooted at repository root.
     wdirvfs = vfsmod.vfs(path, expandpath=True, realpath=True)
 
     # Main VFS for .hg/ directory.
     hgpath = wdirvfs.join(b'.hg')
     hgvfs = vfsmod.vfs(hgpath, cacheaudited=True)
 
     # The .hg/ path should exist and should be a directory. All other
     # cases are errors.
     if not hgvfs.isdir():
         try:
             hgvfs.stat()
         except OSError as e:
             if e.errno != errno.ENOENT:
                 raise
 
         raise error.RepoError(_(b'repository %s not found') % path)
 
     # .hg/requires file contains a newline-delimited list of
     # features/capabilities the opener (us) must have in order to use
     # the repository. This file was introduced in Mercurial 0.9.2,
     # which means very old repositories may not have one. We assume
     # a missing file translates to no requirements.
     try:
         requirements = set(hgvfs.read(b'requires').splitlines())
     except IOError as e:
         if e.errno != errno.ENOENT:
             raise
         requirements = set()
 
     # The .hg/hgrc file may load extensions or contain config options
     # that influence repository construction. Attempt to load it and
     # process any new extensions that it may have pulled in.
     if loadhgrc(ui, wdirvfs, hgvfs, requirements):
         afterhgrcload(ui, wdirvfs, hgvfs, requirements)
         extensions.loadall(ui)
         extensions.populateui(ui)
 
     # Set of module names of extensions loaded for this repository.
     extensionmodulenames = {m.__name__ for n, m in extensions.extensions(ui)}
 
     supportedrequirements = gathersupportedrequirements(ui)
 
     # We first validate the requirements are known.
     ensurerequirementsrecognized(requirements, supportedrequirements)
 
     # Then we validate that the known set is reasonable to use together.
     ensurerequirementscompatible(ui, requirements)
 
     # TODO there are unhandled edge cases related to opening repositories with
     # shared storage. If storage is shared, we should also test for requirements
     # compatibility in the pointed-to repo. This entails loading the .hg/hgrc in
     # that repo, as that repo may load extensions needed to open it. This is a
     # bit complicated because we don't want the other hgrc to overwrite settings
     # in this hgrc.
     #
     # This bug is somewhat mitigated by the fact that we copy the .hg/requires
     # file when sharing repos. But if a requirement is added after the share is
     # performed, thereby introducing a new requirement for the opener, we may
     # will not see that and could encounter a run-time error interacting with
     # that shared store since it has an unknown-to-us requirement.
 
     # At this point, we know we should be capable of opening the repository.
     # Now get on with doing that.
 
     features = set()
 
     # The "store" part of the repository holds versioned data. How it is
     # accessed is determined by various requirements. The ``shared`` or
     # ``relshared`` requirements indicate the store lives in the path contained
     # in the ``.hg/sharedpath`` file. This is an absolute path for
     # ``shared`` and relative to ``.hg/`` for ``relshared``.
     if b'shared' in requirements or b'relshared' in requirements:
         sharedpath = hgvfs.read(b'sharedpath').rstrip(b'\n')
         if b'relshared' in requirements:
             sharedpath = hgvfs.join(sharedpath)
 
         sharedvfs = vfsmod.vfs(sharedpath, realpath=True)
 
         if not sharedvfs.exists():
             raise error.RepoError(
                 _(b'.hg/sharedpath points to nonexistent directory %s')
                 % sharedvfs.base
             )
 
         features.add(repository.REPO_FEATURE_SHARED_STORAGE)
 
         storebasepath = sharedvfs.base
         cachepath = sharedvfs.join(b'cache')
     else:
         storebasepath = hgvfs.base
         cachepath = hgvfs.join(b'cache')
     wcachepath = hgvfs.join(b'wcache')
 
     # The store has changed over time and the exact layout is dictated by
     # requirements. The store interface abstracts differences across all
     # of them.
     store = makestore(
         requirements,
         storebasepath,
         lambda base: vfsmod.vfs(base, cacheaudited=True),
     )
     hgvfs.createmode = store.createmode
 
     storevfs = store.vfs
     storevfs.options = resolvestorevfsoptions(ui, requirements, features)
 
     # The cache vfs is used to manage cache files.
     cachevfs = vfsmod.vfs(cachepath, cacheaudited=True)
     cachevfs.createmode = store.createmode
     # The cache vfs is used to manage cache files related to the working copy
     wcachevfs = vfsmod.vfs(wcachepath, cacheaudited=True)
     wcachevfs.createmode = store.createmode
 
     # Now resolve the type for the repository object. We do this by repeatedly
     # calling a factory function to produces types for specific aspects of the
     # repo's operation. The aggregate returned types are used as base classes
     # for a dynamically-derived type, which will represent our new repository.
 
     bases = []
     extrastate = {}
 
     for iface, fn in REPO_INTERFACES:
         # We pass all potentially useful state to give extensions tons of
         # flexibility.
         typ = fn()(
             ui=ui,
             intents=intents,
             requirements=requirements,
             features=features,
             wdirvfs=wdirvfs,
             hgvfs=hgvfs,
             store=store,
             storevfs=storevfs,
             storeoptions=storevfs.options,
             cachevfs=cachevfs,
             wcachevfs=wcachevfs,
             extensionmodulenames=extensionmodulenames,
             extrastate=extrastate,
             baseclasses=bases,
         )
 
         if not isinstance(typ, type):
             raise error.ProgrammingError(
                 b'unable to construct type for %s' % iface
             )
 
         bases.append(typ)
 
     # type() allows you to use characters in type names that wouldn't be
     # recognized as Python symbols in source code. We abuse that to add
     # rich information about our constructed repo.
     name = pycompat.sysstr(
         b'derivedrepo:%s<%s>' % (wdirvfs.base, b','.join(sorted(requirements)))
     )
 
     cls = type(name, tuple(bases), {})
 
     return cls(
         baseui=baseui,
         ui=ui,
         origroot=path,
         wdirvfs=wdirvfs,
         hgvfs=hgvfs,
         requirements=requirements,
         supportedrequirements=supportedrequirements,
         sharedpath=storebasepath,
         store=store,
         cachevfs=cachevfs,
         wcachevfs=wcachevfs,
         features=features,
         intents=intents,
     )
 
 
 def loadhgrc(ui, wdirvfs, hgvfs, requirements):
     """Load hgrc files/content into a ui instance.
 
     This is called during repository opening to load any additional
     config files or settings relevant to the current repository.
 
     Returns a bool indicating whether any additional configs were loaded.
 
     Extensions should monkeypatch this function to modify how per-repo
     configs are loaded. For example, an extension may wish to pull in
     configs from alternate files or sources.
     """
-    if b'HGRCSKIPREPO' in encoding.environ:
+    if not rcutil.use_repo_hgrc():
         return False
     try:
         ui.readconfig(hgvfs.join(b'hgrc'), root=wdirvfs.base)
         return True
     except IOError:
         return False
 
 
 def afterhgrcload(ui, wdirvfs, hgvfs, requirements):
     """Perform additional actions after .hg/hgrc is loaded.
 
     This function is called during repository loading immediately after
     the .hg/hgrc file is loaded and before per-repo extensions are loaded.
 
     The function can be used to validate configs, automatically add
     options (including extensions) based on requirements, etc.
     """
 
     # Map of requirements to list of extensions to load automatically when
     # requirement is present.
     autoextensions = {
         b'largefiles': [b'largefiles'],
         b'lfs': [b'lfs'],
     }
 
     for requirement, names in sorted(autoextensions.items()):
         if requirement not in requirements:
             continue
 
         for name in names:
             if not ui.hasconfig(b'extensions', name):
                 ui.setconfig(b'extensions', name, b'', source=b'autoload')
 
 
 def gathersupportedrequirements(ui):
     """Determine the complete set of recognized requirements."""
     # Start with all requirements supported by this file.
     supported = set(localrepository._basesupported)
 
     # Execute ``featuresetupfuncs`` entries if they belong to an extension
     # relevant to this ui instance.
     modules = {m.__name__ for n, m in extensions.extensions(ui)}
 
     for fn in featuresetupfuncs:
         if fn.__module__ in modules:
             fn(ui, supported)
 
     # Add derived requirements from registered compression engines.
     for name in util.compengines:
         engine = util.compengines[name]
         if engine.available() and engine.revlogheader():
             supported.add(b'exp-compression-%s' % name)
             if engine.name() == b'zstd':
                 supported.add(b'revlog-compression-zstd')
 
     return supported
 
 
 def ensurerequirementsrecognized(requirements, supported):
     """Validate that a set of local requirements is recognized.
 
     Receives a set of requirements. Raises an ``error.RepoError`` if there
     exists any requirement in that set that currently loaded code doesn't
     recognize.
 
     Returns a set of supported requirements.
     """
     missing = set()
 
     for requirement in requirements:
         if requirement in supported:
             continue
 
         if not requirement or not requirement[0:1].isalnum():
             raise error.RequirementError(_(b'.hg/requires file is corrupt'))
 
         missing.add(requirement)
 
     if missing:
         raise error.RequirementError(
             _(b'repository requires features unknown to this Mercurial: %s')
             % b' '.join(sorted(missing)),
             hint=_(
                 b'see https://mercurial-scm.org/wiki/MissingRequirement '
                 b'for more information'
             ),
         )
 
 
 def ensurerequirementscompatible(ui, requirements):
     """Validates that a set of recognized requirements is mutually compatible.
 
     Some requirements may not be compatible with others or require
     config options that aren't enabled. This function is called during
     repository opening to ensure that the set of requirements needed
     to open a repository is sane and compatible with config options.
 
     Extensions can monkeypatch this function to perform additional
     checking.
 
     ``error.RepoError`` should be raised on failure.
     """
     if b'exp-sparse' in requirements and not sparse.enabled:
         raise error.RepoError(
             _(
                 b'repository is using sparse feature but '
                 b'sparse is not enabled; enable the '
                 b'"sparse" extensions to access'
             )
         )
 
 
 def makestore(requirements, path, vfstype):
     """Construct a storage object for a repository."""
     if b'store' in requirements:
         if b'fncache' in requirements:
             return storemod.fncachestore(
                 path, vfstype, b'dotencode' in requirements
             )
 
         return storemod.encodedstore(path, vfstype)
 
     return storemod.basicstore(path, vfstype)
 
 
 def resolvestorevfsoptions(ui, requirements, features):
     """Resolve the options to pass to the store vfs opener.
 
     The returned dict is used to influence behavior of the storage layer.
     """
     options = {}
 
     if b'treemanifest' in requirements:
         options[b'treemanifest'] = True
 
     # experimental config: format.manifestcachesize
     manifestcachesize = ui.configint(b'format', b'manifestcachesize')
     if manifestcachesize is not None:
         options[b'manifestcachesize'] = manifestcachesize
 
     # In the absence of another requirement superseding a revlog-related
     # requirement, we have to assume the repo is using revlog version 0.
     # This revlog format is super old and we don't bother trying to parse
     # opener options for it because those options wouldn't do anything
     # meaningful on such old repos.
     if b'revlogv1' in requirements or REVLOGV2_REQUIREMENT in requirements:
         options.update(resolverevlogstorevfsoptions(ui, requirements, features))
     else:  # explicitly mark repo as using revlogv0
         options[b'revlogv0'] = True
 
     if COPIESSDC_REQUIREMENT in requirements:
         options[b'copies-storage'] = b'changeset-sidedata'
     else:
         writecopiesto = ui.config(b'experimental', b'copies.write-to')
         copiesextramode = (b'changeset-only', b'compatibility')
         if writecopiesto in copiesextramode:
             options[b'copies-storage'] = b'extra'
 
     return options
 
 
 def resolverevlogstorevfsoptions(ui, requirements, features):
     """Resolve opener options specific to revlogs."""
 
     options = {}
     options[b'flagprocessors'] = {}
 
     if b'revlogv1' in requirements:
         options[b'revlogv1'] = True
     if REVLOGV2_REQUIREMENT in requirements:
         options[b'revlogv2'] = True
 
     if b'generaldelta' in requirements:
         options[b'generaldelta'] = True
 
     # experimental config: format.chunkcachesize
     chunkcachesize = ui.configint(b'format', b'chunkcachesize')
     if chunkcachesize is not None:
         options[b'chunkcachesize'] = chunkcachesize
 
     deltabothparents = ui.configbool(
         b'storage', b'revlog.optimize-delta-parent-choice'
     )
     options[b'deltabothparents'] = deltabothparents
 
     lazydelta = ui.configbool(b'storage', b'revlog.reuse-external-delta')
     lazydeltabase = False
     if lazydelta:
         lazydeltabase = ui.configbool(
             b'storage', b'revlog.reuse-external-delta-parent'
         )
     if lazydeltabase is None:
         lazydeltabase = not scmutil.gddeltaconfig(ui)
     options[b'lazydelta'] = lazydelta
     options[b'lazydeltabase'] = lazydeltabase
 
     chainspan = ui.configbytes(b'experimental', b'maxdeltachainspan')
     if 0 <= chainspan:
         options[b'maxdeltachainspan'] = chainspan
 
     mmapindexthreshold = ui.configbytes(b'experimental', b'mmapindexthreshold')
     if mmapindexthreshold is not None:
         options[b'mmapindexthreshold'] = mmapindexthreshold
 
     withsparseread = ui.configbool(b'experimental', b'sparse-read')
     srdensitythres = float(
         ui.config(b'experimental', b'sparse-read.density-threshold')
     )
     srmingapsize = ui.configbytes(b'experimental', b'sparse-read.min-gap-size')
     options[b'with-sparse-read'] = withsparseread
     options[b'sparse-read-density-threshold'] = srdensitythres
     options[b'sparse-read-min-gap-size'] = srmingapsize
 
     sparserevlog = SPARSEREVLOG_REQUIREMENT in requirements
     options[b'sparse-revlog'] = sparserevlog
     if sparserevlog:
         options[b'generaldelta'] = True
 
     sidedata = SIDEDATA_REQUIREMENT in requirements
     options[b'side-data'] = sidedata
 
     maxchainlen = None
     if sparserevlog:
         maxchainlen = revlogconst.SPARSE_REVLOG_MAX_CHAIN_LENGTH
     # experimental config: format.maxchainlen
     maxchainlen = ui.configint(b'format', b'maxchainlen', maxchainlen)
     if maxchainlen is not None:
         options[b'maxchainlen'] = maxchainlen
 
     for r in requirements:
         # we allow multiple compression engine requirement to co-exist because
         # strickly speaking, revlog seems to support mixed compression style.
         #
         # The compression used for new entries will be "the last one"
         prefix = r.startswith
         if prefix(b'revlog-compression-') or prefix(b'exp-compression-'):
             options[b'compengine'] = r.split(b'-', 2)[2]
 
     options[b'zlib.level'] = ui.configint(b'storage', b'revlog.zlib.level')
     if options[b'zlib.level'] is not None:
         if not (0 <= options[b'zlib.level'] <= 9):
             msg = _(b'invalid value for `storage.revlog.zlib.level` config: %d')
             raise error.Abort(msg % options[b'zlib.level'])
     options[b'zstd.level'] = ui.configint(b'storage', b'revlog.zstd.level')
     if options[b'zstd.level'] is not None:
         if not (0 <= options[b'zstd.level'] <= 22):
             msg = _(b'invalid value for `storage.revlog.zstd.level` config: %d')
             raise error.Abort(msg % options[b'zstd.level'])
 
     if repository.NARROW_REQUIREMENT in requirements:
         options[b'enableellipsis'] = True
 
     if ui.configbool(b'experimental', b'rust.index'):
         options[b'rust.index'] = True
 
     return options
 
 
 def makemain(**kwargs):
     """Produce a type conforming to ``ilocalrepositorymain``."""
     return localrepository
 
 
 @interfaceutil.implementer(repository.ilocalrepositoryfilestorage)
 class revlogfilestorage(object):
     """File storage when using revlogs."""
 
     def file(self, path):
         if path[0] == b'/':
             path = path[1:]
 
         return filelog.filelog(self.svfs, path)
 
 
 @interfaceutil.implementer(repository.ilocalrepositoryfilestorage)
 class revlognarrowfilestorage(object):
     """File storage when using revlogs and narrow files."""
 
     def file(self, path):
         if path[0] == b'/':
             path = path[1:]
 
         return filelog.narrowfilelog(self.svfs, path, self._storenarrowmatch)
 
 
 def makefilestorage(requirements, features, **kwargs):
     """Produce a type conforming to ``ilocalrepositoryfilestorage``."""
     features.add(repository.REPO_FEATURE_REVLOG_FILE_STORAGE)
     features.add(repository.REPO_FEATURE_STREAM_CLONE)
 
     if repository.NARROW_REQUIREMENT in requirements:
         return revlognarrowfilestorage
     else:
         return revlogfilestorage
 
 
 # List of repository interfaces and factory functions for them. Each
 # will be called in order during ``makelocalrepository()`` to iteratively
 # derive the final type for a local repository instance. We capture the
 # function as a lambda so we don't hold a reference and the module-level
 # functions can be wrapped.
 REPO_INTERFACES = [
     (repository.ilocalrepositorymain, lambda: makemain),
     (repository.ilocalrepositoryfilestorage, lambda: makefilestorage),
 ]
 
 
 @interfaceutil.implementer(repository.ilocalrepositorymain)
 class localrepository(object):
     """Main class for representing local repositories.
 
     All local repositories are instances of this class.
 
     Constructed on its own, instances of this class are not usable as
     repository objects. To obtain a usable repository object, call
     ``hg.repository()``, ``localrepo.instance()``, or
     ``localrepo.makelocalrepository()``. The latter is the lowest-level.
     ``instance()`` adds support for creating new repositories.
     ``hg.repository()`` adds more extension integration, including calling
     ``reposetup()``. Generally speaking, ``hg.repository()`` should be
     used.
     """
 
     # obsolete experimental requirements:
     #  - manifestv2: An experimental new manifest format that allowed
     #    for stem compression of long paths. Experiment ended up not
     #    being successful (repository sizes went up due to worse delta
     #    chains), and the code was deleted in 4.6.
     supportedformats = {
         b'revlogv1',
         b'generaldelta',
         b'treemanifest',
         COPIESSDC_REQUIREMENT,
         REVLOGV2_REQUIREMENT,
         SIDEDATA_REQUIREMENT,
         SPARSEREVLOG_REQUIREMENT,
         bookmarks.BOOKMARKS_IN_STORE_REQUIREMENT,
     }
     _basesupported = supportedformats | {
         b'store',
         b'fncache',
         b'shared',
         b'relshared',
         b'dotencode',
         b'exp-sparse',
         b'internal-phase',
     }
 
     # list of prefix for file which can be written without 'wlock'
     # Extensions should extend this list when needed
     _wlockfreeprefix = {
         # We migh consider requiring 'wlock' for the next
         # two, but pretty much all the existing code assume
         # wlock is not needed so we keep them excluded for
         # now.
         b'hgrc',
         b'requires',
         # XXX cache is a complicatged business someone
         # should investigate this in depth at some point
         b'cache/',
         # XXX shouldn't be dirstate covered by the wlock?
         b'dirstate',
         # XXX bisect was still a bit too messy at the time
         # this changeset was introduced. Someone should fix
         # the remainig bit and drop this line
         b'bisect.state',
     }
 
     def __init__(
         self,
         baseui,
         ui,
         origroot,
         wdirvfs,
         hgvfs,
         requirements,
         supportedrequirements,
         sharedpath,
         store,
         cachevfs,
         wcachevfs,
         features,
         intents=None,
     ):
         """Create a new local repository instance.
 
         Most callers should use ``hg.repository()``, ``localrepo.instance()``,
         or ``localrepo.makelocalrepository()`` for obtaining a new repository
         object.
 
         Arguments:
 
         baseui
            ``ui.ui`` instance that ``ui`` argument was based off of.
 
         ui
            ``ui.ui`` instance for use by the repository.
 
         origroot
            ``bytes`` path to working directory root of this repository.
 
         wdirvfs
            ``vfs.vfs`` rooted at the working directory.
 
         hgvfs
            ``vfs.vfs`` rooted at .hg/
 
         requirements
            ``set`` of bytestrings representing repository opening requirements.
 
         supportedrequirements
            ``set`` of bytestrings representing repository requirements that we
            know how to open. May be a supetset of ``requirements``.
 
         sharedpath
            ``bytes`` Defining path to storage base directory. Points to a
            ``.hg/`` directory somewhere.
 
         store
            ``store.basicstore`` (or derived) instance providing access to
            versioned storage.
 
         cachevfs
            ``vfs.vfs`` used for cache files.
 
         wcachevfs
            ``vfs.vfs`` used for cache files related to the working copy.
 
         features
            ``set`` of bytestrings defining features/capabilities of this
            instance.
 
         intents
            ``set`` of system strings indicating what this repo will be used
            for.
         """
         self.baseui = baseui
         self.ui = ui
         self.origroot = origroot
         # vfs rooted at working directory.
         self.wvfs = wdirvfs
         self.root = wdirvfs.base
         # vfs rooted at .hg/. Used to access most non-store paths.
         self.vfs = hgvfs
         self.path = hgvfs.base
         self.requirements = requirements
         self.supported = supportedrequirements
         self.sharedpath = sharedpath
         self.store = store
         self.cachevfs = cachevfs
         self.wcachevfs = wcachevfs
         self.features = features
 
         self.filtername = None
 
         if self.ui.configbool(b'devel', b'all-warnings') or self.ui.configbool(
             b'devel', b'check-locks'
         ):
             self.vfs.audit = self._getvfsward(self.vfs.audit)
         # A list of callback to shape the phase if no data were found.
         # Callback are in the form: func(repo, roots) --> processed root.
         # This list it to be filled by extension during repo setup
         self._phasedefaults = []
 
         color.setup(self.ui)
 
         self.spath = self.store.path
         self.svfs = self.store.vfs
         self.sjoin = self.store.join
         if self.ui.configbool(b'devel', b'all-warnings') or self.ui.configbool(
             b'devel', b'check-locks'
         ):
             if util.safehasattr(self.svfs, b'vfs'):  # this is filtervfs
                 self.svfs.vfs.audit = self._getsvfsward(self.svfs.vfs.audit)
             else:  # standard vfs
                 self.svfs.audit = self._getsvfsward(self.svfs.audit)
 
         self._dirstatevalidatewarned = False
 
         self._branchcaches = branchmap.BranchMapCache()
         self._revbranchcache = None
         self._filterpats = {}
         self._datafilters = {}
         self._transref = self._lockref = self._wlockref = None
 
         # A cache for various files under .hg/ that tracks file changes,
         # (used by the filecache decorator)
         #
         # Maps a property name to its util.filecacheentry
         self._filecache = {}
 
         # hold sets of revision to be filtered
         # should be cleared when something might have changed the filter value:
         # - new changesets,
         # - phase change,
         # - new obsolescence marker,
         # - working directory parent change,
         # - bookmark changes
         self.filteredrevcache = {}
 
         # post-dirstate-status hooks
         self._postdsstatus = []
 
         # generic mapping between names and nodes
         self.names = namespaces.namespaces()
 
         # Key to signature value.
         self._sparsesignaturecache = {}
         # Signature to cached matcher instance.
         self._sparsematchercache = {}
 
         self._extrafilterid = repoview.extrafilter(ui)
 
         self.filecopiesmode = None
         if COPIESSDC_REQUIREMENT in self.requirements:
             self.filecopiesmode = b'changeset-sidedata'
 
     def _getvfsward(self, origfunc):
         """build a ward for self.vfs"""
         rref = weakref.ref(self)
 
         def checkvfs(path, mode=None):
             ret = origfunc(path, mode=mode)
             repo = rref()
             if (
                 repo is None
                 or not util.safehasattr(repo, b'_wlockref')
                 or not util.safehasattr(repo, b'_lockref')
             ):
                 return
             if mode in (None, b'r', b'rb'):
                 return
             if path.startswith(repo.path):
                 # truncate name relative to the repository (.hg)
                 path = path[len(repo.path) + 1 :]
             if path.startswith(b'cache/'):
                 msg = b'accessing cache with vfs instead of cachevfs: "%s"'
                 repo.ui.develwarn(msg % path, stacklevel=3, config=b"cache-vfs")
             if path.startswith(b'journal.') or path.startswith(b'undo.'):
                 # journal is covered by 'lock'
                 if repo._currentlock(repo._lockref) is None:
                     repo.ui.develwarn(
                         b'write with no lock: "%s"' % path,
                         stacklevel=3,
                         config=b'check-locks',
                     )
             elif repo._currentlock(repo._wlockref) is None:
                 # rest of vfs files are covered by 'wlock'
                 #
                 # exclude special files
                 for prefix in self._wlockfreeprefix:
                     if path.startswith(prefix):
                         return
                 repo.ui.develwarn(
                     b'write with no wlock: "%s"' % path,
                     stacklevel=3,
                     config=b'check-locks',
                 )
             return ret
 
         return checkvfs
 
     def _getsvfsward(self, origfunc):
         """build a ward for self.svfs"""
         rref = weakref.ref(self)
 
         def checksvfs(path, mode=None):
             ret = origfunc(path, mode=mode)
             repo = rref()
             if repo is None or not util.safehasattr(repo, b'_lockref'):
                 return
             if mode in (None, b'r', b'rb'):
                 return
             if path.startswith(repo.sharedpath):
                 # truncate name relative to the repository (.hg)
                 path = path[len(repo.sharedpath) + 1 :]
             if repo._currentlock(repo._lockref) is None:
                 repo.ui.develwarn(
                     b'write with no lock: "%s"' % path, stacklevel=4
                 )
             return ret
 
         return checksvfs
 
     def close(self):
         self._writecaches()
 
     def _writecaches(self):
         if self._revbranchcache:
             self._revbranchcache.write()
 
     def _restrictcapabilities(self, caps):
         if self.ui.configbool(b'experimental', b'bundle2-advertise'):
             caps = set(caps)
             capsblob = bundle2.encodecaps(
                 bundle2.getrepocaps(self, role=b'client')
             )
             caps.add(b'bundle2=' + urlreq.quote(capsblob))
         return caps
 
     def _writerequirements(self):
         scmutil.writerequires(self.vfs, self.requirements)
 
     # Don't cache auditor/nofsauditor, or you'll end up with reference cycle:
     # self -> auditor -> self._checknested -> self
 
     @property
     def auditor(self):
         # This is only used by context.workingctx.match in order to
         # detect files in subrepos.
         return pathutil.pathauditor(self.root, callback=self._checknested)
 
     @property
     def nofsauditor(self):
         # This is only used by context.basectx.match in order to detect
         # files in subrepos.
         return pathutil.pathauditor(
             self.root, callback=self._checknested, realfs=False, cached=True
         )
 
     def _checknested(self, path):
         """Determine if path is a legal nested repository."""
         if not path.startswith(self.root):
             return False
         subpath = path[len(self.root) + 1 :]
         normsubpath = util.pconvert(subpath)
 
         # XXX: Checking against the current working copy is wrong in
         # the sense that it can reject things like
         #
         #   $ hg cat -r 10 sub/x.txt
         #
         # if sub/ is no longer a subrepository in the working copy
         # parent revision.
         #
         # However, it can of course also allow things that would have
         # been rejected before, such as the above cat command if sub/
         # is a subrepository now, but was a normal directory before.
         # The old path auditor would have rejected by mistake since it
         # panics when it sees sub/.hg/.
         #
         # All in all, checking against the working copy seems sensible
         # since we want to prevent access to nested repositories on
         # the filesystem *now*.
         ctx = self[None]
         parts = util.splitpath(subpath)
         while parts:
             prefix = b'/'.join(parts)
             if prefix in ctx.substate:
                 if prefix == normsubpath:
                     return True
                 else:
                     sub = ctx.sub(prefix)
                     return sub.checknested(subpath[len(prefix) + 1 :])
             else:
                 parts.pop()
         return False
 
     def peer(self):
         return localpeer(self)  # not cached to avoid reference cycle
 
     def unfiltered(self):
         """Return unfiltered version of the repository
 
         Intended to be overwritten by filtered repo."""
         return self
 
     def filtered(self, name, visibilityexceptions=None):
         """Return a filtered version of a repository
 
         The `name` parameter is the identifier of the requested view. This
         will return a repoview object set "exactly" to the specified view.
 
         This function does not apply recursive filtering to a repository. For
         example calling `repo.filtered("served")` will return a repoview using
         the "served" view, regardless of the initial view used by `repo`.
 
         In other word, there is always only one level of `repoview` "filtering".
         """
         if self._extrafilterid is not None and b'%' not in name:
             name = name + b'%' + self._extrafilterid
 
         cls = repoview.newtype(self.unfiltered().__class__)
         return cls(self, name, visibilityexceptions)
 
     @mixedrepostorecache(
         (b'bookmarks', b'plain'),
         (b'bookmarks.current', b'plain'),
         (b'bookmarks', b''),
         (b'00changelog.i', b''),
     )
     def _bookmarks(self):
         # Since the multiple files involved in the transaction cannot be
         # written atomically (with current repository format), there is a race
         # condition here.
         #
         # 1) changelog content A is read
         # 2) outside transaction update changelog to content B
         # 3) outside transaction update bookmark file referring to content B
         # 4) bookmarks file content is read and filtered against changelog-A
         #
         # When this happens, bookmarks against nodes missing from A are dropped.
         #
         # Having this happening during read is not great, but it become worse
         # when this happen during write because the bookmarks to the "unknown"
         # nodes will be dropped for good. However, writes happen within locks.
         # This locking makes it possible to have a race free consistent read.
         # For this purpose data read from disc before locking  are
         # "invalidated" right after the locks are taken. This invalidations are
         # "light", the `filecache` mechanism keep the data in memory and will
         # reuse them if the underlying files did not changed. Not parsing the
         # same data multiple times helps performances.
         #
         # Unfortunately in the case describe above, the files tracked by the
         # bookmarks file cache might not have changed, but the in-memory
         # content is still "wrong" because we used an older changelog content
         # to process the on-disk data. So after locking, the changelog would be
         # refreshed but `_bookmarks` would be preserved.
         # Adding `00changelog.i` to the list of tracked file is not
         # enough, because at the time we build the content for `_bookmarks` in
         # (4), the changelog file has already diverged from the content used
         # for loading `changelog` in (1)
         #
         # To prevent the issue, we force the changelog to be explicitly
         # reloaded while computing `_bookmarks`. The data race can still happen
         # without the lock (with a narrower window), but it would no longer go
         # undetected during the lock time refresh.
         #
         # The new schedule is as follow
         #
         # 1) filecache logic detect that `_bookmarks` needs to be computed
         # 2) cachestat for `bookmarks` and `changelog` are captured (for book)
         # 3) We force `changelog` filecache to be tested
         # 4) cachestat for `changelog` are captured (for changelog)
         # 5) `_bookmarks` is computed and cached
         #
         # The step in (3) ensure we have a changelog at least as recent as the
         # cache stat computed in (1). As a result at locking time:
         #  * if the changelog did not changed since (1) -> we can reuse the data
         #  * otherwise -> the bookmarks get refreshed.
         self._refreshchangelog()
         return bookmarks.bmstore(self)
 
     def _refreshchangelog(self):
         """make sure the in memory changelog match the on-disk one"""
         if 'changelog' in vars(self) and self.currenttransaction() is None:
             del self.changelog
 
     @property
     def _activebookmark(self):
         return self._bookmarks.active
 
     # _phasesets depend on changelog. what we need is to call
     # _phasecache.invalidate() if '00changelog.i' was changed, but it
     # can't be easily expressed in filecache mechanism.
     @storecache(b'phaseroots', b'00changelog.i')
     def _phasecache(self):
         return phases.phasecache(self, self._phasedefaults)
 
     @storecache(b'obsstore')
     def obsstore(self):
         return obsolete.makestore(self.ui, self)
 
     @storecache(b'00changelog.i')
     def changelog(self):
         return self.store.changelog(txnutil.mayhavepending(self.root))
 
     @storecache(b'00manifest.i')
     def manifestlog(self):
         return self.store.manifestlog(self, self._storenarrowmatch)
 
     @repofilecache(b'dirstate')
     def dirstate(self):
         return self._makedirstate()
 
     def _makedirstate(self):
         """Extension point for wrapping the dirstate per-repo."""
         sparsematchfn = lambda: sparse.matcher(self)
 
         return dirstate.dirstate(
             self.vfs, self.ui, self.root, self._dirstatevalidate, sparsematchfn
         )
 
     def _dirstatevalidate(self, node):
         try:
             self.changelog.rev(node)
             return node
         except error.LookupError:
             if not self._dirstatevalidatewarned:
                 self._dirstatevalidatewarned = True
                 self.ui.warn(
                     _(b"warning: ignoring unknown working parent %s!\n")
                     % short(node)
                 )
             return nullid
 
     @storecache(narrowspec.FILENAME)
     def narrowpats(self):
         """matcher patterns for this repository's narrowspec
 
         A tuple of (includes, excludes).
         """
         return narrowspec.load(self)
 
     @storecache(narrowspec.FILENAME)
     def _storenarrowmatch(self):
         if repository.NARROW_REQUIREMENT not in self.requirements:
             return matchmod.always()
         include, exclude = self.narrowpats
         return narrowspec.match(self.root, include=include, exclude=exclude)
 
     @storecache(narrowspec.FILENAME)
     def _narrowmatch(self):
         if repository.NARROW_REQUIREMENT not in self.requirements:
             return matchmod.always()
         narrowspec.checkworkingcopynarrowspec(self)
         include, exclude = self.narrowpats
         return narrowspec.match(self.root, include=include, exclude=exclude)
 
     def narrowmatch(self, match=None, includeexact=False):
         """matcher corresponding the the repo's narrowspec
 
         If `match` is given, then that will be intersected with the narrow
         matcher.
 
         If `includeexact` is True, then any exact matches from `match` will
         be included even if they're outside the narrowspec.
         """
         if match:
             if includeexact and not self._narrowmatch.always():
                 # do not exclude explicitly-specified paths so that they can
                 # be warned later on
                 em = matchmod.exact(match.files())
                 nm = matchmod.unionmatcher([self._narrowmatch, em])
                 return matchmod.intersectmatchers(match, nm)
             return matchmod.intersectmatchers(match, self._narrowmatch)
         return self._narrowmatch
 
     def setnarrowpats(self, newincludes, newexcludes):
         narrowspec.save(self, newincludes, newexcludes)
         self.invalidate(clearfilecache=True)
 
     @unfilteredpropertycache
     def _quick_access_changeid_null(self):
         return {
             b'null': (nullrev, nullid),
             nullrev: (nullrev, nullid),
             nullid: (nullrev, nullid),
         }
 
     @unfilteredpropertycache
     def _quick_access_changeid_wc(self):
         # also fast path access to the working copy parents
         # however, only do it for filter that ensure wc is visible.
         quick = {}
         cl = self.unfiltered().changelog
         for node in self.dirstate.parents():
             if node == nullid:
                 continue
             rev = cl.index.get_rev(node)
             if rev is None:
                 # unknown working copy parent case:
                 #
                 #   skip the fast path and let higher code deal with it
                 continue
             pair = (rev, node)
             quick[rev] = pair
             quick[node] = pair
             # also add the parents of the parents
             for r in cl.parentrevs(rev):
                 if r == nullrev:
                     continue
                 n = cl.node(r)
                 pair = (r, n)
                 quick[r] = pair
                 quick[n] = pair
         p1node = self.dirstate.p1()
         if p1node != nullid:
             quick[b'.'] = quick[p1node]
         return quick
 
     @unfilteredmethod
     def _quick_access_changeid_invalidate(self):
         if '_quick_access_changeid_wc' in vars(self):
             del self.__dict__['_quick_access_changeid_wc']
 
     @property
     def _quick_access_changeid(self):
         """an helper dictionnary for __getitem__ calls
 
         This contains a list of symbol we can recognise right away without
         further processing.
         """
         mapping = self._quick_access_changeid_null
         if self.filtername in repoview.filter_has_wc:
             mapping = mapping.copy()
             mapping.update(self._quick_access_changeid_wc)
         return mapping
 
     def __getitem__(self, changeid):
         # dealing with special cases
         if changeid is None:
             return context.workingctx(self)
         if isinstance(changeid, context.basectx):
             return changeid
 
         # dealing with multiple revisions
         if isinstance(changeid, slice):
             # wdirrev isn't contiguous so the slice shouldn't include it
             return [
                 self[i]
                 for i in pycompat.xrange(*changeid.indices(len(self)))
                 if i not in self.changelog.filteredrevs
             ]
 
         # dealing with some special values
         quick_access = self._quick_access_changeid.get(changeid)
         if quick_access is not None:
             rev, node = quick_access
             return context.changectx(self, rev, node, maybe_filtered=False)
         if changeid == b'tip':
             node = self.changelog.tip()
             rev = self.changelog.rev(node)
             return context.changectx(self, rev, node)
 
         # dealing with arbitrary values
         try:
             if isinstance(changeid, int):
                 node = self.changelog.node(changeid)
                 rev = changeid
             elif changeid == b'.':
                 # this is a hack to delay/avoid loading obsmarkers
                 # when we know that '.' won't be hidden
                 node = self.dirstate.p1()
                 rev = self.unfiltered().changelog.rev(node)
             elif len(changeid) == 20:
                 try:
                     node = changeid
                     rev = self.changelog.rev(changeid)
                 except error.FilteredLookupError:
                     changeid = hex(changeid)  # for the error message
                     raise
                 except LookupError:
                     # check if it might have come from damaged dirstate
                     #
                     # XXX we could avoid the unfiltered if we had a recognizable
                     # exception for filtered changeset access
                     if (
                         self.local()
                         and changeid in self.unfiltered().dirstate.parents()
                     ):
                         msg = _(b"working directory has unknown parent '%s'!")
                         raise error.Abort(msg % short(changeid))
                     changeid = hex(changeid)  # for the error message
                     raise
 
             elif len(changeid) == 40:
                 node = bin(changeid)
                 rev = self.changelog.rev(node)
             else:
                 raise error.ProgrammingError(
                     b"unsupported changeid '%s' of type %s"
                     % (changeid, pycompat.bytestr(type(changeid)))
                 )
 
             return context.changectx(self, rev, node)
 
         except (error.FilteredIndexError, error.FilteredLookupError):
             raise error.FilteredRepoLookupError(
                 _(b"filtered revision '%s'") % pycompat.bytestr(changeid)
             )
         except (IndexError, LookupError):
             raise error.RepoLookupError(
                 _(b"unknown revision '%s'") % pycompat.bytestr(changeid)
             )
         except error.WdirUnsupported:
             return context.workingctx(self)
 
     def __contains__(self, changeid):
         """True if the given changeid exists
 
         error.AmbiguousPrefixLookupError is raised if an ambiguous node
         specified.
         """
         try:
             self[changeid]
             return True
         except error.RepoLookupError:
             return False
 
     def __nonzero__(self):
         return True
 
     __bool__ = __nonzero__
 
     def __len__(self):
         # no need to pay the cost of repoview.changelog
         unfi = self.unfiltered()
         return len(unfi.changelog)
 
     def __iter__(self):
         return iter(self.changelog)
 
     def revs(self, expr, *args):
         '''Find revisions matching a revset.
 
         The revset is specified as a string ``expr`` that may contain
         %-formatting to escape certain types. See ``revsetlang.formatspec``.
 
         Revset aliases from the configuration are not expanded. To expand
         user aliases, consider calling ``scmutil.revrange()`` or
         ``repo.anyrevs([expr], user=True)``.
 
         Returns a smartset.abstractsmartset, which is a list-like interface
         that contains integer revisions.
         '''
         tree = revsetlang.spectree(expr, *args)
         return revset.makematcher(tree)(self)
 
     def set(self, expr, *args):
         '''Find revisions matching a revset and emit changectx instances.
 
         This is a convenience wrapper around ``revs()`` that iterates the
         result and is a generator of changectx instances.
 
         Revset aliases from the configuration are not expanded. To expand
         user aliases, consider calling ``scmutil.revrange()``.
         '''
         for r in self.revs(expr, *args):
             yield self[r]
 
     def anyrevs(self, specs, user=False, localalias=None):
         '''Find revisions matching one of the given revsets.
 
         Revset aliases from the configuration are not expanded by default. To
         expand user aliases, specify ``user=True``. To provide some local
         definitions overriding user aliases, set ``localalias`` to
         ``{name: definitionstring}``.
         '''
         if specs == [b'null']:
             return revset.baseset([nullrev])
         if specs == [b'.']:
             quick_data = self._quick_access_changeid.get(b'.')
             if quick_data is not None:
                 return revset.baseset([quick_data[0]])
         if user:
             m = revset.matchany(
                 self.ui,
                 specs,
                 lookup=revset.lookupfn(self),
                 localalias=localalias,
             )
         else:
             m = revset.matchany(None, specs, localalias=localalias)
         return m(self)
 
     def url(self):
         return b'file:' + self.root
 
     def hook(self, name, throw=False, **args):
         """Call a hook, passing this repo instance.
 
         This a convenience method to aid invoking hooks. Extensions likely
         won't call this unless they have registered a custom hook or are
         replacing code that is expected to call a hook.
         """
         return hook.hook(self.ui, self, name, throw, **args)
 
     @filteredpropertycache
     def _tagscache(self):
         '''Returns a tagscache object that contains various tags related
         caches.'''
 
         # This simplifies its cache management by having one decorated
         # function (this one) and the rest simply fetch things from it.
         class tagscache(object):
             def __init__(self):
                 # These two define the set of tags for this repository. tags
                 # maps tag name to node; tagtypes maps tag name to 'global' or
                 # 'local'. (Global tags are defined by .hgtags across all
                 # heads, and local tags are defined in .hg/localtags.)
                 # They constitute the in-memory cache of tags.
                 self.tags = self.tagtypes = None
 
                 self.nodetagscache = self.tagslist = None
 
         cache = tagscache()
         cache.tags, cache.tagtypes = self._findtags()
 
         return cache
 
     def tags(self):
         '''return a mapping of tag to node'''
         t = {}
         if self.changelog.filteredrevs:
             tags, tt = self._findtags()
         else:
             tags = self._tagscache.tags
         rev = self.changelog.rev
         for k, v in pycompat.iteritems(tags):
             try:
                 # ignore tags to unknown nodes
                 rev(v)
                 t[k] = v
             except (error.LookupError, ValueError):
                 pass
         return t
 
     def _findtags(self):
         '''Do the hard work of finding tags.  Return a pair of dicts
         (tags, tagtypes) where tags maps tag name to node, and tagtypes
         maps tag name to a string like \'global\' or \'local\'.
         Subclasses or extensions are free to add their own tags, but
         should be aware that the returned dicts will be retained for the
         duration of the localrepo object.'''
 
         # XXX what tagtype should subclasses/extensions use?  Currently
         # mq and bookmarks add tags, but do not set the tagtype at all.
         # Should each extension invent its own tag type?  Should there
         # be one tagtype for all such "virtual" tags?  Or is the status
         # quo fine?
 
         # map tag name to (node, hist)
         alltags = tagsmod.findglobaltags(self.ui, self)
         # map tag name to tag type
         tagtypes = dict((tag, b'global') for tag in alltags)
 
         tagsmod.readlocaltags(self.ui, self, alltags, tagtypes)
 
         # Build the return dicts.  Have to re-encode tag names because
         # the tags module always uses UTF-8 (in order not to lose info
         # writing to the cache), but the rest of Mercurial wants them in
         # local encoding.
         tags = {}
         for (name, (node, hist)) in pycompat.iteritems(alltags):
             if node != nullid:
                 tags[encoding.tolocal(name)] = node
         tags[b'tip'] = self.changelog.tip()
         tagtypes = dict(
             [
                 (encoding.tolocal(name), value)
                 for (name, value) in pycompat.iteritems(tagtypes)
             ]
         )
         return (tags, tagtypes)
 
     def tagtype(self, tagname):
         '''
         return the type of the given tag. result can be:
 
         'local'  : a local tag
         'global' : a global tag
         None     : tag does not exist
         '''
 
         return self._tagscache.tagtypes.get(tagname)
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         if not self._tagscache.tagslist:
             l = []
             for t, n in pycompat.iteritems(self.tags()):
                 l.append((self.changelog.rev(n), t, n))
             self._tagscache.tagslist = [(t, n) for r, t, n in sorted(l)]
 
         return self._tagscache.tagslist
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self._tagscache.nodetagscache:
             nodetagscache = {}
             for t, n in pycompat.iteritems(self._tagscache.tags):
                 nodetagscache.setdefault(n, []).append(t)
             for tags in pycompat.itervalues(nodetagscache):
                 tags.sort()
             self._tagscache.nodetagscache = nodetagscache
         return self._tagscache.nodetagscache.get(node, [])
 
     def nodebookmarks(self, node):
         """return the list of bookmarks pointing to the specified node"""
         return self._bookmarks.names(node)
 
     def branchmap(self):
         '''returns a dictionary {branch: [branchheads]} with branchheads
         ordered by increasing revision number'''
         return self._branchcaches[self]
 
     @unfilteredmethod
     def revbranchcache(self):
         if not self._revbranchcache:
             self._revbranchcache = branchmap.revbranchcache(self.unfiltered())
         return self._revbranchcache
 
     def branchtip(self, branch, ignoremissing=False):
         '''return the tip node for a given branch
 
         If ignoremissing is True, then this method will not raise an error.
         This is helpful for callers that only expect None for a missing branch
         (e.g. namespace).
 
         '''
         try:
             return self.branchmap().branchtip(branch)
         except KeyError:
             if not ignoremissing:
                 raise error.RepoLookupError(_(b"unknown branch '%s'") % branch)
             else:
                 pass
 
     def lookup(self, key):
         node = scmutil.revsymbol(self, key).node()
         if node is None:
             raise error.RepoLookupError(_(b"unknown revision '%s'") % key)
         return node
 
     def lookupbranch(self, key):
         if self.branchmap().hasbranch(key):
             return key
 
         return scmutil.revsymbol(self, key).branch()
 
     def known(self, nodes):
         cl = self.changelog
         get_rev = cl.index.get_rev
         filtered = cl.filteredrevs
         result = []
         for n in nodes:
             r = get_rev(n)
             resp = not (r is None or r in filtered)
             result.append(resp)
         return result
 
     def local(self):
         return self
 
     def publishing(self):
         # it's safe (and desirable) to trust the publish flag unconditionally
         # so that we don't finalize changes shared between users via ssh or nfs
         return self.ui.configbool(b'phases', b'publish', untrusted=True)
 
     def cancopy(self):
         # so statichttprepo's override of local() works
         if not self.local():
             return False
         if not self.publishing():
             return True
         # if publishing we can't copy if there is filtered content
         return not self.filtered(b'visible').changelog.filteredrevs
 
     def shared(self):
         '''the type of shared repository (None if not shared)'''
         if self.sharedpath != self.path:
             return b'store'
         return None
 
     def wjoin(self, f, *insidef):
         return self.vfs.reljoin(self.root, f, *insidef)
 
     def setparents(self, p1, p2=nullid):
         self[None].setparents(p1, p2)
         self._quick_access_changeid_invalidate()
 
     def filectx(self, path, changeid=None, fileid=None, changectx=None):
         """changeid must be a changeset revision, if specified.
            fileid can be a file revision or node."""
         return context.filectx(
             self, path, changeid, fileid, changectx=changectx
         )
 
     def getcwd(self):
         return self.dirstate.getcwd()
 
     def pathto(self, f, cwd=None):
         return self.dirstate.pathto(f, cwd)
 
     def _loadfilter(self, filter):
         if filter not in self._filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 if cmd == b'!':
                     continue
                 mf = matchmod.match(self.root, b'', [pat])
                 fn = None
                 params = cmd
                 for name, filterfn in pycompat.iteritems(self._datafilters):
                     if cmd.startswith(name):
                         fn = filterfn
                         params = cmd[len(name) :].lstrip()
                         break
                 if not fn:
                     fn = lambda s, c, **kwargs: procutil.filter(s, c)
                     fn.__name__ = 'commandfilter'
                 # Wrap old filters not supporting keyword arguments
                 if not pycompat.getargspec(fn)[2]:
                     oldfn = fn
                     fn = lambda s, c, oldfn=oldfn, **kwargs: oldfn(s, c)
                     fn.__name__ = 'compat-' + oldfn.__name__
                 l.append((mf, fn, params))
             self._filterpats[filter] = l
         return self._filterpats[filter]
 
     def _filter(self, filterpats, filename, data):
         for mf, fn, cmd in filterpats:
             if mf(filename):
                 self.ui.debug(
                     b"filtering %s through %s\n"
                     % (filename, cmd or pycompat.sysbytes(fn.__name__))
                 )
                 data = fn(data, cmd, ui=self.ui, repo=self, filename=filename)
                 break
 
         return data
 
     @unfilteredpropertycache
     def _encodefilterpats(self):
         return self._loadfilter(b'encode')
 
     @unfilteredpropertycache
     def _decodefilterpats(self):
         return self._loadfilter(b'decode')
 
     def adddatafilter(self, name, filter):
         self._datafilters[name] = filter
 
     def wread(self, filename):
         if self.wvfs.islink(filename):
             data = self.wvfs.readlink(filename)
         else:
             data = self.wvfs.read(filename)
         return self._filter(self._encodefilterpats, filename, data)
 
     def wwrite(self, filename, data, flags, backgroundclose=False, **kwargs):
         """write ``data`` into ``filename`` in the working directory
 
         This returns length of written (maybe decoded) data.
         """
         data = self._filter(self._decodefilterpats, filename, data)
         if b'l' in flags:
             self.wvfs.symlink(data, filename)
         else:
             self.wvfs.write(
                 filename, data, backgroundclose=backgroundclose, **kwargs
             )
             if b'x' in flags:
                 self.wvfs.setflags(filename, False, True)
             else:
                 self.wvfs.setflags(filename, False, False)
         return len(data)
 
     def wwritedata(self, filename, data):
         return self._filter(self._decodefilterpats, filename, data)
 
     def currenttransaction(self):
         """return the current transaction or None if non exists"""
         if self._transref:
             tr = self._transref()
         else:
             tr = None
 
         if tr and tr.running():
             return tr
         return None
 
     def transaction(self, desc, report=None):
         if self.ui.configbool(b'devel', b'all-warnings') or self.ui.configbool(
             b'devel', b'check-locks'
         ):
             if self._currentlock(self._lockref) is None:
                 raise error.ProgrammingError(b'transaction requires locking')
         tr = self.currenttransaction()
         if tr is not None:
             return tr.nest(name=desc)
 
         # abort here if the journal already exists
         if self.svfs.exists(b"journal"):
             raise error.RepoError(
                 _(b"abandoned transaction found"),
                 hint=_(b"run 'hg recover' to clean up transaction"),
             )
 
         idbase = b"%.40f#%f" % (random.random(), time.time())
         ha = hex(hashutil.sha1(idbase).digest())
         txnid = b'TXN:' + ha
         self.hook(b'pretxnopen', throw=True, txnname=desc, txnid=txnid)
 
         self._writejournal(desc)
         renames = [(vfs, x, undoname(x)) for vfs, x in self._journalfiles()]
         if report:
             rp = report
         else:
             rp = self.ui.warn
         vfsmap = {b'plain': self.vfs, b'store': self.svfs}  # root of .hg/
         # we must avoid cyclic reference between repo and transaction.
         reporef = weakref.ref(self)
         # Code to track tag movement
         #
         # Since tags are all handled as file content, it is actually quite hard
         # to track these movement from a code perspective. So we fallback to a
         # tracking at the repository level. One could envision to track changes
         # to the '.hgtags' file through changegroup apply but that fails to
         # cope with case where transaction expose new heads without changegroup
         # being involved (eg: phase movement).
         #
         # For now, We gate the feature behind a flag since this likely comes
         # with performance impacts. The current code run more often than needed
         # and do not use caches as much as it could.  The current focus is on
         # the behavior of the feature so we disable it by default. The flag
         # will be removed when we are happy with the performance impact.
         #
         # Once this feature is no longer experimental move the following
         # documentation to the appropriate help section:
         #
         # The ``HG_TAG_MOVED`` variable will be set if the transaction touched
         # tags (new or changed or deleted tags). In addition the details of
         # these changes are made available in a file at:
         #     ``REPOROOT/.hg/changes/tags.changes``.
         # Make sure you check for HG_TAG_MOVED before reading that file as it
         # might exist from a previous transaction even if no tag were touched
         # in this one. Changes are recorded in a line base format::
         #
         #     <action> <hex-node> <tag-name>\n
         #
         # Actions are defined as follow:
         #   "-R": tag is removed,
         #   "+A": tag is added,
         #   "-M": tag is moved (old value),
         #   "+M": tag is moved (new value),
         tracktags = lambda x: None
         # experimental config: experimental.hook-track-tags
         shouldtracktags = self.ui.configbool(
             b'experimental', b'hook-track-tags'
         )
         if desc != b'strip' and shouldtracktags:
             oldheads = self.changelog.headrevs()
 
             def tracktags(tr2):
                 repo = reporef()
                 oldfnodes = tagsmod.fnoderevs(repo.ui, repo, oldheads)
                 newheads = repo.changelog.headrevs()
                 newfnodes = tagsmod.fnoderevs(repo.ui, repo, newheads)
                 # notes: we compare lists here.
                 # As we do it only once buiding set would not be cheaper
                 changes = tagsmod.difftags(repo.ui, repo, oldfnodes, newfnodes)
                 if changes:
                     tr2.hookargs[b'tag_moved'] = b'1'
                     with repo.vfs(
                         b'changes/tags.changes', b'w', atomictemp=True
                     ) as changesfile:
                         # note: we do not register the file to the transaction
                         # because we needs it to still exist on the transaction
                         # is close (for txnclose hooks)
                         tagsmod.writediff(changesfile, changes)
 
         def validate(tr2):
             """will run pre-closing hooks"""
             # XXX the transaction API is a bit lacking here so we take a hacky
             # path for now
             #
             # We cannot add this as a "pending" hooks since the 'tr.hookargs'
             # dict is copied before these run. In addition we needs the data
             # available to in memory hooks too.
             #
             # Moreover, we also need to make sure this runs before txnclose
             # hooks and there is no "pending" mechanism that would execute
             # logic only if hooks are about to run.
             #
             # Fixing this limitation of the transaction is also needed to track
             # other families of changes (bookmarks, phases, obsolescence).
             #
             # This will have to be fixed before we remove the experimental
             # gating.
             tracktags(tr2)
             repo = reporef()
 
             singleheadopt = (b'experimental', b'single-head-per-branch')
             singlehead = repo.ui.configbool(*singleheadopt)
             if singlehead:
                 singleheadsub = repo.ui.configsuboptions(*singleheadopt)[1]
                 accountclosed = singleheadsub.get(
                     b"account-closed-heads", False
                 )
                 scmutil.enforcesinglehead(repo, tr2, desc, accountclosed)
             if hook.hashook(repo.ui, b'pretxnclose-bookmark'):
                 for name, (old, new) in sorted(
                     tr.changes[b'bookmarks'].items()
                 ):
                     args = tr.hookargs.copy()
                     args.update(bookmarks.preparehookargs(name, old, new))
                     repo.hook(
                         b'pretxnclose-bookmark',
                         throw=True,
                         **pycompat.strkwargs(args)
                     )
             if hook.hashook(repo.ui, b'pretxnclose-phase'):
                 cl = repo.unfiltered().changelog
                 for rev, (old, new) in tr.changes[b'phases'].items():
                     args = tr.hookargs.copy()
                     node = hex(cl.node(rev))
                     args.update(phases.preparehookargs(node, old, new))
                     repo.hook(
                         b'pretxnclose-phase',
                         throw=True,
                         **pycompat.strkwargs(args)
                     )
 
             repo.hook(
                 b'pretxnclose', throw=True, **pycompat.strkwargs(tr.hookargs)
             )
 
         def releasefn(tr, success):
             repo = reporef()
             if repo is None:
                 # If the repo has been GC'd (and this release function is being
                 # called from transaction.__del__), there's not much we can do,
                 # so just leave the unfinished transaction there and let the
                 # user run `hg recover`.
                 return
             if success:
                 # this should be explicitly invoked here, because
                 # in-memory changes aren't written out at closing
                 # transaction, if tr.addfilegenerator (via
                 # dirstate.write or so) isn't invoked while
                 # transaction running
                 repo.dirstate.write(None)
             else:
                 # discard all changes (including ones already written
                 # out) in this transaction
                 narrowspec.restorebackup(self, b'journal.narrowspec')
                 narrowspec.restorewcbackup(self, b'journal.narrowspec.dirstate')
                 repo.dirstate.restorebackup(None, b'journal.dirstate')
 
                 repo.invalidate(clearfilecache=True)
 
         tr = transaction.transaction(
             rp,
             self.svfs,
             vfsmap,
             b"journal",
             b"undo",
             aftertrans(renames),
             self.store.createmode,
             validator=validate,
             releasefn=releasefn,
             checkambigfiles=_cachedfiles,
             name=desc,
         )
         tr.changes[b'origrepolen'] = len(self)
         tr.changes[b'obsmarkers'] = set()
         tr.changes[b'phases'] = {}
         tr.changes[b'bookmarks'] = {}
 
         tr.hookargs[b'txnid'] = txnid
         tr.hookargs[b'txnname'] = desc
         # note: writing the fncache only during finalize mean that the file is
         # outdated when running hooks. As fncache is used for streaming clone,
         # this is not expected to break anything that happen during the hooks.
         tr.addfinalize(b'flush-fncache', self.store.write)
 
         def txnclosehook(tr2):
             """To be run if transaction is successful, will schedule a hook run
             """
             # Don't reference tr2 in hook() so we don't hold a reference.
             # This reduces memory consumption when there are multiple
             # transactions per lock. This can likely go away if issue5045
             # fixes the function accumulation.
             hookargs = tr2.hookargs
 
             def hookfunc(unused_success):
                 repo = reporef()
                 if hook.hashook(repo.ui, b'txnclose-bookmark'):
                     bmchanges = sorted(tr.changes[b'bookmarks'].items())
                     for name, (old, new) in bmchanges:
                         args = tr.hookargs.copy()
                         args.update(bookmarks.preparehookargs(name, old, new))
                         repo.hook(
                             b'txnclose-bookmark',
                             throw=False,
                             **pycompat.strkwargs(args)
                         )
 
                 if hook.hashook(repo.ui, b'txnclose-phase'):
                     cl = repo.unfiltered().changelog
                     phasemv = sorted(tr.changes[b'phases'].items())
                     for rev, (old, new) in phasemv:
                         args = tr.hookargs.copy()
                         node = hex(cl.node(rev))
                         args.update(phases.preparehookargs(node, old, new))
                         repo.hook(
                             b'txnclose-phase',
                             throw=False,
                             **pycompat.strkwargs(args)
                         )
 
                 repo.hook(
                     b'txnclose', throw=False, **pycompat.strkwargs(hookargs)
                 )
 
             reporef()._afterlock(hookfunc)
 
         tr.addfinalize(b'txnclose-hook', txnclosehook)
         # Include a leading "-" to make it happen before the transaction summary
         # reports registered via scmutil.registersummarycallback() whose names
         # are 00-txnreport etc. That way, the caches will be warm when the
         # callbacks run.
         tr.addpostclose(b'-warm-cache', self._buildcacheupdater(tr))
 
         def txnaborthook(tr2):
             """To be run if transaction is aborted
             """
             reporef().hook(
                 b'txnabort', throw=False, **pycompat.strkwargs(tr2.hookargs)
             )
 
         tr.addabort(b'txnabort-hook', txnaborthook)
         # avoid eager cache invalidation. in-memory data should be identical
         # to stored data if transaction has no error.
         tr.addpostclose(b'refresh-filecachestats', self._refreshfilecachestats)
         self._transref = weakref.ref(tr)
         scmutil.registersummarycallback(self, tr, desc)
         return tr
 
     def _journalfiles(self):
         return (
             (self.svfs, b'journal'),
             (self.svfs, b'journal.narrowspec'),
             (self.vfs, b'journal.narrowspec.dirstate'),
             (self.vfs, b'journal.dirstate'),
             (self.vfs, b'journal.branch'),
             (self.vfs, b'journal.desc'),
             (bookmarks.bookmarksvfs(self), b'journal.bookmarks'),
             (self.svfs, b'journal.phaseroots'),
         )
 
     def undofiles(self):
         return [(vfs, undoname(x)) for vfs, x in self._journalfiles()]
 
     @unfilteredmethod
     def _writejournal(self, desc):
         self.dirstate.savebackup(None, b'journal.dirstate')
         narrowspec.savewcbackup(self, b'journal.narrowspec.dirstate')
         narrowspec.savebackup(self, b'journal.narrowspec')
         self.vfs.write(
             b"journal.branch", encoding.fromlocal(self.dirstate.branch())
         )
         self.vfs.write(b"journal.desc", b"%d\n%s\n" % (len(self), desc))
         bookmarksvfs = bookmarks.bookmarksvfs(self)
         bookmarksvfs.write(
             b"journal.bookmarks", bookmarksvfs.tryread(b"bookmarks")
         )
         self.svfs.write(b"journal.phaseroots", self.svfs.tryread(b"phaseroots"))
 
     def recover(self):
         with self.lock():
             if self.svfs.exists(b"journal"):
                 self.ui.status(_(b"rolling back interrupted transaction\n"))
                 vfsmap = {
                     b'': self.svfs,
                     b'plain': self.vfs,
                 }
                 transaction.rollback(
                     self.svfs,
                     vfsmap,
                     b"journal",
                     self.ui.warn,
                     checkambigfiles=_cachedfiles,
                 )
                 self.invalidate()
                 return True
             else:
                 self.ui.warn(_(b"no interrupted transaction available\n"))
                 return False
 
     def rollback(self, dryrun=False, force=False):
         wlock = lock = dsguard = None
         try:
             wlock = self.wlock()
             lock = self.lock()
             if self.svfs.exists(b"undo"):
                 dsguard = dirstateguard.dirstateguard(self, b'rollback')
 
                 return self._rollback(dryrun, force, dsguard)
             else:
                 self.ui.warn(_(b"no rollback information available\n"))
                 return 1
         finally:
             release(dsguard, lock, wlock)
 
     @unfilteredmethod  # Until we get smarter cache management
     def _rollback(self, dryrun, force, dsguard):
         ui = self.ui
         try:
             args = self.vfs.read(b'undo.desc').splitlines()
             (oldlen, desc, detail) = (int(args[0]), args[1], None)
             if len(args) >= 3:
                 detail = args[2]
             oldtip = oldlen - 1
 
             if detail and ui.verbose:
                 msg = _(
                     b'repository tip rolled back to revision %d'
                     b' (undo %s: %s)\n'
                 ) % (oldtip, desc, detail)
             else:
                 msg = _(
                     b'repository tip rolled back to revision %d (undo %s)\n'
                 ) % (oldtip, desc)
         except IOError:
             msg = _(b'rolling back unknown transaction\n')
             desc = None
 
         if not force and self[b'.'] != self[b'tip'] and desc == b'commit':
             raise error.Abort(
                 _(
                     b'rollback of last commit while not checked out '
                     b'may lose data'
                 ),
                 hint=_(b'use -f to force'),
             )
 
         ui.status(msg)
         if dryrun:
             return 0
 
         parents = self.dirstate.parents()
         self.destroying()
         vfsmap = {b'plain': self.vfs, b'': self.svfs}
         transaction.rollback(
             self.svfs, vfsmap, b'undo', ui.warn, checkambigfiles=_cachedfiles
         )
         bookmarksvfs = bookmarks.bookmarksvfs(self)
         if bookmarksvfs.exists(b'undo.bookmarks'):
             bookmarksvfs.rename(
                 b'undo.bookmarks', b'bookmarks', checkambig=True
             )
         if self.svfs.exists(b'undo.phaseroots'):
             self.svfs.rename(b'undo.phaseroots', b'phaseroots', checkambig=True)
         self.invalidate()
 
         has_node = self.changelog.index.has_node
         parentgone = any(not has_node(p) for p in parents)
         if parentgone:
             # prevent dirstateguard from overwriting already restored one
             dsguard.close()
 
             narrowspec.restorebackup(self, b'undo.narrowspec')
             narrowspec.restorewcbackup(self, b'undo.narrowspec.dirstate')
             self.dirstate.restorebackup(None, b'undo.dirstate')
             try:
                 branch = self.vfs.read(b'undo.branch')
                 self.dirstate.setbranch(encoding.tolocal(branch))
             except IOError:
                 ui.warn(
                     _(
                         b'named branch could not be reset: '
                         b'current branch is still \'%s\'\n'
                     )
                     % self.dirstate.branch()
                 )
 
             parents = tuple([p.rev() for p in self[None].parents()])
             if len(parents) > 1:
                 ui.status(
                     _(
                         b'working directory now based on '
                         b'revisions %d and %d\n'
                     )
                     % parents
                 )
             else:
                 ui.status(
                     _(b'working directory now based on revision %d\n') % parents
                 )
             mergemod.mergestate.clean(self, self[b'.'].node())
 
         # TODO: if we know which new heads may result from this rollback, pass
         # them to destroy(), which will prevent the branchhead cache from being
         # invalidated.
         self.destroyed()
         return 0
 
     def _buildcacheupdater(self, newtransaction):
         """called during transaction to build the callback updating cache
 
         Lives on the repository to help extension who might want to augment
         this logic. For this purpose, the created transaction is passed to the
         method.
         """
         # we must avoid cyclic reference between repo and transaction.
         reporef = weakref.ref(self)
 
         def updater(tr):
             repo = reporef()
             repo.updatecaches(tr)
 
         return updater
 
     @unfilteredmethod
     def updatecaches(self, tr=None, full=False):
         """warm appropriate caches
 
         If this function is called after a transaction closed. The transaction
         will be available in the 'tr' argument. This can be used to selectively
         update caches relevant to the changes in that transaction.
 
         If 'full' is set, make sure all caches the function knows about have
         up-to-date data. Even the ones usually loaded more lazily.
         """
         if tr is not None and tr.hookargs.get(b'source') == b'strip':
             # During strip, many caches are invalid but
             # later call to `destroyed` will refresh them.
             return
 
         if tr is None or tr.changes[b'origrepolen'] < len(self):
             # accessing the 'ser ved' branchmap should refresh all the others,
             self.ui.debug(b'updating the branch cache\n')
             self.filtered(b'served').branchmap()
             self.filtered(b'served.hidden').branchmap()
 
         if full:
             unfi = self.unfiltered()
             rbc = unfi.revbranchcache()
             for r in unfi.changelog:
                 rbc.branchinfo(r)
             rbc.write()
 
             # ensure the working copy parents are in the manifestfulltextcache
             for ctx in self[b'.'].parents():
                 ctx.manifest()  # accessing the manifest is enough
 
             # accessing fnode cache warms the cache
             tagsmod.fnoderevs(self.ui, unfi, unfi.changelog.revs())
             # accessing tags warm the cache
             self.tags()
             self.filtered(b'served').tags()
 
             # The `full` arg is documented as updating even the lazily-loaded
             # caches immediately, so we're forcing a write to cause these caches
             # to be warmed up even if they haven't explicitly been requested
             # yet (if they've never been used by hg, they won't ever have been
             # written, even if they're a subset of another kind of cache that
             # *has* been used).
             for filt in repoview.filtertable.keys():
                 filtered = self.filtered(filt)
                 filtered.branchmap().write(filtered)
 
     def invalidatecaches(self):
 
         if '_tagscache' in vars(self):
             # can't use delattr on proxy
             del self.__dict__['_tagscache']
 
         self._branchcaches.clear()
         self.invalidatevolatilesets()
         self._sparsesignaturecache.clear()
 
     def invalidatevolatilesets(self):
         self.filteredrevcache.clear()
         obsolete.clearobscaches(self)
         self._quick_access_changeid_invalidate()
 
     def invalidatedirstate(self):
         '''Invalidates the dirstate, causing the next call to dirstate
         to check if it was modified since the last time it was read,
         rereading it if it has.
 
         This is different to dirstate.invalidate() that it doesn't always
         rereads the dirstate. Use dirstate.invalidate() if you want to
         explicitly read the dirstate again (i.e. restoring it to a previous
         known good state).'''
         if hasunfilteredcache(self, 'dirstate'):
             for k in self.dirstate._filecache:
                 try:
                     delattr(self.dirstate, k)
                 except AttributeError:
                     pass
             delattr(self.unfiltered(), 'dirstate')
 
     def invalidate(self, clearfilecache=False):
         '''Invalidates both store and non-store parts other than dirstate
 
         If a transaction is running, invalidation of store is omitted,
         because discarding in-memory changes might cause inconsistency
         (e.g. incomplete fncache causes unintentional failure, but
         redundant one doesn't).
         '''
         unfiltered = self.unfiltered()  # all file caches are stored unfiltered
         for k in list(self._filecache.keys()):
             # dirstate is invalidated separately in invalidatedirstate()
             if k == b'dirstate':
                 continue
             if (
                 k == b'changelog'
                 and self.currenttransaction()
                 and self.changelog._delayed
             ):
                 # The changelog object may store unwritten revisions. We don't
                 # want to lose them.
                 # TODO: Solve the problem instead of working around it.
                 continue
 
             if clearfilecache:
                 del self._filecache[k]
             try:
                 delattr(unfiltered, k)
             except AttributeError:
                 pass
         self.invalidatecaches()
         if not self.currenttransaction():
             # TODO: Changing contents of store outside transaction
             # causes inconsistency. We should make in-memory store
             # changes detectable, and abort if changed.
             self.store.invalidatecaches()
 
     def invalidateall(self):
         '''Fully invalidates both store and non-store parts, causing the
         subsequent operation to reread any outside changes.'''
         # extension should hook this to invalidate its caches
         self.invalidate()
         self.invalidatedirstate()
 
     @unfilteredmethod
     def _refreshfilecachestats(self, tr):
         """Reload stats of cached files so that they are flagged as valid"""
         for k, ce in self._filecache.items():
             k = pycompat.sysstr(k)
             if k == 'dirstate' or k not in self.__dict__:
                 continue
             ce.refresh()
 
     def _lock(
         self,
         vfs,
         lockname,
         wait,
         releasefn,
         acquirefn,
         desc,
         inheritchecker=None,
         parentenvvar=None,
     ):
         parentlock = None
         # the contents of parentenvvar are used by the underlying lock to
         # determine whether it can be inherited
         if parentenvvar is not None:
             parentlock = encoding.environ.get(parentenvvar)
 
         timeout = 0
         warntimeout = 0
         if wait:
             timeout = self.ui.configint(b"ui", b"timeout")
             warntimeout = self.ui.configint(b"ui", b"timeout.warn")
         # internal config: ui.signal-safe-lock
         signalsafe = self.ui.configbool(b'ui', b'signal-safe-lock')
 
         l = lockmod.trylock(
             self.ui,
             vfs,
             lockname,
             timeout,
             warntimeout,
             releasefn=releasefn,
             acquirefn=acquirefn,
             desc=desc,
             inheritchecker=inheritchecker,
             parentlock=parentlock,
             signalsafe=signalsafe,
         )
         return l
 
     def _afterlock(self, callback):
         """add a callback to be run when the repository is fully unlocked
 
         The callback will be executed when the outermost lock is released
         (with wlock being higher level than 'lock')."""
         for ref in (self._wlockref, self._lockref):
             l = ref and ref()
             if l and l.held:
                 l.postrelease.append(callback)
                 break
         else:  # no lock have been found.
             callback(True)
 
     def lock(self, wait=True):
         '''Lock the repository store (.hg/store) and return a weak reference
         to the lock. Use this before modifying the store (e.g. committing or
         stripping). If you are opening a transaction, get a lock as well.)
 
         If both 'lock' and 'wlock' must be acquired, ensure you always acquires
         'wlock' first to avoid a dead-lock hazard.'''
         l = self._currentlock(self._lockref)
         if l is not None:
             l.lock()
             return l
 
         l = self._lock(
             vfs=self.svfs,
             lockname=b"lock",
             wait=wait,
             releasefn=None,
             acquirefn=self.invalidate,
             desc=_(b'repository %s') % self.origroot,
         )
         self._lockref = weakref.ref(l)
         return l
 
     def _wlockchecktransaction(self):
         if self.currenttransaction() is not None:
             raise error.LockInheritanceContractViolation(
                 b'wlock cannot be inherited in the middle of a transaction'
             )
 
     def wlock(self, wait=True):
         '''Lock the non-store parts of the repository (everything under
         .hg except .hg/store) and return a weak reference to the lock.
 
         Use this before modifying files in .hg.
 
         If both 'lock' and 'wlock' must be acquired, ensure you always acquires
         'wlock' first to avoid a dead-lock hazard.'''
         l = self._wlockref and self._wlockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         # We do not need to check for non-waiting lock acquisition.  Such
         # acquisition would not cause dead-lock as they would just fail.
         if wait and (
             self.ui.configbool(b'devel', b'all-warnings')
             or self.ui.configbool(b'devel', b'check-locks')
         ):
             if self._currentlock(self._lockref) is not None:
                 self.ui.develwarn(b'"wlock" acquired after "lock"')
 
         def unlock():
             if self.dirstate.pendingparentchange():
                 self.dirstate.invalidate()
             else:
                 self.dirstate.write(None)
 
             self._filecache[b'dirstate'].refresh()
 
         l = self._lock(
             self.vfs,
             b"wlock",
             wait,
             unlock,
             self.invalidatedirstate,
             _(b'working directory of %s') % self.origroot,
             inheritchecker=self._wlockchecktransaction,
             parentenvvar=b'HG_WLOCK_LOCKER',
         )
         self._wlockref = weakref.ref(l)
         return l
 
     def _currentlock(self, lockref):
         """Returns the lock if it's held, or None if it's not."""
         if lockref is None:
             return None
         l = lockref()
         if l is None or not l.held:
             return None
         return l
 
     def currentwlock(self):
         """Returns the wlock if it's held, or None if it's not."""
         return self._currentlock(self._wlockref)
 
     def _filecommit(
         self,
         fctx,
         manifest1,
         manifest2,
         linkrev,
         tr,
         changelist,
         includecopymeta,
     ):
         """
         commit an individual file as part of a larger transaction
         """
 
         fname = fctx.path()
         fparent1 = manifest1.get(fname, nullid)
         fparent2 = manifest2.get(fname, nullid)
         if isinstance(fctx, context.filectx):
             node = fctx.filenode()
             if node in [fparent1, fparent2]:
                 self.ui.debug(b'reusing %s filelog entry\n' % fname)
                 if (
                     fparent1 != nullid
                     and manifest1.flags(fname) != fctx.flags()
                 ) or (
                     fparent2 != nullid
                     and manifest2.flags(fname) != fctx.flags()
                 ):
                     changelist.append(fname)
                 return node
 
         flog = self.file(fname)
         meta = {}
         cfname = fctx.copysource()
         if cfname and cfname != fname:
             # Mark the new revision of this file as a copy of another
             # file.  This copy data will effectively act as a parent
             # of this new revision.  If this is a merge, the first
             # parent will be the nullid (meaning "look up the copy data")
             # and the second one will be the other parent.  For example:
             #
             # 0 --- 1 --- 3   rev1 changes file foo
             #   \       /     rev2 renames foo to bar and changes it
             #    \- 2 -/      rev3 should have bar with all changes and
             #                      should record that bar descends from
             #                      bar in rev2 and foo in rev1
             #
             # this allows this merge to succeed:
             #
             # 0 --- 1 --- 3   rev4 reverts the content change from rev2
             #   \       /     merging rev3 and rev4 should use bar@rev2
             #    \- 2 --- 4        as the merge base
             #
 
             cnode = manifest1.get(cfname)
             newfparent = fparent2
 
             if manifest2:  # branch merge
                 if fparent2 == nullid or cnode is None:  # copied on remote side
                     if cfname in manifest2:
                         cnode = manifest2[cfname]
                         newfparent = fparent1
 
             # Here, we used to search backwards through history to try to find
             # where the file copy came from if the source of a copy was not in
             # the parent directory. However, this doesn't actually make sense to
             # do (what does a copy from something not in your working copy even
             # mean?) and it causes bugs (eg, issue4476). Instead, we will warn
             # the user that copy information was dropped, so if they didn't
             # expect this outcome it can be fixed, but this is the correct
             # behavior in this circumstance.
 
             if cnode:
                 self.ui.debug(
                     b" %s: copy %s:%s\n" % (fname, cfname, hex(cnode))
                 )
                 if includecopymeta:
                     meta[b"copy"] = cfname
                     meta[b"copyrev"] = hex(cnode)
                 fparent1, fparent2 = nullid, newfparent
             else:
                 self.ui.warn(
                     _(
                         b"warning: can't find ancestor for '%s' "
                         b"copied from '%s'!\n"
                     )
                     % (fname, cfname)
                 )
 
         elif fparent1 == nullid:
             fparent1, fparent2 = fparent2, nullid
         elif fparent2 != nullid:
             # is one parent an ancestor of the other?
             fparentancestors = flog.commonancestorsheads(fparent1, fparent2)
             if fparent1 in fparentancestors:
                 fparent1, fparent2 = fparent2, nullid
             elif fparent2 in fparentancestors:
                 fparent2 = nullid
 
         # is the file changed?
         text = fctx.data()
         if fparent2 != nullid or flog.cmp(fparent1, text) or meta:
             changelist.append(fname)
             return flog.add(text, meta, tr, linkrev, fparent1, fparent2)
         # are just the flags changed during merge?
         elif fname in manifest1 and manifest1.flags(fname) != fctx.flags():
             changelist.append(fname)
 
         return fparent1
 
     def checkcommitpatterns(self, wctx, match, status, fail):
         """check for commit arguments that aren't committable"""
         if match.isexact() or match.prefix():
             matched = set(status.modified + status.added + status.removed)
 
             for f in match.files():
                 f = self.dirstate.normalize(f)
                 if f == b'.' or f in matched or f in wctx.substate:
                     continue
                 if f in status.deleted:
                     fail(f, _(b'file not found!'))
                 # Is it a directory that exists or used to exist?
                 if self.wvfs.isdir(f) or wctx.p1().hasdir(f):
                     d = f + b'/'
                     for mf in matched:
                         if mf.startswith(d):
                             break
                     else:
                         fail(f, _(b"no match under directory!"))
                 elif f not in self.dirstate:
                     fail(f, _(b"file not tracked!"))
 
     @unfilteredmethod
     def commit(
         self,
         text=b"",
         user=None,
         date=None,
         match=None,
         force=False,
         editor=None,
         extra=None,
     ):
         """Add a new revision to current repository.
 
         Revision information is gathered from the working directory,
         match can be used to filter the committed files. If editor is
         supplied, it is called to get a commit message.
         """
         if extra is None:
             extra = {}
 
         def fail(f, msg):
             raise error.Abort(b'%s: %s' % (f, msg))
 
         if not match:
             match = matchmod.always()
 
         if not force:
             match.bad = fail
 
         # lock() for recent changelog (see issue4368)
         with self.wlock(), self.lock():
             wctx = self[None]
             merge = len(wctx.parents()) > 1
 
             if not force and merge and not match.always():
                 raise error.Abort(
                     _(
                         b'cannot partially commit a merge '
                         b'(do not specify files or patterns)'
                     )
                 )
 
             status = self.status(match=match, clean=force)
             if force:
                 status.modified.extend(
                     status.clean
                 )  # mq may commit clean files
 
             # check subrepos
             subs, commitsubs, newstate = subrepoutil.precommit(
                 self.ui, wctx, status, match, force=force
             )
 
             # make sure all explicit patterns are matched
             if not force:
                 self.checkcommitpatterns(wctx, match, status, fail)
 
             cctx = context.workingcommitctx(
                 self, status, text, user, date, extra
             )
 
             # internal config: ui.allowemptycommit
             allowemptycommit = (
                 wctx.branch() != wctx.p1().branch()
                 or extra.get(b'close')
                 or merge
                 or cctx.files()
                 or self.ui.configbool(b'ui', b'allowemptycommit')
             )
             if not allowemptycommit:
                 return None
 
             if merge and cctx.deleted():
                 raise error.Abort(_(b"cannot commit merge with missing files"))
 
             ms = mergemod.mergestate.read(self)
             mergeutil.checkunresolved(ms)
 
             if editor:
                 cctx._text = editor(self, cctx, subs)
             edited = text != cctx._text
 
             # Save commit message in case this transaction gets rolled back
             # (e.g. by a pretxncommit hook).  Leave the content alone on
             # the assumption that the user will use the same editor again.
             msgfn = self.savecommitmessage(cctx._text)
 
             # commit subs and write new state
             if subs:
                 uipathfn = scmutil.getuipathfn(self)
                 for s in sorted(commitsubs):
                     sub = wctx.sub(s)
                     self.ui.status(
                         _(b'committing subrepository %s\n')
                         % uipathfn(subrepoutil.subrelpath(sub))
                     )
                     sr = sub.commit(cctx._text, user, date)
                     newstate[s] = (newstate[s][0], sr)
                 subrepoutil.writestate(self, newstate)
 
             p1, p2 = self.dirstate.parents()
             hookp1, hookp2 = hex(p1), (p2 != nullid and hex(p2) or b'')
             try:
                 self.hook(
                     b"precommit", throw=True, parent1=hookp1, parent2=hookp2
                 )
                 with self.transaction(b'commit'):
                     ret = self.commitctx(cctx, True)
                     # update bookmarks, dirstate and mergestate
                     bookmarks.update(self, [p1, p2], ret)
                     cctx.markcommitted(ret)
                     ms.reset()
             except:  # re-raises
                 if edited:
                     self.ui.write(
                         _(b'note: commit message saved in %s\n') % msgfn
                     )
                 raise
 
         def commithook(unused_success):
             # hack for command that use a temporary commit (eg: histedit)
             # temporary commit got stripped before hook release
             if self.changelog.hasnode(ret):
                 self.hook(
                     b"commit", node=hex(ret), parent1=hookp1, parent2=hookp2
                 )
 
         self._afterlock(commithook)
         return ret
 
     @unfilteredmethod
     def commitctx(self, ctx, error=False, origctx=None):
         """Add a new revision to current repository.
         Revision information is passed via the context argument.
 
         ctx.files() should list all files involved in this commit, i.e.
         modified/added/removed files. On merge, it may be wider than the
         ctx.files() to be committed, since any file nodes derived directly
         from p1 or p2 are excluded from the committed ctx.files().
 
         origctx is for convert to work around the problem that bug
         fixes to the files list in changesets change hashes. For
         convert to be the identity, it can pass an origctx and this
         function will use the same files list when it makes sense to
         do so.
         """
 
         p1, p2 = ctx.p1(), ctx.p2()
         user = ctx.user()
 
         if self.filecopiesmode == b'changeset-sidedata':
             writechangesetcopy = True
             writefilecopymeta = True
             writecopiesto = None
         else:
             writecopiesto = self.ui.config(b'experimental', b'copies.write-to')
             writefilecopymeta = writecopiesto != b'changeset-only'
             writechangesetcopy = writecopiesto in (
                 b'changeset-only',
                 b'compatibility',
             )
         p1copies, p2copies = None, None
         if writechangesetcopy:
             p1copies = ctx.p1copies()
             p2copies = ctx.p2copies()
         filesadded, filesremoved = None, None
         with self.lock(), self.transaction(b"commit") as tr:
             trp = weakref.proxy(tr)
 
             if ctx.manifestnode():
                 # reuse an existing manifest revision
                 self.ui.debug(b'reusing known manifest\n')
                 mn = ctx.manifestnode()
                 files = ctx.files()
                 if writechangesetcopy:
                     filesadded = ctx.filesadded()
                     filesremoved = ctx.filesremoved()
             elif ctx.files():
                 m1ctx = p1.manifestctx()
                 m2ctx = p2.manifestctx()
                 mctx = m1ctx.copy()
 
                 m = mctx.read()
                 m1 = m1ctx.read()
                 m2 = m2ctx.read()
 
                 # check in files
                 added = []
                 changed = []
                 removed = list(ctx.removed())
                 linkrev = len(self)
                 self.ui.note(_(b"committing files:\n"))
                 uipathfn = scmutil.getuipathfn(self)
                 for f in sorted(ctx.modified() + ctx.added()):
                     self.ui.note(uipathfn(f) + b"\n")
                     try:
                         fctx = ctx[f]
                         if fctx is None:
                             removed.append(f)
                         else:
                             added.append(f)
                             m[f] = self._filecommit(
                                 fctx,
                                 m1,
                                 m2,
                                 linkrev,
                                 trp,
                                 changed,
                                 writefilecopymeta,
                             )
                             m.setflag(f, fctx.flags())
                     except OSError:
                         self.ui.warn(
                             _(b"trouble committing %s!\n") % uipathfn(f)
                         )
                         raise
                     except IOError as inst:
                         errcode = getattr(inst, 'errno', errno.ENOENT)
                         if error or errcode and errcode != errno.ENOENT:
                             self.ui.warn(
                                 _(b"trouble committing %s!\n") % uipathfn(f)
                             )
                         raise
 
                 # update manifest
                 removed = [f for f in removed if f in m1 or f in m2]
                 drop = sorted([f for f in removed if f in m])
                 for f in drop:
                     del m[f]
                 if p2.rev() != nullrev:
 
                     @util.cachefunc
                     def mas():
                         p1n = p1.node()
                         p2n = p2.node()
                         cahs = self.changelog.commonancestorsheads(p1n, p2n)
                         if not cahs:
                             cahs = [nullrev]
                         return [self[r].manifest() for r in cahs]
 
                     def deletionfromparent(f):
                         # When a file is removed relative to p1 in a merge, this
                         # function determines whether the absence is due to a
                         # deletion from a parent, or whether the merge commit
                         # itself deletes the file. We decide this by doing a
                         # simplified three way merge of the manifest entry for
                         # the file. There are two ways we decide the merge
                         # itself didn't delete a file:
                         # - neither parent (nor the merge) contain the file
                         # - exactly one parent contains the file, and that
                         #   parent has the same filelog entry as the merge
                         #   ancestor (or all of them if there two). In other
                         #   words, that parent left the file unchanged while the
                         #   other one deleted it.
                         # One way to think about this is that deleting a file is
                         # similar to emptying it, so the list of changed files
                         # should be similar either way. The computation
                         # described above is not done directly in _filecommit
                         # when creating the list of changed files, however
                         # it does something very similar by comparing filelog
                         # nodes.
                         if f in m1:
                             return f not in m2 and all(
                                 f in ma and ma.find(f) == m1.find(f)
                                 for ma in mas()
                             )
                         elif f in m2:
                             return all(
                                 f in ma and ma.find(f) == m2.find(f)
                                 for ma in mas()
                             )
                         else:
                             return True
 
                     removed = [f for f in removed if not deletionfromparent(f)]
 
                 files = changed + removed
                 md = None
                 if not files:
                     # if no "files" actually changed in terms of the changelog,
                     # try hard to detect unmodified manifest entry so that the
                     # exact same commit can be reproduced later on convert.
                     md = m1.diff(m, scmutil.matchfiles(self, ctx.files()))
                 if not files and md:
                     self.ui.debug(
                         b'not reusing manifest (no file change in '
                         b'changelog, but manifest differs)\n'
                     )
                 if files or md:
                     self.ui.note(_(b"committing manifest\n"))
                     # we're using narrowmatch here since it's already applied at
                     # other stages (such as dirstate.walk), so we're already
                     # ignoring things outside of narrowspec in most cases. The
                     # one case where we might have files outside the narrowspec
                     # at this point is merges, and we already error out in the
                     # case where the merge has files outside of the narrowspec,
                     # so this is safe.
                     mn = mctx.write(
                         trp,
                         linkrev,
                         p1.manifestnode(),
                         p2.manifestnode(),
                         added,
                         drop,
                         match=self.narrowmatch(),
                     )
 
                     if writechangesetcopy:
                         filesadded = [
                             f for f in changed if not (f in m1 or f in m2)
                         ]
                         filesremoved = removed
                 else:
                     self.ui.debug(
                         b'reusing manifest from p1 (listed files '
                         b'actually unchanged)\n'
                     )
                     mn = p1.manifestnode()
             else:
                 self.ui.debug(b'reusing manifest from p1 (no file change)\n')
                 mn = p1.manifestnode()
                 files = []
 
             if writecopiesto == b'changeset-only':
                 # If writing only to changeset extras, use None to indicate that
                 # no entry should be written. If writing to both, write an empty
                 # entry to prevent the reader from falling back to reading
                 # filelogs.
                 p1copies = p1copies or None
                 p2copies = p2copies or None
                 filesadded = filesadded or None
                 filesremoved = filesremoved or None
 
             if origctx and origctx.manifestnode() == mn:
                 files = origctx.files()
 
             # update changelog
             self.ui.note(_(b"committing changelog\n"))
             self.changelog.delayupdate(tr)
             n = self.changelog.add(
                 mn,
                 files,
                 ctx.description(),
                 trp,
                 p1.node(),
                 p2.node(),
                 user,
                 ctx.date(),
                 ctx.extra().copy(),
                 p1copies,
                 p2copies,
                 filesadded,
                 filesremoved,
             )
             xp1, xp2 = p1.hex(), p2 and p2.hex() or b''
             self.hook(
                 b'pretxncommit',
                 throw=True,
                 node=hex(n),
                 parent1=xp1,
                 parent2=xp2,
             )
             # set the new commit is proper phase
             targetphase = subrepoutil.newcommitphase(self.ui, ctx)
             if targetphase:
                 # retract boundary do not alter parent changeset.
                 # if a parent have higher the resulting phase will
                 # be compliant anyway
                 #
                 # if minimal phase was 0 we don't need to retract anything
                 phases.registernew(self, tr, targetphase, [n])
             return n
 
     @unfilteredmethod
     def destroying(self):
         '''Inform the repository that nodes are about to be destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done before destroying history.
 
         This is mostly useful for saving state that is in memory and waiting
         to be flushed when the current lock is released. Because a call to
         destroyed is imminent, the repo will be invalidated causing those
         changes to stay in memory (waiting for the next unlock), or vanish
         completely.
         '''
         # When using the same lock to commit and strip, the phasecache is left
         # dirty after committing. Then when we strip, the repo is invalidated,
         # causing those changes to disappear.
         if '_phasecache' in vars(self):
             self._phasecache.write()
 
     @unfilteredmethod
     def destroyed(self):
         '''Inform the repository that nodes have been destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done after destroying history.
         '''
         # When one tries to:
         # 1) destroy nodes thus calling this method (e.g. strip)
         # 2) use phasecache somewhere (e.g. commit)
         #
         # then 2) will fail because the phasecache contains nodes that were
         # removed. We can either remove phasecache from the filecache,
         # causing it to reload next time it is accessed, or simply filter
         # the removed nodes now and write the updated cache.
         self._phasecache.filterunknown(self)
         self._phasecache.write()
 
         # refresh all repository caches
         self.updatecaches()
 
         # Ensure the persistent tag cache is updated.  Doing it now
         # means that the tag cache only has to worry about destroyed
         # heads immediately after a strip/rollback.  That in turn
         # guarantees that "cachetip == currenttip" (comparing both rev
         # and node) always means no nodes have been added or destroyed.
 
         # XXX this is suboptimal when qrefresh'ing: we strip the current
         # head, refresh the tag cache, then immediately add a new head.
         # But I think doing it this way is necessary for the "instant
         # tag cache retrieval" case to work.
         self.invalidate()
 
     def status(
         self,
         node1=b'.',
         node2=None,
         match=None,
         ignored=False,
         clean=False,
         unknown=False,
         listsubrepos=False,
     ):
         '''a convenience method that calls node1.status(node2)'''
         return self[node1].status(
             node2, match, ignored, clean, unknown, listsubrepos
         )
 
     def addpostdsstatus(self, ps):
         """Add a callback to run within the wlock, at the point at which status
         fixups happen.
 
         On status completion, callback(wctx, status) will be called with the
         wlock held, unless the dirstate has changed from underneath or the wlock
         couldn't be grabbed.
 
         Callbacks should not capture and use a cached copy of the dirstate --
         it might change in the meanwhile. Instead, they should access the
         dirstate via wctx.repo().dirstate.
 
         This list is emptied out after each status run -- extensions should
         make sure it adds to this list each time dirstate.status is called.
         Extensions should also make sure they don't call this for statuses
         that don't involve the dirstate.
         """
 
         # The list is located here for uniqueness reasons -- it is actually
         # managed by the workingctx, but that isn't unique per-repo.
         self._postdsstatus.append(ps)
 
     def postdsstatus(self):
         """Used by workingctx to get the list of post-dirstate-status hooks."""
         return self._postdsstatus
 
     def clearpostdsstatus(self):
         """Used by workingctx to clear post-dirstate-status hooks."""
         del self._postdsstatus[:]
 
     def heads(self, start=None):
         if start is None:
             cl = self.changelog
             headrevs = reversed(cl.headrevs())
             return [cl.node(rev) for rev in headrevs]
 
         heads = self.changelog.heads(start)
         # sort the output in rev descending order
         return sorted(heads, key=self.changelog.rev, reverse=True)
 
     def branchheads(self, branch=None, start=None, closed=False):
         '''return a (possibly filtered) list of heads for the given branch
 
         Heads are returned in topological order, from newest to oldest.
         If branch is None, use the dirstate branch.
         If start is not None, return only heads reachable from start.
         If closed is True, return heads that are marked as closed as well.
         '''
         if branch is None:
             branch = self[None].branch()
         branches = self.branchmap()
         if not branches.hasbranch(branch):
             return []
         # the cache returns heads ordered lowest to highest
         bheads = list(reversed(branches.branchheads(branch, closed=closed)))
         if start is not None:
             # filter out the heads that cannot be reached from startrev
             fbheads = set(self.changelog.nodesbetween([start], bheads)[2])
             bheads = [h for h in bheads if h in fbheads]
         return bheads
 
     def branches(self, nodes):
         if not nodes:
             nodes = [self.changelog.tip()]
         b = []
         for n in nodes:
             t = n
             while True:
                 p = self.changelog.parents(n)
                 if p[1] != nullid or p[0] == nullid:
                     b.append((t, n, p[0], p[1]))
                     break
                 n = p[0]
         return b
 
     def between(self, pairs):
         r = []
 
         for top, bottom in pairs:
             n, l, i = top, [], 0
             f = 1
 
             while n != bottom and n != nullid:
                 p = self.changelog.parents(n)[0]
                 if i == f:
                     l.append(n)
                     f = f * 2
                 n = p
                 i += 1
 
             r.append(l)
 
         return r
 
     def checkpush(self, pushop):
         """Extensions can override this function if additional checks have
         to be performed before pushing, or call it if they override push
         command.
         """
 
     @unfilteredpropertycache
     def prepushoutgoinghooks(self):
         """Return util.hooks consists of a pushop with repo, remote, outgoing
         methods, which are called before pushing changesets.
         """
         return util.hooks()
 
     def pushkey(self, namespace, key, old, new):
         try:
             tr = self.currenttransaction()
             hookargs = {}
             if tr is not None:
                 hookargs.update(tr.hookargs)
             hookargs = pycompat.strkwargs(hookargs)
             hookargs['namespace'] = namespace
             hookargs['key'] = key
             hookargs['old'] = old
             hookargs['new'] = new
             self.hook(b'prepushkey', throw=True, **hookargs)
         except error.HookAbort as exc:
             self.ui.write_err(_(b"pushkey-abort: %s\n") % exc)
             if exc.hint:
                 self.ui.write_err(_(b"(%s)\n") % exc.hint)
             return False
         self.ui.debug(b'pushing key for "%s:%s"\n' % (namespace, key))
         ret = pushkey.push(self, namespace, key, old, new)
 
         def runhook(unused_success):
             self.hook(
                 b'pushkey',
                 namespace=namespace,
                 key=key,
                 old=old,
                 new=new,
                 ret=ret,
             )
 
         self._afterlock(runhook)
         return ret
 
     def listkeys(self, namespace):
         self.hook(b'prelistkeys', throw=True, namespace=namespace)
         self.ui.debug(b'listing keys for "%s"\n' % namespace)
         values = pushkey.list(self, namespace)
         self.hook(b'listkeys', namespace=namespace, values=values)
         return values
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         '''used to test argument passing over the wire'''
         return b"%s %s %s %s %s" % (
             one,
             two,
             pycompat.bytestr(three),
             pycompat.bytestr(four),
             pycompat.bytestr(five),
         )
 
     def savecommitmessage(self, text):
         fp = self.vfs(b'last-message.txt', b'wb')
         try:
             fp.write(text)
         finally:
             fp.close()
         return self.pathto(fp.name[len(self.root) + 1 :])
 
 
 # used to avoid circular references so destructors work
 def aftertrans(files):
     renamefiles = [tuple(t) for t in files]
 
     def a():
         for vfs, src, dest in renamefiles:
             # if src and dest refer to a same file, vfs.rename is a no-op,
             # leaving both src and dest on disk. delete dest to make sure
             # the rename couldn't be such a no-op.
             vfs.tryunlink(dest)
             try:
                 vfs.rename(src, dest)
             except OSError:  # journal file does not yet exist
                 pass
 
     return a
 
 
 def undoname(fn):
     base, name = os.path.split(fn)
     assert name.startswith(b'journal')
     return os.path.join(base, name.replace(b'journal', b'undo', 1))
 
 
 def instance(ui, path, create, intents=None, createopts=None):
     localpath = util.urllocalpath(path)
     if create:
         createrepository(ui, localpath, createopts=createopts)
 
     return makelocalrepository(ui, localpath, intents=intents)
 
 
 def islocal(path):
     return True
 
 
 def defaultcreateopts(ui, createopts=None):
     """Populate the default creation options for a repository.
 
     A dictionary of explicitly requested creation options can be passed
     in. Missing keys will be populated.
     """
     createopts = dict(createopts or {})
 
     if b'backend' not in createopts:
         # experimental config: storage.new-repo-backend
         createopts[b'backend'] = ui.config(b'storage', b'new-repo-backend')
 
     return createopts
 
 
 def newreporequirements(ui, createopts):
     """Determine the set of requirements for a new local repository.
 
     Extensions can wrap this function to specify custom requirements for
     new repositories.
     """
     # If the repo is being created from a shared repository, we copy
     # its requirements.
     if b'sharedrepo' in createopts:
         requirements = set(createopts[b'sharedrepo'].requirements)
         if createopts.get(b'sharedrelative'):
             requirements.add(b'relshared')
         else:
             requirements.add(b'shared')
 
         return requirements
 
     if b'backend' not in createopts:
         raise error.ProgrammingError(
             b'backend key not present in createopts; '
             b'was defaultcreateopts() called?'
         )
 
     if createopts[b'backend'] != b'revlogv1':
         raise error.Abort(
             _(
                 b'unable to determine repository requirements for '
                 b'storage backend: %s'
             )
             % createopts[b'backend']
         )
 
     requirements = {b'revlogv1'}
     if ui.configbool(b'format', b'usestore'):
         requirements.add(b'store')
         if ui.configbool(b'format', b'usefncache'):
             requirements.add(b'fncache')
             if ui.configbool(b'format', b'dotencode'):
                 requirements.add(b'dotencode')
 
     compengine = ui.config(b'format', b'revlog-compression')
     if compengine not in util.compengines:
         raise error.Abort(
             _(
                 b'compression engine %s defined by '
                 b'format.revlog-compression not available'
             )
             % compengine,
             hint=_(
                 b'run "hg debuginstall" to list available '
                 b'compression engines'
             ),
         )
 
     # zlib is the historical default and doesn't need an explicit requirement.
     elif compengine == b'zstd':
         requirements.add(b'revlog-compression-zstd')
     elif compengine != b'zlib':
         requirements.add(b'exp-compression-%s' % compengine)
 
     if scmutil.gdinitconfig(ui):
         requirements.add(b'generaldelta')
         if ui.configbool(b'format', b'sparse-revlog'):
             requirements.add(SPARSEREVLOG_REQUIREMENT)
 
     # experimental config: format.exp-use-side-data
     if ui.configbool(b'format', b'exp-use-side-data'):
         requirements.add(SIDEDATA_REQUIREMENT)
     # experimental config: format.exp-use-copies-side-data-changeset
     if ui.configbool(b'format', b'exp-use-copies-side-data-changeset'):
         requirements.add(SIDEDATA_REQUIREMENT)
         requirements.add(COPIESSDC_REQUIREMENT)
     if ui.configbool(b'experimental', b'treemanifest'):
         requirements.add(b'treemanifest')
 
     revlogv2 = ui.config(b'experimental', b'revlogv2')
     if revlogv2 == b'enable-unstable-format-and-corrupt-my-data':
         requirements.remove(b'revlogv1')
         # generaldelta is implied by revlogv2.
         requirements.discard(b'generaldelta')
         requirements.add(REVLOGV2_REQUIREMENT)
     # experimental config: format.internal-phase
     if ui.configbool(b'format', b'internal-phase'):
         requirements.add(b'internal-phase')
 
     if createopts.get(b'narrowfiles'):
         requirements.add(repository.NARROW_REQUIREMENT)
 
     if createopts.get(b'lfs'):
         requirements.add(b'lfs')
 
     if ui.configbool(b'format', b'bookmarks-in-store'):
         requirements.add(bookmarks.BOOKMARKS_IN_STORE_REQUIREMENT)
 
     return requirements
 
 
 def filterknowncreateopts(ui, createopts):
     """Filters a dict of repo creation options against options that are known.
 
     Receives a dict of repo creation options and returns a dict of those
     options that we don't know how to handle.
 
     This function is called as part of repository creation. If the
     returned dict contains any items, repository creation will not
     be allowed, as it means there was a request to create a repository
     with options not recognized by loaded code.
 
     Extensions can wrap this function to filter out creation options
     they know how to handle.
     """
     known = {
         b'backend',
         b'lfs',
         b'narrowfiles',
         b'sharedrepo',
         b'sharedrelative',
         b'shareditems',
         b'shallowfilestore',
     }
 
     return {k: v for k, v in createopts.items() if k not in known}
 
 
 def createrepository(ui, path, createopts=None):
     """Create a new repository in a vfs.
 
     ``path`` path to the new repo's working directory.
     ``createopts`` options for the new repository.
 
     The following keys for ``createopts`` are recognized:
 
     backend
        The storage backend to use.
     lfs
        Repository will be created with ``lfs`` requirement. The lfs extension
        will automatically be loaded when the repository is accessed.
     narrowfiles
        Set up repository to support narrow file storage.
     sharedrepo
        Repository object from which storage should be shared.
     sharedrelative
        Boolean indicating if the path to the shared repo should be
        stored as relative. By default, the pointer to the "parent" repo
        is stored as an absolute path.
     shareditems
        Set of items to share to the new repository (in addition to storage).
     shallowfilestore
        Indicates that storage for files should be shallow (not all ancestor
        revisions are known).
     """
     createopts = defaultcreateopts(ui, createopts=createopts)
 
     unknownopts = filterknowncreateopts(ui, createopts)
 
     if not isinstance(unknownopts, dict):
         raise error.ProgrammingError(
             b'filterknowncreateopts() did not return a dict'
         )
 
     if unknownopts:
         raise error.Abort(
             _(
                 b'unable to create repository because of unknown '
                 b'creation option: %s'
             )
             % b', '.join(sorted(unknownopts)),
             hint=_(b'is a required extension not loaded?'),
         )
 
     requirements = newreporequirements(ui, createopts=createopts)
 
     wdirvfs = vfsmod.vfs(path, expandpath=True, realpath=True)
 
     hgvfs = vfsmod.vfs(wdirvfs.join(b'.hg'))
     if hgvfs.exists():
         raise error.RepoError(_(b'repository %s already exists') % path)
 
     if b'sharedrepo' in createopts:
         sharedpath = createopts[b'sharedrepo'].sharedpath
 
         if createopts.get(b'sharedrelative'):
             try:
                 sharedpath = os.path.relpath(sharedpath, hgvfs.base)
             except (IOError, ValueError) as e:
                 # ValueError is raised on Windows if the drive letters differ
                 # on each path.
                 raise error.Abort(
                     _(b'cannot calculate relative path'),
                     hint=stringutil.forcebytestr(e),
                 )
 
     if not wdirvfs.exists():
         wdirvfs.makedirs()
 
     hgvfs.makedir(notindexed=True)
     if b'sharedrepo' not in createopts:
         hgvfs.mkdir(b'cache')
     hgvfs.mkdir(b'wcache')
 
     if b'store' in requirements and b'sharedrepo' not in createopts:
         hgvfs.mkdir(b'store')
 
         # We create an invalid changelog outside the store so very old
         # Mercurial versions (which didn't know about the requirements
         # file) encounter an error on reading the changelog. This
         # effectively locks out old clients and prevents them from
         # mucking with a repo in an unknown format.
         #
         # The revlog header has version 2, which won't be recognized by
         # such old clients.
         hgvfs.append(
             b'00changelog.i',
             b'\0\0\0\2 dummy changelog to prevent using the old repo '
             b'layout',
         )
 
     scmutil.writerequires(hgvfs, requirements)
 
     # Write out file telling readers where to find the shared store.
     if b'sharedrepo' in createopts:
         hgvfs.write(b'sharedpath', sharedpath)
 
     if createopts.get(b'shareditems'):
         shared = b'\n'.join(sorted(createopts[b'shareditems'])) + b'\n'
         hgvfs.write(b'shared', shared)
 
 
 def poisonrepository(repo):
     """Poison a repository instance so it can no longer be used."""
     # Perform any cleanup on the instance.
     repo.close()
 
     # Our strategy is to replace the type of the object with one that
     # has all attribute lookups result in error.
     #
     # But we have to allow the close() method because some constructors
     # of repos call close() on repo references.
     class poisonedrepository(object):
         def __getattribute__(self, item):
             if item == 'close':
                 return object.__getattribute__(self, item)
 
             raise error.ProgrammingError(
                 b'repo instances should not be used after unshare'
             )
 
         def close(self):
             pass
 
     # We may have a repoview, which intercepts __setattr__. So be sure
     # we operate at the lowest level possible.
     object.__setattr__(repo, '__class__', poisonedrepository)

mercurial/manifest.py

@@ -1,2262 +1,2264 b''
 # manifest.py - manifest revision class for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # 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
 
 import heapq
 import itertools
 import struct
 import weakref
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
 )
 from .pycompat import getattr
 from . import (
+    encoding,
     error,
     mdiff,
     pathutil,
     policy,
     pycompat,
     revlog,
     util,
 )
 from .interfaces import (
     repository,
     util as interfaceutil,
 )
 
 parsers = policy.importmod('parsers')
 propertycache = util.propertycache
 
 # Allow tests to more easily test the alternate path in manifestdict.fastdelta()
 FASTDELTA_TEXTDIFF_THRESHOLD = 1000
 
 
 def _parse(data):
     # This method does a little bit of excessive-looking
     # precondition checking. This is so that the behavior of this
     # class exactly matches its C counterpart to try and help
     # prevent surprise breakage for anyone that develops against
     # the pure version.
     if data and data[-1:] != b'\n':
         raise ValueError(b'Manifest did not end in a newline.')
     prev = None
     for l in data.splitlines():
         if prev is not None and prev > l:
             raise ValueError(b'Manifest lines not in sorted order.')
         prev = l
         f, n = l.split(b'\0')
         if len(n) > 40:
             yield f, bin(n[:40]), n[40:]
         else:
             yield f, bin(n), b''
 
 
 def _text(it):
     files = []
     lines = []
     for f, n, fl in it:
         files.append(f)
         # if this is changed to support newlines in filenames,
         # be sure to check the templates/ dir again (especially *-raw.tmpl)
         lines.append(b"%s\0%s%s\n" % (f, hex(n), fl))
 
     _checkforbidden(files)
     return b''.join(lines)
 
 
 class lazymanifestiter(object):
     def __init__(self, lm):
         self.pos = 0
         self.lm = lm
 
     def __iter__(self):
         return self
 
     def next(self):
         try:
             data, pos = self.lm._get(self.pos)
         except IndexError:
             raise StopIteration
         if pos == -1:
             self.pos += 1
             return data[0]
         self.pos += 1
         zeropos = data.find(b'\x00', pos)
         return data[pos:zeropos]
 
     __next__ = next
 
 
 class lazymanifestiterentries(object):
     def __init__(self, lm):
         self.lm = lm
         self.pos = 0
 
     def __iter__(self):
         return self
 
     def next(self):
         try:
             data, pos = self.lm._get(self.pos)
         except IndexError:
             raise StopIteration
         if pos == -1:
             self.pos += 1
             return data
         zeropos = data.find(b'\x00', pos)
         hashval = unhexlify(data, self.lm.extrainfo[self.pos], zeropos + 1, 40)
         flags = self.lm._getflags(data, self.pos, zeropos)
         self.pos += 1
         return (data[pos:zeropos], hashval, flags)
 
     __next__ = next
 
 
 def unhexlify(data, extra, pos, length):
     s = bin(data[pos : pos + length])
     if extra:
         s += chr(extra & 0xFF)
     return s
 
 
 def _cmp(a, b):
     return (a > b) - (a < b)
 
 
 class _lazymanifest(object):
     """A pure python manifest backed by a byte string.  It is supplimented with
     internal lists as it is modified, until it is compacted back to a pure byte
     string.
 
     ``data`` is the initial manifest data.
 
     ``positions`` is a list of offsets, one per manifest entry.  Positive
     values are offsets into ``data``, negative values are offsets into the
     ``extradata`` list.  When an entry is removed, its entry is dropped from
     ``positions``.  The values are encoded such that when walking the list and
     indexing into ``data`` or ``extradata`` as appropriate, the entries are
     sorted by filename.
 
     ``extradata`` is a list of (key, hash, flags) for entries that were added or
     modified since the manifest was created or compacted.
     """
 
     def __init__(
         self,
         data,
         positions=None,
         extrainfo=None,
         extradata=None,
         hasremovals=False,
     ):
         if positions is None:
             self.positions = self.findlines(data)
             self.extrainfo = [0] * len(self.positions)
             self.data = data
             self.extradata = []
             self.hasremovals = False
         else:
             self.positions = positions[:]
             self.extrainfo = extrainfo[:]
             self.extradata = extradata[:]
             self.data = data
             self.hasremovals = hasremovals
 
     def findlines(self, data):
         if not data:
             return []
         pos = data.find(b"\n")
         if pos == -1 or data[-1:] != b'\n':
             raise ValueError(b"Manifest did not end in a newline.")
         positions = [0]
         prev = data[: data.find(b'\x00')]
         while pos < len(data) - 1 and pos != -1:
             positions.append(pos + 1)
             nexts = data[pos + 1 : data.find(b'\x00', pos + 1)]
             if nexts < prev:
                 raise ValueError(b"Manifest lines not in sorted order.")
             prev = nexts
             pos = data.find(b"\n", pos + 1)
         return positions
 
     def _get(self, index):
         # get the position encoded in pos:
         #   positive number is an index in 'data'
         #   negative number is in extrapieces
         pos = self.positions[index]
         if pos >= 0:
             return self.data, pos
         return self.extradata[-pos - 1], -1
 
     def _getkey(self, pos):
         if pos >= 0:
             return self.data[pos : self.data.find(b'\x00', pos + 1)]
         return self.extradata[-pos - 1][0]
 
     def bsearch(self, key):
         first = 0
         last = len(self.positions) - 1
 
         while first <= last:
             midpoint = (first + last) // 2
             nextpos = self.positions[midpoint]
             candidate = self._getkey(nextpos)
             r = _cmp(key, candidate)
             if r == 0:
                 return midpoint
             else:
                 if r < 0:
                     last = midpoint - 1
                 else:
                     first = midpoint + 1
         return -1
 
     def bsearch2(self, key):
         # same as the above, but will always return the position
         # done for performance reasons
         first = 0
         last = len(self.positions) - 1
 
         while first <= last:
             midpoint = (first + last) // 2
             nextpos = self.positions[midpoint]
             candidate = self._getkey(nextpos)
             r = _cmp(key, candidate)
             if r == 0:
                 return (midpoint, True)
             else:
                 if r < 0:
                     last = midpoint - 1
                 else:
                     first = midpoint + 1
         return (first, False)
 
     def __contains__(self, key):
         return self.bsearch(key) != -1
 
     def _getflags(self, data, needle, pos):
         start = pos + 41
         end = data.find(b"\n", start)
         if end == -1:
             end = len(data) - 1
         if start == end:
             return b''
         return self.data[start:end]
 
     def __getitem__(self, key):
         if not isinstance(key, bytes):
             raise TypeError(b"getitem: manifest keys must be a bytes.")
         needle = self.bsearch(key)
         if needle == -1:
             raise KeyError
         data, pos = self._get(needle)
         if pos == -1:
             return (data[1], data[2])
         zeropos = data.find(b'\x00', pos)
         assert 0 <= needle <= len(self.positions)
         assert len(self.extrainfo) == len(self.positions)
         hashval = unhexlify(data, self.extrainfo[needle], zeropos + 1, 40)
         flags = self._getflags(data, needle, zeropos)
         return (hashval, flags)
 
     def __delitem__(self, key):
         needle, found = self.bsearch2(key)
         if not found:
             raise KeyError
         cur = self.positions[needle]
         self.positions = self.positions[:needle] + self.positions[needle + 1 :]
         self.extrainfo = self.extrainfo[:needle] + self.extrainfo[needle + 1 :]
         if cur >= 0:
             # This does NOT unsort the list as far as the search functions are
             # concerned, as they only examine lines mapped by self.positions.
             self.data = self.data[:cur] + b'\x00' + self.data[cur + 1 :]
             self.hasremovals = True
 
     def __setitem__(self, key, value):
         if not isinstance(key, bytes):
             raise TypeError(b"setitem: manifest keys must be a byte string.")
         if not isinstance(value, tuple) or len(value) != 2:
             raise TypeError(
                 b"Manifest values must be a tuple of (node, flags)."
             )
         hashval = value[0]
         if not isinstance(hashval, bytes) or not 20 <= len(hashval) <= 22:
             raise TypeError(b"node must be a 20-byte byte string")
         flags = value[1]
         if len(hashval) == 22:
             hashval = hashval[:-1]
         if not isinstance(flags, bytes) or len(flags) > 1:
             raise TypeError(b"flags must a 0 or 1 byte string, got %r", flags)
         needle, found = self.bsearch2(key)
         if found:
             # put the item
             pos = self.positions[needle]
             if pos < 0:
                 self.extradata[-pos - 1] = (key, hashval, value[1])
             else:
                 # just don't bother
                 self.extradata.append((key, hashval, value[1]))
                 self.positions[needle] = -len(self.extradata)
         else:
             # not found, put it in with extra positions
             self.extradata.append((key, hashval, value[1]))
             self.positions = (
                 self.positions[:needle]
                 + [-len(self.extradata)]
                 + self.positions[needle:]
             )
             self.extrainfo = (
                 self.extrainfo[:needle] + [0] + self.extrainfo[needle:]
             )
 
     def copy(self):
         # XXX call _compact like in C?
         return _lazymanifest(
             self.data,
             self.positions,
             self.extrainfo,
             self.extradata,
             self.hasremovals,
         )
 
     def _compact(self):
         # hopefully not called TOO often
         if len(self.extradata) == 0 and not self.hasremovals:
             return
         l = []
         i = 0
         offset = 0
         self.extrainfo = [0] * len(self.positions)
         while i < len(self.positions):
             if self.positions[i] >= 0:
                 cur = self.positions[i]
                 last_cut = cur
 
                 # Collect all contiguous entries in the buffer at the current
                 # offset, breaking out only for added/modified items held in
                 # extradata, or a deleted line prior to the next position.
                 while True:
                     self.positions[i] = offset
                     i += 1
                     if i == len(self.positions) or self.positions[i] < 0:
                         break
 
                     # A removed file has no positions[] entry, but does have an
                     # overwritten first byte.  Break out and find the end of the
                     # current good entry/entries if there is a removed file
                     # before the next position.
                     if (
                         self.hasremovals
                         and self.data.find(b'\n\x00', cur, self.positions[i])
                         != -1
                     ):
                         break
 
                     offset += self.positions[i] - cur
                     cur = self.positions[i]
                 end_cut = self.data.find(b'\n', cur)
                 if end_cut != -1:
                     end_cut += 1
                 offset += end_cut - cur
                 l.append(self.data[last_cut:end_cut])
             else:
                 while i < len(self.positions) and self.positions[i] < 0:
                     cur = self.positions[i]
                     t = self.extradata[-cur - 1]
                     l.append(self._pack(t))
                     self.positions[i] = offset
                     if len(t[1]) > 20:
                         self.extrainfo[i] = ord(t[1][21])
                     offset += len(l[-1])
                     i += 1
         self.data = b''.join(l)
         self.hasremovals = False
         self.extradata = []
 
     def _pack(self, d):
         return d[0] + b'\x00' + hex(d[1][:20]) + d[2] + b'\n'
 
     def text(self):
         self._compact()
         return self.data
 
     def diff(self, m2, clean=False):
         '''Finds changes between the current manifest and m2.'''
         # XXX think whether efficiency matters here
         diff = {}
 
         for fn, e1, flags in self.iterentries():
             if fn not in m2:
                 diff[fn] = (e1, flags), (None, b'')
             else:
                 e2 = m2[fn]
                 if (e1, flags) != e2:
                     diff[fn] = (e1, flags), e2
                 elif clean:
                     diff[fn] = None
 
         for fn, e2, flags in m2.iterentries():
             if fn not in self:
                 diff[fn] = (None, b''), (e2, flags)
 
         return diff
 
     def iterentries(self):
         return lazymanifestiterentries(self)
 
     def iterkeys(self):
         return lazymanifestiter(self)
 
     def __iter__(self):
         return lazymanifestiter(self)
 
     def __len__(self):
         return len(self.positions)
 
     def filtercopy(self, filterfn):
         # XXX should be optimized
         c = _lazymanifest(b'')
         for f, n, fl in self.iterentries():
             if filterfn(f):
                 c[f] = n, fl
         return c
 
 
 try:
     _lazymanifest = parsers.lazymanifest
 except AttributeError:
     pass
 
 
 @interfaceutil.implementer(repository.imanifestdict)
 class manifestdict(object):
     def __init__(self, data=b''):
         self._lm = _lazymanifest(data)
 
     def __getitem__(self, key):
         return self._lm[key][0]
 
     def find(self, key):
         return self._lm[key]
 
     def __len__(self):
         return len(self._lm)
 
     def __nonzero__(self):
         # nonzero is covered by the __len__ function, but implementing it here
         # makes it easier for extensions to override.
         return len(self._lm) != 0
 
     __bool__ = __nonzero__
 
     def __setitem__(self, key, node):
         self._lm[key] = node, self.flags(key)
 
     def __contains__(self, key):
         if key is None:
             return False
         return key in self._lm
 
     def __delitem__(self, key):
         del self._lm[key]
 
     def __iter__(self):
         return self._lm.__iter__()
 
     def iterkeys(self):
         return self._lm.iterkeys()
 
     def keys(self):
         return list(self.iterkeys())
 
     def filesnotin(self, m2, match=None):
         '''Set of files in this manifest that are not in the other'''
         if match:
             m1 = self.matches(match)
             m2 = m2.matches(match)
             return m1.filesnotin(m2)
         diff = self.diff(m2)
         files = set(
             filepath
             for filepath, hashflags in pycompat.iteritems(diff)
             if hashflags[1][0] is None
         )
         return files
 
     @propertycache
     def _dirs(self):
         return pathutil.dirs(self)
 
     def dirs(self):
         return self._dirs
 
     def hasdir(self, dir):
         return dir in self._dirs
 
     def _filesfastpath(self, match):
         '''Checks whether we can correctly and quickly iterate over matcher
         files instead of over manifest files.'''
         files = match.files()
         return len(files) < 100 and (
             match.isexact()
             or (match.prefix() and all(fn in self for fn in files))
         )
 
     def walk(self, match):
         '''Generates matching file names.
 
         Equivalent to manifest.matches(match).iterkeys(), but without creating
         an entirely new manifest.
 
         It also reports nonexistent files by marking them bad with match.bad().
         '''
         if match.always():
             for f in iter(self):
                 yield f
             return
 
         fset = set(match.files())
 
         # avoid the entire walk if we're only looking for specific files
         if self._filesfastpath(match):
             for fn in sorted(fset):
                 if fn in self:
                     yield fn
             return
 
         for fn in self:
             if fn in fset:
                 # specified pattern is the exact name
                 fset.remove(fn)
             if match(fn):
                 yield fn
 
         # for dirstate.walk, files=[''] means "walk the whole tree".
         # follow that here, too
         fset.discard(b'')
 
         for fn in sorted(fset):
             if not self.hasdir(fn):
                 match.bad(fn, None)
 
     def matches(self, match):
         '''generate a new manifest filtered by the match argument'''
         if match.always():
             return self.copy()
 
         if self._filesfastpath(match):
             m = manifestdict()
             lm = self._lm
             for fn in match.files():
                 if fn in lm:
                     m._lm[fn] = lm[fn]
             return m
 
         m = manifestdict()
         m._lm = self._lm.filtercopy(match)
         return m
 
     def diff(self, m2, match=None, clean=False):
         '''Finds changes between the current manifest and m2.
 
         Args:
           m2: the manifest to which this manifest should be compared.
           clean: if true, include files unchanged between these manifests
                  with a None value in the returned dictionary.
 
         The result is returned as a dict with filename as key and
         values of the form ((n1,fl1),(n2,fl2)), where n1/n2 is the
         nodeid in the current/other manifest and fl1/fl2 is the flag
         in the current/other manifest. Where the file does not exist,
         the nodeid will be None and the flags will be the empty
         string.
         '''
         if match:
             m1 = self.matches(match)
             m2 = m2.matches(match)
             return m1.diff(m2, clean=clean)
         return self._lm.diff(m2._lm, clean)
 
     def setflag(self, key, flag):
         self._lm[key] = self[key], flag
 
     def get(self, key, default=None):
         try:
             return self._lm[key][0]
         except KeyError:
             return default
 
     def flags(self, key):
         try:
             return self._lm[key][1]
         except KeyError:
             return b''
 
     def copy(self):
         c = manifestdict()
         c._lm = self._lm.copy()
         return c
 
     def items(self):
         return (x[:2] for x in self._lm.iterentries())
 
     def iteritems(self):
         return (x[:2] for x in self._lm.iterentries())
 
     def iterentries(self):
         return self._lm.iterentries()
 
     def text(self):
         # most likely uses native version
         return self._lm.text()
 
     def fastdelta(self, base, changes):
         """Given a base manifest text as a bytearray and a list of changes
         relative to that text, compute a delta that can be used by revlog.
         """
         delta = []
         dstart = None
         dend = None
         dline = [b""]
         start = 0
         # zero copy representation of base as a buffer
         addbuf = util.buffer(base)
 
         changes = list(changes)
         if len(changes) < FASTDELTA_TEXTDIFF_THRESHOLD:
             # start with a readonly loop that finds the offset of
             # each line and creates the deltas
             for f, todelete in changes:
                 # bs will either be the index of the item or the insert point
                 start, end = _msearch(addbuf, f, start)
                 if not todelete:
                     h, fl = self._lm[f]
                     l = b"%s\0%s%s\n" % (f, hex(h), fl)
                 else:
                     if start == end:
                         # item we want to delete was not found, error out
                         raise AssertionError(
                             _(b"failed to remove %s from manifest") % f
                         )
                     l = b""
                 if dstart is not None and dstart <= start and dend >= start:
                     if dend < end:
                         dend = end
                     if l:
                         dline.append(l)
                 else:
                     if dstart is not None:
                         delta.append([dstart, dend, b"".join(dline)])
                     dstart = start
                     dend = end
                     dline = [l]
 
             if dstart is not None:
                 delta.append([dstart, dend, b"".join(dline)])
             # apply the delta to the base, and get a delta for addrevision
             deltatext, arraytext = _addlistdelta(base, delta)
         else:
             # For large changes, it's much cheaper to just build the text and
             # diff it.
             arraytext = bytearray(self.text())
             deltatext = mdiff.textdiff(
                 util.buffer(base), util.buffer(arraytext)
             )
 
         return arraytext, deltatext
 
 
 def _msearch(m, s, lo=0, hi=None):
     '''return a tuple (start, end) that says where to find s within m.
 
     If the string is found m[start:end] are the line containing
     that string.  If start == end the string was not found and
     they indicate the proper sorted insertion point.
 
     m should be a buffer, a memoryview or a byte string.
     s is a byte string'''
 
     def advance(i, c):
         while i < lenm and m[i : i + 1] != c:
             i += 1
         return i
 
     if not s:
         return (lo, lo)
     lenm = len(m)
     if not hi:
         hi = lenm
     while lo < hi:
         mid = (lo + hi) // 2
         start = mid
         while start > 0 and m[start - 1 : start] != b'\n':
             start -= 1
         end = advance(start, b'\0')
         if bytes(m[start:end]) < s:
             # we know that after the null there are 40 bytes of sha1
             # this translates to the bisect lo = mid + 1
             lo = advance(end + 40, b'\n') + 1
         else:
             # this translates to the bisect hi = mid
             hi = start
     end = advance(lo, b'\0')
     found = m[lo:end]
     if s == found:
         # we know that after the null there are 40 bytes of sha1
         end = advance(end + 40, b'\n')
         return (lo, end + 1)
     else:
         return (lo, lo)
 
 
 def _checkforbidden(l):
     """Check filenames for illegal characters."""
     for f in l:
         if b'\n' in f or b'\r' in f:
             raise error.StorageError(
                 _(b"'\\n' and '\\r' disallowed in filenames: %r")
                 % pycompat.bytestr(f)
             )
 
 
 # apply the changes collected during the bisect loop to our addlist
 # return a delta suitable for addrevision
 def _addlistdelta(addlist, x):
     # for large addlist arrays, building a new array is cheaper
     # than repeatedly modifying the existing one
     currentposition = 0
     newaddlist = bytearray()
 
     for start, end, content in x:
         newaddlist += addlist[currentposition:start]
         if content:
             newaddlist += bytearray(content)
 
         currentposition = end
 
     newaddlist += addlist[currentposition:]
 
     deltatext = b"".join(
         struct.pack(b">lll", start, end, len(content)) + content
         for start, end, content in x
     )
     return deltatext, newaddlist
 
 
 def _splittopdir(f):
     if b'/' in f:
         dir, subpath = f.split(b'/', 1)
         return dir + b'/', subpath
     else:
         return b'', f
 
 
 _noop = lambda s: None
 
 
 class treemanifest(object):
     def __init__(self, dir=b'', text=b''):
         self._dir = dir
         self._node = nullid
         self._loadfunc = _noop
         self._copyfunc = _noop
         self._dirty = False
         self._dirs = {}
         self._lazydirs = {}
         # Using _lazymanifest here is a little slower than plain old dicts
         self._files = {}
         self._flags = {}
         if text:
 
             def readsubtree(subdir, subm):
                 raise AssertionError(
                     b'treemanifest constructor only accepts flat manifests'
                 )
 
             self.parse(text, readsubtree)
             self._dirty = True  # Mark flat manifest dirty after parsing
 
     def _subpath(self, path):
         return self._dir + path
 
     def _loadalllazy(self):
         selfdirs = self._dirs
         for d, (path, node, readsubtree, docopy) in pycompat.iteritems(
             self._lazydirs
         ):
             if docopy:
                 selfdirs[d] = readsubtree(path, node).copy()
             else:
                 selfdirs[d] = readsubtree(path, node)
         self._lazydirs = {}
 
     def _loadlazy(self, d):
         v = self._lazydirs.get(d)
         if v:
             path, node, readsubtree, docopy = v
             if docopy:
                 self._dirs[d] = readsubtree(path, node).copy()
             else:
                 self._dirs[d] = readsubtree(path, node)
             del self._lazydirs[d]
 
     def _loadchildrensetlazy(self, visit):
         if not visit:
             return None
         if visit == b'all' or visit == b'this':
             self._loadalllazy()
             return None
 
         loadlazy = self._loadlazy
         for k in visit:
             loadlazy(k + b'/')
         return visit
 
     def _loaddifflazy(self, t1, t2):
         """load items in t1 and t2 if they're needed for diffing.
 
         The criteria currently is:
         - if it's not present in _lazydirs in either t1 or t2, load it in the
           other (it may already be loaded or it may not exist, doesn't matter)
         - if it's present in _lazydirs in both, compare the nodeid; if it
           differs, load it in both
         """
         toloadlazy = []
         for d, v1 in pycompat.iteritems(t1._lazydirs):
             v2 = t2._lazydirs.get(d)
             if not v2 or v2[1] != v1[1]:
                 toloadlazy.append(d)
         for d, v1 in pycompat.iteritems(t2._lazydirs):
             if d not in t1._lazydirs:
                 toloadlazy.append(d)
 
         for d in toloadlazy:
             t1._loadlazy(d)
             t2._loadlazy(d)
 
     def __len__(self):
         self._load()
         size = len(self._files)
         self._loadalllazy()
         for m in self._dirs.values():
             size += m.__len__()
         return size
 
     def __nonzero__(self):
         # Faster than "__len() != 0" since it avoids loading sub-manifests
         return not self._isempty()
 
     __bool__ = __nonzero__
 
     def _isempty(self):
         self._load()  # for consistency; already loaded by all callers
         # See if we can skip loading everything.
         if self._files or (
             self._dirs and any(not m._isempty() for m in self._dirs.values())
         ):
             return False
         self._loadalllazy()
         return not self._dirs or all(m._isempty() for m in self._dirs.values())
 
+    @encoding.strmethod
     def __repr__(self):
         return (
-            b'<treemanifest dir=%s, node=%s, loaded=%s, dirty=%s at 0x%x>'
+            b'<treemanifest dir=%s, node=%s, loaded=%r, dirty=%r at 0x%x>'
             % (
                 self._dir,
                 hex(self._node),
                 bool(self._loadfunc is _noop),
                 self._dirty,
                 id(self),
             )
         )
 
     def dir(self):
         '''The directory that this tree manifest represents, including a
         trailing '/'. Empty string for the repo root directory.'''
         return self._dir
 
     def node(self):
         '''This node of this instance. nullid for unsaved instances. Should
         be updated when the instance is read or written from a revlog.
         '''
         assert not self._dirty
         return self._node
 
     def setnode(self, node):
         self._node = node
         self._dirty = False
 
     def iterentries(self):
         self._load()
         self._loadalllazy()
         for p, n in sorted(
             itertools.chain(self._dirs.items(), self._files.items())
         ):
             if p in self._files:
                 yield self._subpath(p), n, self._flags.get(p, b'')
             else:
                 for x in n.iterentries():
                     yield x
 
     def items(self):
         self._load()
         self._loadalllazy()
         for p, n in sorted(
             itertools.chain(self._dirs.items(), self._files.items())
         ):
             if p in self._files:
                 yield self._subpath(p), n
             else:
                 for f, sn in pycompat.iteritems(n):
                     yield f, sn
 
     iteritems = items
 
     def iterkeys(self):
         self._load()
         self._loadalllazy()
         for p in sorted(itertools.chain(self._dirs, self._files)):
             if p in self._files:
                 yield self._subpath(p)
             else:
                 for f in self._dirs[p]:
                     yield f
 
     def keys(self):
         return list(self.iterkeys())
 
     def __iter__(self):
         return self.iterkeys()
 
     def __contains__(self, f):
         if f is None:
             return False
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             if dir not in self._dirs:
                 return False
 
             return self._dirs[dir].__contains__(subpath)
         else:
             return f in self._files
 
     def get(self, f, default=None):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             if dir not in self._dirs:
                 return default
             return self._dirs[dir].get(subpath, default)
         else:
             return self._files.get(f, default)
 
     def __getitem__(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             return self._dirs[dir].__getitem__(subpath)
         else:
             return self._files[f]
 
     def flags(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             if dir not in self._dirs:
                 return b''
             return self._dirs[dir].flags(subpath)
         else:
             if f in self._lazydirs or f in self._dirs:
                 return b''
             return self._flags.get(f, b'')
 
     def find(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             return self._dirs[dir].find(subpath)
         else:
             return self._files[f], self._flags.get(f, b'')
 
     def __delitem__(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             self._dirs[dir].__delitem__(subpath)
             # If the directory is now empty, remove it
             if self._dirs[dir]._isempty():
                 del self._dirs[dir]
         else:
             del self._files[f]
             if f in self._flags:
                 del self._flags[f]
         self._dirty = True
 
     def __setitem__(self, f, n):
         assert n is not None
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
             if dir not in self._dirs:
                 self._dirs[dir] = treemanifest(self._subpath(dir))
             self._dirs[dir].__setitem__(subpath, n)
         else:
             self._files[f] = n[:21]  # to match manifestdict's behavior
         self._dirty = True
 
     def _load(self):
         if self._loadfunc is not _noop:
             lf, self._loadfunc = self._loadfunc, _noop
             lf(self)
         elif self._copyfunc is not _noop:
             cf, self._copyfunc = self._copyfunc, _noop
             cf(self)
 
     def setflag(self, f, flags):
         """Set the flags (symlink, executable) for path f."""
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
             if dir not in self._dirs:
                 self._dirs[dir] = treemanifest(self._subpath(dir))
             self._dirs[dir].setflag(subpath, flags)
         else:
             self._flags[f] = flags
         self._dirty = True
 
     def copy(self):
         copy = treemanifest(self._dir)
         copy._node = self._node
         copy._dirty = self._dirty
         if self._copyfunc is _noop:
 
             def _copyfunc(s):
                 self._load()
                 s._lazydirs = {
                     d: (p, n, r, True)
                     for d, (p, n, r, c) in pycompat.iteritems(self._lazydirs)
                 }
                 sdirs = s._dirs
                 for d, v in pycompat.iteritems(self._dirs):
                     sdirs[d] = v.copy()
                 s._files = dict.copy(self._files)
                 s._flags = dict.copy(self._flags)
 
             if self._loadfunc is _noop:
                 _copyfunc(copy)
             else:
                 copy._copyfunc = _copyfunc
         else:
             copy._copyfunc = self._copyfunc
         return copy
 
     def filesnotin(self, m2, match=None):
         '''Set of files in this manifest that are not in the other'''
         if match and not match.always():
             m1 = self.matches(match)
             m2 = m2.matches(match)
             return m1.filesnotin(m2)
 
         files = set()
 
         def _filesnotin(t1, t2):
             if t1._node == t2._node and not t1._dirty and not t2._dirty:
                 return
             t1._load()
             t2._load()
             self._loaddifflazy(t1, t2)
             for d, m1 in pycompat.iteritems(t1._dirs):
                 if d in t2._dirs:
                     m2 = t2._dirs[d]
                     _filesnotin(m1, m2)
                 else:
                     files.update(m1.iterkeys())
 
             for fn in t1._files:
                 if fn not in t2._files:
                     files.add(t1._subpath(fn))
 
         _filesnotin(self, m2)
         return files
 
     @propertycache
     def _alldirs(self):
         return pathutil.dirs(self)
 
     def dirs(self):
         return self._alldirs
 
     def hasdir(self, dir):
         self._load()
         topdir, subdir = _splittopdir(dir)
         if topdir:
             self._loadlazy(topdir)
             if topdir in self._dirs:
                 return self._dirs[topdir].hasdir(subdir)
             return False
         dirslash = dir + b'/'
         return dirslash in self._dirs or dirslash in self._lazydirs
 
     def walk(self, match):
         '''Generates matching file names.
 
         Equivalent to manifest.matches(match).iterkeys(), but without creating
         an entirely new manifest.
 
         It also reports nonexistent files by marking them bad with match.bad().
         '''
         if match.always():
             for f in iter(self):
                 yield f
             return
 
         fset = set(match.files())
 
         for fn in self._walk(match):
             if fn in fset:
                 # specified pattern is the exact name
                 fset.remove(fn)
             yield fn
 
         # for dirstate.walk, files=[''] means "walk the whole tree".
         # follow that here, too
         fset.discard(b'')
 
         for fn in sorted(fset):
             if not self.hasdir(fn):
                 match.bad(fn, None)
 
     def _walk(self, match):
         '''Recursively generates matching file names for walk().'''
         visit = match.visitchildrenset(self._dir[:-1])
         if not visit:
             return
 
         # yield this dir's files and walk its submanifests
         self._load()
         visit = self._loadchildrensetlazy(visit)
         for p in sorted(list(self._dirs) + list(self._files)):
             if p in self._files:
                 fullp = self._subpath(p)
                 if match(fullp):
                     yield fullp
             else:
                 if not visit or p[:-1] in visit:
                     for f in self._dirs[p]._walk(match):
                         yield f
 
     def matches(self, match):
         '''generate a new manifest filtered by the match argument'''
         if match.always():
             return self.copy()
 
         return self._matches(match)
 
     def _matches(self, match):
         '''recursively generate a new manifest filtered by the match argument.
         '''
 
         visit = match.visitchildrenset(self._dir[:-1])
         if visit == b'all':
             return self.copy()
         ret = treemanifest(self._dir)
         if not visit:
             return ret
 
         self._load()
         for fn in self._files:
             # While visitchildrenset *usually* lists only subdirs, this is
             # actually up to the matcher and may have some files in the set().
             # If visit == 'this', we should obviously look at the files in this
             # directory; if visit is a set, and fn is in it, we should inspect
             # fn (but no need to inspect things not in the set).
             if visit != b'this' and fn not in visit:
                 continue
             fullp = self._subpath(fn)
             # visitchildrenset isn't perfect, we still need to call the regular
             # matcher code to further filter results.
             if not match(fullp):
                 continue
             ret._files[fn] = self._files[fn]
             if fn in self._flags:
                 ret._flags[fn] = self._flags[fn]
 
         visit = self._loadchildrensetlazy(visit)
         for dir, subm in pycompat.iteritems(self._dirs):
             if visit and dir[:-1] not in visit:
                 continue
             m = subm._matches(match)
             if not m._isempty():
                 ret._dirs[dir] = m
 
         if not ret._isempty():
             ret._dirty = True
         return ret
 
     def diff(self, m2, match=None, clean=False):
         '''Finds changes between the current manifest and m2.
 
         Args:
           m2: the manifest to which this manifest should be compared.
           clean: if true, include files unchanged between these manifests
                  with a None value in the returned dictionary.
 
         The result is returned as a dict with filename as key and
         values of the form ((n1,fl1),(n2,fl2)), where n1/n2 is the
         nodeid in the current/other manifest and fl1/fl2 is the flag
         in the current/other manifest. Where the file does not exist,
         the nodeid will be None and the flags will be the empty
         string.
         '''
         if match and not match.always():
             m1 = self.matches(match)
             m2 = m2.matches(match)
             return m1.diff(m2, clean=clean)
         result = {}
         emptytree = treemanifest()
 
         def _iterativediff(t1, t2, stack):
             """compares two tree manifests and append new tree-manifests which
             needs to be compared to stack"""
             if t1._node == t2._node and not t1._dirty and not t2._dirty:
                 return
             t1._load()
             t2._load()
             self._loaddifflazy(t1, t2)
 
             for d, m1 in pycompat.iteritems(t1._dirs):
                 m2 = t2._dirs.get(d, emptytree)
                 stack.append((m1, m2))
 
             for d, m2 in pycompat.iteritems(t2._dirs):
                 if d not in t1._dirs:
                     stack.append((emptytree, m2))
 
             for fn, n1 in pycompat.iteritems(t1._files):
                 fl1 = t1._flags.get(fn, b'')
                 n2 = t2._files.get(fn, None)
                 fl2 = t2._flags.get(fn, b'')
                 if n1 != n2 or fl1 != fl2:
                     result[t1._subpath(fn)] = ((n1, fl1), (n2, fl2))
                 elif clean:
                     result[t1._subpath(fn)] = None
 
             for fn, n2 in pycompat.iteritems(t2._files):
                 if fn not in t1._files:
                     fl2 = t2._flags.get(fn, b'')
                     result[t2._subpath(fn)] = ((None, b''), (n2, fl2))
 
         stackls = []
         _iterativediff(self, m2, stackls)
         while stackls:
             t1, t2 = stackls.pop()
             # stackls is populated in the function call
             _iterativediff(t1, t2, stackls)
         return result
 
     def unmodifiedsince(self, m2):
         return not self._dirty and not m2._dirty and self._node == m2._node
 
     def parse(self, text, readsubtree):
         selflazy = self._lazydirs
         subpath = self._subpath
         for f, n, fl in _parse(text):
             if fl == b't':
                 f = f + b'/'
                 # False below means "doesn't need to be copied" and can use the
                 # cached value from readsubtree directly.
                 selflazy[f] = (subpath(f), n, readsubtree, False)
             elif b'/' in f:
                 # This is a flat manifest, so use __setitem__ and setflag rather
                 # than assigning directly to _files and _flags, so we can
                 # assign a path in a subdirectory, and to mark dirty (compared
                 # to nullid).
                 self[f] = n
                 if fl:
                     self.setflag(f, fl)
             else:
                 # Assigning to _files and _flags avoids marking as dirty,
                 # and should be a little faster.
                 self._files[f] = n
                 if fl:
                     self._flags[f] = fl
 
     def text(self):
         """Get the full data of this manifest as a bytestring."""
         self._load()
         return _text(self.iterentries())
 
     def dirtext(self):
         """Get the full data of this directory as a bytestring. Make sure that
         any submanifests have been written first, so their nodeids are correct.
         """
         self._load()
         flags = self.flags
         lazydirs = [
             (d[:-1], v[1], b't') for d, v in pycompat.iteritems(self._lazydirs)
         ]
         dirs = [(d[:-1], self._dirs[d]._node, b't') for d in self._dirs]
         files = [(f, self._files[f], flags(f)) for f in self._files]
         return _text(sorted(dirs + files + lazydirs))
 
     def read(self, gettext, readsubtree):
         def _load_for_read(s):
             s.parse(gettext(), readsubtree)
             s._dirty = False
 
         self._loadfunc = _load_for_read
 
     def writesubtrees(self, m1, m2, writesubtree, match):
         self._load()  # for consistency; should never have any effect here
         m1._load()
         m2._load()
         emptytree = treemanifest()
 
         def getnode(m, d):
             ld = m._lazydirs.get(d)
             if ld:
                 return ld[1]
             return m._dirs.get(d, emptytree)._node
 
         # let's skip investigating things that `match` says we do not need.
         visit = match.visitchildrenset(self._dir[:-1])
         visit = self._loadchildrensetlazy(visit)
         if visit == b'this' or visit == b'all':
             visit = None
         for d, subm in pycompat.iteritems(self._dirs):
             if visit and d[:-1] not in visit:
                 continue
             subp1 = getnode(m1, d)
             subp2 = getnode(m2, d)
             if subp1 == nullid:
                 subp1, subp2 = subp2, subp1
             writesubtree(subm, subp1, subp2, match)
 
     def walksubtrees(self, matcher=None):
         """Returns an iterator of the subtrees of this manifest, including this
         manifest itself.
 
         If `matcher` is provided, it only returns subtrees that match.
         """
         if matcher and not matcher.visitdir(self._dir[:-1]):
             return
         if not matcher or matcher(self._dir[:-1]):
             yield self
 
         self._load()
         # OPT: use visitchildrenset to avoid loading everything.
         self._loadalllazy()
         for d, subm in pycompat.iteritems(self._dirs):
             for subtree in subm.walksubtrees(matcher=matcher):
                 yield subtree
 
 
 class manifestfulltextcache(util.lrucachedict):
     """File-backed LRU cache for the manifest cache
 
     File consists of entries, up to EOF:
 
     - 20 bytes node, 4 bytes length, <length> manifest data
 
     These are written in reverse cache order (oldest to newest).
 
     """
 
     _file = b'manifestfulltextcache'
 
     def __init__(self, max):
         super(manifestfulltextcache, self).__init__(max)
         self._dirty = False
         self._read = False
         self._opener = None
 
     def read(self):
         if self._read or self._opener is None:
             return
 
         try:
             with self._opener(self._file) as fp:
                 set = super(manifestfulltextcache, self).__setitem__
                 # ignore trailing data, this is a cache, corruption is skipped
                 while True:
                     node = fp.read(20)
                     if len(node) < 20:
                         break
                     try:
                         size = struct.unpack(b'>L', fp.read(4))[0]
                     except struct.error:
                         break
                     value = bytearray(fp.read(size))
                     if len(value) != size:
                         break
                     set(node, value)
         except IOError:
             # the file is allowed to be missing
             pass
 
         self._read = True
         self._dirty = False
 
     def write(self):
         if not self._dirty or self._opener is None:
             return
         # rotate backwards to the first used node
         with self._opener(
             self._file, b'w', atomictemp=True, checkambig=True
         ) as fp:
             node = self._head.prev
             while True:
                 if node.key in self._cache:
                     fp.write(node.key)
                     fp.write(struct.pack(b'>L', len(node.value)))
                     fp.write(node.value)
                 if node is self._head:
                     break
                 node = node.prev
 
     def __len__(self):
         if not self._read:
             self.read()
         return super(manifestfulltextcache, self).__len__()
 
     def __contains__(self, k):
         if not self._read:
             self.read()
         return super(manifestfulltextcache, self).__contains__(k)
 
     def __iter__(self):
         if not self._read:
             self.read()
         return super(manifestfulltextcache, self).__iter__()
 
     def __getitem__(self, k):
         if not self._read:
             self.read()
         # the cache lru order can change on read
         setdirty = self._cache.get(k) is not self._head
         value = super(manifestfulltextcache, self).__getitem__(k)
         if setdirty:
             self._dirty = True
         return value
 
     def __setitem__(self, k, v):
         if not self._read:
             self.read()
         super(manifestfulltextcache, self).__setitem__(k, v)
         self._dirty = True
 
     def __delitem__(self, k):
         if not self._read:
             self.read()
         super(manifestfulltextcache, self).__delitem__(k)
         self._dirty = True
 
     def get(self, k, default=None):
         if not self._read:
             self.read()
         return super(manifestfulltextcache, self).get(k, default=default)
 
     def clear(self, clear_persisted_data=False):
         super(manifestfulltextcache, self).clear()
         if clear_persisted_data:
             self._dirty = True
             self.write()
         self._read = False
 
 
 # and upper bound of what we expect from compression
 # (real live value seems to be "3")
 MAXCOMPRESSION = 3
 
 
 @interfaceutil.implementer(repository.imanifeststorage)
 class manifestrevlog(object):
     '''A revlog that stores manifest texts. This is responsible for caching the
     full-text manifest contents.
     '''
 
     def __init__(
         self,
         opener,
         tree=b'',
         dirlogcache=None,
         indexfile=None,
         treemanifest=False,
     ):
         """Constructs a new manifest revlog
 
         `indexfile` - used by extensions to have two manifests at once, like
         when transitioning between flatmanifeset and treemanifests.
 
         `treemanifest` - used to indicate this is a tree manifest revlog. Opener
         options can also be used to make this a tree manifest revlog. The opener
         option takes precedence, so if it is set to True, we ignore whatever
         value is passed in to the constructor.
         """
         # During normal operations, we expect to deal with not more than four
         # revs at a time (such as during commit --amend). When rebasing large
         # stacks of commits, the number can go up, hence the config knob below.
         cachesize = 4
         optiontreemanifest = False
         opts = getattr(opener, 'options', None)
         if opts is not None:
             cachesize = opts.get(b'manifestcachesize', cachesize)
             optiontreemanifest = opts.get(b'treemanifest', False)
 
         self._treeondisk = optiontreemanifest or treemanifest
 
         self._fulltextcache = manifestfulltextcache(cachesize)
 
         if tree:
             assert self._treeondisk, b'opts is %r' % opts
 
         if indexfile is None:
             indexfile = b'00manifest.i'
             if tree:
                 indexfile = b"meta/" + tree + indexfile
 
         self.tree = tree
 
         # The dirlogcache is kept on the root manifest log
         if tree:
             self._dirlogcache = dirlogcache
         else:
             self._dirlogcache = {b'': self}
 
         self._revlog = revlog.revlog(
             opener,
             indexfile,
             # only root indexfile is cached
             checkambig=not bool(tree),
             mmaplargeindex=True,
             upperboundcomp=MAXCOMPRESSION,
         )
 
         self.index = self._revlog.index
         self.version = self._revlog.version
         self._generaldelta = self._revlog._generaldelta
 
     def _setupmanifestcachehooks(self, repo):
         """Persist the manifestfulltextcache on lock release"""
         if not util.safehasattr(repo, b'_wlockref'):
             return
 
         self._fulltextcache._opener = repo.wcachevfs
         if repo._currentlock(repo._wlockref) is None:
             return
 
         reporef = weakref.ref(repo)
         manifestrevlogref = weakref.ref(self)
 
         def persistmanifestcache(success):
             # Repo is in an unknown state, do not persist.
             if not success:
                 return
 
             repo = reporef()
             self = manifestrevlogref()
             if repo is None or self is None:
                 return
             if repo.manifestlog.getstorage(b'') is not self:
                 # there's a different manifest in play now, abort
                 return
             self._fulltextcache.write()
 
         repo._afterlock(persistmanifestcache)
 
     @property
     def fulltextcache(self):
         return self._fulltextcache
 
     def clearcaches(self, clear_persisted_data=False):
         self._revlog.clearcaches()
         self._fulltextcache.clear(clear_persisted_data=clear_persisted_data)
         self._dirlogcache = {self.tree: self}
 
     def dirlog(self, d):
         if d:
             assert self._treeondisk
         if d not in self._dirlogcache:
             mfrevlog = manifestrevlog(
                 self.opener, d, self._dirlogcache, treemanifest=self._treeondisk
             )
             self._dirlogcache[d] = mfrevlog
         return self._dirlogcache[d]
 
     def add(
         self,
         m,
         transaction,
         link,
         p1,
         p2,
         added,
         removed,
         readtree=None,
         match=None,
     ):
         if p1 in self.fulltextcache and util.safehasattr(m, b'fastdelta'):
             # If our first parent is in the manifest cache, we can
             # compute a delta here using properties we know about the
             # manifest up-front, which may save time later for the
             # revlog layer.
 
             _checkforbidden(added)
             # combine the changed lists into one sorted iterator
             work = heapq.merge(
                 [(x, False) for x in sorted(added)],
                 [(x, True) for x in sorted(removed)],
             )
 
             arraytext, deltatext = m.fastdelta(self.fulltextcache[p1], work)
             cachedelta = self._revlog.rev(p1), deltatext
             text = util.buffer(arraytext)
             n = self._revlog.addrevision(
                 text, transaction, link, p1, p2, cachedelta
             )
         else:
             # The first parent manifest isn't already loaded, so we'll
             # just encode a fulltext of the manifest and pass that
             # through to the revlog layer, and let it handle the delta
             # process.
             if self._treeondisk:
                 assert readtree, b"readtree must be set for treemanifest writes"
                 assert match, b"match must be specified for treemanifest writes"
                 m1 = readtree(self.tree, p1)
                 m2 = readtree(self.tree, p2)
                 n = self._addtree(
                     m, transaction, link, m1, m2, readtree, match=match
                 )
                 arraytext = None
             else:
                 text = m.text()
                 n = self._revlog.addrevision(text, transaction, link, p1, p2)
                 arraytext = bytearray(text)
 
         if arraytext is not None:
             self.fulltextcache[n] = arraytext
 
         return n
 
     def _addtree(self, m, transaction, link, m1, m2, readtree, match):
         # If the manifest is unchanged compared to one parent,
         # don't write a new revision
         if self.tree != b'' and (
             m.unmodifiedsince(m1) or m.unmodifiedsince(m2)
         ):
             return m.node()
 
         def writesubtree(subm, subp1, subp2, match):
             sublog = self.dirlog(subm.dir())
             sublog.add(
                 subm,
                 transaction,
                 link,
                 subp1,
                 subp2,
                 None,
                 None,
                 readtree=readtree,
                 match=match,
             )
 
         m.writesubtrees(m1, m2, writesubtree, match)
         text = m.dirtext()
         n = None
         if self.tree != b'':
             # Double-check whether contents are unchanged to one parent
             if text == m1.dirtext():
                 n = m1.node()
             elif text == m2.dirtext():
                 n = m2.node()
 
         if not n:
             n = self._revlog.addrevision(
                 text, transaction, link, m1.node(), m2.node()
             )
 
         # Save nodeid so parent manifest can calculate its nodeid
         m.setnode(n)
         return n
 
     def __len__(self):
         return len(self._revlog)
 
     def __iter__(self):
         return self._revlog.__iter__()
 
     def rev(self, node):
         return self._revlog.rev(node)
 
     def node(self, rev):
         return self._revlog.node(rev)
 
     def lookup(self, value):
         return self._revlog.lookup(value)
 
     def parentrevs(self, rev):
         return self._revlog.parentrevs(rev)
 
     def parents(self, node):
         return self._revlog.parents(node)
 
     def linkrev(self, rev):
         return self._revlog.linkrev(rev)
 
     def checksize(self):
         return self._revlog.checksize()
 
     def revision(self, node, _df=None, raw=False):
         return self._revlog.revision(node, _df=_df, raw=raw)
 
     def rawdata(self, node, _df=None):
         return self._revlog.rawdata(node, _df=_df)
 
     def revdiff(self, rev1, rev2):
         return self._revlog.revdiff(rev1, rev2)
 
     def cmp(self, node, text):
         return self._revlog.cmp(node, text)
 
     def deltaparent(self, rev):
         return self._revlog.deltaparent(rev)
 
     def emitrevisions(
         self,
         nodes,
         nodesorder=None,
         revisiondata=False,
         assumehaveparentrevisions=False,
         deltamode=repository.CG_DELTAMODE_STD,
     ):
         return self._revlog.emitrevisions(
             nodes,
             nodesorder=nodesorder,
             revisiondata=revisiondata,
             assumehaveparentrevisions=assumehaveparentrevisions,
             deltamode=deltamode,
         )
 
     def addgroup(self, deltas, linkmapper, transaction, addrevisioncb=None):
         return self._revlog.addgroup(
             deltas, linkmapper, transaction, addrevisioncb=addrevisioncb
         )
 
     def rawsize(self, rev):
         return self._revlog.rawsize(rev)
 
     def getstrippoint(self, minlink):
         return self._revlog.getstrippoint(minlink)
 
     def strip(self, minlink, transaction):
         return self._revlog.strip(minlink, transaction)
 
     def files(self):
         return self._revlog.files()
 
     def clone(self, tr, destrevlog, **kwargs):
         if not isinstance(destrevlog, manifestrevlog):
             raise error.ProgrammingError(b'expected manifestrevlog to clone()')
 
         return self._revlog.clone(tr, destrevlog._revlog, **kwargs)
 
     def storageinfo(
         self,
         exclusivefiles=False,
         sharedfiles=False,
         revisionscount=False,
         trackedsize=False,
         storedsize=False,
     ):
         return self._revlog.storageinfo(
             exclusivefiles=exclusivefiles,
             sharedfiles=sharedfiles,
             revisionscount=revisionscount,
             trackedsize=trackedsize,
             storedsize=storedsize,
         )
 
     @property
     def indexfile(self):
         return self._revlog.indexfile
 
     @indexfile.setter
     def indexfile(self, value):
         self._revlog.indexfile = value
 
     @property
     def opener(self):
         return self._revlog.opener
 
     @opener.setter
     def opener(self, value):
         self._revlog.opener = value
 
 
 @interfaceutil.implementer(repository.imanifestlog)
 class manifestlog(object):
     """A collection class representing the collection of manifest snapshots
     referenced by commits in the repository.
 
     In this situation, 'manifest' refers to the abstract concept of a snapshot
     of the list of files in the given commit. Consumers of the output of this
     class do not care about the implementation details of the actual manifests
     they receive (i.e. tree or flat or lazily loaded, etc)."""
 
     def __init__(self, opener, repo, rootstore, narrowmatch):
         usetreemanifest = False
         cachesize = 4
 
         opts = getattr(opener, 'options', None)
         if opts is not None:
             usetreemanifest = opts.get(b'treemanifest', usetreemanifest)
             cachesize = opts.get(b'manifestcachesize', cachesize)
 
         self._treemanifests = usetreemanifest
 
         self._rootstore = rootstore
         self._rootstore._setupmanifestcachehooks(repo)
         self._narrowmatch = narrowmatch
 
         # A cache of the manifestctx or treemanifestctx for each directory
         self._dirmancache = {}
         self._dirmancache[b''] = util.lrucachedict(cachesize)
 
         self._cachesize = cachesize
 
     def __getitem__(self, node):
         """Retrieves the manifest instance for the given node. Throws a
         LookupError if not found.
         """
         return self.get(b'', node)
 
     def get(self, tree, node, verify=True):
         """Retrieves the manifest instance for the given node. Throws a
         LookupError if not found.
 
         `verify` - if True an exception will be thrown if the node is not in
                    the revlog
         """
         if node in self._dirmancache.get(tree, ()):
             return self._dirmancache[tree][node]
 
         if not self._narrowmatch.always():
             if not self._narrowmatch.visitdir(tree[:-1]):
                 return excludeddirmanifestctx(tree, node)
         if tree:
             if self._rootstore._treeondisk:
                 if verify:
                     # Side-effect is LookupError is raised if node doesn't
                     # exist.
                     self.getstorage(tree).rev(node)
 
                 m = treemanifestctx(self, tree, node)
             else:
                 raise error.Abort(
                     _(
                         b"cannot ask for manifest directory '%s' in a flat "
                         b"manifest"
                     )
                     % tree
                 )
         else:
             if verify:
                 # Side-effect is LookupError is raised if node doesn't exist.
                 self._rootstore.rev(node)
 
             if self._treemanifests:
                 m = treemanifestctx(self, b'', node)
             else:
                 m = manifestctx(self, node)
 
         if node != nullid:
             mancache = self._dirmancache.get(tree)
             if not mancache:
                 mancache = util.lrucachedict(self._cachesize)
                 self._dirmancache[tree] = mancache
             mancache[node] = m
         return m
 
     def getstorage(self, tree):
         return self._rootstore.dirlog(tree)
 
     def clearcaches(self, clear_persisted_data=False):
         self._dirmancache.clear()
         self._rootstore.clearcaches(clear_persisted_data=clear_persisted_data)
 
     def rev(self, node):
         return self._rootstore.rev(node)
 
 
 @interfaceutil.implementer(repository.imanifestrevisionwritable)
 class memmanifestctx(object):
     def __init__(self, manifestlog):
         self._manifestlog = manifestlog
         self._manifestdict = manifestdict()
 
     def _storage(self):
         return self._manifestlog.getstorage(b'')
 
     def copy(self):
         memmf = memmanifestctx(self._manifestlog)
         memmf._manifestdict = self.read().copy()
         return memmf
 
     def read(self):
         return self._manifestdict
 
     def write(self, transaction, link, p1, p2, added, removed, match=None):
         return self._storage().add(
             self._manifestdict,
             transaction,
             link,
             p1,
             p2,
             added,
             removed,
             match=match,
         )
 
 
 @interfaceutil.implementer(repository.imanifestrevisionstored)
 class manifestctx(object):
     """A class representing a single revision of a manifest, including its
     contents, its parent revs, and its linkrev.
     """
 
     def __init__(self, manifestlog, node):
         self._manifestlog = manifestlog
         self._data = None
 
         self._node = node
 
         # TODO: We eventually want p1, p2, and linkrev exposed on this class,
         # but let's add it later when something needs it and we can load it
         # lazily.
         # self.p1, self.p2 = store.parents(node)
         # rev = store.rev(node)
         # self.linkrev = store.linkrev(rev)
 
     def _storage(self):
         return self._manifestlog.getstorage(b'')
 
     def node(self):
         return self._node
 
     def copy(self):
         memmf = memmanifestctx(self._manifestlog)
         memmf._manifestdict = self.read().copy()
         return memmf
 
     @propertycache
     def parents(self):
         return self._storage().parents(self._node)
 
     def read(self):
         if self._data is None:
             if self._node == nullid:
                 self._data = manifestdict()
             else:
                 store = self._storage()
                 if self._node in store.fulltextcache:
                     text = pycompat.bytestr(store.fulltextcache[self._node])
                 else:
                     text = store.revision(self._node)
                     arraytext = bytearray(text)
                     store.fulltextcache[self._node] = arraytext
                 self._data = manifestdict(text)
         return self._data
 
     def readfast(self, shallow=False):
         '''Calls either readdelta or read, based on which would be less work.
         readdelta is called if the delta is against the p1, and therefore can be
         read quickly.
 
         If `shallow` is True, nothing changes since this is a flat manifest.
         '''
         store = self._storage()
         r = store.rev(self._node)
         deltaparent = store.deltaparent(r)
         if deltaparent != nullrev and deltaparent in store.parentrevs(r):
             return self.readdelta()
         return self.read()
 
     def readdelta(self, shallow=False):
         '''Returns a manifest containing just the entries that are present
         in this manifest, but not in its p1 manifest. This is efficient to read
         if the revlog delta is already p1.
 
         Changing the value of `shallow` has no effect on flat manifests.
         '''
         store = self._storage()
         r = store.rev(self._node)
         d = mdiff.patchtext(store.revdiff(store.deltaparent(r), r))
         return manifestdict(d)
 
     def find(self, key):
         return self.read().find(key)
 
 
 @interfaceutil.implementer(repository.imanifestrevisionwritable)
 class memtreemanifestctx(object):
     def __init__(self, manifestlog, dir=b''):
         self._manifestlog = manifestlog
         self._dir = dir
         self._treemanifest = treemanifest()
 
     def _storage(self):
         return self._manifestlog.getstorage(b'')
 
     def copy(self):
         memmf = memtreemanifestctx(self._manifestlog, dir=self._dir)
         memmf._treemanifest = self._treemanifest.copy()
         return memmf
 
     def read(self):
         return self._treemanifest
 
     def write(self, transaction, link, p1, p2, added, removed, match=None):
         def readtree(dir, node):
             return self._manifestlog.get(dir, node).read()
 
         return self._storage().add(
             self._treemanifest,
             transaction,
             link,
             p1,
             p2,
             added,
             removed,
             readtree=readtree,
             match=match,
         )
 
 
 @interfaceutil.implementer(repository.imanifestrevisionstored)
 class treemanifestctx(object):
     def __init__(self, manifestlog, dir, node):
         self._manifestlog = manifestlog
         self._dir = dir
         self._data = None
 
         self._node = node
 
         # TODO: Load p1/p2/linkrev lazily. They need to be lazily loaded so that
         # we can instantiate treemanifestctx objects for directories we don't
         # have on disk.
         # self.p1, self.p2 = store.parents(node)
         # rev = store.rev(node)
         # self.linkrev = store.linkrev(rev)
 
     def _storage(self):
         narrowmatch = self._manifestlog._narrowmatch
         if not narrowmatch.always():
             if not narrowmatch.visitdir(self._dir[:-1]):
                 return excludedmanifestrevlog(self._dir)
         return self._manifestlog.getstorage(self._dir)
 
     def read(self):
         if self._data is None:
             store = self._storage()
             if self._node == nullid:
                 self._data = treemanifest()
             # TODO accessing non-public API
             elif store._treeondisk:
                 m = treemanifest(dir=self._dir)
 
                 def gettext():
                     return store.revision(self._node)
 
                 def readsubtree(dir, subm):
                     # Set verify to False since we need to be able to create
                     # subtrees for trees that don't exist on disk.
                     return self._manifestlog.get(dir, subm, verify=False).read()
 
                 m.read(gettext, readsubtree)
                 m.setnode(self._node)
                 self._data = m
             else:
                 if self._node in store.fulltextcache:
                     text = pycompat.bytestr(store.fulltextcache[self._node])
                 else:
                     text = store.revision(self._node)
                     arraytext = bytearray(text)
                     store.fulltextcache[self._node] = arraytext
                 self._data = treemanifest(dir=self._dir, text=text)
 
         return self._data
 
     def node(self):
         return self._node
 
     def copy(self):
         memmf = memtreemanifestctx(self._manifestlog, dir=self._dir)
         memmf._treemanifest = self.read().copy()
         return memmf
 
     @propertycache
     def parents(self):
         return self._storage().parents(self._node)
 
     def readdelta(self, shallow=False):
         '''Returns a manifest containing just the entries that are present
         in this manifest, but not in its p1 manifest. This is efficient to read
         if the revlog delta is already p1.
 
         If `shallow` is True, this will read the delta for this directory,
         without recursively reading subdirectory manifests. Instead, any
         subdirectory entry will be reported as it appears in the manifest, i.e.
         the subdirectory will be reported among files and distinguished only by
         its 't' flag.
         '''
         store = self._storage()
         if shallow:
             r = store.rev(self._node)
             d = mdiff.patchtext(store.revdiff(store.deltaparent(r), r))
             return manifestdict(d)
         else:
             # Need to perform a slow delta
             r0 = store.deltaparent(store.rev(self._node))
             m0 = self._manifestlog.get(self._dir, store.node(r0)).read()
             m1 = self.read()
             md = treemanifest(dir=self._dir)
             for f, ((n0, fl0), (n1, fl1)) in pycompat.iteritems(m0.diff(m1)):
                 if n1:
                     md[f] = n1
                     if fl1:
                         md.setflag(f, fl1)
             return md
 
     def readfast(self, shallow=False):
         '''Calls either readdelta or read, based on which would be less work.
         readdelta is called if the delta is against the p1, and therefore can be
         read quickly.
 
         If `shallow` is True, it only returns the entries from this manifest,
         and not any submanifests.
         '''
         store = self._storage()
         r = store.rev(self._node)
         deltaparent = store.deltaparent(r)
         if deltaparent != nullrev and deltaparent in store.parentrevs(r):
             return self.readdelta(shallow=shallow)
 
         if shallow:
             return manifestdict(store.revision(self._node))
         else:
             return self.read()
 
     def find(self, key):
         return self.read().find(key)
 
 
 class excludeddir(treemanifest):
     """Stand-in for a directory that is excluded from the repository.
 
     With narrowing active on a repository that uses treemanifests,
     some of the directory revlogs will be excluded from the resulting
     clone. This is a huge storage win for clients, but means we need
     some sort of pseudo-manifest to surface to internals so we can
     detect a merge conflict outside the narrowspec. That's what this
     class is: it stands in for a directory whose node is known, but
     whose contents are unknown.
     """
 
     def __init__(self, dir, node):
         super(excludeddir, self).__init__(dir)
         self._node = node
         # Add an empty file, which will be included by iterators and such,
         # appearing as the directory itself (i.e. something like "dir/")
         self._files[b''] = node
         self._flags[b''] = b't'
 
     # Manifests outside the narrowspec should never be modified, so avoid
     # copying. This makes a noticeable difference when there are very many
     # directories outside the narrowspec. Also, it makes sense for the copy to
     # be of the same type as the original, which would not happen with the
     # super type's copy().
     def copy(self):
         return self
 
 
 class excludeddirmanifestctx(treemanifestctx):
     """context wrapper for excludeddir - see that docstring for rationale"""
 
     def __init__(self, dir, node):
         self._dir = dir
         self._node = node
 
     def read(self):
         return excludeddir(self._dir, self._node)
 
     def write(self, *args):
         raise error.ProgrammingError(
             b'attempt to write manifest from excluded dir %s' % self._dir
         )
 
 
 class excludedmanifestrevlog(manifestrevlog):
     """Stand-in for excluded treemanifest revlogs.
 
     When narrowing is active on a treemanifest repository, we'll have
     references to directories we can't see due to the revlog being
     skipped. This class exists to conform to the manifestrevlog
     interface for those directories and proactively prevent writes to
     outside the narrowspec.
     """
 
     def __init__(self, dir):
         self._dir = dir
 
     def __len__(self):
         raise error.ProgrammingError(
             b'attempt to get length of excluded dir %s' % self._dir
         )
 
     def rev(self, node):
         raise error.ProgrammingError(
             b'attempt to get rev from excluded dir %s' % self._dir
         )
 
     def linkrev(self, node):
         raise error.ProgrammingError(
             b'attempt to get linkrev from excluded dir %s' % self._dir
         )
 
     def node(self, rev):
         raise error.ProgrammingError(
             b'attempt to get node from excluded dir %s' % self._dir
         )
 
     def add(self, *args, **kwargs):
         # We should never write entries in dirlogs outside the narrow clone.
         # However, the method still gets called from writesubtree() in
         # _addtree(), so we need to handle it. We should possibly make that
         # avoid calling add() with a clean manifest (_dirty is always False
         # in excludeddir instances).
         pass