diff options
| -rw-r--r-- | Documentation/glossary-content.txt | 23 | ||||
| -rw-r--r-- | builtin/add.c | 2 | ||||
| -rw-r--r-- | builtin/diff-files.c | 2 | ||||
| -rw-r--r-- | builtin/diff.c | 16 | ||||
| -rw-r--r-- | builtin/fast-export.c | 2 | ||||
| -rw-r--r-- | builtin/grep.c | 196 | ||||
| -rw-r--r-- | builtin/log.c | 2 | ||||
| -rw-r--r-- | builtin/update-index.c | 8 | ||||
| -rw-r--r-- | cache.h | 17 | ||||
| -rw-r--r-- | diff-lib.c | 6 | ||||
| -rw-r--r-- | diff-no-index.c | 13 | ||||
| -rw-r--r-- | diff.h | 4 | ||||
| -rw-r--r-- | dir.c | 151 | ||||
| -rw-r--r-- | dir.h | 4 | ||||
| -rw-r--r-- | preload-index.c | 5 | ||||
| -rw-r--r-- | read-cache.c | 25 | ||||
| -rw-r--r-- | revision.c | 21 | ||||
| -rw-r--r-- | revision.h | 2 | ||||
| -rwxr-xr-x | t/t4010-diff-pathspec.sh | 32 | ||||
| -rwxr-xr-x | t/t6004-rev-list-path-optim.sh | 69 | ||||
| -rwxr-xr-x | t/t7810-grep.sh | 18 | ||||
| -rw-r--r-- | tree-diff.c | 280 | ||||
| -rw-r--r-- | tree-walk.c | 184 | ||||
| -rw-r--r-- | tree-walk.h | 2 | ||||
| -rw-r--r-- | wt-status.c | 9 |
25 files changed, 649 insertions, 444 deletions
diff --git a/Documentation/glossary-content.txt b/Documentation/glossary-content.txt index f04b48ef0d..33716a31d0 100644 --- a/Documentation/glossary-content.txt +++ b/Documentation/glossary-content.txt @@ -273,6 +273,29 @@ This commit is referred to as a "merge commit", or sometimes just a <<def_pack,pack>>, to assist in efficiently accessing the contents of a pack. +[[def_pathspec]]pathspec:: + Pattern used to specify paths. ++ +Pathspecs are used on the command line of "git ls-files", "git +ls-tree", "git grep", "git checkout", and many other commands to +limit the scope of operations to some subset of the tree or +worktree. See the documentation of each command for whether +paths are relative to the current directory or toplevel. The +pathspec syntax is as follows: + +* any path matches itself +* the pathspec up to the last slash represents a + directory prefix. The scope of that pathspec is + limited to that subtree. +* the rest of the pathspec is a pattern for the remainder + of the pathname. Paths relative to the directory + prefix will be matched against that pattern using fnmatch(3); + in particular, '*' and '?' _can_ match directory separators. ++ +For example, Documentation/*.jpg will match all .jpg files +in the Documentation subtree, +including Documentation/chapter_1/figure_1.jpg. + [[def_parent]]parent:: A <<def_commit_object,commit object>> contains a (possibly empty) list of the logical predecessor(s) in the line of development, i.e. its diff --git a/builtin/add.c b/builtin/add.c index 5c9f4afef2..f7a17e43f6 100644 --- a/builtin/add.c +++ b/builtin/add.c @@ -86,7 +86,7 @@ int add_files_to_cache(const char *prefix, const char **pathspec, int flags) struct rev_info rev; init_revisions(&rev, prefix); setup_revisions(0, NULL, &rev, NULL); - rev.prune_data = pathspec; + init_pathspec(&rev.prune_data, pathspec); rev.diffopt.output_format = DIFF_FORMAT_CALLBACK; rev.diffopt.format_callback = update_callback; data.flags = flags; diff --git a/builtin/diff-files.c b/builtin/diff-files.c index 951c7c8994..46085f862f 100644 --- a/builtin/diff-files.c +++ b/builtin/diff-files.c @@ -61,7 +61,7 @@ int cmd_diff_files(int argc, const char **argv, const char *prefix) (rev.diffopt.output_format & DIFF_FORMAT_PATCH)) rev.combine_merges = rev.dense_combined_merges = 1; - if (read_cache_preload(rev.diffopt.paths) < 0) { + if (read_cache_preload(rev.diffopt.pathspec.raw) < 0) { perror("read_cache_preload"); return -1; } diff --git a/builtin/diff.c b/builtin/diff.c index 42822cd537..4c9deb28ec 100644 --- a/builtin/diff.c +++ b/builtin/diff.c @@ -135,7 +135,7 @@ static int builtin_diff_index(struct rev_info *revs, revs->max_count != -1 || revs->min_age != -1 || revs->max_age != -1) usage(builtin_diff_usage); - if (read_cache_preload(revs->diffopt.paths) < 0) { + if (read_cache_preload(revs->diffopt.pathspec.raw) < 0) { perror("read_cache_preload"); return -1; } @@ -237,7 +237,7 @@ static int builtin_diff_files(struct rev_info *revs, int argc, const char **argv revs->combine_merges = revs->dense_combined_merges = 1; setup_work_tree(); - if (read_cache_preload(revs->diffopt.paths) < 0) { + if (read_cache_preload(revs->diffopt.pathspec.raw) < 0) { perror("read_cache_preload"); return -1; } @@ -374,14 +374,10 @@ int cmd_diff(int argc, const char **argv, const char *prefix) } die("unhandled object '%s' given.", name); } - if (rev.prune_data) { - const char **pathspec = rev.prune_data; - while (*pathspec) { - if (!path) - path = *pathspec; - paths++; - pathspec++; - } + if (rev.prune_data.nr) { + if (!path) + path = rev.prune_data.items[0].match; + paths += rev.prune_data.nr; } /* diff --git a/builtin/fast-export.c b/builtin/fast-export.c index c8fd46b872..ba57457cc5 100644 --- a/builtin/fast-export.c +++ b/builtin/fast-export.c @@ -651,7 +651,7 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix) if (import_filename) import_marks(import_filename); - if (import_filename && revs.prune_data) + if (import_filename && revs.prune_data.nr) full_tree = 1; get_tags_and_duplicates(&revs.pending, &extra_refs); diff --git a/builtin/grep.c b/builtin/grep.c index fdf7131efd..c3af8760cc 100644 --- a/builtin/grep.c +++ b/builtin/grep.c @@ -329,106 +329,6 @@ static int grep_config(const char *var, const char *value, void *cb) return 0; } -/* - * Return non-zero if max_depth is negative or path has no more then max_depth - * slashes. - */ -static int accept_subdir(const char *path, int max_depth) -{ - if (max_depth < 0) - return 1; - - while ((path = strchr(path, '/')) != NULL) { - max_depth--; - if (max_depth < 0) - return 0; - path++; - } - return 1; -} - -/* - * Return non-zero if name is a subdirectory of match and is not too deep. - */ -static int is_subdir(const char *name, int namelen, - const char *match, int matchlen, int max_depth) -{ - if (matchlen > namelen || strncmp(name, match, matchlen)) - return 0; - - if (name[matchlen] == '\0') /* exact match */ - return 1; - - if (!matchlen || match[matchlen-1] == '/' || name[matchlen] == '/') - return accept_subdir(name + matchlen + 1, max_depth); - - return 0; -} - -/* - * git grep pathspecs are somewhat different from diff-tree pathspecs; - * pathname wildcards are allowed. - */ -static int pathspec_matches(const char **paths, const char *name, int max_depth) -{ - int namelen, i; - if (!paths || !*paths) - return accept_subdir(name, max_depth); - namelen = strlen(name); - for (i = 0; paths[i]; i++) { - const char *match = paths[i]; - int matchlen = strlen(match); - const char *cp, *meta; - - if (is_subdir(name, namelen, match, matchlen, max_depth)) - return 1; - if (!fnmatch(match, name, 0)) - return 1; - if (name[namelen-1] != '/') - continue; - - /* We are being asked if the directory ("name") is worth - * descending into. - * - * Find the longest leading directory name that does - * not have metacharacter in the pathspec; the name - * we are looking at must overlap with that directory. - */ - for (cp = match, meta = NULL; cp - match < matchlen; cp++) { - char ch = *cp; - if (ch == '*' || ch == '[' || ch == '?') { - meta = cp; - break; - } - } - if (!meta) - meta = cp; /* fully literal */ - - if (namelen <= meta - match) { - /* Looking at "Documentation/" and - * the pattern says "Documentation/howto/", or - * "Documentation/diff*.txt". The name we - * have should match prefix. - */ - if (!memcmp(match, name, namelen)) - return 1; - continue; - } - - if (meta - match < namelen) { - /* Looking at "Documentation/howto/" and - * the pattern says "Documentation/h*"; - * match up to "Do.../h"; this avoids descending - * into "Documentation/technical/". - */ - if (!memcmp(match, name, meta - match)) - return 1; - continue; - } - } - return 0; -} - static void *lock_and_read_sha1_file(const unsigned char *sha1, enum object_type *type, unsigned long *size) { void *data; @@ -581,7 +481,7 @@ static void run_pager(struct grep_opt *opt, const char *prefix) free(argv); } -static int grep_cache(struct grep_opt *opt, const char **paths, int cached) +static int grep_cache(struct grep_opt *opt, const struct pathspec *pathspec, int cached) { int hit = 0; int nr; @@ -591,7 +491,7 @@ static int grep_cache(struct grep_opt *opt, const char **paths, int cached) struct cache_entry *ce = active_cache[nr]; if (!S_ISREG(ce->ce_mode)) continue; - if (!pathspec_matches(paths, ce->name, opt->max_depth)) + if (!match_pathspec_depth(pathspec, ce->name, ce_namelen(ce), 0, NULL)) continue; /* * If CE_VALID is on, we assume worktree file and its cache entry @@ -618,44 +518,29 @@ static int grep_cache(struct grep_opt *opt, const char **paths, int cached) return hit; } -static int grep_tree(struct grep_opt *opt, const char **paths, - struct tree_desc *tree, - const char *tree_name, const char *base) +static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec, + struct tree_desc *tree, struct strbuf *base, int tn_len) { - int len; - int hit = 0; + int hit = 0, matched = 0; struct name_entry entry; - char *down; - int tn_len = strlen(tree_name); - struct strbuf pathbuf; - - strbuf_init(&pathbuf, PATH_MAX + tn_len); - - if (tn_len) { - strbuf_add(&pathbuf, tree_name, tn_len); - strbuf_addch(&pathbuf, ':'); - tn_len = pathbuf.len; - } - strbuf_addstr(&pathbuf, base); - len = pathbuf.len; + int old_baselen = base->len; while (tree_entry(tree, &entry)) { int te_len = tree_entry_len(entry.path, entry.sha1); - pathbuf.len = len; - strbuf_add(&pathbuf, entry.path, te_len); - - if (S_ISDIR(entry.mode)) - /* Match "abc/" against pathspec to - * decide if we want to descend into "abc" - * directory. - */ - strbuf_addch(&pathbuf, '/'); - - down = pathbuf.buf + tn_len; - if (!pathspec_matches(paths, down, opt->max_depth)) - ; - else if (S_ISREG(entry.mode)) - hit |= grep_sha1(opt, entry.sha1, pathbuf.buf, tn_len); + + if (matched != 2) { + matched = tree_entry_interesting(&entry, base, tn_len, pathspec); + if (matched == -1) + break; /* no more matches */ + if (!matched) + continue; + } + + strbuf_add(base, entry.path, te_len); + + if (S_ISREG(entry.mode)) { + hit |= grep_sha1(opt, entry.sha1, base->buf, tn_len); + } else if (S_ISDIR(entry.mode)) { enum object_type type; struct tree_desc sub; @@ -666,18 +551,21 @@ static int grep_tree(struct grep_opt *opt, const char **paths, if (!data) die("unable to read tree (%s)", sha1_to_hex(entry.sha1)); + + strbuf_addch(base, '/'); init_tree_desc(&sub, data, size); - hit |= grep_tree(opt, paths, &sub, tree_name, down); + hit |= grep_tree(opt, pathspec, &sub, base, tn_len); free(data); } + strbuf_setlen(base, old_baselen); + if (hit && opt->status_only) break; } - strbuf_release(&pathbuf); return hit; } -static int grep_object(struct grep_opt *opt, const char **paths, +static int grep_object(struct grep_opt *opt, const struct pathspec *pathspec, struct object *obj, const char *name) { if (obj->type == OBJ_BLOB) @@ -686,20 +574,30 @@ static int grep_object(struct grep_opt *opt, const char **paths, struct tree_desc tree; void *data; unsigned long size; - int hit; + struct strbuf base; + int hit, len; + data = read_object_with_reference(obj->sha1, tree_type, &size, NULL); if (!data) die("unable to read tree (%s)", sha1_to_hex(obj->sha1)); + + len = name ? strlen(name) : 0; + strbuf_init(&base, PATH_MAX + len + 1); + if (len) { + strbuf_add(&base, name, len); + strbuf_addch(&base, ':'); + } init_tree_desc(&tree, data, size); - hit = grep_tree(opt, paths, &tree, name, ""); + hit = grep_tree(opt, pathspec, &tree, &base, base.len); + strbuf_release(&base); free(data); return hit; } die("unable to grep from object of type %s", typename(obj->type)); } -static int grep_objects(struct grep_opt *opt, const char **paths, +static int grep_objects(struct grep_opt *opt, const struct pathspec *pathspec, const struct object_array *list) { unsigned int i; @@ -709,7 +607,7 @@ static int grep_objects(struct grep_opt *opt, const char **paths, for (i = 0; i < nr; i++) { struct object *real_obj; real_obj = deref_tag(list->objects[i].item, NULL, 0); - if (grep_object(opt, paths, real_obj, list->objects[i].name)) { + if (grep_object(opt, pathspec, real_obj, list->objects[i].name)) { hit = 1; if (opt->status_only) break; @@ -718,7 +616,7 @@ static int grep_objects(struct grep_opt *opt, const char **paths, return hit; } -static int grep_directory(struct grep_opt *opt, const char **paths) +static int grep_directory(struct grep_opt *opt, const struct pathspec *pathspec) { struct dir_struct dir; int i, hit = 0; @@ -726,7 +624,7 @@ static int grep_directory(struct grep_opt *opt, const char **paths) memset(&dir, 0, sizeof(dir)); setup_standard_excludes(&dir); - fill_directory(&dir, paths); + fill_directory(&dir, pathspec->raw); for (i = 0; i < dir.nr; i++) { hit |= grep_file(opt, dir.entries[i]->name); if (hit && opt->status_only) @@ -832,6 +730,7 @@ int cmd_grep(int argc, const char **argv, const char *prefix) struct grep_opt opt; struct object_array list = OBJECT_ARRAY_INIT; const char **paths = NULL; + struct pathspec pathspec; struct string_list path_list = STRING_LIST_INIT_NODUP; int i; int dummy; @@ -1059,6 +958,9 @@ int cmd_grep(int argc, const char **argv, const char *prefix) paths[0] = prefix; paths[1] = NULL; } + init_pathspec(&pathspec, paths); + pathspec.max_depth = opt.max_depth; + pathspec.recursive = 1; if (show_in_pager && (cached || list.nr)) die("--open-files-in-pager only works on the worktree"); @@ -1089,16 +991,16 @@ int cmd_grep(int argc, const char **argv, const char *prefix) die("--cached cannot be used with --no-index."); if (list.nr) die("--no-index cannot be used with revs."); - hit = grep_directory(&opt, paths); + hit = grep_directory(&opt, &pathspec); } else if (!list.nr) { if (!cached) setup_work_tree(); - hit = grep_cache(&opt, paths, cached); + hit = grep_cache(&opt, &pathspec, cached); } else { if (cached) die("both --cached and trees are given."); - hit = grep_objects(&opt, paths, &list); + hit = grep_objects(&opt, &pathspec, &list); } if (use_threads) diff --git a/builtin/log.c b/builtin/log.c index d8c6c28d2f..f5ed690c43 100644 --- a/builtin/log.c +++ b/builtin/log.c @@ -89,7 +89,7 @@ static void cmd_log_init(int argc, const char **argv, const char *prefix, rev->always_show_header = 0; if (DIFF_OPT_TST(&rev->diffopt, FOLLOW_RENAMES)) { rev->always_show_header = 0; - if (rev->diffopt.nr_paths != 1) + if (rev->diffopt.pathspec.nr != 1) usage("git logs can only follow renames on one pathname at a time"); } for (i = 1; i < argc; i++) { diff --git a/builtin/update-index.c b/builtin/update-index.c index 56baf27fb7..d7850c6309 100644 --- a/builtin/update-index.c +++ b/builtin/update-index.c @@ -546,7 +546,10 @@ static int do_reupdate(int ac, const char **av, */ int pos; int has_head = 1; - const char **pathspec = get_pathspec(prefix, av + 1); + const char **paths = get_pathspec(prefix, av + 1); + struct pathspec pathspec; + + init_pathspec(&pathspec, paths); if (read_ref("HEAD", head_sha1)) /* If there is no HEAD, that means it is an initial @@ -559,7 +562,7 @@ static int do_reupdate(int ac, const char **av, struct cache_entry *old = NULL; int save_nr; - if (ce_stage(ce) || !ce_path_match(ce, pathspec)) + if (ce_stage(ce) || !ce_path_match(ce, &pathspec)) continue; if (has_head) old = read_one_ent(NULL, head_sha1, @@ -578,6 +581,7 @@ static int do_reupdate(int ac, const char **av, if (save_nr != active_nr) goto redo; } + free_pathspec(&pathspec); return 0; } @@ -500,7 +500,22 @@ extern int index_name_is_other(const struct index_state *, const char *, int); extern int ie_match_stat(const struct index_state *, struct cache_entry *, struct stat *, unsigned int); extern int ie_modified(const struct index_state *, struct cache_entry *, struct stat *, unsigned int); -extern int ce_path_match(const struct cache_entry *ce, const char **pathspec); +struct pathspec { + const char **raw; /* get_pathspec() result, not freed by free_pathspec() */ + int nr; + int has_wildcard:1; + int recursive:1; + int max_depth; + struct pathspec_item { + const char *match; + int len; + int has_wildcard:1; + } *items; +}; + +extern int init_pathspec(struct pathspec *, const char **); +extern void free_pathspec(struct pathspec *); +extern int ce_path_match(const struct cache_entry *ce, const struct pathspec *pathspec); extern int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, enum object_type type, const char *path); extern int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object); extern void fill_stat_cache_info(struct cache_entry *ce, struct stat *st); diff --git a/diff-lib.c b/diff-lib.c index 392ce2bef0..1e22992cb1 100644 --- a/diff-lib.c +++ b/diff-lib.c @@ -106,7 +106,7 @@ int run_diff_files(struct rev_info *revs, unsigned int option) DIFF_OPT_TST(&revs->diffopt, HAS_CHANGES)) break; - if (!ce_path_match(ce, revs->prune_data)) + if (!ce_path_match(ce, &revs->prune_data)) continue; if (ce_stage(ce)) { @@ -427,7 +427,7 @@ static int oneway_diff(struct cache_entry **src, struct unpack_trees_options *o) if (tree == o->df_conflict_entry) tree = NULL; - if (ce_path_match(idx ? idx : tree, revs->prune_data)) + if (ce_path_match(idx ? idx : tree, &revs->prune_data)) do_oneway_diff(o, idx, tree); return 0; @@ -501,7 +501,7 @@ int do_diff_cache(const unsigned char *tree_sha1, struct diff_options *opt) active_nr = dst - active_cache; init_revisions(&revs, NULL); - revs.prune_data = opt->paths; + init_pathspec(&revs.prune_data, opt->pathspec.raw); tree = parse_tree_indirect(tree_sha1); if (!tree) die("bad tree object %s", sha1_to_hex(tree_sha1)); diff --git a/diff-no-index.c b/diff-no-index.c index ce9e783407..3a36144687 100644 --- a/diff-no-index.c +++ b/diff-no-index.c @@ -231,8 +231,9 @@ void diff_no_index(struct rev_info *revs, if (prefix) { int len = strlen(prefix); + const char *paths[3]; + memset(paths, 0, sizeof(paths)); - revs->diffopt.paths = xcalloc(2, sizeof(char *)); for (i = 0; i < 2; i++) { const char *p = argv[argc - 2 + i]; /* @@ -242,12 +243,12 @@ void diff_no_index(struct rev_info *revs, p = (strcmp(p, "-") ? xstrdup(prefix_filename(prefix, len, p)) : p); - revs->diffopt.paths[i] = p; + paths[i] = p; } + diff_tree_setup_paths(paths, &revs->diffopt); } else - revs->diffopt.paths = argv + argc - 2; - revs->diffopt.nr_paths = 2; + diff_tree_setup_paths(argv + argc - 2, &revs->diffopt); revs->diffopt.skip_stat_unmatch = 1; if (!revs->diffopt.output_format) revs->diffopt.output_format = DIFF_FORMAT_PATCH; @@ -259,8 +260,8 @@ void diff_no_index(struct rev_info *revs, if (diff_setup_done(&revs->diffopt) < 0) die("diff_setup_done failed"); - if (queue_diff(&revs->diffopt, revs->diffopt.paths[0], - revs->diffopt.paths[1])) + if (queue_diff(&revs->diffopt, revs->diffopt.pathspec.raw[0], + revs->diffopt.pathspec.raw[1])) exit(1); diff_set_mnemonic_prefix(&revs->diffopt, "1/", "2/"); diffcore_std(&revs->diffopt); @@ -133,9 +133,7 @@ struct diff_options { FILE *file; int close_file; - int nr_paths; - const char **paths; - int *pathlens; + struct pathspec pathspec; change_fn_t change; add_remove_fn_t add_remove; diff_format_fn_t format_callback; @@ -87,6 +87,21 @@ int fill_directory(struct dir_struct *dir, const char **pathspec) return len; } +int within_depth(const char *name, int namelen, + int depth, int max_depth) +{ + const char *cp = name, *cpe = name + namelen; + + while (cp < cpe) { + if (*cp++ != '/') + continue; + depth++; + if (depth > max_depth) + return 0; + } + return 1; +} + /* * Does 'match' match the given name? * A match is found if @@ -184,6 +199,95 @@ int match_pathspec(const char **pathspec, const char *name, int namelen, return retval; } +/* + * Does 'match' match the given name? + * A match is found if + * + * (1) the 'match' string is leading directory of 'name', or + * (2) the 'match' string is a wildcard and matches 'name', or + * (3) the 'match' string is exactly the same as 'name'. + * + * and the return value tells which case it was. + * + * It returns 0 when there is no match. + */ +static int match_pathspec_item(const struct pathspec_item *item, int prefix, + const char *name, int namelen) +{ + /* name/namelen has prefix cut off by caller */ + const char *match = item->match + prefix; + int matchlen = item->len - prefix; + + /* If the match was just the prefix, we matched */ + if (!*match) + return MATCHED_RECURSIVELY; + + if (matchlen <= namelen && !strncmp(match, name, matchlen)) { + if (matchlen == namelen) + return MATCHED_EXACTLY; + + if (match[matchlen-1] == '/' || name[matchlen] == '/') + return MATCHED_RECURSIVELY; + } + + if (item->has_wildcard && !fnmatch(match, name, 0)) + return MATCHED_FNMATCH; + + return 0; +} + +/* + * Given a name and a list of pathspecs, see if the name matches + * any of the pathspecs. The caller is also interested in seeing + * all pathspec matches some names it calls this function with + * (otherwise the user could have mistyped the unmatched pathspec), + * and a mark is left in seen[] array for pathspec element that + * actually matched anything. + */ +int match_pathspec_depth(const struct pathspec *ps, + const char *name, int namelen, + int prefix, char *seen) +{ + int i, retval = 0; + + if (!ps->nr) { + if (!ps->recursive || ps->max_depth == -1) + return MATCHED_RECURSIVELY; + + if (within_depth(name, namelen, 0, ps->max_depth)) + return MATCHED_EXACTLY; + else + return 0; + } + + name += prefix; + namelen -= prefix; + + for (i = ps->nr - 1; i >= 0; i--) { + int how; + if (seen && seen[i] == MATCHED_EXACTLY) + continue; + how = match_pathspec_item(ps->items+i, prefix, name, namelen); + if (ps->recursive && ps->max_depth != -1 && + how && how != MATCHED_FNMATCH) { + int len = ps->items[i].len; + if (name[len] == '/') + len++; + if (within_depth(name+len, namelen-len, 0, ps->max_depth)) + how = MATCHED_EXACTLY; + else + how = 0; + } + if (how) { + if (retval < how) + retval = how; + if (seen && seen[i] < how) + seen[i] = how; + } + } + return retval; +} + static int no_wildcard(const char *string) { return string[strcspn(string, "*?[{\\")] == '\0'; @@ -1151,3 +1255,50 @@ int remove_path(const char *name) return 0; } +static int pathspec_item_cmp(const void *a_, const void *b_) +{ + struct pathspec_item *a, *b; + + a = (struct pathspec_item *)a_; + b = (struct pathspec_item *)b_; + return strcmp(a->match, b->match); +} + +int init_pathspec(struct pathspec *pathspec, const char **paths) +{ + const char **p = paths; + int i; + + memset(pathspec, 0, sizeof(*pathspec)); + if (!p) + return 0; + while (*p) + p++; + pathspec->raw = paths; + pathspec->nr = p - paths; + if (!pathspec->nr) + return 0; + + pathspec->items = xmalloc(sizeof(struct pathspec_item)*pathspec->nr); + for (i = 0; i < pathspec->nr; i++) { + struct pathspec_item *item = pathspec->items+i; + const char *path = paths[i]; + + item->match = path; + item->len = strlen(path); + item->has_wildcard = !no_wildcard(path); + if (item->has_wildcard) + pathspec->has_wildcard = 1; + } + + qsort(pathspec->items, pathspec->nr, + sizeof(struct pathspec_item), pathspec_item_cmp); + + return 0; +} + +void free_pathspec(struct pathspec *pathspec) +{ + free(pathspec->items); + pathspec->items = NULL; +} @@ -65,6 +65,10 @@ struct dir_struct { #define MATCHED_FNMATCH 2 #define MATCHED_EXACTLY 3 extern int match_pathspec(const char **pathspec, const char *name, int namelen, int prefix, char *seen); +extern int match_pathspec_depth(const struct pathspec *pathspec, + const char *name, int namelen, + int prefix, char *seen); +extern int within_depth(const char *name, int namelen, int depth, int max_depth); extern int fill_directory(struct dir_struct *dir, const char **pathspec); extern int read_directory(struct dir_struct *, const char *path, int len, const char **pathspec); diff --git a/preload-index.c b/preload-index.c index e3d0bda31a..49cb08df96 100644 --- a/preload-index.c +++ b/preload-index.c @@ -35,7 +35,9 @@ static void *preload_thread(void *_data) struct index_state *index = p->index; struct cache_entry **cep = index->cache + p->offset; struct cache_def cache; + struct pathspec pathspec; + init_pathspec(&pathspec, p->pathspec); memset(&cache, 0, sizeof(cache)); nr = p->nr; if (nr + p->offset > index->cache_nr) @@ -51,7 +53,7 @@ static void *preload_thread(void *_data) continue; if (ce_uptodate(ce)) continue; - if (!ce_path_match(ce, p->pathspec)) + if (!ce_path_match(ce, &pathspec)) continue; if (threaded_has_symlink_leading_path(&cache, ce->name, ce_namelen(ce))) continue; @@ -61,6 +63,7 @@ static void *preload_thread(void *_data) continue; ce_mark_uptodate(ce); } while (--nr > 0); + free_pathspec(&pathspec); return NULL; } diff --git a/read-cache.c b/read-cache.c index 15b0a73b62..b97b5668eb 100644 --- a/read-cache.c +++ b/read-cache.c @@ -706,30 +706,9 @@ int ce_same_name(struct cache_entry *a, struct cache_entry *b) return ce_namelen(b) == len && !memcmp(a->name, b->name, len); } -int ce_path_match(const struct cache_entry *ce, const char **pathspec) +int ce_path_match(const struct cache_entry *ce, const struct pathspec *pathspec) { - const char *match, *name; - int len; - - if (!pathspec) - return 1; - - len = ce_namelen(ce); - name = ce->name; - while ((match = *pathspec++) != NULL) { - int matchlen = strlen(match); - if (matchlen > len) - continue; - if (memcmp(name, match, matchlen)) - continue; - if (matchlen && name[matchlen-1] == '/') - return 1; - if (name[matchlen] == '/' || !name[matchlen]) - return 1; - if (!matchlen) - return 1; - } - return 0; + return match_pathspec_depth(pathspec, ce->name, ce_namelen(ce), 0, NULL); } /* diff --git a/revision.c b/revision.c index 7b9eaefae4..86d2470489 100644 --- a/revision.c +++ b/revision.c @@ -323,7 +323,7 @@ static int rev_compare_tree(struct rev_info *revs, struct commit *parent, struct * tagged commit by specifying both --simplify-by-decoration * and pathspec. */ - if (!revs->prune_data) + if (!revs->prune_data.nr) return REV_TREE_SAME; } @@ -553,11 +553,7 @@ static void cherry_pick_list(struct commit_list *list, struct rev_info *revs) left_first = left_count < right_count; init_patch_ids(&ids); - if (revs->diffopt.nr_paths) { - ids.diffopts.nr_paths = revs->diffopt.nr_paths; - ids.diffopts.paths = revs->diffopt.paths; - ids.diffopts.pathlens = revs->diffopt.pathlens; - } + ids.diffopts.pathspec = revs->diffopt.pathspec; /* Compute patch-ids for one side */ for (p = list; p; p = p->next) { @@ -973,7 +969,7 @@ static void prepare_show_merge(struct rev_info *revs) struct cache_entry *ce = active_cache[i]; if (!ce_stage(ce)) continue; - if (ce_path_match(ce, revs->prune_data)) { + if (ce_path_match(ce, &revs->prune_data)) { prune_num++; prune = xrealloc(prune, sizeof(*prune) * prune_num); prune[prune_num-2] = ce->name; @@ -983,7 +979,8 @@ static void prepare_show_merge(struct rev_info *revs) ce_same_name(ce, active_cache[i+1])) i++; } - revs->prune_data = prune; + free_pathspec(&revs->prune_data); + init_pathspec(&revs->prune_data, prune); revs->limited = 1; } @@ -1620,7 +1617,7 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s } if (prune_data) - revs->prune_data = get_pathspec(revs->prefix, prune_data); + init_pathspec(&revs->prune_data, get_pathspec(revs->prefix, prune_data)); if (revs->def == NULL) revs->def = opt ? opt->def : NULL; @@ -1651,13 +1648,13 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s if (revs->topo_order) revs->limited = 1; - if (revs->prune_data) { - diff_tree_setup_paths(revs->prune_data, &revs->pruning); + if (revs->prune_data.nr) { + diff_tree_setup_paths(revs->prune_data.raw, &revs->pruning); /* Can't prune commits with rename following: the paths change.. */ if (!DIFF_OPT_TST(&revs->diffopt, FOLLOW_RENAMES)) revs->prune = 1; if (!revs->full_diff) - diff_tree_setup_paths(revs->prune_data, &revs->diffopt); + diff_tree_setup_paths(revs->prune_data.raw, &revs->diffopt); } if (revs->combine_merges) revs->ignore_merges = 0; diff --git a/revision.h b/revision.h index 05659c64ac..82509dd1d9 100644 --- a/revision.h +++ b/revision.h @@ -34,7 +34,7 @@ struct rev_info { /* Basic information */ const char *prefix; const char *def; - void *prune_data; + struct pathspec prune_data; unsigned int early_output; /* Traversal flags */ diff --git a/t/t4010-diff-pathspec.sh b/t/t4010-diff-pathspec.sh index 94df7ae53a..fbc8cd8f05 100755 --- a/t/t4010-diff-pathspec.sh +++ b/t/t4010-diff-pathspec.sh @@ -70,4 +70,36 @@ test_expect_success 'diff-tree pathspec' ' test_cmp expected current ' +EMPTY_TREE=4b825dc642cb6eb9a060e54bf8d69288fbee4904 + +test_expect_success 'diff-tree with wildcard shows dir also matches' ' + git diff-tree --name-only $EMPTY_TREE $tree -- "f*" >result && + echo file0 >expected && + test_cmp expected result +' + +test_expect_success 'diff-tree -r with wildcard' ' + git diff-tree -r --name-only $EMPTY_TREE $tree -- "*file1" >result && + echo path1/file1 >expected && + test_cmp expected result +' + +test_expect_success 'diff-tree with wildcard shows dir also matches' ' + git diff-tree --name-only $tree $tree2 -- "path1/f*" >result && + echo path1 >expected && + test_cmp expected result +' + +test_expect_success 'diff-tree -r with wildcard from beginning' ' + git diff-tree -r --name-only $tree $tree2 -- "path1/*file1" >result && + echo path1/file1 >expected && + test_cmp expected result +' + +test_expect_success 'diff-tree -r with wildcard' ' + git diff-tree -r --name-only $tree $tree2 -- "path1/f*" >result && + echo path1/file1 >expected && + test_cmp expected result +' + test_done diff --git a/t/t6004-rev-list-path-optim.sh b/t/t6004-rev-list-path-optim.sh index 5dabf1c5e3..3e8c42ee0b 100755 --- a/t/t6004-rev-list-path-optim.sh +++ b/t/t6004-rev-list-path-optim.sh @@ -1,51 +1,96 @@ #!/bin/sh -test_description='git rev-list trivial path optimization test' +test_description='git rev-list trivial path optimization test + + d/z1 + b0 b1 + o------------------------*----o master + / / + o---------o----o----o----o side + a0 c0 c1 a1 c2 + d/f0 d/f1 + d/z0 + +' . ./test-lib.sh test_expect_success setup ' -echo Hello > a && -git add a && -git commit -m "Initial commit" a && -initial=$(git rev-parse --verify HEAD) + echo Hello >a && + mkdir d && + echo World >d/f && + echo World >d/z && + git add a d && + test_tick && + git commit -m "Initial commit" && + git rev-parse --verify HEAD && + git tag initial ' test_expect_success path-optimization ' - commit=$(echo "Unchanged tree" | git commit-tree "HEAD^{tree}" -p HEAD) && - test $(git rev-list $commit | wc -l) = 2 && - test $(git rev-list $commit -- . | wc -l) = 1 + test_tick && + commit=$(echo "Unchanged tree" | git commit-tree "HEAD^{tree}" -p HEAD) && + test $(git rev-list $commit | wc -l) = 2 && + test $(git rev-list $commit -- . | wc -l) = 1 ' test_expect_success 'further setup' ' git checkout -b side && echo Irrelevant >c && - git add c && + echo Irrelevant >d/f && + git add c d/f && + test_tick && git commit -m "Side makes an irrelevant commit" && + git tag side_c0 && echo "More Irrelevancy" >c && git add c && + test_tick && git commit -m "Side makes another irrelevant commit" && echo Bye >a && git add a && + test_tick && git commit -m "Side touches a" && - side=$(git rev-parse --verify HEAD) && + git tag side_a1 && echo "Yet more Irrelevancy" >c && git add c && + test_tick && git commit -m "Side makes yet another irrelevant commit" && git checkout master && echo Another >b && - git add b && + echo Munged >d/z && + git add b d/z && + test_tick && git commit -m "Master touches b" && + git tag master_b0 && git merge side && echo Touched >b && git add b && + test_tick && git commit -m "Master touches b again" ' test_expect_success 'path optimization 2' ' - ( echo "$side"; echo "$initial" ) >expected && + git rev-parse side_a1 initial >expected && git rev-list HEAD -- a >actual && test_cmp expected actual ' +test_expect_success 'pathspec with leading path' ' + git rev-parse master^ master_b0 side_c0 initial >expected && + git rev-list HEAD -- d >actual && + test_cmp expected actual +' + +test_expect_success 'pathspec with glob (1)' ' + git rev-parse master^ master_b0 side_c0 initial >expected && + git rev-list HEAD -- "d/*" >actual && + test_cmp expected actual +' + +test_expect_success 'pathspec with glob (2)' ' + git rev-parse side_c0 initial >expected && + git rev-list HEAD -- "d/[a-m]*" >actual && + test_cmp expected actual +' + test_done diff --git a/t/t7810-grep.sh b/t/t7810-grep.sh index c8777589ca..8a7788dc39 100755 --- a/t/t7810-grep.sh +++ b/t/t7810-grep.sh @@ -182,6 +182,24 @@ do test_cmp expected actual ' + test_expect_success "grep --max-depth 0 -- . t $L" ' + { + echo ${HC}t/v:1:vvv + echo ${HC}v:1:vvv + } >expected && + git grep --max-depth 0 -n -e vvv $H -- . t >actual && + test_cmp expected actual + ' + + test_expect_success "grep --max-depth 0 -- t . $L" ' + { + echo ${HC}t/v:1:vvv + echo ${HC}v:1:vvv + } >expected && + git grep --max-depth 0 -n -e vvv $H -- t . >actual && + test_cmp expected actual + ' + done cat >expected <<EOF diff --git a/tree-diff.c b/tree-diff.c index 12c9a88884..3954281f50 100644 --- a/tree-diff.c +++ b/tree-diff.c @@ -6,34 +6,18 @@ #include "diffcore.h" #include "tree.h" -static char *malloc_base(const char *base, int baselen, const char *path, int pathlen) -{ - char *newbase = xmalloc(baselen + pathlen + 2); - memcpy(newbase, base, baselen); - memcpy(newbase + baselen, path, pathlen); - memcpy(newbase + baselen + pathlen, "/", 2); - return newbase; -} +static void show_entry(struct diff_options *opt, const char *prefix, + struct tree_desc *desc, struct strbuf *base); -static char *malloc_fullname(const char *base, int baselen, const char *path, int pathlen) -{ - char *fullname = xmalloc(baselen + pathlen + 1); - memcpy(fullname, base, baselen); - memcpy(fullname + baselen, path, pathlen); - fullname[baselen + pathlen] = 0; - return fullname; -} - -static void show_entry(struct diff_options *opt, const char *prefix, struct tree_desc *desc, - const char *base, int baselen); - -static int compare_tree_entry(struct tree_desc *t1, struct tree_desc *t2, const char *base, int baselen, struct diff_options *opt) +static int compare_tree_entry(struct tree_desc *t1, struct tree_desc *t2, + struct strbuf *base, struct diff_options *opt) { unsigned mode1, mode2; const char *path1, *path2; const unsigned char *sha1, *sha2; int cmp, pathlen1, pathlen2; - char *fullname; + int old_baselen = base->len; + int retval = 0; sha1 = tree_entry_extract(t1, &path1, &mode1); sha2 = tree_entry_extract(t2, &path2, &mode2); @@ -42,11 +26,11 @@ static int compare_tree_entry(struct tree_desc *t1, struct tree_desc *t2, const pathlen2 = tree_entry_len(path2, sha2); cmp = base_name_compare(path1, pathlen1, mode1, path2, pathlen2, mode2); if (cmp < 0) { - show_entry(opt, "-", t1, base, baselen); + show_entry(opt, "-", t1, base); return -1; } if (cmp > 0) { - show_entry(opt, "+", t2, base, baselen); + show_entry(opt, "+", t2, base); return 1; } if (!DIFF_OPT_TST(opt, FIND_COPIES_HARDER) && !hashcmp(sha1, sha2) && mode1 == mode2) @@ -57,149 +41,29 @@ static int compare_tree_entry(struct tree_desc *t1, struct tree_desc *t2, const * file, we need to consider it a remove and an add. */ if (S_ISDIR(mode1) != S_ISDIR(mode2)) { - show_entry(opt, "-", t1, base, baselen); - show_entry(opt, "+", t2, base, baselen); + show_entry(opt, "-", t1, base); + show_entry(opt, "+", t2, base); return 0; } + strbuf_add(base, path1, pathlen1); if (DIFF_OPT_TST(opt, RECURSIVE) && S_ISDIR(mode1)) { - int retval; - char *newbase = malloc_base(base, baselen, path1, pathlen1); if (DIFF_OPT_TST(opt, TREE_IN_RECURSIVE)) { - newbase[baselen + pathlen1] = 0; opt->change(opt, mode1, mode2, - sha1, sha2, newbase, 0, 0); - newbase[baselen + pathlen1] = '/'; + sha1, sha2, base->buf, 0, 0); } - retval = diff_tree_sha1(sha1, sha2, newbase, opt); - free(newbase); - return retval; + strbuf_addch(base, '/'); + retval = diff_tree_sha1(sha1, sha2, base->buf, opt); + } else { + opt->change(opt, mode1, mode2, sha1, sha2, base->buf, 0, 0); } - - fullname = malloc_fullname(base, baselen, path1, pathlen1); - opt->change(opt, mode1, mode2, sha1, sha2, fullname, 0, 0); - free(fullname); + strbuf_setlen(base, old_baselen); return 0; } -/* - * Is a tree entry interesting given the pathspec we have? - * - * Pre-condition: baselen == 0 || base[baselen-1] == '/' - * - * Return: - * - 2 for "yes, and all subsequent entries will be" - * - 1 for yes - * - zero for no - * - negative for "no, and no subsequent entries will be either" - */ -static int tree_entry_interesting(struct tree_desc *desc, const char *base, int baselen, struct diff_options *opt) -{ - const char *path; - const unsigned char *sha1; - unsigned mode; - int i; - int pathlen; - int never_interesting = -1; - - if (!opt->nr_paths) - return 2; - - sha1 = tree_entry_extract(desc, &path, &mode); - - pathlen = tree_entry_len(path, sha1); - - for (i = 0; i < opt->nr_paths; i++) { - const char *match = opt->paths[i]; - int matchlen = opt->pathlens[i]; - int m = -1; /* signals that we haven't called strncmp() */ - - if (baselen >= matchlen) { - /* If it doesn't match, move along... */ - if (strncmp(base, match, matchlen)) - continue; - - /* - * If the base is a subdirectory of a path which - * was specified, all of them are interesting. - */ - if (!matchlen || - base[matchlen] == '/' || - match[matchlen - 1] == '/') - return 2; - - /* Just a random prefix match */ - continue; - } - - /* Does the base match? */ - if (strncmp(base, match, baselen)) - continue; - - match += baselen; - matchlen -= baselen; - - if (never_interesting) { - /* - * We have not seen any match that sorts later - * than the current path. - */ - - /* - * Does match sort strictly earlier than path - * with their common parts? - */ - m = strncmp(match, path, - (matchlen < pathlen) ? matchlen : pathlen); - if (m < 0) - continue; - - /* - * If we come here even once, that means there is at - * least one pathspec that would sort equal to or - * later than the path we are currently looking at. - * In other words, if we have never reached this point - * after iterating all pathspecs, it means all - * pathspecs are either outside of base, or inside the - * base but sorts strictly earlier than the current - * one. In either case, they will never match the - * subsequent entries. In such a case, we initialized - * the variable to -1 and that is what will be - * returned, allowing the caller to terminate early. - */ - never_interesting = 0; - } - - if (pathlen > matchlen) - continue; - - if (matchlen > pathlen) { - if (match[pathlen] != '/') - continue; - if (!S_ISDIR(mode)) - continue; - } - - if (m == -1) - /* - * we cheated and did not do strncmp(), so we do - * that here. - */ - m = strncmp(match, path, pathlen); - - /* - * If common part matched earlier then it is a hit, - * because we rejected the case where path is not a - * leading directory and is shorter than match. - */ - if (!m) - return 1; - } - return never_interesting; /* No matches */ -} - /* A whole sub-tree went away or appeared */ -static void show_tree(struct diff_options *opt, const char *prefix, struct tree_desc *desc, const char *base, int baselen) +static void show_tree(struct diff_options *opt, const char *prefix, + struct tree_desc *desc, struct strbuf *base) { int all_interesting = 0; while (desc->size) { @@ -208,31 +72,32 @@ static void show_tree(struct diff_options *opt, const char *prefix, struct tree_ if (all_interesting) show = 1; else { - show = tree_entry_interesting(desc, base, baselen, - opt); + show = tree_entry_interesting(&desc->entry, base, 0, + &opt->pathspec); if (show == 2) all_interesting = 1; } if (show < 0) break; if (show) - show_entry(opt, prefix, desc, base, baselen); + show_entry(opt, prefix, desc, base); update_tree_entry(desc); } } /* A file entry went away or appeared */ -static void show_entry(struct diff_options *opt, const char *prefix, struct tree_desc *desc, - const char *base, int baselen) +static void show_entry(struct diff_options *opt, const char *prefix, + struct tree_desc *desc, struct strbuf *base) { unsigned mode; const char *path; const unsigned char *sha1 = tree_entry_extract(desc, &path, &mode); int pathlen = tree_entry_len(path, sha1); + int old_baselen = base->len; + strbuf_add(base, path, pathlen); if (DIFF_OPT_TST(opt, RECURSIVE) && S_ISDIR(mode)) { enum object_type type; - char *newbase = malloc_base(base, baselen, path, pathlen); struct tree_desc inner; void *tree; unsigned long size; @@ -241,28 +106,25 @@ static void show_entry(struct diff_options *opt, const char *prefix, struct tree if (!tree || type != OBJ_TREE) die("corrupt tree sha %s", sha1_to_hex(sha1)); - if (DIFF_OPT_TST(opt, TREE_IN_RECURSIVE)) { - newbase[baselen + pathlen] = 0; - opt->add_remove(opt, *prefix, mode, sha1, newbase, 0); - newbase[baselen + pathlen] = '/'; - } + if (DIFF_OPT_TST(opt, TREE_IN_RECURSIVE)) + opt->add_remove(opt, *prefix, mode, sha1, base->buf, 0); - init_tree_desc(&inner, tree, size); - show_tree(opt, prefix, &inner, newbase, baselen + 1 + pathlen); + strbuf_addch(base, '/'); + init_tree_desc(&inner, tree, size); + show_tree(opt, prefix, &inner, base); free(tree); - free(newbase); - } else { - char *fullname = malloc_fullname(base, baselen, path, pathlen); - opt->add_remove(opt, prefix[0], mode, sha1, fullname, 0); - free(fullname); - } + } else + opt->add_remove(opt, prefix[0], mode, sha1, base->buf, 0); + + strbuf_setlen(base, old_baselen); } -static void skip_uninteresting(struct tree_desc *t, const char *base, int baselen, struct diff_options *opt, int *all_interesting) +static void skip_uninteresting(struct tree_desc *t, struct strbuf *base, + struct diff_options *opt, int *all_interesting) { while (t->size) { - int show = tree_entry_interesting(t, base, baselen, opt); + int show = tree_entry_interesting(&t->entry, base, 0, &opt->pathspec); if (show == 2) *all_interesting = 1; if (!show) { @@ -276,37 +138,44 @@ static void skip_uninteresting(struct tree_desc *t, const char *base, int basele } } -int diff_tree(struct tree_desc *t1, struct tree_desc *t2, const char *base, struct diff_options *opt) +int diff_tree(struct tree_desc *t1, struct tree_desc *t2, + const char *base_str, struct diff_options *opt) { - int baselen = strlen(base); + struct strbuf base; + int baselen = strlen(base_str); int all_t1_interesting = 0; int all_t2_interesting = 0; + /* Enable recursion indefinitely */ + opt->pathspec.recursive = DIFF_OPT_TST(opt, RECURSIVE); + opt->pathspec.max_depth = -1; + + strbuf_init(&base, PATH_MAX); + strbuf_add(&base, base_str, baselen); + for (;;) { if (DIFF_OPT_TST(opt, QUICK) && DIFF_OPT_TST(opt, HAS_CHANGES)) break; - if (opt->nr_paths) { + if (opt->pathspec.nr) { if (!all_t1_interesting) - skip_uninteresting(t1, base, baselen, opt, - &all_t1_interesting); + skip_uninteresting(t1, &base, opt, &all_t1_interesting); if (!all_t2_interesting) - skip_uninteresting(t2, base, baselen, opt, - &all_t2_interesting); + skip_uninteresting(t2, &base, opt, &all_t2_interesting); } if (!t1->size) { if (!t2->size) break; - show_entry(opt, "+", t2, base, baselen); + show_entry(opt, "+", t2, &base); update_tree_entry(t2); continue; } if (!t2->size) { - show_entry(opt, "-", t1, base, baselen); + show_entry(opt, "-", t1, &base); update_tree_entry(t1); continue; } - switch (compare_tree_entry(t1, t2, base, baselen, opt)) { + switch (compare_tree_entry(t1, t2, &base, opt)) { case -1: update_tree_entry(t1); continue; @@ -319,6 +188,8 @@ int diff_tree(struct tree_desc *t1, struct tree_desc *t2, const char *base, stru } die("git diff-tree: internal error"); } + + strbuf_release(&base); return 0; } @@ -349,7 +220,7 @@ static void try_to_follow_renames(struct tree_desc *t1, struct tree_desc *t2, co DIFF_OPT_SET(&diff_opts, RECURSIVE); DIFF_OPT_SET(&diff_opts, FIND_COPIES_HARDER); diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; - diff_opts.single_follow = opt->paths[0]; + diff_opts.single_follow = opt->pathspec.raw[0]; diff_opts.break_opt = opt->break_opt; paths[0] = NULL; diff_tree_setup_paths(paths, &diff_opts); @@ -369,15 +240,16 @@ static void try_to_follow_renames(struct tree_desc *t1, struct tree_desc *t2, co * diff_queued_diff, we will also use that as the path in * the future! */ - if ((p->status == 'R' || p->status == 'C') && !strcmp(p->two->path, opt->paths[0])) { + if ((p->status == 'R' || p->status == 'C') && + !strcmp(p->two->path, opt->pathspec.raw[0])) { /* Switch the file-pairs around */ q->queue[i] = choice; choice = p; /* Update the path we use from now on.. */ diff_tree_release_paths(opt); - opt->paths[0] = xstrdup(p->one->path); - diff_tree_setup_paths(opt->paths, opt); + opt->pathspec.raw[0] = xstrdup(p->one->path); + diff_tree_setup_paths(opt->pathspec.raw, opt); /* * The caller expects us to return a set of vanilla @@ -452,36 +324,12 @@ int diff_root_tree_sha1(const unsigned char *new, const char *base, struct diff_ return retval; } -static int count_paths(const char **paths) -{ - int i = 0; - while (*paths++) - i++; - return i; -} - void diff_tree_release_paths(struct diff_options *opt) { - free(opt->pathlens); + free_pathspec(&opt->pathspec); } void diff_tree_setup_paths(const char **p, struct diff_options *opt) { - opt->nr_paths = 0; - opt->pathlens = NULL; - opt->paths = NULL; - - if (p) { - int i; - - opt->paths = p; - opt->nr_paths = count_paths(p); - if (opt->nr_paths == 0) { - opt->pathlens = NULL; - return; - } - opt->pathlens = xmalloc(opt->nr_paths * sizeof(int)); - for (i=0; i < opt->nr_paths; i++) - opt->pathlens[i] = strlen(p[i]); - } + init_pathspec(&opt->pathspec, p); } diff --git a/tree-walk.c b/tree-walk.c index a9bbf4e235..322becc3b4 100644 --- a/tree-walk.c +++ b/tree-walk.c @@ -1,6 +1,7 @@ #include "cache.h" #include "tree-walk.h" #include "unpack-trees.h" +#include "dir.h" #include "tree.h" static const char *get_mode(const char *str, unsigned int *modep) @@ -455,3 +456,186 @@ int get_tree_entry(const unsigned char *tree_sha1, const char *name, unsigned ch free(tree); return retval; } + +static int match_entry(const struct name_entry *entry, int pathlen, + const char *match, int matchlen, + int *never_interesting) +{ + int m = -1; /* signals that we haven't called strncmp() */ + + if (*never_interesting) { + /* + * We have not seen any match that sorts later + * than the current path. + */ + + /* + * Does match sort strictly earlier than path + * with their common parts? + */ + m = strncmp(match, entry->path, + (matchlen < pathlen) ? matchlen : pathlen); + if (m < 0) + return 0; + + /* + * If we come here even once, that means there is at + * least one pathspec that would sort equal to or + * later than the path we are currently looking at. + * In other words, if we have never reached this point + * after iterating all pathspecs, it means all + * pathspecs are either outside of base, or inside the + * base but sorts strictly earlier than the current + * one. In either case, they will never match the + * subsequent entries. In such a case, we initialized + * the variable to -1 and that is what will be + * returned, allowing the caller to terminate early. + */ + *never_interesting = 0; + } + + if (pathlen > matchlen) + return 0; + + if (matchlen > pathlen) { + if (match[pathlen] != '/') + return 0; + if (!S_ISDIR(entry->mode)) + return 0; + } + + if (m == -1) + /* + * we cheated and did not do strncmp(), so we do + * that here. + */ + m = strncmp(match, entry->path, pathlen); + + /* + * If common part matched earlier then it is a hit, + * because we rejected the case where path is not a + * leading directory and is shorter than match. + */ + if (!m) + return 1; + + return 0; +} + +static int match_dir_prefix(const char *base, int baselen, + const char *match, int matchlen) +{ + if (strncmp(base, match, matchlen)) + return 0; + + /* + * If the base is a subdirectory of a path which + * was specified, all of them are interesting. + */ + if (!matchlen || + base[matchlen] == '/' || + match[matchlen - 1] == '/') + return 1; + + /* Just a random prefix match */ + return 0; +} + +/* + * Is a tree entry interesting given the pathspec we have? + * + * Pre-condition: either baselen == base_offset (i.e. empty path) + * or base[baselen-1] == '/' (i.e. with trailing slash). + * + * Return: + * - 2 for "yes, and all subsequent entries will be" + * - 1 for yes + * - zero for no + * - negative for "no, and no subsequent entries will be either" + */ +int tree_entry_interesting(const struct name_entry *entry, + struct strbuf *base, int base_offset, + const struct pathspec *ps) +{ + int i; + int pathlen, baselen = base->len - base_offset; + int never_interesting = ps->has_wildcard ? 0 : -1; + + if (!ps->nr) { + if (!ps->recursive || ps->max_depth == -1) + return 2; + return !!within_depth(base->buf + base_offset, baselen, + !!S_ISDIR(entry->mode), + ps->max_depth); + } + + pathlen = tree_entry_len(entry->path, entry->sha1); + + for (i = ps->nr - 1; i >= 0; i--) { + const struct pathspec_item *item = ps->items+i; + const char *match = item->match; + const char *base_str = base->buf + base_offset; + int matchlen = item->len; + + if (baselen >= matchlen) { + /* If it doesn't match, move along... */ + if (!match_dir_prefix(base_str, baselen, match, matchlen)) + goto match_wildcards; + + if (!ps->recursive || ps->max_depth == -1) + return 2; + + return !!within_depth(base_str + matchlen + 1, + baselen - matchlen - 1, + !!S_ISDIR(entry->mode), + ps->max_depth); + } + + /* Does the base match? */ + if (!strncmp(base_str, match, baselen)) { + if (match_entry(entry, pathlen, + match + baselen, matchlen - baselen, + &never_interesting)) + return 1; + + if (ps->items[i].has_wildcard) { + if (!fnmatch(match + baselen, entry->path, 0)) + return 1; + + /* + * Match all directories. We'll try to + * match files later on. + */ + if (ps->recursive && S_ISDIR(entry->mode)) + return 1; + } + + continue; + } + +match_wildcards: + if (!ps->items[i].has_wildcard) + continue; + + /* + * Concatenate base and entry->path into one and do + * fnmatch() on it. + */ + + strbuf_add(base, entry->path, pathlen); + + if (!fnmatch(match, base->buf + base_offset, 0)) { + strbuf_setlen(base, base_offset + baselen); + return 1; + } + strbuf_setlen(base, base_offset + baselen); + + /* + * Match all directories. We'll try to match files + * later on. + */ + if (ps->recursive && S_ISDIR(entry->mode)) + return 1; + } + return never_interesting; /* No matches */ +} diff --git a/tree-walk.h b/tree-walk.h index 7e3e0b5ad1..39524b7dba 100644 --- a/tree-walk.h +++ b/tree-walk.h @@ -60,4 +60,6 @@ static inline int traverse_path_len(const struct traverse_info *info, const stru return info->pathlen + tree_entry_len(n->path, n->sha1); } +extern int tree_entry_interesting(const struct name_entry *, struct strbuf *, int, const struct pathspec *ps); + #endif diff --git a/wt-status.c b/wt-status.c index 123582b6cb..a82b11d341 100644 --- a/wt-status.c +++ b/wt-status.c @@ -323,7 +323,7 @@ static void wt_status_collect_changes_worktree(struct wt_status *s) } rev.diffopt.format_callback = wt_status_collect_changed_cb; rev.diffopt.format_callback_data = s; - rev.prune_data = s->pathspec; + init_pathspec(&rev.prune_data, s->pathspec); run_diff_files(&rev, 0); } @@ -348,20 +348,22 @@ static void wt_status_collect_changes_index(struct wt_status *s) rev.diffopt.detect_rename = 1; rev.diffopt.rename_limit = 200; rev.diffopt.break_opt = 0; - rev.prune_data = s->pathspec; + init_pathspec(&rev.prune_data, s->pathspec); run_diff_index(&rev, 1); } static void wt_status_collect_changes_initial(struct wt_status *s) { + struct pathspec pathspec; int i; + init_pathspec(&pathspec, s->pathspec); for (i = 0; i < active_nr; i++) { struct string_list_item *it; struct wt_status_change_data *d; struct cache_entry *ce = active_cache[i]; - if (!ce_path_match(ce, s->pathspec)) + if (!ce_path_match(ce, &pathspec)) continue; it = string_list_insert(&s->change, ce->name); d = it->util; @@ -376,6 +378,7 @@ static void wt_status_collect_changes_initial(struct wt_status *s) else d->index_status = DIFF_STATUS_ADDED; } + free_pathspec(&pathspec); } static void wt_status_collect_untracked(struct wt_status *s) |