使用任意列中的通用值合并行

使用任意列中的通用值合并行

我有一个制表符分隔的文件,如下所示,并且希望根据任何列中的匹配来合并行。列数通常为 2,但在某些情况下可能会有所不同,为 3。

输入:

AMAZON NILE 
ALASKA NILE
HELLO MY
MANGROVE AMAZON
MY NAME
IS NAME

期望的输出:

AMAZON NILE ALASKA MANGROVE
HELLO MY NAME IS

怎样才能解决这个问题呢awk

这也适用于以下文件吗?输入:

apple_bin2file       strawberry_24files
mango2files      strawberry_39files
apple_bin8file       strawberry_39files
dastool_bin6files  strawberry_40files
apple_bin6file       strawberry_40files
orange_bin004file      dastool_bin004files
orange_bin005file      dastool_bin005files
apple_bin3file       dastool_bin3files
apple_bin5file       dastool_bin5files
apple_bin6file       dastool_bin6files
apple_bin7file       dastool_bin7files
apple_bin8file       mango2files

制表符分隔格式的预期输出:

apple_bin2file strawberry_24files
mango2files strawberry_39files apple_bin8file
dastool_bin6files strawberry_40files apple_bin6file
orange_bin004file dastool_bin004files
orange_bin005file dastool_bin005files
apple_bin3file dastool_bin3files
apple_bin5file dastool_bin5files
apple_bin7file dastool_bin7files

对于那些回答的人,我很抱歉,我更新了输入文件!

答案1

使用 GNU awk

gawk '
    {
        grp = 0
        # see if any of these words already have a group
        for (i=1; i<=NF; i++) {
            if (group[$i]) {
                grp = group[$i]
                break
            }
        }
        # no words have been seen before: new group
        if (!grp) {
            grp = ++n
        }
        # if we have not seen this word, add it to the output
        for (i=1; i<=NF; i++) {
            if (!group[$i]) {
                line[grp] = line[grp] $i OFS
            }
            group[$i] = grp
        }
    }
    END {
        PROCINFO["sorted_in"] = "@ind_num_asc"
        for (n in line) {
            print line[n]
        }
    }
' input.file

第一个输入:

AMAZON NILE ALASKA MANGROVE
HELLO MY NAME IS

使用第二个输入(将输出通过管道传输到column -t):

apple_bin2file     strawberry_24files
mango2files        strawberry_39files   apple_bin8file
dastool_bin6files  strawberry_40files   apple_bin6file
orange_bin004file  dastool_bin004files
orange_bin005file  dastool_bin005files
apple_bin3file     dastool_bin3files
apple_bin5file     dastool_bin5files
apple_bin7file     dastool_bin7files

答案2

对于您给出的示例,请尝试

awk '
    {for (j=1; j<=MX; j++)  {for (i=1; i<=NF && !(m=match (LN[j], $i)); i++);
                 if (m) {$i = ""
                     break
                    }
                }
     LN[j] = LN[j] $0 " "
     if (j>MX) MX = j
    }
END {for (l in LN) print LN[l]
    }
' file3
AMAZON NILE  ALASKA  MANGROVE  
HELLO MY  NAME IS  

编辑:使用新数据,这应该有效:

awk '
        {for (j=1; j<=MX; j++)  {m = 0
                                 for (i=1; i<=NF; i++)  {if (match (LN[j], $i)) {$i = ""
                                                                                 m = 1
                                                                                }
                                                        }
                                 if (m) break
                                }
         LN[j] = LN[j] $0 OFS
         if (j>MX) MX = j
        }
END     {for (l in LN)  {gsub (/ +/, OFS, LN[l])
                         gsub (OFS"+", OFS, LN[l])
                         print LN[l]
                        }
        }
' OFS="\t" file

相关内容