* Junio Hamano, 2005-2006
*/
#include "cache.h"
+#include "config.h"
#include "dir.h"
+#include "object-store.h"
+#include "attr.h"
#include "refs.h"
+#include "wildmatch.h"
+#include "pathspec.h"
+#include "utf8.h"
+#include "varint.h"
+#include "ewah/ewok.h"
+#include "fsmonitor.h"
+#include "submodule-config.h"
-struct path_simplify {
- int len;
- const char *path;
+/*
+ * Tells read_directory_recursive how a file or directory should be treated.
+ * Values are ordered by significance, e.g. if a directory contains both
+ * excluded and untracked files, it is listed as untracked because
+ * path_untracked > path_excluded.
+ */
+enum path_treatment {
+ path_none = 0,
+ path_recurse,
+ path_excluded,
+ path_untracked
};
-static int read_directory_recursive(struct dir_struct *dir, const char *path, int len,
- int check_only, const struct path_simplify *simplify);
-static int get_dtype(struct dirent *de, const char *path, int len);
+/*
+ * Support data structure for our opendir/readdir/closedir wrappers
+ */
+struct cached_dir {
+ DIR *fdir;
+ struct untracked_cache_dir *untracked;
+ int nr_files;
+ int nr_dirs;
+
+ const char *d_name;
+ int d_type;
+ const char *file;
+ struct untracked_cache_dir *ucd;
+};
-/* helper string functions with support for the ignore_case flag */
-int strcmp_icase(const char *a, const char *b)
+static enum path_treatment read_directory_recursive(struct dir_struct *dir,
+ struct index_state *istate, const char *path, int len,
+ struct untracked_cache_dir *untracked,
+ int check_only, int stop_at_first_file, const struct pathspec *pathspec);
+static int resolve_dtype(int dtype, struct index_state *istate,
+ const char *path, int len);
+
+int count_slashes(const char *s)
+{
+ int cnt = 0;
+ while (*s)
+ if (*s++ == '/')
+ cnt++;
+ return cnt;
+}
+
+int fspathcmp(const char *a, const char *b)
{
return ignore_case ? strcasecmp(a, b) : strcmp(a, b);
}
-int strncmp_icase(const char *a, const char *b, size_t count)
+int fspathncmp(const char *a, const char *b, size_t count)
{
return ignore_case ? strncasecmp(a, b, count) : strncmp(a, b, count);
}
-int fnmatch_icase(const char *pattern, const char *string, int flags)
+int git_fnmatch(const struct pathspec_item *item,
+ const char *pattern, const char *string,
+ int prefix)
+{
+ if (prefix > 0) {
+ if (ps_strncmp(item, pattern, string, prefix))
+ return WM_NOMATCH;
+ pattern += prefix;
+ string += prefix;
+ }
+ if (item->flags & PATHSPEC_ONESTAR) {
+ int pattern_len = strlen(++pattern);
+ int string_len = strlen(string);
+ return string_len < pattern_len ||
+ ps_strcmp(item, pattern,
+ string + string_len - pattern_len);
+ }
+ if (item->magic & PATHSPEC_GLOB)
+ return wildmatch(pattern, string,
+ WM_PATHNAME |
+ (item->magic & PATHSPEC_ICASE ? WM_CASEFOLD : 0));
+ else
+ /* wildmatch has not learned no FNM_PATHNAME mode yet */
+ return wildmatch(pattern, string,
+ item->magic & PATHSPEC_ICASE ? WM_CASEFOLD : 0);
+}
+
+static int fnmatch_icase_mem(const char *pattern, int patternlen,
+ const char *string, int stringlen,
+ int flags)
{
- return fnmatch(pattern, string, flags | (ignore_case ? FNM_CASEFOLD : 0));
+ int match_status;
+ struct strbuf pat_buf = STRBUF_INIT;
+ struct strbuf str_buf = STRBUF_INIT;
+ const char *use_pat = pattern;
+ const char *use_str = string;
+
+ if (pattern[patternlen]) {
+ strbuf_add(&pat_buf, pattern, patternlen);
+ use_pat = pat_buf.buf;
+ }
+ if (string[stringlen]) {
+ strbuf_add(&str_buf, string, stringlen);
+ use_str = str_buf.buf;
+ }
+
+ if (ignore_case)
+ flags |= WM_CASEFOLD;
+ match_status = wildmatch(use_pat, use_str, flags);
+
+ strbuf_release(&pat_buf);
+ strbuf_release(&str_buf);
+
+ return match_status;
}
-static size_t common_prefix_len(const char **pathspec)
+static size_t common_prefix_len(const struct pathspec *pathspec)
{
- const char *n, *first;
+ int n;
size_t max = 0;
- if (!pathspec)
- return max;
-
- first = *pathspec;
- while ((n = *pathspec++)) {
- size_t i, len = 0;
- for (i = 0; first == n || i < max; i++) {
- char c = n[i];
- if (!c || c != first[i] || is_glob_special(c))
+ /*
+ * ":(icase)path" is treated as a pathspec full of
+ * wildcard. In other words, only prefix is considered common
+ * prefix. If the pathspec is abc/foo abc/bar, running in
+ * subdir xyz, the common prefix is still xyz, not xyz/abc as
+ * in non-:(icase).
+ */
+ GUARD_PATHSPEC(pathspec,
+ PATHSPEC_FROMTOP |
+ PATHSPEC_MAXDEPTH |
+ PATHSPEC_LITERAL |
+ PATHSPEC_GLOB |
+ PATHSPEC_ICASE |
+ PATHSPEC_EXCLUDE |
+ PATHSPEC_ATTR);
+
+ for (n = 0; n < pathspec->nr; n++) {
+ size_t i = 0, len = 0, item_len;
+ if (pathspec->items[n].magic & PATHSPEC_EXCLUDE)
+ continue;
+ if (pathspec->items[n].magic & PATHSPEC_ICASE)
+ item_len = pathspec->items[n].prefix;
+ else
+ item_len = pathspec->items[n].nowildcard_len;
+ while (i < item_len && (n == 0 || i < max)) {
+ char c = pathspec->items[n].match[i];
+ if (c != pathspec->items[0].match[i])
break;
if (c == '/')
len = i + 1;
+ i++;
}
- if (first == n || len < max) {
+ if (n == 0 || len < max) {
max = len;
if (!max)
break;
* Returns a copy of the longest leading path common among all
* pathspecs.
*/
-char *common_prefix(const char **pathspec)
+char *common_prefix(const struct pathspec *pathspec)
{
unsigned long len = common_prefix_len(pathspec);
- return len ? xmemdupz(*pathspec, len) : NULL;
+ return len ? xmemdupz(pathspec->items[0].match, len) : NULL;
}
-int fill_directory(struct dir_struct *dir, const char **pathspec)
+int fill_directory(struct dir_struct *dir,
+ struct index_state *istate,
+ const struct pathspec *pathspec)
{
- const char *path;
- size_t len;
+ const char *prefix;
+ size_t prefix_len;
/*
* Calculate common prefix for the pathspec, and
* use that to optimize the directory walk
*/
- len = common_prefix_len(pathspec);
- path = "";
-
- if (len)
- path = xmemdupz(*pathspec, len);
+ prefix_len = common_prefix_len(pathspec);
+ prefix = prefix_len ? pathspec->items[0].match : "";
/* Read the directory and prune it */
- read_directory(dir, path, len, pathspec);
- if (*path)
- free((char *)path);
- return len;
+ read_directory(dir, istate, prefix, prefix_len, pathspec);
+
+ return prefix_len;
}
int within_depth(const char *name, int namelen,
}
/*
- * Does 'match' match the given name?
- * A match is found if
+ * Read the contents of the blob with the given OID into a buffer.
+ * Append a trailing LF to the end if the last line doesn't have one.
*
- * (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'.
+ * Returns:
+ * -1 when the OID is invalid or unknown or does not refer to a blob.
+ * 0 when the blob is empty.
+ * 1 along with { data, size } of the (possibly augmented) buffer
+ * when successful.
*
- * and the return value tells which case it was.
- *
- * It returns 0 when there is no match.
+ * Optionally updates the given oid_stat with the given OID (when valid).
*/
-static int match_one(const char *match, const char *name, int namelen)
+static int do_read_blob(const struct object_id *oid, struct oid_stat *oid_stat,
+ size_t *size_out, char **data_out)
{
- int matchlen;
+ enum object_type type;
+ unsigned long sz;
+ char *data;
- /* If the match was just the prefix, we matched */
- if (!*match)
- return MATCHED_RECURSIVELY;
+ *size_out = 0;
+ *data_out = NULL;
- if (ignore_case) {
- for (;;) {
- unsigned char c1 = tolower(*match);
- unsigned char c2 = tolower(*name);
- if (c1 == '\0' || is_glob_special(c1))
- break;
- if (c1 != c2)
- return 0;
- match++;
- name++;
- namelen--;
- }
- } else {
- for (;;) {
- unsigned char c1 = *match;
- unsigned char c2 = *name;
- if (c1 == '\0' || is_glob_special(c1))
- break;
- if (c1 != c2)
- return 0;
- match++;
- name++;
- namelen--;
- }
+ data = read_object_file(oid, &type, &sz);
+ if (!data || type != OBJ_BLOB) {
+ free(data);
+ return -1;
}
+ if (oid_stat) {
+ memset(&oid_stat->stat, 0, sizeof(oid_stat->stat));
+ oidcpy(&oid_stat->oid, oid);
+ }
- /*
- * If we don't match the matchstring exactly,
- * we need to match by fnmatch
- */
- matchlen = strlen(match);
- if (strncmp_icase(match, name, matchlen))
- return !fnmatch_icase(match, name, 0) ? MATCHED_FNMATCH : 0;
-
- if (namelen == matchlen)
- return MATCHED_EXACTLY;
- if (match[matchlen-1] == '/' || name[matchlen] == '/')
- return MATCHED_RECURSIVELY;
- 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(const char **pathspec, const char *name, int namelen,
- int prefix, char *seen)
-{
- int i, retval = 0;
+ if (sz == 0) {
+ free(data);
+ return 0;
+ }
- if (!pathspec)
- return 1;
+ if (data[sz - 1] != '\n') {
+ data = xrealloc(data, st_add(sz, 1));
+ data[sz++] = '\n';
+ }
- name += prefix;
- namelen -= prefix;
+ *size_out = xsize_t(sz);
+ *data_out = data;
- for (i = 0; pathspec[i] != NULL; i++) {
- int how;
- const char *match = pathspec[i] + prefix;
- if (seen && seen[i] == MATCHED_EXACTLY)
- continue;
- how = match_one(match, name, namelen);
- if (how) {
- if (retval < how)
- retval = how;
- if (seen && seen[i] < how)
- seen[i] = how;
- }
- }
- return retval;
+ return 1;
}
+#define DO_MATCH_EXCLUDE (1<<0)
+#define DO_MATCH_DIRECTORY (1<<1)
+#define DO_MATCH_LEADING_PATHSPEC (1<<2)
+
/*
- * Does 'match' match the given name?
- * A match is found if
+ * Does the given pathspec match the given name? A match is found if
+ *
+ * (1) the pathspec string is leading directory of 'name' ("RECURSIVELY"), or
+ * (2) the pathspec string has a leading part matching 'name' ("LEADING"), or
+ * (3) the pathspec string is a wildcard and matches 'name' ("WILDCARD"), or
+ * (4) the pathspec string is exactly the same as 'name' ("EXACT").
*
- * (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'.
+ * Return value tells which case it was (1-4), or 0 when there is no match.
*
- * and the return value tells which case it was.
+ * It may be instructive to look at a small table of concrete examples
+ * to understand the differences between 1, 2, and 4:
*
- * It returns 0 when there is no match.
+ * Pathspecs
+ * | a/b | a/b/ | a/b/c
+ * ------+-----------+-----------+------------
+ * a/b | EXACT | EXACT[1] | LEADING[2]
+ * Names a/b/ | RECURSIVE | EXACT | LEADING[2]
+ * a/b/c | RECURSIVE | RECURSIVE | EXACT
+ *
+ * [1] Only if DO_MATCH_DIRECTORY is passed; otherwise, this is NOT a match.
+ * [2] Only if DO_MATCH_LEADING_PATHSPEC is passed; otherwise, not a match.
*/
-static int match_pathspec_item(const struct pathspec_item *item, int prefix,
- const char *name, int namelen)
+static int match_pathspec_item(const struct index_state *istate,
+ const struct pathspec_item *item, int prefix,
+ const char *name, int namelen, unsigned flags)
{
/* name/namelen has prefix cut off by caller */
const char *match = item->match + prefix;
int matchlen = item->len - prefix;
+ /*
+ * The normal call pattern is:
+ * 1. prefix = common_prefix_len(ps);
+ * 2. prune something, or fill_directory
+ * 3. match_pathspec()
+ *
+ * 'prefix' at #1 may be shorter than the command's prefix and
+ * it's ok for #2 to match extra files. Those extras will be
+ * trimmed at #3.
+ *
+ * Suppose the pathspec is 'foo' and '../bar' running from
+ * subdir 'xyz'. The common prefix at #1 will be empty, thanks
+ * to "../". We may have xyz/foo _and_ XYZ/foo after #2. The
+ * user does not want XYZ/foo, only the "foo" part should be
+ * case-insensitive. We need to filter out XYZ/foo here. In
+ * other words, we do not trust the caller on comparing the
+ * prefix part when :(icase) is involved. We do exact
+ * comparison ourselves.
+ *
+ * Normally the caller (common_prefix_len() in fact) does
+ * _exact_ matching on name[-prefix+1..-1] and we do not need
+ * to check that part. Be defensive and check it anyway, in
+ * case common_prefix_len is changed, or a new caller is
+ * introduced that does not use common_prefix_len.
+ *
+ * If the penalty turns out too high when prefix is really
+ * long, maybe change it to
+ * strncmp(match, name, item->prefix - prefix)
+ */
+ if (item->prefix && (item->magic & PATHSPEC_ICASE) &&
+ strncmp(item->match, name - prefix, item->prefix))
+ return 0;
+
+ if (item->attr_match_nr &&
+ !match_pathspec_attrs(istate, name, namelen, item))
+ return 0;
+
/* If the match was just the prefix, we matched */
if (!*match)
return MATCHED_RECURSIVELY;
- if (matchlen <= namelen && !strncmp(match, name, matchlen)) {
+ if (matchlen <= namelen && !ps_strncmp(item, match, name, matchlen)) {
if (matchlen == namelen)
return MATCHED_EXACTLY;
if (match[matchlen-1] == '/' || name[matchlen] == '/')
return MATCHED_RECURSIVELY;
- }
+ } else if ((flags & DO_MATCH_DIRECTORY) &&
+ match[matchlen - 1] == '/' &&
+ namelen == matchlen - 1 &&
+ !ps_strncmp(item, match, name, namelen))
+ return MATCHED_EXACTLY;
- if (item->use_wildcard && !fnmatch(match, name, 0))
+ if (item->nowildcard_len < item->len &&
+ !git_fnmatch(item, match, name,
+ item->nowildcard_len - prefix))
return MATCHED_FNMATCH;
+ /* Perform checks to see if "name" is a leading string of the pathspec */
+ if (flags & DO_MATCH_LEADING_PATHSPEC) {
+ /* name is a literal prefix of the pathspec */
+ int offset = name[namelen-1] == '/' ? 1 : 0;
+ if ((namelen < matchlen) &&
+ (match[namelen-offset] == '/') &&
+ !ps_strncmp(item, match, name, namelen))
+ return MATCHED_RECURSIVELY_LEADING_PATHSPEC;
+
+ /* name doesn't match up to the first wild character */
+ if (item->nowildcard_len < item->len &&
+ ps_strncmp(item, match, name,
+ item->nowildcard_len - prefix))
+ return 0;
+
+ /*
+ * name has no wildcard, and it didn't match as a leading
+ * pathspec so return.
+ */
+ if (item->nowildcard_len == item->len)
+ return 0;
+
+ /*
+ * Here is where we would perform a wildmatch to check if
+ * "name" can be matched as a directory (or a prefix) against
+ * the pathspec. Since wildmatch doesn't have this capability
+ * at the present we have to punt and say that it is a match,
+ * potentially returning a false positive
+ * The submodules themselves will be able to perform more
+ * accurate matching to determine if the pathspec matches.
+ */
+ return MATCHED_RECURSIVELY_LEADING_PATHSPEC;
+ }
+
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.
+ * Given a name and a list of pathspecs, returns the nature of the
+ * closest (i.e. most specific) match of the name to any of the
+ * pathspecs.
+ *
+ * The caller typically calls this multiple times with the same
+ * pathspec and seen[] array but with different name/namelen
+ * (e.g. entries from the index) and is interested in seeing if and
+ * how each pathspec matches all the names it calls this function
+ * with. A mark is left in the seen[] array for each pathspec element
+ * indicating the closest type of match that element achieved, so if
+ * seen[n] remains zero after multiple invocations, that means the nth
+ * pathspec did not match any names, which could indicate that the
+ * user mistyped the nth pathspec.
*/
-int match_pathspec_depth(const struct pathspec *ps,
- const char *name, int namelen,
- int prefix, char *seen)
+static int do_match_pathspec(const struct index_state *istate,
+ const struct pathspec *ps,
+ const char *name, int namelen,
+ int prefix, char *seen,
+ unsigned flags)
{
- int i, retval = 0;
+ int i, retval = 0, exclude = flags & DO_MATCH_EXCLUDE;
+
+ GUARD_PATHSPEC(ps,
+ PATHSPEC_FROMTOP |
+ PATHSPEC_MAXDEPTH |
+ PATHSPEC_LITERAL |
+ PATHSPEC_GLOB |
+ PATHSPEC_ICASE |
+ PATHSPEC_EXCLUDE |
+ PATHSPEC_ATTR);
if (!ps->nr) {
- if (!ps->recursive || ps->max_depth == -1)
+ if (!ps->recursive ||
+ !(ps->magic & PATHSPEC_MAXDEPTH) ||
+ ps->max_depth == -1)
return MATCHED_RECURSIVELY;
if (within_depth(name, namelen, 0, ps->max_depth))
for (i = ps->nr - 1; i >= 0; i--) {
int how;
+
+ if ((!exclude && ps->items[i].magic & PATHSPEC_EXCLUDE) ||
+ ( exclude && !(ps->items[i].magic & PATHSPEC_EXCLUDE)))
+ continue;
+
if (seen && seen[i] == MATCHED_EXACTLY)
continue;
- how = match_pathspec_item(ps->items+i, prefix, name, namelen);
- if (ps->recursive && ps->max_depth != -1 &&
+ /*
+ * Make exclude patterns optional and never report
+ * "pathspec ':(exclude)foo' matches no files"
+ */
+ if (seen && ps->items[i].magic & PATHSPEC_EXCLUDE)
+ seen[i] = MATCHED_FNMATCH;
+ how = match_pathspec_item(istate, ps->items+i, prefix, name,
+ namelen, flags);
+ if (ps->recursive &&
+ (ps->magic & PATHSPEC_MAXDEPTH) &&
+ ps->max_depth != -1 &&
how && how != MATCHED_FNMATCH) {
int len = ps->items[i].len;
if (name[len] == '/')
return retval;
}
-static int no_wildcard(const char *string)
+int match_pathspec(const struct index_state *istate,
+ const struct pathspec *ps,
+ const char *name, int namelen,
+ int prefix, char *seen, int is_dir)
+{
+ int positive, negative;
+ unsigned flags = is_dir ? DO_MATCH_DIRECTORY : 0;
+ positive = do_match_pathspec(istate, ps, name, namelen,
+ prefix, seen, flags);
+ if (!(ps->magic & PATHSPEC_EXCLUDE) || !positive)
+ return positive;
+ negative = do_match_pathspec(istate, ps, name, namelen,
+ prefix, seen,
+ flags | DO_MATCH_EXCLUDE);
+ return negative ? 0 : positive;
+}
+
+/**
+ * Check if a submodule is a superset of the pathspec
+ */
+int submodule_path_match(const struct index_state *istate,
+ const struct pathspec *ps,
+ const char *submodule_name,
+ char *seen)
+{
+ int matched = do_match_pathspec(istate, ps, submodule_name,
+ strlen(submodule_name),
+ 0, seen,
+ DO_MATCH_DIRECTORY |
+ DO_MATCH_LEADING_PATHSPEC);
+ return matched;
+}
+
+int report_path_error(const char *ps_matched,
+ const struct pathspec *pathspec)
{
- return string[strcspn(string, "*?[{\\")] == '\0';
+ /*
+ * Make sure all pathspec matched; otherwise it is an error.
+ */
+ int num, errors = 0;
+ for (num = 0; num < pathspec->nr; num++) {
+ int other, found_dup;
+
+ if (ps_matched[num])
+ continue;
+ /*
+ * The caller might have fed identical pathspec
+ * twice. Do not barf on such a mistake.
+ * FIXME: parse_pathspec should have eliminated
+ * duplicate pathspec.
+ */
+ for (found_dup = other = 0;
+ !found_dup && other < pathspec->nr;
+ other++) {
+ if (other == num || !ps_matched[other])
+ continue;
+ if (!strcmp(pathspec->items[other].original,
+ pathspec->items[num].original))
+ /*
+ * Ok, we have a match already.
+ */
+ found_dup = 1;
+ }
+ if (found_dup)
+ continue;
+
+ error(_("pathspec '%s' did not match any file(s) known to git"),
+ pathspec->items[num].original);
+ errors++;
+ }
+ return errors;
}
-void add_exclude(const char *string, const char *base,
- int baselen, struct exclude_list *which)
+/*
+ * Return the length of the "simple" part of a path match limiter.
+ */
+int simple_length(const char *match)
{
- struct exclude *x;
- size_t len;
- int to_exclude = 1;
- int flags = 0;
+ int len = -1;
- if (*string == '!') {
- to_exclude = 0;
- string++;
+ for (;;) {
+ unsigned char c = *match++;
+ len++;
+ if (c == '\0' || is_glob_special(c))
+ return len;
}
- len = strlen(string);
- if (len && string[len - 1] == '/') {
- char *s;
- x = xmalloc(sizeof(*x) + len);
- s = (char *)(x+1);
- memcpy(s, string, len - 1);
- s[len - 1] = '\0';
- string = s;
- x->pattern = s;
- flags = EXC_FLAG_MUSTBEDIR;
+}
+
+int no_wildcard(const char *string)
+{
+ return string[simple_length(string)] == '\0';
+}
+
+void parse_path_pattern(const char **pattern,
+ int *patternlen,
+ unsigned *flags,
+ int *nowildcardlen)
+{
+ const char *p = *pattern;
+ size_t i, len;
+
+ *flags = 0;
+ if (*p == '!') {
+ *flags |= PATTERN_FLAG_NEGATIVE;
+ p++;
+ }
+ len = strlen(p);
+ if (len && p[len - 1] == '/') {
+ len--;
+ *flags |= PATTERN_FLAG_MUSTBEDIR;
+ }
+ for (i = 0; i < len; i++) {
+ if (p[i] == '/')
+ break;
+ }
+ if (i == len)
+ *flags |= PATTERN_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 |= PATTERN_FLAG_ENDSWITH;
+ *pattern = p;
+ *patternlen = len;
+}
+
+int pl_hashmap_cmp(const void *unused_cmp_data,
+ const struct hashmap_entry *a,
+ const struct hashmap_entry *b,
+ const void *key)
+{
+ const struct pattern_entry *ee1 =
+ container_of(a, struct pattern_entry, ent);
+ const struct pattern_entry *ee2 =
+ container_of(b, struct pattern_entry, ent);
+
+ size_t min_len = ee1->patternlen <= ee2->patternlen
+ ? ee1->patternlen
+ : ee2->patternlen;
+
+ if (ignore_case)
+ return strncasecmp(ee1->pattern, ee2->pattern, min_len);
+ return strncmp(ee1->pattern, ee2->pattern, min_len);
+}
+
+static void add_pattern_to_hashsets(struct pattern_list *pl, struct path_pattern *given)
+{
+ struct pattern_entry *translated;
+ char *truncated;
+ char *data = NULL;
+
+ if (!pl->use_cone_patterns)
+ return;
+
+ if (given->flags & PATTERN_FLAG_NEGATIVE &&
+ given->flags & PATTERN_FLAG_MUSTBEDIR &&
+ !strcmp(given->pattern, "/*")) {
+ pl->full_cone = 0;
+ return;
+ }
+
+ if (!given->flags && !strcmp(given->pattern, "/*")) {
+ pl->full_cone = 1;
+ return;
+ }
+
+ if (given->patternlen > 2 &&
+ !strcmp(given->pattern + given->patternlen - 2, "/*")) {
+ if (!(given->flags & PATTERN_FLAG_NEGATIVE)) {
+ /* Not a cone pattern. */
+ pl->use_cone_patterns = 0;
+ warning(_("unrecognized pattern: '%s'"), given->pattern);
+ goto clear_hashmaps;
+ }
+
+ truncated = xstrdup(given->pattern);
+ truncated[given->patternlen - 2] = 0;
+
+ translated = xmalloc(sizeof(struct pattern_entry));
+ translated->pattern = truncated;
+ translated->patternlen = given->patternlen - 2;
+ hashmap_entry_init(&translated->ent,
+ ignore_case ?
+ strihash(translated->pattern) :
+ strhash(translated->pattern));
+
+ if (!hashmap_get_entry(&pl->recursive_hashmap,
+ translated, ent, NULL)) {
+ /* We did not see the "parent" included */
+ warning(_("unrecognized negative pattern: '%s'"),
+ given->pattern);
+ free(truncated);
+ free(translated);
+ goto clear_hashmaps;
+ }
+
+ hashmap_add(&pl->parent_hashmap, &translated->ent);
+ hashmap_remove(&pl->recursive_hashmap, &translated->ent, &data);
+ free(data);
+ return;
+ }
+
+ if (given->flags & PATTERN_FLAG_NEGATIVE) {
+ warning(_("unrecognized negative pattern: '%s'"),
+ given->pattern);
+ goto clear_hashmaps;
+ }
+
+ translated = xmalloc(sizeof(struct pattern_entry));
+
+ translated->pattern = xstrdup(given->pattern);
+ translated->patternlen = given->patternlen;
+ hashmap_entry_init(&translated->ent,
+ ignore_case ?
+ strihash(translated->pattern) :
+ strhash(translated->pattern));
+
+ hashmap_add(&pl->recursive_hashmap, &translated->ent);
+
+ if (hashmap_get_entry(&pl->parent_hashmap, translated, ent, NULL)) {
+ /* we already included this at the parent level */
+ warning(_("your sparse-checkout file may have issues: pattern '%s' is repeated"),
+ given->pattern);
+ hashmap_remove(&pl->parent_hashmap, &translated->ent, &data);
+ free(data);
+ free(translated);
+ }
+
+ return;
+
+clear_hashmaps:
+ warning(_("disabling cone pattern matching"));
+ hashmap_free_entries(&pl->parent_hashmap, struct pattern_entry, ent);
+ hashmap_free_entries(&pl->recursive_hashmap, struct pattern_entry, ent);
+ pl->use_cone_patterns = 0;
+}
+
+static int hashmap_contains_path(struct hashmap *map,
+ struct strbuf *pattern)
+{
+ struct pattern_entry p;
+
+ /* Check straight mapping */
+ p.pattern = pattern->buf;
+ p.patternlen = pattern->len;
+ hashmap_entry_init(&p.ent,
+ ignore_case ?
+ strihash(p.pattern) :
+ strhash(p.pattern));
+ return !!hashmap_get_entry(map, &p, ent, NULL);
+}
+
+int hashmap_contains_parent(struct hashmap *map,
+ const char *path,
+ struct strbuf *buffer)
+{
+ char *slash_pos;
+
+ strbuf_setlen(buffer, 0);
+
+ if (path[0] != '/')
+ strbuf_addch(buffer, '/');
+
+ strbuf_addstr(buffer, path);
+
+ slash_pos = strrchr(buffer->buf, '/');
+
+ while (slash_pos > buffer->buf) {
+ strbuf_setlen(buffer, slash_pos - buffer->buf);
+
+ if (hashmap_contains_path(map, buffer))
+ return 1;
+
+ slash_pos = strrchr(buffer->buf, '/');
+ }
+
+ return 0;
+}
+
+void add_pattern(const char *string, const char *base,
+ int baselen, struct pattern_list *pl, int srcpos)
+{
+ struct path_pattern *pattern;
+ int patternlen;
+ unsigned flags;
+ int nowildcardlen;
+
+ parse_path_pattern(&string, &patternlen, &flags, &nowildcardlen);
+ if (flags & PATTERN_FLAG_MUSTBEDIR) {
+ FLEXPTR_ALLOC_MEM(pattern, pattern, string, patternlen);
} else {
- x = xmalloc(sizeof(*x));
- x->pattern = string;
- }
- x->to_exclude = to_exclude;
- x->patternlen = strlen(string);
- 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;
-}
-
-static void *read_skip_worktree_file_from_index(const char *path, size_t *size)
+ pattern = xmalloc(sizeof(*pattern));
+ pattern->pattern = string;
+ }
+ pattern->patternlen = patternlen;
+ pattern->nowildcardlen = nowildcardlen;
+ pattern->base = base;
+ pattern->baselen = baselen;
+ pattern->flags = flags;
+ pattern->srcpos = srcpos;
+ ALLOC_GROW(pl->patterns, pl->nr + 1, pl->alloc);
+ pl->patterns[pl->nr++] = pattern;
+ pattern->pl = pl;
+
+ add_pattern_to_hashsets(pl, pattern);
+}
+
+static int read_skip_worktree_file_from_index(const struct index_state *istate,
+ const char *path,
+ size_t *size_out, char **data_out,
+ struct oid_stat *oid_stat)
{
int pos, len;
- unsigned long sz;
- enum object_type type;
- void *data;
- struct index_state *istate = &the_index;
len = strlen(path);
pos = index_name_pos(istate, path, len);
if (pos < 0)
- return NULL;
+ return -1;
if (!ce_skip_worktree(istate->cache[pos]))
+ return -1;
+
+ return do_read_blob(&istate->cache[pos]->oid, oid_stat, size_out, data_out);
+}
+
+/*
+ * Frees memory within pl which was allocated for exclude patterns and
+ * the file buffer. Does not free pl itself.
+ */
+void clear_pattern_list(struct pattern_list *pl)
+{
+ int i;
+
+ for (i = 0; i < pl->nr; i++)
+ free(pl->patterns[i]);
+ free(pl->patterns);
+ free(pl->filebuf);
+
+ memset(pl, 0, sizeof(*pl));
+}
+
+static void trim_trailing_spaces(char *buf)
+{
+ char *p, *last_space = NULL;
+
+ for (p = buf; *p; p++)
+ switch (*p) {
+ case ' ':
+ if (!last_space)
+ last_space = p;
+ break;
+ case '\\':
+ p++;
+ if (!*p)
+ return;
+ /* fallthrough */
+ default:
+ last_space = NULL;
+ }
+
+ if (last_space)
+ *last_space = '\0';
+}
+
+/*
+ * Given a subdirectory name and "dir" of the current directory,
+ * search the subdir in "dir" and return it, or create a new one if it
+ * does not exist in "dir".
+ *
+ * If "name" has the trailing slash, it'll be excluded in the search.
+ */
+static struct untracked_cache_dir *lookup_untracked(struct untracked_cache *uc,
+ struct untracked_cache_dir *dir,
+ const char *name, int len)
+{
+ int first, last;
+ struct untracked_cache_dir *d;
+ if (!dir)
return NULL;
- data = read_sha1_file(istate->cache[pos]->sha1, &type, &sz);
- if (!data || type != OBJ_BLOB) {
- free(data);
- return NULL;
+ if (len && name[len - 1] == '/')
+ len--;
+ first = 0;
+ last = dir->dirs_nr;
+ while (last > first) {
+ int cmp, next = first + ((last - first) >> 1);
+ d = dir->dirs[next];
+ cmp = strncmp(name, d->name, len);
+ if (!cmp && strlen(d->name) > len)
+ cmp = -1;
+ if (!cmp)
+ return d;
+ if (cmp < 0) {
+ last = next;
+ continue;
+ }
+ first = next+1;
+ }
+
+ uc->dir_created++;
+ FLEX_ALLOC_MEM(d, name, name, len);
+
+ ALLOC_GROW(dir->dirs, dir->dirs_nr + 1, dir->dirs_alloc);
+ MOVE_ARRAY(dir->dirs + first + 1, dir->dirs + first,
+ dir->dirs_nr - first);
+ dir->dirs_nr++;
+ dir->dirs[first] = d;
+ return d;
+}
+
+static void do_invalidate_gitignore(struct untracked_cache_dir *dir)
+{
+ int i;
+ dir->valid = 0;
+ dir->untracked_nr = 0;
+ for (i = 0; i < dir->dirs_nr; i++)
+ do_invalidate_gitignore(dir->dirs[i]);
+}
+
+static void invalidate_gitignore(struct untracked_cache *uc,
+ struct untracked_cache_dir *dir)
+{
+ uc->gitignore_invalidated++;
+ do_invalidate_gitignore(dir);
+}
+
+static void invalidate_directory(struct untracked_cache *uc,
+ struct untracked_cache_dir *dir)
+{
+ int i;
+
+ /*
+ * Invalidation increment here is just roughly correct. If
+ * untracked_nr or any of dirs[].recurse is non-zero, we
+ * should increment dir_invalidated too. But that's more
+ * expensive to do.
+ */
+ if (dir->valid)
+ uc->dir_invalidated++;
+
+ dir->valid = 0;
+ dir->untracked_nr = 0;
+ for (i = 0; i < dir->dirs_nr; i++)
+ dir->dirs[i]->recurse = 0;
+}
+
+static int add_patterns_from_buffer(char *buf, size_t size,
+ const char *base, int baselen,
+ struct pattern_list *pl);
+
+/*
+ * Given a file with name "fname", read it (either from disk, or from
+ * an index if 'istate' is non-null), parse it and store the
+ * exclude rules in "pl".
+ *
+ * If "ss" is not NULL, compute SHA-1 of the exclude file and fill
+ * stat data from disk (only valid if add_patterns returns zero). If
+ * ss_valid is non-zero, "ss" must contain good value as input.
+ */
+static int add_patterns(const char *fname, const char *base, int baselen,
+ struct pattern_list *pl, struct index_state *istate,
+ struct oid_stat *oid_stat)
+{
+ struct stat st;
+ int r;
+ int fd;
+ size_t size = 0;
+ char *buf;
+
+ fd = open(fname, O_RDONLY);
+ if (fd < 0 || fstat(fd, &st) < 0) {
+ if (fd < 0)
+ warn_on_fopen_errors(fname);
+ else
+ close(fd);
+ if (!istate)
+ return -1;
+ r = read_skip_worktree_file_from_index(istate, fname,
+ &size, &buf,
+ oid_stat);
+ if (r != 1)
+ return r;
+ } else {
+ size = xsize_t(st.st_size);
+ if (size == 0) {
+ if (oid_stat) {
+ fill_stat_data(&oid_stat->stat, &st);
+ oidcpy(&oid_stat->oid, the_hash_algo->empty_blob);
+ oid_stat->valid = 1;
+ }
+ close(fd);
+ return 0;
+ }
+ buf = xmallocz(size);
+ if (read_in_full(fd, buf, size) != size) {
+ free(buf);
+ close(fd);
+ return -1;
+ }
+ buf[size++] = '\n';
+ close(fd);
+ if (oid_stat) {
+ int pos;
+ if (oid_stat->valid &&
+ !match_stat_data_racy(istate, &oid_stat->stat, &st))
+ ; /* no content change, ss->sha1 still good */
+ else if (istate &&
+ (pos = index_name_pos(istate, fname, strlen(fname))) >= 0 &&
+ !ce_stage(istate->cache[pos]) &&
+ ce_uptodate(istate->cache[pos]) &&
+ !would_convert_to_git(istate, fname))
+ oidcpy(&oid_stat->oid,
+ &istate->cache[pos]->oid);
+ else
+ hash_object_file(buf, size, "blob",
+ &oid_stat->oid);
+ fill_stat_data(&oid_stat->stat, &st);
+ oid_stat->valid = 1;
+ }
+ }
+
+ add_patterns_from_buffer(buf, size, base, baselen, pl);
+ return 0;
+}
+
+static int add_patterns_from_buffer(char *buf, size_t size,
+ const char *base, int baselen,
+ struct pattern_list *pl)
+{
+ int i, lineno = 1;
+ char *entry;
+
+ hashmap_init(&pl->recursive_hashmap, pl_hashmap_cmp, NULL, 0);
+ hashmap_init(&pl->parent_hashmap, pl_hashmap_cmp, NULL, 0);
+
+ pl->filebuf = buf;
+
+ if (skip_utf8_bom(&buf, size))
+ size -= buf - pl->filebuf;
+
+ entry = buf;
+
+ for (i = 0; i < size; i++) {
+ if (buf[i] == '\n') {
+ if (entry != buf + i && entry[0] != '#') {
+ buf[i - (i && buf[i-1] == '\r')] = 0;
+ trim_trailing_spaces(entry);
+ add_pattern(entry, base, baselen, pl, lineno);
+ }
+ lineno++;
+ entry = buf + i + 1;
+ }
+ }
+ return 0;
+}
+
+int add_patterns_from_file_to_list(const char *fname, const char *base,
+ int baselen, struct pattern_list *pl,
+ struct index_state *istate)
+{
+ return add_patterns(fname, base, baselen, pl, istate, NULL);
+}
+
+int add_patterns_from_blob_to_list(
+ struct object_id *oid,
+ const char *base, int baselen,
+ struct pattern_list *pl)
+{
+ char *buf;
+ size_t size;
+ int r;
+
+ r = do_read_blob(oid, NULL, &size, &buf);
+ if (r != 1)
+ return r;
+
+ add_patterns_from_buffer(buf, size, base, baselen, pl);
+ return 0;
+}
+
+struct pattern_list *add_pattern_list(struct dir_struct *dir,
+ int group_type, const char *src)
+{
+ struct pattern_list *pl;
+ struct exclude_list_group *group;
+
+ group = &dir->exclude_list_group[group_type];
+ ALLOC_GROW(group->pl, group->nr + 1, group->alloc);
+ pl = &group->pl[group->nr++];
+ memset(pl, 0, sizeof(*pl));
+ pl->src = src;
+ return pl;
+}
+
+/*
+ * Used to set up core.excludesfile and .git/info/exclude lists.
+ */
+static void add_patterns_from_file_1(struct dir_struct *dir, const char *fname,
+ struct oid_stat *oid_stat)
+{
+ struct pattern_list *pl;
+ /*
+ * catch setup_standard_excludes() that's called before
+ * dir->untracked is assigned. That function behaves
+ * differently when dir->untracked is non-NULL.
+ */
+ if (!dir->untracked)
+ dir->unmanaged_exclude_files++;
+ pl = add_pattern_list(dir, EXC_FILE, fname);
+ if (add_patterns(fname, "", 0, pl, NULL, oid_stat) < 0)
+ die(_("cannot use %s as an exclude file"), fname);
+}
+
+void add_patterns_from_file(struct dir_struct *dir, const char *fname)
+{
+ dir->unmanaged_exclude_files++; /* see validate_untracked_cache() */
+ add_patterns_from_file_1(dir, fname, NULL);
+}
+
+int match_basename(const char *basename, int basenamelen,
+ const char *pattern, int prefix, int patternlen,
+ unsigned flags)
+{
+ if (prefix == patternlen) {
+ if (patternlen == basenamelen &&
+ !fspathncmp(pattern, basename, basenamelen))
+ return 1;
+ } else if (flags & PATTERN_FLAG_ENDSWITH) {
+ /* "*literal" matching against "fooliteral" */
+ if (patternlen - 1 <= basenamelen &&
+ !fspathncmp(pattern + 1,
+ basename + basenamelen - (patternlen - 1),
+ patternlen - 1))
+ return 1;
+ } else {
+ if (fnmatch_icase_mem(pattern, patternlen,
+ basename, basenamelen,
+ 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,
+ unsigned flags)
+{
+ const char *name;
+ int namelen;
+
+ /*
+ * match with FNM_PATHNAME; the pattern has base implicitly
+ * in front of it.
+ */
+ if (*pattern == '/') {
+ pattern++;
+ patternlen--;
+ 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] != '/') ||
+ fspathncmp(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 (fspathncmp(pattern, name, prefix))
+ return 0;
+ pattern += prefix;
+ patternlen -= prefix;
+ name += prefix;
+ namelen -= prefix;
+
+ /*
+ * If the whole pattern did not have a wildcard,
+ * then our prefix match is all we need; we
+ * do not need to call fnmatch at all.
+ */
+ if (!patternlen && !namelen)
+ return 1;
}
- *size = xsize_t(sz);
- return data;
+
+ return fnmatch_icase_mem(pattern, patternlen,
+ name, namelen,
+ WM_PATHNAME) == 0;
}
-void free_excludes(struct exclude_list *el)
+/*
+ * Scan the given exclude list in reverse to see whether pathname
+ * should be ignored. The first match (i.e. the last on the list), if
+ * any, determines the fate. Returns the exclude_list element which
+ * matched, or NULL for undecided.
+ */
+static struct path_pattern *last_matching_pattern_from_list(const char *pathname,
+ int pathlen,
+ const char *basename,
+ int *dtype,
+ struct pattern_list *pl,
+ struct index_state *istate)
{
+ struct path_pattern *res = NULL; /* undecided */
int i;
- for (i = 0; i < el->nr; i++)
- free(el->excludes[i]);
- free(el->excludes);
+ if (!pl->nr)
+ return NULL; /* undefined */
- el->nr = 0;
- el->excludes = NULL;
-}
+ for (i = pl->nr - 1; 0 <= i; i--) {
+ struct path_pattern *pattern = pl->patterns[i];
+ const char *exclude = pattern->pattern;
+ int prefix = pattern->nowildcardlen;
-int add_excludes_from_file_to_list(const char *fname,
- const char *base,
- int baselen,
- char **buf_p,
- struct exclude_list *which,
- int check_index)
-{
- struct stat st;
- int fd, i;
- size_t size = 0;
- char *buf, *entry;
+ if (pattern->flags & PATTERN_FLAG_MUSTBEDIR) {
+ *dtype = resolve_dtype(*dtype, istate, pathname, pathlen);
+ if (*dtype != DT_DIR)
+ continue;
+ }
- fd = open(fname, O_RDONLY);
- if (fd < 0 || fstat(fd, &st) < 0) {
- if (0 <= fd)
- close(fd);
- if (!check_index ||
- (buf = read_skip_worktree_file_from_index(fname, &size)) == NULL)
- return -1;
- if (size == 0) {
- free(buf);
- return 0;
+ if (pattern->flags & PATTERN_FLAG_NODIR) {
+ if (match_basename(basename,
+ pathlen - (basename - pathname),
+ exclude, prefix, pattern->patternlen,
+ pattern->flags)) {
+ res = pattern;
+ break;
+ }
+ continue;
}
- if (buf[size-1] != '\n') {
- buf = xrealloc(buf, size+1);
- buf[size++] = '\n';
+
+ assert(pattern->baselen == 0 ||
+ pattern->base[pattern->baselen - 1] == '/');
+ if (match_pathname(pathname, pathlen,
+ pattern->base,
+ pattern->baselen ? pattern->baselen - 1 : 0,
+ exclude, prefix, pattern->patternlen,
+ pattern->flags)) {
+ res = pattern;
+ break;
}
}
- else {
- size = xsize_t(st.st_size);
- if (size == 0) {
- close(fd);
- return 0;
- }
- buf = xmalloc(size+1);
- if (read_in_full(fd, buf, size) != size) {
- free(buf);
- close(fd);
- return -1;
+ return res;
+}
+
+/*
+ * Scan the list of patterns to determine if the ordered list
+ * of patterns matches on 'pathname'.
+ *
+ * Return 1 for a match, 0 for not matched and -1 for undecided.
+ */
+enum pattern_match_result path_matches_pattern_list(
+ const char *pathname, int pathlen,
+ const char *basename, int *dtype,
+ struct pattern_list *pl,
+ struct index_state *istate)
+{
+ struct path_pattern *pattern;
+ struct strbuf parent_pathname = STRBUF_INIT;
+ int result = NOT_MATCHED;
+ const char *slash_pos;
+
+ if (!pl->use_cone_patterns) {
+ pattern = last_matching_pattern_from_list(pathname, pathlen, basename,
+ dtype, pl, istate);
+ if (pattern) {
+ if (pattern->flags & PATTERN_FLAG_NEGATIVE)
+ return NOT_MATCHED;
+ else
+ return MATCHED;
}
- buf[size++] = '\n';
- close(fd);
+
+ return UNDECIDED;
}
- if (buf_p)
- *buf_p = buf;
- entry = buf;
- for (i = 0; i < size; i++) {
- if (buf[i] == '\n') {
- if (entry != buf + i && entry[0] != '#') {
- buf[i - (i && buf[i-1] == '\r')] = 0;
- add_exclude(entry, base, baselen, which);
- }
- entry = buf + i + 1;
- }
+ if (pl->full_cone)
+ return MATCHED;
+
+ strbuf_addch(&parent_pathname, '/');
+ strbuf_add(&parent_pathname, pathname, pathlen);
+
+ if (hashmap_contains_path(&pl->recursive_hashmap,
+ &parent_pathname)) {
+ result = MATCHED_RECURSIVE;
+ goto done;
}
- return 0;
+
+ slash_pos = strrchr(parent_pathname.buf, '/');
+
+ if (slash_pos == parent_pathname.buf) {
+ /* include every file in root */
+ result = MATCHED;
+ goto done;
+ }
+
+ strbuf_setlen(&parent_pathname, slash_pos - parent_pathname.buf);
+
+ if (hashmap_contains_path(&pl->parent_hashmap, &parent_pathname)) {
+ result = MATCHED;
+ goto done;
+ }
+
+ if (hashmap_contains_parent(&pl->recursive_hashmap,
+ pathname,
+ &parent_pathname))
+ result = MATCHED_RECURSIVE;
+
+done:
+ strbuf_release(&parent_pathname);
+ return result;
}
-void add_excludes_from_file(struct dir_struct *dir, const char *fname)
+static struct path_pattern *last_matching_pattern_from_lists(
+ struct dir_struct *dir, struct index_state *istate,
+ const char *pathname, int pathlen,
+ const char *basename, int *dtype_p)
{
- if (add_excludes_from_file_to_list(fname, "", 0, NULL,
- &dir->exclude_list[EXC_FILE], 0) < 0)
- die("cannot use %s as an exclude file", fname);
+ int i, j;
+ struct exclude_list_group *group;
+ struct path_pattern *pattern;
+ for (i = EXC_CMDL; i <= EXC_FILE; i++) {
+ group = &dir->exclude_list_group[i];
+ for (j = group->nr - 1; j >= 0; j--) {
+ pattern = last_matching_pattern_from_list(
+ pathname, pathlen, basename, dtype_p,
+ &group->pl[j], istate);
+ if (pattern)
+ return pattern;
+ }
+ }
+ return NULL;
}
-static void prep_exclude(struct dir_struct *dir, const char *base, int baselen)
+/*
+ * Loads the per-directory exclude list for the substring of base
+ * which has a char length of baselen.
+ */
+static void prep_exclude(struct dir_struct *dir,
+ struct index_state *istate,
+ const char *base, int baselen)
{
- struct exclude_list *el;
+ struct exclude_list_group *group;
+ struct pattern_list *pl;
struct exclude_stack *stk = NULL;
+ struct untracked_cache_dir *untracked;
int current;
- if ((!dir->exclude_per_dir) ||
- (baselen + strlen(dir->exclude_per_dir) >= PATH_MAX))
- return; /* too long a path -- ignore */
+ group = &dir->exclude_list_group[EXC_DIRS];
- /* Pop the ones that are not the prefix of the path being checked. */
- el = &dir->exclude_list[EXC_DIRS];
+ /*
+ * Pop the exclude lists from the EXCL_DIRS exclude_list_group
+ * which originate from directories not in the prefix of the
+ * path being checked.
+ */
while ((stk = dir->exclude_stack) != NULL) {
if (stk->baselen <= baselen &&
- !strncmp(dir->basebuf, base, stk->baselen))
+ !strncmp(dir->basebuf.buf, base, stk->baselen))
break;
+ pl = &group->pl[dir->exclude_stack->exclude_ix];
dir->exclude_stack = stk->prev;
- while (stk->exclude_ix < el->nr)
- free(el->excludes[--el->nr]);
- free(stk->filebuf);
+ dir->pattern = NULL;
+ free((char *)pl->src); /* see strbuf_detach() below */
+ clear_pattern_list(pl);
free(stk);
+ group->nr--;
}
+ /* Skip traversing into sub directories if the parent is excluded */
+ if (dir->pattern)
+ return;
+
+ /*
+ * Lazy initialization. All call sites currently just
+ * memset(dir, 0, sizeof(*dir)) before use. Changing all of
+ * them seems lots of work for little benefit.
+ */
+ if (!dir->basebuf.buf)
+ strbuf_init(&dir->basebuf, PATH_MAX);
+
/* Read from the parent directories and push them down. */
current = stk ? stk->baselen : -1;
+ strbuf_setlen(&dir->basebuf, current < 0 ? 0 : current);
+ if (dir->untracked)
+ untracked = stk ? stk->ucd : dir->untracked->root;
+ else
+ untracked = NULL;
+
while (current < baselen) {
- struct exclude_stack *stk = xcalloc(1, sizeof(*stk));
const char *cp;
+ struct oid_stat oid_stat;
+ stk = xcalloc(1, sizeof(*stk));
if (current < 0) {
cp = base;
current = 0;
- }
- else {
+ } else {
cp = strchr(base + current + 1, '/');
if (!cp)
die("oops in prep_exclude");
cp++;
+ untracked =
+ lookup_untracked(dir->untracked, untracked,
+ base + current,
+ cp - base - current);
}
stk->prev = dir->exclude_stack;
stk->baselen = cp - base;
- stk->exclude_ix = el->nr;
- memcpy(dir->basebuf + current, base + current,
- stk->baselen - current);
- strcpy(dir->basebuf + stk->baselen, dir->exclude_per_dir);
- add_excludes_from_file_to_list(dir->basebuf,
- dir->basebuf, stk->baselen,
- &stk->filebuf, el, 1);
+ stk->exclude_ix = group->nr;
+ stk->ucd = untracked;
+ pl = add_pattern_list(dir, EXC_DIRS, NULL);
+ strbuf_add(&dir->basebuf, base + current, stk->baselen - current);
+ assert(stk->baselen == dir->basebuf.len);
+
+ /* Abort if the directory is excluded */
+ if (stk->baselen) {
+ int dt = DT_DIR;
+ dir->basebuf.buf[stk->baselen - 1] = 0;
+ dir->pattern = last_matching_pattern_from_lists(dir,
+ istate,
+ dir->basebuf.buf, stk->baselen - 1,
+ dir->basebuf.buf + current, &dt);
+ dir->basebuf.buf[stk->baselen - 1] = '/';
+ if (dir->pattern &&
+ dir->pattern->flags & PATTERN_FLAG_NEGATIVE)
+ dir->pattern = NULL;
+ if (dir->pattern) {
+ dir->exclude_stack = stk;
+ return;
+ }
+ }
+
+ /* Try to read per-directory file */
+ oidclr(&oid_stat.oid);
+ oid_stat.valid = 0;
+ if (dir->exclude_per_dir &&
+ /*
+ * If we know that no files have been added in
+ * this directory (i.e. valid_cached_dir() has
+ * been executed and set untracked->valid) ..
+ */
+ (!untracked || !untracked->valid ||
+ /*
+ * .. and .gitignore does not exist before
+ * (i.e. null exclude_oid). Then we can skip
+ * loading .gitignore, which would result in
+ * ENOENT anyway.
+ */
+ !is_null_oid(&untracked->exclude_oid))) {
+ /*
+ * dir->basebuf gets reused by the traversal, but we
+ * need fname to remain unchanged to ensure the src
+ * member of each struct path_pattern correctly
+ * back-references its source file. Other invocations
+ * of add_pattern_list provide stable strings, so we
+ * strbuf_detach() and free() here in the caller.
+ */
+ struct strbuf sb = STRBUF_INIT;
+ strbuf_addbuf(&sb, &dir->basebuf);
+ strbuf_addstr(&sb, dir->exclude_per_dir);
+ pl->src = strbuf_detach(&sb, NULL);
+ add_patterns(pl->src, pl->src, stk->baselen, pl, istate,
+ untracked ? &oid_stat : NULL);
+ }
+ /*
+ * NEEDSWORK: when untracked cache is enabled, prep_exclude()
+ * will first be called in valid_cached_dir() then maybe many
+ * times more in last_matching_pattern(). When the cache is
+ * used, last_matching_pattern() will not be called and
+ * reading .gitignore content will be a waste.
+ *
+ * So when it's called by valid_cached_dir() and we can get
+ * .gitignore SHA-1 from the index (i.e. .gitignore is not
+ * modified on work tree), we could delay reading the
+ * .gitignore content until we absolutely need it in
+ * last_matching_pattern(). Be careful about ignore rule
+ * order, though, if you do that.
+ */
+ if (untracked &&
+ !oideq(&oid_stat.oid, &untracked->exclude_oid)) {
+ invalidate_gitignore(dir->untracked, untracked);
+ oidcpy(&untracked->exclude_oid, &oid_stat.oid);
+ }
dir->exclude_stack = stk;
current = stk->baselen;
}
- dir->basebuf[baselen] = '\0';
+ strbuf_setlen(&dir->basebuf, baselen);
}
-/* Scan the list and let the last match determine the fate.
- * Return 1 for exclude, 0 for include and -1 for undecided.
+/*
+ * Loads the exclude lists for the directory containing pathname, then
+ * scans all exclude lists to determine whether pathname is excluded.
+ * Returns the exclude_list element which matched, or NULL for
+ * undecided.
*/
-int excluded_from_list(const char *pathname,
- int pathlen, const char *basename, int *dtype,
- struct exclude_list *el)
+struct path_pattern *last_matching_pattern(struct dir_struct *dir,
+ struct index_state *istate,
+ const char *pathname,
+ int *dtype_p)
{
- int i;
+ int pathlen = strlen(pathname);
+ const char *basename = strrchr(pathname, '/');
+ basename = (basename) ? basename+1 : pathname;
- 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;
- }
+ prep_exclude(dir, istate, pathname, basename-pathname);
- 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;
- }
- }
- }
- }
- return -1; /* undecided */
+ if (dir->pattern)
+ return dir->pattern;
+
+ return last_matching_pattern_from_lists(dir, istate, pathname, pathlen,
+ basename, dtype_p);
}
-int excluded(struct dir_struct *dir, const char *pathname, int *dtype_p)
+/*
+ * Loads the exclude lists for the directory containing pathname, then
+ * scans all exclude lists to determine whether pathname is excluded.
+ * Returns 1 if true, otherwise 0.
+ */
+int is_excluded(struct dir_struct *dir, struct index_state *istate,
+ const char *pathname, int *dtype_p)
{
- int pathlen = strlen(pathname);
- int st;
- const char *basename = strrchr(pathname, '/');
- basename = (basename) ? basename+1 : pathname;
-
- prep_exclude(dir, pathname, basename-pathname);
- for (st = EXC_CMDL; st <= EXC_FILE; st++) {
- switch (excluded_from_list(pathname, pathlen, basename,
- dtype_p, &dir->exclude_list[st])) {
- case 0:
- return 0;
- case 1:
- return 1;
- }
- }
+ struct path_pattern *pattern =
+ last_matching_pattern(dir, istate, pathname, dtype_p);
+ if (pattern)
+ return pattern->flags & PATTERN_FLAG_NEGATIVE ? 0 : 1;
return 0;
}
{
struct dir_entry *ent;
- ent = xmalloc(sizeof(*ent) + len + 1);
+ FLEX_ALLOC_MEM(ent, name, pathname, len);
ent->len = len;
- memcpy(ent->name, pathname, len);
- ent->name[len] = 0;
return ent;
}
-static struct dir_entry *dir_add_name(struct dir_struct *dir, const char *pathname, int len)
+static struct dir_entry *dir_add_name(struct dir_struct *dir,
+ struct index_state *istate,
+ const char *pathname, int len)
{
- if (cache_name_exists(pathname, len, ignore_case))
+ if (index_file_exists(istate, pathname, len, ignore_case))
return NULL;
ALLOC_GROW(dir->entries, dir->nr+1, dir->alloc);
return dir->entries[dir->nr++] = dir_entry_new(pathname, len);
}
-struct dir_entry *dir_add_ignored(struct dir_struct *dir, const char *pathname, int len)
+struct dir_entry *dir_add_ignored(struct dir_struct *dir,
+ struct index_state *istate,
+ const char *pathname, int len)
{
- if (!cache_name_is_other(pathname, len))
+ if (!index_name_is_other(istate, pathname, len))
return NULL;
ALLOC_GROW(dir->ignored, dir->ignored_nr+1, dir->ignored_alloc);
};
/*
- * Do not use the alphabetically stored index to look up
+ * Do not use the alphabetically sorted index to look up
* the directory name; instead, use the case insensitive
- * name hash.
+ * directory hash.
*/
-static enum exist_status directory_exists_in_index_icase(const char *dirname, int len)
+static enum exist_status directory_exists_in_index_icase(struct index_state *istate,
+ const char *dirname, int len)
{
- struct cache_entry *ce = index_name_exists(&the_index, dirname, len + 1, ignore_case);
- unsigned char endchar;
-
- if (!ce)
- return index_nonexistent;
- endchar = ce->name[len];
+ struct cache_entry *ce;
- /*
- * The cache_entry structure returned will contain this dirname
- * and possibly additional path components.
- */
- if (endchar == '/')
+ if (index_dir_exists(istate, dirname, len))
return index_directory;
- /*
- * If there are no additional path components, then this cache_entry
- * represents a submodule. Submodules, despite being directories,
- * are stored in the cache without a closing slash.
- */
- if (!endchar && S_ISGITLINK(ce->ce_mode))
+ ce = index_file_exists(istate, dirname, len, ignore_case);
+ if (ce && S_ISGITLINK(ce->ce_mode))
return index_gitdir;
- /* This should never be hit, but it exists just in case. */
return index_nonexistent;
}
* the files it contains) will sort with the '/' at the
* end.
*/
-static enum exist_status directory_exists_in_index(const char *dirname, int len)
+static enum exist_status directory_exists_in_index(struct index_state *istate,
+ const char *dirname, int len)
{
int pos;
if (ignore_case)
- return directory_exists_in_index_icase(dirname, len);
+ return directory_exists_in_index_icase(istate, dirname, len);
- pos = cache_name_pos(dirname, len);
+ pos = index_name_pos(istate, dirname, len);
if (pos < 0)
pos = -pos-1;
- while (pos < active_nr) {
- struct cache_entry *ce = active_cache[pos++];
+ while (pos < istate->cache_nr) {
+ const struct cache_entry *ce = istate->cache[pos++];
unsigned char endchar;
if (strncmp(ce->name, dirname, len))
*
* (a) if "show_other_directories" is true, we show it as
* just a directory, unless "hide_empty_directories" is
- * also true and the directory is empty, in which case
- * we just ignore it entirely.
+ * also true, in which case we need to check if it contains any
+ * untracked and / or ignored files.
* (b) if it looks like a git directory, and we don't have
* 'no_gitlinks' set we treat it as a gitlink, and show it
* as a directory.
* (c) otherwise, we recurse into it.
*/
-enum directory_treatment {
- show_directory,
- ignore_directory,
- recurse_into_directory
-};
-
-static enum directory_treatment treat_directory(struct dir_struct *dir,
- const char *dirname, int len,
- const struct path_simplify *simplify)
+static enum path_treatment treat_directory(struct dir_struct *dir,
+ struct index_state *istate,
+ struct untracked_cache_dir *untracked,
+ const char *dirname, int len, int baselen, int exclude,
+ const struct pathspec *pathspec)
{
+ int nested_repo = 0;
+
/* The "len-1" is to strip the final '/' */
- switch (directory_exists_in_index(dirname, len-1)) {
+ switch (directory_exists_in_index(istate, dirname, len-1)) {
case index_directory:
- return recurse_into_directory;
+ return path_recurse;
case index_gitdir:
- if (dir->flags & DIR_SHOW_OTHER_DIRECTORIES)
- return ignore_directory;
- return show_directory;
+ return path_none;
case index_nonexistent:
+ if ((dir->flags & DIR_SKIP_NESTED_GIT) ||
+ !(dir->flags & DIR_NO_GITLINKS)) {
+ struct strbuf sb = STRBUF_INIT;
+ strbuf_addstr(&sb, dirname);
+ nested_repo = is_nonbare_repository_dir(&sb);
+ strbuf_release(&sb);
+ }
+ if (nested_repo)
+ return ((dir->flags & DIR_SKIP_NESTED_GIT) ? path_none :
+ (exclude ? path_excluded : path_untracked));
+
if (dir->flags & DIR_SHOW_OTHER_DIRECTORIES)
break;
- if (!(dir->flags & DIR_NO_GITLINKS)) {
- unsigned char sha1[20];
- if (resolve_gitlink_ref(dirname, "HEAD", sha1) == 0)
- return show_directory;
+ if (exclude &&
+ (dir->flags & DIR_SHOW_IGNORED_TOO) &&
+ (dir->flags & DIR_SHOW_IGNORED_TOO_MODE_MATCHING)) {
+
+ /*
+ * This is an excluded directory and we are
+ * showing ignored paths that match an exclude
+ * pattern. (e.g. show directory as ignored
+ * only if it matches an exclude pattern).
+ * This path will either be 'path_excluded`
+ * (if we are showing empty directories or if
+ * the directory is not empty), or will be
+ * 'path_none' (empty directory, and we are
+ * not showing empty directories).
+ */
+ if (!(dir->flags & DIR_HIDE_EMPTY_DIRECTORIES))
+ return path_excluded;
+
+ if (read_directory_recursive(dir, istate, dirname, len,
+ untracked, 1, 1, pathspec) == path_excluded)
+ return path_excluded;
+
+ return path_none;
}
- return recurse_into_directory;
+ return path_recurse;
}
/* This is the "show_other_directories" case */
+
if (!(dir->flags & DIR_HIDE_EMPTY_DIRECTORIES))
- return show_directory;
- if (!read_directory_recursive(dir, dirname, len, 1, simplify))
- return ignore_directory;
- return show_directory;
+ return exclude ? path_excluded : path_untracked;
+
+ untracked = lookup_untracked(dir->untracked, untracked,
+ dirname + baselen, len - baselen);
+
+ /*
+ * If this is an excluded directory, then we only need to check if
+ * the directory contains any files.
+ */
+ return read_directory_recursive(dir, istate, dirname, len,
+ untracked, 1, exclude, pathspec);
}
/*
* reading - if the path cannot possibly be in the pathspec,
* return true, and we'll skip it early.
*/
-static int simplify_away(const char *path, int pathlen, const struct path_simplify *simplify)
+static int simplify_away(const char *path, int pathlen,
+ const struct pathspec *pathspec)
{
- if (simplify) {
- for (;;) {
- const char *match = simplify->path;
- int len = simplify->len;
+ int i;
- if (!match)
- break;
- if (len > pathlen)
- len = pathlen;
- if (!memcmp(path, match, len))
- return 0;
- simplify++;
- }
- return 1;
+ if (!pathspec || !pathspec->nr)
+ return 0;
+
+ GUARD_PATHSPEC(pathspec,
+ PATHSPEC_FROMTOP |
+ PATHSPEC_MAXDEPTH |
+ PATHSPEC_LITERAL |
+ PATHSPEC_GLOB |
+ PATHSPEC_ICASE |
+ PATHSPEC_EXCLUDE |
+ PATHSPEC_ATTR);
+
+ for (i = 0; i < pathspec->nr; i++) {
+ const struct pathspec_item *item = &pathspec->items[i];
+ int len = item->nowildcard_len;
+
+ if (len > pathlen)
+ len = pathlen;
+ if (!ps_strncmp(item, item->match, path, len))
+ return 0;
}
- return 0;
+
+ return 1;
}
/*
* 2. the path is a directory prefix of some element in the
* pathspec
*/
-static int exclude_matches_pathspec(const char *path, int len,
- const struct path_simplify *simplify)
-{
- if (simplify) {
- for (; simplify->path; simplify++) {
- if (len == simplify->len
- && !memcmp(path, simplify->path, len))
- return 1;
- if (len < simplify->len
- && simplify->path[len] == '/'
- && !memcmp(path, simplify->path, len))
- return 1;
- }
+static int exclude_matches_pathspec(const char *path, int pathlen,
+ const struct pathspec *pathspec)
+{
+ int i;
+
+ if (!pathspec || !pathspec->nr)
+ return 0;
+
+ GUARD_PATHSPEC(pathspec,
+ PATHSPEC_FROMTOP |
+ PATHSPEC_MAXDEPTH |
+ PATHSPEC_LITERAL |
+ PATHSPEC_GLOB |
+ PATHSPEC_ICASE |
+ PATHSPEC_EXCLUDE);
+
+ for (i = 0; i < pathspec->nr; i++) {
+ const struct pathspec_item *item = &pathspec->items[i];
+ int len = item->nowildcard_len;
+
+ if (len == pathlen &&
+ !ps_strncmp(item, item->match, path, pathlen))
+ return 1;
+ if (len > pathlen &&
+ item->match[pathlen] == '/' &&
+ !ps_strncmp(item, item->match, path, pathlen))
+ return 1;
}
return 0;
}
-static int get_index_dtype(const char *path, int len)
+static int get_index_dtype(struct index_state *istate,
+ const char *path, int len)
{
int pos;
- struct cache_entry *ce;
+ const struct cache_entry *ce;
- ce = cache_name_exists(path, len, 0);
+ ce = index_file_exists(istate, path, len, 0);
if (ce) {
if (!ce_uptodate(ce))
return DT_UNKNOWN;
}
/* Try to look it up as a directory */
- pos = cache_name_pos(path, len);
+ pos = index_name_pos(istate, path, len);
if (pos >= 0)
return DT_UNKNOWN;
pos = -pos-1;
- while (pos < active_nr) {
- ce = active_cache[pos++];
+ while (pos < istate->cache_nr) {
+ ce = istate->cache[pos++];
if (strncmp(ce->name, path, len))
break;
if (ce->name[len] > '/')
return DT_UNKNOWN;
}
-static int get_dtype(struct dirent *de, const char *path, int len)
+static int resolve_dtype(int dtype, struct index_state *istate,
+ const char *path, int len)
{
- int dtype = de ? DTYPE(de) : DT_UNKNOWN;
struct stat st;
if (dtype != DT_UNKNOWN)
return dtype;
- dtype = get_index_dtype(path, len);
+ dtype = get_index_dtype(istate, path, len);
if (dtype != DT_UNKNOWN)
return dtype;
if (lstat(path, &st))
return dtype;
}
-enum path_treatment {
- path_ignored,
- path_handled,
- path_recurse
-};
-
static enum path_treatment treat_one_path(struct dir_struct *dir,
- char *path, int *len,
- const struct path_simplify *simplify,
- int dtype, struct dirent *de)
+ struct untracked_cache_dir *untracked,
+ struct index_state *istate,
+ struct strbuf *path,
+ int baselen,
+ const struct pathspec *pathspec,
+ int dtype)
{
- int exclude = excluded(dir, path, &dtype);
- if (exclude && (dir->flags & DIR_COLLECT_IGNORED)
- && exclude_matches_pathspec(path, *len, simplify))
- dir_add_ignored(dir, path, *len);
+ int exclude;
+ int has_path_in_index = !!index_file_exists(istate, path->buf, path->len, ignore_case);
+ enum path_treatment path_treatment;
+
+ dtype = resolve_dtype(dtype, istate, path->buf, path->len);
+
+ /* Always exclude indexed files */
+ if (dtype != DT_DIR && has_path_in_index)
+ return path_none;
/*
- * Excluded? If we don't explicitly want to show
- * ignored files, ignore it
+ * When we are looking at a directory P in the working tree,
+ * there are three cases:
+ *
+ * (1) P exists in the index. Everything inside the directory P in
+ * the working tree needs to go when P is checked out from the
+ * index.
+ *
+ * (2) P does not exist in the index, but there is P/Q in the index.
+ * We know P will stay a directory when we check out the contents
+ * of the index, but we do not know yet if there is a directory
+ * P/Q in the working tree to be killed, so we need to recurse.
+ *
+ * (3) P does not exist in the index, and there is no P/Q in the index
+ * to require P to be a directory, either. Only in this case, we
+ * know that everything inside P will not be killed without
+ * recursing.
*/
- if (exclude && !(dir->flags & DIR_SHOW_IGNORED))
- return path_ignored;
+ if ((dir->flags & DIR_COLLECT_KILLED_ONLY) &&
+ (dtype == DT_DIR) &&
+ !has_path_in_index &&
+ (directory_exists_in_index(istate, path->buf, path->len) == index_nonexistent))
+ return path_none;
- if (dtype == DT_UNKNOWN)
- dtype = get_dtype(de, path, *len);
+ exclude = is_excluded(dir, istate, path->buf, &dtype);
/*
- * Do we want to see just the ignored files?
- * We still need to recurse into directories,
- * even if we don't ignore them, since the
- * directory may contain files that we do..
+ * Excluded? If we don't explicitly want to show
+ * ignored files, ignore it
*/
- if (!exclude && (dir->flags & DIR_SHOW_IGNORED)) {
- if (dtype != DT_DIR)
- return path_ignored;
- }
+ if (exclude && !(dir->flags & (DIR_SHOW_IGNORED|DIR_SHOW_IGNORED_TOO)))
+ return path_excluded;
switch (dtype) {
default:
- return path_ignored;
+ return path_none;
case DT_DIR:
- memcpy(path + *len, "/", 2);
- (*len)++;
- switch (treat_directory(dir, path, *len, simplify)) {
- case show_directory:
- if (exclude != !!(dir->flags
- & DIR_SHOW_IGNORED))
- return path_ignored;
- break;
- case recurse_into_directory:
+ strbuf_addch(path, '/');
+ path_treatment = treat_directory(dir, istate, untracked,
+ path->buf, path->len,
+ baselen, exclude, pathspec);
+ /*
+ * If 1) we only want to return directories that
+ * match an exclude pattern and 2) this directory does
+ * not match an exclude pattern but all of its
+ * contents are excluded, then indicate that we should
+ * recurse into this directory (instead of marking the
+ * directory itself as an ignored path).
+ */
+ if (!exclude &&
+ path_treatment == path_excluded &&
+ (dir->flags & DIR_SHOW_IGNORED_TOO) &&
+ (dir->flags & DIR_SHOW_IGNORED_TOO_MODE_MATCHING))
return path_recurse;
- case ignore_directory:
- return path_ignored;
- }
- break;
+ return path_treatment;
case DT_REG:
case DT_LNK:
- break;
+ return exclude ? path_excluded : path_untracked;
+ }
+}
+
+static enum path_treatment treat_path_fast(struct dir_struct *dir,
+ struct untracked_cache_dir *untracked,
+ struct cached_dir *cdir,
+ struct index_state *istate,
+ struct strbuf *path,
+ int baselen,
+ const struct pathspec *pathspec)
+{
+ strbuf_setlen(path, baselen);
+ if (!cdir->ucd) {
+ strbuf_addstr(path, cdir->file);
+ return path_untracked;
}
- return path_handled;
+ strbuf_addstr(path, cdir->ucd->name);
+ /* treat_one_path() does this before it calls treat_directory() */
+ strbuf_complete(path, '/');
+ if (cdir->ucd->check_only)
+ /*
+ * check_only is set as a result of treat_directory() getting
+ * to its bottom. Verify again the same set of directories
+ * with check_only set.
+ */
+ return read_directory_recursive(dir, istate, path->buf, path->len,
+ cdir->ucd, 1, 0, pathspec);
+ /*
+ * We get path_recurse in the first run when
+ * directory_exists_in_index() returns index_nonexistent. We
+ * are sure that new changes in the index does not impact the
+ * outcome. Return now.
+ */
+ return path_recurse;
}
static enum path_treatment treat_path(struct dir_struct *dir,
- struct dirent *de,
- char *path, int path_max,
+ struct untracked_cache_dir *untracked,
+ struct cached_dir *cdir,
+ struct index_state *istate,
+ struct strbuf *path,
int baselen,
- const struct path_simplify *simplify,
- int *len)
+ const struct pathspec *pathspec)
+{
+ if (!cdir->d_name)
+ return treat_path_fast(dir, untracked, cdir, istate, path,
+ baselen, pathspec);
+ if (is_dot_or_dotdot(cdir->d_name) || !fspathcmp(cdir->d_name, ".git"))
+ return path_none;
+ strbuf_setlen(path, baselen);
+ strbuf_addstr(path, cdir->d_name);
+ if (simplify_away(path->buf, path->len, pathspec))
+ return path_none;
+
+ return treat_one_path(dir, untracked, istate, path, baselen, pathspec,
+ cdir->d_type);
+}
+
+static void add_untracked(struct untracked_cache_dir *dir, const char *name)
+{
+ if (!dir)
+ return;
+ ALLOC_GROW(dir->untracked, dir->untracked_nr + 1,
+ dir->untracked_alloc);
+ dir->untracked[dir->untracked_nr++] = xstrdup(name);
+}
+
+static int valid_cached_dir(struct dir_struct *dir,
+ struct untracked_cache_dir *untracked,
+ struct index_state *istate,
+ struct strbuf *path,
+ int check_only)
+{
+ struct stat st;
+
+ if (!untracked)
+ return 0;
+
+ /*
+ * With fsmonitor, we can trust the untracked cache's valid field.
+ */
+ refresh_fsmonitor(istate);
+ if (!(dir->untracked->use_fsmonitor && untracked->valid)) {
+ if (lstat(path->len ? path->buf : ".", &st)) {
+ memset(&untracked->stat_data, 0, sizeof(untracked->stat_data));
+ return 0;
+ }
+ if (!untracked->valid ||
+ match_stat_data_racy(istate, &untracked->stat_data, &st)) {
+ fill_stat_data(&untracked->stat_data, &st);
+ return 0;
+ }
+ }
+
+ if (untracked->check_only != !!check_only)
+ return 0;
+
+ /*
+ * prep_exclude will be called eventually on this directory,
+ * but it's called much later in last_matching_pattern(). We
+ * need it now to determine the validity of the cache for this
+ * path. The next calls will be nearly no-op, the way
+ * prep_exclude() is designed.
+ */
+ if (path->len && path->buf[path->len - 1] != '/') {
+ strbuf_addch(path, '/');
+ prep_exclude(dir, istate, path->buf, path->len);
+ strbuf_setlen(path, path->len - 1);
+ } else
+ prep_exclude(dir, istate, path->buf, path->len);
+
+ /* hopefully prep_exclude() haven't invalidated this entry... */
+ return untracked->valid;
+}
+
+static int open_cached_dir(struct cached_dir *cdir,
+ struct dir_struct *dir,
+ struct untracked_cache_dir *untracked,
+ struct index_state *istate,
+ struct strbuf *path,
+ int check_only)
+{
+ const char *c_path;
+
+ memset(cdir, 0, sizeof(*cdir));
+ cdir->untracked = untracked;
+ if (valid_cached_dir(dir, untracked, istate, path, check_only))
+ return 0;
+ c_path = path->len ? path->buf : ".";
+ cdir->fdir = opendir(c_path);
+ if (!cdir->fdir)
+ warning_errno(_("could not open directory '%s'"), c_path);
+ if (dir->untracked) {
+ invalidate_directory(dir->untracked, untracked);
+ dir->untracked->dir_opened++;
+ }
+ if (!cdir->fdir)
+ return -1;
+ return 0;
+}
+
+static int read_cached_dir(struct cached_dir *cdir)
+{
+ struct dirent *de;
+
+ if (cdir->fdir) {
+ de = readdir(cdir->fdir);
+ if (!de) {
+ cdir->d_name = NULL;
+ cdir->d_type = DT_UNKNOWN;
+ return -1;
+ }
+ cdir->d_name = de->d_name;
+ cdir->d_type = DTYPE(de);
+ return 0;
+ }
+ while (cdir->nr_dirs < cdir->untracked->dirs_nr) {
+ struct untracked_cache_dir *d = cdir->untracked->dirs[cdir->nr_dirs];
+ if (!d->recurse) {
+ cdir->nr_dirs++;
+ continue;
+ }
+ cdir->ucd = d;
+ cdir->nr_dirs++;
+ return 0;
+ }
+ cdir->ucd = NULL;
+ if (cdir->nr_files < cdir->untracked->untracked_nr) {
+ struct untracked_cache_dir *d = cdir->untracked;
+ cdir->file = d->untracked[cdir->nr_files++];
+ return 0;
+ }
+ return -1;
+}
+
+static void close_cached_dir(struct cached_dir *cdir)
+{
+ if (cdir->fdir)
+ closedir(cdir->fdir);
+ /*
+ * We have gone through this directory and found no untracked
+ * entries. Mark it valid.
+ */
+ if (cdir->untracked) {
+ cdir->untracked->valid = 1;
+ cdir->untracked->recurse = 1;
+ }
+}
+
+static void add_path_to_appropriate_result_list(struct dir_struct *dir,
+ struct untracked_cache_dir *untracked,
+ struct cached_dir *cdir,
+ struct index_state *istate,
+ struct strbuf *path,
+ int baselen,
+ const struct pathspec *pathspec,
+ enum path_treatment state)
{
- int dtype;
+ /* add the path to the appropriate result list */
+ switch (state) {
+ case path_excluded:
+ if (dir->flags & DIR_SHOW_IGNORED)
+ dir_add_name(dir, istate, path->buf, path->len);
+ else if ((dir->flags & DIR_SHOW_IGNORED_TOO) ||
+ ((dir->flags & DIR_COLLECT_IGNORED) &&
+ exclude_matches_pathspec(path->buf, path->len,
+ pathspec)))
+ dir_add_ignored(dir, istate, path->buf, path->len);
+ break;
- 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))
- return path_ignored;
+ case path_untracked:
+ if (dir->flags & DIR_SHOW_IGNORED)
+ break;
+ dir_add_name(dir, istate, path->buf, path->len);
+ if (cdir->fdir)
+ add_untracked(untracked, path->buf + baselen);
+ break;
- dtype = DTYPE(de);
- return treat_one_path(dir, path, len, simplify, dtype, de);
+ default:
+ break;
+ }
}
/*
*
* Also, we ignore the name ".git" (even if it is not a directory).
* That likely will not change.
+ *
+ * If 'stop_at_first_file' is specified, 'path_excluded' is returned
+ * to signal that a file was found. This is the least significant value that
+ * indicates that a file was encountered that does not depend on the order of
+ * whether an untracked or exluded path was encountered first.
+ *
+ * Returns the most significant path_treatment value encountered in the scan.
+ * If 'stop_at_first_file' is specified, `path_excluded` is the most
+ * significant path_treatment value that will be returned.
*/
-static int read_directory_recursive(struct dir_struct *dir,
- const char *base, int baselen,
- int check_only,
- const struct path_simplify *simplify)
+
+static enum path_treatment read_directory_recursive(struct dir_struct *dir,
+ struct index_state *istate, const char *base, int baselen,
+ struct untracked_cache_dir *untracked, int check_only,
+ int stop_at_first_file, const struct pathspec *pathspec)
{
- DIR *fdir = opendir(*base ? base : ".");
- int contents = 0;
- struct dirent *de;
- char path[PATH_MAX + 1];
+ /*
+ * WARNING WARNING WARNING:
+ *
+ * Any updates to the traversal logic here may need corresponding
+ * updates in treat_leading_path(). See the commit message for the
+ * commit adding this warning as well as the commit preceding it
+ * for details.
+ */
- if (!fdir)
- return 0;
+ struct cached_dir cdir;
+ enum path_treatment state, subdir_state, dir_state = path_none;
+ struct strbuf path = STRBUF_INIT;
+
+ strbuf_add(&path, base, baselen);
+
+ if (open_cached_dir(&cdir, dir, untracked, istate, &path, check_only))
+ goto out;
+
+ if (untracked)
+ untracked->check_only = !!check_only;
+
+ while (!read_cached_dir(&cdir)) {
+ /* check how the file or directory should be treated */
+ state = treat_path(dir, untracked, &cdir, istate, &path,
+ baselen, pathspec);
+
+ if (state > dir_state)
+ dir_state = state;
+
+ /* recurse into subdir if instructed by treat_path */
+ if ((state == path_recurse) ||
+ ((state == path_untracked) &&
+ (resolve_dtype(cdir.d_type, istate, path.buf, path.len) == DT_DIR) &&
+ ((dir->flags & DIR_SHOW_IGNORED_TOO) ||
+ (pathspec &&
+ do_match_pathspec(istate, pathspec, path.buf, path.len,
+ baselen, NULL, DO_MATCH_LEADING_PATHSPEC) == MATCHED_RECURSIVELY_LEADING_PATHSPEC)))) {
+ struct untracked_cache_dir *ud;
+ ud = lookup_untracked(dir->untracked, untracked,
+ path.buf + baselen,
+ path.len - baselen);
+ subdir_state =
+ read_directory_recursive(dir, istate, path.buf,
+ path.len, ud,
+ check_only, stop_at_first_file, pathspec);
+ if (subdir_state > dir_state)
+ dir_state = subdir_state;
+
+ if (pathspec &&
+ !match_pathspec(istate, pathspec, path.buf, path.len,
+ 0 /* prefix */, NULL,
+ 0 /* do NOT special case dirs */))
+ state = path_none;
+ }
- memcpy(path, base, baselen);
+ if (check_only) {
+ if (stop_at_first_file) {
+ /*
+ * If stopping at first file, then
+ * signal that a file was found by
+ * returning `path_excluded`. This is
+ * to return a consistent value
+ * regardless of whether an ignored or
+ * excluded file happened to be
+ * encountered 1st.
+ *
+ * In current usage, the
+ * `stop_at_first_file` is passed when
+ * an ancestor directory has matched
+ * an exclude pattern, so any found
+ * files will be excluded.
+ */
+ if (dir_state >= path_excluded) {
+ dir_state = path_excluded;
+ break;
+ }
+ }
- while ((de = readdir(fdir)) != NULL) {
- int len;
- switch (treat_path(dir, de, path, sizeof(path),
- baselen, simplify, &len)) {
- case path_recurse:
- contents += read_directory_recursive(dir, path, len, 0, simplify);
- continue;
- case path_ignored:
+ /* abort early if maximum state has been reached */
+ if (dir_state == path_untracked) {
+ if (cdir.fdir)
+ add_untracked(untracked, path.buf + baselen);
+ break;
+ }
+ /* skip the dir_add_* part */
continue;
- case path_handled:
- break;
}
- contents++;
- if (check_only)
- goto exit_early;
- else
- dir_add_name(dir, path, len);
+
+ add_path_to_appropriate_result_list(dir, untracked, &cdir,
+ istate, &path, baselen,
+ pathspec, state);
}
-exit_early:
- closedir(fdir);
+ close_cached_dir(&cdir);
+ out:
+ strbuf_release(&path);
- return contents;
+ return dir_state;
}
-static int cmp_name(const void *p1, const void *p2)
+int cmp_dir_entry(const void *p1, const void *p2)
{
const struct dir_entry *e1 = *(const struct dir_entry **)p1;
const struct dir_entry *e2 = *(const struct dir_entry **)p2;
- return cache_name_compare(e1->name, e1->len,
- 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;
- struct path_simplify *simplify = NULL;
-
- if (!pathspec)
- return NULL;
-
- for (nr = 0 ; ; nr++) {
- const char *match;
- if (nr >= alloc) {
- alloc = alloc_nr(alloc);
- simplify = xrealloc(simplify, alloc * sizeof(*simplify));
- }
- match = *pathspec++;
- if (!match)
- break;
- simplify[nr].path = match;
- simplify[nr].len = simple_length(match);
- }
- simplify[nr].path = NULL;
- simplify[nr].len = 0;
- return simplify;
+ return name_compare(e1->name, e1->len, e2->name, e2->len);
}
-static void free_simplify(struct path_simplify *simplify)
+/* check if *out lexically strictly contains *in */
+int check_dir_entry_contains(const struct dir_entry *out, const struct dir_entry *in)
{
- free(simplify);
+ return (out->len < in->len) &&
+ (out->name[out->len - 1] == '/') &&
+ !memcmp(out->name, in->name, out->len);
}
static int treat_leading_path(struct dir_struct *dir,
+ struct index_state *istate,
const char *path, int len,
- const struct path_simplify *simplify)
+ const struct pathspec *pathspec)
{
- char pathbuf[PATH_MAX];
- int baselen, blen;
+ /*
+ * WARNING WARNING WARNING:
+ *
+ * Any updates to the traversal logic here may need corresponding
+ * updates in read_directory_recursive(). See 777b420347 (dir:
+ * synchronize treat_leading_path() and read_directory_recursive(),
+ * 2019-12-19) and its parent commit for details.
+ */
+
+ struct strbuf sb = STRBUF_INIT;
+ struct strbuf subdir = STRBUF_INIT;
+ int prevlen, baselen;
const char *cp;
+ struct cached_dir cdir;
+ enum path_treatment state = path_none;
+
+ /*
+ * For each directory component of path, we are going to check whether
+ * that path is relevant given the pathspec. For example, if path is
+ * foo/bar/baz/
+ * then we will ask treat_path() whether we should go into foo, then
+ * whether we should go into bar, then whether baz is relevant.
+ * Checking each is important because e.g. if path is
+ * .git/info/
+ * then we need to check .git to know we shouldn't traverse it.
+ * If the return from treat_path() is:
+ * * path_none, for any path, we return false.
+ * * path_recurse, for all path components, we return true
+ * * <anything else> for some intermediate component, we make sure
+ * to add that path to the relevant list but return false
+ * signifying that we shouldn't recurse into it.
+ */
while (len && path[len - 1] == '/')
len--;
if (!len)
return 1;
+
+ memset(&cdir, 0, sizeof(cdir));
+ cdir.d_type = DT_DIR;
baselen = 0;
+ prevlen = 0;
while (1) {
- cp = path + baselen + !!baselen;
+ prevlen = baselen + !!baselen;
+ cp = path + prevlen;
cp = memchr(cp, '/', path + len - cp);
if (!cp)
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,
- DT_DIR, NULL) == path_ignored)
- return 0; /* do not recurse into it */
+ strbuf_reset(&sb);
+ strbuf_add(&sb, path, baselen);
+ if (!is_directory(sb.buf))
+ break;
+ strbuf_reset(&sb);
+ strbuf_add(&sb, path, prevlen);
+ strbuf_reset(&subdir);
+ strbuf_add(&subdir, path+prevlen, baselen-prevlen);
+ cdir.d_name = subdir.buf;
+ state = treat_path(dir, NULL, &cdir, istate, &sb, prevlen,
+ pathspec);
+ if (state == path_untracked &&
+ resolve_dtype(cdir.d_type, istate, sb.buf, sb.len) == DT_DIR &&
+ (dir->flags & DIR_SHOW_IGNORED_TOO ||
+ do_match_pathspec(istate, pathspec, sb.buf, sb.len,
+ baselen, NULL, DO_MATCH_LEADING_PATHSPEC) == MATCHED_RECURSIVELY_LEADING_PATHSPEC)) {
+ if (!match_pathspec(istate, pathspec, sb.buf, sb.len,
+ 0 /* prefix */, NULL,
+ 0 /* do NOT special case dirs */))
+ state = path_none;
+ add_path_to_appropriate_result_list(dir, NULL, &cdir,
+ istate,
+ &sb, baselen,
+ pathspec, state);
+ state = path_recurse;
+ }
+
+ if (state != path_recurse)
+ break; /* do not recurse into it */
if (len <= baselen)
- return 1; /* finished checking */
+ break; /* finished checking */
+ }
+ add_path_to_appropriate_result_list(dir, NULL, &cdir, istate,
+ &sb, baselen, pathspec,
+ state);
+
+ strbuf_release(&subdir);
+ strbuf_release(&sb);
+ return state == path_recurse;
+}
+
+static const char *get_ident_string(void)
+{
+ static struct strbuf sb = STRBUF_INIT;
+ struct utsname uts;
+
+ if (sb.len)
+ return sb.buf;
+ if (uname(&uts) < 0)
+ die_errno(_("failed to get kernel name and information"));
+ strbuf_addf(&sb, "Location %s, system %s", get_git_work_tree(),
+ uts.sysname);
+ return sb.buf;
+}
+
+static int ident_in_untracked(const struct untracked_cache *uc)
+{
+ /*
+ * Previous git versions may have saved many NUL separated
+ * strings in the "ident" field, but it is insane to manage
+ * many locations, so just take care of the first one.
+ */
+
+ return !strcmp(uc->ident.buf, get_ident_string());
+}
+
+static void set_untracked_ident(struct untracked_cache *uc)
+{
+ strbuf_reset(&uc->ident);
+ strbuf_addstr(&uc->ident, get_ident_string());
+
+ /*
+ * This strbuf used to contain a list of NUL separated
+ * strings, so save NUL too for backward compatibility.
+ */
+ strbuf_addch(&uc->ident, 0);
+}
+
+static void new_untracked_cache(struct index_state *istate)
+{
+ struct untracked_cache *uc = xcalloc(1, sizeof(*uc));
+ strbuf_init(&uc->ident, 100);
+ uc->exclude_per_dir = ".gitignore";
+ /* should be the same flags used by git-status */
+ uc->dir_flags = DIR_SHOW_OTHER_DIRECTORIES | DIR_HIDE_EMPTY_DIRECTORIES;
+ set_untracked_ident(uc);
+ istate->untracked = uc;
+ istate->cache_changed |= UNTRACKED_CHANGED;
+}
+
+void add_untracked_cache(struct index_state *istate)
+{
+ if (!istate->untracked) {
+ new_untracked_cache(istate);
+ } else {
+ if (!ident_in_untracked(istate->untracked)) {
+ free_untracked_cache(istate->untracked);
+ new_untracked_cache(istate);
+ }
+ }
+}
+
+void remove_untracked_cache(struct index_state *istate)
+{
+ if (istate->untracked) {
+ free_untracked_cache(istate->untracked);
+ istate->untracked = NULL;
+ istate->cache_changed |= UNTRACKED_CHANGED;
+ }
+}
+
+static struct untracked_cache_dir *validate_untracked_cache(struct dir_struct *dir,
+ int base_len,
+ const struct pathspec *pathspec)
+{
+ struct untracked_cache_dir *root;
+ static int untracked_cache_disabled = -1;
+
+ if (!dir->untracked)
+ return NULL;
+ if (untracked_cache_disabled < 0)
+ untracked_cache_disabled = git_env_bool("GIT_DISABLE_UNTRACKED_CACHE", 0);
+ if (untracked_cache_disabled)
+ return NULL;
+
+ /*
+ * We only support $GIT_DIR/info/exclude and core.excludesfile
+ * as the global ignore rule files. Any other additions
+ * (e.g. from command line) invalidate the cache. This
+ * condition also catches running setup_standard_excludes()
+ * before setting dir->untracked!
+ */
+ if (dir->unmanaged_exclude_files)
+ return NULL;
+
+ /*
+ * Optimize for the main use case only: whole-tree git
+ * status. More work involved in treat_leading_path() if we
+ * use cache on just a subset of the worktree. pathspec
+ * support could make the matter even worse.
+ */
+ if (base_len || (pathspec && pathspec->nr))
+ return NULL;
+
+ /* Different set of flags may produce different results */
+ if (dir->flags != dir->untracked->dir_flags ||
+ /*
+ * See treat_directory(), case index_nonexistent. Without
+ * this flag, we may need to also cache .git file content
+ * for the resolve_gitlink_ref() call, which we don't.
+ */
+ !(dir->flags & DIR_SHOW_OTHER_DIRECTORIES) ||
+ /* We don't support collecting ignore files */
+ (dir->flags & (DIR_SHOW_IGNORED | DIR_SHOW_IGNORED_TOO |
+ DIR_COLLECT_IGNORED)))
+ return NULL;
+
+ /*
+ * If we use .gitignore in the cache and now you change it to
+ * .gitexclude, everything will go wrong.
+ */
+ if (dir->exclude_per_dir != dir->untracked->exclude_per_dir &&
+ strcmp(dir->exclude_per_dir, dir->untracked->exclude_per_dir))
+ return NULL;
+
+ /*
+ * EXC_CMDL is not considered in the cache. If people set it,
+ * skip the cache.
+ */
+ if (dir->exclude_list_group[EXC_CMDL].nr)
+ return NULL;
+
+ if (!ident_in_untracked(dir->untracked)) {
+ warning(_("untracked cache is disabled on this system or location"));
+ return NULL;
+ }
+
+ if (!dir->untracked->root) {
+ const int len = sizeof(*dir->untracked->root);
+ dir->untracked->root = xmalloc(len);
+ memset(dir->untracked->root, 0, len);
+ }
+
+ /* Validate $GIT_DIR/info/exclude and core.excludesfile */
+ root = dir->untracked->root;
+ if (!oideq(&dir->ss_info_exclude.oid,
+ &dir->untracked->ss_info_exclude.oid)) {
+ invalidate_gitignore(dir->untracked, root);
+ dir->untracked->ss_info_exclude = dir->ss_info_exclude;
+ }
+ if (!oideq(&dir->ss_excludes_file.oid,
+ &dir->untracked->ss_excludes_file.oid)) {
+ invalidate_gitignore(dir->untracked, root);
+ dir->untracked->ss_excludes_file = dir->ss_excludes_file;
}
+
+ /* Make sure this directory is not dropped out at saving phase */
+ root->recurse = 1;
+ return root;
}
-int read_directory(struct dir_struct *dir, const char *path, int len, const char **pathspec)
+int read_directory(struct dir_struct *dir, struct index_state *istate,
+ const char *path, int len, const struct pathspec *pathspec)
{
- struct path_simplify *simplify;
+ struct untracked_cache_dir *untracked;
+
+ trace_performance_enter();
- if (has_symlink_leading_path(path, len))
+ if (has_symlink_leading_path(path, len)) {
+ trace_performance_leave("read directory %.*s", len, path);
return dir->nr;
+ }
+
+ untracked = validate_untracked_cache(dir, len, pathspec);
+ if (!untracked)
+ /*
+ * make sure untracked cache code path is disabled,
+ * e.g. prep_exclude()
+ */
+ dir->untracked = NULL;
+ if (!len || treat_leading_path(dir, istate, path, len, pathspec))
+ read_directory_recursive(dir, istate, path, len, untracked, 0, 0, pathspec);
+ QSORT(dir->entries, dir->nr, cmp_dir_entry);
+ QSORT(dir->ignored, dir->ignored_nr, cmp_dir_entry);
- simplify = create_simplify(pathspec);
- if (!len || treat_leading_path(dir, path, len, simplify))
- read_directory_recursive(dir, path, len, 0, simplify);
- free_simplify(simplify);
- qsort(dir->entries, dir->nr, sizeof(struct dir_entry *), cmp_name);
- qsort(dir->ignored, dir->ignored_nr, sizeof(struct dir_entry *), cmp_name);
+ /*
+ * If DIR_SHOW_IGNORED_TOO is set, read_directory_recursive() will
+ * also pick up untracked contents of untracked dirs; by default
+ * we discard these, but given DIR_KEEP_UNTRACKED_CONTENTS we do not.
+ */
+ if ((dir->flags & DIR_SHOW_IGNORED_TOO) &&
+ !(dir->flags & DIR_KEEP_UNTRACKED_CONTENTS)) {
+ int i, j;
+
+ /* remove from dir->entries untracked contents of untracked dirs */
+ for (i = j = 0; j < dir->nr; j++) {
+ if (i &&
+ check_dir_entry_contains(dir->entries[i - 1], dir->entries[j])) {
+ FREE_AND_NULL(dir->entries[j]);
+ } else {
+ dir->entries[i++] = dir->entries[j];
+ }
+ }
+
+ dir->nr = i;
+ }
+
+ trace_performance_leave("read directory %.*s", len, path);
+ if (dir->untracked) {
+ static int force_untracked_cache = -1;
+ static struct trace_key trace_untracked_stats = TRACE_KEY_INIT(UNTRACKED_STATS);
+
+ if (force_untracked_cache < 0)
+ force_untracked_cache =
+ git_env_bool("GIT_FORCE_UNTRACKED_CACHE", 0);
+ trace_printf_key(&trace_untracked_stats,
+ "node creation: %u\n"
+ "gitignore invalidation: %u\n"
+ "directory invalidation: %u\n"
+ "opendir: %u\n",
+ dir->untracked->dir_created,
+ dir->untracked->gitignore_invalidated,
+ dir->untracked->dir_invalidated,
+ dir->untracked->dir_opened);
+ if (force_untracked_cache &&
+ dir->untracked == istate->untracked &&
+ (dir->untracked->dir_opened ||
+ dir->untracked->gitignore_invalidated ||
+ dir->untracked->dir_invalidated))
+ istate->cache_changed |= UNTRACKED_CHANGED;
+ if (dir->untracked != istate->untracked) {
+ FREE_AND_NULL(dir->untracked);
+ }
+ }
return dir->nr;
}
return lstat(f, &sb) == 0;
}
+int repo_file_exists(struct repository *repo, const char *path)
+{
+ if (repo != the_repository)
+ BUG("do not know how to check file existence in arbitrary repo");
+
+ return file_exists(path);
+}
+
+static int cmp_icase(char a, char b)
+{
+ if (a == b)
+ return 0;
+ if (ignore_case)
+ return toupper(a) - toupper(b);
+ return a - b;
+}
+
/*
* Given two normalized paths (a trailing slash is ok), if subdir is
* outside dir, return -1. Otherwise return the offset in subdir that
assert(dir && subdir && *dir && *subdir);
- while (*dir && *subdir && *dir == *subdir) {
+ while (*dir && *subdir && !cmp_icase(*dir, *subdir)) {
dir++;
subdir++;
offset++;
int is_inside_dir(const char *dir)
{
- char cwd[PATH_MAX];
+ char *cwd;
+ int rc;
+
if (!dir)
return 0;
- if (!getcwd(cwd, sizeof(cwd)))
- die_errno("can't find the current directory");
- return dir_inside_of(cwd, dir) >= 0;
+
+ cwd = xgetcwd();
+ rc = (dir_inside_of(cwd, dir) >= 0);
+ free(cwd);
+ return rc;
}
int is_empty_dir(const char *path)
int ret = 0, original_len = path->len, len, kept_down = 0;
int only_empty = (flag & REMOVE_DIR_EMPTY_ONLY);
int keep_toplevel = (flag & REMOVE_DIR_KEEP_TOPLEVEL);
- unsigned char submodule_head[20];
+ struct object_id submodule_head;
if ((flag & REMOVE_DIR_KEEP_NESTED_GIT) &&
- !resolve_gitlink_ref(path->buf, "HEAD", submodule_head)) {
+ !resolve_gitlink_ref(path->buf, "HEAD", &submodule_head)) {
/* Do not descend and nuke a nested git work tree. */
if (kept_up)
*kept_up = 1;
flag &= ~REMOVE_DIR_KEEP_TOPLEVEL;
dir = opendir(path->buf);
if (!dir) {
- /* an empty dir could be removed even if it is unreadble */
- if (!keep_toplevel)
+ if (errno == ENOENT)
+ return keep_toplevel ? -1 : 0;
+ else if (errno == EACCES && !keep_toplevel)
+ /*
+ * An empty dir could be removable even if it
+ * is unreadable:
+ */
return rmdir(path->buf);
else
return -1;
}
- if (path->buf[original_len - 1] != '/')
- strbuf_addch(path, '/');
+ strbuf_complete(path, '/');
len = path->len;
while ((e = readdir(dir)) != NULL) {
strbuf_setlen(path, len);
strbuf_addstr(path, e->d_name);
- if (lstat(path->buf, &st))
- ; /* fall thru */
- else if (S_ISDIR(st.st_mode)) {
+ if (lstat(path->buf, &st)) {
+ if (errno == ENOENT)
+ /*
+ * file disappeared, which is what we
+ * wanted anyway
+ */
+ continue;
+ /* fall through */
+ } else if (S_ISDIR(st.st_mode)) {
if (!remove_dir_recurse(path, flag, &kept_down))
continue; /* happy */
- } else if (!only_empty && !unlink(path->buf))
+ } else if (!only_empty &&
+ (!unlink(path->buf) || errno == ENOENT)) {
continue; /* happy, too */
+ }
/* path too long, stat fails, or non-directory still exists */
ret = -1;
strbuf_setlen(path, original_len);
if (!ret && !keep_toplevel && !kept_down)
- ret = rmdir(path->buf);
+ ret = (!rmdir(path->buf) || errno == ENOENT) ? 0 : -1;
else if (kept_up)
/*
* report the uplevel that it is not an error that we
return remove_dir_recurse(path, flag, NULL);
}
+static GIT_PATH_FUNC(git_path_info_exclude, "info/exclude")
+
void setup_standard_excludes(struct dir_struct *dir)
{
- const char *path;
-
dir->exclude_per_dir = ".gitignore";
- path = git_path("info/exclude");
- if (!access(path, R_OK))
- add_excludes_from_file(dir, path);
- if (excludes_file && !access(excludes_file, R_OK))
- add_excludes_from_file(dir, excludes_file);
+
+ /* core.excludesfile defaulting to $XDG_CONFIG_HOME/git/ignore */
+ if (!excludes_file)
+ excludes_file = xdg_config_home("ignore");
+ if (excludes_file && !access_or_warn(excludes_file, R_OK, 0))
+ add_patterns_from_file_1(dir, excludes_file,
+ dir->untracked ? &dir->ss_excludes_file : NULL);
+
+ /* per repository user preference */
+ if (startup_info->have_repository) {
+ const char *path = git_path_info_exclude();
+ if (!access_or_warn(path, R_OK, 0))
+ add_patterns_from_file_1(dir, path,
+ dir->untracked ? &dir->ss_info_exclude : NULL);
+ }
}
int remove_path(const char *name)
{
char *slash;
- if (unlink(name) && errno != ENOENT)
+ if (unlink(name) && !is_missing_file_error(errno))
return -1;
slash = strrchr(name, '/');
return 0;
}
-static int pathspec_item_cmp(const void *a_, const void *b_)
+/*
+ * Frees memory within dir which was allocated for exclude lists and
+ * the exclude_stack. Does not free dir itself.
+ */
+void clear_directory(struct dir_struct *dir)
+{
+ int i, j;
+ struct exclude_list_group *group;
+ struct pattern_list *pl;
+ struct exclude_stack *stk;
+
+ for (i = EXC_CMDL; i <= EXC_FILE; i++) {
+ group = &dir->exclude_list_group[i];
+ for (j = 0; j < group->nr; j++) {
+ pl = &group->pl[j];
+ if (i == EXC_DIRS)
+ free((char *)pl->src);
+ clear_pattern_list(pl);
+ }
+ free(group->pl);
+ }
+
+ stk = dir->exclude_stack;
+ while (stk) {
+ struct exclude_stack *prev = stk->prev;
+ free(stk);
+ stk = prev;
+ }
+ strbuf_release(&dir->basebuf);
+}
+
+struct ondisk_untracked_cache {
+ struct stat_data info_exclude_stat;
+ struct stat_data excludes_file_stat;
+ uint32_t dir_flags;
+};
+
+#define ouc_offset(x) offsetof(struct ondisk_untracked_cache, x)
+
+struct write_data {
+ int index; /* number of written untracked_cache_dir */
+ struct ewah_bitmap *check_only; /* from untracked_cache_dir */
+ struct ewah_bitmap *valid; /* from untracked_cache_dir */
+ struct ewah_bitmap *sha1_valid; /* set if exclude_sha1 is not null */
+ struct strbuf out;
+ struct strbuf sb_stat;
+ struct strbuf sb_sha1;
+};
+
+static void stat_data_to_disk(struct stat_data *to, const struct stat_data *from)
+{
+ to->sd_ctime.sec = htonl(from->sd_ctime.sec);
+ to->sd_ctime.nsec = htonl(from->sd_ctime.nsec);
+ to->sd_mtime.sec = htonl(from->sd_mtime.sec);
+ to->sd_mtime.nsec = htonl(from->sd_mtime.nsec);
+ to->sd_dev = htonl(from->sd_dev);
+ to->sd_ino = htonl(from->sd_ino);
+ to->sd_uid = htonl(from->sd_uid);
+ to->sd_gid = htonl(from->sd_gid);
+ to->sd_size = htonl(from->sd_size);
+}
+
+static void write_one_dir(struct untracked_cache_dir *untracked,
+ struct write_data *wd)
+{
+ struct stat_data stat_data;
+ struct strbuf *out = &wd->out;
+ unsigned char intbuf[16];
+ unsigned int intlen, value;
+ int i = wd->index++;
+
+ /*
+ * untracked_nr should be reset whenever valid is clear, but
+ * for safety..
+ */
+ if (!untracked->valid) {
+ untracked->untracked_nr = 0;
+ untracked->check_only = 0;
+ }
+
+ if (untracked->check_only)
+ ewah_set(wd->check_only, i);
+ if (untracked->valid) {
+ ewah_set(wd->valid, i);
+ stat_data_to_disk(&stat_data, &untracked->stat_data);
+ strbuf_add(&wd->sb_stat, &stat_data, sizeof(stat_data));
+ }
+ if (!is_null_oid(&untracked->exclude_oid)) {
+ ewah_set(wd->sha1_valid, i);
+ strbuf_add(&wd->sb_sha1, untracked->exclude_oid.hash,
+ the_hash_algo->rawsz);
+ }
+
+ intlen = encode_varint(untracked->untracked_nr, intbuf);
+ strbuf_add(out, intbuf, intlen);
+
+ /* skip non-recurse directories */
+ for (i = 0, value = 0; i < untracked->dirs_nr; i++)
+ if (untracked->dirs[i]->recurse)
+ value++;
+ intlen = encode_varint(value, intbuf);
+ strbuf_add(out, intbuf, intlen);
+
+ strbuf_add(out, untracked->name, strlen(untracked->name) + 1);
+
+ for (i = 0; i < untracked->untracked_nr; i++)
+ strbuf_add(out, untracked->untracked[i],
+ strlen(untracked->untracked[i]) + 1);
+
+ for (i = 0; i < untracked->dirs_nr; i++)
+ if (untracked->dirs[i]->recurse)
+ write_one_dir(untracked->dirs[i], wd);
+}
+
+void write_untracked_extension(struct strbuf *out, struct untracked_cache *untracked)
{
- struct pathspec_item *a, *b;
+ struct ondisk_untracked_cache *ouc;
+ struct write_data wd;
+ unsigned char varbuf[16];
+ int varint_len;
+ const unsigned hashsz = the_hash_algo->rawsz;
+
+ ouc = xcalloc(1, sizeof(*ouc));
+ stat_data_to_disk(&ouc->info_exclude_stat, &untracked->ss_info_exclude.stat);
+ stat_data_to_disk(&ouc->excludes_file_stat, &untracked->ss_excludes_file.stat);
+ ouc->dir_flags = htonl(untracked->dir_flags);
+
+ varint_len = encode_varint(untracked->ident.len, varbuf);
+ strbuf_add(out, varbuf, varint_len);
+ strbuf_addbuf(out, &untracked->ident);
+
+ strbuf_add(out, ouc, sizeof(*ouc));
+ strbuf_add(out, untracked->ss_info_exclude.oid.hash, hashsz);
+ strbuf_add(out, untracked->ss_excludes_file.oid.hash, hashsz);
+ strbuf_add(out, untracked->exclude_per_dir, strlen(untracked->exclude_per_dir) + 1);
+ FREE_AND_NULL(ouc);
+
+ if (!untracked->root) {
+ varint_len = encode_varint(0, varbuf);
+ strbuf_add(out, varbuf, varint_len);
+ return;
+ }
- a = (struct pathspec_item *)a_;
- b = (struct pathspec_item *)b_;
- return strcmp(a->match, b->match);
+ wd.index = 0;
+ wd.check_only = ewah_new();
+ wd.valid = ewah_new();
+ wd.sha1_valid = ewah_new();
+ strbuf_init(&wd.out, 1024);
+ strbuf_init(&wd.sb_stat, 1024);
+ strbuf_init(&wd.sb_sha1, 1024);
+ write_one_dir(untracked->root, &wd);
+
+ varint_len = encode_varint(wd.index, varbuf);
+ strbuf_add(out, varbuf, varint_len);
+ strbuf_addbuf(out, &wd.out);
+ ewah_serialize_strbuf(wd.valid, out);
+ ewah_serialize_strbuf(wd.check_only, out);
+ ewah_serialize_strbuf(wd.sha1_valid, out);
+ strbuf_addbuf(out, &wd.sb_stat);
+ strbuf_addbuf(out, &wd.sb_sha1);
+ strbuf_addch(out, '\0'); /* safe guard for string lists */
+
+ ewah_free(wd.valid);
+ ewah_free(wd.check_only);
+ ewah_free(wd.sha1_valid);
+ strbuf_release(&wd.out);
+ strbuf_release(&wd.sb_stat);
+ strbuf_release(&wd.sb_sha1);
}
-int init_pathspec(struct pathspec *pathspec, const char **paths)
+static void free_untracked(struct untracked_cache_dir *ucd)
{
- const char **p = paths;
int i;
+ if (!ucd)
+ return;
+ for (i = 0; i < ucd->dirs_nr; i++)
+ free_untracked(ucd->dirs[i]);
+ for (i = 0; i < ucd->untracked_nr; i++)
+ free(ucd->untracked[i]);
+ free(ucd->untracked);
+ free(ucd->dirs);
+ free(ucd);
+}
- memset(pathspec, 0, sizeof(*pathspec));
- if (!p)
- return 0;
- while (*p)
- p++;
- pathspec->raw = paths;
- pathspec->nr = p - paths;
- if (!pathspec->nr)
- return 0;
+void free_untracked_cache(struct untracked_cache *uc)
+{
+ if (uc)
+ free_untracked(uc->root);
+ free(uc);
+}
- 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];
+struct read_data {
+ int index;
+ struct untracked_cache_dir **ucd;
+ struct ewah_bitmap *check_only;
+ struct ewah_bitmap *valid;
+ struct ewah_bitmap *sha1_valid;
+ const unsigned char *data;
+ const unsigned char *end;
+};
+
+static void stat_data_from_disk(struct stat_data *to, const unsigned char *data)
+{
+ memcpy(to, data, sizeof(*to));
+ to->sd_ctime.sec = ntohl(to->sd_ctime.sec);
+ to->sd_ctime.nsec = ntohl(to->sd_ctime.nsec);
+ to->sd_mtime.sec = ntohl(to->sd_mtime.sec);
+ to->sd_mtime.nsec = ntohl(to->sd_mtime.nsec);
+ to->sd_dev = ntohl(to->sd_dev);
+ to->sd_ino = ntohl(to->sd_ino);
+ to->sd_uid = ntohl(to->sd_uid);
+ to->sd_gid = ntohl(to->sd_gid);
+ to->sd_size = ntohl(to->sd_size);
+}
- item->match = path;
- item->len = strlen(path);
- item->use_wildcard = !no_wildcard(path);
- if (item->use_wildcard)
- pathspec->has_wildcard = 1;
+static int read_one_dir(struct untracked_cache_dir **untracked_,
+ struct read_data *rd)
+{
+ struct untracked_cache_dir ud, *untracked;
+ const unsigned char *data = rd->data, *end = rd->end;
+ const unsigned char *eos;
+ unsigned int value;
+ int i;
+
+ memset(&ud, 0, sizeof(ud));
+
+ value = decode_varint(&data);
+ if (data > end)
+ return -1;
+ ud.recurse = 1;
+ ud.untracked_alloc = value;
+ ud.untracked_nr = value;
+ if (ud.untracked_nr)
+ ALLOC_ARRAY(ud.untracked, ud.untracked_nr);
+
+ ud.dirs_alloc = ud.dirs_nr = decode_varint(&data);
+ if (data > end)
+ return -1;
+ ALLOC_ARRAY(ud.dirs, ud.dirs_nr);
+
+ eos = memchr(data, '\0', end - data);
+ if (!eos || eos == end)
+ return -1;
+
+ *untracked_ = untracked = xmalloc(st_add3(sizeof(*untracked), eos - data, 1));
+ memcpy(untracked, &ud, sizeof(ud));
+ memcpy(untracked->name, data, eos - data + 1);
+ data = eos + 1;
+
+ for (i = 0; i < untracked->untracked_nr; i++) {
+ eos = memchr(data, '\0', end - data);
+ if (!eos || eos == end)
+ return -1;
+ untracked->untracked[i] = xmemdupz(data, eos - data);
+ data = eos + 1;
}
- qsort(pathspec->items, pathspec->nr,
- sizeof(struct pathspec_item), pathspec_item_cmp);
+ rd->ucd[rd->index++] = untracked;
+ rd->data = data;
+ for (i = 0; i < untracked->dirs_nr; i++) {
+ if (read_one_dir(untracked->dirs + i, rd) < 0)
+ return -1;
+ }
return 0;
}
-void free_pathspec(struct pathspec *pathspec)
+static void set_check_only(size_t pos, void *cb)
+{
+ struct read_data *rd = cb;
+ struct untracked_cache_dir *ud = rd->ucd[pos];
+ ud->check_only = 1;
+}
+
+static void read_stat(size_t pos, void *cb)
{
- free(pathspec->items);
- pathspec->items = NULL;
+ struct read_data *rd = cb;
+ struct untracked_cache_dir *ud = rd->ucd[pos];
+ if (rd->data + sizeof(struct stat_data) > rd->end) {
+ rd->data = rd->end + 1;
+ return;
+ }
+ stat_data_from_disk(&ud->stat_data, rd->data);
+ rd->data += sizeof(struct stat_data);
+ ud->valid = 1;
+}
+
+static void read_oid(size_t pos, void *cb)
+{
+ struct read_data *rd = cb;
+ struct untracked_cache_dir *ud = rd->ucd[pos];
+ if (rd->data + the_hash_algo->rawsz > rd->end) {
+ rd->data = rd->end + 1;
+ return;
+ }
+ hashcpy(ud->exclude_oid.hash, rd->data);
+ rd->data += the_hash_algo->rawsz;
+}
+
+static void load_oid_stat(struct oid_stat *oid_stat, const unsigned char *data,
+ const unsigned char *sha1)
+{
+ stat_data_from_disk(&oid_stat->stat, data);
+ hashcpy(oid_stat->oid.hash, sha1);
+ oid_stat->valid = 1;
+}
+
+struct untracked_cache *read_untracked_extension(const void *data, unsigned long sz)
+{
+ struct untracked_cache *uc;
+ struct read_data rd;
+ const unsigned char *next = data, *end = (const unsigned char *)data + sz;
+ const char *ident;
+ int ident_len;
+ ssize_t len;
+ const char *exclude_per_dir;
+ const unsigned hashsz = the_hash_algo->rawsz;
+ const unsigned offset = sizeof(struct ondisk_untracked_cache);
+ const unsigned exclude_per_dir_offset = offset + 2 * hashsz;
+
+ if (sz <= 1 || end[-1] != '\0')
+ return NULL;
+ end--;
+
+ ident_len = decode_varint(&next);
+ if (next + ident_len > end)
+ return NULL;
+ ident = (const char *)next;
+ next += ident_len;
+
+ if (next + exclude_per_dir_offset + 1 > end)
+ return NULL;
+
+ uc = xcalloc(1, sizeof(*uc));
+ strbuf_init(&uc->ident, ident_len);
+ strbuf_add(&uc->ident, ident, ident_len);
+ load_oid_stat(&uc->ss_info_exclude,
+ next + ouc_offset(info_exclude_stat),
+ next + offset);
+ load_oid_stat(&uc->ss_excludes_file,
+ next + ouc_offset(excludes_file_stat),
+ next + offset + hashsz);
+ uc->dir_flags = get_be32(next + ouc_offset(dir_flags));
+ exclude_per_dir = (const char *)next + exclude_per_dir_offset;
+ uc->exclude_per_dir = xstrdup(exclude_per_dir);
+ /* NUL after exclude_per_dir is covered by sizeof(*ouc) */
+ next += exclude_per_dir_offset + strlen(exclude_per_dir) + 1;
+ if (next >= end)
+ goto done2;
+
+ len = decode_varint(&next);
+ if (next > end || len == 0)
+ goto done2;
+
+ rd.valid = ewah_new();
+ rd.check_only = ewah_new();
+ rd.sha1_valid = ewah_new();
+ rd.data = next;
+ rd.end = end;
+ rd.index = 0;
+ ALLOC_ARRAY(rd.ucd, len);
+
+ if (read_one_dir(&uc->root, &rd) || rd.index != len)
+ goto done;
+
+ next = rd.data;
+ len = ewah_read_mmap(rd.valid, next, end - next);
+ if (len < 0)
+ goto done;
+
+ next += len;
+ len = ewah_read_mmap(rd.check_only, next, end - next);
+ if (len < 0)
+ goto done;
+
+ next += len;
+ len = ewah_read_mmap(rd.sha1_valid, next, end - next);
+ if (len < 0)
+ goto done;
+
+ ewah_each_bit(rd.check_only, set_check_only, &rd);
+ rd.data = next + len;
+ ewah_each_bit(rd.valid, read_stat, &rd);
+ ewah_each_bit(rd.sha1_valid, read_oid, &rd);
+ next = rd.data;
+
+done:
+ free(rd.ucd);
+ ewah_free(rd.valid);
+ ewah_free(rd.check_only);
+ ewah_free(rd.sha1_valid);
+done2:
+ if (next != end) {
+ free_untracked_cache(uc);
+ uc = NULL;
+ }
+ return uc;
+}
+
+static void invalidate_one_directory(struct untracked_cache *uc,
+ struct untracked_cache_dir *ucd)
+{
+ uc->dir_invalidated++;
+ ucd->valid = 0;
+ ucd->untracked_nr = 0;
+}
+
+/*
+ * Normally when an entry is added or removed from a directory,
+ * invalidating that directory is enough. No need to touch its
+ * ancestors. When a directory is shown as "foo/bar/" in git-status
+ * however, deleting or adding an entry may have cascading effect.
+ *
+ * Say the "foo/bar/file" has become untracked, we need to tell the
+ * untracked_cache_dir of "foo" that "bar/" is not an untracked
+ * directory any more (because "bar" is managed by foo as an untracked
+ * "file").
+ *
+ * Similarly, if "foo/bar/file" moves from untracked to tracked and it
+ * was the last untracked entry in the entire "foo", we should show
+ * "foo/" instead. Which means we have to invalidate past "bar" up to
+ * "foo".
+ *
+ * This function traverses all directories from root to leaf. If there
+ * is a chance of one of the above cases happening, we invalidate back
+ * to root. Otherwise we just invalidate the leaf. There may be a more
+ * sophisticated way than checking for SHOW_OTHER_DIRECTORIES to
+ * detect these cases and avoid unnecessary invalidation, for example,
+ * checking for the untracked entry named "bar/" in "foo", but for now
+ * stick to something safe and simple.
+ */
+static int invalidate_one_component(struct untracked_cache *uc,
+ struct untracked_cache_dir *dir,
+ const char *path, int len)
+{
+ const char *rest = strchr(path, '/');
+
+ if (rest) {
+ int component_len = rest - path;
+ struct untracked_cache_dir *d =
+ lookup_untracked(uc, dir, path, component_len);
+ int ret =
+ invalidate_one_component(uc, d, rest + 1,
+ len - (component_len + 1));
+ if (ret)
+ invalidate_one_directory(uc, dir);
+ return ret;
+ }
+
+ invalidate_one_directory(uc, dir);
+ return uc->dir_flags & DIR_SHOW_OTHER_DIRECTORIES;
+}
+
+void untracked_cache_invalidate_path(struct index_state *istate,
+ const char *path, int safe_path)
+{
+ if (!istate->untracked || !istate->untracked->root)
+ return;
+ if (!safe_path && !verify_path(path, 0))
+ return;
+ invalidate_one_component(istate->untracked, istate->untracked->root,
+ path, strlen(path));
+}
+
+void untracked_cache_remove_from_index(struct index_state *istate,
+ const char *path)
+{
+ untracked_cache_invalidate_path(istate, path, 1);
+}
+
+void untracked_cache_add_to_index(struct index_state *istate,
+ const char *path)
+{
+ untracked_cache_invalidate_path(istate, path, 1);
+}
+
+static void connect_wt_gitdir_in_nested(const char *sub_worktree,
+ const char *sub_gitdir)
+{
+ int i;
+ struct repository subrepo;
+ struct strbuf sub_wt = STRBUF_INIT;
+ struct strbuf sub_gd = STRBUF_INIT;
+
+ const struct submodule *sub;
+
+ /* If the submodule has no working tree, we can ignore it. */
+ if (repo_init(&subrepo, sub_gitdir, sub_worktree))
+ return;
+
+ if (repo_read_index(&subrepo) < 0)
+ die(_("index file corrupt in repo %s"), subrepo.gitdir);
+
+ for (i = 0; i < subrepo.index->cache_nr; i++) {
+ const struct cache_entry *ce = subrepo.index->cache[i];
+
+ if (!S_ISGITLINK(ce->ce_mode))
+ continue;
+
+ while (i + 1 < subrepo.index->cache_nr &&
+ !strcmp(ce->name, subrepo.index->cache[i + 1]->name))
+ /*
+ * Skip entries with the same name in different stages
+ * to make sure an entry is returned only once.
+ */
+ i++;
+
+ sub = submodule_from_path(&subrepo, &null_oid, ce->name);
+ if (!sub || !is_submodule_active(&subrepo, ce->name))
+ /* .gitmodules broken or inactive sub */
+ continue;
+
+ strbuf_reset(&sub_wt);
+ strbuf_reset(&sub_gd);
+ strbuf_addf(&sub_wt, "%s/%s", sub_worktree, sub->path);
+ strbuf_addf(&sub_gd, "%s/modules/%s", sub_gitdir, sub->name);
+
+ connect_work_tree_and_git_dir(sub_wt.buf, sub_gd.buf, 1);
+ }
+ strbuf_release(&sub_wt);
+ strbuf_release(&sub_gd);
+ repo_clear(&subrepo);
+}
+
+void connect_work_tree_and_git_dir(const char *work_tree_,
+ const char *git_dir_,
+ int recurse_into_nested)
+{
+ struct strbuf gitfile_sb = STRBUF_INIT;
+ struct strbuf cfg_sb = STRBUF_INIT;
+ struct strbuf rel_path = STRBUF_INIT;
+ char *git_dir, *work_tree;
+
+ /* Prepare .git file */
+ strbuf_addf(&gitfile_sb, "%s/.git", work_tree_);
+ if (safe_create_leading_directories_const(gitfile_sb.buf))
+ die(_("could not create directories for %s"), gitfile_sb.buf);
+
+ /* Prepare config file */
+ strbuf_addf(&cfg_sb, "%s/config", git_dir_);
+ if (safe_create_leading_directories_const(cfg_sb.buf))
+ die(_("could not create directories for %s"), cfg_sb.buf);
+
+ git_dir = real_pathdup(git_dir_, 1);
+ work_tree = real_pathdup(work_tree_, 1);
+
+ /* Write .git file */
+ write_file(gitfile_sb.buf, "gitdir: %s",
+ relative_path(git_dir, work_tree, &rel_path));
+ /* Update core.worktree setting */
+ git_config_set_in_file(cfg_sb.buf, "core.worktree",
+ relative_path(work_tree, git_dir, &rel_path));
+
+ strbuf_release(&gitfile_sb);
+ strbuf_release(&cfg_sb);
+ strbuf_release(&rel_path);
+
+ if (recurse_into_nested)
+ connect_wt_gitdir_in_nested(work_tree, git_dir);
+
+ free(work_tree);
+ free(git_dir);
+}
+
+/*
+ * Migrate the git directory of the given path from old_git_dir to new_git_dir.
+ */
+void relocate_gitdir(const char *path, const char *old_git_dir, const char *new_git_dir)
+{
+ if (rename(old_git_dir, new_git_dir) < 0)
+ die_errno(_("could not migrate git directory from '%s' to '%s'"),
+ old_git_dir, new_git_dir);
+
+ connect_work_tree_and_git_dir(path, new_git_dir, 0);
}
projects / platform / upstream / git.git / blobdiff