Bash :: Find and remove large files in Git history

git_rm_large_files.sh

#!/bin/bash

set -o verbose

# Checkout and pull in the local copy of all existing branches in the repository
for branch in $(git branch -a |grep remotes/origin |grep -v HEAD |sed "s/remotes\/origin\///g")
do
    git checkout $branch
    git pull
done

# Get the existing large files in Git history
git rev-list master | while read rev; do git ls-tree -lr $rev | cut -c54- | grep -v '^ '; done | sort -u | perl -e '
    while (<>) {
        chomp;
        @stuff=split("\t");
        $sums{$stuff[1]} += $stuff[0];
    }
    print "$sums{$_} $_\n" for (keys %sums);
' | sort -rn >> large_files.txt

# Remove the large files stored in the 'large_files.txt' file
for file in $(cat large_files.txt |awk '{print $2}')
do
    git filter-branch --force --index-filter "git rm --cached --ignore-unmatch $file" --prune-empty --tag-name-filter cat -- --all
done

# Force-push the local changes made in the branches of the repository
git push origin --force --all

# Force-push the local changes made in the tags of the repository
git push origin --force --tags

# Remove the 'large_files.txt' file
rm large_files.txt