Add Parquet support to view, less, and a new parquet2tab

README.md

@@ -8,6 +8,26 @@ For more information, see here: [https://compgen.io/tabl](https://compgen.io/tab
 
 Note: The `tabl less` pager forces 256-color output to keep formatting/colors consistent on terminals like tmux/screen (especially on RHEL8).
 
+## Parquet
+
+`view`, `less`, and `parquet2tab` can read Parquet files. Parquet is detected
+automatically from the file's magic bytes, so no flag is needed:
+
+    tabl view data.parquet
+    tabl less data.parquet
+    tabl parquet2tab data.parquet > data.txt
+
+Use `--parquet` to force it for a file that isn't named/detected as one.
+
+The parquet schema supplies the header. Nested structs are flattened into dotted
+column names (`addr.city`), while lists and maps are rendered as JSON in a single
+cell. NULL cells are written as an empty value; use `--na=STRING` to change that
+(e.g. `--na=NA`).
+
+Because a parquet file's schema lives in a footer at the end of the file,
+reading one requires random access -- parquet cannot be read from a pipe, so a
+real file path is required.
+
 ## Examples
 
 ![Demo](https://github.com/compgen-io/tabl-docs/raw/master/assets/img/tabl-demo-2.gif)

cmd/less.go

@@ -13,6 +13,8 @@ func init() {
 	lessCmd.Flags().BoolVar(&NoHeader, "no-header", false, "File has no header")
 	lessCmd.Flags().BoolVar(&HeaderComment, "header-comment", false, "The header is the last commented line")
 	lessCmd.Flags().BoolVar(&IsCSV, "csv", false, "The file is a CSV file")
+	lessCmd.Flags().BoolVar(&IsParquet, "parquet", false, "The file is a Parquet file")
+	lessCmd.Flags().StringVar(&NAString, "na", "", "Value shown for NULL cells (Parquet)")
 	lessCmd.Flags().IntVar(&MinWidth, "min", 0, "Minimum column width")
 	lessCmd.Flags().IntVar(&MaxWidth, "max", 0, "Maximum column width")
 	rootCmd.AddCommand(lessCmd)
@@ -34,16 +36,11 @@ var lessCmd = &cobra.Command{
 		if len(args) == 0 {
 			args = []string{"-"}
 		}
-		var txt *textfile.DelimitedTextFile
-		if !IsCSV {
-			txt = textfile.NewTabFile(args[0])
-		} else {
-			txt = textfile.NewCSVFile(args[0])
+		txt, err := openReader(cmd, args[0])
+		if err != nil {
+			er(err)
 		}
 
-		txt = txt.WithNoHeader(NoHeader).
-			WithHeaderComment(HeaderComment)
-
 		textfile.NewTextPager(txt).
 			WithShowLineNum(ShowLineNum).
 			WithMaxWidth(MaxWidth).

cmd/parquet2tab.go

@@ -0,0 +1,52 @@
+package cmd
+
+import (
+	"fmt"
+	"os"
+
+	"github.com/compgen-io/tabl/textfile"
+	"github.com/spf13/cobra"
+)
+
+func init() {
+	parquet2TabCmd.Flags().StringVar(&NAString, "na", "", "Value to write for NULL cells")
+	rootCmd.AddCommand(parquet2TabCmd)
+}
+
+var parquet2TabCmd = &cobra.Command{
+	Use:   "parquet2tab [file]",
+	Short: "Convert a Parquet file to tab-delimited format",
+	Long: `Convert a Parquet file to tab-delimited format.
+
+The parquet schema becomes the header. Nested structs are flattened into
+dotted column names (addr.city), and lists and maps are written as JSON.
+
+NULL cells are written as an empty value unless --na is given.
+
+Note that parquet files can't be read from a pipe -- the schema lives in a
+footer at the end of the file, so a real file path is required.
+`,
+	Args: func(cmd *cobra.Command, args []string) error {
+		if len(args) == 0 {
+			return fmt.Errorf("Missing [file]")
+		}
+		if args[0] == "-" {
+			return textfile.ErrParquetStdin
+		}
+		_, err := os.Stat(args[0])
+		if os.IsNotExist(err) {
+			return fmt.Errorf("Missing file: %s", args[0])
+		}
+		return nil
+	},
+	Run: func(cmd *cobra.Command, args []string) {
+		pq := textfile.NewParquetFile(args[0]).WithNAString(NAString)
+		if err := pq.Open(); err != nil {
+			er(err)
+		}
+
+		if err := textfile.NewCSVExporter(pq).WriteFile(os.Stdout); err != nil {
+			er(err)
+		}
+	},
+}

cmd/root.go

@@ -1,15 +1,24 @@
 package cmd
 
 import (
+	"bytes"
 	"fmt"
+	"io"
 	"os"
 
+	"github.com/compgen-io/tabl/textfile"
 	"github.com/spf13/cobra"
 )
 
 // IsCSV -- the file is a CSV file
 var IsCSV bool
 
+// IsParquet -- the file is a Parquet file
+var IsParquet bool
+
+// NAString -- the value written for NULL cells (Parquet only)
+var NAString string
+
 // NoHeader -- the file has no header
 var NoHeader bool
 
@@ -45,3 +54,63 @@ func er(msg interface{}) {
 	fmt.Println("Error:", msg)
 	os.Exit(1)
 }
+
+// parquetMagic is the marker written at the start (and end) of a parquet file
+var parquetMagic = []byte("PAR1")
+
+// looksLikeParquet sniffs the leading magic bytes, in the same spirit as the
+// gzip detection the delimited reader already does.
+func looksLikeParquet(fname string) bool {
+	if fname == "-" {
+		return false
+	}
+
+	f, err := os.Open(fname)
+	if err != nil {
+		return false
+	}
+	defer f.Close()
+
+	buf := make([]byte, len(parquetMagic))
+	if _, err := io.ReadFull(f, buf); err != nil {
+		return false
+	}
+	return bytes.Equal(buf, parquetMagic)
+}
+
+// openReader builds the appropriate reader for a file. --parquet and --csv
+// force the format; otherwise we sniff for parquet and fall back to text.
+func openReader(cmd *cobra.Command, fname string) (textfile.RecordReader, error) {
+	if IsParquet || (!IsCSV && looksLikeParquet(fname)) {
+		if err := rejectTextOnlyFlags(cmd); err != nil {
+			return nil, err
+		}
+		pq := textfile.NewParquetFile(fname).WithNAString(NAString)
+		// open now so a bad path or corrupt file is reported before we start
+		// writing output
+		if err := pq.Open(); err != nil {
+			return nil, err
+		}
+		return pq, nil
+	}
+
+	var txt *textfile.DelimitedTextFile
+	if IsCSV {
+		txt = textfile.NewCSVFile(fname)
+	} else {
+		txt = textfile.NewTabFile(fname)
+	}
+
+	return txt.WithNoHeader(NoHeader).WithHeaderComment(HeaderComment), nil
+}
+
+// rejectTextOnlyFlags errors on flags that mean nothing for parquet input. We
+// check Changed so that only flags the user actually typed complain.
+func rejectTextOnlyFlags(cmd *cobra.Command) error {
+	for _, name := range []string{"csv", "no-header", "header-comment", "show-comments"} {
+		if f := cmd.Flags().Lookup(name); f != nil && f.Changed {
+			return fmt.Errorf("--%s cannot be used with parquet input", name)
+		}
+	}
+	return nil
+}

cmd/view.go

@@ -12,6 +12,8 @@ func init() {
 	viewCmd.Flags().BoolVarP(&ShowComments, "show-comments", "H", false, "Show comments")
 	viewCmd.Flags().BoolVarP(&ShowLineNum, "show-linenum", "L", false, "Show line number")
 	viewCmd.Flags().BoolVar(&IsCSV, "csv", false, "The file is a CSV file")
+	viewCmd.Flags().BoolVar(&IsParquet, "parquet", false, "The file is a Parquet file")
+	viewCmd.Flags().StringVar(&NAString, "na", "", "Value shown for NULL cells (Parquet)")
 	viewCmd.Flags().BoolVar(&HeaderComment, "header-comment", false, "The header is the last commented line")
 	viewCmd.Flags().BoolVar(&NoHeader, "no-header", false, "File has no header")
 	viewCmd.Flags().IntVar(&MinWidth, "min", 0, "Minimum column width")
@@ -35,16 +37,11 @@ var viewCmd = &cobra.Command{
 		if len(args) == 0 {
 			args = []string{"-"}
 		}
-		var txt *textfile.DelimitedTextFile
-		if !IsCSV {
-			txt = textfile.NewTabFile(args[0])
-		} else {
-			txt = textfile.NewCSVFile(args[0])
+		txt, err := openReader(cmd, args[0])
+		if err != nil {
+			er(err)
 		}
 
-		txt = txt.WithNoHeader(NoHeader).
-			WithHeaderComment(HeaderComment)
-
 		textfile.NewTextViewer(txt).
 			WithShowComments(ShowComments).
 			WithShowLineNum(ShowLineNum).

go.mod

@@ -5,12 +5,20 @@ go 1.22
 require (
 	github.com/gizak/termui/v3 v3.1.0
 	github.com/nsf/termbox-go v0.0.0-20190121233118-02980233997d
+	github.com/parquet-go/parquet-go v0.24.0
 	github.com/spf13/cobra v1.0.0
 )
 
 require (
+	github.com/andybalholm/brotli v1.1.0 // indirect
+	github.com/google/uuid v1.6.0 // indirect
 	github.com/inconshreveable/mousetrap v1.0.0 // indirect
-	github.com/mattn/go-runewidth v0.0.2 // indirect
+	github.com/klauspost/compress v1.17.9 // indirect
+	github.com/mattn/go-runewidth v0.0.15 // indirect
 	github.com/mitchellh/go-wordwrap v0.0.0-20150314170334-ad45545899c7 // indirect
+	github.com/olekukonko/tablewriter v0.0.5 // indirect
+	github.com/pierrec/lz4/v4 v4.1.21 // indirect
+	github.com/rivo/uniseg v0.4.7 // indirect
 	github.com/spf13/pflag v1.0.3 // indirect
+	golang.org/x/sys v0.21.0 // indirect
 )

go.sum

@@ -3,6 +3,8 @@ github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03
 github.com/OneOfOne/xxhash v1.2.2/go.mod h1:HSdplMjZKSmBqAxg5vPj2TmRDmfkzw+cTzAElWljhcU=
 github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
 github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
+github.com/andybalholm/brotli v1.1.0 h1:eLKJA0d02Lf0mVpIDgYnqXcUn0GqVmEFny3VuID1U3M=
+github.com/andybalholm/brotli v1.1.0/go.mod h1:sms7XGricyQI9K10gOSf56VKKWS4oLer58Q+mhRPtnY=
 github.com/armon/consul-api v0.0.0-20180202201655-eb2c6b5be1b6/go.mod h1:grANhF5doyWs3UAsr3K4I6qtAmlQcZDesFNEHPZAzj8=
 github.com/beorn7/perks v0.0.0-20180321164747-3a771d992973/go.mod h1:Dwedo/Wpr24TaqPxmxbtue+5NUziq4I4S80YR8gNf3Q=
 github.com/beorn7/perks v1.0.0/go.mod h1:KWe93zE9D1o94FZ5RNwFwVgaQK1VOXiVxmqh+CedLV8=
@@ -34,25 +36,33 @@ github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5y
 github.com/golang/protobuf v1.3.1/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
 github.com/google/btree v1.0.0/go.mod h1:lNA+9X1NB3Zf8V7Ke586lFgjr2dZNuvo3lPJSGZ5JPQ=
 github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5aqRK0M=
+github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
+github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/gorilla/websocket v1.4.0/go.mod h1:E7qHFY5m1UJ88s3WnNqhKjPHQ0heANvMoAMk2YaljkQ=
 github.com/grpc-ecosystem/go-grpc-middleware v1.0.0/go.mod h1:FiyG127CGDf3tlThmgyCl78X/SZQqEOJBCDaAfeWzPs=
 github.com/grpc-ecosystem/go-grpc-prometheus v1.2.0/go.mod h1:8NvIoxWQoOIhqOTXgfV/d3M/q6VIi02HzZEHgUlZvzk=
 github.com/grpc-ecosystem/grpc-gateway v1.9.0/go.mod h1:vNeuVxBJEsws4ogUvrchl83t/GYV9WGTSLVdBhOQFDY=
 github.com/hashicorp/hcl v1.0.0/go.mod h1:E5yfLk+7swimpb2L/Alb/PJmXilQ/rhwaUYs4T20WEQ=
+github.com/hexops/gotextdiff v1.0.3 h1:gitA9+qJrrTCsiCl7+kh75nPqQt1cx4ZkudSTLoUqJM=
+github.com/hexops/gotextdiff v1.0.3/go.mod h1:pSWU5MAI3yDq+fZBTazCSJysOMbxWL1BSow5/V2vxeg=
 github.com/inconshreveable/mousetrap v1.0.0 h1:Z8tu5sraLXCXIcARxBp/8cbvlwVa7Z1NHg9XEKhtSvM=
 github.com/inconshreveable/mousetrap v1.0.0/go.mod h1:PxqpIevigyE2G7u3NXJIT2ANytuPF1OarO4DADm73n8=
 github.com/jonboulle/clockwork v0.1.0/go.mod h1:Ii8DK3G1RaLaWxj9trq07+26W01tbo22gdxWY5EU2bo=
 github.com/julienschmidt/httprouter v1.2.0/go.mod h1:SYymIcj16QtmaHHD7aYtjjsJG7VTCxuUUipMqKk8s4w=
 github.com/kisielk/errcheck v1.1.0/go.mod h1:EZBBE59ingxPouuu3KfxchcWSUPOHkagtvWXihfKN4Q=
 github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
+github.com/klauspost/compress v1.17.9 h1:6KIumPrER1LHsvBVuDa0r5xaG0Es51mhhB9BQB2qeMA=
+github.com/klauspost/compress v1.17.9/go.mod h1:Di0epgTjJY877eYKx5yC51cX2A2Vl2ibi7bDH9ttBbw=
 github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
 github.com/kr/logfmt v0.0.0-20140226030751-b84e30acd515/go.mod h1:+0opPa2QZZtGFBFZlji/RkVcI2GknAs/DXo4wKdlNEc=
 github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
 github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
 github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
 github.com/magiconair/properties v1.8.0/go.mod h1:PppfXfuXeibc/6YijjN8zIbojt8czPbwD3XqdrwzmxQ=
-github.com/mattn/go-runewidth v0.0.2 h1:UnlwIPBGaTZfPQ6T1IGzPI0EkYAQmT9fAEJ/poFC63o=
 github.com/mattn/go-runewidth v0.0.2/go.mod h1:LwmH8dsx7+W8Uxz3IHJYH5QSwggIsqBzpuz5H//U1FU=
+github.com/mattn/go-runewidth v0.0.9/go.mod h1:H031xJmbD/WCDINGzjvQ9THkh0rPKHF+m2gUSrubnMI=
+github.com/mattn/go-runewidth v0.0.15 h1:UNAjwbU9l54TA3KzvqLGxwWjHmMgBUVhBiTjelZgg3U=
+github.com/mattn/go-runewidth v0.0.15/go.mod h1:Jdepj2loyihRzMpdS35Xk/zdY8IAYHsh153qUoGf23w=
 github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0=
 github.com/mitchellh/go-homedir v1.1.0/go.mod h1:SfyaCUpYCn1Vlf4IUYiD9fPX4A5wJrkLzIz1N1q0pr0=
 github.com/mitchellh/go-wordwrap v0.0.0-20150314170334-ad45545899c7 h1:DpOJ2HYzCv8LZP15IdmG+YdwD2luVPHITV96TkirNBM=
@@ -62,7 +72,13 @@ github.com/mwitkow/go-conntrack v0.0.0-20161129095857-cc309e4a2223/go.mod h1:qRW
 github.com/nsf/termbox-go v0.0.0-20190121233118-02980233997d h1:x3S6kxmy49zXVVyhcnrFqxvNVCBPb2KZ9hV2RBdS840=
 github.com/nsf/termbox-go v0.0.0-20190121233118-02980233997d/go.mod h1:IuKpRQcYE1Tfu+oAQqaLisqDeXgjyyltCfsaoYN18NQ=
 github.com/oklog/ulid v1.3.1/go.mod h1:CirwcVhetQ6Lv90oh/F+FBtV6XMibvdAFo93nm5qn4U=
+github.com/olekukonko/tablewriter v0.0.5 h1:P2Ga83D34wi1o9J6Wh1mRuqd4mF/x/lgBS7N7AbDhec=
+github.com/olekukonko/tablewriter v0.0.5/go.mod h1:hPp6KlRPjbx+hW8ykQs1w3UBbZlj6HuIJcUGPhkA7kY=
+github.com/parquet-go/parquet-go v0.24.0 h1:VrsifmLPDnas8zpoHmYiWDZ1YHzLmc7NmNwPGkI2JM4=
+github.com/parquet-go/parquet-go v0.24.0/go.mod h1:OqBBRGBl7+llplCvDMql8dEKaDqjaFA/VAPw+OJiNiw=
 github.com/pelletier/go-toml v1.2.0/go.mod h1:5z9KED0ma1S8pY6P1sdut58dfprrGBbd/94hg7ilaic=
+github.com/pierrec/lz4/v4 v4.1.21 h1:yOVMLb6qSIDP67pl/5F7RepeKYu/VmTyEXvuMI5d9mQ=
+github.com/pierrec/lz4/v4 v4.1.21/go.mod h1:gZWDp/Ze/IJXGXf23ltt2EXimqmTUXEy0GFuRQyBid4=
 github.com/pkg/errors v0.8.0/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/prometheus/client_golang v0.9.1/go.mod h1:7SWBe2y4D6OKWSNQJUaRYU/AaXPKyh/dDVn+NZz0KFw=
@@ -74,6 +90,9 @@ github.com/prometheus/common v0.4.0/go.mod h1:TNfzLD0ON7rHzMJeJkieUDPYmFC7Snx/y8
 github.com/prometheus/procfs v0.0.0-20181005140218-185b4288413d/go.mod h1:c3At6R/oaqEKCNdg8wHV1ftS6bRYblBhIjjI8uT2IGk=
 github.com/prometheus/procfs v0.0.0-20190507164030-5867b95ac084/go.mod h1:TjEm7ze935MbeOT/UhFTIMYKhuLP4wbCsTZCD3I8kEA=
 github.com/prometheus/tsdb v0.7.1/go.mod h1:qhTCs0VvXwvX/y3TZrWD7rabWM+ijKTux40TwIPHuXU=
+github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
+github.com/rivo/uniseg v0.4.7 h1:WUdvkW8uEhrYfLC4ZzdpI2ztxP1I582+49Oc5Mq64VQ=
+github.com/rivo/uniseg v0.4.7/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=
 github.com/rogpeppe/fastuuid v0.0.0-20150106093220-6724a57986af/go.mod h1:XWv6SoW27p1b0cqNHllgS5HIMJraePCO15w5zCzIWYg=
 github.com/russross/blackfriday/v2 v2.0.1/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
 github.com/shurcooL/sanitized_anchor_name v1.0.0/go.mod h1:1NzhyTcUVG4SuEtjjoZeVRXNmyL/1OwPU0+IJeTBvfc=
@@ -116,6 +135,8 @@ golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5h
 golang.org/x/sys v0.0.0-20181107165924-66b7b1311ac8/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20181116152217-5ac8a444bdc5/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.21.0 h1:rF+pYz3DAGSQAxAu1CbC7catZg4ebC4UIeIhKxBZvws=
+golang.org/x/sys v0.21.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/tools v0.0.0-20180221164845-07fd8470d635/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
@@ -125,6 +146,8 @@ google.golang.org/appengine v1.1.0/go.mod h1:EbEs0AVv82hx2wNQdGPgUI5lhzA/G0D9Ywl
 google.golang.org/genproto v0.0.0-20180817151627-c66870c02cf8/go.mod h1:JiN7NxoALGmiZfu7CAH4rXhgtRTLTxftemlI0sWmxmc=
 google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c=
 google.golang.org/grpc v1.21.0/go.mod h1:oYelfM1adQP15Ek0mdvEgi9Df8B9CZIaU1084ijfRaM=
+google.golang.org/protobuf v1.34.2 h1:6xV6lTsCfpGD21XK49h7MhtcApnLqkfYgPcdHftf6hg=
+google.golang.org/protobuf v1.34.2/go.mod h1:qYOHts0dSfpeUzUFpOMr/WGzszTmLH+DiWniOlNbLDw=
 gopkg.in/alecthomas/kingpin.v2 v2.2.6/go.mod h1:FMv+mEhP44yOT+4EoQTLFTRgOQ1FBLkstjWtayDeSgw=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=

textfile/csv_to_tab.go

@@ -9,12 +9,12 @@ import (
 
 // CSVExporter is used to export specific columns from a tab delimited file
 type CSVExporter struct {
-	txt          *DelimitedTextFile
+	txt          RecordReader
 	showComments bool
 }
 
 // NewCSVExporter - create a new text exporter
-func NewCSVExporter(f *DelimitedTextFile) *CSVExporter {
+func NewCSVExporter(f RecordReader) *CSVExporter {
 	return &CSVExporter{
 		txt:          f,
 		showComments: false,
@@ -36,6 +36,10 @@ func (tex *CSVExporter) WriteFile(out io.Writer) error {
 	for err == nil {
 		line, err = tex.txt.ReadLine()
 		if err != nil {
+			if err != io.EOF {
+				tex.txt.Close()
+				return err
+			}
 			break
 		}
 
@@ -48,7 +52,7 @@ func (tex *CSVExporter) WriteFile(out io.Writer) error {
 		}
 
 		if !wroteHeader {
-			if !tex.txt.noHeader {
+			if !tex.txt.NoHeader() {
 				err := tex.writeHeader(out)
 				if err != nil {
 					return err
@@ -68,10 +72,10 @@ func (tex *CSVExporter) WriteFile(out io.Writer) error {
 }
 
 func (tex *CSVExporter) writeHeader(out io.Writer) error {
-	if tex.txt.noHeader {
+	if tex.txt.NoHeader() {
 		return nil
 	}
-	for i, v := range tex.txt.Header {
+	for i, v := range tex.txt.GetHeader() {
 		if i > 0 {
 			fmt.Fprint(out, "\t")
 		}