From 2e86c5fe02332189948672df1fec49b68584bfc3 Mon Sep 17 00:00:00 2001
From: Dirk Engling <erdgeist@erdgeist.org>
Date: Thu, 7 Mar 2019 15:25:31 +0100
Subject: merge_entries uses siphash to identify common chunks
---
src/postprocess/halfsiphash.c | 152 ++++++++++++++++++++++++++++++++++++++++++
1 file changed, 152 insertions(+)
create mode 100644 src/postprocess/halfsiphash.c
(limited to 'src')
diff --git a/src/postprocess/halfsiphash.c b/src/postprocess/halfsiphash.c
new file mode 100644
index 0000000..d74d3be
--- /dev/null
+++ b/src/postprocess/halfsiphash.c
@@ -0,0 +1,152 @@
+
+/*
+ SipHash reference C implementation
+
+ Copyright (c) 2016 Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com>
+
+ To the extent possible under law, the author(s) have dedicated all copyright
+ and related and neighboring rights to this software to the public domain
+ worldwide. This software is distributed without any warranty.
+
+ You should have received a copy of the CC0 Public Domain Dedication along
+ with
+ this software. If not, see
+ <http://creativecommons.org/publicdomain/zero/1.0/>.
+ */
+#include <assert.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <string.h>
+
+/* default: SipHash-2-4 */
+#define cROUNDS 2
+#define dROUNDS 4
+
+#define ROTL(x, b) (uint32_t)(((x) << (b)) | ((x) >> (32 - (b))))
+
+#define U32TO8_LE(p, v) \
+ (p)[0] = (uint8_t)((v)); \
+ (p)[1] = (uint8_t)((v) >> 8); \
+ (p)[2] = (uint8_t)((v) >> 16); \
+ (p)[3] = (uint8_t)((v) >> 24);
+
+#define U32TO8_LE(p, v) \
+ (p)[0] = (uint8_t)((v)); \
+ (p)[1] = (uint8_t)((v) >> 8); \
+ (p)[2] = (uint8_t)((v) >> 16); \
+ (p)[3] = (uint8_t)((v) >> 24);
+
+#define U8TO32_LE(p) \
+ (((uint32_t)((p)[0])) | ((uint32_t)((p)[1]) << 8) | \
+ ((uint32_t)((p)[2]) << 16) | ((uint32_t)((p)[3]) << 24))
+
+#define SIPROUND \
+ do { \
+ v0 += v1; \
+ v1 = ROTL(v1, 5); \
+ v1 ^= v0; \
+ v0 = ROTL(v0, 16); \
+ v2 += v3; \
+ v3 = ROTL(v3, 8); \
+ v3 ^= v2; \
+ v0 += v3; \
+ v3 = ROTL(v3, 7); \
+ v3 ^= v0; \
+ v2 += v1; \
+ v1 = ROTL(v1, 13); \
+ v1 ^= v2; \
+ v2 = ROTL(v2, 16); \
+ } while (0)
+
+#ifdef DEBUG
+#define TRACE \
+ do { \
+ printf("(%3d) v0 %08x\n", (int)inlen, v0); \
+ printf("(%3d) v1 %08x\n", (int)inlen, v1); \
+ printf("(%3d) v2 %08x\n", (int)inlen, v2); \
+ printf("(%3d) v3 %08x\n", (int)inlen, v3); \
+ } while (0)
+#else
+#define TRACE
+#endif
+
+int halfsiphash(const uint8_t *in, const size_t inlen, const uint8_t *k,
+ uint8_t *out, const size_t outlen) {
+
+ assert((outlen == 4) || (outlen == 8));
+ uint32_t v0 = 0;
+ uint32_t v1 = 0;
+ uint32_t v2 = 0x6c796765;
+ uint32_t v3 = 0x74656462;
+ uint32_t k0 = U8TO32_LE(k);
+ uint32_t k1 = U8TO32_LE(k + 4);
+ uint32_t m;
+ int i;
+ const uint8_t *end = in + inlen - (inlen % sizeof(uint32_t));
+ const int left = inlen & 3;
+ uint32_t b = ((uint32_t)inlen) << 24;
+ v3 ^= k1;
+ v2 ^= k0;
+ v1 ^= k1;
+ v0 ^= k0;
+
+ if (outlen == 8)
+ v1 ^= 0xee;
+
+ for (; in != end; in += 4) {
+ m = U8TO32_LE(in);
+ v3 ^= m;
+
+ TRACE;
+ for (i = 0; i < cROUNDS; ++i)
+ SIPROUND;
+
+ v0 ^= m;
+ }
+
+ switch (left) {
+ case 3:
+ b |= ((uint32_t)in[2]) << 16;
+ case 2:
+ b |= ((uint32_t)in[1]) << 8;
+ case 1:
+ b |= ((uint32_t)in[0]);
+ break;
+ case 0:
+ break;
+ }
+
+ v3 ^= b;
+
+ TRACE;
+ for (i = 0; i < cROUNDS; ++i)
+ SIPROUND;
+
+ v0 ^= b;
+
+ if (outlen == 8)
+ v2 ^= 0xee;
+ else
+ v2 ^= 0xff;
+
+ TRACE;
+ for (i = 0; i < dROUNDS; ++i)
+ SIPROUND;
+
+ b = v1 ^ v3;
+ U32TO8_LE(out, b);
+
+ if (outlen == 4)
+ return 0;
+
+ v1 ^= 0xdd;
+
+ TRACE;
+ for (i = 0; i < dROUNDS; ++i)
+ SIPROUND;
+
+ b = v1 ^ v3;
+ U32TO8_LE(out + 4, b);
+
+ return 0;
+}
--
cgit v1.2.3