Awk 根据特定列中的数据输出文件
使用输入文件，我将生成所需的输出 我正在尝试使用下面所示的代码，找出如何准确地获得所需的输出结果 第2列中输入文件的信息需要在输出文件中，从第21列到80列，填充所有范围。Awk 根据特定列中的数据输出文件,awk,Awk,使用输入文件，我将生成所需的输出 我正在尝试使用下面所示的代码，找出如何准确地获得所需的输出结果 第2列中输入文件的信息需要在输出文件中，从第21列到80列，填充所有范围。 awk ' function range_to_out() { out=(out sep (start == last
awk '
function range_to_out() {
out=(out sep (start == last ? start : (start "-" last)))
}
function print_out() {
printf "%s %s\n", p1, out","
}
NR == 1 { start=last=$2; p1=$1; next }
{
if ($2 == last+1) { last=$2 } else {
range_to_out(); sep=","; start=last=$2
}
}
$1 != p1 || length(out) > 50 { print_out(); sep=out=""; p1=$1 }
END { range_to_out(); print_out() }
' file
X52152 1214-1216,1218-1221,1233,1222,1245,1223,1246,1249,1251,
X52152 1224-1232,1234-1243,1247,1250,1253-1254,1332,1331,1333-1336,
X52152 1338,1337,1339-1340,1467.
X52155 1215-1216,1218-1221,1233,1222,1245,1223,1246,1249,1251,1248,
X52155 1224-1232,1234-1243,1247,1250,1253-1254,1332,1331,1333-1336,
X52155 1338,1337,1339-1341.
awk '
function range_to_out() {
out=(out sep (start == last ? start : (start "-" last)))
}
function print_out() {
printf "%s %s\n", p1, out","
}
NR == 1 { start=last=$2; p1=$1; next }
{
if ($2 == last+1) { last=$2 } else {
range_to_out(); sep=","; start=last=$2
}
}
$1 != p1 || length(out) > 50 { print_out(); sep=out=""; p1=$1 }
END { range_to_out(); print_out() }
' file
awk '
function printrange() { print start (start == last ? "" : "-" last) }
NR == 1 {start=last=$1; next}
$1 == last+1 {last=$1; next}
{printrange(); start=last=$1}
END {printrange()}
' file | paste -sd" " | fold -sw 60 | tr ' ' ',' | sed 's/^/111111 /'
X52152 1214
X52152 1215
X52152 1216
X52152 1218
X52152 1219
X52152 1220
X52152 1221
X52152 1233
X52152 1222
X52152 1245
X52152 1223
X52152 1246
X52152 1249
X52152 1251
X52152 1224
X52152 1225
X52152 1226
X52152 1227
X52152 1228
X52152 1229
X52152 1230
X52152 1231
X52152 1232
X52152 1234
X52152 1235
X52152 1236
X52152 1237
X52152 1238
X52152 1239
X52152 1240
X52152 1241
X52152 1242
X52152 1243
X52152 1247
X52152 1250
X52152 1253
X52152 1254
X52152 1332
X52152 1331
X52152 1333
X52152 1334
X52152 1335
X52152 1336
X52152 1338
X52152 1337
X52152 1339
X52152 1340
X52152 1467
X52155 1215
X52155 1216
X52155 1218
X52155 1219
X52155 1220
X52155 1221
X52155 1233
X52155 1222
X52155 1245
X52155 1223
X52155 1246
X52155 1249
X52155 1251
X52155 1248
X52155 1224
X52155 1225
X52155 1226
X52155 1227
X52155 1228
X52155 1229
X52155 1230
X52155 1231
X52155 1232
X52155 1234
X52155 1235
X52155 1236
X52155 1237
X52155 1238
X52155 1239
X52155 1240
X52155 1241
X52155 1242
X52155 1243
X52155 1247
X52155 1250
X52155 1253
X52155 1254
X52155 1332
X52155 1331
X52155 1333
X52155 1334
X52155 1335
X52155 1336
X52155 1338
X52155 1337
X52155 1339
X52155 1340
X52155 1341
您的
awkfunction print_stuff(label,string, t) {
# abuse $0 as it makes life easy
t = $0; $0 = string;
# replace values with "-" if a-1,a,a+1
for (i=2;i<NF;++i) {
if ($i == $(i-1)+1 && $i == $(i+1)-1) $i="-"
else if ($(i-1) == "-" && $i == $(i+1)-1) $i="-"
else if ($i == $(i-1)+1) $i="- "$i
}
# substitute all " - - - " with "-" and all " " with ","
gsub(/ [ -]+/,"-"); gsub(/ /,",")
# print columns
while (length($0)>=60) {
match(substr($0,1,60),/,[^,]*$/)
printf "%-20s", label; print substr($0,1,RSTART)
$0=substr($0,RSTART+1)
}
printf "%-20s", label; print $0"."
$0 = t;
}
{ gsub(/\r/,"",$0) } # get rid of the cariage return
(NR == 1) { a=$1; b = $2; next } # initialize
(a == $1) { b = b" "$2; next } # append values
(a != $1) { print_stuff(a,b); a = $1; b = $2 } # print
END { print_stuff(a,b) } # print last
函数打印内容（标签、字符串、t）{
#滥用0美元，因为它使生活变得轻松
t=$0；$0=字符串；
#如果a-1、a、a+1，则将值替换为“-”
对于（i=2；i=60）{
匹配（substr（$0,1,60），/，[^，]*$/）
printf“%-20s”，标签；打印子文件（$0,1，RSTART）
$0=substr（$0，RSTART+1）
}
printf“%-20s”，标签；打印$0“
$0=t；
}
{gsub（/\r/，“”，$0）}摆脱cariage返回
（NR==1）{a=$1；b=$2；next}#初始化
（a==1）{b=b”“$2；next}#追加值
（a！=$1）{打印（a，b）；a=$1；b=$2}打印
结束{打印（a，b）}最后打印
$ awk -f main.awk <file>
X52152 1214-1216,1218-1221,1233,1222,1245,1223,1246,1249,1251,
X52152 1224-1232,1234-1243,1247,1250,1253-1254,1332,1331,1333-1336,
X52152 1338,1337,1339-1340,1467.
X52155 1215-1216,1218-1221,1233,1222,1245,1223,1246,1249,1251,1248,
X52155 1224-1232,1234-1243,1247,1250,1253-1254,1332,1331,1333-1336,
X52155 1338,1337,1339-1341.
$awk-f main.awk
X5215214-12161218-12211233122124512212451223124612491251，
X5215224-12321234-1243124712503-1254133213311313-1336，
X5215213381371339-13401467。
X521551215-12161218-1221123312212124512231246124912511248，
X52155 1224-12321234-1243124712503-1254133213311313-1336，
X52155 13381371339-1341。
awkfunction print_stuff(label,string, t) {
# abuse $0 as it makes life easy
t = $0; $0 = string;
# replace values with "-" if a-1,a,a+1
for (i=2;i<NF;++i) {
if ($i == $(i-1)+1 && $i == $(i+1)-1) $i="-"
else if ($(i-1) == "-" && $i == $(i+1)-1) $i="-"
else if ($i == $(i-1)+1) $i="- "$i
}
# substitute all " - - - " with "-" and all " " with ","
gsub(/ [ -]+/,"-"); gsub(/ /,",")
# print columns
while (length($0)>=60) {
match(substr($0,1,60),/,[^,]*$/)
printf "%-20s", label; print substr($0,1,RSTART)
$0=substr($0,RSTART+1)
}
printf "%-20s", label; print $0"."
$0 = t;
}
{ gsub(/\r/,"",$0) } # get rid of the cariage return
(NR == 1) { a=$1; b = $2; next } # initialize
(a == $1) { b = b" "$2; next } # append values
(a != $1) { print_stuff(a,b); a = $1; b = $2 } # print
END { print_stuff(a,b) } # print last
函数打印内容（标签、字符串、t）{
#滥用0美元，因为它使生活变得轻松
t=$0；$0=字符串；
#如果a-1、a、a+1，则将值替换为“-”
对于（i=2；i=60）{
匹配（substr（$0,1,60），/，[^，]*$/）
printf“%-20s”，标签；打印子文件（$0,1，RSTART）
$0=substr（$0，RSTART+1）
}
printf“%-20s”，标签；打印$0“
$0=t；
}
{gsub（/\r/，“”，$0）}摆脱cariage返回
（NR==1）{a=$1；b=$2；next}#初始化
（a==1）{b=b”“$2；next}#追加值
（a！=$1）{打印（a，b）；a=$1；b=$2}打印
结束{打印（a，b）}最后打印
$ awk -f main.awk <file>
X52152 1214-1216,1218-1221,1233,1222,1245,1223,1246,1249,1251,
X52152 1224-1232,1234-1243,1247,1250,1253-1254,1332,1331,1333-1336,
X52152 1338,1337,1339-1340,1467.
X52155 1215-1216,1218-1221,1233,1222,1245,1223,1246,1249,1251,1248,
X52155 1224-1232,1234-1243,1247,1250,1253-1254,1332,1331,1333-1336,
X52155 1338,1337,1339-1341.
$awk-f main.awk
X5215214-12161218-12211233122124512212451223124612491251，
X5215224-12321234-1243124712503-1254133213311313-1336，
X5215213381371339-13401467。
X521551215-12161218-1221123312212124512231246124912511248，
X52155 1224-12321234-1243124712503-1254133213311313-1336，
X52155 13381371339-1341。
\r\r