options: remove unused 'exe' parameter

[bup.git] / cmd / split-cmd.py

diff --git a/cmd/split-cmd.py b/cmd/split-cmd.py
index 26340bfe9a06c0e03d69169d65a6ffd9c7d623bd..1673b2b1dcee765c976649e4a4933be58b4894da 100755 (executable)
--- a/cmd/split-cmd.py
+++ b/cmd/split-cmd.py
@@ -12,9 +12,12 @@ b,blobs    output a series of blob ids
 t,tree     output a tree id
 c,commit   output a commit id
 n,name=    name of backup set to update (if any)
-N,noop     don't actually save the data anywhere
+d,date=    date for the commit (seconds since the epoch)
 q,quiet    don't print progress messages
 v,verbose  increase log output (can be used more than once)
+git-ids    read a list of git object ids from stdin and split their contents
+keep-boundaries  don't let one chunk span two input files
+noop       don't actually save the data anywhere
 copy       just copy input to output, hashsplitting along the way
 bench      print benchmark timings to stderr
 max-pack-size=  maximum bytes in a single pack
@@ -22,7 +25,7 @@ max-pack-objects=  maximum number of objects in a single pack
 fanout=    maximum number of blobs in a single tree
 bwlimit=   maximum bytes/sec to transmit to server
 """
-o = options.Options('bup split', optspec)
+o = options.Options(optspec)
 (opt, flags, extra) = o.parse(sys.argv[1:])
 
 handle_ctrl_c()
@@ -33,6 +36,8 @@ if not (opt.blobs or opt.tree or opt.commit or opt.name or
 if (opt.noop or opt.copy) and (opt.blobs or opt.tree or 
                                opt.commit or opt.name):
     o.fatal('-N and --copy are incompatible with -b, -t, -c, -n')
+if extra and opt.git_ids:
+    o.fatal("don't provide filenames when using --git-ids")
 
 if opt.verbose >= 2:
     git.verbose = opt.verbose - 1
@@ -47,12 +52,34 @@ if opt.blobs:
     hashsplit.fanout = 0
 if opt.bwlimit:
     client.bwlimit = parse_num(opt.bwlimit)
+if opt.date:
+    date = parse_date_or_fatal(opt.date, o.fatal)
+else:
+    date = time.time()
+
+
+last_prog = total_bytes = 0
+def prog(filenum, nbytes):
+    global last_prog, total_bytes
+    total_bytes += nbytes
+    now = time.time()
+    if now - last_prog < 0.2:
+        return
+    if filenum > 0:
+        progress('Splitting: file #%d, %d kbytes\r'
+                 % (filenum+1, total_bytes/1024))
+    else:
+        progress('Splitting: %d kbytes\r' % (total_bytes/1024))
+    last_prog = now
+
 
 is_reverse = os.environ.get('BUP_SERVER_REVERSE')
 if is_reverse and opt.remote:
     o.fatal("don't use -r in reverse mode; it's automatic")
 start_time = time.time()
 
+if opt.name and opt.name.startswith('.'):
+    o.fatal("'%s' is not a valid branch name." % opt.name)
 refname = opt.name and 'refs/heads/%s' % opt.name or None
 if opt.noop or opt.copy:
     cli = pack_writer = oldref = None
@@ -65,13 +92,51 @@ else:
     oldref = refname and git.read_ref(refname) or None
     pack_writer = git.PackWriter()
 
-files = extra and (open(fn) for fn in extra) or [sys.stdin]
+if opt.git_ids:
+    # the input is actually a series of git object ids that we should retrieve
+    # and split.
+    #
+    # This is a bit messy, but basically it converts from a series of
+    # CatPipe.get() iterators into a series of file-type objects.
+    # It would be less ugly if either CatPipe.get() returned a file-like object
+    # (not very efficient), or split_to_shalist() expected an iterator instead
+    # of a file.
+    cp = git.CatPipe()
+    class IterToFile:
+        def __init__(self, it):
+            self.it = iter(it)
+        def read(self, size):
+            v = next(self.it)
+            return v or ''
+    def read_ids():
+        while 1:
+            line = sys.stdin.readline()
+            if not line:
+                break
+            if line:
+                line = line.strip()
+            try:
+                it = cp.get(line.strip())
+                next(it)  # skip the file type
+            except KeyError, e:
+                add_error('error: %s' % e)
+                continue
+            yield IterToFile(it)
+    files = read_ids()
+else:
+    # the input either comes from a series of files or from stdin.
+    files = extra and (open(fn) for fn in extra) or [sys.stdin]
+
 if pack_writer:
-    shalist = hashsplit.split_to_shalist(pack_writer, files)
+    shalist = hashsplit.split_to_shalist(pack_writer, files,
+                                         keep_boundaries=opt.keep_boundaries,
+                                         progress=prog)
     tree = pack_writer.new_tree(shalist)
 else:
     last = 0
-    for (blob, bits) in hashsplit.hashsplit_iter(files):
+    for (blob, bits) in hashsplit.hashsplit_iter(files,
+                                    keep_boundaries=opt.keep_boundaries,
+                                    progress=prog):
         hashsplit.total_split += len(blob)
         if opt.copy:
             sys.stdout.write(str(blob))
@@ -91,7 +156,7 @@ if opt.tree:
 if opt.commit or opt.name:
     msg = 'bup split\n\nGenerated by command:\n%r' % sys.argv
     ref = opt.name and ('refs/heads/%s' % opt.name) or None
-    commit = pack_writer.new_commit(oldref, tree, msg)
+    commit = pack_writer.new_commit(oldref, tree, date, msg)
     if opt.commit:
         print commit.encode('hex')
 
@@ -112,3 +177,7 @@ size = hashsplit.total_split
 if opt.bench:
     log('\nbup: %.2fkbytes in %.2f secs = %.2f kbytes/sec\n'
         % (size/1024., secs, size/1024./secs))
+
+if saved_errors:
+    log('WARNING: %d errors encountered while saving.\n' % len(saved_errors))
+    sys.exit(1)