linux 中删除除第一次匹配特定字符串所在行之外的所有行

 

001、shell实现

root@PC1:/home/test2# ls
test.txt
root@PC1:/home/test2# cat test.txt   ## 测试数据， 删除第一次匹配xpehh以外的所有匹配xpehh的行
01 ee ff
02 ee de
03 dd ee
04 jj xpehh
05 jj kk
06 ee de
07 mm xpehh
08 ff ww
09 jj kk
10 mm xpehh
11 dd ee
root@PC1:/home/test2# awk 'BEGIN{idx = 0} {if($0 ~ /xpehh/ && idx == 0 || $0 !~ /xpehh/) {print $0}; if($0 ~ /xpehh/) {idx++}}' test.txt
01 ee ff
02 ee de
03 dd ee
04 jj xpehh
05 jj kk
06 ee de
08 ff ww
09 jj kk
11 dd ee

 

002、python实现

root@PC1:/home/test2# ls
test.py  test.txt
root@PC1:/home/test2# cat test.txt
01 ee ff
02 ee de
03 dd ee
04 jj xpehh
05 jj kk
06 ee de
07 mm xpehh
08 ff ww
09 jj kk
10 mm xpehh
11 dd ee
root@PC1:/home/test2# cat test.py
#!/usr/bin/python

in_file = open("test.txt", "r")
out_file = open("result.txt", "w")
lines = in_file.readlines()

idx = 0
for i in lines:
    if idx == 0 and "xpehh" in i or "xpehh" not in i:
        out_file.write(i)
    if "xpehh" in i:
        idx = idx + 1

in_file.close()
out_file.close()
root@PC1:/home/test2# python test.py
root@PC1:/home/test2# ls
result.txt  test.py  test.txt
root@PC1:/home/test2# cat result.txt    ## 结果文件
01 ee ff
02 ee de
03 dd ee
04 jj xpehh
05 jj kk
06 ee de
08 ff ww
09 jj kk
11 dd ee

 

003、R实现

dir()
dat <- read.table("test.txt")
result <- vector()
idx = 0
for (i in 1:nrow(dat)) {
  if (sum(grepl("xpehh", dat[i,])) != 0 & idx == 0 | 
      sum(grepl("xpehh", dat[i,])) == 0) {
      result <- c(result, i)
  }
  if(sum(grepl("xpehh", dat[i,])) != 0){
    idx = idx + 1
  }
}
final <- dat[result,]
final