Implement 'cid-fmt' utility.

cid-fmt/main.go

 package main
 
 import (
+	"bytes"
 	"fmt"
 	"os"
+	"strings"
 
 	c "github.com/ipfs/go-cid"
 
+	mb "github.com/multiformats/go-multibase"
 	mh "github.com/multiformats/go-multihash"
 )
 
+func usage() {
+	fmt.Fprintf(os.Stderr, "usage: %s [-b multibase-code] <fmt-str> <cid> ...\n\n", os.Args[0])
+	fmt.Fprintf(os.Stderr, "<fmt-str> is either 'prefix' or a printf style format string:\n%s", fmtRef)
+	os.Exit(1)
+}
+
+const fmtRef = `
+   %% literal %
+   %b multibase name 
+   %B multibase code
+   %v version string
+   %V version number
+   %c codec name
+   %C codec code
+   %h multihash name
+   %H multihash code
+   %L hash digest length
+   %m multihash encoded in base %b (with multibase prefix)
+   %M multihash encoded in base %b without multibase prefix
+   %d hash digest encoded in base %b (with multibase prefix)
+   %D hash digest encoded in base %b without multibase prefix
+   %s cid string encoded in base %b (1)
+   %s cid string encoded in base %b without multibase prefix
+   %P cid prefix: %v-%c-%h-%L
+
+(1) For CID version 0 the multibase must be base58btc and no prefix is
+used.  For Cid version 1 the multibase prefix is included.
+`
+
 func main() {
 	if len(os.Args) < 2 {
-		fmt.Fprintf(os.Stderr, "usage: %s prefix ...\n", os.Args[0])
-		os.Exit(1)
+		usage()
+	}
+	newBase := mb.Encoding(-1)
+	args := os.Args[1:]
+	if args[0] == "-b" {
+		if len(args) < 2 {
+			usage()
+		}
+		if len(args[1]) != 1 {
+			fmt.Fprintf(os.Stderr, "Error: Invalid multibase code: %s\n", args[1])
+		}
+		newBase = mb.Encoding(args[1][0])
+		args = args[2:]
+	}
+	if len(args) < 2 {
+		usage()
 	}
-	switch os.Args[1] {
+	fmtStr := args[0]
+	switch fmtStr {
 	case "prefix":
-		err := prefixCmd(os.Args[2:])
+		fmtStr = "%P"
+	default:
+		if strings.IndexByte(fmtStr, '%') == -1 {
+			fmt.Fprintf(os.Stderr, "Error: Invalid format string: %s\n", fmtStr)
+		}
+	}
+	for _, cidStr := range args[1:] {
+		base, cid, err := decode(cidStr)
+		if newBase != -1 {
+			base = newBase
+		}
 		if err != nil {
-			fmt.Fprintf(os.Stderr, "%v\n", err)
+			fmt.Fprintf(os.Stderr, "Error: %s: %v\n", cidStr, err)
+			fmt.Fprintf(os.Stdout, "!INVALID_CID!\n")
+			// Don't abort on a bad cid
+			continue
+		}
+		str, err := fmtCid(fmtStr, base, cid)
+		if err != nil {
+			fmt.Fprintf(os.Stderr, "Error: %v\n", err)
+			// An error here means a bad format string, no point in continuing
 			os.Exit(1)
 		}
-	default:
-		fmt.Fprintf(os.Stderr, "usage: %s prefix ...\n")
-		os.Exit(1)
+		fmt.Fprintf(os.Stdout, "%s\n", str)
 	}
 }
 
-func prefixCmd(args []string) error {
-	for _, cid := range args {
-		p, err := prefix(cid)
+func decode(v string) (mb.Encoding, *c.Cid, error) {
+	if len(v) < 2 {
+		return 0, nil, c.ErrCidTooShort
+	}
+
+	if len(v) == 46 && v[:2] == "Qm" {
+		hash, err := mh.FromB58String(v)
 		if err != nil {
-			return err
+			return 0, nil, err
 		}
-		fmt.Fprintf(os.Stdout, "%s\n", p)
+
+		return mb.Base58BTC, c.NewCidV0(hash), nil
 	}
-	return nil
-}
 
-func prefix(str string) (string, error) {
-	cid, err := c.Decode(str)
+	base, data, err := mb.Decode(v)
 	if err != nil {
-		return "", err
+		return 0, nil, err
 	}
+
+	cid, err := c.Cast(data)
+
+	return base, cid, err
+}
+
+const ERR_STR = "!ERROR!"
+
+func fmtCid(fmtStr string, base mb.Encoding, cid *c.Cid) (string, error) {
 	p := cid.Prefix()
-	return fmt.Sprintf("cidv%d-%s-%s-%d",
-		p.Version,
-		codecToStr(p.Codec),
-		mhToStr(p.MhType),
-		p.MhLength,
-	), nil
+	out := new(bytes.Buffer)
+	for i := 0; i < len(fmtStr); i++ {
+		if fmtStr[i] != '%' {
+			out.WriteByte(fmtStr[i])
+			continue
+		}
+		i++
+		if i >= len(fmtStr) {
+			return "", fmt.Errorf("premature end of format string")
+		}
+		switch fmtStr[i] {
+		case '%':
+			out.WriteByte('%')
+		case 'b': // base name
+			out.WriteString(baseToString(base))
+		case 'B': // base code
+			out.WriteByte(byte(base))
+		case 'v': // version string
+			fmt.Fprintf(out, "cidv%d", p.Version)
+		case 'V': // version num
+			fmt.Fprintf(out, "%d", p.Version)
+		case 'c': // codec name
+			out.WriteString(codecToString(p.Codec))
+		case 'C': // codec code
+			fmt.Fprintf(out, "%d", p.Codec)
+		case 'h': // hash fun name
+			out.WriteString(hashToString(p.MhType))
+		case 'H': // hash fun code
+			fmt.Fprintf(out, "%d", p.MhType)
+		case 'L': // hash length
+			fmt.Fprintf(out, "%d", p.MhLength)
+		case 'm', 'M': // multihash encoded in base %b
+			out.WriteString(encode(base, cid.Hash(), fmtStr[i] == 'M'))
+		case 'd', 'D': // hash digest encoded in base %b
+			dec, err := mh.Decode(cid.Hash())
+			if err != nil {
+				out.WriteString(ERR_STR)
+				fmt.Fprintf(os.Stderr, "Error: %v\n", err)
+				continue
+			}
+			out.WriteString(encode(base, dec.Digest, fmtStr[i] == 'D'))
+		case 's': // cid string encoded in base %b
+			str, err := cid.StringOfBase(base)
+			if err != nil {
+				out.WriteString(ERR_STR)
+				fmt.Fprintf(os.Stderr, "Error: %v\n", err)
+				continue
+			}
+			out.WriteString(str)
+		case 'S': // cid string without base prefix
+			out.WriteString(encode(base, cid.Bytes(), true))
+		case 'P': // prefix
+			fmt.Fprintf(out, "cidv%d-%s-%s-%d",
+				p.Version,
+				codecToString(p.Codec),
+				hashToString(p.MhType),
+				p.MhLength,
+			)
+		default:
+			return "", fmt.Errorf("unrecognized specifier in format string: %c\n", fmtStr[i])
+		}
+
+	}
+	return out.String(), nil
 }
 
-func codecToStr(num uint64) string {
+func baseToString(base mb.Encoding) string {
+	// FIXME: Use lookup tables when they are added to go-multibase
+	switch base {
+	case mb.Base58BTC:
+		return "base58btc"
+	default:
+		return fmt.Sprintf("base?%c", base)
+	}
+}
+
+func codecToString(num uint64) string {
 	name, ok := c.CodecToStr[num]
 	if !ok {
-		return fmt.Sprintf("c?%d", num)
+		return fmt.Sprintf("codec?%d", num)
 	}
 	return name
 }
 
-func mhToStr(num uint64) string {
+func hashToString(num uint64) string {
 	name, ok := mh.Codes[num]
 	if !ok {
-		return fmt.Sprintf("h?%d", num)
+		return fmt.Sprintf("hash?%d", num)
 	}
 	return name
 }
+
+func encode(base mb.Encoding, data []byte, strip bool) string {
+	str, err := mb.Encode(base, data)
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "Error: %v\n", err)
+		return ERR_STR
+	}
+	if strip {
+		return str[1:]
+	}
+	return str
+}

cid-fmt/main_test.go

+package main
+
+import (
+	"fmt"
+	"testing"
+
+	mb "github.com/multiformats/go-multibase"
+)
+
+func TestFmt(t *testing.T) {
+	cids := map[string]string{
+		"cidv0": "QmUNLLsPACCz1vLxQVkXqqLX5R1X345qqfHbsf67hvA3Nn",
+		"cidv1": "zdj7WfLr9DhLrb1hsoSi4fSdjjxuZmeqgEtBPWxMLtPbDNbFD",
+	}
+	tests := []struct {
+		cidId   string
+		newBase mb.Encoding
+		fmtStr  string
+		result  string
+	}{
+		{"cidv0", -1, "%P", "cidv0-protobuf-sha2-256-32"},
+		{"cidv0", -1, "%b-%v-%c-%h-%L", "base58btc-cidv0-protobuf-sha2-256-32"},
+		{"cidv0", -1, "%s", "QmUNLLsPACCz1vLxQVkXqqLX5R1X345qqfHbsf67hvA3Nn"},
+		{"cidv0", -1, "%S", "QmUNLLsPACCz1vLxQVkXqqLX5R1X345qqfHbsf67hvA3Nn"},
+		{"cidv0", -1, "ver#%V/#%C/#%H/%L", "ver#0/#112/#18/32"},
+		{"cidv0", -1, "%m", "zQmUNLLsPACCz1vLxQVkXqqLX5R1X345qqfHbsf67hvA3Nn"},
+		{"cidv0", -1, "%M", "QmUNLLsPACCz1vLxQVkXqqLX5R1X345qqfHbsf67hvA3Nn"},
+		{"cidv0", -1, "%d", "z72gdmFAgRzYHkJzKiL8MgMMRW3BTSCGyDHroPxJbxMJn"},
+		{"cidv0", -1, "%D", "72gdmFAgRzYHkJzKiL8MgMMRW3BTSCGyDHroPxJbxMJn"},
+		{"cidv0", 'B', "%S", "CIQFTFEEHEDF6KLBT32BFAGLXEZL4UWFNWM4LFTLMXQBCERZ6CMLX3Y"},
+		{"cidv0", 'B', "%B%S", "BCIQFTFEEHEDF6KLBT32BFAGLXEZL4UWFNWM4LFTLMXQBCERZ6CMLX3Y"},
+		{"cidv1", -1, "%P", "cidv1-protobuf-sha2-256-32"},
+		{"cidv1", -1, "%b-%v-%c-%h-%L", "base58btc-cidv1-protobuf-sha2-256-32"},
+		{"cidv1", -1, "%s", "zdj7WfLr9DhLrb1hsoSi4fSdjjxuZmeqgEtBPWxMLtPbDNbFD"},
+		{"cidv1", -1, "%S", "dj7WfLr9DhLrb1hsoSi4fSdjjxuZmeqgEtBPWxMLtPbDNbFD"},
+		{"cidv1", -1, "ver#%V/#%C/#%H/%L", "ver#1/#112/#18/32"},
+		{"cidv1", -1, "%m", "zQmYFbmndVP7QqAVWyKhpmMuQHMaD88pkK57RgYVimmoh5H"},
+		{"cidv1", -1, "%M", "QmYFbmndVP7QqAVWyKhpmMuQHMaD88pkK57RgYVimmoh5H"},
+		{"cidv1", -1, "%d", "zAux4gVVsLRMXtsZ9fd3tFEZN4jGYB6kP37fgoZNTc11H"},
+		{"cidv1", -1, "%D", "Aux4gVVsLRMXtsZ9fd3tFEZN4jGYB6kP37fgoZNTc11H"},
+		{"cidv1", 'B', "%s", "bAFYBEIETJGSRL3EQPQPCABV3G6IUBYTSIFVQ24XRRHD3JUETSKLTGQ7DJA"},
+		// note: ^ "bAFYB.." should probably be "BAFYB.." (upper case b)
+		{"cidv1", 'B', "%S", "AFYBEIETJGSRL3EQPQPCABV3G6IUBYTSIFVQ24XRRHD3JUETSKLTGQ7DJA"},
+		{"cidv1", 'B', "%B%S", "BAFYBEIETJGSRL3EQPQPCABV3G6IUBYTSIFVQ24XRRHD3JUETSKLTGQ7DJA"},
+	}
+	for _, tc := range tests {
+		name := fmt.Sprintf("%s/%s", tc.cidId, tc.fmtStr)
+		if tc.newBase != -1 {
+			name = fmt.Sprintf("%s/%c", name, tc.newBase)
+		}
+		cidStr := cids[tc.cidId]
+		t.Run(name, func(t *testing.T) {
+			testFmt(t, cidStr, tc.newBase, tc.fmtStr, tc.result)
+		})
+	}
+}
+
+func testFmt(t *testing.T, cidStr string, newBase mb.Encoding, fmtStr string, result string) {
+	base, cid, err := decode(cidStr)
+	if newBase != -1 {
+		base = newBase
+	}
+	if err != nil {
+		t.Fatal(err)
+	}
+	str, err := fmtCid(fmtStr, base, cid)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if str != result {
+		t.Error(fmt.Sprintf("expected: %s; but got: %s", result, str))
+	}
+}