sapling/mercurial
Stephen Darnell b2e16a8dbf Add support for cloning with hardlinks on windows.
In order to use hardlinks, the win32file module is needed, and this is
present in ActivePython.  If it isn't present, or hardlinks are not supported
on the underlying filesystem, a regular copy is used.

When using hardlinks the biggest benefit is probably the saving in space,
but cloning can be much quicker.  For example cloning the Xen tree
(non trivial) without an update goes from about 95s to 15s.

Unix-like platforms should be unaffected, although should be more tolerant on
filesystems that don't support hard links.

(tweaked by mpm to deal with new copyfiles function)

--- hg.orig/mercurial/commands.py	2005-09-13 19:32:53.000000000 -0500
+++ hg/mercurial/commands.py	2005-09-14 12:11:34.000000000 -0500
@@ -620,10 +620,6 @@ def clone(ui, source, dest=None, **opts)

     if other.dev() != -1:
         abspath = os.path.abspath(source)
-        copyfile = (os.stat(dest).st_dev == other.dev()
-                    and getattr(os, 'link', None) or shutil.copy2)
-        if copyfile is not shutil.copy2:
-            ui.note("cloning by hardlink\n")

         # we use a lock here because if we race with commit, we can
         # end up with extra data in the cloned revlogs that's not
@@ -638,7 +634,7 @@ def clone(ui, source, dest=None, **opts)
         for f in files.split():
             src = os.path.join(source, ".hg", f)
             dst = os.path.join(dest, ".hg", f)
-            util.copyfiles(src, dst, copyfile)
+            util.copyfiles(src, dst)

         repo = hg.repository(ui, dest)

Index: hg/mercurial/util.py
===================================================================
--- hg.orig/mercurial/util.py	2005-09-08 00:15:25.000000000 -0500
+++ hg/mercurial/util.py	2005-09-14 12:16:49.000000000 -0500
@@ -12,7 +12,7 @@ platform-specific details from the core.

 import os, errno
 from demandload import *
-demandload(globals(), "re cStringIO")
+demandload(globals(), "re cStringIO shutil")

 def binary(s):
     """return true if a string is binary data using diff's heuristic"""
@@ -217,17 +217,28 @@ def rename(src, dst):
         os.unlink(dst)
         os.rename(src, dst)

-def copyfiles(src, dst, copyfile):
-    """Copy a directory tree, files are copied using 'copyfile'."""
+def copyfiles(src, dst, hardlink=None):
+    """Copy a directory tree using hardlinks if possible"""
+
+    if hardlink is None:
+        hardlink = (os.stat(src).st_dev ==
+                    os.stat(os.path.dirname(dst)).st_dev)

     if os.path.isdir(src):
         os.mkdir(dst)
         for name in os.listdir(src):
             srcname = os.path.join(src, name)
             dstname = os.path.join(dst, name)
-            copyfiles(srcname, dstname, copyfile)
+            copyfiles(srcname, dstname, hardlink)
     else:
-        copyfile(src, dst)
+        if hardlink:
+            try:
+                os_link(src, dst)
+            except:
+                hardlink = False
+                shutil.copy2(src, dst)
+        else:
+            shutil.copy2(src, dst)

 def opener(base):
     """
@@ -244,13 +255,13 @@ def opener(base):

         if mode[0] != "r":
             try:
-                s = os.stat(f)
+                nlink = nlinks(f)
             except OSError:
                 d = os.path.dirname(f)
                 if not os.path.isdir(d):
                     os.makedirs(d)
             else:
-                if s.st_nlink > 1:
+                if nlink > 1:
                     file(f + ".tmp", "wb").write(file(f, "rb").read())
                     rename(f+".tmp", f)

@@ -266,10 +277,41 @@ def _makelock_file(info, pathname):
 def _readlock_file(pathname):
     return file(pathname).read()

+def nlinks(pathname):
+    """Return number of hardlinks for the given file."""
+    return os.stat(pathname).st_nlink
+
+if hasattr(os, 'link'):
+    os_link = os.link
+else:
+    def os_link(src, dst):
+        raise OSError(0, "Hardlinks not supported")
+
 # Platform specific variants
 if os.name == 'nt':
     nulldev = 'NUL:'

+    try: # ActivePython can create hard links using win32file module
+        import win32file
+
+        def os_link(src, dst): # NB will only succeed on NTFS
+            win32file.CreateHardLink(dst, src)
+
+        def nlinks(pathname):
+            """Return number of hardlinks for the given file."""
+            try:
+                fh = win32file.CreateFile(pathname,
+                    win32file.GENERIC_READ, win32file.FILE_SHARE_READ,
+                    None, win32file.OPEN_EXISTING, 0, None)
+                res = win32file.GetFileInformationByHandle(fh)
+                fh.Close()
+                return res[7]
+            except:
+                return os.stat(pathname).st_nlink
+
+    except ImportError:
+        pass
+
     def is_exec(f, last):
         return last
2005-09-14 12:22:20 -05:00
..
__init__.py Add back links from file revisions to changeset revisions 2005-05-03 13:16:10 -08:00
bdiff.c Fix possible unitialized variable warnings 2005-08-20 01:29:04 -07:00
byterange.py Make consistent use of str.startswith() in conditionals. 2005-07-10 16:14:56 -08:00
changelog.py Commit date validation: more stringent checks, more useful error messages. 2005-09-04 14:47:02 -07:00
commands.py Add support for cloning with hardlinks on windows. 2005-09-14 12:22:20 -05:00
demandload.py implement demand loading hack 2005-06-05 10:48:39 -08:00
dirstate.py dirstate: two more stat -> lstat changes 2005-09-09 12:17:51 -07:00
fancyopts.py Map long option names containing dashes to ones containing underscores. 2005-08-24 22:25:55 -07:00
filelog.py fix some rename/copy bugs 2005-08-27 22:04:17 -07:00
hg.py localrepo: minor opener usage restructuring 2005-08-27 16:34:54 -07:00
hgweb.py hgweb: fix scope for RepoError 2005-09-08 10:49:33 -07:00
httprangereader.py Move httprangereader into its own file 2005-06-15 19:58:48 -08:00
httprepo.py Break apart hg.py 2005-08-27 14:21:25 -07:00
localrepo.py Fix bug with co -C across branches, update tests 2005-09-13 18:38:27 -05:00
lock.py pep-0008 cleanup 2005-08-26 13:06:58 +02:00
manifest.py manifest: convert sys.stderr bits to AssertionError 2005-08-27 15:13:52 -07:00
mdiff.py Add automatic binary file detection to diff and export 2005-08-23 19:58:46 -07:00
mpatch.c [PATCH] use <arpa/inet.h> instead of <netinet/in.h> for ntohl/htonl 2005-07-03 12:26:45 -08:00
node.py Move hash function back to revlog from node 2005-08-27 14:43:20 -07:00
remoterepo.py Break apart hg.py 2005-08-27 14:21:25 -07:00
repo.py Break apart hg.py 2005-08-27 14:21:25 -07:00
revlog.py Revert some exception type changes in revlog 2005-09-13 14:16:15 -05:00
sshrepo.py Fix sshrepo imports 2005-08-27 16:40:24 -07:00
statichttprepo.py Separate out old-http support 2005-08-27 16:28:53 -07:00
transaction.py [PATCH] raise exceptions with Exception subclasses 2005-08-26 19:08:25 -07:00
ui.py Merge with TAH. 2005-08-29 10:31:41 -07:00
util.py Add support for cloning with hardlinks on windows. 2005-09-14 12:22:20 -05:00
version.py [PATCH] /dev/null for other OS 2005-06-24 22:58:14 -08:00