X-Git-Url: https://git.tokkee.org/?a=blobdiff_plain;f=git-filter-branch.sh;h=a4b6577bd496819232754c1275b7c1e798b0470c;hb=d225ae59c9102f2769c55749f80f7a94a92713e4;hp=22fb5bf6ad929e2028ec1cf98f9073b14cdd8b51;hpb=c401b33c349beaf4c218c6441c3e2b58a958de6f;p=git.git diff --git a/git-filter-branch.sh b/git-filter-branch.sh old mode 100644 new mode 100755 index 22fb5bf6a..a4b6577bd --- a/git-filter-branch.sh +++ b/git-filter-branch.sh @@ -8,16 +8,43 @@ # a new branch. You can specify a number of filters to modify the commits, # files and trees. -set -e - -USAGE="git-filter-branch [-d TEMPDIR] [FILTERS] DESTBRANCH [REV-RANGE]" -. git-sh-setup +warn () { + echo "$*" >&2 +} map() { # if it was not rewritten, take the original - test -r "$workdir/../map/$1" || echo "$1" - cat "$workdir/../map/$1" + if test -r "$workdir/../map/$1" + then + cat "$workdir/../map/$1" + else + echo "$1" + fi +} + +# if you run 'skip_commit "$@"' in a commit filter, it will print +# the (mapped) parents, effectively skipping the commit. + +skip_commit() +{ + shift; + while [ -n "$1" ]; + do + shift; + map "$1"; + shift; + done; +} + +# override die(): this version puts in an extra line break, so that +# the progress is still visible + +die() +{ + echo >&2 + echo "$*" >&2 + exit 1 } # When piped a commit, output a script to set the ident of either @@ -53,6 +80,20 @@ set_ident () { echo "[ -n \"\$GIT_${uid}_NAME\" ] || export GIT_${uid}_NAME=\"\${GIT_${uid}_EMAIL%%@*}\"" } +# This script can be sourced by the commit filter to get the functions +test "a$SOURCE_FUNCTIONS" = a1 && return +this_script="$(cd "$(dirname "$0")"; pwd)"/$(basename "$0") +export this_script + +USAGE="[--env-filter ] [--tree-filter ] \ +[--index-filter ] [--parent-filter ] \ +[--msg-filter ] [--commit-filter ] \ +[--tag-name-filter ] [--subdirectory-filter ] \ +[--original ] [-d ] [-f | --force] \ +[...]" + +. git-sh-setup + tempdir=.git-rewrite filter_env= filter_tree= @@ -62,6 +103,8 @@ filter_msg=cat filter_commit='git commit-tree "$@"' filter_tag_name= filter_subdir= +orig_namespace=refs/original/ +force= while case "$#" in 0) usage;; esac do case "$1" in @@ -69,6 +112,11 @@ do shift break ;; + --force|-f) + shift + force=t + continue + ;; -*) ;; *) @@ -102,7 +150,7 @@ do filter_msg="$OPTARG" ;; --commit-filter) - filter_commit="$OPTARG" + filter_commit='SOURCE_FUNCTIONS=1 . "$this_script";'" $OPTARG" ;; --tag-name-filter) filter_tag_name="$OPTARG" @@ -110,39 +158,75 @@ do --subdirectory-filter) filter_subdir="$OPTARG" ;; + --original) + orig_namespace=$(expr "$OPTARG/" : '\(.*[^/]\)/*$')/ + ;; *) usage ;; esac done -dstbranch="$1" -shift -test -n "$dstbranch" || die "missing branch name" -git show-ref "refs/heads/$dstbranch" 2> /dev/null && - die "branch $dstbranch already exists" +case "$force" in +t) + rm -rf "$tempdir" +;; +'') + test -d "$tempdir" && + die "$tempdir already exists, please remove it" +esac +mkdir -p "$tempdir/t" && +tempdir="$(cd "$tempdir"; pwd)" && +cd "$tempdir/t" && +workdir="$(pwd)" || +die "" + +# Make sure refs/original is empty +git for-each-ref > "$tempdir"/backup-refs +while read sha1 type name +do + case "$force,$name" in + ,$orig_namespace*) + die "Namespace $orig_namespace not empty" + ;; + t,$orig_namespace*) + git update-ref -d "$name" $sha1 + ;; + esac +done < "$tempdir"/backup-refs + +export GIT_DIR GIT_WORK_TREE=. -test ! -e "$tempdir" || die "$tempdir already exists, please remove it" -mkdir -p "$tempdir/t" -cd "$tempdir/t" -workdir="$(pwd)" +# These refs should be updated if their heads were rewritten -case "$GIT_DIR" in -/*) +git rev-parse --revs-only --symbolic "$@" | +while read ref +do + # normalize ref + case "$ref" in + HEAD) + ref="$(git symbolic-ref "$ref")" ;; -*) - GIT_DIR="$(pwd)/../../$GIT_DIR" + refs/*) ;; -esac -export GIT_DIR GIT_WORK_TREE=. + *) + ref="$(git for-each-ref --format='%(refname)' | + grep /"$ref")" + esac + + git check-ref-format "$ref" && echo "$ref" +done > "$tempdir"/heads + +test -s "$tempdir"/heads || + die "Which ref do you want to rewrite?" export GIT_INDEX_FILE="$(pwd)/../index" -git read-tree # seed the index file +git read-tree || die "Could not seed the index" ret=0 - -mkdir ../map # map old->new commit ids for rewriting parents +# map old->new commit ids for rewriting parents +mkdir ../map || die "Could not create map/ directory" case "$filter_subdir" in "") @@ -152,15 +236,17 @@ case "$filter_subdir" in *) git rev-list --reverse --topo-order --default HEAD \ --parents --full-history "$@" -- "$filter_subdir" -esac > ../revs -commits=$(cat ../revs | wc -l | tr -d " ") +esac > ../revs || die "Could not get the commits" +commits=$(wc -l <../revs | tr -d " ") test $commits -eq 0 && die "Found nothing to rewrite" +# Rewrite the commits + i=0 while read commit parents; do i=$(($i+1)) - printf "$commit ($i/$commits) " + printf "\rRewrite $commit ($i/$commits)" case "$filter_subdir" in "") @@ -168,28 +254,36 @@ while read commit parents; do ;; *) git read-tree -i -m $commit:"$filter_subdir" - esac + esac || die "Could not initialize the index" export GIT_COMMIT=$commit - git cat-file commit "$commit" >../commit + git cat-file commit "$commit" >../commit || + die "Cannot read commit $commit" - eval "$(set_ident AUTHOR <../commit)" - eval "$(set_ident COMMITTER <../commit)" - eval "$filter_env" < /dev/null + eval "$(set_ident AUTHOR <../commit)" || + die "setting author failed for commit $commit" + eval "$(set_ident COMMITTER <../commit)" || + die "setting committer failed for commit $commit" + eval "$filter_env" < /dev/null || + die "env filter failed: $filter_env" if [ "$filter_tree" ]; then - git checkout-index -f -u -a + git checkout-index -f -u -a || + die "Could not checkout the index" # files that $commit removed are now still in the working tree; # remove them, else they would be added again git ls-files -z --others | xargs -0 rm -f - eval "$filter_tree" < /dev/null + eval "$filter_tree" < /dev/null || + die "tree filter failed: $filter_tree" + git diff-index -r $commit | cut -f 2- | tr '\n' '\0' | \ xargs -0 git update-index --add --replace --remove git ls-files -z --others | \ xargs -0 git update-index --add --replace --remove fi - eval "$filter_index" < /dev/null + eval "$filter_index" < /dev/null || + die "index filter failed: $filter_index" parentstr= for parent in $parents; do @@ -198,30 +292,86 @@ while read commit parents; do done done if [ "$filter_parent" ]; then - parentstr="$(echo "$parentstr" | eval "$filter_parent")" + parentstr="$(echo "$parentstr" | eval "$filter_parent")" || + die "parent filter failed: $filter_parent" fi sed -e '1,/^$/d' <../commit | \ - eval "$filter_msg" | \ - sh -c "$filter_commit" "git commit-tree" $(git write-tree) $parentstr | \ - tee ../map/$commit + eval "$filter_msg" > ../message || + die "msg filter failed: $filter_msg" + sh -c "$filter_commit" "git commit-tree" \ + $(git write-tree) $parentstr < ../message > ../map/$commit done <../revs -src_head=$(tail -n 1 ../revs | sed -e 's/ .*//') -target_head=$(head -n 1 ../map/$src_head) -case "$target_head" in -'') - echo Nothing rewritten +# In case of a subdirectory filter, it is possible that a specified head +# is not in the set of rewritten commits, because it was pruned by the +# revision walker. Fix it by mapping these heads to the next rewritten +# ancestor(s), i.e. the boundaries in the set of rewritten commits. + +# NEEDSWORK: we should sort the unmapped refs topologically first +while read ref +do + sha1=$(git rev-parse "$ref"^0) + test -f "$workdir"/../map/$sha1 && continue + # Assign the boundarie(s) in the set of rewritten commits + # as the replacement commit(s). + # (This would look a bit nicer if --not --stdin worked.) + for p in $( (cd "$workdir"/../map; ls | sed "s/^/^/") | + git rev-list $ref --boundary --stdin | + sed -n "s/^-//p") + do + map $p >> "$workdir"/../map/$sha1 + done +done < "$tempdir"/heads + +# Finally update the refs + +_x40='[0-9a-f][0-9a-f][0-9a-f][0-9a-f][0-9a-f]' +_x40="$_x40$_x40$_x40$_x40$_x40$_x40$_x40$_x40" +count=0 +echo +while read ref +do + # avoid rewriting a ref twice + test -f "$orig_namespace$ref" && continue + + sha1=$(git rev-parse "$ref"^0) + rewritten=$(map $sha1) + + test $sha1 = "$rewritten" && + warn "WARNING: Ref '$ref' is unchanged" && + continue + + case "$rewritten" in + '') + echo "Ref '$ref' was deleted" + git update-ref -m "filter-branch: delete" -d "$ref" $sha1 || + die "Could not delete $ref" ;; -*) - git update-ref refs/heads/"$dstbranch" $target_head - if [ $(cat ../map/$src_head | wc -l) -gt 1 ]; then - echo "WARNING: Your commit filter caused the head commit to expand to several rewritten commits. Only the first such commit was recorded as the current $dstbranch head but you will need to resolve the situation now (probably by manually merging the other commits). These are all the commits:" >&2 - sed 's/^/ /' ../map/$src_head >&2 - ret=1 - fi + $_x40) + echo "Ref '$ref' was rewritten" + git update-ref -m "filter-branch: rewrite" \ + "$ref" $rewritten $sha1 || + die "Could not rewrite $ref" ;; -esac + *) + # NEEDSWORK: possibly add -Werror, making this an error + warn "WARNING: '$ref' was rewritten into multiple commits:" + warn "$rewritten" + warn "WARNING: Ref '$ref' points to the first one now." + rewritten=$(echo "$rewritten" | head -n 1) + git update-ref -m "filter-branch: rewrite to first" \ + "$ref" $rewritten $sha1 || + die "Could not rewrite $ref" + ;; + esac + git update-ref -m "filter-branch: backup" "$orig_namespace$ref" $sha1 + count=$(($count+1)) +done < "$tempdir"/heads + +# TODO: This should possibly go, with the semantics that all positive given +# refs are updated, and their original heads stored in refs/original/ +# Filter tags if [ "$filter_tag_name" ]; then git for-each-ref --format='%(objectname) %(objecttype) %(refname)' refs/tags | @@ -241,7 +391,8 @@ if [ "$filter_tag_name" ]; then [ -f "../map/$sha1" ] || continue new_sha1="$(cat "../map/$sha1")" export GIT_COMMIT="$sha1" - new_ref="$(echo "$ref" | eval "$filter_tag_name")" + new_ref="$(echo "$ref" | eval "$filter_tag_name")" || + die "tag name filter failed: $filter_tag_name" echo "$ref -> $new_ref ($sha1 -> $new_sha1)" @@ -250,12 +401,15 @@ if [ "$filter_tag_name" ]; then warn "unreferencing tag object $sha1t" fi - git update-ref "refs/tags/$new_ref" "$new_sha1" + git update-ref "refs/tags/$new_ref" "$new_sha1" || + die "Could not write tag $new_ref" done fi cd ../.. rm -rf "$tempdir" -echo "Rewritten history saved to the $dstbranch branch" +echo +test $count -gt 0 && echo "These refs were rewritten:" +git show-ref | grep ^"$orig_namespace" exit $ret