我目前正在将一个cvs项目导入git。 导入后，我想重写历史记录，将现有目录移动到单独的子模块中。
假设我有这样的结构：
file1
file2
file3
dir1
dir2
library
现在我想重写历史记录，以便目录library始终是一个git子模块。比如说，将指定的目录拆分为自己的子模块/子项目
这是我目前的代码：
文件重写 - 子模块（被调用）
cd project
git filter-branch --tree-filter $PWD/../$0-tree-filter --tag-name-filter cat -- --all
文件重写 - 子模块树过滤器
#!/bin/bash
function gitCommit()
{
unset GIT_DIR
unset GIT_WORK_TREE
git add -A
if [ -n "$(git diff --cached --name-only)" ]
then
# something to commit
git commit -F $_msg
fi
}
_git_dir=$GIT_DIR
_git_work_tree=$GIT_WORK_TREE
unset GIT_DIR
unset GIT_WORK_TREE
_dir=$PWD
if [ -d "library" ]
then
_msg=$(tempfile)
git log ${GIT_COMMIT}^! --format="%B" > $_msg
git rm -r --cached lib
cd library
if [ -d ".git" ]
then
gitCommit
else
git init
gitCommit
fi
cd ..
export GIT_DIR=$_git_dir
export GIT_WORK_TREE=$_git_work_tree
git submodule add -f ./lib
fi
GIT_DIR=$_git_dir
GIT_WORK_TREE=$_git_work_tree
此代码创建.gitmodules文件，但不创建主存储库中的子模块提交条目（行Subproject commit <sha1-hash>，由git diff输出），目录library中的文件仍在主存储库中而不是在子项目存储库中。
提前感谢任何提示
.gitmodules看起来像这样：
[submodule "library"]
path = library
url = ./library
我解决了自己的问题，这是解决方案：
git-submodule-split library another_library
脚本git-submodule-split：
#!/bin/bash
set -eu
if [ $# -eq 0 ]
then
echo "Usage: $0 submodules-to-split"
fi
export _tmp=$(mktemp -d)
export _libs="$@"
for i in $_libs
do
mkdir -p $_tmp/$i
done
git filter-branch --commit-filter '
function gitCommit()
{
git add -A
if [ -n "$(git diff --cached --name-only)" ]
then
git commit -F $_msg
fi
} >/dev/null
# from git-filter-branch
git checkout-index -f -u -a || die "Could not checkout the index"
# files that $commit removed are now still in the working tree;
# remove them, else they would be added again
git clean -d -q -f -x
_git_dir=$GIT_DIR
_git_work_tree=$GIT_WORK_TREE
_git_index_file=$GIT_INDEX_FILE
unset GIT_DIR
unset GIT_WORK_TREE
unset GIT_INDEX_FILE
_msg=$(tempfile)
cat /dev/stdin > $_msg
for i in $_libs
do
if [ -d "$i" ]
then
unset GIT_DIR
unset GIT_WORK_TREE
unset GIT_INDEX_FILE
cd $i
if [ -d ".git" ]
then
gitCommit
else
git init >/dev/null
gitCommit
fi
cd ..
rsync -a -rtu $i/.git/ $_tmp/$i/.git/
export GIT_DIR=$_git_dir
export GIT_WORK_TREE=$_git_work_tree
export GIT_INDEX_FILE=$_git_index_file
git rm -q -r --cached $i
git submodule add ./$i >/dev/null
git add $i
fi
done
rm $_msg
export GIT_DIR=$_git_dir
export GIT_WORK_TREE=$_git_work_tree
export GIT_INDEX_FILE=$_git_index_file
if [ -f ".gitmodules" ]
then
git add .gitmodules
fi
_new_rev=$(git write-tree)
shift
git commit-tree "$_new_rev" "$@";
' --tag-name-filter cat -- --all
for i in $_libs
do
if [ -d "$_tmp/$i/.git" ]
then
rsync -a -i -rtu $_tmp/$i/.git/ $i/.git/
cd $i
git reset --hard
cd ..
fi
done
rm -r $_tmp
git for-each-ref refs/original --format="%(refname)" | while read i; do git update-ref -d $i; done
git reflog expire --expire=now --all
git gc --aggressive --prune=now
我有一个带有utils库的项目，它在其他项目中开始有用，并希望将其历史记录拆分为子模块。没想到先看看SO所以我自己编写了它，它在本地构建历史所以它更快一点，之后如果你想要你可以设置helper命令的.gitmodules文件等，并推送子模块历史本身任何你想的地点都可以。
剥离的命令本身就在这里，注释中的文档，后面的未提取的命令。运行它作为自己的命令，使用subdir设置，如subdir=utils git split-submodule，如果你拆分utils目录。这是hacky，因为它是一次性的，但我在Git历史记录的Documentation子目录中测试了它。
#!/bin/bash
# put this or the commented version below in e.g. ~/bin/git-split-submodule
${GIT_COMMIT-exec git filter-branch --index-filter "subdir=$subdir; ${debug+debug=$debug;} $(sed 1,/SNIP/d "$0")" "$@"}
${debug+set -x}
fam=(`git rev-list --no-walk --parents $GIT_COMMIT`)
pathcheck=(`printf "%s:$subdir\\n" ${fam[@]} \
| git cat-file --batch-check='%(objectname)' | uniq`)
[[ $pathcheck = *:* ]] || {
subfam=($( set -- ${fam[@]}; shift;
for par; do tpar=`map $par`; [[ $tpar != $par ]] &&
git rev-parse -q --verify $tpar:"$subdir"
done
))
git rm -rq --cached --ignore-unmatch "$subdir"
if (( ${#pathcheck[@]} == 1 && ${#fam[@]} > 1 && ${#subfam[@]} > 0)); then
git update-index --add --cacheinfo 160000,$subfam,"$subdir"
else
subnew=`git cat-file -p $GIT_COMMIT | sed 1,/^$/d \
| git commit-tree $GIT_COMMIT:"$subdir" $(
${subfam:+printf ' -p %s' ${subfam[@]}}) 2>&-
` &&
git update-index --add --cacheinfo 160000,$subnew,"$subdir"
fi
}
${debug+set +x}
#!/bin/bash
# Git filter-branch to split a subdirectory into a submodule history.
# In each commit, the subdirectory tree is replaced in the index with an
# appropriate submodule commit.
# * If the subdirectory tree has changed from any parent, or there are
# no parents, a new submodule commit is made for the subdirectory (with
# the current commit's message, which should presumably say something
# about the change). The new submodule commit's parents are the
# submodule commits in any rewrites of the current commit's parents.
# * Otherwise, the submodule commit is copied from a parent.
# Since the new history includes references to the new submodule
# history, the new submodule history isn't dangling, it's incorporated.
# Branches for any part of it can be made casually and pushed into any
# other repo as desired, so hooking up the `git submodule` helper
# command's conveniences is easy, e.g.
# subdir=utils git split-submodule master
# git branch utils $(git rev-parse master:utils)
# git clone -sb utils . ../utilsrepo
# and you can then submodule add from there in other repos, but really,
# for small utility libraries and such, just fetching the submodule
# histories into your own repo is easiest. Setup on cloning a
# project using "incorporated" submodules like this is:
# setup: utils/.git
#
# utils/.git:
# @if _=`git rev-parse -q --verify utils`; then \
# git config submodule.utils.active true \
# && git config submodule.utils.url "`pwd -P`" \
# && git clone -s . utils -nb utils \
# && git submodule absorbgitdirs utils \
# && git -C utils checkout $$(git rev-parse :utils); \
# fi
# with `git config -f .gitmodules submodule.utils.path utils` and
# `git config -f .gitmodules submodule.utils.url ./`; cloners don't
# have to do anything but `make setup`, and `setup` should be a prereq
# on most things anyway.
# You can test that a commit and its rewrite put the same tree in the
# same place with this function:
# testit ()
# {
# tree=($(git rev-parse `git rev-parse $1`: refs/original/refs/heads/$1));
# echo $tree `test $tree != ${tree[1]} && echo ${tree[1]}`
# }
# so e.g. `testit make~95^2:t` will print the `t` tree there and if
# the `t` tree at ~95^2 from the original differs it'll print that too.
# To run it, say `subdir=path/to/it git split-submodule` with whatever
# filter-branch args you want.
# $GIT_COMMIT is set if we're already in filter-branch, if not, get there:
${GIT_COMMIT-exec git filter-branch --index-filter "subdir=$subdir; ${debug+debug=$debug;} $(sed 1,/SNIP/d "$0")" "$@"}
${debug+set -x}
fam=(`git rev-list --no-walk --parents $GIT_COMMIT`)
pathcheck=(`printf "%s:$subdir\\n" ${fam[@]} \
| git cat-file --batch-check='%(objectname)' | uniq`)
[[ $pathcheck = *:* ]] || {
subfam=($( set -- ${fam[@]}; shift;
for par; do tpar=`map $par`; [[ $tpar != $par ]] &&
git rev-parse -q --verify $tpar:"$subdir"
done
))
git rm -rq --cached --ignore-unmatch "$subdir"
if (( ${#pathcheck[@]} == 1 && ${#fam[@]} > 1 && ${#subfam[@]} > 0)); then
# one id same for all entries, copy mapped mom's submod commit
git update-index --add --cacheinfo 160000,$subfam,"$subdir"
else
# no mapped parents or something changed somewhere, make new
# submod commit for current subdir content. The new submod
# commit has all mapped parents' submodule commits as parents:
subnew=`git cat-file -p $GIT_COMMIT | sed 1,/^$/d \
| git commit-tree $GIT_COMMIT:"$subdir" $(
${subfam:+printf ' -p %s' ${subfam[@]}}) 2>&-
` &&
git update-index --add --cacheinfo 160000,$subnew,"$subdir"
fi
}
${debug+set +x}
注意：子模块条目仅在您从父存储库创建时创建
git submodule init
git submodule update
您在rewrite-submodule-tree-filter脚本中不需要这些命令，因为它只是关于正确设置.gitmodules文件内容。
只有在第一次使用父级仓库时，才会执行这些“git submodule”命令：请参阅“Cloning a Project with Submodules”。
这是一个更新的答案，适用于MacOSX。主要的变化是使用pushd / popd来改变目录，因此子模块可以是模块/ glop而不仅仅是glop。
#!/bin/bash
set -eu
if [ $# -eq 0 ]
then
echo "Usage: $0 submodules-to-split"
fi
export _tmp=$(mktemp -d /tmp/git-submodule-split.XXXXXX)
export _libs="$@"
for i in $_libs
do
mkdir -p $_tmp/$i
done
git filter-branch --commit-filter '
function gitCommit()
{
git add -A
if [ -n "$(git diff --cached --name-only)" ]
then
git commit -F $_msg
fi
} >/dev/null
# from git-filter-branch
git checkout-index -f -u -a || die "Could not checkout the index"
# files that $commit removed are now still in the working tree;
# remove them, else they would be added again
git clean -d -q -f -x >&2
_git_dir=$GIT_DIR
_git_work_tree=$GIT_WORK_TREE
_git_index_file=$GIT_INDEX_FILE
unset GIT_DIR
unset GIT_WORK_TREE
unset GIT_INDEX_FILE
_msg=$(mktemp /tmp/git-submodule-split-msg.XXXXXX)
cat /dev/stdin > $_msg
for i in $_libs
do
if [ -d "$i" ]
then
unset GIT_DIR
unset GIT_WORK_TREE
unset GIT_INDEX_FILE
pushd $i > /dev/null
if [ -d ".git" ]
then
gitCommit
else
git init >/dev/null
gitCommit
fi
popd > /dev/null
mkdir -p $_tmp/$i
rsync -a -rtu $i/.git/ $_tmp/$i/.git/
export GIT_DIR=$_git_dir
export GIT_WORK_TREE=$_git_work_tree
export GIT_INDEX_FILE=$_git_index_file
git rm -q -r --cached $i >&2
git submodule add ./$i $i >&2
git add $i >&2
fi
done
export GIT_DIR=$_git_dir
export GIT_WORK_TREE=$_git_work_tree
export GIT_INDEX_FILE=$_git_index_file
if [ -f ".gitmodules" ]
then
git add .gitmodules >&2
fi
_new_rev=$(git write-tree)
shift
git commit-tree -F $_msg "$_new_rev" $@;
rm -f $_msg
' --tag-name-filter cat -- --all
for i in $_libs
do
if [ -d "$_tmp/$i/.git" ]
then
rsync -a -i -rtu $_tmp/$i/.git/ $i/.git/
pushd $i
git reset --hard
popd
fi
done
rm -rf $_tmp
git for-each-ref refs/original --format="%(refname)" | while read i; do git update-ref -d $i; done
git reflog expire --expire=now --all
git gc --aggressive --prune=now