git-commit-vandalism/dir.c

1737 lines
43 KiB
C
Raw Normal View History

/*
* This handles recursive filename detection with exclude
* files, index knowledge etc..
*
* See Documentation/technical/api-directory-listing.txt
*
* Copyright (C) Linus Torvalds, 2005-2006
* Junio Hamano, 2005-2006
*/
#include "cache.h"
#include "dir.h"
#include "refs.h"
#include "wildmatch.h"
#include "pathspec.h"
#include "utf8.h"
struct path_simplify {
int len;
const char *path;
};
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
/*
* 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 enum path_treatment 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);
/* helper string functions with support for the ignore_case flag */
int strcmp_icase(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)
{
return ignore_case ? strncasecmp(a, b, count) : strncmp(a, b, count);
}
int fnmatch_icase(const char *pattern, const char *string, int flags)
{
return wildmatch(pattern, string,
flags | (ignore_case ? WM_CASEFOLD : 0),
NULL);
}
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),
NULL);
else
/* wildmatch has not learned no FNM_PATHNAME mode yet */
return wildmatch(pattern, string,
item->magic & PATHSPEC_ICASE ? WM_CASEFOLD : 0,
NULL);
}
static int fnmatch_icase_mem(const char *pattern, int patternlen,
const char *string, int stringlen,
int flags)
{
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, NULL);
strbuf_release(&pat_buf);
strbuf_release(&str_buf);
return match_status;
}
static size_t common_prefix_len(const struct pathspec *pathspec)
{
int n;
size_t max = 0;
/*
* ":(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 xuz/abc as
* in non-:(icase).
*/
GUARD_PATHSPEC(pathspec,
PATHSPEC_FROMTOP |
PATHSPEC_MAXDEPTH |
PATHSPEC_LITERAL |
PATHSPEC_GLOB |
PATHSPEC_ICASE |
PATHSPEC_EXCLUDE);
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 (n == 0 || len < max) {
max = len;
if (!max)
break;
}
}
return max;
}
/*
* Returns a copy of the longest leading path common among all
* pathspecs.
*/
char *common_prefix(const struct pathspec *pathspec)
{
unsigned long len = common_prefix_len(pathspec);
return len ? xmemdupz(pathspec->items[0].match, len) : NULL;
}
int fill_directory(struct dir_struct *dir, const struct pathspec *pathspec)
{
size_t len;
/*
* Calculate common prefix for the pathspec, and
* use that to optimize the directory walk
*/
len = common_prefix_len(pathspec);
/* Read the directory and prune it */
read_directory(dir, pathspec->nr ? pathspec->_raw[0] : "", len, pathspec);
return len;
}
int within_depth(const char *name, int namelen,
int depth, int max_depth)
{
const char *cp = name, *cpe = name + namelen;
while (cp < cpe) {
if (*cp++ != '/')
continue;
depth++;
if (depth > max_depth)
return 0;
}
return 1;
}
#define DO_MATCH_EXCLUDE 1
#define DO_MATCH_DIRECTORY 2
/*
* Does 'match' match the given name?
* A match is found if
*
* (1) the 'match' string is leading directory of 'name', or
* (2) the 'match' string is a wildcard and matches 'name', or
* (3) the 'match' string is exactly the same as 'name'.
*
* and the return value tells which case it was.
*
* It returns 0 when there is no match.
*/
static int match_pathspec_item(const struct pathspec_item *item, int prefix,
const char *name, int namelen, 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 the match was just the prefix, we matched */
if (!*match)
return MATCHED_RECURSIVELY;
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->nowildcard_len < item->len &&
!git_fnmatch(item, match, name,
item->nowildcard_len - prefix))
return MATCHED_FNMATCH;
return 0;
}
/*
* 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.
*/
static int do_match_pathspec(const struct pathspec *ps,
const char *name, int namelen,
int prefix, char *seen,
unsigned flags)
{
int i, retval = 0, exclude = flags & DO_MATCH_EXCLUDE;
GUARD_PATHSPEC(ps,
PATHSPEC_FROMTOP |
PATHSPEC_MAXDEPTH |
PATHSPEC_LITERAL |
PATHSPEC_GLOB |
PATHSPEC_ICASE |
PATHSPEC_EXCLUDE);
if (!ps->nr) {
if (!ps->recursive ||
!(ps->magic & PATHSPEC_MAXDEPTH) ||
ps->max_depth == -1)
return MATCHED_RECURSIVELY;
if (within_depth(name, namelen, 0, ps->max_depth))
return MATCHED_EXACTLY;
else
return 0;
}
name += prefix;
namelen -= prefix;
for (i = ps->nr - 1; i >= 0; i--) {
int how;
if ((!exclude && ps->items[i].magic & PATHSPEC_EXCLUDE) ||
( exclude && !(ps->items[i].magic & PATHSPEC_EXCLUDE)))
continue;
if (seen && seen[i] == MATCHED_EXACTLY)
continue;
/*
* 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(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] == '/')
len++;
if (within_depth(name+len, namelen-len, 0, ps->max_depth))
how = MATCHED_EXACTLY;
else
how = 0;
}
if (how) {
if (retval < how)
retval = how;
if (seen && seen[i] < how)
seen[i] = how;
}
}
return retval;
}
int match_pathspec(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(ps, name, namelen,
prefix, seen, flags);
if (!(ps->magic & PATHSPEC_EXCLUDE) || !positive)
return positive;
negative = do_match_pathspec(ps, name, namelen,
prefix, seen,
flags | DO_MATCH_EXCLUDE);
return negative ? 0 : positive;
}
int report_path_error(const char *ps_matched,
const struct pathspec *pathspec,
const char *prefix)
{
/*
* Make sure all pathspec matched; otherwise it is an error.
*/
struct strbuf sb = STRBUF_INIT;
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++;
}
strbuf_release(&sb);
return errors;
}
/*
* Return the length of the "simple" part of a path match limiter.
*/
int simple_length(const char *match)
{
int len = -1;
for (;;) {
unsigned char c = *match++;
len++;
if (c == '\0' || is_glob_special(c))
return len;
}
}
int no_wildcard(const char *string)
{
return string[simple_length(string)] == '\0';
}
void parse_exclude_pattern(const char **pattern,
int *patternlen,
int *flags,
int *nowildcardlen)
{
const char *p = *pattern;
size_t i, len;
*flags = 0;
if (*p == '!') {
*flags |= EXC_FLAG_NEGATIVE;
p++;
}
len = strlen(p);
if (len && p[len - 1] == '/') {
len--;
*flags |= EXC_FLAG_MUSTBEDIR;
}
for (i = 0; i < len; i++) {
if (p[i] == '/')
break;
}
if (i == len)
*flags |= EXC_FLAG_NODIR;
*nowildcardlen = simple_length(p);
/*
* we should have excluded the trailing slash from 'p' too,
* but that's one more allocation. Instead just make sure
* nowildcardlen does not exceed real patternlen
*/
if (*nowildcardlen > len)
*nowildcardlen = len;
if (*p == '*' && no_wildcard(p + 1))
*flags |= EXC_FLAG_ENDSWITH;
*pattern = p;
*patternlen = len;
}
void add_exclude(const char *string, const char *base,
int baselen, struct exclude_list *el, int srcpos)
{
struct exclude *x;
int patternlen;
int flags;
int nowildcardlen;
parse_exclude_pattern(&string, &patternlen, &flags, &nowildcardlen);
if (flags & EXC_FLAG_MUSTBEDIR) {
char *s;
x = xmalloc(sizeof(*x) + patternlen + 1);
s = (char *)(x+1);
memcpy(s, string, patternlen);
s[patternlen] = '\0';
x->pattern = s;
} else {
x = xmalloc(sizeof(*x));
x->pattern = string;
}
x->patternlen = patternlen;
x->nowildcardlen = nowildcardlen;
x->base = base;
x->baselen = baselen;
x->flags = flags;
x->srcpos = srcpos;
ALLOC_GROW(el->excludes, el->nr + 1, el->alloc);
el->excludes[el->nr++] = x;
x->el = el;
}
static void *read_skip_worktree_file_from_index(const char *path, size_t *size)
{
int pos, len;
unsigned long sz;
enum object_type type;
void *data;
len = strlen(path);
pos = cache_name_pos(path, len);
if (pos < 0)
return NULL;
if (!ce_skip_worktree(active_cache[pos]))
return NULL;
data = read_sha1_file(active_cache[pos]->sha1, &type, &sz);
if (!data || type != OBJ_BLOB) {
free(data);
return NULL;
}
*size = xsize_t(sz);
return data;
}
/*
* Frees memory within el which was allocated for exclude patterns and
* the file buffer. Does not free el itself.
*/
void clear_exclude_list(struct exclude_list *el)
{
int i;
for (i = 0; i < el->nr; i++)
free(el->excludes[i]);
free(el->excludes);
free(el->filebuf);
el->nr = 0;
el->excludes = NULL;
el->filebuf = NULL;
}
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';
}
int add_excludes_from_file_to_list(const char *fname,
const char *base,
int baselen,
struct exclude_list *el,
int check_index)
{
struct stat st;
int fd, i, lineno = 1;
size_t size = 0;
char *buf, *entry;
fd = open(fname, O_RDONLY);
if (fd < 0 || fstat(fd, &st) < 0) {
if (errno != ENOENT)
warn_on_inaccessible(fname);
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 (buf[size-1] != '\n') {
buf = xrealloc(buf, size+1);
buf[size++] = '\n';
}
} 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;
}
buf[size++] = '\n';
close(fd);
}
el->filebuf = buf;
if (skip_utf8_bom(&buf, size))
size -= buf - el->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_exclude(entry, base, baselen, el, lineno);
}
lineno++;
entry = buf + i + 1;
}
}
return 0;
}
struct exclude_list *add_exclude_list(struct dir_struct *dir,
int group_type, const char *src)
{
struct exclude_list *el;
struct exclude_list_group *group;
group = &dir->exclude_list_group[group_type];
ALLOC_GROW(group->el, group->nr + 1, group->alloc);
el = &group->el[group->nr++];
memset(el, 0, sizeof(*el));
el->src = src;
return el;
}
/*
* Used to set up core.excludesfile and .git/info/exclude lists.
*/
void add_excludes_from_file(struct dir_struct *dir, const char *fname)
{
struct exclude_list *el;
el = add_exclude_list(dir, EXC_FILE, fname);
if (add_excludes_from_file_to_list(fname, "", 0, el, 0) < 0)
die("cannot use %s as an exclude file", fname);
}
int match_basename(const char *basename, int basenamelen,
const char *pattern, int prefix, int patternlen,
int flags)
{
if (prefix == patternlen) {
if (patternlen == basenamelen &&
!strncmp_icase(pattern, basename, basenamelen))
return 1;
} else if (flags & EXC_FLAG_ENDSWITH) {
/* "*literal" matching against "fooliteral" */
if (patternlen - 1 <= basenamelen &&
!strncmp_icase(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,
int 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] != '/') ||
strncmp_icase(pathname, base, baselen))
return 0;
namelen = baselen ? pathlen - baselen - 1 : pathlen;
name = pathname + pathlen - namelen;
if (prefix) {
/*
* if the non-wildcard part is longer than the
* remaining pathname, surely it cannot match.
*/
if (prefix > namelen)
return 0;
if (strncmp_icase(pattern, name, prefix))
return 0;
pattern += prefix;
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;
}
return fnmatch_icase_mem(pattern, patternlen,
name, namelen,
WM_PATHNAME) == 0;
}
/*
* 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 exclude *last_exclude_matching_from_list(const char *pathname,
int pathlen,
const char *basename,
int *dtype,
struct exclude_list *el)
{
int i;
if (!el->nr)
return NULL; /* undefined */
for (i = el->nr - 1; 0 <= i; i--) {
struct exclude *x = el->excludes[i];
const char *exclude = x->pattern;
int prefix = x->nowildcardlen;
if (x->flags & EXC_FLAG_MUSTBEDIR) {
if (*dtype == DT_UNKNOWN)
*dtype = get_dtype(NULL, pathname, pathlen);
if (*dtype != DT_DIR)
continue;
}
if (x->flags & EXC_FLAG_NODIR) {
if (match_basename(basename,
pathlen - (basename - pathname),
exclude, prefix, x->patternlen,
x->flags))
return x;
continue;
}
assert(x->baselen == 0 || x->base[x->baselen - 1] == '/');
if (match_pathname(pathname, pathlen,
x->base, x->baselen ? x->baselen - 1 : 0,
exclude, prefix, x->patternlen, x->flags))
return x;
}
return NULL; /* undecided */
}
/*
* Scan the list and let the last match determine the fate.
* Return 1 for exclude, 0 for include and -1 for undecided.
*/
int is_excluded_from_list(const char *pathname,
int pathlen, const char *basename, int *dtype,
struct exclude_list *el)
{
struct exclude *exclude;
exclude = last_exclude_matching_from_list(pathname, pathlen, basename, dtype, el);
if (exclude)
return exclude->flags & EXC_FLAG_NEGATIVE ? 0 : 1;
return -1; /* undecided */
}
static struct exclude *last_exclude_matching_from_lists(struct dir_struct *dir,
const char *pathname, int pathlen, const char *basename,
int *dtype_p)
{
int i, j;
struct exclude_list_group *group;
struct exclude *exclude;
for (i = EXC_CMDL; i <= EXC_FILE; i++) {
group = &dir->exclude_list_group[i];
for (j = group->nr - 1; j >= 0; j--) {
exclude = last_exclude_matching_from_list(
pathname, pathlen, basename, dtype_p,
&group->el[j]);
if (exclude)
return exclude;
}
}
return NULL;
}
/*
* 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, const char *base, int baselen)
{
struct exclude_list_group *group;
struct exclude_list *el;
struct exclude_stack *stk = NULL;
int current;
group = &dir->exclude_list_group[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.buf, base, stk->baselen))
break;
el = &group->el[dir->exclude_stack->exclude_ix];
dir->exclude_stack = stk->prev;
dir.c: unify is_excluded and is_path_excluded APIs The is_excluded and is_path_excluded APIs are very similar, except for a few noteworthy differences: is_excluded doesn't handle ignored directories, results for paths within ignored directories are incorrect. This is probably based on the premise that recursive directory scans should stop at ignored directories, which is no longer true (in certain cases, read_directory_recursive currently calls is_excluded *and* is_path_excluded to get correct ignored state). is_excluded caches parsed .gitignore files of the last directory in struct dir_struct. If the directory changes, it finds a common parent directory and is very careful to drop only as much state as necessary. On the other hand, is_excluded will also read and parse .gitignore files in already ignored directories, which are completely irrelevant. is_path_excluded correctly handles ignored directories by checking if any component in the path is excluded. As it uses is_excluded internally, this unfortunately forces is_excluded to drop and re-read all .gitignore files, as there is no common parent directory for the root dir. is_path_excluded tracks state in a separate struct path_exclude_check, which is essentially a wrapper of dir_struct with two more fields. However, as is_path_excluded also modifies dir_struct, it is not possible to e.g. use multiple path_exclude_check structures with the same dir_struct in parallel. The additional structure just unnecessarily complicates the API. Teach is_excluded / prep_exclude about ignored directories: whenever entering a new directory, first check if the entire directory is excluded. Remember the excluded state in dir_struct. Don't traverse into already ignored directories (i.e. don't read irrelevant .gitignore files). Directories could also be excluded by exclude patterns specified on the command line or .git/info/exclude, so we cannot simply skip prep_exclude entirely if there's no .gitignore file name (dir_struct.exclude_per_dir). Move this check to just before actually reading the file. is_path_excluded is now equivalent to is_excluded, so we can simply redirect to it (the public API is cleaned up in the next patch). The performance impact of the additional ignored check per directory is hardly noticeable when reading directories recursively (e.g. 'git status'). However, performance of git commands using the is_path_excluded API (e.g. 'git ls-files --cached --ignored --exclude-standard') is greatly improved as this no longer re-reads .gitignore files on each call. Here's some performance data from the linux and WebKit repos (best of 10 runs on a Debian Linux on SSD, core.preloadIndex=true): | ls-files -ci | status | status --ignored | linux | WebKit | linux | WebKit | linux | WebKit -------+-------+--------+-------+--------+-------+--------- before | 0.506 | 6.539 | 0.212 | 1.555 | 0.323 | 2.541 after | 0.080 | 1.191 | 0.218 | 1.583 | 0.321 | 2.579 gain | 6.325 | 5.490 | 0.972 | 0.982 | 1.006 | 0.985 Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:12:14 +02:00
dir->exclude = NULL;
free((char *)el->src); /* see strbuf_detach() below */
clear_exclude_list(el);
free(stk);
group->nr--;
}
dir.c: unify is_excluded and is_path_excluded APIs The is_excluded and is_path_excluded APIs are very similar, except for a few noteworthy differences: is_excluded doesn't handle ignored directories, results for paths within ignored directories are incorrect. This is probably based on the premise that recursive directory scans should stop at ignored directories, which is no longer true (in certain cases, read_directory_recursive currently calls is_excluded *and* is_path_excluded to get correct ignored state). is_excluded caches parsed .gitignore files of the last directory in struct dir_struct. If the directory changes, it finds a common parent directory and is very careful to drop only as much state as necessary. On the other hand, is_excluded will also read and parse .gitignore files in already ignored directories, which are completely irrelevant. is_path_excluded correctly handles ignored directories by checking if any component in the path is excluded. As it uses is_excluded internally, this unfortunately forces is_excluded to drop and re-read all .gitignore files, as there is no common parent directory for the root dir. is_path_excluded tracks state in a separate struct path_exclude_check, which is essentially a wrapper of dir_struct with two more fields. However, as is_path_excluded also modifies dir_struct, it is not possible to e.g. use multiple path_exclude_check structures with the same dir_struct in parallel. The additional structure just unnecessarily complicates the API. Teach is_excluded / prep_exclude about ignored directories: whenever entering a new directory, first check if the entire directory is excluded. Remember the excluded state in dir_struct. Don't traverse into already ignored directories (i.e. don't read irrelevant .gitignore files). Directories could also be excluded by exclude patterns specified on the command line or .git/info/exclude, so we cannot simply skip prep_exclude entirely if there's no .gitignore file name (dir_struct.exclude_per_dir). Move this check to just before actually reading the file. is_path_excluded is now equivalent to is_excluded, so we can simply redirect to it (the public API is cleaned up in the next patch). The performance impact of the additional ignored check per directory is hardly noticeable when reading directories recursively (e.g. 'git status'). However, performance of git commands using the is_path_excluded API (e.g. 'git ls-files --cached --ignored --exclude-standard') is greatly improved as this no longer re-reads .gitignore files on each call. Here's some performance data from the linux and WebKit repos (best of 10 runs on a Debian Linux on SSD, core.preloadIndex=true): | ls-files -ci | status | status --ignored | linux | WebKit | linux | WebKit | linux | WebKit -------+-------+--------+-------+--------+-------+--------- before | 0.506 | 6.539 | 0.212 | 1.555 | 0.323 | 2.541 after | 0.080 | 1.191 | 0.218 | 1.583 | 0.321 | 2.579 gain | 6.325 | 5.490 | 0.972 | 0.982 | 1.006 | 0.985 Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:12:14 +02:00
/* Skip traversing into sub directories if the parent is excluded */
if (dir->exclude)
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);
while (current < baselen) {
const char *cp;
stk = xcalloc(1, sizeof(*stk));
if (current < 0) {
cp = base;
current = 0;
} else {
cp = strchr(base + current + 1, '/');
if (!cp)
die("oops in prep_exclude");
cp++;
}
stk->prev = dir->exclude_stack;
stk->baselen = cp - base;
dir.c: unify is_excluded and is_path_excluded APIs The is_excluded and is_path_excluded APIs are very similar, except for a few noteworthy differences: is_excluded doesn't handle ignored directories, results for paths within ignored directories are incorrect. This is probably based on the premise that recursive directory scans should stop at ignored directories, which is no longer true (in certain cases, read_directory_recursive currently calls is_excluded *and* is_path_excluded to get correct ignored state). is_excluded caches parsed .gitignore files of the last directory in struct dir_struct. If the directory changes, it finds a common parent directory and is very careful to drop only as much state as necessary. On the other hand, is_excluded will also read and parse .gitignore files in already ignored directories, which are completely irrelevant. is_path_excluded correctly handles ignored directories by checking if any component in the path is excluded. As it uses is_excluded internally, this unfortunately forces is_excluded to drop and re-read all .gitignore files, as there is no common parent directory for the root dir. is_path_excluded tracks state in a separate struct path_exclude_check, which is essentially a wrapper of dir_struct with two more fields. However, as is_path_excluded also modifies dir_struct, it is not possible to e.g. use multiple path_exclude_check structures with the same dir_struct in parallel. The additional structure just unnecessarily complicates the API. Teach is_excluded / prep_exclude about ignored directories: whenever entering a new directory, first check if the entire directory is excluded. Remember the excluded state in dir_struct. Don't traverse into already ignored directories (i.e. don't read irrelevant .gitignore files). Directories could also be excluded by exclude patterns specified on the command line or .git/info/exclude, so we cannot simply skip prep_exclude entirely if there's no .gitignore file name (dir_struct.exclude_per_dir). Move this check to just before actually reading the file. is_path_excluded is now equivalent to is_excluded, so we can simply redirect to it (the public API is cleaned up in the next patch). The performance impact of the additional ignored check per directory is hardly noticeable when reading directories recursively (e.g. 'git status'). However, performance of git commands using the is_path_excluded API (e.g. 'git ls-files --cached --ignored --exclude-standard') is greatly improved as this no longer re-reads .gitignore files on each call. Here's some performance data from the linux and WebKit repos (best of 10 runs on a Debian Linux on SSD, core.preloadIndex=true): | ls-files -ci | status | status --ignored | linux | WebKit | linux | WebKit | linux | WebKit -------+-------+--------+-------+--------+-------+--------- before | 0.506 | 6.539 | 0.212 | 1.555 | 0.323 | 2.541 after | 0.080 | 1.191 | 0.218 | 1.583 | 0.321 | 2.579 gain | 6.325 | 5.490 | 0.972 | 0.982 | 1.006 | 0.985 Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:12:14 +02:00
stk->exclude_ix = group->nr;
el = add_exclude_list(dir, EXC_DIRS, NULL);
strbuf_add(&dir->basebuf, base + current, stk->baselen - current);
assert(stk->baselen == dir->basebuf.len);
dir.c: unify is_excluded and is_path_excluded APIs The is_excluded and is_path_excluded APIs are very similar, except for a few noteworthy differences: is_excluded doesn't handle ignored directories, results for paths within ignored directories are incorrect. This is probably based on the premise that recursive directory scans should stop at ignored directories, which is no longer true (in certain cases, read_directory_recursive currently calls is_excluded *and* is_path_excluded to get correct ignored state). is_excluded caches parsed .gitignore files of the last directory in struct dir_struct. If the directory changes, it finds a common parent directory and is very careful to drop only as much state as necessary. On the other hand, is_excluded will also read and parse .gitignore files in already ignored directories, which are completely irrelevant. is_path_excluded correctly handles ignored directories by checking if any component in the path is excluded. As it uses is_excluded internally, this unfortunately forces is_excluded to drop and re-read all .gitignore files, as there is no common parent directory for the root dir. is_path_excluded tracks state in a separate struct path_exclude_check, which is essentially a wrapper of dir_struct with two more fields. However, as is_path_excluded also modifies dir_struct, it is not possible to e.g. use multiple path_exclude_check structures with the same dir_struct in parallel. The additional structure just unnecessarily complicates the API. Teach is_excluded / prep_exclude about ignored directories: whenever entering a new directory, first check if the entire directory is excluded. Remember the excluded state in dir_struct. Don't traverse into already ignored directories (i.e. don't read irrelevant .gitignore files). Directories could also be excluded by exclude patterns specified on the command line or .git/info/exclude, so we cannot simply skip prep_exclude entirely if there's no .gitignore file name (dir_struct.exclude_per_dir). Move this check to just before actually reading the file. is_path_excluded is now equivalent to is_excluded, so we can simply redirect to it (the public API is cleaned up in the next patch). The performance impact of the additional ignored check per directory is hardly noticeable when reading directories recursively (e.g. 'git status'). However, performance of git commands using the is_path_excluded API (e.g. 'git ls-files --cached --ignored --exclude-standard') is greatly improved as this no longer re-reads .gitignore files on each call. Here's some performance data from the linux and WebKit repos (best of 10 runs on a Debian Linux on SSD, core.preloadIndex=true): | ls-files -ci | status | status --ignored | linux | WebKit | linux | WebKit | linux | WebKit -------+-------+--------+-------+--------+-------+--------- before | 0.506 | 6.539 | 0.212 | 1.555 | 0.323 | 2.541 after | 0.080 | 1.191 | 0.218 | 1.583 | 0.321 | 2.579 gain | 6.325 | 5.490 | 0.972 | 0.982 | 1.006 | 0.985 Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:12:14 +02:00
/* Abort if the directory is excluded */
if (stk->baselen) {
int dt = DT_DIR;
dir->basebuf.buf[stk->baselen - 1] = 0;
dir.c: unify is_excluded and is_path_excluded APIs The is_excluded and is_path_excluded APIs are very similar, except for a few noteworthy differences: is_excluded doesn't handle ignored directories, results for paths within ignored directories are incorrect. This is probably based on the premise that recursive directory scans should stop at ignored directories, which is no longer true (in certain cases, read_directory_recursive currently calls is_excluded *and* is_path_excluded to get correct ignored state). is_excluded caches parsed .gitignore files of the last directory in struct dir_struct. If the directory changes, it finds a common parent directory and is very careful to drop only as much state as necessary. On the other hand, is_excluded will also read and parse .gitignore files in already ignored directories, which are completely irrelevant. is_path_excluded correctly handles ignored directories by checking if any component in the path is excluded. As it uses is_excluded internally, this unfortunately forces is_excluded to drop and re-read all .gitignore files, as there is no common parent directory for the root dir. is_path_excluded tracks state in a separate struct path_exclude_check, which is essentially a wrapper of dir_struct with two more fields. However, as is_path_excluded also modifies dir_struct, it is not possible to e.g. use multiple path_exclude_check structures with the same dir_struct in parallel. The additional structure just unnecessarily complicates the API. Teach is_excluded / prep_exclude about ignored directories: whenever entering a new directory, first check if the entire directory is excluded. Remember the excluded state in dir_struct. Don't traverse into already ignored directories (i.e. don't read irrelevant .gitignore files). Directories could also be excluded by exclude patterns specified on the command line or .git/info/exclude, so we cannot simply skip prep_exclude entirely if there's no .gitignore file name (dir_struct.exclude_per_dir). Move this check to just before actually reading the file. is_path_excluded is now equivalent to is_excluded, so we can simply redirect to it (the public API is cleaned up in the next patch). The performance impact of the additional ignored check per directory is hardly noticeable when reading directories recursively (e.g. 'git status'). However, performance of git commands using the is_path_excluded API (e.g. 'git ls-files --cached --ignored --exclude-standard') is greatly improved as this no longer re-reads .gitignore files on each call. Here's some performance data from the linux and WebKit repos (best of 10 runs on a Debian Linux on SSD, core.preloadIndex=true): | ls-files -ci | status | status --ignored | linux | WebKit | linux | WebKit | linux | WebKit -------+-------+--------+-------+--------+-------+--------- before | 0.506 | 6.539 | 0.212 | 1.555 | 0.323 | 2.541 after | 0.080 | 1.191 | 0.218 | 1.583 | 0.321 | 2.579 gain | 6.325 | 5.490 | 0.972 | 0.982 | 1.006 | 0.985 Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:12:14 +02:00
dir->exclude = last_exclude_matching_from_lists(dir,
dir->basebuf.buf, stk->baselen - 1,
dir->basebuf.buf + current, &dt);
dir->basebuf.buf[stk->baselen - 1] = '/';
if (dir->exclude &&
dir->exclude->flags & EXC_FLAG_NEGATIVE)
dir->exclude = NULL;
dir.c: unify is_excluded and is_path_excluded APIs The is_excluded and is_path_excluded APIs are very similar, except for a few noteworthy differences: is_excluded doesn't handle ignored directories, results for paths within ignored directories are incorrect. This is probably based on the premise that recursive directory scans should stop at ignored directories, which is no longer true (in certain cases, read_directory_recursive currently calls is_excluded *and* is_path_excluded to get correct ignored state). is_excluded caches parsed .gitignore files of the last directory in struct dir_struct. If the directory changes, it finds a common parent directory and is very careful to drop only as much state as necessary. On the other hand, is_excluded will also read and parse .gitignore files in already ignored directories, which are completely irrelevant. is_path_excluded correctly handles ignored directories by checking if any component in the path is excluded. As it uses is_excluded internally, this unfortunately forces is_excluded to drop and re-read all .gitignore files, as there is no common parent directory for the root dir. is_path_excluded tracks state in a separate struct path_exclude_check, which is essentially a wrapper of dir_struct with two more fields. However, as is_path_excluded also modifies dir_struct, it is not possible to e.g. use multiple path_exclude_check structures with the same dir_struct in parallel. The additional structure just unnecessarily complicates the API. Teach is_excluded / prep_exclude about ignored directories: whenever entering a new directory, first check if the entire directory is excluded. Remember the excluded state in dir_struct. Don't traverse into already ignored directories (i.e. don't read irrelevant .gitignore files). Directories could also be excluded by exclude patterns specified on the command line or .git/info/exclude, so we cannot simply skip prep_exclude entirely if there's no .gitignore file name (dir_struct.exclude_per_dir). Move this check to just before actually reading the file. is_path_excluded is now equivalent to is_excluded, so we can simply redirect to it (the public API is cleaned up in the next patch). The performance impact of the additional ignored check per directory is hardly noticeable when reading directories recursively (e.g. 'git status'). However, performance of git commands using the is_path_excluded API (e.g. 'git ls-files --cached --ignored --exclude-standard') is greatly improved as this no longer re-reads .gitignore files on each call. Here's some performance data from the linux and WebKit repos (best of 10 runs on a Debian Linux on SSD, core.preloadIndex=true): | ls-files -ci | status | status --ignored | linux | WebKit | linux | WebKit | linux | WebKit -------+-------+--------+-------+--------+-------+--------- before | 0.506 | 6.539 | 0.212 | 1.555 | 0.323 | 2.541 after | 0.080 | 1.191 | 0.218 | 1.583 | 0.321 | 2.579 gain | 6.325 | 5.490 | 0.972 | 0.982 | 1.006 | 0.985 Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:12:14 +02:00
if (dir->exclude) {
dir->exclude_stack = stk;
return;
}
}
/* Try to read per-directory file */
if (dir->exclude_per_dir) {
dir.c: unify is_excluded and is_path_excluded APIs The is_excluded and is_path_excluded APIs are very similar, except for a few noteworthy differences: is_excluded doesn't handle ignored directories, results for paths within ignored directories are incorrect. This is probably based on the premise that recursive directory scans should stop at ignored directories, which is no longer true (in certain cases, read_directory_recursive currently calls is_excluded *and* is_path_excluded to get correct ignored state). is_excluded caches parsed .gitignore files of the last directory in struct dir_struct. If the directory changes, it finds a common parent directory and is very careful to drop only as much state as necessary. On the other hand, is_excluded will also read and parse .gitignore files in already ignored directories, which are completely irrelevant. is_path_excluded correctly handles ignored directories by checking if any component in the path is excluded. As it uses is_excluded internally, this unfortunately forces is_excluded to drop and re-read all .gitignore files, as there is no common parent directory for the root dir. is_path_excluded tracks state in a separate struct path_exclude_check, which is essentially a wrapper of dir_struct with two more fields. However, as is_path_excluded also modifies dir_struct, it is not possible to e.g. use multiple path_exclude_check structures with the same dir_struct in parallel. The additional structure just unnecessarily complicates the API. Teach is_excluded / prep_exclude about ignored directories: whenever entering a new directory, first check if the entire directory is excluded. Remember the excluded state in dir_struct. Don't traverse into already ignored directories (i.e. don't read irrelevant .gitignore files). Directories could also be excluded by exclude patterns specified on the command line or .git/info/exclude, so we cannot simply skip prep_exclude entirely if there's no .gitignore file name (dir_struct.exclude_per_dir). Move this check to just before actually reading the file. is_path_excluded is now equivalent to is_excluded, so we can simply redirect to it (the public API is cleaned up in the next patch). The performance impact of the additional ignored check per directory is hardly noticeable when reading directories recursively (e.g. 'git status'). However, performance of git commands using the is_path_excluded API (e.g. 'git ls-files --cached --ignored --exclude-standard') is greatly improved as this no longer re-reads .gitignore files on each call. Here's some performance data from the linux and WebKit repos (best of 10 runs on a Debian Linux on SSD, core.preloadIndex=true): | ls-files -ci | status | status --ignored | linux | WebKit | linux | WebKit | linux | WebKit -------+-------+--------+-------+--------+-------+--------- before | 0.506 | 6.539 | 0.212 | 1.555 | 0.323 | 2.541 after | 0.080 | 1.191 | 0.218 | 1.583 | 0.321 | 2.579 gain | 6.325 | 5.490 | 0.972 | 0.982 | 1.006 | 0.985 Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:12:14 +02:00
/*
* dir->basebuf gets reused by the traversal, but we
* need fname to remain unchanged to ensure the src
* member of each struct exclude correctly
* back-references its source file. Other invocations
* of add_exclude_list provide stable strings, so we
* strbuf_detach() and free() here in the caller.
dir.c: unify is_excluded and is_path_excluded APIs The is_excluded and is_path_excluded APIs are very similar, except for a few noteworthy differences: is_excluded doesn't handle ignored directories, results for paths within ignored directories are incorrect. This is probably based on the premise that recursive directory scans should stop at ignored directories, which is no longer true (in certain cases, read_directory_recursive currently calls is_excluded *and* is_path_excluded to get correct ignored state). is_excluded caches parsed .gitignore files of the last directory in struct dir_struct. If the directory changes, it finds a common parent directory and is very careful to drop only as much state as necessary. On the other hand, is_excluded will also read and parse .gitignore files in already ignored directories, which are completely irrelevant. is_path_excluded correctly handles ignored directories by checking if any component in the path is excluded. As it uses is_excluded internally, this unfortunately forces is_excluded to drop and re-read all .gitignore files, as there is no common parent directory for the root dir. is_path_excluded tracks state in a separate struct path_exclude_check, which is essentially a wrapper of dir_struct with two more fields. However, as is_path_excluded also modifies dir_struct, it is not possible to e.g. use multiple path_exclude_check structures with the same dir_struct in parallel. The additional structure just unnecessarily complicates the API. Teach is_excluded / prep_exclude about ignored directories: whenever entering a new directory, first check if the entire directory is excluded. Remember the excluded state in dir_struct. Don't traverse into already ignored directories (i.e. don't read irrelevant .gitignore files). Directories could also be excluded by exclude patterns specified on the command line or .git/info/exclude, so we cannot simply skip prep_exclude entirely if there's no .gitignore file name (dir_struct.exclude_per_dir). Move this check to just before actually reading the file. is_path_excluded is now equivalent to is_excluded, so we can simply redirect to it (the public API is cleaned up in the next patch). The performance impact of the additional ignored check per directory is hardly noticeable when reading directories recursively (e.g. 'git status'). However, performance of git commands using the is_path_excluded API (e.g. 'git ls-files --cached --ignored --exclude-standard') is greatly improved as this no longer re-reads .gitignore files on each call. Here's some performance data from the linux and WebKit repos (best of 10 runs on a Debian Linux on SSD, core.preloadIndex=true): | ls-files -ci | status | status --ignored | linux | WebKit | linux | WebKit | linux | WebKit -------+-------+--------+-------+--------+-------+--------- before | 0.506 | 6.539 | 0.212 | 1.555 | 0.323 | 2.541 after | 0.080 | 1.191 | 0.218 | 1.583 | 0.321 | 2.579 gain | 6.325 | 5.490 | 0.972 | 0.982 | 1.006 | 0.985 Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:12:14 +02:00
*/
struct strbuf sb = STRBUF_INIT;
strbuf_addbuf(&sb, &dir->basebuf);
strbuf_addstr(&sb, dir->exclude_per_dir);
el->src = strbuf_detach(&sb, NULL);
add_excludes_from_file_to_list(el->src, el->src,
stk->baselen, el, 1);
dir.c: unify is_excluded and is_path_excluded APIs The is_excluded and is_path_excluded APIs are very similar, except for a few noteworthy differences: is_excluded doesn't handle ignored directories, results for paths within ignored directories are incorrect. This is probably based on the premise that recursive directory scans should stop at ignored directories, which is no longer true (in certain cases, read_directory_recursive currently calls is_excluded *and* is_path_excluded to get correct ignored state). is_excluded caches parsed .gitignore files of the last directory in struct dir_struct. If the directory changes, it finds a common parent directory and is very careful to drop only as much state as necessary. On the other hand, is_excluded will also read and parse .gitignore files in already ignored directories, which are completely irrelevant. is_path_excluded correctly handles ignored directories by checking if any component in the path is excluded. As it uses is_excluded internally, this unfortunately forces is_excluded to drop and re-read all .gitignore files, as there is no common parent directory for the root dir. is_path_excluded tracks state in a separate struct path_exclude_check, which is essentially a wrapper of dir_struct with two more fields. However, as is_path_excluded also modifies dir_struct, it is not possible to e.g. use multiple path_exclude_check structures with the same dir_struct in parallel. The additional structure just unnecessarily complicates the API. Teach is_excluded / prep_exclude about ignored directories: whenever entering a new directory, first check if the entire directory is excluded. Remember the excluded state in dir_struct. Don't traverse into already ignored directories (i.e. don't read irrelevant .gitignore files). Directories could also be excluded by exclude patterns specified on the command line or .git/info/exclude, so we cannot simply skip prep_exclude entirely if there's no .gitignore file name (dir_struct.exclude_per_dir). Move this check to just before actually reading the file. is_path_excluded is now equivalent to is_excluded, so we can simply redirect to it (the public API is cleaned up in the next patch). The performance impact of the additional ignored check per directory is hardly noticeable when reading directories recursively (e.g. 'git status'). However, performance of git commands using the is_path_excluded API (e.g. 'git ls-files --cached --ignored --exclude-standard') is greatly improved as this no longer re-reads .gitignore files on each call. Here's some performance data from the linux and WebKit repos (best of 10 runs on a Debian Linux on SSD, core.preloadIndex=true): | ls-files -ci | status | status --ignored | linux | WebKit | linux | WebKit | linux | WebKit -------+-------+--------+-------+--------+-------+--------- before | 0.506 | 6.539 | 0.212 | 1.555 | 0.323 | 2.541 after | 0.080 | 1.191 | 0.218 | 1.583 | 0.321 | 2.579 gain | 6.325 | 5.490 | 0.972 | 0.982 | 1.006 | 0.985 Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:12:14 +02:00
}
dir->exclude_stack = stk;
current = stk->baselen;
}
strbuf_setlen(&dir->basebuf, baselen);
}
/*
* 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.
*/
struct exclude *last_exclude_matching(struct dir_struct *dir,
const char *pathname,
int *dtype_p)
{
int pathlen = strlen(pathname);
const char *basename = strrchr(pathname, '/');
basename = (basename) ? basename+1 : pathname;
prep_exclude(dir, pathname, basename-pathname);
dir.c: unify is_excluded and is_path_excluded APIs The is_excluded and is_path_excluded APIs are very similar, except for a few noteworthy differences: is_excluded doesn't handle ignored directories, results for paths within ignored directories are incorrect. This is probably based on the premise that recursive directory scans should stop at ignored directories, which is no longer true (in certain cases, read_directory_recursive currently calls is_excluded *and* is_path_excluded to get correct ignored state). is_excluded caches parsed .gitignore files of the last directory in struct dir_struct. If the directory changes, it finds a common parent directory and is very careful to drop only as much state as necessary. On the other hand, is_excluded will also read and parse .gitignore files in already ignored directories, which are completely irrelevant. is_path_excluded correctly handles ignored directories by checking if any component in the path is excluded. As it uses is_excluded internally, this unfortunately forces is_excluded to drop and re-read all .gitignore files, as there is no common parent directory for the root dir. is_path_excluded tracks state in a separate struct path_exclude_check, which is essentially a wrapper of dir_struct with two more fields. However, as is_path_excluded also modifies dir_struct, it is not possible to e.g. use multiple path_exclude_check structures with the same dir_struct in parallel. The additional structure just unnecessarily complicates the API. Teach is_excluded / prep_exclude about ignored directories: whenever entering a new directory, first check if the entire directory is excluded. Remember the excluded state in dir_struct. Don't traverse into already ignored directories (i.e. don't read irrelevant .gitignore files). Directories could also be excluded by exclude patterns specified on the command line or .git/info/exclude, so we cannot simply skip prep_exclude entirely if there's no .gitignore file name (dir_struct.exclude_per_dir). Move this check to just before actually reading the file. is_path_excluded is now equivalent to is_excluded, so we can simply redirect to it (the public API is cleaned up in the next patch). The performance impact of the additional ignored check per directory is hardly noticeable when reading directories recursively (e.g. 'git status'). However, performance of git commands using the is_path_excluded API (e.g. 'git ls-files --cached --ignored --exclude-standard') is greatly improved as this no longer re-reads .gitignore files on each call. Here's some performance data from the linux and WebKit repos (best of 10 runs on a Debian Linux on SSD, core.preloadIndex=true): | ls-files -ci | status | status --ignored | linux | WebKit | linux | WebKit | linux | WebKit -------+-------+--------+-------+--------+-------+--------- before | 0.506 | 6.539 | 0.212 | 1.555 | 0.323 | 2.541 after | 0.080 | 1.191 | 0.218 | 1.583 | 0.321 | 2.579 gain | 6.325 | 5.490 | 0.972 | 0.982 | 1.006 | 0.985 Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:12:14 +02:00
if (dir->exclude)
return dir->exclude;
return last_exclude_matching_from_lists(dir, pathname, pathlen,
basename, 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, const char *pathname, int *dtype_p)
{
struct exclude *exclude =
last_exclude_matching(dir, pathname, dtype_p);
if (exclude)
return exclude->flags & EXC_FLAG_NEGATIVE ? 0 : 1;
return 0;
}
static struct dir_entry *dir_entry_new(const char *pathname, int len)
{
struct dir_entry *ent;
ent = xmalloc(sizeof(*ent) + len + 1);
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)
{
if (cache_file_exists(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)
{
if (!cache_name_is_other(pathname, len))
return NULL;
ALLOC_GROW(dir->ignored, dir->ignored_nr+1, dir->ignored_alloc);
return dir->ignored[dir->ignored_nr++] = dir_entry_new(pathname, len);
}
enum exist_status {
index_nonexistent = 0,
index_directory,
index_gitdir
};
/*
* Do not use the alphabetically sorted index to look up
* the directory name; instead, use the case insensitive
* directory hash.
*/
static enum exist_status directory_exists_in_index_icase(const char *dirname, int len)
{
name-hash: stop storing trailing '/' on paths in index_state.dir_hash When 5102c617 (Add case insensitivity support for directories when using git status, 2010-10-03) added directories to the name-hash there was only a single hash table in which both real cache entries and leading directory prefixes were registered. To distinguish between the two types of entries, directories were stored with a trailing '/'. 2092678c (name-hash.c: fix endless loop with core.ignorecase=true, 2013-02-28), however, moved directories to a separate hash table (index_state.dir_hash) but retained the (now) redundant trailing '/', thus callers continue to bear the burden of ensuring the slash's presence before searching the index for a directory. Eliminate this redundancy by storing paths in the dir-hash without the trailing '/'. An important benefit of this change is that it eliminates undocumented and dangerous behavior of dir.c:directory_exists_in_index_icase() in which it assumes not only that it can validly access one character beyond the end of its incoming directory argument, but also that that character will unconditionally be a '/'. This perilous behavior was "tolerated" because the string passed in by its lone caller always had a '/' in that position, however, things broke [1] when 2eac2a4c (ls-files -k: a directory only can be killed if the index has a non-directory, 2013-08-15) added a new caller which failed to respect the undocumented assumption. [1]: http://thread.gmane.org/gmane.comp.version-control.git/232727 Signed-off-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-09-17 09:06:16 +02:00
const struct cache_entry *ce = cache_dir_exists(dirname, len);
unsigned char endchar;
if (!ce)
return index_nonexistent;
endchar = ce->name[len];
/*
* The cache_entry structure returned will contain this dirname
* and possibly additional path components.
*/
if (endchar == '/')
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))
return index_gitdir;
/* This should never be hit, but it exists just in case. */
return index_nonexistent;
}
/*
* The index sorts alphabetically by entry name, which
* means that a gitlink sorts as '\0' at the end, while
* a directory (which is defined not as an entry, but as
* the files it contains) will sort with the '/' at the
* end.
*/
static enum exist_status directory_exists_in_index(const char *dirname, int len)
{
int pos;
if (ignore_case)
return directory_exists_in_index_icase(dirname, len);
pos = cache_name_pos(dirname, len);
if (pos < 0)
pos = -pos-1;
while (pos < active_nr) {
Convert "struct cache_entry *" to "const ..." wherever possible I attempted to make index_state->cache[] a "const struct cache_entry **" to find out how existing entries in index are modified and where. The question I have is what do we do if we really need to keep track of on-disk changes in the index. The result is - diff-lib.c: setting CE_UPTODATE - name-hash.c: setting CE_HASHED - preload-index.c, read-cache.c, unpack-trees.c and builtin/update-index: obvious - entry.c: write_entry() may refresh the checked out entry via fill_stat_cache_info(). This causes "non-const struct cache_entry *" in builtin/apply.c, builtin/checkout-index.c and builtin/checkout.c - builtin/ls-files.c: --with-tree changes stagemask and may set CE_UPDATE Of these, write_entry() and its call sites are probably most interesting because it modifies on-disk info. But this is stat info and can be retrieved via refresh, at least for porcelain commands. Other just uses ce_flags for local purposes. So, keeping track of "dirty" entries is just a matter of setting a flag in index modification functions exposed by read-cache.c. Except unpack-trees, the rest of the code base does not do anything funny behind read-cache's back. The actual patch is less valueable than the summary above. But if anyone wants to re-identify the above sites. Applying this patch, then this: diff --git a/cache.h b/cache.h index 430d021..1692891 100644 --- a/cache.h +++ b/cache.h @@ -267,7 +267,7 @@ static inline unsigned int canon_mode(unsigned int mode) #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1) struct index_state { - struct cache_entry **cache; + const struct cache_entry **cache; unsigned int version; unsigned int cache_nr, cache_alloc, cache_changed; struct string_list *resolve_undo; will help quickly identify them without bogus warnings. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-09 17:29:00 +02:00
const struct cache_entry *ce = active_cache[pos++];
unsigned char endchar;
if (strncmp(ce->name, dirname, len))
break;
endchar = ce->name[len];
if (endchar > '/')
break;
if (endchar == '/')
return index_directory;
if (!endchar && S_ISGITLINK(ce->ce_mode))
return index_gitdir;
}
return index_nonexistent;
}
/*
* When we find a directory when traversing the filesystem, we
* have three distinct cases:
*
* - ignore it
* - see it as a directory
* - recurse into it
*
* and which one we choose depends on a combination of existing
* git index contents and the flags passed into the directory
* traversal routine.
*
* Case 1: If we *already* have entries in the index under that
* directory name, we always recurse into the directory to see
* all the files.
*
* Case 2: If we *already* have that directory name as a gitlink,
* we always continue to see it as a gitlink, regardless of whether
* there is an actual git directory there or not (it might not
* be checked out as a subproject!)
*
* Case 3: if we didn't have it in the index previously, we
* have a few sub-cases:
*
* (a) if "show_other_directories" is true, we show it as
* just a directory, unless "hide_empty_directories" is
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
* 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.
*/
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
static enum path_treatment treat_directory(struct dir_struct *dir,
const char *dirname, int len, int exclude,
const struct path_simplify *simplify)
{
/* The "len-1" is to strip the final '/' */
switch (directory_exists_in_index(dirname, len-1)) {
case index_directory:
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
return path_recurse;
case index_gitdir:
return path_none;
case index_nonexistent:
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)
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
return path_untracked;
}
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
return path_recurse;
}
/* This is the "show_other_directories" case */
if (!(dir->flags & DIR_HIDE_EMPTY_DIRECTORIES))
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
return exclude ? path_excluded : path_untracked;
return read_directory_recursive(dir, dirname, len, 1, simplify);
}
/*
* This is an inexact early pruning of any recursive directory
* 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)
{
if (simplify) {
for (;;) {
const char *match = simplify->path;
int len = simplify->len;
if (!match)
break;
if (len > pathlen)
len = pathlen;
if (!memcmp(path, match, len))
return 0;
simplify++;
}
return 1;
}
return 0;
}
/*
* This function tells us whether an excluded path matches a
* list of "interesting" pathspecs. That is, whether a path matched
* by any of the pathspecs could possibly be ignored by excluding
* the specified path. This can happen if:
*
* 1. the path is mentioned explicitly in the pathspec
*
* 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;
}
}
return 0;
}
static int get_index_dtype(const char *path, int len)
{
int pos;
Convert "struct cache_entry *" to "const ..." wherever possible I attempted to make index_state->cache[] a "const struct cache_entry **" to find out how existing entries in index are modified and where. The question I have is what do we do if we really need to keep track of on-disk changes in the index. The result is - diff-lib.c: setting CE_UPTODATE - name-hash.c: setting CE_HASHED - preload-index.c, read-cache.c, unpack-trees.c and builtin/update-index: obvious - entry.c: write_entry() may refresh the checked out entry via fill_stat_cache_info(). This causes "non-const struct cache_entry *" in builtin/apply.c, builtin/checkout-index.c and builtin/checkout.c - builtin/ls-files.c: --with-tree changes stagemask and may set CE_UPDATE Of these, write_entry() and its call sites are probably most interesting because it modifies on-disk info. But this is stat info and can be retrieved via refresh, at least for porcelain commands. Other just uses ce_flags for local purposes. So, keeping track of "dirty" entries is just a matter of setting a flag in index modification functions exposed by read-cache.c. Except unpack-trees, the rest of the code base does not do anything funny behind read-cache's back. The actual patch is less valueable than the summary above. But if anyone wants to re-identify the above sites. Applying this patch, then this: diff --git a/cache.h b/cache.h index 430d021..1692891 100644 --- a/cache.h +++ b/cache.h @@ -267,7 +267,7 @@ static inline unsigned int canon_mode(unsigned int mode) #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1) struct index_state { - struct cache_entry **cache; + const struct cache_entry **cache; unsigned int version; unsigned int cache_nr, cache_alloc, cache_changed; struct string_list *resolve_undo; will help quickly identify them without bogus warnings. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-09 17:29:00 +02:00
const struct cache_entry *ce;
ce = cache_file_exists(path, len, 0);
if (ce) {
if (!ce_uptodate(ce))
return DT_UNKNOWN;
if (S_ISGITLINK(ce->ce_mode))
return DT_DIR;
/*
* Nobody actually cares about the
* difference between DT_LNK and DT_REG
*/
return DT_REG;
}
/* Try to look it up as a directory */
pos = cache_name_pos(path, len);
if (pos >= 0)
return DT_UNKNOWN;
pos = -pos-1;
while (pos < active_nr) {
ce = active_cache[pos++];
if (strncmp(ce->name, path, len))
break;
if (ce->name[len] > '/')
break;
if (ce->name[len] < '/')
continue;
if (!ce_uptodate(ce))
break; /* continue? */
return DT_DIR;
}
return DT_UNKNOWN;
}
static int get_dtype(struct dirent *de, 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);
if (dtype != DT_UNKNOWN)
return dtype;
if (lstat(path, &st))
return dtype;
if (S_ISREG(st.st_mode))
return DT_REG;
if (S_ISDIR(st.st_mode))
return DT_DIR;
if (S_ISLNK(st.st_mode))
return DT_LNK;
return dtype;
}
static enum path_treatment treat_one_path(struct dir_struct *dir,
struct strbuf *path,
const struct path_simplify *simplify,
int dtype, struct dirent *de)
{
int exclude;
int has_path_in_index = !!cache_file_exists(path->buf, path->len, ignore_case);
ls-files -k: a directory only can be killed if the index has a non-directory "ls-files -o" and "ls-files -k" both traverse the working tree down to find either all untracked paths or those that will be "killed" (removed from the working tree to make room) when the paths recorded in the index are checked out. It is necessary to traverse the working tree fully when enumerating all the "other" paths, but when we are only interested in "killed" paths, we can take advantage of the fact that paths that do not overlap with entries in the index can never be killed. The treat_one_path() helper function, which is called during the recursive traversal, is the ideal place to implement an optimization. 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. Note that this helper is called by treat_leading_path() that decides if we need to traverse only subdirectories of a single common leading directory, which is essential for this optimization to be correct. This caller checks each level of the leading path component from shallower directory to deeper ones, and that is what allows us to only check if the path appears in the index. If the call to treat_one_path() weren't there, given a path P/Q/R, the real traversal may start from directory P/Q/R, even when the index records P as a regular file, and we would end up having to check if any leading subpath in P/Q/R, e.g. P, appears in the index. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-08-15 21:13:46 +02:00
if (dtype == DT_UNKNOWN)
dtype = get_dtype(de, path->buf, path->len);
/* Always exclude indexed files */
ls-files -k: a directory only can be killed if the index has a non-directory "ls-files -o" and "ls-files -k" both traverse the working tree down to find either all untracked paths or those that will be "killed" (removed from the working tree to make room) when the paths recorded in the index are checked out. It is necessary to traverse the working tree fully when enumerating all the "other" paths, but when we are only interested in "killed" paths, we can take advantage of the fact that paths that do not overlap with entries in the index can never be killed. The treat_one_path() helper function, which is called during the recursive traversal, is the ideal place to implement an optimization. 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. Note that this helper is called by treat_leading_path() that decides if we need to traverse only subdirectories of a single common leading directory, which is essential for this optimization to be correct. This caller checks each level of the leading path component from shallower directory to deeper ones, and that is what allows us to only check if the path appears in the index. If the call to treat_one_path() weren't there, given a path P/Q/R, the real traversal may start from directory P/Q/R, even when the index records P as a regular file, and we would end up having to check if any leading subpath in P/Q/R, e.g. P, appears in the index. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-08-15 21:13:46 +02:00
if (dtype != DT_DIR && has_path_in_index)
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
return path_none;
ls-files -k: a directory only can be killed if the index has a non-directory "ls-files -o" and "ls-files -k" both traverse the working tree down to find either all untracked paths or those that will be "killed" (removed from the working tree to make room) when the paths recorded in the index are checked out. It is necessary to traverse the working tree fully when enumerating all the "other" paths, but when we are only interested in "killed" paths, we can take advantage of the fact that paths that do not overlap with entries in the index can never be killed. The treat_one_path() helper function, which is called during the recursive traversal, is the ideal place to implement an optimization. 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. Note that this helper is called by treat_leading_path() that decides if we need to traverse only subdirectories of a single common leading directory, which is essential for this optimization to be correct. This caller checks each level of the leading path component from shallower directory to deeper ones, and that is what allows us to only check if the path appears in the index. If the call to treat_one_path() weren't there, given a path P/Q/R, the real traversal may start from directory P/Q/R, even when the index records P as a regular file, and we would end up having to check if any leading subpath in P/Q/R, e.g. P, appears in the index. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-08-15 21:13:46 +02:00
/*
* 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 ((dir->flags & DIR_COLLECT_KILLED_ONLY) &&
(dtype == DT_DIR) &&
!has_path_in_index &&
(directory_exists_in_index(path->buf, path->len) == index_nonexistent))
return path_none;
exclude = is_excluded(dir, path->buf, &dtype);
/*
* Excluded? If we don't explicitly want to show
* ignored files, ignore it
*/
dir.c: git-status --ignored: don't scan the work tree twice 'git-status --ignored' still scans the work tree twice to collect untracked and ignored files, respectively. fill_directory / read_directory already supports collecting untracked and ignored files in a single directory scan. However, the DIR_COLLECT_IGNORED flag to enable this has some git-add specific side-effects (e.g. it doesn't recurse into ignored directories, so listing ignored files with --untracked=all doesn't work). The DIR_SHOW_IGNORED flag doesn't list untracked files and returns ignored files in dir_struct.entries[] (instead of dir_struct.ignored[] as DIR_COLLECT_IGNORED). DIR_SHOW_IGNORED is used all throughout git. We don't want to break the existing API, so lets introduce a new flag DIR_SHOW_IGNORED_TOO that lists untracked as well as ignored files similar to DIR_COLLECT_FILES, but will recurse into sub-directories based on the other flags as DIR_SHOW_IGNORED does. In dir.c::read_directory_recursive, add ignored files to either dir_struct.entries[] or dir_struct.ignored[] based on the flags. Also move the DIR_COLLECT_IGNORED case here so that filling result lists is in a common place. In wt-status.c::wt_status_collect_untracked, use the new flag and read results from dir_struct.ignored[]. Remove the extra fill_directory call. builtin/check-ignore.c doesn't call fill_directory, setting the git-add specific DIR_COLLECT_IGNORED flag has no effect here. Remove for clarity. Update API documentation to reflect the changes. Performance: with this patch, 'git-status --ignored' is typically as fast as 'git-status'. Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:15:03 +02:00
if (exclude && !(dir->flags & (DIR_SHOW_IGNORED|DIR_SHOW_IGNORED_TOO)))
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
return path_excluded;
switch (dtype) {
default:
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
return path_none;
case DT_DIR:
strbuf_addch(path, '/');
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
return treat_directory(dir, path->buf, path->len, exclude,
simplify);
case DT_REG:
case DT_LNK:
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
return exclude ? path_excluded : path_untracked;
}
}
static enum path_treatment treat_path(struct dir_struct *dir,
struct dirent *de,
struct strbuf *path,
int baselen,
const struct path_simplify *simplify)
{
int dtype;
if (is_dot_or_dotdot(de->d_name) || !strcmp(de->d_name, ".git"))
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
return path_none;
strbuf_setlen(path, baselen);
strbuf_addstr(path, de->d_name);
if (simplify_away(path->buf, path->len, simplify))
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
return path_none;
dtype = DTYPE(de);
return treat_one_path(dir, path, simplify, dtype, de);
}
/*
* Read a directory tree. We currently ignore anything but
* directories, regular files and symlinks. That's because git
* doesn't handle them at all yet. Maybe that will change some
* day.
*
* Also, we ignore the name ".git" (even if it is not a directory).
* That likely will not change.
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
*
* Returns the most significant path_treatment value encountered in the scan.
*/
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
static enum path_treatment read_directory_recursive(struct dir_struct *dir,
const char *base, int baselen,
int check_only,
const struct path_simplify *simplify)
{
DIR *fdir;
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
enum path_treatment state, subdir_state, dir_state = path_none;
struct dirent *de;
struct strbuf path = STRBUF_INIT;
strbuf_add(&path, base, baselen);
fdir = opendir(path.len ? path.buf : ".");
if (!fdir)
goto out;
while ((de = readdir(fdir)) != NULL) {
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
/* check how the file or directory should be treated */
state = treat_path(dir, de, &path, baselen, simplify);
if (state > dir_state)
dir_state = state;
/* recurse into subdir if instructed by treat_path */
if (state == path_recurse) {
subdir_state = read_directory_recursive(dir, path.buf,
path.len, check_only, simplify);
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
if (subdir_state > dir_state)
dir_state = subdir_state;
}
if (check_only) {
/* abort early if maximum state has been reached */
if (dir_state == path_untracked)
break;
/* skip the dir_add_* part */
continue;
}
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
/* add the path to the appropriate result list */
switch (state) {
case path_excluded:
if (dir->flags & DIR_SHOW_IGNORED)
dir_add_name(dir, path.buf, path.len);
dir.c: git-status --ignored: don't scan the work tree twice 'git-status --ignored' still scans the work tree twice to collect untracked and ignored files, respectively. fill_directory / read_directory already supports collecting untracked and ignored files in a single directory scan. However, the DIR_COLLECT_IGNORED flag to enable this has some git-add specific side-effects (e.g. it doesn't recurse into ignored directories, so listing ignored files with --untracked=all doesn't work). The DIR_SHOW_IGNORED flag doesn't list untracked files and returns ignored files in dir_struct.entries[] (instead of dir_struct.ignored[] as DIR_COLLECT_IGNORED). DIR_SHOW_IGNORED is used all throughout git. We don't want to break the existing API, so lets introduce a new flag DIR_SHOW_IGNORED_TOO that lists untracked as well as ignored files similar to DIR_COLLECT_FILES, but will recurse into sub-directories based on the other flags as DIR_SHOW_IGNORED does. In dir.c::read_directory_recursive, add ignored files to either dir_struct.entries[] or dir_struct.ignored[] based on the flags. Also move the DIR_COLLECT_IGNORED case here so that filling result lists is in a common place. In wt-status.c::wt_status_collect_untracked, use the new flag and read results from dir_struct.ignored[]. Remove the extra fill_directory call. builtin/check-ignore.c doesn't call fill_directory, setting the git-add specific DIR_COLLECT_IGNORED flag has no effect here. Remove for clarity. Update API documentation to reflect the changes. Performance: with this patch, 'git-status --ignored' is typically as fast as 'git-status'. Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:15:03 +02:00
else if ((dir->flags & DIR_SHOW_IGNORED_TOO) ||
((dir->flags & DIR_COLLECT_IGNORED) &&
exclude_matches_pathspec(path.buf, path.len,
simplify)))
dir_add_ignored(dir, path.buf, path.len);
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
break;
case path_untracked:
if (!(dir->flags & DIR_SHOW_IGNORED))
dir_add_name(dir, path.buf, path.len);
break;
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
default:
break;
}
}
closedir(fdir);
out:
strbuf_release(&path);
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
return dir_state;
}
static int cmp_name(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 name_compare(e1->name, e1->len, e2->name, e2->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;
ALLOC_GROW(simplify, nr + 1, alloc);
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;
}
static void free_simplify(struct path_simplify *simplify)
{
Avoid unnecessary "if-before-free" tests. This change removes all obvious useless if-before-free tests. E.g., it replaces code like this: if (some_expression) free (some_expression); with the now-equivalent: free (some_expression); It is equivalent not just because POSIX has required free(NULL) to work for a long time, but simply because it has worked for so long that no reasonable porting target fails the test. Here's some evidence from nearly 1.5 years ago: http://www.winehq.org/pipermail/wine-patches/2006-October/031544.html FYI, the change below was prepared by running the following: git ls-files -z | xargs -0 \ perl -0x3b -pi -e \ 's/\bif\s*\(\s*(\S+?)(?:\s*!=\s*NULL)?\s*\)\s+(free\s*\(\s*\1\s*\))/$2/s' Note however, that it doesn't handle brace-enclosed blocks like "if (x) { free (x); }". But that's ok, since there were none like that in git sources. Beware: if you do use the above snippet, note that it can produce syntactically invalid C code. That happens when the affected "if"-statement has a matching "else". E.g., it would transform this if (x) free (x); else foo (); into this: free (x); else foo (); There were none of those here, either. If you're interested in automating detection of the useless tests, you might like the useless-if-before-free script in gnulib: [it *does* detect brace-enclosed free statements, and has a --name=S option to make it detect free-like functions with different names] http://git.sv.gnu.org/gitweb/?p=gnulib.git;a=blob;f=build-aux/useless-if-before-free Addendum: Remove one more (in imap-send.c), spotted by Jean-Luc Herren <jlh@gmx.ch>. Signed-off-by: Jim Meyering <meyering@redhat.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-01-31 18:26:32 +01:00
free(simplify);
}
static int treat_leading_path(struct dir_struct *dir,
const char *path, int len,
const struct path_simplify *simplify)
{
struct strbuf sb = STRBUF_INIT;
int baselen, rc = 0;
const char *cp;
int old_flags = dir->flags;
while (len && path[len - 1] == '/')
len--;
if (!len)
return 1;
baselen = 0;
dir->flags &= ~DIR_SHOW_OTHER_DIRECTORIES;
while (1) {
cp = path + baselen + !!baselen;
cp = memchr(cp, '/', path + len - cp);
if (!cp)
baselen = len;
else
baselen = cp - path;
strbuf_setlen(&sb, 0);
strbuf_add(&sb, path, baselen);
if (!is_directory(sb.buf))
break;
if (simplify_away(sb.buf, sb.len, simplify))
break;
if (treat_one_path(dir, &sb, simplify,
dir.c: git-status --ignored: don't scan the work tree three times 'git-status --ignored' recursively scans directories up to three times: 1. To collect untracked files. 2. To collect ignored files. 3. When collecting ignored files, to check that an untracked directory that potentially contains ignored files doesn't also contain untracked files (i.e. isn't already listed as untracked). Let's get rid of case 3 first. Currently, read_directory_recursive returns a boolean whether a directory contains the requested files or not (actually, it returns the number of files, but no caller actually needs that), and DIR_SHOW_IGNORED specifies what we're looking for. To be able to test for both untracked and ignored files in a single scan, we need to return a bit more info, and the result must be independent of the DIR_SHOW_IGNORED flag. Reuse the path_treatment enum as return value of read_directory_recursive. Split path_handled in two separate values path_excluded and path_untracked that don't change their meaning with the DIR_SHOW_IGNORED flag. We don't need an extra value path_untracked_and_excluded, as directories with both untracked and ignored files should be listed as untracked. Rename path_ignored to path_none for clarity (i.e. "don't treat that path" in contrast to "the path is ignored and should be treated according to DIR_SHOW_IGNORED"). Replace enum directory_treatment with path_treatment. That's just another enum with the same meaning, no need to translate back and forth. In treat_directory, get rid of the extra read_directory_recursive call and all the DIR_SHOW_IGNORED-specific code. In read_directory_recursive, decide whether to dir_add_name path_excluded or path_untracked paths based on the DIR_SHOW_IGNORED flag. The return value of read_directory_recursive is the maximum path_treatment of all files and sub-directories. In the check_only case, abort when we've reached the most significant value (path_untracked). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:14:22 +02:00
DT_DIR, NULL) == path_none)
break; /* do not recurse into it */
if (len <= baselen) {
rc = 1;
break; /* finished checking */
}
}
strbuf_release(&sb);
dir->flags = old_flags;
return rc;
}
int read_directory(struct dir_struct *dir, const char *path, int len, const struct pathspec *pathspec)
{
struct path_simplify *simplify;
/*
* Check out create_simplify()
*/
if (pathspec)
GUARD_PATHSPEC(pathspec,
PATHSPEC_FROMTOP |
PATHSPEC_MAXDEPTH |
PATHSPEC_LITERAL |
PATHSPEC_GLOB |
PATHSPEC_ICASE |
PATHSPEC_EXCLUDE);
if (has_symlink_leading_path(path, len))
return dir->nr;
/*
* exclude patterns are treated like positive ones in
* create_simplify. Usually exclude patterns should be a
* subset of positive ones, which has no impacts on
* create_simplify().
*/
simplify = create_simplify(pathspec ? pathspec->_raw : NULL);
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);
return dir->nr;
}
int file_exists(const char *f)
{
struct stat sb;
return lstat(f, &sb) == 0;
}
/*
* Given two normalized paths (a trailing slash is ok), if subdir is
* outside dir, return -1. Otherwise return the offset in subdir that
* can be used as relative path to dir.
*/
int dir_inside_of(const char *subdir, const char *dir)
{
int offset = 0;
assert(dir && subdir && *dir && *subdir);
while (*dir && *subdir && *dir == *subdir) {
dir++;
subdir++;
offset++;
}
/* hel[p]/me vs hel[l]/yeah */
if (*dir && *subdir)
return -1;
if (!*subdir)
return !*dir ? offset : -1; /* same dir */
/* foo/[b]ar vs foo/[] */
if (is_dir_sep(dir[-1]))
return is_dir_sep(subdir[-1]) ? offset : -1;
/* foo[/]bar vs foo[] */
return is_dir_sep(*subdir) ? offset + 1 : -1;
}
int is_inside_dir(const char *dir)
{
char *cwd;
int rc;
if (!dir)
return 0;
cwd = xgetcwd();
rc = (dir_inside_of(cwd, dir) >= 0);
free(cwd);
return rc;
}
int is_empty_dir(const char *path)
{
DIR *dir = opendir(path);
struct dirent *e;
int ret = 1;
if (!dir)
return 0;
while ((e = readdir(dir)) != NULL)
if (!is_dot_or_dotdot(e->d_name)) {
ret = 0;
break;
}
closedir(dir);
return ret;
}
static int remove_dir_recurse(struct strbuf *path, int flag, int *kept_up)
{
DIR *dir;
struct dirent *e;
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];
if ((flag & REMOVE_DIR_KEEP_NESTED_GIT) &&
!resolve_gitlink_ref(path->buf, "HEAD", submodule_head)) {
/* Do not descend and nuke a nested git work tree. */
if (kept_up)
*kept_up = 1;
return 0;
}
flag &= ~REMOVE_DIR_KEEP_TOPLEVEL;
dir = opendir(path->buf);
if (!dir) {
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, '/');
len = path->len;
while ((e = readdir(dir)) != NULL) {
struct stat st;
if (is_dot_or_dotdot(e->d_name))
continue;
strbuf_setlen(path, len);
strbuf_addstr(path, e->d_name);
if (lstat(path->buf, &st)) {
if (errno == ENOENT)
/*
* file disappeared, which is what we
* wanted anyway
*/
continue;
/* fall thru */
} else if (S_ISDIR(st.st_mode)) {
if (!remove_dir_recurse(path, flag, &kept_down))
continue; /* happy */
} else if (!only_empty &&
(!unlink(path->buf) || errno == ENOENT)) {
continue; /* happy, too */
}
/* path too long, stat fails, or non-directory still exists */
ret = -1;
break;
}
closedir(dir);
strbuf_setlen(path, original_len);
if (!ret && !keep_toplevel && !kept_down)
ret = (!rmdir(path->buf) || errno == ENOENT) ? 0 : -1;
else if (kept_up)
/*
* report the uplevel that it is not an error that we
* did not rmdir() our directory.
*/
*kept_up = !ret;
return ret;
}
core.excludesfile clean-up There are inconsistencies in the way commands currently handle the core.excludesfile configuration variable. The problem is the variable is too new to be noticed by anything other than git-add and git-status. * git-ls-files does not notice any of the "ignore" files by default, as it predates the standardized set of ignore files. The calling scripts established the convention to use .git/info/exclude, .gitignore, and later core.excludesfile. * git-add and git-status know about it because they call add_excludes_from_file() directly with their own notion of which standard set of ignore files to use. This is just a stupid duplication of code that need to be updated every time the definition of the standard set of ignore files is changed. * git-read-tree takes --exclude-per-directory=<gitignore>, not because the flexibility was needed. Again, this was because the option predates the standardization of the ignore files. * git-merge-recursive uses hardcoded per-directory .gitignore and nothing else. git-clean (scripted version) does not honor core.* because its call to underlying ls-files does not know about it. git-clean in C (parked in 'pu') doesn't either. We probably could change git-ls-files to use the standard set when no excludes are specified on the command line and ignore processing was asked, or something like that, but that will be a change in semantics and might break people's scripts in a subtle way. I am somewhat reluctant to make such a change. On the other hand, I think it makes perfect sense to fix git-read-tree, git-merge-recursive and git-clean to follow the same rule as other commands. I do not think of a valid use case to give an exclude-per-directory that is nonstandard to read-tree command, outside a "negative" test in the t1004 test script. This patch is the first step to untangle this mess. The next step would be to teach read-tree, merge-recursive and clean (in C) to use setup_standard_excludes(). Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-14 09:05:00 +01:00
int remove_dir_recursively(struct strbuf *path, int flag)
{
return remove_dir_recurse(path, flag, NULL);
}
core.excludesfile clean-up There are inconsistencies in the way commands currently handle the core.excludesfile configuration variable. The problem is the variable is too new to be noticed by anything other than git-add and git-status. * git-ls-files does not notice any of the "ignore" files by default, as it predates the standardized set of ignore files. The calling scripts established the convention to use .git/info/exclude, .gitignore, and later core.excludesfile. * git-add and git-status know about it because they call add_excludes_from_file() directly with their own notion of which standard set of ignore files to use. This is just a stupid duplication of code that need to be updated every time the definition of the standard set of ignore files is changed. * git-read-tree takes --exclude-per-directory=<gitignore>, not because the flexibility was needed. Again, this was because the option predates the standardization of the ignore files. * git-merge-recursive uses hardcoded per-directory .gitignore and nothing else. git-clean (scripted version) does not honor core.* because its call to underlying ls-files does not know about it. git-clean in C (parked in 'pu') doesn't either. We probably could change git-ls-files to use the standard set when no excludes are specified on the command line and ignore processing was asked, or something like that, but that will be a change in semantics and might break people's scripts in a subtle way. I am somewhat reluctant to make such a change. On the other hand, I think it makes perfect sense to fix git-read-tree, git-merge-recursive and git-clean to follow the same rule as other commands. I do not think of a valid use case to give an exclude-per-directory that is nonstandard to read-tree command, outside a "negative" test in the t1004 test script. This patch is the first step to untangle this mess. The next step would be to teach read-tree, merge-recursive and clean (in C) to use setup_standard_excludes(). Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-14 09:05:00 +01:00
void setup_standard_excludes(struct dir_struct *dir)
{
const char *path;
char *xdg_path;
core.excludesfile clean-up There are inconsistencies in the way commands currently handle the core.excludesfile configuration variable. The problem is the variable is too new to be noticed by anything other than git-add and git-status. * git-ls-files does not notice any of the "ignore" files by default, as it predates the standardized set of ignore files. The calling scripts established the convention to use .git/info/exclude, .gitignore, and later core.excludesfile. * git-add and git-status know about it because they call add_excludes_from_file() directly with their own notion of which standard set of ignore files to use. This is just a stupid duplication of code that need to be updated every time the definition of the standard set of ignore files is changed. * git-read-tree takes --exclude-per-directory=<gitignore>, not because the flexibility was needed. Again, this was because the option predates the standardization of the ignore files. * git-merge-recursive uses hardcoded per-directory .gitignore and nothing else. git-clean (scripted version) does not honor core.* because its call to underlying ls-files does not know about it. git-clean in C (parked in 'pu') doesn't either. We probably could change git-ls-files to use the standard set when no excludes are specified on the command line and ignore processing was asked, or something like that, but that will be a change in semantics and might break people's scripts in a subtle way. I am somewhat reluctant to make such a change. On the other hand, I think it makes perfect sense to fix git-read-tree, git-merge-recursive and git-clean to follow the same rule as other commands. I do not think of a valid use case to give an exclude-per-directory that is nonstandard to read-tree command, outside a "negative" test in the t1004 test script. This patch is the first step to untangle this mess. The next step would be to teach read-tree, merge-recursive and clean (in C) to use setup_standard_excludes(). Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-14 09:05:00 +01:00
dir->exclude_per_dir = ".gitignore";
path = git_path("info/exclude");
if (!excludes_file) {
home_config_paths(NULL, &xdg_path, "ignore");
excludes_file = xdg_path;
}
config: allow inaccessible configuration under $HOME The changes v1.7.12.1~2^2~4 (config: warn on inaccessible files, 2012-08-21) and v1.8.1.1~22^2~2 (config: treat user and xdg config permission problems as errors, 2012-10-13) were intended to prevent important configuration (think "[transfer] fsckobjects") from being ignored when the configuration is unintentionally unreadable (for example with EIO on a flaky filesystem, or with ENOMEM due to a DoS attack). Usually ~/.gitconfig and ~/.config/git are readable by the current user, and if they aren't then it would be easy to fix those permissions, so the damage from adding this check should have been minimal. Unfortunately the access() check often trips when git is being run as a server. A daemon (such as inetd or git-daemon) starts as "root", creates a listening socket, and then drops privileges, meaning that when git commands are invoked they cannot access $HOME and die with fatal: unable to access '/root/.config/git/config': Permission denied Any patch to fix this would have one of three problems: 1. We annoy sysadmins who need to take an extra step to handle HOME when dropping privileges (the current behavior, or any other proposal that they have to opt into). 2. We annoy sysadmins who want to set HOME when dropping privileges, either by making what they want to do impossible, or making them set an extra variable or option to accomplish what used to work (e.g., a patch to git-daemon to set HOME when --user is passed). 3. We loosen the check, so some cases which might be noteworthy are not caught. This patch is of type (3). Treat user and xdg configuration that are inaccessible due to permissions (EACCES) as though no user configuration was provided at all. An alternative method would be to check if $HOME is readable, but that would not help in cases where the user who dropped privileges had a globally readable HOME with only .config or .gitconfig being private. This does not change the behavior when /etc/gitconfig or .git/config is unreadable (since those are more serious configuration errors), nor when ~/.gitconfig or ~/.config/git is unreadable due to problems other than permissions. Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Improved-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-12 23:03:18 +02:00
if (!access_or_warn(path, R_OK, 0))
core.excludesfile clean-up There are inconsistencies in the way commands currently handle the core.excludesfile configuration variable. The problem is the variable is too new to be noticed by anything other than git-add and git-status. * git-ls-files does not notice any of the "ignore" files by default, as it predates the standardized set of ignore files. The calling scripts established the convention to use .git/info/exclude, .gitignore, and later core.excludesfile. * git-add and git-status know about it because they call add_excludes_from_file() directly with their own notion of which standard set of ignore files to use. This is just a stupid duplication of code that need to be updated every time the definition of the standard set of ignore files is changed. * git-read-tree takes --exclude-per-directory=<gitignore>, not because the flexibility was needed. Again, this was because the option predates the standardization of the ignore files. * git-merge-recursive uses hardcoded per-directory .gitignore and nothing else. git-clean (scripted version) does not honor core.* because its call to underlying ls-files does not know about it. git-clean in C (parked in 'pu') doesn't either. We probably could change git-ls-files to use the standard set when no excludes are specified on the command line and ignore processing was asked, or something like that, but that will be a change in semantics and might break people's scripts in a subtle way. I am somewhat reluctant to make such a change. On the other hand, I think it makes perfect sense to fix git-read-tree, git-merge-recursive and git-clean to follow the same rule as other commands. I do not think of a valid use case to give an exclude-per-directory that is nonstandard to read-tree command, outside a "negative" test in the t1004 test script. This patch is the first step to untangle this mess. The next step would be to teach read-tree, merge-recursive and clean (in C) to use setup_standard_excludes(). Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-14 09:05:00 +01:00
add_excludes_from_file(dir, path);
config: allow inaccessible configuration under $HOME The changes v1.7.12.1~2^2~4 (config: warn on inaccessible files, 2012-08-21) and v1.8.1.1~22^2~2 (config: treat user and xdg config permission problems as errors, 2012-10-13) were intended to prevent important configuration (think "[transfer] fsckobjects") from being ignored when the configuration is unintentionally unreadable (for example with EIO on a flaky filesystem, or with ENOMEM due to a DoS attack). Usually ~/.gitconfig and ~/.config/git are readable by the current user, and if they aren't then it would be easy to fix those permissions, so the damage from adding this check should have been minimal. Unfortunately the access() check often trips when git is being run as a server. A daemon (such as inetd or git-daemon) starts as "root", creates a listening socket, and then drops privileges, meaning that when git commands are invoked they cannot access $HOME and die with fatal: unable to access '/root/.config/git/config': Permission denied Any patch to fix this would have one of three problems: 1. We annoy sysadmins who need to take an extra step to handle HOME when dropping privileges (the current behavior, or any other proposal that they have to opt into). 2. We annoy sysadmins who want to set HOME when dropping privileges, either by making what they want to do impossible, or making them set an extra variable or option to accomplish what used to work (e.g., a patch to git-daemon to set HOME when --user is passed). 3. We loosen the check, so some cases which might be noteworthy are not caught. This patch is of type (3). Treat user and xdg configuration that are inaccessible due to permissions (EACCES) as though no user configuration was provided at all. An alternative method would be to check if $HOME is readable, but that would not help in cases where the user who dropped privileges had a globally readable HOME with only .config or .gitconfig being private. This does not change the behavior when /etc/gitconfig or .git/config is unreadable (since those are more serious configuration errors), nor when ~/.gitconfig or ~/.config/git is unreadable due to problems other than permissions. Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Improved-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-12 23:03:18 +02:00
if (excludes_file && !access_or_warn(excludes_file, R_OK, 0))
core.excludesfile clean-up There are inconsistencies in the way commands currently handle the core.excludesfile configuration variable. The problem is the variable is too new to be noticed by anything other than git-add and git-status. * git-ls-files does not notice any of the "ignore" files by default, as it predates the standardized set of ignore files. The calling scripts established the convention to use .git/info/exclude, .gitignore, and later core.excludesfile. * git-add and git-status know about it because they call add_excludes_from_file() directly with their own notion of which standard set of ignore files to use. This is just a stupid duplication of code that need to be updated every time the definition of the standard set of ignore files is changed. * git-read-tree takes --exclude-per-directory=<gitignore>, not because the flexibility was needed. Again, this was because the option predates the standardization of the ignore files. * git-merge-recursive uses hardcoded per-directory .gitignore and nothing else. git-clean (scripted version) does not honor core.* because its call to underlying ls-files does not know about it. git-clean in C (parked in 'pu') doesn't either. We probably could change git-ls-files to use the standard set when no excludes are specified on the command line and ignore processing was asked, or something like that, but that will be a change in semantics and might break people's scripts in a subtle way. I am somewhat reluctant to make such a change. On the other hand, I think it makes perfect sense to fix git-read-tree, git-merge-recursive and git-clean to follow the same rule as other commands. I do not think of a valid use case to give an exclude-per-directory that is nonstandard to read-tree command, outside a "negative" test in the t1004 test script. This patch is the first step to untangle this mess. The next step would be to teach read-tree, merge-recursive and clean (in C) to use setup_standard_excludes(). Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-14 09:05:00 +01:00
add_excludes_from_file(dir, excludes_file);
}
int remove_path(const char *name)
{
char *slash;
if (unlink(name) && errno != ENOENT && errno != ENOTDIR)
return -1;
slash = strrchr(name, '/');
if (slash) {
char *dirs = xstrdup(name);
slash = dirs + (slash - name);
do {
*slash = '\0';
} while (rmdir(dirs) == 0 && (slash = strrchr(dirs, '/')));
free(dirs);
}
return 0;
}
/*
* 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 exclude_list *el;
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++) {
el = &group->el[j];
if (i == EXC_DIRS)
free((char *)el->src);
clear_exclude_list(el);
}
free(group->el);
}
stk = dir->exclude_stack;
while (stk) {
struct exclude_stack *prev = stk->prev;
free(stk);
stk = prev;
}
strbuf_release(&dir->basebuf);
}