#include "cache.h"
#include "dir.h"
#include "refs.h"
+#include "wildmatch.h"
struct path_simplify {
int len;
int fill_directory(struct dir_struct *dir, const char **pathspec)
{
- const char *path;
size_t len;
/*
* use that to optimize the directory walk
*/
len = common_prefix_len(pathspec);
- path = "";
-
- if (len)
- path = xmemdupz(*pathspec, len);
/* Read the directory and prune it */
- read_directory(dir, path, len, pathspec);
- if (*path)
- free((char *)path);
+ read_directory(dir, pathspec ? *pathspec : "", len, pathspec);
return len;
}
return retval;
}
+/*
+ * Return the length of the "simple" part of a path match limiter.
+ */
+static int simple_length(const char *match)
+{
+ int len = -1;
+
+ for (;;) {
+ unsigned char c = *match++;
+ len++;
+ if (c == '\0' || is_glob_special(c))
+ return len;
+ }
+}
+
static int no_wildcard(const char *string)
{
- return string[strcspn(string, "*?[{\\")] == '\0';
+ return string[simple_length(string)] == '\0';
+}
+
+void parse_exclude_pattern(const char **pattern,
+ int *patternlen,
+ int *flags,
+ int *nowildcardlen)
+{
+ const char *p = *pattern;
+ size_t i, len;
+
+ *flags = 0;
+ if (*p == '!') {
+ *flags |= EXC_FLAG_NEGATIVE;
+ p++;
+ }
+ len = strlen(p);
+ if (len && p[len - 1] == '/') {
+ len--;
+ *flags |= EXC_FLAG_MUSTBEDIR;
+ }
+ for (i = 0; i < len; i++) {
+ if (p[i] == '/')
+ break;
+ }
+ if (i == len)
+ *flags |= EXC_FLAG_NODIR;
+ *nowildcardlen = simple_length(p);
+ /*
+ * we should have excluded the trailing slash from 'p' too,
+ * but that's one more allocation. Instead just make sure
+ * nowildcardlen does not exceed real patternlen
+ */
+ if (*nowildcardlen > len)
+ *nowildcardlen = len;
+ if (*p == '*' && no_wildcard(p + 1))
+ *flags |= EXC_FLAG_ENDSWITH;
+ *pattern = p;
+ *patternlen = len;
}
void add_exclude(const char *string, const char *base,
int baselen, struct exclude_list *which)
{
struct exclude *x;
- size_t len;
- int to_exclude = 1;
- int flags = 0;
+ int patternlen;
+ int flags;
+ int nowildcardlen;
- if (*string == '!') {
- to_exclude = 0;
- string++;
- }
- len = strlen(string);
- if (len && string[len - 1] == '/') {
+ parse_exclude_pattern(&string, &patternlen, &flags, &nowildcardlen);
+ if (flags & EXC_FLAG_MUSTBEDIR) {
char *s;
- x = xmalloc(sizeof(*x) + len);
+ x = xmalloc(sizeof(*x) + patternlen + 1);
s = (char *)(x+1);
- memcpy(s, string, len - 1);
- s[len - 1] = '\0';
- string = s;
+ memcpy(s, string, patternlen);
+ s[patternlen] = '\0';
x->pattern = s;
- flags = EXC_FLAG_MUSTBEDIR;
} else {
x = xmalloc(sizeof(*x));
x->pattern = string;
}
- x->to_exclude = to_exclude;
- x->patternlen = strlen(string);
+ x->patternlen = patternlen;
+ x->nowildcardlen = nowildcardlen;
x->base = base;
x->baselen = baselen;
x->flags = flags;
- if (!strchr(string, '/'))
- x->flags |= EXC_FLAG_NODIR;
- if (no_wildcard(string))
- x->flags |= EXC_FLAG_NOWILDCARD;
- if (*string == '*' && no_wildcard(string+1))
- x->flags |= EXC_FLAG_ENDSWITH;
ALLOC_GROW(which->excludes, which->nr + 1, which->alloc);
which->excludes[which->nr++] = x;
}
dir->basebuf[baselen] = '\0';
}
+int match_basename(const char *basename, int basenamelen,
+ const char *pattern, int prefix, int patternlen,
+ int flags)
+{
+ if (prefix == patternlen) {
+ if (!strcmp_icase(pattern, basename))
+ return 1;
+ } else if (flags & EXC_FLAG_ENDSWITH) {
+ if (patternlen - 1 <= basenamelen &&
+ !strcmp_icase(pattern + 1,
+ basename + basenamelen - patternlen + 1))
+ return 1;
+ } else {
+ if (fnmatch_icase(pattern, basename, 0) == 0)
+ return 1;
+ }
+ return 0;
+}
+
+int match_pathname(const char *pathname, int pathlen,
+ const char *base, int baselen,
+ const char *pattern, int prefix, int patternlen,
+ int flags)
+{
+ const char *name;
+ int namelen;
+
+ /*
+ * match with FNM_PATHNAME; the pattern has base implicitly
+ * in front of it.
+ */
+ if (*pattern == '/') {
+ pattern++;
+ prefix--;
+ }
+
+ /*
+ * baselen does not count the trailing slash. base[] may or
+ * may not end with a trailing slash though.
+ */
+ if (pathlen < baselen + 1 ||
+ (baselen && pathname[baselen] != '/') ||
+ strncmp_icase(pathname, base, baselen))
+ return 0;
+
+ namelen = baselen ? pathlen - baselen - 1 : pathlen;
+ name = pathname + pathlen - namelen;
+
+ if (prefix) {
+ /*
+ * if the non-wildcard part is longer than the
+ * remaining pathname, surely it cannot match.
+ */
+ if (prefix > namelen)
+ return 0;
+
+ if (strncmp_icase(pattern, name, prefix))
+ return 0;
+ pattern += prefix;
+ name += prefix;
+ namelen -= prefix;
+ }
+
+ return wildmatch(pattern, name,
+ ignore_case ? WM_CASEFOLD : 0,
+ NULL) == 0;
+}
+
/* Scan the list and let the last match determine the fate.
* Return 1 for exclude, 0 for include and -1 for undecided.
*/
{
int i;
- if (el->nr) {
- for (i = el->nr - 1; 0 <= i; i--) {
- struct exclude *x = el->excludes[i];
- const char *exclude = x->pattern;
- int to_exclude = x->to_exclude;
-
- if (x->flags & EXC_FLAG_MUSTBEDIR) {
- if (*dtype == DT_UNKNOWN)
- *dtype = get_dtype(NULL, pathname, pathlen);
- if (*dtype != DT_DIR)
- continue;
- }
+ if (!el->nr)
+ return -1; /* undefined */
- if (x->flags & EXC_FLAG_NODIR) {
- /* match basename */
- if (x->flags & EXC_FLAG_NOWILDCARD) {
- if (!strcmp_icase(exclude, basename))
- return to_exclude;
- } else if (x->flags & EXC_FLAG_ENDSWITH) {
- if (x->patternlen - 1 <= pathlen &&
- !strcmp_icase(exclude + 1, pathname + pathlen - x->patternlen + 1))
- return to_exclude;
- } else {
- if (fnmatch_icase(exclude, basename, 0) == 0)
- return to_exclude;
- }
- }
- else {
- /* match with FNM_PATHNAME:
- * exclude has base (baselen long) implicitly
- * in front of it.
- */
- int baselen = x->baselen;
- if (*exclude == '/')
- exclude++;
-
- if (pathlen < baselen ||
- (baselen && pathname[baselen-1] != '/') ||
- strncmp_icase(pathname, x->base, baselen))
- continue;
-
- if (x->flags & EXC_FLAG_NOWILDCARD) {
- if (!strcmp_icase(exclude, pathname + baselen))
- return to_exclude;
- } else {
- if (fnmatch_icase(exclude, pathname+baselen,
- FNM_PATHNAME) == 0)
- return to_exclude;
- }
- }
+ for (i = el->nr - 1; 0 <= i; i--) {
+ struct exclude *x = el->excludes[i];
+ const char *exclude = x->pattern;
+ int to_exclude = x->flags & EXC_FLAG_NEGATIVE ? 0 : 1;
+ int prefix = x->nowildcardlen;
+
+ if (x->flags & EXC_FLAG_MUSTBEDIR) {
+ if (*dtype == DT_UNKNOWN)
+ *dtype = get_dtype(NULL, pathname, pathlen);
+ if (*dtype != DT_DIR)
+ continue;
}
+
+ if (x->flags & EXC_FLAG_NODIR) {
+ if (match_basename(basename,
+ pathlen - (basename - pathname),
+ exclude, prefix, x->patternlen,
+ x->flags))
+ return to_exclude;
+ continue;
+ }
+
+ assert(x->baselen == 0 || x->base[x->baselen - 1] == '/');
+ if (match_pathname(pathname, pathlen,
+ x->base, x->baselen ? x->baselen - 1 : 0,
+ exclude, prefix, x->patternlen, x->flags))
+ return to_exclude;
}
return -1; /* undecided */
}
-int excluded(struct dir_struct *dir, const char *pathname, int *dtype_p)
+static int excluded(struct dir_struct *dir, const char *pathname, int *dtype_p)
{
int pathlen = strlen(pathname);
int st;
return 0;
}
+void path_exclude_check_init(struct path_exclude_check *check,
+ struct dir_struct *dir)
+{
+ check->dir = dir;
+ strbuf_init(&check->path, 256);
+}
+
+void path_exclude_check_clear(struct path_exclude_check *check)
+{
+ strbuf_release(&check->path);
+}
+
+/*
+ * Is this name excluded? This is for a caller like show_files() that
+ * do not honor directory hierarchy and iterate through paths that are
+ * possibly in an ignored directory.
+ *
+ * A path to a directory known to be excluded is left in check->path to
+ * optimize for repeated checks for files in the same excluded directory.
+ */
+int path_excluded(struct path_exclude_check *check,
+ const char *name, int namelen, int *dtype)
+{
+ int i;
+ struct strbuf *path = &check->path;
+
+ /*
+ * we allow the caller to pass namelen as an optimization; it
+ * must match the length of the name, as we eventually call
+ * excluded() on the whole name string.
+ */
+ if (namelen < 0)
+ namelen = strlen(name);
+
+ if (path->len &&
+ path->len <= namelen &&
+ !memcmp(name, path->buf, path->len) &&
+ (!name[path->len] || name[path->len] == '/'))
+ return 1;
+
+ strbuf_setlen(path, 0);
+ for (i = 0; name[i]; i++) {
+ int ch = name[i];
+
+ if (ch == '/') {
+ int dt = DT_DIR;
+ if (excluded(check->dir, path->buf, &dt))
+ return 1;
+ }
+ strbuf_addch(path, ch);
+ }
+
+ /* An entry in the index; cannot be a directory with subentries */
+ strbuf_setlen(path, 0);
+
+ return excluded(check->dir, name, dtype);
+}
+
static struct dir_entry *dir_entry_new(const char *pathname, int len)
{
struct dir_entry *ent;
};
static enum path_treatment treat_one_path(struct dir_struct *dir,
- char *path, int *len,
+ struct strbuf *path,
const struct path_simplify *simplify,
int dtype, struct dirent *de)
{
- int exclude = excluded(dir, path, &dtype);
+ int exclude = excluded(dir, path->buf, &dtype);
if (exclude && (dir->flags & DIR_COLLECT_IGNORED)
- && exclude_matches_pathspec(path, *len, simplify))
- dir_add_ignored(dir, path, *len);
+ && exclude_matches_pathspec(path->buf, path->len, simplify))
+ dir_add_ignored(dir, path->buf, path->len);
/*
* Excluded? If we don't explicitly want to show
return path_ignored;
if (dtype == DT_UNKNOWN)
- dtype = get_dtype(de, path, *len);
+ dtype = get_dtype(de, path->buf, path->len);
/*
* Do we want to see just the ignored files?
default:
return path_ignored;
case DT_DIR:
- memcpy(path + *len, "/", 2);
- (*len)++;
- switch (treat_directory(dir, path, *len, simplify)) {
+ strbuf_addch(path, '/');
+ switch (treat_directory(dir, path->buf, path->len, simplify)) {
case show_directory:
if (exclude != !!(dir->flags
& DIR_SHOW_IGNORED))
static enum path_treatment treat_path(struct dir_struct *dir,
struct dirent *de,
- char *path, int path_max,
+ struct strbuf *path,
int baselen,
- const struct path_simplify *simplify,
- int *len)
+ const struct path_simplify *simplify)
{
int dtype;
if (is_dot_or_dotdot(de->d_name) || !strcmp(de->d_name, ".git"))
return path_ignored;
- *len = strlen(de->d_name);
- /* Ignore overly long pathnames! */
- if (*len + baselen + 8 > path_max)
- return path_ignored;
- memcpy(path + baselen, de->d_name, *len + 1);
- *len += baselen;
- if (simplify_away(path, *len, simplify))
+ strbuf_setlen(path, baselen);
+ strbuf_addstr(path, de->d_name);
+ if (simplify_away(path->buf, path->len, simplify))
return path_ignored;
dtype = DTYPE(de);
- return treat_one_path(dir, path, len, simplify, dtype, de);
+ return treat_one_path(dir, path, simplify, dtype, de);
}
/*
int check_only,
const struct path_simplify *simplify)
{
- DIR *fdir = opendir(*base ? base : ".");
+ DIR *fdir;
int contents = 0;
struct dirent *de;
- char path[PATH_MAX + 1];
+ struct strbuf path = STRBUF_INIT;
- if (!fdir)
- return 0;
+ strbuf_add(&path, base, baselen);
- memcpy(path, base, baselen);
+ fdir = opendir(path.len ? path.buf : ".");
+ if (!fdir)
+ goto out;
while ((de = readdir(fdir)) != NULL) {
- int len;
- switch (treat_path(dir, de, path, sizeof(path),
- baselen, simplify, &len)) {
+ switch (treat_path(dir, de, &path, baselen, simplify)) {
case path_recurse:
- contents += read_directory_recursive(dir, path, len, 0, simplify);
+ contents += read_directory_recursive(dir, path.buf,
+ path.len, 0,
+ simplify);
continue;
case path_ignored:
continue;
}
contents++;
if (check_only)
- goto exit_early;
- else
- dir_add_name(dir, path, len);
+ break;
+ dir_add_name(dir, path.buf, path.len);
}
-exit_early:
closedir(fdir);
+ out:
+ strbuf_release(&path);
return contents;
}
e2->name, e2->len);
}
-/*
- * Return the length of the "simple" part of a path match limiter.
- */
-static int simple_length(const char *match)
-{
- int len = -1;
-
- for (;;) {
- unsigned char c = *match++;
- len++;
- if (c == '\0' || is_glob_special(c))
- return len;
- }
-}
-
static struct path_simplify *create_simplify(const char **pathspec)
{
int nr, alloc = 0;
const char *path, int len,
const struct path_simplify *simplify)
{
- char pathbuf[PATH_MAX];
- int baselen, blen;
+ struct strbuf sb = STRBUF_INIT;
+ int baselen, rc = 0;
const char *cp;
while (len && path[len - 1] == '/')
baselen = len;
else
baselen = cp - path;
- memcpy(pathbuf, path, baselen);
- pathbuf[baselen] = '\0';
- if (!is_directory(pathbuf))
- return 0;
- if (simplify_away(pathbuf, baselen, simplify))
- return 0;
- blen = baselen;
- if (treat_one_path(dir, pathbuf, &blen, simplify,
+ strbuf_setlen(&sb, 0);
+ strbuf_add(&sb, path, baselen);
+ if (!is_directory(sb.buf))
+ break;
+ if (simplify_away(sb.buf, sb.len, simplify))
+ break;
+ if (treat_one_path(dir, &sb, simplify,
DT_DIR, NULL) == path_ignored)
- return 0; /* do not recurse into it */
- if (len <= baselen)
- return 1; /* finished checking */
+ break; /* do not recurse into it */
+ if (len <= baselen) {
+ rc = 1;
+ break; /* finished checking */
+ }
}
+ strbuf_release(&sb);
+ return rc;
}
int read_directory(struct dir_struct *dir, const char *path, int len, const char **pathspec)