rugged 0.1.2 → 0.16.0b1

data/ext/rugged/vendor/libgit2-dist/src/sha1.c

@@ -0,0 +1,280 @@
+/*
+ * Copyright (C) 2009-2011 the libgit2 contributors
+ *
+ * This file is part of libgit2, distributed under the GNU GPL v2 with
+ * a Linking Exception. For full terms see the included COPYING file.
+ */
+
+#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(*(const unsigned int *)(p))
+#define put_be32(p, v)	do { *(unsigned int *)(p) = htonl(v); } while (0)
+
+#else
+
+#define get_be32(p)	( \
+	(*((const unsigned char *)(p) + 0) << 24) | \
+	(*((const unsigned char *)(p) + 1) << 16) | \
+	(*((const unsigned char *)(p) + 2) << 8) | \
+	(*((const 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]);
+}

data/ext/rugged/vendor/libgit2-dist/src/sha1.h

@@ -0,0 +1,21 @@
+/*
+ * Copyright (C) 2009-2011 the libgit2 contributors
+ *
+ * This file is part of libgit2, distributed under the GNU GPL v2 with
+ * a Linking Exception. For full terms see the included COPYING file.
+ */
+
+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

data/ext/rugged/vendor/libgit2-dist/src/sha1_lookup.c

@@ -0,0 +1,177 @@
+/*
+ * Copyright (C) 2009-2011 the libgit2 contributors
+ *
+ * This file is part of libgit2, distributed under the GNU GPL v2 with
+ * a Linking Exception. For full terms see the included COPYING file.
+ */
+
+#include <stdio.h>
+
+#include "sha1_lookup.h"
+#include "common.h"
+
+/*
+ * Conventional binary search loop looks like this:
+ *
+ *	unsigned lo, hi;
+ *		do {
+ *				unsigned mi = (lo + hi) / 2;
+ *				int cmp = "entry pointed at by mi" minus "target";
+ *				if (!cmp)
+ *						return (mi is the wanted one)
+ *				if (cmp > 0)
+ *						hi = mi; "mi is larger than target"
+ *				else
+ *						lo = mi+1; "mi is smaller than target"
+ *		} while (lo < hi);
+ *
+ * The invariants are:
+ *
+ * - When entering the loop, lo points at a slot that is never
+ *	above the target (it could be at the target), hi points at a
+ *	slot that is guaranteed to be above the target (it can never
+ *	be at the target).
+ *
+ * - We find a point 'mi' between lo and hi (mi could be the same
+ *	as lo, but never can be as same as hi), and check if it hits
+ *	the target. There are three cases:
+ *
+ *	- if it is a hit, we are happy.
+ *
+ *	- if it is strictly higher than the target, we set it to hi,
+ *		and repeat the search.
+ *
+ *	- if it is strictly lower than the target, we update lo to
+ *		one slot after it, because we allow lo to be at the target.
+ *
+ *	If the loop exits, there is no matching entry.
+ *
+ * When choosing 'mi', we do not have to take the "middle" but
+ * anywhere in between lo and hi, as long as lo <= mi < hi is
+ * satisfied. When we somehow know that the distance between the
+ * target and lo is much shorter than the target and hi, we could
+ * pick mi that is much closer to lo than the midway.
+ *
+ * Now, we can take advantage of the fact that SHA-1 is a good hash
+ * function, and as long as there are enough entries in the table, we
+ * can expect uniform distribution. An entry that begins with for
+ * example "deadbeef..." is much likely to appear much later than in
+ * the midway of the table. It can reasonably be expected to be near
+ * 87% (222/256) from the top of the table.
+ *
+ * However, we do not want to pick "mi" too precisely. If the entry at
+ * the 87% in the above example turns out to be higher than the target
+ * we are looking for, we would end up narrowing the search space down
+ * only by 13%, instead of 50% we would get if we did a simple binary
+ * search. So we would want to hedge our bets by being less aggressive.
+ *
+ * The table at "table" holds at least "nr" entries of "elem_size"
+ * bytes each. Each entry has the SHA-1 key at "key_offset". The
+ * table is sorted by the SHA-1 key of the entries. The caller wants
+ * to find the entry with "key", and knows that the entry at "lo" is
+ * not higher than the entry it is looking for, and that the entry at
+ * "hi" is higher than the entry it is looking for.
+ */
+int sha1_entry_pos(const void *table,
+			size_t elem_size,
+			size_t key_offset,
+			unsigned lo, unsigned hi, unsigned nr,
+			const unsigned char *key)
+{
+	const unsigned char *base = (const unsigned char*)table;
+	const unsigned char *hi_key, *lo_key;
+	unsigned ofs_0;
+
+	if (!nr || lo >= hi)
+		return -1;
+
+	if (nr == hi)
+		hi_key = NULL;
+	else
+		hi_key = base + elem_size * hi + key_offset;
+	lo_key = base + elem_size * lo + key_offset;
+
+	ofs_0 = 0;
+	do {
+		int cmp;
+		unsigned ofs, mi, range;
+		unsigned lov, hiv, kyv;
+		const unsigned char *mi_key;
+
+		range = hi - lo;
+		if (hi_key) {
+			for (ofs = ofs_0; ofs < 20; ofs++)
+				if (lo_key[ofs] != hi_key[ofs])
+					break;
+			ofs_0 = ofs;
+			/*
+			 * byte 0 thru (ofs-1) are the same between
+			 * lo and hi; ofs is the first byte that is
+			 * different.
+			 */
+			hiv = hi_key[ofs_0];
+			if (ofs_0 < 19)
+				hiv = (hiv << 8) | hi_key[ofs_0+1];
+		} else {
+			hiv = 256;
+			if (ofs_0 < 19)
+				hiv <<= 8;
+		}
+		lov = lo_key[ofs_0];
+		kyv = key[ofs_0];
+		if (ofs_0 < 19) {
+			lov = (lov << 8) | lo_key[ofs_0+1];
+			kyv = (kyv << 8) | key[ofs_0+1];
+		}
+		assert(lov < hiv);
+
+		if (kyv < lov)
+			return -1 - lo;
+		if (hiv < kyv)
+			return -1 - hi;
+
+		/*
+		 * Even if we know the target is much closer to 'hi'
+		 * than 'lo', if we pick too precisely and overshoot
+		 * (e.g. when we know 'mi' is closer to 'hi' than to
+		 * 'lo', pick 'mi' that is higher than the target), we
+		 * end up narrowing the search space by a smaller
+		 * amount (i.e. the distance between 'mi' and 'hi')
+		 * than what we would have (i.e. about half of 'lo'
+		 * and 'hi'). Hedge our bets to pick 'mi' less
+		 * aggressively, i.e. make 'mi' a bit closer to the
+		 * middle than we would otherwise pick.
+		 */
+		kyv = (kyv * 6 + lov + hiv) / 8;
+		if (lov < hiv - 1) {
+			if (kyv == lov)
+				kyv++;
+			else if (kyv == hiv)
+				kyv--;
+		}
+		mi = (range - 1) * (kyv - lov) / (hiv - lov) + lo;
+
+#ifdef INDEX_DEBUG_LOOKUP
+		printf("lo %u hi %u rg %u mi %u ", lo, hi, range, mi);
+		printf("ofs %u lov %x, hiv %x, kyv %x\n",
+				ofs_0, lov, hiv, kyv);
+#endif
+
+		if (!(lo <= mi && mi < hi)) {
+			return git__throw(GIT_ERROR, "Assertion failure. Binary search invariant is false");
+		}
+
+		mi_key = base + elem_size * mi + key_offset;
+		cmp = memcmp(mi_key + ofs_0, key + ofs_0, 20 - ofs_0);
+		if (!cmp)
+			return mi;
+		if (cmp > 0) {
+			hi = mi;
+			hi_key = mi_key;
+		} else {
+			lo = mi + 1;
+			lo_key = mi_key + elem_size;
+		}
+	} while (lo < hi);
+	return -((int)lo)-1;
+}