The parser for FASTA files in elPrep didn't accept empty lines before…

… new description lines. This is fixed.

cmd/util.go

@@ -37,7 +37,7 @@ const (
 	// ProgramName is "elprep"
 	ProgramName = "elprep"
 	// ProgramVersion is the version of the elprep binary
-	ProgramVersion = "4.1.2"
+	ProgramVersion = "4.1.3"
 	// ProgramURL is the repository for the elprep source code
 	ProgramURL = "http://github.com/exascience/elprep"
 )

fasta/fasta-files.go

@@ -1,5 +1,5 @@
 // elPrep: a high-performance tool for preparing SAM/BAM files.
-// Copyright (c) 2017, 2018 imec vzw.
+// Copyright (c) 2017-2019 imec vzw.
 
 // This program is free software: you can redistribute it and/or modify
 // it under the terms of the GNU Affero General Public License as
@@ -156,8 +156,11 @@ func ParseFasta(filename string, fai map[string]FaiReference, toUpper, toN bool)
 		return nil, fmt.Errorf("empty fasta file %v", filename)
 	}
 	b := scanner.Bytes()
-	if len(b) == 0 {
-		return nil, fmt.Errorf("invalid fasta file %v - empty line", filename)
+	for len(b) == 0 {
+		if !scanner.Scan() {
+			return nil, fmt.Errorf("empty fasta file %v", filename)
+		}
+		b = scanner.Bytes()
 	}
 	if b[0] != '>' {
 		return nil, fmt.Errorf("invalid fasta file %v - missing first header", filename)
@@ -167,10 +170,23 @@ func ParseFasta(filename string, fai map[string]FaiReference, toUpper, toN bool)
 	seq := initSeq(contig, fai)
 	fasta = make(map[string][]byte)
 
+scanLoop:
 	for scanner.Scan() {
 		b := scanner.Bytes()
 		if len(b) == 0 {
-			return nil, fmt.Errorf("invalid fasta file %v - empty line", filename)
+			if !scanner.Scan() {
+				break scanLoop
+			}
+			b = scanner.Bytes()
+			for len(b) == 0 {
+				if !scanner.Scan() {
+					break scanLoop
+				}
+				b = scanner.Bytes()
+			}
+			if b[0] != '>' {
+				return nil, fmt.Errorf("invalid fasta file %v - empty line", filename)
+			}
 		}
 		if b[0] == '>' {
 			fasta[contig] = seq
@@ -391,8 +407,11 @@ func OpenConcurrentFasta(filename, fai string, toUpper, toN bool) (fasta Concurr
 		return nil, fmt.Errorf("empty fasta file %v", filename)
 	}
 	b := scanner.Bytes()
-	if len(b) == 0 {
-		return nil, fmt.Errorf("invalid fasta file %v - empty line", filename)
+	for len(b) == 0 {
+		if !scanner.Scan() {
+			return nil, fmt.Errorf("empty fasta file %v", filename)
+		}
+		b = scanner.Bytes()
 	}
 	if b[0] != '>' {
 		return nil, fmt.Errorf("invalid fasta file %v - missing first header", filename)
@@ -409,10 +428,23 @@ func OpenConcurrentFasta(filename, fai string, toUpper, toN bool) (fasta Concurr
 		ref := faiMap[contig]
 		seq := make([]byte, 0, ref.Length)
 
+	scanLoop:
 		for scanner.Scan() {
 			b := scanner.Bytes()
 			if len(b) == 0 {
-				log.Fatal(fmt.Errorf("invalid fasta file %v - empty line", filename))
+				if !scanner.Scan() {
+					break scanLoop
+				}
+				b = scanner.Bytes()
+				for len(b) == 0 {
+					if !scanner.Scan() {
+						break scanLoop
+					}
+					b = scanner.Bytes()
+				}
+				if b[0] != '>' {
+					log.Fatal(fmt.Errorf("invalid fasta file %v - empty line", filename))
+				}
 			}
 			if b[0] == '>' {
 				entry := fasta[contig]

go.mod

@@ -1,8 +1,9 @@
 module github.com/exascience/elprep/v4
 
 require (
-	github.com/exascience/pargo v1.0.0
-	golang.org/x/sys v0.0.0-20181011152604-fa43e7bc11ba
-	gonum.org/v1/gonum v0.0.0-20181017130424-4c3d8206805c // indirect
-	gonum.org/v1/netlib v0.0.0-20181018051557-57e1e4db57a7 // indirect
+	github.com/exascience/pargo v1.0.1
+	golang.org/x/exp v0.0.0-20190426190305-956cc1757749 // indirect
+	golang.org/x/sys v0.0.0-20190429094411-2cc0cad0ac78
+	gonum.org/v1/gonum v0.0.0-20190424212039-2a1643c79af2 // indirect
+	gonum.org/v1/netlib v0.0.0-20190331212654-76723241ea4e // indirect
 )

go.sum

@@ -1,11 +1,30 @@
-github.com/exascience/pargo v1.0.0 h1:q2dUG8+KeoRPCHMEGJYG6O0OUOFWL5EqLA4a0+9r8mc=
-github.com/exascience/pargo v1.0.0/go.mod h1:S4dDBaMIgxplCJMMiIqd+TG7gHUo8h7dhLxsCWBiyWU=
-golang.org/x/exp v0.0.0-20180321215751-8460e604b9de h1:xSjD6HQTqT0H/k60N5yYBtnN1OEkVy7WIo/DYyxKRO0=
-golang.org/x/exp v0.0.0-20180321215751-8460e604b9de/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
-golang.org/x/sys v0.0.0-20181011152604-fa43e7bc11ba h1:nZJIJPGow0Kf9bU9QTc1U6OXbs/7Hu4e+cNv+hxH+Zc=
-golang.org/x/sys v0.0.0-20181011152604-fa43e7bc11ba/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
-golang.org/x/tools v0.0.0-20180525024113-a5b4c53f6e8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
-gonum.org/v1/gonum v0.0.0-20181017130424-4c3d8206805c h1:d95cUzTUV6w+XVqfxIr/EyaPdDUW569t0SYM+Bmvxao=
-gonum.org/v1/gonum v0.0.0-20181017130424-4c3d8206805c/go.mod h1:Y+Yx5eoAFn32cQvJDxZx5Dpnq+c3wtXuadVZAcxbbBo=
-gonum.org/v1/netlib v0.0.0-20181018051557-57e1e4db57a7 h1:biGE8p3sxXv+JdArdlsXEJZBPPFk51mQHVwOv6h1gnY=
-gonum.org/v1/netlib v0.0.0-20181018051557-57e1e4db57a7/go.mod h1:wa6Ws7BG/ESfp6dHfk7C6KdzKA7wR7u/rKwOGE66zvw=
+github.com/BurntSushi/xgb v0.0.0-20160522181843-27f122750802/go.mod h1:IVnqGOEym/WlBOVXweHU+Q+/VP0lqqI8lqeDx9IjBqo=
+github.com/exascience/pargo v1.0.1 h1:SFxXIEHI5fQ50b5aEzB7bRTBtxzva/uqCi4Yg/CkFLI=
+github.com/exascience/pargo v1.0.1/go.mod h1:S4dDBaMIgxplCJMMiIqd+TG7gHUo8h7dhLxsCWBiyWU=
+github.com/remyoudompheng/bigfft v0.0.0-20170806203942-52369c62f446/go.mod h1:uYEyJGbgTkfkS4+E/PavXkNJcbFIpEtjt2B0KDQ5+9M=
+golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/exp v0.0.0-20190125153040-c74c464bbbf2/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
+golang.org/x/exp v0.0.0-20190312203227-4b39c73a6495/go.mod h1:ZjyILWgesfNpC6sMxTJOJm9Kp84zZh5NQWvqDGG3Qr8=
+golang.org/x/exp v0.0.0-20190426190305-956cc1757749 h1:Bduxdpx1O6126WsH6F6NwKywZ/FPncphlTduoPxFG78=
+golang.org/x/exp v0.0.0-20190426190305-956cc1757749/go.mod h1:ZjyILWgesfNpC6sMxTJOJm9Kp84zZh5NQWvqDGG3Qr8=
+golang.org/x/image v0.0.0-20190227222117-0694c2d4d067/go.mod h1:kZ7UVZpmo3dzQBMxlp+ypCbDeSB+sBbTgSJuh5dn5js=
+golang.org/x/mobile v0.0.0-20190312151609-d3739f865fa6/go.mod h1:z+o9i4GpDbdi3rU15maQ/Ox0txvL9dWGYEHz965HBQE=
+golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20190312061237-fead79001313/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190429094411-2cc0cad0ac78 h1:ddnrbGOgFiC0zV+uaYoSkl0f47vnII6Zu426zWQrWkg=
+golang.org/x/sys v0.0.0-20190429094411-2cc0cad0ac78/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
+golang.org/x/tools v0.0.0-20190206041539-40960b6deb8e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20190312151545-0bb0c0a6e846/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
+gonum.org/v1/gonum v0.0.0-20190331200053-3d26580ed485/go.mod h1:2ltnJ7xHfj0zHS40VVPYEAAMTa3ZGguvHGBSJeRWqE0=
+gonum.org/v1/gonum v0.0.0-20190424212039-2a1643c79af2 h1:KTRD63fFTJiXuYJfxAI7BLujKCVAi7s9QD7rgzfY7MU=
+gonum.org/v1/gonum v0.0.0-20190424212039-2a1643c79af2/go.mod h1:2ltnJ7xHfj0zHS40VVPYEAAMTa3ZGguvHGBSJeRWqE0=
+gonum.org/v1/netlib v0.0.0-20190313105609-8cb42192e0e0/go.mod h1:wa6Ws7BG/ESfp6dHfk7C6KdzKA7wR7u/rKwOGE66zvw=
+gonum.org/v1/netlib v0.0.0-20190331212654-76723241ea4e h1:jRyg0XfpwWlhEV8mDfdNGBeSJM2fuyh9Yjrnd8kF2Ts=
+gonum.org/v1/netlib v0.0.0-20190331212654-76723241ea4e/go.mod h1:kS+toOQn6AQKjmKJ7gzohV1XkqsFehRA2FbsbkopSuQ=
+modernc.org/cc v1.0.0/go.mod h1:1Sk4//wdnYJiUIxnW8ddKpaOJCF37yAdqYnkxUpaYxw=
+modernc.org/golex v1.0.0/go.mod h1:b/QX9oBD/LhixY6NDh+IdGv17hgB+51fET1i2kPSmvk=
+modernc.org/mathutil v1.0.0/go.mod h1:wU0vUrJsVWBZ4P6e7xtFJEhFSNsfRLJ8H458uRjg03k=
+modernc.org/strutil v1.0.0/go.mod h1:lstksw84oURvj9y3tn8lGvRxyRC1S2+g5uuIzNfIOBs=
+modernc.org/xc v1.0.0/go.mod h1:mRNCo0bvLjGhHO9WsyuKVU4q0ceiDDDoEeWDJHrNx8I=