Adds a strip and strip-path option to bup save.

If the strip option is given bup uses all given filenames as base paths
and tries to stripe them from long to short.

If the strip-path option is given bup strip the given prefix from all
paths.

Signed-off-by: Zoran Zaric <zz@zoranzaric.de>

diff --git a/cmd/save-cmd.py b/cmd/save-cmd.py
index df51a6c74934c8aca99631e70122752e9986c815..d8c73cc711222fbf6195a59ed5389b949dd564fc 100755 (executable)
--- a/cmd/save-cmd.py
+++ b/cmd/save-cmd.py
@@ -16,6 +16,8 @@ v,verbose  increase log output (can be used more than once)
 q,quiet    don't show progress meter
 smaller=   only back up files smaller than n bytes
 bwlimit=   maximum bytes/sec to transmit to server
+strip      strips the path to every filename given
+strip-path= path-prefix to be stripped when saving
 """
 o = options.Options('bup save', optspec)
 (opt, flags, extra) = o.parse(sys.argv[1:])
@@ -36,6 +38,9 @@ if opt.date:
 else:
     date = time.time()
 
+if opt.strip and opt.strip_path:
+    o.fatal("--strip is incompatible with --strip-path")
+
 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")
@@ -195,7 +200,13 @@ for (transname,ent) in r.filter(extra, wantrecurse=wantrecurse_during):
         continue
 
     assert(dir.startswith('/'))
-    dirp = dir.split('/')
+    if opt.strip:
+        stripped_base_path = strip_base_path(dir, extra)
+        dirp = stripped_base_path.split('/')
+    elif opt.strip_path:
+        dirp = strip_path(opt.strip_path, dir).split('/')
+    else:
+        dirp = dir.split('/')
     while parts > dirp:
         _pop(force_tree = None)
     if dir != '/':

diff --git a/lib/bup/helpers.py b/lib/bup/helpers.py
index cb7854338ead99ad13358ad5ec41617dfb31e121..3c78c1890945b96046a9759061564e988b51805b 100644 (file)
--- a/lib/bup/helpers.py
+++ b/lib/bup/helpers.py
@@ -411,6 +411,39 @@ def parse_date_or_fatal(str, fatal):
     else:
         return date
 
+def strip_path(prefix, path):
+    """Strips a given prefix from a path.
+
+    First both paths are normalized.
+
+    Raises an Exception if no prefix is given.
+    """
+    if prefix == None:
+        raise Exception('no path given')
+
+    normalized_prefix = realpath(prefix)
+    print "normalized_prefix: " + normalized_prefix
+    normalized_path = realpath(path)
+    print "normalized_path: " + normalized_path
+    if normalized_path.startswith(normalized_prefix):
+        return normalized_path[len(normalized_prefix):]
+    else:
+        return path
+
+def strip_base_path(path, base_paths):
+    """Strips the base path from a given path.
+
+    Determines the base path for the given string and the strips it
+    using strip_path().
+    Iterates over all base_paths from long to short, to prevent that
+    a too short base_path is removed.
+    """
+    sorted_base_paths = sorted(base_paths, key=len, reverse=True)
+    for bp in sorted_base_paths:
+        if path.startswith(realpath(bp)):
+            return strip_path(bp, path)
+    return path
+
 
 # hashlib is only available in python 2.5 or higher, but the 'sha' module
 # produces a DeprecationWarning in python 2.6 or higher.  We want to support

diff --git a/lib/bup/t/thelpers.py b/lib/bup/t/thelpers.py
index 9f24962644fb25072c27879968f98e38ee62fba8..306d39b943118b3dc0698354fd00e518ac3b2a9b 100644 (file)
--- a/lib/bup/t/thelpers.py
+++ b/lib/bup/t/thelpers.py
@@ -10,3 +10,21 @@ def test_parse_num():
     WVPASSEQ(pn('2 gb'), 2*1024*1024*1024)
     WVPASSEQ(pn('1e+9 k'), 1000000000 * 1024)
     WVPASSEQ(pn('-3e-3mb'), int(-0.003 * 1024 * 1024))
+
+@wvtest
+def test_strip_path():
+    prefix = "/var/backup/daily.0/localhost"
+    empty_prefix = ""
+    non_matching_prefix = "/home"
+    path = "/var/backup/daily.0/localhost/etc/"
+
+    WVPASSEQ(strip_path(prefix, path), '/etc')
+    WVPASSEQ(strip_path(empty_prefix, path), path)
+    WVPASSEQ(strip_path(non_matching_prefix, path), path)
+    WVEXCEPT(Exception, strip_path, None, path)
+
+@wvtest
+def test_strip_base_path():
+    path = "/var/backup/daily.0/localhost/etc/"
+    base_paths = ["/var", "/var/backup", "/var/backup/daily.0/localhost"]
+    WVPASSEQ(strip_base_path(path, base_paths), '/etc')