Counts and groups files by file type (extension).

histo

#!/bin/bash
#
# Usage: histo [path]
#
# Counts and groups files by file type (extension).
#
# Example:
# histo /etc
#   ...
#   bash    5
#   db      5
#   pem     5
#   local   6
#   xml     6
#   menu    8
#   csh     10
#   repo    12
#   txt     19
#   sh      22
#   desktop 26
#   ctb     29
#   tti     29
#   kti     67
#   ttb     86
#   ktb     97
#   conf    351
#   pp      396
#   
#
# Implementation:
# Finds all files in path (default: current directory ) and groups them by filetype. Type detection is done via extension.
#
# Needs Bash > 4.0
#


if [ "$1" == "" ]
then
  root=.
else
  root=$1
fi

function file_type_by_extension()
{
    # http://stackoverflow.com/a/1403489
    fullpath="$1"
    filename="${fullpath##*/}"                      # Strip longest match of */ from start
    dir="${fullpath:0:${#fullpath} - ${#filename}}" # Substring from 0 thru pos of filename
    base="${filename%.[^.]*}"                       # Strip shortest match of . plus at least one non-dot char from end
    ext="${filename:${#base} + 1}"                  # Substring from len of base thru end
    if [[ -z "$base" && -n "$ext" ]]; then          # If we have an extension and no base, it's really the base
        base=".$ext"
        ext=""
    fi
    echo $ext
}

function file_type_via_file_util()
{
  filename="$1"
  file -b "$filename"
}


function print_histo()
{
  histo=$1
  for ft in "${!histo[@]}"
  do
    if [ ! -z "${histo["$ft"]}" ]
    then
      echo -e $ft\\t${histo["$ft"]}
    fi
  done|sort -t$'\t' -b -n --key=2,2
}


declare -A histo

while read filename
do
  # Change to file_type_via_file_util to use the 'file' util to get the filetype
  ft=$(file_type_by_extension "$filename")
  if [[ ! -z "$ft" ]]
  then
          if [[ -z ${histo["$ft"]} ]]
          then
            histo["$ft"]=1
          else
            histo["$ft"]=$(( ${histo["$ft"]} + 1 ))
          fi
  fi
done < <(find $root -type f)


print_histo $histo