方案一:
#!/bin/sh
#定義源文件和臨時文件
srcfile=word.txt
tempfile_words=tempfile_words
tempfile_words_uniq=tempfile_words_uniq
#取出所有單詞,存入臨時文件$tempfile_words,一行一個單詞
#去除$tempfile_words中重複單詞,並把換行符替換爲空格,存入臨時文件$tempfile_words_uniq
tr "[\015]" "[\n]"<$srcfile|sed 's/[^0-9a-zA-Z ]*\([0-9a-zA-Z]*\)[^0-9a-zA-Z]*/\1\n/g'|sed '/^$/d'>$tempfile_words
sort $tempfile_words|uniq|tr "[\n]" "[ ]">$tempfile_words_uniq
#遍歷所有單詞,統計數目
words=$(cat $tempfile_words_uniq)
for word in $words
do
word_num=$(grep $word $tempfile_words|wc -l)
echo $word $word_num
done
方案二:
tr -s "\t| " "\n" < filename | sort | uniq -c | sort -n -k 1 -r