Hackzine

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102

#!/bin/bash
 
#
# FileName cleaner - v0.1
# Replaces all special chars from filenames, allowing only use of:
# letters, numbers, underscore, dash, dot.
# Converts also UTF-8 characters to their "similar" ASCII-128 char.
# 
# (c)2009 Samuele ~redShadow~ Santi - <redshadow@hackzine.org> - Under GPL
#
# TODO find a way to remove in-name extra dots.
#       We don't just need to leave the last dot, since there are files
#       such as .tar.gz and .tar.bz2 with "double-extension"
#
# TODO make it work recursively on dirs (..a bit dangerous..)
# 
# ATTENTION:  Do NOT use on complex paths (eg. containing the '/' symbol) since
#             behaviour could be different from expected (in a future version,
#             it will be supported, though)
#
 
#
# Leave only allowed chars, removing UTF-8 chars etc.
#
function allowedchars(){
  #sed "s/[^A-Za-z0-9_\\.\\-]\{1,\}/_/g"
  # WE NEED ALL LETTERS LISTING TO AVOID PROBLEMS WITH ACCENTED LETTERS
  # (included in A-Za-z set when using utf-8)
 
  UC_ST="ÀÁÂÃÄÅĂĄÇĆČĎĐàáâãäåăąçćčďđÈÉÊËĘĚĞÌÍÎÏİĹĽŁèéêëęěğìíîïıĺľłÑŃŇÒÓÔÕÖØŐŔŘŚŞŠñńňòóôõöøőŕřśşšŢŤÙÚÛŲÜŮŰÝŹŻŽţťùúûųüůűýÿźżž"
  UC_RP="AAAAAAAACCCDDaaaaaaaacccddEEEEEEGIIIIILLLeeeeeegiiiiilllNNNOOOOOOORRSSSnnnooooooorrssTTUUUUUUUUYZZZttuuuuuuuyyzzz"
 
  sed "y/àèìòùÀÈÌÒÙ/aeiouAEIOU/" |  # Replace accented
  sed "y/$UC_ST/$UC_RP/" |          # Replace UTF-8
  biletters |
  sed "s/[^ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\\._0-9\\-]\\+/_/g" # replace strange chars
}
 
#
# Convert biletter chars to their transliterations
#
function biletters(){
  sed "s/Æ/AE/" |
  sed "s/Œ/CE/" |
  sed "s/æ/ae/" |
  sed "s/œ/ce/" |
  sed "s/ß/ss/"
}
 
#
# Remove double-dots from filename
#
function nodoubledots(){
  # no double dot           # no trailing dot
  sed "s/[\\.]\{2,\}/./g" | sed "s/\\.*\$//"
  #cat
}
 
#
# Convert to lower-case the file extension
# TODO write this
#
function lowerext(){
  #FN="`cat`"
  #FBN="$( echo $FN | sed "s/\(\.*\)\.\([^\.]*\)$/\1/" )"
  #FEX="$( echo $FN | sed "s/\.*\.\([^\.]*\)\$/\1/" | tr "[:upper:]" "[:lower:]" )"
  #echo -e "NAME=$FBN\nEXT=$FEX"
  cat
}
 
function die_subdir(){
  echo -e "@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@\n"
  echo -e " \033[1;31mATTENTION\033[0m:  Do NOT use on complex paths (eg. containing the '/' symbol) since"
  echo "             behaviour could be different from expected one."
  echo "             It will probably supported in a future version, though"
  echo -e "\n@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@"
  exit 1
}
 
#
# Main script loop..
#
if [ "$1" == "" ]; then
  echo "Usage: $0 <files...>"
  echo "Clean filenames of specified files/directories"
else
  for OLDNAME in "$@"; do
    echo "$OLDNAME" | grep -v / &>/dev/null || die_subdir
    echo -en " * \e[1;33m\"$OLDNAME\"\e[0m ... "
    NEWNAME="` echo "$OLDNAME" | allowedchars | nodoubledots | lowerext `"
    if [ "$NEWNAME" != "$OLDNAME" ]; then
      echo -e "New name: \e[1;31m\"$NEWNAME\"\e[0m"
      if [ ! -e "$NEWNAME" ]; then
        mv "$OLDNAME" "$NEWNAME"
      else
        echo -e "   >> \e[1;31mATTENTION!\e[0m A file with the same name already exists (not overwriting)"
      fi
    else
      echo -e "\e[1;32mFilename is OK\e[0m"
    fi
  done
fi