WIP on a fastq-sort program.

[fastq-tools.git] / src / parse.c

diff --git a/src/parse.c b/src/parse.c
index 8a6123e9b97f14e6818421e8d2a9f06303fad78c..fd139218506c0ab91a4aa449cd22217a6b11d1cd 100644 (file)
--- a/src/parse.c
+++ b/src/parse.c
@@ -66,6 +66,88 @@ void seq_free(seq_t* seq)
 }
 
 
+/* This is MurmurHash3. The original C++ code was placed in the public domain
+ * by its author, Austin Appleby. */
+
+static inline uint32_t fmix(uint32_t h)
+{
+    h ^= h >> 16;
+    h *= 0x85ebca6b;
+    h ^= h >> 13;
+    h *= 0xc2b2ae35;
+    h ^= h >> 16;
+
+    return h;
+}
+
+
+static inline uint32_t rotl32(uint32_t x, int8_t r)
+{
+    return (x << r) | (x >> (32 - r));
+}
+
+
+uint32_t murmurhash3(const uint8_t* data, size_t len_)
+{
+    const int len = (int) len_;
+    const int nblocks = len / 4;
+
+    uint32_t h1 = 0xc062fb4a;
+
+    uint32_t c1 = 0xcc9e2d51;
+    uint32_t c2 = 0x1b873593;
+
+    //----------
+    // body
+
+    const uint32_t * blocks = (const uint32_t*) (data + nblocks * 4);
+
+    int i;
+    for(i = -nblocks; i; i++)
+    {
+        uint32_t k1 = blocks[i];
+
+        k1 *= c1;
+        k1 = rotl32(k1, 15);
+        k1 *= c2;
+
+        h1 ^= k1;
+        h1 = rotl32(h1, 13);
+        h1 = h1*5+0xe6546b64;
+    }
+
+    //----------
+    // tail
+
+    const uint8_t * tail = (const uint8_t*)(data + nblocks*4);
+
+    uint32_t k1 = 0;
+
+    switch(len & 3)
+    {
+        case 3: k1 ^= tail[2] << 16;
+        case 2: k1 ^= tail[1] << 8;
+        case 1: k1 ^= tail[0];
+              k1 *= c1; k1 = rotl32(k1,15); k1 *= c2; h1 ^= k1;
+    }
+
+    //----------
+    // finalization
+
+    h1 ^= len;
+
+    h1 = fmix(h1);
+
+    return h1;
+}
+
+
+uint32_t seq_hash(const seq_t* seq)
+{
+    /* TODO */
+    return 0;
+}
+
 static const size_t parser_buf_size = 1000000;