gpertea

#!/bin/env python3
#Usage: mstrg_prep.py merged.gtf > merged_prep.gtf
import re, fileinput
g={} #gene_id => {ref_gene_ids}
prep=[] #array of [line, mstrg_id]
for line in fileinput.input():
  line=line.rstrip()
  t=line.split('\t')
  if len(t)<9:
    print(line)

gpertea

#!/bin/env perl
#Usage: mstrg_prep.pl merged.gtf > merged_prep.gtf
use strict;
my %g; # gene_id => \%ref_gene_ids (or gene_names)
my @prep; # array of [line, original_id]
while (<>) {
 s/ +$//;
 my @t=split(/\t/);
 unless (@t>8) { print $_; next }
 my ($gid)=($t[8]=~m/gene_id "(MSTRG\.\d+)"/);

gpertea

char* str=brec->tag_str("ZD"); //let's say the tag is "ZD"
GVec<int> vals;
char* p=str; //slice start
for (int i=0;;++i) {
  char ch=str[i];
  if (ch==',') {
    str[i]=0;
    int v=atoi(p); //check for int parsing errors?
    vals.Add(v);
    p=str+i+1;