Script to find the largest files in a git history, with the intent to use the list to filter-branch remove the files forever.

git-largest-files.sh

#!/bin/bash

# Adapted from http://blog.jessitron.com/2013/08/finding-and-removing-large-files-in-git.html

BRANCH_LIST=$@


filesAndSizes() {

	# Get all files recursively in this revision
	git ls-tree -lr $1 | \
	# Remove all but the filesize
	cut -c54- | \
	# Remove ones who start with empty, they are
	# less than a million bytes
	grep -v '^ '

}

getAllFilesAndSizes() {

	for REVISION in $1; do

		filesAndSizes $REVISION

	done

}

REVISIONS=`git rev-list $BRANCH_LIST`

getAllFilesAndSizes $REVISIONS | \
sort -u | \
perl -e '
  while (<>) {
    chomp;
    @stuff=split("\t");
    $sums{$stuff[1]} += $stuff[0];
  }
  print "$sums{$_} $_\n" for (keys %sums);
' | \
sort -rn