Merge multiple repos into single monorepo maintaining git history

merge.sh

#!/bin/bash
set -euo pipefail

NEW_REPO_DIR=${NEW_REPO_DIR:-'new-repo'}
BASE_CODE_DIR=${BASE_CODE_DIR:-'apps'}
# expected starting structue: 
# merge.sh
# repo1
# repo2
# repo3

BASE_DIR=$(pwd)
repos="repo1 repo2 repo3"

rm -rf $NEW_REPO_DIR
mkdir $NEW_REPO_DIR
cd $NEW_REPO_DIR

git init .

# add all service repos
for repo in $repos; do
  git remote add $repo ../$repo
  git fetch $repo
  git checkout -b $repo $repo/main
  git filter-branch \
    -f \
    --tree-filter "mkdir -p $BASE_CODE_DIR/$repo && rsync -a --remove-source-files ./ $BASE_CODE_DIR/$repo/" \
    --msg-filter "cat | tr '\n' ' ' | awk '{print \"$repo: \" \$0}'" \
    --env-filter 'GIT_COMMITTER_DATE="$GIT_AUTHOR_DATE"' \
    $repo
  git tag -d $(git tag -l)
done

# create main
git checkout --orphan main
git rm -rf .

# cherry pick into the main
for i in $(git log --pretty='%H' --author-date-order --reverse $repos); do
  GIT_COMMITTER_DATE=$(git log -1 --pretty='%at' $i) \
    git cherry-pick $i || git commit --allow-empty
done

for repo in $repos; do
  git branch -D $repo
  git remote remove $repo
  git update-ref -d refs/original/refs/heads/$repo
done

git gc --aggressive