git/tree-walk.h

92 lines
2.7 KiB
C
Raw Normal View History

#ifndef TREE_WALK_H
#define TREE_WALK_H
#include "cache.h"
struct name_entry {
struct object_id oid;
const char *path;
int pathlen;
unsigned int mode;
};
struct tree_desc {
const void *buffer;
struct name_entry entry;
unsigned int size;
};
static inline const struct object_id *tree_entry_extract(struct tree_desc *desc, const char **pathp, unsigned int *modep)
{
*pathp = desc->entry.path;
tree-walk: finally switch over tree descriptors to contain a pre-parsed entry This continues 4651ece8 (Switch over tree descriptors to contain a pre-parsed entry) and moves the only rest computational part mode = canon_mode(mode) from tree_entry_extract() to tree entry decode phase - to decode_tree_entry(). The reason to do it, is that canon_mode() is at least 2 conditional jumps for regular files, and that could be noticeable should canon_mode() be invoked several times. That does not matter for current Git codebase, where typical tree traversal is while (t->size) { sha1 = tree_entry_extract(t, &path, &mode); ... update_tree_entry(t); } i.e. we do t -> sha1,path.mode "extraction" only once per entry. In such cases, it does not matter performance-wise, where that mode canonicalization is done - either once in tree_entry_extract(), or once in decode_tree_entry() called by update_tree_entry() - it is approximately the same. But for future code, which could need to work with several tree_desc's in parallel, it could be handy to operate on tree_desc descriptors, and do "extracts" only when needed, or at all, access only relevant part of it through structure fields directly. And for such situations, having canon_mode() be done once in decode phase is better - we won't need to pay the performance price of 2 extra conditional jumps on every t->mode access. So let's move mode canonicalization to decode_tree_entry(). That was the final bit. Now after tree entry is decoded, it is fully ready and could be accessed either directly via field, or through tree_entry_extract() which this time got really "totally trivial". Signed-off-by: Kirill Smelkov <kirr@mns.spb.ru> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-02-06 19:36:31 +08:00
*modep = desc->entry.mode;
return &desc->entry.oid;
}
static inline int tree_entry_len(const struct name_entry *ne)
{
return ne->pathlen;
}
/*
* The _gently versions of these functions warn and return false on a
* corrupt tree entry rather than dying,
*/
void update_tree_entry(struct tree_desc *);
int update_tree_entry_gently(struct tree_desc *);
void init_tree_desc(struct tree_desc *desc, const void *buf, unsigned long size);
int init_tree_desc_gently(struct tree_desc *desc, const void *buf, unsigned long size);
/*
* Helper function that does both tree_entry_extract() and update_tree_entry()
* and returns true for success
*/
tree_entry(): new tree-walking helper function This adds a "tree_entry()" function that combines the common operation of doing a "tree_entry_extract()" + "update_tree_entry()". It also has a simplified calling convention, designed for simple loops that traverse over a whole tree: the arguments are pointers to the tree descriptor and a name_entry structure to fill in, and it returns a boolean "true" if there was an entry left to be gotten in the tree. This allows tree traversal with struct tree_desc desc; struct name_entry entry; desc.buf = tree->buffer; desc.size = tree->size; while (tree_entry(&desc, &entry) { ... use "entry.{path, sha1, mode, pathlen}" ... } which is not only shorter than writing it out in full, it's hopefully less error prone too. [ It's actually a tad faster too - we don't need to recalculate the entry pathlength in both extract and update, but need to do it only once. Also, some callers can avoid doing a "strlen()" on the result, since it's returned as part of the name_entry structure. However, by now we're talking just 1% speedup on "git-rev-list --objects --all", and we're definitely at the point where tree walking is no longer the issue any more. ] NOTE! Not everybody wants to use this new helper function, since some of the tree walkers very much on purpose do the descriptor update separately from the entry extraction. So the "extract + update" sequence still remains as the core sequence, this is just a simplified interface. We should probably add a silly two-line inline helper function for initializing the descriptor from the "struct tree" too, just to cut down on the noise from that common "desc" initializer. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-31 00:45:45 +08:00
int tree_entry(struct tree_desc *, struct name_entry *);
int tree_entry_gently(struct tree_desc *, struct name_entry *);
tree_entry(): new tree-walking helper function This adds a "tree_entry()" function that combines the common operation of doing a "tree_entry_extract()" + "update_tree_entry()". It also has a simplified calling convention, designed for simple loops that traverse over a whole tree: the arguments are pointers to the tree descriptor and a name_entry structure to fill in, and it returns a boolean "true" if there was an entry left to be gotten in the tree. This allows tree traversal with struct tree_desc desc; struct name_entry entry; desc.buf = tree->buffer; desc.size = tree->size; while (tree_entry(&desc, &entry) { ... use "entry.{path, sha1, mode, pathlen}" ... } which is not only shorter than writing it out in full, it's hopefully less error prone too. [ It's actually a tad faster too - we don't need to recalculate the entry pathlength in both extract and update, but need to do it only once. Also, some callers can avoid doing a "strlen()" on the result, since it's returned as part of the name_entry structure. However, by now we're talking just 1% speedup on "git-rev-list --objects --all", and we're definitely at the point where tree walking is no longer the issue any more. ] NOTE! Not everybody wants to use this new helper function, since some of the tree walkers very much on purpose do the descriptor update separately from the entry extraction. So the "extract + update" sequence still remains as the core sequence, this is just a simplified interface. We should probably add a silly two-line inline helper function for initializing the descriptor from the "struct tree" too, just to cut down on the noise from that common "desc" initializer. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-31 00:45:45 +08:00
void *fill_tree_descriptor(struct tree_desc *desc, const struct object_id *oid);
struct traverse_info;
typedef int (*traverse_callback_t)(int n, unsigned long mask, unsigned long dirmask, struct name_entry *entry, struct traverse_info *);
int traverse_trees(struct index_state *istate, int n, struct tree_desc *t, struct traverse_info *info);
enum get_oid_result get_tree_entry_follow_symlinks(struct object_id *tree_oid, const char *name, struct object_id *result, struct strbuf *result_path, unsigned *mode);
struct traverse_info {
const char *traverse_path;
struct traverse_info *prev;
struct name_entry name;
int pathlen;
struct pathspec *pathspec;
unsigned long df_conflicts;
traverse_callback_t fn;
void *data;
int show_all_errors;
};
int get_tree_entry(const struct object_id *, const char *, struct object_id *, unsigned *);
extern char *make_traverse_path(char *path, const struct traverse_info *info, const struct name_entry *n);
extern void setup_traverse_info(struct traverse_info *info, const char *base);
static inline int traverse_path_len(const struct traverse_info *info, const struct name_entry *n)
{
return info->pathlen + tree_entry_len(n);
}
/* in general, positive means "kind of interesting" */
enum interesting {
all_entries_not_interesting = -1, /* no, and no subsequent entries will be either */
entry_not_interesting = 0,
entry_interesting = 1,
all_entries_interesting = 2 /* yes, and all subsequent entries will be */
};
enum interesting tree_entry_interesting(struct index_state *istate,
const struct name_entry *,
struct strbuf *, int,
const struct pathspec *ps);
#endif