From: Junio C Hamano Date: Mon, 19 Jun 2017 19:38:44 +0000 (-0700) Subject: Merge branch 'bw/object-id' X-Git-Tag: v2.14.0-rc0~86 X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/a6f38c109b6e70a1c788581194fc9b8669eea231?ds=inline;hp=-c Merge branch 'bw/object-id' Conversion from uchar[20] to struct object_id continues. * bw/object-id: (33 commits) diff: rename diff_fill_sha1_info to diff_fill_oid_info diffcore-rename: use is_empty_blob_oid tree-diff: convert path_appendnew to object_id tree-diff: convert diff_tree_paths to struct object_id tree-diff: convert try_to_follow_renames to struct object_id builtin/diff-tree: cleanup references to sha1 diff-tree: convert diff_tree_sha1 to struct object_id notes-merge: convert write_note_to_worktree to struct object_id notes-merge: convert verify_notes_filepair to struct object_id notes-merge: convert find_notes_merge_pair_ps to struct object_id notes-merge: convert merge_from_diffs to struct object_id notes-merge: convert notes_merge* to struct object_id tree-diff: convert diff_root_tree_sha1 to struct object_id combine-diff: convert find_paths_* to struct object_id combine-diff: convert diff_tree_combined to struct object_id diff: convert diff_flush_patch_id to struct object_id patch-ids: convert to struct object_id diff: finish conversion for prepare_temp_file to struct object_id diff: convert reuse_worktree_file to struct object_id diff: convert fill_filespec to struct object_id ... --- a6f38c109b6e70a1c788581194fc9b8669eea231 diff --combined blame.c index 843c845cba,0000000000..194b58e960 mode 100644,000000..100644 --- a/blame.c +++ b/blame.c @@@ -1,1863 -1,0 +1,1863 @@@ +#include "cache.h" +#include "refs.h" +#include "cache-tree.h" +#include "mergesort.h" +#include "diff.h" +#include "diffcore.h" +#include "tag.h" +#include "blame.h" + +void blame_origin_decref(struct blame_origin *o) +{ + if (o && --o->refcnt <= 0) { + struct blame_origin *p, *l = NULL; + if (o->previous) + blame_origin_decref(o->previous); + free(o->file.ptr); + /* Should be present exactly once in commit chain */ + for (p = o->commit->util; p; l = p, p = p->next) { + if (p == o) { + if (l) + l->next = p->next; + else + o->commit->util = p->next; + free(o); + return; + } + } + die("internal error in blame_origin_decref"); + } +} + +/* + * Given a commit and a path in it, create a new origin structure. + * The callers that add blame to the scoreboard should use + * get_origin() to obtain shared, refcounted copy instead of calling + * this function directly. + */ +static struct blame_origin *make_origin(struct commit *commit, const char *path) +{ + struct blame_origin *o; + FLEX_ALLOC_STR(o, path, path); + o->commit = commit; + o->refcnt = 1; + o->next = commit->util; + commit->util = o; + return o; +} + +/* + * Locate an existing origin or create a new one. + * This moves the origin to front position in the commit util list. + */ +static struct blame_origin *get_origin(struct commit *commit, const char *path) +{ + struct blame_origin *o, *l; + + for (o = commit->util, l = NULL; o; l = o, o = o->next) { + if (!strcmp(o->path, path)) { + /* bump to front */ + if (l) { + l->next = o->next; + o->next = commit->util; + commit->util = o; + } + return blame_origin_incref(o); + } + } + return make_origin(commit, path); +} + + + +static void verify_working_tree_path(struct commit *work_tree, const char *path) +{ + struct commit_list *parents; + int pos; + + for (parents = work_tree->parents; parents; parents = parents->next) { + const struct object_id *commit_oid = &parents->item->object.oid; + struct object_id blob_oid; + unsigned mode; + + if (!get_tree_entry(commit_oid->hash, path, blob_oid.hash, &mode) && + sha1_object_info(blob_oid.hash, NULL) == OBJ_BLOB) + return; + } + + pos = cache_name_pos(path, strlen(path)); + if (pos >= 0) + ; /* path is in the index */ + else if (-1 - pos < active_nr && + !strcmp(active_cache[-1 - pos]->name, path)) + ; /* path is in the index, unmerged */ + else + die("no such path '%s' in HEAD", path); +} + +static struct commit_list **append_parent(struct commit_list **tail, const struct object_id *oid) +{ + struct commit *parent; + + parent = lookup_commit_reference(oid); + if (!parent) + die("no such commit %s", oid_to_hex(oid)); + return &commit_list_insert(parent, tail)->next; +} + +static void append_merge_parents(struct commit_list **tail) +{ + int merge_head; + struct strbuf line = STRBUF_INIT; + + merge_head = open(git_path_merge_head(), O_RDONLY); + if (merge_head < 0) { + if (errno == ENOENT) + return; + die("cannot open '%s' for reading", git_path_merge_head()); + } + + while (!strbuf_getwholeline_fd(&line, merge_head, '\n')) { + struct object_id oid; + if (line.len < GIT_SHA1_HEXSZ || get_oid_hex(line.buf, &oid)) + die("unknown line in '%s': %s", git_path_merge_head(), line.buf); + tail = append_parent(tail, &oid); + } + close(merge_head); + strbuf_release(&line); +} + +/* + * This isn't as simple as passing sb->buf and sb->len, because we + * want to transfer ownership of the buffer to the commit (so we + * must use detach). + */ +static void set_commit_buffer_from_strbuf(struct commit *c, struct strbuf *sb) +{ + size_t len; + void *buf = strbuf_detach(sb, &len); + set_commit_buffer(c, buf, len); +} + +/* + * Prepare a dummy commit that represents the work tree (or staged) item. + * Note that annotating work tree item never works in the reverse. + */ +static struct commit *fake_working_tree_commit(struct diff_options *opt, + const char *path, + const char *contents_from) +{ + struct commit *commit; + struct blame_origin *origin; + struct commit_list **parent_tail, *parent; + struct object_id head_oid; + struct strbuf buf = STRBUF_INIT; + const char *ident; + time_t now; + int size, len; + struct cache_entry *ce; + unsigned mode; + struct strbuf msg = STRBUF_INIT; + + read_cache(); + time(&now); + commit = alloc_commit_node(); + commit->object.parsed = 1; + commit->date = now; + parent_tail = &commit->parents; + + if (!resolve_ref_unsafe("HEAD", RESOLVE_REF_READING, head_oid.hash, NULL)) + die("no such ref: HEAD"); + + parent_tail = append_parent(parent_tail, &head_oid); + append_merge_parents(parent_tail); + verify_working_tree_path(commit, path); + + origin = make_origin(commit, path); + + ident = fmt_ident("Not Committed Yet", "not.committed.yet", NULL, 0); + strbuf_addstr(&msg, "tree 0000000000000000000000000000000000000000\n"); + for (parent = commit->parents; parent; parent = parent->next) + strbuf_addf(&msg, "parent %s\n", + oid_to_hex(&parent->item->object.oid)); + strbuf_addf(&msg, + "author %s\n" + "committer %s\n\n" + "Version of %s from %s\n", + ident, ident, path, + (!contents_from ? path : + (!strcmp(contents_from, "-") ? "standard input" : contents_from))); + set_commit_buffer_from_strbuf(commit, &msg); + + if (!contents_from || strcmp("-", contents_from)) { + struct stat st; + const char *read_from; + char *buf_ptr; + unsigned long buf_len; + + if (contents_from) { + if (stat(contents_from, &st) < 0) + die_errno("Cannot stat '%s'", contents_from); + read_from = contents_from; + } + else { + if (lstat(path, &st) < 0) + die_errno("Cannot lstat '%s'", path); + read_from = path; + } + mode = canon_mode(st.st_mode); + + switch (st.st_mode & S_IFMT) { + case S_IFREG: + if (DIFF_OPT_TST(opt, ALLOW_TEXTCONV) && + textconv_object(read_from, mode, &null_oid, 0, &buf_ptr, &buf_len)) + strbuf_attach(&buf, buf_ptr, buf_len, buf_len + 1); + else if (strbuf_read_file(&buf, read_from, st.st_size) != st.st_size) + die_errno("cannot open or read '%s'", read_from); + break; + case S_IFLNK: + if (strbuf_readlink(&buf, read_from, st.st_size) < 0) + die_errno("cannot readlink '%s'", read_from); + break; + default: + die("unsupported file type %s", read_from); + } + } + else { + /* Reading from stdin */ + mode = 0; + if (strbuf_read(&buf, 0, 0) < 0) + die_errno("failed to read from stdin"); + } + convert_to_git(path, buf.buf, buf.len, &buf, 0); + origin->file.ptr = buf.buf; + origin->file.size = buf.len; + pretend_sha1_file(buf.buf, buf.len, OBJ_BLOB, origin->blob_oid.hash); + + /* + * Read the current index, replace the path entry with + * origin->blob_sha1 without mucking with its mode or type + * bits; we are not going to write this index out -- we just + * want to run "diff-index --cached". + */ + discard_cache(); + read_cache(); + + len = strlen(path); + if (!mode) { + int pos = cache_name_pos(path, len); + if (0 <= pos) + mode = active_cache[pos]->ce_mode; + else + /* Let's not bother reading from HEAD tree */ + mode = S_IFREG | 0644; + } + size = cache_entry_size(len); + ce = xcalloc(1, size); + oidcpy(&ce->oid, &origin->blob_oid); + memcpy(ce->name, path, len); + ce->ce_flags = create_ce_flags(0); + ce->ce_namelen = len; + ce->ce_mode = create_ce_mode(mode); + add_cache_entry(ce, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE); + + cache_tree_invalidate_path(&the_index, path); + + return commit; +} + + + +static int diff_hunks(mmfile_t *file_a, mmfile_t *file_b, + xdl_emit_hunk_consume_func_t hunk_func, void *cb_data, int xdl_opts) +{ + xpparam_t xpp = {0}; + xdemitconf_t xecfg = {0}; + xdemitcb_t ecb = {NULL}; + + xpp.flags = xdl_opts; + xecfg.hunk_func = hunk_func; + ecb.priv = cb_data; + return xdi_diff(file_a, file_b, &xpp, &xecfg, &ecb); +} + +/* + * Given an origin, prepare mmfile_t structure to be used by the + * diff machinery + */ +static void fill_origin_blob(struct diff_options *opt, + struct blame_origin *o, mmfile_t *file, int *num_read_blob) +{ + if (!o->file.ptr) { + enum object_type type; + unsigned long file_size; + + (*num_read_blob)++; + if (DIFF_OPT_TST(opt, ALLOW_TEXTCONV) && + textconv_object(o->path, o->mode, &o->blob_oid, 1, &file->ptr, &file_size)) + ; + else + file->ptr = read_sha1_file(o->blob_oid.hash, &type, + &file_size); + file->size = file_size; + + if (!file->ptr) + die("Cannot read blob %s for path %s", + oid_to_hex(&o->blob_oid), + o->path); + o->file = *file; + } + else + *file = o->file; +} + +static void drop_origin_blob(struct blame_origin *o) +{ + if (o->file.ptr) { + free(o->file.ptr); + o->file.ptr = NULL; + } +} + +/* + * Any merge of blames happens on lists of blames that arrived via + * different parents in a single suspect. In this case, we want to + * sort according to the suspect line numbers as opposed to the final + * image line numbers. The function body is somewhat longish because + * it avoids unnecessary writes. + */ + +static struct blame_entry *blame_merge(struct blame_entry *list1, + struct blame_entry *list2) +{ + struct blame_entry *p1 = list1, *p2 = list2, + **tail = &list1; + + if (!p1) + return p2; + if (!p2) + return p1; + + if (p1->s_lno <= p2->s_lno) { + do { + tail = &p1->next; + if ((p1 = *tail) == NULL) { + *tail = p2; + return list1; + } + } while (p1->s_lno <= p2->s_lno); + } + for (;;) { + *tail = p2; + do { + tail = &p2->next; + if ((p2 = *tail) == NULL) { + *tail = p1; + return list1; + } + } while (p1->s_lno > p2->s_lno); + *tail = p1; + do { + tail = &p1->next; + if ((p1 = *tail) == NULL) { + *tail = p2; + return list1; + } + } while (p1->s_lno <= p2->s_lno); + } +} + +static void *get_next_blame(const void *p) +{ + return ((struct blame_entry *)p)->next; +} + +static void set_next_blame(void *p1, void *p2) +{ + ((struct blame_entry *)p1)->next = p2; +} + +/* + * Final image line numbers are all different, so we don't need a + * three-way comparison here. + */ + +static int compare_blame_final(const void *p1, const void *p2) +{ + return ((struct blame_entry *)p1)->lno > ((struct blame_entry *)p2)->lno + ? 1 : -1; +} + +static int compare_blame_suspect(const void *p1, const void *p2) +{ + const struct blame_entry *s1 = p1, *s2 = p2; + /* + * to allow for collating suspects, we sort according to the + * respective pointer value as the primary sorting criterion. + * The actual relation is pretty unimportant as long as it + * establishes a total order. Comparing as integers gives us + * that. + */ + if (s1->suspect != s2->suspect) + return (intptr_t)s1->suspect > (intptr_t)s2->suspect ? 1 : -1; + if (s1->s_lno == s2->s_lno) + return 0; + return s1->s_lno > s2->s_lno ? 1 : -1; +} + +void blame_sort_final(struct blame_scoreboard *sb) +{ + sb->ent = llist_mergesort(sb->ent, get_next_blame, set_next_blame, + compare_blame_final); +} + +static int compare_commits_by_reverse_commit_date(const void *a, + const void *b, + void *c) +{ + return -compare_commits_by_commit_date(a, b, c); +} + +/* + * For debugging -- origin is refcounted, and this asserts that + * we do not underflow. + */ +static void sanity_check_refcnt(struct blame_scoreboard *sb) +{ + int baa = 0; + struct blame_entry *ent; + + for (ent = sb->ent; ent; ent = ent->next) { + /* Nobody should have zero or negative refcnt */ + if (ent->suspect->refcnt <= 0) { + fprintf(stderr, "%s in %s has negative refcnt %d\n", + ent->suspect->path, + oid_to_hex(&ent->suspect->commit->object.oid), + ent->suspect->refcnt); + baa = 1; + } + } + if (baa) + sb->on_sanity_fail(sb, baa); +} + +/* + * If two blame entries that are next to each other came from + * contiguous lines in the same origin (i.e. pair), + * merge them together. + */ +void blame_coalesce(struct blame_scoreboard *sb) +{ + struct blame_entry *ent, *next; + + for (ent = sb->ent; ent && (next = ent->next); ent = next) { + if (ent->suspect == next->suspect && + ent->s_lno + ent->num_lines == next->s_lno) { + ent->num_lines += next->num_lines; + ent->next = next->next; + blame_origin_decref(next->suspect); + free(next); + ent->score = 0; + next = ent; /* again */ + } + } + + if (sb->debug) /* sanity */ + sanity_check_refcnt(sb); +} + +/* + * Merge the given sorted list of blames into a preexisting origin. + * If there were no previous blames to that commit, it is entered into + * the commit priority queue of the score board. + */ + +static void queue_blames(struct blame_scoreboard *sb, struct blame_origin *porigin, + struct blame_entry *sorted) +{ + if (porigin->suspects) + porigin->suspects = blame_merge(porigin->suspects, sorted); + else { + struct blame_origin *o; + for (o = porigin->commit->util; o; o = o->next) { + if (o->suspects) { + porigin->suspects = sorted; + return; + } + } + porigin->suspects = sorted; + prio_queue_put(&sb->commits, porigin->commit); + } +} + +/* + * Fill the blob_sha1 field of an origin if it hasn't, so that later + * call to fill_origin_blob() can use it to locate the data. blob_sha1 + * for an origin is also used to pass the blame for the entire file to + * the parent to detect the case where a child's blob is identical to + * that of its parent's. + * + * This also fills origin->mode for corresponding tree path. + */ +static int fill_blob_sha1_and_mode(struct blame_origin *origin) +{ + if (!is_null_oid(&origin->blob_oid)) + return 0; + if (get_tree_entry(origin->commit->object.oid.hash, + origin->path, + origin->blob_oid.hash, &origin->mode)) + goto error_out; + if (sha1_object_info(origin->blob_oid.hash, NULL) != OBJ_BLOB) + goto error_out; + return 0; + error_out: + oidclr(&origin->blob_oid); + origin->mode = S_IFINVALID; + return -1; +} + +/* + * We have an origin -- check if the same path exists in the + * parent and return an origin structure to represent it. + */ +static struct blame_origin *find_origin(struct commit *parent, + struct blame_origin *origin) +{ + struct blame_origin *porigin; + struct diff_options diff_opts; + const char *paths[2]; + + /* First check any existing origins */ + for (porigin = parent->util; porigin; porigin = porigin->next) + if (!strcmp(porigin->path, origin->path)) { + /* + * The same path between origin and its parent + * without renaming -- the most common case. + */ + return blame_origin_incref (porigin); + } + + /* See if the origin->path is different between parent + * and origin first. Most of the time they are the + * same and diff-tree is fairly efficient about this. + */ + diff_setup(&diff_opts); + DIFF_OPT_SET(&diff_opts, RECURSIVE); + diff_opts.detect_rename = 0; + diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; + paths[0] = origin->path; + paths[1] = NULL; + + parse_pathspec(&diff_opts.pathspec, + PATHSPEC_ALL_MAGIC & ~PATHSPEC_LITERAL, + PATHSPEC_LITERAL_PATH, "", paths); + diff_setup_done(&diff_opts); + + if (is_null_oid(&origin->commit->object.oid)) + do_diff_cache(&parent->tree->object.oid, &diff_opts); + else - diff_tree_sha1(parent->tree->object.oid.hash, - origin->commit->tree->object.oid.hash, - "", &diff_opts); ++ diff_tree_oid(&parent->tree->object.oid, ++ &origin->commit->tree->object.oid, ++ "", &diff_opts); + diffcore_std(&diff_opts); + + if (!diff_queued_diff.nr) { + /* The path is the same as parent */ + porigin = get_origin(parent, origin->path); + oidcpy(&porigin->blob_oid, &origin->blob_oid); + porigin->mode = origin->mode; + } else { + /* + * Since origin->path is a pathspec, if the parent + * commit had it as a directory, we will see a whole + * bunch of deletion of files in the directory that we + * do not care about. + */ + int i; + struct diff_filepair *p = NULL; + for (i = 0; i < diff_queued_diff.nr; i++) { + const char *name; + p = diff_queued_diff.queue[i]; + name = p->one->path ? p->one->path : p->two->path; + if (!strcmp(name, origin->path)) + break; + } + if (!p) + die("internal error in blame::find_origin"); + switch (p->status) { + default: + die("internal error in blame::find_origin (%c)", + p->status); + case 'M': + porigin = get_origin(parent, origin->path); + oidcpy(&porigin->blob_oid, &p->one->oid); + porigin->mode = p->one->mode; + break; + case 'A': + case 'T': + /* Did not exist in parent, or type changed */ + break; + } + } + diff_flush(&diff_opts); + clear_pathspec(&diff_opts.pathspec); + return porigin; +} + +/* + * We have an origin -- find the path that corresponds to it in its + * parent and return an origin structure to represent it. + */ +static struct blame_origin *find_rename(struct commit *parent, + struct blame_origin *origin) +{ + struct blame_origin *porigin = NULL; + struct diff_options diff_opts; + int i; + + diff_setup(&diff_opts); + DIFF_OPT_SET(&diff_opts, RECURSIVE); + diff_opts.detect_rename = DIFF_DETECT_RENAME; + diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; + diff_opts.single_follow = origin->path; + diff_setup_done(&diff_opts); + + if (is_null_oid(&origin->commit->object.oid)) + do_diff_cache(&parent->tree->object.oid, &diff_opts); + else - diff_tree_sha1(parent->tree->object.oid.hash, - origin->commit->tree->object.oid.hash, - "", &diff_opts); ++ diff_tree_oid(&parent->tree->object.oid, ++ &origin->commit->tree->object.oid, ++ "", &diff_opts); + diffcore_std(&diff_opts); + + for (i = 0; i < diff_queued_diff.nr; i++) { + struct diff_filepair *p = diff_queued_diff.queue[i]; + if ((p->status == 'R' || p->status == 'C') && + !strcmp(p->two->path, origin->path)) { + porigin = get_origin(parent, p->one->path); + oidcpy(&porigin->blob_oid, &p->one->oid); + porigin->mode = p->one->mode; + break; + } + } + diff_flush(&diff_opts); + clear_pathspec(&diff_opts.pathspec); + return porigin; +} + +/* + * Append a new blame entry to a given output queue. + */ +static void add_blame_entry(struct blame_entry ***queue, + const struct blame_entry *src) +{ + struct blame_entry *e = xmalloc(sizeof(*e)); + memcpy(e, src, sizeof(*e)); + blame_origin_incref(e->suspect); + + e->next = **queue; + **queue = e; + *queue = &e->next; +} + +/* + * src typically is on-stack; we want to copy the information in it to + * a malloced blame_entry that gets added to the given queue. The + * origin of dst loses a refcnt. + */ +static void dup_entry(struct blame_entry ***queue, + struct blame_entry *dst, struct blame_entry *src) +{ + blame_origin_incref(src->suspect); + blame_origin_decref(dst->suspect); + memcpy(dst, src, sizeof(*src)); + dst->next = **queue; + **queue = dst; + *queue = &dst->next; +} + +const char *blame_nth_line(struct blame_scoreboard *sb, long lno) +{ + return sb->final_buf + sb->lineno[lno]; +} + +/* + * It is known that lines between tlno to same came from parent, and e + * has an overlap with that range. it also is known that parent's + * line plno corresponds to e's line tlno. + * + * <---- e -----> + * <------> + * <------------> + * <------------> + * <------------------> + * + * Split e into potentially three parts; before this chunk, the chunk + * to be blamed for the parent, and after that portion. + */ +static void split_overlap(struct blame_entry *split, + struct blame_entry *e, + int tlno, int plno, int same, + struct blame_origin *parent) +{ + int chunk_end_lno; + memset(split, 0, sizeof(struct blame_entry [3])); + + if (e->s_lno < tlno) { + /* there is a pre-chunk part not blamed on parent */ + split[0].suspect = blame_origin_incref(e->suspect); + split[0].lno = e->lno; + split[0].s_lno = e->s_lno; + split[0].num_lines = tlno - e->s_lno; + split[1].lno = e->lno + tlno - e->s_lno; + split[1].s_lno = plno; + } + else { + split[1].lno = e->lno; + split[1].s_lno = plno + (e->s_lno - tlno); + } + + if (same < e->s_lno + e->num_lines) { + /* there is a post-chunk part not blamed on parent */ + split[2].suspect = blame_origin_incref(e->suspect); + split[2].lno = e->lno + (same - e->s_lno); + split[2].s_lno = e->s_lno + (same - e->s_lno); + split[2].num_lines = e->s_lno + e->num_lines - same; + chunk_end_lno = split[2].lno; + } + else + chunk_end_lno = e->lno + e->num_lines; + split[1].num_lines = chunk_end_lno - split[1].lno; + + /* + * if it turns out there is nothing to blame the parent for, + * forget about the splitting. !split[1].suspect signals this. + */ + if (split[1].num_lines < 1) + return; + split[1].suspect = blame_origin_incref(parent); +} + +/* + * split_overlap() divided an existing blame e into up to three parts + * in split. Any assigned blame is moved to queue to + * reflect the split. + */ +static void split_blame(struct blame_entry ***blamed, + struct blame_entry ***unblamed, + struct blame_entry *split, + struct blame_entry *e) +{ + if (split[0].suspect && split[2].suspect) { + /* The first part (reuse storage for the existing entry e) */ + dup_entry(unblamed, e, &split[0]); + + /* The last part -- me */ + add_blame_entry(unblamed, &split[2]); + + /* ... and the middle part -- parent */ + add_blame_entry(blamed, &split[1]); + } + else if (!split[0].suspect && !split[2].suspect) + /* + * The parent covers the entire area; reuse storage for + * e and replace it with the parent. + */ + dup_entry(blamed, e, &split[1]); + else if (split[0].suspect) { + /* me and then parent */ + dup_entry(unblamed, e, &split[0]); + add_blame_entry(blamed, &split[1]); + } + else { + /* parent and then me */ + dup_entry(blamed, e, &split[1]); + add_blame_entry(unblamed, &split[2]); + } +} + +/* + * After splitting the blame, the origins used by the + * on-stack blame_entry should lose one refcnt each. + */ +static void decref_split(struct blame_entry *split) +{ + int i; + + for (i = 0; i < 3; i++) + blame_origin_decref(split[i].suspect); +} + +/* + * reverse_blame reverses the list given in head, appending tail. + * That allows us to build lists in reverse order, then reverse them + * afterwards. This can be faster than building the list in proper + * order right away. The reason is that building in proper order + * requires writing a link in the _previous_ element, while building + * in reverse order just requires placing the list head into the + * _current_ element. + */ + +static struct blame_entry *reverse_blame(struct blame_entry *head, + struct blame_entry *tail) +{ + while (head) { + struct blame_entry *next = head->next; + head->next = tail; + tail = head; + head = next; + } + return tail; +} + +/* + * Process one hunk from the patch between the current suspect for + * blame_entry e and its parent. This first blames any unfinished + * entries before the chunk (which is where target and parent start + * differing) on the parent, and then splits blame entries at the + * start and at the end of the difference region. Since use of -M and + * -C options may lead to overlapping/duplicate source line number + * ranges, all we can rely on from sorting/merging is the order of the + * first suspect line number. + */ +static void blame_chunk(struct blame_entry ***dstq, struct blame_entry ***srcq, + int tlno, int offset, int same, + struct blame_origin *parent) +{ + struct blame_entry *e = **srcq; + struct blame_entry *samep = NULL, *diffp = NULL; + + while (e && e->s_lno < tlno) { + struct blame_entry *next = e->next; + /* + * current record starts before differing portion. If + * it reaches into it, we need to split it up and + * examine the second part separately. + */ + if (e->s_lno + e->num_lines > tlno) { + /* Move second half to a new record */ + int len = tlno - e->s_lno; + struct blame_entry *n = xcalloc(1, sizeof (struct blame_entry)); + n->suspect = e->suspect; + n->lno = e->lno + len; + n->s_lno = e->s_lno + len; + n->num_lines = e->num_lines - len; + e->num_lines = len; + e->score = 0; + /* Push new record to diffp */ + n->next = diffp; + diffp = n; + } else + blame_origin_decref(e->suspect); + /* Pass blame for everything before the differing + * chunk to the parent */ + e->suspect = blame_origin_incref(parent); + e->s_lno += offset; + e->next = samep; + samep = e; + e = next; + } + /* + * As we don't know how much of a common stretch after this + * diff will occur, the currently blamed parts are all that we + * can assign to the parent for now. + */ + + if (samep) { + **dstq = reverse_blame(samep, **dstq); + *dstq = &samep->next; + } + /* + * Prepend the split off portions: everything after e starts + * after the blameable portion. + */ + e = reverse_blame(diffp, e); + + /* + * Now retain records on the target while parts are different + * from the parent. + */ + samep = NULL; + diffp = NULL; + while (e && e->s_lno < same) { + struct blame_entry *next = e->next; + + /* + * If current record extends into sameness, need to split. + */ + if (e->s_lno + e->num_lines > same) { + /* + * Move second half to a new record to be + * processed by later chunks + */ + int len = same - e->s_lno; + struct blame_entry *n = xcalloc(1, sizeof (struct blame_entry)); + n->suspect = blame_origin_incref(e->suspect); + n->lno = e->lno + len; + n->s_lno = e->s_lno + len; + n->num_lines = e->num_lines - len; + e->num_lines = len; + e->score = 0; + /* Push new record to samep */ + n->next = samep; + samep = n; + } + e->next = diffp; + diffp = e; + e = next; + } + **srcq = reverse_blame(diffp, reverse_blame(samep, e)); + /* Move across elements that are in the unblamable portion */ + if (diffp) + *srcq = &diffp->next; +} + +struct blame_chunk_cb_data { + struct blame_origin *parent; + long offset; + struct blame_entry **dstq; + struct blame_entry **srcq; +}; + +/* diff chunks are from parent to target */ +static int blame_chunk_cb(long start_a, long count_a, + long start_b, long count_b, void *data) +{ + struct blame_chunk_cb_data *d = data; + if (start_a - start_b != d->offset) + die("internal error in blame::blame_chunk_cb"); + blame_chunk(&d->dstq, &d->srcq, start_b, start_a - start_b, + start_b + count_b, d->parent); + d->offset = start_a + count_a - (start_b + count_b); + return 0; +} + +/* + * We are looking at the origin 'target' and aiming to pass blame + * for the lines it is suspected to its parent. Run diff to find + * which lines came from parent and pass blame for them. + */ +static void pass_blame_to_parent(struct blame_scoreboard *sb, + struct blame_origin *target, + struct blame_origin *parent) +{ + mmfile_t file_p, file_o; + struct blame_chunk_cb_data d; + struct blame_entry *newdest = NULL; + + if (!target->suspects) + return; /* nothing remains for this target */ + + d.parent = parent; + d.offset = 0; + d.dstq = &newdest; d.srcq = &target->suspects; + + fill_origin_blob(&sb->revs->diffopt, parent, &file_p, &sb->num_read_blob); + fill_origin_blob(&sb->revs->diffopt, target, &file_o, &sb->num_read_blob); + sb->num_get_patch++; + + if (diff_hunks(&file_p, &file_o, blame_chunk_cb, &d, sb->xdl_opts)) + die("unable to generate diff (%s -> %s)", + oid_to_hex(&parent->commit->object.oid), + oid_to_hex(&target->commit->object.oid)); + /* The rest are the same as the parent */ + blame_chunk(&d.dstq, &d.srcq, INT_MAX, d.offset, INT_MAX, parent); + *d.dstq = NULL; + queue_blames(sb, parent, newdest); + + return; +} + +/* + * The lines in blame_entry after splitting blames many times can become + * very small and trivial, and at some point it becomes pointless to + * blame the parents. E.g. "\t\t}\n\t}\n\n" appears everywhere in any + * ordinary C program, and it is not worth to say it was copied from + * totally unrelated file in the parent. + * + * Compute how trivial the lines in the blame_entry are. + */ +unsigned blame_entry_score(struct blame_scoreboard *sb, struct blame_entry *e) +{ + unsigned score; + const char *cp, *ep; + + if (e->score) + return e->score; + + score = 1; + cp = blame_nth_line(sb, e->lno); + ep = blame_nth_line(sb, e->lno + e->num_lines); + while (cp < ep) { + unsigned ch = *((unsigned char *)cp); + if (isalnum(ch)) + score++; + cp++; + } + e->score = score; + return score; +} + +/* + * best_so_far[] and this[] are both a split of an existing blame_entry + * that passes blame to the parent. Maintain best_so_far the best split + * so far, by comparing this and best_so_far and copying this into + * bst_so_far as needed. + */ +static void copy_split_if_better(struct blame_scoreboard *sb, + struct blame_entry *best_so_far, + struct blame_entry *this) +{ + int i; + + if (!this[1].suspect) + return; + if (best_so_far[1].suspect) { + if (blame_entry_score(sb, &this[1]) < blame_entry_score(sb, &best_so_far[1])) + return; + } + + for (i = 0; i < 3; i++) + blame_origin_incref(this[i].suspect); + decref_split(best_so_far); + memcpy(best_so_far, this, sizeof(struct blame_entry [3])); +} + +/* + * We are looking at a part of the final image represented by + * ent (tlno and same are offset by ent->s_lno). + * tlno is where we are looking at in the final image. + * up to (but not including) same match preimage. + * plno is where we are looking at in the preimage. + * + * <-------------- final image ----------------------> + * <------ent------> + * ^tlno ^same + * <---------preimage-----> + * ^plno + * + * All line numbers are 0-based. + */ +static void handle_split(struct blame_scoreboard *sb, + struct blame_entry *ent, + int tlno, int plno, int same, + struct blame_origin *parent, + struct blame_entry *split) +{ + if (ent->num_lines <= tlno) + return; + if (tlno < same) { + struct blame_entry this[3]; + tlno += ent->s_lno; + same += ent->s_lno; + split_overlap(this, ent, tlno, plno, same, parent); + copy_split_if_better(sb, split, this); + decref_split(this); + } +} + +struct handle_split_cb_data { + struct blame_scoreboard *sb; + struct blame_entry *ent; + struct blame_origin *parent; + struct blame_entry *split; + long plno; + long tlno; +}; + +static int handle_split_cb(long start_a, long count_a, + long start_b, long count_b, void *data) +{ + struct handle_split_cb_data *d = data; + handle_split(d->sb, d->ent, d->tlno, d->plno, start_b, d->parent, + d->split); + d->plno = start_a + count_a; + d->tlno = start_b + count_b; + return 0; +} + +/* + * Find the lines from parent that are the same as ent so that + * we can pass blames to it. file_p has the blob contents for + * the parent. + */ +static void find_copy_in_blob(struct blame_scoreboard *sb, + struct blame_entry *ent, + struct blame_origin *parent, + struct blame_entry *split, + mmfile_t *file_p) +{ + const char *cp; + mmfile_t file_o; + struct handle_split_cb_data d; + + memset(&d, 0, sizeof(d)); + d.sb = sb; d.ent = ent; d.parent = parent; d.split = split; + /* + * Prepare mmfile that contains only the lines in ent. + */ + cp = blame_nth_line(sb, ent->lno); + file_o.ptr = (char *) cp; + file_o.size = blame_nth_line(sb, ent->lno + ent->num_lines) - cp; + + /* + * file_o is a part of final image we are annotating. + * file_p partially may match that image. + */ + memset(split, 0, sizeof(struct blame_entry [3])); + if (diff_hunks(file_p, &file_o, handle_split_cb, &d, sb->xdl_opts)) + die("unable to generate diff (%s)", + oid_to_hex(&parent->commit->object.oid)); + /* remainder, if any, all match the preimage */ + handle_split(sb, ent, d.tlno, d.plno, ent->num_lines, parent, split); +} + +/* Move all blame entries from list *source that have a score smaller + * than score_min to the front of list *small. + * Returns a pointer to the link pointing to the old head of the small list. + */ + +static struct blame_entry **filter_small(struct blame_scoreboard *sb, + struct blame_entry **small, + struct blame_entry **source, + unsigned score_min) +{ + struct blame_entry *p = *source; + struct blame_entry *oldsmall = *small; + while (p) { + if (blame_entry_score(sb, p) <= score_min) { + *small = p; + small = &p->next; + p = *small; + } else { + *source = p; + source = &p->next; + p = *source; + } + } + *small = oldsmall; + *source = NULL; + return small; +} + +/* + * See if lines currently target is suspected for can be attributed to + * parent. + */ +static void find_move_in_parent(struct blame_scoreboard *sb, + struct blame_entry ***blamed, + struct blame_entry **toosmall, + struct blame_origin *target, + struct blame_origin *parent) +{ + struct blame_entry *e, split[3]; + struct blame_entry *unblamed = target->suspects; + struct blame_entry *leftover = NULL; + mmfile_t file_p; + + if (!unblamed) + return; /* nothing remains for this target */ + + fill_origin_blob(&sb->revs->diffopt, parent, &file_p, &sb->num_read_blob); + if (!file_p.ptr) + return; + + /* At each iteration, unblamed has a NULL-terminated list of + * entries that have not yet been tested for blame. leftover + * contains the reversed list of entries that have been tested + * without being assignable to the parent. + */ + do { + struct blame_entry **unblamedtail = &unblamed; + struct blame_entry *next; + for (e = unblamed; e; e = next) { + next = e->next; + find_copy_in_blob(sb, e, parent, split, &file_p); + if (split[1].suspect && + sb->move_score < blame_entry_score(sb, &split[1])) { + split_blame(blamed, &unblamedtail, split, e); + } else { + e->next = leftover; + leftover = e; + } + decref_split(split); + } + *unblamedtail = NULL; + toosmall = filter_small(sb, toosmall, &unblamed, sb->move_score); + } while (unblamed); + target->suspects = reverse_blame(leftover, NULL); +} + +struct blame_list { + struct blame_entry *ent; + struct blame_entry split[3]; +}; + +/* + * Count the number of entries the target is suspected for, + * and prepare a list of entry and the best split. + */ +static struct blame_list *setup_blame_list(struct blame_entry *unblamed, + int *num_ents_p) +{ + struct blame_entry *e; + int num_ents, i; + struct blame_list *blame_list = NULL; + + for (e = unblamed, num_ents = 0; e; e = e->next) + num_ents++; + if (num_ents) { + blame_list = xcalloc(num_ents, sizeof(struct blame_list)); + for (e = unblamed, i = 0; e; e = e->next) + blame_list[i++].ent = e; + } + *num_ents_p = num_ents; + return blame_list; +} + +/* + * For lines target is suspected for, see if we can find code movement + * across file boundary from the parent commit. porigin is the path + * in the parent we already tried. + */ +static void find_copy_in_parent(struct blame_scoreboard *sb, + struct blame_entry ***blamed, + struct blame_entry **toosmall, + struct blame_origin *target, + struct commit *parent, + struct blame_origin *porigin, + int opt) +{ + struct diff_options diff_opts; + int i, j; + struct blame_list *blame_list; + int num_ents; + struct blame_entry *unblamed = target->suspects; + struct blame_entry *leftover = NULL; + + if (!unblamed) + return; /* nothing remains for this target */ + + diff_setup(&diff_opts); + DIFF_OPT_SET(&diff_opts, RECURSIVE); + diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; + + diff_setup_done(&diff_opts); + + /* Try "find copies harder" on new path if requested; + * we do not want to use diffcore_rename() actually to + * match things up; find_copies_harder is set only to - * force diff_tree_sha1() to feed all filepairs to diff_queue, ++ * force diff_tree_oid() to feed all filepairs to diff_queue, + * and this code needs to be after diff_setup_done(), which + * usually makes find-copies-harder imply copy detection. + */ + if ((opt & PICKAXE_BLAME_COPY_HARDEST) + || ((opt & PICKAXE_BLAME_COPY_HARDER) + && (!porigin || strcmp(target->path, porigin->path)))) + DIFF_OPT_SET(&diff_opts, FIND_COPIES_HARDER); + + if (is_null_oid(&target->commit->object.oid)) + do_diff_cache(&parent->tree->object.oid, &diff_opts); + else - diff_tree_sha1(parent->tree->object.oid.hash, - target->commit->tree->object.oid.hash, - "", &diff_opts); ++ diff_tree_oid(&parent->tree->object.oid, ++ &target->commit->tree->object.oid, ++ "", &diff_opts); + + if (!DIFF_OPT_TST(&diff_opts, FIND_COPIES_HARDER)) + diffcore_std(&diff_opts); + + do { + struct blame_entry **unblamedtail = &unblamed; + blame_list = setup_blame_list(unblamed, &num_ents); + + for (i = 0; i < diff_queued_diff.nr; i++) { + struct diff_filepair *p = diff_queued_diff.queue[i]; + struct blame_origin *norigin; + mmfile_t file_p; + struct blame_entry this[3]; + + if (!DIFF_FILE_VALID(p->one)) + continue; /* does not exist in parent */ + if (S_ISGITLINK(p->one->mode)) + continue; /* ignore git links */ + if (porigin && !strcmp(p->one->path, porigin->path)) + /* find_move already dealt with this path */ + continue; + + norigin = get_origin(parent, p->one->path); + oidcpy(&norigin->blob_oid, &p->one->oid); + norigin->mode = p->one->mode; + fill_origin_blob(&sb->revs->diffopt, norigin, &file_p, &sb->num_read_blob); + if (!file_p.ptr) + continue; + + for (j = 0; j < num_ents; j++) { + find_copy_in_blob(sb, blame_list[j].ent, + norigin, this, &file_p); + copy_split_if_better(sb, blame_list[j].split, + this); + decref_split(this); + } + blame_origin_decref(norigin); + } + + for (j = 0; j < num_ents; j++) { + struct blame_entry *split = blame_list[j].split; + if (split[1].suspect && + sb->copy_score < blame_entry_score(sb, &split[1])) { + split_blame(blamed, &unblamedtail, split, + blame_list[j].ent); + } else { + blame_list[j].ent->next = leftover; + leftover = blame_list[j].ent; + } + decref_split(split); + } + free(blame_list); + *unblamedtail = NULL; + toosmall = filter_small(sb, toosmall, &unblamed, sb->copy_score); + } while (unblamed); + target->suspects = reverse_blame(leftover, NULL); + diff_flush(&diff_opts); + clear_pathspec(&diff_opts.pathspec); +} + +/* + * The blobs of origin and porigin exactly match, so everything + * origin is suspected for can be blamed on the parent. + */ +static void pass_whole_blame(struct blame_scoreboard *sb, + struct blame_origin *origin, struct blame_origin *porigin) +{ + struct blame_entry *e, *suspects; + + if (!porigin->file.ptr && origin->file.ptr) { + /* Steal its file */ + porigin->file = origin->file; + origin->file.ptr = NULL; + } + suspects = origin->suspects; + origin->suspects = NULL; + for (e = suspects; e; e = e->next) { + blame_origin_incref(porigin); + blame_origin_decref(e->suspect); + e->suspect = porigin; + } + queue_blames(sb, porigin, suspects); +} + +/* + * We pass blame from the current commit to its parents. We keep saying + * "parent" (and "porigin"), but what we mean is to find scapegoat to + * exonerate ourselves. + */ +static struct commit_list *first_scapegoat(struct rev_info *revs, struct commit *commit, + int reverse) +{ + if (!reverse) { + if (revs->first_parent_only && + commit->parents && + commit->parents->next) { + free_commit_list(commit->parents->next); + commit->parents->next = NULL; + } + return commit->parents; + } + return lookup_decoration(&revs->children, &commit->object); +} + +static int num_scapegoats(struct rev_info *revs, struct commit *commit, int reverse) +{ + struct commit_list *l = first_scapegoat(revs, commit, reverse); + return commit_list_count(l); +} + +/* Distribute collected unsorted blames to the respected sorted lists + * in the various origins. + */ +static void distribute_blame(struct blame_scoreboard *sb, struct blame_entry *blamed) +{ + blamed = llist_mergesort(blamed, get_next_blame, set_next_blame, + compare_blame_suspect); + while (blamed) + { + struct blame_origin *porigin = blamed->suspect; + struct blame_entry *suspects = NULL; + do { + struct blame_entry *next = blamed->next; + blamed->next = suspects; + suspects = blamed; + blamed = next; + } while (blamed && blamed->suspect == porigin); + suspects = reverse_blame(suspects, NULL); + queue_blames(sb, porigin, suspects); + } +} + +#define MAXSG 16 + +static void pass_blame(struct blame_scoreboard *sb, struct blame_origin *origin, int opt) +{ + struct rev_info *revs = sb->revs; + int i, pass, num_sg; + struct commit *commit = origin->commit; + struct commit_list *sg; + struct blame_origin *sg_buf[MAXSG]; + struct blame_origin *porigin, **sg_origin = sg_buf; + struct blame_entry *toosmall = NULL; + struct blame_entry *blames, **blametail = &blames; + + num_sg = num_scapegoats(revs, commit, sb->reverse); + if (!num_sg) + goto finish; + else if (num_sg < ARRAY_SIZE(sg_buf)) + memset(sg_buf, 0, sizeof(sg_buf)); + else + sg_origin = xcalloc(num_sg, sizeof(*sg_origin)); + + /* + * The first pass looks for unrenamed path to optimize for + * common cases, then we look for renames in the second pass. + */ + for (pass = 0; pass < 2 - sb->no_whole_file_rename; pass++) { + struct blame_origin *(*find)(struct commit *, struct blame_origin *); + find = pass ? find_rename : find_origin; + + for (i = 0, sg = first_scapegoat(revs, commit, sb->reverse); + i < num_sg && sg; + sg = sg->next, i++) { + struct commit *p = sg->item; + int j, same; + + if (sg_origin[i]) + continue; + if (parse_commit(p)) + continue; + porigin = find(p, origin); + if (!porigin) + continue; + if (!oidcmp(&porigin->blob_oid, &origin->blob_oid)) { + pass_whole_blame(sb, origin, porigin); + blame_origin_decref(porigin); + goto finish; + } + for (j = same = 0; j < i; j++) + if (sg_origin[j] && + !oidcmp(&sg_origin[j]->blob_oid, &porigin->blob_oid)) { + same = 1; + break; + } + if (!same) + sg_origin[i] = porigin; + else + blame_origin_decref(porigin); + } + } + + sb->num_commits++; + for (i = 0, sg = first_scapegoat(revs, commit, sb->reverse); + i < num_sg && sg; + sg = sg->next, i++) { + struct blame_origin *porigin = sg_origin[i]; + if (!porigin) + continue; + if (!origin->previous) { + blame_origin_incref(porigin); + origin->previous = porigin; + } + pass_blame_to_parent(sb, origin, porigin); + if (!origin->suspects) + goto finish; + } + + /* + * Optionally find moves in parents' files. + */ + if (opt & PICKAXE_BLAME_MOVE) { + filter_small(sb, &toosmall, &origin->suspects, sb->move_score); + if (origin->suspects) { + for (i = 0, sg = first_scapegoat(revs, commit, sb->reverse); + i < num_sg && sg; + sg = sg->next, i++) { + struct blame_origin *porigin = sg_origin[i]; + if (!porigin) + continue; + find_move_in_parent(sb, &blametail, &toosmall, origin, porigin); + if (!origin->suspects) + break; + } + } + } + + /* + * Optionally find copies from parents' files. + */ + if (opt & PICKAXE_BLAME_COPY) { + if (sb->copy_score > sb->move_score) + filter_small(sb, &toosmall, &origin->suspects, sb->copy_score); + else if (sb->copy_score < sb->move_score) { + origin->suspects = blame_merge(origin->suspects, toosmall); + toosmall = NULL; + filter_small(sb, &toosmall, &origin->suspects, sb->copy_score); + } + if (!origin->suspects) + goto finish; + + for (i = 0, sg = first_scapegoat(revs, commit, sb->reverse); + i < num_sg && sg; + sg = sg->next, i++) { + struct blame_origin *porigin = sg_origin[i]; + find_copy_in_parent(sb, &blametail, &toosmall, + origin, sg->item, porigin, opt); + if (!origin->suspects) + goto finish; + } + } + +finish: + *blametail = NULL; + distribute_blame(sb, blames); + /* + * prepend toosmall to origin->suspects + * + * There is no point in sorting: this ends up on a big + * unsorted list in the caller anyway. + */ + if (toosmall) { + struct blame_entry **tail = &toosmall; + while (*tail) + tail = &(*tail)->next; + *tail = origin->suspects; + origin->suspects = toosmall; + } + for (i = 0; i < num_sg; i++) { + if (sg_origin[i]) { + drop_origin_blob(sg_origin[i]); + blame_origin_decref(sg_origin[i]); + } + } + drop_origin_blob(origin); + if (sg_buf != sg_origin) + free(sg_origin); +} + +/* + * The main loop -- while we have blobs with lines whose true origin + * is still unknown, pick one blob, and allow its lines to pass blames + * to its parents. */ +void assign_blame(struct blame_scoreboard *sb, int opt) +{ + struct rev_info *revs = sb->revs; + struct commit *commit = prio_queue_get(&sb->commits); + + while (commit) { + struct blame_entry *ent; + struct blame_origin *suspect = commit->util; + + /* find one suspect to break down */ + while (suspect && !suspect->suspects) + suspect = suspect->next; + + if (!suspect) { + commit = prio_queue_get(&sb->commits); + continue; + } + + assert(commit == suspect->commit); + + /* + * We will use this suspect later in the loop, + * so hold onto it in the meantime. + */ + blame_origin_incref(suspect); + parse_commit(commit); + if (sb->reverse || + (!(commit->object.flags & UNINTERESTING) && + !(revs->max_age != -1 && commit->date < revs->max_age))) + pass_blame(sb, suspect, opt); + else { + commit->object.flags |= UNINTERESTING; + if (commit->object.parsed) + mark_parents_uninteresting(commit); + } + /* treat root commit as boundary */ + if (!commit->parents && !sb->show_root) + commit->object.flags |= UNINTERESTING; + + /* Take responsibility for the remaining entries */ + ent = suspect->suspects; + if (ent) { + suspect->guilty = 1; + for (;;) { + struct blame_entry *next = ent->next; + if (sb->found_guilty_entry) + sb->found_guilty_entry(ent, sb->found_guilty_entry_data); + if (next) { + ent = next; + continue; + } + ent->next = sb->ent; + sb->ent = suspect->suspects; + suspect->suspects = NULL; + break; + } + } + blame_origin_decref(suspect); + + if (sb->debug) /* sanity */ + sanity_check_refcnt(sb); + } +} + +static const char *get_next_line(const char *start, const char *end) +{ + const char *nl = memchr(start, '\n', end - start); + return nl ? nl + 1 : end; +} + +/* + * To allow quick access to the contents of nth line in the + * final image, prepare an index in the scoreboard. + */ +static int prepare_lines(struct blame_scoreboard *sb) +{ + const char *buf = sb->final_buf; + unsigned long len = sb->final_buf_size; + const char *end = buf + len; + const char *p; + int *lineno; + int num = 0; + + for (p = buf; p < end; p = get_next_line(p, end)) + num++; + + ALLOC_ARRAY(sb->lineno, num + 1); + lineno = sb->lineno; + + for (p = buf; p < end; p = get_next_line(p, end)) + *lineno++ = p - buf; + + *lineno = len; + + sb->num_lines = num; + return sb->num_lines; +} + +static struct commit *find_single_final(struct rev_info *revs, + const char **name_p) +{ + int i; + struct commit *found = NULL; + const char *name = NULL; + + for (i = 0; i < revs->pending.nr; i++) { + struct object *obj = revs->pending.objects[i].item; + if (obj->flags & UNINTERESTING) + continue; + obj = deref_tag(obj, NULL, 0); + if (obj->type != OBJ_COMMIT) + die("Non commit %s?", revs->pending.objects[i].name); + if (found) + die("More than one commit to dig from %s and %s?", + revs->pending.objects[i].name, name); + found = (struct commit *)obj; + name = revs->pending.objects[i].name; + } + if (name_p) + *name_p = name; + return found; +} + +static struct commit *dwim_reverse_initial(struct rev_info *revs, + const char **name_p) +{ + /* + * DWIM "git blame --reverse ONE -- PATH" as + * "git blame --reverse ONE..HEAD -- PATH" but only do so + * when it makes sense. + */ + struct object *obj; + struct commit *head_commit; + struct object_id head_oid; + + if (revs->pending.nr != 1) + return NULL; + + /* Is that sole rev a committish? */ + obj = revs->pending.objects[0].item; + obj = deref_tag(obj, NULL, 0); + if (obj->type != OBJ_COMMIT) + return NULL; + + /* Do we have HEAD? */ + if (!resolve_ref_unsafe("HEAD", RESOLVE_REF_READING, head_oid.hash, NULL)) + return NULL; + head_commit = lookup_commit_reference_gently(&head_oid, 1); + if (!head_commit) + return NULL; + + /* Turn "ONE" into "ONE..HEAD" then */ + obj->flags |= UNINTERESTING; + add_pending_object(revs, &head_commit->object, "HEAD"); + + if (name_p) + *name_p = revs->pending.objects[0].name; + return (struct commit *)obj; +} + +static struct commit *find_single_initial(struct rev_info *revs, + const char **name_p) +{ + int i; + struct commit *found = NULL; + const char *name = NULL; + + /* + * There must be one and only one negative commit, and it must be + * the boundary. + */ + for (i = 0; i < revs->pending.nr; i++) { + struct object *obj = revs->pending.objects[i].item; + if (!(obj->flags & UNINTERESTING)) + continue; + obj = deref_tag(obj, NULL, 0); + if (obj->type != OBJ_COMMIT) + die("Non commit %s?", revs->pending.objects[i].name); + if (found) + die("More than one commit to dig up from, %s and %s?", + revs->pending.objects[i].name, name); + found = (struct commit *) obj; + name = revs->pending.objects[i].name; + } + + if (!name) + found = dwim_reverse_initial(revs, &name); + if (!name) + die("No commit to dig up from?"); + + if (name_p) + *name_p = name; + return found; +} + +void init_scoreboard(struct blame_scoreboard *sb) +{ + memset(sb, 0, sizeof(struct blame_scoreboard)); + sb->move_score = BLAME_DEFAULT_MOVE_SCORE; + sb->copy_score = BLAME_DEFAULT_COPY_SCORE; +} + +void setup_scoreboard(struct blame_scoreboard *sb, const char *path, struct blame_origin **orig) +{ + const char *final_commit_name = NULL; + struct blame_origin *o; + struct commit *final_commit = NULL; + enum object_type type; + + if (sb->reverse && sb->contents_from) + die(_("--contents and --reverse do not blend well.")); + + if (!sb->reverse) { + sb->final = find_single_final(sb->revs, &final_commit_name); + sb->commits.compare = compare_commits_by_commit_date; + } else { + sb->final = find_single_initial(sb->revs, &final_commit_name); + sb->commits.compare = compare_commits_by_reverse_commit_date; + } + + if (sb->final && sb->contents_from) + die(_("cannot use --contents with final commit object name")); + + if (sb->reverse && sb->revs->first_parent_only) + sb->revs->children.name = NULL; + + if (!sb->final) { + /* + * "--not A B -- path" without anything positive; + * do not default to HEAD, but use the working tree + * or "--contents". + */ + setup_work_tree(); + sb->final = fake_working_tree_commit(&sb->revs->diffopt, + path, sb->contents_from); + add_pending_object(sb->revs, &(sb->final->object), ":"); + } + + if (sb->reverse && sb->revs->first_parent_only) { + final_commit = find_single_final(sb->revs, NULL); + if (!final_commit) + die(_("--reverse and --first-parent together require specified latest commit")); + } + + /* + * If we have bottom, this will mark the ancestors of the + * bottom commits we would reach while traversing as + * uninteresting. + */ + if (prepare_revision_walk(sb->revs)) + die(_("revision walk setup failed")); + + if (sb->reverse && sb->revs->first_parent_only) { + struct commit *c = final_commit; + + sb->revs->children.name = "children"; + while (c->parents && + oidcmp(&c->object.oid, &sb->final->object.oid)) { + struct commit_list *l = xcalloc(1, sizeof(*l)); + + l->item = c; + if (add_decoration(&sb->revs->children, + &c->parents->item->object, l)) + die("BUG: not unique item in first-parent chain"); + c = c->parents->item; + } + + if (oidcmp(&c->object.oid, &sb->final->object.oid)) + die(_("--reverse --first-parent together require range along first-parent chain")); + } + + if (is_null_oid(&sb->final->object.oid)) { + o = sb->final->util; + sb->final_buf = xmemdupz(o->file.ptr, o->file.size); + sb->final_buf_size = o->file.size; + } + else { + o = get_origin(sb->final, path); + if (fill_blob_sha1_and_mode(o)) + die(_("no such path %s in %s"), path, final_commit_name); + + if (DIFF_OPT_TST(&sb->revs->diffopt, ALLOW_TEXTCONV) && + textconv_object(path, o->mode, &o->blob_oid, 1, (char **) &sb->final_buf, + &sb->final_buf_size)) + ; + else + sb->final_buf = read_sha1_file(o->blob_oid.hash, &type, + &sb->final_buf_size); + + if (!sb->final_buf) + die(_("cannot read blob %s for path %s"), + oid_to_hex(&o->blob_oid), + path); + } + sb->num_read_blob++; + prepare_lines(sb); + + if (orig) + *orig = o; +} + + + +struct blame_entry *blame_entry_prepend(struct blame_entry *head, + long start, long end, + struct blame_origin *o) +{ + struct blame_entry *new_head = xcalloc(1, sizeof(struct blame_entry)); + new_head->lno = start; + new_head->num_lines = end - start; + new_head->suspect = o; + new_head->s_lno = start; + new_head->next = head; + blame_origin_incref(o); + return new_head; +} diff --combined builtin/am.c index 8881d73615,d9fdddac4a..3985f9a89f --- a/builtin/am.c +++ b/builtin/am.c @@@ -563,7 -563,7 +563,7 @@@ static int copy_notes_for_rebase(const goto finish; } - if (copy_note_for_rewrite(c, from_obj.hash, to_obj.hash)) + if (copy_note_for_rewrite(c, &from_obj, &to_obj)) ret = error(_("Failed to copy notes from '%s' to '%s'"), oid_to_hex(&from_obj), oid_to_hex(&to_obj)); } @@@ -1275,8 -1275,12 +1275,8 @@@ static int parse_mail(struct am_state * die("BUG: invalid value for state->scissors"); } - mi.input = fopen(mail, "r"); - if (!mi.input) - die("could not open input"); - mi.output = fopen(am_path(state, "info"), "w"); - if (!mi.output) - die("could not open output 'info'"); + mi.input = xfopen(mail, "r"); + mi.output = xfopen(am_path(state, "info"), "w"); if (mailinfo(&mi, am_path(state, "msg"), am_path(state, "patch"))) die("could not parse patch"); @@@ -2307,9 -2311,6 +2307,9 @@@ int cmd_am(int argc, const char **argv OPT_END() }; + if (argc == 2 && !strcmp(argv[1], "-h")) + usage_with_options(usage, options); + git_config(git_am_config, NULL); am_state_init(&state); diff --combined builtin/commit.c index ef52457eff,7587810045..e3c9e190b0 --- a/builtin/commit.c +++ b/builtin/commit.c @@@ -1699,7 -1699,10 +1699,7 @@@ int cmd_commit(int argc, const char **a if (!reflog_msg) reflog_msg = "commit (merge)"; pptr = commit_list_append(current_head, pptr); - fp = fopen(git_path_merge_head(), "r"); - if (fp == NULL) - die_errno(_("could not open '%s' for reading"), - git_path_merge_head()); + fp = xfopen(git_path_merge_head(), "r"); while (strbuf_getline_lf(&m, fp) != EOF) { struct commit *parent; @@@ -1806,7 -1809,7 +1806,7 @@@ cfg = init_copy_notes_for_rewrite("amend"); if (cfg) { /* we are amending, so current_head is not NULL */ - copy_note_for_rewrite(cfg, current_head->object.oid.hash, oid.hash); + copy_note_for_rewrite(cfg, ¤t_head->object.oid, &oid); finish_copy_notes_for_rewrite(cfg, "Notes added by 'git commit --amend'"); } run_rewrite_hook(¤t_head->object.oid, &oid); diff --combined builtin/diff-tree.c index 492245f428,8b26a66a95..1fd06eac4b --- a/builtin/diff-tree.c +++ b/builtin/diff-tree.c @@@ -7,7 -7,7 +7,7 @@@ static struct rev_info log_tree_opt; - static int diff_tree_commit_sha1(const struct object_id *oid) + static int diff_tree_commit_oid(const struct object_id *oid) { struct commit *commit = lookup_commit_reference(oid); if (!commit) @@@ -49,8 -49,8 +49,8 @@@ static int stdin_diff_trees(struct tre return -1; printf("%s %s\n", oid_to_hex(&tree1->object.oid), oid_to_hex(&tree2->object.oid)); - diff_tree_sha1(tree1->object.oid.hash, tree2->object.oid.hash, - "", &log_tree_opt.diffopt); + diff_tree_oid(&tree1->object.oid, &tree2->object.oid, + "", &log_tree_opt.diffopt); log_tree_diff_flush(&log_tree_opt); return 0; } @@@ -98,16 -98,15 +98,15 @@@ static void diff_tree_tweak_rev(struct int cmd_diff_tree(int argc, const char **argv, const char *prefix) { - int nr_sha1; char line[1000]; struct object *tree1, *tree2; static struct rev_info *opt = &log_tree_opt; struct setup_revision_opt s_r_opt; int read_stdin = 0; + git_config(git_diff_basic_config, NULL); /* no "diff" UI options */ init_revisions(opt, prefix); gitmodules_config(); - git_config(git_diff_basic_config, NULL); /* no "diff" UI options */ opt->abbrev = 0; opt->diff = 1; opt->disable_stdin = 1; @@@ -128,21 -127,18 +127,20 @@@ } /* - * NOTE! We expect "a ^b" to be equal to "a..b", so we - * reverse the order of the objects if the second one - * is marked UNINTERESTING. + * NOTE! We expect "a..b" to expand to "^a b" but it is + * perfectly valid for revision range parser to yield "b ^a", + * which means the same thing. If we get the latter, i.e. the + * second one is marked UNINTERESTING, we recover the original + * order the user gave, i.e. "a..b", by swapping the trees. */ - nr_sha1 = opt->pending.nr; - switch (nr_sha1) { + switch (opt->pending.nr) { case 0: if (!read_stdin) usage(diff_tree_usage); break; case 1: tree1 = opt->pending.objects[0].item; - diff_tree_commit_sha1(&tree1->oid); + diff_tree_commit_oid(&tree1->oid); break; case 2: tree1 = opt->pending.objects[0].item; @@@ -150,9 -146,7 +148,7 @@@ if (tree2->flags & UNINTERESTING) { SWAP(tree2, tree1); } - diff_tree_sha1(tree1->oid.hash, - tree2->oid.hash, - "", &opt->diffopt); + diff_tree_oid(&tree1->oid, &tree2->oid, "", &opt->diffopt); log_tree_diff_flush(opt); break; } diff --combined builtin/diff.c index 0c8f86e40d,4c6a1a962f..d9152c21bf --- a/builtin/diff.c +++ b/builtin/diff.c @@@ -20,22 -20,23 +20,22 @@@ #define DIFF_NO_INDEX_EXPLICIT 1 #define DIFF_NO_INDEX_IMPLICIT 2 -struct blobinfo { - struct object_id oid; - const char *name; - unsigned mode; -}; - static const char builtin_diff_usage[] = "git diff [] [ []] [--] [...]"; +static const char *blob_path(struct object_array_entry *entry) +{ + return entry->path ? entry->path : entry->name; +} + static void stuff_change(struct diff_options *opt, unsigned old_mode, unsigned new_mode, const struct object_id *old_oid, const struct object_id *new_oid, int old_oid_valid, int new_oid_valid, - const char *old_name, - const char *new_name) + const char *old_path, + const char *new_path) { struct diff_filespec *one, *two; @@@ -46,25 -47,25 +46,25 @@@ if (DIFF_OPT_TST(opt, REVERSE_DIFF)) { SWAP(old_mode, new_mode); SWAP(old_oid, new_oid); - SWAP(old_name, new_name); + SWAP(old_path, new_path); } if (opt->prefix && - (strncmp(old_name, opt->prefix, opt->prefix_length) || - strncmp(new_name, opt->prefix, opt->prefix_length))) + (strncmp(old_path, opt->prefix, opt->prefix_length) || + strncmp(new_path, opt->prefix, opt->prefix_length))) return; - one = alloc_filespec(old_name); - two = alloc_filespec(new_name); + one = alloc_filespec(old_path); + two = alloc_filespec(new_path); - fill_filespec(one, old_oid->hash, old_oid_valid, old_mode); - fill_filespec(two, new_oid->hash, new_oid_valid, new_mode); + fill_filespec(one, old_oid, old_oid_valid, old_mode); + fill_filespec(two, new_oid, new_oid_valid, new_mode); diff_queue(&diff_queued_diff, one, two); } static int builtin_diff_b_f(struct rev_info *revs, int argc, const char **argv, - struct blobinfo *blob) + struct object_array_entry **blob) { /* Blob vs file in the working tree*/ struct stat st; @@@ -83,15 -84,14 +83,15 @@@ diff_set_mnemonic_prefix(&revs->diffopt, "o/", "w/"); - if (blob[0].mode == S_IFINVALID) - blob[0].mode = canon_mode(st.st_mode); + if (blob[0]->mode == S_IFINVALID) + blob[0]->mode = canon_mode(st.st_mode); stuff_change(&revs->diffopt, - blob[0].mode, canon_mode(st.st_mode), - &blob[0].oid, &null_oid, + blob[0]->mode, canon_mode(st.st_mode), + &blob[0]->item->oid, &null_oid, 1, 0, - path, path); + blob[0]->path ? blob[0]->path : path, + path); diffcore_std(&revs->diffopt); diff_flush(&revs->diffopt); return 0; @@@ -99,24 -99,24 +99,24 @@@ static int builtin_diff_blobs(struct rev_info *revs, int argc, const char **argv, - struct blobinfo *blob) + struct object_array_entry **blob) { unsigned mode = canon_mode(S_IFREG | 0644); if (argc > 1) usage(builtin_diff_usage); - if (blob[0].mode == S_IFINVALID) - blob[0].mode = mode; + if (blob[0]->mode == S_IFINVALID) + blob[0]->mode = mode; - if (blob[1].mode == S_IFINVALID) - blob[1].mode = mode; + if (blob[1]->mode == S_IFINVALID) + blob[1]->mode = mode; stuff_change(&revs->diffopt, - blob[0].mode, blob[1].mode, - &blob[0].oid, &blob[1].oid, + blob[0]->mode, blob[1]->mode, + &blob[0]->item->oid, &blob[1]->item->oid, 1, 1, - blob[0].name, blob[1].name); + blob_path(blob[0]), blob_path(blob[1])); diffcore_std(&revs->diffopt); diff_flush(&revs->diffopt); return 0; @@@ -174,7 -174,7 +174,7 @@@ static int builtin_diff_tree(struct rev swap = 1; oid[swap] = &ent0->item->oid; oid[1 - swap] = &ent1->item->oid; - diff_tree_sha1(oid[0]->hash, oid[1]->hash, "", &revs->diffopt); + diff_tree_oid(oid[0], oid[1], "", &revs->diffopt); log_tree_diff_flush(revs); return 0; } @@@ -194,7 -194,7 +194,7 @@@ static int builtin_diff_combined(struc revs->dense_combined_merges = revs->combine_merges = 1; for (i = 1; i < ents; i++) oid_array_append(&parents, &ent[i].item->oid); - diff_tree_combined(ent[0].item->oid.hash, &parents, + diff_tree_combined(&ent[0].item->oid, &parents, revs->dense_combined_merges, revs); oid_array_clear(&parents); return 0; @@@ -259,7 -259,7 +259,7 @@@ int cmd_diff(int argc, const char **arg struct rev_info rev; struct object_array ent = OBJECT_ARRAY_INIT; int blobs = 0, paths = 0; - struct blobinfo blob[2]; + struct object_array_entry *blob[2]; int nongit = 0, no_index = 0; int result = 0; @@@ -408,7 -408,9 +408,7 @@@ } else if (obj->type == OBJ_BLOB) { if (2 <= blobs) die(_("more than two blobs given: '%s'"), name); - oidcpy(&blob[blobs].oid, &obj->oid); - blob[blobs].name = name; - blob[blobs].mode = entry->mode; + blob[blobs] = entry; blobs++; } else { diff --combined builtin/fast-export.c index 2dfed87454,d57f36c438..a932be04f4 --- a/builtin/fast-export.c +++ b/builtin/fast-export.c @@@ -562,12 -562,12 +562,12 @@@ static void handle_commit(struct commi get_object_mark(&commit->parents->item->object) != 0 && !full_tree) { parse_commit_or_die(commit->parents->item); - diff_tree_sha1(commit->parents->item->tree->object.oid.hash, - commit->tree->object.oid.hash, "", &rev->diffopt); + diff_tree_oid(&commit->parents->item->tree->object.oid, + &commit->tree->object.oid, "", &rev->diffopt); } else - diff_root_tree_sha1(commit->tree->object.oid.hash, - "", &rev->diffopt); + diff_root_tree_oid(&commit->tree->object.oid, + "", &rev->diffopt); /* Export the referenced blobs, and remember the marks. */ for (i = 0; i < diff_queued_diff.nr; i++) @@@ -907,7 -907,9 +907,7 @@@ static void export_marks(char *file static void import_marks(char *input_file) { char line[512]; - FILE *f = fopen(input_file, "r"); - if (!f) - die_errno("cannot read '%s'", input_file); + FILE *f = xfopen(input_file, "r"); while (fgets(line, sizeof(line), f)) { uint32_t mark; diff --combined builtin/grep.c index 26d43b4e4c,623c13a939..3e4b9600e8 --- a/builtin/grep.c +++ b/builtin/grep.c @@@ -73,14 -73,14 +73,14 @@@ static pthread_mutex_t grep_mutex static inline void grep_lock(void) { - if (num_threads) - pthread_mutex_lock(&grep_mutex); + assert(num_threads); + pthread_mutex_lock(&grep_mutex); } static inline void grep_unlock(void) { - if (num_threads) - pthread_mutex_unlock(&grep_mutex); + assert(num_threads); + pthread_mutex_unlock(&grep_mutex); } /* Signalled when a new work_item is added to todo. */ @@@ -224,8 -224,7 +224,8 @@@ static void start_threads(struct grep_o int err; struct grep_opt *o = grep_opt_dup(opt); o->output = strbuf_out; - o->debug = 0; + if (i) + o->debug = 0; compile_grep_patterns(o); err = pthread_create(&threads[i], NULL, run, o); @@@ -290,22 -289,8 +290,22 @@@ static int grep_cmd_config(const char * if (num_threads < 0) die(_("invalid number of threads specified (%d) for %s"), num_threads, var); +#ifdef NO_PTHREADS + else if (num_threads && num_threads != 1) { + /* + * TRANSLATORS: %s is the configuration + * variable for tweaking threads, currently + * grep.threads + */ + warning(_("no threads support, ignoring %s"), var); + num_threads = 0; + } +#endif } + if (!strcmp(var, "submodule.recurse")) + recurse_submodules = git_config_bool(var, value); + return st; } @@@ -342,7 -327,7 +342,7 @@@ static int grep_oid(struct grep_opt *op #ifndef NO_PTHREADS if (num_threads) { - add_work(opt, GREP_SOURCE_SHA1, pathbuf.buf, path, oid); + add_work(opt, GREP_SOURCE_OID, pathbuf.buf, path, oid); strbuf_release(&pathbuf); return 0; } else @@@ -351,7 -336,7 +351,7 @@@ struct grep_source gs; int hit; - grep_source_init(&gs, GREP_SOURCE_SHA1, pathbuf.buf, path, oid); + grep_source_init(&gs, GREP_SOURCE_OID, pathbuf.buf, path, oid); strbuf_release(&pathbuf); hit = grep_source(opt, &gs); @@@ -510,8 -495,6 +510,8 @@@ static void compile_submodule_options(c break; case GREP_PATTERN_TYPE_UNSPECIFIED: break; + default: + die("BUG: Added a new grep pattern type without updating switch statement"); } for (pattern = opt->pattern_list; pattern != NULL; @@@ -587,7 -570,7 +587,7 @@@ static int grep_submodule_launch(struc * with the object's name: 'tree-name:filename'. In order to * provide uniformity of output we want to pass the name of the * parent project's object name to the submodule so the submodule can - * prefix its output with the parent's name and not its own SHA1. + * prefix its output with the parent's name and not its own OID. */ if (gs->identifier && end_of_base) argv_array_pushf(&cp.args, "--parent-basename=%.*s", @@@ -600,12 -583,12 +600,12 @@@ * If there is a tree identifier for the submodule, add the * rev after adding the submodule options but before the * pathspecs. To do this we listen for the '--' and insert the - * sha1 before pushing the '--' onto the child process argv + * oid before pushing the '--' onto the child process argv * array. */ if (gs->identifier && !strcmp("--", submodule_options.argv[i])) { - argv_array_push(&cp.args, sha1_to_hex(gs->identifier)); + argv_array_push(&cp.args, oid_to_hex(gs->identifier)); } argv_array_push(&cp.args, submodule_options.argv[i]); @@@ -635,11 -618,11 +635,11 @@@ /* * Prep grep structures for a submodule grep - * sha1: the sha1 of the submodule or NULL if using the working tree + * oid: the oid of the submodule or NULL if using the working tree * filename: name of the submodule including tree name of parent * path: location of the submodule */ - static int grep_submodule(struct grep_opt *opt, const unsigned char *sha1, + static int grep_submodule(struct grep_opt *opt, const struct object_id *oid, const char *filename, const char *path) { if (!is_submodule_initialized(path)) @@@ -649,7 -632,7 +649,7 @@@ * If searching history, check for the presense of the * submodule's gitdir before skipping the submodule. */ - if (sha1) { + if (oid) { const struct submodule *sub = submodule_from_path(null_sha1, path); if (sub) @@@ -664,7 -647,7 +664,7 @@@ #ifndef NO_PTHREADS if (num_threads) { - add_work(opt, GREP_SOURCE_SUBMODULE, filename, path, sha1); + add_work(opt, GREP_SOURCE_SUBMODULE, filename, path, oid); return 0; } else #endif @@@ -673,7 -656,7 +673,7 @@@ int hit; grep_source_init(&gs, GREP_SOURCE_SUBMODULE, - filename, path, sha1); + filename, path, oid); hit = grep_submodule_launch(opt, &gs); grep_source_clear(&gs); @@@ -792,7 -775,7 +792,7 @@@ static int grep_tree(struct grep_opt *o check_attr); free(data); } else if (recurse_submodules && S_ISGITLINK(entry.mode)) { - hit |= grep_submodule(opt, entry.oid->hash, base->buf, + hit |= grep_submodule(opt, entry.oid, base->buf, base->buf + tn_len); } @@@ -1171,6 -1154,8 +1171,6 @@@ int cmd_grep(int argc, const char **arg if (!opt.fixed && opt.ignore_case) opt.regflags |= REG_ICASE; - compile_grep_patterns(&opt); - /* * We have to find "--" in a separate pass, because its presence * influences how we will parse arguments that come before it. @@@ -1205,8 -1190,7 +1205,8 @@@ break; } - if (get_sha1_with_context(arg, 0, oid.hash, &oc)) { + if (get_sha1_with_context(arg, GET_SHA1_RECORD_PATH, + oid.hash, &oc)) { if (seen_dashdash) die(_("unable to resolve revision: %s"), arg); break; @@@ -1216,7 -1200,6 +1216,7 @@@ if (!seen_dashdash) verify_non_filename(prefix, arg); add_object_array_with_path(object, arg, &list, oc.mode, oc.path); + free(oc.path); } /* @@@ -1243,23 -1226,10 +1243,23 @@@ num_threads = GREP_NUM_THREADS_DEFAULT; else if (num_threads < 0) die(_("invalid number of threads specified (%d)"), num_threads); + if (num_threads == 1) + num_threads = 0; #else + if (num_threads) + warning(_("no threads support, ignoring --threads")); num_threads = 0; #endif + if (!num_threads) + /* + * The compiled patterns on the main path are only + * used when not using threading. Otherwise + * start_threads() below calls compile_grep_patterns() + * for each thread. + */ + compile_grep_patterns(&opt); + #ifndef NO_PTHREADS if (num_threads) { if (!(opt.name_only || opt.unmatch_name_only || opt.count) diff --combined builtin/log.c index a33c1a70ab,4ef522ee50..998437b23d --- a/builtin/log.c +++ b/builtin/log.c @@@ -483,20 -483,16 +483,20 @@@ static int show_blob_object(const struc !DIFF_OPT_TST(&rev->diffopt, ALLOW_TEXTCONV)) return stream_blob_to_fd(1, oid, NULL, 0); - if (get_sha1_with_context(obj_name, 0, oidc.hash, &obj_context)) + if (get_sha1_with_context(obj_name, GET_SHA1_RECORD_PATH, + oidc.hash, &obj_context)) die(_("Not a valid object name %s"), obj_name); - if (!obj_context.path[0] || - !textconv_object(obj_context.path, obj_context.mode, &oidc, 1, &buf, &size)) + if (!obj_context.path || + !textconv_object(obj_context.path, obj_context.mode, &oidc, 1, &buf, &size)) { + free(obj_context.path); return stream_blob_to_fd(1, oid, NULL, 0); + } if (!buf) die(_("git show %s: bad file"), obj_name); write_or_die(1, buf, size); + free(obj_context.path); return 0; } @@@ -846,10 -842,8 +846,10 @@@ static int open_next_file(struct commi if (output_directory) { strbuf_addstr(&filename, output_directory); if (filename.len >= - PATH_MAX - FORMAT_PATCH_NAME_MAX - suffix_len) + PATH_MAX - FORMAT_PATCH_NAME_MAX - suffix_len) { + strbuf_release(&filename); return error(_("name of output directory is too long")); + } strbuf_complete(&filename, '/'); } @@@ -863,11 -857,8 +863,11 @@@ if (!quiet) printf("%s\n", filename.buf + outdir_offset); - if ((rev->diffopt.file = fopen(filename.buf, "w")) == NULL) - return error(_("Cannot open patch file %s"), filename.buf); + if ((rev->diffopt.file = fopen(filename.buf, "w")) == NULL) { + error_errno(_("Cannot open patch file %s"), filename.buf); + strbuf_release(&filename); + return -1; + } strbuf_release(&filename); return 0; @@@ -1052,9 -1043,9 +1052,9 @@@ static void make_cover_letter(struct re diff_setup_done(&opts); - diff_tree_sha1(origin->tree->object.oid.hash, - head->tree->object.oid.hash, - "", &opts); + diff_tree_oid(&origin->tree->object.oid, + &head->tree->object.oid, + "", &opts); diffcore_std(&opts); diff_flush(&opts); @@@ -1363,7 -1354,7 +1363,7 @@@ static void prepare_bases(struct base_t struct object_id *patch_id; if (commit->util) continue; - if (commit_patch_id(commit, &diffopt, oid.hash, 0)) + if (commit_patch_id(commit, &diffopt, &oid, 0)) die(_("cannot get patch id")); ALLOC_GROW(bases->patch_id, bases->nr_patch_id + 1, bases->alloc_patch_id); patch_id = bases->patch_id + bases->nr_patch_id; diff --combined builtin/merge.c index eab03a026d,afaed6a2c2..84970cd85e --- a/builtin/merge.c +++ b/builtin/merge.c @@@ -415,7 -415,7 +415,7 @@@ static void finish(struct commit *head_ DIFF_FORMAT_SUMMARY | DIFF_FORMAT_DIFFSTAT; opts.detect_rename = DIFF_DETECT_RENAME; diff_setup_done(&opts); - diff_tree_sha1(head->hash, new_head->hash, "", &opts); + diff_tree_oid(head, new_head, "", &opts); diffcore_std(&opts); diff_flush(&opts); } @@@ -839,7 -839,9 +839,7 @@@ static int suggest_conflicts(void struct strbuf msgbuf = STRBUF_INIT; filename = git_path_merge_msg(); - fp = fopen(filename, "a"); - if (!fp) - die_errno(_("Could not open '%s' for writing"), filename); + fp = xfopen(filename, "a"); append_conflicts_hint(&msgbuf); fputs(msgbuf.buf, fp); diff --combined builtin/notes.c index 7196bff0eb,2ebc2b7c43..c939a84b76 --- a/builtin/notes.c +++ b/builtin/notes.c @@@ -109,11 -109,11 +109,11 @@@ static void free_note_data(struct note_ strbuf_release(&d->buf); } - static int list_each_note(const unsigned char *object_sha1, - const unsigned char *note_sha1, char *note_path, + static int list_each_note(const struct object_id *object_oid, + const struct object_id *note_oid, char *note_path, void *cb_data) { - printf("%s %s\n", sha1_to_hex(note_sha1), sha1_to_hex(object_sha1)); + printf("%s %s\n", oid_to_hex(note_oid), oid_to_hex(object_oid)); return 0; } @@@ -129,10 -129,10 +129,10 @@@ static void copy_obj_to_fd(int fd, cons } } - static void write_commented_object(int fd, const unsigned char *object) + static void write_commented_object(int fd, const struct object_id *object) { const char *show_args[5] = - {"show", "--stat", "--no-notes", sha1_to_hex(object), NULL}; + {"show", "--stat", "--no-notes", oid_to_hex(object), NULL}; struct child_process show = CHILD_PROCESS_INIT; struct strbuf buf = STRBUF_INIT; struct strbuf cbuf = STRBUF_INIT; @@@ -145,7 -145,7 +145,7 @@@ show.git_cmd = 1; if (start_command(&show)) die(_("unable to start 'show' for object '%s'"), - sha1_to_hex(object)); + oid_to_hex(object)); if (strbuf_read(&buf, show.out, 0) < 0) die_errno(_("could not read 'show' output")); @@@ -157,10 -157,10 +157,10 @@@ if (finish_command(&show)) die(_("failed to finish 'show' for object '%s'"), - sha1_to_hex(object)); + oid_to_hex(object)); } - static void prepare_note_data(const unsigned char *object, struct note_data *d, + static void prepare_note_data(const struct object_id *object, struct note_data *d, const unsigned char *old_note) { if (d->use_editor || !d->given) { @@@ -243,16 -243,16 +243,16 @@@ static int parse_reuse_arg(const struc { struct note_data *d = opt->value; char *buf; - unsigned char object[20]; + struct object_id object; enum object_type type; unsigned long len; if (d->buf.len) strbuf_addch(&d->buf, '\n'); - if (get_sha1(arg, object)) + if (get_oid(arg, &object)) die(_("failed to resolve '%s' as a valid ref."), arg); - if (!(buf = read_sha1_file(object, &type, &len))) { + if (!(buf = read_sha1_file(object.hash, &type, &len))) { free(buf); die(_("failed to read object '%s'."), arg); } @@@ -292,7 -292,7 +292,7 @@@ static int notes_copy_from_stdin(int fo } while (strbuf_getline_lf(&buf, stdin) != EOF) { - unsigned char from_obj[20], to_obj[20]; + struct object_id from_obj, to_obj; struct strbuf **split; int err; @@@ -301,15 -301,15 +301,15 @@@ die(_("malformed input line: '%s'."), buf.buf); strbuf_rtrim(split[0]); strbuf_rtrim(split[1]); - if (get_sha1(split[0]->buf, from_obj)) + if (get_oid(split[0]->buf, &from_obj)) die(_("failed to resolve '%s' as a valid ref."), split[0]->buf); - if (get_sha1(split[1]->buf, to_obj)) + if (get_oid(split[1]->buf, &to_obj)) die(_("failed to resolve '%s' as a valid ref."), split[1]->buf); if (rewrite_cmd) - err = copy_note_for_rewrite(c, from_obj, to_obj); + err = copy_note_for_rewrite(c, &from_obj, &to_obj); else - err = copy_note(t, from_obj, to_obj, force, + err = copy_note(t, &from_obj, &to_obj, force, combine_notes_overwrite); if (err) { @@@ -340,10 -340,8 +340,10 @@@ static struct notes_tree *init_notes_ch ref = (flags & NOTES_INIT_WRITABLE) ? t->update_ref : t->ref; if (!starts_with(ref, "refs/notes/")) - /* TRANSLATORS: the first %s will be replaced by a - git notes command: 'add', 'merge', 'remove', etc.*/ + /* + * TRANSLATORS: the first %s will be replaced by a git + * notes command: 'add', 'merge', 'remove', etc. + */ die(_("refusing to %s notes in %s (outside of refs/notes/)"), subcommand, ref); return t; @@@ -352,8 -350,8 +352,8 @@@ static int list(int argc, const char **argv, const char *prefix) { struct notes_tree *t; - unsigned char object[20]; - const unsigned char *note; + struct object_id object; + const struct object_id *note; int retval = -1; struct option options[] = { OPT_END() @@@ -370,15 -368,15 +370,15 @@@ t = init_notes_check("list", 0); if (argc) { - if (get_sha1(argv[0], object)) + if (get_oid(argv[0], &object)) die(_("failed to resolve '%s' as a valid ref."), argv[0]); - note = get_note(t, object); + note = get_note(t, &object); if (note) { - puts(sha1_to_hex(note)); + puts(oid_to_hex(note)); retval = 0; } else retval = error(_("no note found for object %s."), - sha1_to_hex(object)); + oid_to_hex(&object)); } else retval = for_each_note(t, 0, list_each_note, NULL); @@@ -393,8 -391,8 +393,8 @@@ static int add(int argc, const char **a int force = 0, allow_empty = 0; const char *object_ref; struct notes_tree *t; - unsigned char object[20], new_note[20]; - const unsigned char *note; + struct object_id object, new_note; + const struct object_id *note; struct note_data d = { 0, 0, NULL, STRBUF_INIT }; struct option options[] = { { OPTION_CALLBACK, 'm', "message", &d, N_("message"), @@@ -425,11 -423,11 +425,11 @@@ object_ref = argc > 1 ? argv[1] : "HEAD"; - if (get_sha1(object_ref, object)) + if (get_oid(object_ref, &object)) die(_("failed to resolve '%s' as a valid ref."), object_ref); t = init_notes_check("add", NOTES_INIT_WRITABLE); - note = get_note(t, object); + note = get_note(t, &object); if (note) { if (!force) { @@@ -439,7 -437,7 +439,7 @@@ return error(_("Cannot add notes. " "Found existing notes for object %s. " "Use '-f' to overwrite existing notes"), - sha1_to_hex(object)); + oid_to_hex(&object)); } /* * Redirect to "edit" subcommand. @@@ -452,19 -450,19 +452,19 @@@ return append_edit(argc, argv, prefix); } fprintf(stderr, _("Overwriting existing notes for object %s\n"), - sha1_to_hex(object)); + oid_to_hex(&object)); } - prepare_note_data(object, &d, note); + prepare_note_data(&object, &d, note->hash); if (d.buf.len || allow_empty) { - write_note_data(&d, new_note); - if (add_note(t, object, new_note, combine_notes_overwrite)) + write_note_data(&d, new_note.hash); + if (add_note(t, &object, &new_note, combine_notes_overwrite)) die("BUG: combine_notes_overwrite failed"); commit_notes(t, "Notes added by 'git notes add'"); } else { fprintf(stderr, _("Removing note for object %s\n"), - sha1_to_hex(object)); - remove_note(t, object); + oid_to_hex(&object)); + remove_note(t, object.hash); commit_notes(t, "Notes removed by 'git notes add'"); } @@@ -476,9 -474,9 +476,9 @@@ static int copy(int argc, const char **argv, const char *prefix) { int retval = 0, force = 0, from_stdin = 0; - const unsigned char *from_note, *note; + const struct object_id *from_note, *note; const char *object_ref; - unsigned char object[20], from_obj[20]; + struct object_id object, from_obj; struct notes_tree *t; const char *rewrite_cmd = NULL; struct option options[] = { @@@ -511,37 -509,37 +511,37 @@@ usage_with_options(git_notes_copy_usage, options); } - if (get_sha1(argv[0], from_obj)) + if (get_oid(argv[0], &from_obj)) die(_("failed to resolve '%s' as a valid ref."), argv[0]); object_ref = 1 < argc ? argv[1] : "HEAD"; - if (get_sha1(object_ref, object)) + if (get_oid(object_ref, &object)) die(_("failed to resolve '%s' as a valid ref."), object_ref); t = init_notes_check("copy", NOTES_INIT_WRITABLE); - note = get_note(t, object); + note = get_note(t, &object); if (note) { if (!force) { retval = error(_("Cannot copy notes. Found existing " "notes for object %s. Use '-f' to " "overwrite existing notes"), - sha1_to_hex(object)); + oid_to_hex(&object)); goto out; } fprintf(stderr, _("Overwriting existing notes for object %s\n"), - sha1_to_hex(object)); + oid_to_hex(&object)); } - from_note = get_note(t, from_obj); + from_note = get_note(t, &from_obj); if (!from_note) { retval = error(_("missing notes on source object %s. Cannot " - "copy."), sha1_to_hex(from_obj)); + "copy."), oid_to_hex(&from_obj)); goto out; } - if (add_note(t, object, from_note, combine_notes_overwrite)) + if (add_note(t, &object, from_note, combine_notes_overwrite)) die("BUG: combine_notes_overwrite failed"); commit_notes(t, "Notes added by 'git notes copy'"); out: @@@ -554,8 -552,8 +554,8 @@@ static int append_edit(int argc, const int allow_empty = 0; const char *object_ref; struct notes_tree *t; - unsigned char object[20], new_note[20]; - const unsigned char *note; + struct object_id object, new_note; + const struct object_id *note; char *logmsg; const char * const *usage; struct note_data d = { 0, 0, NULL, STRBUF_INIT }; @@@ -594,19 -592,19 +594,19 @@@ object_ref = 1 < argc ? argv[1] : "HEAD"; - if (get_sha1(object_ref, object)) + if (get_oid(object_ref, &object)) die(_("failed to resolve '%s' as a valid ref."), object_ref); t = init_notes_check(argv[0], NOTES_INIT_WRITABLE); - note = get_note(t, object); + note = get_note(t, &object); - prepare_note_data(object, &d, edit ? note : NULL); + prepare_note_data(&object, &d, edit && note ? note->hash : NULL); if (note && !edit) { /* Append buf to previous note contents */ unsigned long size; enum object_type type; - char *prev_buf = read_sha1_file(note, &type, &size); + char *prev_buf = read_sha1_file(note->hash, &type, &size); strbuf_grow(&d.buf, size + 1); if (d.buf.len && prev_buf && size) @@@ -617,14 -615,14 +617,14 @@@ } if (d.buf.len || allow_empty) { - write_note_data(&d, new_note); - if (add_note(t, object, new_note, combine_notes_overwrite)) + write_note_data(&d, new_note.hash); + if (add_note(t, &object, &new_note, combine_notes_overwrite)) die("BUG: combine_notes_overwrite failed"); logmsg = xstrfmt("Notes added by 'git notes %s'", argv[0]); } else { fprintf(stderr, _("Removing note for object %s\n"), - sha1_to_hex(object)); - remove_note(t, object); + oid_to_hex(&object)); + remove_note(t, object.hash); logmsg = xstrfmt("Notes removed by 'git notes %s'", argv[0]); } commit_notes(t, logmsg); @@@ -639,8 -637,8 +639,8 @@@ static int show(int argc, const char ** { const char *object_ref; struct notes_tree *t; - unsigned char object[20]; - const unsigned char *note; + struct object_id object; + const struct object_id *note; int retval; struct option options[] = { OPT_END() @@@ -656,17 -654,17 +656,17 @@@ object_ref = argc ? argv[0] : "HEAD"; - if (get_sha1(object_ref, object)) + if (get_oid(object_ref, &object)) die(_("failed to resolve '%s' as a valid ref."), object_ref); t = init_notes_check("show", 0); - note = get_note(t, object); + note = get_note(t, &object); if (!note) retval = error(_("no note found for object %s."), - sha1_to_hex(object)); + oid_to_hex(&object)); else { - const char *show_args[3] = {"show", sha1_to_hex(note), NULL}; + const char *show_args[3] = {"show", oid_to_hex(note), NULL}; retval = execv_git_cmd(show_args); } free_notes(t); @@@ -726,7 -724,7 +726,7 @@@ static int merge_commit(struct notes_me if (!o->local_ref) die(_("failed to resolve NOTES_MERGE_REF")); - if (notes_merge_commit(o, t, partial, oid.hash)) + if (notes_merge_commit(o, t, partial, &oid)) die(_("failed to finalize notes merge")); /* Reuse existing commit message in reflog message */ @@@ -762,7 -760,7 +762,7 @@@ static int git_config_get_notes_strateg static int merge(int argc, const char **argv, const char *prefix) { struct strbuf remote_ref = STRBUF_INIT, msg = STRBUF_INIT; - unsigned char result_sha1[20]; + struct object_id result_oid; struct notes_tree *t; struct notes_merge_options o; int do_merge = 0, do_commit = 0, do_abort = 0; @@@ -844,16 -842,16 +844,16 @@@ remote_ref.buf, default_notes_ref()); strbuf_add(&(o.commit_msg), msg.buf + 7, msg.len - 7); /* skip "notes: " */ - result = notes_merge(&o, t, result_sha1); + result = notes_merge(&o, t, &result_oid); - if (result >= 0) /* Merge resulted (trivially) in result_sha1 */ + if (result >= 0) /* Merge resulted (trivially) in result_oid */ /* Update default notes ref with new commit */ - update_ref(msg.buf, default_notes_ref(), result_sha1, NULL, + update_ref(msg.buf, default_notes_ref(), result_oid.hash, NULL, 0, UPDATE_REFS_DIE_ON_ERR); else { /* Merge has unresolved conflicts */ const struct worktree *wt; /* Update .git/NOTES_MERGE_PARTIAL with partial merge result */ - update_ref(msg.buf, "NOTES_MERGE_PARTIAL", result_sha1, NULL, + update_ref(msg.buf, "NOTES_MERGE_PARTIAL", result_oid.hash, NULL, 0, UPDATE_REFS_DIE_ON_ERR); /* Store ref-to-be-updated into .git/NOTES_MERGE_REF */ wt = find_shared_symref("NOTES_MERGE_REF", default_notes_ref()); @@@ -880,10 -878,10 +880,10 @@@ static int remove_one_note(struct notes_tree *t, const char *name, unsigned flag) { int status; - unsigned char sha1[20]; - if (get_sha1(name, sha1)) + struct object_id oid; + if (get_oid(name, &oid)) return error(_("Failed to resolve '%s' as a valid ref."), name); - status = remove_note(t, sha1); + status = remove_note(t, oid.hash); if (status) fprintf(stderr, _("Object %s has no note\n"), name); else diff --combined cache.h index 4d92aae0e8,50fd2b3ccf..d6ba8a2f11 --- a/cache.h +++ b/cache.h @@@ -1026,6 -1026,13 +1026,13 @@@ static inline void oidcpy(struct object hashcpy(dst->hash, src->hash); } + static inline struct object_id *oiddup(const struct object_id *src) + { + struct object_id *dst = xmalloc(sizeof(struct object_id)); + oidcpy(dst, src); + return dst; + } + static inline void hashclr(unsigned char *hash) { memset(hash, 0, GIT_SHA1_RAWSZ); @@@ -1334,18 -1341,13 +1341,18 @@@ static inline int hex2chr(const char *s struct object_context { unsigned char tree[20]; - char path[PATH_MAX]; unsigned mode; /* * symlink_path is only used by get_tree_entry_follow_symlinks, * and only for symlinks that point outside the repository. */ struct strbuf symlink_path; + /* + * If GET_SHA1_RECORD_PATH is set, this will record path (if any) + * found when resolving the name. The caller is responsible for + * releasing the memory. + */ + char *path; }; #define GET_SHA1_QUIETLY 01 @@@ -1355,7 -1357,6 +1362,7 @@@ #define GET_SHA1_TREEISH 020 #define GET_SHA1_BLOB 040 #define GET_SHA1_FOLLOW_SYMLINKS 0100 +#define GET_SHA1_RECORD_PATH 0200 #define GET_SHA1_ONLY_TO_DIE 04000 #define GET_SHA1_DISAMBIGUATORS \ @@@ -1370,7 -1371,7 +1377,7 @@@ extern int get_sha1_tree(const char *st extern int get_sha1_treeish(const char *str, unsigned char *sha1); extern int get_sha1_blob(const char *str, unsigned char *sha1); extern void maybe_die_on_misspelt_object_name(const char *name, const char *prefix); -extern int get_sha1_with_context(const char *str, unsigned flags, unsigned char *sha1, struct object_context *orc); +extern int get_sha1_with_context(const char *str, unsigned flags, unsigned char *sha1, struct object_context *oc); extern int get_oid(const char *str, struct object_id *oid); diff --combined diff-lib.c index 76c8f185cd,9e076a4886..0c0e20f7c0 --- a/diff-lib.c +++ b/diff-lib.c @@@ -29,7 -29,7 +29,7 @@@ static int check_removed(const struct cache_entry *ce, struct stat *st) { if (lstat(ce->name, st) < 0) { - if (errno != ENOENT && errno != ENOTDIR) + if (!is_missing_file_error(errno)) return -1; return 1; } @@@ -101,7 -101,7 +101,7 @@@ int run_diff_files(struct rev_info *rev struct cache_entry *ce = active_cache[i]; int changed; unsigned dirty_submodule = 0; - const unsigned char *old_sha1, *new_sha1; + const struct object_id *old_oid, *new_oid; if (diff_can_quit_early(&revs->diffopt)) break; @@@ -210,14 -210,14 +210,14 @@@ continue; } diff_addremove(&revs->diffopt, '-', ce->ce_mode, - ce->oid.hash, + &ce->oid, !is_null_oid(&ce->oid), ce->name, 0); continue; } else if (revs->diffopt.ita_invisible_in_index && ce_intent_to_add(ce)) { diff_addremove(&revs->diffopt, '+', ce->ce_mode, - EMPTY_BLOB_SHA1_BIN, 0, + &empty_tree_oid, 0, ce->name, 0); continue; } @@@ -233,12 -233,12 +233,12 @@@ continue; } oldmode = ce->ce_mode; - old_sha1 = ce->oid.hash; - new_sha1 = changed ? null_sha1 : ce->oid.hash; + old_oid = &ce->oid; + new_oid = changed ? &null_oid : &ce->oid; diff_change(&revs->diffopt, oldmode, newmode, - old_sha1, new_sha1, - !is_null_sha1(old_sha1), - !is_null_sha1(new_sha1), + old_oid, new_oid, + !is_null_oid(old_oid), + !is_null_oid(new_oid), ce->name, 0, dirty_submodule); } @@@ -255,21 -255,21 +255,21 @@@ static void diff_index_show_file(struct rev_info *revs, const char *prefix, const struct cache_entry *ce, - const unsigned char *sha1, int sha1_valid, + const struct object_id *oid, int oid_valid, unsigned int mode, unsigned dirty_submodule) { diff_addremove(&revs->diffopt, prefix[0], mode, - sha1, sha1_valid, ce->name, dirty_submodule); + oid, oid_valid, ce->name, dirty_submodule); } static int get_stat_data(const struct cache_entry *ce, - const unsigned char **sha1p, + const struct object_id **oidp, unsigned int *modep, int cached, int match_missing, unsigned *dirty_submodule, struct diff_options *diffopt) { - const unsigned char *sha1 = ce->oid.hash; + const struct object_id *oid = &ce->oid; unsigned int mode = ce->ce_mode; if (!cached && !ce_uptodate(ce)) { @@@ -280,7 -280,7 +280,7 @@@ return -1; else if (changed) { if (match_missing) { - *sha1p = sha1; + *oidp = oid; *modep = mode; return 0; } @@@ -290,11 -290,11 +290,11 @@@ 0, dirty_submodule); if (changed) { mode = ce_mode_from_stat(ce, st.st_mode); - sha1 = null_sha1; + oid = &null_oid; } } - *sha1p = sha1; + *oidp = oid; *modep = mode; return 0; } @@@ -303,7 -303,7 +303,7 @@@ static void show_new_file(struct rev_in const struct cache_entry *new, int cached, int match_missing) { - const unsigned char *sha1; + const struct object_id *oid; unsigned int mode; unsigned dirty_submodule = 0; @@@ -311,11 -311,11 +311,11 @@@ * New file in the index: it might actually be different in * the working tree. */ - if (get_stat_data(new, &sha1, &mode, cached, match_missing, + if (get_stat_data(new, &oid, &mode, cached, match_missing, &dirty_submodule, &revs->diffopt) < 0) return; - diff_index_show_file(revs, "+", new, sha1, !is_null_sha1(sha1), mode, dirty_submodule); + diff_index_show_file(revs, "+", new, oid, !is_null_oid(oid), mode, dirty_submodule); } static int show_modified(struct rev_info *revs, @@@ -325,20 -325,20 +325,20 @@@ int cached, int match_missing) { unsigned int mode, oldmode; - const unsigned char *sha1; + const struct object_id *oid; unsigned dirty_submodule = 0; - if (get_stat_data(new, &sha1, &mode, cached, match_missing, + if (get_stat_data(new, &oid, &mode, cached, match_missing, &dirty_submodule, &revs->diffopt) < 0) { if (report_missing) diff_index_show_file(revs, "-", old, - old->oid.hash, 1, old->ce_mode, + &old->oid, 1, old->ce_mode, 0); return -1; } if (revs->combine_merges && !cached && - (hashcmp(sha1, old->oid.hash) || oidcmp(&old->oid, &new->oid))) { + (oidcmp(oid, &old->oid) || oidcmp(&old->oid, &new->oid))) { struct combine_diff_path *p; int pathlen = ce_namelen(new); @@@ -362,12 -362,12 +362,12 @@@ } oldmode = old->ce_mode; - if (mode == oldmode && !hashcmp(sha1, old->oid.hash) && !dirty_submodule && + if (mode == oldmode && !oidcmp(oid, &old->oid) && !dirty_submodule && !DIFF_OPT_TST(&revs->diffopt, FIND_COPIES_HARDER)) return 0; diff_change(&revs->diffopt, oldmode, mode, - old->oid.hash, sha1, 1, !is_null_sha1(sha1), + &old->oid, oid, 1, !is_null_oid(oid), old->name, 0, dirty_submodule); return 0; } @@@ -409,7 -409,7 +409,7 @@@ static void do_oneway_diff(struct unpac struct diff_filepair *pair; pair = diff_unmerge(&revs->diffopt, idx->name); if (tree) - fill_filespec(pair->one, tree->oid.hash, 1, + fill_filespec(pair->one, &tree->oid, 1, tree->ce_mode); return; } @@@ -426,7 -426,7 +426,7 @@@ * Something removed from the tree? */ if (!idx) { - diff_index_show_file(revs, "-", tree, tree->oid.hash, 1, + diff_index_show_file(revs, "-", tree, &tree->oid, 1, tree->ce_mode, 0); return; } diff --combined diff.c index e35cf6c704,c758a0d73e..acedf86aec --- a/diff.c +++ b/diff.c @@@ -27,7 -27,7 +27,7 @@@ #endif static int diff_detect_rename_default; -static int diff_indent_heuristic; /* experimental */ +static int diff_indent_heuristic = 1; static int diff_rename_limit_default = 400; static int diff_suppress_blank_empty; static int diff_use_color_default = -1; @@@ -290,6 -290,9 +290,6 @@@ int git_diff_ui_config(const char *var return 0; } - if (git_diff_heuristic_config(var, value, cb) < 0) - return -1; - if (!strcmp(var, "diff.wserrorhighlight")) { int val = parse_ws_error_highlight(value); if (val < 0) @@@ -348,9 -351,6 +348,9 @@@ int git_diff_basic_config(const char *v if (starts_with(var, "submodule.")) return parse_submodule_config_option(var, value); + if (git_diff_heuristic_config(var, value, cb) < 0) + return -1; + return git_default_config(var, value, cb); } @@@ -2702,13 -2702,13 +2702,13 @@@ void free_filespec(struct diff_filespe } } - void fill_filespec(struct diff_filespec *spec, const unsigned char *sha1, - int sha1_valid, unsigned short mode) + void fill_filespec(struct diff_filespec *spec, const struct object_id *oid, + int oid_valid, unsigned short mode) { if (mode) { spec->mode = canon_mode(mode); - hashcpy(spec->oid.hash, sha1); - spec->oid_valid = sha1_valid; + oidcpy(&spec->oid, oid); + spec->oid_valid = oid_valid; } } @@@ -2717,7 -2717,7 +2717,7 @@@ * the work tree has that object contents, return true, so that * prepare_temp_file() does not have to inflate and extract. */ - static int reuse_worktree_file(const char *name, const unsigned char *sha1, int want_file) + static int reuse_worktree_file(const char *name, const struct object_id *oid, int want_file) { const struct cache_entry *ce; struct stat st; @@@ -2748,7 -2748,7 +2748,7 @@@ * objects however would tend to be slower as they need * to be individually opened and inflated. */ - if (!FAST_WORKING_DIRECTORY && !want_file && has_sha1_pack(sha1)) + if (!FAST_WORKING_DIRECTORY && !want_file && has_sha1_pack(oid->hash)) return 0; /* @@@ -2768,7 -2768,7 +2768,7 @@@ * This is not the sha1 we are looking for, or * unreusable because it is not a regular file. */ - if (hashcmp(sha1, ce->oid.hash) || !S_ISREG(ce->ce_mode)) + if (oidcmp(oid, &ce->oid) || !S_ISREG(ce->ce_mode)) return 0; /* @@@ -2842,7 -2842,7 +2842,7 @@@ int diff_populate_filespec(struct diff_ return diff_populate_gitlink(s, size_only); if (!s->oid_valid || - reuse_worktree_file(s->path, s->oid.hash, 0)) { + reuse_worktree_file(s->path, &s->oid, 0)) { struct strbuf buf = STRBUF_INIT; struct stat st; int fd; @@@ -3008,7 -3008,7 +3008,7 @@@ static struct diff_tempfile *prepare_te if (!S_ISGITLINK(one->mode) && (!one->oid_valid || - reuse_worktree_file(name, one->oid.hash, 1))) { + reuse_worktree_file(name, &one->oid, 1))) { struct stat st; if (lstat(name, &st) < 0) { if (errno == ENOENT) @@@ -3030,13 -3030,13 +3030,13 @@@ /* we can borrow from the file in the work tree */ temp->name = name; if (!one->oid_valid) - sha1_to_hex_r(temp->hex, null_sha1); + oid_to_hex_r(temp->hex, &null_oid); else oid_to_hex_r(temp->hex, &one->oid); /* Even though we may sometimes borrow the * contents from the work tree, we always want * one->mode. mode is trustworthy even when - * !(one->sha1_valid), as long as + * !(one->oid_valid), as long as * DIFF_FILE_VALID(one). */ xsnprintf(temp->mode, sizeof(temp->mode), "%06o", one->mode); @@@ -3239,7 -3239,7 +3239,7 @@@ static void run_diff_cmd(const char *pg fprintf(o->file, "* Unmerged path %s\n", name); } - static void diff_fill_sha1_info(struct diff_filespec *one) + static void diff_fill_oid_info(struct diff_filespec *one) { if (DIFF_FILE_VALID(one)) { if (!one->oid_valid) { @@@ -3298,8 -3298,8 +3298,8 @@@ static void run_diff(struct diff_filepa return; } - diff_fill_sha1_info(one); - diff_fill_sha1_info(two); + diff_fill_oid_info(one); + diff_fill_oid_info(two); if (!pgm && DIFF_FILE_VALID(one) && DIFF_FILE_VALID(two) && @@@ -3344,8 -3344,8 +3344,8 @@@ static void run_diffstat(struct diff_fi if (o->prefix_length) strip_prefix(o->prefix_length, &name, &other); - diff_fill_sha1_info(p->one); - diff_fill_sha1_info(p->two); + diff_fill_oid_info(p->one); + diff_fill_oid_info(p->two); builtin_diffstat(name, other, p->one, p->two, diffstat, o, p); } @@@ -3368,8 -3368,8 +3368,8 @@@ static void run_checkdiff(struct diff_f if (o->prefix_length) strip_prefix(o->prefix_length, &name, &other); - diff_fill_sha1_info(p->one); - diff_fill_sha1_info(p->two); + diff_fill_oid_info(p->one); + diff_fill_oid_info(p->two); builtin_checkdiff(name, other, attr_path, p->one, p->two, o); } @@@ -4071,7 -4071,9 +4071,7 @@@ int diff_opt_parse(struct diff_options DIFF_OPT_CLR(options, FUNCCONTEXT); else if ((argcount = parse_long_opt("output", av, &optarg))) { char *path = prefix_filename(prefix, optarg); - options->file = fopen(path, "w"); - if (!options->file) - die_errno("Could not open '%s'", path); + options->file = xfopen(path, "w"); options->close_file = 1; if (options->use_color != GIT_COLOR_ALWAYS) options->use_color = GIT_COLOR_NEVER; @@@ -4582,7 -4584,7 +4582,7 @@@ static void patch_id_add_mode(git_SHA_C } /* returns 0 upon success, and writes result into sha1 */ - static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1, int diff_header_only) + static int diff_get_patch_id(struct diff_options *options, struct object_id *oid, int diff_header_only) { struct diff_queue_struct *q = &diff_queued_diff; int i; @@@ -4614,8 -4616,8 +4614,8 @@@ if (DIFF_PAIR_UNMERGED(p)) continue; - diff_fill_sha1_info(p->one); - diff_fill_sha1_info(p->two); + diff_fill_oid_info(p->one); + diff_fill_oid_info(p->two); len1 = remove_space(p->one->path, strlen(p->one->path)); len2 = remove_space(p->two->path, strlen(p->two->path)); @@@ -4654,9 -4656,9 +4654,9 @@@ if (diff_filespec_is_binary(p->one) || diff_filespec_is_binary(p->two)) { git_SHA1_Update(&ctx, oid_to_hex(&p->one->oid), - 40); + GIT_SHA1_HEXSZ); git_SHA1_Update(&ctx, oid_to_hex(&p->two->oid), - 40); + GIT_SHA1_HEXSZ); continue; } @@@ -4669,15 -4671,15 +4669,15 @@@ p->one->path); } - git_SHA1_Final(sha1, &ctx); + git_SHA1_Final(oid->hash, &ctx); return 0; } - int diff_flush_patch_id(struct diff_options *options, unsigned char *sha1, int diff_header_only) + int diff_flush_patch_id(struct diff_options *options, struct object_id *oid, int diff_header_only) { struct diff_queue_struct *q = &diff_queued_diff; int i; - int result = diff_get_patch_id(options, sha1, diff_header_only); + int result = diff_get_patch_id(options, oid, diff_header_only); for (i = 0; i < q->nr; i++) diff_free_filepair(q->queue[i]); @@@ -4805,7 -4807,9 +4805,7 @@@ void diff_flush(struct diff_options *op */ if (options->close_file) fclose(options->file); - options->file = fopen("/dev/null", "w"); - if (!options->file) - die_errno("Could not open /dev/null"); + options->file = xfopen("/dev/null", "w"); options->close_file = 1; for (i = 0; i < q->nr; i++) { struct diff_filepair *p = q->queue[i]; @@@ -5077,8 -5081,8 +5077,8 @@@ static int is_submodule_ignored(const c void diff_addremove(struct diff_options *options, int addremove, unsigned mode, - const unsigned char *sha1, - int sha1_valid, + const struct object_id *oid, + int oid_valid, const char *concatpath, unsigned dirty_submodule) { struct diff_filespec *one, *two; @@@ -5110,9 -5114,9 +5110,9 @@@ two = alloc_filespec(concatpath); if (addremove != '+') - fill_filespec(one, sha1, sha1_valid, mode); + fill_filespec(one, oid, oid_valid, mode); if (addremove != '-') { - fill_filespec(two, sha1, sha1_valid, mode); + fill_filespec(two, oid, oid_valid, mode); two->dirty_submodule = dirty_submodule; } @@@ -5123,9 -5127,9 +5123,9 @@@ void diff_change(struct diff_options *options, unsigned old_mode, unsigned new_mode, - const unsigned char *old_sha1, - const unsigned char *new_sha1, - int old_sha1_valid, int new_sha1_valid, + const struct object_id *old_oid, + const struct object_id *new_oid, + int old_oid_valid, int new_oid_valid, const char *concatpath, unsigned old_dirty_submodule, unsigned new_dirty_submodule) { @@@ -5138,8 -5142,8 +5138,8 @@@ if (DIFF_OPT_TST(options, REVERSE_DIFF)) { SWAP(old_mode, new_mode); - SWAP(old_sha1, new_sha1); - SWAP(old_sha1_valid, new_sha1_valid); + SWAP(old_oid, new_oid); + SWAP(old_oid_valid, new_oid_valid); SWAP(old_dirty_submodule, new_dirty_submodule); } @@@ -5149,8 -5153,8 +5149,8 @@@ one = alloc_filespec(concatpath); two = alloc_filespec(concatpath); - fill_filespec(one, old_sha1, old_sha1_valid, old_mode); - fill_filespec(two, new_sha1, new_sha1_valid, new_mode); + fill_filespec(one, old_oid, old_oid_valid, old_mode); + fill_filespec(two, new_oid, new_oid_valid, new_mode); one->dirty_submodule = old_dirty_submodule; two->dirty_submodule = new_dirty_submodule; p = diff_queue(&diff_queued_diff, one, two); @@@ -5266,29 -5270,6 +5266,29 @@@ size_t fill_textconv(struct userdiff_dr return size; } +int textconv_object(const char *path, + unsigned mode, + const struct object_id *oid, + int oid_valid, + char **buf, + unsigned long *buf_size) +{ + struct diff_filespec *df; + struct userdiff_driver *textconv; + + df = alloc_filespec(path); - fill_filespec(df, oid->hash, oid_valid, mode); ++ fill_filespec(df, oid, oid_valid, mode); + textconv = get_textconv(df); + if (!textconv) { + free_filespec(df); + return 0; + } + + *buf_size = fill_textconv(textconv, df, buf); + free_filespec(df); + return 1; +} + void setup_diff_pager(struct diff_options *opt) { /* diff --combined diff.h index 67537f17ed,0d0c14f285..2d442e296f --- a/diff.h +++ b/diff.h @@@ -23,16 -23,16 +23,16 @@@ typedef int (*pathchange_fn_t)(struct d typedef void (*change_fn_t)(struct diff_options *options, unsigned old_mode, unsigned new_mode, - const unsigned char *old_sha1, - const unsigned char *new_sha1, - int old_sha1_valid, int new_sha1_valid, + const struct object_id *old_oid, + const struct object_id *new_oid, + int old_oid_valid, int new_oid_valid, const char *fullpath, unsigned old_dirty_submodule, unsigned new_dirty_submodule); typedef void (*add_remove_fn_t)(struct diff_options *options, int addremove, unsigned mode, - const unsigned char *sha1, - int sha1_valid, + const struct object_id *oid, + int oid_valid, const char *fullpath, unsigned dirty_submodule); typedef void (*diff_format_fn_t)(struct diff_queue_struct *q, @@@ -210,13 -210,14 +210,14 @@@ const char *diff_line_prefix(struct dif extern const char mime_boundary_leader[]; extern struct combine_diff_path *diff_tree_paths( - struct combine_diff_path *p, const unsigned char *sha1, - const unsigned char **parent_sha1, int nparent, + struct combine_diff_path *p, const struct object_id *oid, + const struct object_id **parents_oid, int nparent, struct strbuf *base, struct diff_options *opt); - extern int diff_tree_sha1(const unsigned char *old, const unsigned char *new, - const char *base, struct diff_options *opt); - extern int diff_root_tree_sha1(const unsigned char *new, const char *base, - struct diff_options *opt); + extern int diff_tree_oid(const struct object_id *old_oid, + const struct object_id *new_oid, + const char *base, struct diff_options *opt); + extern int diff_root_tree_oid(const struct object_id *new_oid, const char *base, + struct diff_options *opt); struct combine_diff_path { struct combine_diff_path *next; @@@ -236,7 -237,7 +237,7 @@@ extern void show_combined_diff(struct combine_diff_path *elem, int num_parent, int dense, struct rev_info *); - extern void diff_tree_combined(const unsigned char *sha1, const struct oid_array *parents, int dense, struct rev_info *rev); + extern void diff_tree_combined(const struct object_id *oid, const struct oid_array *parents, int dense, struct rev_info *rev); extern void diff_tree_combined_merge(const struct commit *commit, int dense, struct rev_info *rev); @@@ -247,16 -248,15 +248,15 @@@ extern int diff_can_quit_early(struct d extern void diff_addremove(struct diff_options *, int addremove, unsigned mode, - const unsigned char *sha1, - int sha1_valid, + const struct object_id *oid, + int oid_valid, const char *fullpath, unsigned dirty_submodule); extern void diff_change(struct diff_options *, unsigned mode1, unsigned mode2, - const unsigned char *sha1, - const unsigned char *sha2, - int sha1_valid, - int sha2_valid, + const struct object_id *old_oid, + const struct object_id *new_oid, + int old_oid_valid, int new_oid_valid, const char *fullpath, unsigned dirty_submodule1, unsigned dirty_submodule2); @@@ -355,7 -355,7 +355,7 @@@ extern int run_diff_files(struct rev_in extern int run_diff_index(struct rev_info *revs, int cached); extern int do_diff_cache(const struct object_id *, struct diff_options *); - extern int diff_flush_patch_id(struct diff_options *, unsigned char *, int); + extern int diff_flush_patch_id(struct diff_options *, struct object_id *, int); extern int diff_result_code(struct diff_options *, int); @@@ -385,13 -385,6 +385,13 @@@ extern size_t fill_textconv(struct user */ extern struct userdiff_driver *get_textconv(struct diff_filespec *one); +/* + * Prepare diff_filespec and convert it using diff textconv API + * if the textconv driver exists. + * Return 1 if the conversion succeeds, 0 otherwise. + */ +extern int textconv_object(const char *path, unsigned mode, const struct object_id *oid, int oid_valid, char **buf, unsigned long *buf_size); + extern int parse_rename_score(const char **cp_p); extern long parse_algorithm_value(const char *value); diff --combined grep.c index d0bf37858a,3e21c92b9d..d7ef21358e --- a/grep.c +++ b/grep.c @@@ -178,38 -178,26 +178,38 @@@ static void grep_set_pattern_type_optio case GREP_PATTERN_TYPE_BRE: opt->fixed = 0; - opt->pcre = 0; - opt->regflags &= ~REG_EXTENDED; + opt->pcre1 = 0; + opt->pcre2 = 0; break; case GREP_PATTERN_TYPE_ERE: opt->fixed = 0; - opt->pcre = 0; + opt->pcre1 = 0; + opt->pcre2 = 0; opt->regflags |= REG_EXTENDED; break; case GREP_PATTERN_TYPE_FIXED: opt->fixed = 1; - opt->pcre = 0; - opt->regflags &= ~REG_EXTENDED; + opt->pcre1 = 0; + opt->pcre2 = 0; break; case GREP_PATTERN_TYPE_PCRE: opt->fixed = 0; - opt->pcre = 1; - opt->regflags &= ~REG_EXTENDED; +#ifdef USE_LIBPCRE2 + opt->pcre1 = 0; + opt->pcre2 = 1; +#else + /* + * It's important that pcre1 always be assigned to + * even when there's no USE_LIBPCRE* defined. We still + * call the PCRE stub function, it just dies with + * "cannot use Perl-compatible regexes[...]". + */ + opt->pcre1 = 1; + opt->pcre2 = 0; +#endif break; } } @@@ -336,32 -324,8 +336,32 @@@ static NORETURN void compile_regexp_fai die("%s'%s': %s", where, p->pattern, error); } -#ifdef USE_LIBPCRE -static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt) +static int is_fixed(const char *s, size_t len) +{ + size_t i; + + for (i = 0; i < len; i++) { + if (is_regex_special(s[i])) + return 0; + } + + return 1; +} + +static int has_null(const char *s, size_t len) +{ + /* + * regcomp cannot accept patterns with NULs so when using it + * we consider any pattern containing a NUL fixed. + */ + if (memchr(s, 0, len)) + return 1; + + return 0; +} + +#ifdef USE_LIBPCRE1 +static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt) { const char *error; int erroffset; @@@ -369,36 -333,23 +369,36 @@@ if (opt->ignore_case) { if (has_non_ascii(p->pattern)) - p->pcre_tables = pcre_maketables(); + p->pcre1_tables = pcre_maketables(); options |= PCRE_CASELESS; } if (is_utf8_locale() && has_non_ascii(p->pattern)) options |= PCRE_UTF8; - p->pcre_regexp = pcre_compile(p->pattern, options, &error, &erroffset, - p->pcre_tables); - if (!p->pcre_regexp) + p->pcre1_regexp = pcre_compile(p->pattern, options, &error, &erroffset, + p->pcre1_tables); + if (!p->pcre1_regexp) compile_regexp_failed(p, error); - p->pcre_extra_info = pcre_study(p->pcre_regexp, 0, &error); - if (!p->pcre_extra_info && error) + p->pcre1_extra_info = pcre_study(p->pcre1_regexp, PCRE_STUDY_JIT_COMPILE, &error); + if (!p->pcre1_extra_info && error) die("%s", error); + +#ifdef GIT_PCRE1_USE_JIT + pcre_config(PCRE_CONFIG_JIT, &p->pcre1_jit_on); + if (p->pcre1_jit_on == 1) { + p->pcre1_jit_stack = pcre_jit_stack_alloc(1, 1024 * 1024); + if (!p->pcre1_jit_stack) + die("Couldn't allocate PCRE JIT stack"); + pcre_assign_jit_stack(p->pcre1_extra_info, NULL, p->pcre1_jit_stack); + } else if (p->pcre1_jit_on != 0) { + die("BUG: The pcre1_jit_on variable should be 0 or 1, not %d", + p->pcre1_jit_on); + } +#endif } -static int pcrematch(struct grep_pat *p, const char *line, const char *eol, +static int pcre1match(struct grep_pat *p, const char *line, const char *eol, regmatch_t *match, int eflags) { int ovector[30], ret, flags = 0; @@@ -406,19 -357,8 +406,19 @@@ if (eflags & REG_NOTBOL) flags |= PCRE_NOTBOL; - ret = pcre_exec(p->pcre_regexp, p->pcre_extra_info, line, eol - line, - 0, flags, ovector, ARRAY_SIZE(ovector)); +#ifdef GIT_PCRE1_USE_JIT + if (p->pcre1_jit_on) { + ret = pcre_jit_exec(p->pcre1_regexp, p->pcre1_extra_info, line, + eol - line, 0, flags, ovector, + ARRAY_SIZE(ovector), p->pcre1_jit_stack); + } else +#endif + { + ret = pcre_exec(p->pcre1_regexp, p->pcre1_extra_info, line, + eol - line, 0, flags, ovector, + ARRAY_SIZE(ovector)); + } + if (ret < 0 && ret != PCRE_ERROR_NOMATCH) die("pcre_exec failed with error code %d", ret); if (ret > 0) { @@@ -430,165 -370,55 +430,165 @@@ return ret; } -static void free_pcre_regexp(struct grep_pat *p) +static void free_pcre1_regexp(struct grep_pat *p) { - pcre_free(p->pcre_regexp); - pcre_free(p->pcre_extra_info); - pcre_free((void *)p->pcre_tables); + pcre_free(p->pcre1_regexp); +#ifdef GIT_PCRE1_USE_JIT + if (p->pcre1_jit_on) { + pcre_free_study(p->pcre1_extra_info); + pcre_jit_stack_free(p->pcre1_jit_stack); + } else +#endif + { + pcre_free(p->pcre1_extra_info); + } + pcre_free((void *)p->pcre1_tables); } -#else /* !USE_LIBPCRE */ -static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt) +#else /* !USE_LIBPCRE1 */ +static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt) { die("cannot use Perl-compatible regexes when not compiled with USE_LIBPCRE"); } -static int pcrematch(struct grep_pat *p, const char *line, const char *eol, +static int pcre1match(struct grep_pat *p, const char *line, const char *eol, regmatch_t *match, int eflags) { return 1; } -static void free_pcre_regexp(struct grep_pat *p) +static void free_pcre1_regexp(struct grep_pat *p) { } -#endif /* !USE_LIBPCRE */ +#endif /* !USE_LIBPCRE1 */ -static int is_fixed(const char *s, size_t len) +#ifdef USE_LIBPCRE2 +static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt) { - size_t i; + int error; + PCRE2_UCHAR errbuf[256]; + PCRE2_SIZE erroffset; + int options = PCRE2_MULTILINE; + const uint8_t *character_tables = NULL; + int jitret; - /* regcomp cannot accept patterns with NULs so we - * consider any pattern containing a NUL fixed. - */ - if (memchr(s, 0, len)) - return 1; + assert(opt->pcre2); - for (i = 0; i < len; i++) { - if (is_regex_special(s[i])) - return 0; + p->pcre2_compile_context = NULL; + + if (opt->ignore_case) { + if (has_non_ascii(p->pattern)) { + character_tables = pcre2_maketables(NULL); + p->pcre2_compile_context = pcre2_compile_context_create(NULL); + pcre2_set_character_tables(p->pcre2_compile_context, character_tables); + } + options |= PCRE2_CASELESS; + } + if (is_utf8_locale() && has_non_ascii(p->pattern)) + options |= PCRE2_UTF; + + p->pcre2_pattern = pcre2_compile((PCRE2_SPTR)p->pattern, + p->patternlen, options, &error, &erroffset, + p->pcre2_compile_context); + + if (p->pcre2_pattern) { + p->pcre2_match_data = pcre2_match_data_create_from_pattern(p->pcre2_pattern, NULL); + if (!p->pcre2_match_data) + die("Couldn't allocate PCRE2 match data"); + } else { + pcre2_get_error_message(error, errbuf, sizeof(errbuf)); + compile_regexp_failed(p, (const char *)&errbuf); + } + + pcre2_config(PCRE2_CONFIG_JIT, &p->pcre2_jit_on); + if (p->pcre2_jit_on == 1) { + jitret = pcre2_jit_compile(p->pcre2_pattern, PCRE2_JIT_COMPLETE); + if (jitret) + die("Couldn't JIT the PCRE2 pattern '%s', got '%d'\n", p->pattern, jitret); + p->pcre2_jit_stack = pcre2_jit_stack_create(1, 1024 * 1024, NULL); + if (!p->pcre2_jit_stack) + die("Couldn't allocate PCRE2 JIT stack"); + p->pcre2_match_context = pcre2_match_context_create(NULL); + if (!p->pcre2_jit_stack) + die("Couldn't allocate PCRE2 match context"); + pcre2_jit_stack_assign(p->pcre2_match_context, NULL, p->pcre2_jit_stack); + } else if (p->pcre2_jit_on != 0) { + die("BUG: The pcre2_jit_on variable should be 0 or 1, not %d", + p->pcre1_jit_on); + } +} + +static int pcre2match(struct grep_pat *p, const char *line, const char *eol, + regmatch_t *match, int eflags) +{ + int ret, flags = 0; + PCRE2_SIZE *ovector; + PCRE2_UCHAR errbuf[256]; + + if (eflags & REG_NOTBOL) + flags |= PCRE2_NOTBOL; + + if (p->pcre2_jit_on) + ret = pcre2_jit_match(p->pcre2_pattern, (unsigned char *)line, + eol - line, 0, flags, p->pcre2_match_data, + NULL); + else + ret = pcre2_match(p->pcre2_pattern, (unsigned char *)line, + eol - line, 0, flags, p->pcre2_match_data, + NULL); + + if (ret < 0 && ret != PCRE2_ERROR_NOMATCH) { + pcre2_get_error_message(ret, errbuf, sizeof(errbuf)); + die("%s failed with error code %d: %s", + (p->pcre2_jit_on ? "pcre2_jit_match" : "pcre2_match"), ret, + errbuf); + } + if (ret > 0) { + ovector = pcre2_get_ovector_pointer(p->pcre2_match_data); + ret = 0; + match->rm_so = (int)ovector[0]; + match->rm_eo = (int)ovector[1]; } + return ret; +} + +static void free_pcre2_pattern(struct grep_pat *p) +{ + pcre2_compile_context_free(p->pcre2_compile_context); + pcre2_code_free(p->pcre2_pattern); + pcre2_match_data_free(p->pcre2_match_data); + pcre2_jit_stack_free(p->pcre2_jit_stack); + pcre2_match_context_free(p->pcre2_match_context); +} +#else /* !USE_LIBPCRE2 */ +static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt) +{ + /* + * Unreachable until USE_LIBPCRE2 becomes synonymous with + * USE_LIBPCRE. See the sibling comment in + * grep_set_pattern_type_option(). + */ + die("cannot use Perl-compatible regexes when not compiled with USE_LIBPCRE"); +} + +static int pcre2match(struct grep_pat *p, const char *line, const char *eol, + regmatch_t *match, int eflags) +{ return 1; } +static void free_pcre2_pattern(struct grep_pat *p) +{ +} +#endif /* !USE_LIBPCRE2 */ + static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt) { struct strbuf sb = STRBUF_INIT; int err; - int regflags; + int regflags = opt->regflags; basic_regex_quote_buf(&sb, p->pattern); - regflags = opt->regflags & ~REG_EXTENDED; if (opt->ignore_case) regflags |= REG_ICASE; err = regcomp(&p->regexp, sb.buf, regflags); @@@ -625,9 -455,7 +625,9 @@@ static void compile_regexp(struct grep_ * simple string match using kws. p->fixed tells us if we * want to use kws. */ - if (opt->fixed || is_fixed(p->pattern, p->patternlen)) + if (opt->fixed || + has_null(p->pattern, p->patternlen) || + is_fixed(p->pattern, p->patternlen)) p->fixed = !icase || ascii_only; else p->fixed = 0; @@@ -647,13 -475,8 +647,13 @@@ return; } - if (opt->pcre) { - compile_pcre_regexp(p, opt); + if (opt->pcre2) { + compile_pcre2_pattern(p, opt); + return; + } + + if (opt->pcre1) { + compile_pcre1_regexp(p, opt); return; } @@@ -1009,10 -832,8 +1009,10 @@@ void free_grep_patterns(struct grep_op case GREP_PATTERN_BODY: if (p->kws) kwsfree(p->kws); - else if (p->pcre_regexp) - free_pcre_regexp(p); + else if (p->pcre1_regexp) + free_pcre1_regexp(p); + else if (p->pcre2_pattern) + free_pcre2_pattern(p); else regfree(&p->regexp); free(p->pattern); @@@ -1091,10 -912,8 +1091,10 @@@ static int patmatch(struct grep_pat *p if (p->fixed) hit = !fixmatch(p, line, eol, match); - else if (p->pcre_regexp) - hit = !pcrematch(p, line, eol, match, eflags); + else if (p->pcre1_regexp) + hit = !pcre1match(p, line, eol, match, eflags); + else if (p->pcre2_pattern) + hit = !pcre2match(p, line, eol, match, eflags); else hit = !regexec_buf(&p->regexp, line, eol - line, 1, match, eflags); @@@ -1584,11 -1403,11 +1584,11 @@@ static int fill_textconv_grep(struct us */ df = alloc_filespec(gs->path); switch (gs->type) { - case GREP_SOURCE_SHA1: + case GREP_SOURCE_OID: fill_filespec(df, gs->identifier, 1, 0100644); break; case GREP_SOURCE_FILE: - fill_filespec(df, null_sha1, 0, 0100644); + fill_filespec(df, &null_oid, 0, 0100644); break; default: die("BUG: attempt to textconv something without a path?"); @@@ -1928,9 -1747,8 +1928,8 @@@ void grep_source_init(struct grep_sourc * If the identifier is non-NULL (in the submodule case) it * will be a SHA1 that needs to be copied. */ - case GREP_SOURCE_SHA1: - gs->identifier = xmalloc(20); - hashcpy(gs->identifier, identifier); + case GREP_SOURCE_OID: + gs->identifier = oiddup(identifier); break; case GREP_SOURCE_BUF: gs->identifier = NULL; @@@ -1953,7 -1771,7 +1952,7 @@@ void grep_source_clear_data(struct grep { switch (gs->type) { case GREP_SOURCE_FILE: - case GREP_SOURCE_SHA1: + case GREP_SOURCE_OID: case GREP_SOURCE_SUBMODULE: free(gs->buf); gs->buf = NULL; @@@ -1965,7 -1783,7 +1964,7 @@@ } } - static int grep_source_load_sha1(struct grep_source *gs) + static int grep_source_load_oid(struct grep_source *gs) { enum object_type type; @@@ -1976,7 -1794,7 +1975,7 @@@ if (!gs->buf) return error(_("'%s': unable to read %s"), gs->name, - sha1_to_hex(gs->identifier)); + oid_to_hex(gs->identifier)); return 0; } @@@ -2022,8 -1840,8 +2021,8 @@@ static int grep_source_load(struct grep switch (gs->type) { case GREP_SOURCE_FILE: return grep_source_load_file(gs); - case GREP_SOURCE_SHA1: - return grep_source_load_sha1(gs); + case GREP_SOURCE_OID: + return grep_source_load_oid(gs); case GREP_SOURCE_BUF: return gs->buf ? 0 : -1; case GREP_SOURCE_SUBMODULE: diff --combined grep.h index 6f3d4e1954,c88b40bdc4..b8f93bfc2d --- a/grep.h +++ b/grep.h @@@ -1,35 -1,11 +1,35 @@@ #ifndef GREP_H #define GREP_H #include "color.h" -#ifdef USE_LIBPCRE +#ifdef USE_LIBPCRE1 #include +#ifdef PCRE_CONFIG_JIT +#if PCRE_MAJOR >= 8 && PCRE_MINOR >= 32 +#ifndef NO_LIBPCRE1_JIT +#define GIT_PCRE1_USE_JIT +#endif +#endif +#endif +#ifndef PCRE_STUDY_JIT_COMPILE +#define PCRE_STUDY_JIT_COMPILE 0 +#endif +#if PCRE_MAJOR <= 8 && PCRE_MINOR < 20 +typedef int pcre_jit_stack; +#endif #else typedef int pcre; typedef int pcre_extra; +typedef int pcre_jit_stack; +#endif +#ifdef USE_LIBPCRE2 +#define PCRE2_CODE_UNIT_WIDTH 8 +#include +#else +typedef int pcre2_code; +typedef int pcre2_match_data; +typedef int pcre2_compile_context; +typedef int pcre2_match_context; +typedef int pcre2_jit_stack; #endif #include "kwset.h" #include "thread-utils.h" @@@ -70,17 -46,9 +70,17 @@@ struct grep_pat size_t patternlen; enum grep_header_field field; regex_t regexp; - pcre *pcre_regexp; - pcre_extra *pcre_extra_info; - const unsigned char *pcre_tables; + pcre *pcre1_regexp; + pcre_extra *pcre1_extra_info; + pcre_jit_stack *pcre1_jit_stack; + const unsigned char *pcre1_tables; + int pcre1_jit_on; + pcre2_code *pcre2_pattern; + pcre2_match_data *pcre2_match_data; + pcre2_compile_context *pcre2_compile_context; + pcre2_match_context *pcre2_match_context; + pcre2_jit_stack *pcre2_jit_stack; + uint32_t pcre2_jit_on; kwset_t kws; unsigned fixed:1; unsigned ignore_case:1; @@@ -143,8 -111,7 +143,8 @@@ struct grep_opt int allow_textconv; int extended; int use_reflog_filter; - int pcre; + int pcre1; + int pcre2; int relative; int pathname; int null_following_name; @@@ -191,7 -158,7 +191,7 @@@ struct grep_source char *name; enum grep_source_type { - GREP_SOURCE_SHA1, + GREP_SOURCE_OID, GREP_SOURCE_FILE, GREP_SOURCE_BUF, GREP_SOURCE_SUBMODULE, diff --combined notes-utils.c index 031503d7b2,b2aada90a2..9ebf841956 --- a/notes-utils.c +++ b/notes-utils.c @@@ -132,11 -132,8 +132,11 @@@ struct notes_rewrite_cfg *init_copy_not c->mode_from_env = 1; c->combine = parse_combine_notes_fn(rewrite_mode_env); if (!c->combine) - /* TRANSLATORS: The first %s is the name of the - environment variable, the second %s is its value */ + /* + * TRANSLATORS: The first %s is the name of + * the environment variable, the second %s is + * its value. + */ error(_("Bad %s value: '%s'"), GIT_NOTES_REWRITE_MODE_ENVIRONMENT, rewrite_mode_env); } @@@ -158,7 -155,7 +158,7 @@@ } int copy_note_for_rewrite(struct notes_rewrite_cfg *c, - const unsigned char *from_obj, const unsigned char *to_obj) + const struct object_id *from_obj, const struct object_id *to_obj) { int ret = 0; int i; diff --combined remote-testsvn.c index 50404ef343,8e8d5c7947..e034ea00d4 --- a/remote-testsvn.c +++ b/remote-testsvn.c @@@ -51,17 -51,17 +51,17 @@@ static void terminate_batch(void } /* NOTE: 'ref' refers to a git reference, while 'rev' refers to a svn revision. */ - static char *read_ref_note(const unsigned char sha1[20]) + static char *read_ref_note(const struct object_id *oid) { - const unsigned char *note_sha1; + const struct object_id *note_oid; char *msg = NULL; unsigned long msglen; enum object_type type; init_notes(NULL, notes_ref, NULL, 0); - if (!(note_sha1 = get_note(NULL, sha1))) + if (!(note_oid = get_note(NULL, oid))) return NULL; /* note tree not found */ - if (!(msg = read_sha1_file(note_sha1, &type, &msglen))) + if (!(msg = read_sha1_file(note_oid->hash, &type, &msglen))) error("Empty notes tree. %s", notes_ref); else if (!msglen || type != OBJ_BLOB) { error("Note contains unusable content. " @@@ -99,8 -99,8 +99,8 @@@ static int parse_rev_note(const char *m return -1; } - static int note2mark_cb(const unsigned char *object_sha1, - const unsigned char *note_sha1, char *note_path, + static int note2mark_cb(const struct object_id *object_oid, + const struct object_id *note_oid, char *note_path, void *cb_data) { FILE *file = (FILE *)cb_data; @@@ -109,14 -109,14 +109,14 @@@ enum object_type type; struct rev_note note; - if (!(msg = read_sha1_file(note_sha1, &type, &msglen)) || + if (!(msg = read_sha1_file(note_oid->hash, &type, &msglen)) || !msglen || type != OBJ_BLOB) { free(msg); return 1; } if (parse_rev_note(msg, ¬e)) return 2; - if (fprintf(file, ":%d %s\n", note.rev_nr, sha1_to_hex(object_sha1)) < 1) + if (fprintf(file, ":%d %s\n", note.rev_nr, oid_to_hex(object_oid)) < 1) return 3; return 0; } @@@ -124,8 -124,10 +124,8 @@@ static void regenerate_marks(void) { int ret; - FILE *marksfile = fopen(marksfilename, "w+"); + FILE *marksfile = xfopen(marksfilename, "w+"); - if (!marksfile) - die_errno("Couldn't create mark file %s.", marksfilename); ret = for_each_note(NULL, 0, note2mark_cb, marksfile); if (ret) die("Regeneration of marks failed, returned %d.", ret); @@@ -146,7 -148,9 +146,7 @@@ static void check_or_regenerate_marks(i marksfile = fopen(marksfilename, "r"); if (!marksfile) { regenerate_marks(); - marksfile = fopen(marksfilename, "r"); - if (!marksfile) - die_errno("cannot read marks file %s!", marksfilename); + marksfile = xfopen(marksfilename, "r"); fclose(marksfile); } else { strbuf_addf(&sb, ":%d ", latestrev); @@@ -170,15 -174,15 +170,15 @@@ static int cmd_import(const char *line int code; int dumpin_fd; char *note_msg; - unsigned char head_sha1[20]; + struct object_id head_oid; unsigned int startrev; struct child_process svndump_proc = CHILD_PROCESS_INIT; const char *command = "svnrdump"; - if (read_ref(private_ref, head_sha1)) + if (read_ref(private_ref, head_oid.hash)) startrev = 0; else { - note_msg = read_ref_note(head_sha1); + note_msg = read_ref_note(&head_oid); if(note_msg == NULL) { warning("No note found for %s.", private_ref); startrev = 0; diff --combined revision.c index 3b09cd6ee9,3030f33eed..12eb332350 --- a/revision.c +++ b/revision.c @@@ -401,8 -401,8 +401,8 @@@ static int tree_difference = REV_TREE_S static void file_add_remove(struct diff_options *options, int addremove, unsigned mode, - const unsigned char *sha1, - int sha1_valid, + const struct object_id *oid, + int oid_valid, const char *fullpath, unsigned dirty_submodule) { int diff = addremove == '+' ? REV_TREE_NEW : REV_TREE_OLD; @@@ -414,9 -414,9 +414,9 @@@ static void file_change(struct diff_options *options, unsigned old_mode, unsigned new_mode, - const unsigned char *old_sha1, - const unsigned char *new_sha1, - int old_sha1_valid, int new_sha1_valid, + const struct object_id *old_oid, + const struct object_id *new_oid, + int old_oid_valid, int new_oid_valid, const char *fullpath, unsigned old_dirty_submodule, unsigned new_dirty_submodule) { @@@ -455,7 -455,7 +455,7 @@@ static int rev_compare_tree(struct rev_ tree_difference = REV_TREE_SAME; DIFF_OPT_CLR(&revs->pruning, HAS_CHANGES); - if (diff_tree_sha1(t1->object.oid.hash, t2->object.oid.hash, "", + if (diff_tree_oid(&t1->object.oid, &t2->object.oid, "", &revs->pruning) < 0) return REV_TREE_DIFFERENT; return tree_difference; @@@ -471,7 -471,7 +471,7 @@@ static int rev_same_tree_as_empty(struc tree_difference = REV_TREE_SAME; DIFF_OPT_CLR(&revs->pruning, HAS_CHANGES); - retval = diff_tree_sha1(NULL, t1->object.oid.hash, "", &revs->pruning); + retval = diff_tree_oid(NULL, &t1->object.oid, "", &revs->pruning); return retval >= 0 && (tree_difference == REV_TREE_SAME); } @@@ -1429,168 -1429,134 +1429,168 @@@ static void prepare_show_merge(struct r revs->limited = 1; } +static int dotdot_missing(const char *arg, char *dotdot, + struct rev_info *revs, int symmetric) +{ + if (revs->ignore_missing) + return 0; + /* de-munge so we report the full argument */ + *dotdot = '.'; + die(symmetric + ? "Invalid symmetric difference expression %s" + : "Invalid revision range %s", arg); +} + +static int handle_dotdot_1(const char *arg, char *dotdot, + struct rev_info *revs, int flags, + int cant_be_filename, + struct object_context *a_oc, + struct object_context *b_oc) +{ + const char *a_name, *b_name; + struct object_id a_oid, b_oid; + struct object *a_obj, *b_obj; + unsigned int a_flags, b_flags; + int symmetric = 0; + unsigned int flags_exclude = flags ^ (UNINTERESTING | BOTTOM); + unsigned int oc_flags = GET_SHA1_COMMITTISH | GET_SHA1_RECORD_PATH; + + a_name = arg; + if (!*a_name) + a_name = "HEAD"; + + b_name = dotdot + 2; + if (*b_name == '.') { + symmetric = 1; + b_name++; + } + if (!*b_name) + b_name = "HEAD"; + + if (get_sha1_with_context(a_name, oc_flags, a_oid.hash, a_oc) || + get_sha1_with_context(b_name, oc_flags, b_oid.hash, b_oc)) + return -1; + + if (!cant_be_filename) { + *dotdot = '.'; + verify_non_filename(revs->prefix, arg); + *dotdot = '\0'; + } + + a_obj = parse_object(&a_oid); + b_obj = parse_object(&b_oid); + if (!a_obj || !b_obj) + return dotdot_missing(arg, dotdot, revs, symmetric); + + if (!symmetric) { + /* just A..B */ + b_flags = flags; + a_flags = flags_exclude; + } else { + /* A...B -- find merge bases between the two */ + struct commit *a, *b; + struct commit_list *exclude; + + a = lookup_commit_reference(&a_obj->oid); + b = lookup_commit_reference(&b_obj->oid); + if (!a || !b) + return dotdot_missing(arg, dotdot, revs, symmetric); + + exclude = get_merge_bases(a, b); + add_rev_cmdline_list(revs, exclude, REV_CMD_MERGE_BASE, + flags_exclude); + add_pending_commit_list(revs, exclude, flags_exclude); + free_commit_list(exclude); + + b_flags = flags; + a_flags = flags | SYMMETRIC_LEFT; + } + + a_obj->flags |= a_flags; + b_obj->flags |= b_flags; + add_rev_cmdline(revs, a_obj, a_name, REV_CMD_LEFT, a_flags); + add_rev_cmdline(revs, b_obj, b_name, REV_CMD_RIGHT, b_flags); + add_pending_object_with_path(revs, a_obj, a_name, a_oc->mode, a_oc->path); + add_pending_object_with_path(revs, b_obj, b_name, b_oc->mode, b_oc->path); + return 0; +} + +static int handle_dotdot(const char *arg, + struct rev_info *revs, int flags, + int cant_be_filename) +{ + struct object_context a_oc, b_oc; + char *dotdot = strstr(arg, ".."); + int ret; + + if (!dotdot) + return -1; + + memset(&a_oc, 0, sizeof(a_oc)); + memset(&b_oc, 0, sizeof(b_oc)); + + *dotdot = '\0'; + ret = handle_dotdot_1(arg, dotdot, revs, flags, cant_be_filename, + &a_oc, &b_oc); + *dotdot = '.'; + + free(a_oc.path); + free(b_oc.path); + + return ret; +} + int handle_revision_arg(const char *arg_, struct rev_info *revs, int flags, unsigned revarg_opt) { struct object_context oc; - char *dotdot; + char *mark; struct object *object; struct object_id oid; int local_flags; const char *arg = arg_; int cant_be_filename = revarg_opt & REVARG_CANNOT_BE_FILENAME; - unsigned get_sha1_flags = 0; + unsigned get_sha1_flags = GET_SHA1_RECORD_PATH; flags = flags & UNINTERESTING ? flags | BOTTOM : flags & ~BOTTOM; - dotdot = strstr(arg, ".."); - if (dotdot) { - struct object_id from_oid; - const char *next = dotdot + 2; - const char *this = arg; - int symmetric = *next == '.'; - unsigned int flags_exclude = flags ^ (UNINTERESTING | BOTTOM); - static const char head_by_default[] = "HEAD"; - unsigned int a_flags; - - *dotdot = 0; - next += symmetric; - - if (!*next) - next = head_by_default; - if (dotdot == arg) - this = head_by_default; - if (this == head_by_default && next == head_by_default && - !symmetric) { - /* - * Just ".."? That is not a range but the - * pathspec for the parent directory. - */ - if (!cant_be_filename) { - *dotdot = '.'; - return -1; - } - } - if (!get_sha1_committish(this, from_oid.hash) && - !get_sha1_committish(next, oid.hash)) { - struct object *a_obj, *b_obj; - - if (!cant_be_filename) { - *dotdot = '.'; - verify_non_filename(revs->prefix, arg); - } - - a_obj = parse_object(&from_oid); - b_obj = parse_object(&oid); - if (!a_obj || !b_obj) { - missing: - if (revs->ignore_missing) - return 0; - die(symmetric - ? "Invalid symmetric difference expression %s" - : "Invalid revision range %s", arg); - } - - if (!symmetric) { - /* just A..B */ - a_flags = flags_exclude; - } else { - /* A...B -- find merge bases between the two */ - struct commit *a, *b; - struct commit_list *exclude; - - a = (a_obj->type == OBJ_COMMIT - ? (struct commit *)a_obj - : lookup_commit_reference(&a_obj->oid)); - b = (b_obj->type == OBJ_COMMIT - ? (struct commit *)b_obj - : lookup_commit_reference(&b_obj->oid)); - if (!a || !b) - goto missing; - exclude = get_merge_bases(a, b); - add_rev_cmdline_list(revs, exclude, - REV_CMD_MERGE_BASE, - flags_exclude); - add_pending_commit_list(revs, exclude, - flags_exclude); - free_commit_list(exclude); - - a_flags = flags | SYMMETRIC_LEFT; - } - - a_obj->flags |= a_flags; - b_obj->flags |= flags; - add_rev_cmdline(revs, a_obj, this, - REV_CMD_LEFT, a_flags); - add_rev_cmdline(revs, b_obj, next, - REV_CMD_RIGHT, flags); - add_pending_object(revs, a_obj, this); - add_pending_object(revs, b_obj, next); - return 0; - } - *dotdot = '.'; + if (!cant_be_filename && !strcmp(arg, "..")) { + /* + * Just ".."? That is not a range but the + * pathspec for the parent directory. + */ + return -1; } - dotdot = strstr(arg, "^@"); - if (dotdot && !dotdot[2]) { - *dotdot = 0; + if (!handle_dotdot(arg, revs, flags, revarg_opt)) + return 0; + + mark = strstr(arg, "^@"); + if (mark && !mark[2]) { + *mark = 0; if (add_parents_only(revs, arg, flags, 0)) return 0; - *dotdot = '^'; + *mark = '^'; } - dotdot = strstr(arg, "^!"); - if (dotdot && !dotdot[2]) { - *dotdot = 0; + mark = strstr(arg, "^!"); + if (mark && !mark[2]) { + *mark = 0; if (!add_parents_only(revs, arg, flags ^ (UNINTERESTING | BOTTOM), 0)) - *dotdot = '^'; + *mark = '^'; } - dotdot = strstr(arg, "^-"); - if (dotdot) { + mark = strstr(arg, "^-"); + if (mark) { int exclude_parent = 1; - if (dotdot[2]) { + if (mark[2]) { char *end; - exclude_parent = strtoul(dotdot + 2, &end, 10); + exclude_parent = strtoul(mark + 2, &end, 10); if (*end != '\0' || !exclude_parent) return -1; } - *dotdot = 0; + *mark = 0; if (!add_parents_only(revs, arg, flags ^ (UNINTERESTING | BOTTOM), exclude_parent)) - *dotdot = '^'; + *mark = '^'; } local_flags = 0; @@@ -1600,7 -1566,7 +1600,7 @@@ } if (revarg_opt & REVARG_COMMITTISH) - get_sha1_flags = GET_SHA1_COMMITTISH; + get_sha1_flags |= GET_SHA1_COMMITTISH; if (get_sha1_with_context(arg, get_sha1_flags, oid.hash, &oc)) return revs->ignore_missing ? 0 : -1; @@@ -1608,8 -1574,7 +1608,8 @@@ verify_non_filename(revs->prefix, arg); object = get_reference(revs, arg, &oid, flags ^ local_flags); add_rev_cmdline(revs, object, arg_, REV_CMD_REV, flags ^ local_flags); - add_pending_object_with_mode(revs, object, arg, oc.mode); + add_pending_object_with_path(revs, object, arg, oc.mode, oc.path); + free(oc.path); return 0; } @@@ -2026,12 -1991,11 +2026,12 @@@ static int handle_revision_opt(struct r } else if (!strcmp(arg, "--extended-regexp") || !strcmp(arg, "-E")) { revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_ERE; } else if (!strcmp(arg, "--regexp-ignore-case") || !strcmp(arg, "-i")) { + revs->grep_filter.ignore_case = 1; revs->grep_filter.regflags |= REG_ICASE; DIFF_OPT_SET(&revs->diffopt, PICKAXE_IGNORE_CASE); } else if (!strcmp(arg, "--fixed-strings") || !strcmp(arg, "-F")) { revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_FIXED; - } else if (!strcmp(arg, "--perl-regexp")) { + } else if (!strcmp(arg, "--perl-regexp") || !strcmp(arg, "-P")) { revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_PCRE; } else if (!strcmp(arg, "--all-match")) { revs->grep_filter.all_match = 1; @@@ -2944,7 -2908,7 +2944,7 @@@ static int commit_match(struct commit * if (opt->show_notes) { if (!buf.len) strbuf_addstr(&buf, message); - format_display_notes(commit->object.oid.hash, &buf, encoding, 1); + format_display_notes(&commit->object.oid, &buf, encoding, 1); } /* diff --combined sequencer.c index 5282fb849c,7a114def84..d63099d50f --- a/sequencer.c +++ b/sequencer.c @@@ -464,8 -464,7 +464,8 @@@ static int do_recursive_merge(struct co if (active_cache_changed && write_locked_index(&the_index, &index_lock, COMMIT_LOCK)) - /* TRANSLATORS: %s will be "revert", "cherry-pick" or + /* + * TRANSLATORS: %s will be "revert", "cherry-pick" or * "rebase -i". */ return error(_("%s: Unable to write new index file"), @@@ -899,8 -898,8 +899,8 @@@ static void flush_rewritten_pending(voi FILE *out; if (strbuf_read_file(&buf, rebase_path_rewritten_pending(), 82) > 0 && - !get_sha1("HEAD", newsha1) && - (out = fopen(rebase_path_rewritten_list(), "a"))) { + !get_sha1("HEAD", newsha1) && + (out = fopen_or_warn(rebase_path_rewritten_list(), "a"))) { char *bol = buf.buf, *eol; while (*bol) { @@@ -919,7 -918,7 +919,7 @@@ static void record_in_rewritten(struct object_id *oid, enum todo_command next_command) { - FILE *out = fopen(rebase_path_rewritten_pending(), "a"); + FILE *out = fopen_or_warn(rebase_path_rewritten_pending(), "a"); if (!out) return; @@@ -1381,7 -1380,7 +1381,7 @@@ static int read_populate_todo(struct to if (is_rebase_i(opts)) { struct todo_list done = TODO_LIST_INIT; - FILE *f = fopen(rebase_path_msgtotal(), "w"); + FILE *f = fopen_or_warn(rebase_path_msgtotal(), "w"); if (strbuf_read_file(&done.buf, rebase_path_done(), 0) > 0 && !parse_insn_buffer(done.buf.buf, &done)) @@@ -2130,8 -2129,8 +2130,8 @@@ cleanup_head_ref if (read_oneliner(&buf, rebase_path_orig_head(), 0) && !get_sha1(buf.buf, orig.hash) && !get_sha1("HEAD", head.hash)) { - diff_tree_sha1(orig.hash, head.hash, - "", &log_tree_opt.diffopt); + diff_tree_oid(&orig, &head, "", + &log_tree_opt.diffopt); log_tree_diff_flush(&log_tree_opt); } }