[PATCH 2/6] hashmap: allow memihash computation to be continued

From: git@jeffhostetler.com <git@jeffhostetler.com>
Date: Mar 22, 2017, 17:14 UTC
Message-ID: <1490202865-31325-3-git-send-email-git@jeffhostetler.com>
In-Reply-To: <1490202865-31325-1-git-send-email-git@jeffhostetler.com>

From: Jeff Hostetler <jeffhost@microsoft.com>

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>
---
 hashmap.c | 17 +++++++++++++++++
 hashmap.h |  1 +
 2 files changed, 18 insertions(+)

diff --git a/hashmap.c b/hashmap.c
index b10b642..505e63f 100644
--- 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 ab7958a..45eda69 100644
--- 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)
 {

-- 
2.7.4