Shell Programming and Scripting

Number of disabled taxa: 9
Loading mapping file: ncbi.map
Load mapping:
taxId2TaxLevel: 469951
--- Subsample reads (20%): 66680 of 334386
Processing: tree-from-summary
Running tree-from-summary algorithm
Taxonomy:
          Gammaproteobacteria: 2767
       Alphaproteobacteria: 4123
         Deltaproteobacteria: 1343
                         Epsilonproteobacteria: 26
     Betaproteobacteria: 397
                        unclassified Proteobacteria: 48
                  Spirochaetes (class): 15
        Nitrospira (class): 1
        Bacilli: 25
  Not assigned: 1445
  No hits: 220253
+++++++++++End of summary for file: B-Red-sum.txt
--- Subsample reads (20%): 67037 of 334386
Processing: tree-from-summary
Running tree-from-summary algorithm
Taxonomy:
    Gammaproteobacteria: 2809
                Alphaproteobacteria: 4001
       Deltaproteobacteria: 1208
Epsilonproteobacteria: 15
Not assigned: 299
No hits: 461890
+++++++++++End of summary for file: B-Red-sum.txt

::::: and so on

#!/usr/bin/perl -w

$#ARGV==0 or die "Usage: 2ndprocess-megan-script 1st-output-file-as-inputfile\n";

$i=1;
while (<>){
chomp;
   
 if (/Taxonomy:/ ) { 
     $x = $1; $x =~ s/^\s+|\s+$//g;    ##for this line there is the error, without this line it works
     open(OUT,">>","output_".$i++) or die "Cannot open for writing:$!\n";
     $f=1; next;
 }
 
 if (/\+*End of summary for file/ ){
    $f=0;close(OUT);next;
 }
 if ($f) { print OUT $_."\n";}
}

perl -ne '{$/=""; $i=1;
  while (/^Taxonomy:.(.*?)\+{11}/msgi) {
    $x = $1; $x =~ s/(^|\n)\s+/\1/g;
    open(OUT,">outfile".$i++.".txt"); print OUT $x; close(OUT);
  }}' input.txt

#!/usr/bin/perl -w

$#ARGV==0 or die "Usage: 2ndprocess-script 1st-output-file-as-inputfile\n";

$input=shift;

perl -ne '{$/=""; $i=1;
while (/^Taxonomy:.(.*?)\+{11}/msgi) {
$x = $1; $x =~ s/(^|\n)\s+/\1/g;
open(OUT,">outfile".$i++.".txt"); print OUT $x; close(OUT);
}}' $1;

#! /usr/bin/python

f=0;i=0
for line in open(input file):
    line=line.strip()
    if line.startswith("+++++++++++"): 
        f=0
        o.close()
    if "Taxonomy:" in line: 
        f=1;i=i+1
        o=open("out_"+str(i)+".txt","w")
    if f:
        print >>o, line

# ./test.py
# more out_2.txt
Taxonomy:
Gammaproteobacteria: 2809
Alphaproteobacteria: 4001
Deltaproteobacteria: 1208
Epsilonproteobacteria: 15
Not assigned: 299
No hits: 461890

# more out_1.txt
Taxonomy:
Gammaproteobacteria: 2767
Alphaproteobacteria: 4123
Deltaproteobacteria: 1343
Epsilonproteobacteria: 26
Betaproteobacteria: 397
unclassified Proteobacteria: 48
Spirochaetes (class): 15
Nitrospira (class): 1
Bacilli: 25
Not assigned: 1445
No hits: 220253

#! /usr/bin/python
input=$1
inputfile="`pwd`/$name"
f=0;i=0
for line in open(inputfile):
    line=line.strip()
    if line.startswith("+++++++++++"): 
        f=0
        o.close()
    if "Taxonomy:" in line: 
        f=1;i=i+1
        o=open("out_"+str(i)+".txt","w")
    if f:
        print >>o, line

#! /usr/bin/python
import sys
inputfile=sys.argv[1]
f=0;i=0
for line in open(inputfile):
    line=line.strip()
    if line.startswith("+++++++++++"): 
        f=0
        o.close()
    if "Taxonomy:" in line: 
        f=1;i=i+1
        o=open("out_"+str(i)+".txt","w")
    if f:
        print >>o, line

#! /usr/bin/python
import sys
inputfile=sys.argv[1]
f=0;i=0
for line in open(inputfile):
    line=line.strip()
    if line.startswith("+++++++++++"): 
        f=0
        o.close()
    if "Taxonomy:" in line: 
        f=1;i=i+1
        o=open("out_"+str(i)+".txt","w")
    if f:
        print >>o, line

mitra:testNextPart mitra$ ./2ndprocess-2.py 1st-output.txt 
Traceback (most recent call last):
  File "./2ndprocess-2.py", line 9, in <module>
    o.close()
NameError: name 'o' is not defined

#! /usr/bin/python
import sys
inputfile=sys.argv[1]
f=0;i=0
o=open("out_"+str(i)+".txt","w")

for line in open(inputfile):
    line=line.strip()
    if line.startswith("+++++++++++"): 
        f=0
        o.close()
    if "Taxonomy:" in line: 
        f=1;i=i+1
        o=open("out_"+str(i)+".txt","w")
    if f:
        print >>o, line

#! /usr/bin/python
import sys
inputfile=sys.argv[1]
f=0;i=0
for line in open(inputfile):
    line=line.strip()
    if line.startswith("+++++++++++"): 
        f=0
    if "Taxonomy:" in line: 
        f=1;i=i+1
        o=open("out_"+str(i)+".txt","w")
    if f:
        print >>o, line