Implement md5c function, slower than Golang's implementation

keeping it in repo to make further improvements and also rename

        minio-hash ---> crypto

Makefile

@@ -22,6 +22,7 @@ build-cpu:
 
 build-md5:
 	@godep go test -race -coverprofile=cover.out github.com/minio-io/minio/pkgs/crypto/md5/
+	@godep go test -race -coverprofile=cover.out github.com/minio-io/minio/pkgs/crypto/md5c/
 
 build-sha1:
 	@godep go test -race -coverprofile=cover.out github.com/minio-io/minio/pkgs/crypto/sha1/
@@ -58,7 +59,7 @@ cover: build-erasure build-signify build-split build-crc32c build-cpu build-scsi
 install: build-erasure
 	@godep go install github.com/minio-io/minio/cmd/minio && echo "Installed minio into ${GOPATH}/bin"
 	@godep go install github.com/minio-io/minio/cmd/minio-cli && echo "Installed minio-cli into ${GOPATH}/bin"
-	@godep go install github.com/minio-io/minio/cmd/minio-hash && echo "Installed minio-hash into ${GOPATH}/bin"
+	@godep go install github.com/minio-io/minio/cmd/crypto && echo "Installed crypto into ${GOPATH}/bin"
 
 save: restore
 	@godep save ./...

cmd/crypto/.gitignore

@@ -0,0 +1 @@
+crypto

cmd/crypto/crypto.go

@@ -24,8 +24,8 @@ import (
 
 func main() {
 	app := cli.NewApp()
-	app.Name = "minio-hash"
+	app.Name = "crypto"
-	app.Usage = ""
+	app.Usage = "calculate cryptosum on a given stream"
 	app.Commands = Options
 	app.Run(os.Args)
 }

cmd/crypto/crypto.md

@@ -0,0 +1,33 @@
+% MINIO(1) Minio Manual
+% Minio community
+% December 2014
+# NAME
+crypto - calculate crypto sum on a stream
+
+# SYNOPSIS
+
+# DESCRIPTION
+```sh
+NAME:
+   crypto - calculate cryptosum on a given stream
+
+USAGE:
+   crypto [global options] command [command options] [arguments...]
+
+VERSION:
+   0.0.0
+
+COMMANDS:
+   md5sum
+   sha1sum
+   sha256sum
+   sha512sum
+   help, h      Shows a list of commands or help for one command
+
+GLOBAL OPTIONS:
+   --help, -h           show help
+   --version, -v        print the version
+```
+# EXAMPLES
+
+# AUTHORS

cmd/minio-hash/minio-hash.md

@@ -1,13 +0,0 @@
-% MINIO(1) Minio Manual
-% Minio community
-% December 2014
-# NAME
-md5sum - 
-
-# SYNOPSIS
-
-# DESCRIPTION
-
-# EXAMPLES
-
-# AUTHORS

pkgs/crypto/md5/md5.go

@@ -8,10 +8,15 @@ import (
 func Sum(reader io.Reader) ([]byte, error) {
 	hash := md5.New()
 	var err error
+	var length int
 	for err == nil {
-		length := 0
 		byteBuffer := make([]byte, 1024*1024)
 		length, err = reader.Read(byteBuffer)
+		// While hash.Write() wouldn't mind a Nil byteBuffer
+		// It is necessary for us to verify this and break
+		if length == 0 {
+			break
+		}
 		byteBuffer = byteBuffer[0:length]
 		hash.Write(byteBuffer)
 	}

pkgs/crypto/md5c/md5.c

@@ -0,0 +1,291 @@
+/*
+ * This is an OpenSSL-compatible implementation of the RSA Data Security, Inc.
+ * MD5 Message-Digest Algorithm (RFC 1321).
+ *
+ * Homepage:
+ * http://openwall.info/wiki/people/solar/software/public-domain-source-code/md5
+ *
+ * Author:
+ * Alexander Peslyak, better known as Solar Designer <solar at openwall.com>
+ *
+ * This software was written by Alexander Peslyak in 2001.  No copyright is
+ * claimed, and the software is hereby placed in the public domain.
+ * In case this attempt to disclaim copyright and place the software in the
+ * public domain is deemed null and void, then the software is
+ * Copyright (c) 2001 Alexander Peslyak and it is hereby released to the
+ * general public under the following terms:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted.
+ *
+ * There's ABSOLUTELY NO WARRANTY, express or implied.
+ *
+ * (This is a heavily cut-down "BSD license".)
+ *
+ * This differs from Colin Plumb's older public domain implementation in that
+ * no exactly 32-bit integer data type is required (any 32-bit or wider
+ * unsigned integer data type will do), there's no compile-time endianness
+ * configuration, and the function prototypes match OpenSSL's.  No code from
+ * Colin Plumb's implementation has been reused; this comment merely compares
+ * the properties of the two independent implementations.
+ *
+ * The primary goals of this implementation are portability and ease of use.
+ * It is meant to be fast, but not as fast as possible.  Some known
+ * optimizations are not included to reduce source code size and avoid
+ * compile-time configuration.
+ */
+
+#include <string.h>
+#include "md5.h"
+
+/*
+ * The basic MD5 functions.
+ *
+ * F and G are optimized compared to their RFC 1321 definitions for
+ * architectures that lack an AND-NOT instruction, just like in Colin Plumb's
+ * implementation.
+ */
+#define F(x, y, z)			((z) ^ ((x) & ((y) ^ (z))))
+#define G(x, y, z)			((y) ^ ((z) & ((x) ^ (y))))
+#define H(x, y, z)			(((x) ^ (y)) ^ (z))
+#define H2(x, y, z)			((x) ^ ((y) ^ (z)))
+#define I(x, y, z)			((y) ^ ((x) | ~(z)))
+
+/*
+ * The MD5 transformation for all four rounds.
+ */
+#define STEP(f, a, b, c, d, x, t, s) \
+	(a) += f((b), (c), (d)) + (x) + (t); \
+	(a) = (((a) << (s)) | (((a) & 0xffffffff) >> (32 - (s)))); \
+	(a) += (b);
+
+/*
+ * SET reads 4 input bytes in little-endian byte order and stores them
+ * in a properly aligned word in host byte order.
+ *
+ * The check for little-endian architectures that tolerate unaligned
+ * memory accesses is just an optimization.  Nothing will break if it
+ * doesn't work.
+ */
+#if defined(__i386__) || defined(__x86_64__) || defined(__vax__)
+#define SET(n) \
+	(*(MD5_u32plus *)&ptr[(n) * 4])
+#define GET(n) \
+	SET(n)
+#else
+#define SET(n) \
+	(ctx->block[(n)] = \
+	(MD5_u32plus)ptr[(n) * 4] | \
+	((MD5_u32plus)ptr[(n) * 4 + 1] << 8) | \
+	((MD5_u32plus)ptr[(n) * 4 + 2] << 16) | \
+	((MD5_u32plus)ptr[(n) * 4 + 3] << 24))
+#define GET(n) \
+	(ctx->block[(n)])
+#endif
+
+/*
+ * This processes one or more 64-byte data blocks, but does NOT update
+ * the bit counters.  There are no alignment requirements.
+ */
+static const void *body(MD5_CTX *ctx, const void *data, unsigned long size)
+{
+	const unsigned char *ptr;
+	MD5_u32plus a, b, c, d;
+	MD5_u32plus saved_a, saved_b, saved_c, saved_d;
+
+	ptr = (const unsigned char *)data;
+
+	a = ctx->a;
+	b = ctx->b;
+	c = ctx->c;
+	d = ctx->d;
+
+	do {
+		saved_a = a;
+		saved_b = b;
+		saved_c = c;
+		saved_d = d;
+
+/* Round 1 */
+		STEP(F, a, b, c, d, SET(0), 0xd76aa478, 7)
+		STEP(F, d, a, b, c, SET(1), 0xe8c7b756, 12)
+		STEP(F, c, d, a, b, SET(2), 0x242070db, 17)
+		STEP(F, b, c, d, a, SET(3), 0xc1bdceee, 22)
+		STEP(F, a, b, c, d, SET(4), 0xf57c0faf, 7)
+		STEP(F, d, a, b, c, SET(5), 0x4787c62a, 12)
+		STEP(F, c, d, a, b, SET(6), 0xa8304613, 17)
+		STEP(F, b, c, d, a, SET(7), 0xfd469501, 22)
+		STEP(F, a, b, c, d, SET(8), 0x698098d8, 7)
+		STEP(F, d, a, b, c, SET(9), 0x8b44f7af, 12)
+		STEP(F, c, d, a, b, SET(10), 0xffff5bb1, 17)
+		STEP(F, b, c, d, a, SET(11), 0x895cd7be, 22)
+		STEP(F, a, b, c, d, SET(12), 0x6b901122, 7)
+		STEP(F, d, a, b, c, SET(13), 0xfd987193, 12)
+		STEP(F, c, d, a, b, SET(14), 0xa679438e, 17)
+		STEP(F, b, c, d, a, SET(15), 0x49b40821, 22)
+
+/* Round 2 */
+		STEP(G, a, b, c, d, GET(1), 0xf61e2562, 5)
+		STEP(G, d, a, b, c, GET(6), 0xc040b340, 9)
+		STEP(G, c, d, a, b, GET(11), 0x265e5a51, 14)
+		STEP(G, b, c, d, a, GET(0), 0xe9b6c7aa, 20)
+		STEP(G, a, b, c, d, GET(5), 0xd62f105d, 5)
+		STEP(G, d, a, b, c, GET(10), 0x02441453, 9)
+		STEP(G, c, d, a, b, GET(15), 0xd8a1e681, 14)
+		STEP(G, b, c, d, a, GET(4), 0xe7d3fbc8, 20)
+		STEP(G, a, b, c, d, GET(9), 0x21e1cde6, 5)
+		STEP(G, d, a, b, c, GET(14), 0xc33707d6, 9)
+		STEP(G, c, d, a, b, GET(3), 0xf4d50d87, 14)
+		STEP(G, b, c, d, a, GET(8), 0x455a14ed, 20)
+		STEP(G, a, b, c, d, GET(13), 0xa9e3e905, 5)
+		STEP(G, d, a, b, c, GET(2), 0xfcefa3f8, 9)
+		STEP(G, c, d, a, b, GET(7), 0x676f02d9, 14)
+		STEP(G, b, c, d, a, GET(12), 0x8d2a4c8a, 20)
+
+/* Round 3 */
+		STEP(H, a, b, c, d, GET(5), 0xfffa3942, 4)
+		STEP(H2, d, a, b, c, GET(8), 0x8771f681, 11)
+		STEP(H, c, d, a, b, GET(11), 0x6d9d6122, 16)
+		STEP(H2, b, c, d, a, GET(14), 0xfde5380c, 23)
+		STEP(H, a, b, c, d, GET(1), 0xa4beea44, 4)
+		STEP(H2, d, a, b, c, GET(4), 0x4bdecfa9, 11)
+		STEP(H, c, d, a, b, GET(7), 0xf6bb4b60, 16)
+		STEP(H2, b, c, d, a, GET(10), 0xbebfbc70, 23)
+		STEP(H, a, b, c, d, GET(13), 0x289b7ec6, 4)
+		STEP(H2, d, a, b, c, GET(0), 0xeaa127fa, 11)
+		STEP(H, c, d, a, b, GET(3), 0xd4ef3085, 16)
+		STEP(H2, b, c, d, a, GET(6), 0x04881d05, 23)
+		STEP(H, a, b, c, d, GET(9), 0xd9d4d039, 4)
+		STEP(H2, d, a, b, c, GET(12), 0xe6db99e5, 11)
+		STEP(H, c, d, a, b, GET(15), 0x1fa27cf8, 16)
+		STEP(H2, b, c, d, a, GET(2), 0xc4ac5665, 23)
+
+/* Round 4 */
+		STEP(I, a, b, c, d, GET(0), 0xf4292244, 6)
+		STEP(I, d, a, b, c, GET(7), 0x432aff97, 10)
+		STEP(I, c, d, a, b, GET(14), 0xab9423a7, 15)
+		STEP(I, b, c, d, a, GET(5), 0xfc93a039, 21)
+		STEP(I, a, b, c, d, GET(12), 0x655b59c3, 6)
+		STEP(I, d, a, b, c, GET(3), 0x8f0ccc92, 10)
+		STEP(I, c, d, a, b, GET(10), 0xffeff47d, 15)
+		STEP(I, b, c, d, a, GET(1), 0x85845dd1, 21)
+		STEP(I, a, b, c, d, GET(8), 0x6fa87e4f, 6)
+		STEP(I, d, a, b, c, GET(15), 0xfe2ce6e0, 10)
+		STEP(I, c, d, a, b, GET(6), 0xa3014314, 15)
+		STEP(I, b, c, d, a, GET(13), 0x4e0811a1, 21)
+		STEP(I, a, b, c, d, GET(4), 0xf7537e82, 6)
+		STEP(I, d, a, b, c, GET(11), 0xbd3af235, 10)
+		STEP(I, c, d, a, b, GET(2), 0x2ad7d2bb, 15)
+		STEP(I, b, c, d, a, GET(9), 0xeb86d391, 21)
+
+		a += saved_a;
+		b += saved_b;
+		c += saved_c;
+		d += saved_d;
+
+		ptr += 64;
+	} while (size -= 64);
+
+	ctx->a = a;
+	ctx->b = b;
+	ctx->c = c;
+	ctx->d = d;
+
+	return ptr;
+}
+
+void MD5_Init(MD5_CTX *ctx)
+{
+	ctx->a = 0x67452301;
+	ctx->b = 0xefcdab89;
+	ctx->c = 0x98badcfe;
+	ctx->d = 0x10325476;
+
+	ctx->lo = 0;
+	ctx->hi = 0;
+}
+
+void MD5_Update(MD5_CTX *ctx, const void *data, unsigned long size)
+{
+	MD5_u32plus saved_lo;
+	unsigned long used, available;
+
+	saved_lo = ctx->lo;
+	if ((ctx->lo = (saved_lo + size) & 0x1fffffff) < saved_lo)
+		ctx->hi++;
+	ctx->hi += size >> 29;
+
+	used = saved_lo & 0x3f;
+
+	if (used) {
+		available = 64 - used;
+
+		if (size < available) {
+			memcpy(&ctx->buffer[used], data, size);
+			return;
+		}
+
+		memcpy(&ctx->buffer[used], data, available);
+		data = (const unsigned char *)data + available;
+		size -= available;
+		body(ctx, ctx->buffer, 64);
+	}
+
+	if (size >= 64) {
+		data = body(ctx, data, size & ~(unsigned long)0x3f);
+		size &= 0x3f;
+	}
+
+	memcpy(ctx->buffer, data, size);
+}
+
+void MD5_Final(unsigned char *result, MD5_CTX *ctx)
+{
+	unsigned long used, available;
+
+	used = ctx->lo & 0x3f;
+
+	ctx->buffer[used++] = 0x80;
+
+	available = 64 - used;
+
+	if (available < 8) {
+		memset(&ctx->buffer[used], 0, available);
+		body(ctx, ctx->buffer, 64);
+		used = 0;
+		available = 64;
+	}
+
+	memset(&ctx->buffer[used], 0, available - 8);
+
+	ctx->lo <<= 3;
+	ctx->buffer[56] = ctx->lo;
+	ctx->buffer[57] = ctx->lo >> 8;
+	ctx->buffer[58] = ctx->lo >> 16;
+	ctx->buffer[59] = ctx->lo >> 24;
+	ctx->buffer[60] = ctx->hi;
+	ctx->buffer[61] = ctx->hi >> 8;
+	ctx->buffer[62] = ctx->hi >> 16;
+	ctx->buffer[63] = ctx->hi >> 24;
+
+	body(ctx, ctx->buffer, 64);
+
+	result[0] = ctx->a;
+	result[1] = ctx->a >> 8;
+	result[2] = ctx->a >> 16;
+	result[3] = ctx->a >> 24;
+	result[4] = ctx->b;
+	result[5] = ctx->b >> 8;
+	result[6] = ctx->b >> 16;
+	result[7] = ctx->b >> 24;
+	result[8] = ctx->c;
+	result[9] = ctx->c >> 8;
+	result[10] = ctx->c >> 16;
+	result[11] = ctx->c >> 24;
+	result[12] = ctx->d;
+	result[13] = ctx->d >> 8;
+	result[14] = ctx->d >> 16;
+	result[15] = ctx->d >> 24;
+
+	memset(ctx, 0, sizeof(*ctx));
+}

pkgs/crypto/md5c/md5.h

@@ -0,0 +1,43 @@
+/*
+ * This is an OpenSSL-compatible implementation of the RSA Data Security, Inc.
+ * MD5 Message-Digest Algorithm (RFC 1321).
+ *
+ * Homepage:
+ * http://openwall.info/wiki/people/solar/software/public-domain-source-code/md5
+ *
+ * Author:
+ * Alexander Peslyak, better known as Solar Designer <solar at openwall.com>
+ *
+ * This software was written by Alexander Peslyak in 2001.  No copyright is
+ * claimed, and the software is hereby placed in the public domain.
+ * In case this attempt to disclaim copyright and place the software in the
+ * public domain is deemed null and void, then the software is
+ * Copyright (c) 2001 Alexander Peslyak and it is hereby released to the
+ * general public under the following terms:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted.
+ *
+ * There's ABSOLUTELY NO WARRANTY, express or implied.
+ *
+ * See md5.c for more information.
+ */
+
+#ifndef __MD5_H__
+#define __MD5_H__
+
+/* Any 32-bit or wider unsigned integer data type will do */
+typedef unsigned int MD5_u32plus;
+
+typedef struct {
+	MD5_u32plus lo, hi;
+	MD5_u32plus a, b, c, d;
+	unsigned char buffer[64];
+	MD5_u32plus block[16];
+} MD5_CTX;
+
+extern void MD5_Init(MD5_CTX *ctx);
+extern void MD5_Update(MD5_CTX *ctx, const void *data, unsigned long size);
+extern void MD5_Final(unsigned char *result, MD5_CTX *ctx);
+
+#endif /* __MD5_H__ */

pkgs/crypto/md5c/md5_test.go

@@ -0,0 +1,23 @@
+package md5c
+
+import (
+	"bytes"
+	"encoding/hex"
+	"testing"
+
+	. "gopkg.in/check.v1"
+)
+
+func Test(t *testing.T) { TestingT(t) }
+
+type MySuite struct{}
+
+var _ = Suite(&MySuite{})
+
+func (s *MySuite) TestMd5sum(c *C) {
+	testString := []byte("Test string")
+	expectedHash, _ := hex.DecodeString("0fd3dbec9730101bff92acc820befc34")
+	hash, err := Sum(bytes.NewBuffer(testString))
+	c.Assert(err, IsNil)
+	c.Assert(bytes.Equal(expectedHash, hash), Equals, true)
+}

pkgs/crypto/md5c/md5c.go

@@ -0,0 +1,48 @@
+// !build linux,amd64
+
+package md5c
+
+// #include "md5.h"
+import "C"
+import (
+	"io"
+	"unsafe"
+)
+
+func context() *C.MD5_CTX {
+	var ctx C.MD5_CTX
+	C.MD5_Init(&ctx)
+	return &ctx
+}
+
+func write(buffer []byte, ctx *C.MD5_CTX) {
+	size := len(buffer)
+	data := unsafe.Pointer(&buffer[0])
+	C.MD5_Update(ctx, data, C.ulong(size))
+}
+
+func Sum(reader io.Reader) ([]byte, error) {
+	ctx := context()
+	var err error
+	var length int
+	for err == nil {
+		byteBuffer := make([]byte, 1024*1024)
+		length, err = reader.Read(byteBuffer)
+		// break here since byteBuffer will go out of range
+		// when invoking subsequent write() call
+		if length == 0 {
+			break
+		}
+		byteBuffer = byteBuffer[0:length]
+		write(byteBuffer, ctx)
+	}
+
+	if err != io.EOF {
+		return nil, err
+	}
+
+	outputBuffer := make([]byte, 16)
+	coutputbuff := (*C.uchar)(unsafe.Pointer(&outputBuffer[0]))
+	C.MD5_Final(coutputbuff, ctx)
+	return outputBuffer, nil
+}