diff options
| -rw-r--r-- | builtin/ls-files.c | 2 | ||||
| -rw-r--r-- | builtin/ls-tree.c | 2 | ||||
| -rw-r--r-- | cache.h | 5 | ||||
| -rw-r--r-- | dir.c | 36 | ||||
| -rw-r--r-- | dir.h | 9 | ||||
| -rw-r--r-- | tree-walk.c | 77 |
6 files changed, 120 insertions, 11 deletions
diff --git a/builtin/ls-files.c b/builtin/ls-files.c index b5434af0c8..4a9ee690c7 100644 --- a/builtin/ls-files.c +++ b/builtin/ls-files.c @@ -337,7 +337,7 @@ void overlay_tree_on_cache(const char *tree_name, const char *prefix) matchbuf[0] = prefix; matchbuf[1] = NULL; init_pathspec(&pathspec, matchbuf); - pathspec.items[0].use_wildcard = 0; + pathspec.items[0].nowildcard_len = pathspec.items[0].len; } else init_pathspec(&pathspec, NULL); if (read_tree(tree, 1, &pathspec)) diff --git a/builtin/ls-tree.c b/builtin/ls-tree.c index 235c17cc01..fb76e38d84 100644 --- a/builtin/ls-tree.c +++ b/builtin/ls-tree.c @@ -168,7 +168,7 @@ int cmd_ls_tree(int argc, const char **argv, const char *prefix) init_pathspec(&pathspec, get_pathspec(prefix, argv + 1)); for (i = 0; i < pathspec.nr; i++) - pathspec.items[i].use_wildcard = 0; + pathspec.items[i].nowildcard_len = pathspec.items[i].len; pathspec.has_wildcard = 0; tree = parse_tree_indirect(sha1); if (!tree) @@ -473,6 +473,8 @@ 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); +#define PATHSPEC_ONESTAR 1 /* the pathspec pattern sastisfies GFNM_ONESTAR */ + struct pathspec { const char **raw; /* get_pathspec() result, not freed by free_pathspec() */ int nr; @@ -482,7 +484,8 @@ struct pathspec { struct pathspec_item { const char *match; int len; - unsigned int use_wildcard:1; + int nowildcard_len; + int flags; } *items; }; @@ -34,6 +34,28 @@ int fnmatch_icase(const char *pattern, const char *string, int flags) return fnmatch(pattern, string, flags | (ignore_case ? FNM_CASEFOLD : 0)); } +inline int git_fnmatch(const char *pattern, const char *string, + int flags, int prefix) +{ + int fnm_flags = 0; + if (flags & GFNM_PATHNAME) + fnm_flags |= FNM_PATHNAME; + if (prefix > 0) { + if (strncmp(pattern, string, prefix)) + return FNM_NOMATCH; + pattern += prefix; + string += prefix; + } + if (flags & GFNM_ONESTAR) { + int pattern_len = strlen(++pattern); + int string_len = strlen(string); + return string_len < pattern_len || + strcmp(pattern, + string + string_len - pattern_len); + } + return fnmatch(pattern, string, fnm_flags); +} + static size_t common_prefix_len(const char **pathspec) { const char *n, *first; @@ -230,7 +252,10 @@ static int match_pathspec_item(const struct pathspec_item *item, int prefix, return MATCHED_RECURSIVELY; } - if (item->use_wildcard && !fnmatch(match, name, 0)) + if (item->nowildcard_len < item->len && + !git_fnmatch(match, name, + item->flags & PATHSPEC_ONESTAR ? GFNM_ONESTAR : 0, + item->nowildcard_len - prefix)) return MATCHED_FNMATCH; return 0; @@ -1429,9 +1454,14 @@ int init_pathspec(struct pathspec *pathspec, const char **paths) item->match = path; item->len = strlen(path); - item->use_wildcard = !no_wildcard(path); - if (item->use_wildcard) + item->nowildcard_len = simple_length(path); + item->flags = 0; + if (item->nowildcard_len < item->len) { pathspec->has_wildcard = 1; + if (path[item->nowildcard_len] == '*' && + no_wildcard(path + item->nowildcard_len + 1)) + item->flags |= PATHSPEC_ONESTAR; + } } qsort(pathspec->items, pathspec->nr, @@ -139,4 +139,13 @@ extern int strcmp_icase(const char *a, const char *b); extern int strncmp_icase(const char *a, const char *b, size_t count); extern int fnmatch_icase(const char *pattern, const char *string, int flags); +/* + * The prefix part of pattern must not contains wildcards. + */ +#define GFNM_PATHNAME 1 /* similar to FNM_PATHNAME */ +#define GFNM_ONESTAR 2 /* there is only _one_ wildcard, a star */ + +extern int git_fnmatch(const char *pattern, const char *string, + int flags, int prefix); + #endif diff --git a/tree-walk.c b/tree-walk.c index 3f54c02d76..6e30ef9d04 100644 --- a/tree-walk.c +++ b/tree-walk.c @@ -573,6 +573,54 @@ static int match_dir_prefix(const char *base, } /* + * Perform matching on the leading non-wildcard part of + * pathspec. item->nowildcard_len must be greater than zero. Return + * non-zero if base is matched. + */ +static int match_wildcard_base(const struct pathspec_item *item, + const char *base, int baselen, + int *matched) +{ + const char *match = item->match; + /* the wildcard part is not considered in this function */ + int matchlen = item->nowildcard_len; + + if (baselen) { + int dirlen; + /* + * Return early if base is longer than the + * non-wildcard part but it does not match. + */ + if (baselen >= matchlen) { + *matched = matchlen; + return !strncmp(base, match, matchlen); + } + + dirlen = matchlen; + while (dirlen && match[dirlen - 1] != '/') + dirlen--; + + /* + * Return early if base is shorter than the + * non-wildcard part but it does not match. Note that + * base ends with '/' so we are sure it really matches + * directory + */ + if (strncmp(base, match, baselen)) + return 0; + *matched = baselen; + } else + *matched = 0; + /* + * we could have checked entry against the non-wildcard part + * that is not in base and does similar never_interesting + * optimization as in match_entry. For now just be happy with + * base comparison. + */ + return entry_interesting; +} + +/* * Is a tree entry interesting given the pathspec we have? * * Pre-condition: either baselen == base_offset (i.e. empty path) @@ -602,7 +650,7 @@ enum interesting tree_entry_interesting(const struct name_entry *entry, 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; + int matchlen = item->len, matched = 0; if (baselen >= matchlen) { /* If it doesn't match, move along... */ @@ -626,8 +674,10 @@ enum interesting tree_entry_interesting(const struct name_entry *entry, &never_interesting)) return entry_interesting; - if (item->use_wildcard) { - if (!fnmatch(match + baselen, entry->path, 0)) + if (item->nowildcard_len < item->len) { + if (!git_fnmatch(match + baselen, entry->path, + item->flags & PATHSPEC_ONESTAR ? GFNM_ONESTAR : 0, + item->nowildcard_len - baselen)) return entry_interesting; /* @@ -642,17 +692,34 @@ enum interesting tree_entry_interesting(const struct name_entry *entry, } match_wildcards: - if (!item->use_wildcard) + if (item->nowildcard_len == item->len) continue; + if (item->nowildcard_len && + !match_wildcard_base(item, base_str, baselen, &matched)) + return entry_not_interesting; + /* * Concatenate base and entry->path into one and do * fnmatch() on it. + * + * While we could avoid concatenation in certain cases + * [1], which saves a memcpy and potentially a + * realloc, it turns out not worth it. Measurement on + * linux-2.6 does not show any clear improvements, + * partly because of the nowildcard_len optimization + * in git_fnmatch(). Avoid micro-optimizations here. + * + * [1] if match_wildcard_base() says the base + * directory is already matched, we only need to match + * the rest, which is shorter so _in theory_ faster. */ strbuf_add(base, entry->path, pathlen); - if (!fnmatch(match, base->buf + base_offset, 0)) { + if (!git_fnmatch(match, base->buf + base_offset, + item->flags & PATHSPEC_ONESTAR ? GFNM_ONESTAR : 0, + item->nowildcard_len)) { strbuf_setlen(base, base_offset + baselen); return entry_interesting; } |