9aae808cd0
before, and be more bugfree than ever! 2000-10-25 Not Zed <NotZed@HelixCode.com> * ibex_internal.h (IBEX_VERSION): Bumped to another version. The file format hasn't changed, but earlier bugs may create invalid files. * block.c (ibex_block_read): Use the root data directly. (ibex_block_cache_open): As well. (ibex_block_get): And here too. (ibex_block_cache_sync): Sync the root block directly here. * block.h: Pad root block out to 1024 bytes. Added root block to struct _memcache. * disktail.c (tail_get): Dirty the root block. (tail_get): Fix for changes to root access. (disk_remove): And here too. * wordindexmem.c (sync_cache_entry): Handle the case of not having any files in the list, which can happen now. (word_index_pre): Make sure we set the wordid on the new cache entry. * ibex_block.c (ibex_save): Sigh. Pass the right argument to index_post. * block.c (ibex_block_cache_open): Create a word_index_mem for indexing the words, rather than a word_index. * ibex_block.c (ibex_index_buffer): If we haven't called index_pre yet, do it before indexing anything. (ibex_save): If wehave called index_pre previously, call index_post. (ibex_close): And same for here. * index.h: Added a cursor class, and cursor retrieval function for iterating through an index's keys. * wordindexmem.c (ibex_create_word_index_mem): New word class, similar to wordindex, but meant to be faster for updates. (word_index_pre): Implement. We load all keys into memory. (word_index_post): Implement. We sync and free all keys. (find): Remove lru code, its no longer a cache, but a lookup table. (add_index_cache): Remove lru code here too. (find_name): And here. (word_flush): Flush the hashtable direct. (word_close): Call flush to flush, rather than doing it ourselves. (add_index_cache): If we are in an index state, we can assume a cache miss == a new word. (word_index_post): Maintain whether or not we are in an index state, and the depth of the state. (word_index_pre): Likewise. Dont reread the index if we have already. (cache_sanity): Fixed for struct changes. * wordindex.h (IBEXWordClass): Added functions to prepare/cleanup for lots of indexing. i.e. can be used to optimise indexing speed at the cost of extra memory usage during the indexing process. * hash.c (hash_cursor_create): Create a new cursor for iterating through a hashtable. (hash_cursor_close): 'close' the cursor. It is upto the application to close any cursors it creates. (hash_cursor_next): Goto the next key id. (hash_cursor_next_key): Goto the next key, reutrn the key. (hash_get_cursor): Return a cursor object. * wordindex.c (word_index_post): (word_index_pre): Added (empty) callbacks for pre/post functions. svn path=/trunk/; revision=6165
73 lines
2.7 KiB
C
73 lines
2.7 KiB
C
/* -*- Mode: C; tab-width: 8; indent-tabs-mode: t; c-basic-offset: 8 -*-
|
|
*
|
|
* Copyright (C) 2000 Helix Code, Inc.
|
|
*
|
|
* Authors: Michael Zucchi <notzed@helixcode.com>
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU Library General Public License
|
|
* as published by the Free Software Foundation; either version 2 of
|
|
* the License, or (at your option) any later version.
|
|
*
|
|
* This library is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
* Library General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU Library General Public
|
|
* License along with the Gnome Library; see the file COPYING.LIB. If not,
|
|
* write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
|
|
* Boston, MA 02111-1307, USA.
|
|
*/
|
|
|
|
#ifndef _WORDINDEX_H
|
|
#define _WORDINDEX_H
|
|
|
|
#include <glib.h>
|
|
|
|
#include "block.h"
|
|
#include "index.h"
|
|
|
|
struct _IBEXWord;
|
|
|
|
/* not used yet */
|
|
typedef void (*IBEXNormaliseFunc)(char *source, int len, char *dest);
|
|
|
|
struct _IBEXWordClass {
|
|
int (*sync)(struct _IBEXWord *);
|
|
int (*flush)(struct _IBEXWord *);
|
|
int (*close)(struct _IBEXWord *);
|
|
|
|
void (*index_pre)(struct _IBEXWord *); /* get ready for doing a lot of indexing. may be a nop */
|
|
void (*index_post)(struct _IBEXWord *);
|
|
|
|
void (*unindex_name)(struct _IBEXWord *, const char *name); /* unindex all entries for name */
|
|
gboolean (*contains_name)(struct _IBEXWord *, const char *name); /* index contains data for name */
|
|
GPtrArray *(*find)(struct _IBEXWord *, const char *word); /* returns all matches for word */
|
|
gboolean (*find_name)(struct _IBEXWord *, const char *name, const char *word); /* find if name contains word */
|
|
void (*add)(struct _IBEXWord *, const char *name, const char *word); /* adds a single word to name */
|
|
void (*add_list)(struct _IBEXWord *, const char *name, GPtrArray *words);/* adds a bunch of words to a given name */
|
|
};
|
|
|
|
struct _IBEXWord {
|
|
struct _IBEXWordClass *klass;
|
|
struct _IBEXStore *wordstore;
|
|
struct _IBEXIndex *wordindex;
|
|
struct _IBEXStore *namestore;
|
|
struct _IBEXIndex *nameindex;
|
|
|
|
/* word caching info (should probably be modularised) */
|
|
GHashTable *wordcache; /* word->struct _wordcache mapping */
|
|
struct _list wordnodes; /* LRU list of wordcache structures */
|
|
int wordcount; /* how much space used in cache */
|
|
int precount;
|
|
};
|
|
|
|
|
|
struct _IBEXWord *ibex_create_word_index(struct _memcache *bc, blockid_t *wordroot, blockid_t *nameroot);
|
|
|
|
/* alternate implemenation */
|
|
struct _IBEXWord *ibex_create_word_index_mem(struct _memcache *bc, blockid_t *wordroot, blockid_t *nameroot);
|
|
|
|
#endif /* !_WORDINDEX_H */
|