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 | 24 | ||||
| -rw-r--r-- | apply.c | 5 | ||||
| -rw-r--r-- | builtin-add.c | 189 | ||||
| -rw-r--r-- | builtin-rm.c | 151 | ||||
| -rw-r--r-- | builtin-tar-tree.c (renamed from tar-tree.c) | 62 | ||||
| -rw-r--r-- | builtin-upload-tar.c | 74 | ||||
| -rw-r--r-- | builtin.h | 4 | ||||
| -rw-r--r-- | cache-tree.c | 557 | ||||
| -rw-r--r-- | cache-tree.h | 33 | ||||
| -rw-r--r-- | cache.h | 2 | ||||
| -rw-r--r-- | checkout-index.c | 1 | ||||
| -rw-r--r-- | dir.c | 401 | ||||
| -rw-r--r-- | dir.h | 51 | ||||
| -rw-r--r-- | dump-cache-tree.c | 64 | ||||
| -rw-r--r-- | fsck-objects.c | 25 | ||||
| -rwxr-xr-x | git-add.sh | 56 | ||||
| -rwxr-xr-x | git-rm.sh | 70 | ||||
| -rw-r--r-- | git.c | 4 | ||||
| -rw-r--r-- | ls-files.c | 381 | ||||
| -rw-r--r-- | read-cache.c | 138 | ||||
| -rw-r--r-- | read-tree.c | 134 | ||||
| -rwxr-xr-x | t/t0000-basic.sh | 14 | ||||
| -rw-r--r-- | update-index.c | 77 | ||||
| -rw-r--r-- | write-tree.c | 166 |
27 files changed, 2010 insertions, 693 deletions
diff --git a/.gitignore b/.gitignore index b5959d6311..7906909b30 100644 --- a/.gitignore +++ b/.gitignore @@ -123,6 +123,7 @@ 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> @@ -113,14 +113,14 @@ SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__ ### --- END CONFIGURATION SECTION --- SCRIPT_SH = \ - git-add.sh git-bisect.sh git-branch.sh git-checkout.sh \ + git-bisect.sh git-branch.sh git-checkout.sh \ git-cherry.sh git-clean.sh git-clone.sh git-commit.sh \ git-fetch.sh \ git-ls-remote.sh \ git-merge-one-file.sh git-parse-remote.sh \ git-prune.sh git-pull.sh git-rebase.sh \ git-repack.sh git-request-pull.sh git-reset.sh \ - git-resolve.sh git-revert.sh git-rm.sh git-sh-setup.sh \ + git-resolve.sh git-revert.sh git-sh-setup.sh \ git-tag.sh git-verify-tag.sh \ git-applymbox.sh git-applypatch.sh git-am.sh \ git-merge.sh git-merge-stupid.sh git-merge-octopus.sh \ @@ -161,7 +161,7 @@ PROGRAMS = \ git-receive-pack$X git-rev-parse$X \ git-send-pack$X git-show-branch$X git-shell$X \ git-show-index$X git-ssh-fetch$X \ - git-ssh-upload$X git-tar-tree$X git-unpack-file$X \ + git-ssh-upload$X git-unpack-file$X \ git-unpack-objects$X git-update-index$X git-update-server-info$X \ git-upload-pack$X git-verify-pack$X git-write-tree$X \ git-update-ref$X git-symbolic-ref$X \ @@ -170,8 +170,9 @@ PROGRAMS = \ BUILT_INS = git-log$X git-whatchanged$X git-show$X \ git-count-objects$X git-diff$X git-push$X \ - git-grep$X git-rev-list$X git-check-ref-format$X \ - git-init-db$X git-format-patch$X + git-grep$X git-add$X git-rm$X git-rev-list$X \ + git-check-ref-format$X \ + git-init-db$X git-tar-tree$X git-upload-tar$X git-format-patch$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -200,7 +201,7 @@ LIB_H = \ blob.h cache.h commit.h csum-file.h delta.h \ diff.h object.h pack.h pkt-line.h quote.h refs.h \ run-command.h strbuf.h tag.h tree.h git-compat-util.h revision.h \ - tree-walk.h log-tree.h + tree-walk.h log-tree.h dir.h DIFF_OBJS = \ diff.o diff-lib.o diffcore-break.o diffcore-order.o \ @@ -208,10 +209,10 @@ 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 \ + quote.o read-cache.o refs.o run-command.o dir.o \ server-info.o setup.o sha1_file.o sha1_name.o strbuf.o \ tag.o tree.o usage.o config.o environment.o ctype.o copy.o \ fetch-clone.o revision.o pager.o tree-walk.o xdiff-interface.o \ @@ -219,8 +220,8 @@ LIB_OBJS = \ BUILTIN_OBJS = \ builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \ - builtin-grep.o builtin-rev-list.o builtin-check-ref-format.o \ - builtin-init-db.o + builtin-grep.o builtin-add.o builtin-rev-list.o builtin-check-ref-format.o \ + builtin-rm.o builtin-init-db.o builtin-tar-tree.o builtin-upload-tar.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) LIBS = $(GITLIBS) -lz @@ -609,6 +610,9 @@ test-date$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 @@ -8,6 +8,7 @@ */ #include <fnmatch.h> #include "cache.h" +#include "cache-tree.h" #include "quote.h" #include "blob.h" #include "delta.h" @@ -1917,6 +1918,7 @@ 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); @@ -2018,8 +2020,9 @@ 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-add.c b/builtin-add.c new file mode 100644 index 0000000000..02fe38b0c4 --- /dev/null +++ b/builtin-add.c @@ -0,0 +1,189 @@ +/* + * "git add" builtin command + * + * Copyright (C) 2006 Linus Torvalds + */ +#include <fnmatch.h> + +#include "cache.h" +#include "builtin.h" +#include "dir.h" +#include "cache-tree.h" + +static const char builtin_add_usage[] = +"git-add [-n] [-v] <filepattern>..."; + +static void prune_directory(struct dir_struct *dir, const char **pathspec, int prefix) +{ + char *seen; + int i, specs; + struct dir_entry **src, **dst; + + for (specs = 0; pathspec[specs]; specs++) + /* nothing */; + seen = xmalloc(specs); + memset(seen, 0, specs); + + src = dst = dir->entries; + i = dir->nr; + while (--i >= 0) { + struct dir_entry *entry = *src++; + if (!match_pathspec(pathspec, entry->name, entry->len, prefix, seen)) { + free(entry); + continue; + } + *dst++ = entry; + } + dir->nr = dst - dir->entries; + + for (i = 0; i < specs; i++) { + struct stat st; + const char *match; + if (seen[i]) + continue; + + /* Existing file? We must have ignored it */ + match = pathspec[i]; + if (!match[0] || !lstat(match, &st)) + continue; + die("pathspec '%s' did not match any files", match); + } +} + +static void fill_directory(struct dir_struct *dir, const char **pathspec) +{ + const char *path, *base; + int baselen; + + /* Set up the default git porcelain excludes */ + memset(dir, 0, sizeof(*dir)); + dir->exclude_per_dir = ".gitignore"; + path = git_path("info/exclude"); + if (!access(path, R_OK)) + add_excludes_from_file(dir, path); + + /* + * Calculate common prefix for the pathspec, and + * use that to optimize the directory walk + */ + baselen = common_prefix(pathspec); + path = "."; + base = ""; + if (baselen) { + char *common = xmalloc(baselen + 1); + common = xmalloc(baselen + 1); + memcpy(common, *pathspec, baselen); + common[baselen] = 0; + path = base = common; + } + + /* Read the directory and prune it */ + read_directory(dir, path, base, baselen); + if (pathspec) + prune_directory(dir, pathspec, baselen); +} + +static int add_file_to_index(const char *path, int verbose) +{ + int size, namelen; + struct stat st; + struct cache_entry *ce; + + if (lstat(path, &st)) + die("%s: unable to stat (%s)", path, strerror(errno)); + + if (!S_ISREG(st.st_mode) && !S_ISLNK(st.st_mode)) + die("%s: can only add regular files or symbolic links", path); + + namelen = strlen(path); + size = cache_entry_size(namelen); + ce = xcalloc(1, size); + memcpy(ce->name, path, namelen); + ce->ce_flags = htons(namelen); + fill_stat_cache_info(ce, &st); + + ce->ce_mode = create_ce_mode(st.st_mode); + if (!trust_executable_bit) { + /* If there is an existing entry, pick the mode bits + * from it. + */ + int pos = cache_name_pos(path, namelen); + if (pos >= 0) + ce->ce_mode = active_cache[pos]->ce_mode; + } + + if (index_path(ce->sha1, path, &st, 1)) + die("unable to index file %s", path); + if (add_cache_entry(ce, ADD_CACHE_OK_TO_ADD)) + 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; +} + +static struct cache_file cache_file; + +int cmd_add(int argc, const char **argv, char **envp) +{ + int i, newfd; + int verbose = 0, show_only = 0; + const char *prefix = setup_git_directory(); + const char **pathspec; + struct dir_struct dir; + + git_config(git_default_config); + + newfd = hold_index_file_for_update(&cache_file, get_index_file()); + if (newfd < 0) + die("unable to create new cachefile"); + + if (read_cache() < 0) + die("index file corrupt"); + + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + + if (arg[0] != '-') + break; + if (!strcmp(arg, "--")) { + i++; + break; + } + if (!strcmp(arg, "-n")) { + show_only = 1; + continue; + } + if (!strcmp(arg, "-v")) { + verbose = 1; + continue; + } + die(builtin_add_usage); + } + git_config(git_default_config); + pathspec = get_pathspec(prefix, argv + i); + + fill_directory(&dir, pathspec); + + if (show_only) { + const char *sep = "", *eof = ""; + for (i = 0; i < dir.nr; i++) { + printf("%s%s", sep, dir.entries[i]->name); + sep = " "; + eof = "\n"; + } + fputs(eof, stdout); + return 0; + } + + for (i = 0; i < dir.nr; i++) + add_file_to_index(dir.entries[i]->name, verbose); + + if (active_cache_changed) { + if (write_cache(newfd, active_cache, active_nr) || + commit_index_file(&cache_file)) + die("Unable to write new index file"); + } + + return 0; +} diff --git a/builtin-rm.c b/builtin-rm.c new file mode 100644 index 0000000000..0beb86dc3d --- /dev/null +++ b/builtin-rm.c @@ -0,0 +1,151 @@ +/* + * "git rm" builtin command + * + * Copyright (C) Linus Torvalds 2006 + */ +#include "cache.h" +#include "builtin.h" +#include "dir.h" + +static const char builtin_rm_usage[] = +"git-rm [-n] [-v] [-f] <filepattern>..."; + +static struct { + int nr, alloc; + const char **name; +} list; + +static void add_list(const char *name) +{ + if (list.nr >= list.alloc) { + list.alloc = alloc_nr(list.alloc); + list.name = xrealloc(list.name, list.alloc * sizeof(const char *)); + } + list.name[list.nr++] = name; +} + +static int remove_file(const char *name) +{ + int ret; + char *slash; + + ret = unlink(name); + if (!ret && (slash = strrchr(name, '/'))) { + char *n = strdup(name); + do { + n[slash - name] = 0; + name = n; + } while (!rmdir(name) && (slash = strrchr(name, '/'))); + } + return ret; +} + +static struct cache_file cache_file; + +int cmd_rm(int argc, const char **argv, char **envp) +{ + int i, newfd; + int verbose = 0, show_only = 0, force = 0; + const char *prefix = setup_git_directory(); + const char **pathspec; + char *seen; + + git_config(git_default_config); + + newfd = hold_index_file_for_update(&cache_file, get_index_file()); + if (newfd < 0) + die("unable to create new index file"); + + if (read_cache() < 0) + die("index file corrupt"); + + for (i = 1 ; i < argc ; i++) { + const char *arg = argv[i]; + + if (*arg != '-') + break; + if (!strcmp(arg, "--")) { + i++; + break; + } + if (!strcmp(arg, "-n")) { + show_only = 1; + continue; + } + if (!strcmp(arg, "-v")) { + verbose = 1; + continue; + } + if (!strcmp(arg, "-f")) { + force = 1; + continue; + } + die(builtin_rm_usage); + } + pathspec = get_pathspec(prefix, argv + i); + + seen = NULL; + if (pathspec) { + for (i = 0; pathspec[i] ; i++) + /* nothing */; + seen = xmalloc(i); + memset(seen, 0, i); + } + + for (i = 0; i < active_nr; i++) { + struct cache_entry *ce = active_cache[i]; + if (!match_pathspec(pathspec, ce->name, ce_namelen(ce), 0, seen)) + continue; + add_list(ce->name); + } + + if (pathspec) { + const char *match; + for (i = 0; (match = pathspec[i]) != NULL ; i++) { + if (*match && !seen[i]) + die("pathspec '%s' did not match any files", match); + } + } + + /* + * First remove the names from the index: we won't commit + * the index unless all of them succeed + */ + for (i = 0; i < list.nr; i++) { + const char *path = list.name[i]; + printf("rm '%s'\n", path); + + if (remove_file_from_cache(path)) + die("git rm: unable to remove %s", path); + cache_tree_invalidate_path(active_cache_tree, path); + } + + /* + * Then, if we used "-f", remove the filenames from the + * workspace. If we fail to remove the first one, we + * abort the "git rm" (but once we've successfully removed + * any file at all, we'll go ahead and commit to it all: + * by then we've already committed ourself and can't fail + * in the middle) + */ + if (force) { + int removed = 0; + for (i = 0; i < list.nr; i++) { + const char *path = list.name[i]; + if (!remove_file(path)) { + removed = 1; + continue; + } + if (!removed) + die("git rm: %s: %s", path, strerror(errno)); + } + } + + if (active_cache_changed) { + if (write_cache(newfd, active_cache, active_nr) || + commit_index_file(&cache_file)) + die("Unable to write new index file"); + } + + return 0; +} diff --git a/tar-tree.c b/builtin-tar-tree.c index 33087366c3..e97e0af985 100644 --- a/tar-tree.c +++ b/builtin-tar-tree.c @@ -7,11 +7,14 @@ #include "commit.h" #include "strbuf.h" #include "tar.h" +#include "builtin.h" +#include "pkt-line.h" #define RECORDSIZE (512) #define BLOCKSIZE (RECORDSIZE * 20) -static const char tar_tree_usage[] = "git-tar-tree <key> [basedir]"; +static const char tar_tree_usage[] = +"git-tar-tree [--remote=<repo>] <ent> [basedir]"; static char block[BLOCKSIZE]; static unsigned long offset; @@ -301,7 +304,7 @@ static void traverse_tree(struct tree_desc *tree, struct strbuf *path) } } -int main(int argc, char **argv) +int generate_tar(int argc, const char **argv) { unsigned char sha1[20], tree_sha1[20]; struct commit *commit; @@ -348,3 +351,58 @@ int main(int argc, char **argv) free(current_path.buf); return 0; } + +static const char *exec = "git-upload-tar"; + +static int remote_tar(int argc, const char **argv) +{ + int fd[2], ret, len; + pid_t pid; + char buf[1024]; + char *url; + + if (argc < 3 || 4 < argc) + usage(tar_tree_usage); + + /* --remote=<repo> */ + url = strdup(argv[1]+9); + pid = git_connect(fd, url, exec); + if (pid < 0) + return 1; + + packet_write(fd[1], "want %s\n", argv[2]); + if (argv[3]) + packet_write(fd[1], "base %s\n", argv[3]); + packet_flush(fd[1]); + + len = packet_read_line(fd[0], buf, sizeof(buf)); + if (!len) + die("git-tar-tree: expected ACK/NAK, got EOF"); + if (buf[len-1] == '\n') + buf[--len] = 0; + if (strcmp(buf, "ACK")) { + if (5 < len && !strncmp(buf, "NACK ", 5)) + die("git-tar-tree: NACK %s", buf + 5); + die("git-tar-tree: protocol error"); + } + /* expect a flush */ + len = packet_read_line(fd[0], buf, sizeof(buf)); + if (len) + die("git-tar-tree: expected a flush"); + + /* Now, start reading from fd[0] and spit it out to stdout */ + ret = copy_fd(fd[0], 1); + close(fd[0]); + + ret |= finish_connect(pid); + return !!ret; +} + +int cmd_tar_tree(int argc, const char **argv, char **envp) +{ + if (argc < 2) + usage(tar_tree_usage); + if (!strncmp("--remote=", argv[1], 9)) + return remote_tar(argc, argv); + return generate_tar(argc, argv); +} diff --git a/builtin-upload-tar.c b/builtin-upload-tar.c new file mode 100644 index 0000000000..d4fa7b56c3 --- /dev/null +++ b/builtin-upload-tar.c @@ -0,0 +1,74 @@ +/* + * Copyright (c) 2006 Junio C Hamano + */ +#include "cache.h" +#include "pkt-line.h" +#include "exec_cmd.h" +#include "builtin.h" + +static const char upload_tar_usage[] = "git-upload-tar <repo>"; + +static int nak(const char *reason) +{ + packet_write(1, "NACK %s\n", reason); + packet_flush(1); + return 1; +} + +int cmd_upload_tar(int argc, const char **argv, char **envp) +{ + int len; + const char *dir = argv[1]; + char buf[8192]; + unsigned char sha1[20]; + char *base = NULL; + char hex[41]; + int ac; + const char *av[4]; + + if (argc != 2) + usage(upload_tar_usage); + if (strlen(dir) < sizeof(buf)-1) + strcpy(buf, dir); /* enter-repo smudges its argument */ + else + packet_write(1, "NACK insanely long repository name %s\n", dir); + if (!enter_repo(buf, 0)) { + packet_write(1, "NACK not a git archive %s\n", dir); + packet_flush(1); + return 1; + } + + len = packet_read_line(0, buf, sizeof(buf)); + if (len < 5 || strncmp("want ", buf, 5)) + return nak("expected want"); + if (buf[len-1] == '\n') + buf[--len] = 0; + if (get_sha1(buf + 5, sha1)) + return nak("expected sha1"); + strcpy(hex, sha1_to_hex(sha1)); + + len = packet_read_line(0, buf, sizeof(buf)); + if (len) { + if (len < 5 || strncmp("base ", buf, 5)) + return nak("expected (optional) base"); + if (buf[len-1] == '\n') + buf[--len] = 0; + base = strdup(buf + 5); + len = packet_read_line(0, buf, sizeof(buf)); + } + if (len) + return nak("expected flush"); + + packet_write(1, "ACK\n"); + packet_flush(1); + + ac = 0; + av[ac++] = "tar-tree"; + av[ac++] = hex; + if (base) + av[ac++] = base; + av[ac++] = NULL; + execv_git_cmd(av); + /* should it return that is an error */ + return 1; +} @@ -25,8 +25,12 @@ extern int cmd_count_objects(int argc, const char **argv, char **envp); extern int cmd_push(int argc, const char **argv, char **envp); extern int cmd_grep(int argc, const char **argv, char **envp); +extern int cmd_rm(int argc, const char **argv, char **envp); +extern int cmd_add(int argc, const char **argv, char **envp); extern int cmd_rev_list(int argc, const char **argv, char **envp); extern int cmd_check_ref_format(int argc, const char **argv, char **envp); extern int cmd_init_db(int argc, const char **argv, char **envp); +extern int cmd_tar_tree(int argc, const char **argv, char **envp); +extern int cmd_upload_tar(int argc, const char **argv, char **envp); #endif 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" @@ -142,6 +143,7 @@ extern void verify_non_filename(const char *prefix, const char *name); /* Initialize and use the cache information */ extern int read_cache(void); extern int write_cache(int newfd, struct cache_entry **cache, int entries); +extern int verify_path(const char *path); extern int cache_name_pos(const char *name, int namelen); #define ADD_CACHE_OK_TO_ADD 1 /* Ok to add */ #define ADD_CACHE_OK_TO_REPLACE 2 /* Ok to replace file/directory */ diff --git a/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; @@ -0,0 +1,401 @@ +/* + * This handles recursive filename detection with exclude + * files, index knowledge etc.. + * + * Copyright (C) Linus Torvalds, 2005-2006 + * Junio Hamano, 2005-2006 + */ +#include <dirent.h> +#include <fnmatch.h> + +#include "cache.h" +#include "dir.h" + +int common_prefix(const char **pathspec) +{ + const char *path, *slash, *next; + int prefix; + + if (!pathspec) + return 0; + + path = *pathspec; + slash = strrchr(path, '/'); + if (!slash) + return 0; + + prefix = slash - path + 1; + while ((next = *++pathspec) != NULL) { + int len = strlen(next); + if (len >= prefix && !memcmp(path, next, len)) + continue; + for (;;) { + if (!len) + return 0; + if (next[--len] != '/') + continue; + if (memcmp(path, next, len+1)) + continue; + prefix = len + 1; + break; + } + } + return prefix; +} + +static int match_one(const char *match, const char *name, int namelen) +{ + int matchlen; + + /* If the match was just the prefix, we matched */ + matchlen = strlen(match); + if (!matchlen) + return 1; + + /* + * If we don't match the matchstring exactly, + * we need to match by fnmatch + */ + if (strncmp(match, name, matchlen)) + return !fnmatch(match, name, 0); + + /* + * If we did match the string exactly, we still + * need to make sure that it happened on a path + * component boundary (ie either the last character + * of the match was '/', or the next character of + * the name was '/' or the terminating NUL. + */ + return match[matchlen-1] == '/' || + name[matchlen] == '/' || + !name[matchlen]; +} + +int match_pathspec(const char **pathspec, const char *name, int namelen, int prefix, char *seen) +{ + int retval; + const char *match; + + name += prefix; + namelen -= prefix; + + for (retval = 0; (match = *pathspec++) != NULL; seen++) { + if (retval & *seen) + continue; + match += prefix; + if (match_one(match, name, namelen)) { + retval = 1; + *seen = 1; + } + } + return retval; +} + +void add_exclude(const char *string, const char *base, + int baselen, struct exclude_list *which) +{ + struct exclude *x = xmalloc(sizeof (*x)); + + x->pattern = string; + x->base = base; + x->baselen = baselen; + if (which->nr == which->alloc) { + which->alloc = alloc_nr(which->alloc); + which->excludes = realloc(which->excludes, + which->alloc * sizeof(x)); + } + which->excludes[which->nr++] = x; +} + +static int add_excludes_from_file_1(const char *fname, + const char *base, + int baselen, + struct exclude_list *which) +{ + int fd, i; + long size; + char *buf, *entry; + + fd = open(fname, O_RDONLY); + if (fd < 0) + goto err; + size = lseek(fd, 0, SEEK_END); + if (size < 0) + goto err; + lseek(fd, 0, SEEK_SET); + if (size == 0) { + close(fd); + return 0; + } + buf = xmalloc(size+1); + if (read(fd, buf, size) != size) + goto err; + close(fd); + + buf[size++] = '\n'; + entry = buf; + for (i = 0; i < size; i++) { + if (buf[i] == '\n') { + if (entry != buf + i && entry[0] != '#') { + buf[i - (i && buf[i-1] == '\r')] = 0; + add_exclude(entry, base, baselen, which); + } + entry = buf + i + 1; + } + } + return 0; + + err: + if (0 <= fd) + close(fd); + return -1; +} + +void add_excludes_from_file(struct dir_struct *dir, const char *fname) +{ + if (add_excludes_from_file_1(fname, "", 0, + &dir->exclude_list[EXC_FILE]) < 0) + die("cannot use %s as an exclude file", fname); +} + +static int push_exclude_per_directory(struct dir_struct *dir, const char *base, int baselen) +{ + char exclude_file[PATH_MAX]; + struct exclude_list *el = &dir->exclude_list[EXC_DIRS]; + int current_nr = el->nr; + + if (dir->exclude_per_dir) { + memcpy(exclude_file, base, baselen); + strcpy(exclude_file + baselen, dir->exclude_per_dir); + add_excludes_from_file_1(exclude_file, base, baselen, el); + } + return current_nr; +} + +static void pop_exclude_per_directory(struct dir_struct *dir, int stk) +{ + struct exclude_list *el = &dir->exclude_list[EXC_DIRS]; + + while (stk < el->nr) + free(el->excludes[--el->nr]); +} + +/* Scan the list and let the last match determines the fate. + * Return 1 for exclude, 0 for include and -1 for undecided. + */ +static int excluded_1(const char *pathname, + int pathlen, + struct exclude_list *el) +{ + int i; + + if (el->nr) { + for (i = el->nr - 1; 0 <= i; i--) { + struct exclude *x = el->excludes[i]; + const char *exclude = x->pattern; + int to_exclude = 1; + + if (*exclude == '!') { + to_exclude = 0; + exclude++; + } + + if (!strchr(exclude, '/')) { + /* match basename */ + const char *basename = strrchr(pathname, '/'); + basename = (basename) ? basename+1 : pathname; + if (fnmatch(exclude, basename, 0) == 0) + return to_exclude; + } + else { + /* match with FNM_PATHNAME: + * exclude has base (baselen long) implicitly + * in front of it. + */ + int baselen = x->baselen; + if (*exclude == '/') + exclude++; + + if (pathlen < baselen || + (baselen && pathname[baselen-1] != '/') || + strncmp(pathname, x->base, baselen)) + continue; + + if (fnmatch(exclude, pathname+baselen, + FNM_PATHNAME) == 0) + return to_exclude; + } + } + } + return -1; /* undecided */ +} + +int excluded(struct dir_struct *dir, const char *pathname) +{ + int pathlen = strlen(pathname); + int st; + + for (st = EXC_CMDL; st <= EXC_FILE; st++) { + switch (excluded_1(pathname, pathlen, &dir->exclude_list[st])) { + case 0: + return 0; + case 1: + return 1; + } + } + return 0; +} + +static void add_name(struct dir_struct *dir, const char *pathname, int len) +{ + struct dir_entry *ent; + + if (cache_name_pos(pathname, len) >= 0) + return; + + if (dir->nr == dir->alloc) { + int alloc = alloc_nr(dir->alloc); + dir->alloc = alloc; + dir->entries = xrealloc(dir->entries, alloc*sizeof(ent)); + } + ent = xmalloc(sizeof(*ent) + len + 1); + ent->len = len; + memcpy(ent->name, pathname, len); + ent->name[len] = 0; + dir->entries[dir->nr++] = ent; +} + +static int dir_exists(const char *dirname, int len) +{ + int pos = cache_name_pos(dirname, len); + if (pos >= 0) + return 1; + pos = -pos-1; + if (pos >= active_nr) /* can't */ + return 0; + return !strncmp(active_cache[pos]->name, dirname, len); +} + +/* + * Read a directory tree. We currently ignore anything but + * directories, regular files and symlinks. That's because git + * doesn't handle them at all yet. Maybe that will change some + * day. + * + * Also, we ignore the name ".git" (even if it is not a directory). + * That likely will not change. + */ +static int read_directory_recursive(struct dir_struct *dir, const char *path, const char *base, int baselen) +{ + DIR *fdir = opendir(path); + int contents = 0; + + if (fdir) { + int exclude_stk; + struct dirent *de; + char fullname[MAXPATHLEN + 1]; + memcpy(fullname, base, baselen); + + exclude_stk = push_exclude_per_directory(dir, base, baselen); + + while ((de = readdir(fdir)) != NULL) { + int len; + + if ((de->d_name[0] == '.') && + (de->d_name[1] == 0 || + !strcmp(de->d_name + 1, ".") || + !strcmp(de->d_name + 1, "git"))) + continue; + len = strlen(de->d_name); + memcpy(fullname + baselen, de->d_name, len+1); + if (excluded(dir, fullname) != dir->show_ignored) { + if (!dir->show_ignored || DTYPE(de) != DT_DIR) { + continue; + } + } + + switch (DTYPE(de)) { + struct stat st; + int subdir, rewind_base; + default: + continue; + case DT_UNKNOWN: + if (lstat(fullname, &st)) + continue; + if (S_ISREG(st.st_mode) || S_ISLNK(st.st_mode)) + break; + if (!S_ISDIR(st.st_mode)) + continue; + /* fallthrough */ + case DT_DIR: + memcpy(fullname + baselen + len, "/", 2); + len++; + rewind_base = dir->nr; + subdir = read_directory_recursive(dir, fullname, fullname, + baselen + len); + if (dir->show_other_directories && + (subdir || !dir->hide_empty_directories) && + !dir_exists(fullname, baselen + len)) { + // Rewind the read subdirectory + while (dir->nr > rewind_base) + free(dir->entries[--dir->nr]); + break; + } + contents += subdir; + continue; + case DT_REG: + case DT_LNK: + break; + } + add_name(dir, fullname, baselen + len); + contents++; + } + closedir(fdir); + + pop_exclude_per_directory(dir, exclude_stk); + } + + return contents; +} + +static int cmp_name(const void *p1, const void *p2) +{ + const struct dir_entry *e1 = *(const struct dir_entry **)p1; + const struct dir_entry *e2 = *(const struct dir_entry **)p2; + + return cache_name_compare(e1->name, e1->len, + e2->name, e2->len); +} + +int read_directory(struct dir_struct *dir, const char *path, const char *base, int baselen) +{ + /* + * Make sure to do the per-directory exclude for all the + * directories leading up to our base. + */ + if (baselen) { + if (dir->exclude_per_dir) { + char *p, *pp = xmalloc(baselen+1); + memcpy(pp, base, baselen+1); + p = pp; + while (1) { + char save = *p; + *p = 0; + push_exclude_per_directory(dir, pp, p-pp); + *p++ = save; + if (!save) + break; + p = strchr(p, '/'); + if (p) + p++; + else + p = pp + baselen; + } + free(pp); + } + } + + read_directory_recursive(dir, path, base, baselen); + qsort(dir->entries, dir->nr, sizeof(struct dir_entry *), cmp_name); + return dir->nr; +} @@ -0,0 +1,51 @@ +#ifndef DIR_H +#define DIR_H + +/* + * We maintain three exclude pattern lists: + * EXC_CMDL lists patterns explicitly given on the command line. + * EXC_DIRS lists patterns obtained from per-directory ignore files. + * EXC_FILE lists patterns from fallback ignore files. + */ +#define EXC_CMDL 0 +#define EXC_DIRS 1 +#define EXC_FILE 2 + + +struct dir_entry { + int len; + char name[FLEX_ARRAY]; /* more */ +}; + +struct exclude_list { + int nr; + int alloc; + struct exclude { + const char *pattern; + const char *base; + int baselen; + } **excludes; +}; + +struct dir_struct { + int nr, alloc; + unsigned int show_ignored:1, + show_other_directories:1, + hide_empty_directories:1; + struct dir_entry **entries; + + /* Exclude info */ + const char *exclude_per_dir; + struct exclude_list exclude_list[3]; +}; + +extern int common_prefix(const char **pathspec); +extern int match_pathspec(const char **pathspec, const char *name, int namelen, int prefix, char *seen); + +extern int read_directory(struct dir_struct *, const char *path, const char *base, int baselen); +extern int excluded(struct dir_struct *, const char *); +extern void add_excludes_from_file(struct dir_struct *, const char *fname); +extern void add_exclude(const char *string, const char *base, + int baselen, struct exclude_list *which); + +#endif 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/git-add.sh b/git-add.sh deleted file mode 100755 index d6a4bc7d09..0000000000 --- a/git-add.sh +++ /dev/null @@ -1,56 +0,0 @@ -#!/bin/sh - -USAGE='[-n] [-v] <file>...' -SUBDIRECTORY_OK='Yes' -. git-sh-setup - -show_only= -verbose= -while : ; do - case "$1" in - -n) - show_only=true - ;; - -v) - verbose=--verbose - ;; - --) - shift - break - ;; - -*) - usage - ;; - *) - break - ;; - esac - shift -done - -# Check misspelled pathspec -case "$#" in -0) ;; -*) - git-ls-files --error-unmatch --others --cached -- "$@" >/dev/null || { - echo >&2 "Maybe you misspelled it?" - exit 1 - } - ;; -esac - -if test -f "$GIT_DIR/info/exclude" -then - git-ls-files -z \ - --exclude-from="$GIT_DIR/info/exclude" \ - --others --exclude-per-directory=.gitignore -- "$@" -else - git-ls-files -z \ - --others --exclude-per-directory=.gitignore -- "$@" -fi | -case "$show_only" in -true) - xargs -0 echo ;; -*) - git-update-index --add $verbose -z --stdin ;; -esac diff --git a/git-rm.sh b/git-rm.sh deleted file mode 100755 index fda4541c76..0000000000 --- a/git-rm.sh +++ /dev/null @@ -1,70 +0,0 @@ -#!/bin/sh - -USAGE='[-f] [-n] [-v] [--] <file>...' -SUBDIRECTORY_OK='Yes' -. git-sh-setup - -remove_files= -show_only= -verbose= -while : ; do - case "$1" in - -f) - remove_files=true - ;; - -n) - show_only=true - ;; - -v) - verbose=--verbose - ;; - --) - shift; break - ;; - -*) - usage - ;; - *) - break - ;; - esac - shift -done - -# This is typo-proofing. If some paths match and some do not, we want -# to do nothing. -case "$#" in -0) ;; -*) - git-ls-files --error-unmatch -- "$@" >/dev/null || { - echo >&2 "Maybe you misspelled it?" - exit 1 - } - ;; -esac - -if test -f "$GIT_DIR/info/exclude" -then - git-ls-files -z \ - --exclude-from="$GIT_DIR/info/exclude" \ - --exclude-per-directory=.gitignore -- "$@" -else - git-ls-files -z \ - --exclude-per-directory=.gitignore -- "$@" -fi | -case "$show_only,$remove_files" in -true,*) - xargs -0 echo - ;; -*,true) - xargs -0 sh -c " - while [ \$# -gt 0 ]; do - file=\$1; shift - rm -- \"\$file\" && git-update-index --remove $verbose \"\$file\" - done - " inline - ;; -*) - git-update-index --force-remove $verbose -z --stdin - ;; -esac @@ -51,8 +51,12 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "count-objects", cmd_count_objects }, { "diff", cmd_diff }, { "grep", cmd_grep }, + { "rm", cmd_rm }, + { "add", cmd_add }, { "rev-list", cmd_rev_list }, { "init-db", cmd_init_db }, + { "tar-tree", cmd_tar_tree }, + { "upload-tar", cmd_upload_tar }, { "check-ref-format", cmd_check_ref_format } }; int i; diff --git a/ls-files.c b/ls-files.c index 4a4af1ca3b..dfe1481a35 100644 --- a/ls-files.c +++ b/ls-files.c @@ -5,23 +5,20 @@ * * Copyright (C) Linus Torvalds, 2005 */ -#include <dirent.h> #include <fnmatch.h> #include "cache.h" #include "quote.h" +#include "dir.h" static int abbrev = 0; static int show_deleted = 0; static int show_cached = 0; static int show_others = 0; -static int show_ignored = 0; static int show_stage = 0; static int show_unmerged = 0; static int show_modified = 0; static int show_killed = 0; -static int show_other_directories = 0; -static int hide_empty_directories = 0; static int show_valid_bit = 0; static int line_terminator = '\n'; @@ -38,309 +35,6 @@ static const char *tag_other = ""; static const char *tag_killed = ""; static const char *tag_modified = ""; -static const char *exclude_per_dir = NULL; - -/* We maintain three exclude pattern lists: - * EXC_CMDL lists patterns explicitly given on the command line. - * EXC_DIRS lists patterns obtained from per-directory ignore files. - * EXC_FILE lists patterns from fallback ignore files. - */ -#define EXC_CMDL 0 -#define EXC_DIRS 1 -#define EXC_FILE 2 -static struct exclude_list { - int nr; - int alloc; - struct exclude { - const char *pattern; - const char *base; - int baselen; - } **excludes; -} exclude_list[3]; - -static void add_exclude(const char *string, const char *base, - int baselen, struct exclude_list *which) -{ - struct exclude *x = xmalloc(sizeof (*x)); - - x->pattern = string; - x->base = base; - x->baselen = baselen; - if (which->nr == which->alloc) { - which->alloc = alloc_nr(which->alloc); - which->excludes = realloc(which->excludes, - which->alloc * sizeof(x)); - } - which->excludes[which->nr++] = x; -} - -static int add_excludes_from_file_1(const char *fname, - const char *base, - int baselen, - struct exclude_list *which) -{ - int fd, i; - long size; - char *buf, *entry; - - fd = open(fname, O_RDONLY); - if (fd < 0) - goto err; - size = lseek(fd, 0, SEEK_END); - if (size < 0) - goto err; - lseek(fd, 0, SEEK_SET); - if (size == 0) { - close(fd); - return 0; - } - buf = xmalloc(size+1); - if (read(fd, buf, size) != size) - goto err; - close(fd); - - buf[size++] = '\n'; - entry = buf; - for (i = 0; i < size; i++) { - if (buf[i] == '\n') { - if (entry != buf + i && entry[0] != '#') { - buf[i - (i && buf[i-1] == '\r')] = 0; - add_exclude(entry, base, baselen, which); - } - entry = buf + i + 1; - } - } - return 0; - - err: - if (0 <= fd) - close(fd); - return -1; -} - -static void add_excludes_from_file(const char *fname) -{ - if (add_excludes_from_file_1(fname, "", 0, - &exclude_list[EXC_FILE]) < 0) - die("cannot use %s as an exclude file", fname); -} - -static int push_exclude_per_directory(const char *base, int baselen) -{ - char exclude_file[PATH_MAX]; - struct exclude_list *el = &exclude_list[EXC_DIRS]; - int current_nr = el->nr; - - if (exclude_per_dir) { - memcpy(exclude_file, base, baselen); - strcpy(exclude_file + baselen, exclude_per_dir); - add_excludes_from_file_1(exclude_file, base, baselen, el); - } - return current_nr; -} - -static void pop_exclude_per_directory(int stk) -{ - struct exclude_list *el = &exclude_list[EXC_DIRS]; - - while (stk < el->nr) - free(el->excludes[--el->nr]); -} - -/* Scan the list and let the last match determines the fate. - * Return 1 for exclude, 0 for include and -1 for undecided. - */ -static int excluded_1(const char *pathname, - int pathlen, - struct exclude_list *el) -{ - int i; - - if (el->nr) { - for (i = el->nr - 1; 0 <= i; i--) { - struct exclude *x = el->excludes[i]; - const char *exclude = x->pattern; - int to_exclude = 1; - - if (*exclude == '!') { - to_exclude = 0; - exclude++; - } - - if (!strchr(exclude, '/')) { - /* match basename */ - const char *basename = strrchr(pathname, '/'); - basename = (basename) ? basename+1 : pathname; - if (fnmatch(exclude, basename, 0) == 0) - return to_exclude; - } - else { - /* match with FNM_PATHNAME: - * exclude has base (baselen long) implicitly - * in front of it. - */ - int baselen = x->baselen; - if (*exclude == '/') - exclude++; - - if (pathlen < baselen || - (baselen && pathname[baselen-1] != '/') || - strncmp(pathname, x->base, baselen)) - continue; - - if (fnmatch(exclude, pathname+baselen, - FNM_PATHNAME) == 0) - return to_exclude; - } - } - } - return -1; /* undecided */ -} - -static int excluded(const char *pathname) -{ - int pathlen = strlen(pathname); - int st; - - for (st = EXC_CMDL; st <= EXC_FILE; st++) { - switch (excluded_1(pathname, pathlen, &exclude_list[st])) { - case 0: - return 0; - case 1: - return 1; - } - } - return 0; -} - -struct nond_on_fs { - int len; - char name[FLEX_ARRAY]; /* more */ -}; - -static struct nond_on_fs **dir; -static int nr_dir; -static int dir_alloc; - -static void add_name(const char *pathname, int len) -{ - struct nond_on_fs *ent; - - if (cache_name_pos(pathname, len) >= 0) - return; - - if (nr_dir == dir_alloc) { - dir_alloc = alloc_nr(dir_alloc); - dir = xrealloc(dir, dir_alloc*sizeof(ent)); - } - ent = xmalloc(sizeof(*ent) + len + 1); - ent->len = len; - memcpy(ent->name, pathname, len); - ent->name[len] = 0; - dir[nr_dir++] = ent; -} - -static int dir_exists(const char *dirname, int len) -{ - int pos = cache_name_pos(dirname, len); - if (pos >= 0) - return 1; - pos = -pos-1; - if (pos >= active_nr) /* can't */ - return 0; - return !strncmp(active_cache[pos]->name, dirname, len); -} - -/* - * Read a directory tree. We currently ignore anything but - * directories, regular files and symlinks. That's because git - * doesn't handle them at all yet. Maybe that will change some - * day. - * - * Also, we ignore the name ".git" (even if it is not a directory). - * That likely will not change. - */ -static int read_directory(const char *path, const char *base, int baselen) -{ - DIR *fdir = opendir(path); - int contents = 0; - - if (fdir) { - int exclude_stk; - struct dirent *de; - char fullname[MAXPATHLEN + 1]; - memcpy(fullname, base, baselen); - - exclude_stk = push_exclude_per_directory(base, baselen); - - while ((de = readdir(fdir)) != NULL) { - int len; - - if ((de->d_name[0] == '.') && - (de->d_name[1] == 0 || - !strcmp(de->d_name + 1, ".") || - !strcmp(de->d_name + 1, "git"))) - continue; - len = strlen(de->d_name); - memcpy(fullname + baselen, de->d_name, len+1); - if (excluded(fullname) != show_ignored) { - if (!show_ignored || DTYPE(de) != DT_DIR) { - continue; - } - } - - switch (DTYPE(de)) { - struct stat st; - int subdir, rewind_base; - default: - continue; - case DT_UNKNOWN: - if (lstat(fullname, &st)) - continue; - if (S_ISREG(st.st_mode) || S_ISLNK(st.st_mode)) - break; - if (!S_ISDIR(st.st_mode)) - continue; - /* fallthrough */ - case DT_DIR: - memcpy(fullname + baselen + len, "/", 2); - len++; - rewind_base = nr_dir; - subdir = read_directory(fullname, fullname, - baselen + len); - if (show_other_directories && - (subdir || !hide_empty_directories) && - !dir_exists(fullname, baselen + len)) { - // Rewind the read subdirectory - while (nr_dir > rewind_base) - free(dir[--nr_dir]); - break; - } - contents += subdir; - continue; - case DT_REG: - case DT_LNK: - break; - } - add_name(fullname, baselen + len); - contents++; - } - closedir(fdir); - - pop_exclude_per_directory(exclude_stk); - } - - return contents; -} - -static int cmp_name(const void *p1, const void *p2) -{ - const struct nond_on_fs *e1 = *(const struct nond_on_fs **)p1; - const struct nond_on_fs *e2 = *(const struct nond_on_fs **)p2; - - return cache_name_compare(e1->name, e1->len, - e2->name, e2->len); -} /* * Match a pathspec against a filename. The first "len" characters @@ -377,7 +71,7 @@ static int match(const char **spec, char *ps_matched, return 0; } -static void show_dir_entry(const char *tag, struct nond_on_fs *ent) +static void show_dir_entry(const char *tag, struct dir_entry *ent) { int len = prefix_len; int offset = prefix_offset; @@ -393,14 +87,14 @@ static void show_dir_entry(const char *tag, struct nond_on_fs *ent) putchar(line_terminator); } -static void show_other_files(void) +static void show_other_files(struct dir_struct *dir) { int i; - for (i = 0; i < nr_dir; i++) { + for (i = 0; i < dir->nr; i++) { /* We should not have a matching entry, but we * may have an unmerged entry for this path. */ - struct nond_on_fs *ent = dir[i]; + struct dir_entry *ent = dir->entries[i]; int pos = cache_name_pos(ent->name, ent->len); struct cache_entry *ce; if (0 <= pos) @@ -416,11 +110,11 @@ static void show_other_files(void) } } -static void show_killed_files(void) +static void show_killed_files(struct dir_struct *dir) { int i; - for (i = 0; i < nr_dir; i++) { - struct nond_on_fs *ent = dir[i]; + for (i = 0; i < dir->nr; i++) { + struct dir_entry *ent = dir->entries[i]; char *cp, *sp; int pos, len, killed = 0; @@ -461,7 +155,7 @@ static void show_killed_files(void) } } if (killed) - show_dir_entry(tag_killed, dir[i]); + show_dir_entry(tag_killed, dir->entries[i]); } } @@ -512,7 +206,7 @@ static void show_ce_entry(const char *tag, struct cache_entry *ce) } } -static void show_files(void) +static void show_files(struct dir_struct *dir) { int i; @@ -521,39 +215,18 @@ static void show_files(void) const char *path = ".", *base = ""; int baselen = prefix_len; - if (baselen) { + if (baselen) path = base = prefix; - if (exclude_per_dir) { - char *p, *pp = xmalloc(baselen+1); - memcpy(pp, prefix, baselen+1); - p = pp; - while (1) { - char save = *p; - *p = 0; - push_exclude_per_directory(pp, p-pp); - *p++ = save; - if (!save) - break; - p = strchr(p, '/'); - if (p) - p++; - else - p = pp + baselen; - } - free(pp); - } - } - read_directory(path, base, baselen); - qsort(dir, nr_dir, sizeof(struct nond_on_fs *), cmp_name); + read_directory(dir, path, base, baselen); if (show_others) - show_other_files(); + show_other_files(dir); if (show_killed) - show_killed_files(); + show_killed_files(dir); } if (show_cached | show_stage) { for (i = 0; i < active_nr; i++) { struct cache_entry *ce = active_cache[i]; - if (excluded(ce->name) != show_ignored) + if (excluded(dir, ce->name) != dir->show_ignored) continue; if (show_unmerged && !ce_stage(ce)) continue; @@ -565,7 +238,7 @@ static void show_files(void) struct cache_entry *ce = active_cache[i]; struct stat st; int err; - if (excluded(ce->name) != show_ignored) + if (excluded(dir, ce->name) != dir->show_ignored) continue; err = lstat(ce->name, &st); if (show_deleted && err) @@ -652,7 +325,9 @@ int main(int argc, const char **argv) { int i; int exc_given = 0; + struct dir_struct dir; + memset(&dir, 0, sizeof(dir)); prefix = setup_git_directory(); if (prefix) prefix_offset = strlen(prefix); @@ -697,7 +372,7 @@ int main(int argc, const char **argv) continue; } if (!strcmp(arg, "-i") || !strcmp(arg, "--ignored")) { - show_ignored = 1; + dir.show_ignored = 1; continue; } if (!strcmp(arg, "-s") || !strcmp(arg, "--stage")) { @@ -709,11 +384,11 @@ int main(int argc, const char **argv) continue; } if (!strcmp(arg, "--directory")) { - show_other_directories = 1; + dir.show_other_directories = 1; continue; } if (!strcmp(arg, "--no-empty-directory")) { - hide_empty_directories = 1; + dir.hide_empty_directories = 1; continue; } if (!strcmp(arg, "-u") || !strcmp(arg, "--unmerged")) { @@ -726,27 +401,27 @@ int main(int argc, const char **argv) } if (!strcmp(arg, "-x") && i+1 < argc) { exc_given = 1; - add_exclude(argv[++i], "", 0, &exclude_list[EXC_CMDL]); + add_exclude(argv[++i], "", 0, &dir.exclude_list[EXC_CMDL]); continue; } if (!strncmp(arg, "--exclude=", 10)) { exc_given = 1; - add_exclude(arg+10, "", 0, &exclude_list[EXC_CMDL]); + add_exclude(arg+10, "", 0, &dir.exclude_list[EXC_CMDL]); continue; } if (!strcmp(arg, "-X") && i+1 < argc) { exc_given = 1; - add_excludes_from_file(argv[++i]); + add_excludes_from_file(&dir, argv[++i]); continue; } if (!strncmp(arg, "--exclude-from=", 15)) { exc_given = 1; - add_excludes_from_file(arg+15); + add_excludes_from_file(&dir, arg+15); continue; } if (!strncmp(arg, "--exclude-per-directory=", 24)) { exc_given = 1; - exclude_per_dir = arg + 24; + dir.exclude_per_dir = arg + 24; continue; } if (!strcmp(arg, "--full-name")) { @@ -788,7 +463,7 @@ int main(int argc, const char **argv) ps_matched = xcalloc(1, num); } - if (show_ignored && !exc_given) { + if (dir.show_ignored && !exc_given) { fprintf(stderr, "%s: --ignored needs some exclude pattern\n", argv[0]); exit(1); @@ -802,7 +477,7 @@ int main(int argc, const char **argv) read_cache(); if (prefix) prune_cache(); - show_files(); + show_files(&dir); if (ps_matched) { /* We need to make sure all pathspec matched otherwise diff --git a/read-cache.c b/read-cache.c index b95edcc14c..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 @@ -332,6 +347,70 @@ int ce_path_match(const struct cache_entry *ce, const char **pathspec) } /* + * We fundamentally don't like some paths: we don't want + * dot or dot-dot anywhere, and for obvious reasons don't + * want to recurse into ".git" either. + * + * Also, we don't want double slashes or slashes at the + * end that can make pathnames ambiguous. + */ +static int verify_dotfile(const char *rest) +{ + /* + * The first character was '.', but that + * has already been discarded, we now test + * the rest. + */ + switch (*rest) { + /* "." is not allowed */ + case '\0': case '/': + return 0; + + /* + * ".git" followed by NUL or slash is bad. This + * shares the path end test with the ".." case. + */ + case 'g': + if (rest[1] != 'i') + break; + if (rest[2] != 't') + break; + rest += 2; + /* fallthrough */ + case '.': + if (rest[1] == '\0' || rest[1] == '/') + return 0; + } + return 1; +} + +int verify_path(const char *path) +{ + char c; + + goto inside; + for (;;) { + if (!c) + return 1; + if (c == '/') { +inside: + c = *path++; + switch (c) { + default: + continue; + case '/': case '\0': + break; + case '.': + if (verify_dotfile(path)) + continue; + } + return 0; + } + c = *path++; + } +} + +/* * Do we have another file that has the beginning components being a * proper superset of the name we're trying to add? */ @@ -472,6 +551,8 @@ int add_cache_entry(struct cache_entry *ce, int option) if (!ok_to_add) return -1; + if (!verify_path(ce->name)) + return -1; if (!skip_df_check && check_file_directory_conflict(ce, pos, ok_to_replace)) { @@ -630,6 +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; @@ -678,6 +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: @@ -712,6 +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; @@ -808,5 +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/read-tree.c b/read-tree.c index 82e2a9a4d3..55f7f87133 100644 --- a/read-tree.c +++ b/read-tree.c @@ -9,6 +9,7 @@ #include "object.h" #include "tree.h" +#include "cache-tree.h" #include <sys/time.h> #include <signal.h> @@ -21,6 +22,7 @@ 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; @@ -369,7 +371,8 @@ 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; } @@ -426,6 +429,12 @@ 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. @@ -456,10 +465,13 @@ 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); @@ -474,6 +486,7 @@ 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; } @@ -709,6 +722,28 @@ 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: @@ -723,8 +758,10 @@ 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; @@ -749,6 +786,7 @@ 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) @@ -759,7 +797,40 @@ 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; @@ -804,9 +875,24 @@ int main(int argc, char **argv) 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; @@ -827,7 +913,7 @@ int main(int argc, char **argv) /* "-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"); @@ -849,21 +935,39 @@ int main(int argc, char **argv) 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; } @@ -874,6 +978,18 @@ int main(int argc, char **argv) } 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/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/update-index.c b/update-index.c index 7d6de821e2..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 @@ -120,70 +128,6 @@ static int add_file_to_cache(const char *path) return 0; } -/* - * We fundamentally don't like some paths: we don't want - * dot or dot-dot anywhere, and for obvious reasons don't - * want to recurse into ".git" either. - * - * Also, we don't want double slashes or slashes at the - * end that can make pathnames ambiguous. - */ -static int verify_dotfile(const char *rest) -{ - /* - * The first character was '.', but that - * has already been discarded, we now test - * the rest. - */ - switch (*rest) { - /* "." is not allowed */ - case '\0': case '/': - return 0; - - /* - * ".git" followed by NUL or slash is bad. This - * shares the path end test with the ".." case. - */ - case 'g': - if (rest[1] != 'i') - break; - if (rest[2] != 't') - break; - rest += 2; - /* fallthrough */ - case '.': - if (rest[1] == '\0' || rest[1] == '/') - return 0; - } - return 1; -} - -static int verify_path(const char *path) -{ - char c; - - goto inside; - for (;;) { - if (!c) - return 1; - if (c == '/') { -inside: - c = *path++; - switch (c) { - default: - continue; - case '/': case '\0': - break; - case '.': - if (verify_dotfile(path)) - continue; - } - return 0; - } - c = *path++; - } -} - static int add_cacheinfo(unsigned int mode, const unsigned char *sha1, const char *path, int stage) { @@ -209,6 +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; } @@ -233,6 +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; @@ -254,6 +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)) @@ -332,6 +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 */ @@ -438,6 +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; } |