mercurial/streamclone.py
changeset 2612 ffb895f16925
child 2621 5a5852a417b1
new file mode 100644
--- /dev/null
+++ b/mercurial/streamclone.py
@@ -0,0 +1,82 @@
+# streamclone.py - streaming clone server support for mercurial
+#
+# Copyright 2006 Vadim Gelfer <vadim.gelfer@gmail.com>
+#
+# This software may be used and distributed according to the terms
+# of the GNU General Public License, incorporated herein by reference.
+
+from demandload import demandload
+from i18n import gettext as _
+demandload(globals(), "os stat util")
+
+# if server supports streaming clone, it advertises "stream"
+# capability with value that is version+flags of repo it is serving.
+# client only streams if it can read that repo format.
+
+def walkrepo(root):
+    '''iterate over metadata files in repository.
+    walk in natural (sorted) order.
+    yields 2-tuples: name of .d or .i file, size of file.'''
+
+    strip_count = len(root) + len(os.sep)
+    def walk(path, recurse):
+        ents = os.listdir(path)
+        ents.sort()
+        for e in ents:
+            pe = os.path.join(path, e)
+            st = os.lstat(pe)
+            if stat.S_ISDIR(st.st_mode):
+                if recurse:
+                    for x in walk(pe, True):
+                        yield x
+            else:
+                if not stat.S_ISREG(st.st_mode) or len(e) < 2:
+                    continue
+                sfx = e[-2:]
+                if sfx in ('.d', '.i'):
+                    yield pe[strip_count:], st.st_size
+    # write file data first
+    for x in walk(os.path.join(root, 'data'), True):
+        yield x
+    # write manifest before changelog
+    meta = list(walk(root, False))
+    meta.sort(reverse=True)
+    for x in meta:
+        yield x
+
+# stream file format is simple.
+#
+# server writes out line that says how many files, how many total
+# bytes.  separator is ascii space, byte counts are strings.
+#
+# then for each file:
+#
+#   server writes out line that says file name, how many bytes in
+#   file.  separator is ascii nul, byte count is string.
+#
+#   server writes out raw file data.
+
+def stream_out(repo, fileobj):
+    '''stream out all metadata files in repository.
+    writes to file-like object, must support write() and optional flush().'''
+    # get consistent snapshot of repo. lock during scan so lock not
+    # needed while we stream, and commits can happen.
+    lock = repo.lock()
+    repo.ui.debug('scanning\n')
+    entries = []
+    total_bytes = 0
+    for name, size in walkrepo(repo.path):
+        entries.append((name, size))
+        total_bytes += size
+    lock.release()
+
+    repo.ui.debug('%d files, %d bytes to transfer\n' %
+                  (len(entries), total_bytes))
+    fileobj.write('%d %d\n' % (len(entries), total_bytes))
+    for name, size in entries:
+        repo.ui.debug('sending %s (%d bytes)\n' % (name, size))
+        fileobj.write('%s\0%d\n' % (name, size))
+        for chunk in util.filechunkiter(repo.opener(name), limit=size):
+            fileobj.write(chunk)
+    flush = getattr(fileobj, 'flush', None)
+    if flush: flush()