Question

想要打印连续序列号 - 从第一个字段开始序列和结束序列，以及$ 2，substr（$ 3,1,9），substr（$ 4,4,6），$ 6，$ 8，$ 10字段的组合。输入文件未按第一列排序。

INPUT.TXT

11,abc,22-JUN-12.08:06:03,22-JUN-12.08:06:03,19-Apr-16,1,INR,RO0412,RC03,L7,,31
12,abc,22-JUN-12.08:06:03,22-JUN-12.08:06:03,19-Apr-16,1,INR,RO0412,RC03,L7,,31
13,abc,22-JUN-12.08:06:03,22-JUN-12.08:06:03,19-Apr-16,1,INR,RO0412,RC03,L7,,31
14,abc,30-JUN-12.01:06:49,30-JUN-12.01:06:49,19-Apr-16,1,INR,RO0412,RC03,L7,,29
28,abc,30-JUN-12.01:06:49,30-JUN-12.01:06:49,19-Apr-16,1,INR,RO0412,RC03,L7,,29
32,def,29-MAY-13.12:05:11,29-MAY-13.12:05:11,15-Feb-17,1350,INR,RO0213,CD,K1,,30
33,def,29-MAY-13.12:05:11,29-MAY-13.12:05:11,15-Feb-17,1350,INR,RO0213,CD,K1,,30
41,abc,20-FEB-14.11:02:37,20-FEB-14.11:02:37,31-Dec-20,650,INR,EN1113,ch650,S317,,28
50,abc,20-FEB-14.11:02:37,20-FEB-14.11:02:37,31-Dec-20,650,INR,EN1113,ch650,S317,,28
51,abc,20-FEB-14.11:02:37,20-FEB-14.11:02:37,31-Dec-20,650,INR,EN1113,ch650,S317,,28
52,abc,20-FEB-14.11:02:37,20-FEB-14.11:02:37,31-Dec-20,650,INR,EN1113,ch650,S317,,28

仅针对第一个字段尝试了此命令并获得了部分输出：

cat Input.txt | sort -k1 -t,| awk -F, 'NR==1 {a=$1;b=$1;next} ($1 != b+1){print a,"-",b; a=$1} {b=$1} END{print a,"-",b}'

11 - 14
28 - 28
32 - 33
41 - 41
50 - 52

期望的输出：

$ 2，$ 3，$ 4，$ 6，$ 8 $ 10 Start_No，End_No

abc,22-JUN-12,JUN-12,1,RO0412,L7,11,13
abc,30-JUN-12,JUN-12,1,RO0412,L7,14,14
abc,30-JUN-12,JUN-12,1,RO0412,L7,28,28
def,29-MAY-13,MAY-13,1350,RO0213,K1,32,33
abc,20-FEB-14,FEB-14,650,EN1113,S317,41,41
abc,20-FEB-14,FEB-14,650,EN1113,S317,50,52

编辑：不按排序顺序更新SampleInput.txt，Ed Morton你是对的，我的实际输入文件不按排序顺序，想知道如何点蜡下面的样本。

13,abc,22-JUN-12.08:06:03,22-JUN-12.08:06:03,19-Apr-16,1,INR,RO0412,RC03,L7,,31
14,abc,30-JUN-12.01:06:49,30-JUN-12.01:06:49,19-Apr-16,1,INR,RO0412,RC03,L7,,29
11,abc,22-JUN-12.08:06:03,22-JUN-12.08:06:03,19-Apr-16,1,INR,RO0412,RC03,L7,,31
12,abc,22-JUN-12.08:06:03,22-JUN-12.08:06:03,19-Apr-16,1,INR,RO0412,RC03,L7,,31
28,abc,30-JUN-12.01:06:49,30-JUN-12.01:06:49,19-Apr-16,1,INR,RO0412,RC03,L7,,29
32,def,29-MAY-13.12:05:11,29-MAY-13.12:05:11,15-Feb-17,1350,INR,RO0213,CD,K1,,30
33,def,29-MAY-13.12:05:11,29-MAY-13.12:05:11,15-Feb-17,1350,INR,RO0213,CD,K1,,30
41,abc,20-FEB-14.11:02:37,20-FEB-14.11:02:37,31-Dec-20,650,INR,EN1113,ch650,S317,,28
50,abc,20-FEB-14.11:02:37,20-FEB-14.11:02:37,31-Dec-20,650,INR,EN1113,ch650,S317,,28
52,abc,20-FEB-14.11:02:37,20-FEB-14.11:02:37,31-Dec-20,650,INR,EN1113,ch650,S317,,28
51,abc,20-FEB-14.11:02:37,20-FEB-14.11:02:37,31-Dec-20,650,INR,EN1113,ch650,S317,,28

Answer 1

像这样的剧本可能会这样做。我希望有人不只是做一个浓缩版本：

#!/usr/bin/awk -f
BEGIN {
    FS = OFS = ","
}
{
    # sub(/[.].*$/, "", $3)  ## Uncomment if you don't want to include the time.
    # sub(/[.].*$/, "", $4)  ## Uncomment if you don't want to include the time.
    key = $2 "," $3 "," $4 "," $6 "," $8 "," $10
    if (!(key in s)) {
        s[key] = e[key] = $1
        keys[k++] = key
    } else if ($1 < s[key]) {
        s[key] = $1
    } else if ($1 > e[key]) {
        e[key] = $1
    }
}
END {
    for (k = 0; k in keys; ++k) {
        key = keys[k]
        print key, s[key], e[key]
    }
}

也许类似：

#!/usr/bin/awk -f
BEGIN {
    FS = OFS = ","
}
{
    # sub(/[.].*$/, "", $3)
    # sub(/[.].*$/, "", $4)
    key = $2 "," $3 "," $4 "," $6 "," $8 "," $10
}
!s[key] {
    s[key] = e[key] = $1
    keys[k++] = key
    next
}
$1 < s[key] {
    s[key] = $1
    next  ## Optional.
}
$1 > e[key] {
    e[key] = $1
}
END {
    for (k = 0; k in keys; ++k) {
        key = keys[k]
        print key, s[key], e[key]
    }
}

使用

awk -f script.awk file

输出：

abc,22-JUN-12.08:06:03,22-JUN-12.08:06:03,1,RO0412,L7,11,13
abc,30-JUN-12.01:06:49,30-JUN-12.01:06:49,1,RO0412,L7,14,28
def,29-MAY-13.12:05:11,29-MAY-13.12:05:11,1350,RO0213,K1,32,33
abc,20-FEB-14.11:02:37,20-FEB-14.11:02:37,650,EN1113,S317,41,52

排除时间的输出（取消注释sub()行）：

abc,22-JUN-12,22-JUN-12,1,RO0412,L7,11,13
abc,30-JUN-12,30-JUN-12,1,RO0412,L7,14,28
def,29-MAY-13,29-MAY-13,1350,RO0213,K1,32,33
abc,20-FEB-14,20-FEB-14,650,EN1113,S317,41,52

Answer 2

我相信这会产生你想要的输出（与你所显示的相同）。

sort -k1 -t, Input.txt |
awk '
  function prn() {print f2,d1,substr(f4,1,6),f6,f8,f10,n1,n2}
  function sav() {n1=$1;d1=d;f2=$2;f4=$4;f6=$6;f8=$8;f10=$10}
  BEGIN {FS=OFS=","}
  {d = substr($3,1,9)}
  NR == 1 {sav(); n2=n1; d2=d1; next}
  $1 != n2 + 1 || d1 != d {prn(); sav()}
  {n2=$1; d2=d}
  END {prn()}
'

我假设您实际上想要第一个 6个字段4（日期和月份）而不是最后6个月（月和年）。

Answer 3

$ cat tst.awk
BEGIN{ FS=OFS="," }
{
    seq = $1
    key = $2 FS substr($3,1,9) FS substr($4,4,6) FS $6 FS $8 FS $10

    if ( (seq != (prevSeq+1)) || (key != prevKey) ) {
        if (startSeq != "")
            print prevKey, startSeq, prevSeq
        startSeq = seq
    }

    prevSeq = seq
    prevKey = key
}
END {
    print key, startSeq, prevSeq
}
$
$ awk -f tst.awk file
abc,22-JUN-12,JUN-12,1,RO0412,L7,11,13
abc,30-JUN-12,JUN-12,1,RO0412,L7,14,14
abc,30-JUN-12,JUN-12,1,RO0412,L7,28,28
def,29-MAY-13,MAY-13,1350,RO0213,K1,32,33
abc,20-FEB-14,FEB-14,650,EN1113,S317,41,41
abc,20-FEB-14,FEB-14,650,EN1113,S317,50,52

awk打印连续序列号 - 开始序列和结束序列：

$ 2，$ 3，$ 4，$ 6，$ 8 $ 10 Start_No，End_No

3 个答案: