diff options
Diffstat (limited to 'builtin/fast-export.c')
-rw-r--r-- | builtin/fast-export.c | 237 |
1 files changed, 112 insertions, 125 deletions
diff --git a/builtin/fast-export.c b/builtin/fast-export.c index 9f37895..4693d18 100644 --- a/builtin/fast-export.c +++ b/builtin/fast-export.c @@ -4,11 +4,13 @@ * Copyright (C) 2007 Johannes E. Schindelin */ #include "builtin.h" -#include "cache.h" #include "config.h" +#include "gettext.h" +#include "hex.h" #include "refs.h" #include "refspec.h" -#include "object-store.h" +#include "object-file.h" +#include "object-store-ll.h" #include "commit.h" #include "object.h" #include "tag.h" @@ -23,17 +25,16 @@ #include "quote.h" #include "remote.h" #include "blob.h" -#include "commit-slab.h" static const char *fast_export_usage[] = { - N_("git fast-export [rev-list-opts]"), + N_("git fast-export [<rev-list-opts>]"), NULL }; static int progress; -static enum { SIGNED_TAG_ABORT, VERBATIM, WARN, WARN_STRIP, STRIP } signed_tag_mode = SIGNED_TAG_ABORT; -static enum { TAG_FILTERING_ABORT, DROP, REWRITE } tag_of_filtered_mode = TAG_FILTERING_ABORT; -static enum { REENCODE_ABORT, REENCODE_YES, REENCODE_NO } reencode_mode = REENCODE_ABORT; +static enum signed_tag_mode { SIGNED_TAG_ABORT, VERBATIM, WARN, WARN_STRIP, STRIP } signed_tag_mode = SIGNED_TAG_ABORT; +static enum tag_of_filtered_mode { TAG_FILTERING_ABORT, DROP, REWRITE } tag_of_filtered_mode = TAG_FILTERING_ABORT; +static enum reencode_mode { REENCODE_ABORT, REENCODE_YES, REENCODE_NO } reencode_mode = REENCODE_ABORT; static int fake_missing_tagger; static int use_done_feature; static int no_data; @@ -51,16 +52,18 @@ static struct revision_sources revision_sources; static int parse_opt_signed_tag_mode(const struct option *opt, const char *arg, int unset) { + enum signed_tag_mode *val = opt->value; + if (unset || !strcmp(arg, "abort")) - signed_tag_mode = SIGNED_TAG_ABORT; + *val = SIGNED_TAG_ABORT; else if (!strcmp(arg, "verbatim") || !strcmp(arg, "ignore")) - signed_tag_mode = VERBATIM; + *val = VERBATIM; else if (!strcmp(arg, "warn")) - signed_tag_mode = WARN; + *val = WARN; else if (!strcmp(arg, "warn-strip")) - signed_tag_mode = WARN_STRIP; + *val = WARN_STRIP; else if (!strcmp(arg, "strip")) - signed_tag_mode = STRIP; + *val = STRIP; else return error("Unknown signed-tags mode: %s", arg); return 0; @@ -69,12 +72,14 @@ static int parse_opt_signed_tag_mode(const struct option *opt, static int parse_opt_tag_of_filtered_mode(const struct option *opt, const char *arg, int unset) { + enum tag_of_filtered_mode *val = opt->value; + if (unset || !strcmp(arg, "abort")) - tag_of_filtered_mode = TAG_FILTERING_ABORT; + *val = TAG_FILTERING_ABORT; else if (!strcmp(arg, "drop")) - tag_of_filtered_mode = DROP; + *val = DROP; else if (!strcmp(arg, "rewrite")) - tag_of_filtered_mode = REWRITE; + *val = REWRITE; else return error("Unknown tag-of-filtered mode: %s", arg); return 0; @@ -83,21 +88,23 @@ static int parse_opt_tag_of_filtered_mode(const struct option *opt, static int parse_opt_reencode_mode(const struct option *opt, const char *arg, int unset) { + enum reencode_mode *val = opt->value; + if (unset) { - reencode_mode = REENCODE_ABORT; + *val = REENCODE_ABORT; return 0; } switch (git_parse_maybe_bool(arg)) { case 0: - reencode_mode = REENCODE_NO; + *val = REENCODE_NO; break; case 1: - reencode_mode = REENCODE_YES; + *val = REENCODE_YES; break; default: if (!strcasecmp(arg, "abort")) - reencode_mode = REENCODE_ABORT; + *val = REENCODE_ABORT; else return error("Unknown reencoding mode: %s", arg); } @@ -107,21 +114,9 @@ static int parse_opt_reencode_mode(const struct option *opt, static struct decoration idnums; static uint32_t last_idnum; - -static int has_unshown_parent(struct commit *commit) -{ - struct commit_list *parent; - - for (parent = commit->parents; parent; parent = parent->next) - if (!(parent->item->object.flags & SHOWN) && - !(parent->item->object.flags & UNINTERESTING)) - return 1; - return 0; -} - struct anonymized_entry { struct hashmap_entry hash; - const char *anon; + char *anon; const char orig[FLEX_ARRAY]; }; @@ -131,7 +126,7 @@ struct anonymized_entry_key { size_t orig_len; }; -static int anonymized_entry_cmp(const void *unused_cmp_data, +static int anonymized_entry_cmp(const void *cmp_data UNUSED, const struct hashmap_entry *eptr, const struct hashmap_entry *entry_or_key, const void *keydata) @@ -141,8 +136,7 @@ static int anonymized_entry_cmp(const void *unused_cmp_data, a = container_of(eptr, const struct anonymized_entry, hash); if (keydata) { const struct anonymized_entry_key *key = keydata; - int equal = !strncmp(a->orig, key->orig, key->orig_len) && - !a->orig[key->orig_len]; + int equal = !xstrncmpz(a->orig, key->orig, key->orig_len); return !equal; } @@ -150,43 +144,56 @@ static int anonymized_entry_cmp(const void *unused_cmp_data, return strcmp(a->orig, b->orig); } +static struct anonymized_entry *add_anonymized_entry(struct hashmap *map, + unsigned hash, + const char *orig, size_t len, + char *anon) +{ + struct anonymized_entry *ret, *old; + + if (!map->cmpfn) + hashmap_init(map, anonymized_entry_cmp, NULL, 0); + + FLEX_ALLOC_MEM(ret, orig, orig, len); + hashmap_entry_init(&ret->hash, hash); + ret->anon = anon; + old = hashmap_put_entry(map, ret, hash); + + if (old) { + free(old->anon); + free(old); + } + + return ret; +} + /* * Basically keep a cache of X->Y so that we can repeatedly replace * the same anonymized string with another. The actual generation * is farmed out to the generate function. */ static const char *anonymize_str(struct hashmap *map, - char *(*generate)(void *), - const char *orig, size_t len, - void *data) + char *(*generate)(void), + const char *orig, size_t len) { struct anonymized_entry_key key; struct anonymized_entry *ret; - if (!map->cmpfn) - hashmap_init(map, anonymized_entry_cmp, NULL, 0); - hashmap_entry_init(&key.hash, memhash(orig, len)); key.orig = orig; key.orig_len = len; /* First check if it's a token the user configured manually... */ - if (anonymized_seeds.cmpfn) - ret = hashmap_get_entry(&anonymized_seeds, &key, hash, &key); - else - ret = NULL; + ret = hashmap_get_entry(&anonymized_seeds, &key, hash, &key); /* ...otherwise check if we've already seen it in this context... */ if (!ret) ret = hashmap_get_entry(map, &key, hash, &key); /* ...and finally generate a new mapping if necessary */ - if (!ret) { - FLEX_ALLOC_MEM(ret, orig, orig, len); - hashmap_entry_init(&ret->hash, key.hash.hash); - ret->anon = generate(data); - hashmap_put(map, &ret->hash); - } + if (!ret) + ret = add_anonymized_entry(map, key.hash.hash, + orig, len, generate()); return ret->anon; } @@ -199,12 +206,12 @@ static const char *anonymize_str(struct hashmap *map, */ static void anonymize_path(struct strbuf *out, const char *path, struct hashmap *map, - char *(*generate)(void *)) + char *(*generate)(void)) { while (*path) { const char *end_of_component = strchrnul(path, '/'); size_t len = end_of_component - path; - const char *c = anonymize_str(map, generate, path, len, NULL); + const char *c = anonymize_str(map, generate, path, len); strbuf_addstr(out, c); path = end_of_component; if (*path) @@ -308,11 +315,11 @@ static void export_blob(const struct object_id *oid) object = (struct object *)lookup_blob(the_repository, oid); eaten = 0; } else { - buf = read_object_file(oid, &type, &size); + buf = repo_read_object_file(the_repository, oid, &type, &size); if (!buf) die("could not read blob %s", oid_to_hex(oid)); if (check_object_signature(the_repository, oid, buf, size, - type_name(type)) < 0) + type) < 0) die("oid mismatch in blob %s", oid_to_hex(oid)); object = parse_object_buffer(the_repository, oid, type, size, buf, &eaten); @@ -379,7 +386,7 @@ static void print_path_1(const char *path) printf("%s", path); } -static char *anonymize_path_component(void *data) +static char *anonymize_path_component(void) { static int counter; struct strbuf out = STRBUF_INIT; @@ -401,27 +408,27 @@ static void print_path(const char *path) } } -static char *generate_fake_oid(void *data) +static char *generate_fake_oid(void) { static uint32_t counter = 1; /* avoid null oid */ const unsigned hashsz = the_hash_algo->rawsz; - unsigned char out[GIT_MAX_RAWSZ]; + struct object_id oid; char *hex = xmallocz(GIT_MAX_HEXSZ); - hashclr(out); - put_be32(out + hashsz - 4, counter++); - return hash_to_hex_algop_r(hex, out, the_hash_algo); + oidclr(&oid); + put_be32(oid.hash + hashsz - 4, counter++); + return oid_to_hex_r(hex, &oid); } static const char *anonymize_oid(const char *oid_hex) { static struct hashmap objs; size_t len = strlen(oid_hex); - return anonymize_str(&objs, generate_fake_oid, oid_hex, len, NULL); + return anonymize_str(&objs, generate_fake_oid, oid_hex, len); } static void show_filemodify(struct diff_queue_struct *q, - struct diff_options *options, void *data) + struct diff_options *options UNUSED, void *data) { int i; struct string_list *changed = data; @@ -514,7 +521,7 @@ static const char *find_encoding(const char *begin, const char *end) return bol; } -static char *anonymize_ref_component(void *data) +static char *anonymize_ref_component(void) { static int counter; struct strbuf out = STRBUF_INIT; @@ -554,13 +561,13 @@ static const char *anonymize_refname(const char *refname) * We do not even bother to cache commit messages, as they are unlikely * to be repeated verbatim, and it is not that interesting when they are. */ -static char *anonymize_commit_message(const char *old) +static char *anonymize_commit_message(void) { static int counter; return xstrfmt("subject %d\n\nbody\n", counter++); } -static char *anonymize_ident(void *data) +static char *anonymize_ident(void) { static int counter; struct strbuf out = STRBUF_INIT; @@ -603,7 +610,7 @@ static void anonymize_ident_line(const char **beg, const char **end) len = split.mail_end - split.name_begin; ident = anonymize_str(&idents, anonymize_ident, - split.name_begin, len, NULL); + split.name_begin, len); strbuf_addstr(out, ident); strbuf_addch(out, ' '); strbuf_add(out, split.date_begin, split.tz_end - split.date_begin); @@ -630,7 +637,7 @@ static void handle_commit(struct commit *commit, struct rev_info *rev, rev->diffopt.output_format = DIFF_FORMAT_CALLBACK; parse_commit_or_die(commit); - commit_buffer = get_commit_buffer(commit, NULL); + commit_buffer = repo_get_commit_buffer(the_repository, commit, NULL); author = strstr(commit_buffer, "\nauthor "); if (!author) die("could not find author in commit %s", @@ -681,7 +688,7 @@ static void handle_commit(struct commit *commit, struct rev_info *rev, mark_next_object(&commit->object); if (anonymize) { - reencoded = anonymize_commit_message(message); + reencoded = anonymize_commit_message(); } else if (encoding) { switch(reencode_mode) { case REENCODE_YES: @@ -711,7 +718,7 @@ static void handle_commit(struct commit *commit, struct rev_info *rev, ? strlen(message) : 0), reencoded ? reencoded : message ? message : ""); free(reencoded); - unuse_commit_buffer(commit, commit_buffer); + repo_unuse_commit_buffer(the_repository, commit, commit_buffer); for (i = 0, p = commit->parents; p; p = p->next) { struct object *obj = &p->item->object; @@ -744,7 +751,7 @@ static void handle_commit(struct commit *commit, struct rev_info *rev, show_progress(); } -static char *anonymize_tag(void *data) +static char *anonymize_tag(void) { static int counter; struct strbuf out = STRBUF_INIT; @@ -752,20 +759,6 @@ static char *anonymize_tag(void *data) return strbuf_detach(&out, NULL); } -static void handle_tail(struct object_array *commits, struct rev_info *revs, - struct string_list *paths_of_changed_objects) -{ - struct commit *commit; - while (commits->nr) { - commit = (struct commit *)object_array_pop(commits); - if (has_unshown_parent(commit)) { - /* Queue again, to be handled later */ - add_object_array(&commit->object, NULL, commits); - return; - } - handle_commit(commit, revs, paths_of_changed_objects); - } -} static void handle_tag(const char *name, struct tag *tag) { @@ -792,7 +785,8 @@ static void handle_tag(const char *name, struct tag *tag) return; } - buf = read_object_file(&tag->object.oid, &type, &size); + buf = repo_read_object_file(the_repository, &tag->object.oid, &type, + &size); if (!buf) die("could not read tag %s", oid_to_hex(&tag->object.oid)); message = memmem(buf, size, "\n\n", 2); @@ -820,7 +814,8 @@ static void handle_tag(const char *name, struct tag *tag) if (message) { static struct hashmap tags; message = anonymize_str(&tags, anonymize_tag, - message, message_size, NULL); + message, message_size); + message_size = strlen(message); } } @@ -870,7 +865,7 @@ static void handle_tag(const char *name, struct tag *tag) p = rewrite_commit((struct commit *)tagged); if (!p) { printf("reset %s\nfrom %s\n\n", - name, oid_to_hex(&null_oid)); + name, oid_to_hex(null_oid())); free(buf); return; } @@ -884,7 +879,7 @@ static void handle_tag(const char *name, struct tag *tag) if (tagged->type == OBJ_TAG) { printf("reset %s\nfrom %s\n\n", - name, oid_to_hex(&null_oid)); + name, oid_to_hex(null_oid())); } skip_prefix(name, "refs/tags/", &name); printf("tag %s\n", name); @@ -923,7 +918,6 @@ static struct commit *get_commit(struct rev_cmdline_entry *e, char *full_name) if (!tag) die("Tag %s points nowhere?", e->name); return (struct commit *)tag; - break; } default: return NULL; @@ -943,7 +937,8 @@ static void get_tags_and_duplicates(struct rev_cmdline_info *info) if (e->flags & UNINTERESTING) continue; - if (dwim_ref(e->name, strlen(e->name), &oid, &full_name) != 1) + if (repo_dwim_ref(the_repository, e->name, strlen(e->name), + &oid, &full_name, 0) != 1) continue; if (refspecs.nr) { @@ -1017,7 +1012,7 @@ static void handle_tags_and_duplicates(struct string_list *extras) * it. */ printf("reset %s\nfrom %s\n\n", - name, oid_to_hex(&null_oid)); + name, oid_to_hex(null_oid())); continue; } @@ -1026,7 +1021,7 @@ static void handle_tags_and_duplicates(struct string_list *extras) /* * Getting here means we have a commit which * was excluded by a negative refspec (e.g. - * fast-export ^master master). If we are + * fast-export ^HEAD HEAD). If we are * referencing excluded commits, set the ref * to the exact commit. Otherwise, the user * wants the branch exported but every commit @@ -1036,7 +1031,7 @@ static void handle_tags_and_duplicates(struct string_list *extras) if (!reference_excluded_commits) { /* delete the ref */ printf("reset %s\nfrom %s\n\n", - name, oid_to_hex(&null_oid)); + name, oid_to_hex(null_oid())); continue; } /* set ref to commit using oid, not mark */ @@ -1147,15 +1142,10 @@ static void handle_deletes(void) continue; printf("reset %s\nfrom %s\n\n", - refspec->dst, oid_to_hex(&null_oid)); + refspec->dst, oid_to_hex(null_oid())); } } -static char *anonymize_seed(void *data) -{ - return xstrdup(data); -} - static int parse_opt_anonymize_map(const struct option *opt, const char *arg, int unset) { @@ -1177,7 +1167,8 @@ static int parse_opt_anonymize_map(const struct option *opt, if (!keylen || !*value) return error(_("--anonymize-map token cannot be empty")); - anonymize_str(map, anonymize_seed, arg, keylen, (void *)value); + add_anonymized_entry(map, memhash(arg, keylen), arg, keylen, + xstrdup(value)); return 0; } @@ -1185,7 +1176,6 @@ static int parse_opt_anonymize_map(const struct option *opt, int cmd_fast_export(int argc, const char **argv, const char *prefix) { struct rev_info revs; - struct object_array commits = OBJECT_ARRAY_INIT; struct commit *commit; char *export_filename = NULL, *import_filename = NULL, @@ -1206,32 +1196,32 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix) N_("select handling of commit messages in an alternate encoding"), parse_opt_reencode_mode), OPT_STRING(0, "export-marks", &export_filename, N_("file"), - N_("Dump marks to this file")), + N_("dump marks to this file")), OPT_STRING(0, "import-marks", &import_filename, N_("file"), - N_("Import marks from this file")), + N_("import marks from this file")), OPT_STRING(0, "import-marks-if-exists", &import_filename_if_exists, N_("file"), - N_("Import marks from this file if it exists")), + N_("import marks from this file if it exists")), OPT_BOOL(0, "fake-missing-tagger", &fake_missing_tagger, - N_("Fake a tagger when tags lack one")), + N_("fake a tagger when tags lack one")), OPT_BOOL(0, "full-tree", &full_tree, - N_("Output full tree for each commit")), + N_("output full tree for each commit")), OPT_BOOL(0, "use-done-feature", &use_done_feature, - N_("Use the done feature to terminate the stream")), - OPT_BOOL(0, "no-data", &no_data, N_("Skip output of blob data")), + N_("use the done feature to terminate the stream")), + OPT_BOOL(0, "no-data", &no_data, N_("skip output of blob data")), OPT_STRING_LIST(0, "refspec", &refspecs_list, N_("refspec"), - N_("Apply refspec to exported refs")), + N_("apply refspec to exported refs")), OPT_BOOL(0, "anonymize", &anonymize, N_("anonymize output")), OPT_CALLBACK_F(0, "anonymize-map", &anonymized_seeds, N_("from:to"), N_("convert <from> to <to> in anonymized output"), PARSE_OPT_NONEG, parse_opt_anonymize_map), OPT_BOOL(0, "reference-excluded-parents", - &reference_excluded_commits, N_("Reference parents which are not in fast-export stream by object id")), + &reference_excluded_commits, N_("reference parents which are not in fast-export stream by object id")), OPT_BOOL(0, "show-original-ids", &show_original_ids, - N_("Show original object ids of blobs/commits")), + N_("show original object ids of blobs/commits")), OPT_BOOL(0, "mark-tags", &mark_tags, - N_("Label tags with mark ids")), + N_("label tags with mark ids")), OPT_END() }; @@ -1248,13 +1238,13 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix) revs.sources = &revision_sources; revs.rewrite_parents = 1; argc = parse_options(argc, argv, prefix, options, fast_export_usage, - PARSE_OPT_KEEP_ARGV0 | PARSE_OPT_KEEP_UNKNOWN); + PARSE_OPT_KEEP_ARGV0 | PARSE_OPT_KEEP_UNKNOWN_OPT); argc = setup_revisions(argc, argv, &revs, NULL); if (argc > 1) usage_with_options (fast_export_usage, options); if (anonymized_seeds.cmpfn && !anonymize) - die(_("--anonymize-map without --anonymize does not make sense")); + die(_("the option '%s' requires '%s'"), "--anonymize-map", "--anonymize"); if (refspecs_list.nr) { int i; @@ -1269,7 +1259,7 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix) printf("feature done\n"); if (import_filename && import_filename_if_exists) - die(_("Cannot pass both --import-marks and --import-marks-if-exists")); + die(_("options '%s' and '%s' cannot be used together"), "--import-marks", "--import-marks-if-exists"); if (import_filename) import_marks(import_filename, 0); else if (import_filename_if_exists) @@ -1283,18 +1273,14 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix) if (prepare_revision_walk(&revs)) die("revision walk setup failed"); + + revs.reverse = 1; revs.diffopt.format_callback = show_filemodify; revs.diffopt.format_callback_data = &paths_of_changed_objects; revs.diffopt.flags.recursive = 1; - while ((commit = get_revision(&revs))) { - if (has_unshown_parent(commit)) { - add_object_array(&commit->object, NULL, &commits); - } - else { - handle_commit(commit, &revs, &paths_of_changed_objects); - handle_tail(&commits, &revs, &paths_of_changed_objects); - } - } + revs.diffopt.no_free = 1; + while ((commit = get_revision(&revs))) + handle_commit(commit, &revs, &paths_of_changed_objects); handle_tags_and_duplicates(&extra_refs); handle_tags_and_duplicates(&tag_refs); @@ -1307,6 +1293,7 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix) printf("done\n"); refspec_clear(&refspecs); + release_revisions(&revs); return 0; } |