hashmap: factor out getting a hash code from a SHA1

kblees · gitster · commit 039dc71a7cb8 · 2014-07-07T13:56:24.000-07:00
Copying the first bytes of a SHA1 is duplicated in six places,
however, the implications (the actual value would depend on the
endianness of the platform) is documented only once.

Add a properly documented API for this.

Signed-off-by: Karsten Blees &lt;blees@dcon.de&gt;
Signed-off-by: Junio C Hamano &lt;gitster@pobox.com&gt;
diff --git a/Documentation/technical/api-hashmap.txt b/Documentation/technical/api-hashmap.txt
@@ -58,6 +58,15 @@ Functions
 +
 `strihash` and `memihash` are case insensitive versions.
 
+`unsigned int sha1hash(const unsigned char *sha1)`::
+
+	Converts a cryptographic hash (e.g. SHA-1) into an int-sized hash code
+	for use in hash tables. Cryptographic hashes are supposed to have
+	uniform distribution, so in contrast to `memhash()`, this just copies
+	the first `sizeof(int)` bytes without shuffling any bits. Note that
+	the results will be different on big-endian and little-endian
+	platforms, so they should not be stored or transferred over the net.
+
 `void hashmap_init(struct hashmap *map, hashmap_cmp_fn equals_function, size_t initial_size)`::
 
 	Initializes a hashmap structure.
diff --git a/builtin/describe.c b/builtin/describe.c
@@ -56,17 +56,10 @@ static int commit_name_cmp(const struct commit_name *cn1,
 	return hashcmp(cn1->peeled, peeled ? peeled : cn2->peeled);
 }
 
-static inline unsigned int hash_sha1(const unsigned char *sha1)
-{
-	unsigned int hash;
-	memcpy(&hash, sha1, sizeof(hash));
-	return hash;
-}
-
 static inline struct commit_name *find_commit_name(const unsigned char *peeled)
 {
 	struct commit_name key;
-	hashmap_entry_init(&key, hash_sha1(peeled));
+	hashmap_entry_init(&key, sha1hash(peeled));
 	return hashmap_get(&names, &key, peeled);
 }
 
@@ -114,7 +107,7 @@ static void add_to_known_names(const char *path,
 		if (!e) {
 			e = xmalloc(sizeof(struct commit_name));
 			hashcpy(e->peeled, peeled);
-			hashmap_entry_init(e, hash_sha1(peeled));
+			hashmap_entry_init(e, sha1hash(peeled));
 			hashmap_add(&names, e);
 			e->path = NULL;
 		}
diff --git a/decorate.c b/decorate.c
@@ -8,10 +8,7 @@
 
 static unsigned int hash_obj(const struct object *obj, unsigned int n)
 {
-	unsigned int hash;
-
-	memcpy(&hash, obj->sha1, sizeof(unsigned int));
-	return hash % n;
+	return sha1hash(obj->sha1) % n;
 }
 
 static void *insert_decoration(struct decoration *n, const struct object *base, void *decoration)
diff --git a/diffcore-rename.c b/diffcore-rename.c
@@ -242,14 +242,12 @@ struct file_similarity {
 
 static unsigned int hash_filespec(struct diff_filespec *filespec)
 {
-	unsigned int hash;
 	if (!filespec->sha1_valid) {
 		if (diff_populate_filespec(filespec, 0))
 			return 0;
 		hash_sha1_file(filespec->data, filespec->size, "blob", filespec->sha1);
 	}
-	memcpy(&hash, filespec->sha1, sizeof(hash));
-	return hash;
+	return sha1hash(filespec->sha1);
 }
 
 static int find_identical_files(struct hashmap *srcs,
diff --git a/hashmap.h b/hashmap.h
@@ -13,6 +13,17 @@ 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);
 
+static inline unsigned int sha1hash(const unsigned char *sha1)
+{
+	/*
+	 * Equivalent to 'return *(unsigned int *)sha1;', but safe on
+	 * platforms that don't support unaligned reads.
+	 */
+	unsigned int hash;
+	memcpy(&hash, sha1, sizeof(hash));
+	return hash;
+}
+
 /* data structures */
 
 struct hashmap_entry {
diff --git a/khash.h b/khash.h
@@ -320,19 +320,12 @@ static const double __ac_HASH_UPPER = 0.77;
 		code;												\
 	} }
 
-static inline khint_t __kh_oid_hash(const unsigned char *oid)
-{
-	khint_t hash;
-	memcpy(&hash, oid, sizeof(hash));
-	return hash;
-}
-
 #define __kh_oid_cmp(a, b) (hashcmp(a, b) == 0)
 
-KHASH_INIT(sha1, const unsigned char *, void *, 1, __kh_oid_hash, __kh_oid_cmp)
+KHASH_INIT(sha1, const unsigned char *, void *, 1, sha1hash, __kh_oid_cmp)
 typedef kh_sha1_t khash_sha1;
 
-KHASH_INIT(sha1_pos, const unsigned char *, int, 1, __kh_oid_hash, __kh_oid_cmp)
+KHASH_INIT(sha1_pos, const unsigned char *, int, 1, sha1hash, __kh_oid_cmp)
 typedef kh_sha1_pos_t khash_sha1_pos;
 
 #endif /* __AC_KHASH_H */
diff --git a/object.c b/object.c
@@ -50,18 +50,7 @@ int type_from_string(const char *str)
  */
 static unsigned int hash_obj(const unsigned char *sha1, unsigned int n)
 {
-	unsigned int hash;
-
-	/*
-	 * Since the sha1 is essentially random, we just take the
-	 * required number of bits directly from the first
-	 * sizeof(unsigned int) bytes of sha1.  First we have to copy
-	 * the bytes into a properly aligned integer.  If we cared
-	 * about getting consistent results across architectures, we
-	 * would have to call ntohl() here, too.
-	 */
-	memcpy(&hash, sha1, sizeof(unsigned int));
-	return hash & (n - 1);
+	return sha1hash(sha1) & (n - 1);
 }
 
 /*
diff --git a/pack-objects.c b/pack-objects.c
@@ -7,10 +7,9 @@ static uint32_t locate_object_entry_hash(struct packing_data *pdata,
 					 const unsigned char *sha1,
 					 int *found)
 {
-	uint32_t i, hash, mask = (pdata->index_size - 1);
+	uint32_t i, mask = (pdata->index_size - 1);
 
-	memcpy(&hash, sha1, sizeof(uint32_t));
-	i = hash & mask;
+	i = sha1hash(sha1) & mask;
 
 	while (pdata->index[i] > 0) {
 		uint32_t pos = pdata->index[i] - 1;

Original file line number	Diff line number	Diff line change
`@@ -8,10 +8,7 @@`
`8`	`8`
`9`	`9`	`static unsigned int hash_obj(const struct object *obj, unsigned int n)`
`10`	`10`	`{`
`11`		`- unsigned int hash;`
`12`		`-`
`13`		`- memcpy(&hash, obj->sha1, sizeof(unsigned int));`
`14`		`- return hash % n;`
	`11`	`+ return sha1hash(obj->sha1) % n;`
`15`	`12`	`}`
`16`	`13`
`17`	`14`	`static void insert_decoration(struct decoration n, const struct object base, void decoration)`
Original file line number	Diff line number	Diff line change
`@@ -242,14 +242,12 @@ struct file_similarity {`
`242`	`242`
`243`	`243`	`static unsigned int hash_filespec(struct diff_filespec *filespec)`
`244`	`244`	`{`
`245`		`- unsigned int hash;`
`246`	`245`	`if (!filespec->sha1_valid) {`
`247`	`246`	`if (diff_populate_filespec(filespec, 0))`
`248`	`247`	`return 0;`
`249`	`248`	`hash_sha1_file(filespec->data, filespec->size, "blob", filespec->sha1);`
`250`	`249`	`}`
`251`		`- memcpy(&hash, filespec->sha1, sizeof(hash));`
`252`		`- return hash;`
	`250`	`+ return sha1hash(filespec->sha1);`
`253`	`251`	`}`
`254`	`252`
`255`	`253`	`static int find_identical_files(struct hashmap *srcs,`