New upstream version 0.11.6 (6d79d533) · Commits · Debian Med / gffread

gff_utils.cpp

+2 −2

Original line number	Diff line number	Diff line
		@@ -734,7 +734,7 @@ void GffLoader::load(GList<GenomicSeqData>& seqdata, GFValidateFunc* gf_validate
		GffNameList& attrnames = GffObj::names->attrs;//gffr->names->attrs;
		for (int i=0;i<attrnames.Count();i++) {
		char* n=attrnames[i]->name;
		if (endsiWith(n, "_type")) {
		if (endsiWith(n, "type")) {
		pseudoTypeAttrIds.Add(attrnames[i]->idx);
		}// else {
		char* p=strifind(n, "pseudo");
		@@ -783,7 +783,7 @@ void GffLoader::load(GList<GenomicSeqData>& seqdata, GFValidateFunc* gf_validate
		if (verbose) warnPseudo(*m);
		continue;
		}
		// _type=_pseudogene
		// type=_pseudogene
		//find all attributes ending with _type and have value like: *_pseudogene
		for (int i=0;i<pseudoTypeAttrIds.Count();++i) {
		char* attrv=NULL;

gffread.cpp

+39 −10

Original line number	Diff line number	Diff line
		@@ -4,7 +4,7 @@
		#define __STDC_FORMAT_MACROS
		#include <inttypes.h>

		#define VERSION "0.11.5"
		#define VERSION "0.11.6"

		#define USAGE "gffread v" VERSION ". Usage:\n\
		gffread <input_gff> [-g <genomic_seqs_fasta> \| <dir>][-s <seq_info.fsize>] \n\
		@@ -100,7 +100,9 @@ Output options:\n\
		-g full path to a multi-fasta file with the genomic sequences\n\
		for all input mappings, OR a directory with single-fasta files\n\
		(one per genomic sequence, with file names matching sequence names)\n\
		-w write a fasta file with spliced exons for each GFF transcript\n\
		-w write a fasta file with spliced exons for each transcript\n\
		--w-add <N> for the -w option, extract additional <N> bases\n\
		both upstream and downstream of the transcript boundaries\n\
		-x write a fasta file with spliced CDS for each GFF transcript\n\
		-y write a protein fasta file with the translation of CDS for each record\n\
		-W for -w and -x options, write in the FASTA defline the exon\n\
		@@ -111,8 +113,6 @@ Output options:\n\
		-m <chr_replace> is a name mapping table for converting reference \n\
		sequence names, having this 2-column format:\n\
		<original_ref_ID> <new_ref_ID>\n\
		WARNING: all GFF records on reference sequences whose original IDs\n\
		are not found in the 1st column of this table will be discarded!\n\
		-t use <trackname> in the 2nd column of each GFF/GTF output line\n\
		-o write the records into <outfile> instead of stdout\n\
		-T main output will be GTF instead of GFF3\n\
		@@ -184,9 +184,10 @@ class CTableField {
		FILE* ffasta=NULL;
		FILE* f_in=NULL;
		FILE* f_out=NULL;
		FILE* f_w=NULL; //fasta with spliced exons (transcripts)
		FILE* f_x=NULL; //fasta with spliced CDS
		FILE* f_y=NULL; //fasta with translated CDS
		FILE* f_w=NULL; //writing fasta with spliced exons (transcripts)
		int wPadding = 0; //padding for -w option
		FILE* f_x=NULL; //writing fasta with spliced CDS
		FILE* f_y=NULL; //wrting fasta with translated CDS

		bool wCDSonly=false;
		bool wNConly=false;
		@@ -697,7 +698,21 @@ bool process_transcript(GFastaDb& gfasta, GffObj& gffrec) {
		uint cds_start=0;
		uint cds_end=0;
		seglst.Clear();
		//TODO: ? if wPadding is set, temporarily change first and last exon coordinates ?!?
		// or perhaps getSpliced() should take an additional padding parameter ?!?
		int padLeft=0;
		int padRight=0;
		if (wPadding>0) {
		padLeft= (gffrec.start>(uint)wPadding) ? wPadding : gffrec.start - 1;
		int ediff=faseq->getseqlen()-gffrec.end;
		padRight=(wPadding>ediff) ? ediff : wPadding;
		gffrec.addPadding(padLeft, padRight);
		}
		char* exont=gffrec.getSpliced(faseq, false, &seqlen, &cds_start, &cds_end, &seglst);
		//restore exons to normal (remove padding)
		if (wPadding>0)
		gffrec.removePadding(padLeft, padRight);

		GStr defline(gffrec.getID());
		if (exont!=NULL) {
		if (gffrec.CDstart>0) {
		@@ -719,6 +734,13 @@ bool process_transcript(GFastaDb& gfasta, GffObj& gffrec) {
		defline.append("-");
		defline+=(int)gffrec.exons[i]->end;
		}
		if (wPadding>0) {
		defline.append(" padding:");
		defline.append(padLeft);
		defline+=(char)'\|';
		defline.append(padRight);
		}

		defline.append(" segs:");
		for (int i=0;i<seglst.Count();i++) {
		if (i>0) defline.append(",");
		@@ -727,6 +749,7 @@ bool process_transcript(GFastaDb& gfasta, GffObj& gffrec) {
		defline+=(int)seglst[i].end;
		}
		}

		if (gffrec.attrs!=NULL) {
		//append all attributes found for each transcripts
		for (int i=0;i<gffrec.attrs->Count();i++) {
		@@ -821,12 +844,13 @@ bool validateGffRec(GffObj* gffrec, GList<GffObj>* gfnew) {
		if (rt) {
		gffrec->setRefName(rt->new_name);
		}
		/* //no, do not discard non-matching entries, let them pass through!
		else {
		if (verbose)
		GMessage("Info: %s discarded due to reference %s not being mapped\n",
		gffrec->getID(), refname.chars());
		return false; //discard, ref seq not in the given translation table
		}
		}*/
		}
		if (gffloader.transcriptsOnly && gffrec->isDiscarded()) {
		//discard generic "locus" features with no other detailed subfeatures
		@@ -1006,7 +1030,7 @@ void printAsTable(FILE* f, GffObj* gfo, int* out_counter=NULL) {
		int main(int argc, char* argv[]) {
		GArgs args(argc, argv,
		"version;debug;merge;adj-stop;bed;in-bed;tlf;in-tlf;cluster-only;nc;cov-info;help;"
		"sort-alpha;keep-genes;keep-comments;keep-exon-attrs;force-exons;t-adopt;gene2exon;"
		"sort-alpha;keep-genes;w-add=;keep-comments;keep-exon-attrs;force-exons;t-adopt;gene2exon;"
		"ignore-locus;no-pseudo;table=sort-by=hvOUNHPWCVJMKQYTDARSZFGLEBm:g:i:r:s:l:t:o:w:x:y:d:");
		args.printError(USAGE, true);
		if (args.getOpt('h') \|\| args.getOpt("help")) {
		@@ -1207,13 +1231,18 @@ int main(int argc, char* argv[]) {
		//if (f_out==NULL) f_out=stdout;
		if (gfasta.fastaPath==NULL && (validCDSonly \|\| spliceCheck \|\| args.getOpt('w')!=NULL \|\| args.getOpt('x')!=NULL \|\| args.getOpt('y')!=NULL))
		GError("Error: -g option is required for options -w, -x, -y, -V, -N, -M !\n");

		openfw(f_w, args, 'w');
		openfw(f_x, args, 'x');
		openfw(f_y, args, 'y');
		s=args.getOpt("w-add");
		if (!s.is_empty()) {
		if (f_w==NULL) GError("Error: --w-add option requires -w option!\n");
		wPadding=s.asInt();
		}

		if (f_out==NULL && f_w==NULL && f_x==NULL && f_y==NULL && !covInfo)
		f_out=stdout;

		//if (f_y!=NULL \|\| f_x!=NULL) wCDSonly=true;
		//useBadCDS=useBadCDS \|\| (fgtfok==NULL && fgtfbad==NULL && f_y==NULL && f_x==NULL);