Adding the --usermap/--groupmap/--chown options.

NEWS

@@ -26,6 +26,9 @@ Changes since 3.0.4:
       protocol 31), and 3) to follow the file-count, created-count, and
       deleted-count with a break-out list of each count by type.
 
+    - Added the --usermap/--groupmap/--chown options for manipulating file
+      ownership during the copy.
+
     - Added the "%C" escape to the log-output handling, which will output the
       MD5 checksum of any transferred file, or all files if --checksum was
       specified (when protocol 30 or above is in effect).

flist.c

@@ -72,6 +72,7 @@ extern int sender_keeps_checksum;
 extern int unsort_ndx;
 extern struct stats stats;
 extern char *filesfrom_host;
+extern char *usermap, *groupmap;
 
 extern char curr_dir[MAXPATHLEN];
 
@@ -802,7 +803,7 @@ static struct file_struct *recv_file_entry(struct file_list *flist,
 			uid = (uid_t)read_varint(f);
 			if (xflags & XMIT_USER_NAME_FOLLOWS)
 				uid = recv_user_name(f, uid);
-			else if (inc_recurse && am_root && !numeric_ids)
+			else if (inc_recurse && am_root && (!numeric_ids || usermap))
 				uid = match_uid(uid);
 		}
 	}
@@ -814,7 +815,7 @@ static struct file_struct *recv_file_entry(struct file_list *flist,
 			gid_flags = 0;
 			if (xflags & XMIT_GROUP_NAME_FOLLOWS)
 				gid = recv_group_name(f, gid, &gid_flags);
-			else if (inc_recurse && (!am_root || !numeric_ids))
+			else if (inc_recurse && (!am_root || !numeric_ids || groupmap))
 				gid = match_gid(gid, &gid_flags);
 		}
 	}
@@ -2303,6 +2304,10 @@ struct file_list *recv_file_list(int f)
 		else if (inc_recurse && INFO_GTE(FLIST, 1) && !am_server)
 			rprintf(FCLIENT, "receiving incremental file list\n");
 		rprintf(FLOG, "receiving file list\n");
+		if (usermap)
+			parse_name_map(usermap, True);
+		if (groupmap)
+			parse_name_map(groupmap, False);
 	}
 
 	start_read = stats.total_read;

options.c

@@ -167,6 +167,8 @@ char *rsync_path = RSYNC_PATH;
 char *backup_dir = NULL;
 char backup_dir_buf[MAXPATHLEN];
 char *sockopts = NULL;
+char *usermap = NULL;
+char *groupmap = NULL;
 int rsync_port = 0;
 int compare_dest = 0;
 int copy_dest = 0;
@@ -296,6 +298,7 @@ static int refused_delete, refused_archive_part, refused_compress;
 static int refused_partial, refused_progress, refused_delete_before;
 static int refused_delete_during;
 static int refused_inplace, refused_no_iconv;
+static BOOL usermap_via_chown, groupmap_via_chown;
 static char *max_size_arg, *min_size_arg;
 static char tmp_partialdir[] = ".~tmp~";
 
@@ -725,6 +728,9 @@ void usage(enum logcode F)
   rprintf(F,"     --delay-updates         put all updated files into place at transfer's end\n");
   rprintf(F," -m, --prune-empty-dirs      prune empty directory chains from the file-list\n");
   rprintf(F,"     --numeric-ids           don't map uid/gid values by user/group name\n");
+  rprintf(F,"     --usermap=STRING        custom username mapping\n");
+  rprintf(F,"     --groupmap=STRING       custom groupname mapping\n");
+  rprintf(F,"     --chown=USER:GROUP      simple username/groupname mapping\n");
   rprintf(F,"     --timeout=SECONDS       set I/O timeout in seconds\n");
   rprintf(F,"     --contimeout=SECONDS    set daemon connection timeout in seconds\n");
   rprintf(F," -I, --ignore-times          don't skip files that match in size and mod-time\n");
@@ -789,6 +795,7 @@ enum {OPT_VERSION = 1000, OPT_DAEMON, OPT_SENDER, OPT_EXCLUDE, OPT_EXCLUDE_FROM,
       OPT_INCLUDE, OPT_INCLUDE_FROM, OPT_MODIFY_WINDOW, OPT_MIN_SIZE, OPT_CHMOD,
       OPT_READ_BATCH, OPT_WRITE_BATCH, OPT_ONLY_WRITE_BATCH, OPT_MAX_SIZE,
       OPT_NO_D, OPT_APPEND, OPT_NO_ICONV, OPT_INFO, OPT_DEBUG,
+      OPT_USERMAP, OPT_GROUPMAP, OPT_CHOWN,
       OPT_SERVER, OPT_REFUSED_BASE = 9000};
 
 static struct poptOption long_options[] = {
@@ -969,6 +976,9 @@ static struct poptOption long_options[] = {
   {"no-s",             0,  POPT_ARG_VAL,    &protect_args, 0, 0, 0},
   {"numeric-ids",      0,  POPT_ARG_VAL,    &numeric_ids, 1, 0, 0 },
   {"no-numeric-ids",   0,  POPT_ARG_VAL,    &numeric_ids, 0, 0, 0 },
+  {"usermap",          0,  POPT_ARG_STRING, 0, OPT_USERMAP, 0, 0 },
+  {"groupmap",         0,  POPT_ARG_STRING, 0, OPT_GROUPMAP, 0, 0 },
+  {"chown",            0,  POPT_ARG_STRING, 0, OPT_CHOWN, 0, 0 },
   {"timeout",          0,  POPT_ARG_INT,    &io_timeout, 0, 0, 0 },
   {"no-timeout",       0,  POPT_ARG_VAL,    &io_timeout, 0, 0, 0 },
   {"contimeout",       0,  POPT_ARG_INT,    &connect_timeout, 0, 0, 0 },
@@ -1625,6 +1635,76 @@ int parse_arguments(int *argc_p, const char ***argv_p)
 			parse_output_words(debug_words, debug_levels, arg, USER_PRIORITY);
 			break;
 
+		case OPT_USERMAP:
+			if (usermap) {
+				if (usermap_via_chown) {
+					snprintf(err_buf, sizeof err_buf,
+					    "--usermap conflicts with prior --chown.\n");
+					return 0;
+				}
+				snprintf(err_buf, sizeof err_buf,
+				    "You can only specify --usermap once.\n");
+				return 0;
+			}
+			usermap = (char *)poptGetOptArg(pc);
+			usermap_via_chown = False;
+			break;
+
+		case OPT_GROUPMAP:
+			if (groupmap) {
+				if (groupmap_via_chown) {
+					snprintf(err_buf, sizeof err_buf,
+					    "--groupmap conflicts with prior --chown.\n");
+					return 0;
+				}
+				snprintf(err_buf, sizeof err_buf,
+				    "You can only specify --groupmap once.\n");
+				return 0;
+			}
+			groupmap = (char *)poptGetOptArg(pc);
+			groupmap_via_chown = False;
+			break;
+
+		case OPT_CHOWN: {
+			const char *chown = poptGetOptArg(pc);
+			int len;
+			if ((arg = strchr(chown, ':')) != NULL)
+				len = arg++ - chown;
+			else
+				len = strlen(chown);
+			if (len) {
+				if (usermap) {
+					if (!usermap_via_chown) {
+						snprintf(err_buf, sizeof err_buf,
+						    "--chown conflicts with prior --usermap.\n");
+						return 0;
+					}
+					snprintf(err_buf, sizeof err_buf,
+					    "You can only specify a user-affecting --chown once.\n");
+					return 0;
+				}
+				if (asprintf(&usermap, "*:%.*s", len, chown) < 0)
+					out_of_memory("parse_arguments");
+				usermap_via_chown = True;
+			}
+			if (arg && *arg) {
+				if (groupmap) {
+					if (!groupmap_via_chown) {
+						snprintf(err_buf, sizeof err_buf,
+						    "--chown conflicts with prior --groupmap.\n");
+						return 0;
+					}
+					snprintf(err_buf, sizeof err_buf,
+					    "You can only specify a group-affecting --chown once.\n");
+					return 0;
+				}
+				if (asprintf(&groupmap, "*:%s", arg) < 0)
+					out_of_memory("parse_arguments");
+				groupmap_via_chown = True;
+			}
+			break;
+		}
+
 		case OPT_HELP:
 			usage(FINFO);
 			exit_cleanup(0);
@@ -2435,6 +2515,18 @@ void server_options(char **args, int *argc_p)
 		args[ac++] = "--use-qsort";
 
 	if (am_sender) {
+		if (usermap) {
+			if (asprintf(&arg, "--usermap=%s", usermap) < 0)
+				goto oom;
+			args[ac++] = arg;
+		}
+
+		if (groupmap) {
+			if (asprintf(&arg, "--groupmap=%s", groupmap) < 0)
+				goto oom;
+			args[ac++] = arg;
+		}
+
 		if (ignore_existing)
 			args[ac++] = "--ignore-existing";
 

rsync.yo

@@ -385,6 +385,9 @@ to the detailed description below for a complete description.  verb(
      --delay-updates         put all updated files into place at end
  -m, --prune-empty-dirs      prune empty directory chains from file-list
      --numeric-ids           don't map uid/gid values by user/group name
+     --usermap=STRING        custom username mapping
+     --groupmap=STRING       custom groupname mapping
+     --chown=USER:GROUP      simple username/groupname mapping
      --timeout=SECONDS       set I/O timeout in seconds
      --contimeout=SECONDS    set daemon connection timeout in seconds
  -I, --ignore-times          don't skip files that match size and time
@@ -1716,6 +1719,57 @@ from the source system is used instead.  See also the comments on the
 the chroot setting affects rsync's ability to look up the names of the
 users and groups and what you can do about it.
 
+dit(bf(--usermap=STRING, --groupmap=STRING)) These options allow you to
+specify users and groups that should be mapped to other values by the
+receiving side.  The bf(STRING) is one or more bf(FROM):bf(TO) pairs of
+values separated by commas.  Any matching bf(FROM) value from the sender is
+replaced with a bf(TO) value from the receiver.  You may specify usernames
+or user IDs for the bf(FROM) and bf(TO) values, and the bf(FROM) value may
+also be a wild-card string, which will be matched against the sender's
+names (wild-cards do NOT match against ID numbers, though see below for
+why a '*' matches everything).  You may instead specify a range of ID
+numbers via an inclusive range: LOW-HIGH.  For example:
+
+verb(  --usermap=0-99:nobody,wayne:admin,*:normal --groupmap=usr:1,1:usr)
+
+The first match in the list is the one that is used.  You should specify
+all your user mappings using a single bf(--usermap) option, and/or all
+your group mappings using a single bf(--groupmap) option.
+
+Note that the sender's name for the 0 user and group are not transmitted
+to the receiver, so you should either match these values using a 0, or use
+the names in effect on the receiving side (typically "root").  All other
+bf(FROM) names match those in use on the sending side.  All bf(TO) names
+match those in use on the receiving side.
+
+Any IDs that do not have a name on the sending side are treated as having an
+empty name for the purpose of matching.  This allows them to be matched via
+a "*" or using an empty name.  For instance:
+
+verb(  --usermap=:nobody --groupmap=*:nobody)
+
+When the bf(--numeric-ids) option is used, the sender does not send any
+names, so all the IDs are treated as having an empty name.  This means that
+you will need to specify numeric bf(FROM) values if you want to map these
+nameless IDs to different values.
+
+For the bf(--usermap) option to have any effect, the bf(-o) (bf(--owner))
+option must be used (or implied), and the receiver will need to be running
+as a super-user (see also the bf(--fake-super) option).  For the bf(--groupmap)
+option to have any effect, the bf(-g) (bf(--groups)) option must be used
+(or implied), and the receiver will need to have permissions to set that
+group.
+
+dit(bf(--chown=USER:GROUP)) This option forces all files to be owned by USER
+with group GROUP.  This is a simpler interface than using bf(--usermap) and
+bf(--groupmap) directly, but it is implemented using those options internally,
+so you cannot mix them.  If either the USER or GROUP is empty, no mapping for
+the omitted user/group will occur.  If GROUP is empty, the trailing colon may
+be omitted, but if USER is empty, a leading colon must be supplied.
+
+If you specify "--chown=foo:bar, this is exactly the same as specifying
+"--usermap=*:foo --groupmap=*:bar", only easier.
+
 dit(bf(--timeout=TIMEOUT)) This option allows you to set a maximum I/O
 timeout in seconds. If no data is transferred for the specified time
 then rsync will exit. The default is 0, which means no timeout.

support/mapfrom

@@ -0,0 +1,5 @@
+#!/usr/bin/perl
+while (<>) {
+    push @_, "$2:$1" if /^(\w+):[^:]+:(\d+)/;
+}
+print join(',', @_), "\n";

support/mapto

@@ -0,0 +1,5 @@
+#!/usr/bin/perl
+while (<>) {
+    push @_, "$1:$2" if /^(\w+):[^:]+:(\d+)/;
+}
+print join(',', @_), "\n";

uidlist.c

@@ -24,6 +24,8 @@
  * are special. */
 
 #include "rsync.h"
+#include "ifuncs.h"
+#include "itypes.h"
 #include "io.h"
 
 extern int am_root;
@@ -31,6 +33,8 @@ extern int preserve_uid;
 extern int preserve_gid;
 extern int preserve_acls;
 extern int numeric_ids;
+extern char *usermap;
+extern char *groupmap;
 
 #ifdef HAVE_GETGROUPS
 # ifndef GETGROUPS_T
@@ -40,6 +44,9 @@ extern int numeric_ids;
 
 #define GID_NONE ((gid_t)-1)
 
+#define NFLAGS_WILD_NAME_MATCH (1<<0)
+#define NFLAGS_NAME_MATCH (1<<1)
+
 struct idlist {
 	struct idlist *next;
 	const char *name;
@@ -47,8 +54,8 @@ struct idlist {
 	uint16 flags;
 };
 
-static struct idlist *uidlist;
-static struct idlist *gidlist;
+static struct idlist *uidlist, *uidmap;
+static struct idlist *gidlist, *gidmap;
 
 static struct idlist *add_to_list(struct idlist **root, id_t id, const char *name,
 				  id_t id2, uint16 flags)
@@ -83,22 +90,6 @@ static const char *gid_to_name(gid_t gid)
 	return NULL;
 }
 
-static uid_t map_uid(uid_t id, const char *name)
-{
-	uid_t uid;
-	if (id != 0 && name_to_uid(name, &uid))
-		return uid;
-	return id;
-}
-
-static gid_t map_gid(gid_t id, const char *name)
-{
-	gid_t gid;
-	if (id != 0 && name_to_gid(name, &gid))
-		return gid;
-	return id;
-}
-
 static int is_in_group(gid_t gid)
 {
 #ifdef HAVE_GETGROUPS
@@ -158,34 +149,53 @@ static int is_in_group(gid_t gid)
 #endif
 }
 
-/* Add a uid to the list of uids.  Only called on receiving side. */
-static struct idlist *recv_add_uid(uid_t id, const char *name)
+/* Add a uid/gid to its list of ids.  Only called on receiving side. */
+static struct idlist *recv_add_id(struct idlist **idlist_ptr, struct idlist *idmap,
+				  id_t id, const char *name)
 {
-	uid_t id2 = name ? map_uid(id, name) : id;
 	struct idlist *node;
+	int flag;
+	id_t id2;
 
-	node = add_to_list(&uidlist, id, name, id2, 0);
+	if (!name)
+		name = "";
 
-	if (DEBUG_GTE(OWN, 2)) {
-		rprintf(FINFO, "uid %u(%s) maps to %u\n",
-			(unsigned)id, name ? name : "", (unsigned)id2);
+	for (node = idmap; node; node = node->next) {
+		if (node->flags & NFLAGS_WILD_NAME_MATCH) {
+			if (!wildmatch(node->name, name))
+				continue;
+		} else if (node->flags & NFLAGS_NAME_MATCH) {
+			if (strcmp(node->name, name) != 0)
+				continue;
+		} else if (node->name) {
+			if (id < node->id || id > (unsigned long)node->name)
+				continue;
+		} else {
+			if (node->id != id)
+				continue;
+		}
+		break;
 	}
+	if (node)
+		id2 = node->id2;
+	else if (*name && id) {
+		if (idmap == uidmap) {
+			uid_t uid;
+			id2 = name_to_uid(name, &uid) ? uid : id;
+		} else {
+			gid_t gid;
+			id2 = name_to_gid(name, &gid) ? gid : id;
+		}
+	} else
+		id2 = id;
 
-	return node;
-}
-
-/* Add a gid to the list of gids.  Only called on receiving side. */
-static struct idlist *recv_add_gid(gid_t id, const char *name)
-{
-	gid_t id2 = name ? map_gid(id, name) : id;
-	struct idlist *node;
-
-	node = add_to_list(&gidlist, id, name, id2,
-		!am_root && !is_in_group(id2) ? FLAG_SKIP_GROUP : 0);
+	flag = idmap == gidmap && !am_root && !is_in_group(id2) ? FLAG_SKIP_GROUP : 0;
+	node = add_to_list(idlist_ptr, id, *name ? name : NULL, id2, flag);
 
 	if (DEBUG_GTE(OWN, 2)) {
-		rprintf(FINFO, "gid %u(%s) maps to %u\n",
-			(unsigned)id, name ? name : "", (unsigned)id2);
+		rprintf(FINFO, "%sid %u(%s) maps to %u\n",
+			idmap == uidmap ? "u" : "g",
+			(unsigned)id, name, (unsigned)id2);
 	}
 
 	return node;
@@ -194,12 +204,9 @@ static struct idlist *recv_add_gid(gid_t id, const char *name)
 /* this function is a definate candidate for a faster algorithm */
 uid_t match_uid(uid_t uid)
 {
-	static uid_t last_in, last_out;
+	static uid_t last_in = -1, last_out = -1;
 	struct idlist *list;
 
-	if (uid == 0)
-		return 0;
-
 	if (uid == last_in)
 		return last_out;
 
@@ -207,10 +214,13 @@ uid_t match_uid(uid_t uid)
 
 	for (list = uidlist; list; list = list->next) {
 		if (list->id == uid)
-			return last_out = list->id2;
+			break;
 	}
 
-	return last_out = uid;
+	if (!list)
+		list = recv_add_id(&uidlist, uidmap, uid, NULL);
+
+	return last_out = list->id2;
 }
 
 gid_t match_gid(gid_t gid, uint16 *flags_ptr)
@@ -226,7 +236,7 @@ gid_t match_gid(gid_t gid, uint16 *flags_ptr)
 				break;
 		}
 		if (!list)
-			list = recv_add_gid(gid, NULL);
+			list = recv_add_id(&gidlist, gidmap, gid, NULL);
 		last = list;
 	}
 
@@ -319,7 +329,7 @@ uid_t recv_user_name(int f, uid_t uid)
 		free(name);
 		name = NULL;
 	}
-	node = recv_add_uid(uid, name); /* node keeps name's memory */
+	node = recv_add_id(&uidlist, uidmap, uid, name); /* node keeps name's memory */
 	return node->id2;
 }
 
@@ -335,7 +345,7 @@ gid_t recv_group_name(int f, gid_t gid, uint16 *flags_ptr)
 		free(name);
 		name = NULL;
 	}
-	node = recv_add_gid(gid, name); /* node keeps name's memory */
+	node = recv_add_id(&gidlist, gidmap, gid, name); /* node keeps name's memory */
 	if (flags_ptr && node->flags & FLAG_SKIP_GROUP)
 		*flags_ptr |= FLAG_SKIP_GROUP;
 	return node->id2;
@@ -362,17 +372,103 @@ void recv_id_list(int f, struct file_list *flist)
 
 	/* Now convert all the uids/gids from sender values to our values. */
 #ifdef SUPPORT_ACLS
-	if (preserve_acls && !numeric_ids)
+	if (preserve_acls && (!numeric_ids || usermap || groupmap))
 		match_acl_ids();
 #endif
-	if (am_root && preserve_uid && !numeric_ids) {
+	if (am_root && preserve_uid && (!numeric_ids || usermap)) {
 		for (i = 0; i < flist->used; i++)
 			F_OWNER(flist->files[i]) = match_uid(F_OWNER(flist->files[i]));
 	}
-	if (preserve_gid && (!am_root || !numeric_ids)) {
+	if (preserve_gid && (!am_root || !numeric_ids || groupmap)) {
 		for (i = 0; i < flist->used; i++) {
 			F_GROUP(flist->files[i]) = match_gid(F_GROUP(flist->files[i]),
 							     &flist->files[i]->flags);
 		}
 	}
 }
+
+void parse_name_map(char *map, BOOL usernames)
+{
+	struct idlist **idmap_ptr = usernames ? &uidmap : &gidmap;
+	struct idlist **idlist_ptr = usernames ? &uidlist : &gidlist;
+	char *colon, *end, *name, *cp = map + strlen(map);
+	id_t id1;
+	uint16 flags;
+
+	/* Parse the list in reverse, so the order in the struct is right. */
+	while (1) {
+		end = cp;
+		while (cp > map && cp[-1] != ',') cp--;
+		if (!(colon = strchr(cp, ':'))) {
+			rprintf(FERROR, "No colon found in --%smap: %s\n",
+				usernames ? "user" : "group", cp);
+			exit_cleanup(RERR_SYNTAX);
+		}
+		if (!colon[1]) {
+			rprintf(FERROR, "No name found after colon --%smap: %s\n",
+				usernames ? "user" : "group", cp);
+			exit_cleanup(RERR_SYNTAX);
+		}
+		*colon = '\0';
+
+		if (isDigit(cp)) {
+			char *dash = strchr(cp, '-');
+			if (strspn(cp, "0123456789-") != (size_t)(colon - cp)
+			 || (dash && (!dash[1] || strchr(dash+1, '-')))) {
+			  bad_number:
+				rprintf(FERROR, "Invalid number in --%smap: %s\n",
+					usernames ? "user" : "group", cp);
+				exit_cleanup(RERR_SYNTAX);
+			}
+			if (dash)
+				name = (char *)atol(dash+1);
+			else
+				name = (char *)0;
+			flags = 0;
+			id1 = atol(cp);
+		} else if (strpbrk(cp, "*[?")) {
+			flags = NFLAGS_WILD_NAME_MATCH;
+			name = cp;
+			id1 = 0;
+		} else {
+			flags = NFLAGS_NAME_MATCH;
+			name = cp;
+			id1 = 0;
+		}
+
+		if (isDigit(colon+1)) {
+			if (strspn(colon+1, "0123456789") != (size_t)(end - colon - 1)) {
+				cp = colon+1;
+				goto bad_number;
+			}
+			add_to_list(idmap_ptr, id1, name, atol(colon+1), flags);
+		} else if (usernames) {
+			uid_t uid;
+			if (name_to_uid(colon+1, &uid))
+				add_to_list(idmap_ptr, id1, name, uid, flags);
+			else {
+				rprintf(FERROR,
+				    "Unknown --usermap name on receiver: %s\n",
+				    colon+1);
+			}
+		} else {
+			gid_t gid;
+			if (name_to_gid(colon+1, &gid))
+				add_to_list(idmap_ptr, id1, name, gid, flags);
+			else {
+				rprintf(FERROR,
+				    "Unknown --groupmap name on receiver: %s\n",
+				    colon+1);
+			}
+		}
+
+		if (cp == map)
+			break;
+
+		*--cp = '\0'; /* replace comma */
+	}
+
+	/* The 0 user/group doesn't get its name sent, so add it explicitly. */
+	recv_add_id(idlist_ptr, *idmap_ptr, 0,
+		    numeric_ids ? NULL : usernames ? uid_to_name(0) : gid_to_name(0));
+}