Script num=c3=a9ro 4

#!/bin/bash
####################################################################
# Name:
# decode_headers
#
# Description:
# Script used for decoding RFC 2047 MIME encoded headers.
#
# Example:
# decode_headers <<POTIRON
# Message-ID: <c5a9-1@part.org>
# From: arvo@part.org (=?ASCII?Q?Arvo?= =?L1?Q?=20?= =?UTF-8?Q?P=C3=A4rt?=)
# To: =?Latin1?Q?Fr=E9d=E9ric_Chopin?= <fred@chopin.org>,
# =?Latin2?Q?Anton=EDn_Dvo=F8=E1k?= <anton@dvorak.org>
# Cc: Arvo =?UTF-8?Q?P=C3=A4rt?= <arvo@part.org>
# References: <A65R-4d@chopin.org> <c5a7-3@part.org>
# <A72Q-5a@chopin.org>
# In-Reply-To: <A72Q-5a@chopin.org>
# Subject: Re: Going to =?Shift-JIS?B?k4yLngo=?= (Tokyo) =?UTF-8?B?zpEK?=
# =?UTF-8?B?zrjOrs69zrEK?= (Athens) and =?ISO-8859-5?Q?=BC=DE=E1=DA?=
# =?ISO-8859-5?Q?=D2=D0?= (Moscow)
# POTIRON
# ->
# Message-ID: <c5a9-1@part.org>
# From: arvo@part.org (Arvo Pärt)
# To: Frédéric Chopin <fred@chopin.org>, Antonín Dvořák <anton@dvorak.org>
# Cc: Arvo Pärt <arvo@part.org>
# References: <A65R-4d@chopin.org> <c5a7-3@part.org> <A72Q-5a@chopin.org>
# In-Reply-To: <A72Q-5a@chopin.org>
# Subject: Re: Going to 東京 (Tokyo) Αθήνα (Athens) and Москва (Moscow)
####################################################################

#
# The following constants should be adapted for your system.
# For example, the executable base64 could be at /usr/local/bin instead
# of /usr/bin, and it could require parameter -D instead of -d.
#
CUT="/usr/bin/cut"
TR="/usr/bin/tr"
ICONV="/usr/bin/iconv"
if [ "$(uname)" = "Linux" ]; then
# GNU/Linux
DECODE_QP="/usr/bin/qprint -d"
DECODE_B64="/usr/bin/base64 -d"
else
# MacOS X
DECODE_QP="/usr/local/bin/qprint -d"
DECODE_B64="/usr/bin/base64 -D"
fi

#
# This script uses the following global variables
# VARY
# used when a function has to return a string and not only a number
# DECODED_LINE
# The current state of a header being currently decoded
# STATUS
# Has three possible values:
# - "none" at the beginning of a new header
# - "decoded-word" after a correctly decoded MIME part
# - "normal" after any other string
#
VARY=""
DECODED_LINE=""
STATUS="none"

#
# Function: usage
#
usage()
{
printf "Usage: %s [OPTION...] [FILE...]\n" $0
printf "Decode headers from given files for RFC 2047 MIME encodings.\n"
printf "\n"
printf "With no FILE, or when FILE is -, read standard input.\n"
printf "\n"
printf " -h, --help Give this help list\n"
exit 1
}

#
# Function: decode_word
#
# Description:
# Check that the parameter is an encoded word, then decode it and
# convert it to UTF-8.
#
# Parameter:
# A single (possibly MIME-encoded) word.
#
# Return value:
# If decoding is ok, set the result into VARY and return 0
# Otherwise return 1
#
decode_word()
{
word="$*"
###################################################################
# An encoded word contains only ASCII characters in range from
# '!' (Ascii value 0x21) to '~' (Ascii value 0x7e). This excludes
# in particular the SPACE (Ascii 0x20) and the TAB (Ascii 0x09).
#
# More specifically, it consists of five parts separated by
# question marks '?'
# 1. A character "="
# 2. The charset, e.g. "UTF-8" or "ISO-8859-1"
# 3. The encoding, B or Q in upper or lower case
# 4. The encoded text
# 5. A character "="
###################################################################

# Check that:
# - there is no character outside range from '!' to '~'
# - the 1st part is a "="
# - the 5th part is a "=" and it is the end of the string
if [ $(LANG=C expr "_$word" : '_[!-~]*$') = 0 ]; then return 1; fi
part1=$(printf "$word" | $CUT -f 1 -d '?')
part5=$(printf "$word" | $CUT -f 5- -d '?')
if [ "$part1" != "=" -o "$part5" != "=" ]; then return 1; fi

# Extract charset, encoding, and encoded text
charset=$(printf "$word" | $CUT -f 2 -d '?')
encoding=$(printf "$word" | $CUT -f 3 -d '?')
encoded=$(printf "$word" | $CUT -f 4 -d '?')

case $encoding in
B | b)
decoded=$(printf "$encoded" | $DECODE_B64 2>/dev/null)
if [ $? != 0 ]; then return 1; fi
;;
Q | q)
decoded=$(printf "$encoded" | $TR "_" " " | $DECODE_QP 2>/dev/null)
if [ $? != 0 ]; then return 1; fi
;;
*)
return 1
;;
esac

VARY=$(printf "$decoded" | $ICONV -f $charset -t UTF-8 2>/dev/null)
return $?
}

#
# Function: add_word
#
# Description:
# Try to decode a new word, and update DECODED_LINE and STATUS
# depending on the result and the previous STATUS.
#
# Parameter:
# A single (possibly MIME-encoded) word.
#
# Return value:
# None
#
# Side effects:
# Change DECODED_LINE and STATUS
#
add_word()
{
word="$*"
prefix=""
suffix=""

# Manage possible initial and final parentheses
while [ $(LANG=C expr "_$word" : '_[()]') != 0 ]; do
prefix="${prefix}${word:0:1}"
word="${word:1}"
done
while [ $(LANG=C expr "_$word" : '_.*[()]$') != 0 ]; do
suffix="${word: -1}${suffix}"
word="${word:0: -1}"
done

if decode_word "$word"; then
word="${prefix}${VARY}${suffix}"
if [ "$STATUS" = "normal" ]; then
DECODED_LINE="${DECODED_LINE} "
elif [ "$STATUS" != "none" -a -n "${prefix}" ]; then
DECODED_LINE="${DECODED_LINE} "
fi
DECODED_LINE="${DECODED_LINE}${word}"
if [ -n "${suffix}" ]; then
STATUS="normal"
else
STATUS="decoded-word"
fi
else
word="${prefix}${word}${suffix}"
if [ "$STATUS" != "none" ]; then
DECODED_LINE="${DECODED_LINE} "
fi
DECODED_LINE="${DECODED_LINE}${word}"
STATUS="normal"
fi
}

#
# Function: flush_line
#
# Description:
# Before beginning to manage a new header, or just before ending
# the script, print the pending DECODED_LINE if any.
#
# Parameter:
# None
#
# Return value:
# None
#
# Side effects:
# Print things to stdout
# Change DECODED_LINE and STATUS
#
flush_line()
{
if [ -n "${DECODED_LINE}" ]; then
printf "%s\n" "${DECODED_LINE}"
DECODED_LINE=""
STATUS="none"
fi
}

#
# Function: manage_line
#
# Description:
# Manage a new line, which can be either the beginning or the
# continuation of a mail/news header.
# This function prints the previous line if this is a new one,
# then it adds successive parts to the new DECODED_LINE, while
# updating STATUS as needed.
#
# Parameter:
# An input line.
#
# Return value:
# None
#
# Side effects:
# Print things to stdout
# Change DECODED_LINE and STATUS
#
manage_line()
{
line="$*"

# Is it a continuation line?
if [ $(LANG=C expr "_$line" : "_[ \t]") = 0 ]; then
# No: new header
flush_line
fi

for word in $line; do
add_word "$word"
done
}

#
# Function: manage_file
#
# Description:
# Call manage_line for each line in a given file
#
# Parameter:
# A file name, or "-" for stdin
#
# Return value:
# None
#
# Side effects:
# Same as manage_line
#
manage_file()
{
file=${1--} # POSIX-compliant; ${1:--} can be used either.
while IFS= read -r line; do
manage_line "$line"
done < <(cat -- "$file")
}

#
# Parse arguments for -h or --help
#
for i in "$@"; do
case $i in
-h | --help)
usage
;;
-)
;;
-*)
printf "Unknown argument '%s'\n" "$i"
usage
;;
esac
done

#
# Main loop.
# Call manage_file for each filename in parameters,
# then print the last pending DECODED_LINE if any.
#
if [ "$*" = "" ]; then
manage_file "-"
else
for file in "$@"; do
manage_file "$file"
done
fi
flush_line

exit 0
--
Olivier Miakinen