比较两个文件中的字段与计算

时间:2012-07-08 22:49:53

标签: bash awk

WORKS !!

见下文......

更新我的剧本......

问题是它只输出外部循环中的第一行。简单的事情是错的,我没有看到它。

此脚本从两个文件中读取并进行计算。 这是文件......

$  awk -F',' '{print $1, $2, $3, $4}' s1.txt
2017 5155 41.46097500 -78.99436944
2017 5156 41.46157778 -78.99437500
2017 5157 41.46218611 -78.99437778
2017 5158 41.46278611 -78.99438056
2017 5159 41.46339722 -78.99438333
2017 5160 41.46399444 -78.99438611


$  awk -F',' '{print $11, $12}' data.txt
41.46098533 -78.99440559
41.46217481 -78.99440703
41.46158424 -78.99439119
41.46278446 -78.99439355
41.46338829 -78.99440672
41.46399091 -78.99439231
#! /usr/bin/awk -f

BEGIN { 
   while (getline < "s1.txt") {
      split($0, ft, ",")
      line =    ft[1]
      station = ft[2]
      lat1 =    ft[3]
      lon1 =    ft[4]

      while (getline < "data.txt") {
          split($0, ft, ",")
          lat2 = ft[11]
          lon2 = ft[12]

          x = (lon2 - lon1) * cos((lat1 + lat2) / 2)
          y = (lat2 - lat1)
          d = sqrt(x * x + y * y) * 6371

          print line","station","lat1","lon1","lat2","lon2","d | "sort -t, -h -k7 |head -1" 

      }
   }
}

输出..

2017,5155,41.46097500,-78.99436944,41.46098533,-78.99440559,0.198629

这会加载s1.txt中的第一行并比较data.txt中的所有行。

我需要将s1.txt推进到下一行并循环直到我到达s1.txt的末尾。

???

我添加了一些打印命令

#! /usr/bin/awk -f

BEGIN { 
   while (getline < "s1.txt") {
      split($0, ft, ",")
      line =    ft[1]
      station = ft[2]
      lat1 =    ft[3]
      lon1 =    ft[4]
      print "loop1"
      while (getline < "data.txt") {
          split($0, ft, ",")
          lat2 = ft[11]
          lon2 = ft[12]

          x = (lon2 - lon1) * cos((lat1 + lat2) / 2)
          y = (lat2 - lat1)
          d = sqrt(x * x + y * y) * 6371
          print "loop2"
          print line","station","lat1","lon1","lat2","lon2","d | "sort -t, -h -k7 |head -1" 

      }
   }
}

看起来它有效一次。之后它不会进入第二个循环。

$ resolv.awk
loop1
loop2
loop2
loop2
loop2
loop2
loop2
loop2
loop2
loop2
loop1
loop1
loop1
loop1
loop1
loop1
loop1
2017,5155,41.46097500,-78.99436944,41.46104466,-78.99446284,0.656815

如果我在内部循环上使用了一个中断,它会正确循环但是中断不会让它正常工作,因为它每次从匹配文件中取出第一行。我想也许这些文件需要交换。匹配文件的内循环和数据的外循环。

或休息时的一些条件声明。

#! /usr/bin/awk -f
BEGIN { 
   while (getline < "s1.txt") {
      split($0, ft, ",")
      line =    ft[1]
      station = ft[2]
      lat1 =    ft[3]
      lon1 =    ft[4]
      print "loop1"
      while (getline < "data.txt") {
          split($0, ft, ",")
          lat2 = ft[11]
          lon2 = ft[12]

          x = (lon2 - lon1) * cos((lat1 + lat2) / 2)
          y = (lat2 - lat1)
          d = sqrt(x * x + y * y) * 6371
      print "loop2"
          print line","station","lat1","lon1","lat2","lon2","d 
      break
      }
   }
}

    $ resolv.awk
loop1
loop2
2017,5155,41.46097500,-78.99436944,41.46104466,-78.99446284,0.656815
loop1
loop2
2017,5156,41.46157778,-78.99437500,41.46162354,-78.9943992,0.317363
loop1
loop2
2017,5157,41.46218611,-78.99437778,41.46215576,-78.99438806,0.200558
loop1
loop2
2017,5158,41.46278611,-78.99438056,41.46281488,-78.99439355,0.195243
loop1
loop2
2017,5159,41.46339722,-78.99438333,41.46458318,-78.99436234,7.55653
loop1
loop2
2017,5160,41.46399444,-78.99438611,41.46517654,-78.99437141,7.53154
loop1
loop2
2017,5161,41.46459722,-78.99438889,41.46580453,-78.99434083,7.69578
loop1

这个有用.. 我将不得不在脚本的外部排序和删除重复项,而不是在我最初计划的内部。

#! /usr/bin/awk -f
BEGIN { 
   while (getline < "s2.txt") {
      split($0, ft, ",")
      line =    ft[1]
      station = ft[2]
      lat1 =    ft[3]
      lon1 =    ft[4]
      while (getline < "data.txt") {
          split($0, ft, ",")
          lat2 = ft[11]
          lon2 = ft[12]
          ln2 =  ft[14]
          stn2 = ft[15]

          x = (lon2 - lon1) * cos((lat1 + lat2) / 2)
          y = (lat2 - lat1)
          d = sqrt(x * x + y * y) * 6371
          print line","station","lat1","lon1","ln2","stn2","lat2","lon2","d
      }

      # edited here
      close ( "data.txt" )

   }
}

2017,5155,41.46097500,-78.99436944,2017,5155,41.46104466,-78.99446284,0.656815
2017,5155,41.46097500,-78.99436944,2017,5156,41.46162354,-78.9943992,4.13473
2017,5155,41.46097500,-78.99436944,2017,5157,41.46215576,-78.99438806,7.52324
2017,5156,41.46157778,-78.99437500,2017,5155,41.46104466,-78.99446284,3.42688
2017,5156,41.46157778,-78.99437500,2017,5156,41.46162354,-78.9943992,0.317363
2017,5156,41.46157778,-78.99437500,2017,5157,41.46215576,-78.99438806,3.68293
2017,5157,41.46218611,-78.99437778,2017,5155,41.46104466,-78.99446284,7.28552
2017,5157,41.46218611,-78.99437778,2017,5156,41.46162354,-78.9943992,3.58585
2017,5157,41.46218611,-78.99437778,2017,5157,41.46215576,-78.99438806,0.200558
2017,5158,41.46278611,-78.99438056,2017,5155,41.46104466,-78.99446284,11.103
2017,5158,41.46278611,-78.99438056,2017,5156,41.46162354,-78.9943992,7.40736
2017,5158,41.46278611,-78.99438056,2017,5157,41.46215576,-78.99438806,4.01615
2017,5159,41.46339722,-78.99438333,2017,5155,41.46104466,-78.99446284,14.9938
2017,5159,41.46339722,-78.99438333,2017,5156,41.46162354,-78.9943992,11.3004
2017,5159,41.46339722,-78.99438333,2017,5157,41.46215576,-78.99438806,7.90938

 resolv.awk |sort -h -k9 -t, |awk -F',' '!_[$1$2]++' | awk -F',' '!_[$7$8]++'
2017,5157,41.46218611,-78.99437778,2017,5157,41.46215576,-78.99438806,0.200558
2017,5156,41.46157778,-78.99437500,2017,5156,41.46162354,-78.9943992,0.317363
2017,5155,41.46097500,-78.99436944,2017,5155,41.46104466,-78.99446284,0.656815

1 个答案:

答案 0 :(得分:0)

好像你错过了close声明。

#! / usr / bin / awk -f

BEGIN { 
   while (getline < "s1.txt") {
      split($0, ft, ",")
      line =    ft[1]
      station = ft[2]
      lat1 =    ft[3]
      lon1 =    ft[4]

      while (getline < "data.txt") {
          split($0, ft, ",")
          lat2 = ft[11]
          lon2 = ft[12]

          x = (lon2 - lon1) * cos((lat1 + lat2) / 2)
          y = (lat2 - lat1)
          d = sqrt(x * x + y * y) * 6371

          print line","station","lat1","lon1","lat2","lon2","d | "sort -t, -h -k7 |head -1" 

      }

      # edited here
      close ( "data.txt" )

   }
}