I have awk file named throughput.awk to calculate throughput from trace files in NS-2.
BEGIN {
FS="[[:space:]]|_"
}
{
action = $1;
node_id = $4;
time = $2;
dest = $6;
app = $10;
pkt_size = $11;
if ( action == "r" && dest == "MAC" && app == "cbr" && time > 10 && (node_id == 1)) {
sum_ = sum_ + pkt_size;
}
}
END {
}
what I want is I have to calculate each node's throughput for multiple nodes from TCL script maybe like this :
for {set node 1} {$node < N } {incr node}
exec awk -f throughput.awk test.tr
}
so "node" variable inside trace files can be changed from TCL. How to do that?
Just use -v parameter:
for (node=1;node<N;node++){
exec awk -v node=$node -f throughput.awk test.tr
}
And inside awk
if ( action == "r" && dest == "MAC" && app == "cbr" && time > 10 && (node_id == node)) {
sum_ = sum_ + pkt_size;
}
Before the "=" node will be the name of the variable inside awk and it's value ($node) will be node val in Tcl
Related
I have a bash script calling awk. I want to test whether ukeys contains elements in array kaggr, if so setting display=1.
My problem is how to avoid the array test when keywords or ukeys are empty. What can I do?
awk -v ukeys="$keys" -v beg_ere="$beg_ere" -v pn_ere="$pn_ere" -v end_ere="$end_ere" \
'$0 ~ beg_ere {
title=gensub(beg_ere, "\\2", 1, $0);
subtitle=gensub(beg_ere, "\\3", 1, $0);
keywords=gensub(beg_ere, "\\4", 1, $0);
nk = split(keywords, kaggr, ",");
nu = split(ukeys, uaggr, ",");
for (i in uaggr) {
match=0;
for (j in kaggr) {
if (uaggr[i] == kaggr[j]) { match=1; break; }
}
if (match == 1) { display=1; break; }
}
next
}
$0 ~ end_ere { display=0 ; print "" }
display { sub(pn_ere, "") ; print }
' "$filename"
I am passing keys="resource" to match values in keywords. But when keys is empty, I do not want to match anything in keywords.
Just to clarify, if the array "ukeys" or "keywords" are empty you want to skip the for-loop? Would this approach solve your issue?
awk -v ukeys="$keys" -v beg_ere="$beg_ere" -v pn_ere="$pn_ere" -v end_ere="$end_ere" \
'$0 ~ beg_ere {
title=gensub(beg_ere, "\\2", 1, $0);
subtitle=gensub(beg_ere, "\\3", 1, $0);
keywords=gensub(beg_ere, "\\4", 1, $0);
nk = split(keywords, kaggr, ",");
nu = split(ukeys, uaggr, ",");
if(length(keys) > 0 && length(keywords) > 0) { # if either arrays are empty, skip this part
for (i in uaggr) {
match=0;
for (j in kaggr) {
if (uaggr[i] == kaggr[j]) {
match=1; break
}
}
if (match == 1) {
display=1; break
}
}
next
}
}
$0 ~ end_ere { display=0 ; print "" }
display { sub(pn_ere, "") ; print }
' "$filename"
NR>NRMIN{
if($3 == "Leu") {
if($4 == "CD1" || $4 == "HD11" || $4 == "HD12" || $4 == "HD13") {
next;
}
}
elseif($3 == "Val") {
if($4 == "CD1" || $4 == "HD11" || $4 == "HD12" || $4 == "HD13") {
next;
}
}
else {
print;
}
}
I intend to selectively print lines of a space-delimited file.
Please let me know why the above code is giving an error when gawk -f FILE_Modifier.awk NRMIN = 90 FILE > NEWFILE
Error Message
gawk: FILE_Modifier.awk:7: elseif($3 == "Val") {
gawk: FILE_Modifier.awk:7: ^ syntax error
gawk: FILE_Modifier.awk:12: else {
gawk: FILE_Modifier.awk:12: ^ syntax error
There is no elseif. Anyway, you can rewrite the script as just:
awk -v nrmin=90 '(NR > nrmin) && !(($3 ~ /^(Leu|Val)$/) && ($4 ~ /^(CD1|HD11|HD12|HD13)$/))' file
Don't use all upper case variable names to avoid clashes with builtin names. Do set variables up front using -v unless you have a specific reason not to.
this script is supposed to read in csv in the following format
Name,Date,ID,Number
John Smith,09/05/2015,s,999-999-99
Mike Smith,09/06/2015,s,989-979-99
Fred Smith,09/03/2015,s,781-999-99
The first line is a header it is supposed to be skipped. So when script runs every .csv file seems to be moving to the GoodFile direcotory which i think is false positive, i fudged with the validation steps like the 3rd one and entered QE instead of SE(it has to be S or E) it doesn't even hit the code? i am not sure why.. for(linenum = 1; linenum <nr; linenum++) {
if (length(dataArr[linenum,3]) == 0){
printf "Failed 3rd a validation"
exit 1
#!/bin/sh
for file in test/*.csv ; do
awk -F',' '
# skip the header and blank lines
NR = 1 || NF == 0 {next}
#save the data in to a 2d array called dataArr
{ for (i=1; i <= NF; i++) dataArr[++nr,i] = $i }
END {
STATUS = "GOOD"
#verify coulmn 1
for( linenum=1; linenum <= nr; linenum++) {
if (length(dataArr[linenum,1]) == 0){
printf "Failed 1st validation"
exit 1
}
}
printf "file: %s, verify column 1, STATUS: %s\n", FILENAME, STATUS
#verify coulmn 2
for(linenum = 1; linenum <nr; linenum++) {
if (length(dataArr[linenum,2]) == 0){
printf "Failed 2nd a validation"
exit 1
}
if ((dataArr[linenum,2]) !~ /^(0[1-9]|1[012])[- /.](0[1-9]|[12][0-9]|3[01])[- /.](19|20)[0-9][0-9]$/){
printf "Failed 2nd b validation"
exit 1
}
}
#verify coulmn 3
for(linenum = 1; linenum <nr; linenum++) {
if (length(dataArr[linenum,3]) == 0){
printf "Failed 3rd a validation"
exit 1
}
# has to be either S or E
if ((dataArr[linenum,3]) !~ /^[SE]$/){
printf "Failed 3rd b validation"
exit 1
}
}
#verify coulmn 4
for(linenum = 1; linenum <nr; linenum++) {
#lenght has to between 9 AND 11
if ((length(dataArr[linenum,4])) < 9 || (length(dataArr[linenum,4]) > 11)){
printf "Failed 4th validation"
exit 1
}
}
}' "$file"
if [[ $? -eq 0 ]]; then
# "good" status
mv ${file} test1/goodFile
else
# "bad" status
mv ${file} test1/badFile
fi
done
You don't need to save the file in an array, all you need is:
awk -F',' '
# skip the header and blank lines
NR == 1 || NF == 0 {next}
$1 == "" { fails1++ }
$2 == "" { fails2a++ }
$2 !~ /^(0[1-9]|1[012])[- /.](0[1-9]|[12][0-9]|3[01])[- /.](19|20)[0-9][0-9]$/) { fails2b++ }
$3 == "" { fails3a++ }
$3 !~ /^[SE]$/ { fails3b++ }
length($4) < 9 || length($4) > 11 { fails4++ }
END {
if (fails1) { print "Failed 1st validation"; exit 1 }
if (fails2a) { print "Failed 2nd a validation"; exit 1 }
if (fails2b) { print "Failed 2nd b validation"; exit 1 }
if (fails3a) { print "Failed 3rd a validation"; exit 1 }
if (fails3b) { print "Failed 3rd b validation"; exit 1 }
if (fails4) { print "Failed 4th validation"; exit 1 }
}' "$file"
To print the failure messages to stderr instead of stdout, btw, would portably be:
if (fails4) { print "Failed 4th validation" | "cat>&2"; exit 1 }
Here's the version if you don't care which error is reported first when the file contains multiple errors:
awk -F',' '
# skip the header and blank lines
NR == 1 || NF == 0 {next}
$1 == "" { print "Failed 1st validation"; exit 1 }
$2 == "" { print "Failed 2nd a validation"; exit 1 }
$2 !~ /^(0[1-9]|1[012])[- /.](0[1-9]|[12][0-9]|3[01])[- /.](19|20)[0-9][0-9]$/) { print "Failed 2nd b validation"; exit 1 }
$3 == "" { print "Failed 3rd a validation"; exit 1 }
$3 !~ /^[SE]$/ { print "Failed 3rd b validation"; exit 1 }
length($4) < 9 || length($4) > 11 { print "Failed 4th validation"; exit 1 }
' "$file"
I am trying to build a script which tail -f | awk the log file which is getting updated every second. awk part will fetch me only the required part of the log file based on my search parameter. Output XML is also captured in an output file. Script is working fine - as expected.
Issue - However ever after the search is performed it stays hung due to tail -f. Any idea how to update below script - so that once the output XML is captured, it should break the tail part??
XMLF=/appl/logs/abc.log
aa_pam=${1-xml}
[[ ${2-xml} = "xml" ]] && tof=xml_$(date +%Y%m%d%H%M%S).xml || tof=$2
tail -f $XMLF | \
awk ' BEGIN { Print_SW=0; Cnt_line=1; i=0}
/\<\?xml version\=/ { if (Print_SW==1) p_out(Cnt_Line,i)
Print_SW=0; Cnt_line=1;
}
{ Trap_arry[Cnt_line++]=$0;
}
/'${1-xml}'/ { Print_SW=1;
}
/\<\/XYZ_999/ { if (Print_SW==1) p_out(Cnt_Line, i);
Print_SW=0; Cnt_line=1; }
END { if (Print_SW==1) p_out(Cnt_Line, i); }
function p_out(Cnt_Line, i) {
for (i=1;i<Cnt_line;i++) {print Trap_arry[i] | "tee '$tof'" }
}
' | tee $tof
Update Tried as per below suggestion of using exit - it is existing the script successfully - however the xml that is getting captured at output is getting duplicated. So in the output file - same XML appears twice..!!
XMLF=/appl/logs/abc.log
aa_pam=${1-xml}
[[ ${2-xml} = "xml" ]] && tof=xml_$(date +%Y%m%d%H%M%S).xml || tof=$2
tail -f $XMLF | \
awk ' BEGIN { Print_SW=0; Cnt_line=1; i=0}
/\<\?xml version\=/ { if (Print_SW==1) p_out(Cnt_Line,i)
Print_SW=0; Cnt_line=1;
}
{ Trap_arry[Cnt_line++]=$0;
}
/'${1-xml}'/ { Print_SW=1;
}
/\<\/XYZ_999/ { if (Print_SW==1) p_out(Cnt_Line, i);
Print_SW=0; Cnt_line=1; }
END { if (Print_SW==1) p_out(Cnt_Line, i); }
function p_out(Cnt_Line, i) {
for (i=1;i<Cnt_line;i++) {print Trap_arry[i] | "tee '$tof'" } { exit }
}
' | tee $tof
Call exit (which will jump to your END block prior to termination) after you are finished capturing your output.
When awk terminates, the next write() to stdout by tail -f will result in an EPIPE error. tail knows to terminate when that happens.
UPDATE: You seem to be having some problem trying to decide where to put the exit. It should not be in p_out because you call p_out from both the closing XML tag match expression and from the END block. Try this instead:
XMLF=/appl/logs/abc.log
aa_pam=${1-xml}
[[ ${2-xml} = "xml" ]] && tof=xml_$(date +%Y%m%d%H%M%S).xml || tof=$2
tail -f $XMLF | \
awk '
BEGIN {
Print_SW=0
Cnt_line=1
i=0
}
/\<\?xml version\=/ {
if (Print_SW==1)
p_out(Cnt_Line,i)
Print_SW=0
Cnt_line=1
}
{
Trap_arry[Cnt_line++]=$0
}
/'${1-xml}'/ {
Print_SW=1;
}
/\<\/XYZ_999/ {
if (Print_SW==1)
p_out(Cnt_Line, i)
Print_SW=0
Cnt_line=1
exit
}
END {
if (Print_SW==1)
p_out(Cnt_Line, i);
}
function p_out(Cnt_Line, i) {
for (i=1;i<Cnt_line;i++) {
print Trap_arry[i] | "tee '$tof'"
}
}
' | tee $tof
You could, in the awk script, add a line such as:
/some-end-of-xml-marker/ { close(/dev/stdin) ; }
I didn't try it, but you get the idea: close STDIN when you reached the end of the file, so that the loop in awk stops and you get to the END part (not tested, I hope this proves to be correct...)
Based on this question How to break a tail -f command in bash you could try
#! /bin/bash
XMLF=/appl/logs/abc.log
aa_pam=${1-xml}
[[ ${2-xml} = "xml" ]] && tof=xml_$(date +%Y%m%d%H%M%S).xml || tof=$2
mkfifo log.pipe
tail -f "$XMLF" > log.pipe & tail_pid=$!
awk -vpar1="$aa_pam" -vtof="$tof" -f t.awk < log.pipe
kill $tail_pid
rm log.pipe
where t.awk is:
/<\?xml version\=/ {
if (Print_SW==1) {
p_out(Cnt_Line)
}
Print_SW=0
Cnt_line=0
}
{
Trap_arry[++Cnt_line]=$0
}
$0 ~ par1 {
Print_SW=1;
}
/<\/XYZ_999/ {
if (Print_SW==1)
p_out(Cnt_Line)
Print_SW=0
Cnt_line=0
}
function p_out(Cnt_Line, i) {
for (i=1; i<Cnt_line; i++) {
print Trap_arry[i] | ("tee " tof)
}
exit 1
}
Could you help me with the following syntax error? When I have one statement after the “if” , the program works. But when I want two statements after an “if” , I get errors.
Thanks,
Carl.
BEGIN { FS = “,” }
{ if ( $2 == “” && ( $6 == “Install” || $6 == “Add” || $6 == “New”) )
{
print $1″,”$2″,”$3″,”$4″,”$5″,”$6″,”$7″,”$8″,”$9 > “Email_Asset_Add” ;
print “$8″,”$9 > “Email_Asset_Add_Mitul” ;
}
else if ( $2 == “” && ( $6 == “Change” || $6 == “Update” || $6 == “Existing”) )
{
print $1″,”$2″,”$3″,”$4″,”$5″,”$6″,”$7″,”$8″,”$9 > “Email_Asset_Update” ;
print “$8″,”$9 > “Email_Asset_Update_Mitul” ;
}
}
awk -f awk_program test_email
awk: newline in string near line 23
awk: newline in string near line 28
I recommend simplifying your code using printf().
For example, this:
print $1”,”$2”,”$3”,”$4”,”$5”,”$6”,”$7”,”$8”,”$9 > “Email_Asset_Add” ;
could become this:
printf("%s,%s,%s,%s,%s,%s,%s,%s,%s\n", $1,$2,$3,$4,$5,$6,$7,$8,$9) > “Email_Asset_Add”;
Much easier to see where things are that way.
In fact, the whole thing could do with a bit of refactoring:
BEGIN {
FS = “,”;
}
{
if ( $2 == “” && ( $6 == “Install” || $6 == “Add” || $6 == “New”) ) {
output="Email_Asset_Add";
} else
if ( $2 == “” && ( $6 == “Change” || $6 == “Update” || $6 == “Existing”) ) {
output="Email_Asset_Update";
} else {
next;
}
printf("%s,%s,%s,%s,%s,%s,%s,%s,%s\n", $1,$2,$3,$4,$5,$6,$7,$8,$9) > output;
printf("%s,%s\n", $8,$9); > “Email_Asset_Update_Mitul” ;
}