[PATCH 4/7] Make hash_name_lookup able to do case-independent lookups
- From
Linus Torvalds <torvalds@linux-foundation.org>
- Date
- Mar 22, 2008, 17:30 UTC
- Message-ID
- <alpine.LFD.1.00.0803221028170.3020@woody.linux-foundation.org>
- In-Reply-To
- <alpine.LFD.1.00.0803221025410.3020@woody.linux-foundation.org>
From: Linus Torvalds <torvalds@woody.linux-foundation.org> Date: Fri, 21 Mar 2008 15:55:19 -0700
Right now nobody uses it, but "index_name_exists()" gets a flag so you can enable it on a case-by-case basis.
Signed-of-by: Linus Torvalds <torvalds@linux-foundation.org> ---
Oooh.. We actually have some (admittedly stupid) case insensitivity code starting to appear. So we now hash the names insensitively, and we have the _capability_ to do case-insensitive lookups, but nobody actually uses that insensitive lookup capability yet.
But things are now starting to get interesting.
cache.h | 4 ++-- dir.c | 2 +- name-hash.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++++-- unpack-trees.c | 2 +- 4 files changed, 52 insertions(+), 6 deletions(-)
diff --git a/cache.h b/cache.h index 76d95d2..a9ddaa1 100644 --- a/cache.h +++ b/cache.h @@ -264,7 +264,7 @@ static inline void remove_name_hash(struct cache_entry *ce) #define refresh_cache(flags) refresh_index(&the_index, (flags), NULL, NULL) #define ce_match_stat(ce, st, options) ie_match_stat(&the_index, (ce), (st), (options)) #define ce_modified(ce, st, options) ie_modified(&the_index, (ce), (st), (options)) -#define cache_name_exists(name, namelen) index_name_exists(&the_index, (name), (namelen)) +#define cache_name_exists(name, namelen, igncase) index_name_exists(&the_index, (name), (namelen), (igncase)) #endif enum object_type { @@ -353,7 +353,7 @@ extern int write_index(const struct index_state *, int newfd); extern int discard_index(struct index_state *); extern int unmerged_index(const struct index_state *); extern int verify_path(const char *path); -extern struct cache_entry *index_name_exists(struct index_state *istate, const char *name, int namelen); +extern struct cache_entry *index_name_exists(struct index_state *istate, const char *name, int namelen, int igncase); extern int index_name_pos(const struct index_state *, const char *name, int namelen); #define ADD_CACHE_OK_TO_ADD 1 /* Ok to add */ #define ADD_CACHE_OK_TO_REPLACE 2 /* Ok to replace file/directory */ diff --git a/dir.c b/dir.c index edc458e..7362e83 100644 --- a/dir.c +++ b/dir.c @@ -371,7 +371,7 @@ static struct dir_entry *dir_entry_new(const char *pathname, int len) struct dir_entry *dir_add_name(struct dir_struct *dir, const char *pathname, int len) { - if (cache_name_exists(pathname, len)) + if (cache_name_exists(pathname, len, 0)) return NULL; ALLOC_GROW(dir->entries, dir->nr+1, dir->alloc); diff --git a/name-hash.c b/name-hash.c index 2678148..2253870 100644 --- a/name-hash.c +++ b/name-hash.c @@ -8,12 +8,25 @@ #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; do { unsigned char c = *name++; + c = icase_hash(c); hash = hash*101 + c; } while (--namelen); return hash; @@ -54,7 +67,40 @@ void add_name_hash(struct index_state *istate, struct cache_entry *ce) hash_index_entry(istate, ce); } -struct cache_entry *index_name_exists(struct index_state *istate, const char *name, int namelen) +static int slow_same_name(const char *name1, int len1, const char *name2, int len2) +{ + if (len1 != len2) + return 0; + + while (len1) { + unsigned char c1 = *name1++; + unsigned char c2 = *name2++; + len1--; + if (c1 != c2) { + c1 = toupper(c1); + c2 = toupper(c2); + if (c1 != c2) + return 0; + } + } + return 1; +} + +static int same_name(const struct cache_entry *ce, const char *name, int namelen, int icase) +{ + int len = ce_namelen(ce); + + /* + * Always fo exact compare (even if we want a case-ignoring comparison + * we do the quick exact one first, because it will be the common case). + */ + if (len == namelen && !cache_name_compare(name, namelen, ce->name, len)) + return 1; + + return icase && slow_same_name(name, namelen, ce->name, len); +} + +struct cache_entry *index_name_exists(struct index_state *istate, const char *name, int namelen, int icase) { unsigned int hash = hash_name(name, namelen); struct cache_entry *ce; @@ -64,7 +110,7 @@ struct cache_entry *index_name_exists(struct index_state *istate, const char *na while (ce) { if (!(ce->ce_flags & CE_UNHASHED)) { - if (!cache_name_compare(name, namelen, ce->name, ce->ce_flags)) + if (same_name(ce, name, namelen, icase)) return ce; } ce = ce->next; diff --git a/unpack-trees.c b/unpack-trees.c index ca4c845..bf7d8f6 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -582,7 +582,7 @@ static int verify_absent(struct cache_entry *ce, const char *action, * delete this path, which is in a subdirectory that * is being replaced with a blob. */ - result = index_name_exists(&o->result, ce->name, ce_namelen(ce)); + result = index_name_exists(&o->result, ce->name, ce_namelen(ce), 0); if (result) { if (result->ce_flags & CE_REMOVE) return 0;
-- 1.5.5.rc0.28.g61a0.dirty