From: Junio C Hamano Date: Tue, 20 Oct 2015 22:24:00 +0000 (-0700) Subject: Merge branch 'jk/war-on-sprintf' X-Git-Tag: v2.7.0-rc0~87 X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/78891795df91a313fac590dd6cff9d8aace0dc9a?ds=inline;hp=-c Merge branch 'jk/war-on-sprintf' Many allocations that is manually counted (correctly) that are followed by strcpy/sprintf have been replaced with a less error prone constructs such as xstrfmt. Macintosh-specific breakage was noticed and corrected in this reroll. * jk/war-on-sprintf: (70 commits) name-rev: use strip_suffix to avoid magic numbers use strbuf_complete to conditionally append slash fsck: use for_each_loose_file_in_objdir Makefile: drop D_INO_IN_DIRENT build knob fsck: drop inode-sorting code convert strncpy to memcpy notes: document length of fanout path with a constant color: add color_set helper for copying raw colors prefer memcpy to strcpy help: clean up kfmclient munging receive-pack: simplify keep_arg computation avoid sprintf and strcpy with flex arrays use alloc_ref rather than hand-allocating "struct ref" color: add overflow checks for parsing colors drop strcpy in favor of raw sha1_to_hex use sha1_to_hex_r() instead of strcpy daemon: use cld->env_array when re-spawning stat_tracking_info: convert to argv_array http-push: use an argv_array for setup_revisions fetch-pack: use argv_array for index-pack / unpack-objects ... --- 78891795df91a313fac590dd6cff9d8aace0dc9a diff --combined Makefile index 36bc54ccd1,2f350cae35..0d9f5dddbc --- a/Makefile +++ b/Makefile @@@ -74,8 -74,6 +74,6 @@@ all: # Define HAVE_PATHS_H if you have paths.h and want to use the default PATH # it specifies. # - # Define NO_D_INO_IN_DIRENT if you don't have d_ino in your struct dirent. - # # Define NO_D_TYPE_IN_DIRENT if your platform defines DT_UNKNOWN but lacks # d_type in struct dirent (Cygwin 1.5, fixed in Cygwin 1.7). # @@@ -375,9 -373,6 +373,9 @@@ ALL_CFLAGS = $(CPPFLAGS) $(CFLAGS ALL_LDFLAGS = $(LDFLAGS) STRIP ?= strip +# Create as necessary, replace existing, make ranlib unneeded. +ARFLAGS = rcs + # Among the variables below, these: # gitexecdir # template_dir @@@ -905,7 -900,6 +903,7 @@@ BUILTIN_OBJS += builtin/shortlog. BUILTIN_OBJS += builtin/show-branch.o BUILTIN_OBJS += builtin/show-ref.o BUILTIN_OBJS += builtin/stripspace.o +BUILTIN_OBJS += builtin/submodule--helper.o BUILTIN_OBJS += builtin/symbolic-ref.o BUILTIN_OBJS += builtin/tag.o BUILTIN_OBJS += builtin/unpack-file.o @@@ -1164,9 -1158,6 +1162,6 @@@ endi ifdef NO_D_TYPE_IN_DIRENT BASIC_CFLAGS += -DNO_D_TYPE_IN_DIRENT endif - ifdef NO_D_INO_IN_DIRENT - BASIC_CFLAGS += -DNO_D_INO_IN_DIRENT - endif ifdef NO_GECOS_IN_PWENT BASIC_CFLAGS += -DNO_GECOS_IN_PWENT endif @@@ -1469,13 -1460,13 +1464,13 @@@ endi QUIET_SUBDIR0 = +$(MAKE) -C # space to separate -C and subdir QUIET_SUBDIR1 = -ifneq ($(findstring $(MAKEFLAGS),w),w) +ifneq ($(findstring w,$(MAKEFLAGS)),w) PRINT_DIR = --no-print-directory else # "make -w" NO_SUBDIR = : endif -ifneq ($(findstring $(MAKEFLAGS),s),s) +ifneq ($(findstring s,$(MAKEFLAGS)),s) ifndef V QUIET_CC = @echo ' ' CC $@; QUIET_AR = @echo ' ' AR $@; @@@ -1999,13 -1990,13 +1994,13 @@@ $(REMOTE_CURL_PRIMARY): remote-curl.o h $(LIBS) $(CURL_LIBCURL) $(EXPAT_LIBEXPAT) $(LIB_FILE): $(LIB_OBJS) - $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $^ + $(QUIET_AR)$(RM) $@ && $(AR) $(ARFLAGS) $@ $^ $(XDIFF_LIB): $(XDIFF_OBJS) - $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $^ + $(QUIET_AR)$(RM) $@ && $(AR) $(ARFLAGS) $@ $^ $(VCSSVN_LIB): $(VCSSVN_OBJS) - $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $^ + $(QUIET_AR)$(RM) $@ && $(AR) $(ARFLAGS) $@ $^ export DEFAULT_EDITOR DEFAULT_PAGER diff --combined builtin/blame.c index 203a981cd0,e70fb6dac3..6fc7bff9a3 --- a/builtin/blame.c +++ b/builtin/blame.c @@@ -459,12 -459,13 +459,13 @@@ static void queue_blames(struct scorebo static struct origin *make_origin(struct commit *commit, const char *path) { struct origin *o; - o = xcalloc(1, sizeof(*o) + strlen(path) + 1); + size_t pathlen = strlen(path) + 1; + o = xcalloc(1, sizeof(*o) + pathlen); o->commit = commit; o->refcnt = 1; o->next = commit->util; commit->util = o; - strcpy(o->path, path); + memcpy(o->path, path, pathlen); /* includes NUL */ return o; } @@@ -974,10 -975,7 +975,10 @@@ static void pass_blame_to_parent(struc fill_origin_blob(&sb->revs->diffopt, target, &file_o); num_get_patch++; - diff_hunks(&file_p, &file_o, 0, blame_chunk_cb, &d); + if (diff_hunks(&file_p, &file_o, 0, blame_chunk_cb, &d)) + die("unable to generate diff (%s -> %s)", + sha1_to_hex(parent->commit->object.sha1), + sha1_to_hex(target->commit->object.sha1)); /* The rest are the same as the parent */ blame_chunk(&d.dstq, &d.srcq, INT_MAX, d.offset, INT_MAX, parent); *d.dstq = NULL; @@@ -1123,9 -1121,7 +1124,9 @@@ static void find_copy_in_blob(struct sc * file_p partially may match that image. */ memset(split, 0, sizeof(struct blame_entry [3])); - diff_hunks(file_p, &file_o, 1, handle_split_cb, &d); + if (diff_hunks(file_p, &file_o, 1, handle_split_cb, &d)) + die("unable to generate diff (%s)", + sha1_to_hex(parent->commit->object.sha1)); /* remainder, if any, all match the preimage */ handle_split(sb, ent, d.tlno, d.plno, ent->num_lines, parent, split); } @@@ -1371,15 -1367,8 +1372,15 @@@ static void pass_whole_blame(struct sco */ static struct commit_list *first_scapegoat(struct rev_info *revs, struct commit *commit) { - if (!reverse) + if (!reverse) { + if (revs->first_parent_only && + commit->parents && + commit->parents->next) { + free_commit_list(commit->parents->next); + commit->parents->next = NULL; + } return commit->parents; + } return lookup_decoration(&revs->children, &commit->object); } @@@ -1879,9 -1868,9 +1880,9 @@@ static void emit_porcelain(struct score int cnt; const char *cp; struct origin *suspect = ent->suspect; - char hex[41]; + char hex[GIT_SHA1_HEXSZ + 1]; - strcpy(hex, sha1_to_hex(suspect->commit->object.sha1)); + sha1_to_hex_r(hex, suspect->commit->object.sha1); printf("%s %d %d %d\n", hex, ent->s_lno + 1, @@@ -1917,11 -1906,11 +1918,11 @@@ static void emit_other(struct scoreboar const char *cp; struct origin *suspect = ent->suspect; struct commit_info ci; - char hex[41]; + char hex[GIT_SHA1_HEXSZ + 1]; int show_raw_time = !!(opt & OUTPUT_RAW_TIMESTAMP); get_commit_info(suspect->commit, &ci, 1); - strcpy(hex, sha1_to_hex(suspect->commit->object.sha1)); + sha1_to_hex_r(hex, suspect->commit->object.sha1); cp = nth_line(sb, ent->lno); for (cnt = 0; cnt < ent->num_lines; cnt++) { @@@ -2612,6 -2601,7 +2613,6 @@@ parse_done fewer display columns. */ blame_date_width = utf8_strwidth(_("4 years, 11 months ago")) + 1; /* add the null */ break; - case DATE_LOCAL: case DATE_NORMAL: blame_date_width = sizeof("Thu Oct 19 16:00:04 2006 -0700"); break; @@@ -2691,8 -2681,6 +2692,8 @@@ } else if (contents_from) die("--contents and --children do not blend well."); + else if (revs.first_parent_only) + die("combining --first-parent and --reverse is not supported"); else { final_commit_name = prepare_initial(&sb); sb.commits.compare = compare_commits_by_reverse_commit_date; diff --combined builtin/fsck.c index b9a74f0cf6,d50efd5e8c..8b8bb42c51 --- a/builtin/fsck.c +++ b/builtin/fsck.c @@@ -38,16 -38,7 +38,8 @@@ static int show_dangling = 1 #define ERROR_OBJECT 01 #define ERROR_REACHABLE 02 #define ERROR_PACK 04 +#define ERROR_REFS 010 - #ifdef NO_D_INO_IN_DIRENT - #define SORT_DIRENT 0 - #define DIRENT_SORT_HINT(de) 0 - #else - #define SORT_DIRENT 1 - #define DIRENT_SORT_HINT(de) ((de)->d_ino) - #endif - static int fsck_config(const char *var, const char *value, void *cb) { if (strcmp(var, "fsck.skiplist") == 0) { @@@ -374,102 -365,6 +366,6 @@@ static int fsck_obj_buffer(const unsign return fsck_obj(obj); } - /* - * This is the sorting chunk size: make it reasonably - * big so that we can sort well.. - */ - #define MAX_SHA1_ENTRIES (1024) - - struct sha1_entry { - unsigned long ino; - unsigned char sha1[20]; - }; - - static struct { - unsigned long nr; - struct sha1_entry *entry[MAX_SHA1_ENTRIES]; - } sha1_list; - - static int ino_compare(const void *_a, const void *_b) - { - const struct sha1_entry *a = _a, *b = _b; - unsigned long ino1 = a->ino, ino2 = b->ino; - return ino1 < ino2 ? -1 : ino1 > ino2 ? 1 : 0; - } - - static void fsck_sha1_list(void) - { - int i, nr = sha1_list.nr; - - if (SORT_DIRENT) - qsort(sha1_list.entry, nr, - sizeof(struct sha1_entry *), ino_compare); - for (i = 0; i < nr; i++) { - struct sha1_entry *entry = sha1_list.entry[i]; - unsigned char *sha1 = entry->sha1; - - sha1_list.entry[i] = NULL; - if (fsck_sha1(sha1)) - errors_found |= ERROR_OBJECT; - free(entry); - } - sha1_list.nr = 0; - } - - static void add_sha1_list(unsigned char *sha1, unsigned long ino) - { - struct sha1_entry *entry = xmalloc(sizeof(*entry)); - int nr; - - entry->ino = ino; - hashcpy(entry->sha1, sha1); - nr = sha1_list.nr; - if (nr == MAX_SHA1_ENTRIES) { - fsck_sha1_list(); - nr = 0; - } - sha1_list.entry[nr] = entry; - sha1_list.nr = ++nr; - } - - static inline int is_loose_object_file(struct dirent *de, - char *name, unsigned char *sha1) - { - if (strlen(de->d_name) != 38) - return 0; - memcpy(name + 2, de->d_name, 39); - return !get_sha1_hex(name, sha1); - } - - static void fsck_dir(int i, char *path) - { - DIR *dir = opendir(path); - struct dirent *de; - char name[100]; - - if (!dir) - return; - - if (verbose) - fprintf(stderr, "Checking directory %s\n", path); - - sprintf(name, "%02x", i); - while ((de = readdir(dir)) != NULL) { - unsigned char sha1[20]; - - if (is_dot_or_dotdot(de->d_name)) - continue; - if (is_loose_object_file(de, name, sha1)) { - add_sha1_list(sha1, DIRENT_SORT_HINT(de)); - continue; - } - if (starts_with(de->d_name, "tmp_obj_")) - continue; - fprintf(stderr, "bad sha1 file: %s/%s\n", path, de->d_name); - } - closedir(dir); - } - static int default_refs; static void fsck_handle_reflog_sha1(const char *refname, unsigned char *sha1) @@@ -522,10 -417,8 +418,10 @@@ static int fsck_handle_ref(const char * /* We'll continue with the rest despite the error.. */ return 0; } - if (obj->type != OBJ_COMMIT && is_branch(refname)) + if (obj->type != OBJ_COMMIT && is_branch(refname)) { error("%s: not a commit", refname); + errors_found |= ERROR_REFS; + } default_refs++; obj->used = 1; mark_object_reachable(obj); @@@ -559,9 -452,28 +455,28 @@@ static void get_default_heads(void } } + static int fsck_loose(const unsigned char *sha1, const char *path, void *data) + { + if (fsck_sha1(sha1)) + errors_found |= ERROR_OBJECT; + return 0; + } + + static int fsck_cruft(const char *basename, const char *path, void *data) + { + if (!starts_with(basename, "tmp_obj_")) + fprintf(stderr, "bad sha1 file: %s\n", path); + return 0; + } + + static int fsck_subdir(int nr, const char *path, void *progress) + { + display_progress(progress, nr + 1); + return 0; + } + static void fsck_object_dir(const char *path) { - int i; struct progress *progress = NULL; if (verbose) @@@ -569,14 -481,11 +484,11 @@@ if (show_progress) progress = start_progress(_("Checking object directories"), 256); - for (i = 0; i < 256; i++) { - static char dir[4096]; - sprintf(dir, "%s/%02x", path, i); - fsck_dir(i, dir); - display_progress(progress, i+1); - } + + for_each_loose_file_in_objdir(path, fsck_loose, fsck_cruft, fsck_subdir, + progress); + display_progress(progress, 256); stop_progress(&progress); - fsck_sha1_list(); } static int fsck_head_link(void) @@@ -588,23 -497,17 +500,23 @@@ fprintf(stderr, "Checking HEAD link\n"); head_points_at = resolve_ref_unsafe("HEAD", 0, head_oid.hash, &flag); - if (!head_points_at) + if (!head_points_at) { + errors_found |= ERROR_REFS; return error("Invalid HEAD"); + } if (!strcmp(head_points_at, "HEAD")) /* detached HEAD */ null_is_error = 1; - else if (!starts_with(head_points_at, "refs/heads/")) + else if (!starts_with(head_points_at, "refs/heads/")) { + errors_found |= ERROR_REFS; return error("HEAD points to something strange (%s)", head_points_at); + } if (is_null_oid(&head_oid)) { - if (null_is_error) + if (null_is_error) { + errors_found |= ERROR_REFS; return error("HEAD: detached HEAD points at nothing"); + } fprintf(stderr, "notice: HEAD points to an unborn branch (%s)\n", head_points_at + 11); } @@@ -624,7 -527,6 +536,7 @@@ static int fsck_cache_tree(struct cache if (!obj) { error("%s: invalid sha1 pointer in cache-tree", sha1_to_hex(it->sha1)); + errors_found |= ERROR_REFS; return 1; } obj->used = 1; @@@ -688,16 -590,18 +600,18 @@@ int cmd_fsck(int argc, const char **arg git_config(fsck_config, NULL); fsck_head_link(); - if (!connectivity_only) + if (!connectivity_only) { fsck_object_dir(get_object_directory()); - prepare_alt_odb(); - for (alt = alt_odb_list; alt; alt = alt->next) { - char namebuf[PATH_MAX]; - int namelen = alt->name - alt->base; - memcpy(namebuf, alt->base, namelen); - namebuf[namelen - 1] = 0; - fsck_object_dir(namebuf); + prepare_alt_odb(); + for (alt = alt_odb_list; alt; alt = alt->next) { + /* directory name, minus trailing slash */ + size_t namelen = alt->name - alt->base - 1; + struct strbuf name = STRBUF_INIT; + strbuf_add(&name, alt->base, namelen); + fsck_object_dir(name.buf); + strbuf_release(&name); + } } if (check_full) { diff --combined builtin/gc.c index 9ff0204940,57584bc99f..eeeb21b1c4 --- a/builtin/gc.c +++ b/builtin/gc.c @@@ -44,7 -44,6 +44,7 @@@ static struct argv_array prune_worktree static struct argv_array rerere = ARGV_ARRAY_INIT; static struct tempfile pidfile; +static struct lock_file log_lock; static void git_config_date_string(const char *key, const char **output) { @@@ -57,28 -56,6 +57,28 @@@ } } +static void process_log_file(void) +{ + struct stat st; + if (!fstat(get_lock_file_fd(&log_lock), &st) && st.st_size) + commit_lock_file(&log_lock); + else + rollback_lock_file(&log_lock); +} + +static void process_log_file_at_exit(void) +{ + fflush(stderr); + process_log_file(); +} + +static void process_log_file_on_signal(int signo) +{ + process_log_file(); + sigchain_pop(signo); + raise(signo); +} + static void gc_config(void) { const char *value; @@@ -217,7 -194,7 +217,7 @@@ static const char *lock_repo_for_gc(in return NULL; if (gethostname(my_host, sizeof(my_host))) - strcpy(my_host, "unknown"); + xsnprintf(my_host, sizeof(my_host), "unknown"); pidfile_path = git_pathdup("gc.pid"); fd = hold_lock_file_for_update(&lock, pidfile_path, @@@ -264,24 -241,6 +264,24 @@@ return NULL; } +static int report_last_gc_error(void) +{ + struct strbuf sb = STRBUF_INIT; + int ret; + + ret = strbuf_read_file(&sb, git_path("gc.log"), 0); + if (ret > 0) + return error(_("The last gc run reported the following. " + "Please correct the root cause\n" + "and remove %s.\n" + "Automatic cleanup will not be performed " + "until the file is removed.\n\n" + "%s"), + git_path("gc.log"), sb.buf); + strbuf_release(&sb); + return 0; +} + static int gc_before_repack(void) { if (pack_refs && run_command_v_opt(pack_refs_cmd.argv, RUN_GIT_CMD)) @@@ -303,7 -262,6 +303,7 @@@ int cmd_gc(int argc, const char **argv int force = 0; const char *name; pid_t pid; + int daemonized = 0; struct option builtin_gc_options[] = { OPT__QUIET(&quiet, N_("suppress progress reporting")), @@@ -360,16 -318,13 +360,16 @@@ fprintf(stderr, _("See \"git help gc\" for manual housekeeping.\n")); } if (detach_auto) { + if (report_last_gc_error()) + return -1; + if (gc_before_repack()) return -1; /* * failure to daemonize is ok, we'll continue * in foreground */ - daemonize(); + daemonized = !daemonize(); } } else add_repack_all_option(); @@@ -382,15 -337,6 +382,15 @@@ name, (uintmax_t)pid); } + if (daemonized) { + hold_lock_file_for_update(&log_lock, + git_path("gc.log"), + LOCK_DIE_ON_ERROR); + dup2(get_lock_file_fd(&log_lock), 2); + sigchain_push_common(process_log_file_on_signal); + atexit(process_log_file_at_exit); + } + if (gc_before_repack()) return -1; diff --combined builtin/ls-remote.c index 5e9d5450b7,5b6d679a63..a31024900b --- a/builtin/ls-remote.c +++ b/builtin/ls-remote.c @@@ -4,7 -4,7 +4,7 @@@ #include "remote.h" static const char ls_remote_usage[] = -"git ls-remote [--heads] [--tags] [-u | --upload-pack ]\n" +"git ls-remote [--heads] [--tags] [--upload-pack=]\n" " [-q | --quiet] [--exit-code] [--get-url] [ [...]]"; /* @@@ -93,12 -93,8 +93,8 @@@ int cmd_ls_remote(int argc, const char if (argv[i]) { int j; pattern = xcalloc(argc - i + 1, sizeof(const char *)); - for (j = i; j < argc; j++) { - int len = strlen(argv[j]); - char *p = xmalloc(len + 3); - sprintf(p, "*/%s", argv[j]); - pattern[j - i] = p; - } + for (j = i; j < argc; j++) + pattern[j - i] = xstrfmt("*/%s", argv[j]); } remote = remote_get(dest); if (!remote) { diff --combined cache.h index 44c0260000,d206d64550..f735d14dc2 --- a/cache.h +++ b/cache.h @@@ -443,7 -443,6 +443,7 @@@ extern char *get_object_directory(void) extern char *get_index_file(void); extern char *get_graft_file(void); extern int set_git_dir(const char *path); +extern int get_common_dir_noenv(struct strbuf *sb, const char *gitdir); extern int get_common_dir(struct strbuf *sb, const char *gitdir); extern const char *get_git_namespace(void); extern const char *strip_namespace(const char *namespaced_ref); @@@ -724,6 -723,8 +724,8 @@@ extern char *mksnpath(char *buf, size_ __attribute__((format (printf, 3, 4))); extern void strbuf_git_path(struct strbuf *sb, const char *fmt, ...) __attribute__((format (printf, 2, 3))); + extern char *git_path_buf(struct strbuf *buf, const char *fmt, ...) + __attribute__((format (printf, 2, 3))); extern void strbuf_git_path_submodule(struct strbuf *sb, const char *path, const char *fmt, ...) __attribute__((format (printf, 3, 4))); @@@ -784,7 -785,24 +786,24 @@@ extern char *sha1_pack_name(const unsig */ extern char *sha1_pack_index_name(const unsigned char *sha1); - extern const char *find_unique_abbrev(const unsigned char *sha1, int); + /* + * Return an abbreviated sha1 unique within this repository's object database. + * The result will be at least `len` characters long, and will be NUL + * terminated. + * + * The non-`_r` version returns a static buffer which will be overwritten by + * subsequent calls. + * + * The `_r` variant writes to a buffer supplied by the caller, which must be at + * least `GIT_SHA1_HEXSZ + 1` bytes. The return value is the number of bytes + * written (excluding the NUL terminator). + * + * Note that while this version avoids the static buffer, it is not fully + * reentrant, as it calls into other non-reentrant git code. + */ + extern const char *find_unique_abbrev(const unsigned char *sha1, int len); + extern int find_unique_abbrev_r(char *hex, const unsigned char *sha1, int len); + extern const unsigned char null_sha1[GIT_SHA1_RAWSZ]; static inline int hashcmp(const unsigned char *sha1, const unsigned char *sha2) @@@ -1066,6 -1084,18 +1085,18 @@@ extern int for_each_abbrev(const char * extern int get_sha1_hex(const char *hex, unsigned char *sha1); extern int get_oid_hex(const char *hex, struct object_id *sha1); + /* + * Convert a binary sha1 to its hex equivalent. The `_r` variant is reentrant, + * and writes the NUL-terminated output to the buffer `out`, which must be at + * least `GIT_SHA1_HEXSZ + 1` bytes, and returns a pointer to out for + * convenience. + * + * The non-`_r` variant returns a static buffer, but uses a ring of 4 + * buffers, making it safe to make multiple calls for a single statement, like: + * + * printf("%s -> %s", sha1_to_hex(one), sha1_to_hex(two)); + */ + extern char *sha1_to_hex_r(char *out, const unsigned char *sha1); extern char *sha1_to_hex(const unsigned char *sha1); /* static buffer result! */ extern char *oid_to_hex(const struct object_id *oid); /* same static buffer as sha1_to_hex */ @@@ -1092,6 -1122,7 +1123,6 @@@ struct date_mode DATE_NORMAL = 0, DATE_RELATIVE, DATE_SHORT, - DATE_LOCAL, DATE_ISO8601, DATE_ISO8601_STRICT, DATE_RFC2822, @@@ -1099,7 -1130,6 +1130,7 @@@ DATE_RAW } type; const char *strftime_fmt; + int local; }; /* @@@ -1276,11 -1306,10 +1307,11 @@@ extern void close_pack_index(struct pac extern unsigned char *use_pack(struct packed_git *, struct pack_window **, off_t, unsigned long *); extern void close_pack_windows(struct packed_git *); +extern void close_all_packs(void); extern void unuse_pack(struct pack_window **); extern void free_pack_by_name(const char *); extern void clear_delta_base_cache(void); - extern struct packed_git *add_packed_git(const char *, int, int); + extern struct packed_git *add_packed_git(const char *path, size_t path_len, int local); /* * Return the SHA-1 of the nth object within the specified packfile. diff --combined connect.c index d3283b8a4f,1d5c5e0055..108f5ab60e --- a/connect.c +++ b/connect.c @@@ -9,7 -9,6 +9,7 @@@ #include "url.h" #include "string-list.h" #include "sha1-array.h" +#include "transport.h" static char *server_capabilities; static const char *parse_feature_value(const char *, const char *, int *); @@@ -255,7 -254,7 +255,7 @@@ static const char *prot_name(enum proto case PROTO_GIT: return "git"; default: - return "unkown protocol"; + return "unknown protocol"; } } @@@ -333,7 -332,7 +333,7 @@@ static const char *ai_name(const struc static char addr[NI_MAXHOST]; if (getnameinfo(ai->ai_addr, ai->ai_addrlen, addr, sizeof(addr), NULL, 0, NI_NUMERICHOST) != 0) - strcpy(addr, "(unknown)"); + xsnprintf(addr, sizeof(addr), "(unknown)"); return addr; } @@@ -695,8 -694,6 +695,8 @@@ struct child_process *git_connect(int f else target_host = xstrdup(hostandport); + transport_check_allowed("git"); + /* These underlying connection commands die() if they * cannot connect. */ @@@ -724,16 -721,12 +724,16 @@@ strbuf_addch(&cmd, ' '); sq_quote_buf(&cmd, path); + /* remove repo-local variables from the environment */ + conn->env = local_repo_env; + conn->use_shell = 1; conn->in = conn->out = -1; if (protocol == PROTO_SSH) { const char *ssh; - int putty, tortoiseplink = 0; + int putty = 0, tortoiseplink = 0; char *ssh_host = hostandport; const char *port = NULL; + transport_check_allowed("ssh"); get_host_and_port(&ssh_host, &port); if (!port) @@@ -753,17 -746,13 +753,17 @@@ } ssh = getenv("GIT_SSH_COMMAND"); - if (ssh) { - conn->use_shell = 1; - putty = 0; - } else { + if (!ssh) { const char *base; char *ssh_dup; + /* + * GIT_SSH is the no-shell version of + * GIT_SSH_COMMAND (and must remain so for + * historical compatibility). + */ + conn->use_shell = 0; + ssh = getenv("GIT_SSH"); if (!ssh) ssh = "ssh"; @@@ -773,9 -762,8 +773,9 @@@ tortoiseplink = !strcasecmp(base, "tortoiseplink") || !strcasecmp(base, "tortoiseplink.exe"); - putty = !strcasecmp(base, "plink") || - !strcasecmp(base, "plink.exe") || tortoiseplink; + putty = tortoiseplink || + !strcasecmp(base, "plink") || + !strcasecmp(base, "plink.exe"); free(ssh_dup); } @@@ -790,7 -778,9 +790,7 @@@ } argv_array_push(&conn->args, ssh_host); } else { - /* remove repo-local variables from the environment */ - conn->env = local_repo_env; - conn->use_shell = 1; + transport_check_allowed("file"); } argv_array_push(&conn->args, cmd.buf); diff --combined diff.c index 46260ed7a1,2a37378ec8..835a12e84d --- a/diff.c +++ b/diff.c @@@ -322,7 -322,7 +322,7 @@@ static struct diff_tempfile */ const char *name; - char hex[41]; + char hex[GIT_SHA1_HEXSZ + 1]; char mode[10]; /* @@@ -1041,9 -1041,8 +1041,9 @@@ static void diff_words_show(struct diff xpp.flags = 0; /* as only the hunk header will be parsed, we need a 0-context */ xecfg.ctxlen = 0; - xdi_diff_outf(&minus, &plus, fn_out_diff_words_aux, diff_words, - &xpp, &xecfg); + if (xdi_diff_outf(&minus, &plus, fn_out_diff_words_aux, diff_words, + &xpp, &xecfg)) + die("unable to generate word diff"); free(minus.ptr); free(plus.ptr); if (diff_words->current_plus != diff_words->plus.text.ptr + @@@ -2450,9 -2449,8 +2450,9 @@@ static void builtin_diff(const char *na xecfg.ctxlen = strtoul(v, NULL, 10); if (o->word_diff) init_diff_words_data(&ecbdata, o, one, two); - xdi_diff_outf(&mf1, &mf2, fn_out_consume, &ecbdata, - &xpp, &xecfg); + if (xdi_diff_outf(&mf1, &mf2, fn_out_consume, &ecbdata, + &xpp, &xecfg)) + die("unable to generate diff for %s", one->path); if (o->word_diff) free_diff_words_data(&ecbdata); if (textconv_one) @@@ -2529,9 -2527,8 +2529,9 @@@ static void builtin_diffstat(const cha xpp.flags = o->xdl_opts; xecfg.ctxlen = o->context; xecfg.interhunkctxlen = o->interhunkcontext; - xdi_diff_outf(&mf1, &mf2, diffstat_consume, diffstat, - &xpp, &xecfg); + if (xdi_diff_outf(&mf1, &mf2, diffstat_consume, diffstat, + &xpp, &xecfg)) + die("unable to generate diffstat for %s", one->path); } diff_free_filespec_data(one); @@@ -2577,9 -2574,8 +2577,9 @@@ static void builtin_checkdiff(const cha memset(&xecfg, 0, sizeof(xecfg)); xecfg.ctxlen = 1; /* at least one context line */ xpp.flags = 0; - xdi_diff_outf(&mf1, &mf2, checkdiff_consume, &data, - &xpp, &xecfg); + if (xdi_diff_outf(&mf1, &mf2, checkdiff_consume, &data, + &xpp, &xecfg)) + die("unable to generate checkdiff for %s", one->path); if (data.ws_rule & WS_BLANK_AT_EOF) { struct emit_callback ecbdata; @@@ -2882,9 -2878,8 +2882,8 @@@ static void prep_temp_blob(const char * die_errno("unable to write temp-file"); close_tempfile(&temp->tempfile); temp->name = get_tempfile_path(&temp->tempfile); - strcpy(temp->hex, sha1_to_hex(sha1)); - temp->hex[40] = 0; - sprintf(temp->mode, "%06o", mode); + sha1_to_hex_r(temp->hex, sha1); + xsnprintf(temp->mode, sizeof(temp->mode), "%06o", mode); strbuf_release(&buf); strbuf_release(&template); free(path_dup); @@@ -2901,8 -2896,8 +2900,8 @@@ static struct diff_tempfile *prepare_te * a '+' entry produces this for file-1. */ temp->name = "/dev/null"; - strcpy(temp->hex, "."); - strcpy(temp->mode, "."); + xsnprintf(temp->hex, sizeof(temp->hex), "."); + xsnprintf(temp->mode, sizeof(temp->mode), "."); return temp; } @@@ -2930,16 -2925,16 +2929,16 @@@ /* we can borrow from the file in the work tree */ temp->name = name; if (!one->sha1_valid) - strcpy(temp->hex, sha1_to_hex(null_sha1)); + sha1_to_hex_r(temp->hex, null_sha1); else - strcpy(temp->hex, sha1_to_hex(one->sha1)); + sha1_to_hex_r(temp->hex, one->sha1); /* Even though we may sometimes borrow the * contents from the work tree, we always want * one->mode. mode is trustworthy even when * !(one->sha1_valid), as long as * DIFF_FILE_VALID(one). */ - sprintf(temp->mode, "%06o", one->mode); + xsnprintf(temp->mode, sizeof(temp->mode), "%06o", one->mode); } return temp; } @@@ -4085,9 -4080,9 +4084,9 @@@ const char *diff_unique_abbrev(const un if (abblen < 37) { static char hex[41]; if (len < abblen && abblen <= len + 2) - sprintf(hex, "%s%.*s", abbrev, len+3-abblen, ".."); + xsnprintf(hex, sizeof(hex), "%s%.*s", abbrev, len+3-abblen, ".."); else - sprintf(hex, "%s...", abbrev); + xsnprintf(hex, sizeof(hex), "%s...", abbrev); return hex; } return sha1_to_hex(sha1); @@@ -4514,10 -4509,8 +4513,10 @@@ static int diff_get_patch_id(struct dif xpp.flags = 0; xecfg.ctxlen = 3; xecfg.flags = 0; - xdi_diff_outf(&mf1, &mf2, patch_id_consume, &data, - &xpp, &xecfg); + if (xdi_diff_outf(&mf1, &mf2, patch_id_consume, &data, + &xpp, &xecfg)) + return error("unable to generate patch-id diff for %s", + p->one->path); } git_SHA1_Final(sha1, &ctx); diff --combined dir.c index fba938b701,79fdad8425..109ceeaed3 --- a/dir.c +++ b/dir.c @@@ -882,25 -882,6 +882,25 @@@ int match_pathname(const char *pathname */ if (!patternlen && !namelen) return 1; + /* + * This can happen when we ignore some exclude rules + * on directories in other to see if negative rules + * may match. E.g. + * + * /abc + * !/abc/def/ghi + * + * The pattern of interest is "/abc". On the first + * try, we should match path "abc" with this pattern + * in the "if" statement right above, but the caller + * ignores it. + * + * On the second try with paths within "abc", + * e.g. "abc/xyz", we come here and try to match it + * with "/abc". + */ + if (!patternlen && namelen && *name == '/') + return 1; } return fnmatch_icase_mem(pattern, patternlen, @@@ -908,48 -889,6 +908,48 @@@ WM_PATHNAME) == 0; } +/* + * Return non-zero if pathname is a directory and an ancestor of the + * literal path in a (negative) pattern. This is used to keep + * descending in "foo" and "foo/bar" when the pattern is + * "!foo/bar/.gitignore". "foo/notbar" will not be descended however. + */ +static int match_neg_path(const char *pathname, int pathlen, int *dtype, + const char *base, int baselen, + const char *pattern, int prefix, int patternlen, + int flags) +{ + assert((flags & EXC_FLAG_NEGATIVE) && !(flags & EXC_FLAG_NODIR)); + + if (*dtype == DT_UNKNOWN) + *dtype = get_dtype(NULL, pathname, pathlen); + if (*dtype != DT_DIR) + return 0; + + if (*pattern == '/') { + pattern++; + patternlen--; + prefix--; + } + + if (baselen) { + if (((pathlen < baselen && base[pathlen] == '/') || + pathlen == baselen) && + !strncmp_icase(pathname, base, pathlen)) + return 1; + pathname += baselen + 1; + pathlen -= baselen + 1; + } + + + if (prefix && + ((pathlen < prefix && pattern[pathlen] == '/') && + !strncmp_icase(pathname, pattern, pathlen))) + return 1; + + return 0; +} + /* * Scan the given exclude list in reverse to see whether pathname * should be ignored. The first match (i.e. the last on the list), if @@@ -962,8 -901,7 +962,8 @@@ static struct exclude *last_exclude_mat int *dtype, struct exclude_list *el) { - int i; + struct exclude *exc = NULL; /* undecided */ + int i, matched_negative_path = 0; if (!el->nr) return NULL; /* undefined */ @@@ -984,33 -922,18 +984,33 @@@ if (match_basename(basename, pathlen - (basename - pathname), exclude, prefix, x->patternlen, - x->flags)) - return x; + x->flags)) { + exc = x; + break; + } continue; } assert(x->baselen == 0 || x->base[x->baselen - 1] == '/'); if (match_pathname(pathname, pathlen, x->base, x->baselen ? x->baselen - 1 : 0, + exclude, prefix, x->patternlen, x->flags)) { + exc = x; + break; + } + + if ((x->flags & EXC_FLAG_NEGATIVE) && !matched_negative_path && + match_neg_path(pathname, pathlen, dtype, x->base, + x->baselen ? x->baselen - 1 : 0, exclude, prefix, x->patternlen, x->flags)) - return x; + matched_negative_path = 1; } - return NULL; /* undecided */ + if (exc && + !(exc->flags & EXC_FLAG_NEGATIVE) && + !(exc->flags & EXC_FLAG_NODIR) && + matched_negative_path) + exc = NULL; + return exc; } /* @@@ -1596,8 -1519,7 +1596,7 @@@ static enum path_treatment treat_path_f } strbuf_addstr(path, cdir->ucd->name); /* treat_one_path() does this before it calls treat_directory() */ - if (path->buf[path->len - 1] != '/') - strbuf_addch(path, '/'); + strbuf_complete(path, '/'); if (cdir->ucd->check_only) /* * check_only is set as a result of treat_directory() getting @@@ -2107,15 -2029,6 +2106,15 @@@ int file_exists(const char *f return lstat(f, &sb) == 0; } +static int cmp_icase(char a, char b) +{ + if (a == b) + return 0; + if (ignore_case) + return toupper(a) - toupper(b); + return a - b; +} + /* * Given two normalized paths (a trailing slash is ok), if subdir is * outside dir, return -1. Otherwise return the offset in subdir that @@@ -2127,7 -2040,7 +2126,7 @@@ int dir_inside_of(const char *subdir, c assert(dir && subdir && *dir && *subdir); - while (*dir && *subdir && *dir == *subdir) { + while (*dir && *subdir && !cmp_icase(*dir, *subdir)) { dir++; subdir++; offset++; @@@ -2212,8 -2125,7 +2211,7 @@@ static int remove_dir_recurse(struct st else return -1; } - if (path->buf[original_len - 1] != '/') - strbuf_addch(path, '/'); + strbuf_complete(path, '/'); len = path->len; while ((e = readdir(dir)) != NULL) { diff --combined fast-import.c index adcbfc67dc,4d01efcb9d..e3b421d514 --- a/fast-import.c +++ b/fast-import.c @@@ -424,7 -424,7 +424,7 @@@ static void write_crash_report(const ch fprintf(rpt, "fast-import crash report:\n"); fprintf(rpt, " fast-import process: %"PRIuMAX"\n", (uintmax_t) getpid()); fprintf(rpt, " parent process : %"PRIuMAX"\n", (uintmax_t) getppid()); - fprintf(rpt, " at %s\n", show_date(time(NULL), 0, DATE_MODE(LOCAL))); + fprintf(rpt, " at %s\n", show_date(time(NULL), 0, DATE_MODE(ISO8601))); fputc('\n', rpt); fputs("fatal: ", rpt); @@@ -644,8 -644,9 +644,9 @@@ static void *pool_calloc(size_t count, static char *pool_strdup(const char *s) { - char *r = pool_alloc(strlen(s) + 1); - strcpy(r, s); + size_t len = strlen(s) + 1; + char *r = pool_alloc(len); + memcpy(r, s, len); return r; } @@@ -702,7 -703,7 +703,7 @@@ static struct atom_str *to_atom(const c c = pool_alloc(sizeof(struct atom_str) + len + 1); c->str_len = len; - strncpy(c->str_dat, s, len); + memcpy(c->str_dat, s, len); c->str_dat[len] = 0; c->next_atom = atom_table[hc]; atom_table[hc] = c; @@@ -863,13 -864,15 +864,15 @@@ static void start_packfile(void { static char tmp_file[PATH_MAX]; struct packed_git *p; + int namelen; struct pack_header hdr; int pack_fd; pack_fd = odb_mkstemp(tmp_file, sizeof(tmp_file), "pack/tmp_pack_XXXXXX"); - p = xcalloc(1, sizeof(*p) + strlen(tmp_file) + 2); - strcpy(p->pack_name, tmp_file); + namelen = strlen(tmp_file) + 2; + p = xcalloc(1, sizeof(*p) + namelen); + xsnprintf(p->pack_name, namelen, "%s", tmp_file); p->pack_fd = pack_fd; p->do_not_close = 1; pack_file = sha1fd(pack_fd, p->pack_name); @@@ -1035,8 -1038,8 +1038,8 @@@ static int store_object git_SHA_CTX c; git_zstream s; - hdrlen = sprintf((char *)hdr,"%s %lu", typename(type), - (unsigned long)dat->len) + 1; + hdrlen = xsnprintf((char *)hdr, sizeof(hdr), "%s %lu", + typename(type), (unsigned long)dat->len) + 1; git_SHA1_Init(&c); git_SHA1_Update(&c, hdr, hdrlen); git_SHA1_Update(&c, dat->buf, dat->len); diff --combined git-compat-util.h index 1df82fa598,9a3e5591cb..88964f7886 --- a/git-compat-util.h +++ b/git-compat-util.h @@@ -229,7 -229,7 +229,7 @@@ typedef unsigned long uintptr_t #else #define precompose_str(in,i_nfd2nfc) #define precompose_argv(c,v) - #define probe_utf8_pathname_composition(a,b) + #define probe_utf8_pathname_composition() #endif #ifdef MKDIR_WO_TRAILING_SLASH @@@ -744,6 -744,9 +744,9 @@@ static inline size_t xsize_t(off_t len return (size_t)len; } + __attribute__((format (printf, 3, 4))) + extern int xsnprintf(char *dst, size_t max, const char *fmt, ...); + /* in ctype.c, for kwset users */ extern const unsigned char tolower_trans_tbl[256]; @@@ -814,9 -817,6 +817,9 @@@ static inline int strtoul_ui(char cons char *p; errno = 0; + /* negative values would be accepted by strtoul */ + if (strchr(s, '-')) + return -1; ul = strtoul(s, &p, base); if (errno || *p || p == s || (unsigned int) ul != ul) return -1; diff --combined http.c index 0f924a8b48,e0ff876cd9..7da76edda1 --- a/http.c +++ b/http.c @@@ -9,7 -9,6 +9,7 @@@ #include "version.h" #include "pkt-line.h" #include "gettext.h" +#include "transport.h" int active_requests; int http_is_verbose; @@@ -357,7 -356,6 +357,7 @@@ static void set_curl_keepalive(CURL *c static CURL *get_curl_handle(void) { CURL *result = curl_easy_init(); + long allowed_protocols = 0; if (!result) die("curl_easy_init failed"); @@@ -427,27 -425,11 +427,27 @@@ } curl_easy_setopt(result, CURLOPT_FOLLOWLOCATION, 1); + curl_easy_setopt(result, CURLOPT_MAXREDIRS, 20); #if LIBCURL_VERSION_NUM >= 0x071301 curl_easy_setopt(result, CURLOPT_POSTREDIR, CURL_REDIR_POST_ALL); #elif LIBCURL_VERSION_NUM >= 0x071101 curl_easy_setopt(result, CURLOPT_POST301, 1); #endif +#if LIBCURL_VERSION_NUM >= 0x071304 + if (is_transport_allowed("http")) + allowed_protocols |= CURLPROTO_HTTP; + if (is_transport_allowed("https")) + allowed_protocols |= CURLPROTO_HTTPS; + if (is_transport_allowed("ftp")) + allowed_protocols |= CURLPROTO_FTP; + if (is_transport_allowed("ftps")) + allowed_protocols |= CURLPROTO_FTPS; + curl_easy_setopt(result, CURLOPT_REDIR_PROTOCOLS, allowed_protocols); +#else + if (transport_restrict_protocols()) + warning("protocol restrictions not applied to curl redirects because\n" + "your curl version is too old (>= 7.19.4)"); +#endif if (getenv("GIT_CURL_VERBOSE")) curl_easy_setopt(result, CURLOPT_VERBOSE, 1); @@@ -1122,7 -1104,7 +1122,7 @@@ static void write_accept_language(struc decimal_places++, max_q *= 10) ; - sprintf(q_format, ";q=0.%%0%dd", decimal_places); + xsnprintf(q_format, sizeof(q_format), ";q=0.%%0%dd", decimal_places); strbuf_addstr(buf, "Accept-Language: "); @@@ -1529,6 -1511,7 +1529,7 @@@ int finish_http_pack_request(struct htt struct packed_git **lst; struct packed_git *p = preq->target; char *tmp_idx; + size_t len; struct child_process ip = CHILD_PROCESS_INIT; const char *ip_argv[8]; @@@ -1542,9 -1525,9 +1543,9 @@@ lst = &((*lst)->next); *lst = (*lst)->next; - tmp_idx = xstrdup(preq->tmpfile); - strcpy(tmp_idx + strlen(tmp_idx) - strlen(".pack.temp"), - ".idx.temp"); + if (!strip_suffix(preq->tmpfile, ".pack.temp", &len)) + die("BUG: pack tmpfile does not end in .pack.temp?"); + tmp_idx = xstrfmt("%.*s.idx.temp", (int)len, preq->tmpfile); ip_argv[0] = "index-pack"; ip_argv[1] = "-o"; @@@ -1619,7 -1602,7 +1620,7 @@@ struct http_pack_request *new_http_pack fprintf(stderr, "Resuming fetch of pack %s at byte %ld\n", sha1_to_hex(target->sha1), prev_posn); - sprintf(range, "Range: bytes=%ld-", prev_posn); + xsnprintf(range, sizeof(range), "Range: bytes=%ld-", prev_posn); preq->range_header = curl_slist_append(NULL, range); curl_easy_setopt(preq->slot->curl, CURLOPT_HTTPHEADER, preq->range_header); @@@ -1779,7 -1762,7 +1780,7 @@@ struct http_object_request *new_http_ob fprintf(stderr, "Resuming fetch of object %s at byte %ld\n", hex, prev_posn); - sprintf(range, "Range: bytes=%ld-", prev_posn); + xsnprintf(range, sizeof(range), "Range: bytes=%ld-", prev_posn); range_header = curl_slist_append(range_header, range); curl_easy_setopt(freq->slot->curl, CURLOPT_HTTPHEADER, range_header); diff --combined ll-merge.c index bf83290793,56f73b3932..0338630fc2 --- a/ll-merge.c +++ b/ll-merge.c @@@ -89,10 -89,7 +89,10 @@@ static int ll_xdl_merge(const struct ll xmparam_t xmp; assert(opts); - if (buffer_is_binary(orig->ptr, orig->size) || + if (orig->size > MAX_XDIFF_SIZE || + src1->size > MAX_XDIFF_SIZE || + src2->size > MAX_XDIFF_SIZE || + buffer_is_binary(orig->ptr, orig->size) || buffer_is_binary(src1->ptr, src1->size) || buffer_is_binary(src2->ptr, src2->size)) { return ll_binary_merge(drv_unused, result, @@@ -145,11 -142,11 +145,11 @@@ static struct ll_merge_driver ll_merge_ { "union", "built-in union merge", ll_union_merge }, }; - static void create_temp(mmfile_t *src, char *path) + static void create_temp(mmfile_t *src, char *path, size_t len) { int fd; - strcpy(path, ".merge_file_XXXXXX"); + xsnprintf(path, len, ".merge_file_XXXXXX"); fd = xmkstemp(path); if (write_in_full(fd, src->ptr, src->size) != src->size) die_errno("unable to write temp-file"); @@@ -190,10 -187,10 +190,10 @@@ static int ll_ext_merge(const struct ll result->ptr = NULL; result->size = 0; - create_temp(orig, temp[0]); - create_temp(src1, temp[1]); - create_temp(src2, temp[2]); - sprintf(temp[3], "%d", marker_size); + create_temp(orig, temp[0], sizeof(temp[0])); + create_temp(src1, temp[1], sizeof(temp[1])); + create_temp(src2, temp[2], sizeof(temp[2])); + xsnprintf(temp[3], sizeof(temp[3]), "%d", marker_size); strbuf_expand(&cmd, fn->cmdline, strbuf_expand_dict_cb, &dict); diff --combined path.c index 1352952616,c105a9e083..c740c4ff94 --- a/path.c +++ b/path.c @@@ -91,274 -91,54 +91,274 @@@ static void replace_dir(struct strbuf * buf->buf[newlen] = '/'; } -static const char *common_list[] = { - "/branches", "/hooks", "/info", "!/logs", "/lost-found", - "/objects", "/refs", "/remotes", "/worktrees", "/rr-cache", "/svn", - "config", "!gc.pid", "packed-refs", "shallow", - NULL +struct common_dir { + /* Not considered garbage for report_linked_checkout_garbage */ + unsigned ignore_garbage:1; + unsigned is_dir:1; + /* Not common even though its parent is */ + unsigned exclude:1; + const char *dirname; }; -static void update_common_dir(struct strbuf *buf, int git_dir_len) +static struct common_dir common_list[] = { + { 0, 1, 0, "branches" }, + { 0, 1, 0, "hooks" }, + { 0, 1, 0, "info" }, + { 0, 0, 1, "info/sparse-checkout" }, + { 1, 1, 0, "logs" }, + { 1, 1, 1, "logs/HEAD" }, + { 0, 1, 1, "logs/refs/bisect" }, + { 0, 1, 0, "lost-found" }, + { 0, 1, 0, "objects" }, + { 0, 1, 0, "refs" }, + { 0, 1, 1, "refs/bisect" }, + { 0, 1, 0, "remotes" }, + { 0, 1, 0, "worktrees" }, + { 0, 1, 0, "rr-cache" }, + { 0, 1, 0, "svn" }, + { 0, 0, 0, "config" }, + { 1, 0, 0, "gc.pid" }, + { 0, 0, 0, "packed-refs" }, + { 0, 0, 0, "shallow" }, + { 0, 0, 0, NULL } +}; + +/* + * A compressed trie. A trie node consists of zero or more characters that + * are common to all elements with this prefix, optionally followed by some + * children. If value is not NULL, the trie node is a terminal node. + * + * For example, consider the following set of strings: + * abc + * def + * definite + * definition + * + * The trie would look look like: + * root: len = 0, children a and d non-NULL, value = NULL. + * a: len = 2, contents = bc, value = (data for "abc") + * d: len = 2, contents = ef, children i non-NULL, value = (data for "def") + * i: len = 3, contents = nit, children e and i non-NULL, value = NULL + * e: len = 0, children all NULL, value = (data for "definite") + * i: len = 2, contents = on, children all NULL, + * value = (data for "definition") + */ +struct trie { + struct trie *children[256]; + int len; + char *contents; + void *value; +}; + +static struct trie *make_trie_node(const char *key, void *value) { - char *base = buf->buf + git_dir_len; - const char **p; - - if (is_dir_file(base, "logs", "HEAD") || - is_dir_file(base, "info", "sparse-checkout")) - return; /* keep this in $GIT_DIR */ - for (p = common_list; *p; p++) { - const char *path = *p; - int is_dir = 0; - if (*path == '!') - path++; - if (*path == '/') { - path++; - is_dir = 1; + struct trie *new_node = xcalloc(1, sizeof(*new_node)); + new_node->len = strlen(key); + if (new_node->len) { + new_node->contents = xmalloc(new_node->len); + memcpy(new_node->contents, key, new_node->len); + } + new_node->value = value; + return new_node; +} + +/* + * Add a key/value pair to a trie. The key is assumed to be \0-terminated. + * If there was an existing value for this key, return it. + */ +static void *add_to_trie(struct trie *root, const char *key, void *value) +{ + struct trie *child; + void *old; + int i; + + if (!*key) { + /* we have reached the end of the key */ + old = root->value; + root->value = value; + return old; + } + + for (i = 0; i < root->len; i++) { + if (root->contents[i] == key[i]) + continue; + + /* + * Split this node: child will contain this node's + * existing children. + */ + child = malloc(sizeof(*child)); + memcpy(child->children, root->children, sizeof(root->children)); + + child->len = root->len - i - 1; + if (child->len) { + child->contents = xstrndup(root->contents + i + 1, + child->len); } - if (is_dir && dir_prefix(base, path)) { - replace_dir(buf, git_dir_len, get_git_common_dir()); - return; + child->value = root->value; + root->value = NULL; + root->len = i; + + memset(root->children, 0, sizeof(root->children)); + root->children[(unsigned char)root->contents[i]] = child; + + /* This is the newly-added child. */ + root->children[(unsigned char)key[i]] = + make_trie_node(key + i + 1, value); + return NULL; + } + + /* We have matched the entire compressed section */ + if (key[i]) { + child = root->children[(unsigned char)key[root->len]]; + if (child) { + return add_to_trie(child, key + root->len + 1, value); + } else { + child = make_trie_node(key + root->len + 1, value); + root->children[(unsigned char)key[root->len]] = child; + return NULL; } - if (!is_dir && !strcmp(base, path)) { - replace_dir(buf, git_dir_len, get_git_common_dir()); - return; + } + + old = root->value; + root->value = value; + return old; +} + +typedef int (*match_fn)(const char *unmatched, void *data, void *baton); + +/* + * Search a trie for some key. Find the longest /-or-\0-terminated + * prefix of the key for which the trie contains a value. Call fn + * with the unmatched portion of the key and the found value, and + * return its return value. If there is no such prefix, return -1. + * + * The key is partially normalized: consecutive slashes are skipped. + * + * For example, consider the trie containing only [refs, + * refs/worktree] (both with values). + * + * | key | unmatched | val from node | return value | + * |-----------------|------------|---------------|--------------| + * | a | not called | n/a | -1 | + * | refs | \0 | refs | as per fn | + * | refs/ | / | refs | as per fn | + * | refs/w | /w | refs | as per fn | + * | refs/worktree | \0 | refs/worktree | as per fn | + * | refs/worktree/ | / | refs/worktree | as per fn | + * | refs/worktree/a | /a | refs/worktree | as per fn | + * |-----------------|------------|---------------|--------------| + * + */ +static int trie_find(struct trie *root, const char *key, match_fn fn, + void *baton) +{ + int i; + int result; + struct trie *child; + + if (!*key) { + /* we have reached the end of the key */ + if (root->value && !root->len) + return fn(key, root->value, baton); + else + return -1; + } + + for (i = 0; i < root->len; i++) { + /* Partial path normalization: skip consecutive slashes. */ + if (key[i] == '/' && key[i+1] == '/') { + key++; + continue; } + if (root->contents[i] != key[i]) + return -1; } + + /* Matched the entire compressed section */ + key += i; + if (!*key) + /* End of key */ + return fn(key, root->value, baton); + + /* Partial path normalization: skip consecutive slashes */ + while (key[0] == '/' && key[1] == '/') + key++; + + child = root->children[(unsigned char)*key]; + if (child) + result = trie_find(child, key + 1, fn, baton); + else + result = -1; + + if (result >= 0 || (*key != '/' && *key != 0)) + return result; + if (root->value) + return fn(key, root->value, baton); + else + return -1; +} + +static struct trie common_trie; +static int common_trie_done_setup; + +static void init_common_trie(void) +{ + struct common_dir *p; + + if (common_trie_done_setup) + return; + + for (p = common_list; p->dirname; p++) + add_to_trie(&common_trie, p->dirname, p); + + common_trie_done_setup = 1; +} + +/* + * Helper function for update_common_dir: returns 1 if the dir + * prefix is common. + */ +static int check_common(const char *unmatched, void *value, void *baton) +{ + struct common_dir *dir = value; + + if (!dir) + return 0; + + if (dir->is_dir && (unmatched[0] == 0 || unmatched[0] == '/')) + return !dir->exclude; + + if (!dir->is_dir && unmatched[0] == 0) + return !dir->exclude; + + return 0; +} + +static void update_common_dir(struct strbuf *buf, int git_dir_len, + const char *common_dir) +{ + char *base = buf->buf + git_dir_len; + init_common_trie(); + if (!common_dir) + common_dir = get_git_common_dir(); + if (trie_find(&common_trie, base, check_common, NULL) > 0) + replace_dir(buf, git_dir_len, common_dir); } void report_linked_checkout_garbage(void) { struct strbuf sb = STRBUF_INIT; - const char **p; + const struct common_dir *p; int len; if (!git_common_dir_env) return; strbuf_addf(&sb, "%s/", get_git_dir()); len = sb.len; - for (p = common_list; *p; p++) { - const char *path = *p; - if (*path == '!') + for (p = common_list; p->dirname; p++) { + const char *path = p->dirname; + if (p->ignore_garbage) continue; strbuf_setlen(&sb, len); strbuf_addstr(&sb, path); @@@ -380,7 -160,7 +380,7 @@@ static void adjust_git_path(struct strb else if (git_db_env && dir_prefix(base, "objects")) replace_dir(buf, git_dir_len + 7, get_object_directory()); else if (git_common_dir_env) - update_common_dir(buf, git_dir_len); + update_common_dir(buf, git_dir_len, NULL); } static void do_git_path(struct strbuf *buf, const char *fmt, va_list args) @@@ -395,6 -175,16 +395,16 @@@ strbuf_cleanup_path(buf); } + char *git_path_buf(struct strbuf *buf, const char *fmt, ...) + { + va_list args; + strbuf_reset(buf); + va_start(args, fmt); + do_git_path(buf, fmt, args); + va_end(args); + return buf->buf; + } + void strbuf_git_path(struct strbuf *sb, const char *fmt, ...) { va_list args; @@@ -448,12 -238,9 +458,11 @@@ static void do_submodule_path(struct st const char *fmt, va_list args) { const char *git_dir; + struct strbuf git_submodule_common_dir = STRBUF_INIT; + struct strbuf git_submodule_dir = STRBUF_INIT; strbuf_addstr(buf, path); - if (buf->len && buf->buf[buf->len - 1] != '/') - strbuf_addch(buf, '/'); + strbuf_complete(buf, '/'); strbuf_addstr(buf, ".git"); git_dir = read_gitfile(buf->buf); @@@ -462,17 -249,9 +471,17 @@@ strbuf_addstr(buf, git_dir); } strbuf_addch(buf, '/'); + strbuf_addstr(&git_submodule_dir, buf->buf); strbuf_vaddf(buf, fmt, args); + + if (get_common_dir_noenv(&git_submodule_common_dir, git_submodule_dir.buf)) + update_common_dir(buf, git_submodule_dir.len, git_submodule_common_dir.buf); + strbuf_cleanup_path(buf); + + strbuf_release(&git_submodule_dir); + strbuf_release(&git_submodule_common_dir); } char *git_pathdup_submodule(const char *path, const char *fmt, ...) @@@ -611,8 -390,8 +620,8 @@@ return_null */ const char *enter_repo(const char *path, int strict) { - static char used_path[PATH_MAX]; - static char validated_path[PATH_MAX]; + static struct strbuf validated_path = STRBUF_INIT; + static struct strbuf used_path = STRBUF_INIT; if (!path) return NULL; @@@ -627,56 -406,53 +636,57 @@@ while ((1 < len) && (path[len-1] == '/')) len--; + /* + * We can handle arbitrary-sized buffers, but this remains as a + * sanity check on untrusted input. + */ if (PATH_MAX <= len) return NULL; - strncpy(used_path, path, len); used_path[len] = 0 ; - strcpy(validated_path, used_path); - if (used_path[0] == '~') { - char *newpath = expand_user_path(used_path); - if (!newpath || (PATH_MAX - 10 < strlen(newpath))) { - free(newpath); + strbuf_reset(&used_path); + strbuf_reset(&validated_path); + strbuf_add(&used_path, path, len); + strbuf_add(&validated_path, path, len); + + if (used_path.buf[0] == '~') { + char *newpath = expand_user_path(used_path.buf); + if (!newpath) return NULL; - } - /* - * Copy back into the static buffer. A pity - * since newpath was not bounded, but other - * branches of the if are limited by PATH_MAX - * anyway. - */ - strcpy(used_path, newpath); free(newpath); + strbuf_attach(&used_path, newpath, strlen(newpath), + strlen(newpath)); } - else if (PATH_MAX - 10 < len) - return NULL; - len = strlen(used_path); for (i = 0; suffix[i]; i++) { struct stat st; - strcpy(used_path + len, suffix[i]); - if (!stat(used_path, &st) && + size_t baselen = used_path.len; + strbuf_addstr(&used_path, suffix[i]); + if (!stat(used_path.buf, &st) && (S_ISREG(st.st_mode) || - (S_ISDIR(st.st_mode) && is_git_directory(used_path)))) { - strcat(validated_path, suffix[i]); + (S_ISDIR(st.st_mode) && is_git_directory(used_path.buf)))) { + strbuf_addstr(&validated_path, suffix[i]); break; } + strbuf_setlen(&used_path, baselen); } if (!suffix[i]) return NULL; - gitfile = read_gitfile(used_path); - if (gitfile) - strcpy(used_path, gitfile); - if (chdir(used_path)) - gitfile = read_gitfile(used_path.buf) ; ++ gitfile = read_gitfile(used_path.buf); + if (gitfile) { + strbuf_reset(&used_path); + strbuf_addstr(&used_path, gitfile); + } + if (chdir(used_path.buf)) return NULL; - path = validated_path; + path = validated_path.buf; } - else if (chdir(path)) - return NULL; + else { + const char *gitfile = read_gitfile(path); + if (gitfile) + path = gitfile; + if (chdir(path)) + return NULL; + } - if (access("objects", X_OK) == 0 && access("refs", X_OK) == 0 && - validate_headref("HEAD") == 0) { + if (is_git_directory(".")) { set_git_dir("."); check_repository_format(); return path; @@@ -855,7 -631,7 +865,7 @@@ const char *relative_path(const char *i */ const char *remove_leading_path(const char *in, const char *prefix) { - static char buf[PATH_MAX + 1]; + static struct strbuf buf = STRBUF_INIT; int i = 0, j = 0; if (!prefix || !prefix[0]) @@@ -884,11 -660,13 +894,13 @@@ return in; while (is_dir_sep(in[j])) j++; + + strbuf_reset(&buf); if (!in[j]) - strcpy(buf, "."); + strbuf_addstr(&buf, "."); else - strcpy(buf, in + j); - return buf; + strbuf_addstr(&buf, in + j); + return buf.buf; } /* @@@ -910,11 -688,6 +922,11 @@@ * normalized, any time "../" eats up to the prefix_len part, * prefix_len is reduced. In the end prefix_len is the remaining * prefix that has not been overridden by user pathspec. + * + * NEEDSWORK: This function doesn't perform normalization w.r.t. trailing '/'. + * For everything but the root folder itself, the normalized path should not + * end with a '/', then the callers need to be fixed up accordingly. + * */ int normalize_path_copy_len(char *dst, const char *src, int *prefix_len) { diff --combined ref-filter.c index dbd8fcec24,1f718704e7..1194f10ed6 --- a/ref-filter.c +++ b/ref-filter.c @@@ -9,10 -9,6 +9,10 @@@ #include "tag.h" #include "quote.h" #include "ref-filter.h" +#include "revision.h" +#include "utf8.h" +#include "git-compat-util.h" +#include "version.h" typedef enum { FIELD_STR, FIELD_ULONG, FIELD_TIME } cmp_type; @@@ -47,48 -43,15 +47,48 @@@ static struct { "subject" }, { "body" }, { "contents" }, - { "contents:subject" }, - { "contents:body" }, - { "contents:signature" }, { "upstream" }, { "push" }, { "symref" }, { "flag" }, { "HEAD" }, { "color" }, + { "align" }, + { "end" }, +}; + +#define REF_FORMATTING_STATE_INIT { 0, NULL } + +struct align { + align_type position; + unsigned int width; +}; + +struct contents { + unsigned int lines; + struct object_id oid; +}; + +struct ref_formatting_stack { + struct ref_formatting_stack *prev; + struct strbuf output; + void (*at_end)(struct ref_formatting_stack *stack); + void *at_end_data; +}; + +struct ref_formatting_state { + int quote_style; + struct ref_formatting_stack *stack; +}; + +struct atom_value { + const char *s; + union { + struct align align; + struct contents contents; + } u; + void (*handler)(struct atom_value *atomv, struct ref_formatting_state *state); + unsigned long ul; /* used for sorting when not FIELD_STR */ }; /* @@@ -160,120 -123,6 +160,120 @@@ int parse_ref_filter_atom(const char *a return at; } +static void quote_formatting(struct strbuf *s, const char *str, int quote_style) +{ + switch (quote_style) { + case QUOTE_NONE: + strbuf_addstr(s, str); + break; + case QUOTE_SHELL: + sq_quote_buf(s, str); + break; + case QUOTE_PERL: + perl_quote_buf(s, str); + break; + case QUOTE_PYTHON: + python_quote_buf(s, str); + break; + case QUOTE_TCL: + tcl_quote_buf(s, str); + break; + } +} + +static void append_atom(struct atom_value *v, struct ref_formatting_state *state) +{ + /* + * Quote formatting is only done when the stack has a single + * element. Otherwise quote formatting is done on the + * element's entire output strbuf when the %(end) atom is + * encountered. + */ + if (!state->stack->prev) + quote_formatting(&state->stack->output, v->s, state->quote_style); + else + strbuf_addstr(&state->stack->output, v->s); +} + +static void push_stack_element(struct ref_formatting_stack **stack) +{ + struct ref_formatting_stack *s = xcalloc(1, sizeof(struct ref_formatting_stack)); + + strbuf_init(&s->output, 0); + s->prev = *stack; + *stack = s; +} + +static void pop_stack_element(struct ref_formatting_stack **stack) +{ + struct ref_formatting_stack *current = *stack; + struct ref_formatting_stack *prev = current->prev; + + if (prev) + strbuf_addbuf(&prev->output, ¤t->output); + strbuf_release(¤t->output); + free(current); + *stack = prev; +} + +static void end_align_handler(struct ref_formatting_stack *stack) +{ + struct align *align = (struct align *)stack->at_end_data; + struct strbuf s = STRBUF_INIT; + + strbuf_utf8_align(&s, align->position, align->width, stack->output.buf); + strbuf_swap(&stack->output, &s); + strbuf_release(&s); +} + +static void align_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state) +{ + struct ref_formatting_stack *new; + + push_stack_element(&state->stack); + new = state->stack; + new->at_end = end_align_handler; + new->at_end_data = &atomv->u.align; +} + +static void end_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state) +{ + struct ref_formatting_stack *current = state->stack; + struct strbuf s = STRBUF_INIT; + + if (!current->at_end) + die(_("format: %%(end) atom used without corresponding atom")); + current->at_end(current); + + /* + * Perform quote formatting when the stack element is that of + * a supporting atom. If nested then perform quote formatting + * only on the topmost supporting atom. + */ + if (!state->stack->prev->prev) { + quote_formatting(&s, current->output.buf, state->quote_style); + strbuf_swap(¤t->output, &s); + } + strbuf_release(&s); + pop_stack_element(&state->stack); +} + +static int match_atom_name(const char *name, const char *atom_name, const char **val) +{ + const char *body; + + if (!skip_prefix(name, atom_name, &body)) + return 0; /* doesn't even begin with "atom_name" */ + if (!body[0]) { + *val = NULL; /* %(atom_name) and no customization */ + return 1; + } + if (body[0] != ':') + return 0; /* "atom_namefoo" is not "atom_name" or "atom_name:..." */ + *val = body + 1; /* "atom_name:val" */ + return 1; +} + /* * In a format string, find the next occurrence of %(atom). */ @@@ -343,9 -192,7 +343,7 @@@ static int grab_objectname(const char * struct atom_value *v) { if (!strcmp(name, "objectname")) { - char *s = xmalloc(41); - strcpy(s, sha1_to_hex(sha1)); - v->s = s; + v->s = xstrdup(sha1_to_hex(sha1)); return 1; } if (!strcmp(name, "objectname:short")) { @@@ -370,10 -217,8 +368,8 @@@ static void grab_common_values(struct a if (!strcmp(name, "objecttype")) v->s = typename(obj->type); else if (!strcmp(name, "objectsize")) { - char *s = xmalloc(40); - sprintf(s, "%lu", sz); v->ul = sz; - v->s = s; + v->s = xstrfmt("%lu", sz); } else if (deref) grab_objectname(name, obj->sha1, v); @@@ -397,11 -242,8 +393,8 @@@ static void grab_tag_values(struct atom v->s = tag->tag; else if (!strcmp(name, "type") && tag->tagged) v->s = typename(tag->tagged->type); - else if (!strcmp(name, "object") && tag->tagged) { - char *s = xmalloc(41); - strcpy(s, sha1_to_hex(tag->tagged->sha1)); - v->s = s; - } + else if (!strcmp(name, "object") && tag->tagged) + v->s = xstrdup(sha1_to_hex(tag->tagged->sha1)); } } @@@ -419,32 -261,22 +412,22 @@@ static void grab_commit_values(struct a if (deref) name++; if (!strcmp(name, "tree")) { - char *s = xmalloc(41); - strcpy(s, sha1_to_hex(commit->tree->object.sha1)); - v->s = s; + v->s = xstrdup(sha1_to_hex(commit->tree->object.sha1)); } - if (!strcmp(name, "numparent")) { - char *s = xmalloc(40); + else if (!strcmp(name, "numparent")) { v->ul = commit_list_count(commit->parents); - sprintf(s, "%lu", v->ul); - v->s = s; + v->s = xstrfmt("%lu", v->ul); } else if (!strcmp(name, "parent")) { - int num = commit_list_count(commit->parents); - int i; struct commit_list *parents; - char *s = xmalloc(41 * num + 1); - v->s = s; - for (i = 0, parents = commit->parents; - parents; - parents = parents->next, i = i + 41) { + struct strbuf s = STRBUF_INIT; + for (parents = commit->parents; parents; parents = parents->next) { struct commit *parent = parents->item; - strcpy(s+i, sha1_to_hex(parent->object.sha1)); - if (parents->next) - s[i+40] = ' '; + if (parents != commit->parents) + strbuf_addch(&s, ' '); + strbuf_addstr(&s, sha1_to_hex(parent->object.sha1)); } - if (!i) - *s = '\0'; + v->s = strbuf_detach(&s, NULL); } } } @@@ -648,30 -480,6 +631,30 @@@ static void find_subpos(const char *buf *nonsiglen = *sig - buf; } +/* + * If 'lines' is greater than 0, append that many lines from the given + * 'buf' of length 'size' to the given strbuf. + */ +static void append_lines(struct strbuf *out, const char *buf, unsigned long size, int lines) +{ + int i; + const char *sp, *eol; + size_t len; + + sp = buf; + + for (i = 0; i < lines && sp < buf + size; i++) { + if (i) + strbuf_addstr(out, "\n "); + eol = memchr(sp, '\n', size - (sp - buf)); + len = eol ? eol - sp : size - (sp - buf); + strbuf_add(out, sp, len); + if (!eol) + break; + sp = eol + 1; + } +} + /* See grab_values */ static void grab_sub_body_contents(struct atom_value *val, int deref, struct object *obj, void *buf, unsigned long sz) { @@@ -682,7 -490,6 +665,7 @@@ for (i = 0; i < used_atom_cnt; i++) { const char *name = used_atom[i]; struct atom_value *v = &val[i]; + const char *valp = NULL; if (!!deref != (*name == '*')) continue; if (deref) @@@ -692,8 -499,7 +675,8 @@@ strcmp(name, "contents") && strcmp(name, "contents:subject") && strcmp(name, "contents:body") && - strcmp(name, "contents:signature")) + strcmp(name, "contents:signature") && + !starts_with(name, "contents:lines=")) continue; if (!subpos) find_subpos(buf, sz, @@@ -713,16 -519,6 +696,16 @@@ v->s = xmemdupz(sigpos, siglen); else if (!strcmp(name, "contents")) v->s = xstrdup(subpos); + else if (skip_prefix(name, "contents:lines=", &valp)) { + struct strbuf s = STRBUF_INIT; + const char *contents_end = bodylen + bodypos - siglen; + + if (strtoul_ui(valp, 10, &v->u.contents.lines)) + die(_("positive value expected contents:lines=%s"), valp); + /* Size is the length of the message after removing the signature */ + append_lines(&s, subpos, contents_end - subpos, v->u.contents.lines); + v->s = strbuf_detach(&s, NULL); + } } } @@@ -808,11 -604,8 +791,11 @@@ static void populate_value(struct ref_a int deref = 0; const char *refname; const char *formatp; + const char *valp; struct branch *branch = NULL; + v->handler = append_atom; + if (*name == '*') { deref = 1; name++; @@@ -843,12 -636,10 +826,12 @@@ refname = branch_get_push(branch, NULL); if (!refname) continue; - } else if (starts_with(name, "color:")) { + } else if (match_atom_name(name, "color", &valp)) { char color[COLOR_MAXLEN] = ""; - if (color_parse(name + 6, color) < 0) + if (!valp) + die(_("expected format: %%(color:)")); + if (color_parse(valp, color) < 0) die(_("unable to parse format")); v->s = xstrdup(color); continue; @@@ -878,48 -669,6 +861,48 @@@ else v->s = " "; continue; + } else if (match_atom_name(name, "align", &valp)) { + struct align *align = &v->u.align; + struct strbuf **s, **to_free; + int width = -1; + + if (!valp) + die(_("expected format: %%(align:,)")); + + /* + * TODO: Implement a function similar to strbuf_split_str() + * which would omit the separator from the end of each value. + */ + s = to_free = strbuf_split_str(valp, ',', 0); + + align->position = ALIGN_LEFT; + + while (*s) { + /* Strip trailing comma */ + if (s[1]) + strbuf_setlen(s[0], s[0]->len - 1); + if (!strtoul_ui(s[0]->buf, 10, (unsigned int *)&width)) + ; + else if (!strcmp(s[0]->buf, "left")) + align->position = ALIGN_LEFT; + else if (!strcmp(s[0]->buf, "right")) + align->position = ALIGN_RIGHT; + else if (!strcmp(s[0]->buf, "middle")) + align->position = ALIGN_MIDDLE; + else + die(_("improper format entered align:%s"), s[0]->buf); + s++; + } + + if (width < 0) + die(_("positive width expected with the %%(align) atom")); + align->width = width; + strbuf_list_free(to_free); + v->handler = align_atom_handler; + continue; + } else if (!strcmp(name, "end")) { + v->handler = end_atom_handler; + continue; } else continue; @@@ -934,7 -683,6 +917,6 @@@ else if (!strcmp(formatp, "track") && (starts_with(name, "upstream") || starts_with(name, "push"))) { - char buf[40]; if (stat_tracking_info(branch, &num_ours, &num_theirs, NULL)) @@@ -942,17 -690,13 +924,13 @@@ if (!num_ours && !num_theirs) v->s = ""; - else if (!num_ours) { - sprintf(buf, "[behind %d]", num_theirs); - v->s = xstrdup(buf); - } else if (!num_theirs) { - sprintf(buf, "[ahead %d]", num_ours); - v->s = xstrdup(buf); - } else { - sprintf(buf, "[ahead %d, behind %d]", - num_ours, num_theirs); - v->s = xstrdup(buf); - } + else if (!num_ours) + v->s = xstrfmt("[behind %d]", num_theirs); + else if (!num_theirs) + v->s = xstrfmt("[ahead %d]", num_ours); + else + v->s = xstrfmt("[ahead %d, behind %d]", + num_ours, num_theirs); continue; } else if (!strcmp(formatp, "trackshort") && (starts_with(name, "upstream") || @@@ -979,12 -723,8 +957,8 @@@ if (!deref) v->s = refname; - else { - int len = strlen(refname); - char *s = xmalloc(len + 4); - sprintf(s, "%s^{}", refname); - v->s = s; - } + else + v->s = xstrfmt("%s^{}", refname); } for (i = 0; i < used_atom_cnt; i++) { @@@ -1051,143 -791,11 +1025,143 @@@ static void get_ref_atom_value(struct r *v = &ref->value[atom]; } +enum contains_result { + CONTAINS_UNKNOWN = -1, + CONTAINS_NO = 0, + CONTAINS_YES = 1 +}; + +/* + * Mimicking the real stack, this stack lives on the heap, avoiding stack + * overflows. + * + * At each recursion step, the stack items points to the commits whose + * ancestors are to be inspected. + */ +struct contains_stack { + int nr, alloc; + struct contains_stack_entry { + struct commit *commit; + struct commit_list *parents; + } *contains_stack; +}; + +static int in_commit_list(const struct commit_list *want, struct commit *c) +{ + for (; want; want = want->next) + if (!hashcmp(want->item->object.sha1, c->object.sha1)) + return 1; + return 0; +} + +/* + * Test whether the candidate or one of its parents is contained in the list. + * Do not recurse to find out, though, but return -1 if inconclusive. + */ +static enum contains_result contains_test(struct commit *candidate, + const struct commit_list *want) +{ + /* was it previously marked as containing a want commit? */ + if (candidate->object.flags & TMP_MARK) + return 1; + /* or marked as not possibly containing a want commit? */ + if (candidate->object.flags & UNINTERESTING) + return 0; + /* or are we it? */ + if (in_commit_list(want, candidate)) { + candidate->object.flags |= TMP_MARK; + return 1; + } + + if (parse_commit(candidate) < 0) + return 0; + + return -1; +} + +static void push_to_contains_stack(struct commit *candidate, struct contains_stack *contains_stack) +{ + ALLOC_GROW(contains_stack->contains_stack, contains_stack->nr + 1, contains_stack->alloc); + contains_stack->contains_stack[contains_stack->nr].commit = candidate; + contains_stack->contains_stack[contains_stack->nr++].parents = candidate->parents; +} + +static enum contains_result contains_tag_algo(struct commit *candidate, + const struct commit_list *want) +{ + struct contains_stack contains_stack = { 0, 0, NULL }; + int result = contains_test(candidate, want); + + if (result != CONTAINS_UNKNOWN) + return result; + + push_to_contains_stack(candidate, &contains_stack); + while (contains_stack.nr) { + struct contains_stack_entry *entry = &contains_stack.contains_stack[contains_stack.nr - 1]; + struct commit *commit = entry->commit; + struct commit_list *parents = entry->parents; + + if (!parents) { + commit->object.flags |= UNINTERESTING; + contains_stack.nr--; + } + /* + * If we just popped the stack, parents->item has been marked, + * therefore contains_test will return a meaningful 0 or 1. + */ + else switch (contains_test(parents->item, want)) { + case CONTAINS_YES: + commit->object.flags |= TMP_MARK; + contains_stack.nr--; + break; + case CONTAINS_NO: + entry->parents = parents->next; + break; + case CONTAINS_UNKNOWN: + push_to_contains_stack(parents->item, &contains_stack); + break; + } + } + free(contains_stack.contains_stack); + return contains_test(candidate, want); +} + +static int commit_contains(struct ref_filter *filter, struct commit *commit) +{ + if (filter->with_commit_tag_algo) + return contains_tag_algo(commit, filter->with_commit); + return is_descendant_of(commit, filter->with_commit); +} + +/* + * Return 1 if the refname matches one of the patterns, otherwise 0. + * A pattern can be a literal prefix (e.g. a refname "refs/heads/master" + * matches a pattern "refs/heads/mas") or a wildcard (e.g. the same ref + * matches "refs/heads/mas*", too). + */ +static int match_pattern(const char **patterns, const char *refname) +{ + /* + * When no '--format' option is given we need to skip the prefix + * for matching refs of tags and branches. + */ + (void)(skip_prefix(refname, "refs/tags/", &refname) || + skip_prefix(refname, "refs/heads/", &refname) || + skip_prefix(refname, "refs/remotes/", &refname) || + skip_prefix(refname, "refs/", &refname)); + + for (; *patterns; patterns++) { + if (!wildmatch(*patterns, refname, 0, NULL)) + return 1; + } + return 0; +} + /* * Return 1 if the refname matches one of the patterns, otherwise 0. * A pattern can be path prefix (e.g. a refname "refs/heads/master" - * matches a pattern "refs/heads/") or a wildcard (e.g. the same ref - * matches "refs/heads/m*",too). + * matches a pattern "refs/heads/" but not "refs/heads/m") or a + * wildcard (e.g. the same ref matches "refs/heads/m*", too). */ static int match_name_as_path(const char **pattern, const char *refname) { @@@ -1208,48 -816,6 +1182,48 @@@ return 0; } +/* Return 1 if the refname matches one of the patterns, otherwise 0. */ +static int filter_pattern_match(struct ref_filter *filter, const char *refname) +{ + if (!*filter->name_patterns) + return 1; /* No pattern always matches */ + if (filter->match_as_path) + return match_name_as_path(filter->name_patterns, refname); + return match_pattern(filter->name_patterns, refname); +} + +/* + * Given a ref (sha1, refname), check if the ref belongs to the array + * of sha1s. If the given ref is a tag, check if the given tag points + * at one of the sha1s in the given sha1 array. + * the given sha1_array. + * NEEDSWORK: + * 1. Only a single level of inderection is obtained, we might want to + * change this to account for multiple levels (e.g. annotated tags + * pointing to annotated tags pointing to a commit.) + * 2. As the refs are cached we might know what refname peels to without + * the need to parse the object via parse_object(). peel_ref() might be a + * more efficient alternative to obtain the pointee. + */ +static const unsigned char *match_points_at(struct sha1_array *points_at, + const unsigned char *sha1, + const char *refname) +{ + const unsigned char *tagged_sha1 = NULL; + struct object *obj; + + if (sha1_array_lookup(points_at, sha1) >= 0) + return sha1; + obj = parse_object(sha1); + if (!obj) + die(_("malformed object at '%s'"), refname); + if (obj->type == OBJ_TAG) + tagged_sha1 = ((struct tag *)obj)->tagged->sha1; + if (tagged_sha1 && sha1_array_lookup(points_at, tagged_sha1) >= 0) + return tagged_sha1; + return NULL; +} + /* Allocate space for a new ref_array_item and copy the objectname and flag to it */ static struct ref_array_item *new_ref_array_item(const char *refname, const unsigned char *objectname, @@@ -1265,34 -831,6 +1239,34 @@@ return ref; } +static int filter_ref_kind(struct ref_filter *filter, const char *refname) +{ + unsigned int i; + + static struct { + const char *prefix; + unsigned int kind; + } ref_kind[] = { + { "refs/heads/" , FILTER_REFS_BRANCHES }, + { "refs/remotes/" , FILTER_REFS_REMOTES }, + { "refs/tags/", FILTER_REFS_TAGS} + }; + + if (filter->kind == FILTER_REFS_BRANCHES || + filter->kind == FILTER_REFS_REMOTES || + filter->kind == FILTER_REFS_TAGS) + return filter->kind; + else if (!strcmp(refname, "HEAD")) + return FILTER_REFS_DETACHED_HEAD; + + for (i = 0; i < ARRAY_SIZE(ref_kind); i++) { + if (starts_with(refname, ref_kind[i].prefix)) + return ref_kind[i].kind; + } + + return FILTER_REFS_OTHERS; +} + /* * A call-back given to for_each_ref(). Filter refs and keep them for * later object processing. @@@ -1302,8 -840,6 +1276,8 @@@ static int ref_filter_handler(const cha struct ref_filter_cbdata *ref_cbdata = cb_data; struct ref_filter *filter = ref_cbdata->filter; struct ref_array_item *ref; + struct commit *commit = NULL; + unsigned int kind; if (flag & REF_BAD_NAME) { warning("ignoring ref with broken name %s", refname); @@@ -1315,43 -851,18 +1289,43 @@@ return 0; } - if (*filter->name_patterns && !match_name_as_path(filter->name_patterns, refname)) + /* Obtain the current ref kind from filter_ref_kind() and ignore unwanted refs. */ + kind = filter_ref_kind(filter, refname); + if (!(kind & filter->kind)) + return 0; + + if (!filter_pattern_match(filter, refname)) + return 0; + + if (filter->points_at.nr && !match_points_at(&filter->points_at, oid->hash, refname)) return 0; + /* + * A merge filter is applied on refs pointing to commits. Hence + * obtain the commit using the 'oid' available and discard all + * non-commits early. The actual filtering is done later. + */ + if (filter->merge_commit || filter->with_commit || filter->verbose) { + commit = lookup_commit_reference_gently(oid->hash, 1); + if (!commit) + return 0; + /* We perform the filtering for the '--contains' option */ + if (filter->with_commit && + !commit_contains(filter, commit)) + return 0; + } + /* * We do not open the object yet; sort may only need refname * to do its job and the resulting list may yet to be pruned * by maxcount logic. */ ref = new_ref_array_item(refname, oid->hash, flag); + ref->commit = commit; REALLOC_ARRAY(ref_cbdata->array->items, ref_cbdata->array->nr + 1); ref_cbdata->array->items[ref_cbdata->array->nr++] = ref; + ref->kind = kind; return 0; } @@@ -1374,50 -885,6 +1348,50 @@@ void ref_array_clear(struct ref_array * array->nr = array->alloc = 0; } +static void do_merge_filter(struct ref_filter_cbdata *ref_cbdata) +{ + struct rev_info revs; + int i, old_nr; + struct ref_filter *filter = ref_cbdata->filter; + struct ref_array *array = ref_cbdata->array; + struct commit **to_clear = xcalloc(sizeof(struct commit *), array->nr); + + init_revisions(&revs, NULL); + + for (i = 0; i < array->nr; i++) { + struct ref_array_item *item = array->items[i]; + add_pending_object(&revs, &item->commit->object, item->refname); + to_clear[i] = item->commit; + } + + filter->merge_commit->object.flags |= UNINTERESTING; + add_pending_object(&revs, &filter->merge_commit->object, ""); + + revs.limited = 1; + if (prepare_revision_walk(&revs)) + die(_("revision walk setup failed")); + + old_nr = array->nr; + array->nr = 0; + + for (i = 0; i < old_nr; i++) { + struct ref_array_item *item = array->items[i]; + struct commit *commit = item->commit; + + int is_merged = !!(commit->object.flags & UNINTERESTING); + + if (is_merged == (filter->merge == REF_FILTER_MERGED_INCLUDE)) + array->items[array->nr++] = array->items[i]; + else + free_array_item(item); + } + + for (i = 0; i < old_nr; i++) + clear_commit_marks(to_clear[i], ALL_REV_FLAGS); + clear_commit_marks(filter->merge_commit, ALL_REV_FLAGS); + free(to_clear); +} + /* * API for filtering a set of refs. Based on the type of refs the user * has requested, we iterate through those refs and apply filters @@@ -1427,44 -894,17 +1401,44 @@@ int filter_refs(struct ref_array *array, struct ref_filter *filter, unsigned int type) { struct ref_filter_cbdata ref_cbdata; + int ret = 0; + unsigned int broken = 0; ref_cbdata.array = array; ref_cbdata.filter = filter; - if (type & (FILTER_REFS_ALL | FILTER_REFS_INCLUDE_BROKEN)) - return for_each_rawref(ref_filter_handler, &ref_cbdata); - else if (type & FILTER_REFS_ALL) - return for_each_ref(ref_filter_handler, &ref_cbdata); - else + if (type & FILTER_REFS_INCLUDE_BROKEN) + broken = 1; + filter->kind = type & FILTER_REFS_KIND_MASK; + + /* Simple per-ref filtering */ + if (!filter->kind) die("filter_refs: invalid type"); - return 0; + else { + /* + * For common cases where we need only branches or remotes or tags, + * we only iterate through those refs. If a mix of refs is needed, + * we iterate over all refs and filter out required refs with the help + * of filter_ref_kind(). + */ + if (filter->kind == FILTER_REFS_BRANCHES) + ret = for_each_fullref_in("refs/heads/", ref_filter_handler, &ref_cbdata, broken); + else if (filter->kind == FILTER_REFS_REMOTES) + ret = for_each_fullref_in("refs/remotes/", ref_filter_handler, &ref_cbdata, broken); + else if (filter->kind == FILTER_REFS_TAGS) + ret = for_each_fullref_in("refs/tags/", ref_filter_handler, &ref_cbdata, broken); + else if (filter->kind & FILTER_REFS_ALL) + ret = for_each_fullref_in("", ref_filter_handler, &ref_cbdata, broken); + if (!ret && (filter->kind & FILTER_REFS_DETACHED_HEAD)) + head_ref(ref_filter_handler, &ref_cbdata); + } + + + /* Filters that need revision walking */ + if (filter->merge_commit) + do_merge_filter(&ref_cbdata); + + return ret; } static int cmp_ref_sorting(struct ref_sorting *s, struct ref_array_item *a, struct ref_array_item *b) @@@ -1475,19 -915,19 +1449,19 @@@ get_ref_atom_value(a, s->atom, &va); get_ref_atom_value(b, s->atom, &vb); - switch (cmp_type) { - case FIELD_STR: + if (s->version) + cmp = versioncmp(va->s, vb->s); + else if (cmp_type == FIELD_STR) cmp = strcmp(va->s, vb->s); - break; - default: + else { if (va->ul < vb->ul) cmp = -1; else if (va->ul == vb->ul) cmp = 0; else cmp = 1; - break; } + return (s->reverse) ? -cmp : cmp; } @@@ -1512,6 -952,32 +1486,6 @@@ void ref_array_sort(struct ref_sorting qsort(array->items, array->nr, sizeof(struct ref_array_item *), compare_refs); } -static void print_value(struct atom_value *v, int quote_style) -{ - struct strbuf sb = STRBUF_INIT; - switch (quote_style) { - case QUOTE_NONE: - fputs(v->s, stdout); - break; - case QUOTE_SHELL: - sq_quote_buf(&sb, v->s); - break; - case QUOTE_PERL: - perl_quote_buf(&sb, v->s); - break; - case QUOTE_PYTHON: - python_quote_buf(&sb, v->s); - break; - case QUOTE_TCL: - tcl_quote_buf(&sb, v->s); - break; - } - if (quote_style != QUOTE_NONE) { - fputs(sb.buf, stdout); - strbuf_release(&sb); - } -} - static int hex1(char ch) { if ('0' <= ch && ch <= '9') @@@ -1530,10 -996,8 +1504,10 @@@ static int hex2(const char *cp return -1; } -static void emit(const char *cp, const char *ep) +static void append_literal(const char *cp, const char *ep, struct ref_formatting_state *state) { + struct strbuf *s = &state->stack->output; + while (*cp && (!ep || cp < ep)) { if (*cp == '%') { if (cp[1] == '%') @@@ -1541,13 -1005,13 +1515,13 @@@ else { int ch = hex2(cp + 1); if (0 <= ch) { - putchar(ch); + strbuf_addch(s, ch); cp += 3; continue; } } } - putchar(*cp); + strbuf_addch(s, *cp); cp++; } } @@@ -1555,24 -1019,19 +1529,24 @@@ void show_ref_array_item(struct ref_array_item *info, const char *format, int quote_style) { const char *cp, *sp, *ep; + struct strbuf *final_buf; + struct ref_formatting_state state = REF_FORMATTING_STATE_INIT; + + state.quote_style = quote_style; + push_stack_element(&state.stack); for (cp = format; *cp && (sp = find_next(cp)); cp = ep + 1) { struct atom_value *atomv; ep = strchr(sp, ')'); if (cp < sp) - emit(cp, sp); + append_literal(cp, sp, &state); get_ref_atom_value(info, parse_ref_filter_atom(sp + 2, ep), &atomv); - print_value(atomv, quote_style); + atomv->handler(atomv, &state); } if (*cp) { sp = cp + strlen(cp); - emit(cp, sp); + append_literal(cp, sp, &state); } if (need_color_reset_at_eol) { struct atom_value resetv; @@@ -1581,13 -1040,8 +1555,13 @@@ if (color_parse("reset", color) < 0) die("BUG: couldn't parse 'reset' as a color"); resetv.s = color; - print_value(&resetv, quote_style); + append_atom(&resetv, &state); } + if (state.stack->prev) + die(_("format: %%(end) atom missing")); + final_buf = &state.stack->output; + fwrite(final_buf->buf, 1, final_buf->len, stdout); + pop_stack_element(&state.stack); putchar('\n'); } @@@ -1620,29 -1074,7 +1594,29 @@@ int parse_opt_ref_sorting(const struct s->reverse = 1; arg++; } + if (skip_prefix(arg, "version:", &arg) || + skip_prefix(arg, "v:", &arg)) + s->version = 1; len = strlen(arg); s->atom = parse_ref_filter_atom(arg, arg+len); return 0; } + +int parse_opt_merge_filter(const struct option *opt, const char *arg, int unset) +{ + struct ref_filter *rf = opt->value; + unsigned char sha1[20]; + + rf->merge = starts_with(opt->long_name, "no") + ? REF_FILTER_MERGED_OMIT + : REF_FILTER_MERGED_INCLUDE; + + if (get_sha1(arg, sha1)) + die(_("malformed object name %s"), arg); + + rf->merge_commit = lookup_commit_reference_gently(sha1, 0); + if (!rf->merge_commit) + return opterror(opt, "must point to a commit", 0); + + return 0; +} diff --combined refs.c index 91c88bad4a,b2a922945d..132eff52ca --- a/refs.c +++ b/refs.c @@@ -304,11 -304,6 +304,11 @@@ struct ref_entry }; static void read_loose_refs(const char *dirname, struct ref_dir *dir); +static int search_ref_dir(struct ref_dir *dir, const char *refname, size_t len); +static struct ref_entry *create_dir_entry(struct ref_cache *ref_cache, + const char *dirname, size_t len, + int incomplete); +static void add_entry_to_dir(struct ref_dir *dir, struct ref_entry *entry); static struct ref_dir *get_ref_dir(struct ref_entry *entry) { @@@ -317,24 -312,6 +317,24 @@@ dir = &entry->u.subdir; if (entry->flag & REF_INCOMPLETE) { read_loose_refs(entry->name, dir); + + /* + * Manually add refs/bisect, which, being + * per-worktree, might not appear in the directory + * listing for refs/ in the main repo. + */ + if (!strcmp(entry->name, "refs/")) { + int pos = search_ref_dir(dir, "refs/bisect/", 12); + if (pos < 0) { + struct ref_entry *child_entry; + child_entry = create_dir_entry(dir->ref_cache, + "refs/bisect/", + 12, 1); + add_entry_to_dir(dir, child_entry); + read_loose_refs("refs/bisect", + &child_entry->u.subdir); + } + } entry->flag &= ~REF_INCOMPLETE; } return dir; @@@ -1602,16 -1579,15 +1602,15 @@@ static int resolve_missing_loose_ref(co } /* This function needs to return a meaningful errno on failure */ - static const char *resolve_ref_unsafe_1(const char *refname, - int resolve_flags, - unsigned char *sha1, - int *flags, - struct strbuf *sb_path) + static const char *resolve_ref_1(const char *refname, + int resolve_flags, + unsigned char *sha1, + int *flags, + struct strbuf *sb_refname, + struct strbuf *sb_path, + struct strbuf *sb_contents) { int depth = MAXDEPTH; - ssize_t len; - char buffer[256]; - static char refname_buffer[256]; int bad_name = 0; if (flags) @@@ -1677,19 -1653,18 +1676,18 @@@ /* Follow "normalized" - ie "refs/.." symlinks by hand */ if (S_ISLNK(st.st_mode)) { - len = readlink(path, buffer, sizeof(buffer)-1); - if (len < 0) { + strbuf_reset(sb_contents); + if (strbuf_readlink(sb_contents, path, 0) < 0) { if (errno == ENOENT || errno == EINVAL) /* inconsistent with lstat; retry */ goto stat_ref; else return NULL; } - buffer[len] = 0; - if (starts_with(buffer, "refs/") && - !check_refname_format(buffer, 0)) { - strcpy(refname_buffer, buffer); - refname = refname_buffer; + if (starts_with(sb_contents->buf, "refs/") && + !check_refname_format(sb_contents->buf, 0)) { + strbuf_swap(sb_refname, sb_contents); + refname = sb_refname->buf; if (flags) *flags |= REF_ISSYMREF; if (resolve_flags & RESOLVE_REF_NO_RECURSE) { @@@ -1718,28 -1693,26 +1716,26 @@@ else return NULL; } - len = read_in_full(fd, buffer, sizeof(buffer)-1); - if (len < 0) { + strbuf_reset(sb_contents); + if (strbuf_read(sb_contents, fd, 256) < 0) { int save_errno = errno; close(fd); errno = save_errno; return NULL; } close(fd); - while (len && isspace(buffer[len-1])) - len--; - buffer[len] = '\0'; + strbuf_rtrim(sb_contents); /* * Is it a symbolic ref? */ - if (!starts_with(buffer, "ref:")) { + if (!starts_with(sb_contents->buf, "ref:")) { /* * Please note that FETCH_HEAD has a second * line containing other data. */ - if (get_sha1_hex(buffer, sha1) || - (buffer[40] != '\0' && !isspace(buffer[40]))) { + if (get_sha1_hex(sb_contents->buf, sha1) || + (sb_contents->buf[40] != '\0' && !isspace(sb_contents->buf[40]))) { if (flags) *flags |= REF_ISBROKEN; errno = EINVAL; @@@ -1754,10 -1727,12 +1750,12 @@@ } if (flags) *flags |= REF_ISSYMREF; - buf = buffer + 4; + buf = sb_contents->buf + 4; while (isspace(*buf)) buf++; - refname = strcpy(refname_buffer, buf); + strbuf_reset(sb_refname); + strbuf_addstr(sb_refname, buf); + refname = sb_refname->buf; if (resolve_flags & RESOLVE_REF_NO_RECURSE) { hashclr(sha1); return refname; @@@ -1779,10 -1754,15 +1777,15 @@@ const char *resolve_ref_unsafe(const char *refname, int resolve_flags, unsigned char *sha1, int *flags) { + static struct strbuf sb_refname = STRBUF_INIT; + struct strbuf sb_contents = STRBUF_INIT; struct strbuf sb_path = STRBUF_INIT; - const char *ret = resolve_ref_unsafe_1(refname, resolve_flags, - sha1, flags, &sb_path); + const char *ret; + + ret = resolve_ref_1(refname, resolve_flags, sha1, flags, + &sb_refname, &sb_path, &sb_contents); strbuf_release(&sb_path); + strbuf_release(&sb_contents); return ret; } @@@ -2131,15 -2111,6 +2134,15 @@@ int for_each_ref_in(const char *prefix return do_for_each_ref(&ref_cache, prefix, fn, strlen(prefix), 0, cb_data); } +int for_each_fullref_in(const char *prefix, each_ref_fn fn, void *cb_data, unsigned int broken) +{ + unsigned int flag = 0; + + if (broken) + flag = DO_FOR_EACH_INCLUDE_BROKEN; + return do_for_each_ref(&ref_cache, prefix, fn, 0, flag, cb_data); +} + int for_each_ref_in_submodule(const char *submodule, const char *prefix, each_ref_fn fn, void *cb_data) { @@@ -2222,8 -2193,7 +2225,7 @@@ int for_each_glob_ref_in(each_ref_fn fn if (!has_glob_specials(pattern)) { /* Append implied '/' '*' if not present. */ - if (real_pattern.buf[real_pattern.len - 1] != '/') - strbuf_addch(&real_pattern, '/'); + strbuf_complete(&real_pattern, '/'); /* No need to check for '*', there is none. */ strbuf_addch(&real_pattern, '*'); } @@@ -2681,8 -2651,6 +2683,8 @@@ struct pack_refs_cb_data struct ref_to_prune *ref_to_prune; }; +static int is_per_worktree_ref(const char *refname); + /* * An each_ref_entry_fn that is run over loose references only. If * the loose reference can be packed, add an entry in the packed ref @@@ -2696,10 -2664,6 +2698,10 @@@ static int pack_if_possible_fn(struct r struct ref_entry *packed_entry; int is_tag_ref = starts_with(entry->name, "refs/tags/"); + /* Do not pack per-worktree refs: */ + if (is_per_worktree_ref(entry->name)) + return 0; + /* ALWAYS pack tags */ if (!(cb->flags & PACK_REFS_ALL) && !is_tag_ref) return 0; @@@ -2730,7 -2694,7 +2732,7 @@@ int namelen = strlen(entry->name) + 1; struct ref_to_prune *n = xcalloc(1, sizeof(*n) + namelen); hashcpy(n->sha1, entry->u.value.oid.hash); - strcpy(n->name, entry->name); + memcpy(n->name, entry->name, namelen); /* includes NUL */ n->next = cb->ref_to_prune; cb->ref_to_prune = n; } @@@ -2894,8 -2858,7 +2896,8 @@@ static int delete_ref_loose(struct ref_ static int is_per_worktree_ref(const char *refname) { - return !strcmp(refname, "HEAD"); + return !strcmp(refname, "HEAD") || + starts_with(refname, "refs/bisect/"); } static int is_pseudoref_syntax(const char *refname) @@@ -3365,10 -3328,10 +3367,10 @@@ static int log_ref_write_fd(int fd, con msglen = msg ? strlen(msg) : 0; maxlen = strlen(committer) + msglen + 100; logrec = xmalloc(maxlen); - len = sprintf(logrec, "%s %s %s\n", - sha1_to_hex(old_sha1), - sha1_to_hex(new_sha1), - committer); + len = xsnprintf(logrec, maxlen, "%s %s %s\n", + sha1_to_hex(old_sha1), + sha1_to_hex(new_sha1), + committer); if (msglen) len += copy_msg(logrec + len - 1, msg) - 1; @@@ -4020,10 -3983,10 +4022,10 @@@ void ref_transaction_free(struct ref_tr static struct ref_update *add_update(struct ref_transaction *transaction, const char *refname) { - size_t len = strlen(refname); - struct ref_update *update = xcalloc(1, sizeof(*update) + len + 1); + size_t len = strlen(refname) + 1; + struct ref_update *update = xcalloc(1, sizeof(*update) + len); - strcpy((char *)update->refname, refname); + memcpy((char *)update->refname, refname, len); /* includes NUL */ ALLOC_GROW(transaction->updates, transaction->nr + 1, transaction->alloc); transaction->updates[transaction->nr++] = update; return update; diff --combined setup.c index e41e5e1a82,2b64cbbbfa..b264471691 --- a/setup.c +++ b/setup.c @@@ -99,10 -99,7 +99,7 @@@ char *prefix_path_gently(const char *pr return NULL; } } else { - sanitized = xmalloc(len + strlen(path) + 1); - if (len) - memcpy(sanitized, prefix, len); - strcpy(sanitized + len, path); + sanitized = xstrfmt("%.*s%s", len, prefix, path); if (remaining_prefix) *remaining_prefix = len; if (normalize_path_copy_len(sanitized, sanitized, remaining_prefix)) { @@@ -228,22 -225,15 +225,22 @@@ void verify_non_filename(const char *pr } int get_common_dir(struct strbuf *sb, const char *gitdir) +{ + const char *git_env_common_dir = getenv(GIT_COMMON_DIR_ENVIRONMENT); + if (git_env_common_dir) { + strbuf_addstr(sb, git_env_common_dir); + return 1; + } else { + return get_common_dir_noenv(sb, gitdir); + } +} + +int get_common_dir_noenv(struct strbuf *sb, const char *gitdir) { struct strbuf data = STRBUF_INIT; struct strbuf path = STRBUF_INIT; - const char *git_common_dir = getenv(GIT_COMMON_DIR_ENVIRONMENT); int ret = 0; - if (git_common_dir) { - strbuf_addstr(sb, git_common_dir); - return 1; - } + strbuf_addf(&path, "%s/commondir", gitdir); if (file_exists(path.buf)) { if (strbuf_read_file(&data, path.buf, 0) <= 0) @@@ -475,11 -465,8 +472,8 @@@ const char *read_gitfile_gently(const c if (!is_absolute_path(dir) && (slash = strrchr(path, '/'))) { size_t pathlen = slash+1 - path; - size_t dirlen = pathlen + len - 8; - dir = xmalloc(dirlen + 1); - strncpy(dir, path, pathlen); - strncpy(dir + pathlen, buf + 8, len - 8); - dir[dirlen] = '\0'; + dir = xstrfmt("%.*s%.*s", (int)pathlen, path, + (int)(len - 8), buf + 8); free(buf); buf = dir; } diff --combined sha1_file.c index ca699d7beb,cc3de244eb..50896ff1eb --- a/sha1_file.c +++ b/sha1_file.c @@@ -208,44 -208,25 +208,25 @@@ const char *sha1_file_name(const unsign * provided by the caller. which should be "pack" or "idx". */ static char *sha1_get_pack_name(const unsigned char *sha1, - char **name, char **base, const char *which) + struct strbuf *buf, + const char *which) { - static const char hex[] = "0123456789abcdef"; - char *buf; - int i; - - if (!*base) { - const char *sha1_file_directory = get_object_directory(); - int len = strlen(sha1_file_directory); - *base = xmalloc(len + 60); - sprintf(*base, "%s/pack/pack-1234567890123456789012345678901234567890.%s", - sha1_file_directory, which); - *name = *base + len + 11; - } - - buf = *name; - - for (i = 0; i < 20; i++) { - unsigned int val = *sha1++; - *buf++ = hex[val >> 4]; - *buf++ = hex[val & 0xf]; - } - - return *base; + strbuf_reset(buf); + strbuf_addf(buf, "%s/pack/pack-%s.%s", get_object_directory(), + sha1_to_hex(sha1), which); + return buf->buf; } char *sha1_pack_name(const unsigned char *sha1) { - static char *name, *base; - - return sha1_get_pack_name(sha1, &name, &base, "pack"); + static struct strbuf buf = STRBUF_INIT; + return sha1_get_pack_name(sha1, &buf, "pack"); } char *sha1_pack_index_name(const unsigned char *sha1) { - static char *name, *base; - - return sha1_get_pack_name(sha1, &name, &base, "idx"); + static struct strbuf buf = STRBUF_INIT; + return sha1_get_pack_name(sha1, &buf, "idx"); } struct alternate_object_database *alt_odb_list; @@@ -671,13 -652,15 +652,15 @@@ static int check_packed_git_idx(const c int open_pack_index(struct packed_git *p) { char *idx_name; + size_t len; int ret; if (p->index_data) return 0; - idx_name = xstrdup(p->pack_name); - strcpy(idx_name + strlen(idx_name) - strlen(".pack"), ".idx"); + if (!strip_suffix(p->pack_name, ".pack", &len)) + die("BUG: pack_name does not end in .pack"); + idx_name = xstrfmt("%.*s.idx", (int)len, p->pack_name); ret = check_packed_git_idx(idx_name, p); free(idx_name); return ret; @@@ -786,37 -769,6 +769,37 @@@ void close_pack_windows(struct packed_g } } +static int close_pack_fd(struct packed_git *p) +{ + if (p->pack_fd < 0) + return 0; + + close(p->pack_fd); + pack_open_fds--; + p->pack_fd = -1; + + return 1; +} + +static void close_pack(struct packed_git *p) +{ + close_pack_windows(p); + close_pack_fd(p); + close_pack_index(p); +} + +void close_all_packs(void) +{ + struct packed_git *p; + + for (p = packed_git; p; p = p->next) + if (p->do_not_close) + die("BUG! Want to close pack marked 'do-not-close'"); + else + close_pack(p); +} + + /* * The LRU pack is the one with the oldest MRU window, preferring packs * with no used windows, or the oldest mtime if it has no windows allocated. @@@ -884,8 -836,12 +867,8 @@@ static int close_one_pack(void find_lru_pack(p, &lru_p, &mru_w, &accept_windows_inuse); } - if (lru_p) { - close(lru_p->pack_fd); - pack_open_fds--; - lru_p->pack_fd = -1; - return 1; - } + if (lru_p) + return close_pack_fd(lru_p); return 0; } @@@ -925,7 -881,12 +908,7 @@@ void free_pack_by_name(const char *pack p = *pp; if (strcmp(pack_name, p->pack_name) == 0) { clear_delta_base_cache(); - close_pack_windows(p); - if (p->pack_fd != -1) { - close(p->pack_fd); - pack_open_fds--; - } - close_pack_index(p); + close_pack(p); free(p->bad_object_sha1); *pp = p->next; if (last_found_pack == p) @@@ -1059,7 -1020,11 +1042,7 @@@ static int open_packed_git(struct packe { if (!open_packed_git_1(p)) return 0; - if (p->pack_fd != -1) { - close(p->pack_fd); - pack_open_fds--; - p->pack_fd = -1; - } + close_pack_fd(p); return -1; } @@@ -1125,8 -1090,11 +1108,8 @@@ unsigned char *use_pack(struct packed_g p->pack_name, strerror(errno)); if (!win->offset && win->len == p->pack_size - && !p->do_not_close) { - close(p->pack_fd); - pack_open_fds--; - p->pack_fd = -1; - } + && !p->do_not_close) + close_pack_fd(p); pack_mmap_calls++; pack_open_windows++; if (pack_mapped > peak_pack_mapped) @@@ -1161,11 -1129,12 +1144,12 @@@ static void try_to_free_pack_memory(siz release_pack_memory(size); } - struct packed_git *add_packed_git(const char *path, int path_len, int local) + struct packed_git *add_packed_git(const char *path, size_t path_len, int local) { static int have_set_try_to_free_routine; struct stat st; - struct packed_git *p = alloc_packed_git(path_len + 2); + size_t alloc; + struct packed_git *p; if (!have_set_try_to_free_routine) { have_set_try_to_free_routine = 1; @@@ -1176,18 -1145,22 +1160,22 @@@ * Make sure a corresponding .pack file exists and that * the index looks sane. */ - path_len -= strlen(".idx"); - if (path_len < 1) { - free(p); + if (!strip_suffix_mem(path, &path_len, ".idx")) return NULL; - } + + /* + * ".pack" is long enough to hold any suffix we're adding (and + * the use xsnprintf double-checks that) + */ + alloc = path_len + strlen(".pack") + 1; + p = alloc_packed_git(alloc); memcpy(p->pack_name, path, path_len); - strcpy(p->pack_name + path_len, ".keep"); + xsnprintf(p->pack_name + path_len, alloc - path_len, ".keep"); if (!access(p->pack_name, F_OK)) p->pack_keep = 1; - strcpy(p->pack_name + path_len, ".pack"); + xsnprintf(p->pack_name + path_len, alloc - path_len, ".pack"); if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) { free(p); return NULL; @@@ -1207,9 -1180,10 +1195,10 @@@ struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path) { const char *path = sha1_pack_name(sha1); - struct packed_git *p = alloc_packed_git(strlen(path) + 1); + int alloc = strlen(path) + 1; + struct packed_git *p = alloc_packed_git(alloc); - strcpy(p->pack_name, path); + memcpy(p->pack_name, path, alloc); /* includes NUL */ hashcpy(p->sha1, sha1); if (check_packed_git_idx(idx_path, p)) { free(p); @@@ -1479,7 -1453,7 +1468,7 @@@ int check_sha1_signature(const unsigne return -1; /* Generate the header */ - hdrlen = sprintf(hdr, "%s %lu", typename(obj_type), size) + 1; + hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %lu", typename(obj_type), size) + 1; /* Sha1.. */ git_SHA1_Init(&c); @@@ -2945,7 -2919,7 +2934,7 @@@ static void write_sha1_file_prepare(con git_SHA_CTX c; /* Generate the header */ - *hdrlen = sprintf(hdr, "%s %lu", type, len)+1; + *hdrlen = xsnprintf(hdr, *hdrlen, "%s %lu", type, len)+1; /* Sha1.. */ git_SHA1_Init(&c); @@@ -3008,7 -2982,7 +2997,7 @@@ int hash_sha1_file(const void *buf, uns unsigned char *sha1) { char hdr[32]; - int hdrlen; + int hdrlen = sizeof(hdr); write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen); return 0; } @@@ -3038,29 -3012,31 +3027,31 @@@ static inline int directory_size(const * We want to avoid cross-directory filename renames, because those * can have problems on various filesystems (FAT, NFS, Coda). */ - static int create_tmpfile(char *buffer, size_t bufsiz, const char *filename) + static int create_tmpfile(struct strbuf *tmp, const char *filename) { int fd, dirlen = directory_size(filename); - if (dirlen + 20 > bufsiz) { - errno = ENAMETOOLONG; - return -1; - } - memcpy(buffer, filename, dirlen); - strcpy(buffer + dirlen, "tmp_obj_XXXXXX"); - fd = git_mkstemp_mode(buffer, 0444); + strbuf_reset(tmp); + strbuf_add(tmp, filename, dirlen); + strbuf_addstr(tmp, "tmp_obj_XXXXXX"); + fd = git_mkstemp_mode(tmp->buf, 0444); if (fd < 0 && dirlen && errno == ENOENT) { - /* Make sure the directory exists */ - memcpy(buffer, filename, dirlen); - buffer[dirlen-1] = 0; - if (mkdir(buffer, 0777) && errno != EEXIST) + /* + * Make sure the directory exists; note that the contents + * of the buffer are undefined after mkstemp returns an + * error, so we have to rewrite the whole buffer from + * scratch. + */ + strbuf_reset(tmp); + strbuf_add(tmp, filename, dirlen - 1); + if (mkdir(tmp->buf, 0777) && errno != EEXIST) return -1; - if (adjust_shared_perm(buffer)) + if (adjust_shared_perm(tmp->buf)) return -1; /* Try again */ - strcpy(buffer + dirlen - 1, "/tmp_obj_XXXXXX"); - fd = git_mkstemp_mode(buffer, 0444); + strbuf_addstr(tmp, "/tmp_obj_XXXXXX"); + fd = git_mkstemp_mode(tmp->buf, 0444); } return fd; } @@@ -3073,10 -3049,10 +3064,10 @@@ static int write_loose_object(const uns git_zstream stream; git_SHA_CTX c; unsigned char parano_sha1[20]; - static char tmp_file[PATH_MAX]; + static struct strbuf tmp_file = STRBUF_INIT; const char *filename = sha1_file_name(sha1); - fd = create_tmpfile(tmp_file, sizeof(tmp_file), filename); + fd = create_tmpfile(&tmp_file, filename); if (fd < 0) { if (errno == EACCES) return error("insufficient permission for adding an object to repository database %s", get_object_directory()); @@@ -3125,12 -3101,12 +3116,12 @@@ struct utimbuf utb; utb.actime = mtime; utb.modtime = mtime; - if (utime(tmp_file, &utb) < 0) + if (utime(tmp_file.buf, &utb) < 0) warning("failed utime() on %s: %s", - tmp_file, strerror(errno)); + tmp_file.buf, strerror(errno)); } - return finalize_object_file(tmp_file, filename); + return finalize_object_file(tmp_file.buf, filename); } static int freshen_loose_object(const unsigned char *sha1) @@@ -3154,7 -3130,7 +3145,7 @@@ static int freshen_packed_object(const int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *sha1) { char hdr[32]; - int hdrlen; + int hdrlen = sizeof(hdr); /* Normally if we have it in the pack then we do not bother writing * it out into .git/objects/??/?{38} file. @@@ -3172,7 -3148,8 +3163,8 @@@ int hash_sha1_file_literally(const voi int hdrlen, status = 0; /* type string, SP, %lu of the length plus NUL must fit this */ - header = xmalloc(strlen(type) + 32); + hdrlen = strlen(type) + 32; + header = xmalloc(hdrlen); write_sha1_file_prepare(buf, len, type, sha1, header, &hdrlen); if (!(flags & HASH_WRITE_OBJECT)) @@@ -3200,7 -3177,7 +3192,7 @@@ int force_object_loose(const unsigned c buf = read_packed_sha1(sha1, &type, &len); if (!buf) return error("cannot read sha1_file for %s", sha1_to_hex(sha1)); - hdrlen = sprintf(hdr, "%s %lu", typename(type), len) + 1; + hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %lu", typename(type), len) + 1; ret = write_loose_object(sha1, hdr, hdrlen, buf, len, mtime); free(buf); diff --combined submodule.c index 5e5a46fe2a,c480ed53b4..5879cfb158 --- a/submodule.c +++ b/submodule.c @@@ -122,8 -122,16 +122,9 @@@ static int add_submodule_odb(const cha struct strbuf objects_directory = STRBUF_INIT; struct alternate_object_database *alt_odb; int ret = 0; + int alloc; - const char *git_dir; - strbuf_addf(&objects_directory, "%s/.git", path); - git_dir = read_gitfile(objects_directory.buf); - if (git_dir) { - strbuf_reset(&objects_directory); - strbuf_addstr(&objects_directory, git_dir); - } - strbuf_addstr(&objects_directory, "/objects/"); + strbuf_git_path_submodule(&objects_directory, path, "objects/"); if (!is_directory(objects_directory.buf)) { ret = -1; goto done; @@@ -135,9 -143,10 +136,10 @@@ objects_directory.len)) goto done; - alt_odb = xmalloc(objects_directory.len + 42 + sizeof(*alt_odb)); + alloc = objects_directory.len + 42; /* for "12/345..." sha1 */ + alt_odb = xmalloc(sizeof(*alt_odb) + alloc); alt_odb->next = alt_odb_list; - strcpy(alt_odb->base, objects_directory.buf); + xsnprintf(alt_odb->base, alloc, "%s", objects_directory.buf); alt_odb->name = alt_odb->base + objects_directory.len; alt_odb->name[2] = '/'; alt_odb->name[40] = '\0'; diff --combined transport.c index 863eb524f9,3b47d493d1..23b2ed6f0c --- a/transport.c +++ b/transport.c @@@ -654,23 -654,24 +654,24 @@@ static void print_ok_ref_status(struct "[new branch]"), ref, ref->peer_ref, NULL, porcelain); else { - char quickref[84]; + struct strbuf quickref = STRBUF_INIT; char type; const char *msg; - strcpy(quickref, status_abbrev(ref->old_sha1)); + strbuf_addstr(&quickref, status_abbrev(ref->old_sha1)); if (ref->forced_update) { - strcat(quickref, "..."); + strbuf_addstr(&quickref, "..."); type = '+'; msg = "forced update"; } else { - strcat(quickref, ".."); + strbuf_addstr(&quickref, ".."); type = ' '; msg = NULL; } - strcat(quickref, status_abbrev(ref->new_sha1)); + strbuf_addstr(&quickref, status_abbrev(ref->new_sha1)); - print_ref_status(type, quickref, ref, ref->peer_ref, msg, porcelain); + print_ref_status(type, quickref.buf, ref, ref->peer_ref, msg, porcelain); + strbuf_release(&quickref); } } @@@ -915,42 -916,6 +916,42 @@@ static int external_specification_len(c return strchr(url, ':') - url; } +static const struct string_list *protocol_whitelist(void) +{ + static int enabled = -1; + static struct string_list allowed = STRING_LIST_INIT_DUP; + + if (enabled < 0) { + const char *v = getenv("GIT_ALLOW_PROTOCOL"); + if (v) { + string_list_split(&allowed, v, ':', -1); + string_list_sort(&allowed); + enabled = 1; + } else { + enabled = 0; + } + } + + return enabled ? &allowed : NULL; +} + +int is_transport_allowed(const char *type) +{ + const struct string_list *allowed = protocol_whitelist(); + return !allowed || string_list_has_string(allowed, type); +} + +void transport_check_allowed(const char *type) +{ + if (!is_transport_allowed(type)) + die("transport '%s' not allowed", type); +} + +int transport_restrict_protocols(void) +{ + return !!protocol_whitelist(); +} + struct transport *transport_get(struct remote *remote, const char *url) { const char *helper; @@@ -982,14 -947,12 +983,14 @@@ if (helper) { transport_helper_init(ret, helper); } else if (starts_with(url, "rsync:")) { + transport_check_allowed("rsync"); ret->get_refs_list = get_refs_via_rsync; ret->fetch = fetch_objs_via_rsync; ret->push = rsync_transport_push; ret->smart_options = NULL; } else if (url_is_local_not_ssh(url) && is_file(url) && is_bundle(url, 1)) { struct bundle_transport_data *data = xcalloc(1, sizeof(*data)); + transport_check_allowed("file"); ret->data = data; ret->get_refs_list = get_refs_from_bundle; ret->fetch = fetch_refs_from_bundle; @@@ -1001,10 -964,7 +1002,10 @@@ || starts_with(url, "ssh://") || starts_with(url, "git+ssh://") || starts_with(url, "ssh+git://")) { - /* These are builtin smart transports. */ + /* + * These are builtin smart transports; "allowed" transports + * will be checked individually in git_connect. + */ struct git_transport_data *data = xcalloc(1, sizeof(*data)); ret->data = data; ret->set_option = NULL;