encoding.bash

#!/bin/bash

# Validates utf-8 input
function uu() {
  iconv --from-code=utf-8 --to-code=utf-8
}

# Converts UTF-8 -> ISO-8859-1
function ui() {
  iconv --from-code=utf-8 --to-code=iso-8859-1
}

# Converts ISO-8859-1 -> UTF-8
function iu() {
  iconv --from-code=iso-8859-1 --to-code=utf-8
}

# All that follows assume a unicode environment
if [[ 'fr_FR.UTF-8' != $LANG ]]; then
  exit 1
fi


echo UTF-8 encoding
echo -n é | uu | hexdump

echo ISO-8859-1 encoding
echo -n é | uu | ui | hexdump

echo Identity
echo -n é | ui | iu | hexdump

echo Misinterpret UTF-8 bytes as ISO-8859-1
echo -n é | iu | hexdump # 'é'