Submodules to subtrees

[maxhbr]

This automatically converts all submodules in ./data to subtrees to have the commits in this history and not to depend on third parties.

The script:

see also:

• https://gist.github.com/Nikita240/0c98cea8f53a15e69699cd8bc40657c4
• https://stackoverflow.com/questions/28215244/convert-git-submodule-to-subtree

#!/usr/bin/env bash
# This script will convert all your git submodules into git subtrees.
# This script ensures that your new subtrees point to the same commits as the
# old submodules did, unlike most other scripts that do this.
# THIS SCRIPT MUST BE PLACED OUTSIDE OF YOUR REPOSITORY!!!!!!!!!!
# Otherwise, the script will interfere with the git commits (unless you add it to .gitignore).
# Save the script in your home directory as `~/subtrees.sh`
# `cd` into your repository
# Run `~/subtrees.sh`
# Enjoy!
#
# see:
# - https://gist.github.com/Nikita240/0c98cea8f53a15e69699cd8bc40657c4
# - https://stackoverflow.com/questions/28215244/convert-git-submodule-to-subtree

set -euo pipefail

# set -x

# extract the list of submodules from .gitmodule
cat .gitmodules |while read i; do
    if [[ $i == \[submodule* ]]; then

      read i
      # extract the module's prefix
      mpath=$(echo $i | grep -E "(\S+)$" -o)
      read i
      # extract the url of the submodule
      murl=$(echo $i|cut -d\= -f2|xargs)
      if [[ "$mpath" != "data/"* ]] then
        continue
      fi
      if [[ "$mpath" == "data/"*"/"* ]] then
        continue
      fi
      if [[ ! -d "$mpath" ]]; then
        continue
      fi
      echo converting $i
      echo path: $mpath
      echo url: $murl

      branch=main
      case "$mpath" in
        "data/wking-fsf-api")
          branch=gh-pages
          ;;
        "data/finos-OSLC-handbook")
          branch=master
          ;;
        "data/openSUSE-cavil")
          branch=master
          ;;
        "data/librariesio-license-compatibility")
          branch=master
          ;;
        "data/HansHammel-license-compatibility-checker")
          branch=master
          ;;
        "data/okfn-licenses")
          branch=master
          ;;
        "data/oslic")
          branch=master
          ;;
        "data/telekom-oslic")
          branch=master
          ;;
        "data/warpr-licensedb")
          branch=master
          ;;
        "data/Hitachi-open-license")
          branch=master
          ;;
        "data/ifrOSS-ifrOSS")
          branch=master
          ;;
        "data/github-choosealicense.com")
          branch=gh-pages
          ;;
        "data/ErikMcClure-bad-licenses")
          branch=master
          ;;
        "data/AmadeusITGroup-oscad2")
          branch=master
          ;;
        "data/OpenSourceOrg-licenses")
          branch=master
          ;;
        "data/fedora-modularity-check_modulemd")
          branch=master
          ;;
      esac

      # extract the module name
      mname=$(basename $mpath)
      # extract the referenced commit
      mcommit=$(git submodule status $mpath | grep -E "\S+" -o | head -1)
      if [[ "$mcommit" == "-"* ]]; then
        mcommit="${mcommit//-}"
      fi
      echo name: $mname
      echo commit: $mcommit

      set -x
      git submodule deinit -f $mpath # deinit the module
      git rm -r --cached $mpath # remove the module from git
      rm -rf $mpath # remove the module from the filesystem
      git commit -m "Removed $mpath submodule at commit $mcommit" # commit the change


      ./data/add_subtree.sh "$mname" "$murl" "$mcommit" "$branch"
      git commit --allow-empty -a -m "$mname update script and cleaned up" # commit any left over uncommited changes
      set +x

      echo
    fi
  done