Merge pull request #6 from Koeng101/prime

Added Seqhash functions

commands.go

@@ -3,11 +3,13 @@ package main
 import (
 	"bufio"
 	"bytes"
+	"crypto"
 	"encoding/json"
 	"fmt"
 	"io"
 	"os"
 	"path/filepath"
+	"strings"
 	"sync"
 
 	"github.com/urfave/cli/v2"
@@ -40,16 +42,7 @@ parse them, and then spit out a similiarly named file with the .json extension.
 func convert(c *cli.Context) error {
 	if isPipe() {
 
-		var annotatedSequence AnnotatedSequence
-
-		// logic for determining input format, then parses accordingly.
-		if c.String("i") == "json" {
-			json.Unmarshal([]byte(stdinToString(os.Stdin)), &annotatedSequence)
-		} else if c.String("i") == "gbk" || c.String("i") == "gb" {
-			annotatedSequence = ParseGbk(stdinToString(os.Stdin))
-		} else if c.String("i") == "gff" {
-			annotatedSequence = ParseGff(stdinToString(os.Stdin))
-		}
+		annotatedSequence := parseStdin(c)
 
 		var output []byte
 
@@ -66,16 +59,8 @@ func convert(c *cli.Context) error {
 		//
 	} else {
 
-		var matches []string
-
-		//take all args and get their pattern matches.
-		for argIndex := 0; argIndex < c.Args().Len(); argIndex++ {
-			match, _ := filepath.Glob(c.Args().Get(argIndex))
-			matches = append(matches, match...)
-		}
-
-		//filtering pattern matches for duplicates.
-		matches = uniqueNonEmptyElementsOf(matches)
+		// gets glob pattern matches to determine which files to use.
+		matches := getMatches(c)
 
 		// TODO write basic check to see if input flag or all paths have accepted file extensions.
 
@@ -93,18 +78,7 @@ func convert(c *cli.Context) error {
 			// executing Go routine.
 			go func(match string) {
 				extension := filepath.Ext(match)
-				var annotatedSequence AnnotatedSequence
-
-				// determining which reader to use and parse into AnnotatedSequence struct.
-				if extension == ".gff" || c.String("i") == "gff" {
-					annotatedSequence = ReadGff(match)
-				} else if extension == ".gbk" || extension == ".gb" || c.String("i") == "gbk" || c.String("i") == "gb" {
-					annotatedSequence = ReadGbk(match)
-				} else if extension == ".json" || c.String("i") == "json" {
-					annotatedSequence = ReadJSON(match)
-				} else {
-					// TODO put default error handling here.
-				}
+				annotatedSequence := fileParser(c, match)
 
 				// determining output format and name, then writing out to name.
 				outputPath := match[0 : len(match)-len(extension)]
@@ -130,6 +104,95 @@ func convert(c *cli.Context) error {
 	return nil
 }
 
+/******************************************************************************
+
+hash currently has two modes. Pipe and fileio.
+
+The function isPipe() detects if input is coming from a pipe like:
+
+	cat data/bsub.gbk | poly hash -i gbk -o json > test.json
+
+In this case the output goes directly to standard out and can be redirected
+into a file.
+
+Without the "-o json" json flag only the hash is printed to stdout.
+
+to force all output to go to stdout use --stdout.
+
+If not from a pipe convert checks args for file patterns to find, then iterates
+over each matched file pattern to read in a file, then spit out the desired
+output.
+
+For example:
+
+	poly hash -o json *.gbk *.gff
+
+will read all files in a directory with ".gbk" or ".gff" as their extension
+parse them, and then spit out a similiarly named file with the .json extension along with their hashes.
+
+******************************************************************************/
+func hash(c *cli.Context) {
+
+	if isPipe() {
+		annotatedSequence := parseStdin(c)
+		sequenceHash := flagSwitchHash(c, annotatedSequence)
+		if c.String("o") == "json" {
+			annotatedSequence.Sequence.Hash = sequenceHash
+			annotatedSequence.Sequence.HashFunction = strings.ToUpper(c.String("t"))
+			output, _ := json.MarshalIndent(annotatedSequence, "", " ")
+			fmt.Print(string(output))
+		} else {
+			fmt.Print(sequenceHash)
+		}
+	} else {
+
+		// gets glob pattern matches to determine which files to use.
+		matches := getMatches(c)
+
+		// declaring wait group outside loop
+		var wg sync.WaitGroup
+
+		// concurrently iterate through each pattern match, read the file, output to new format.
+		for _, match := range matches {
+
+			// incrementing wait group for Go routine
+			wg.Add(1)
+
+			// executing Go routine.
+			go func(match string) {
+				extension := filepath.Ext(match)
+				annotatedSequence := fileParser(c, match)
+				sequenceHash := flagSwitchHash(c, annotatedSequence)
+				if c.String("o") == "json" {
+					annotatedSequence.Sequence.Hash = sequenceHash
+					annotatedSequence.Sequence.HashFunction = strings.ToUpper(c.String("t"))
+
+					if c.Bool("stdout") == true {
+						output, _ := json.MarshalIndent(annotatedSequence, "", " ")
+						fmt.Print(string(output))
+					} else {
+						outputPath := match[0 : len(match)-len(extension)]
+						WriteJSON(annotatedSequence, outputPath+".json")
+					}
+
+				} else {
+					fmt.Println(sequenceHash)
+				}
+
+				// decrementing wait group.
+				wg.Done()
+
+			}(match) // passing match to Go routine anonymous function.
+
+		}
+
+		// waiting outside for loop for Go routines so they can run concurrently.
+		wg.Wait()
+
+	}
+
+}
+
 // a simple helper function to convert an *os.File type into a string.
 func stdinToString(file *os.File) string {
 	var stringBuffer bytes.Buffer
@@ -173,3 +236,100 @@ func isPipe() bool {
 	}
 	return flag
 }
+
+// a simple helper function to take stdin from a pipe and parse it into an annotated sequence
+func parseStdin(c *cli.Context) AnnotatedSequence {
+	var annotatedSequence AnnotatedSequence
+
+	// logic for determining input format, then parses accordingly.
+	if c.String("i") == "json" {
+		json.Unmarshal([]byte(stdinToString(os.Stdin)), &annotatedSequence)
+	} else if c.String("i") == "gbk" || c.String("i") == "gb" {
+		annotatedSequence = ParseGbk(stdinToString(os.Stdin))
+	} else if c.String("i") == "gff" {
+		annotatedSequence = ParseGff(stdinToString(os.Stdin))
+	}
+	return annotatedSequence
+}
+
+// helper function to hash sequence based on flag using generic hash.
+func flagSwitchHash(c *cli.Context, annotatedSequence AnnotatedSequence) string {
+
+	var hashString string
+	switch strings.ToUpper(c.String("t")) {
+	case "MD5":
+		hashString = annotatedSequence.hash(crypto.MD5)
+	case "SHA1":
+		hashString = annotatedSequence.hash(crypto.SHA1)
+	case "SHA244":
+		hashString = annotatedSequence.hash(crypto.SHA224)
+	case "SHA256":
+		hashString = annotatedSequence.hash(crypto.SHA256)
+	case "SHA384":
+		hashString = annotatedSequence.hash(crypto.SHA384)
+	case "SHA512":
+		hashString = annotatedSequence.hash(crypto.SHA512)
+	case "RIPEMD160":
+		hashString = annotatedSequence.hash(crypto.RIPEMD160)
+	case "SHA3_224":
+		hashString = annotatedSequence.hash(crypto.SHA3_224)
+	case "SHA3_256":
+		hashString = annotatedSequence.hash(crypto.SHA3_256)
+	case "SHA3_384":
+		hashString = annotatedSequence.hash(crypto.SHA3_384)
+	case "SHA3_512":
+		hashString = annotatedSequence.hash(crypto.SHA3_512)
+	case "SHA512_224":
+		hashString = annotatedSequence.hash(crypto.SHA512_224)
+	case "SHA512_256":
+		hashString = annotatedSequence.hash(crypto.SHA512_256)
+	case "BLAKE2s_256":
+		hashString = annotatedSequence.hash(crypto.BLAKE2s_256)
+	case "BLAKE2b_256":
+		hashString = annotatedSequence.hash(crypto.BLAKE2b_256)
+	case "BLAKE2b_384":
+		hashString = annotatedSequence.hash(crypto.BLAKE2b_384)
+	case "BLAKE2b_512":
+		hashString = annotatedSequence.hash(crypto.BLAKE2b_512)
+	case "BLAKE3":
+		hashString = annotatedSequence.blake3Hash()
+	default:
+		break
+	}
+	return hashString
+}
+
+// helper function to get unique glob patterns from cli.context
+func getMatches(c *cli.Context) []string {
+	var matches []string
+
+	//take all args and get their pattern matches.
+	for argIndex := 0; argIndex < c.Args().Len(); argIndex++ {
+		match, _ := filepath.Glob(c.Args().Get(argIndex))
+		matches = append(matches, match...)
+	}
+
+	//filtering pattern matches for duplicates.
+	matches = uniqueNonEmptyElementsOf(matches)
+
+	return matches
+
+}
+
+// function to parse whatever file is at a matched path.
+func fileParser(c *cli.Context, match string) AnnotatedSequence {
+	extension := filepath.Ext(match)
+	var annotatedSequence AnnotatedSequence
+
+	// determining which reader to use and parse into AnnotatedSequence struct.
+	if extension == ".gff" || c.String("i") == "gff" {
+		annotatedSequence = ReadGff(match)
+	} else if extension == ".gbk" || extension == ".gb" || c.String("i") == "gbk" || c.String("i") == "gb" {
+		annotatedSequence = ReadGbk(match)
+	} else if extension == ".json" || c.String("i") == "json" {
+		annotatedSequence = ReadJSON(match)
+	} else {
+		// TODO put default error handling here.
+	}
+	return annotatedSequence
+}

commands_test.go

@@ -3,6 +3,7 @@ package main
 import (
 	"os"
 	"os/exec"
+	"strings"
 	"testing"
 
 	"github.com/google/go-cmp/cmp"
@@ -58,3 +59,37 @@ func TestConvert(t *testing.T) {
 	}
 
 }
+
+func TestHash(t *testing.T) {
+
+	puc19GbkBlake3Hash := "4031e1971acc8ff1bf0aa4ed623bc58beefc15e043075866a0854d592d80b28b"
+
+	// testing pipe input
+	command := "cat data/puc19.gbk | poly hash -i gbk"
+	hashOutput, _ := exec.Command("bash", "-c", command).Output()
+	hashOutputString := strings.TrimSpace(string(hashOutput))
+
+	if hashOutputString != puc19GbkBlake3Hash {
+		t.Errorf("TestHash for piped input has failed. Returned %q, want %q", hashOutputString, puc19GbkBlake3Hash)
+	}
+
+	// testing regular input
+	command = "poly hash data/puc19.gbk"
+	hashOutput, _ = exec.Command("bash", "-c", command).Output()
+	hashOutputString = strings.TrimSpace(string(hashOutput))
+
+	if hashOutputString != puc19GbkBlake3Hash {
+		t.Errorf("TestHash for regular input has failed. Returned %q, want %q", hashOutputString, puc19GbkBlake3Hash)
+	}
+
+	// testing json write output
+	command = "poly hash -o json data/puc19.gbk"
+	exec.Command("bash", "-c", command).Output()
+	hashOutputString = ReadJSON("data/puc19.json").Sequence.Hash
+	os.Remove("data/puc19.json")
+
+	if hashOutputString != puc19GbkBlake3Hash {
+		t.Errorf("TestHash for json write output has failed. Returned %q, want %q", hashOutputString, puc19GbkBlake3Hash)
+	}
+
+}

go.mod

@@ -6,5 +6,8 @@ require (
 	github.com/PuerkitoBio/goquery v1.5.1
 	github.com/google/go-cmp v0.4.1
 	github.com/pmezard/go-difflib v1.0.0
+	github.com/sergi/go-diff v1.1.0
 	github.com/urfave/cli/v2 v2.2.0
+	golang.org/x/crypto v0.0.0-20200604202706-70a84ac30bf9
+	lukechampine.com/blake3 v1.0.0
 )

go.sum

@@ -5,23 +5,47 @@ github.com/andybalholm/cascadia v1.1.0 h1:BuuO6sSfQNFRu1LppgbD25Hr2vLYW25JvxHs5z
 github.com/andybalholm/cascadia v1.1.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y=
 github.com/cpuguy83/go-md2man/v2 v2.0.0-20190314233015-f79a8a8ca69d h1:U+s90UTSYgptZMwQh2aRr3LuazLJIa+Pg3Kc1ylSYVY=
 github.com/cpuguy83/go-md2man/v2 v2.0.0-20190314233015-f79a8a8ca69d/go.mod h1:maD7wRr/U5Z6m/iR4s+kqSMx2CaBsrgA7czyZG/E6dU=
+github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
+github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/google/go-cmp v0.4.1 h1:/exdXoGamhu5ONeUJH0deniYLWYvQwW66yvlfiiKTu0=
 github.com/google/go-cmp v0.4.1/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/kr/pretty v0.1.0 h1:L/CwN0zerZDmRFUapSPitk6f+Q3+0za1rQkzVuMiMFI=
+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 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE=
+github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/russross/blackfriday/v2 v2.0.1 h1:lPqVAte+HuHNfhJ/0LC98ESWRz8afy9tM/0RK8m9o+Q=
 github.com/russross/blackfriday/v2 v2.0.1/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
+github.com/sergi/go-diff v1.1.0 h1:we8PVUC3FE2uYfodKH/nBHMSetSfHDR6scGdBi+erh0=
+github.com/sergi/go-diff v1.1.0/go.mod h1:STckp+ISIX8hZLjrqAeVduY0gWCT9IjLuqbuNXdaHfM=
 github.com/shurcooL/sanitized_anchor_name v1.0.0 h1:PdmoCO6wvbs+7yrJyMORt4/BmY5IYyJwS/kOiWx8mHo=
 github.com/shurcooL/sanitized_anchor_name v1.0.0/go.mod h1:1NzhyTcUVG4SuEtjjoZeVRXNmyL/1OwPU0+IJeTBvfc=
+github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
+github.com/stretchr/testify v1.4.0 h1:2E4SXV/wtOkTonXsotYi4li6zVWxYlZuYNCXe9XRJyk=
+github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
 github.com/urfave/cli/v2 v2.2.0 h1:JTTnM6wKzdA0Jqodd966MVj4vWbbquZykeX1sKbe2C4=
 github.com/urfave/cli/v2 v2.2.0/go.mod h1:SE9GqnLQmjVa0iPEY0f1w3ygNIYcIJ0OKPMoW2caLfQ=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/crypto v0.0.0-20200604202706-70a84ac30bf9 h1:vEg9joUBmeBcK9iSJftGNf3coIG4HqZElCPehJsfAYM=
+golang.org/x/crypto v0.0.0-20200604202706-70a84ac30bf9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
 golang.org/x/net v0.0.0-20180218175443-cbe0f9307d01/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/net v0.0.0-20200202094626-16171245cfb2 h1:CCH4IOTTfewWjGOlSp+zGcjutRKlBEZQ6wTn8ozI/nI=
 golang.org/x/net v0.0.0-20200202094626-16171245cfb2/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20190412213103-97732733099d h1:+R4KGOnez64A81RvjARKc4UT5/tI9ujCIVX+P5KiHuI=
+golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543 h1:E7g+9GITq07hpfrRu66IVDexMakfv52eLZ2CXBWiKr4=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15 h1:YR8cESwS4TdDjEe65xsg0ogRM/Nc3DYOhEAlW+xobZo=
+gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/yaml.v2 v2.2.4 h1:/eiJrUcujPVeJ3xlSWaiNi3uSVmDGBK1pDHUHAnao1I=
+gopkg.in/yaml.v2 v2.2.4/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+lukechampine.com/blake3 v1.0.0 h1:dNj1NVD7SLgkU7dykKjmmOSOTTx7ZmxnDyUyvxnQP2Q=
+lukechampine.com/blake3 v1.0.0/go.mod h1:e0XQzEQp6LtbXBhzYxRoh6s3kcmX+fMMg8sC9VgWloQ=