@@ -1,3 +1,8 @@

+2008-06-12  Michal Ludvig  <michal@logix.cz>

+

+	* s3cmd, s3cmd.1: Added GLOB (shell-style wildcard) exclude, renamed

+	  orig regexp-style --exclude to --rexclude

+

 2008-06-11  Michal Ludvig  <michal@logix.cz>

 	* S3/PkgInfo.py: Version 0.9.8-rc1

@@ -12,6 +12,7 @@ import os

 import re

 import errno

 import pwd, grp

+import glob

 from copy import copy

 from optparse import OptionParser, Option, OptionValueError, IndentedHelpFormatter

@@ -806,6 +807,15 @@ def run_configure(config_file):

 		error("Writing config file failed: %s: %s" % (config_file, e.strerror))

 		sys.exit(1)

+def process_exclude_from_file(exf, exclude_array):

+	exfi = open(exf, "rt")

+	for ex in exfi:

+		ex = ex.strip()

+		if re.match("^#", ex) or re.match("^\s*$", ex):

+			continue

+		debug("adding rule: %s" % ex)

+		exclude_array.append(ex)

+

 commands = {}

 commands_list = [

 	{"cmd":"mb", "label":"Make bucket", "param":"s3://BUCKET", "func":cmd_bucket_create, "argc":1},

@@ -877,8 +887,10 @@ if __name__ == '__main__':

 	optparser.add_option(      "--no-delete-removed", dest="delete_removed", action="store_false", help="Don't delete remote objects.")

 	optparser.add_option("-p", "--preserve", dest="preserve_attrs", action="store_true", help="Preserve filesystem attributes (mode, ownership, timestamps). Default for [sync] command.")

 	optparser.add_option(      "--no-preserve", dest="preserve_attrs", action="store_false", help="Don't store FS attributes")

-	optparser.add_option(      "--exclude", dest="exclude", action="append", metavar="REGEXP", help="Filenames and paths matching REGEXP will be excluded from sync")

-	optparser.add_option(      "--exclude-from", dest="exclude_from", action="append", metavar="FILE", help="Read --exclude REGEXPs from FILE")

+	optparser.add_option(      "--exclude", dest="exclude", action="append", metavar="GLOB", help="Filenames and paths matching GLOB will be excluded from sync")

+	optparser.add_option(      "--exclude-from", dest="exclude_from", action="append", metavar="FILE", help="Read --exclude GLOBs from FILE")

+	optparser.add_option(      "--rexclude", dest="rexclude", action="append", metavar="REGEXP", help="Filenames and paths matching REGEXP (regular expression) will be excluded from sync")

+	optparser.add_option(      "--rexclude-from", dest="rexclude_from", action="append", metavar="FILE", help="Read --rexclude REGEXPs from FILE")

 	optparser.add_option(      "--debug-syncmatch", dest="debug_syncmatch", action="store_true", help="Output detailed information about remote vs. local filelist matching and then exit")

 	optparser.add_option(      "--bucket-location", dest="bucket_location", help="Datacentre to create bucket in. Either EU or US (default)")

@@ -938,23 +950,35 @@ if __name__ == '__main__':

 			## Some Config() options are not settable from command line

 			pass

+	## Process GLOB (shell wildcard style) excludes

 	if options.exclude is None:

 		options.exclude = []

 	if options.exclude_from:

 		for exf in options.exclude_from:

 			debug("processing --exclude-from %s" % exf)

-			exfi = open(exf, "rt")

-			for ex in exfi:

-				ex = ex.strip()

-				if re.match("^#", ex) or re.match("^\s*$", ex):

-					continue

-				debug("adding rule: %s" % ex)

-				options.exclude.append(ex)

+			process_exclude_from_file(exf, options.exclude)

 	if options.exclude:

 		for ex in options.exclude:

 			debug("processing rule: %s" % ex)

+			exc = re.compile(glob.fnmatch.translate(ex))

+			cfg.exclude.append(exc)

+			if options.debug_syncmatch:

+				cfg.debug_exclude[exc] = ex

+

+	## Process REGEXP style excludes

+	if options.rexclude is None:

+		options.rexclude = []

+

+	if options.rexclude_from:

+		for exf in options.rexclude_from:

+			debug("processing --rexclude-from %s" % exf)

+			process_exclude_from_file(exf, options.rexclude)

+

+	if options.rexclude:

+		for ex in options.rexclude:

+			debug("processing rule: %s" % ex)

 			exc = re.compile(ex)

 			cfg.exclude.append(exc)

 			if options.debug_syncmatch:

@@ -86,11 +86,17 @@ Preserve filesystem attributes (mode, ownership, timestamps). Default for 'sync'

 \fB\-\-no\-preserve\fR

 Don't store filesystem attributes with uploaded files.

 .TP

-\fB\-\-exclude REGEXP\fR

-Exclude files matching REGEXP from \fIsync\fI. See SYNC COMMAND section for more information.

+\fB\-\-exclude GLOB\fR

+Exclude files matching GLOB (a.k.a. shell-style wildcard) from \fIsync\fI. See SYNC COMMAND section for more information.

 .TP

 \fB\-\-exclude\-from FILE\fR

-Same as \-\-exclude but reads REGEXPs from the given FILE instead of expecting them on the command line.

+Same as \-\-exclude but reads GLOBs from the given FILE instead of expecting them on the command line.

+.TP

+\fB\-\-rexclude REGEXP\fR

+Same as \-\-exclude but works with REGEXPs (Regular expressions).

+.TP

+\fB\-\-rexclude\-from FILE\fR

+Same as \-\-exclude\-from but works with REGEXPs.

 .TP

 \fB\-\-debug\-syncmatch\fR

 Display detailed information about matching file names against exclude\-rules as well as information about remote vs local filelists matching. S3cmd exits after performing the match and no actual transfer takes place.

@@ -177,21 +183,26 @@ will be \fB/\fRfile1.ext and \fB/\fRdir123/file2.bin, that is both with the lead

 slash regardless whether you specified s3://test-bucket/backup or 

 s3://test-bucket/backup/ (note the trailing slash) on the command line.

-Both \fB\-\-exclude\fR and \fB\-\-exclude\-from\fR options expect regular expressions, not 

-shell-style wildcards! Run s3cmd with \fB\-\-debug\-syncmatch\fR to get detailed information

+Both \fB\-\-exclude\fR and \fB\-\-exclude\-from\fR work with shell-style wildcards (a.k.a. GLOB).

+For a greater flexibility s3cmd provides Regular-expression versions of the two exclude options 

+named \fB\-\-rexclude\fR and \fB\-\-rexclude\-from\fR. 

+

+Run s3cmd with \fB\-\-debug\-syncmatch\fR to get detailed information

 about matching file names against exclude rules.

-For example to exclude all files with ".bin" extension use:

+For example to exclude all files with ".bin" extension with a REGEXP use:

+.PP

+	\-\-rexclude '\.bin$'

 .PP

-	\-\-exclude '\.bin$'

+to exclude all hidden files and subdirectories (i.e. those whose name begins with dot ".") use GLOB:

 .PP

-to exclude all hidden files and subdirectories (i.e. those whose name begins with dot ".") use:

+	\-\-exclude '/.*'

 .PP

-	\-\-exclude '/\.'

+on the other hand to exclude only hidden files but not hidden subdirectories use REGEXP:

 .PP

-on the other hand to exclude only hidden files but not hidden subdirectories use:

+	\-\-rexclude '/\.[^/]*$'

 .PP

-	\-\-exclude '/\.[^/]*$'

+etc...

 .SH AUTHOR

 Written by Michal Ludvig <michal@logix.cz>