thodg/libgit2

diff --git a/CMakeLists.txt b/CMakeLists.txt
index 6e48adb..42f81a7 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -60,22 +60,20 @@ IF (THREADSAFE)
 ENDIF()
 
 # Collect sourcefiles
-FILE(GLOB SRC src/*.c src/backends/*.c)
+FILE(GLOB SRC src/*.c)
 FILE(GLOB SRC_ZLIB deps/zlib/*.c)
-FILE(GLOB SRC_SHA1 src/block-sha1/*.c)
-FILE(GLOB SRC_PLAT src/unix/*.c)
 FILE(GLOB SRC_H include/git2/*.h)
 
 # On Windows use specific platform sources
 IF (WIN32 AND NOT CYGWIN)
     ADD_DEFINITIONS(-DWIN32 -D_DEBUG -D_LIB)
-    FILE(GLOB SRC_PLAT src/win32/*.c)
+	FILE(GLOB SRC src/*.c src/win32/*.c)
 ENDIF ()
 
 ADD_DEFINITIONS(-D_FILE_OFFSET_BITS=64)
 
 # Compile and link libgit2
-ADD_LIBRARY(git2 ${SRC} ${SRC_PLAT} ${SRC_SHA1} ${SRC_ZLIB})
+ADD_LIBRARY(git2 ${SRC} ${SRC_ZLIB})
 TARGET_LINK_LIBRARIES(git2 ${CMAKE_THREAD_LIBS_INIT})
 SET_TARGET_PROPERTIES(git2 PROPERTIES VERSION ${LIBGIT2_VERSION_STRING})
 SET_TARGET_PROPERTIES(git2 PROPERTIES SOVERSION ${LIBGIT2_VERSION_MAJOR})
@@ -97,7 +95,7 @@ IF (BUILD_TESTS)
     INCLUDE_DIRECTORIES(tests)
 	FILE(GLOB SRC_TEST tests/t??-*.c)
 
-	ADD_EXECUTABLE(libgit2_test tests/test_main.c tests/test_lib.c tests/test_helpers.c ${SRC} ${SRC_PLAT} ${SRC_SHA1} ${SRC_TEST} ${SRC_ZLIB})
+	ADD_EXECUTABLE(libgit2_test tests/test_main.c tests/test_lib.c tests/test_helpers.c ${SRC} ${SRC_TEST} ${SRC_ZLIB})
 	TARGET_LINK_LIBRARIES(libgit2_test ${CMAKE_THREAD_LIBS_INIT})
 
 	ENABLE_TESTING()
diff --git a/src/block-sha1/sha1.c b/src/block-sha1/sha1.c
deleted file mode 100644
index 8c14601..0000000
--- a/src/block-sha1/sha1.c
+++ /dev/null
@@ -1,281 +0,0 @@
-/*
- * SHA1 routine optimized to do word accesses rather than byte accesses,
- * and to avoid unnecessary copies into the context array.
- *
- * This was initially based on the Mozilla SHA1 implementation, although
- * none of the original Mozilla code remains.
- */
-
-#include "common.h"
-#include "sha1.h"
-
-#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
-
-/*
- * Force usage of rol or ror by selecting the one with the smaller constant.
- * It _can_ generate slightly smaller code (a constant of 1 is special), but
- * perhaps more importantly it's possibly faster on any uarch that does a
- * rotate with a loop.
- */
-
-#define SHA_ASM(op, x, n) ({ unsigned int __res; __asm__(op " %1,%0":"=r" (__res):"i" (n), "0" (x)); __res; })
-#define SHA_ROL(x,n)	SHA_ASM("rol", x, n)
-#define SHA_ROR(x,n)	SHA_ASM("ror", x, n)
-
-#else
-
-#define SHA_ROT(X,l,r)	(((X) << (l)) | ((X) >> (r)))
-#define SHA_ROL(X,n)	SHA_ROT(X,n,32-(n))
-#define SHA_ROR(X,n)	SHA_ROT(X,32-(n),n)
-
-#endif
-
-/*
- * If you have 32 registers or more, the compiler can (and should)
- * try to change the array[] accesses into registers. However, on
- * machines with less than ~25 registers, that won't really work,
- * and at least gcc will make an unholy mess of it.
- *
- * So to avoid that mess which just slows things down, we force
- * the stores to memory to actually happen (we might be better off
- * with a 'W(t)=(val);asm("":"+m" (W(t))' there instead, as
- * suggested by Artur Skawina - that will also make gcc unable to
- * try to do the silly "optimize away loads" part because it won't
- * see what the value will be).
- *
- * Ben Herrenschmidt reports that on PPC, the C version comes close
- * to the optimized asm with this (ie on PPC you don't want that
- * 'volatile', since there are lots of registers).
- *
- * On ARM we get the best code generation by forcing a full memory barrier
- * between each SHA_ROUND, otherwise gcc happily get wild with spilling and
- * the stack frame size simply explode and performance goes down the drain.
- */
-
-#if defined(__i386__) || defined(__x86_64__)
-  #define setW(x, val) (*(volatile unsigned int *)&W(x) = (val))
-#elif defined(__GNUC__) && defined(__arm__)
-  #define setW(x, val) do { W(x) = (val); __asm__("":::"memory"); } while (0)
-#else
-  #define setW(x, val) (W(x) = (val))
-#endif
-
-/*
- * Performance might be improved if the CPU architecture is OK with
- * unaligned 32-bit loads and a fast ntohl() is available.
- * Otherwise fall back to byte loads and shifts which is portable,
- * and is faster on architectures with memory alignment issues.
- */
-
-#if defined(__i386__) || defined(__x86_64__) || \
-    defined(_M_IX86) || defined(_M_X64) || \
-    defined(__ppc__) || defined(__ppc64__) || \
-    defined(__powerpc__) || defined(__powerpc64__) || \
-    defined(__s390__) || defined(__s390x__)
-
-#define get_be32(p)	ntohl(*(unsigned int *)(p))
-#define put_be32(p, v)	do { *(unsigned int *)(p) = htonl(v); } while (0)
-
-#else
-
-#define get_be32(p)	( \
-	(*((unsigned char *)(p) + 0) << 24) | \
-	(*((unsigned char *)(p) + 1) << 16) | \
-	(*((unsigned char *)(p) + 2) <<  8) | \
-	(*((unsigned char *)(p) + 3) <<  0) )
-#define put_be32(p, v)	do { \
-	unsigned int __v = (v); \
-	*((unsigned char *)(p) + 0) = __v >> 24; \
-	*((unsigned char *)(p) + 1) = __v >> 16; \
-	*((unsigned char *)(p) + 2) = __v >>  8; \
-	*((unsigned char *)(p) + 3) = __v >>  0; } while (0)
-
-#endif
-
-/* This "rolls" over the 512-bit array */
-#define W(x) (array[(x)&15])
-
-/*
- * Where do we get the source from? The first 16 iterations get it from
- * the input data, the next mix it from the 512-bit array.
- */
-#define SHA_SRC(t) get_be32(data + t)
-#define SHA_MIX(t) SHA_ROL(W(t+13) ^ W(t+8) ^ W(t+2) ^ W(t), 1)
-
-#define SHA_ROUND(t, input, fn, constant, A, B, C, D, E) do { \
-	unsigned int TEMP = input(t); setW(t, TEMP); \
-	E += TEMP + SHA_ROL(A,5) + (fn) + (constant); \
-	B = SHA_ROR(B, 2); } while (0)
-
-#define T_0_15(t, A, B, C, D, E)  SHA_ROUND(t, SHA_SRC, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E )
-#define T_16_19(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E )
-#define T_20_39(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) , 0x6ed9eba1, A, B, C, D, E )
-#define T_40_59(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, ((B&C)+(D&(B^C))) , 0x8f1bbcdc, A, B, C, D, E )
-#define T_60_79(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) ,  0xca62c1d6, A, B, C, D, E )
-
-static void blk_SHA1_Block(blk_SHA_CTX *ctx, const unsigned int *data)
-{
-	unsigned int A,B,C,D,E;
-	unsigned int array[16];
-
-	A = ctx->H[0];
-	B = ctx->H[1];
-	C = ctx->H[2];
-	D = ctx->H[3];
-	E = ctx->H[4];
-
-	/* Round 1 - iterations 0-16 take their input from 'data' */
-	T_0_15( 0, A, B, C, D, E);
-	T_0_15( 1, E, A, B, C, D);
-	T_0_15( 2, D, E, A, B, C);
-	T_0_15( 3, C, D, E, A, B);
-	T_0_15( 4, B, C, D, E, A);
-	T_0_15( 5, A, B, C, D, E);
-	T_0_15( 6, E, A, B, C, D);
-	T_0_15( 7, D, E, A, B, C);
-	T_0_15( 8, C, D, E, A, B);
-	T_0_15( 9, B, C, D, E, A);
-	T_0_15(10, A, B, C, D, E);
-	T_0_15(11, E, A, B, C, D);
-	T_0_15(12, D, E, A, B, C);
-	T_0_15(13, C, D, E, A, B);
-	T_0_15(14, B, C, D, E, A);
-	T_0_15(15, A, B, C, D, E);
-
-	/* Round 1 - tail. Input from 512-bit mixing array */
-	T_16_19(16, E, A, B, C, D);
-	T_16_19(17, D, E, A, B, C);
-	T_16_19(18, C, D, E, A, B);
-	T_16_19(19, B, C, D, E, A);
-
-	/* Round 2 */
-	T_20_39(20, A, B, C, D, E);
-	T_20_39(21, E, A, B, C, D);
-	T_20_39(22, D, E, A, B, C);
-	T_20_39(23, C, D, E, A, B);
-	T_20_39(24, B, C, D, E, A);
-	T_20_39(25, A, B, C, D, E);
-	T_20_39(26, E, A, B, C, D);
-	T_20_39(27, D, E, A, B, C);
-	T_20_39(28, C, D, E, A, B);
-	T_20_39(29, B, C, D, E, A);
-	T_20_39(30, A, B, C, D, E);
-	T_20_39(31, E, A, B, C, D);
-	T_20_39(32, D, E, A, B, C);
-	T_20_39(33, C, D, E, A, B);
-	T_20_39(34, B, C, D, E, A);
-	T_20_39(35, A, B, C, D, E);
-	T_20_39(36, E, A, B, C, D);
-	T_20_39(37, D, E, A, B, C);
-	T_20_39(38, C, D, E, A, B);
-	T_20_39(39, B, C, D, E, A);
-
-	/* Round 3 */
-	T_40_59(40, A, B, C, D, E);
-	T_40_59(41, E, A, B, C, D);
-	T_40_59(42, D, E, A, B, C);
-	T_40_59(43, C, D, E, A, B);
-	T_40_59(44, B, C, D, E, A);
-	T_40_59(45, A, B, C, D, E);
-	T_40_59(46, E, A, B, C, D);
-	T_40_59(47, D, E, A, B, C);
-	T_40_59(48, C, D, E, A, B);
-	T_40_59(49, B, C, D, E, A);
-	T_40_59(50, A, B, C, D, E);
-	T_40_59(51, E, A, B, C, D);
-	T_40_59(52, D, E, A, B, C);
-	T_40_59(53, C, D, E, A, B);
-	T_40_59(54, B, C, D, E, A);
-	T_40_59(55, A, B, C, D, E);
-	T_40_59(56, E, A, B, C, D);
-	T_40_59(57, D, E, A, B, C);
-	T_40_59(58, C, D, E, A, B);
-	T_40_59(59, B, C, D, E, A);
-
-	/* Round 4 */
-	T_60_79(60, A, B, C, D, E);
-	T_60_79(61, E, A, B, C, D);
-	T_60_79(62, D, E, A, B, C);
-	T_60_79(63, C, D, E, A, B);
-	T_60_79(64, B, C, D, E, A);
-	T_60_79(65, A, B, C, D, E);
-	T_60_79(66, E, A, B, C, D);
-	T_60_79(67, D, E, A, B, C);
-	T_60_79(68, C, D, E, A, B);
-	T_60_79(69, B, C, D, E, A);
-	T_60_79(70, A, B, C, D, E);
-	T_60_79(71, E, A, B, C, D);
-	T_60_79(72, D, E, A, B, C);
-	T_60_79(73, C, D, E, A, B);
-	T_60_79(74, B, C, D, E, A);
-	T_60_79(75, A, B, C, D, E);
-	T_60_79(76, E, A, B, C, D);
-	T_60_79(77, D, E, A, B, C);
-	T_60_79(78, C, D, E, A, B);
-	T_60_79(79, B, C, D, E, A);
-
-	ctx->H[0] += A;
-	ctx->H[1] += B;
-	ctx->H[2] += C;
-	ctx->H[3] += D;
-	ctx->H[4] += E;
-}
-
-void git__blk_SHA1_Init(blk_SHA_CTX *ctx)
-{
-	ctx->size = 0;
-
-	/* Initialize H with the magic constants (see FIPS180 for constants) */
-	ctx->H[0] = 0x67452301;
-	ctx->H[1] = 0xefcdab89;
-	ctx->H[2] = 0x98badcfe;
-	ctx->H[3] = 0x10325476;
-	ctx->H[4] = 0xc3d2e1f0;
-}
-
-void git__blk_SHA1_Update(blk_SHA_CTX *ctx, const void *data, unsigned long len)
-{
-	unsigned int lenW = ctx->size & 63;
-
-	ctx->size += len;
-
-	/* Read the data into W and process blocks as they get full */
-	if (lenW) {
-		unsigned int left = 64 - lenW;
-		if (len < left)
-			left = len;
-		memcpy(lenW + (char *)ctx->W, data, left);
-		lenW = (lenW + left) & 63;
-		len -= left;
-		data = ((const char *)data + left);
-		if (lenW)
-			return;
-		blk_SHA1_Block(ctx, ctx->W);
-	}
-	while (len >= 64) {
-		blk_SHA1_Block(ctx, data);
-		data = ((const char *)data + 64);
-		len -= 64;
-	}
-	if (len)
-		memcpy(ctx->W, data, len);
-}
-
-void git__blk_SHA1_Final(unsigned char hashout[20], blk_SHA_CTX *ctx)
-{
-	static const unsigned char pad[64] = { 0x80 };
-	unsigned int padlen[2];
-	int i;
-
-	/* Pad with a binary 1 (ie 0x80), then zeroes, then length */
-	padlen[0] = htonl((uint32_t)(ctx->size >> 29));
-	padlen[1] = htonl((uint32_t)(ctx->size << 3));
-
-	i = ctx->size & 63;
-	git__blk_SHA1_Update(ctx, pad, 1+ (63 & (55 - i)));
-	git__blk_SHA1_Update(ctx, padlen, 8);
-
-	/* Output hash */
-	for (i = 0; i < 5; i++)
-		put_be32(hashout + i*4, ctx->H[i]);
-}
diff --git a/src/block-sha1/sha1.h b/src/block-sha1/sha1.h
deleted file mode 100644
index 558d6ae..0000000
--- a/src/block-sha1/sha1.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * SHA1 routine optimized to do word accesses rather than byte accesses,
- * and to avoid unnecessary copies into the context array.
- *
- * This was initially based on the Mozilla SHA1 implementation, although
- * none of the original Mozilla code remains.
- */
-
-typedef struct {
-	unsigned long long size;
-	unsigned int H[5];
-	unsigned int W[16];
-} blk_SHA_CTX;
-
-void git__blk_SHA1_Init(blk_SHA_CTX *ctx);
-void git__blk_SHA1_Update(blk_SHA_CTX *ctx, const void *dataIn, unsigned long len);
-void git__blk_SHA1_Final(unsigned char hashout[20], blk_SHA_CTX *ctx);
-
-#define SHA_CTX		blk_SHA_CTX
-#define SHA1_Init	git__blk_SHA1_Init
-#define SHA1_Update	git__blk_SHA1_Update
-#define SHA1_Final	git__blk_SHA1_Final
diff --git a/src/hash.c b/src/hash.c
index 775e4b4..b8b311b 100644
--- a/src/hash.c
+++ b/src/hash.c
@@ -28,10 +28,8 @@
 
 #if defined(PPC_SHA1)
 # include "ppc/sha1.h"
-#elif defined(OPENSSL_SHA1)
-# include <openssl/sha.h>
 #else
-# include "block-sha1/sha1.h"
+# include "sha1.h"
 #endif
 
 struct git_hash_ctx {
diff --git a/src/map_posix.c b/src/map_posix.c
new file mode 100644
index 0000000..1f50bcf
--- /dev/null
+++ b/src/map_posix.c
@@ -0,0 +1,64 @@
+#include <git2/common.h>
+
+#ifndef GIT_WIN32
+
+#include "map.h"
+#include <sys/mman.h>
+#include <errno.h>
+
+int git__mmap(git_map *out, size_t len, int prot, int flags, int fd, git_off_t offset)
+{
+	int mprot = 0;
+	int mflag = 0;
+
+	assert((out != NULL) && (len > 0));
+
+	if ((out == NULL) || (len == 0)) {
+		errno = EINVAL;
+		return git__throw(GIT_ERROR, "Failed to mmap. No map or zero length");
+	}
+
+	out->data = NULL;
+	out->len = 0;
+
+	if (prot & GIT_PROT_WRITE)
+		mprot = PROT_WRITE;
+	else if (prot & GIT_PROT_READ)
+		mprot = PROT_READ;
+	else {
+		errno = EINVAL;
+		return git__throw(GIT_ERROR, "Failed to mmap. Invalid protection parameters");
+	}
+
+	if ((flags & GIT_MAP_TYPE) == GIT_MAP_SHARED)
+		mflag = MAP_SHARED;
+	else if ((flags & GIT_MAP_TYPE) == GIT_MAP_PRIVATE)
+		mflag = MAP_PRIVATE;
+
+	if (flags & GIT_MAP_FIXED) {
+		errno = EINVAL;
+		return git__throw(GIT_ERROR, "Failed to mmap. FIXED not set");
+	}
+
+	out->data = mmap(NULL, len, mprot, mflag, fd, offset);
+	if (!out->data || out->data == MAP_FAILED)
+		return git__throw(GIT_EOSERR, "Failed to mmap. Could not write data");
+	out->len = len;
+
+	return GIT_SUCCESS;
+}
+
+int git__munmap(git_map *map)
+{
+	assert(map != NULL);
+
+	if (!map)
+		return git__throw(GIT_ERROR, "Failed to munmap. Map does not exist");
+
+	munmap(map->data, map->len);
+
+	return GIT_SUCCESS;
+}
+
+#endif
+
diff --git a/src/sha1.c b/src/sha1.c
new file mode 100644
index 0000000..8c14601
--- /dev/null
+++ b/src/sha1.c
@@ -0,0 +1,281 @@
+/*
+ * SHA1 routine optimized to do word accesses rather than byte accesses,
+ * and to avoid unnecessary copies into the context array.
+ *
+ * This was initially based on the Mozilla SHA1 implementation, although
+ * none of the original Mozilla code remains.
+ */
+
+#include "common.h"
+#include "sha1.h"
+
+#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
+
+/*
+ * Force usage of rol or ror by selecting the one with the smaller constant.
+ * It _can_ generate slightly smaller code (a constant of 1 is special), but
+ * perhaps more importantly it's possibly faster on any uarch that does a
+ * rotate with a loop.
+ */
+
+#define SHA_ASM(op, x, n) ({ unsigned int __res; __asm__(op " %1,%0":"=r" (__res):"i" (n), "0" (x)); __res; })
+#define SHA_ROL(x,n)	SHA_ASM("rol", x, n)
+#define SHA_ROR(x,n)	SHA_ASM("ror", x, n)
+
+#else
+
+#define SHA_ROT(X,l,r)	(((X) << (l)) | ((X) >> (r)))
+#define SHA_ROL(X,n)	SHA_ROT(X,n,32-(n))
+#define SHA_ROR(X,n)	SHA_ROT(X,32-(n),n)
+
+#endif
+
+/*
+ * If you have 32 registers or more, the compiler can (and should)
+ * try to change the array[] accesses into registers. However, on
+ * machines with less than ~25 registers, that won't really work,
+ * and at least gcc will make an unholy mess of it.
+ *
+ * So to avoid that mess which just slows things down, we force
+ * the stores to memory to actually happen (we might be better off
+ * with a 'W(t)=(val);asm("":"+m" (W(t))' there instead, as
+ * suggested by Artur Skawina - that will also make gcc unable to
+ * try to do the silly "optimize away loads" part because it won't
+ * see what the value will be).
+ *
+ * Ben Herrenschmidt reports that on PPC, the C version comes close
+ * to the optimized asm with this (ie on PPC you don't want that
+ * 'volatile', since there are lots of registers).
+ *
+ * On ARM we get the best code generation by forcing a full memory barrier
+ * between each SHA_ROUND, otherwise gcc happily get wild with spilling and
+ * the stack frame size simply explode and performance goes down the drain.
+ */
+
+#if defined(__i386__) || defined(__x86_64__)
+  #define setW(x, val) (*(volatile unsigned int *)&W(x) = (val))
+#elif defined(__GNUC__) && defined(__arm__)
+  #define setW(x, val) do { W(x) = (val); __asm__("":::"memory"); } while (0)
+#else
+  #define setW(x, val) (W(x) = (val))
+#endif
+
+/*
+ * Performance might be improved if the CPU architecture is OK with
+ * unaligned 32-bit loads and a fast ntohl() is available.
+ * Otherwise fall back to byte loads and shifts which is portable,
+ * and is faster on architectures with memory alignment issues.
+ */
+
+#if defined(__i386__) || defined(__x86_64__) || \
+    defined(_M_IX86) || defined(_M_X64) || \
+    defined(__ppc__) || defined(__ppc64__) || \
+    defined(__powerpc__) || defined(__powerpc64__) || \
+    defined(__s390__) || defined(__s390x__)
+
+#define get_be32(p)	ntohl(*(unsigned int *)(p))
+#define put_be32(p, v)	do { *(unsigned int *)(p) = htonl(v); } while (0)
+
+#else
+
+#define get_be32(p)	( \
+	(*((unsigned char *)(p) + 0) << 24) | \
+	(*((unsigned char *)(p) + 1) << 16) | \
+	(*((unsigned char *)(p) + 2) <<  8) | \
+	(*((unsigned char *)(p) + 3) <<  0) )
+#define put_be32(p, v)	do { \
+	unsigned int __v = (v); \
+	*((unsigned char *)(p) + 0) = __v >> 24; \
+	*((unsigned char *)(p) + 1) = __v >> 16; \
+	*((unsigned char *)(p) + 2) = __v >>  8; \
+	*((unsigned char *)(p) + 3) = __v >>  0; } while (0)
+
+#endif
+
+/* This "rolls" over the 512-bit array */
+#define W(x) (array[(x)&15])
+
+/*
+ * Where do we get the source from? The first 16 iterations get it from
+ * the input data, the next mix it from the 512-bit array.
+ */
+#define SHA_SRC(t) get_be32(data + t)
+#define SHA_MIX(t) SHA_ROL(W(t+13) ^ W(t+8) ^ W(t+2) ^ W(t), 1)
+
+#define SHA_ROUND(t, input, fn, constant, A, B, C, D, E) do { \
+	unsigned int TEMP = input(t); setW(t, TEMP); \
+	E += TEMP + SHA_ROL(A,5) + (fn) + (constant); \
+	B = SHA_ROR(B, 2); } while (0)
+
+#define T_0_15(t, A, B, C, D, E)  SHA_ROUND(t, SHA_SRC, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E )
+#define T_16_19(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E )
+#define T_20_39(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) , 0x6ed9eba1, A, B, C, D, E )
+#define T_40_59(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, ((B&C)+(D&(B^C))) , 0x8f1bbcdc, A, B, C, D, E )
+#define T_60_79(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) ,  0xca62c1d6, A, B, C, D, E )
+
+static void blk_SHA1_Block(blk_SHA_CTX *ctx, const unsigned int *data)
+{
+	unsigned int A,B,C,D,E;
+	unsigned int array[16];
+
+	A = ctx->H[0];
+	B = ctx->H[1];
+	C = ctx->H[2];
+	D = ctx->H[3];
+	E = ctx->H[4];
+
+	/* Round 1 - iterations 0-16 take their input from 'data' */
+	T_0_15( 0, A, B, C, D, E);
+	T_0_15( 1, E, A, B, C, D);
+	T_0_15( 2, D, E, A, B, C);
+	T_0_15( 3, C, D, E, A, B);
+	T_0_15( 4, B, C, D, E, A);
+	T_0_15( 5, A, B, C, D, E);
+	T_0_15( 6, E, A, B, C, D);
+	T_0_15( 7, D, E, A, B, C);
+	T_0_15( 8, C, D, E, A, B);
+	T_0_15( 9, B, C, D, E, A);
+	T_0_15(10, A, B, C, D, E);
+	T_0_15(11, E, A, B, C, D);
+	T_0_15(12, D, E, A, B, C);
+	T_0_15(13, C, D, E, A, B);
+	T_0_15(14, B, C, D, E, A);
+	T_0_15(15, A, B, C, D, E);
+
+	/* Round 1 - tail. Input from 512-bit mixing array */
+	T_16_19(16, E, A, B, C, D);
+	T_16_19(17, D, E, A, B, C);
+	T_16_19(18, C, D, E, A, B);
+	T_16_19(19, B, C, D, E, A);
+
+	/* Round 2 */
+	T_20_39(20, A, B, C, D, E);
+	T_20_39(21, E, A, B, C, D);
+	T_20_39(22, D, E, A, B, C);
+	T_20_39(23, C, D, E, A, B);
+	T_20_39(24, B, C, D, E, A);
+	T_20_39(25, A, B, C, D, E);
+	T_20_39(26, E, A, B, C, D);
+	T_20_39(27, D, E, A, B, C);
+	T_20_39(28, C, D, E, A, B);
+	T_20_39(29, B, C, D, E, A);
+	T_20_39(30, A, B, C, D, E);
+	T_20_39(31, E, A, B, C, D);
+	T_20_39(32, D, E, A, B, C);
+	T_20_39(33, C, D, E, A, B);
+	T_20_39(34, B, C, D, E, A);
+	T_20_39(35, A, B, C, D, E);
+	T_20_39(36, E, A, B, C, D);
+	T_20_39(37, D, E, A, B, C);
+	T_20_39(38, C, D, E, A, B);
+	T_20_39(39, B, C, D, E, A);
+
+	/* Round 3 */
+	T_40_59(40, A, B, C, D, E);
+	T_40_59(41, E, A, B, C, D);
+	T_40_59(42, D, E, A, B, C);
+	T_40_59(43, C, D, E, A, B);
+	T_40_59(44, B, C, D, E, A);
+	T_40_59(45, A, B, C, D, E);
+	T_40_59(46, E, A, B, C, D);
+	T_40_59(47, D, E, A, B, C);
+	T_40_59(48, C, D, E, A, B);
+	T_40_59(49, B, C, D, E, A);
+	T_40_59(50, A, B, C, D, E);
+	T_40_59(51, E, A, B, C, D);
+	T_40_59(52, D, E, A, B, C);
+	T_40_59(53, C, D, E, A, B);
+	T_40_59(54, B, C, D, E, A);
+	T_40_59(55, A, B, C, D, E);
+	T_40_59(56, E, A, B, C, D);
+	T_40_59(57, D, E, A, B, C);
+	T_40_59(58, C, D, E, A, B);
+	T_40_59(59, B, C, D, E, A);
+
+	/* Round 4 */
+	T_60_79(60, A, B, C, D, E);
+	T_60_79(61, E, A, B, C, D);
+	T_60_79(62, D, E, A, B, C);
+	T_60_79(63, C, D, E, A, B);
+	T_60_79(64, B, C, D, E, A);
+	T_60_79(65, A, B, C, D, E);
+	T_60_79(66, E, A, B, C, D);
+	T_60_79(67, D, E, A, B, C);
+	T_60_79(68, C, D, E, A, B);
+	T_60_79(69, B, C, D, E, A);
+	T_60_79(70, A, B, C, D, E);
+	T_60_79(71, E, A, B, C, D);
+	T_60_79(72, D, E, A, B, C);
+	T_60_79(73, C, D, E, A, B);
+	T_60_79(74, B, C, D, E, A);
+	T_60_79(75, A, B, C, D, E);
+	T_60_79(76, E, A, B, C, D);
+	T_60_79(77, D, E, A, B, C);
+	T_60_79(78, C, D, E, A, B);
+	T_60_79(79, B, C, D, E, A);
+
+	ctx->H[0] += A;
+	ctx->H[1] += B;
+	ctx->H[2] += C;
+	ctx->H[3] += D;
+	ctx->H[4] += E;
+}
+
+void git__blk_SHA1_Init(blk_SHA_CTX *ctx)
+{
+	ctx->size = 0;
+
+	/* Initialize H with the magic constants (see FIPS180 for constants) */
+	ctx->H[0] = 0x67452301;
+	ctx->H[1] = 0xefcdab89;
+	ctx->H[2] = 0x98badcfe;
+	ctx->H[3] = 0x10325476;
+	ctx->H[4] = 0xc3d2e1f0;
+}
+
+void git__blk_SHA1_Update(blk_SHA_CTX *ctx, const void *data, unsigned long len)
+{
+	unsigned int lenW = ctx->size & 63;
+
+	ctx->size += len;
+
+	/* Read the data into W and process blocks as they get full */
+	if (lenW) {
+		unsigned int left = 64 - lenW;
+		if (len < left)
+			left = len;
+		memcpy(lenW + (char *)ctx->W, data, left);
+		lenW = (lenW + left) & 63;
+		len -= left;
+		data = ((const char *)data + left);
+		if (lenW)
+			return;
+		blk_SHA1_Block(ctx, ctx->W);
+	}
+	while (len >= 64) {
+		blk_SHA1_Block(ctx, data);
+		data = ((const char *)data + 64);
+		len -= 64;
+	}
+	if (len)
+		memcpy(ctx->W, data, len);
+}
+
+void git__blk_SHA1_Final(unsigned char hashout[20], blk_SHA_CTX *ctx)
+{
+	static const unsigned char pad[64] = { 0x80 };
+	unsigned int padlen[2];
+	int i;
+
+	/* Pad with a binary 1 (ie 0x80), then zeroes, then length */
+	padlen[0] = htonl((uint32_t)(ctx->size >> 29));
+	padlen[1] = htonl((uint32_t)(ctx->size << 3));
+
+	i = ctx->size & 63;
+	git__blk_SHA1_Update(ctx, pad, 1+ (63 & (55 - i)));
+	git__blk_SHA1_Update(ctx, padlen, 8);
+
+	/* Output hash */
+	for (i = 0; i < 5; i++)
+		put_be32(hashout + i*4, ctx->H[i]);
+}
diff --git a/src/sha1.h b/src/sha1.h
new file mode 100644
index 0000000..558d6ae
--- /dev/null
+++ b/src/sha1.h
@@ -0,0 +1,22 @@
+/*
+ * SHA1 routine optimized to do word accesses rather than byte accesses,
+ * and to avoid unnecessary copies into the context array.
+ *
+ * This was initially based on the Mozilla SHA1 implementation, although
+ * none of the original Mozilla code remains.
+ */
+
+typedef struct {
+	unsigned long long size;
+	unsigned int H[5];
+	unsigned int W[16];
+} blk_SHA_CTX;
+
+void git__blk_SHA1_Init(blk_SHA_CTX *ctx);
+void git__blk_SHA1_Update(blk_SHA_CTX *ctx, const void *dataIn, unsigned long len);
+void git__blk_SHA1_Final(unsigned char hashout[20], blk_SHA_CTX *ctx);
+
+#define SHA_CTX		blk_SHA_CTX
+#define SHA1_Init	git__blk_SHA1_Init
+#define SHA1_Update	git__blk_SHA1_Update
+#define SHA1_Final	git__blk_SHA1_Final
diff --git a/src/unix/map.c b/src/unix/map.c
deleted file mode 100644
index 9bc6178..0000000
--- a/src/unix/map.c
+++ /dev/null
@@ -1,61 +0,0 @@
-
-#include "map.h"
-#include <sys/mman.h>
-#include <errno.h>
-
-
-int git__mmap(git_map *out, size_t len, int prot, int flags, int fd, git_off_t offset)
-{
-	int mprot = 0;
-	int mflag = 0;
-
-	assert((out != NULL) && (len > 0));
-
-	if ((out == NULL) || (len == 0)) {
-		errno = EINVAL;
-		return git__throw(GIT_ERROR, "Failed to mmap. No map or zero length");
-	}
-
-	out->data = NULL;
-	out->len = 0;
-
-	if (prot & GIT_PROT_WRITE)
-		mprot = PROT_WRITE;
-	else if (prot & GIT_PROT_READ)
-		mprot = PROT_READ;
-	else {
-		errno = EINVAL;
-		return git__throw(GIT_ERROR, "Failed to mmap. Invalid protection parameters");
-	}
-
-	if ((flags & GIT_MAP_TYPE) == GIT_MAP_SHARED)
-		mflag = MAP_SHARED;
-	else if ((flags & GIT_MAP_TYPE) == GIT_MAP_PRIVATE)
-		mflag = MAP_PRIVATE;
-
-	if (flags & GIT_MAP_FIXED) {
-		errno = EINVAL;
-		return git__throw(GIT_ERROR, "Failed to mmap. FIXED not set");
-	}
-
-	out->data = mmap(NULL, len, mprot, mflag, fd, offset);
-	if (!out->data || out->data == MAP_FAILED)
-		return git__throw(GIT_EOSERR, "Failed to mmap. Could not write data");
-	out->len = len;
-
-	return GIT_SUCCESS;
-}
-
-int git__munmap(git_map *map)
-{
-	assert(map != NULL);
-
-	if (!map)
-		return git__throw(GIT_ERROR, "Failed to munmap. Map does not exist");
-
-	munmap(map->data, map->len);
-
-	return GIT_SUCCESS;
-}
-
-