#!/bin/ksh
# The awk on Mac OS X Version 10.7.5 does not meet POSIX/UNIX requirements for
# handing multibyte characters (it processes bytes instead of characters) at
# least in the length() and substr() functions.  This problem should be easy to
# handle in awk, but this script is written entirely as a ksh script which does
# handle multibyte characters correctly.  (The bash on OS X Version 10.7.5 also
# handles multibyte characters correctly and, although this script uses many
# features that are not defined by the standards, this script works both with
# ksh and bash on OS X.  If using this script on another system, you will need
# to use a 1993 or later version of ksh.)

# Read chinese string.
while IFS="" read -r c
do      # Read corresponding Chinese pinyin string with tone marks.
        IFS="" read -r cp <&3
        # Strip a trailing space character class character from each string, if
        # there is one.
        c=${c%[[:space:]]}
        cp=${cp%[[:space:]]}
        # Is there a tone mark at the end of the Chinese pinyin string?
        if [[ ${cp:$((${#cp} - 1))} != [[:digit:]] ]]
        then    # No.  Add "0" as a tone mark.
                cp="${cp}0"
        fi
        # Strip everything but tone marks from the Chinese pinyin string.
        cp=${cp//[![:digit:]]/}
        # Print the Chinese characters with their corresponding tone marks.
        sep=""  # No separator for first character pair.
        for ((i = 0; i < ${#cp}; i++))
        do      printf "%s%s,%s" "$sep" "${c:$i:1}" "${cp:$i:1}"
                sep="," # Separator for all following character pairs.
        done
        # Add the trailing newline.
        echo
done < Word_list_1 3< Word_list_2