diff options
Diffstat (limited to 'sha1_name.c')
-rw-r--r-- | sha1_name.c | 1281 |
1 files changed, 944 insertions, 337 deletions
diff --git a/sha1_name.c b/sha1_name.c index 44bb62d270..cb88170252 100644 --- a/sha1_name.c +++ b/sha1_name.c @@ -5,15 +5,86 @@ #include "blob.h" #include "tree-walk.h" #include "refs.h" +#include "remote.h" + +static int get_sha1_oneline(const char *, unsigned char *, struct commit_list *); + +typedef int (*disambiguate_hint_fn)(const unsigned char *, void *); + +struct disambiguate_state { + disambiguate_hint_fn fn; + void *cb_data; + unsigned char candidate[20]; + unsigned candidate_exists:1; + unsigned candidate_checked:1; + unsigned candidate_ok:1; + unsigned disambiguate_fn_used:1; + unsigned ambiguous:1; + unsigned always_call_fn:1; +}; + +static void update_candidates(struct disambiguate_state *ds, const unsigned char *current) +{ + if (ds->always_call_fn) { + ds->ambiguous = ds->fn(current, ds->cb_data) ? 1 : 0; + return; + } + if (!ds->candidate_exists) { + /* this is the first candidate */ + hashcpy(ds->candidate, current); + ds->candidate_exists = 1; + return; + } else if (!hashcmp(ds->candidate, current)) { + /* the same as what we already have seen */ + return; + } + + if (!ds->fn) { + /* cannot disambiguate between ds->candidate and current */ + ds->ambiguous = 1; + return; + } + + if (!ds->candidate_checked) { + ds->candidate_ok = ds->fn(ds->candidate, ds->cb_data); + ds->disambiguate_fn_used = 1; + ds->candidate_checked = 1; + } + + if (!ds->candidate_ok) { + /* discard the candidate; we know it does not satisfy fn */ + hashcpy(ds->candidate, current); + ds->candidate_checked = 0; + return; + } -static int find_short_object_filename(int len, const char *name, unsigned char *sha1) + /* if we reach this point, we know ds->candidate satisfies fn */ + if (ds->fn(current, ds->cb_data)) { + /* + * if both current and candidate satisfy fn, we cannot + * disambiguate. + */ + ds->candidate_ok = 0; + ds->ambiguous = 1; + } + + /* otherwise, current can be discarded and candidate is still good */ +} + +static void find_short_object_filename(int len, const char *hex_pfx, struct disambiguate_state *ds) { struct alternate_object_database *alt; char hex[40]; - int found = 0; static struct alternate_object_database *fakeent; if (!fakeent) { + /* + * Create a "fake" alternate object database that + * points to our own object database, to make it + * easier to get a temporary working space in + * alt->name/alt->base while iterating over the + * object databases including our own. + */ const char *objdir = get_object_directory(); int objdir_len = strlen(objdir); int entlen = objdir_len + 43; @@ -24,33 +95,28 @@ static int find_short_object_filename(int len, const char *name, unsigned char * } fakeent->next = alt_odb_list; - sprintf(hex, "%.2s", name); - for (alt = fakeent; alt && found < 2; alt = alt->next) { + sprintf(hex, "%.2s", hex_pfx); + for (alt = fakeent; alt && !ds->ambiguous; alt = alt->next) { struct dirent *de; DIR *dir; - sprintf(alt->name, "%.2s/", name); + sprintf(alt->name, "%.2s/", hex_pfx); dir = opendir(alt->base); if (!dir) continue; - while ((de = readdir(dir)) != NULL) { + + while (!ds->ambiguous && (de = readdir(dir)) != NULL) { + unsigned char sha1[20]; + if (strlen(de->d_name) != 38) continue; - if (memcmp(de->d_name, name + 2, len - 2)) + if (memcmp(de->d_name, hex_pfx + 2, len - 2)) continue; - if (!found) { - memcpy(hex + 2, de->d_name, 38); - found++; - } - else if (memcmp(hex + 2, de->d_name, 38)) { - found = 2; - break; - } + memcpy(hex + 2, de->d_name, 38); + if (!get_sha1_hex(hex, sha1)) + update_candidates(ds, sha1); } closedir(dir); } - if (found == 1) - return get_sha1_hex(hex, sha1) == 0; - return found; } static int match_sha(unsigned len, const unsigned char *a, const unsigned char *b) @@ -68,103 +134,157 @@ static int match_sha(unsigned len, const unsigned char *a, const unsigned char * return 1; } -static int find_short_packed_object(int len, const unsigned char *match, unsigned char *sha1) +static void unique_in_pack(int len, + const unsigned char *bin_pfx, + struct packed_git *p, + struct disambiguate_state *ds) { - struct packed_git *p; - const unsigned char *found_sha1 = NULL; - int found = 0; - - prepare_packed_git(); - for (p = packed_git; p && found < 2; p = p->next) { - uint32_t num, last; - uint32_t first = 0; - open_pack_index(p); - num = p->num_objects; - last = num; - while (first < last) { - uint32_t mid = (first + last) / 2; - const unsigned char *now; - int cmp; - - now = nth_packed_object_sha1(p, mid); - cmp = hashcmp(match, now); - if (!cmp) { - first = mid; - break; - } - if (cmp > 0) { - first = mid+1; - continue; - } - last = mid; + uint32_t num, last, i, first = 0; + const unsigned char *current = NULL; + + open_pack_index(p); + num = p->num_objects; + last = num; + while (first < last) { + uint32_t mid = (first + last) / 2; + const unsigned char *current; + int cmp; + + current = nth_packed_object_sha1(p, mid); + cmp = hashcmp(bin_pfx, current); + if (!cmp) { + first = mid; + break; } - if (first < num) { - const unsigned char *now, *next; - now = nth_packed_object_sha1(p, first); - if (match_sha(len, match, now)) { - next = nth_packed_object_sha1(p, first+1); - if (!next|| !match_sha(len, match, next)) { - /* unique within this pack */ - if (!found) { - found_sha1 = now; - found++; - } - else if (hashcmp(found_sha1, now)) { - found = 2; - break; - } - } - else { - /* not even unique within this pack */ - found = 2; - break; - } - } + if (cmp > 0) { + first = mid+1; + continue; } + last = mid; } - if (found == 1) - hashcpy(sha1, found_sha1); - return found; + + /* + * At this point, "first" is the location of the lowest object + * with an object name that could match "bin_pfx". See if we have + * 0, 1 or more objects that actually match(es). + */ + for (i = first; i < num && !ds->ambiguous; i++) { + current = nth_packed_object_sha1(p, i); + if (!match_sha(len, bin_pfx, current)) + break; + update_candidates(ds, current); + } +} + +static void find_short_packed_object(int len, const unsigned char *bin_pfx, + struct disambiguate_state *ds) +{ + struct packed_git *p; + + prepare_packed_git(); + for (p = packed_git; p && !ds->ambiguous; p = p->next) + unique_in_pack(len, bin_pfx, p, ds); } #define SHORT_NAME_NOT_FOUND (-1) #define SHORT_NAME_AMBIGUOUS (-2) -static int find_unique_short_object(int len, char *canonical, - unsigned char *res, unsigned char *sha1) +static int finish_object_disambiguation(struct disambiguate_state *ds, + unsigned char *sha1) { - int has_unpacked, has_packed; - unsigned char unpacked_sha1[20], packed_sha1[20]; + if (ds->ambiguous) + return SHORT_NAME_AMBIGUOUS; - prepare_alt_odb(); - has_unpacked = find_short_object_filename(len, canonical, unpacked_sha1); - has_packed = find_short_packed_object(len, res, packed_sha1); - if (!has_unpacked && !has_packed) + if (!ds->candidate_exists) return SHORT_NAME_NOT_FOUND; - if (1 < has_unpacked || 1 < has_packed) + + if (!ds->candidate_checked) + /* + * If this is the only candidate, there is no point + * calling the disambiguation hint callback. + * + * On the other hand, if the current candidate + * replaced an earlier candidate that did _not_ pass + * the disambiguation hint callback, then we do have + * more than one objects that match the short name + * given, so we should make sure this one matches; + * otherwise, if we discovered this one and the one + * that we previously discarded in the reverse order, + * we would end up showing different results in the + * same repository! + */ + ds->candidate_ok = (!ds->disambiguate_fn_used || + ds->fn(ds->candidate, ds->cb_data)); + + if (!ds->candidate_ok) return SHORT_NAME_AMBIGUOUS; - if (has_unpacked != has_packed) { - hashcpy(sha1, (has_packed ? packed_sha1 : unpacked_sha1)); + + hashcpy(sha1, ds->candidate); + return 0; +} + +static int disambiguate_commit_only(const unsigned char *sha1, void *cb_data_unused) +{ + int kind = sha1_object_info(sha1, NULL); + return kind == OBJ_COMMIT; +} + +static int disambiguate_committish_only(const unsigned char *sha1, void *cb_data_unused) +{ + struct object *obj; + int kind; + + kind = sha1_object_info(sha1, NULL); + if (kind == OBJ_COMMIT) + return 1; + if (kind != OBJ_TAG) return 0; - } - /* Both have unique ones -- do they match? */ - if (hashcmp(packed_sha1, unpacked_sha1)) - return SHORT_NAME_AMBIGUOUS; - hashcpy(sha1, packed_sha1); + + /* We need to do this the hard way... */ + obj = deref_tag(parse_object(sha1), NULL, 0); + if (obj && obj->type == OBJ_COMMIT) + return 1; return 0; } -static int get_short_sha1(const char *name, int len, unsigned char *sha1, - int quietly) +static int disambiguate_tree_only(const unsigned char *sha1, void *cb_data_unused) { - int i, status; - char canonical[40]; - unsigned char res[20]; + int kind = sha1_object_info(sha1, NULL); + return kind == OBJ_TREE; +} - if (len < MINIMUM_ABBREV || len > 40) - return -1; - hashclr(res); - memset(canonical, 'x', 40); +static int disambiguate_treeish_only(const unsigned char *sha1, void *cb_data_unused) +{ + struct object *obj; + int kind; + + kind = sha1_object_info(sha1, NULL); + if (kind == OBJ_TREE || kind == OBJ_COMMIT) + return 1; + if (kind != OBJ_TAG) + return 0; + + /* We need to do this the hard way... */ + obj = deref_tag(lookup_object(sha1), NULL, 0); + if (obj && (obj->type == OBJ_TREE || obj->type == OBJ_COMMIT)) + return 1; + return 0; +} + +static int disambiguate_blob_only(const unsigned char *sha1, void *cb_data_unused) +{ + int kind = sha1_object_info(sha1, NULL); + return kind == OBJ_BLOB; +} + +static int prepare_prefixes(const char *name, int len, + unsigned char *bin_pfx, + char *hex_pfx) +{ + int i; + + hashclr(bin_pfx); + memset(hex_pfx, 'x', 40); for (i = 0; i < len ;i++) { unsigned char c = name[i]; unsigned char val; @@ -178,30 +298,87 @@ static int get_short_sha1(const char *name, int len, unsigned char *sha1, } else return -1; - canonical[i] = c; + hex_pfx[i] = c; if (!(i & 1)) val <<= 4; - res[i >> 1] |= val; + bin_pfx[i >> 1] |= val; } + return 0; +} + +static int get_short_sha1(const char *name, int len, unsigned char *sha1, + unsigned flags) +{ + int status; + char hex_pfx[40]; + unsigned char bin_pfx[20]; + struct disambiguate_state ds; + int quietly = !!(flags & GET_SHA1_QUIETLY); + + if (len < MINIMUM_ABBREV || len > 40) + return -1; + if (prepare_prefixes(name, len, bin_pfx, hex_pfx) < 0) + return -1; + + prepare_alt_odb(); + + memset(&ds, 0, sizeof(ds)); + if (flags & GET_SHA1_COMMIT) + ds.fn = disambiguate_commit_only; + else if (flags & GET_SHA1_COMMITTISH) + ds.fn = disambiguate_committish_only; + else if (flags & GET_SHA1_TREE) + ds.fn = disambiguate_tree_only; + else if (flags & GET_SHA1_TREEISH) + ds.fn = disambiguate_treeish_only; + else if (flags & GET_SHA1_BLOB) + ds.fn = disambiguate_blob_only; + + find_short_object_filename(len, hex_pfx, &ds); + find_short_packed_object(len, bin_pfx, &ds); + status = finish_object_disambiguation(&ds, sha1); - status = find_unique_short_object(i, canonical, res, sha1); if (!quietly && (status == SHORT_NAME_AMBIGUOUS)) - return error("short SHA1 %.*s is ambiguous.", len, canonical); + return error("short SHA1 %.*s is ambiguous.", len, hex_pfx); return status; } +int for_each_abbrev(const char *prefix, each_abbrev_fn fn, void *cb_data) +{ + char hex_pfx[40]; + unsigned char bin_pfx[20]; + struct disambiguate_state ds; + int len = strlen(prefix); + + if (len < MINIMUM_ABBREV || len > 40) + return -1; + if (prepare_prefixes(prefix, len, bin_pfx, hex_pfx) < 0) + return -1; + + prepare_alt_odb(); + + memset(&ds, 0, sizeof(ds)); + ds.always_call_fn = 1; + ds.cb_data = cb_data; + ds.fn = fn; + + find_short_object_filename(len, hex_pfx, &ds); + find_short_packed_object(len, bin_pfx, &ds); + return ds.ambiguous; +} + const char *find_unique_abbrev(const unsigned char *sha1, int len) { int status, exists; static char hex[41]; - exists = has_sha1_file(sha1); memcpy(hex, sha1_to_hex(sha1), 40); if (len == 40 || !len) return hex; + exists = has_sha1_file(sha1); while (len < 40) { unsigned char sha1_ret[20]; - status = get_short_sha1(hex, len, sha1_ret, 1); + status = get_short_sha1(hex, len, sha1_ret, GET_SHA1_QUIETLY); if (exists ? !status : status == SHORT_NAME_NOT_FOUND) { @@ -238,110 +415,71 @@ static int ambiguous_path(const char *path, int len) return slash; } -/* - * *string and *len will only be substituted, and *string returned (for - * later free()ing) if the string passed in is of the form @{-<n>}. - */ -static char *substitute_branch_name(const char **string, int *len) -{ - struct strbuf buf = STRBUF_INIT; - int ret = interpret_branch_name(*string, &buf); - - if (ret == *len) { - size_t size; - *string = strbuf_detach(&buf, &size); - *len = size; - return (char *)*string; - } - - return NULL; -} - -int dwim_ref(const char *str, int len, unsigned char *sha1, char **ref) -{ - char *last_branch = substitute_branch_name(&str, &len); - const char **p, *r; - int refs_found = 0; - - *ref = NULL; - for (p = ref_rev_parse_rules; *p; p++) { - char fullref[PATH_MAX]; - unsigned char sha1_from_ref[20]; - unsigned char *this_result; - int flag; - - this_result = refs_found ? sha1_from_ref : sha1; - mksnpath(fullref, sizeof(fullref), *p, len, str); - r = resolve_ref(fullref, this_result, 1, &flag); - if (r) { - if (!refs_found++) - *ref = xstrdup(r); - if (!warn_ambiguous_refs) - break; - } else if ((flag & REF_ISSYMREF) && - (len != 4 || strcmp(str, "HEAD"))) - warning("ignoring dangling symref %s.", fullref); - } - free(last_branch); - return refs_found; -} - -int dwim_log(const char *str, int len, unsigned char *sha1, char **log) +static inline int upstream_mark(const char *string, int len) { - char *last_branch = substitute_branch_name(&str, &len); - const char **p; - int logs_found = 0; - - *log = NULL; - for (p = ref_rev_parse_rules; *p; p++) { - struct stat st; - unsigned char hash[20]; - char path[PATH_MAX]; - const char *ref, *it; - - mksnpath(path, sizeof(path), *p, len, str); - ref = resolve_ref(path, hash, 1, NULL); - if (!ref) - continue; - if (!stat(git_path("logs/%s", path), &st) && - S_ISREG(st.st_mode)) - it = path; - else if (strcmp(ref, path) && - !stat(git_path("logs/%s", ref), &st) && - S_ISREG(st.st_mode)) - it = ref; - else - continue; - if (!logs_found++) { - *log = xstrdup(it); - hashcpy(sha1, hash); - } - if (!warn_ambiguous_refs) - break; + const char *suffix[] = { "@{upstream}", "@{u}" }; + int i; + + for (i = 0; i < ARRAY_SIZE(suffix); i++) { + int suffix_len = strlen(suffix[i]); + if (suffix_len <= len + && !memcmp(string, suffix[i], suffix_len)) + return suffix_len; } - free(last_branch); - return logs_found; + return 0; } -static int get_sha1_1(const char *name, int len, unsigned char *sha1); +static int get_sha1_1(const char *name, int len, unsigned char *sha1, unsigned lookup_flags); +static int interpret_nth_prior_checkout(const char *name, int namelen, struct strbuf *buf); -static int get_sha1_basic(const char *str, int len, unsigned char *sha1) +static int get_sha1_basic(const char *str, int len, unsigned char *sha1, + unsigned int flags) { - static const char *warning = "warning: refname '%.*s' is ambiguous.\n"; + static const char *warn_msg = "refname '%.*s' is ambiguous."; + static const char *object_name_msg = N_( + "Git normally never creates a ref that ends with 40 hex characters\n" + "because it will be ignored when you just specify 40-hex. These refs\n" + "may be created by mistake. For example,\n" + "\n" + " git checkout -b $br $(git rev-parse ...)\n" + "\n" + "where \"$br\" is somehow empty and a 40-hex ref is created. Please\n" + "examine these refs and maybe delete them. Turn this message off by\n" + "running \"git config advice.objectNameWarning false\""); + unsigned char tmp_sha1[20]; char *real_ref = NULL; int refs_found = 0; - int at, reflog_len; - - if (len == 40 && !get_sha1_hex(str, sha1)) + int at, reflog_len, nth_prior = 0; + + if (len == 40 && !get_sha1_hex(str, sha1)) { + if (warn_ambiguous_refs && warn_on_object_refname_ambiguity) { + refs_found = dwim_ref(str, len, tmp_sha1, &real_ref); + if (refs_found > 0) { + warning(warn_msg, len, str); + if (advice_object_name_warning) + fprintf(stderr, "%s\n", _(object_name_msg)); + } + free(real_ref); + } return 0; + } /* basic@{time or number or -number} format to query ref-log */ reflog_len = at = 0; if (len && str[len-1] == '}') { - for (at = len-2; at >= 0; at--) { + for (at = len-4; at >= 0; at--) { if (str[at] == '@' && str[at+1] == '{') { - reflog_len = (len-1) - (at+2); - len = at; + if (str[at+2] == '-') { + if (at != 0) + /* @{-N} not at start */ + return -1; + nth_prior = 1; + continue; + } + if (!upstream_mark(str + at, len - at)) { + reflog_len = (len-1) - (at+2); + len = at; + } break; } } @@ -351,20 +489,22 @@ static int get_sha1_basic(const char *str, int len, unsigned char *sha1) if (len && ambiguous_path(str, len)) return -1; - if (!len && reflog_len) { + if (nth_prior) { struct strbuf buf = STRBUF_INIT; - int ret; - /* try the @{-N} syntax for n-th checkout */ - ret = interpret_branch_name(str+at, &buf); - if (ret > 0) { - /* substitute this branch name and restart */ - return get_sha1_1(buf.buf, buf.len, sha1); - } else if (ret == 0) { - return -1; + int detached; + + if (interpret_nth_prior_checkout(str, len, &buf) > 0) { + detached = (buf.len == 40 && !get_sha1_hex(buf.buf, sha1)); + strbuf_release(&buf); + if (detached) + return 0; } + } + + if (!len && reflog_len) /* allow "@{...}" to mean the current branch reflog */ refs_found = dwim_ref("HEAD", 4, sha1, &real_ref); - } else if (reflog_len) + else if (reflog_len) refs_found = dwim_log(str, len, sha1, &real_ref); else refs_found = dwim_ref(str, len, sha1, &real_ref); @@ -372,8 +512,10 @@ static int get_sha1_basic(const char *str, int len, unsigned char *sha1) if (!refs_found) return -1; - if (warn_ambiguous_refs && refs_found > 1) - fprintf(stderr, warning, len, str); + if (warn_ambiguous_refs && !(flags & GET_SHA1_QUIETLY) && + (refs_found > 1 || + !get_short_sha1(str, len, tmp_sha1, GET_SHA1_QUIETLY))) + warning(warn_msg, len, str); if (reflog_len) { int nth, i; @@ -395,21 +537,40 @@ static int get_sha1_basic(const char *str, int len, unsigned char *sha1) } else if (0 <= nth) at_time = 0; else { + int errors = 0; char *tmp = xstrndup(str + at + 2, reflog_len); - at_time = approxidate(tmp); + at_time = approxidate_careful(tmp, &errors); free(tmp); + if (errors) { + free(real_ref); + return -1; + } } - if (read_ref_at(real_ref, at_time, nth, sha1, NULL, + if (read_ref_at(real_ref, flags, at_time, nth, sha1, NULL, &co_time, &co_tz, &co_cnt)) { - if (at_time) - fprintf(stderr, - "warning: Log for '%.*s' only goes " - "back to %s.\n", len, str, - show_date(co_time, co_tz, DATE_RFC2822)); - else - fprintf(stderr, - "warning: Log for '%.*s' only has " - "%d entries.\n", len, str, co_cnt); + if (!len) { + if (starts_with(real_ref, "refs/heads/")) { + str = real_ref + 11; + len = strlen(real_ref + 11); + } else { + /* detached HEAD */ + str = "HEAD"; + len = 4; + } + } + if (at_time) { + if (!(flags & GET_SHA1_QUIETLY)) { + warning("Log for '%.*s' only goes " + "back to %s.", len, str, + show_date(co_time, co_tz, DATE_RFC2822)); + } + } else { + if (flags & GET_SHA1_QUIETLY) { + exit(128); + } + die("Log for '%.*s' only has %d entries.", + len, str, co_cnt); + } } } @@ -421,15 +582,13 @@ static int get_parent(const char *name, int len, unsigned char *result, int idx) { unsigned char sha1[20]; - int ret = get_sha1_1(name, len, sha1); + int ret = get_sha1_1(name, len, sha1, GET_SHA1_COMMITTISH); struct commit *commit; struct commit_list *p; if (ret) return ret; commit = lookup_commit_reference(sha1); - if (!commit) - return -1; if (parse_commit(commit)) return -1; if (!idx) { @@ -454,7 +613,7 @@ static int get_nth_ancestor(const char *name, int len, struct commit *commit; int ret; - ret = get_sha1_1(name, len, sha1); + ret = get_sha1_1(name, len, sha1, GET_SHA1_COMMITTISH); if (ret) return ret; commit = lookup_commit_reference(sha1); @@ -475,16 +634,10 @@ struct object *peel_to_type(const char *name, int namelen, { if (name && !namelen) namelen = strlen(name); - if (!o) { - unsigned char sha1[20]; - if (get_sha1_1(name, namelen, sha1)) - return NULL; - o = parse_object(sha1); - } while (1) { if (!o || (!o->parsed && !parse_object(o->sha1))) return NULL; - if (o->type == expected_type) + if (expected_type == OBJ_ANY || o->type == expected_type) return o; if (o->type == OBJ_TAG) o = ((struct tag*) o)->tagged; @@ -506,6 +659,7 @@ static int peel_onion(const char *name, int len, unsigned char *sha1) unsigned char outer[20]; const char *sp; unsigned int expected_type = 0; + unsigned lookup_flags = 0; struct object *o; /* @@ -528,18 +682,29 @@ static int peel_onion(const char *name, int len, unsigned char *sha1) return -1; sp++; /* beginning of type name, or closing brace for empty */ - if (!strncmp(commit_type, sp, 6) && sp[6] == '}') + if (starts_with(sp, "commit}")) expected_type = OBJ_COMMIT; - else if (!strncmp(tree_type, sp, 4) && sp[4] == '}') + else if (starts_with(sp, "tag}")) + expected_type = OBJ_TAG; + else if (starts_with(sp, "tree}")) expected_type = OBJ_TREE; - else if (!strncmp(blob_type, sp, 4) && sp[4] == '}') + else if (starts_with(sp, "blob}")) expected_type = OBJ_BLOB; + else if (starts_with(sp, "object}")) + expected_type = OBJ_ANY; else if (sp[0] == '}') expected_type = OBJ_NONE; + else if (sp[0] == '/') + expected_type = OBJ_COMMIT; else return -1; - if (get_sha1_1(name, sp - name - 2, outer)) + if (expected_type == OBJ_COMMIT) + lookup_flags = GET_SHA1_COMMITTISH; + else if (expected_type == OBJ_TREE) + lookup_flags = GET_SHA1_TREEISH; + + if (get_sha1_1(name, sp - name - 2, outer, lookup_flags)) return -1; o = parse_object(outer); @@ -550,19 +715,37 @@ static int peel_onion(const char *name, int len, unsigned char *sha1) if (!o || (!o->parsed && !parse_object(o->sha1))) return -1; hashcpy(sha1, o->sha1); + return 0; } - else { + + /* + * At this point, the syntax look correct, so + * if we do not get the needed object, we should + * barf. + */ + o = peel_to_type(name, len, o, expected_type); + if (!o) + return -1; + + hashcpy(sha1, o->sha1); + if (sp[0] == '/') { + /* "$commit^{/foo}" */ + char *prefix; + int ret; + struct commit_list *list = NULL; + /* - * At this point, the syntax look correct, so - * if we do not get the needed object, we should - * barf. + * $commit^{/}. Some regex implementation may reject. + * We don't need regex anyway. '' pattern always matches. */ - o = peel_to_type(name, len, o, expected_type); - if (o) { - hashcpy(sha1, o->sha1); + if (sp[1] == '}') return 0; - } - return -1; + + prefix = xstrndup(sp + 1, name + len - 1 - (sp + 1)); + commit_list_insert((struct commit *)o, &list); + ret = get_sha1_oneline(prefix, sha1, list); + free(prefix); + return ret; } return 0; } @@ -570,6 +753,7 @@ static int peel_onion(const char *name, int len, unsigned char *sha1) static int get_describe_name(const char *name, int len, unsigned char *sha1) { const char *cp; + unsigned flags = GET_SHA1_QUIETLY | GET_SHA1_COMMIT; for (cp = name + len - 1; name + 2 <= cp; cp--) { char ch = *cp; @@ -580,14 +764,14 @@ static int get_describe_name(const char *name, int len, unsigned char *sha1) if (ch == 'g' && cp[-1] == '-') { cp++; len -= cp - name; - return get_short_sha1(cp, len, sha1, 1); + return get_short_sha1(cp, len, sha1, flags); } } } return -1; } -static int get_sha1_1(const char *name, int len, unsigned char *sha1) +static int get_sha1_1(const char *name, int len, unsigned char *sha1, unsigned lookup_flags) { int ret, has_suffix; const char *cp; @@ -623,7 +807,7 @@ static int get_sha1_1(const char *name, int len, unsigned char *sha1) if (!ret) return 0; - ret = get_sha1_basic(name, len, sha1); + ret = get_sha1_basic(name, len, sha1, lookup_flags); if (!ret) return 0; @@ -632,9 +816,21 @@ static int get_sha1_1(const char *name, int len, unsigned char *sha1) if (!ret) return 0; - return get_short_sha1(name, len, sha1, 0); + return get_short_sha1(name, len, sha1, lookup_flags); } +/* + * This interprets names like ':/Initial revision of "git"' by searching + * through history and returning the first commit whose message starts + * the given regular expression. + * + * For future extension, ':/!' is reserved. If you want to match a message + * beginning with a '!', you have to repeat the exclamation mark. + */ + +/* Remember to update object flag allocation in object.h */ +#define ONELINE_SEEN (1u<<20) + static int handle_one_ref(const char *path, const unsigned char *sha1, int flag, void *cb_data) { @@ -649,70 +845,60 @@ static int handle_one_ref(const char *path, } if (object->type != OBJ_COMMIT) return 0; - insert_by_date((struct commit *)object, list); + commit_list_insert((struct commit *)object, list); return 0; } -/* - * This interprets names like ':/Initial revision of "git"' by searching - * through history and returning the first commit whose message starts - * with the given string. - * - * For future extension, ':/!' is reserved. If you want to match a message - * beginning with a '!', you have to repeat the exclamation mark. - */ - -#define ONELINE_SEEN (1u<<20) -static int get_sha1_oneline(const char *prefix, unsigned char *sha1) +static int get_sha1_oneline(const char *prefix, unsigned char *sha1, + struct commit_list *list) { - struct commit_list *list = NULL, *backup = NULL, *l; - int retval = -1; - char *temp_commit_buffer = NULL; + struct commit_list *backup = NULL, *l; + int found = 0; + regex_t regex; if (prefix[0] == '!') { if (prefix[1] != '!') die ("Invalid search pattern: %s", prefix); prefix++; } - for_each_ref(handle_one_ref, &list); - for (l = list; l; l = l->next) + + if (regcomp(®ex, prefix, REG_EXTENDED)) + die("Invalid search pattern: %s", prefix); + + for (l = list; l; l = l->next) { + l->item->object.flags |= ONELINE_SEEN; commit_list_insert(l->item, &backup); + } while (list) { - char *p; + const char *p, *buf; struct commit *commit; - enum object_type type; - unsigned long size; + int matches; commit = pop_most_recent_commit(&list, ONELINE_SEEN); if (!parse_object(commit->object.sha1)) continue; - free(temp_commit_buffer); - if (commit->buffer) - p = commit->buffer; - else { - p = read_sha1_file(commit->object.sha1, &type, &size); - if (!p) - continue; - temp_commit_buffer = p; - } - if (!(p = strstr(p, "\n\n"))) - continue; - if (!prefixcmp(p + 2, prefix)) { + buf = get_commit_buffer(commit, NULL); + p = strstr(buf, "\n\n"); + matches = p && !regexec(®ex, p + 2, 0, NULL, 0); + unuse_commit_buffer(commit, buf); + + if (matches) { hashcpy(sha1, commit->object.sha1); - retval = 0; + found = 1; break; } } - free(temp_commit_buffer); + regfree(®ex); free_commit_list(list); for (l = backup; l; l = l->next) clear_commit_marks(l->item, ONELINE_SEEN); - return retval; + free_commit_list(backup); + return found ? 0 : -1; } struct grab_nth_branch_switch_cbdata { - long cnt, alloc; - struct strbuf *buf; + int remaining; + struct strbuf buf; }; static int grab_nth_branch_switch(unsigned char *osha1, unsigned char *nsha1, @@ -722,76 +908,271 @@ static int grab_nth_branch_switch(unsigned char *osha1, unsigned char *nsha1, struct grab_nth_branch_switch_cbdata *cb = cb_data; const char *match = NULL, *target = NULL; size_t len; - int nth; - if (!prefixcmp(message, "checkout: moving from ")) { - match = message + strlen("checkout: moving from "); + if (skip_prefix(message, "checkout: moving from ", &match)) target = strstr(match, " to "); - } if (!match || !target) return 0; - - len = target - match; - nth = cb->cnt++ % cb->alloc; - strbuf_reset(&cb->buf[nth]); - strbuf_add(&cb->buf[nth], match, len); + if (--(cb->remaining) == 0) { + len = target - match; + strbuf_reset(&cb->buf); + strbuf_add(&cb->buf, match, len); + return 1; /* we are done */ + } return 0; } /* - * This reads "@{-N}" syntax, finds the name of the Nth previous - * branch we were on, and places the name of the branch in the given - * buf and returns the number of characters parsed if successful. - * - * If the input is not of the accepted format, it returns a negative - * number to signal an error. - * - * If the input was ok but there are not N branch switches in the - * reflog, it returns 0. + * Parse @{-N} syntax, return the number of characters parsed + * if successful; otherwise signal an error with negative value. */ -int interpret_branch_name(const char *name, struct strbuf *buf) +static int interpret_nth_prior_checkout(const char *name, int namelen, + struct strbuf *buf) { long nth; - int i, retval; + int retval; struct grab_nth_branch_switch_cbdata cb; const char *brace; char *num_end; + if (namelen < 4) + return -1; if (name[0] != '@' || name[1] != '{' || name[2] != '-') return -1; - brace = strchr(name, '}'); + brace = memchr(name, '}', namelen); if (!brace) return -1; - nth = strtol(name+3, &num_end, 10); + nth = strtol(name + 3, &num_end, 10); if (num_end != brace) return -1; if (nth <= 0) return -1; - cb.alloc = nth; - cb.buf = xmalloc(nth * sizeof(struct strbuf)); - for (i = 0; i < nth; i++) - strbuf_init(&cb.buf[i], 20); - cb.cnt = 0; + cb.remaining = nth; + strbuf_init(&cb.buf, 20); + retval = 0; - for_each_recent_reflog_ent("HEAD", grab_nth_branch_switch, 40960, &cb); - if (cb.cnt < nth) { - cb.cnt = 0; - for_each_reflog_ent("HEAD", grab_nth_branch_switch, &cb); - } - if (cb.cnt < nth) - goto release_return; - i = cb.cnt % nth; + if (0 < for_each_reflog_ent_reverse("HEAD", grab_nth_branch_switch, &cb)) { + strbuf_reset(buf); + strbuf_addbuf(buf, &cb.buf); + retval = brace - name + 1; + } + + strbuf_release(&cb.buf); + return retval; +} + +int get_sha1_mb(const char *name, unsigned char *sha1) +{ + struct commit *one, *two; + struct commit_list *mbs; + unsigned char sha1_tmp[20]; + const char *dots; + int st; + + dots = strstr(name, "..."); + if (!dots) + return get_sha1(name, sha1); + if (dots == name) + st = get_sha1("HEAD", sha1_tmp); + else { + struct strbuf sb; + strbuf_init(&sb, dots - name); + strbuf_add(&sb, name, dots - name); + st = get_sha1_committish(sb.buf, sha1_tmp); + strbuf_release(&sb); + } + if (st) + return st; + one = lookup_commit_reference_gently(sha1_tmp, 0); + if (!one) + return -1; + + if (get_sha1_committish(dots[3] ? (dots + 3) : "HEAD", sha1_tmp)) + return -1; + two = lookup_commit_reference_gently(sha1_tmp, 0); + if (!two) + return -1; + mbs = get_merge_bases(one, two, 1); + if (!mbs || mbs->next) + st = -1; + else { + st = 0; + hashcpy(sha1, mbs->item->object.sha1); + } + free_commit_list(mbs); + return st; +} + +/* parse @something syntax, when 'something' is not {.*} */ +static int interpret_empty_at(const char *name, int namelen, int len, struct strbuf *buf) +{ + const char *next; + + if (len || name[1] == '{') + return -1; + + /* make sure it's a single @, or @@{.*}, not @foo */ + next = memchr(name + len + 1, '@', namelen - len - 1); + if (next && next[1] != '{') + return -1; + if (!next) + next = name + namelen; + if (next != name + 1) + return -1; + strbuf_reset(buf); - strbuf_add(buf, cb.buf[i].buf, cb.buf[i].len); - retval = brace-name+1; + strbuf_add(buf, "HEAD", 4); + return 1; +} -release_return: - for (i = 0; i < nth; i++) - strbuf_release(&cb.buf[i]); - free(cb.buf); +static int reinterpret(const char *name, int namelen, int len, struct strbuf *buf) +{ + /* we have extra data, which might need further processing */ + struct strbuf tmp = STRBUF_INIT; + int used = buf->len; + int ret; - return retval; + strbuf_add(buf, name + len, namelen - len); + ret = interpret_branch_name(buf->buf, buf->len, &tmp); + /* that data was not interpreted, remove our cruft */ + if (ret < 0) { + strbuf_setlen(buf, used); + return len; + } + strbuf_reset(buf); + strbuf_addbuf(buf, &tmp); + strbuf_release(&tmp); + /* tweak for size of {-N} versus expanded ref name */ + return ret - used + len; +} + +static void set_shortened_ref(struct strbuf *buf, const char *ref) +{ + char *s = shorten_unambiguous_ref(ref, 0); + strbuf_reset(buf); + strbuf_addstr(buf, s); + free(s); +} + +static const char *get_upstream_branch(const char *branch_buf, int len) +{ + char *branch = xstrndup(branch_buf, len); + struct branch *upstream = branch_get(*branch ? branch : NULL); + + /* + * Upstream can be NULL only if branch refers to HEAD and HEAD + * points to something different than a branch. + */ + if (!upstream) + die(_("HEAD does not point to a branch")); + if (!upstream->merge || !upstream->merge[0]->dst) { + if (!ref_exists(upstream->refname)) + die(_("No such branch: '%s'"), branch); + if (!upstream->merge) { + die(_("No upstream configured for branch '%s'"), + upstream->name); + } + die( + _("Upstream branch '%s' not stored as a remote-tracking branch"), + upstream->merge[0]->src); + } + free(branch); + + return upstream->merge[0]->dst; +} + +static int interpret_upstream_mark(const char *name, int namelen, + int at, struct strbuf *buf) +{ + int len; + + len = upstream_mark(name + at, namelen - at); + if (!len) + return -1; + + if (memchr(name, ':', at)) + return -1; + + set_shortened_ref(buf, get_upstream_branch(name, at)); + return len + at; +} + +/* + * This reads short-hand syntax that not only evaluates to a commit + * object name, but also can act as if the end user spelled the name + * of the branch from the command line. + * + * - "@{-N}" finds the name of the Nth previous branch we were on, and + * places the name of the branch in the given buf and returns the + * number of characters parsed if successful. + * + * - "<branch>@{upstream}" finds the name of the other ref that + * <branch> is configured to merge with (missing <branch> defaults + * to the current branch), and places the name of the branch in the + * given buf and returns the number of characters parsed if + * successful. + * + * If the input is not of the accepted format, it returns a negative + * number to signal an error. + * + * If the input was ok but there are not N branch switches in the + * reflog, it returns 0. + */ +int interpret_branch_name(const char *name, int namelen, struct strbuf *buf) +{ + char *at; + const char *start; + int len = interpret_nth_prior_checkout(name, namelen, buf); + + if (!namelen) + namelen = strlen(name); + + if (!len) { + return len; /* syntax Ok, not enough switches */ + } else if (len > 0) { + if (len == namelen) + return len; /* consumed all */ + else + return reinterpret(name, namelen, len, buf); + } + + for (start = name; + (at = memchr(start, '@', namelen - (start - name))); + start = at + 1) { + + len = interpret_empty_at(name, namelen, at - name, buf); + if (len > 0) + return reinterpret(name, namelen, len, buf); + + len = interpret_upstream_mark(name, namelen, at - name, buf); + if (len > 0) + return len; + } + + return -1; +} + +int strbuf_branchname(struct strbuf *sb, const char *name) +{ + int len = strlen(name); + int used = interpret_branch_name(name, len, sb); + + if (used == len) + return 0; + if (used < 0) + used = 0; + strbuf_add(sb, name + used, len - used); + return len; +} + +int strbuf_check_branch_ref(struct strbuf *sb, const char *name) +{ + strbuf_branchname(sb, name); + if (name[0] == '-') + return -1; + strbuf_splice(sb, 0, 0, "refs/heads/", 11); + return check_refname_format(sb->buf, 0); } /* @@ -800,30 +1181,200 @@ release_return: */ int get_sha1(const char *name, unsigned char *sha1) { - unsigned unused; - return get_sha1_with_mode(name, sha1, &unused); + struct object_context unused; + return get_sha1_with_context(name, 0, sha1, &unused); +} + +/* + * Many callers know that the user meant to name a commit-ish by + * syntactical positions where the object name appears. Calling this + * function allows the machinery to disambiguate shorter-than-unique + * abbreviated object names between commit-ish and others. + * + * Note that this does NOT error out when the named object is not a + * commit-ish. It is merely to give a hint to the disambiguation + * machinery. + */ +int get_sha1_committish(const char *name, unsigned char *sha1) +{ + struct object_context unused; + return get_sha1_with_context(name, GET_SHA1_COMMITTISH, + sha1, &unused); +} + +int get_sha1_treeish(const char *name, unsigned char *sha1) +{ + struct object_context unused; + return get_sha1_with_context(name, GET_SHA1_TREEISH, + sha1, &unused); +} + +int get_sha1_commit(const char *name, unsigned char *sha1) +{ + struct object_context unused; + return get_sha1_with_context(name, GET_SHA1_COMMIT, + sha1, &unused); } -int get_sha1_with_mode(const char *name, unsigned char *sha1, unsigned *mode) +int get_sha1_tree(const char *name, unsigned char *sha1) +{ + struct object_context unused; + return get_sha1_with_context(name, GET_SHA1_TREE, + sha1, &unused); +} + +int get_sha1_blob(const char *name, unsigned char *sha1) +{ + struct object_context unused; + return get_sha1_with_context(name, GET_SHA1_BLOB, + sha1, &unused); +} + +/* Must be called only when object_name:filename doesn't exist. */ +static void diagnose_invalid_sha1_path(const char *prefix, + const char *filename, + const unsigned char *tree_sha1, + const char *object_name, + int object_name_len) +{ + struct stat st; + unsigned char sha1[20]; + unsigned mode; + + if (!prefix) + prefix = ""; + + if (!lstat(filename, &st)) + die("Path '%s' exists on disk, but not in '%.*s'.", + filename, object_name_len, object_name); + if (errno == ENOENT || errno == ENOTDIR) { + char *fullname = xstrfmt("%s%s", prefix, filename); + + if (!get_tree_entry(tree_sha1, fullname, + sha1, &mode)) { + die("Path '%s' exists, but not '%s'.\n" + "Did you mean '%.*s:%s' aka '%.*s:./%s'?", + fullname, + filename, + object_name_len, object_name, + fullname, + object_name_len, object_name, + filename); + } + die("Path '%s' does not exist in '%.*s'", + filename, object_name_len, object_name); + } +} + +/* Must be called only when :stage:filename doesn't exist. */ +static void diagnose_invalid_index_path(int stage, + const char *prefix, + const char *filename) +{ + struct stat st; + const struct cache_entry *ce; + int pos; + unsigned namelen = strlen(filename); + unsigned fullnamelen; + char *fullname; + + if (!prefix) + prefix = ""; + + /* Wrong stage number? */ + pos = cache_name_pos(filename, namelen); + if (pos < 0) + pos = -pos - 1; + if (pos < active_nr) { + ce = active_cache[pos]; + if (ce_namelen(ce) == namelen && + !memcmp(ce->name, filename, namelen)) + die("Path '%s' is in the index, but not at stage %d.\n" + "Did you mean ':%d:%s'?", + filename, stage, + ce_stage(ce), filename); + } + + /* Confusion between relative and absolute filenames? */ + fullnamelen = namelen + strlen(prefix); + fullname = xmalloc(fullnamelen + 1); + strcpy(fullname, prefix); + strcat(fullname, filename); + pos = cache_name_pos(fullname, fullnamelen); + if (pos < 0) + pos = -pos - 1; + if (pos < active_nr) { + ce = active_cache[pos]; + if (ce_namelen(ce) == fullnamelen && + !memcmp(ce->name, fullname, fullnamelen)) + die("Path '%s' is in the index, but not '%s'.\n" + "Did you mean ':%d:%s' aka ':%d:./%s'?", + fullname, filename, + ce_stage(ce), fullname, + ce_stage(ce), filename); + } + + if (!lstat(filename, &st)) + die("Path '%s' exists on disk, but not in the index.", filename); + if (errno == ENOENT || errno == ENOTDIR) + die("Path '%s' does not exist (neither on disk nor in the index).", + filename); + + free(fullname); +} + + +static char *resolve_relative_path(const char *rel) +{ + if (!starts_with(rel, "./") && !starts_with(rel, "../")) + return NULL; + + if (!startup_info) + die("BUG: startup_info struct is not initialized."); + + if (!is_inside_work_tree()) + die("relative path syntax can't be used outside working tree."); + + /* die() inside prefix_path() if resolved path is outside worktree */ + return prefix_path(startup_info->prefix, + startup_info->prefix ? strlen(startup_info->prefix) : 0, + rel); +} + +static int get_sha1_with_context_1(const char *name, + unsigned flags, + const char *prefix, + unsigned char *sha1, + struct object_context *oc) { int ret, bracket_depth; int namelen = strlen(name); const char *cp; + int only_to_die = flags & GET_SHA1_ONLY_TO_DIE; - *mode = S_IFINVALID; - ret = get_sha1_1(name, namelen, sha1); + memset(oc, 0, sizeof(*oc)); + oc->mode = S_IFINVALID; + ret = get_sha1_1(name, namelen, sha1, flags); if (!ret) return ret; - /* sha1:path --> object name of path in ent sha1 - * :path -> object name of path in index + /* + * sha1:path --> object name of path in ent sha1 + * :path -> object name of absolute path in index + * :./path -> object name of path relative to cwd in index * :[0-3]:path -> object name of path in index at stage + * :/foo -> recent commit matching foo */ if (name[0] == ':') { int stage = 0; - struct cache_entry *ce; + const struct cache_entry *ce; + char *new_path = NULL; int pos; - if (namelen > 2 && name[1] == '/') - return get_sha1_oneline(name + 2, sha1); + if (!only_to_die && namelen > 2 && name[1] == '/') { + struct commit_list *list = NULL; + for_each_ref(handle_one_ref, &list); + commit_list_sort_by_date(&list); + return get_sha1_oneline(name + 2, sha1, list); + } if (namelen < 3 || name[2] != ':' || name[1] < '0' || '3' < name[1]) @@ -832,7 +1383,18 @@ int get_sha1_with_mode(const char *name, unsigned char *sha1, unsigned *mode) stage = name[1] - '0'; cp = name + 3; } - namelen = namelen - (cp - name); + new_path = resolve_relative_path(cp); + if (!new_path) { + namelen = namelen - (cp - name); + } else { + cp = new_path; + namelen = strlen(cp); + } + + strncpy(oc->path, cp, + sizeof(oc->path)); + oc->path[sizeof(oc->path)-1] = '\0'; + if (!active_cache) read_cache(); pos = cache_name_pos(cp, namelen); @@ -845,11 +1407,15 @@ int get_sha1_with_mode(const char *name, unsigned char *sha1, unsigned *mode) break; if (ce_stage(ce) == stage) { hashcpy(sha1, ce->sha1); - *mode = ce->ce_mode; + oc->mode = ce->ce_mode; + free(new_path); return 0; } pos++; } + if (only_to_die && name[1] && name[1] != '/') + diagnose_invalid_index_path(stage, prefix, cp); + free(new_path); return -1; } for (cp = name, bracket_depth = 0; *cp; cp++) { @@ -862,9 +1428,50 @@ int get_sha1_with_mode(const char *name, unsigned char *sha1, unsigned *mode) } if (*cp == ':') { unsigned char tree_sha1[20]; - if (!get_sha1_1(name, cp-name, tree_sha1)) - return get_tree_entry(tree_sha1, cp+1, sha1, - mode); + int len = cp - name; + if (!get_sha1_1(name, len, tree_sha1, GET_SHA1_TREEISH)) { + const char *filename = cp+1; + char *new_filename = NULL; + + new_filename = resolve_relative_path(filename); + if (new_filename) + filename = new_filename; + ret = get_tree_entry(tree_sha1, filename, sha1, &oc->mode); + if (ret && only_to_die) { + diagnose_invalid_sha1_path(prefix, filename, + tree_sha1, + name, len); + } + hashcpy(oc->tree, tree_sha1); + strncpy(oc->path, filename, + sizeof(oc->path)); + oc->path[sizeof(oc->path)-1] = '\0'; + + free(new_filename); + return ret; + } else { + if (only_to_die) + die("Invalid object name '%.*s'.", len, name); + } } return ret; } + +/* + * Call this function when you know "name" given by the end user must + * name an object but it doesn't; the function _may_ die with a better + * diagnostic message than "no such object 'name'", e.g. "Path 'doc' does not + * exist in 'HEAD'" when given "HEAD:doc", or it may return in which case + * you have a chance to diagnose the error further. + */ +void maybe_die_on_misspelt_object_name(const char *name, const char *prefix) +{ + struct object_context oc; + unsigned char sha1[20]; + get_sha1_with_context_1(name, GET_SHA1_ONLY_TO_DIE, prefix, sha1, &oc); +} + +int get_sha1_with_context(const char *str, unsigned flags, unsigned char *sha1, struct object_context *orc) +{ + return get_sha1_with_context_1(str, flags, NULL, sha1, orc); +} |