svn -> git migration script

[wiktorn]

#!/usr/bin/env bash

set -e

git init josm-tests
cd josm-tests
# create commit, to keep master branch clear
git commit -m 'init' --allow-empty

###
# define remotes
###

git svn init --trunk=. --prefix=svn_jmapviewer -R jmapviewer \
   https://svn.openstreetmap.org/applications/viewer/jmapviewer
git svn init --trunk=. --prefix=svn_josm -R josm https://josm.openstreetmap.de/svn/trunk
# two separate remotes for commons as this is 2x ~10 minutes instead of 2+ houres to fetch
git svn init --trunk=. --include-paths='commons/proper/jcs/trunk/.*src/main/java/org/apache/commons/jcs' \
  --prefix=svn_commons_jcs -R svn_commons_jcs https://svn.apache.org/repos/asf/commons/proper/jcs/
git svn init --trunk=. --include-paths='commons/proper/logging/trunk/src/main/java/org/apache/commons/logging' \
  --prefix=svn_commons_logging -R svn_commons_logging https://svn.apache.org/repos/asf/commons/proper/logging/trunk/
git remote add commons_compress https://github.com/apache/commons-compress.git

###
# fetch from remotes
###
git svn fetch jmapviewer
git svn fetch josm
git svn fetch --log-window-size=100000 svn_commons_jcs
git svn fetch --log-window-size=100000 svn_commons_logging
git svn fetch svn_commons_jcs
git svn fetch svn_commons_logging
git fetch commons_compress


###
# Reorganize externals
###

# JMapViewer
git branch svn_jmapviewer_rewrite remotes/svn_jmapviewertrunk
git filter-branch -f --tree-filter '
  if [ -d src/org/openstreetmap/gui/jmapviewer ] ; then
      git mv src src.new &&
      find . -depth 1 |
      grep -v ^./src.new | grep -v ^./.git$ |
      xargs -r git rm -fr &&
      mkdir -p src/org/openstreetmap/gui &&
      git add src/org/openstreetmap/gui &&
      git mv src.new/org/openstreetmap/gui/jmapviewer src/org/openstreetmap/gui &&
      git rm -rf --ignore-unmatch src.new
  else
      find . -depth 1 |
      grep -v ^./.git$ |
      xargs -r git rm -fr
  fi' \
  svn_jmapviewer_rewrite

# Apache Commons Compress
# compress is already on git, need first to somehow mix with other repositories (using commit date, not author date)
# as commits sorted by date do not constitue the history.
# So first - order by commit date and mix, then filter the content
# For now it generates a few merge conflicts
# TODO: can it be done using --index-filter?
git branch svn_commons_compress_rewrite remotes/commons_compress/master
git filter-branch -f --tree-filter '
  if [ -d src/main/java ] ; then
      git mv src src.new &&
      find . -depth 1 |
      grep -v ^./src.new | grep -v ^./.git$ |
      xargs -r git rm -fr &&
      git mv src.new/main/java src &&
      git rm -rf --ignore-unmatch src.new
  else
      find . -depth 1 |
      grep -v ^./.git$ |
      xargs -r git rm -fr
  fi' \
  svn_commons_compress_rewrite
# Apache Commons JCS
git branch svn_commons_jcstrunk_rewrite remotes/svn_commons_jcstrunk
git filter-branch -f --tree-filter '
  if [ -d trunk/commons-jcs-core/src/main/java/ ] ; then
      git rm -rf src ;
      git mv trunk/commons-jcs-core/src/main/java src &&
      find . -depth 1 |
      grep -v ^./src$ | grep -v ^./.git$ |
      xargs -r git rm -fr
  else
      find . -depth 1 |
      grep -v ^./.git$ |
      xargs -r git rm -fr
  fi' \
  svn_commons_jcstrunk_rewrite

# Apache Commons Logging
git branch svn_commons_loggingtrunk_rewrite remotes/svn_commons_loggingtrunk
git filter-branch -f --tree-filter '
  if [ -d src/main/java ] ; then
      git mv src src.new &&
      find . -depth 1 |
      grep -v ^./src.new | grep -v ^./.git$ |
      xargs -r git rm -fr &&
      git mv src.new/main/java src &&
      git rm -rf --ignore-unmatch src.new
  else
      find . -depth 1 |
      grep -v ^./.git$ |
      xargs -r git rm -fr
  fi' \
  svn_commons_loggingtrunk_rewrite

###
# Remove empty commits
###

for i in svn_jmapviewer svn_commons_compress  svn_commons_jcstrunk svn_commons_loggingtrunk ; do
  git branch "${i}_clean" "${i}_rewrite"
  git rebase $(git log --reverse --oneline --no-abbrev-commit "${i}_clean" | head -n 1 | cut -d ' ' -f 1) "${i}_clean" || exit 1
done

###
# Merge JOSM repository with externals, commits ordered by date
###

REBASE_CONF=$(mktemp)
(
  git log --pretty="format:%at %H %s" remotes/svn_josmtrunk
  git log --pretty="format:%at %H %s" svn_jmapviewer_rewrite
) | sort -n > "${REBASE_CONF}"

JOSM_EPOCH=$(head -n 1 ${REBASE_CONF} | cut -d ' ' -f1 )
(
  git log --pretty="format:%at %H %s" svn_commons_compress_rewrite
  git log --pretty="format:%at %H %s" svn_commons_jcstrunk_rewrite
  git log --pretty="format:%at %H %s" svn_commons_loggingtrunk_rewrite
) | awk -F ' ' "\$1 > ${JOSM_EPOCH} {print \$1 \" \" \$2} {}" >> "${REBASE_CONF}"

sort -n ${REBASE_CONF} | cut -d ' ' -f2 | sed -e 's/^/p /' > ../rebase_config
rm ${REBASE_CONF}
git config merge.renamelimit 5000
git checkout master
git rebase --keep-empty -i $(git log --reverse --oneline --no-abbrev-commit | head -n 1 | cut -d ' ' -f 1)

# helpful one-liner: git diff --name-only --diff-filter=U | xargs git checkout  ...

# remove empty commits
git rebase $(git log --reverse --oneline --no-abbrev-commit | head -n 1 | cut -d ' ' -f 1)

###
# Move jar files to Git LFS
###
git lfs migrate import --include="*.jar" --include-ref=refs/heads/master
git reflog expire --expire-unreachable=now --all
git gc --prune=now