Linux 使用awk命令按列对文件中的关键词字符串计数

示例数据:

Lorem dolor sit amet consectetur
Lorem ipsum dolor sit ,
Lorem dolor sit amet ,
Lorem dolor ipsum sit !

将示例数据另存为note.txt,使用如下脚本:

awk 'NR==FNR {for(i=1;i<=NF;i++) c[i,$i]++;next} 
               {f=line=""; 
                for(i=1;i<=NF;i++) 
                  {k=i SUBSEP $i; 
                   if(k in c) 
                     {f=1; line=line sprintf("%d %s",c[k],$i); delete c[k]}; 
                   line=line "\t"} 
                   if(f) print line}' note.txt{,}

输出：

4 Lorem 3 dolor 2 sit   2 amet  1 consectetur
        1 ipsum 1 dolor 2 sit   2 ,
                1 ipsum         1 !

或者

awk '{
  for (col = 1; col <= NF; ++col) {
    ++count[col " " $col]
  }
} END {
  for (colWord in count) {
   split(colWord, s, " ")
   col=s[1]
   word=s[2]
   print col " " count[colWord] " " word
  }
}'  note.txt | sort -k1,1n -k2,2nr

输出：

1 4 Lorem
2 3 dolor
2 1 ipsum
3 2 sit
3 1 dolor
3 1 ipsum
4 2 amet
4 2 sit
5 2 ,
5 1 !
5 1 consectetur