Question

我正在尝试使用awk来转动文件。输入文件：

FA-2D_006 10000090fa180e49
FA-2D_011 10000090fa180e49
FA-3D_004 10000090fa180e49
FA-4D_005 10000090fa180e49
FA-2D_004 20010090fa180e49
FA-2D_008 20010090fa180e49
FA-3D_004 20010090fa180e49
FA-1D_006 20020090fa180e49
FA-4D_004 20020090fa180e49
FA-1D_006 20030090fa180e49
FA-4D_004 20030090fa180e49
FA-2D_006 20040090fa180e49
FA-2D_009 20040090fa180e49
FA-3D_005 20040090fa180e49
FA-1D_006 10000090fa180e48
FA-1D_011 10000090fa180e48
FA-2D_006 10000090fa180e48
FA-3D_005 10000090fa180e48
FA-4D_006 10000090fa180e48
FA-1D_004 20010090fa180e48
FA-2D_006 20010090fa180e48
FA-2D_011 20010090fa180e48
FA-3D_004 20010090fa180e48
FA-3D_006 20010090fa180e48
FA-4D_005 20010090fa180e48
FA-1D_006 20020090fa180e48
FA-2D_004 20020090fa180e48
FA-2D_010 20020090fa180e48
FA-3D_004 20020090fa180e48
FA-4D_004 20020090fa180e48
FA-3D_005 20030090fa180e48
FA-3D_007 20030090fa180e48
FA-1D_005 20040090fa180e48

期望的输出：

-----------------------------
FA-1D_004   20010090fa180e48
-----------------------------
FA-1D_005   20040090fa180e48
-----------------------------
FA-1D_006   10000090fa180e48
            20020090fa180e48
            20020090fa180e49
            20030090fa180e49
-----------------------------
FA-1D_011   10000090fa180e48
-----------------------------
FA-2D_004   20020090fa180e48
            20010090fa180e49
-----------------------------
FA-2D_006   10000090fa180e48
            10000090fa180e49
            20010090fa180e48
            20040090fa180e49
-----------------------------
FA-2D_008   20010090fa180e49
-----------------------------
FA-2D_009   20040090fa180e49
-----------------------------
FA-2D_011   20010090fa180e48
-----------------------------

FA-2D_011   10000090fa180e49
            20010090fa180e48
-----------------------------
FA-3D_004   10000090fa180e49
            20010090fa180e49
            20010090fa180e48
            20020090fa180e48
-----------------------------
FA-3D_005   10000090fa180e48
            20040090fa180e49
            20030090fa180e48
-----------------------------
FA-3D_006   20010090fa180e48
-----------------------------
FA-3D_007   20030090fa180e48
-----------------------------
FA-4D_004   20020090fa180e49
            20030090fa180e49
            20020090fa180e48    
-----------------------------
FA-4D_005   10000090fa180e49
            20010090fa180e48
-----------------------------
FA-4D_006   10000090fa180e48
-----------------------------

请知道如何使用awk创建枢轴以形成所需的输出。

Answer 1

如果订单无关紧要

以下是单行：

awk '{k=$1 FS $2; if(!(k in t)){a[$1]=($1 in a? a[$1] RS sprintf("%*s",length($1)+1,"") :"")$2; t[k]}}END{s=sprintf("%0*s\n", length(k),""); gsub(/0/,"-",s); for(i in a)print s i,a[i] }' file

如果添加 GNU awk ，您将获得正确的订单，

You may try here by pasting given data, in stdin tab

BEGIN{
    PROCINFO["sorted_in"]="@ind_str_asc"
}

更好的可读性：

awk 'BEGIN{
           PROCINFO["sorted_in"]="@ind_str_asc"
     }
     {
        k=$1 FS $2; 
        if(!(k in t))
        {
           a[$1]=($1 in a? a[$1] RS sprintf("%*s",length($1)+1,"") :"")$2; 
           t[k]
        }
     }
  END{
         s=sprintf("%0*s\n", length(k),""); 
         gsub(/0/,"-",s); 
         for(i in a)print s i,a[i] 
     }
    ' file

的输入

$ cat file FA-2D_006 10000090fa180e49 FA-2D_011 10000090fa180e49 FA-3D_004 10000090fa180e49 FA-4D_005 10000090fa180e49 FA-2D_004 20010090fa180e49 FA-2D_008 20010090fa180e49 FA-3D_004 20010090fa180e49 FA-1D_006 20020090fa180e49 FA-4D_004 20020090fa180e49 FA-1D_006 20030090fa180e49 FA-4D_004 20030090fa180e49 FA-2D_006 20040090fa180e49 FA-2D_009 20040090fa180e49 FA-3D_005 20040090fa180e49 FA-1D_006 10000090fa180e48 FA-1D_011 10000090fa180e48 FA-2D_006 10000090fa180e48 FA-3D_005 10000090fa180e48 FA-4D_006 10000090fa180e48 FA-1D_004 20010090fa180e48 FA-2D_006 20010090fa180e48 FA-2D_011 20010090fa180e48 FA-3D_004 20010090fa180e48 FA-3D_006 20010090fa180e48 FA-4D_005 20010090fa180e48 FA-1D_006 20020090fa180e48 FA-2D_004 20020090fa180e48 FA-2D_010 20020090fa180e48 FA-3D_004 20020090fa180e48 FA-4D_004 20020090fa180e48 FA-3D_005 20030090fa180e48 FA-3D_007 20030090fa180e48 FA-1D_005 20040090fa180e48

会导致 - 使用GNU awk：

-------------------------- FA-1D_004 20010090fa180e48 -------------------------- FA-1D_005 20040090fa180e48 -------------------------- FA-1D_006 20020090fa180e49 20030090fa180e49 10000090fa180e48 20020090fa180e48 -------------------------- FA-1D_011 10000090fa180e48 -------------------------- FA-2D_004 20010090fa180e49 20020090fa180e48 -------------------------- FA-2D_006 10000090fa180e49 20040090fa180e49 10000090fa180e48 20010090fa180e48 -------------------------- FA-2D_008 20010090fa180e49 -------------------------- FA-2D_009 20040090fa180e49 -------------------------- FA-2D_010 20020090fa180e48 -------------------------- FA-2D_011 10000090fa180e49 20010090fa180e48 -------------------------- FA-3D_004 10000090fa180e49 20010090fa180e49 20010090fa180e48 20020090fa180e48 -------------------------- FA-3D_005 20040090fa180e49 10000090fa180e48 20030090fa180e48 -------------------------- FA-3D_006 20010090fa180e48 -------------------------- FA-3D_007 20030090fa180e48 -------------------------- FA-4D_004 20020090fa180e49 20030090fa180e49 20020090fa180e48 -------------------------- FA-4D_005 10000090fa180e49 20010090fa180e48 -------------------------- FA-4D_006 10000090fa180e48

Answer 2

关注awk可能对您有帮助，它会通过从第一个字段的第二个字符串（如1D或2D等进行排序来为您提供输出：

sort -t"-" -k1.1 Input_file | awk -v s1="-----------------------------" '{a[$1]=a[$1]? a[$1] RS "\t\t" $NF:$NF} !b[$1]++{c[++i]=$1} END{for(j=1;j<=i;j++){print s1 RS c[j]"\t"a[c[j]]}}'

现在添加一种非单线形式的解决方案：

sort -t"-" -k1.1  Input_file |
awk -v s1="-----------------------------" '
{
  a[$1]=a[$1]? a[$1] RS "\t\t" $NF:$NF
}
!b[$1]++{
  c[++i]=$1
}
END{
  for(j=1;j<=i;j++){
    print s1 RS c[j]"\t"a[c[j]]}
}'

输出如下：

-----------------------------
FA-1D_004       20010090fa180e48
-----------------------------
FA-1D_005       20040090fa180e48
-----------------------------
FA-1D_006       10000090fa180e48
                20020090fa180e48
                20020090fa180e49
                20030090fa180e49
-----------------------------
FA-1D_011       10000090fa180e48
-----------------------------
FA-2D_004       20010090fa180e49
                20020090fa180e48
-----------------------------
FA-2D_006       10000090fa180e48
                10000090fa180e49
                20010090fa180e48
                20040090fa180e49
-----------------------------
FA-2D_008       20010090fa180e49
-----------------------------
FA-2D_009       20040090fa180e49
-----------------------------
FA-2D_010       20020090fa180e48
-----------------------------
FA-2D_011       10000090fa180e49
                20010090fa180e48
-----------------------------
FA-3D_004       10000090fa180e49
                20010090fa180e48
                20010090fa180e49
                20020090fa180e48
-----------------------------
FA-3D_005       10000090fa180e48
                20030090fa180e48
                20040090fa180e49
-----------------------------
FA-3D_006       20010090fa180e48
-----------------------------
FA-3D_007       20030090fa180e48
-----------------------------
FA-4D_004       20020090fa180e48
                20020090fa180e49
                20030090fa180e49
-----------------------------
FA-4D_005       10000090fa180e49
                20010090fa180e48
-----------------------------
FA-4D_006       10000090fa180e48

使用awk命令的数据透视表

2 个答案: