diff options
author | Junio C Hamano <gitster@pobox.com> | 2016-07-26 00:13:33 +0300 |
---|---|---|
committer | Junio C Hamano <gitster@pobox.com> | 2016-07-26 00:13:33 +0300 |
commit | 87492cb24d9d8be8e18217b89ae5f090089ff31d (patch) | |
tree | b517e8efaa98fa713d8b6286ed6ee1c08c385a2e /refs | |
parent | 702ebbf4e2937accbac8184f87932f961e626a63 (diff) | |
parent | 2880d16f09635f9d43247b27fd7e6508b992e599 (diff) |
Merge branch 'mh/ref-iterators'
The API to iterate over all the refs (i.e. for_each_ref(), etc.)
has been revamped.
* mh/ref-iterators:
for_each_reflog(): reimplement using iterators
dir_iterator: new API for iterating over a directory tree
for_each_reflog(): don't abort for bad references
do_for_each_ref(): reimplement using reference iteration
refs: introduce an iterator interface
ref_resolves_to_object(): new function
entry_resolves_to_object(): rename function from ref_resolves_to_object()
get_ref_cache(): only create an instance if there is a submodule
remote rm: handle symbolic refs correctly
delete_refs(): add a flags argument
refs: use name "prefix" consistently
do_for_each_ref(): move docstring to the header file
refs: remove unnecessary "extern" keywords
Diffstat (limited to 'refs')
-rw-r--r-- | refs/files-backend.c | 631 | ||||
-rw-r--r-- | refs/iterator.c | 384 | ||||
-rw-r--r-- | refs/refs-internal.h | 226 |
3 files changed, 987 insertions, 254 deletions
diff --git a/refs/files-backend.c b/refs/files-backend.c index 1bf643025c..12290d2496 100644 --- a/refs/files-backend.c +++ b/refs/files-backend.c @@ -1,6 +1,8 @@ #include "../cache.h" #include "../refs.h" #include "refs-internal.h" +#include "../iterator.h" +#include "../dir-iterator.h" #include "../lockfile.h" #include "../object.h" #include "../dir.h" @@ -513,68 +515,36 @@ static void sort_ref_dir(struct ref_dir *dir) } /* - * Return true iff the reference described by entry can be resolved to - * an object in the database. Emit a warning if the referred-to - * object does not exist. + * Return true if refname, which has the specified oid and flags, can + * be resolved to an object in the database. If the referred-to object + * does not exist, emit a warning and return false. */ -static int ref_resolves_to_object(struct ref_entry *entry) +static int ref_resolves_to_object(const char *refname, + const struct object_id *oid, + unsigned int flags) { - if (entry->flag & REF_ISBROKEN) + if (flags & REF_ISBROKEN) return 0; - if (!has_sha1_file(entry->u.value.oid.hash)) { - error("%s does not point to a valid object!", entry->name); + if (!has_sha1_file(oid->hash)) { + error("%s does not point to a valid object!", refname); return 0; } return 1; } /* - * current_ref is a performance hack: when iterating over references - * using the for_each_ref*() functions, current_ref is set to the - * current reference's entry before calling the callback function. If - * the callback function calls peel_ref(), then peel_ref() first - * checks whether the reference to be peeled is the current reference - * (it usually is) and if so, returns that reference's peeled version - * if it is available. This avoids a refname lookup in a common case. + * Return true if the reference described by entry can be resolved to + * an object in the database; otherwise, emit a warning and return + * false. */ -static struct ref_entry *current_ref; - -typedef int each_ref_entry_fn(struct ref_entry *entry, void *cb_data); - -struct ref_entry_cb { - const char *base; - int trim; - int flags; - each_ref_fn *fn; - void *cb_data; -}; - -/* - * Handle one reference in a do_for_each_ref*()-style iteration, - * calling an each_ref_fn for each entry. - */ -static int do_one_ref(struct ref_entry *entry, void *cb_data) +static int entry_resolves_to_object(struct ref_entry *entry) { - struct ref_entry_cb *data = cb_data; - struct ref_entry *old_current_ref; - int retval; - - if (!starts_with(entry->name, data->base)) - return 0; - - if (!(data->flags & DO_FOR_EACH_INCLUDE_BROKEN) && - !ref_resolves_to_object(entry)) - return 0; - - /* Store the old value, in case this is a recursive call: */ - old_current_ref = current_ref; - current_ref = entry; - retval = data->fn(entry->name + data->trim, &entry->u.value.oid, - entry->flag, data->cb_data); - current_ref = old_current_ref; - return retval; + return ref_resolves_to_object(entry->name, + &entry->u.value.oid, entry->flag); } +typedef int each_ref_entry_fn(struct ref_entry *entry, void *cb_data); + /* * Call fn for each reference in dir that has index in the range * offset <= index < dir->nr. Recurse into subdirectories that are in @@ -604,78 +574,6 @@ static int do_for_each_entry_in_dir(struct ref_dir *dir, int offset, } /* - * Call fn for each reference in the union of dir1 and dir2, in order - * by refname. Recurse into subdirectories. If a value entry appears - * in both dir1 and dir2, then only process the version that is in - * dir2. The input dirs must already be sorted, but subdirs will be - * sorted as needed. fn is called for all references, including - * broken ones. - */ -static int do_for_each_entry_in_dirs(struct ref_dir *dir1, - struct ref_dir *dir2, - each_ref_entry_fn fn, void *cb_data) -{ - int retval; - int i1 = 0, i2 = 0; - - assert(dir1->sorted == dir1->nr); - assert(dir2->sorted == dir2->nr); - while (1) { - struct ref_entry *e1, *e2; - int cmp; - if (i1 == dir1->nr) { - return do_for_each_entry_in_dir(dir2, i2, fn, cb_data); - } - if (i2 == dir2->nr) { - return do_for_each_entry_in_dir(dir1, i1, fn, cb_data); - } - e1 = dir1->entries[i1]; - e2 = dir2->entries[i2]; - cmp = strcmp(e1->name, e2->name); - if (cmp == 0) { - if ((e1->flag & REF_DIR) && (e2->flag & REF_DIR)) { - /* Both are directories; descend them in parallel. */ - struct ref_dir *subdir1 = get_ref_dir(e1); - struct ref_dir *subdir2 = get_ref_dir(e2); - sort_ref_dir(subdir1); - sort_ref_dir(subdir2); - retval = do_for_each_entry_in_dirs( - subdir1, subdir2, fn, cb_data); - i1++; - i2++; - } else if (!(e1->flag & REF_DIR) && !(e2->flag & REF_DIR)) { - /* Both are references; ignore the one from dir1. */ - retval = fn(e2, cb_data); - i1++; - i2++; - } else { - die("conflict between reference and directory: %s", - e1->name); - } - } else { - struct ref_entry *e; - if (cmp < 0) { - e = e1; - i1++; - } else { - e = e2; - i2++; - } - if (e->flag & REF_DIR) { - struct ref_dir *subdir = get_ref_dir(e); - sort_ref_dir(subdir); - retval = do_for_each_entry_in_dir( - subdir, 0, fn, cb_data); - } else { - retval = fn(e, cb_data); - } - } - if (retval) - return retval; - } -} - -/* * Load all of the refs from the dir into our in-memory cache. The hard work * of loading loose refs is done by get_ref_dir(), so we just need to recurse * through all of the sub-directories. We do not even need to care about @@ -691,6 +589,153 @@ static void prime_ref_dir(struct ref_dir *dir) } } +/* + * A level in the reference hierarchy that is currently being iterated + * through. + */ +struct cache_ref_iterator_level { + /* + * The ref_dir being iterated over at this level. The ref_dir + * is sorted before being stored here. + */ + struct ref_dir *dir; + + /* + * The index of the current entry within dir (which might + * itself be a directory). If index == -1, then the iteration + * hasn't yet begun. If index == dir->nr, then the iteration + * through this level is over. + */ + int index; +}; + +/* + * Represent an iteration through a ref_dir in the memory cache. The + * iteration recurses through subdirectories. + */ +struct cache_ref_iterator { + struct ref_iterator base; + + /* + * The number of levels currently on the stack. This is always + * at least 1, because when it becomes zero the iteration is + * ended and this struct is freed. + */ + size_t levels_nr; + + /* The number of levels that have been allocated on the stack */ + size_t levels_alloc; + + /* + * A stack of levels. levels[0] is the uppermost level that is + * being iterated over in this iteration. (This is not + * necessary the top level in the references hierarchy. If we + * are iterating through a subtree, then levels[0] will hold + * the ref_dir for that subtree, and subsequent levels will go + * on from there.) + */ + struct cache_ref_iterator_level *levels; +}; + +static int cache_ref_iterator_advance(struct ref_iterator *ref_iterator) +{ + struct cache_ref_iterator *iter = + (struct cache_ref_iterator *)ref_iterator; + + while (1) { + struct cache_ref_iterator_level *level = + &iter->levels[iter->levels_nr - 1]; + struct ref_dir *dir = level->dir; + struct ref_entry *entry; + + if (level->index == -1) + sort_ref_dir(dir); + + if (++level->index == level->dir->nr) { + /* This level is exhausted; pop up a level */ + if (--iter->levels_nr == 0) + return ref_iterator_abort(ref_iterator); + + continue; + } + + entry = dir->entries[level->index]; + + if (entry->flag & REF_DIR) { + /* push down a level */ + ALLOC_GROW(iter->levels, iter->levels_nr + 1, + iter->levels_alloc); + + level = &iter->levels[iter->levels_nr++]; + level->dir = get_ref_dir(entry); + level->index = -1; + } else { + iter->base.refname = entry->name; + iter->base.oid = &entry->u.value.oid; + iter->base.flags = entry->flag; + return ITER_OK; + } + } +} + +static enum peel_status peel_entry(struct ref_entry *entry, int repeel); + +static int cache_ref_iterator_peel(struct ref_iterator *ref_iterator, + struct object_id *peeled) +{ + struct cache_ref_iterator *iter = + (struct cache_ref_iterator *)ref_iterator; + struct cache_ref_iterator_level *level; + struct ref_entry *entry; + + level = &iter->levels[iter->levels_nr - 1]; + + if (level->index == -1) + die("BUG: peel called before advance for cache iterator"); + + entry = level->dir->entries[level->index]; + + if (peel_entry(entry, 0)) + return -1; + hashcpy(peeled->hash, entry->u.value.peeled.hash); + return 0; +} + +static int cache_ref_iterator_abort(struct ref_iterator *ref_iterator) +{ + struct cache_ref_iterator *iter = + (struct cache_ref_iterator *)ref_iterator; + + free(iter->levels); + base_ref_iterator_free(ref_iterator); + return ITER_DONE; +} + +static struct ref_iterator_vtable cache_ref_iterator_vtable = { + cache_ref_iterator_advance, + cache_ref_iterator_peel, + cache_ref_iterator_abort +}; + +static struct ref_iterator *cache_ref_iterator_begin(struct ref_dir *dir) +{ + struct cache_ref_iterator *iter; + struct ref_iterator *ref_iterator; + struct cache_ref_iterator_level *level; + + iter = xcalloc(1, sizeof(*iter)); + ref_iterator = &iter->base; + base_ref_iterator_init(ref_iterator, &cache_ref_iterator_vtable); + ALLOC_GROW(iter->levels, 10, iter->levels_alloc); + + iter->levels_nr = 1; + level = &iter->levels[0]; + level->index = -1; + level->dir = dir; + + return ref_iterator; +} + struct nonmatching_ref_data { const struct string_list *skip; const char *conflicting_refname; @@ -954,15 +999,26 @@ static struct ref_cache *lookup_ref_cache(const char *submodule) /* * Return a pointer to a ref_cache for the specified submodule. For - * the main repository, use submodule==NULL. The returned structure - * will be allocated and initialized but not necessarily populated; it - * should not be freed. + * the main repository, use submodule==NULL; such a call cannot fail. + * For a submodule, the submodule must exist and be a nonbare + * repository, otherwise return NULL. + * + * The returned structure will be allocated and initialized but not + * necessarily populated; it should not be freed. */ static struct ref_cache *get_ref_cache(const char *submodule) { struct ref_cache *refs = lookup_ref_cache(submodule); - if (!refs) - refs = create_ref_cache(submodule); + + if (!refs) { + struct strbuf submodule_sb = STRBUF_INIT; + + strbuf_addstr(&submodule_sb, submodule); + if (is_nonbare_repository_dir(&submodule_sb)) + refs = create_ref_cache(submodule); + strbuf_release(&submodule_sb); + } + return refs; } @@ -1341,13 +1397,10 @@ int resolve_gitlink_ref(const char *path, const char *refname, unsigned char *sh return -1; strbuf_add(&submodule, path, len); - refs = lookup_ref_cache(submodule.buf); + refs = get_ref_cache(submodule.buf); if (!refs) { - if (!is_nonbare_repository_dir(&submodule)) { - strbuf_release(&submodule); - return -1; - } - refs = create_ref_cache(submodule.buf); + strbuf_release(&submodule); + return -1; } strbuf_release(&submodule); @@ -1790,11 +1843,12 @@ int peel_ref(const char *refname, unsigned char *sha1) int flag; unsigned char base[20]; - if (current_ref && (current_ref->name == refname - || !strcmp(current_ref->name, refname))) { - if (peel_entry(current_ref, 0)) + if (current_ref_iter && current_ref_iter->refname == refname) { + struct object_id peeled; + + if (ref_iterator_peel(current_ref_iter, &peeled)) return -1; - hashcpy(sha1, current_ref->u.value.peeled.hash); + hashcpy(sha1, peeled.hash); return 0; } @@ -1822,90 +1876,137 @@ int peel_ref(const char *refname, unsigned char *sha1) return peel_object(base, sha1); } -/* - * Call fn for each reference in the specified ref_cache, omitting - * references not in the containing_dir of base. fn is called for all - * references, including broken ones. If fn ever returns a non-zero - * value, stop the iteration and return that value; otherwise, return - * 0. - */ -static int do_for_each_entry(struct ref_cache *refs, const char *base, - each_ref_entry_fn fn, void *cb_data) -{ +struct files_ref_iterator { + struct ref_iterator base; + struct packed_ref_cache *packed_ref_cache; - struct ref_dir *loose_dir; - struct ref_dir *packed_dir; - int retval = 0; + struct ref_iterator *iter0; + unsigned int flags; +}; - /* - * We must make sure that all loose refs are read before accessing the - * packed-refs file; this avoids a race condition in which loose refs - * are migrated to the packed-refs file by a simultaneous process, but - * our in-memory view is from before the migration. get_packed_ref_cache() - * takes care of making sure our view is up to date with what is on - * disk. - */ - loose_dir = get_loose_refs(refs); - if (base && *base) { - loose_dir = find_containing_dir(loose_dir, base, 0); - } - if (loose_dir) - prime_ref_dir(loose_dir); +static int files_ref_iterator_advance(struct ref_iterator *ref_iterator) +{ + struct files_ref_iterator *iter = + (struct files_ref_iterator *)ref_iterator; + int ok; - packed_ref_cache = get_packed_ref_cache(refs); - acquire_packed_ref_cache(packed_ref_cache); - packed_dir = get_packed_ref_dir(packed_ref_cache); - if (base && *base) { - packed_dir = find_containing_dir(packed_dir, base, 0); - } - - if (packed_dir && loose_dir) { - sort_ref_dir(packed_dir); - sort_ref_dir(loose_dir); - retval = do_for_each_entry_in_dirs( - packed_dir, loose_dir, fn, cb_data); - } else if (packed_dir) { - sort_ref_dir(packed_dir); - retval = do_for_each_entry_in_dir( - packed_dir, 0, fn, cb_data); - } else if (loose_dir) { - sort_ref_dir(loose_dir); - retval = do_for_each_entry_in_dir( - loose_dir, 0, fn, cb_data); + while ((ok = ref_iterator_advance(iter->iter0)) == ITER_OK) { + if (!(iter->flags & DO_FOR_EACH_INCLUDE_BROKEN) && + !ref_resolves_to_object(iter->iter0->refname, + iter->iter0->oid, + iter->iter0->flags)) + continue; + + iter->base.refname = iter->iter0->refname; + iter->base.oid = iter->iter0->oid; + iter->base.flags = iter->iter0->flags; + return ITER_OK; } - release_packed_ref_cache(packed_ref_cache); - return retval; + iter->iter0 = NULL; + if (ref_iterator_abort(ref_iterator) != ITER_DONE) + ok = ITER_ERROR; + + return ok; } -/* - * Call fn for each reference in the specified ref_cache for which the - * refname begins with base. If trim is non-zero, then trim that many - * characters off the beginning of each refname before passing the - * refname to fn. flags can be DO_FOR_EACH_INCLUDE_BROKEN to include - * broken references in the iteration. If fn ever returns a non-zero - * value, stop the iteration and return that value; otherwise, return - * 0. - */ -int do_for_each_ref(const char *submodule, const char *base, - each_ref_fn fn, int trim, int flags, void *cb_data) +static int files_ref_iterator_peel(struct ref_iterator *ref_iterator, + struct object_id *peeled) { - struct ref_entry_cb data; - struct ref_cache *refs; + struct files_ref_iterator *iter = + (struct files_ref_iterator *)ref_iterator; - refs = get_ref_cache(submodule); - data.base = base; - data.trim = trim; - data.flags = flags; - data.fn = fn; - data.cb_data = cb_data; + return ref_iterator_peel(iter->iter0, peeled); +} + +static int files_ref_iterator_abort(struct ref_iterator *ref_iterator) +{ + struct files_ref_iterator *iter = + (struct files_ref_iterator *)ref_iterator; + int ok = ITER_DONE; + + if (iter->iter0) + ok = ref_iterator_abort(iter->iter0); + + release_packed_ref_cache(iter->packed_ref_cache); + base_ref_iterator_free(ref_iterator); + return ok; +} + +static struct ref_iterator_vtable files_ref_iterator_vtable = { + files_ref_iterator_advance, + files_ref_iterator_peel, + files_ref_iterator_abort +}; + +struct ref_iterator *files_ref_iterator_begin( + const char *submodule, + const char *prefix, unsigned int flags) +{ + struct ref_cache *refs = get_ref_cache(submodule); + struct ref_dir *loose_dir, *packed_dir; + struct ref_iterator *loose_iter, *packed_iter; + struct files_ref_iterator *iter; + struct ref_iterator *ref_iterator; + + if (!refs) + return empty_ref_iterator_begin(); if (ref_paranoia < 0) ref_paranoia = git_env_bool("GIT_REF_PARANOIA", 0); if (ref_paranoia) - data.flags |= DO_FOR_EACH_INCLUDE_BROKEN; + flags |= DO_FOR_EACH_INCLUDE_BROKEN; + + iter = xcalloc(1, sizeof(*iter)); + ref_iterator = &iter->base; + base_ref_iterator_init(ref_iterator, &files_ref_iterator_vtable); + + /* + * We must make sure that all loose refs are read before + * accessing the packed-refs file; this avoids a race + * condition if loose refs are migrated to the packed-refs + * file by a simultaneous process, but our in-memory view is + * from before the migration. We ensure this as follows: + * First, we call prime_ref_dir(), which pre-reads the loose + * references for the subtree into the cache. (If they've + * already been read, that's OK; we only need to guarantee + * that they're read before the packed refs, not *how much* + * before.) After that, we call get_packed_ref_cache(), which + * internally checks whether the packed-ref cache is up to + * date with what is on disk, and re-reads it if not. + */ + + loose_dir = get_loose_refs(refs); + + if (prefix && *prefix) + loose_dir = find_containing_dir(loose_dir, prefix, 0); - return do_for_each_entry(refs, base, do_one_ref, &data); + if (loose_dir) { + prime_ref_dir(loose_dir); + loose_iter = cache_ref_iterator_begin(loose_dir); + } else { + /* There's nothing to iterate over. */ + loose_iter = empty_ref_iterator_begin(); + } + + iter->packed_ref_cache = get_packed_ref_cache(refs); + acquire_packed_ref_cache(iter->packed_ref_cache); + packed_dir = get_packed_ref_dir(iter->packed_ref_cache); + + if (prefix && *prefix) + packed_dir = find_containing_dir(packed_dir, prefix, 0); + + if (packed_dir) { + packed_iter = cache_ref_iterator_begin(packed_dir); + } else { + /* There's nothing to iterate over. */ + packed_iter = empty_ref_iterator_begin(); + } + + iter->iter0 = overlay_ref_iterator_begin(loose_iter, packed_iter); + iter->flags = flags; + + return ref_iterator; } /* @@ -2226,7 +2327,7 @@ static int pack_if_possible_fn(struct ref_entry *entry, void *cb_data) return 0; /* Do not pack symbolic or broken refs: */ - if ((entry->flag & REF_ISSYMREF) || !ref_resolves_to_object(entry)) + if ((entry->flag & REF_ISSYMREF) || !entry_resolves_to_object(entry)) return 0; /* Add a packed ref cache entry equivalent to the loose entry. */ @@ -2412,7 +2513,7 @@ static int delete_ref_loose(struct ref_lock *lock, int flag, struct strbuf *err) return 0; } -int delete_refs(struct string_list *refnames) +int delete_refs(struct string_list *refnames, unsigned int flags) { struct strbuf err = STRBUF_INIT; int i, result = 0; @@ -2441,7 +2542,7 @@ int delete_refs(struct string_list *refnames) for (i = 0; i < refnames->nr; i++) { const char *refname = refnames->items[i].string; - if (delete_ref(refname, NULL, 0)) + if (delete_ref(refname, NULL, flags)) result |= error(_("could not remove reference %s"), refname); } @@ -3191,60 +3292,88 @@ int for_each_reflog_ent(const char *refname, each_reflog_ent_fn fn, void *cb_dat strbuf_release(&sb); return ret; } -/* - * Call fn for each reflog in the namespace indicated by name. name - * must be empty or end with '/'. Name will be used as a scratch - * space, but its contents will be restored before return. - */ -static int do_for_each_reflog(struct strbuf *name, each_ref_fn fn, void *cb_data) -{ - DIR *d = opendir(git_path("logs/%s", name->buf)); - int retval = 0; - struct dirent *de; - int oldlen = name->len; - if (!d) - return name->len ? errno : 0; +struct files_reflog_iterator { + struct ref_iterator base; - while ((de = readdir(d)) != NULL) { - struct stat st; + struct dir_iterator *dir_iterator; + struct object_id oid; +}; - if (de->d_name[0] == '.') +static int files_reflog_iterator_advance(struct ref_iterator *ref_iterator) +{ + struct files_reflog_iterator *iter = + (struct files_reflog_iterator *)ref_iterator; + struct dir_iterator *diter = iter->dir_iterator; + int ok; + + while ((ok = dir_iterator_advance(diter)) == ITER_OK) { + int flags; + + if (!S_ISREG(diter->st.st_mode)) continue; - if (ends_with(de->d_name, ".lock")) + if (diter->basename[0] == '.') + continue; + if (ends_with(diter->basename, ".lock")) continue; - strbuf_addstr(name, de->d_name); - if (stat(git_path("logs/%s", name->buf), &st) < 0) { - ; /* silently ignore */ - } else { - if (S_ISDIR(st.st_mode)) { - strbuf_addch(name, '/'); - retval = do_for_each_reflog(name, fn, cb_data); - } else { - struct object_id oid; - if (read_ref_full(name->buf, 0, oid.hash, NULL)) - retval = error("bad ref for %s", name->buf); - else - retval = fn(name->buf, &oid, 0, cb_data); - } - if (retval) - break; + if (read_ref_full(diter->relative_path, 0, + iter->oid.hash, &flags)) { + error("bad ref for %s", diter->path.buf); + continue; } - strbuf_setlen(name, oldlen); + + iter->base.refname = diter->relative_path; + iter->base.oid = &iter->oid; + iter->base.flags = flags; + return ITER_OK; } - closedir(d); - return retval; + + iter->dir_iterator = NULL; + if (ref_iterator_abort(ref_iterator) == ITER_ERROR) + ok = ITER_ERROR; + return ok; +} + +static int files_reflog_iterator_peel(struct ref_iterator *ref_iterator, + struct object_id *peeled) +{ + die("BUG: ref_iterator_peel() called for reflog_iterator"); +} + +static int files_reflog_iterator_abort(struct ref_iterator *ref_iterator) +{ + struct files_reflog_iterator *iter = + (struct files_reflog_iterator *)ref_iterator; + int ok = ITER_DONE; + + if (iter->dir_iterator) + ok = dir_iterator_abort(iter->dir_iterator); + + base_ref_iterator_free(ref_iterator); + return ok; +} + +static struct ref_iterator_vtable files_reflog_iterator_vtable = { + files_reflog_iterator_advance, + files_reflog_iterator_peel, + files_reflog_iterator_abort +}; + +struct ref_iterator *files_reflog_iterator_begin(void) +{ + struct files_reflog_iterator *iter = xcalloc(1, sizeof(*iter)); + struct ref_iterator *ref_iterator = &iter->base; + + base_ref_iterator_init(ref_iterator, &files_reflog_iterator_vtable); + iter->dir_iterator = dir_iterator_begin(git_path("logs")); + return ref_iterator; } int for_each_reflog(each_ref_fn fn, void *cb_data) { - int retval; - struct strbuf name; - strbuf_init(&name, PATH_MAX); - retval = do_for_each_reflog(&name, fn, cb_data); - strbuf_release(&name); - return retval; + return do_for_each_ref_iterator(files_reflog_iterator_begin(), + fn, cb_data); } static int ref_update_reject_duplicates(struct string_list *refnames, diff --git a/refs/iterator.c b/refs/iterator.c new file mode 100644 index 0000000000..bce1f192f7 --- /dev/null +++ b/refs/iterator.c @@ -0,0 +1,384 @@ +/* + * Generic reference iterator infrastructure. See refs-internal.h for + * documentation about the design and use of reference iterators. + */ + +#include "cache.h" +#include "refs.h" +#include "refs/refs-internal.h" +#include "iterator.h" + +int ref_iterator_advance(struct ref_iterator *ref_iterator) +{ + return ref_iterator->vtable->advance(ref_iterator); +} + +int ref_iterator_peel(struct ref_iterator *ref_iterator, + struct object_id *peeled) +{ + return ref_iterator->vtable->peel(ref_iterator, peeled); +} + +int ref_iterator_abort(struct ref_iterator *ref_iterator) +{ + return ref_iterator->vtable->abort(ref_iterator); +} + +void base_ref_iterator_init(struct ref_iterator *iter, + struct ref_iterator_vtable *vtable) +{ + iter->vtable = vtable; + iter->refname = NULL; + iter->oid = NULL; + iter->flags = 0; +} + +void base_ref_iterator_free(struct ref_iterator *iter) +{ + /* Help make use-after-free bugs fail quickly: */ + iter->vtable = NULL; + free(iter); +} + +struct empty_ref_iterator { + struct ref_iterator base; +}; + +static int empty_ref_iterator_advance(struct ref_iterator *ref_iterator) +{ + return ref_iterator_abort(ref_iterator); +} + +static int empty_ref_iterator_peel(struct ref_iterator *ref_iterator, + struct object_id *peeled) +{ + die("BUG: peel called for empty iterator"); +} + +static int empty_ref_iterator_abort(struct ref_iterator *ref_iterator) +{ + base_ref_iterator_free(ref_iterator); + return ITER_DONE; +} + +static struct ref_iterator_vtable empty_ref_iterator_vtable = { + empty_ref_iterator_advance, + empty_ref_iterator_peel, + empty_ref_iterator_abort +}; + +struct ref_iterator *empty_ref_iterator_begin(void) +{ + struct empty_ref_iterator *iter = xcalloc(1, sizeof(*iter)); + struct ref_iterator *ref_iterator = &iter->base; + + base_ref_iterator_init(ref_iterator, &empty_ref_iterator_vtable); + return ref_iterator; +} + +int is_empty_ref_iterator(struct ref_iterator *ref_iterator) +{ + return ref_iterator->vtable == &empty_ref_iterator_vtable; +} + +struct merge_ref_iterator { + struct ref_iterator base; + + struct ref_iterator *iter0, *iter1; + + ref_iterator_select_fn *select; + void *cb_data; + + /* + * A pointer to iter0 or iter1 (whichever is supplying the + * current value), or NULL if advance has not yet been called. + */ + struct ref_iterator **current; +}; + +static int merge_ref_iterator_advance(struct ref_iterator *ref_iterator) +{ + struct merge_ref_iterator *iter = + (struct merge_ref_iterator *)ref_iterator; + int ok; + + if (!iter->current) { + /* Initialize: advance both iterators to their first entries */ + if ((ok = ref_iterator_advance(iter->iter0)) != ITER_OK) { + iter->iter0 = NULL; + if (ok == ITER_ERROR) + goto error; + } + if ((ok = ref_iterator_advance(iter->iter1)) != ITER_OK) { + iter->iter1 = NULL; + if (ok == ITER_ERROR) + goto error; + } + } else { + /* + * Advance the current iterator past the just-used + * entry: + */ + if ((ok = ref_iterator_advance(*iter->current)) != ITER_OK) { + *iter->current = NULL; + if (ok == ITER_ERROR) + goto error; + } + } + + /* Loop until we find an entry that we can yield. */ + while (1) { + struct ref_iterator **secondary; + enum iterator_selection selection = + iter->select(iter->iter0, iter->iter1, iter->cb_data); + + if (selection == ITER_SELECT_DONE) { + return ref_iterator_abort(ref_iterator); + } else if (selection == ITER_SELECT_ERROR) { + ref_iterator_abort(ref_iterator); + return ITER_ERROR; + } + + if ((selection & ITER_CURRENT_SELECTION_MASK) == 0) { + iter->current = &iter->iter0; + secondary = &iter->iter1; + } else { + iter->current = &iter->iter1; + secondary = &iter->iter0; + } + + if (selection & ITER_SKIP_SECONDARY) { + if ((ok = ref_iterator_advance(*secondary)) != ITER_OK) { + *secondary = NULL; + if (ok == ITER_ERROR) + goto error; + } + } + + if (selection & ITER_YIELD_CURRENT) { + iter->base.refname = (*iter->current)->refname; + iter->base.oid = (*iter->current)->oid; + iter->base.flags = (*iter->current)->flags; + return ITER_OK; + } + } + +error: + ref_iterator_abort(ref_iterator); + return ITER_ERROR; +} + +static int merge_ref_iterator_peel(struct ref_iterator *ref_iterator, + struct object_id *peeled) +{ + struct merge_ref_iterator *iter = + (struct merge_ref_iterator *)ref_iterator; + + if (!iter->current) { + die("BUG: peel called before advance for merge iterator"); + } + return ref_iterator_peel(*iter->current, peeled); +} + +static int merge_ref_iterator_abort(struct ref_iterator *ref_iterator) +{ + struct merge_ref_iterator *iter = + (struct merge_ref_iterator *)ref_iterator; + int ok = ITER_DONE; + + if (iter->iter0) { + if (ref_iterator_abort(iter->iter0) != ITER_DONE) + ok = ITER_ERROR; + } + if (iter->iter1) { + if (ref_iterator_abort(iter->iter1) != ITER_DONE) + ok = ITER_ERROR; + } + base_ref_iterator_free(ref_iterator); + return ok; +} + +static struct ref_iterator_vtable merge_ref_iterator_vtable = { + merge_ref_iterator_advance, + merge_ref_iterator_peel, + merge_ref_iterator_abort +}; + +struct ref_iterator *merge_ref_iterator_begin( + struct ref_iterator *iter0, struct ref_iterator *iter1, + ref_iterator_select_fn *select, void *cb_data) +{ + struct merge_ref_iterator *iter = xcalloc(1, sizeof(*iter)); + struct ref_iterator *ref_iterator = &iter->base; + + /* + * We can't do the same kind of is_empty_ref_iterator()-style + * optimization here as overlay_ref_iterator_begin() does, + * because we don't know the semantics of the select function. + * It might, for example, implement "intersect" by passing + * references through only if they exist in both iterators. + */ + + base_ref_iterator_init(ref_iterator, &merge_ref_iterator_vtable); + iter->iter0 = iter0; + iter->iter1 = iter1; + iter->select = select; + iter->cb_data = cb_data; + iter->current = NULL; + return ref_iterator; +} + +/* + * A ref_iterator_select_fn that overlays the items from front on top + * of those from back (like loose refs over packed refs). See + * overlay_ref_iterator_begin(). + */ +static enum iterator_selection overlay_iterator_select( + struct ref_iterator *front, struct ref_iterator *back, + void *cb_data) +{ + int cmp; + + if (!back) + return front ? ITER_SELECT_0 : ITER_SELECT_DONE; + else if (!front) + return ITER_SELECT_1; + + cmp = strcmp(front->refname, back->refname); + + if (cmp < 0) + return ITER_SELECT_0; + else if (cmp > 0) + return ITER_SELECT_1; + else + return ITER_SELECT_0_SKIP_1; +} + +struct ref_iterator *overlay_ref_iterator_begin( + struct ref_iterator *front, struct ref_iterator *back) +{ + /* + * Optimization: if one of the iterators is empty, return the + * other one rather than incurring the overhead of wrapping + * them. + */ + if (is_empty_ref_iterator(front)) { + ref_iterator_abort(front); + return back; + } else if (is_empty_ref_iterator(back)) { + ref_iterator_abort(back); + return front; + } + + return merge_ref_iterator_begin(front, back, + overlay_iterator_select, NULL); +} + +struct prefix_ref_iterator { + struct ref_iterator base; + + struct ref_iterator *iter0; + char *prefix; + int trim; +}; + +static int prefix_ref_iterator_advance(struct ref_iterator *ref_iterator) +{ + struct prefix_ref_iterator *iter = + (struct prefix_ref_iterator *)ref_iterator; + int ok; + + while ((ok = ref_iterator_advance(iter->iter0)) == ITER_OK) { + if (!starts_with(iter->iter0->refname, iter->prefix)) + continue; + + iter->base.refname = iter->iter0->refname + iter->trim; + iter->base.oid = iter->iter0->oid; + iter->base.flags = iter->iter0->flags; + return ITER_OK; + } + + iter->iter0 = NULL; + if (ref_iterator_abort(ref_iterator) != ITER_DONE) + return ITER_ERROR; + return ok; +} + +static int prefix_ref_iterator_peel(struct ref_iterator *ref_iterator, + struct object_id *peeled) +{ + struct prefix_ref_iterator *iter = + (struct prefix_ref_iterator *)ref_iterator; + + return ref_iterator_peel(iter->iter0, peeled); +} + +static int prefix_ref_iterator_abort(struct ref_iterator *ref_iterator) +{ + struct prefix_ref_iterator *iter = + (struct prefix_ref_iterator *)ref_iterator; + int ok = ITER_DONE; + + if (iter->iter0) + ok = ref_iterator_abort(iter->iter0); + free(iter->prefix); + base_ref_iterator_free(ref_iterator); + return ok; +} + +static struct ref_iterator_vtable prefix_ref_iterator_vtable = { + prefix_ref_iterator_advance, + prefix_ref_iterator_peel, + prefix_ref_iterator_abort +}; + +struct ref_iterator *prefix_ref_iterator_begin(struct ref_iterator *iter0, + const char *prefix, + int trim) +{ + struct prefix_ref_iterator *iter; + struct ref_iterator *ref_iterator; + + if (!*prefix && !trim) + return iter0; /* optimization: no need to wrap iterator */ + + iter = xcalloc(1, sizeof(*iter)); + ref_iterator = &iter->base; + + base_ref_iterator_init(ref_iterator, &prefix_ref_iterator_vtable); + + iter->iter0 = iter0; + iter->prefix = xstrdup(prefix); + iter->trim = trim; + + return ref_iterator; +} + +struct ref_iterator *current_ref_iter = NULL; + +int do_for_each_ref_iterator(struct ref_iterator *iter, + each_ref_fn fn, void *cb_data) +{ + int retval = 0, ok; + struct ref_iterator *old_ref_iter = current_ref_iter; + + current_ref_iter = iter; + while ((ok = ref_iterator_advance(iter)) == ITER_OK) { + retval = fn(iter->refname, iter->oid, iter->flags, cb_data); + if (retval) { + /* + * If ref_iterator_abort() returns ITER_ERROR, + * we ignore that error in deference to the + * callback function's return value. + */ + ref_iterator_abort(iter); + goto out; + } + } + +out: + current_ref_iter = old_ref_iter; + if (ok == ITER_ERROR) + return -1; + return retval; +} diff --git a/refs/refs-internal.h b/refs/refs-internal.h index 1bb3d87dc5..efe584701b 100644 --- a/refs/refs-internal.h +++ b/refs/refs-internal.h @@ -249,10 +249,230 @@ int rename_ref_available(const char *oldname, const char *newname); #define DO_FOR_EACH_INCLUDE_BROKEN 0x01 /* - * The common backend for the for_each_*ref* functions + * Reference iterators + * + * A reference iterator encapsulates the state of an in-progress + * iteration over references. Create an instance of `struct + * ref_iterator` via one of the functions in this module. + * + * A freshly-created ref_iterator doesn't yet point at a reference. To + * advance the iterator, call ref_iterator_advance(). If successful, + * this sets the iterator's refname, oid, and flags fields to describe + * the next reference and returns ITER_OK. The data pointed at by + * refname and oid belong to the iterator; if you want to retain them + * after calling ref_iterator_advance() again or calling + * ref_iterator_abort(), you must make a copy. When the iteration has + * been exhausted, ref_iterator_advance() releases any resources + * assocated with the iteration, frees the ref_iterator object, and + * returns ITER_DONE. If you want to abort the iteration early, call + * ref_iterator_abort(), which also frees the ref_iterator object and + * any associated resources. If there was an internal error advancing + * to the next entry, ref_iterator_advance() aborts the iteration, + * frees the ref_iterator, and returns ITER_ERROR. + * + * The reference currently being looked at can be peeled by calling + * ref_iterator_peel(). This function is often faster than peel_ref(), + * so it should be preferred when iterating over references. + * + * Putting it all together, a typical iteration looks like this: + * + * int ok; + * struct ref_iterator *iter = ...; + * + * while ((ok = ref_iterator_advance(iter)) == ITER_OK) { + * if (want_to_stop_iteration()) { + * ok = ref_iterator_abort(iter); + * break; + * } + * + * // Access information about the current reference: + * if (!(iter->flags & REF_ISSYMREF)) + * printf("%s is %s\n", iter->refname, oid_to_hex(&iter->oid)); + * + * // If you need to peel the reference: + * ref_iterator_peel(iter, &oid); + * } + * + * if (ok != ITER_DONE) + * handle_error(); + */ +struct ref_iterator { + struct ref_iterator_vtable *vtable; + const char *refname; + const struct object_id *oid; + unsigned int flags; +}; + +/* + * Advance the iterator to the first or next item and return ITER_OK. + * If the iteration is exhausted, free the resources associated with + * the ref_iterator and return ITER_DONE. On errors, free the iterator + * resources and return ITER_ERROR. It is a bug to use ref_iterator or + * call this function again after it has returned ITER_DONE or + * ITER_ERROR. + */ +int ref_iterator_advance(struct ref_iterator *ref_iterator); + +/* + * If possible, peel the reference currently being viewed by the + * iterator. Return 0 on success. + */ +int ref_iterator_peel(struct ref_iterator *ref_iterator, + struct object_id *peeled); + +/* + * End the iteration before it has been exhausted, freeing the + * reference iterator and any associated resources and returning + * ITER_DONE. If the abort itself failed, return ITER_ERROR. + */ +int ref_iterator_abort(struct ref_iterator *ref_iterator); + +/* + * An iterator over nothing (its first ref_iterator_advance() call + * returns ITER_DONE). + */ +struct ref_iterator *empty_ref_iterator_begin(void); + +/* + * Return true iff ref_iterator is an empty_ref_iterator. + */ +int is_empty_ref_iterator(struct ref_iterator *ref_iterator); + +/* + * A callback function used to instruct merge_ref_iterator how to + * interleave the entries from iter0 and iter1. The function should + * return one of the constants defined in enum iterator_selection. It + * must not advance either of the iterators itself. + * + * The function must be prepared to handle the case that iter0 and/or + * iter1 is NULL, which indicates that the corresponding sub-iterator + * has been exhausted. Its return value must be consistent with the + * current states of the iterators; e.g., it must not return + * ITER_SKIP_1 if iter1 has already been exhausted. + */ +typedef enum iterator_selection ref_iterator_select_fn( + struct ref_iterator *iter0, struct ref_iterator *iter1, + void *cb_data); + +/* + * Iterate over the entries from iter0 and iter1, with the values + * interleaved as directed by the select function. The iterator takes + * ownership of iter0 and iter1 and frees them when the iteration is + * over. + */ +struct ref_iterator *merge_ref_iterator_begin( + struct ref_iterator *iter0, struct ref_iterator *iter1, + ref_iterator_select_fn *select, void *cb_data); + +/* + * An iterator consisting of the union of the entries from front and + * back. If there are entries common to the two sub-iterators, use the + * one from front. Each iterator must iterate over its entries in + * strcmp() order by refname for this to work. + * + * The new iterator takes ownership of its arguments and frees them + * when the iteration is over. As a convenience to callers, if front + * or back is an empty_ref_iterator, then abort that one immediately + * and return the other iterator directly, without wrapping it. + */ +struct ref_iterator *overlay_ref_iterator_begin( + struct ref_iterator *front, struct ref_iterator *back); + +/* + * Wrap iter0, only letting through the references whose names start + * with prefix. If trim is set, set iter->refname to the name of the + * reference with that many characters trimmed off the front; + * otherwise set it to the full refname. The new iterator takes over + * ownership of iter0 and frees it when iteration is over. It makes + * its own copy of prefix. + * + * As an convenience to callers, if prefix is the empty string and + * trim is zero, this function returns iter0 directly, without + * wrapping it. + */ +struct ref_iterator *prefix_ref_iterator_begin(struct ref_iterator *iter0, + const char *prefix, + int trim); + +/* + * Iterate over the packed and loose references in the specified + * submodule that are within find_containing_dir(prefix). If prefix is + * NULL or the empty string, iterate over all references in the + * submodule. + */ +struct ref_iterator *files_ref_iterator_begin(const char *submodule, + const char *prefix, + unsigned int flags); + +/* + * Iterate over the references in the main ref_store that have a + * reflog. The paths within a directory are iterated over in arbitrary + * order. + */ +struct ref_iterator *files_reflog_iterator_begin(void); + +/* Internal implementation of reference iteration: */ + +/* + * Base class constructor for ref_iterators. Initialize the + * ref_iterator part of iter, setting its vtable pointer as specified. + * This is meant to be called only by the initializers of derived + * classes. + */ +void base_ref_iterator_init(struct ref_iterator *iter, + struct ref_iterator_vtable *vtable); + +/* + * Base class destructor for ref_iterators. Destroy the ref_iterator + * part of iter and shallow-free the object. This is meant to be + * called only by the destructors of derived classes. + */ +void base_ref_iterator_free(struct ref_iterator *iter); + +/* Virtual function declarations for ref_iterators: */ + +typedef int ref_iterator_advance_fn(struct ref_iterator *ref_iterator); + +typedef int ref_iterator_peel_fn(struct ref_iterator *ref_iterator, + struct object_id *peeled); + +/* + * Implementations of this function should free any resources specific + * to the derived class, then call base_ref_iterator_free() to clean + * up and free the ref_iterator object. + */ +typedef int ref_iterator_abort_fn(struct ref_iterator *ref_iterator); + +struct ref_iterator_vtable { + ref_iterator_advance_fn *advance; + ref_iterator_peel_fn *peel; + ref_iterator_abort_fn *abort; +}; + +/* + * current_ref_iter is a performance hack: when iterating over + * references using the for_each_ref*() functions, current_ref_iter is + * set to the reference iterator before calling the callback function. + * If the callback function calls peel_ref(), then peel_ref() first + * checks whether the reference to be peeled is the one referred to by + * the iterator (it usually is) and if so, asks the iterator for the + * peeled version of the reference if it is available. This avoids a + * refname lookup in a common case. current_ref_iter is set to NULL + * when the iteration is over. + */ +extern struct ref_iterator *current_ref_iter; + +/* + * The common backend for the for_each_*ref* functions. Call fn for + * each reference in iter. If the iterator itself ever returns + * ITER_ERROR, return -1. If fn ever returns a non-zero value, stop + * the iteration and return that value. Otherwise, return 0. In any + * case, free the iterator when done. This function is basically an + * adapter between the callback style of reference iteration and the + * iterator style. */ -int do_for_each_ref(const char *submodule, const char *base, - each_ref_fn fn, int trim, int flags, void *cb_data); +int do_for_each_ref_iterator(struct ref_iterator *iter, + each_ref_fn fn, void *cb_data); /* * Read the specified reference from the filesystem or packed refs |