使用来自另一个文件的行范围从单独文件中的字符串替换每 2 nth

Question

我有三个文件：

0.txt e 0-1.txt 与以下内容相同：

"#sun\t",
"car_snif = house.group_tree(home_cool)\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree(home_cool)\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree(home_cool)\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree(home_cool)\t",
"machine(shoes_shirt.shop)\t",
"#sun\t",
"car_snif = house.group_tree(home_cool)\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree(home_cool)\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree(home_cool)\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree(home_cool)\t",

和下面的源文件1.txt：

(food, apple,)(bag, tortoise,)
(sky, cat,)(sun, sea,)
(car, shape)(milk, market,)
(man, shirt)(hair, life)
(dog, big)(bal, pink)

对于0.txt，我想用1 nth 1.txt 行替换从home_cool 发生的每一个2 nth，但只使用最多第二个1.txt 的行（然后是sed -n '1,2p'），这样我的2.txt 输出如下：

"#sun\t",
"car_snif = house.group_tree((food, apple,)(bag, tortoise,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((food, apple,)(bag, tortoise,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((sky, cat,)(sun, sea,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((sky, cat,)(sun, sea,))\t",
"machine(shoes_shirt.shop)\t",
"#sun\t",
"car_snif = house.group_tree((food, apple,)(bag, tortoise,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((food, apple,)(bag, tortoise,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((sky, cat,)(sun, sea,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((sky, cat,)(sun, sea,))\t",

当在2.txt 完成该过程时，我想用 1 nth 1.txt 行替换从 home_cool 到 0-1.txt 发生的所有 2 nth使用1.txt 的第三行（然后是sed -n '3,5p'），这样我的3.txt 输出如下：

"#sun\t",
"car_snif = house.group_tree((car, shape)(milk, market,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((car, shape)(milk, market,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((man, shirt)(hair, life))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((man, shirt)(hair, life))\t",
"machine(shoes_shirt.shop)\t",
"#sun\t",
"car_snif = house.group_tree((dog, big)(bal, pink))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((dog, big)(bal, pink))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((car, shape)(milk, market,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((car, shape)(milk, market,))\t",

通过下面的行，我可以将home_cool 替换为0.txt 分为两个步骤（第一步sed -n '1,2p' 和第二步sed -n '3,5p'）。但是我想把第一步保存在2.txt，第二步保存在3.txt：

awk 'NR==FNR {a[NR]=$0; n=NR; next}/home_cool/ { gsub("home_cool", a[int((++i-1)%(n*2)/2)+1])}1' <(cat 1.txt | tee >(sed -n '1,2p') >(sed -n '3,5p')) 0.txt >> 2.txt

所以我真正想要的是（下面的伪代码）：

awk 'NR==FNR {a[NR]=$0; n=NR; next}/home_cool/ { gsub("home_cool", a[int((++i-1)%(n*2)/2)+1])}1' <(cat 1.txt | tee >(sed -n '1,2p') >(sed -n '3,5p')) | "to sed -n '1,2p' make" 0.txt >> 2.txt | "to sed -n '3,5p' make" 0-1.txt >> 3.txt

我怎样才能通过维护一个命令行来做到这一点而不中断几个孤立的 awk 片段？

注意：问题的标题可能应该是“多个输入，相同的过程，不同的输出”

Answer 1

这行得通：

awk \
'FNR==1 {++f}
f==1 {a[i++]=$0}
f==2 {if ($0~/home_cool/) {gsub(/home_cool/, a[int(j++/2)%2]) }; print > "2.txt"}
f==3 {if ($0~/home_cool/) {gsub(/home_cool/, a[int(k++/2)%3 + 2]) }; print > "3.txt"}' \
    1.txt 0.txt 0-1.txt

硬编码"2.txt" 和"3.txt" 的替代方案包括：

• 使用以-v outfile1=2.txt -v outfile2=2.txt 分配的变量
• 将它们替换为outfile，并使用此参数列表：1.txt outfile=2.txt 0.txt outfile=3.txt 0-1.txt
• 将它们替换为ARGV[4] 和ARGV[5]，添加f==4 {exit} 行，并使用此参数列表：1.txt 0.txt 0-1.txt 2.txt 3.txt

注意事项：

• 如果给定的文件是空的，它不会导致f 增加，并相应地破坏。在 gawk 中，可以使用 ENDFILE 代替。看到这个答案：How to get the filenumber that is being processing by an awk script?

Answer 2

参考OP的previous Q&A ...

虽然我们当然可以修改之前的问答（已接受的答案）以在各种输入中执行这些拆分操作，但我会通过将这个新问题分成两个单独的操作来投票支持简单性而不是复杂性，例如：

awk '... from previous Q&A ...' <(head -2 1.txt) 0.txt   > 2.txt
awk '... from previous Q&A ...' <(tail +3 1.txt) 0-1.txt > 3.txt

去掉不必要的/house_cool01/{...} 代码行变成：

awk 'NR==FNR {a[NR]=$0; n=NR; next} /home_cool/ {gsub("home_cool", a[int((i++)%(n*2)/2)+1] )} 1' <(head -2 1.txt) 0.txt   > 2.txt
awk 'NR==FNR {a[NR]=$0; n=NR; next} /home_cool/ {gsub("home_cool", a[int((i++)%(n*2)/2)+1] )} 1' <(tail +3 1.txt) 0-1.txt > 3.txt

这些生成：

$ cat 2.txt
"#sun\t",
"car_snif = house.group_tree((food, apple,)(bag, tortoise,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((food, apple,)(bag, tortoise,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((sky, cat,)(sun, sea,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((sky, cat,)(sun, sea,))\t",
"machine(shoes_shirt.shop)\t",
"#sun\t",
"car_snif = house.group_tree((food, apple,)(bag, tortoise,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((food, apple,)(bag, tortoise,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((sky, cat,)(sun, sea,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((sky, cat,)(sun, sea,))\t",

$ cat 3.txt
"#sun\t",
"car_snif = house.group_tree((car, shape)(milk, market,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((car, shape)(milk, market,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((man, shirt)(hair, life))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((man, shirt)(hair, life))\t",
"machine(shoes_shirt.shop)\t",
"#sun\t",
"car_snif = house.group_tree((dog, big)(bal, pink))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((dog, big)(bal, pink))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((car, shape)(milk, market,))\t",
"machine(shoes_shirt.shop)\t",
"car_snif = house.group_tree((car, shape)(milk, market,))\t",