From: Junio C Hamano Date: Wed, 30 May 2018 05:04:10 +0000 (+0900) Subject: Merge branch 'bc/object-id' X-Git-Tag: v2.18.0-rc0~17 X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/42c8ce1c49f862c98b35e4d89c88aa3d489d6608 Merge branch 'bc/object-id' Conversion from uchar[20] to struct object_id continues. * bc/object-id: (42 commits) merge-one-file: compute empty blob object ID add--interactive: compute the empty tree value Update shell scripts to compute empty tree object ID sha1_file: only expose empty object constants through git_hash_algo dir: use the_hash_algo for empty blob object ID sequencer: use the_hash_algo for empty tree object ID cache-tree: use is_empty_tree_oid sha1_file: convert cached object code to struct object_id builtin/reset: convert use of EMPTY_TREE_SHA1_BIN builtin/receive-pack: convert one use of EMPTY_TREE_SHA1_HEX wt-status: convert two uses of EMPTY_TREE_SHA1_HEX submodule: convert several uses of EMPTY_TREE_SHA1_HEX sequencer: convert one use of EMPTY_TREE_SHA1_HEX merge: convert empty tree constant to the_hash_algo builtin/merge: switch tree functions to use object_id builtin/am: convert uses of EMPTY_TREE_SHA1_BIN to the_hash_algo sha1-file: add functions for hex empty tree and blob OIDs builtin/receive-pack: avoid hard-coded constants for push certs diff: specify abbreviation size in terms of the_hash_algo upload-pack: replace use of several hard-coded constants ... --- 42c8ce1c49f862c98b35e4d89c88aa3d489d6608 diff --cc builtin/pack-objects.c index 53a0fb6ef2,f014523613..e78f3f5220 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@@ -279,10 -264,11 +279,11 @@@ static unsigned long write_no_reuse_obj enum object_type type; void *buf; struct git_istream *st = NULL; + const unsigned hashsz = the_hash_algo->rawsz; if (!usable_delta) { - if (entry->type == OBJ_BLOB && - entry->size > big_file_threshold && + if (oe_type(entry) == OBJ_BLOB && + oe_size_greater_than(&to_pack, entry, big_file_threshold) && (st = open_istream(&entry->idx.oid, &type, &size, NULL)) != NULL) buf = NULL; else { @@@ -356,10 -342,10 +357,10 @@@ return 0; } hashwrite(f, header, hdrlen); - hashwrite(f, DELTA(entry)->idx.oid.hash, 20); - hdrlen += 20; - hashwrite(f, entry->delta->idx.oid.hash, hashsz); ++ hashwrite(f, DELTA(entry)->idx.oid.hash, hashsz); + hdrlen += hashsz; } else { - if (limit && hdrlen + datalen + 20 >= limit) { + if (limit && hdrlen + datalen + hashsz >= limit) { if (st) close_istream(st); free(buf); @@@ -391,13 -377,13 +392,14 @@@ static off_t write_reuse_object(struct unsigned char header[MAX_PACK_OBJECT_HEADER], dheader[MAX_PACK_OBJECT_HEADER]; unsigned hdrlen; + const unsigned hashsz = the_hash_algo->rawsz; + unsigned long entry_size = SIZE(entry); - if (entry->delta) - type = (allow_ofs_delta && entry->delta->idx.offset) ? + if (DELTA(entry)) + type = (allow_ofs_delta && DELTA(entry)->idx.offset) ? OBJ_OFS_DELTA : OBJ_REF_DELTA; hdrlen = encode_in_pack_object_header(header, sizeof(header), - type, entry->size); + type, entry_size); offset = entry->in_pack_offset; revidx = find_pack_revindex(p, offset); @@@ -441,11 -427,11 +443,11 @@@ return 0; } hashwrite(f, header, hdrlen); - hashwrite(f, DELTA(entry)->idx.oid.hash, 20); - hdrlen += 20; - hashwrite(f, entry->delta->idx.oid.hash, hashsz); ++ hashwrite(f, DELTA(entry)->idx.oid.hash, hashsz); + hdrlen += hashsz; reused_delta++; } else { - if (limit && hdrlen + datalen + 20 >= limit) { + if (limit && hdrlen + datalen + hashsz >= limit) { unuse_pack(&w_curs); return 0; } @@@ -1947,12 -1850,12 +1949,12 @@@ static int try_delta(struct unpacked *t return 0; /* Now some size filtering heuristics. */ - trg_size = trg_entry->size; - if (!trg_entry->delta) { + trg_size = SIZE(trg_entry); + if (!DELTA(trg_entry)) { - max_size = trg_size/2 - 20; + max_size = trg_size/2 - the_hash_algo->rawsz; ref_depth = 1; } else { - max_size = trg_entry->delta_size; + max_size = DELTA_SIZE(trg_entry); ref_depth = trg->depth; } max_size = (uint64_t)max_size * (max_depth - src->depth) / diff --cc commit.c index f9714ed74c,9617f85caa..b0e57cc440 --- a/commit.c +++ b/commit.c @@@ -358,10 -331,10 +358,10 @@@ int parse_commit_buffer(struct commit * if (tail <= bufptr + tree_entry_len + 1 || memcmp(bufptr, "tree ", 5) || bufptr[tree_entry_len] != '\n') return error("bogus commit object %s", oid_to_hex(&item->object.oid)); - if (get_sha1_hex(bufptr + 5, parent.hash) < 0) + if (get_oid_hex(bufptr + 5, &parent) < 0) return error("bad tree pointer in commit %s", oid_to_hex(&item->object.oid)); - item->tree = lookup_tree(&parent); + item->maybe_tree = lookup_tree(&parent); bufptr += tree_entry_len + 1; /* "tree " + "hex sha1" + "\n" */ pptr = &item->parents; diff --cc fsck.c index 4db2277ab8,768011f812..bcae2c30e6 --- a/fsck.c +++ b/fsck.c @@@ -795,8 -773,8 +796,8 @@@ static int fsck_commit_buffer(struct co err = fsck_ident(&buffer, &commit->object, options); if (err) return err; - if (!commit->tree) { + if (!get_commit_tree(commit)) { - err = report(options, &commit->object, FSCK_MSG_BAD_TREE, "could not load commit's tree %s", sha1_to_hex(tree_sha1)); + err = report(options, &commit->object, FSCK_MSG_BAD_TREE, "could not load commit's tree %s", oid_to_hex(&tree_oid)); if (err) return err; } diff --cc read-cache.c index cebd24849d,9dbaeeec43..372588260e --- a/read-cache.c +++ b/read-cache.c @@@ -2584,8 -2559,8 +2584,8 @@@ int write_locked_index(struct index_sta goto out; } - if (getenv("GIT_TEST_SPLIT_INDEX")) { + if (git_env_bool("GIT_TEST_SPLIT_INDEX", 0)) { - int v = si->base_sha1[0]; + int v = si->base_oid.hash[0]; if ((v & 15) < 6) istate->cache_changed |= SPLIT_INDEX_ORDERED; } diff --cc sequencer.c index abb6c5dc26,94b6513402..72b4d8ecae --- a/sequencer.c +++ b/sequencer.c @@@ -1246,8 -1118,8 +1246,8 @@@ static int try_to_commit(struct strbuf } if (!(flags & ALLOW_EMPTY) && !oidcmp(current_head ? - ¤t_head->tree->object.oid : + get_commit_tree_oid(current_head) : - &empty_tree_oid, &tree)) { + the_hash_algo->empty_tree, &tree)) { res = 1; /* run 'git commit' to display error message */ goto out; } @@@ -1630,16 -1478,9 +1630,16 @@@ static int do_pick_commit(enum todo_com return error(_("your index file is unmerged.")); } else { unborn = get_oid("HEAD", &head); - if (unborn) + /* Do we want to generate a root commit? */ + if (is_pick_or_similar(command) && opts->have_squash_onto && + !oidcmp(&head, &opts->squash_onto)) { + if (is_fixup(command)) + return error(_("cannot fixup root commit")); + flags |= CREATE_ROOT_COMMIT; + unborn = 1; + } else if (unborn) oidcpy(&head, the_hash_algo->empty_tree); - if (index_differs_from(unborn ? EMPTY_TREE_SHA1_HEX : "HEAD", + if (index_differs_from(unborn ? empty_tree_oid_hex() : "HEAD", NULL, 0)) return error_dirty_index(opts); } diff --cc sha1-file.c index e47098eff2,0000000000..555e780f4b mode 100644,000000..100644 --- a/sha1-file.c +++ b/sha1-file.c @@@ -1,2260 -1,0 +1,2281 @@@ +/* + * GIT - The information manager from hell + * + * Copyright (C) Linus Torvalds, 2005 + * + * This handles basic git sha1 object files - packing, unpacking, + * creation etc. + */ +#include "cache.h" +#include "config.h" +#include "string-list.h" +#include "lockfile.h" +#include "delta.h" +#include "pack.h" +#include "blob.h" +#include "commit.h" +#include "run-command.h" +#include "tag.h" +#include "tree.h" +#include "tree-walk.h" +#include "refs.h" +#include "pack-revindex.h" +#include "sha1-lookup.h" +#include "bulk-checkin.h" +#include "repository.h" +#include "replace-object.h" +#include "streaming.h" +#include "dir.h" +#include "list.h" +#include "mergesort.h" +#include "quote.h" +#include "packfile.h" +#include "fetch-object.h" +#include "object-store.h" + +/* The maximum size for an object header. */ +#define MAX_HEADER_LEN 32 + ++ ++#define EMPTY_TREE_SHA1_BIN_LITERAL \ ++ "\x4b\x82\x5d\xc6\x42\xcb\x6e\xb9\xa0\x60" \ ++ "\xe5\x4b\xf8\xd6\x92\x88\xfb\xee\x49\x04" ++ ++#define EMPTY_BLOB_SHA1_BIN_LITERAL \ ++ "\xe6\x9d\xe2\x9b\xb2\xd1\xd6\x43\x4b\x8b" \ ++ "\x29\xae\x77\x5a\xd8\xc2\xe4\x8c\x53\x91" ++ +const unsigned char null_sha1[GIT_MAX_RAWSZ]; +const struct object_id null_oid; - const struct object_id empty_tree_oid = { ++static const struct object_id empty_tree_oid = { + EMPTY_TREE_SHA1_BIN_LITERAL +}; - const struct object_id empty_blob_oid = { ++static const struct object_id empty_blob_oid = { + EMPTY_BLOB_SHA1_BIN_LITERAL +}; + +static void git_hash_sha1_init(git_hash_ctx *ctx) +{ + git_SHA1_Init(&ctx->sha1); +} + +static void git_hash_sha1_update(git_hash_ctx *ctx, const void *data, size_t len) +{ + git_SHA1_Update(&ctx->sha1, data, len); +} + +static void git_hash_sha1_final(unsigned char *hash, git_hash_ctx *ctx) +{ + git_SHA1_Final(hash, &ctx->sha1); +} + +static void git_hash_unknown_init(git_hash_ctx *ctx) +{ + die("trying to init unknown hash"); +} + +static void git_hash_unknown_update(git_hash_ctx *ctx, const void *data, size_t len) +{ + die("trying to update unknown hash"); +} + +static void git_hash_unknown_final(unsigned char *hash, git_hash_ctx *ctx) +{ + die("trying to finalize unknown hash"); +} + +const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = { + { + NULL, + 0x00000000, + 0, + 0, + git_hash_unknown_init, + git_hash_unknown_update, + git_hash_unknown_final, + NULL, + NULL, + }, + { + "sha-1", + /* "sha1", big-endian */ + 0x73686131, + GIT_SHA1_RAWSZ, + GIT_SHA1_HEXSZ, + git_hash_sha1_init, + git_hash_sha1_update, + git_hash_sha1_final, + &empty_tree_oid, + &empty_blob_oid, + }, +}; + ++const char *empty_tree_oid_hex(void) ++{ ++ static char buf[GIT_MAX_HEXSZ + 1]; ++ return oid_to_hex_r(buf, the_hash_algo->empty_tree); ++} ++ ++const char *empty_blob_oid_hex(void) ++{ ++ static char buf[GIT_MAX_HEXSZ + 1]; ++ return oid_to_hex_r(buf, the_hash_algo->empty_blob); ++} ++ +/* + * This is meant to hold a *small* number of objects that you would + * want read_sha1_file() to be able to return, but yet you do not want + * to write them into the object store (e.g. a browse-only + * application). + */ +static struct cached_object { - unsigned char sha1[20]; ++ struct object_id oid; + enum object_type type; + void *buf; + unsigned long size; +} *cached_objects; +static int cached_object_nr, cached_object_alloc; + +static struct cached_object empty_tree = { - EMPTY_TREE_SHA1_BIN_LITERAL, ++ { EMPTY_TREE_SHA1_BIN_LITERAL }, + OBJ_TREE, + "", + 0 +}; + - static struct cached_object *find_cached_object(const unsigned char *sha1) ++static struct cached_object *find_cached_object(const struct object_id *oid) +{ + int i; + struct cached_object *co = cached_objects; + + for (i = 0; i < cached_object_nr; i++, co++) { - if (!hashcmp(co->sha1, sha1)) ++ if (!oidcmp(&co->oid, oid)) + return co; + } - if (!hashcmp(sha1, empty_tree.sha1)) ++ if (!oidcmp(oid, the_hash_algo->empty_tree)) + return &empty_tree; + return NULL; +} + + +static int get_conv_flags(unsigned flags) +{ + if (flags & HASH_RENORMALIZE) + return CONV_EOL_RENORMALIZE; + else if (flags & HASH_WRITE_OBJECT) + return global_conv_flags_eol | CONV_WRITE_OBJECT; + else + return 0; +} + + +int mkdir_in_gitdir(const char *path) +{ + if (mkdir(path, 0777)) { + int saved_errno = errno; + struct stat st; + struct strbuf sb = STRBUF_INIT; + + if (errno != EEXIST) + return -1; + /* + * Are we looking at a path in a symlinked worktree + * whose original repository does not yet have it? + * e.g. .git/rr-cache pointing at its original + * repository in which the user hasn't performed any + * conflict resolution yet? + */ + if (lstat(path, &st) || !S_ISLNK(st.st_mode) || + strbuf_readlink(&sb, path, st.st_size) || + !is_absolute_path(sb.buf) || + mkdir(sb.buf, 0777)) { + strbuf_release(&sb); + errno = saved_errno; + return -1; + } + strbuf_release(&sb); + } + return adjust_shared_perm(path); +} + +enum scld_error safe_create_leading_directories(char *path) +{ + char *next_component = path + offset_1st_component(path); + enum scld_error ret = SCLD_OK; + + while (ret == SCLD_OK && next_component) { + struct stat st; + char *slash = next_component, slash_character; + + while (*slash && !is_dir_sep(*slash)) + slash++; + + if (!*slash) + break; + + next_component = slash + 1; + while (is_dir_sep(*next_component)) + next_component++; + if (!*next_component) + break; + + slash_character = *slash; + *slash = '\0'; + if (!stat(path, &st)) { + /* path exists */ + if (!S_ISDIR(st.st_mode)) { + errno = ENOTDIR; + ret = SCLD_EXISTS; + } + } else if (mkdir(path, 0777)) { + if (errno == EEXIST && + !stat(path, &st) && S_ISDIR(st.st_mode)) + ; /* somebody created it since we checked */ + else if (errno == ENOENT) + /* + * Either mkdir() failed because + * somebody just pruned the containing + * directory, or stat() failed because + * the file that was in our way was + * just removed. Either way, inform + * the caller that it might be worth + * trying again: + */ + ret = SCLD_VANISHED; + else + ret = SCLD_FAILED; + } else if (adjust_shared_perm(path)) { + ret = SCLD_PERMS; + } + *slash = slash_character; + } + return ret; +} + +enum scld_error safe_create_leading_directories_const(const char *path) +{ + int save_errno; + /* path points to cache entries, so xstrdup before messing with it */ + char *buf = xstrdup(path); + enum scld_error result = safe_create_leading_directories(buf); + + save_errno = errno; + free(buf); + errno = save_errno; + return result; +} + +int raceproof_create_file(const char *path, create_file_fn fn, void *cb) +{ + /* + * The number of times we will try to remove empty directories + * in the way of path. This is only 1 because if another + * process is racily creating directories that conflict with + * us, we don't want to fight against them. + */ + int remove_directories_remaining = 1; + + /* + * The number of times that we will try to create the + * directories containing path. We are willing to attempt this + * more than once, because another process could be trying to + * clean up empty directories at the same time as we are + * trying to create them. + */ + int create_directories_remaining = 3; + + /* A scratch copy of path, filled lazily if we need it: */ + struct strbuf path_copy = STRBUF_INIT; + + int ret, save_errno; + + /* Sanity check: */ + assert(*path); + +retry_fn: + ret = fn(path, cb); + save_errno = errno; + if (!ret) + goto out; + + if (errno == EISDIR && remove_directories_remaining-- > 0) { + /* + * A directory is in the way. Maybe it is empty; try + * to remove it: + */ + if (!path_copy.len) + strbuf_addstr(&path_copy, path); + + if (!remove_dir_recursively(&path_copy, REMOVE_DIR_EMPTY_ONLY)) + goto retry_fn; + } else if (errno == ENOENT && create_directories_remaining-- > 0) { + /* + * Maybe the containing directory didn't exist, or + * maybe it was just deleted by a process that is + * racing with us to clean up empty directories. Try + * to create it: + */ + enum scld_error scld_result; + + if (!path_copy.len) + strbuf_addstr(&path_copy, path); + + do { + scld_result = safe_create_leading_directories(path_copy.buf); + if (scld_result == SCLD_OK) + goto retry_fn; + } while (scld_result == SCLD_VANISHED && create_directories_remaining-- > 0); + } + +out: + strbuf_release(&path_copy); + errno = save_errno; + return ret; +} + +static void fill_sha1_path(struct strbuf *buf, const unsigned char *sha1) +{ + int i; + for (i = 0; i < 20; i++) { + static char hex[] = "0123456789abcdef"; + unsigned int val = sha1[i]; + strbuf_addch(buf, hex[val >> 4]); + strbuf_addch(buf, hex[val & 0xf]); + if (!i) + strbuf_addch(buf, '/'); + } +} + +void sha1_file_name(struct repository *r, struct strbuf *buf, const unsigned char *sha1) +{ + strbuf_addstr(buf, r->objects->objectdir); + strbuf_addch(buf, '/'); + fill_sha1_path(buf, sha1); +} + +struct strbuf *alt_scratch_buf(struct alternate_object_database *alt) +{ + strbuf_setlen(&alt->scratch, alt->base_len); + return &alt->scratch; +} + +static const char *alt_sha1_path(struct alternate_object_database *alt, + const unsigned char *sha1) +{ + struct strbuf *buf = alt_scratch_buf(alt); + fill_sha1_path(buf, sha1); + return buf->buf; +} + +/* + * Return non-zero iff the path is usable as an alternate object database. + */ +static int alt_odb_usable(struct raw_object_store *o, + struct strbuf *path, + const char *normalized_objdir) +{ + struct alternate_object_database *alt; + + /* Detect cases where alternate disappeared */ + if (!is_directory(path->buf)) { + error("object directory %s does not exist; " + "check .git/objects/info/alternates.", + path->buf); + return 0; + } + + /* + * Prevent the common mistake of listing the same + * thing twice, or object directory itself. + */ + for (alt = o->alt_odb_list; alt; alt = alt->next) { + if (!fspathcmp(path->buf, alt->path)) + return 0; + } + if (!fspathcmp(path->buf, normalized_objdir)) + return 0; + + return 1; +} + +/* + * Prepare alternate object database registry. + * + * The variable alt_odb_list points at the list of struct + * alternate_object_database. The elements on this list come from + * non-empty elements from colon separated ALTERNATE_DB_ENVIRONMENT + * environment variable, and $GIT_OBJECT_DIRECTORY/info/alternates, + * whose contents is similar to that environment variable but can be + * LF separated. Its base points at a statically allocated buffer that + * contains "/the/directory/corresponding/to/.git/objects/...", while + * its name points just after the slash at the end of ".git/objects/" + * in the example above, and has enough space to hold 40-byte hex + * SHA1, an extra slash for the first level indirection, and the + * terminating NUL. + */ +static void read_info_alternates(struct repository *r, + const char *relative_base, + int depth); +static int link_alt_odb_entry(struct repository *r, const char *entry, + const char *relative_base, int depth, const char *normalized_objdir) +{ + struct alternate_object_database *ent; + struct strbuf pathbuf = STRBUF_INIT; + + if (!is_absolute_path(entry) && relative_base) { + strbuf_realpath(&pathbuf, relative_base, 1); + strbuf_addch(&pathbuf, '/'); + } + strbuf_addstr(&pathbuf, entry); + + if (strbuf_normalize_path(&pathbuf) < 0 && relative_base) { + error("unable to normalize alternate object path: %s", + pathbuf.buf); + strbuf_release(&pathbuf); + return -1; + } + + /* + * The trailing slash after the directory name is given by + * this function at the end. Remove duplicates. + */ + while (pathbuf.len && pathbuf.buf[pathbuf.len - 1] == '/') + strbuf_setlen(&pathbuf, pathbuf.len - 1); + + if (!alt_odb_usable(r->objects, &pathbuf, normalized_objdir)) { + strbuf_release(&pathbuf); + return -1; + } + + ent = alloc_alt_odb(pathbuf.buf); + + /* add the alternate entry */ + *r->objects->alt_odb_tail = ent; + r->objects->alt_odb_tail = &(ent->next); + ent->next = NULL; + + /* recursively add alternates */ + read_info_alternates(r, pathbuf.buf, depth + 1); + + strbuf_release(&pathbuf); + return 0; +} + +static const char *parse_alt_odb_entry(const char *string, + int sep, + struct strbuf *out) +{ + const char *end; + + strbuf_reset(out); + + if (*string == '#') { + /* comment; consume up to next separator */ + end = strchrnul(string, sep); + } else if (*string == '"' && !unquote_c_style(out, string, &end)) { + /* + * quoted path; unquote_c_style has copied the + * data for us and set "end". Broken quoting (e.g., + * an entry that doesn't end with a quote) falls + * back to the unquoted case below. + */ + } else { + /* normal, unquoted path */ + end = strchrnul(string, sep); + strbuf_add(out, string, end - string); + } + + if (*end) + end++; + return end; +} + +static void link_alt_odb_entries(struct repository *r, const char *alt, + int sep, const char *relative_base, int depth) +{ + struct strbuf objdirbuf = STRBUF_INIT; + struct strbuf entry = STRBUF_INIT; + + if (!alt || !*alt) + return; + + if (depth > 5) { + error("%s: ignoring alternate object stores, nesting too deep.", + relative_base); + return; + } + + strbuf_add_absolute_path(&objdirbuf, r->objects->objectdir); + if (strbuf_normalize_path(&objdirbuf) < 0) + die("unable to normalize object directory: %s", + objdirbuf.buf); + + while (*alt) { + alt = parse_alt_odb_entry(alt, sep, &entry); + if (!entry.len) + continue; + link_alt_odb_entry(r, entry.buf, + relative_base, depth, objdirbuf.buf); + } + strbuf_release(&entry); + strbuf_release(&objdirbuf); +} + +static void read_info_alternates(struct repository *r, + const char *relative_base, + int depth) +{ + char *path; + struct strbuf buf = STRBUF_INIT; + + path = xstrfmt("%s/info/alternates", relative_base); + if (strbuf_read_file(&buf, path, 1024) < 0) { + warn_on_fopen_errors(path); + free(path); + return; + } + + link_alt_odb_entries(r, buf.buf, '\n', relative_base, depth); + strbuf_release(&buf); + free(path); +} + +struct alternate_object_database *alloc_alt_odb(const char *dir) +{ + struct alternate_object_database *ent; + + FLEX_ALLOC_STR(ent, path, dir); + strbuf_init(&ent->scratch, 0); + strbuf_addf(&ent->scratch, "%s/", dir); + ent->base_len = ent->scratch.len; + + return ent; +} + +void add_to_alternates_file(const char *reference) +{ + struct lock_file lock = LOCK_INIT; + char *alts = git_pathdup("objects/info/alternates"); + FILE *in, *out; + int found = 0; + + hold_lock_file_for_update(&lock, alts, LOCK_DIE_ON_ERROR); + out = fdopen_lock_file(&lock, "w"); + if (!out) + die_errno("unable to fdopen alternates lockfile"); + + in = fopen(alts, "r"); + if (in) { + struct strbuf line = STRBUF_INIT; + + while (strbuf_getline(&line, in) != EOF) { + if (!strcmp(reference, line.buf)) { + found = 1; + break; + } + fprintf_or_die(out, "%s\n", line.buf); + } + + strbuf_release(&line); + fclose(in); + } + else if (errno != ENOENT) + die_errno("unable to read alternates file"); + + if (found) { + rollback_lock_file(&lock); + } else { + fprintf_or_die(out, "%s\n", reference); + if (commit_lock_file(&lock)) + die_errno("unable to move new alternates file into place"); + if (the_repository->objects->alt_odb_tail) + link_alt_odb_entries(the_repository, reference, + '\n', NULL, 0); + } + free(alts); +} + +void add_to_alternates_memory(const char *reference) +{ + /* + * Make sure alternates are initialized, or else our entry may be + * overwritten when they are. + */ + prepare_alt_odb(the_repository); + + link_alt_odb_entries(the_repository, reference, + '\n', NULL, 0); +} + +/* + * Compute the exact path an alternate is at and returns it. In case of + * error NULL is returned and the human readable error is added to `err` + * `path` may be relative and should point to $GITDIR. + * `err` must not be null. + */ +char *compute_alternate_path(const char *path, struct strbuf *err) +{ + char *ref_git = NULL; + const char *repo, *ref_git_s; + int seen_error = 0; + + ref_git_s = real_path_if_valid(path); + if (!ref_git_s) { + seen_error = 1; + strbuf_addf(err, _("path '%s' does not exist"), path); + goto out; + } else + /* + * Beware: read_gitfile(), real_path() and mkpath() + * return static buffer + */ + ref_git = xstrdup(ref_git_s); + + repo = read_gitfile(ref_git); + if (!repo) + repo = read_gitfile(mkpath("%s/.git", ref_git)); + if (repo) { + free(ref_git); + ref_git = xstrdup(repo); + } + + if (!repo && is_directory(mkpath("%s/.git/objects", ref_git))) { + char *ref_git_git = mkpathdup("%s/.git", ref_git); + free(ref_git); + ref_git = ref_git_git; + } else if (!is_directory(mkpath("%s/objects", ref_git))) { + struct strbuf sb = STRBUF_INIT; + seen_error = 1; + if (get_common_dir(&sb, ref_git)) { + strbuf_addf(err, + _("reference repository '%s' as a linked " + "checkout is not supported yet."), + path); + goto out; + } + + strbuf_addf(err, _("reference repository '%s' is not a " + "local repository."), path); + goto out; + } + + if (!access(mkpath("%s/shallow", ref_git), F_OK)) { + strbuf_addf(err, _("reference repository '%s' is shallow"), + path); + seen_error = 1; + goto out; + } + + if (!access(mkpath("%s/info/grafts", ref_git), F_OK)) { + strbuf_addf(err, + _("reference repository '%s' is grafted"), + path); + seen_error = 1; + goto out; + } + +out: + if (seen_error) { + FREE_AND_NULL(ref_git); + } + + return ref_git; +} + +int foreach_alt_odb(alt_odb_fn fn, void *cb) +{ + struct alternate_object_database *ent; + int r = 0; + + prepare_alt_odb(the_repository); + for (ent = the_repository->objects->alt_odb_list; ent; ent = ent->next) { + r = fn(ent, cb); + if (r) + break; + } + return r; +} + +void prepare_alt_odb(struct repository *r) +{ + if (r->objects->alt_odb_tail) + return; + + r->objects->alt_odb_tail = &r->objects->alt_odb_list; + link_alt_odb_entries(r, r->objects->alternate_db, PATH_SEP, NULL, 0); + + read_info_alternates(r, r->objects->objectdir, 0); +} + +/* Returns 1 if we have successfully freshened the file, 0 otherwise. */ +static int freshen_file(const char *fn) +{ + struct utimbuf t; + t.actime = t.modtime = time(NULL); + return !utime(fn, &t); +} + +/* + * All of the check_and_freshen functions return 1 if the file exists and was + * freshened (if freshening was requested), 0 otherwise. If they return + * 0, you should not assume that it is safe to skip a write of the object (it + * either does not exist on disk, or has a stale mtime and may be subject to + * pruning). + */ +int check_and_freshen_file(const char *fn, int freshen) +{ + if (access(fn, F_OK)) + return 0; + if (freshen && !freshen_file(fn)) + return 0; + return 1; +} + - static int check_and_freshen_local(const unsigned char *sha1, int freshen) ++static int check_and_freshen_local(const struct object_id *oid, int freshen) +{ + static struct strbuf buf = STRBUF_INIT; + + strbuf_reset(&buf); - sha1_file_name(the_repository, &buf, sha1); ++ sha1_file_name(the_repository, &buf, oid->hash); + + return check_and_freshen_file(buf.buf, freshen); +} + - static int check_and_freshen_nonlocal(const unsigned char *sha1, int freshen) ++static int check_and_freshen_nonlocal(const struct object_id *oid, int freshen) +{ + struct alternate_object_database *alt; + prepare_alt_odb(the_repository); + for (alt = the_repository->objects->alt_odb_list; alt; alt = alt->next) { - const char *path = alt_sha1_path(alt, sha1); ++ const char *path = alt_sha1_path(alt, oid->hash); + if (check_and_freshen_file(path, freshen)) + return 1; + } + return 0; +} + - static int check_and_freshen(const unsigned char *sha1, int freshen) ++static int check_and_freshen(const struct object_id *oid, int freshen) +{ - return check_and_freshen_local(sha1, freshen) || - check_and_freshen_nonlocal(sha1, freshen); ++ return check_and_freshen_local(oid, freshen) || ++ check_and_freshen_nonlocal(oid, freshen); +} + - int has_loose_object_nonlocal(const unsigned char *sha1) ++int has_loose_object_nonlocal(const struct object_id *oid) +{ - return check_and_freshen_nonlocal(sha1, 0); ++ return check_and_freshen_nonlocal(oid, 0); +} + - static int has_loose_object(const unsigned char *sha1) ++static int has_loose_object(const struct object_id *oid) +{ - return check_and_freshen(sha1, 0); ++ return check_and_freshen(oid, 0); +} + +static void mmap_limit_check(size_t length) +{ + static size_t limit = 0; + if (!limit) { + limit = git_env_ulong("GIT_MMAP_LIMIT", 0); + if (!limit) + limit = SIZE_MAX; + } + if (length > limit) + die("attempting to mmap %"PRIuMAX" over limit %"PRIuMAX, + (uintmax_t)length, (uintmax_t)limit); +} + +void *xmmap_gently(void *start, size_t length, + int prot, int flags, int fd, off_t offset) +{ + void *ret; + + mmap_limit_check(length); + ret = mmap(start, length, prot, flags, fd, offset); + if (ret == MAP_FAILED) { + if (!length) + return NULL; + release_pack_memory(length); + ret = mmap(start, length, prot, flags, fd, offset); + } + return ret; +} + +void *xmmap(void *start, size_t length, + int prot, int flags, int fd, off_t offset) +{ + void *ret = xmmap_gently(start, length, prot, flags, fd, offset); + if (ret == MAP_FAILED) + die_errno("mmap failed"); + return ret; +} + +/* + * With an in-core object data in "map", rehash it to make sure the + * object name actually matches "sha1" to detect object corruption. + * With "map" == NULL, try reading the object named with "sha1" using + * the streaming interface and rehash it to do the same. + */ +int check_object_signature(const struct object_id *oid, void *map, + unsigned long size, const char *type) +{ + struct object_id real_oid; + enum object_type obj_type; + struct git_istream *st; + git_hash_ctx c; + char hdr[MAX_HEADER_LEN]; + int hdrlen; + + if (map) { + hash_object_file(map, size, type, &real_oid); + return oidcmp(oid, &real_oid) ? -1 : 0; + } + + st = open_istream(oid, &obj_type, &size, NULL); + if (!st) + return -1; + + /* Generate the header */ + hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %lu", type_name(obj_type), size) + 1; + + /* Sha1.. */ + the_hash_algo->init_fn(&c); + the_hash_algo->update_fn(&c, hdr, hdrlen); + for (;;) { + char buf[1024 * 16]; + ssize_t readlen = read_istream(st, buf, sizeof(buf)); + + if (readlen < 0) { + close_istream(st); + return -1; + } + if (!readlen) + break; + the_hash_algo->update_fn(&c, buf, readlen); + } + the_hash_algo->final_fn(real_oid.hash, &c); + close_istream(st); + return oidcmp(oid, &real_oid) ? -1 : 0; +} + +int git_open_cloexec(const char *name, int flags) +{ + int fd; + static int o_cloexec = O_CLOEXEC; + + fd = open(name, flags | o_cloexec); + if ((o_cloexec & O_CLOEXEC) && fd < 0 && errno == EINVAL) { + /* Try again w/o O_CLOEXEC: the kernel might not support it */ + o_cloexec &= ~O_CLOEXEC; + fd = open(name, flags | o_cloexec); + } + +#if defined(F_GETFD) && defined(F_SETFD) && defined(FD_CLOEXEC) + { + static int fd_cloexec = FD_CLOEXEC; + + if (!o_cloexec && 0 <= fd && fd_cloexec) { + /* Opened w/o O_CLOEXEC? try with fcntl(2) to add it */ + int flags = fcntl(fd, F_GETFD); + if (fcntl(fd, F_SETFD, flags | fd_cloexec)) + fd_cloexec = 0; + } + } +#endif + return fd; +} + +/* + * Find "sha1" as a loose object in the local repository or in an alternate. + * Returns 0 on success, negative on failure. + * + * The "path" out-parameter will give the path of the object we found (if any). + * Note that it may point to static storage and is only valid until another + * call to sha1_file_name(), etc. + */ +static int stat_sha1_file(struct repository *r, const unsigned char *sha1, + struct stat *st, const char **path) +{ + struct alternate_object_database *alt; + static struct strbuf buf = STRBUF_INIT; + + strbuf_reset(&buf); + sha1_file_name(r, &buf, sha1); + *path = buf.buf; + + if (!lstat(*path, st)) + return 0; + + prepare_alt_odb(r); + errno = ENOENT; + for (alt = r->objects->alt_odb_list; alt; alt = alt->next) { + *path = alt_sha1_path(alt, sha1); + if (!lstat(*path, st)) + return 0; + } + + return -1; +} + +/* + * Like stat_sha1_file(), but actually open the object and return the + * descriptor. See the caveats on the "path" parameter above. + */ +static int open_sha1_file(struct repository *r, + const unsigned char *sha1, const char **path) +{ + int fd; + struct alternate_object_database *alt; + int most_interesting_errno; + static struct strbuf buf = STRBUF_INIT; + + strbuf_reset(&buf); + sha1_file_name(r, &buf, sha1); + *path = buf.buf; + + fd = git_open(*path); + if (fd >= 0) + return fd; + most_interesting_errno = errno; + + prepare_alt_odb(r); + for (alt = r->objects->alt_odb_list; alt; alt = alt->next) { + *path = alt_sha1_path(alt, sha1); + fd = git_open(*path); + if (fd >= 0) + return fd; + if (most_interesting_errno == ENOENT) + most_interesting_errno = errno; + } + errno = most_interesting_errno; + return -1; +} + +/* + * Map the loose object at "path" if it is not NULL, or the path found by + * searching for a loose object named "sha1". + */ +static void *map_sha1_file_1(struct repository *r, const char *path, + const unsigned char *sha1, unsigned long *size) +{ + void *map; + int fd; + + if (path) + fd = git_open(path); + else + fd = open_sha1_file(r, sha1, &path); + map = NULL; + if (fd >= 0) { + struct stat st; + + if (!fstat(fd, &st)) { + *size = xsize_t(st.st_size); + if (!*size) { + /* mmap() is forbidden on empty files */ + error("object file %s is empty", path); + return NULL; + } + map = xmmap(NULL, *size, PROT_READ, MAP_PRIVATE, fd, 0); + } + close(fd); + } + return map; +} + +void *map_sha1_file(struct repository *r, + const unsigned char *sha1, unsigned long *size) +{ + return map_sha1_file_1(r, NULL, sha1, size); +} + +static int unpack_sha1_short_header(git_zstream *stream, + unsigned char *map, unsigned long mapsize, + void *buffer, unsigned long bufsiz) +{ + /* Get the data stream */ + memset(stream, 0, sizeof(*stream)); + stream->next_in = map; + stream->avail_in = mapsize; + stream->next_out = buffer; + stream->avail_out = bufsiz; + + git_inflate_init(stream); + return git_inflate(stream, 0); +} + +int unpack_sha1_header(git_zstream *stream, + unsigned char *map, unsigned long mapsize, + void *buffer, unsigned long bufsiz) +{ + int status = unpack_sha1_short_header(stream, map, mapsize, + buffer, bufsiz); + + if (status < Z_OK) + return status; + + /* Make sure we have the terminating NUL */ + if (!memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer)) + return -1; + return 0; +} + +static int unpack_sha1_header_to_strbuf(git_zstream *stream, unsigned char *map, + unsigned long mapsize, void *buffer, + unsigned long bufsiz, struct strbuf *header) +{ + int status; + + status = unpack_sha1_short_header(stream, map, mapsize, buffer, bufsiz); + if (status < Z_OK) + return -1; + + /* + * Check if entire header is unpacked in the first iteration. + */ + if (memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer)) + return 0; + + /* + * buffer[0..bufsiz] was not large enough. Copy the partial + * result out to header, and then append the result of further + * reading the stream. + */ + strbuf_add(header, buffer, stream->next_out - (unsigned char *)buffer); + stream->next_out = buffer; + stream->avail_out = bufsiz; + + do { + status = git_inflate(stream, 0); + strbuf_add(header, buffer, stream->next_out - (unsigned char *)buffer); + if (memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer)) + return 0; + stream->next_out = buffer; + stream->avail_out = bufsiz; + } while (status != Z_STREAM_END); + return -1; +} + +static void *unpack_sha1_rest(git_zstream *stream, void *buffer, unsigned long size, const unsigned char *sha1) +{ + int bytes = strlen(buffer) + 1; + unsigned char *buf = xmallocz(size); + unsigned long n; + int status = Z_OK; + + n = stream->total_out - bytes; + if (n > size) + n = size; + memcpy(buf, (char *) buffer + bytes, n); + bytes = n; + if (bytes <= size) { + /* + * The above condition must be (bytes <= size), not + * (bytes < size). In other words, even though we + * expect no more output and set avail_out to zero, + * the input zlib stream may have bytes that express + * "this concludes the stream", and we *do* want to + * eat that input. + * + * Otherwise we would not be able to test that we + * consumed all the input to reach the expected size; + * we also want to check that zlib tells us that all + * went well with status == Z_STREAM_END at the end. + */ + stream->next_out = buf + bytes; + stream->avail_out = size - bytes; + while (status == Z_OK) + status = git_inflate(stream, Z_FINISH); + } + if (status == Z_STREAM_END && !stream->avail_in) { + git_inflate_end(stream); + return buf; + } + + if (status < 0) + error("corrupt loose object '%s'", sha1_to_hex(sha1)); + else if (stream->avail_in) + error("garbage at end of loose object '%s'", + sha1_to_hex(sha1)); + free(buf); + return NULL; +} + +/* + * We used to just use "sscanf()", but that's actually way + * too permissive for what we want to check. So do an anal + * object header parse by hand. + */ +static int parse_sha1_header_extended(const char *hdr, struct object_info *oi, + unsigned int flags) +{ + const char *type_buf = hdr; + unsigned long size; + int type, type_len = 0; + + /* + * The type can be of any size but is followed by + * a space. + */ + for (;;) { + char c = *hdr++; + if (!c) + return -1; + if (c == ' ') + break; + type_len++; + } + + type = type_from_string_gently(type_buf, type_len, 1); + if (oi->type_name) + strbuf_add(oi->type_name, type_buf, type_len); + /* + * Set type to 0 if its an unknown object and + * we're obtaining the type using '--allow-unknown-type' + * option. + */ + if ((flags & OBJECT_INFO_ALLOW_UNKNOWN_TYPE) && (type < 0)) + type = 0; + else if (type < 0) + die("invalid object type"); + if (oi->typep) + *oi->typep = type; + + /* + * The length must follow immediately, and be in canonical + * decimal format (ie "010" is not valid). + */ + size = *hdr++ - '0'; + if (size > 9) + return -1; + if (size) { + for (;;) { + unsigned long c = *hdr - '0'; + if (c > 9) + break; + hdr++; + size = size * 10 + c; + } + } + + if (oi->sizep) + *oi->sizep = size; + + /* + * The length must be followed by a zero byte + */ + return *hdr ? -1 : type; +} + +int parse_sha1_header(const char *hdr, unsigned long *sizep) +{ + struct object_info oi = OBJECT_INFO_INIT; + + oi.sizep = sizep; + return parse_sha1_header_extended(hdr, &oi, 0); +} + +static int sha1_loose_object_info(struct repository *r, + const unsigned char *sha1, + struct object_info *oi, int flags) +{ + int status = 0; + unsigned long mapsize; + void *map; + git_zstream stream; + char hdr[MAX_HEADER_LEN]; + struct strbuf hdrbuf = STRBUF_INIT; + unsigned long size_scratch; + + if (oi->delta_base_sha1) + hashclr(oi->delta_base_sha1); + + /* + * If we don't care about type or size, then we don't + * need to look inside the object at all. Note that we + * do not optimize out the stat call, even if the + * caller doesn't care about the disk-size, since our + * return value implicitly indicates whether the + * object even exists. + */ + if (!oi->typep && !oi->type_name && !oi->sizep && !oi->contentp) { + const char *path; + struct stat st; + if (stat_sha1_file(r, sha1, &st, &path) < 0) + return -1; + if (oi->disk_sizep) + *oi->disk_sizep = st.st_size; + return 0; + } + + map = map_sha1_file(r, sha1, &mapsize); + if (!map) + return -1; + + if (!oi->sizep) + oi->sizep = &size_scratch; + + if (oi->disk_sizep) + *oi->disk_sizep = mapsize; + if ((flags & OBJECT_INFO_ALLOW_UNKNOWN_TYPE)) { + if (unpack_sha1_header_to_strbuf(&stream, map, mapsize, hdr, sizeof(hdr), &hdrbuf) < 0) + status = error("unable to unpack %s header with --allow-unknown-type", + sha1_to_hex(sha1)); + } else if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0) + status = error("unable to unpack %s header", + sha1_to_hex(sha1)); + if (status < 0) + ; /* Do nothing */ + else if (hdrbuf.len) { + if ((status = parse_sha1_header_extended(hdrbuf.buf, oi, flags)) < 0) + status = error("unable to parse %s header with --allow-unknown-type", + sha1_to_hex(sha1)); + } else if ((status = parse_sha1_header_extended(hdr, oi, flags)) < 0) + status = error("unable to parse %s header", sha1_to_hex(sha1)); + + if (status >= 0 && oi->contentp) { + *oi->contentp = unpack_sha1_rest(&stream, hdr, + *oi->sizep, sha1); + if (!*oi->contentp) { + git_inflate_end(&stream); + status = -1; + } + } else + git_inflate_end(&stream); + + munmap(map, mapsize); + if (status && oi->typep) + *oi->typep = status; + if (oi->sizep == &size_scratch) + oi->sizep = NULL; + strbuf_release(&hdrbuf); + oi->whence = OI_LOOSE; + return (status < 0) ? status : 0; +} + +int fetch_if_missing = 1; + +int oid_object_info_extended(struct repository *r, const struct object_id *oid, + struct object_info *oi, unsigned flags) +{ + static struct object_info blank_oi = OBJECT_INFO_INIT; + struct pack_entry e; + int rtype; + const struct object_id *real = oid; + int already_retried = 0; + + if (flags & OBJECT_INFO_LOOKUP_REPLACE) + real = lookup_replace_object(r, oid); + + if (is_null_oid(real)) + return -1; + + if (!oi) + oi = &blank_oi; + + if (!(flags & OBJECT_INFO_SKIP_CACHED)) { - struct cached_object *co = find_cached_object(real->hash); ++ struct cached_object *co = find_cached_object(real); + if (co) { + if (oi->typep) + *(oi->typep) = co->type; + if (oi->sizep) + *(oi->sizep) = co->size; + if (oi->disk_sizep) + *(oi->disk_sizep) = 0; + if (oi->delta_base_sha1) + hashclr(oi->delta_base_sha1); + if (oi->type_name) + strbuf_addstr(oi->type_name, type_name(co->type)); + if (oi->contentp) + *oi->contentp = xmemdupz(co->buf, co->size); + oi->whence = OI_CACHED; + return 0; + } + } + + while (1) { - if (find_pack_entry(r, real->hash, &e)) ++ if (find_pack_entry(r, real, &e)) + break; + + if (flags & OBJECT_INFO_IGNORE_LOOSE) + return -1; + + /* Most likely it's a loose object. */ + if (!sha1_loose_object_info(r, real->hash, oi, flags)) + return 0; + + /* Not a loose object; someone else may have just packed it. */ + if (!(flags & OBJECT_INFO_QUICK)) { + reprepare_packed_git(r); - if (find_pack_entry(r, real->hash, &e)) ++ if (find_pack_entry(r, real, &e)) + break; + } + + /* Check if it is a missing object */ + if (fetch_if_missing && repository_format_partial_clone && + !already_retried && r == the_repository) { + /* + * TODO Investigate having fetch_object() return + * TODO error/success and stopping the music here. + * TODO Pass a repository struct through fetch_object, + * such that arbitrary repositories work. + */ + fetch_object(repository_format_partial_clone, real->hash); + already_retried = 1; + continue; + } + + return -1; + } + + if (oi == &blank_oi) + /* + * We know that the caller doesn't actually need the + * information below, so return early. + */ + return 0; + rtype = packed_object_info(r, e.p, e.offset, oi); + if (rtype < 0) { + mark_bad_packed_object(e.p, real->hash); + return oid_object_info_extended(r, real, oi, 0); + } else if (oi->whence == OI_PACKED) { + oi->u.packed.offset = e.offset; + oi->u.packed.pack = e.p; + oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA || + rtype == OBJ_OFS_DELTA); + } + + return 0; +} + +/* returns enum object_type or negative */ +int oid_object_info(struct repository *r, + const struct object_id *oid, + unsigned long *sizep) +{ + enum object_type type; + struct object_info oi = OBJECT_INFO_INIT; + + oi.typep = &type; + oi.sizep = sizep; + if (oid_object_info_extended(r, oid, &oi, + OBJECT_INFO_LOOKUP_REPLACE) < 0) + return -1; + return type; +} + +static void *read_object(const unsigned char *sha1, enum object_type *type, + unsigned long *size) +{ + struct object_id oid; + struct object_info oi = OBJECT_INFO_INIT; + void *content; + oi.typep = type; + oi.sizep = size; + oi.contentp = &content; + + hashcpy(oid.hash, sha1); + + if (oid_object_info_extended(the_repository, &oid, &oi, 0) < 0) + return NULL; + return content; +} + +int pretend_object_file(void *buf, unsigned long len, enum object_type type, + struct object_id *oid) +{ + struct cached_object *co; + + hash_object_file(buf, len, type_name(type), oid); - if (has_sha1_file(oid->hash) || find_cached_object(oid->hash)) ++ if (has_sha1_file(oid->hash) || find_cached_object(oid)) + return 0; + ALLOC_GROW(cached_objects, cached_object_nr + 1, cached_object_alloc); + co = &cached_objects[cached_object_nr++]; + co->size = len; + co->type = type; + co->buf = xmalloc(len); + memcpy(co->buf, buf, len); - hashcpy(co->sha1, oid->hash); ++ oidcpy(&co->oid, oid); + return 0; +} + +/* + * This function dies on corrupt objects; the callers who want to + * deal with them should arrange to call read_object() and give error + * messages themselves. + */ +void *read_object_file_extended(const struct object_id *oid, + enum object_type *type, + unsigned long *size, + int lookup_replace) +{ + void *data; + const struct packed_git *p; + const char *path; + struct stat st; + const struct object_id *repl = lookup_replace ? + lookup_replace_object(the_repository, oid) : oid; + + errno = 0; + data = read_object(repl->hash, type, size); + if (data) + return data; + + if (errno && errno != ENOENT) + die_errno("failed to read object %s", oid_to_hex(oid)); + + /* die if we replaced an object with one that does not exist */ + if (repl != oid) + die("replacement %s not found for %s", + oid_to_hex(repl), oid_to_hex(oid)); + + if (!stat_sha1_file(the_repository, repl->hash, &st, &path)) + die("loose object %s (stored in %s) is corrupt", + oid_to_hex(repl), path); + + if ((p = has_packed_and_bad(repl->hash)) != NULL) + die("packed object %s (stored in %s) is corrupt", + oid_to_hex(repl), p->pack_name); + + return NULL; +} + +void *read_object_with_reference(const struct object_id *oid, + const char *required_type_name, + unsigned long *size, + struct object_id *actual_oid_return) +{ + enum object_type type, required_type; + void *buffer; + unsigned long isize; + struct object_id actual_oid; + + required_type = type_from_string(required_type_name); + oidcpy(&actual_oid, oid); + while (1) { + int ref_length = -1; + const char *ref_type = NULL; + + buffer = read_object_file(&actual_oid, &type, &isize); + if (!buffer) + return NULL; + if (type == required_type) { + *size = isize; + if (actual_oid_return) + oidcpy(actual_oid_return, &actual_oid); + return buffer; + } + /* Handle references */ + else if (type == OBJ_COMMIT) + ref_type = "tree "; + else if (type == OBJ_TAG) + ref_type = "object "; + else { + free(buffer); + return NULL; + } + ref_length = strlen(ref_type); + + if (ref_length + GIT_SHA1_HEXSZ > isize || + memcmp(buffer, ref_type, ref_length) || + get_oid_hex((char *) buffer + ref_length, &actual_oid)) { + free(buffer); + return NULL; + } + free(buffer); + /* Now we have the ID of the referred-to object in + * actual_oid. Check again. */ + } +} + +static void write_object_file_prepare(const void *buf, unsigned long len, + const char *type, struct object_id *oid, + char *hdr, int *hdrlen) +{ + git_hash_ctx c; + + /* Generate the header */ + *hdrlen = xsnprintf(hdr, *hdrlen, "%s %lu", type, len)+1; + + /* Sha1.. */ + the_hash_algo->init_fn(&c); + the_hash_algo->update_fn(&c, hdr, *hdrlen); + the_hash_algo->update_fn(&c, buf, len); + the_hash_algo->final_fn(oid->hash, &c); +} + +/* + * Move the just written object into its final resting place. + */ +int finalize_object_file(const char *tmpfile, const char *filename) +{ + int ret = 0; + + if (object_creation_mode == OBJECT_CREATION_USES_RENAMES) + goto try_rename; + else if (link(tmpfile, filename)) + ret = errno; + + /* + * Coda hack - coda doesn't like cross-directory links, + * so we fall back to a rename, which will mean that it + * won't be able to check collisions, but that's not a + * big deal. + * + * The same holds for FAT formatted media. + * + * When this succeeds, we just return. We have nothing + * left to unlink. + */ + if (ret && ret != EEXIST) { + try_rename: + if (!rename(tmpfile, filename)) + goto out; + ret = errno; + } + unlink_or_warn(tmpfile); + if (ret) { + if (ret != EEXIST) { + return error_errno("unable to write sha1 filename %s", filename); + } + /* FIXME!!! Collision check here ? */ + } + +out: + if (adjust_shared_perm(filename)) + return error("unable to set permission to '%s'", filename); + return 0; +} + +static int write_buffer(int fd, const void *buf, size_t len) +{ + if (write_in_full(fd, buf, len) < 0) + return error_errno("file write error"); + return 0; +} + +int hash_object_file(const void *buf, unsigned long len, const char *type, + struct object_id *oid) +{ + char hdr[MAX_HEADER_LEN]; + int hdrlen = sizeof(hdr); + write_object_file_prepare(buf, len, type, oid, hdr, &hdrlen); + return 0; +} + +/* Finalize a file on disk, and close it. */ +static void close_sha1_file(int fd) +{ + if (fsync_object_files) + fsync_or_die(fd, "sha1 file"); + if (close(fd) != 0) + die_errno("error when closing sha1 file"); +} + +/* Size of directory component, including the ending '/' */ +static inline int directory_size(const char *filename) +{ + const char *s = strrchr(filename, '/'); + if (!s) + return 0; + return s - filename + 1; +} + +/* + * This creates a temporary file in the same directory as the final + * 'filename' + * + * We want to avoid cross-directory filename renames, because those + * can have problems on various filesystems (FAT, NFS, Coda). + */ +static int create_tmpfile(struct strbuf *tmp, const char *filename) +{ + int fd, dirlen = directory_size(filename); + + 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; 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(tmp->buf)) + return -1; + + /* Try again */ + strbuf_addstr(tmp, "/tmp_obj_XXXXXX"); + fd = git_mkstemp_mode(tmp->buf, 0444); + } + return fd; +} + +static int write_loose_object(const struct object_id *oid, char *hdr, + int hdrlen, const void *buf, unsigned long len, + time_t mtime) +{ + int fd, ret; + unsigned char compressed[4096]; + git_zstream stream; + git_hash_ctx c; + struct object_id parano_oid; + static struct strbuf tmp_file = STRBUF_INIT; + static struct strbuf filename = STRBUF_INIT; + + strbuf_reset(&filename); + sha1_file_name(the_repository, &filename, oid->hash); + + fd = create_tmpfile(&tmp_file, filename.buf); + if (fd < 0) { + if (errno == EACCES) + return error("insufficient permission for adding an object to repository database %s", get_object_directory()); + else + return error_errno("unable to create temporary file"); + } + + /* Set it up */ + git_deflate_init(&stream, zlib_compression_level); + stream.next_out = compressed; + stream.avail_out = sizeof(compressed); + the_hash_algo->init_fn(&c); + + /* First header.. */ + stream.next_in = (unsigned char *)hdr; + stream.avail_in = hdrlen; + while (git_deflate(&stream, 0) == Z_OK) + ; /* nothing */ + the_hash_algo->update_fn(&c, hdr, hdrlen); + + /* Then the data itself.. */ + stream.next_in = (void *)buf; + stream.avail_in = len; + do { + unsigned char *in0 = stream.next_in; + ret = git_deflate(&stream, Z_FINISH); + the_hash_algo->update_fn(&c, in0, stream.next_in - in0); + if (write_buffer(fd, compressed, stream.next_out - compressed) < 0) + die("unable to write sha1 file"); + stream.next_out = compressed; + stream.avail_out = sizeof(compressed); + } while (ret == Z_OK); + + if (ret != Z_STREAM_END) + die("unable to deflate new object %s (%d)", oid_to_hex(oid), + ret); + ret = git_deflate_end_gently(&stream); + if (ret != Z_OK) + die("deflateEnd on object %s failed (%d)", oid_to_hex(oid), + ret); + the_hash_algo->final_fn(parano_oid.hash, &c); + if (oidcmp(oid, ¶no_oid) != 0) + die("confused by unstable object source data for %s", + oid_to_hex(oid)); + + close_sha1_file(fd); + + if (mtime) { + struct utimbuf utb; + utb.actime = mtime; + utb.modtime = mtime; + if (utime(tmp_file.buf, &utb) < 0) + warning_errno("failed utime() on %s", tmp_file.buf); + } + + return finalize_object_file(tmp_file.buf, filename.buf); +} + - static int freshen_loose_object(const unsigned char *sha1) ++static int freshen_loose_object(const struct object_id *oid) +{ - return check_and_freshen(sha1, 1); ++ return check_and_freshen(oid, 1); +} + - static int freshen_packed_object(const unsigned char *sha1) ++static int freshen_packed_object(const struct object_id *oid) +{ + struct pack_entry e; - if (!find_pack_entry(the_repository, sha1, &e)) ++ if (!find_pack_entry(the_repository, oid, &e)) + return 0; + if (e.p->freshened) + return 1; + if (!freshen_file(e.p->pack_name)) + return 0; + e.p->freshened = 1; + return 1; +} + +int write_object_file(const void *buf, unsigned long len, const char *type, + struct object_id *oid) +{ + char hdr[MAX_HEADER_LEN]; + 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. + */ + write_object_file_prepare(buf, len, type, oid, hdr, &hdrlen); - if (freshen_packed_object(oid->hash) || freshen_loose_object(oid->hash)) ++ if (freshen_packed_object(oid) || freshen_loose_object(oid)) + return 0; + return write_loose_object(oid, hdr, hdrlen, buf, len, 0); +} + +int hash_object_file_literally(const void *buf, unsigned long len, + const char *type, struct object_id *oid, + unsigned flags) +{ + char *header; + int hdrlen, status = 0; + + /* type string, SP, %lu of the length plus NUL must fit this */ + hdrlen = strlen(type) + MAX_HEADER_LEN; + header = xmalloc(hdrlen); + write_object_file_prepare(buf, len, type, oid, header, &hdrlen); + + if (!(flags & HASH_WRITE_OBJECT)) + goto cleanup; - if (freshen_packed_object(oid->hash) || freshen_loose_object(oid->hash)) ++ if (freshen_packed_object(oid) || freshen_loose_object(oid)) + goto cleanup; + status = write_loose_object(oid, header, hdrlen, buf, len, 0); + +cleanup: + free(header); + return status; +} + +int force_object_loose(const struct object_id *oid, time_t mtime) +{ + void *buf; + unsigned long len; + enum object_type type; + char hdr[MAX_HEADER_LEN]; + int hdrlen; + int ret; + - if (has_loose_object(oid->hash)) ++ if (has_loose_object(oid)) + return 0; + buf = read_object(oid->hash, &type, &len); + if (!buf) + return error("cannot read sha1_file for %s", oid_to_hex(oid)); + hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %lu", type_name(type), len) + 1; + ret = write_loose_object(oid, hdr, hdrlen, buf, len, mtime); + free(buf); + + return ret; +} + +int has_sha1_file_with_flags(const unsigned char *sha1, int flags) +{ + struct object_id oid; + if (!startup_info->have_repository) + return 0; + hashcpy(oid.hash, sha1); + return oid_object_info_extended(the_repository, &oid, NULL, + flags | OBJECT_INFO_SKIP_CACHED) >= 0; +} + +int has_object_file(const struct object_id *oid) +{ + return has_sha1_file(oid->hash); +} + +int has_object_file_with_flags(const struct object_id *oid, int flags) +{ + return has_sha1_file_with_flags(oid->hash, flags); +} + +static void check_tree(const void *buf, size_t size) +{ + struct tree_desc desc; + struct name_entry entry; + + init_tree_desc(&desc, buf, size); + while (tree_entry(&desc, &entry)) + /* do nothing + * tree_entry() will die() on malformed entries */ + ; +} + +static void check_commit(const void *buf, size_t size) +{ + struct commit c; + memset(&c, 0, sizeof(c)); + if (parse_commit_buffer(&c, buf, size)) + die("corrupt commit"); +} + +static void check_tag(const void *buf, size_t size) +{ + struct tag t; + memset(&t, 0, sizeof(t)); + if (parse_tag_buffer(&t, buf, size)) + die("corrupt tag"); +} + +static int index_mem(struct object_id *oid, void *buf, size_t size, + enum object_type type, + const char *path, unsigned flags) +{ + int ret, re_allocated = 0; + int write_object = flags & HASH_WRITE_OBJECT; + + if (!type) + type = OBJ_BLOB; + + /* + * Convert blobs to git internal format + */ + if ((type == OBJ_BLOB) && path) { + struct strbuf nbuf = STRBUF_INIT; + if (convert_to_git(&the_index, path, buf, size, &nbuf, + get_conv_flags(flags))) { + buf = strbuf_detach(&nbuf, &size); + re_allocated = 1; + } + } + if (flags & HASH_FORMAT_CHECK) { + if (type == OBJ_TREE) + check_tree(buf, size); + if (type == OBJ_COMMIT) + check_commit(buf, size); + if (type == OBJ_TAG) + check_tag(buf, size); + } + + if (write_object) + ret = write_object_file(buf, size, type_name(type), oid); + else + ret = hash_object_file(buf, size, type_name(type), oid); + if (re_allocated) + free(buf); + return ret; +} + +static int index_stream_convert_blob(struct object_id *oid, int fd, + const char *path, unsigned flags) +{ + int ret; + const int write_object = flags & HASH_WRITE_OBJECT; + struct strbuf sbuf = STRBUF_INIT; + + assert(path); + assert(would_convert_to_git_filter_fd(path)); + + convert_to_git_filter_fd(&the_index, path, fd, &sbuf, + get_conv_flags(flags)); + + if (write_object) + ret = write_object_file(sbuf.buf, sbuf.len, type_name(OBJ_BLOB), + oid); + else + ret = hash_object_file(sbuf.buf, sbuf.len, type_name(OBJ_BLOB), + oid); + strbuf_release(&sbuf); + return ret; +} + +static int index_pipe(struct object_id *oid, int fd, enum object_type type, + const char *path, unsigned flags) +{ + struct strbuf sbuf = STRBUF_INIT; + int ret; + + if (strbuf_read(&sbuf, fd, 4096) >= 0) + ret = index_mem(oid, sbuf.buf, sbuf.len, type, path, flags); + else + ret = -1; + strbuf_release(&sbuf); + return ret; +} + +#define SMALL_FILE_SIZE (32*1024) + +static int index_core(struct object_id *oid, int fd, size_t size, + enum object_type type, const char *path, + unsigned flags) +{ + int ret; + + if (!size) { + ret = index_mem(oid, "", size, type, path, flags); + } else if (size <= SMALL_FILE_SIZE) { + char *buf = xmalloc(size); + ssize_t read_result = read_in_full(fd, buf, size); + if (read_result < 0) + ret = error_errno("read error while indexing %s", + path ? path : ""); + else if (read_result != size) + ret = error("short read while indexing %s", + path ? path : ""); + else + ret = index_mem(oid, buf, size, type, path, flags); + free(buf); + } else { + void *buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0); + ret = index_mem(oid, buf, size, type, path, flags); + munmap(buf, size); + } + return ret; +} + +/* + * This creates one packfile per large blob unless bulk-checkin + * machinery is "plugged". + * + * This also bypasses the usual "convert-to-git" dance, and that is on + * purpose. We could write a streaming version of the converting + * functions and insert that before feeding the data to fast-import + * (or equivalent in-core API described above). However, that is + * somewhat complicated, as we do not know the size of the filter + * result, which we need to know beforehand when writing a git object. + * Since the primary motivation for trying to stream from the working + * tree file and to avoid mmaping it in core is to deal with large + * binary blobs, they generally do not want to get any conversion, and + * callers should avoid this code path when filters are requested. + */ +static int index_stream(struct object_id *oid, int fd, size_t size, + enum object_type type, const char *path, + unsigned flags) +{ + return index_bulk_checkin(oid, fd, size, type, path, flags); +} + +int index_fd(struct object_id *oid, int fd, struct stat *st, + enum object_type type, const char *path, unsigned flags) +{ + int ret; + + /* + * Call xsize_t() only when needed to avoid potentially unnecessary + * die() for large files. + */ + if (type == OBJ_BLOB && path && would_convert_to_git_filter_fd(path)) + ret = index_stream_convert_blob(oid, fd, path, flags); + else if (!S_ISREG(st->st_mode)) + ret = index_pipe(oid, fd, type, path, flags); + else if (st->st_size <= big_file_threshold || type != OBJ_BLOB || + (path && would_convert_to_git(&the_index, path))) + ret = index_core(oid, fd, xsize_t(st->st_size), type, path, + flags); + else + ret = index_stream(oid, fd, xsize_t(st->st_size), type, path, + flags); + close(fd); + return ret; +} + +int index_path(struct object_id *oid, const char *path, struct stat *st, unsigned flags) +{ + int fd; + struct strbuf sb = STRBUF_INIT; + int rc = 0; + + switch (st->st_mode & S_IFMT) { + case S_IFREG: + fd = open(path, O_RDONLY); + if (fd < 0) + return error_errno("open(\"%s\")", path); + if (index_fd(oid, fd, st, OBJ_BLOB, path, flags) < 0) + return error("%s: failed to insert into database", + path); + break; + case S_IFLNK: + if (strbuf_readlink(&sb, path, st->st_size)) + return error_errno("readlink(\"%s\")", path); + if (!(flags & HASH_WRITE_OBJECT)) + hash_object_file(sb.buf, sb.len, blob_type, oid); + else if (write_object_file(sb.buf, sb.len, blob_type, oid)) + rc = error("%s: failed to insert into database", path); + strbuf_release(&sb); + break; + case S_IFDIR: + return resolve_gitlink_ref(path, "HEAD", oid); + default: + return error("%s: unsupported file type", path); + } + return rc; +} + +int read_pack_header(int fd, struct pack_header *header) +{ + if (read_in_full(fd, header, sizeof(*header)) != sizeof(*header)) + /* "eof before pack header was fully read" */ + return PH_ERROR_EOF; + + if (header->hdr_signature != htonl(PACK_SIGNATURE)) + /* "protocol error (pack signature mismatch detected)" */ + return PH_ERROR_PACK_SIGNATURE; + if (!pack_version_ok(header->hdr_version)) + /* "protocol error (pack version unsupported)" */ + return PH_ERROR_PROTOCOL; + return 0; +} + +void assert_oid_type(const struct object_id *oid, enum object_type expect) +{ + enum object_type type = oid_object_info(the_repository, oid, NULL); + if (type < 0) + die("%s is not a valid object", oid_to_hex(oid)); + if (type != expect) + die("%s is not a valid '%s' object", oid_to_hex(oid), + type_name(expect)); +} + +int for_each_file_in_obj_subdir(unsigned int subdir_nr, + struct strbuf *path, + each_loose_object_fn obj_cb, + each_loose_cruft_fn cruft_cb, + each_loose_subdir_fn subdir_cb, + void *data) +{ + size_t origlen, baselen; + DIR *dir; + struct dirent *de; + int r = 0; + struct object_id oid; + + if (subdir_nr > 0xff) + BUG("invalid loose object subdirectory: %x", subdir_nr); + + origlen = path->len; + strbuf_complete(path, '/'); + strbuf_addf(path, "%02x", subdir_nr); + + dir = opendir(path->buf); + if (!dir) { + if (errno != ENOENT) + r = error_errno("unable to open %s", path->buf); + strbuf_setlen(path, origlen); + return r; + } + + oid.hash[0] = subdir_nr; + strbuf_addch(path, '/'); + baselen = path->len; + + while ((de = readdir(dir))) { + size_t namelen; + if (is_dot_or_dotdot(de->d_name)) + continue; + + namelen = strlen(de->d_name); + strbuf_setlen(path, baselen); + strbuf_add(path, de->d_name, namelen); + if (namelen == GIT_SHA1_HEXSZ - 2 && + !hex_to_bytes(oid.hash + 1, de->d_name, + GIT_SHA1_RAWSZ - 1)) { + if (obj_cb) { + r = obj_cb(&oid, path->buf, data); + if (r) + break; + } + continue; + } + + if (cruft_cb) { + r = cruft_cb(de->d_name, path->buf, data); + if (r) + break; + } + } + closedir(dir); + + strbuf_setlen(path, baselen - 1); + if (!r && subdir_cb) + r = subdir_cb(subdir_nr, path->buf, data); + + strbuf_setlen(path, origlen); + + return r; +} + +int for_each_loose_file_in_objdir_buf(struct strbuf *path, + each_loose_object_fn obj_cb, + each_loose_cruft_fn cruft_cb, + each_loose_subdir_fn subdir_cb, + void *data) +{ + int r = 0; + int i; + + for (i = 0; i < 256; i++) { + r = for_each_file_in_obj_subdir(i, path, obj_cb, cruft_cb, + subdir_cb, data); + if (r) + break; + } + + return r; +} + +int for_each_loose_file_in_objdir(const char *path, + each_loose_object_fn obj_cb, + each_loose_cruft_fn cruft_cb, + each_loose_subdir_fn subdir_cb, + void *data) +{ + struct strbuf buf = STRBUF_INIT; + int r; + + strbuf_addstr(&buf, path); + r = for_each_loose_file_in_objdir_buf(&buf, obj_cb, cruft_cb, + subdir_cb, data); + strbuf_release(&buf); + + return r; +} + +struct loose_alt_odb_data { + each_loose_object_fn *cb; + void *data; +}; + +static int loose_from_alt_odb(struct alternate_object_database *alt, + void *vdata) +{ + struct loose_alt_odb_data *data = vdata; + struct strbuf buf = STRBUF_INIT; + int r; + + strbuf_addstr(&buf, alt->path); + r = for_each_loose_file_in_objdir_buf(&buf, + data->cb, NULL, NULL, + data->data); + strbuf_release(&buf); + return r; +} + +int for_each_loose_object(each_loose_object_fn cb, void *data, unsigned flags) +{ + struct loose_alt_odb_data alt; + int r; + + r = for_each_loose_file_in_objdir(get_object_directory(), + cb, NULL, NULL, data); + if (r) + return r; + + if (flags & FOR_EACH_OBJECT_LOCAL_ONLY) + return 0; + + alt.cb = cb; + alt.data = data; + return foreach_alt_odb(loose_from_alt_odb, &alt); +} + +static int check_stream_sha1(git_zstream *stream, + const char *hdr, + unsigned long size, + const char *path, + const unsigned char *expected_sha1) +{ + git_hash_ctx c; + unsigned char real_sha1[GIT_MAX_RAWSZ]; + unsigned char buf[4096]; + unsigned long total_read; + int status = Z_OK; + + the_hash_algo->init_fn(&c); + the_hash_algo->update_fn(&c, hdr, stream->total_out); + + /* + * We already read some bytes into hdr, but the ones up to the NUL + * do not count against the object's content size. + */ + total_read = stream->total_out - strlen(hdr) - 1; + + /* + * This size comparison must be "<=" to read the final zlib packets; + * see the comment in unpack_sha1_rest for details. + */ + while (total_read <= size && + (status == Z_OK || status == Z_BUF_ERROR)) { + stream->next_out = buf; + stream->avail_out = sizeof(buf); + if (size - total_read < stream->avail_out) + stream->avail_out = size - total_read; + status = git_inflate(stream, Z_FINISH); + the_hash_algo->update_fn(&c, buf, stream->next_out - buf); + total_read += stream->next_out - buf; + } + git_inflate_end(stream); + + if (status != Z_STREAM_END) { + error("corrupt loose object '%s'", sha1_to_hex(expected_sha1)); + return -1; + } + if (stream->avail_in) { + error("garbage at end of loose object '%s'", + sha1_to_hex(expected_sha1)); + return -1; + } + + the_hash_algo->final_fn(real_sha1, &c); + if (hashcmp(expected_sha1, real_sha1)) { + error("sha1 mismatch for %s (expected %s)", path, + sha1_to_hex(expected_sha1)); + return -1; + } + + return 0; +} + +int read_loose_object(const char *path, + const struct object_id *expected_oid, + enum object_type *type, + unsigned long *size, + void **contents) +{ + int ret = -1; + void *map = NULL; + unsigned long mapsize; + git_zstream stream; + char hdr[MAX_HEADER_LEN]; + + *contents = NULL; + + map = map_sha1_file_1(the_repository, path, NULL, &mapsize); + if (!map) { + error_errno("unable to mmap %s", path); + goto out; + } + + if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0) { + error("unable to unpack header of %s", path); + goto out; + } + + *type = parse_sha1_header(hdr, size); + if (*type < 0) { + error("unable to parse header of %s", path); + git_inflate_end(&stream); + goto out; + } + + if (*type == OBJ_BLOB && *size > big_file_threshold) { + if (check_stream_sha1(&stream, hdr, *size, path, expected_oid->hash) < 0) + goto out; + } else { + *contents = unpack_sha1_rest(&stream, hdr, *size, expected_oid->hash); + if (!*contents) { + error("unable to unpack contents of %s", path); + git_inflate_end(&stream); + goto out; + } + if (check_object_signature(expected_oid, *contents, + *size, type_name(*type))) { + error("sha1 mismatch for %s (expected %s)", path, + oid_to_hex(expected_oid)); + free(*contents); + goto out; + } + } + + ret = 0; /* everything checks out */ + +out: + if (map) + munmap(map, mapsize); + return ret; +} diff --cc sha1-name.c index 60b8a935cc,0000000000..cc0028ed19 mode 100644,000000..100644 --- a/sha1-name.c +++ b/sha1-name.c @@@ -1,1734 -1,0 +1,1733 @@@ +#include "cache.h" +#include "config.h" +#include "tag.h" +#include "commit.h" +#include "tree.h" +#include "blob.h" +#include "tree-walk.h" +#include "refs.h" +#include "remote.h" +#include "dir.h" +#include "sha1-array.h" +#include "packfile.h" +#include "object-store.h" +#include "repository.h" + +static int get_oid_oneline(const char *, struct object_id *, struct commit_list *); + +typedef int (*disambiguate_hint_fn)(const struct object_id *, void *); + +struct disambiguate_state { + int len; /* length of prefix in hex chars */ + char hex_pfx[GIT_MAX_HEXSZ + 1]; + struct object_id bin_pfx; + + disambiguate_hint_fn fn; + void *cb_data; + struct object_id candidate; + 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 struct object_id *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 */ + oidcpy(&ds->candidate, current); + ds->candidate_exists = 1; + return; + } else if (!oidcmp(&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 */ + oidcpy(&ds->candidate, current); + ds->candidate_checked = 0; + return; + } + + /* 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 int append_loose_object(const struct object_id *oid, const char *path, + void *data) +{ + oid_array_append(data, oid); + return 0; +} + +static int match_sha(unsigned, const unsigned char *, const unsigned char *); + +static void find_short_object_filename(struct disambiguate_state *ds) +{ + int subdir_nr = ds->bin_pfx.hash[0]; + struct alternate_object_database *alt; + 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. + */ + fakeent = alloc_alt_odb(get_object_directory()); + } + fakeent->next = the_repository->objects->alt_odb_list; + + for (alt = fakeent; alt && !ds->ambiguous; alt = alt->next) { + int pos; + + if (!alt->loose_objects_subdir_seen[subdir_nr]) { + struct strbuf *buf = alt_scratch_buf(alt); + for_each_file_in_obj_subdir(subdir_nr, buf, + append_loose_object, + NULL, NULL, + &alt->loose_objects_cache); + alt->loose_objects_subdir_seen[subdir_nr] = 1; + } + + pos = oid_array_lookup(&alt->loose_objects_cache, &ds->bin_pfx); + if (pos < 0) + pos = -1 - pos; + while (!ds->ambiguous && pos < alt->loose_objects_cache.nr) { + const struct object_id *oid; + oid = alt->loose_objects_cache.oid + pos; + if (!match_sha(ds->len, ds->bin_pfx.hash, oid->hash)) + break; + update_candidates(ds, oid); + pos++; + } + } +} + +static int match_sha(unsigned len, const unsigned char *a, const unsigned char *b) +{ + do { + if (*a != *b) + return 0; + a++; + b++; + len -= 2; + } while (len > 1); + if (len) + if ((*a ^ *b) & 0xf0) + return 0; + return 1; +} + +static void unique_in_pack(struct packed_git *p, + struct disambiguate_state *ds) +{ + uint32_t num, i, first = 0; + const struct object_id *current = NULL; + + if (open_pack_index(p) || !p->num_objects) + return; + + num = p->num_objects; + bsearch_pack(&ds->bin_pfx, p, &first); + + /* + * 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++) { + struct object_id oid; + current = nth_packed_object_oid(&oid, p, i); + if (!match_sha(ds->len, ds->bin_pfx.hash, current->hash)) + break; + update_candidates(ds, current); + } +} + +static void find_short_packed_object(struct disambiguate_state *ds) +{ + struct packed_git *p; + + for (p = get_packed_git(the_repository); p && !ds->ambiguous; + p = p->next) + unique_in_pack(p, ds); +} + +#define SHORT_NAME_NOT_FOUND (-1) +#define SHORT_NAME_AMBIGUOUS (-2) + +static int finish_object_disambiguation(struct disambiguate_state *ds, + struct object_id *oid) +{ + if (ds->ambiguous) + return SHORT_NAME_AMBIGUOUS; + + if (!ds->candidate_exists) + return SHORT_NAME_NOT_FOUND; + + 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; + + oidcpy(oid, &ds->candidate); + return 0; +} + +static int disambiguate_commit_only(const struct object_id *oid, void *cb_data_unused) +{ + int kind = oid_object_info(the_repository, oid, NULL); + return kind == OBJ_COMMIT; +} + +static int disambiguate_committish_only(const struct object_id *oid, void *cb_data_unused) +{ + struct object *obj; + int kind; + + kind = oid_object_info(the_repository, oid, NULL); + if (kind == OBJ_COMMIT) + return 1; + if (kind != OBJ_TAG) + return 0; + + /* We need to do this the hard way... */ + obj = deref_tag(parse_object(oid), NULL, 0); + if (obj && obj->type == OBJ_COMMIT) + return 1; + return 0; +} + +static int disambiguate_tree_only(const struct object_id *oid, void *cb_data_unused) +{ + int kind = oid_object_info(the_repository, oid, NULL); + return kind == OBJ_TREE; +} + +static int disambiguate_treeish_only(const struct object_id *oid, void *cb_data_unused) +{ + struct object *obj; + int kind; + + kind = oid_object_info(the_repository, oid, 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(parse_object(oid), NULL, 0); + if (obj && (obj->type == OBJ_TREE || obj->type == OBJ_COMMIT)) + return 1; + return 0; +} + +static int disambiguate_blob_only(const struct object_id *oid, void *cb_data_unused) +{ + int kind = oid_object_info(the_repository, oid, NULL); + return kind == OBJ_BLOB; +} + +static disambiguate_hint_fn default_disambiguate_hint; + +int set_disambiguate_hint_config(const char *var, const char *value) +{ + static const struct { + const char *name; + disambiguate_hint_fn fn; + } hints[] = { + { "none", NULL }, + { "commit", disambiguate_commit_only }, + { "committish", disambiguate_committish_only }, + { "tree", disambiguate_tree_only }, + { "treeish", disambiguate_treeish_only }, + { "blob", disambiguate_blob_only } + }; + int i; + + if (!value) + return config_error_nonbool(var); + + for (i = 0; i < ARRAY_SIZE(hints); i++) { + if (!strcasecmp(value, hints[i].name)) { + default_disambiguate_hint = hints[i].fn; + return 0; + } + } + + return error("unknown hint type for '%s': %s", var, value); +} + +static int init_object_disambiguation(const char *name, int len, + struct disambiguate_state *ds) +{ + int i; + + if (len < MINIMUM_ABBREV || len > GIT_SHA1_HEXSZ) + return -1; + + memset(ds, 0, sizeof(*ds)); + + for (i = 0; i < len ;i++) { + unsigned char c = name[i]; + unsigned char val; + if (c >= '0' && c <= '9') + val = c - '0'; + else if (c >= 'a' && c <= 'f') + val = c - 'a' + 10; + else if (c >= 'A' && c <='F') { + val = c - 'A' + 10; + c -= 'A' - 'a'; + } + else + return -1; + ds->hex_pfx[i] = c; + if (!(i & 1)) + val <<= 4; + ds->bin_pfx.hash[i >> 1] |= val; + } + + ds->len = len; + ds->hex_pfx[len] = '\0'; + prepare_alt_odb(the_repository); + return 0; +} + +static int show_ambiguous_object(const struct object_id *oid, void *data) +{ + const struct disambiguate_state *ds = data; + struct strbuf desc = STRBUF_INIT; + int type; + + + if (ds->fn && !ds->fn(oid, ds->cb_data)) + return 0; + + type = oid_object_info(the_repository, oid, NULL); + if (type == OBJ_COMMIT) { + struct commit *commit = lookup_commit(oid); + if (commit) { + struct pretty_print_context pp = {0}; + pp.date_mode.type = DATE_SHORT; + format_commit_message(commit, " %ad - %s", &desc, &pp); + } + } else if (type == OBJ_TAG) { + struct tag *tag = lookup_tag(oid); + if (!parse_tag(tag) && tag->tag) + strbuf_addf(&desc, " %s", tag->tag); + } + + advise(" %s %s%s", + find_unique_abbrev(oid, DEFAULT_ABBREV), + type_name(type) ? type_name(type) : "unknown type", + desc.buf); + + strbuf_release(&desc); + return 0; +} + +static int get_short_oid(const char *name, int len, struct object_id *oid, + unsigned flags) +{ + int status; + struct disambiguate_state ds; + int quietly = !!(flags & GET_OID_QUIETLY); + + if (init_object_disambiguation(name, len, &ds) < 0) + return -1; + + if (HAS_MULTI_BITS(flags & GET_OID_DISAMBIGUATORS)) + BUG("multiple get_short_oid disambiguator flags"); + + if (flags & GET_OID_COMMIT) + ds.fn = disambiguate_commit_only; + else if (flags & GET_OID_COMMITTISH) + ds.fn = disambiguate_committish_only; + else if (flags & GET_OID_TREE) + ds.fn = disambiguate_tree_only; + else if (flags & GET_OID_TREEISH) + ds.fn = disambiguate_treeish_only; + else if (flags & GET_OID_BLOB) + ds.fn = disambiguate_blob_only; + else + ds.fn = default_disambiguate_hint; + + find_short_object_filename(&ds); + find_short_packed_object(&ds); + status = finish_object_disambiguation(&ds, oid); + + if (!quietly && (status == SHORT_NAME_AMBIGUOUS)) { + error(_("short SHA1 %s is ambiguous"), ds.hex_pfx); + + /* + * We may still have ambiguity if we simply saw a series of + * candidates that did not satisfy our hint function. In + * that case, we still want to show them, so disable the hint + * function entirely. + */ + if (!ds.ambiguous) + ds.fn = NULL; + + advise(_("The candidates are:")); + for_each_abbrev(ds.hex_pfx, show_ambiguous_object, &ds); + } + + return status; +} + +static int collect_ambiguous(const struct object_id *oid, void *data) +{ + oid_array_append(data, oid); + return 0; +} + +int for_each_abbrev(const char *prefix, each_abbrev_fn fn, void *cb_data) +{ + struct oid_array collect = OID_ARRAY_INIT; + struct disambiguate_state ds; + int ret; + + if (init_object_disambiguation(prefix, strlen(prefix), &ds) < 0) + return -1; + + ds.always_call_fn = 1; + ds.fn = collect_ambiguous; + ds.cb_data = &collect; + find_short_object_filename(&ds); + find_short_packed_object(&ds); + + ret = oid_array_for_each_unique(&collect, fn, cb_data); + oid_array_clear(&collect); + return ret; +} + +/* + * Return the slot of the most-significant bit set in "val". There are various + * ways to do this quickly with fls() or __builtin_clzl(), but speed is + * probably not a big deal here. + */ +static unsigned msb(unsigned long val) +{ + unsigned r = 0; + while (val >>= 1) + r++; + return r; +} + +struct min_abbrev_data { + unsigned int init_len; + unsigned int cur_len; + char *hex; + const struct object_id *oid; +}; + +static inline char get_hex_char_from_oid(const struct object_id *oid, + unsigned int pos) +{ + static const char hex[] = "0123456789abcdef"; + + if ((pos & 1) == 0) + return hex[oid->hash[pos >> 1] >> 4]; + else + return hex[oid->hash[pos >> 1] & 0xf]; +} + +static int extend_abbrev_len(const struct object_id *oid, void *cb_data) +{ + struct min_abbrev_data *mad = cb_data; + + unsigned int i = mad->init_len; + while (mad->hex[i] && mad->hex[i] == get_hex_char_from_oid(oid, i)) + i++; + + if (i < GIT_MAX_RAWSZ && i >= mad->cur_len) + mad->cur_len = i + 1; + + return 0; +} + +static void find_abbrev_len_for_pack(struct packed_git *p, + struct min_abbrev_data *mad) +{ + int match = 0; + uint32_t num, first = 0; + struct object_id oid; + const struct object_id *mad_oid; + + if (open_pack_index(p) || !p->num_objects) + return; + + num = p->num_objects; + mad_oid = mad->oid; + match = bsearch_pack(mad_oid, p, &first); + + /* + * first is now the position in the packfile where we would insert + * mad->hash if it does not exist (or the position of mad->hash if + * it does exist). Hence, we consider a maximum of two objects + * nearby for the abbreviation length. + */ + mad->init_len = 0; + if (!match) { + if (nth_packed_object_oid(&oid, p, first)) + extend_abbrev_len(&oid, mad); + } else if (first < num - 1) { + if (nth_packed_object_oid(&oid, p, first + 1)) + extend_abbrev_len(&oid, mad); + } + if (first > 0) { + if (nth_packed_object_oid(&oid, p, first - 1)) + extend_abbrev_len(&oid, mad); + } + mad->init_len = mad->cur_len; +} + +static void find_abbrev_len_packed(struct min_abbrev_data *mad) +{ + struct packed_git *p; + + for (p = get_packed_git(the_repository); p; p = p->next) + find_abbrev_len_for_pack(p, mad); +} + +int find_unique_abbrev_r(char *hex, const struct object_id *oid, int len) +{ + struct disambiguate_state ds; + struct min_abbrev_data mad; + struct object_id oid_ret; + if (len < 0) { + unsigned long count = approximate_object_count(); + /* + * Add one because the MSB only tells us the highest bit set, + * not including the value of all the _other_ bits (so "15" + * is only one off of 2^4, but the MSB is the 3rd bit. + */ + len = msb(count) + 1; + /* + * We now know we have on the order of 2^len objects, which + * expects a collision at 2^(len/2). But we also care about hex + * chars, not bits, and there are 4 bits per hex. So all + * together we need to divide by 2 and round up. + */ + len = DIV_ROUND_UP(len, 2); + /* + * For very small repos, we stick with our regular fallback. + */ + if (len < FALLBACK_DEFAULT_ABBREV) + len = FALLBACK_DEFAULT_ABBREV; + } + + oid_to_hex_r(hex, oid); + if (len == GIT_SHA1_HEXSZ || !len) + return GIT_SHA1_HEXSZ; + + mad.init_len = len; + mad.cur_len = len; + mad.hex = hex; + mad.oid = oid; + + find_abbrev_len_packed(&mad); + + if (init_object_disambiguation(hex, mad.cur_len, &ds) < 0) + return -1; + + ds.fn = extend_abbrev_len; + ds.always_call_fn = 1; + ds.cb_data = (void *)&mad; + + find_short_object_filename(&ds); + (void)finish_object_disambiguation(&ds, &oid_ret); + + hex[mad.cur_len] = 0; + return mad.cur_len; +} + +const char *find_unique_abbrev(const struct object_id *oid, int len) +{ + static int bufno; + static char hexbuffer[4][GIT_MAX_HEXSZ + 1]; + char *hex = hexbuffer[bufno]; + bufno = (bufno + 1) % ARRAY_SIZE(hexbuffer); + find_unique_abbrev_r(hex, oid, len); + return hex; +} + +static int ambiguous_path(const char *path, int len) +{ + int slash = 1; + int cnt; + + for (cnt = 0; cnt < len; cnt++) { + switch (*path++) { + case '\0': + break; + case '/': + if (slash) + break; + slash = 1; + continue; + case '.': + continue; + default: + slash = 0; + continue; + } + break; + } + return slash; +} + +static inline int at_mark(const char *string, int len, + const char **suffix, int nr) +{ + int i; + + for (i = 0; i < nr; i++) { + int suffix_len = strlen(suffix[i]); + if (suffix_len <= len + && !strncasecmp(string, suffix[i], suffix_len)) + return suffix_len; + } + return 0; +} + +static inline int upstream_mark(const char *string, int len) +{ + const char *suffix[] = { "@{upstream}", "@{u}" }; + return at_mark(string, len, suffix, ARRAY_SIZE(suffix)); +} + +static inline int push_mark(const char *string, int len) +{ + const char *suffix[] = { "@{push}" }; + return at_mark(string, len, suffix, ARRAY_SIZE(suffix)); +} + +static int get_oid_1(const char *name, int len, struct object_id *oid, unsigned lookup_flags); +static int interpret_nth_prior_checkout(const char *name, int namelen, struct strbuf *buf); + +static int get_oid_basic(const char *str, int len, struct object_id *oid, + unsigned int flags) +{ + 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\""); + struct object_id tmp_oid; + char *real_ref = NULL; + int refs_found = 0; + int at, reflog_len, nth_prior = 0; + + if (len == GIT_SHA1_HEXSZ && !get_oid_hex(str, oid)) { + if (warn_ambiguous_refs && warn_on_object_refname_ambiguity) { + refs_found = dwim_ref(str, len, &tmp_oid, &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-4; at >= 0; at--) { + if (str[at] == '@' && str[at+1] == '{') { + if (str[at+2] == '-') { + if (at != 0) + /* @{-N} not at start */ + return -1; + nth_prior = 1; + continue; + } + if (!upstream_mark(str + at, len - at) && + !push_mark(str + at, len - at)) { + reflog_len = (len-1) - (at+2); + len = at; + } + break; + } + } + } + + /* Accept only unambiguous ref paths. */ + if (len && ambiguous_path(str, len)) + return -1; + + if (nth_prior) { + struct strbuf buf = STRBUF_INIT; + int detached; + + if (interpret_nth_prior_checkout(str, len, &buf) > 0) { + detached = (buf.len == GIT_SHA1_HEXSZ && !get_oid_hex(buf.buf, oid)); + strbuf_release(&buf); + if (detached) + return 0; + } + } + + if (!len && reflog_len) + /* allow "@{...}" to mean the current branch reflog */ + refs_found = dwim_ref("HEAD", 4, oid, &real_ref); + else if (reflog_len) + refs_found = dwim_log(str, len, oid, &real_ref); + else + refs_found = dwim_ref(str, len, oid, &real_ref); + + if (!refs_found) + return -1; + + if (warn_ambiguous_refs && !(flags & GET_OID_QUIETLY) && + (refs_found > 1 || + !get_short_oid(str, len, &tmp_oid, GET_OID_QUIETLY))) + warning(warn_msg, len, str); + + if (reflog_len) { + int nth, i; + timestamp_t at_time; + timestamp_t co_time; + int co_tz, co_cnt; + + /* Is it asking for N-th entry, or approxidate? */ + for (i = nth = 0; 0 <= nth && i < reflog_len; i++) { + char ch = str[at+2+i]; + if ('0' <= ch && ch <= '9') + nth = nth * 10 + ch - '0'; + else + nth = -1; + } + if (100000000 <= nth) { + at_time = nth; + nth = -1; + } else if (0 <= nth) + at_time = 0; + else { + int errors = 0; + char *tmp = xstrndup(str + at + 2, reflog_len); + at_time = approxidate_careful(tmp, &errors); + free(tmp); + if (errors) { + free(real_ref); + return -1; + } + } + if (read_ref_at(real_ref, flags, at_time, nth, oid, NULL, + &co_time, &co_tz, &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_OID_QUIETLY)) { + warning("Log for '%.*s' only goes " + "back to %s.", len, str, + show_date(co_time, co_tz, DATE_MODE(RFC2822))); + } + } else { + if (flags & GET_OID_QUIETLY) { + exit(128); + } + die("Log for '%.*s' only has %d entries.", + len, str, co_cnt); + } + } + } + + free(real_ref); + return 0; +} + +static int get_parent(const char *name, int len, + struct object_id *result, int idx) +{ + struct object_id oid; + int ret = get_oid_1(name, len, &oid, GET_OID_COMMITTISH); + struct commit *commit; + struct commit_list *p; + + if (ret) + return ret; + commit = lookup_commit_reference(&oid); + if (parse_commit(commit)) + return -1; + if (!idx) { + oidcpy(result, &commit->object.oid); + return 0; + } + p = commit->parents; + while (p) { + if (!--idx) { + oidcpy(result, &p->item->object.oid); + return 0; + } + p = p->next; + } + return -1; +} + +static int get_nth_ancestor(const char *name, int len, + struct object_id *result, int generation) +{ + struct object_id oid; + struct commit *commit; + int ret; + + ret = get_oid_1(name, len, &oid, GET_OID_COMMITTISH); + if (ret) + return ret; + commit = lookup_commit_reference(&oid); + if (!commit) + return -1; + + while (generation--) { + if (parse_commit(commit) || !commit->parents) + return -1; + commit = commit->parents->item; + } + oidcpy(result, &commit->object.oid); + return 0; +} + +struct object *peel_to_type(const char *name, int namelen, + struct object *o, enum object_type expected_type) +{ + if (name && !namelen) + namelen = strlen(name); + while (1) { + if (!o || (!o->parsed && !parse_object(&o->oid))) + return NULL; + if (expected_type == OBJ_ANY || o->type == expected_type) + return o; + if (o->type == OBJ_TAG) + o = ((struct tag*) o)->tagged; + else if (o->type == OBJ_COMMIT) + o = &(get_commit_tree(((struct commit *)o))->object); + else { + if (name) + error("%.*s: expected %s type, but the object " + "dereferences to %s type", + namelen, name, type_name(expected_type), + type_name(o->type)); + return NULL; + } + } +} + +static int peel_onion(const char *name, int len, struct object_id *oid, + unsigned lookup_flags) +{ + struct object_id outer; + const char *sp; + unsigned int expected_type = 0; + struct object *o; + + /* + * "ref^{type}" dereferences ref repeatedly until you cannot + * dereference anymore, or you get an object of given type, + * whichever comes first. "ref^{}" means just dereference + * tags until you get a non-tag. "ref^0" is a shorthand for + * "ref^{commit}". "commit^{tree}" could be used to find the + * top-level tree of the given commit. + */ + if (len < 4 || name[len-1] != '}') + return -1; + + for (sp = name + len - 1; name <= sp; sp--) { + int ch = *sp; + if (ch == '{' && name < sp && sp[-1] == '^') + break; + } + if (sp <= name) + return -1; + + sp++; /* beginning of type name, or closing brace for empty */ + if (starts_with(sp, "commit}")) + expected_type = OBJ_COMMIT; + else if (starts_with(sp, "tag}")) + expected_type = OBJ_TAG; + else if (starts_with(sp, "tree}")) + expected_type = OBJ_TREE; + 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; + + lookup_flags &= ~GET_OID_DISAMBIGUATORS; + if (expected_type == OBJ_COMMIT) + lookup_flags |= GET_OID_COMMITTISH; + else if (expected_type == OBJ_TREE) + lookup_flags |= GET_OID_TREEISH; + + if (get_oid_1(name, sp - name - 2, &outer, lookup_flags)) + return -1; + + o = parse_object(&outer); + if (!o) + return -1; + if (!expected_type) { + o = deref_tag(o, name, sp - name - 2); + if (!o || (!o->parsed && !parse_object(&o->oid))) + return -1; + oidcpy(oid, &o->oid); + return 0; + } + + /* + * 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; + + oidcpy(oid, &o->oid); + if (sp[0] == '/') { + /* "$commit^{/foo}" */ + char *prefix; + int ret; + struct commit_list *list = NULL; + + /* + * $commit^{/}. Some regex implementation may reject. + * We don't need regex anyway. '' pattern always matches. + */ + if (sp[1] == '}') + return 0; + + prefix = xstrndup(sp + 1, name + len - 1 - (sp + 1)); + commit_list_insert((struct commit *)o, &list); + ret = get_oid_oneline(prefix, oid, list); + free(prefix); + return ret; + } + return 0; +} + +static int get_describe_name(const char *name, int len, struct object_id *oid) +{ + const char *cp; + unsigned flags = GET_OID_QUIETLY | GET_OID_COMMIT; + + for (cp = name + len - 1; name + 2 <= cp; cp--) { + char ch = *cp; + if (!isxdigit(ch)) { + /* We must be looking at g in "SOMETHING-g" + * for it to be describe output. + */ + if (ch == 'g' && cp[-1] == '-') { + cp++; + len -= cp - name; + return get_short_oid(cp, len, oid, flags); + } + } + } + return -1; +} + +static int get_oid_1(const char *name, int len, struct object_id *oid, unsigned lookup_flags) +{ + int ret, has_suffix; + const char *cp; + + /* + * "name~3" is "name^^^", "name~" is "name~1", and "name^" is "name^1". + */ + has_suffix = 0; + for (cp = name + len - 1; name <= cp; cp--) { + int ch = *cp; + if ('0' <= ch && ch <= '9') + continue; + if (ch == '~' || ch == '^') + has_suffix = ch; + break; + } + + if (has_suffix) { + int num = 0; + int len1 = cp - name; + cp++; + while (cp < name + len) + num = num * 10 + *cp++ - '0'; + if (!num && len1 == len - 1) + num = 1; + if (has_suffix == '^') + return get_parent(name, len1, oid, num); + /* else if (has_suffix == '~') -- goes without saying */ + return get_nth_ancestor(name, len1, oid, num); + } + + ret = peel_onion(name, len, oid, lookup_flags); + if (!ret) + return 0; + + ret = get_oid_basic(name, len, oid, lookup_flags); + if (!ret) + return 0; + + /* It could be describe output that is "SOMETHING-gXXXX" */ + ret = get_describe_name(name, len, oid); + if (!ret) + return 0; + + return get_short_oid(name, len, oid, 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 negative-matching, prefix the pattern-part with '!-', like: ':/!-WIP'. + * + * For a literal '!' character at the beginning of a pattern, you have to repeat + * that, like: ':/!!foo' + * + * For future extension, all other sequences beginning with ':/!' are reserved. + */ + +/* Remember to update object flag allocation in object.h */ +#define ONELINE_SEEN (1u<<20) + +static int handle_one_ref(const char *path, const struct object_id *oid, + int flag, void *cb_data) +{ + struct commit_list **list = cb_data; + struct object *object = parse_object(oid); + if (!object) + return 0; + if (object->type == OBJ_TAG) { + object = deref_tag(object, path, strlen(path)); + if (!object) + return 0; + } + if (object->type != OBJ_COMMIT) + return 0; + commit_list_insert((struct commit *)object, list); + return 0; +} + +static int get_oid_oneline(const char *prefix, struct object_id *oid, + struct commit_list *list) +{ + struct commit_list *backup = NULL, *l; + int found = 0; + int negative = 0; + regex_t regex; + + if (prefix[0] == '!') { + prefix++; + + if (prefix[0] == '-') { + prefix++; + negative = 1; + } else if (prefix[0] != '!') { + return -1; + } + } + + if (regcomp(®ex, prefix, REG_EXTENDED)) + return -1; + + for (l = list; l; l = l->next) { + l->item->object.flags |= ONELINE_SEEN; + commit_list_insert(l->item, &backup); + } + while (list) { + const char *p, *buf; + struct commit *commit; + int matches; + + commit = pop_most_recent_commit(&list, ONELINE_SEEN); + if (!parse_object(&commit->object.oid)) + continue; + buf = get_commit_buffer(commit, NULL); + p = strstr(buf, "\n\n"); + matches = negative ^ (p && !regexec(®ex, p + 2, 0, NULL, 0)); + unuse_commit_buffer(commit, buf); + + if (matches) { + oidcpy(oid, &commit->object.oid); + found = 1; + break; + } + } + regfree(®ex); + free_commit_list(list); + for (l = backup; l; l = l->next) + clear_commit_marks(l->item, ONELINE_SEEN); + free_commit_list(backup); + return found ? 0 : -1; +} + +struct grab_nth_branch_switch_cbdata { + int remaining; + struct strbuf buf; +}; + +static int grab_nth_branch_switch(struct object_id *ooid, struct object_id *noid, + const char *email, timestamp_t timestamp, int tz, + const char *message, void *cb_data) +{ + struct grab_nth_branch_switch_cbdata *cb = cb_data; + const char *match = NULL, *target = NULL; + size_t len; + + if (skip_prefix(message, "checkout: moving from ", &match)) + target = strstr(match, " to "); + + if (!match || !target) + return 0; + if (--(cb->remaining) == 0) { + len = target - match; + strbuf_reset(&cb->buf); + strbuf_add(&cb->buf, match, len); + return 1; /* we are done */ + } + return 0; +} + +/* + * Parse @{-N} syntax, return the number of characters parsed + * if successful; otherwise signal an error with negative value. + */ +static int interpret_nth_prior_checkout(const char *name, int namelen, + struct strbuf *buf) +{ + long nth; + 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 = memchr(name, '}', namelen); + if (!brace) + return -1; + nth = strtol(name + 3, &num_end, 10); + if (num_end != brace) + return -1; + if (nth <= 0) + return -1; + cb.remaining = nth; + strbuf_init(&cb.buf, 20); + + retval = 0; + 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_oid_mb(const char *name, struct object_id *oid) +{ + struct commit *one, *two; + struct commit_list *mbs; + struct object_id oid_tmp; + const char *dots; + int st; + + dots = strstr(name, "..."); + if (!dots) + return get_oid(name, oid); + if (dots == name) + st = get_oid("HEAD", &oid_tmp); + else { + struct strbuf sb; + strbuf_init(&sb, dots - name); + strbuf_add(&sb, name, dots - name); + st = get_oid_committish(sb.buf, &oid_tmp); + strbuf_release(&sb); + } + if (st) + return st; + one = lookup_commit_reference_gently(&oid_tmp, 0); + if (!one) + return -1; + + if (get_oid_committish(dots[3] ? (dots + 3) : "HEAD", &oid_tmp)) + return -1; + two = lookup_commit_reference_gently(&oid_tmp, 0); + if (!two) + return -1; + mbs = get_merge_bases(one, two); + if (!mbs || mbs->next) + st = -1; + else { + st = 0; + oidcpy(oid, &mbs->item->object.oid); + } + 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, "HEAD", 4); + return 1; +} + +static int reinterpret(const char *name, int namelen, int len, + struct strbuf *buf, unsigned allowed) +{ + /* we have extra data, which might need further processing */ + struct strbuf tmp = STRBUF_INIT; + int used = buf->len; + int ret; + + strbuf_add(buf, name + len, namelen - len); + ret = interpret_branch_name(buf->buf, buf->len, &tmp, allowed); + /* 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 int branch_interpret_allowed(const char *refname, unsigned allowed) +{ + if (!allowed) + return 1; + + if ((allowed & INTERPRET_BRANCH_LOCAL) && + starts_with(refname, "refs/heads/")) + return 1; + if ((allowed & INTERPRET_BRANCH_REMOTE) && + starts_with(refname, "refs/remotes/")) + return 1; + + return 0; +} + +static int interpret_branch_mark(const char *name, int namelen, + int at, struct strbuf *buf, + int (*get_mark)(const char *, int), + const char *(*get_data)(struct branch *, + struct strbuf *), + unsigned allowed) +{ + int len; + struct branch *branch; + struct strbuf err = STRBUF_INIT; + const char *value; + + len = get_mark(name + at, namelen - at); + if (!len) + return -1; + + if (memchr(name, ':', at)) + return -1; + + if (at) { + char *name_str = xmemdupz(name, at); + branch = branch_get(name_str); + free(name_str); + } else + branch = branch_get(NULL); + + value = get_data(branch, &err); + if (!value) + die("%s", err.buf); + + if (!branch_interpret_allowed(value, allowed)) + return -1; + + set_shortened_ref(buf, value); + return len + at; +} + +int interpret_branch_name(const char *name, int namelen, struct strbuf *buf, + unsigned allowed) +{ + char *at; + const char *start; + int len; + + if (!namelen) + namelen = strlen(name); + + if (!allowed || (allowed & INTERPRET_BRANCH_LOCAL)) { + len = interpret_nth_prior_checkout(name, namelen, buf); + 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, allowed); + } + } + + for (start = name; + (at = memchr(start, '@', namelen - (start - name))); + start = at + 1) { + + if (!allowed || (allowed & INTERPRET_BRANCH_HEAD)) { + len = interpret_empty_at(name, namelen, at - name, buf); + if (len > 0) + return reinterpret(name, namelen, len, buf, + allowed); + } + + len = interpret_branch_mark(name, namelen, at - name, buf, + upstream_mark, branch_get_upstream, + allowed); + if (len > 0) + return len; + + len = interpret_branch_mark(name, namelen, at - name, buf, + push_mark, branch_get_push, + allowed); + if (len > 0) + return len; + } + + return -1; +} + +void strbuf_branchname(struct strbuf *sb, const char *name, unsigned allowed) +{ + int len = strlen(name); + int used = interpret_branch_name(name, len, sb, allowed); + + if (used < 0) + used = 0; + strbuf_add(sb, name + used, len - used); +} + +int strbuf_check_branch_ref(struct strbuf *sb, const char *name) +{ + if (startup_info->have_repository) + strbuf_branchname(sb, name, INTERPRET_BRANCH_LOCAL); + else + strbuf_addstr(sb, name); + + /* + * This splice must be done even if we end up rejecting the + * name; builtin/branch.c::copy_or_rename_branch() still wants + * to see what the name expanded to so that "branch -m" can be + * used as a tool to correct earlier mistakes. + */ + strbuf_splice(sb, 0, 0, "refs/heads/", 11); + + if (*name == '-' || + !strcmp(sb->buf, "refs/heads/HEAD")) + return -1; + + return check_refname_format(sb->buf, 0); +} + +/* + * This is like "get_oid_basic()", except it allows "object ID expressions", + * notably "xyz^" for "parent of xyz" + */ +int get_oid(const char *name, struct object_id *oid) +{ + struct object_context unused; + return get_oid_with_context(name, 0, oid, &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_oid_committish(const char *name, struct object_id *oid) +{ + struct object_context unused; + return get_oid_with_context(name, GET_OID_COMMITTISH, + oid, &unused); +} + +int get_oid_treeish(const char *name, struct object_id *oid) +{ + struct object_context unused; + return get_oid_with_context(name, GET_OID_TREEISH, + oid, &unused); +} + +int get_oid_commit(const char *name, struct object_id *oid) +{ + struct object_context unused; + return get_oid_with_context(name, GET_OID_COMMIT, + oid, &unused); +} + +int get_oid_tree(const char *name, struct object_id *oid) +{ + struct object_context unused; + return get_oid_with_context(name, GET_OID_TREE, + oid, &unused); +} + +int get_oid_blob(const char *name, struct object_id *oid) +{ + struct object_context unused; + return get_oid_with_context(name, GET_OID_BLOB, + oid, &unused); +} + +/* Must be called only when object_name:filename doesn't exist. */ +static void diagnose_invalid_oid_path(const char *prefix, + const char *filename, + const struct object_id *tree_oid, + const char *object_name, + int object_name_len) +{ + struct object_id oid; + unsigned mode; + + if (!prefix) + prefix = ""; + + if (file_exists(filename)) + die("Path '%s' exists on disk, but not in '%.*s'.", + filename, object_name_len, object_name); + if (is_missing_file_error(errno)) { + char *fullname = xstrfmt("%s%s", prefix, filename); + + if (!get_tree_entry(tree_oid, fullname, &oid, &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) +{ + const struct cache_entry *ce; + int pos; + unsigned namelen = strlen(filename); + struct strbuf fullname = STRBUF_INIT; + + 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? */ + strbuf_addstr(&fullname, prefix); + strbuf_addstr(&fullname, filename); + pos = cache_name_pos(fullname.buf, fullname.len); + if (pos < 0) + pos = -pos - 1; + if (pos < active_nr) { + ce = active_cache[pos]; + if (ce_namelen(ce) == fullname.len && + !memcmp(ce->name, fullname.buf, fullname.len)) + die("Path '%s' is in the index, but not '%s'.\n" + "Did you mean ':%d:%s' aka ':%d:./%s'?", + fullname.buf, filename, + ce_stage(ce), fullname.buf, + ce_stage(ce), filename); + } + + if (file_exists(filename)) + die("Path '%s' exists on disk, but not in the index.", filename); + if (is_missing_file_error(errno)) + die("Path '%s' does not exist (neither on disk nor in the index).", + filename); + + strbuf_release(&fullname); +} + + +static char *resolve_relative_path(const char *rel) +{ + if (!starts_with(rel, "./") && !starts_with(rel, "../")) + return NULL; + + 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_oid_with_context_1(const char *name, + unsigned flags, + const char *prefix, + struct object_id *oid, + struct object_context *oc) +{ + int ret, bracket_depth; + int namelen = strlen(name); + const char *cp; + int only_to_die = flags & GET_OID_ONLY_TO_DIE; + + if (only_to_die) + flags |= GET_OID_QUIETLY; + + memset(oc, 0, sizeof(*oc)); + oc->mode = S_IFINVALID; + strbuf_init(&oc->symlink_path, 0); + ret = get_oid_1(name, namelen, oid, flags); + if (!ret) + return ret; + /* + * 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; + const struct cache_entry *ce; + char *new_path = NULL; + int pos; + 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_oid_oneline(name + 2, oid, list); + } + if (namelen < 3 || + name[2] != ':' || + name[1] < '0' || '3' < name[1]) + cp = name + 1; + else { + stage = name[1] - '0'; + cp = name + 3; + } + new_path = resolve_relative_path(cp); + if (!new_path) { + namelen = namelen - (cp - name); + } else { + cp = new_path; + namelen = strlen(cp); + } + + if (flags & GET_OID_RECORD_PATH) + oc->path = xstrdup(cp); + + if (!active_cache) + read_cache(); + pos = cache_name_pos(cp, namelen); + if (pos < 0) + pos = -pos - 1; + while (pos < active_nr) { + ce = active_cache[pos]; + if (ce_namelen(ce) != namelen || + memcmp(ce->name, cp, namelen)) + break; + if (ce_stage(ce) == stage) { + oidcpy(oid, &ce->oid); + 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++) { + if (*cp == '{') + bracket_depth++; + else if (bracket_depth && *cp == '}') + bracket_depth--; + else if (!bracket_depth && *cp == ':') + break; + } + if (*cp == ':') { + struct object_id tree_oid; + int len = cp - name; + unsigned sub_flags = flags; + + sub_flags &= ~GET_OID_DISAMBIGUATORS; + sub_flags |= GET_OID_TREEISH; + + if (!get_oid_1(name, len, &tree_oid, sub_flags)) { + const char *filename = cp+1; + char *new_filename = NULL; + + new_filename = resolve_relative_path(filename); + if (new_filename) + filename = new_filename; + if (flags & GET_OID_FOLLOW_SYMLINKS) { - ret = get_tree_entry_follow_symlinks(tree_oid.hash, - filename, oid->hash, &oc->symlink_path, ++ ret = get_tree_entry_follow_symlinks(&tree_oid, ++ filename, oid, &oc->symlink_path, + &oc->mode); + } else { + ret = get_tree_entry(&tree_oid, filename, oid, + &oc->mode); + if (ret && only_to_die) { + diagnose_invalid_oid_path(prefix, + filename, + &tree_oid, + name, len); + } + } - hashcpy(oc->tree, tree_oid.hash); + if (flags & GET_OID_RECORD_PATH) + oc->path = xstrdup(filename); + + 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; + struct object_id oid; + get_oid_with_context_1(name, GET_OID_ONLY_TO_DIE, prefix, &oid, &oc); +} + +int get_oid_with_context(const char *str, unsigned flags, struct object_id *oid, struct object_context *oc) +{ + if (flags & GET_OID_FOLLOW_SYMLINKS && flags & GET_OID_ONLY_TO_DIE) + BUG("incompatible flags for get_sha1_with_context"); + return get_oid_with_context_1(str, flags, NULL, oid, oc); +} diff --cc unpack-trees.c index 7051fcf7d8,038ef7b926..d17f726e75 --- a/unpack-trees.c +++ b/unpack-trees.c @@@ -1284,21 -1284,10 +1284,21 @@@ int unpack_trees(unsigned len, struct t o->result.timestamp.sec = o->src_index->timestamp.sec; o->result.timestamp.nsec = o->src_index->timestamp.nsec; o->result.version = o->src_index->version; - o->result.split_index = o->src_index->split_index; - if (o->result.split_index) + if (!o->src_index->split_index) { + o->result.split_index = NULL; + } else if (o->src_index == o->dst_index) { + /* + * o->dst_index (and thus o->src_index) will be discarded + * and overwritten with o->result at the end of this function, + * so just use src_index's split_index to avoid having to + * create a new one. + */ + o->result.split_index = o->src_index->split_index; o->result.split_index->refcount++; + } else { + o->result.split_index = init_split_index(&o->result); + } - hashcpy(o->result.sha1, o->src_index->sha1); + oidcpy(&o->result.oid, &o->src_index->oid); o->merge_size = len; mark_all_ce_unused(o->src_index); diff --cc upload-pack.c index 87b4d32a6e,1fb4942235..bacc92bbb6 --- a/upload-pack.c +++ b/upload-pack.c @@@ -893,13 -821,10 +895,11 @@@ static void receive_needs(void parse_list_objects_filter(&filter_options, arg); continue; } + if (!skip_prefix(line, "want ", &arg) || - get_oid_hex(arg, &oid_buf)) + parse_oid_hex(arg, &oid_buf, &features)) die("git upload-pack: protocol error, " - "expected to get sha, not '%s'", line); - - features = arg + 40; + "expected to get object ID, not '%s'", line); if (parse_feature_request(features, "deepen-relative")) deepen_relative = 1;