hashmap: allow memihash computation to be continued

Add variant of memihash() to allow the hash computation to
be continued.  There are times when we compute the hash on
a full path and then the hash on just the path to the parent
directory.  This can be expensive on large repositories.

With this, we can hash the parent directory first. And then
continue the computation to include the "/filename".

Signed-off-by: Jeff Hostetler <jeffhost@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/hashmap.c b/hashmap.c
index b10b642229ca0c3e6eb27142f080921dd5c3aece..93793cb954e4bde0df9c57131a782c32fc15dc36 100644 (file)
--- a/hashmap.c
+++ b/hashmap.c
@@ -50,6 +50,23 @@ unsigned int memihash(const void *buf, size_t len)
        return hash;
 }
 
+/*
+ * Incoporate another chunk of data into a memihash
+ * computation.
+ */
+unsigned int memihash_cont(unsigned int hash_seed, const void *buf, size_t len)
+{
+       unsigned int hash = hash_seed;
+       unsigned char *ucbuf = (unsigned char *) buf;
+       while (len--) {
+               unsigned int c = *ucbuf++;
+               if (c >= 'a' && c <= 'z')
+                       c -= 'a' - 'A';
+               hash = (hash * FNV32_PRIME) ^ c;
+       }
+       return hash;
+}
+
 #define HASHMAP_INITIAL_SIZE 64
 /* grow / shrink by 2^2 */
 #define HASHMAP_RESIZE_BITS 2

diff --git a/hashmap.h b/hashmap.h
index ab7958ae333bcc635ba2ac8e40ee8aa6d8814ab4..45eda693bdbc7efc53f6b0ce29a172bcb574cfdf 100644 (file)
--- a/hashmap.h
+++ b/hashmap.h
@@ -12,6 +12,7 @@ extern unsigned int strhash(const char *buf);
 extern unsigned int strihash(const char *buf);
 extern unsigned int memhash(const void *buf, size_t len);
 extern unsigned int memihash(const void *buf, size_t len);
+extern unsigned int memihash_cont(unsigned int hash_seed, const void *buf, size_t len);
 
 static inline unsigned int sha1hash(const unsigned char *sha1)
 {