All of lore.kernel.org
 help / color / mirror / Atom feed
From: Karsten Blees <karsten.blees@gmail.com>
To: Git List <git@vger.kernel.org>, Junio C Hamano <gitster@pobox.com>
Cc: Thomas Rast <tr@thomasrast.ch>,
	Jens Lehmann <Jens.Lehmann@web.de>,
	Karsten Blees <karsten.blees@gmail.com>
Subject: [PATCH v4 07/14] name-hash.c: use new hash map implementation for directories
Date: Thu, 07 Nov 2013 15:38:13 +0100	[thread overview]
Message-ID: <527BA5D5.5070109@gmail.com> (raw)
In-Reply-To: <527BA483.6040803@gmail.com>

Signed-off-by: Karsten Blees <blees@dcon.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 cache.h     |  3 ++-
 name-hash.c | 77 +++++++++++++++----------------------------------------------
 2 files changed, 20 insertions(+), 60 deletions(-)

diff --git a/cache.h b/cache.h
index d1f3c71..84e9ad6 100644
--- a/cache.h
+++ b/cache.h
@@ -4,6 +4,7 @@
 #include "git-compat-util.h"
 #include "strbuf.h"
 #include "hash.h"
+#include "hashmap.h"
 #include "advice.h"
 #include "gettext.h"
 #include "convert.h"
@@ -278,7 +279,7 @@ struct index_state {
 	unsigned name_hash_initialized : 1,
 		 initialized : 1;
 	struct hash_table name_hash;
-	struct hash_table dir_hash;
+	struct hashmap dir_hash;
 };
 
 extern struct index_state the_index;
diff --git a/name-hash.c b/name-hash.c
index e5b6e1a..ae636f8 100644
--- a/name-hash.c
+++ b/name-hash.c
@@ -8,49 +8,28 @@
 #define NO_THE_INDEX_COMPATIBILITY_MACROS
 #include "cache.h"
 
-/*
- * This removes bit 5 if bit 6 is set.
- *
- * That will make US-ASCII characters hash to their upper-case
- * equivalent. We could easily do this one whole word at a time,
- * but that's for future worries.
- */
-static inline unsigned char icase_hash(unsigned char c)
-{
-	return c & ~((c & 0x40) >> 1);
-}
-
-static unsigned int hash_name(const char *name, int namelen)
-{
-	unsigned int hash = 0x123;
-
-	while (namelen--) {
-		unsigned char c = *name++;
-		c = icase_hash(c);
-		hash = hash*101 + c;
-	}
-	return hash;
-}
-
 struct dir_entry {
-	struct dir_entry *next;
+	struct hashmap_entry ent;
 	struct dir_entry *parent;
 	struct cache_entry *ce;
 	int nr;
 	unsigned int namelen;
 };
 
+static int dir_entry_cmp(const struct dir_entry *e1,
+		const struct dir_entry *e2, const char *name)
+{
+	return e1->namelen != e2->namelen || strncasecmp(e1->ce->name,
+			name ? name : e2->ce->name, e1->namelen);
+}
+
 static struct dir_entry *find_dir_entry(struct index_state *istate,
 		const char *name, unsigned int namelen)
 {
-	unsigned int hash = hash_name(name, namelen);
-	struct dir_entry *dir;
-
-	for (dir = lookup_hash(hash, &istate->dir_hash); dir; dir = dir->next)
-		if (dir->namelen == namelen &&
-		    !strncasecmp(dir->ce->name, name, namelen))
-			return dir;
-	return NULL;
+	struct dir_entry key;
+	hashmap_entry_init(&key, memihash(name, namelen));
+	key.namelen = namelen;
+	return hashmap_get(&istate->dir_hash, &key, name);
 }
 
 static struct dir_entry *hash_dir_entry(struct index_state *istate,
@@ -84,18 +63,11 @@ static struct dir_entry *hash_dir_entry(struct index_state *istate,
 	dir = find_dir_entry(istate, ce->name, namelen);
 	if (!dir) {
 		/* not found, create it and add to hash table */
-		void **pdir;
-		unsigned int hash = hash_name(ce->name, namelen);
-
 		dir = xcalloc(1, sizeof(struct dir_entry));
+		hashmap_entry_init(dir, memihash(ce->name, namelen));
 		dir->namelen = namelen;
 		dir->ce = ce;
-
-		pdir = insert_hash(hash, dir, &istate->dir_hash);
-		if (pdir) {
-			dir->next = *pdir;
-			*pdir = dir;
-		}
+		hashmap_add(&istate->dir_hash, dir);
 
 		/* recursively add missing parent directories */
 		dir->parent = hash_dir_entry(istate, ce, namelen);
@@ -134,7 +106,7 @@ static void hash_index_entry(struct index_state *istate, struct cache_entry *ce)
 		return;
 	ce->ce_flags |= CE_HASHED;
 	ce->next = NULL;
-	hash = hash_name(ce->name, ce_namelen(ce));
+	hash = memihash(ce->name, ce_namelen(ce));
 	pos = insert_hash(hash, ce, &istate->name_hash);
 	if (pos) {
 		ce->next = *pos;
@@ -153,6 +125,7 @@ static void lazy_init_name_hash(struct index_state *istate)
 		return;
 	if (istate->cache_nr)
 		preallocate_hash(&istate->name_hash, istate->cache_nr);
+	hashmap_init(&istate->dir_hash, (hashmap_cmp_fn) dir_entry_cmp, 0);
 	for (nr = 0; nr < istate->cache_nr; nr++)
 		hash_index_entry(istate, istate->cache[nr]);
 	istate->name_hash_initialized = 1;
@@ -247,7 +220,7 @@ struct cache_entry *index_dir_exists(struct index_state *istate, const char *nam
 
 struct cache_entry *index_file_exists(struct index_state *istate, const char *name, int namelen, int icase)
 {
-	unsigned int hash = hash_name(name, namelen);
+	unsigned int hash = memihash(name, namelen);
 	struct cache_entry *ce;
 
 	lazy_init_name_hash(istate);
@@ -270,26 +243,12 @@ struct cache_entry *index_name_exists(struct index_state *istate, const char *na
 	return index_file_exists(istate, name, namelen, icase);
 }
 
-static int free_dir_entry(void *entry, void *unused)
-{
-	struct dir_entry *dir = entry;
-	while (dir) {
-		struct dir_entry *next = dir->next;
-		free(dir);
-		dir = next;
-	}
-	return 0;
-}
-
 void free_name_hash(struct index_state *istate)
 {
 	if (!istate->name_hash_initialized)
 		return;
 	istate->name_hash_initialized = 0;
-	if (ignore_case)
-		/* free directory entries */
-		for_each_hash(&istate->dir_hash, free_dir_entry, NULL);
 
 	free_hash(&istate->name_hash);
-	free_hash(&istate->dir_hash);
+	hashmap_free(&istate->dir_hash, free);
 }
-- 
1.8.4.msysgit.0.12.g88f5ed0

  parent reply	other threads:[~2013-11-07 14:38 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-11-07 14:32 [PATCH v4 00/14] New hash table implementation Karsten Blees
2013-11-07 14:33 ` [PATCH v4 01/14] submodule: don't access the .gitmodules cache entry after removing it Karsten Blees
2013-11-07 22:27   ` Heiko Voigt
2013-11-07 14:34 ` [PATCH v4 02/14] add a hashtable implementation that supports O(1) removal Karsten Blees
2013-11-07 21:40   ` Junio C Hamano
2013-11-08 10:27     ` Karsten Blees
2013-11-08 16:45       ` Philip Oakley
2013-11-08 17:08       ` Junio C Hamano
2013-11-13 16:37         ` Karsten Blees
2013-11-07 14:35 ` [PATCH v4 03/14] buitin/describe.c: use new hash map implementation Karsten Blees
2013-11-07 14:36 ` [PATCH v4 04/14] diffcore-rename.c: move code around to prepare for the next patch Karsten Blees
2013-11-07 14:36 ` [PATCH v4 05/14] diffcore-rename.c: simplify finding exact renames Karsten Blees
2013-11-07 14:37 ` [PATCH v4 06/14] diffcore-rename.c: use new hash map implementation Karsten Blees
2013-11-07 14:38 ` Karsten Blees [this message]
2013-11-07 14:38 ` [PATCH v4 08/14] name-hash.c: remove unreferenced directory entries Karsten Blees
2013-11-07 14:39 ` [PATCH v4 09/14] name-hash.c: use new hash map implementation for cache entries Karsten Blees
2013-11-07 14:39 ` [PATCH v4 10/14] name-hash.c: remove cache entries instead of marking them CE_UNHASHED Karsten Blees
2013-11-07 14:40 ` [PATCH v4 11/14] remove old hash.[ch] implementation Karsten Blees
2013-11-07 14:43 ` [PATCH v4 12/14] fix 'git update-index --verbose --again' output Karsten Blees
2013-11-07 22:12   ` Junio C Hamano
2013-11-08 10:27     ` Karsten Blees
2013-11-07 14:44 ` [PATCH v4 13/14] builtin/update-index.c: cleanup update_one Karsten Blees
2013-11-07 21:40   ` Junio C Hamano
2013-11-08 10:27     ` Karsten Blees
2013-11-07 14:45 ` [PATCH v4 14/14] read-cache.c: fix memory leaks caused by removed cache entries Karsten Blees
2013-11-07 21:40   ` Junio C Hamano

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=527BA5D5.5070109@gmail.com \
    --to=karsten.blees@gmail.com \
    --cc=Jens.Lehmann@web.de \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=tr@thomasrast.ch \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.