reintroduces util.unlink, for POSIX and Windows.

windows: factor it out of rename
posix: add alias 'unlink' for os.unlink

Note that this new unlink function now has different semantics than the
unlink() we had before changeset 6bf39d88c857 ("rename util.unlink to
unlinkpath").

mercurial/posix.py

@@ -1,297 +1,298 b''
 # posix.py - Posix utility function implementations for Mercurial
 #
 #  Copyright 2005-2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from i18n import _
 import osutil
 import os, sys, errno, stat, getpass, pwd, grp
 
 posixfile = open
 nulldev = '/dev/null'
 normpath = os.path.normpath
 samestat = os.path.samestat
+unlink = os.unlink
 rename = os.rename
 expandglobs = False
 
 umask = os.umask(0)
 os.umask(umask)
 
 def openhardlinks():
     '''return true if it is safe to hold open file handles to hardlinks'''
     return True
 
 def rcfiles(path):
     rcs = [os.path.join(path, 'hgrc')]
     rcdir = os.path.join(path, 'hgrc.d')
     try:
         rcs.extend([os.path.join(rcdir, f)
                     for f, kind in osutil.listdir(rcdir)
                     if f.endswith(".rc")])
     except OSError:
         pass
     return rcs
 
 def system_rcpath():
     path = []
     # old mod_python does not set sys.argv
     if len(getattr(sys, 'argv', [])) > 0:
         path.extend(rcfiles(os.path.dirname(sys.argv[0]) +
                               '/../etc/mercurial'))
     path.extend(rcfiles('/etc/mercurial'))
     return path
 
 def user_rcpath():
     return [os.path.expanduser('~/.hgrc')]
 
 def parse_patch_output(output_line):
     """parses the output produced by patch and returns the filename"""
     pf = output_line[14:]
     if os.sys.platform == 'OpenVMS':
         if pf[0] == '`':
             pf = pf[1:-1] # Remove the quotes
     else:
         if pf.startswith("'") and pf.endswith("'") and " " in pf:
             pf = pf[1:-1] # Remove the quotes
     return pf
 
 def sshargs(sshcmd, host, user, port):
     '''Build argument list for ssh'''
     args = user and ("%s@%s" % (user, host)) or host
     return port and ("%s -p %s" % (args, port)) or args
 
 def is_exec(f):
     """check whether a file is executable"""
     return (os.lstat(f).st_mode & 0100 != 0)
 
 def set_flags(f, l, x):
     s = os.lstat(f).st_mode
     if l:
         if not stat.S_ISLNK(s):
             # switch file to link
             data = open(f).read()
             os.unlink(f)
             try:
                 os.symlink(data, f)
             except:
                 # failed to make a link, rewrite file
                 open(f, "w").write(data)
         # no chmod needed at this point
         return
     if stat.S_ISLNK(s):
         # switch link to file
         data = os.readlink(f)
         os.unlink(f)
         open(f, "w").write(data)
         s = 0666 & ~umask # avoid restatting for chmod
 
     sx = s & 0100
     if x and not sx:
         # Turn on +x for every +r bit when making a file executable
         # and obey umask.
         os.chmod(f, s | (s & 0444) >> 2 & ~umask)
     elif not x and sx:
         # Turn off all +x bits
         os.chmod(f, s & 0666)
 
 def set_binary(fd):
     pass
 
 def pconvert(path):
     return path
 
 def localpath(path):
     return path
 
 def samefile(fpath1, fpath2):
     """Returns whether path1 and path2 refer to the same file. This is only
     guaranteed to work for files, not directories."""
     return os.path.samefile(fpath1, fpath2)
 
 def samedevice(fpath1, fpath2):
     """Returns whether fpath1 and fpath2 are on the same device. This is only
     guaranteed to work for files, not directories."""
     st1 = os.lstat(fpath1)
     st2 = os.lstat(fpath2)
     return st1.st_dev == st2.st_dev
 
 if sys.platform == 'darwin':
     import fcntl # only needed on darwin, missing on jython
     def realpath(path):
         '''
         Returns the true, canonical file system path equivalent to the given
         path.
 
         Equivalent means, in this case, resulting in the same, unique
         file system link to the path. Every file system entry, whether a file,
         directory, hard link or symbolic link or special, will have a single
         path preferred by the system, but may allow multiple, differing path
         lookups to point to it.
 
         Most regular UNIX file systems only allow a file system entry to be
         looked up by its distinct path. Obviously, this does not apply to case
         insensitive file systems, whether case preserving or not. The most
         complex issue to deal with is file systems transparently reencoding the
         path, such as the non-standard Unicode normalisation required for HFS+
         and HFSX.
         '''
         # Constants copied from /usr/include/sys/fcntl.h
         F_GETPATH = 50
         O_SYMLINK = 0x200000
 
         try:
             fd = os.open(path, O_SYMLINK)
         except OSError, err:
             if err.errno == errno.ENOENT:
                 return path
             raise
 
         try:
             return fcntl.fcntl(fd, F_GETPATH, '\0' * 1024).rstrip('\0')
         finally:
             os.close(fd)
 else:
     # Fallback to the likely inadequate Python builtin function.
     realpath = os.path.realpath
 
 def shellquote(s):
     if os.sys.platform == 'OpenVMS':
         return '"%s"' % s
     else:
         return "'%s'" % s.replace("'", "'\\''")
 
 def quotecommand(cmd):
     return cmd
 
 def popen(command, mode='r'):
     return os.popen(command, mode)
 
 def testpid(pid):
     '''return False if pid dead, True if running or not sure'''
     if os.sys.platform == 'OpenVMS':
         return True
     try:
         os.kill(pid, 0)
         return True
     except OSError, inst:
         return inst.errno != errno.ESRCH
 
 def explain_exit(code):
     """return a 2-tuple (desc, code) describing a subprocess status
     (codes from kill are negative - not os.system/wait encoding)"""
     if code >= 0:
         return _("exited with status %d") % code, code
     return _("killed by signal %d") % -code, -code
 
 def isowner(st):
     """Return True if the stat object st is from the current user."""
     return st.st_uid == os.getuid()
 
 def find_exe(command):
     '''Find executable for command searching like which does.
     If command is a basename then PATH is searched for command.
     PATH isn't searched if command is an absolute or relative path.
     If command isn't found None is returned.'''
     if sys.platform == 'OpenVMS':
         return command
 
     def findexisting(executable):
         'Will return executable if existing file'
         if os.path.exists(executable):
             return executable
         return None
 
     if os.sep in command:
         return findexisting(command)
 
     for path in os.environ.get('PATH', '').split(os.pathsep):
         executable = findexisting(os.path.join(path, command))
         if executable is not None:
             return executable
     return None
 
 def set_signal_handler():
     pass
 
 def statfiles(files):
     'Stat each file in files and yield stat or None if file does not exist.'
     lstat = os.lstat
     for nf in files:
         try:
             st = lstat(nf)
         except OSError, err:
             if err.errno not in (errno.ENOENT, errno.ENOTDIR):
                 raise
             st = None
         yield st
 
 def getuser():
     '''return name of current user'''
     return getpass.getuser()
 
 def expand_glob(pats):
     '''On Windows, expand the implicit globs in a list of patterns'''
     return list(pats)
 
 def username(uid=None):
     """Return the name of the user with the given uid.
 
     If uid is None, return the name of the current user."""
 
     if uid is None:
         uid = os.getuid()
     try:
         return pwd.getpwuid(uid)[0]
     except KeyError:
         return str(uid)
 
 def groupname(gid=None):
     """Return the name of the group with the given gid.
 
     If gid is None, return the name of the current group."""
 
     if gid is None:
         gid = os.getgid()
     try:
         return grp.getgrgid(gid)[0]
     except KeyError:
         return str(gid)
 
 def groupmembers(name):
     """Return the list of members of the group with the given
     name, KeyError if the group does not exist.
     """
     return list(grp.getgrnam(name).gr_mem)
 
 def spawndetached(args):
     return os.spawnvp(os.P_NOWAIT | getattr(os, 'P_DETACH', 0),
                       args[0], args)
 
 def gethgcmd():
     return sys.argv[:1]
 
 def termwidth():
     try:
         import termios, array, fcntl
         for dev in (sys.stderr, sys.stdout, sys.stdin):
             try:
                 try:
                     fd = dev.fileno()
                 except AttributeError:
                     continue
                 if not os.isatty(fd):
                     continue
                 arri = fcntl.ioctl(fd, termios.TIOCGWINSZ, '\0' * 8)
                 return array.array('h', arri)[1]
             except ValueError:
                 pass
             except IOError, e:
                 if e[0] == errno.EINVAL:
                     pass
                 else:
                     raise
     except ImportError:
         pass
     return 80

mercurial/windows.py

@@ -1,377 +1,389 b''
 # windows.py - Windows utility function implementations for Mercurial
 #
 #  Copyright 2005-2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from i18n import _
 import osutil, error
 import errno, msvcrt, os, re, sys, random, subprocess
 
 nulldev = 'NUL:'
 umask = 002
 
 # wrap osutil.posixfile to provide friendlier exceptions
 def posixfile(name, mode='r', buffering=-1):
     try:
         return osutil.posixfile(name, mode, buffering)
     except WindowsError, err:
         raise IOError(err.errno, '%s: %s' % (name, err.strerror))
 posixfile.__doc__ = osutil.posixfile.__doc__
 
 class winstdout(object):
     '''stdout on windows misbehaves if sent through a pipe'''
 
     def __init__(self, fp):
         self.fp = fp
 
     def __getattr__(self, key):
         return getattr(self.fp, key)
 
     def close(self):
         try:
             self.fp.close()
         except: pass
 
     def write(self, s):
         try:
             # This is workaround for "Not enough space" error on
             # writing large size of data to console.
             limit = 16000
             l = len(s)
             start = 0
             self.softspace = 0
             while start < l:
                 end = start + limit
                 self.fp.write(s[start:end])
                 start = end
         except IOError, inst:
             if inst.errno != 0:
                 raise
             self.close()
             raise IOError(errno.EPIPE, 'Broken pipe')
 
     def flush(self):
         try:
             return self.fp.flush()
         except IOError, inst:
             if inst.errno != errno.EINVAL:
                 raise
             self.close()
             raise IOError(errno.EPIPE, 'Broken pipe')
 
 sys.stdout = winstdout(sys.stdout)
 
 def _is_win_9x():
     '''return true if run on windows 95, 98 or me.'''
     try:
         return sys.getwindowsversion()[3] == 1
     except AttributeError:
         return 'command' in os.environ.get('comspec', '')
 
 def openhardlinks():
     return not _is_win_9x() and "win32api" in globals()
 
 def system_rcpath():
     try:
         return system_rcpath_win32()
     except:
         return [r'c:\mercurial\mercurial.ini']
 
 def user_rcpath():
     '''return os-specific hgrc search path to the user dir'''
     try:
         path = user_rcpath_win32()
     except:
         home = os.path.expanduser('~')
         path = [os.path.join(home, 'mercurial.ini'),
                 os.path.join(home, '.hgrc')]
     userprofile = os.environ.get('USERPROFILE')
     if userprofile:
         path.append(os.path.join(userprofile, 'mercurial.ini'))
         path.append(os.path.join(userprofile, '.hgrc'))
     return path
 
 def parse_patch_output(output_line):
     """parses the output produced by patch and returns the filename"""
     pf = output_line[14:]
     if pf[0] == '`':
         pf = pf[1:-1] # Remove the quotes
     return pf
 
 def sshargs(sshcmd, host, user, port):
     '''Build argument list for ssh or Plink'''
     pflag = 'plink' in sshcmd.lower() and '-P' or '-p'
     args = user and ("%s@%s" % (user, host)) or host
     return port and ("%s %s %s" % (args, pflag, port)) or args
 
 def testpid(pid):
     '''return False if pid dead, True if running or not known'''
     return True
 
 def set_flags(f, l, x):
     pass
 
 def set_binary(fd):
     # When run without console, pipes may expose invalid
     # fileno(), usually set to -1.
     if hasattr(fd, 'fileno') and fd.fileno() >= 0:
         msvcrt.setmode(fd.fileno(), os.O_BINARY)
 
 def pconvert(path):
     return '/'.join(path.split(os.sep))
 
 def localpath(path):
     return path.replace('/', '\\')
 
 def normpath(path):
     return pconvert(os.path.normpath(path))
 
 def realpath(path):
     '''
     Returns the true, canonical file system path equivalent to the given
     path.
     '''
     # TODO: There may be a more clever way to do this that also handles other,
     # less common file systems.
     return os.path.normpath(os.path.normcase(os.path.realpath(path)))
 
 def samestat(s1, s2):
     return False
 
 # A sequence of backslashes is special iff it precedes a double quote:
 # - if there's an even number of backslashes, the double quote is not
 #   quoted (i.e. it ends the quoted region)
 # - if there's an odd number of backslashes, the double quote is quoted
 # - in both cases, every pair of backslashes is unquoted into a single
 #   backslash
 # (See http://msdn2.microsoft.com/en-us/library/a1y7w461.aspx )
 # So, to quote a string, we must surround it in double quotes, double
 # the number of backslashes that preceed double quotes and add another
 # backslash before every double quote (being careful with the double
 # quote we've appended to the end)
 _quotere = None
 def shellquote(s):
     global _quotere
     if _quotere is None:
         _quotere = re.compile(r'(\\*)("|\\$)')
     return '"%s"' % _quotere.sub(r'\1\1\\\2', s)
 
 def quotecommand(cmd):
     """Build a command string suitable for os.popen* calls."""
     if sys.version_info < (2, 7, 1):
         # Python versions since 2.7.1 do this extra quoting themselves
         return '"' + cmd + '"'
     return cmd
 
 def popen(command, mode='r'):
     # Work around "popen spawned process may not write to stdout
     # under windows"
     # http://bugs.python.org/issue1366
     command += " 2> %s" % nulldev
     return os.popen(quotecommand(command), mode)
 
 def explain_exit(code):
     return _("exited with status %d") % code, code
 
 # if you change this stub into a real check, please try to implement the
 # username and groupname functions above, too.
 def isowner(st):
     return True
 
 def find_exe(command):
     '''Find executable for command searching like cmd.exe does.
     If command is a basename then PATH is searched for command.
     PATH isn't searched if command is an absolute or relative path.
     An extension from PATHEXT is found and added if not present.
     If command isn't found None is returned.'''
     pathext = os.environ.get('PATHEXT', '.COM;.EXE;.BAT;.CMD')
     pathexts = [ext for ext in pathext.lower().split(os.pathsep)]
     if os.path.splitext(command)[1].lower() in pathexts:
         pathexts = ['']
 
     def findexisting(pathcommand):
         'Will append extension (if needed) and return existing file'
         for ext in pathexts:
             executable = pathcommand + ext
             if os.path.exists(executable):
                 return executable
         return None
 
     if os.sep in command:
         return findexisting(command)
 
     for path in os.environ.get('PATH', '').split(os.pathsep):
         executable = findexisting(os.path.join(path, command))
         if executable is not None:
             return executable
     return findexisting(os.path.expanduser(os.path.expandvars(command)))
 
 def set_signal_handler():
     try:
         set_signal_handler_win32()
     except NameError:
         pass
 
 def statfiles(files):
     '''Stat each file in files and yield stat or None if file does not exist.
     Cluster and cache stat per directory to minimize number of OS stat calls.'''
     ncase = os.path.normcase
     dircache = {} # dirname -> filename -> status | None if file does not exist
     for nf in files:
         nf  = ncase(nf)
         dir, base = os.path.split(nf)
         if not dir:
             dir = '.'
         cache = dircache.get(dir, None)
         if cache is None:
             try:
                 dmap = dict([(ncase(n), s)
                     for n, k, s in osutil.listdir(dir, True)])
             except OSError, err:
                 # handle directory not found in Python version prior to 2.5
                 # Python <= 2.4 returns native Windows code 3 in errno
                 # Python >= 2.5 returns ENOENT and adds winerror field
                 # EINVAL is raised if dir is not a directory.
                 if err.errno not in (3, errno.ENOENT, errno.EINVAL,
                                      errno.ENOTDIR):
                     raise
                 dmap = {}
             cache = dircache.setdefault(dir, dmap)
         yield cache.get(base, None)
 
 def getuser():
     '''return name of current user'''
     raise error.Abort(_('user name not available - set USERNAME '
                        'environment variable'))
 
 def username(uid=None):
     """Return the name of the user with the given uid.
 
     If uid is None, return the name of the current user."""
     return None
 
 def groupname(gid=None):
     """Return the name of the group with the given gid.
 
     If gid is None, return the name of the current group."""
     return None
 
 def _removedirs(name):
     """special version of os.removedirs that does not remove symlinked
     directories or junction points if they actually contain files"""
     if osutil.listdir(name):
         return
     os.rmdir(name)
     head, tail = os.path.split(name)
     if not tail:
         head, tail = os.path.split(head)
     while head and tail:
         try:
             if osutil.listdir(head):
                 return
             os.rmdir(head)
         except:
             break
         head, tail = os.path.split(head)
 
 def unlinkpath(f):
     """unlink and remove the directory if it is empty"""
     os.unlink(f)
     # try removing directories that might now be empty
     try:
         _removedirs(os.path.dirname(f))
     except OSError:
         pass
 
+def unlink(f):
+    '''try to implement POSIX' unlink semantics on Windows'''
+
+    # POSIX allows to unlink and rename open files. Windows has serious
+    # problems with doing that:
+    # - Calling os.unlink (or os.rename) on a file f fails if f or any
+    #   hardlinked copy of f has been opened with Python's open(). There is no
+    #   way such a file can be deleted or renamed on Windows (other than
+    #   scheduling the delete or rename for the next reboot).
+    # - Calling os.unlink on a file that has been opened with Mercurial's
+    #   posixfile (or comparable methods) will delay the actual deletion of
+    #   the file for as long as the file is held open. The filename is blocked
+    #   during that time and cannot be used for recreating a new file under
+    #   that same name ("zombie file"). Directories containing such zombie files
+    #   cannot be removed or moved.
+    # A file that has been opened with posixfile can be renamed, so we rename
+    # f to a random temporary name before calling os.unlink on it. This allows
+    # callers to recreate f immediately while having other readers do their
+    # implicit zombie filename blocking on a temporary name.
+
+    for tries in xrange(10):
+        temp = '%s-%08x' % (f, random.randint(0, 0xffffffff))
+        try:
+            os.rename(f, temp)  # raises OSError EEXIST if temp exists
+            break
+        except OSError, e:
+            if e.errno != errno.EEXIST:
+                raise
+    else:
+        raise IOError, (errno.EEXIST, "No usable temporary filename found")
+
+    try:
+        os.unlink(temp)
+    except:
+        # Some very rude AV-scanners on Windows may cause this unlink to fail.
+        # Not aborting here just leaks the temp file, whereas aborting at this
+        # point may leave serious inconsistencies. Ideally, we would notify
+        # the user in this case here.
+        pass
+
 def rename(src, dst):
     '''atomically rename file src to dst, replacing dst if it exists'''
     try:
         os.rename(src, dst)
     except OSError, e:
         if e.errno != errno.EEXIST:
             raise
-
-        # On windows, rename to existing file is not allowed, so we
-        # must delete destination first. But if a file is open, unlink
-        # schedules it for delete but does not delete it. Rename
-        # happens immediately even for open files, so we rename
-        # destination to a temporary name, then delete that. Then
-        # rename is safe to do.
-        # The temporary name is chosen at random to avoid the situation
-        # where a file is left lying around from a previous aborted run.
-
-        for tries in xrange(10):
-            temp = '%s-%08x' % (dst, random.randint(0, 0xffffffff))
-            try:
-                os.rename(dst, temp)  # raises OSError EEXIST if temp exists
-                break
-            except OSError, e:
-                if e.errno != errno.EEXIST:
-                    raise
-        else:
-            raise IOError, (errno.EEXIST, "No usable temporary filename found")
-
-        try:
-            os.unlink(temp)
-        except:
-            # Some rude AV-scanners on Windows may cause the unlink to
-            # fail. Not aborting here just leaks the temp file, whereas
-            # aborting at this point may leave serious inconsistencies.
-            # Ideally, we would notify the user here.
-            pass
+        unlink(dst)
         os.rename(src, dst)
 
 def spawndetached(args):
     # No standard library function really spawns a fully detached
     # process under win32 because they allocate pipes or other objects
     # to handle standard streams communications. Passing these objects
     # to the child process requires handle inheritance to be enabled
     # which makes really detached processes impossible.
     class STARTUPINFO:
         dwFlags = subprocess.STARTF_USESHOWWINDOW
         hStdInput = None
         hStdOutput = None
         hStdError = None
         wShowWindow = subprocess.SW_HIDE
 
     args = subprocess.list2cmdline(args)
     # Not running the command in shell mode makes python26 hang when
     # writing to hgweb output socket.
     comspec = os.environ.get("COMSPEC", "cmd.exe")
     args = comspec + " /c " + args
     hp, ht, pid, tid = subprocess.CreateProcess(
         None, args,
         # no special security
         None, None,
         # Do not inherit handles
         0,
         # DETACHED_PROCESS
         0x00000008,
         os.environ,
         os.getcwd(),
         STARTUPINFO())
     return pid
 
 def gethgcmd():
     return [sys.executable] + sys.argv[:1]
 
 def termwidth():
     # cmd.exe does not handle CR like a unix console, the CR is
     # counted in the line length. On 80 columns consoles, if 80
     # characters are written, the following CR won't apply on the
     # current line but on the new one. Keep room for it.
     return 79
 
 def groupmembers(name):
     # Don't support groups on Windows for now
     raise KeyError()
 
 try:
     # override functions with win32 versions if possible
     from win32 import *
 except ImportError:
     pass
 
 expandglobs = True