这里有一些我找到的简单有效的解决方案：
http://www.catonmat.net/blog/set-operations-in-unix-shell-simplified/
你需要使用其中一个“集合补集”bash命令。100MB的文件可以在几秒钟或几分钟内解决。
集合成员。
$ grep -xc 'element' set # outputs 1 if element is in set
# outputs >1 if set is a multi-set
# outputs 0 if element is not in set
$ grep -xq 'element' set # returns 0 (true) if element is in set
# returns 1 (false) if element is not in set
$ awk '$0 == "element" { s=1; exit } END { exit !s }' set
# returns 0 if element is in set, 1 otherwise.
$ awk -v e='element' '$0 == e { s=1; exit } END { exit !s }'
集合相等性
$ diff -q <(sort set1) <(sort set2) # returns 0 if set1 is equal to set2
# returns 1 if set1 != set2
$ diff -q <(sort set1 | uniq) <(sort set2 | uniq)
# collapses multi-sets into sets and does the same as previous
$ awk '{ if (!($0 in a)) c++; a[$0] } END{ exit !(c==NR/2) }' set1 set2
# returns 0 if set1 == set2
# returns 1 if set1 != set2
$ awk '{ a[$0] } END{ exit !(length(a)==NR/2) }' set1 set2
# same as previous, requires >= gnu awk 3.1.5
集合基数
$ wc -l set | cut -d' ' -f1
$ wc -l < set
$ awk 'END { print NR }' set
子集测试
$ comm -23 <(sort subset | uniq) <(sort set | uniq) | head -1
# outputs something if subset is not a subset of set
# does not putput anything if subset is a subset of set
$ awk 'NR==FNR { a[$0]; next } { if !($0 in a) exit 1 }' set subset
# returns 0 if subset is a subset of set
# returns 1 if subset is not a subset of set
集合并
$ cat set1 set2
$ awk 1 set1 set2
$ cat set1 set2 ... setn
$ cat set1 set2 | sort -u
$ sort set1 set2 | uniq
$ awk '!a[$0]++'
集合交
$ comm -12 <(sort set1) <(sort set2)
$ grep -xF -f set1 set2
$ sort set1 set2 | uniq -d
$ join <(sort -n A) <(sort -n B)
$ awk 'NR==FNR { a[$0]; next } $0 in a' set1 set2
集合的补集
$ comm -23 <(sort set1) <(sort set2)
$ grep -vxF -f set2 set1
$ sort set2 set2 set1 | uniq -u
$ awk 'NR==FNR { a[$0]; next } !($0 in a)' set2 set1
设置对称差集
$ comm -3 <(sort set1) <(sort set2) | sed 's/\t//g'
$ comm -3 <(sort set1) <(sort set2) | tr -d '\t'
$ sort set1 set2 | uniq -u
$ cat <(grep -vxF -f set1 set2) <(grep -vxF -f set2 set1)
$ grep -vxF -f set1 set2; grep -vxF -f set2 set1
$ awk 'NR==FNR { a[$0]; next } $0 in a { delete a[$0]; next } 1;
END { for (b in a) print b }' set1 set2
幂集
$ p() { [ $# -eq 0 ] && echo || (shift; p "$@") |
while read r ; do echo -e "$1 $r\n$r"; done }
$ p `cat set`
设置笛卡尔积
$ while read a; do while read b; do echo "$a, $b"; done < set1; done < set2
$ awk 'NR==FNR { a[$0]; next } { for (i in a) print i, $0 }' set1 set2
不相交集合测试
$ comm -12 <(sort set1) <(sort set2) # does not output anything if disjoint
$ awk '++seen[$0] == 2 { exit 1 }' set1 set2 # returns 0 if disjoint
# returns 1 if not
空集测试
$ wc -l < set # outputs 0 if the set is empty
# outputs >0 if the set is not empty
$ awk '{ exit 1 }' set # returns 0 if set is empty, 1 otherwise
最低要求
$ head -1 <(sort set) # outputs the minimum element in the set
$ awk 'NR == 1 { min = $0 } $0 < min { min = $0 } END { print min }'
最大值
$ tail -1 <(sort set) # outputs the maximum element in the set
$ awk '$0 > max { max = $0 } END { print max }'
grep的 man 页面。 - Cyrus