diff options
| -rw-r--r-- | .gitignore | 1 | ||||
| -rw-r--r-- | Documentation/git-read-tree.txt | 11 | ||||
| -rw-r--r-- | Documentation/git-write-tree.txt | 8 | ||||
| -rw-r--r-- | Makefile | 5 | ||||
| -rw-r--r-- | builtin-add.c | 2 | ||||
| -rw-r--r-- | builtin-apply.c | 22 | ||||
| -rw-r--r-- | builtin-read-tree.c | 134 | ||||
| -rw-r--r-- | builtin-rm.c | 2 | ||||
| -rw-r--r-- | cache-tree.c | 557 | ||||
| -rw-r--r-- | cache-tree.h | 33 | ||||
| -rw-r--r-- | cache.h | 1 | ||||
| -rw-r--r-- | checkout-index.c | 1 | ||||
| -rw-r--r-- | dump-cache-tree.c | 64 | ||||
| -rw-r--r-- | fsck-objects.c | 25 | ||||
| -rw-r--r-- | http-fetch.c | 4 | ||||
| -rw-r--r-- | mailinfo.c | 129 | ||||
| -rw-r--r-- | read-cache.c | 72 | ||||
| -rwxr-xr-x | t/t0000-basic.sh | 14 | ||||
| -rwxr-xr-x | t/t4113-apply-ending.sh | 53 | ||||
| -rw-r--r-- | update-index.c | 13 | ||||
| -rw-r--r-- | write-tree.c | 166 |
21 files changed, 1112 insertions, 205 deletions
diff --git a/.gitignore b/.gitignore index 199cc310a2..18a7295e6c 100644 --- a/.gitignore +++ b/.gitignore @@ -124,6 +124,7 @@ git-write-tree git-core-*/?* test-date test-delta +test-dump-cache-tree common-cmds.h *.tar.gz *.dsc diff --git a/Documentation/git-read-tree.txt b/Documentation/git-read-tree.txt index 844cfda8d2..1f21d95684 100644 --- a/Documentation/git-read-tree.txt +++ b/Documentation/git-read-tree.txt @@ -8,7 +8,7 @@ git-read-tree - Reads tree information into the index SYNOPSIS -------- -'git-read-tree' (<tree-ish> | [[-m [--aggressive]| --reset] [-u | -i]] <tree-ish1> [<tree-ish2> [<tree-ish3>]]) +'git-read-tree' (<tree-ish> | [[-m [--aggressive] | --reset | --prefix=<prefix>] [-u | -i]] <tree-ish1> [<tree-ish2> [<tree-ish3>]]) DESCRIPTION @@ -63,6 +63,15 @@ OPTIONS * when both sides adds a path identically. The resolution is to add that path. +--prefix=<prefix>/:: + Keep the current index contents, and read the contents + of named tree-ish under directory at `<prefix>`. The + original index file cannot have anything at the path + `<prefix>` itself, and have nothing in `<prefix>/` + directory. Note that the `<prefix>/` value must end + with a slash. + + <tree-ish#>:: The id of the tree object(s) to be read/merged. diff --git a/Documentation/git-write-tree.txt b/Documentation/git-write-tree.txt index 77e12cb949..c85fa89c30 100644 --- a/Documentation/git-write-tree.txt +++ b/Documentation/git-write-tree.txt @@ -8,7 +8,7 @@ git-write-tree - Creates a tree object from the current index SYNOPSIS -------- -'git-write-tree' [--missing-ok] +'git-write-tree' [--missing-ok] [--prefix=<prefix>/] DESCRIPTION ----------- @@ -30,6 +30,12 @@ OPTIONS directory exist in the object database. This option disables this check. +--prefix=<prefix>/:: + Writes a tree object that represents a subdirectory + `<prefix>`. This can be used to write the tree object + for a subproject that is in the named subdirectory. + + Author ------ Written by Linus Torvalds <torvalds@osdl.org> @@ -210,7 +210,7 @@ DIFF_OBJS = \ diffcore-delta.o log-tree.o LIB_OBJS = \ - blob.o commit.o connect.o csum-file.o base85.o \ + blob.o commit.o connect.o csum-file.o cache-tree.o base85.o \ date.o diff-delta.o entry.o exec_cmd.o ident.o index.o \ object.o pack-check.o patch-delta.o path.o pkt-line.o \ quote.o read-cache.o refs.o run-command.o dir.o \ @@ -620,6 +620,9 @@ test-date$X: test-date.c date.o ctype.o test-delta$X: test-delta.c diff-delta.o patch-delta.o $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $^ +test-dump-cache-tree$X: dump-cache-tree.o $(GITLIBS) + $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) + check: for i in *.c; do sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; done diff --git a/builtin-add.c b/builtin-add.c index 6166f66bce..02fe38b0c4 100644 --- a/builtin-add.c +++ b/builtin-add.c @@ -8,6 +8,7 @@ #include "cache.h" #include "builtin.h" #include "dir.h" +#include "cache-tree.h" static const char builtin_add_usage[] = "git-add [-n] [-v] <filepattern>..."; @@ -117,6 +118,7 @@ static int add_file_to_index(const char *path, int verbose) die("unable to add %s to index",path); if (verbose) printf("add '%s'\n", path); + cache_tree_invalidate_path(active_cache_tree, path); return 0; } diff --git a/builtin-apply.c b/builtin-apply.c index 4056b9d67b..6a4fb9663d 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -8,6 +8,7 @@ */ #include <fnmatch.h> #include "cache.h" +#include "cache-tree.h" #include "quote.h" #include "blob.h" #include "delta.h" @@ -1334,6 +1335,7 @@ static int apply_line(char *output, const char *patch, int plen) static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag) { + int match_beginning, match_end; char *buf = desc->buffer; const char *patch = frag->patch; int offset, size = frag->size; @@ -1396,10 +1398,22 @@ static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag) newlines = new; leading = frag->leading; trailing = frag->trailing; + + /* + * If we don't have any leading/trailing data in the patch, + * we want it to match at the beginning/end of the file. + */ + match_beginning = !leading && (frag->oldpos == 1); + match_end = !trailing; + lines = 0; pos = frag->newpos; for (;;) { offset = find_offset(buf, desc->size, oldlines, oldsize, pos, &lines); + if (match_end && offset + oldsize != desc->size) + offset = -1; + if (match_beginning && offset) + offset = -1; if (offset >= 0) { int diff = newsize - oldsize; unsigned long size = desc->size + diff; @@ -1429,6 +1443,10 @@ static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag) /* Am I at my context limits? */ if ((leading <= p_context) && (trailing <= p_context)) break; + if (match_beginning || match_end) { + match_beginning = match_end = 0; + continue; + } /* Reduce the number of context lines * Reduce both leading and trailing if they are equal * otherwise just reduce the larger context. @@ -1918,6 +1936,7 @@ static void remove_file(struct patch *patch) if (write_index) { if (remove_file_from_cache(patch->old_name) < 0) die("unable to remove %s from index", patch->old_name); + cache_tree_invalidate_path(active_cache_tree, patch->old_name); } if (!cached) unlink(patch->old_name); @@ -2019,8 +2038,9 @@ static void create_file(struct patch *patch) if (!mode) mode = S_IFREG | 0644; - create_one_file(path, mode, buf, size); + create_one_file(path, mode, buf, size); add_index_file(path, mode, buf, size); + cache_tree_invalidate_path(active_cache_tree, path); } static void write_out_one_result(struct patch *patch) diff --git a/builtin-read-tree.c b/builtin-read-tree.c index ec40d013c4..629d151639 100644 --- a/builtin-read-tree.c +++ b/builtin-read-tree.c @@ -9,6 +9,7 @@ #include "object.h" #include "tree.h" +#include "cache-tree.h" #include <sys/time.h> #include <signal.h> #include "builtin.h" @@ -22,6 +23,7 @@ static int trivial_merges_only = 0; static int aggressive = 0; static int verbose_update = 0; static volatile int progress_update = 0; +static const char *prefix = NULL; static int head_idx = -1; static int merge_size = 0; @@ -370,7 +372,8 @@ static int unpack_trees(merge_fn_t fn) posns[i] = ((struct tree *) posn->item)->entries; posn = posn->next; } - if (unpack_trees_rec(posns, len, "", fn, &indpos)) + if (unpack_trees_rec(posns, len, prefix ? prefix : "", + fn, &indpos)) return -1; } @@ -427,6 +430,12 @@ static void verify_uptodate(struct cache_entry *ce) die("Entry '%s' not uptodate. Cannot merge.", ce->name); } +static void invalidate_ce_path(struct cache_entry *ce) +{ + if (ce) + cache_tree_invalidate_path(active_cache_tree, ce->name); +} + /* * We do not want to remove or overwrite a working tree file that * is not tracked. @@ -457,10 +466,13 @@ static int merged_entry(struct cache_entry *merge, struct cache_entry *old) *merge = *old; } else { verify_uptodate(old); + invalidate_ce_path(old); } } - else + else { verify_absent(merge->name, "overwritten"); + invalidate_ce_path(merge); + } merge->ce_flags &= ~htons(CE_STAGEMASK); add_cache_entry(merge, ADD_CACHE_OK_TO_ADD); @@ -475,6 +487,7 @@ static int deleted_entry(struct cache_entry *ce, struct cache_entry *old) verify_absent(ce->name, "removed"); ce->ce_mode = 0; add_cache_entry(ce, ADD_CACHE_OK_TO_ADD); + invalidate_ce_path(ce); return 1; } @@ -710,6 +723,28 @@ static int twoway_merge(struct cache_entry **src) } /* + * Bind merge. + * + * Keep the index entries at stage0, collapse stage1 but make sure + * stage0 does not have anything there. + */ +static int bind_merge(struct cache_entry **src) +{ + struct cache_entry *old = src[0]; + struct cache_entry *a = src[1]; + + if (merge_size != 1) + return error("Cannot do a bind merge of %d trees\n", + merge_size); + if (a && old) + die("Entry '%s' overlaps. Cannot bind.", a->name); + if (!a) + return keep_entry(old); + else + return merged_entry(a, NULL); +} + +/* * One-way merge. * * The rule is: @@ -724,8 +759,10 @@ static int oneway_merge(struct cache_entry **src) return error("Cannot do a oneway merge of %d trees", merge_size); - if (!a) + if (!a) { + invalidate_ce_path(old); return deleted_entry(old, old); + } if (old && same(old, a)) { if (reset) { struct stat st; @@ -750,6 +787,7 @@ static int read_cache_unmerged(void) struct cache_entry *ce = active_cache[i]; if (ce_stage(ce)) { deleted++; + invalidate_ce_path(ce); continue; } if (deleted) @@ -760,7 +798,40 @@ static int read_cache_unmerged(void) return deleted; } -static const char read_tree_usage[] = "git-read-tree (<sha> | -m [--aggressive] [-u | -i] <sha1> [<sha2> [<sha3>]])"; +static void prime_cache_tree_rec(struct cache_tree *it, struct tree *tree) +{ + struct tree_entry_list *ent; + int cnt; + + memcpy(it->sha1, tree->object.sha1, 20); + for (cnt = 0, ent = tree->entries; ent; ent = ent->next) { + if (!ent->directory) + cnt++; + else { + struct cache_tree_sub *sub; + struct tree *subtree = (struct tree *)ent->item.tree; + if (!subtree->object.parsed) + parse_tree(subtree); + sub = cache_tree_sub(it, ent->name); + sub->cache_tree = cache_tree(); + prime_cache_tree_rec(sub->cache_tree, subtree); + cnt += sub->cache_tree->entry_count; + } + } + it->entry_count = cnt; +} + +static void prime_cache_tree(void) +{ + struct tree *tree = (struct tree *)trees->item; + if (!tree) + return; + active_cache_tree = cache_tree(); + prime_cache_tree_rec(active_cache_tree, tree); + +} + +static const char read_tree_usage[] = "git-read-tree (<sha> | [[-m [--aggressive] | --reset | --prefix=<prefix>] [-u | -i]] <sha1> [<sha2> [<sha3>]])"; static struct cache_file cache_file; @@ -805,9 +876,24 @@ int cmd_read_tree(int argc, const char **argv, char **envp) continue; } + /* "--prefix=<subdirectory>/" means keep the current index + * entries and put the entries from the tree under the + * given subdirectory. + */ + if (!strncmp(arg, "--prefix=", 9)) { + if (stage || merge || prefix) + usage(read_tree_usage); + prefix = arg + 9; + merge = 1; + stage = 1; + if (read_cache_unmerged()) + die("you need to resolve your current index first"); + continue; + } + /* This differs from "-m" in that we'll silently ignore unmerged entries */ if (!strcmp(arg, "--reset")) { - if (stage || merge) + if (stage || merge || prefix) usage(read_tree_usage); reset = 1; merge = 1; @@ -828,7 +914,7 @@ int cmd_read_tree(int argc, const char **argv, char **envp) /* "-m" stands for "merge", meaning we start in stage 1 */ if (!strcmp(arg, "-m")) { - if (stage || merge) + if (stage || merge || prefix) usage(read_tree_usage); if (read_cache_unmerged()) die("you need to resolve your current index first"); @@ -850,21 +936,39 @@ int cmd_read_tree(int argc, const char **argv, char **envp) if ((update||index_only) && !merge) usage(read_tree_usage); + if (prefix) { + int pfxlen = strlen(prefix); + int pos; + if (prefix[pfxlen-1] != '/') + die("prefix must end with /"); + if (stage != 2) + die("binding merge takes only one tree"); + pos = cache_name_pos(prefix, pfxlen); + if (0 <= pos) + die("corrupt index file"); + pos = -pos-1; + if (pos < active_nr && + !strncmp(active_cache[pos]->name, prefix, pfxlen)) + die("subdirectory '%s' already exists.", prefix); + pos = cache_name_pos(prefix, pfxlen-1); + if (0 <= pos) + die("file '%.*s' already exists.", pfxlen-1, prefix); + } + if (merge) { if (stage < 2) die("just how do you expect me to merge %d trees?", stage-1); switch (stage - 1) { case 1: - fn = oneway_merge; + fn = prefix ? bind_merge : oneway_merge; break; case 2: fn = twoway_merge; break; case 3: - fn = threeway_merge; - break; default: fn = threeway_merge; + cache_tree_free(&active_cache_tree); break; } @@ -875,6 +979,18 @@ int cmd_read_tree(int argc, const char **argv, char **envp) } unpack_trees(fn); + + /* + * When reading only one tree (either the most basic form, + * "-m ent" or "--reset ent" form), we can obtain a fully + * valid cache-tree because the index must match exactly + * what came from the tree. + */ + if (trees && trees->item && (!merge || (stage == 2))) { + cache_tree_free(&active_cache_tree); + prime_cache_tree(); + } + if (write_cache(newfd, active_cache, active_nr) || commit_index_file(&cache_file)) die("unable to write new index file"); diff --git a/builtin-rm.c b/builtin-rm.c index 9014c61556..e7793a20f5 100644 --- a/builtin-rm.c +++ b/builtin-rm.c @@ -6,6 +6,7 @@ #include "cache.h" #include "builtin.h" #include "dir.h" +#include "cache-tree.h" static const char builtin_rm_usage[] = "git-rm [-n] [-v] [-f] <filepattern>..."; @@ -117,6 +118,7 @@ int cmd_rm(int argc, const char **argv, char **envp) if (remove_file_from_cache(path)) die("git rm: unable to remove %s", path); + cache_tree_invalidate_path(active_cache_tree, path); } /* diff --git a/cache-tree.c b/cache-tree.c new file mode 100644 index 0000000000..d9f7e1e3dd --- /dev/null +++ b/cache-tree.c @@ -0,0 +1,557 @@ +#include "cache.h" +#include "tree.h" +#include "cache-tree.h" + +#define DEBUG 0 + +struct cache_tree *cache_tree(void) +{ + struct cache_tree *it = xcalloc(1, sizeof(struct cache_tree)); + it->entry_count = -1; + return it; +} + +void cache_tree_free(struct cache_tree **it_p) +{ + int i; + struct cache_tree *it = *it_p; + + if (!it) + return; + for (i = 0; i < it->subtree_nr; i++) + if (it->down[i]) + cache_tree_free(&it->down[i]->cache_tree); + free(it->down); + free(it); + *it_p = NULL; +} + +static int subtree_name_cmp(const char *one, int onelen, + const char *two, int twolen) +{ + if (onelen < twolen) + return -1; + if (twolen < onelen) + return 1; + return memcmp(one, two, onelen); +} + +static int subtree_pos(struct cache_tree *it, const char *path, int pathlen) +{ + struct cache_tree_sub **down = it->down; + int lo, hi; + lo = 0; + hi = it->subtree_nr; + while (lo < hi) { + int mi = (lo + hi) / 2; + struct cache_tree_sub *mdl = down[mi]; + int cmp = subtree_name_cmp(path, pathlen, + mdl->name, mdl->namelen); + if (!cmp) + return mi; + if (cmp < 0) + hi = mi; + else + lo = mi + 1; + } + return -lo-1; +} + +static struct cache_tree_sub *find_subtree(struct cache_tree *it, + const char *path, + int pathlen, + int create) +{ + struct cache_tree_sub *down; + int pos = subtree_pos(it, path, pathlen); + if (0 <= pos) + return it->down[pos]; + if (!create) + return NULL; + + pos = -pos-1; + if (it->subtree_alloc <= it->subtree_nr) { + it->subtree_alloc = alloc_nr(it->subtree_alloc); + it->down = xrealloc(it->down, it->subtree_alloc * + sizeof(*it->down)); + } + it->subtree_nr++; + + down = xmalloc(sizeof(*down) + pathlen + 1); + down->cache_tree = NULL; + down->namelen = pathlen; + memcpy(down->name, path, pathlen); + down->name[pathlen] = 0; + + if (pos < it->subtree_nr) + memmove(it->down + pos + 1, + it->down + pos, + sizeof(down) * (it->subtree_nr - pos - 1)); + it->down[pos] = down; + return down; +} + +struct cache_tree_sub *cache_tree_sub(struct cache_tree *it, const char *path) +{ + int pathlen = strlen(path); + return find_subtree(it, path, pathlen, 1); +} + +void cache_tree_invalidate_path(struct cache_tree *it, const char *path) +{ + /* a/b/c + * ==> invalidate self + * ==> find "a", have it invalidate "b/c" + * a + * ==> invalidate self + * ==> if "a" exists as a subtree, remove it. + */ + const char *slash; + int namelen; + struct cache_tree_sub *down; + +#if DEBUG + fprintf(stderr, "cache-tree invalidate <%s>\n", path); +#endif + + if (!it) + return; + slash = strchr(path, '/'); + it->entry_count = -1; + if (!slash) { + int pos; + namelen = strlen(path); + pos = subtree_pos(it, path, namelen); + if (0 <= pos) { + cache_tree_free(&it->down[pos]->cache_tree); + free(it->down[pos]); + /* 0 1 2 3 4 5 + * ^ ^subtree_nr = 6 + * pos + * move 4 and 5 up one place (2 entries) + * 2 = 6 - 3 - 1 = subtree_nr - pos - 1 + */ + memmove(it->down+pos, it->down+pos+1, + sizeof(struct cache_tree_sub *) * + (it->subtree_nr - pos - 1)); + it->subtree_nr--; + } + return; + } + namelen = slash - path; + down = find_subtree(it, path, namelen, 0); + if (down) + cache_tree_invalidate_path(down->cache_tree, slash + 1); +} + +static int verify_cache(struct cache_entry **cache, + int entries) +{ + int i, funny; + + /* Verify that the tree is merged */ + funny = 0; + for (i = 0; i < entries; i++) { + struct cache_entry *ce = cache[i]; + if (ce_stage(ce)) { + if (10 < ++funny) { + fprintf(stderr, "...\n"); + break; + } + fprintf(stderr, "%s: unmerged (%s)\n", + ce->name, sha1_to_hex(ce->sha1)); + } + } + if (funny) + return -1; + + /* Also verify that the cache does not have path and path/file + * at the same time. At this point we know the cache has only + * stage 0 entries. + */ + funny = 0; + for (i = 0; i < entries - 1; i++) { + /* path/file always comes after path because of the way + * the cache is sorted. Also path can appear only once, + * which means conflicting one would immediately follow. + */ + const char *this_name = cache[i]->name; + const char *next_name = cache[i+1]->name; + int this_len = strlen(this_name); + if (this_len < strlen(next_name) && + strncmp(this_name, next_name, this_len) == 0 && + next_name[this_len] == '/') { + if (10 < ++funny) { + fprintf(stderr, "...\n"); + break; + } + fprintf(stderr, "You have both %s and %s\n", + this_name, next_name); + } + } + if (funny) + return -1; + return 0; +} + +static void discard_unused_subtrees(struct cache_tree *it) +{ + struct cache_tree_sub **down = it->down; + int nr = it->subtree_nr; + int dst, src; + for (dst = src = 0; src < nr; src++) { + struct cache_tree_sub *s = down[src]; + if (s->used) + down[dst++] = s; + else { + cache_tree_free(&s->cache_tree); + free(s); + it->subtree_nr--; + } + } +} + +int cache_tree_fully_valid(struct cache_tree *it) +{ + int i; + if (!it) + return 0; + if (it->entry_count < 0 || !has_sha1_file(it->sha1)) + return 0; + for (i = 0; i < it->subtree_nr; i++) { + if (!cache_tree_fully_valid(it->down[i]->cache_tree)) + return 0; + } + return 1; +} + +static int update_one(struct cache_tree *it, + struct cache_entry **cache, + int entries, + const char *base, + int baselen, + int missing_ok, + int dryrun) +{ + unsigned long size, offset; + char *buffer; + int i; + + if (0 <= it->entry_count && has_sha1_file(it->sha1)) + return it->entry_count; + + /* + * We first scan for subtrees and update them; we start by + * marking existing subtrees -- the ones that are unmarked + * should not be in the result. + */ + for (i = 0; i < it->subtree_nr; i++) + it->down[i]->used = 0; + + /* + * Find the subtrees and update them. + */ + for (i = 0; i < entries; i++) { + struct cache_entry *ce = cache[i]; + struct cache_tree_sub *sub; + const char *path, *slash; + int pathlen, sublen, subcnt; + + path = ce->name; + pathlen = ce_namelen(ce); + if (pathlen <= baselen || memcmp(base, path, baselen)) + break; /* at the end of this level */ + + slash = strchr(path + baselen, '/'); + if (!slash) + continue; + /* + * a/bbb/c (base = a/, slash = /c) + * ==> + * path+baselen = bbb/c, sublen = 3 + */ + sublen = slash - (path + baselen); + sub = find_subtree(it, path + baselen, sublen, 1); + if (!sub->cache_tree) + sub->cache_tree = cache_tree(); + subcnt = update_one(sub->cache_tree, + cache + i, entries - i, + path, + baselen + sublen + 1, + missing_ok, + dryrun); + i += subcnt - 1; + sub->used = 1; + } + + discard_unused_subtrees(it); + + /* + * Then write out the tree object for this level. + */ + size = 8192; + buffer = xmalloc(size); + offset = 0; + + for (i = 0; i < entries; i++) { + struct cache_entry *ce = cache[i]; + struct cache_tree_sub *sub; + const char *path, *slash; + int pathlen, entlen; + const unsigned char *sha1; + unsigned mode; + + path = ce->name; + pathlen = ce_namelen(ce); + if (pathlen <= baselen || memcmp(base, path, baselen)) + break; /* at the end of this level */ + + slash = strchr(path + baselen, '/'); + if (slash) { + entlen = slash - (path + baselen); + sub = find_subtree(it, path + baselen, entlen, 0); + if (!sub) + die("cache-tree.c: '%.*s' in '%s' not found", + entlen, path + baselen, path); + i += sub->cache_tree->entry_count - 1; + sha1 = sub->cache_tree->sha1; + mode = S_IFDIR; + } + else { + sha1 = ce->sha1; + mode = ntohl(ce->ce_mode); + entlen = pathlen - baselen; + } + if (!missing_ok && !has_sha1_file(sha1)) + return error("invalid object %s", sha1_to_hex(sha1)); + + if (!ce->ce_mode) + continue; /* entry being removed */ + + if (size < offset + entlen + 100) { + size = alloc_nr(offset + entlen + 100); + buffer = xrealloc(buffer, size); + } + offset += sprintf(buffer + offset, + "%o %.*s", mode, entlen, path + baselen); + buffer[offset++] = 0; + memcpy(buffer + offset, sha1, 20); + offset += 20; + +#if DEBUG + fprintf(stderr, "cache-tree update-one %o %.*s\n", + mode, entlen, path + baselen); +#endif + } + + if (dryrun) { + unsigned char hdr[200]; + int hdrlen; + write_sha1_file_prepare(buffer, offset, tree_type, it->sha1, + hdr, &hdrlen); + } + else + write_sha1_file(buffer, offset, tree_type, it->sha1); + free(buffer); + it->entry_count = i; +#if DEBUG + fprintf(stderr, "cache-tree update-one (%d ent, %d subtree) %s\n", + it->entry_count, it->subtree_nr, + sha1_to_hex(it->sha1)); +#endif + return i; +} + +int cache_tree_update(struct cache_tree *it, + struct cache_entry **cache, + int entries, + int missing_ok, + int dryrun) +{ + int i; + i = verify_cache(cache, entries); + if (i) + return i; + i = update_one(it, cache, entries, "", 0, missing_ok, dryrun); + if (i < 0) + return i; + return 0; +} + +static void *write_one(struct cache_tree *it, + char *path, + int pathlen, + char *buffer, + unsigned long *size, + unsigned long *offset) +{ + int i; + + /* One "cache-tree" entry consists of the following: + * path (NUL terminated) + * entry_count, subtree_nr ("%d %d\n") + * tree-sha1 (missing if invalid) + * subtree_nr "cache-tree" entries for subtrees. + */ + if (*size < *offset + pathlen + 100) { + *size = alloc_nr(*offset + pathlen + 100); + buffer = xrealloc(buffer, *size); + } + *offset += sprintf(buffer + *offset, "%.*s%c%d %d\n", + pathlen, path, 0, + it->entry_count, it->subtree_nr); + +#if DEBUG + if (0 <= it->entry_count) + fprintf(stderr, "cache-tree <%.*s> (%d ent, %d subtree) %s\n", + pathlen, path, it->entry_count, it->subtree_nr, + sha1_to_hex(it->sha1)); + else + fprintf(stderr, "cache-tree <%.*s> (%d subtree) invalid\n", + pathlen, path, it->subtree_nr); +#endif + + if (0 <= it->entry_count) { + memcpy(buffer + *offset, it->sha1, 20); + *offset += 20; + } + for (i = 0; i < it->subtree_nr; i++) { + struct cache_tree_sub *down = it->down[i]; + if (i) { + struct cache_tree_sub *prev = it->down[i-1]; + if (subtree_name_cmp(down->name, down->namelen, + prev->name, prev->namelen) <= 0) + die("fatal - unsorted cache subtree"); + } + buffer = write_one(down->cache_tree, down->name, down->namelen, + buffer, size, offset); + } + return buffer; +} + +void *cache_tree_write(struct cache_tree *root, unsigned long *size_p) +{ + char path[PATH_MAX]; + unsigned long size = 8192; + char *buffer = xmalloc(size); + + *size_p = 0; + path[0] = 0; + return write_one(root, path, 0, buffer, &size, size_p); +} + +static struct cache_tree *read_one(const char **buffer, unsigned long *size_p) +{ + const char *buf = *buffer; + unsigned long size = *size_p; + const char *cp; + char *ep; + struct cache_tree *it; + int i, subtree_nr; + + it = NULL; + /* skip name, but make sure name exists */ + while (size && *buf) { + size--; + buf++; + } + if (!size) + goto free_return; + buf++; size--; + it = cache_tree(); + + cp = buf; + it->entry_count = strtol(cp, &ep, 10); + if (cp == ep) + goto free_return; + cp = ep; + subtree_nr = strtol(cp, &ep, 10); + if (cp == ep) + goto free_return; + while (size && *buf && *buf != '\n') { + size--; + buf++; + } + if (!size) + goto free_return; + buf++; size--; + if (0 <= it->entry_count) { + if (size < 20) + goto free_return; + memcpy(it->sha1, buf, 20); + buf += 20; + size -= 20; + } + +#if DEBUG + if (0 <= it->entry_count) + fprintf(stderr, "cache-tree <%s> (%d ent, %d subtree) %s\n", + *buffer, it->entry_count, subtree_nr, + sha1_to_hex(it->sha1)); + else + fprintf(stderr, "cache-tree <%s> (%d subtrees) invalid\n", + *buffer, subtree_nr); +#endif + + /* + * Just a heuristic -- we do not add directories that often but + * we do not want to have to extend it immediately when we do, + * hence +2. + */ + it->subtree_alloc = subtree_nr + 2; + it->down = xcalloc(it->subtree_alloc, sizeof(struct cache_tree_sub *)); + for (i = 0; i < subtree_nr; i++) { + /* read each subtree */ + struct cache_tree *sub; + struct cache_tree_sub *subtree; + const char *name = buf; + + sub = read_one(&buf, &size); + if (!sub) + goto free_return; + subtree = cache_tree_sub(it, name); + subtree->cache_tree = sub; + } + if (subtree_nr != it->subtree_nr) + die("cache-tree: internal error"); + *buffer = buf; + *size_p = size; + return it; + + free_return: + cache_tree_free(&it); + return NULL; +} + +struct cache_tree *cache_tree_read(const char *buffer, unsigned long size) +{ + if (buffer[0]) + return NULL; /* not the whole tree */ + return read_one(&buffer, &size); +} + +struct cache_tree *cache_tree_find(struct cache_tree *it, const char *path) +{ + while (*path) { + const char *slash; + struct cache_tree_sub *sub; + + slash = strchr(path, '/'); + if (!slash) + slash = path + strlen(path); + /* between path and slash is the name of the + * subtree to look for. + */ + sub = find_subtree(it, path, slash - path, 0); + if (!sub) + return NULL; + it = sub->cache_tree; + if (slash) + while (*slash && *slash == '/') + slash++; + if (!slash || !*slash) + return it; /* prefix ended with slashes */ + path = slash; + } + return it; +} diff --git a/cache-tree.h b/cache-tree.h new file mode 100644 index 0000000000..119407e3a1 --- /dev/null +++ b/cache-tree.h @@ -0,0 +1,33 @@ +#ifndef CACHE_TREE_H +#define CACHE_TREE_H + +struct cache_tree; +struct cache_tree_sub { + struct cache_tree *cache_tree; + int namelen; + int used; + char name[FLEX_ARRAY]; +}; + +struct cache_tree { + int entry_count; /* negative means "invalid" */ + unsigned char sha1[20]; + int subtree_nr; + int subtree_alloc; + struct cache_tree_sub **down; +}; + +struct cache_tree *cache_tree(void); +void cache_tree_free(struct cache_tree **); +void cache_tree_invalidate_path(struct cache_tree *, const char *); +struct cache_tree_sub *cache_tree_sub(struct cache_tree *, const char *); + +void *cache_tree_write(struct cache_tree *root, unsigned long *size_p); +struct cache_tree *cache_tree_read(const char *buffer, unsigned long size); + +int cache_tree_fully_valid(struct cache_tree *); +int cache_tree_update(struct cache_tree *, struct cache_entry **, int, int, int); + +struct cache_tree *cache_tree_find(struct cache_tree *, const char *); + +#endif @@ -114,6 +114,7 @@ static inline unsigned int create_ce_mode(unsigned int mode) extern struct cache_entry **active_cache; extern unsigned int active_nr, active_alloc, active_cache_changed; +extern struct cache_tree *active_cache_tree; #define GIT_DIR_ENVIRONMENT "GIT_DIR" #define DEFAULT_GIT_DIR_ENVIRONMENT ".git" diff --git a/checkout-index.c b/checkout-index.c index cc3a745c14..9876af6fd6 100644 --- a/checkout-index.c +++ b/checkout-index.c @@ -39,6 +39,7 @@ #include "cache.h" #include "strbuf.h" #include "quote.h" +#include "cache-tree.h" #define CHECKOUT_ALL 4 static const char *prefix; diff --git a/dump-cache-tree.c b/dump-cache-tree.c new file mode 100644 index 0000000000..1ccaf51773 --- /dev/null +++ b/dump-cache-tree.c @@ -0,0 +1,64 @@ +#include "cache.h" +#include "tree.h" +#include "cache-tree.h" + + +static void dump_one(struct cache_tree *it, const char *pfx, const char *x) +{ + if (it->entry_count < 0) + printf("%-40s %s%s (%d subtrees)\n", + "invalid", x, pfx, it->subtree_nr); + else + printf("%s %s%s (%d entries, %d subtrees)\n", + sha1_to_hex(it->sha1), x, pfx, + it->entry_count, it->subtree_nr); +} + +static int dump_cache_tree(struct cache_tree *it, + struct cache_tree *ref, + const char *pfx) +{ + int i; + int errs = 0; + + if (!it || !ref) + /* missing in either */ + return 0; + + if (it->entry_count < 0) { + dump_one(it, pfx, ""); + dump_one(ref, pfx, "#(ref) "); + if (it->subtree_nr != ref->subtree_nr) + errs = 1; + } + else { + dump_one(it, pfx, ""); + if (memcmp(it->sha1, ref->sha1, 20) || + ref->entry_count != it->entry_count || + ref->subtree_nr != it->subtree_nr) { + dump_one(ref, pfx, "#(ref) "); + errs = 1; + } + } + + for (i = 0; i < it->subtree_nr; i++) { + char path[PATH_MAX]; + struct cache_tree_sub *down = it->down[i]; + struct cache_tree_sub *rdwn; + + rdwn = cache_tree_sub(ref, down->name); + sprintf(path, "%s%.*s/", pfx, down->namelen, down->name); + if (dump_cache_tree(down->cache_tree, rdwn->cache_tree, path)) + errs = 1; + } + return errs; +} + +int main(int ac, char **av) +{ + struct cache_tree *another = cache_tree(); + if (read_cache() < 0) + die("unable to read index file"); + cache_tree_update(another, active_cache, active_nr, 0, 1); + return dump_cache_tree(active_cache_tree, another, ""); +} diff --git a/fsck-objects.c b/fsck-objects.c index 59b25904cb..1922b6d84c 100644 --- a/fsck-objects.c +++ b/fsck-objects.c @@ -8,6 +8,7 @@ #include "tag.h" #include "refs.h" #include "pack.h" +#include "cache-tree.h" #define REACHABLE 0x0001 @@ -438,6 +439,28 @@ static int fsck_head_link(void) return 0; } +static int fsck_cache_tree(struct cache_tree *it) +{ + int i; + int err = 0; + + if (0 <= it->entry_count) { + struct object *obj = parse_object(it->sha1); + if (!obj) { + error("%s: invalid sha1 pointer in cache-tree", + sha1_to_hex(it->sha1)); + return 1; + } + mark_reachable(obj, REACHABLE); + obj->used = 1; + if (obj->type != tree_type) + err |= objerror(obj, "non-tree in cache-tree"); + } + for (i = 0; i < it->subtree_nr; i++) + err |= fsck_cache_tree(it->down[i]->cache_tree); + return err; +} + int main(int argc, char **argv) { int i, heads; @@ -547,6 +570,8 @@ int main(int argc, char **argv) obj->used = 1; mark_reachable(obj, REACHABLE); } + if (active_cache_tree) + fsck_cache_tree(active_cache_tree); } check_connectivity(); diff --git a/http-fetch.c b/http-fetch.c index cc7bd1f367..661c909152 100644 --- a/http-fetch.c +++ b/http-fetch.c @@ -1271,10 +1271,10 @@ int main(int argc, char **argv) if (pull(commit_id)) rc = 1; - curl_slist_free_all(no_pragma_header); - http_cleanup(); + curl_slist_free_all(no_pragma_header); + if (corrupt_object_found) { fprintf(stderr, "Some loose object were found to be corrupt, but they might be just\n" diff --git a/mailinfo.c b/mailinfo.c index b27651935d..78d2a15dd0 100644 --- a/mailinfo.c +++ b/mailinfo.c @@ -72,11 +72,14 @@ static int bogus_from(char *line) return 1; } -static int handle_from(char *line) +static int handle_from(char *in_line) { - char *at = strchr(line, '@'); + char line[1000]; + char *at; char *dst; + strcpy(line, in_line); + at = strchr(line, '@'); if (!at) return bogus_from(line); @@ -237,38 +240,46 @@ static int eatspace(char *line) #define SEEN_FROM 01 #define SEEN_DATE 02 #define SEEN_SUBJECT 04 +#define SEEN_BOGUS_UNIX_FROM 010 +#define SEEN_PREFIX 020 /* First lines of body can have From:, Date:, and Subject: */ -static int handle_inbody_header(int *seen, char *line) +static void handle_inbody_header(int *seen, char *line) { + if (!memcmp(">From", line, 5) && isspace(line[5])) { + if (!(*seen & SEEN_BOGUS_UNIX_FROM)) { + *seen |= SEEN_BOGUS_UNIX_FROM; + return; + } + } if (!memcmp("From:", line, 5) && isspace(line[5])) { if (!(*seen & SEEN_FROM) && handle_from(line+6)) { *seen |= SEEN_FROM; - return 1; + return; } } if (!memcmp("Date:", line, 5) && isspace(line[5])) { if (!(*seen & SEEN_DATE)) { handle_date(line+6); *seen |= SEEN_DATE; - return 1; + return; } } if (!memcmp("Subject:", line, 8) && isspace(line[8])) { if (!(*seen & SEEN_SUBJECT)) { handle_subject(line+9); *seen |= SEEN_SUBJECT; - return 1; + return; } } if (!memcmp("[PATCH]", line, 7) && isspace(line[7])) { if (!(*seen & SEEN_SUBJECT)) { handle_subject(line); *seen |= SEEN_SUBJECT; - return 1; + return; } } - return 0; + *seen |= SEEN_PREFIX; } static char *cleanup_subject(char *subject) @@ -324,6 +335,7 @@ static void cleanup_space(char *buf) } } +static void decode_header_bq(char *it); typedef int (*header_fn_t)(char *); struct header_def { const char *name; @@ -331,7 +343,7 @@ struct header_def { int namelen; }; -static void check_header(char *line, int len, struct header_def *header) +static void check_header(char *line, struct header_def *header) { int i; @@ -343,13 +355,17 @@ static void check_header(char *line, int len, struct header_def *header) int len = header[i].namelen; if (!strncasecmp(line, header[i].name, len) && line[len] == ':' && isspace(line[len + 1])) { + /* Unwrap inline B and Q encoding, and optionally + * normalize the meta information to utf8. + */ + decode_header_bq(line + len + 2); header[i].func(line + len + 2); break; } } } -static void check_subheader_line(char *line, int len) +static void check_subheader_line(char *line) { static struct header_def header[] = { { "Content-Type", handle_subcontent_type }, @@ -357,9 +373,9 @@ static void check_subheader_line(char *line, int len) handle_content_transfer_encoding }, { NULL }, }; - check_header(line, len, header); + check_header(line, header); } -static void check_header_line(char *line, int len) +static void check_header_line(char *line) { static struct header_def header[] = { { "From", handle_from }, @@ -370,27 +386,36 @@ static void check_header_line(char *line, int len) handle_content_transfer_encoding }, { NULL }, }; - check_header(line, len, header); + check_header(line, header); } static int read_one_header_line(char *line, int sz, FILE *in) { int ofs = 0; while (ofs < sz) { + const char *colon; int peek, len; if (fgets(line + ofs, sz - ofs, in) == NULL) - return ofs; + break; len = eatspace(line + ofs); if (len == 0) - return ofs; - peek = fgetc(in); ungetc(peek, in); - if (peek == ' ' || peek == '\t') { - /* Yuck, 2822 header "folding" */ - ofs += len; - continue; + break; + colon = strchr(line, ':'); + if (!colon || !isspace(colon[1])) { + /* Re-add the newline */ + line[ofs + len] = '\n'; + line[ofs + len + 1] = '\0'; + break; } - return ofs + len; + ofs += len; + /* Yuck, 2822 header "folding" */ + peek = fgetc(in); ungetc(peek, in); + if (peek != ' ' && peek != '\t') + break; } + /* Count mbox From headers as headers */ + if (!ofs && !memcmp(line, "From ", 5)) + ofs = 1; return ofs; } @@ -585,25 +610,13 @@ static void decode_transfer_encoding(char *line) static void handle_info(void) { char *sub; - static int done_info = 0; - - if (done_info) - return; - done_info = 1; sub = cleanup_subject(subject); cleanup_space(name); cleanup_space(date); cleanup_space(email); cleanup_space(sub); - /* Unwrap inline B and Q encoding, and optionally - * normalize the meta information to utf8. - */ - decode_header_bq(name); - decode_header_bq(date); - decode_header_bq(email); - decode_header_bq(sub); printf("Author: %s\nEmail: %s\nSubject: %s\nDate: %s\n\n", name, email, sub, date); } @@ -611,7 +624,7 @@ static void handle_info(void) /* We are inside message body and have read line[] already. * Spit out the commit log. */ -static int handle_commit_msg(void) +static int handle_commit_msg(int *seen) { if (!cmitmsg) return 0; @@ -635,6 +648,11 @@ static int handle_commit_msg(void) decode_transfer_encoding(line); if (metainfo_charset) convert_to_utf8(line, charset); + + handle_inbody_header(seen, line); + if (!(*seen & SEEN_PREFIX)) + continue; + fputs(line, cmitmsg); } while (fgets(line, sizeof(line), stdin) != NULL); fclose(cmitmsg); @@ -666,26 +684,16 @@ static void handle_patch(void) * that the first part to contain commit message and a patch, and * handle other parts as pure patches. */ -static int handle_multipart_one_part(void) +static int handle_multipart_one_part(int *seen) { - int seen = 0; int n = 0; - int len; while (fgets(line, sizeof(line), stdin) != NULL) { again: - len = eatspace(line); n++; - if (!len) - continue; if (is_multipart_boundary(line)) break; - if (0 <= seen && handle_inbody_header(&seen, line)) - continue; - seen = -1; /* no more inbody headers */ - line[len] = '\n'; - handle_info(); - if (handle_commit_msg()) + if (handle_commit_msg(seen)) goto again; handle_patch(); break; @@ -697,6 +705,7 @@ static int handle_multipart_one_part(void) static void handle_multipart_body(void) { + int seen = 0; int part_num = 0; /* Skip up to the first boundary */ @@ -709,16 +718,16 @@ static void handle_multipart_body(void) return; /* We are on boundary line. Start slurping the subhead. */ while (1) { - int len = read_one_header_line(line, sizeof(line), stdin); - if (!len) { - if (handle_multipart_one_part() < 0) + int hdr = read_one_header_line(line, sizeof(line), stdin); + if (!hdr) { + if (handle_multipart_one_part(&seen) < 0) return; /* Reset per part headers */ transfer_encoding = TE_DONTCARE; charset[0] = 0; } else - check_subheader_line(line, len); + check_subheader_line(line); } fclose(patchfile); if (!patch_lines) { @@ -732,18 +741,9 @@ static void handle_body(void) { int seen = 0; - while (fgets(line, sizeof(line), stdin) != NULL) { - int len = eatspace(line); - if (!len) - continue; - if (0 <= seen && handle_inbody_header(&seen, line)) - continue; - seen = -1; /* no more inbody headers */ - line[len] = '\n'; - handle_info(); - handle_commit_msg(); + if (line[0] || fgets(line, sizeof(line), stdin) != NULL) { + handle_commit_msg(&seen); handle_patch(); - break; } fclose(patchfile); if (!patch_lines) { @@ -787,15 +787,16 @@ int main(int argc, char **argv) exit(1); } while (1) { - int len = read_one_header_line(line, sizeof(line), stdin); - if (!len) { + int hdr = read_one_header_line(line, sizeof(line), stdin); + if (!hdr) { if (multipart_boundary[0]) handle_multipart_body(); else handle_body(); + handle_info(); break; } - check_header_line(line, len); + check_header_line(line); } return 0; } diff --git a/read-cache.c b/read-cache.c index 32ba917923..36bd4ea0be 100644 --- a/read-cache.c +++ b/read-cache.c @@ -4,11 +4,26 @@ * Copyright (C) Linus Torvalds, 2005 */ #include "cache.h" +#include "cache-tree.h" + +/* Index extensions. + * + * The first letter should be 'A'..'Z' for extensions that are not + * necessary for a correct operation (i.e. optimization data). + * When new extensions are added that _needs_ to be understood in + * order to correctly interpret the index file, pick character that + * is outside the range, to cause the reader to abort. + */ + +#define CACHE_EXT(s) ( (s[0]<<24)|(s[1]<<16)|(s[2]<<8)|(s[3]) ) +#define CACHE_EXT_TREE 0x54524545 /* "TREE" */ struct cache_entry **active_cache = NULL; static time_t index_file_timestamp; unsigned int active_nr = 0, active_alloc = 0, active_cache_changed = 0; +struct cache_tree *active_cache_tree = NULL; + /* * This only updates the "non-critical" parts of the directory * cache, ie the parts that aren't tracked by GIT, and only used @@ -696,6 +711,22 @@ static int verify_hdr(struct cache_header *hdr, unsigned long size) return 0; } +static int read_index_extension(const char *ext, void *data, unsigned long sz) +{ + switch (CACHE_EXT(ext)) { + case CACHE_EXT_TREE: + active_cache_tree = cache_tree_read(data, sz); + break; + default: + if (*ext < 'A' || 'Z' < *ext) + return error("index uses %.4s extension, which we do not understand", + ext); + fprintf(stderr, "ignoring %.4s extension\n", ext); + break; + } + return 0; +} + int read_cache(void) { int fd, i; @@ -744,6 +775,22 @@ int read_cache(void) active_cache[i] = ce; } index_file_timestamp = st.st_mtime; + while (offset <= size - 20 - 8) { + /* After an array of active_nr index entries, + * there can be arbitrary number of extended + * sections, each of which is prefixed with + * extension name (4-byte) and section length + * in 4-byte network byte order. + */ + unsigned long extsize; + memcpy(&extsize, map + offset + 4, 4); + extsize = ntohl(extsize); + if (read_index_extension(map + offset, + map + offset + 8, extsize) < 0) + goto unmap; + offset += 8; + offset += extsize; + } return active_nr; unmap: @@ -778,6 +825,17 @@ static int ce_write(SHA_CTX *context, int fd, void *data, unsigned int len) return 0; } +static int write_index_ext_header(SHA_CTX *context, int fd, + unsigned long ext, unsigned long sz) +{ + ext = htonl(ext); + sz = htonl(sz); + if ((ce_write(context, fd, &ext, 4) < 0) || + (ce_write(context, fd, &sz, 4) < 0)) + return -1; + return 0; +} + static int ce_flush(SHA_CTX *context, int fd) { unsigned int left = write_buffer_len; @@ -874,5 +932,19 @@ int write_cache(int newfd, struct cache_entry **cache, int entries) if (ce_write(&c, newfd, ce, ce_size(ce)) < 0) return -1; } + + /* Write extension data here */ + if (active_cache_tree) { + unsigned long sz; + void *data = cache_tree_write(active_cache_tree, &sz); + if (data && + !write_index_ext_header(&c, newfd, CACHE_EXT_TREE, sz) && + !ce_write(&c, newfd, data, sz)) + ; + else { + free(data); + return -1; + } + } return ce_flush(&c, newfd); } diff --git a/t/t0000-basic.sh b/t/t0000-basic.sh index cf33989b56..2c9bbb59b0 100755 --- a/t/t0000-basic.sh +++ b/t/t0000-basic.sh @@ -195,6 +195,20 @@ test_expect_success \ 'git-ls-tree -r output for a known tree.' \ 'diff current expected' +test_expect_success \ + 'writing partial tree out with git-write-tree --prefix.' \ + 'ptree=$(git-write-tree --prefix=path3)' +test_expect_success \ + 'validate object ID for a known tree.' \ + 'test "$ptree" = 21ae8269cacbe57ae09138dcc3a2887f904d02b3' + +test_expect_success \ + 'writing partial tree out with git-write-tree --prefix.' \ + 'ptree=$(git-write-tree --prefix=path3/subp3)' +test_expect_success \ + 'validate object ID for a known tree.' \ + 'test "$ptree" = 3c5e5399f3a333eddecce7a9b9465b63f65f51e2' + ################################################################ rm .git/index test_expect_success \ diff --git a/t/t4113-apply-ending.sh b/t/t4113-apply-ending.sh new file mode 100755 index 0000000000..7fd0cf62ec --- /dev/null +++ b/t/t4113-apply-ending.sh @@ -0,0 +1,53 @@ +#!/bin/sh +# +# Copyright (c) 2006 Catalin Marinas +# + +test_description='git-apply trying to add an ending line. + +' +. ./test-lib.sh + +# setup + +cat >test-patch <<\EOF +diff --git a/file b/file +--- a/file ++++ b/file +@@ -1,2 +1,3 @@ + a + b ++c +EOF + +echo 'a' >file +echo 'b' >>file +echo 'c' >>file + +test_expect_success setup \ + 'git-update-index --add file' + +# test + +test_expect_failure 'apply at the end' \ + 'git-apply --index test-patch' + +cat >test-patch <<\EOF +diff a/file b/file +--- a/file ++++ b/file +@@ -1,2 +1,3 @@ ++a + b + c +EOF + +echo >file 'a +b +c' +git-update-index file + +test_expect_failure 'apply at the beginning' \ + 'git-apply --index test-patch' + +test_done diff --git a/update-index.c b/update-index.c index 5854d11fd9..956b6b34f9 100644 --- a/update-index.c +++ b/update-index.c @@ -6,6 +6,7 @@ #include "cache.h" #include "strbuf.h" #include "quote.h" +#include "cache-tree.h" #include "tree-walk.h" /* @@ -51,6 +52,7 @@ static int mark_valid(const char *path) active_cache[pos]->ce_flags &= ~htons(CE_VALID); break; } + cache_tree_invalidate_path(active_cache_tree, path); active_cache_changed = 1; return 0; } @@ -64,6 +66,12 @@ static int add_file_to_cache(const char *path) struct stat st; status = lstat(path, &st); + + /* We probably want to do this in remove_file_from_cache() and + * add_cache_entry() instead... + */ + cache_tree_invalidate_path(active_cache_tree, path); + if (status < 0 || S_ISDIR(st.st_mode)) { /* When we used to have "path" and now we want to add * "path/file", we need a way to remove "path" before @@ -145,6 +153,7 @@ static int add_cacheinfo(unsigned int mode, const unsigned char *sha1, return error("%s: cannot add to the index - missing --add option?", path); report("add '%s'", path); + cache_tree_invalidate_path(active_cache_tree, path); return 0; } @@ -169,6 +178,7 @@ static void chmod_path(int flip, const char *path) default: goto fail; } + cache_tree_invalidate_path(active_cache_tree, path); active_cache_changed = 1; report("chmod %cx '%s'", flip, path); return; @@ -190,6 +200,7 @@ static void update_one(const char *path, const char *prefix, int prefix_length) die("Unable to mark file %s", path); goto free_return; } + cache_tree_invalidate_path(active_cache_tree, path); if (force_remove) { if (remove_file_from_cache(p)) @@ -268,6 +279,7 @@ static void read_index_info(int line_termination) free(path_name); continue; } + cache_tree_invalidate_path(active_cache_tree, path_name); if (!mode) { /* mode == 0 means there is no such path -- remove */ @@ -374,6 +386,7 @@ static int unresolve_one(const char *path) goto free_return; } + cache_tree_invalidate_path(active_cache_tree, path); remove_file_from_cache(path); if (add_cache_entry(ce_2, ADD_CACHE_OK_TO_ADD)) { error("%s: cannot add our version to the index.", path); diff --git a/write-tree.c b/write-tree.c index dcad6e6670..895e7a359d 100644 --- a/write-tree.c +++ b/write-tree.c @@ -5,154 +5,68 @@ */ #include "cache.h" #include "tree.h" +#include "cache-tree.h" static int missing_ok = 0; +static char *prefix = NULL; -static int check_valid_sha1(unsigned char *sha1) -{ - int ret; - - /* If we were anal, we'd check that the sha1 of the contents actually matches */ - ret = has_sha1_file(sha1); - if (ret == 0) - perror(sha1_file_name(sha1)); - return ret ? 0 : -1; -} - -static int write_tree(struct cache_entry **cachep, int maxentries, const char *base, int baselen, unsigned char *returnsha1) -{ - unsigned char subdir_sha1[20]; - unsigned long size, offset; - char *buffer; - int nr; - - /* Guess at some random initial size */ - size = 8192; - buffer = xmalloc(size); - offset = 0; - - nr = 0; - while (nr < maxentries) { - struct cache_entry *ce = cachep[nr]; - const char *pathname = ce->name, *filename, *dirname; - int pathlen = ce_namelen(ce), entrylen; - unsigned char *sha1; - unsigned int mode; - - /* Did we hit the end of the directory? Return how many we wrote */ - if (baselen >= pathlen || memcmp(base, pathname, baselen)) - break; - - sha1 = ce->sha1; - mode = ntohl(ce->ce_mode); - - /* Do we have _further_ subdirectories? */ - filename = pathname + baselen; - dirname = strchr(filename, '/'); - if (dirname) { - int subdir_written; - - subdir_written = write_tree(cachep + nr, maxentries - nr, pathname, dirname-pathname+1, subdir_sha1); - nr += subdir_written; - - /* Now we need to write out the directory entry into this tree.. */ - mode = S_IFDIR; - pathlen = dirname - pathname; - - /* ..but the directory entry doesn't count towards the total count */ - nr--; - sha1 = subdir_sha1; - } +static const char write_tree_usage[] = +"git-write-tree [--missing-ok] [--prefix=<prefix>/]"; - if (!missing_ok && check_valid_sha1(sha1) < 0) - exit(1); - - entrylen = pathlen - baselen; - if (offset + entrylen + 100 > size) { - size = alloc_nr(offset + entrylen + 100); - buffer = xrealloc(buffer, size); - } - offset += sprintf(buffer + offset, "%o %.*s", mode, entrylen, filename); - buffer[offset++] = 0; - memcpy(buffer + offset, sha1, 20); - offset += 20; - nr++; - } - - write_sha1_file(buffer, offset, tree_type, returnsha1); - free(buffer); - return nr; -} - -static const char write_tree_usage[] = "git-write-tree [--missing-ok]"; +static struct cache_file cache_file; int main(int argc, char **argv) { - int i, funny; - int entries; - unsigned char sha1[20]; - + int entries, was_valid, newfd; + setup_git_directory(); + newfd = hold_index_file_for_update(&cache_file, get_index_file()); entries = read_cache(); - if (argc == 2) { - if (!strcmp(argv[1], "--missing-ok")) + + while (1 < argc) { + char *arg = argv[1]; + if (!strcmp(arg, "--missing-ok")) missing_ok = 1; + else if (!strncmp(arg, "--prefix=", 9)) + prefix = arg + 9; else die(write_tree_usage); + argc--; argv++; } - + if (argc > 2) die("too many options"); if (entries < 0) die("git-write-tree: error reading cache"); - /* Verify that the tree is merged */ - funny = 0; - for (i = 0; i < entries; i++) { - struct cache_entry *ce = active_cache[i]; - if (ce_stage(ce)) { - if (10 < ++funny) { - fprintf(stderr, "...\n"); - break; - } - fprintf(stderr, "%s: unmerged (%s)\n", ce->name, sha1_to_hex(ce->sha1)); + if (!active_cache_tree) + active_cache_tree = cache_tree(); + + was_valid = cache_tree_fully_valid(active_cache_tree); + if (!was_valid) { + if (cache_tree_update(active_cache_tree, + active_cache, active_nr, + missing_ok, 0) < 0) + die("git-write-tree: error building trees"); + if (0 <= newfd) { + if (!write_cache(newfd, active_cache, active_nr)) + commit_index_file(&cache_file); } - } - if (funny) - die("git-write-tree: not able to write tree"); - - /* Also verify that the cache does not have path and path/file - * at the same time. At this point we know the cache has only - * stage 0 entries. - */ - funny = 0; - for (i = 0; i < entries - 1; i++) { - /* path/file always comes after path because of the way - * the cache is sorted. Also path can appear only once, - * which means conflicting one would immediately follow. + /* Not being able to write is fine -- we are only interested + * in updating the cache-tree part, and if the next caller + * ends up using the old index with unupdated cache-tree part + * it misses the work we did here, but that is just a + * performance penalty and not a big deal. */ - const char *this_name = active_cache[i]->name; - const char *next_name = active_cache[i+1]->name; - int this_len = strlen(this_name); - if (this_len < strlen(next_name) && - strncmp(this_name, next_name, this_len) == 0 && - next_name[this_len] == '/') { - if (10 < ++funny) { - fprintf(stderr, "...\n"); - break; - } - fprintf(stderr, "You have both %s and %s\n", - this_name, next_name); - } } - if (funny) - die("git-write-tree: not able to write tree"); - - /* Ok, write it out */ - if (write_tree(active_cache, entries, "", 0, sha1) != entries) - die("git-write-tree: internal error"); - printf("%s\n", sha1_to_hex(sha1)); + if (prefix) { + struct cache_tree *subtree = + cache_tree_find(active_cache_tree, prefix); + printf("%s\n", sha1_to_hex(subtree->sha1)); + } + else + printf("%s\n", sha1_to_hex(active_cache_tree->sha1)); return 0; } |