rgw: handle instances w/ leading hyphens correctly

Some instance identifiers have leading hyphens, which broke the
rgw-restore-bucket-index script. This fixes those issues and adds a
few features to making debugging easier in the future.

Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
(cherry picked from commit 48acf4712a36936306acfc887f0ab205d3bfe8b4)

diff --git a/src/rgw/rgw-restore-bucket-index b/src/rgw/rgw-restore-bucket-index
index 512ca24d9ec26733a2911a159eb3a1e67edd7433..243a4f49068e5d9aeddff3e6609cf6cfd69c31f3 100755 (executable)
--- a/src/rgw/rgw-restore-bucket-index
+++ b/src/rgw/rgw-restore-bucket-index
@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 
-# version 2023-07-06
+# version 2023-10-30
 
 # rgw-restore-bucket-index is an EXPERIMENTAL tool to use in case
 # bucket index entries for objects in the bucket are somehow lost. It
@@ -37,13 +37,18 @@ export obj_reindex_script=/tmp/rgwrbi-object-list-script.$$
 export zone_info=/tmp/rgwrbi-zone-info.$$
 export olh_info_enc=/tmp/rgwrbi-olh-info-enc.$$
 export olh_info_json=/tmp/rgwrbi-olh-info-json.$$
+export debug_log=/tmp/rgwrbi-debug-log.$$
 
 export clean_temps=1
 
+# make explicit tabs easier to see in code
+export TAB="   "
+
 
 clean() {
-  if [ -n "$clean_temps" ] ;then
-    rm -f $bkt_entry $bkt_inst $marker_ls $obj_list $obj_list_ver $obj_reindex_script $zone_info $olh_info_enc $olh_info_json
+  if [ "$clean_temps" == 1 ] ;then
+    rm -f $bkt_entry $bkt_inst $marker_ls $obj_list $obj_list_ver \
+       $obj_reindex_script $zone_info $olh_info_enc $olh_info_json
   fi
 }
 
@@ -178,8 +183,9 @@ while getopts "b:l:p:r:g:z:yd" o; do
            proceed=1
            ;;
        d)
-           echo setting debug to 1
+           echo Debugging On
            debug=1
+           clean_temps=0
            ;;
        *)
            echo
@@ -217,15 +223,24 @@ handle_versioned() {
            filter_out_last_instance="$last_instance"
        fi
 
+       if [ "$debug" == 1 ] ;then
+           echo "working on versioned $o"
+           echo "last instance is $last_instance"
+           echo "filter_out_last_instance is $filter_out_last_instance"
+       fi >>$debug_log
+
        # we currently don't need the delete marker, but we can have access to it
        # delete_marker=$(jq -r ".removed" $olh_info_json) # true or false
 
        IFS='\t' grep -E "(__:.*[^_])?_$o(\t.*)?$" $marker_ls | # versioned head objects
            while read obj loc ;do
+               if [ "$debug" == 1 ] ;then
+                   echo "obj=$obj ; loc=$loc" >>$debug_log
+               fi
                rados -p $pool stat2 $obj --object-locator "$loc"
            done | # output of stat2, which includes mtime
            sort -k 3 | # stat2 but sorted by mtime earlier to later
-           grep -v "$filter_out_last_instance" | # remove the final instance in case it's not last
+           grep -v -e "$filter_out_last_instance" | # remove the final instance in case it's not last
 
            # sed 1) removes pool and marker, 2) removes indicator of
            # version id, 3) removes obj name including escaped
@@ -238,9 +253,9 @@ handle_versioned() {
                -e 's/^__://' \
                -e "s/_+${o}.*//" \
                -e "s/^/${o}\t/"
-       echo "$o        $last_instance" # now add the final instance; could be delete marker; note TAB
+       echo "${o}${TAB}$last_instance" # now add the final instance; could be delete marker
     done <$obj_list 2>/dev/null | sed 's/\t$//' >$obj_list_ver
-}
+} # handle_versioned
 
 if [ -z "$bucket" ]; then
   echo