andykingking

def sørensen_index(string_a, string_b)
  matches_a = get_bigrams string_a.dup
  matches_b = get_bigrams string_b.dup
  similarities = matches_a & matches_b
  sum_bigrams = matches_a.count + matches_b.count
  2 * similarities.count / sum_bigrams.to_f
end

def get_bigrams(str)
  bigrams = []

andykingking

#!/bin/bash

# output all files in index that haven't been garbage collected
git fsck --cache --unreachable $(git for-each-ref --format="%(objectname)") > badfiles

# output all files by showing them via sub-hash
FILENUM=1
cat badfiles | cut -c 18-24 | while read cur
do
  git show $cur > $FILENUM