Question

Unix在公共列上连接两个文件需要（据我所知）首先对公共列上的两个文件进行排序。如果那是正确的，那么行顺序就会丢失。我想保留第一个文件的行顺序。为此，我在第一个文件中添加一个ghost列，其中包含每行的行号。然后我将公共列上的两个文件排序，加入然后重新排序ghost列上的输出并将其删除。我提供了一个脚本来做到这一点。还有其他更好或更快的方法吗？

#!/bin/bash

input_file1=
input_file2=
output_file='/dev/stdout'
key1=
key2=
ifs_tab=0
rand=$$
key_field_type="" # flag to sort -g or -n or emtpy for numerical (-n) or general or general numeric sort (-g)
appname=`basename "$0"`

function print_help_and_exit {
    echo "Usage : $appname -1 key1 -2 key2 [-t] [-n|-g] file1 file2 [>output]"
    echo "key1: the join column from the first input file (column numbers start from 1)"
    echo "key2: the join column from the second input file"
    echo "optional flag -t uses a single tab as a field separator as opposed to a sequence of white space (which is the default)"
    echo "-n or -g : flags to be passed to sort: -n sort in numeric order, -g sort in general numeric order, default: text, leave empty"
    echo "script by Andreas Hadjiprocopis / Institute of Cancer Research, 2011"
    exit 1
}
    while getopts "1:2:o:tnh" OPTION; do
    case $OPTION in
            1)
                    key1="${OPTARG}"
                    ;;
            2)
                    key2="${OPTARG}"
                    ;;
            o)
                    output_file="${OPTARG}"
                    ;;
            t)
                    ifs_tab=1
                    ;;
            n)
                    key_field_type="-n"
                    ;;
            g)
                    key_field_type="-g"
                    ;;
            h)
                    print_help_and_exit
                    ;;
    esac
done
shift $(($OPTIND - 1))
input_file1=$1; shift
input_file2=$1; shift

if [ "$key1" == "" ] || [ "$key2" == "" ] || [ "$input_file1" == "" ] || [ "$input_file2" == "" ]; then
    echo "$appname : incorrect number of parameters" > /dev/stderr
    print_help_and_exit
fi
if [ ${ifs_tab} -eq 1 ]; then ifs1="-t$'\t'"; ifs2="-F $'\t'"; else ifs1=""; ifs2=""; fi
# note: when you do a join the output file contains the common column first, then all the columns of the first file, then all from second file

# add a new column to the beginning of the input_file1 and increment its join-column number (key1)
# then we will sort the two input files as required by join
# then we will join the two input files on the specified column numbers (key1 and key2)
# then we will sort the output according to the new column we added
# and then delete that column, output to STDOUT

let key1++
cat << EOC | sh
awk ${ifs2} '{print NR"\t"\$0}' "${input_file1}" | sort -k ${key1} ${ifs1} ${key_field_type} > /tmp/${rand}.1
sort ${ifs1} -k ${key2} ${key_field_type} "${input_file2}" > /tmp/${rand}.2
join ${ifs1} -1 ${key1} -2 ${key2} /tmp/${rand}.1 /tmp/${rand}.2 | sort ${ifs1} -k 1 -n | awk ${ifs2} '{str=\$1;for(i=3;i<=NF;i++) str=str"\t"\$i; print str}' > "${output_file}"
EOC

rm -f /tmp/${rand}.*
exit 0

Answer 1

以下是一些建议：

您无需创建临时文件。请改用process substitution。
您不需要cat << EOC | sh

您的三个命令可以合并为一个管道：

join ${ifs1} -1 ${key1} -2 ${key2} \
   <(awk ${ifs2} '{print NR"\t"$0}' "${input_file1}" | sort -k ${key1} ${ifs1} ${key_field_type}) \
   <(sort ${ifs1} -k ${key2} ${key_field_type} "${input_file2}") \
| sort ${ifs1} -k 1 -n \
| awk ${ifs2} '{str=$1;for(i=3;i<=NF;i++) str=str"\t"$i; print str}' > "${output_file}"

unix文件加入 - 如何保存行顺序？

1 个答案: