awk – 在> 2个文件中查找常用元素

awk '
    FNR == NR { arr[$1,$2] = 1; next }
    { if ( arr[$1,$2] ) { arr[$1,$2]++ } }
    END { 
        for ( key in arr ) {
            if ( arr[key] != ARGC - 1 ) { continue }
            split( key,key_arr,SUBSEP )
            printf "%s %sn",key_arr[1],key_arr[2] 
        } 
    }
' file{1..3}

它产生：

"xxx" 0
"aba" 0

编辑添加打印整行的版本(请参阅注释).我添加了另一个带有相同键的数组,我保存了该行,并在printf函数中使用它.我留下旧代码评论.

awk '
    ##FNR == NR { arr[$1,$2] = 1; next }
    FNR == NR { arr[$1,$2] = 1; line[$1,$2] = $0; next }
    { if ( arr[$1,$2]++ } }
    END { 
        for ( key in arr ) {
            if ( arr[key] != ARGC - 1 ) { continue }
            ##split( key,SUBSEP )
            ##printf "%s %sn",key_arr[2] 
            printf "%sn",line[ key ] 
        } 
    }
' file{1..3}

NEW EDIT(请参阅注释)添加处理具有相同键的多行的版本.基本上我加入所有条目而不只保存一个,更改行[$1,$2] = $0行[$1,$2] =行[$1,$2](行[$1,$2]？SUBSEP：“”)$0.在打印时,我使用分隔符(SUBSEP变量)进行反向分割并打印每个条目.

awk '
    FNR == NR { 
        arr[$1,$2] = 1
        line[$1,$2] = line[$1,$2] ( line[$1,$2] ? SUBSEP : "" ) $0
        next
    }
    FNR == 1 { delete found }
    { if ( arr[$1,$2] && ! found[$1,$2]++; found[$1,$2] = 1 } }
    END { 
        num_files = ARGC -1 
        for ( key in arr ) {
            if ( arr[key] < num_files ) { continue }
            split( line[ key ],line_arr,SUBSEP )
            for ( i = 1; i <= length( line_arr ); i++ ) { 
                printf "%sn",line_arr[ i ]
            } 
        } 
    }
' file{1..3}

对于有问题的新数据,它会产生：

"xxx" 0 0
"aba" 0 0 
"aba" 0 0 1