在文件头处打印第N列与现有行bash的总和

Question

我有一个包含数十亿条记录和一个头的输入文件。标题由元信息、总行数和第六列的总和组成。我将文件拆分为较小的大小，因此，当第六列和总行的总和发生更改时，必须更新我的头记录。

这是样品记录

filename:testFile.text

00|STMT|08-09-2022 13:24:56||5|13.10|SHA2
10|000047290|8ddcf4b2356dfa7f326ca8004a9bdb6096330fc4f3b842a971deaf660a395f65|18-01-2020|12:36:57|3.10|00004729018-01-20201|APP
10|000052736|cce280392023b23df2a00ace4b82db8eb61c112bb14509fb273c523550059317|07-02-2017|16:27:49|2.00|00005273607-02-20171|APP
10|000070355|f2e86d2731d32f9ce960a0f5883e9b688c7e57ab9c2ead86057f98426407d87a|17-07-2019|20:25:02|1.00|00007035517-07-20192|APP
10|000070355|54c1fc2667e160a11ae1dbf54d3ba993475cd33d6ececdd555fb5c07e64a241b|17-07-2019|20:25:02|5.00|00007035517-07-20192|APP
10|000072420|f5dac143082631a1693e0fb5429d3a185abcf3c47b091be2f30cd50b5cf4be11|14-06-2021|20:52:21|2.00|00007242014-06-20212|APP

预期：

filename:testFile_1.text

00|STMT|08-09-2022 13:24:56||3|6.10|SHA2
10|000047290|8ddcf4b2356dfa7f326ca8004a9bdb6096330fc4f3b842a971deaf660a395f65|18-01-2020|12:36:57|3.10|00004729018-01-20201|APP
10|000052736|cce280392023b23df2a00ace4b82db8eb61c112bb14509fb273c523550059317|07-02-2017|16:27:49|2.00|00005273607-02-20171|APP
10|000070355|f2e86d2731d32f9ce960a0f5883e9b688c7e57ab9c2ead86057f98426407d87a|17-07-2019|20:25:02|1.00|00007035517-07-20192|APP

filename:testFile_2.text

00|STMT|08-09-2022 13:24:56||2|7.00|SHA2
10|000070355|54c1fc2667e160a11ae1dbf54d3ba993475cd33d6ececdd555fb5c07e64a241b|17-07-2019|20:25:02|5.00|00007035517-07-20192|APP
10|000072420|f5dac143082631a1693e0fb5429d3a185abcf3c47b091be2f30cd50b5cf4be11|14-06-2021|20:52:21|2.00|00007242014-06-20212|APP

我可以拆分文件并计算总和，但无法替换标题部分的值。这是我制作的脚本

#!/bin/bash
splitRowCount=$1
transactionColumn=$2
filename=$(basename -- "$3")
extension="${filename##*.}"
nameWithoutExt="${filename%.*}"
echo "splitRowCount: $splitRowCount"
echo "transactionColumn: $transactionColumn"

awk 'NR == 1 { head = $0 } NR % '$splitRowCount' == 2 { filename = "'$nameWithoutExt'_" int((NR-1)/'$splitRowCount')+1 ".'$extension'"; print head > filename } NR != 1 { print >> filename }' $filename

ls *.txt | while read line
do
firstLine=$(head -n 1 $line);
awk -F '|'  'NR !=1 {sum += '$transactionColumn'}END {print sum} '   $line
done

Answer 1

这里有一个awk解决方案，用于将原始文件拆分为n记录的文件。其想法是累积记录，直到达到给定的计数，然后生成一个具有更新的标头和累积记录的文件：

n=3
file=./testFile.text
awk -v numRecords="$n"  '
BEGIN {
FS = OFS = "|"
if ( match(ARGV[1],/[^/].[^/]*$/) ) {
filePrefix = substr(ARGV[1],1,RSTART)
fileSuffix = substr(ARGV[1],RSTART+1)
} else {
filePrefix = ARGV[1]
fileSuffix = ""
}
if (getline headerStr <= 0)
exit 1
split(headerStr, headerArr)
}
(NR-2) % numRecords == 0 && recordsCount {
outfile = filePrefix "_" ++filesCount fileSuffix
print headerArr[1],headerArr[2],headerArr[3],headerArr[4],recordsCount,recordsSum,headerArr[7] > outfile
printf("%s", records) > outfile
close(outfile)

records = ""
recordsCount = recordsSum = 0
}
{
records = records $0 ORS
recordsCount++
recordsSum += $6
}
END {
if (recordsCount) {
outfile = filePrefix "_" ++filesCount fileSuffix
print headerArr[1],headerArr[2],headerArr[3],headerArr[4],recordsCount,recordsSum,headerArr[7] > outfile
printf("%s", records) > outfile
close(outfile)
}
}
' "$file"

对于给定的样本，您将获得：

• testFile_1.text

00|STMT|08-09-2022 13:24:56||3|6.1|SHA2
10|000047290|8ddcf4b2356dfa7f326ca8004a9bdb6096330fc4f3b842a971deaf660a395f65|18-01-2020|12:36:57|3.10|00004729018-01-20201|APP
10|000052736|cce280392023b23df2a00ace4b82db8eb61c112bb14509fb273c523550059317|07-02-2017|16:27:49|2.00|00005273607-02-20171|APP
10|000070355|f2e86d2731d32f9ce960a0f5883e9b688c7e57ab9c2ead86057f98426407d87a|17-07-2019|20:25:02|1.00|00007035517-07-20192|APP

• testFile_2.text

00|STMT|08-09-2022 13:24:56||2|7|SHA2
10|000070355|54c1fc2667e160a11ae1dbf54d3ba993475cd33d6ececdd555fb5c07e64a241b|17-07-2019|20:25:02|5.00|00007035517-07-20192|APP
10|000072420|f5dac143082631a1693e0fb5429d3a185abcf3c47b091be2f30cd50b5cf4be11|14-06-2021|20:52:21|2.00|00007242014-06-20212|APP

Answer 2

使用您显示的示例，请尝试以下awk代码(在GNUawk中编写和测试(。在这里，我定义了名为fileInitials的awk变量，它包含输出文件的初始名称，例如：testFile，然后是extension，它包含了输出文件的扩展名，例如：这里的.txt。然后是lines，它将是您希望在输出文件中有多少行的值。

您不需要运行shell+awk代码，这可以在单个awk中完成，如下所示。

awk -v count="1" -v fileInitials="testFile" -v extension=".txt" -v lines="3" '
BEGIN { FS=OFS="|" }
FNR==1{
match($0,/^([^|]*|[^|]*|[^|]*|[^|]*|[^|]*)|[^|]*(.*)/,arr)
header1=arr[1]
header2=arr[2]
outputFile=(fileInitials count extension)
next
}
{
if(prev!=count){
print (header1,sum header2 ORS val) > (outputFile)
close(outputFile)
outputFile=(fileInitials count extension)
sum=0
val=""
}
sum+=$6
val=(val?val ORS:"") $0
prev=count
count=(++countline%lines==0?++count:count)
}
END{
if(count && val){
print (header1,sum header2 ORS val) > (outputFile)
close(outputFile)
}
}
'   Input_file