git/dir.c

3427 lines
91 KiB
C
Raw Normal View History

/*
* This handles recursive filename detection with exclude
* files, index knowledge etc..
*
* Copyright (C) Linus Torvalds, 2005-2006
* Junio Hamano, 2005-2006
*/
#include "cache.h"
#include "config.h"
#include "dir.h"
#include "object-store.h"
#include "attr.h"
#include "refs.h"
#include "wildmatch.h"
#include "pathspec.h"
#include "utf8.h"
#include "varint.h"
#include "ewah/ewok.h"
#include "fsmonitor.h"
#include "submodule-config.h"
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 19:14:22 +00:00
/*
* 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
};
/*
* Support data structure for our opendir/readdir/closedir wrappers
*/
struct cached_dir {
DIR *fdir;
struct untracked_cache_dir *untracked;
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
int nr_files;
int nr_dirs;
struct dirent *de;
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
const char *file;
struct untracked_cache_dir *ucd;
};
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 19:14:22 +00:00
static enum path_treatment read_directory_recursive(struct dir_struct *dir,
struct index_state *istate, const char *path, int len,
struct untracked_cache_dir *untracked,
int check_only, int stop_at_first_file, const struct pathspec *pathspec);
static int get_dtype(struct dirent *de, struct index_state *istate,
const char *path, int len);
int count_slashes(const char *s)
{
int cnt = 0;
while (*s)
if (*s++ == '/')
cnt++;
return cnt;
}
int fspathcmp(const char *a, const char *b)
{
return ignore_case ? strcasecmp(a, b) : strcmp(a, b);
}
int fspathncmp(const char *a, const char *b, size_t count)
{
return ignore_case ? strncasecmp(a, b, count) : strncmp(a, b, count);
}
int git_fnmatch(const struct pathspec_item *item,
const char *pattern, const char *string,
int prefix)
{
if (prefix > 0) {
if (ps_strncmp(item, pattern, string, prefix))
return WM_NOMATCH;
pattern += prefix;
string += prefix;
}
if (item->flags & PATHSPEC_ONESTAR) {
int pattern_len = strlen(++pattern);
int string_len = strlen(string);
return string_len < pattern_len ||
ps_strcmp(item, pattern,
string + string_len - pattern_len);
}
if (item->magic & PATHSPEC_GLOB)
return wildmatch(pattern, string,
WM_PATHNAME |
(item->magic & PATHSPEC_ICASE ? WM_CASEFOLD : 0));
else
/* wildmatch has not learned no FNM_PATHNAME mode yet */
return wildmatch(pattern, string,
item->magic & PATHSPEC_ICASE ? WM_CASEFOLD : 0);
}
static int fnmatch_icase_mem(const char *pattern, int patternlen,
const char *string, int stringlen,
int flags)
{
int match_status;
struct strbuf pat_buf = STRBUF_INIT;
struct strbuf str_buf = STRBUF_INIT;
const char *use_pat = pattern;
const char *use_str = string;
if (pattern[patternlen]) {
strbuf_add(&pat_buf, pattern, patternlen);
use_pat = pat_buf.buf;
}
if (string[stringlen]) {
strbuf_add(&str_buf, string, stringlen);
use_str = str_buf.buf;
}
if (ignore_case)
flags |= WM_CASEFOLD;
match_status = wildmatch(use_pat, use_str, flags);
strbuf_release(&pat_buf);
strbuf_release(&str_buf);
return match_status;
}
static size_t common_prefix_len(const 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 xyz/abc as
* in non-:(icase).
*/
GUARD_PATHSPEC(pathspec,
PATHSPEC_FROMTOP |
PATHSPEC_MAXDEPTH |
PATHSPEC_LITERAL |
PATHSPEC_GLOB |
PATHSPEC_ICASE |
PATHSPEC_EXCLUDE |
PATHSPEC_ATTR);
for (n = 0; n < pathspec->nr; n++) {
size_t i = 0, len = 0, item_len;
if (pathspec->items[n].magic & PATHSPEC_EXCLUDE)
continue;
if (pathspec->items[n].magic & PATHSPEC_ICASE)
item_len = pathspec->items[n].prefix;
else
item_len = pathspec->items[n].nowildcard_len;
while (i < item_len && (n == 0 || i < max)) {
char c = pathspec->items[n].match[i];
if (c != pathspec->items[0].match[i])
break;
if (c == '/')
len = i + 1;
i++;
}
if (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,
struct index_state *istate,
const struct pathspec *pathspec)
{
const char *prefix;
size_t prefix_len;
/*
* Calculate common prefix for the pathspec, and
* use that to optimize the directory walk
*/
prefix_len = common_prefix_len(pathspec);
prefix = prefix_len ? pathspec->items[0].match : "";
/* Read the directory and prune it */
read_directory(dir, istate, prefix, prefix_len, pathspec);
return prefix_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;
}
/*
* Read the contents of the blob with the given OID into a buffer.
* Append a trailing LF to the end if the last line doesn't have one.
*
* Returns:
* -1 when the OID is invalid or unknown or does not refer to a blob.
* 0 when the blob is empty.
* 1 along with { data, size } of the (possibly augmented) buffer
* when successful.
*
* Optionally updates the given oid_stat with the given OID (when valid).
*/
static int do_read_blob(const struct object_id *oid, struct oid_stat *oid_stat,
size_t *size_out, char **data_out)
{
enum object_type type;
unsigned long sz;
char *data;
*size_out = 0;
*data_out = NULL;
data = read_object_file(oid, &type, &sz);
if (!data || type != OBJ_BLOB) {
free(data);
return -1;
}
if (oid_stat) {
memset(&oid_stat->stat, 0, sizeof(oid_stat->stat));
oidcpy(&oid_stat->oid, oid);
}
if (sz == 0) {
free(data);
return 0;
}
if (data[sz - 1] != '\n') {
data = xrealloc(data, st_add(sz, 1));
data[sz++] = '\n';
}
*size_out = xsize_t(sz);
*data_out = data;
return 1;
}
#define DO_MATCH_EXCLUDE (1<<0)
#define DO_MATCH_DIRECTORY (1<<1)
#define DO_MATCH_LEADING_PATHSPEC (1<<2)
/*
* Does the given pathspec match the given name? A match is found if
*
* (1) the pathspec string is leading directory of 'name' ("RECURSIVELY"), or
* (2) the pathspec string has a leading part matching 'name' ("LEADING"), or
* (3) the pathspec string is a wildcard and matches 'name' ("WILDCARD"), or
* (4) the pathspec string is exactly the same as 'name' ("EXACT").
*
* Return value tells which case it was (1-4), or 0 when there is no match.
*
* It may be instructive to look at a small table of concrete examples
* to understand the differences between 1, 2, and 4:
*
* Pathspecs
* | a/b | a/b/ | a/b/c
* ------+-----------+-----------+------------
* a/b | EXACT | EXACT[1] | LEADING[2]
* Names a/b/ | RECURSIVE | EXACT | LEADING[2]
* a/b/c | RECURSIVE | RECURSIVE | EXACT
*
* [1] Only if DO_MATCH_DIRECTORY is passed; otherwise, this is NOT a match.
* [2] Only if DO_MATCH_LEADING_PATHSPEC is passed; otherwise, not a match.
*/
static int match_pathspec_item(const struct index_state *istate,
const struct pathspec_item *item, int prefix,
const char *name, int namelen, unsigned flags)
{
/* name/namelen has prefix cut off by caller */
const char *match = item->match + prefix;
int matchlen = item->len - prefix;
/*
* The normal call pattern is:
* 1. prefix = common_prefix_len(ps);
* 2. prune something, or fill_directory
* 3. match_pathspec()
*
* 'prefix' at #1 may be shorter than the command's prefix and
* it's ok for #2 to match extra files. Those extras will be
* trimmed at #3.
*
* Suppose the pathspec is 'foo' and '../bar' running from
* subdir 'xyz'. The common prefix at #1 will be empty, thanks
* to "../". We may have xyz/foo _and_ XYZ/foo after #2. The
* user does not want XYZ/foo, only the "foo" part should be
* case-insensitive. We need to filter out XYZ/foo here. In
* other words, we do not trust the caller on comparing the
* prefix part when :(icase) is involved. We do exact
* comparison ourselves.
*
* Normally the caller (common_prefix_len() in fact) does
* _exact_ matching on name[-prefix+1..-1] and we do not need
* to check that part. Be defensive and check it anyway, in
* case common_prefix_len is changed, or a new caller is
* introduced that does not use common_prefix_len.
*
* If the penalty turns out too high when prefix is really
* long, maybe change it to
* strncmp(match, name, item->prefix - prefix)
*/
if (item->prefix && (item->magic & PATHSPEC_ICASE) &&
strncmp(item->match, name - prefix, item->prefix))
return 0;
if (item->attr_match_nr &&
!match_pathspec_attrs(istate, name, namelen, item))
return 0;
/* If the match was just the prefix, we matched */
if (!*match)
return MATCHED_RECURSIVELY;
if (matchlen <= namelen && !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;
/* Perform checks to see if "name" is a leading string of the pathspec */
if (flags & DO_MATCH_LEADING_PATHSPEC) {
/* name is a literal prefix of the pathspec */
int offset = name[namelen-1] == '/' ? 1 : 0;
if ((namelen < matchlen) &&
(match[namelen-offset] == '/') &&
!ps_strncmp(item, match, name, namelen))
dir: if our pathspec might match files under a dir, recurse into it For git clean, if a directory is entirely untracked and the user did not specify -d (corresponding to DIR_SHOW_IGNORED_TOO), then we usually do not want to remove that directory and thus do not recurse into it. However, if the user manually specified specific (or even globbed) paths somewhere under that directory to remove, then we need to recurse into the directory to make sure we remove the relevant paths under that directory as the user requested. Note that this does not mean that the recursed-into directory will be added to dir->entries for later removal; as of a few commits earlier in this series, there is another more strict match check that is run after returning from a recursed-into directory before deciding to add it to the list of entries. Therefore, this will only result in files underneath the given directory which match one of the pathspecs being added to the entries list. Two notes of potential interest to future readers: * If we wanted to only recurse into a directory when it is specifically matched rather than matched-via-glob (e.g. '*.c'), then we could do so via making the final non-zero return in match_pathspec_item be MATCHED_RECURSIVELY instead of MATCHED_RECURSIVELY_LEADING_PATHSPEC. (Note that the relative order of MATCHED_RECURSIVELY_LEADING_PATHSPEC and MATCHED_RECURSIVELY are important for such a change.) I was leaving open that possibility while writing an RFC asking for the behavior we want, but even though we don't want it, that knowledge might help you understand the code flow better. * There is a growing amount of logic in read_directory_recursive() for deciding whether to recurse into a subdirectory. However, there is a comment immediately preceding this logic that says to recurse if instructed by treat_path(). It may be better for the logic in read_directory_recursive() to ultimately be moved to treat_path() (or another function it calls, such as treat_directory()), but I have left that for someone else to tackle in the future. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-17 16:34:58 +00:00
return MATCHED_RECURSIVELY_LEADING_PATHSPEC;
/* name doesn't match up to the first wild character */
if (item->nowildcard_len < item->len &&
ps_strncmp(item, match, name,
item->nowildcard_len - prefix))
return 0;
/*
* name has no wildcard, and it didn't match as a leading
* pathspec so return.
*/
if (item->nowildcard_len == item->len)
return 0;
/*
* Here is where we would perform a wildmatch to check if
* "name" can be matched as a directory (or a prefix) against
* the pathspec. Since wildmatch doesn't have this capability
* at the present we have to punt and say that it is a match,
* potentially returning a false positive
* The submodules themselves will be able to perform more
* accurate matching to determine if the pathspec matches.
*/
dir: if our pathspec might match files under a dir, recurse into it For git clean, if a directory is entirely untracked and the user did not specify -d (corresponding to DIR_SHOW_IGNORED_TOO), then we usually do not want to remove that directory and thus do not recurse into it. However, if the user manually specified specific (or even globbed) paths somewhere under that directory to remove, then we need to recurse into the directory to make sure we remove the relevant paths under that directory as the user requested. Note that this does not mean that the recursed-into directory will be added to dir->entries for later removal; as of a few commits earlier in this series, there is another more strict match check that is run after returning from a recursed-into directory before deciding to add it to the list of entries. Therefore, this will only result in files underneath the given directory which match one of the pathspecs being added to the entries list. Two notes of potential interest to future readers: * If we wanted to only recurse into a directory when it is specifically matched rather than matched-via-glob (e.g. '*.c'), then we could do so via making the final non-zero return in match_pathspec_item be MATCHED_RECURSIVELY instead of MATCHED_RECURSIVELY_LEADING_PATHSPEC. (Note that the relative order of MATCHED_RECURSIVELY_LEADING_PATHSPEC and MATCHED_RECURSIVELY are important for such a change.) I was leaving open that possibility while writing an RFC asking for the behavior we want, but even though we don't want it, that knowledge might help you understand the code flow better. * There is a growing amount of logic in read_directory_recursive() for deciding whether to recurse into a subdirectory. However, there is a comment immediately preceding this logic that says to recurse if instructed by treat_path(). It may be better for the logic in read_directory_recursive() to ultimately be moved to treat_path() (or another function it calls, such as treat_directory()), but I have left that for someone else to tackle in the future. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-17 16:34:58 +00:00
return MATCHED_RECURSIVELY_LEADING_PATHSPEC;
}
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 index_state *istate,
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 |
PATHSPEC_ATTR);
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(istate, ps->items+i, prefix, name,
namelen, flags);
if (ps->recursive &&
(ps->magic & PATHSPEC_MAXDEPTH) &&
ps->max_depth != -1 &&
how && how != MATCHED_FNMATCH) {
int len = ps->items[i].len;
if (name[len] == '/')
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 index_state *istate,
const struct pathspec *ps,
const char *name, int namelen,
int prefix, char *seen, int is_dir)
{
int positive, negative;
unsigned flags = is_dir ? DO_MATCH_DIRECTORY : 0;
positive = do_match_pathspec(istate, ps, name, namelen,
prefix, seen, flags);
if (!(ps->magic & PATHSPEC_EXCLUDE) || !positive)
return positive;
negative = do_match_pathspec(istate, ps, name, namelen,
prefix, seen,
flags | DO_MATCH_EXCLUDE);
return negative ? 0 : positive;
}
/**
* Check if a submodule is a superset of the pathspec
*/
int submodule_path_match(const struct index_state *istate,
const struct pathspec *ps,
const char *submodule_name,
char *seen)
{
int matched = do_match_pathspec(istate, ps, submodule_name,
strlen(submodule_name),
0, seen,
DO_MATCH_DIRECTORY |
DO_MATCH_LEADING_PATHSPEC);
return matched;
}
int report_path_error(const char *ps_matched,
const struct pathspec *pathspec)
{
/*
* Make sure all pathspec matched; otherwise it is an error.
*/
int num, errors = 0;
for (num = 0; num < pathspec->nr; num++) {
int other, found_dup;
if (ps_matched[num])
continue;
/*
* The caller might have fed identical pathspec
* twice. Do not barf on such a mistake.
* FIXME: parse_pathspec should have eliminated
* duplicate pathspec.
*/
for (found_dup = other = 0;
!found_dup && other < pathspec->nr;
other++) {
if (other == num || !ps_matched[other])
continue;
if (!strcmp(pathspec->items[other].original,
pathspec->items[num].original))
/*
* Ok, we have a match already.
*/
found_dup = 1;
}
if (found_dup)
continue;
error(_("pathspec '%s' did not match any file(s) known to git"),
pathspec->items[num].original);
errors++;
}
return errors;
}
/*
* 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';
}
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
void parse_path_pattern(const char **pattern,
int *patternlen,
unsigned *flags,
int *nowildcardlen)
{
const char *p = *pattern;
size_t i, len;
*flags = 0;
if (*p == '!') {
*flags |= PATTERN_FLAG_NEGATIVE;
p++;
}
len = strlen(p);
if (len && p[len - 1] == '/') {
len--;
*flags |= PATTERN_FLAG_MUSTBEDIR;
}
for (i = 0; i < len; i++) {
if (p[i] == '/')
break;
}
if (i == len)
*flags |= PATTERN_FLAG_NODIR;
*nowildcardlen = simple_length(p);
/*
* we should have excluded the trailing slash from 'p' too,
* but that's one more allocation. Instead just make sure
* nowildcardlen does not exceed real patternlen
*/
if (*nowildcardlen > len)
*nowildcardlen = len;
if (*p == '*' && no_wildcard(p + 1))
*flags |= PATTERN_FLAG_ENDSWITH;
*pattern = p;
*patternlen = len;
}
int pl_hashmap_cmp(const void *unused_cmp_data,
const struct hashmap_entry *a,
const struct hashmap_entry *b,
const void *key)
{
const struct pattern_entry *ee1 =
container_of(a, struct pattern_entry, ent);
const struct pattern_entry *ee2 =
container_of(b, struct pattern_entry, ent);
size_t min_len = ee1->patternlen <= ee2->patternlen
? ee1->patternlen
: ee2->patternlen;
sparse-checkout: respect core.ignoreCase in cone mode When a user uses the sparse-checkout feature in cone mode, they add patterns using "git sparse-checkout set <dir1> <dir2> ..." or by using "--stdin" to provide the directories line-by-line over stdin. This behaviour naturally looks a lot like the way a user would type "git add <dir1> <dir2> ..." If core.ignoreCase is enabled, then "git add" will match the input using a case-insensitive match. Do the same for the sparse-checkout feature. Perform case-insensitive checks while updating the skip-worktree bits during unpack_trees(). This is done by changing the hash algorithm and hashmap comparison methods to optionally use case- insensitive methods. When this is enabled, there is a small performance cost in the hashing algorithm. To tease out the worst possible case, the following was run on a repo with a deep directory structure: git ls-tree -d -r --name-only HEAD | git sparse-checkout set --stdin The 'set' command was timed with core.ignoreCase disabled or enabled. For the repo with a deep history, the numbers were core.ignoreCase=false: 62s core.ignoreCase=true: 74s (+19.3%) For reproducibility, the equivalent test on the Linux kernel repository had these numbers: core.ignoreCase=false: 3.1s core.ignoreCase=true: 3.6s (+16%) Now, this is not an entirely fair comparison, as most users will define their sparse cone using more shallow directories, and the performance improvement from eb42feca97 ("unpack-trees: hash less in cone mode" 2019-11-21) can remove most of the hash cost. For a more realistic test, drop the "-r" from the ls-tree command to store only the first-level directories. In that case, the Linux kernel repository takes 0.2-0.25s in each case, and the deep repository takes one second, plus or minus 0.05s, in each case. Thus, we _can_ demonstrate a cost to this change, but it is unlikely to matter to any reasonable sparse-checkout cone. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-12-13 18:09:53 +00:00
if (ignore_case)
return strncasecmp(ee1->pattern, ee2->pattern, min_len);
return strncmp(ee1->pattern, ee2->pattern, min_len);
}
static void add_pattern_to_hashsets(struct pattern_list *pl, struct path_pattern *given)
{
struct pattern_entry *translated;
char *truncated;
char *data = NULL;
if (!pl->use_cone_patterns)
return;
if (given->flags & PATTERN_FLAG_NEGATIVE &&
given->flags & PATTERN_FLAG_MUSTBEDIR &&
!strcmp(given->pattern, "/*")) {
pl->full_cone = 0;
return;
}
if (!given->flags && !strcmp(given->pattern, "/*")) {
pl->full_cone = 1;
return;
}
if (given->patternlen > 2 &&
!strcmp(given->pattern + given->patternlen - 2, "/*")) {
if (!(given->flags & PATTERN_FLAG_NEGATIVE)) {
/* Not a cone pattern. */
pl->use_cone_patterns = 0;
warning(_("unrecognized pattern: '%s'"), given->pattern);
goto clear_hashmaps;
}
truncated = xstrdup(given->pattern);
truncated[given->patternlen - 2] = 0;
translated = xmalloc(sizeof(struct pattern_entry));
translated->pattern = truncated;
translated->patternlen = given->patternlen - 2;
hashmap_entry_init(&translated->ent,
sparse-checkout: respect core.ignoreCase in cone mode When a user uses the sparse-checkout feature in cone mode, they add patterns using "git sparse-checkout set <dir1> <dir2> ..." or by using "--stdin" to provide the directories line-by-line over stdin. This behaviour naturally looks a lot like the way a user would type "git add <dir1> <dir2> ..." If core.ignoreCase is enabled, then "git add" will match the input using a case-insensitive match. Do the same for the sparse-checkout feature. Perform case-insensitive checks while updating the skip-worktree bits during unpack_trees(). This is done by changing the hash algorithm and hashmap comparison methods to optionally use case- insensitive methods. When this is enabled, there is a small performance cost in the hashing algorithm. To tease out the worst possible case, the following was run on a repo with a deep directory structure: git ls-tree -d -r --name-only HEAD | git sparse-checkout set --stdin The 'set' command was timed with core.ignoreCase disabled or enabled. For the repo with a deep history, the numbers were core.ignoreCase=false: 62s core.ignoreCase=true: 74s (+19.3%) For reproducibility, the equivalent test on the Linux kernel repository had these numbers: core.ignoreCase=false: 3.1s core.ignoreCase=true: 3.6s (+16%) Now, this is not an entirely fair comparison, as most users will define their sparse cone using more shallow directories, and the performance improvement from eb42feca97 ("unpack-trees: hash less in cone mode" 2019-11-21) can remove most of the hash cost. For a more realistic test, drop the "-r" from the ls-tree command to store only the first-level directories. In that case, the Linux kernel repository takes 0.2-0.25s in each case, and the deep repository takes one second, plus or minus 0.05s, in each case. Thus, we _can_ demonstrate a cost to this change, but it is unlikely to matter to any reasonable sparse-checkout cone. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-12-13 18:09:53 +00:00
ignore_case ?
strihash(translated->pattern) :
strhash(translated->pattern));
if (!hashmap_get_entry(&pl->recursive_hashmap,
translated, ent, NULL)) {
/* We did not see the "parent" included */
warning(_("unrecognized negative pattern: '%s'"),
given->pattern);
free(truncated);
free(translated);
goto clear_hashmaps;
}
hashmap_add(&pl->parent_hashmap, &translated->ent);
hashmap_remove(&pl->recursive_hashmap, &translated->ent, &data);
free(data);
return;
}
if (given->flags & PATTERN_FLAG_NEGATIVE) {
warning(_("unrecognized negative pattern: '%s'"),
given->pattern);
goto clear_hashmaps;
}
translated = xmalloc(sizeof(struct pattern_entry));
translated->pattern = xstrdup(given->pattern);
translated->patternlen = given->patternlen;
hashmap_entry_init(&translated->ent,
sparse-checkout: respect core.ignoreCase in cone mode When a user uses the sparse-checkout feature in cone mode, they add patterns using "git sparse-checkout set <dir1> <dir2> ..." or by using "--stdin" to provide the directories line-by-line over stdin. This behaviour naturally looks a lot like the way a user would type "git add <dir1> <dir2> ..." If core.ignoreCase is enabled, then "git add" will match the input using a case-insensitive match. Do the same for the sparse-checkout feature. Perform case-insensitive checks while updating the skip-worktree bits during unpack_trees(). This is done by changing the hash algorithm and hashmap comparison methods to optionally use case- insensitive methods. When this is enabled, there is a small performance cost in the hashing algorithm. To tease out the worst possible case, the following was run on a repo with a deep directory structure: git ls-tree -d -r --name-only HEAD | git sparse-checkout set --stdin The 'set' command was timed with core.ignoreCase disabled or enabled. For the repo with a deep history, the numbers were core.ignoreCase=false: 62s core.ignoreCase=true: 74s (+19.3%) For reproducibility, the equivalent test on the Linux kernel repository had these numbers: core.ignoreCase=false: 3.1s core.ignoreCase=true: 3.6s (+16%) Now, this is not an entirely fair comparison, as most users will define their sparse cone using more shallow directories, and the performance improvement from eb42feca97 ("unpack-trees: hash less in cone mode" 2019-11-21) can remove most of the hash cost. For a more realistic test, drop the "-r" from the ls-tree command to store only the first-level directories. In that case, the Linux kernel repository takes 0.2-0.25s in each case, and the deep repository takes one second, plus or minus 0.05s, in each case. Thus, we _can_ demonstrate a cost to this change, but it is unlikely to matter to any reasonable sparse-checkout cone. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-12-13 18:09:53 +00:00
ignore_case ?
strihash(translated->pattern) :
strhash(translated->pattern));
hashmap_add(&pl->recursive_hashmap, &translated->ent);
if (hashmap_get_entry(&pl->parent_hashmap, translated, ent, NULL)) {
/* we already included this at the parent level */
warning(_("your sparse-checkout file may have issues: pattern '%s' is repeated"),
given->pattern);
hashmap_remove(&pl->parent_hashmap, &translated->ent, &data);
free(data);
free(translated);
}
return;
clear_hashmaps:
warning(_("disabling cone pattern matching"));
hashmap_free_entries(&pl->parent_hashmap, struct pattern_entry, ent);
hashmap_free_entries(&pl->recursive_hashmap, struct pattern_entry, ent);
pl->use_cone_patterns = 0;
}
static int hashmap_contains_path(struct hashmap *map,
struct strbuf *pattern)
{
struct pattern_entry p;
/* Check straight mapping */
p.pattern = pattern->buf;
p.patternlen = pattern->len;
sparse-checkout: respect core.ignoreCase in cone mode When a user uses the sparse-checkout feature in cone mode, they add patterns using "git sparse-checkout set <dir1> <dir2> ..." or by using "--stdin" to provide the directories line-by-line over stdin. This behaviour naturally looks a lot like the way a user would type "git add <dir1> <dir2> ..." If core.ignoreCase is enabled, then "git add" will match the input using a case-insensitive match. Do the same for the sparse-checkout feature. Perform case-insensitive checks while updating the skip-worktree bits during unpack_trees(). This is done by changing the hash algorithm and hashmap comparison methods to optionally use case- insensitive methods. When this is enabled, there is a small performance cost in the hashing algorithm. To tease out the worst possible case, the following was run on a repo with a deep directory structure: git ls-tree -d -r --name-only HEAD | git sparse-checkout set --stdin The 'set' command was timed with core.ignoreCase disabled or enabled. For the repo with a deep history, the numbers were core.ignoreCase=false: 62s core.ignoreCase=true: 74s (+19.3%) For reproducibility, the equivalent test on the Linux kernel repository had these numbers: core.ignoreCase=false: 3.1s core.ignoreCase=true: 3.6s (+16%) Now, this is not an entirely fair comparison, as most users will define their sparse cone using more shallow directories, and the performance improvement from eb42feca97 ("unpack-trees: hash less in cone mode" 2019-11-21) can remove most of the hash cost. For a more realistic test, drop the "-r" from the ls-tree command to store only the first-level directories. In that case, the Linux kernel repository takes 0.2-0.25s in each case, and the deep repository takes one second, plus or minus 0.05s, in each case. Thus, we _can_ demonstrate a cost to this change, but it is unlikely to matter to any reasonable sparse-checkout cone. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-12-13 18:09:53 +00:00
hashmap_entry_init(&p.ent,
ignore_case ?
strihash(p.pattern) :
strhash(p.pattern));
return !!hashmap_get_entry(map, &p, ent, NULL);
}
int hashmap_contains_parent(struct hashmap *map,
const char *path,
struct strbuf *buffer)
{
char *slash_pos;
strbuf_setlen(buffer, 0);
if (path[0] != '/')
strbuf_addch(buffer, '/');
strbuf_addstr(buffer, path);
slash_pos = strrchr(buffer->buf, '/');
while (slash_pos > buffer->buf) {
strbuf_setlen(buffer, slash_pos - buffer->buf);
if (hashmap_contains_path(map, buffer))
return 1;
slash_pos = strrchr(buffer->buf, '/');
}
return 0;
}
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
void add_pattern(const char *string, const char *base,
int baselen, struct pattern_list *pl, int srcpos)
{
struct path_pattern *pattern;
int patternlen;
unsigned flags;
int nowildcardlen;
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
parse_path_pattern(&string, &patternlen, &flags, &nowildcardlen);
if (flags & PATTERN_FLAG_MUSTBEDIR) {
FLEXPTR_ALLOC_MEM(pattern, pattern, string, patternlen);
} else {
pattern = xmalloc(sizeof(*pattern));
pattern->pattern = string;
}
pattern->patternlen = patternlen;
pattern->nowildcardlen = nowildcardlen;
pattern->base = base;
pattern->baselen = baselen;
pattern->flags = flags;
pattern->srcpos = srcpos;
ALLOC_GROW(pl->patterns, pl->nr + 1, pl->alloc);
pl->patterns[pl->nr++] = pattern;
pattern->pl = pl;
add_pattern_to_hashsets(pl, pattern);
}
static int read_skip_worktree_file_from_index(const struct index_state *istate,
const char *path,
size_t *size_out, char **data_out,
struct oid_stat *oid_stat)
{
int pos, len;
len = strlen(path);
pos = index_name_pos(istate, path, len);
if (pos < 0)
return -1;
if (!ce_skip_worktree(istate->cache[pos]))
return -1;
return do_read_blob(&istate->cache[pos]->oid, oid_stat, size_out, data_out);
}
/*
* Frees memory within pl which was allocated for exclude patterns and
* the file buffer. Does not free pl itself.
*/
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
void clear_pattern_list(struct pattern_list *pl)
{
int i;
for (i = 0; i < pl->nr; i++)
free(pl->patterns[i]);
free(pl->patterns);
free(pl->filebuf);
memset(pl, 0, sizeof(*pl));
}
static void trim_trailing_spaces(char *buf)
{
char *p, *last_space = NULL;
for (p = buf; *p; p++)
switch (*p) {
case ' ':
if (!last_space)
last_space = p;
break;
case '\\':
p++;
if (!*p)
return;
/* fallthrough */
default:
last_space = NULL;
}
if (last_space)
*last_space = '\0';
}
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
/*
* Given a subdirectory name and "dir" of the current directory,
* search the subdir in "dir" and return it, or create a new one if it
* does not exist in "dir".
*
* If "name" has the trailing slash, it'll be excluded in the search.
*/
static struct untracked_cache_dir *lookup_untracked(struct untracked_cache *uc,
struct untracked_cache_dir *dir,
const char *name, int len)
{
int first, last;
struct untracked_cache_dir *d;
if (!dir)
return NULL;
if (len && name[len - 1] == '/')
len--;
first = 0;
last = dir->dirs_nr;
while (last > first) {
int cmp, next = first + ((last - first) >> 1);
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
d = dir->dirs[next];
cmp = strncmp(name, d->name, len);
if (!cmp && strlen(d->name) > len)
cmp = -1;
if (!cmp)
return d;
if (cmp < 0) {
last = next;
continue;
}
first = next+1;
}
uc->dir_created++;
FLEX_ALLOC_MEM(d, name, name, len);
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
ALLOC_GROW(dir->dirs, dir->dirs_nr + 1, dir->dirs_alloc);
MOVE_ARRAY(dir->dirs + first + 1, dir->dirs + first,
dir->dirs_nr - first);
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
dir->dirs_nr++;
dir->dirs[first] = d;
return d;
}
static void do_invalidate_gitignore(struct untracked_cache_dir *dir)
{
int i;
dir->valid = 0;
dir->untracked_nr = 0;
for (i = 0; i < dir->dirs_nr; i++)
do_invalidate_gitignore(dir->dirs[i]);
}
static void invalidate_gitignore(struct untracked_cache *uc,
struct untracked_cache_dir *dir)
{
uc->gitignore_invalidated++;
do_invalidate_gitignore(dir);
}
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
static void invalidate_directory(struct untracked_cache *uc,
struct untracked_cache_dir *dir)
{
int i;
dir.c: fix missing dir invalidation in untracked code Let's start with how create a new directory cache after the last one becomes invalid (e.g. because its dir mtime has changed...). In open_cached_dir(): 1. We start out with valid_cached_dir() returning false, which should call invalidate_directory() to put a directory state back to initial state, no untracked entries (untracked_nr zero), no sub directory traversal (dirs[].recurse zero). 2. Since the cache cannot be used, we go the slow path opendir() and go through items one by one via readdir(). All the directories on disk will be added back to the cache (if not already exist in dirs[]) and its flag "recurse" gets changed to one to note that it's part of the cached dir travesal next time. 3. By the time we reach close_cached_dir() we should have a good subdir list in dirs[]. Those with "recurse" flag set are the ones present in the on-disk directory. The directory is now marked "valid". Next time read_directory() is called, since the directory is marked valid, it will skip readdir(), go fast path and traverse through dirs[] array instead. Steps one and two need some tight cooperation. If a subdir is removed, readdir() will not find it and of course we cannot examine/invalidate it. To make sure removed directories on disk are gone from the cache, step one must make sure recurse flag of all subdirs are zero. But that's not true. If "valid" flag is already false, there is a chance we go straight to the end of valid_cached_dir() without calling invalidate_directory(). Or we fail to meet the "if (untracked-valid)" condition and skip over the invalidate_directory(). After step 3, we mark the cache valid. Any stale subdir with incorrect recurse flag becomes a real subdir next time we traverse the directory using dirs[] array. We could avoid this by making sure invalidate_directory() is always called (therefore dirs[].recurse cleared) at the beginning of open_cached_dir(). Which is what this patch does. As to how we get into this situation, the key in the test is this command git checkout master where "one/file" is replaced with "one" in the index. This index update triggers untracked_cache_invalidate_path(), which clears valid flag of the root directory while keeping "recurse" flag on the subdir "one" on. On the next git-status, we go through steps 1-3 above and save an incorrect cache on disk. The second git-status blindly follows the bad cache data and shows the problem. This is arguably because of a bad design where "recurse" flag plays double roles: whether a directory should be saved on disk, and whether it is part of a directory traversal. We need to keep recurse flag set at "checkout master" because of the first role: we need to keep subdir caches (dir "two" for example has not been touched at all, no reason to throw its cache away). As long as we make sure to ignore/reset "recurse" flag at the beginning of a directory traversal, we're good. But maybe eventually we should separate these two roles. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-01-24 09:30:21 +00:00
/*
* Invalidation increment here is just roughly correct. If
* untracked_nr or any of dirs[].recurse is non-zero, we
* should increment dir_invalidated too. But that's more
* expensive to do.
*/
if (dir->valid)
uc->dir_invalidated++;
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
dir->valid = 0;
dir->untracked_nr = 0;
for (i = 0; i < dir->dirs_nr; i++)
dir->dirs[i]->recurse = 0;
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
}
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
static int add_patterns_from_buffer(char *buf, size_t size,
const char *base, int baselen,
struct pattern_list *pl);
/*
* Given a file with name "fname", read it (either from disk, or from
* an index if 'istate' is non-null), parse it and store the
* exclude rules in "pl".
*
* If "ss" is not NULL, compute SHA-1 of the exclude file and fill
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
* stat data from disk (only valid if add_patterns returns zero). If
* ss_valid is non-zero, "ss" must contain good value as input.
*/
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
static int add_patterns(const char *fname, const char *base, int baselen,
struct pattern_list *pl, struct index_state *istate,
struct oid_stat *oid_stat)
{
struct stat st;
int r;
int fd;
size_t size = 0;
char *buf;
fd = open(fname, O_RDONLY);
if (fd < 0 || fstat(fd, &st) < 0) {
if (fd < 0)
warn_on_fopen_errors(fname);
else
close(fd);
if (!istate)
return -1;
r = read_skip_worktree_file_from_index(istate, fname,
&size, &buf,
oid_stat);
if (r != 1)
return r;
} else {
size = xsize_t(st.st_size);
if (size == 0) {
if (oid_stat) {
fill_stat_data(&oid_stat->stat, &st);
oidcpy(&oid_stat->oid, the_hash_algo->empty_blob);
oid_stat->valid = 1;
}
close(fd);
return 0;
}
buf = xmallocz(size);
if (read_in_full(fd, buf, size) != size) {
free(buf);
close(fd);
return -1;
}
buf[size++] = '\n';
close(fd);
if (oid_stat) {
int pos;
if (oid_stat->valid &&
!match_stat_data_racy(istate, &oid_stat->stat, &st))
; /* no content change, ss->sha1 still good */
else if (istate &&
(pos = index_name_pos(istate, fname, strlen(fname))) >= 0 &&
!ce_stage(istate->cache[pos]) &&
ce_uptodate(istate->cache[pos]) &&
!would_convert_to_git(istate, fname))
oidcpy(&oid_stat->oid,
&istate->cache[pos]->oid);
else
hash_object_file(buf, size, "blob",
&oid_stat->oid);
fill_stat_data(&oid_stat->stat, &st);
oid_stat->valid = 1;
}
}
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
add_patterns_from_buffer(buf, size, base, baselen, pl);
return 0;
}
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
static int add_patterns_from_buffer(char *buf, size_t size,
const char *base, int baselen,
struct pattern_list *pl)
{
int i, lineno = 1;
char *entry;
hashmap_init(&pl->recursive_hashmap, pl_hashmap_cmp, NULL, 0);
hashmap_init(&pl->parent_hashmap, pl_hashmap_cmp, NULL, 0);
pl->filebuf = buf;
if (skip_utf8_bom(&buf, size))
size -= buf - pl->filebuf;
entry = buf;
for (i = 0; i < size; i++) {
if (buf[i] == '\n') {
if (entry != buf + i && entry[0] != '#') {
buf[i - (i && buf[i-1] == '\r')] = 0;
trim_trailing_spaces(entry);
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
add_pattern(entry, base, baselen, pl, lineno);
}
lineno++;
entry = buf + i + 1;
}
}
return 0;
}
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
int add_patterns_from_file_to_list(const char *fname, const char *base,
int baselen, struct pattern_list *pl,
struct index_state *istate)
{
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
return add_patterns(fname, base, baselen, pl, istate, NULL);
}
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
int add_patterns_from_blob_to_list(
struct object_id *oid,
const char *base, int baselen,
struct pattern_list *pl)
{
char *buf;
size_t size;
int r;
r = do_read_blob(oid, NULL, &size, &buf);
if (r != 1)
return r;
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
add_patterns_from_buffer(buf, size, base, baselen, pl);
return 0;
}
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
struct pattern_list *add_pattern_list(struct dir_struct *dir,
int group_type, const char *src)
{
struct pattern_list *pl;
struct exclude_list_group *group;
group = &dir->exclude_list_group[group_type];
ALLOC_GROW(group->pl, group->nr + 1, group->alloc);
pl = &group->pl[group->nr++];
memset(pl, 0, sizeof(*pl));
pl->src = src;
return pl;
}
/*
* Used to set up core.excludesfile and .git/info/exclude lists.
*/
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
static void add_patterns_from_file_1(struct dir_struct *dir, const char *fname,
struct oid_stat *oid_stat)
{
struct pattern_list *pl;
/*
* catch setup_standard_excludes() that's called before
* dir->untracked is assigned. That function behaves
* differently when dir->untracked is non-NULL.
*/
if (!dir->untracked)
dir->unmanaged_exclude_files++;
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
pl = add_pattern_list(dir, EXC_FILE, fname);
if (add_patterns(fname, "", 0, pl, NULL, oid_stat) < 0)
die(_("cannot use %s as an exclude file"), fname);
}
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
void add_patterns_from_file(struct dir_struct *dir, const char *fname)
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
{
dir->unmanaged_exclude_files++; /* see validate_untracked_cache() */
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
add_patterns_from_file_1(dir, fname, NULL);
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
}
int match_basename(const char *basename, int basenamelen,
const char *pattern, int prefix, int patternlen,
unsigned flags)
{
if (prefix == patternlen) {
if (patternlen == basenamelen &&
!fspathncmp(pattern, basename, basenamelen))
return 1;
} else if (flags & PATTERN_FLAG_ENDSWITH) {
/* "*literal" matching against "fooliteral" */
if (patternlen - 1 <= basenamelen &&
!fspathncmp(pattern + 1,
basename + basenamelen - (patternlen - 1),
patternlen - 1))
return 1;
} else {
if (fnmatch_icase_mem(pattern, patternlen,
basename, basenamelen,
0) == 0)
return 1;
}
return 0;
}
int match_pathname(const char *pathname, int pathlen,
const char *base, int baselen,
const char *pattern, int prefix, int patternlen,
unsigned flags)
{
const char *name;
int namelen;
/*
* match with FNM_PATHNAME; the pattern has base implicitly
* in front of it.
*/
if (*pattern == '/') {
pattern++;
patternlen--;
prefix--;
}
/*
* baselen does not count the trailing slash. base[] may or
* may not end with a trailing slash though.
*/
if (pathlen < baselen + 1 ||
(baselen && pathname[baselen] != '/') ||
fspathncmp(pathname, base, baselen))
return 0;
namelen = baselen ? pathlen - baselen - 1 : pathlen;
name = pathname + pathlen - namelen;
if (prefix) {
/*
* if the non-wildcard part is longer than the
* remaining pathname, surely it cannot match.
*/
if (prefix > namelen)
return 0;
if (fspathncmp(pattern, name, prefix))
return 0;
pattern += prefix;
patternlen -= prefix;
name += prefix;
namelen -= prefix;
/*
* If the whole pattern did not have a wildcard,
* then our prefix match is all we need; we
* do not need to call fnmatch at all.
*/
if (!patternlen && !namelen)
return 1;
}
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.
*/
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
static struct path_pattern *last_matching_pattern_from_list(const char *pathname,
int pathlen,
const char *basename,
int *dtype,
struct pattern_list *pl,
struct index_state *istate)
{
struct path_pattern *res = NULL; /* undecided */
int i;
if (!pl->nr)
return NULL; /* undefined */
for (i = pl->nr - 1; 0 <= i; i--) {
struct path_pattern *pattern = pl->patterns[i];
const char *exclude = pattern->pattern;
int prefix = pattern->nowildcardlen;
if (pattern->flags & PATTERN_FLAG_MUSTBEDIR) {
if (*dtype == DT_UNKNOWN)
*dtype = get_dtype(NULL, istate, pathname, pathlen);
if (*dtype != DT_DIR)
continue;
}
if (pattern->flags & PATTERN_FLAG_NODIR) {
if (match_basename(basename,
pathlen - (basename - pathname),
exclude, prefix, pattern->patternlen,
pattern->flags)) {
res = pattern;
break;
}
continue;
}
assert(pattern->baselen == 0 ||
pattern->base[pattern->baselen - 1] == '/');
if (match_pathname(pathname, pathlen,
pattern->base,
pattern->baselen ? pattern->baselen - 1 : 0,
exclude, prefix, pattern->patternlen,
pattern->flags)) {
res = pattern;
break;
}
}
return res;
}
/*
* Scan the list of patterns to determine if the ordered list
* of patterns matches on 'pathname'.
*
* Return 1 for a match, 0 for not matched and -1 for undecided.
*/
enum pattern_match_result path_matches_pattern_list(
const char *pathname, int pathlen,
const char *basename, int *dtype,
struct pattern_list *pl,
struct index_state *istate)
{
struct path_pattern *pattern;
struct strbuf parent_pathname = STRBUF_INIT;
int result = NOT_MATCHED;
const char *slash_pos;
if (!pl->use_cone_patterns) {
pattern = last_matching_pattern_from_list(pathname, pathlen, basename,
dtype, pl, istate);
if (pattern) {
if (pattern->flags & PATTERN_FLAG_NEGATIVE)
return NOT_MATCHED;
else
return MATCHED;
}
return UNDECIDED;
}
if (pl->full_cone)
return MATCHED;
strbuf_addch(&parent_pathname, '/');
strbuf_add(&parent_pathname, pathname, pathlen);
if (hashmap_contains_path(&pl->recursive_hashmap,
&parent_pathname)) {
result = MATCHED_RECURSIVE;
goto done;
}
slash_pos = strrchr(parent_pathname.buf, '/');
if (slash_pos == parent_pathname.buf) {
/* include every file in root */
result = MATCHED;
goto done;
}
strbuf_setlen(&parent_pathname, slash_pos - parent_pathname.buf);
if (hashmap_contains_path(&pl->parent_hashmap, &parent_pathname)) {
result = MATCHED;
goto done;
}
if (hashmap_contains_parent(&pl->recursive_hashmap,
pathname,
&parent_pathname))
result = MATCHED_RECURSIVE;
done:
strbuf_release(&parent_pathname);
return result;
}
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
static struct path_pattern *last_matching_pattern_from_lists(
struct dir_struct *dir, struct index_state *istate,
const char *pathname, int pathlen,
const char *basename, int *dtype_p)
{
int i, j;
struct exclude_list_group *group;
struct path_pattern *pattern;
for (i = EXC_CMDL; i <= EXC_FILE; i++) {
group = &dir->exclude_list_group[i];
for (j = group->nr - 1; j >= 0; j--) {
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
pattern = last_matching_pattern_from_list(
pathname, pathlen, basename, dtype_p,
&group->pl[j], istate);
if (pattern)
return pattern;
}
}
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,
struct index_state *istate,
const char *base, int baselen)
{
struct exclude_list_group *group;
struct pattern_list *pl;
struct exclude_stack *stk = NULL;
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
struct untracked_cache_dir *untracked;
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;
pl = &group->pl[dir->exclude_stack->exclude_ix];
dir->exclude_stack = stk->prev;
dir->pattern = NULL;
free((char *)pl->src); /* see strbuf_detach() below */
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
clear_pattern_list(pl);
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 19:12:14 +00:00
/* Skip traversing into sub directories if the parent is excluded */
if (dir->pattern)
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 19:12:14 +00:00
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);
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
if (dir->untracked)
untracked = stk ? stk->ucd : dir->untracked->root;
else
untracked = NULL;
while (current < baselen) {
const char *cp;
struct oid_stat oid_stat;
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++;
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
untracked =
lookup_untracked(dir->untracked, untracked,
base + current,
cp - base - current);
}
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 19:12:14 +00:00
stk->exclude_ix = group->nr;
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
stk->ucd = untracked;
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
pl = add_pattern_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 19:12:14 +00:00
/* Abort if the directory is excluded */
if (stk->baselen) {
int dt = DT_DIR;
dir->basebuf.buf[stk->baselen - 1] = 0;
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
dir->pattern = last_matching_pattern_from_lists(dir,
istate,
dir->basebuf.buf, stk->baselen - 1,
dir->basebuf.buf + current, &dt);
dir->basebuf.buf[stk->baselen - 1] = '/';
if (dir->pattern &&
dir->pattern->flags & PATTERN_FLAG_NEGATIVE)
dir->pattern = NULL;
if (dir->pattern) {
dir.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 19:12:14 +00:00
dir->exclude_stack = stk;
return;
}
}
/* Try to read per-directory file */
oidclr(&oid_stat.oid);
oid_stat.valid = 0;
if (dir->exclude_per_dir &&
/*
* If we know that no files have been added in
* this directory (i.e. valid_cached_dir() has
* been executed and set untracked->valid) ..
*/
(!untracked || !untracked->valid ||
/*
* .. and .gitignore does not exist before
* (i.e. null exclude_oid). Then we can skip
* loading .gitignore, which would result in
* ENOENT anyway.
*/
!is_null_oid(&untracked->exclude_oid))) {
dir.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 19:12:14 +00:00
/*
* dir->basebuf gets reused by the traversal, but we
* need fname to remain unchanged to ensure the src
* member of each struct path_pattern correctly
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 19:12:14 +00:00
* back-references its source file. Other invocations
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
* of add_pattern_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 19:12:14 +00:00
*/
struct strbuf sb = STRBUF_INIT;
strbuf_addbuf(&sb, &dir->basebuf);
strbuf_addstr(&sb, dir->exclude_per_dir);
pl->src = strbuf_detach(&sb, NULL);
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
add_patterns(pl->src, pl->src, stk->baselen, pl, istate,
untracked ? &oid_stat : NULL);
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
}
/*
* NEEDSWORK: when untracked cache is enabled, prep_exclude()
* will first be called in valid_cached_dir() then maybe many
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
* times more in last_matching_pattern(). When the cache is
* used, last_matching_pattern() will not be called and
* reading .gitignore content will be a waste.
*
* So when it's called by valid_cached_dir() and we can get
* .gitignore SHA-1 from the index (i.e. .gitignore is not
* modified on work tree), we could delay reading the
* .gitignore content until we absolutely need it in
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
* last_matching_pattern(). Be careful about ignore rule
* order, though, if you do that.
*/
if (untracked &&
!oideq(&oid_stat.oid, &untracked->exclude_oid)) {
invalidate_gitignore(dir->untracked, untracked);
oidcpy(&untracked->exclude_oid, &oid_stat.oid);
dir.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 19:12:14 +00:00
}
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.
*/
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
struct path_pattern *last_matching_pattern(struct dir_struct *dir,
struct index_state *istate,
const char *pathname,
int *dtype_p)
{
int pathlen = strlen(pathname);
const char *basename = strrchr(pathname, '/');
basename = (basename) ? basename+1 : pathname;
prep_exclude(dir, istate, pathname, basename-pathname);
if (dir->pattern)
return dir->pattern;
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 19:12:14 +00:00
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
return last_matching_pattern_from_lists(dir, istate, 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, struct index_state *istate,
const char *pathname, int *dtype_p)
{
struct path_pattern *pattern =
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
last_matching_pattern(dir, istate, pathname, dtype_p);
if (pattern)
return pattern->flags & PATTERN_FLAG_NEGATIVE ? 0 : 1;
return 0;
}
static struct dir_entry *dir_entry_new(const char *pathname, int len)
{
struct dir_entry *ent;
FLEX_ALLOC_MEM(ent, name, pathname, len);
ent->len = len;
return ent;
}
static struct dir_entry *dir_add_name(struct dir_struct *dir,
struct index_state *istate,
const char *pathname, int len)
{
if (index_file_exists(istate, pathname, len, ignore_case))
return NULL;
ALLOC_GROW(dir->entries, dir->nr+1, dir->alloc);
return dir->entries[dir->nr++] = dir_entry_new(pathname, len);
}
struct dir_entry *dir_add_ignored(struct dir_struct *dir,
struct index_state *istate,
const char *pathname, int len)
{
if (!index_name_is_other(istate, 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(struct index_state *istate,
const char *dirname, int len)
{
struct cache_entry *ce;
if (index_dir_exists(istate, dirname, len))
return index_directory;
ce = index_file_exists(istate, dirname, len, ignore_case);
if (ce && S_ISGITLINK(ce->ce_mode))
return index_gitdir;
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(struct index_state *istate,
const char *dirname, int len)
{
int pos;
if (ignore_case)
return directory_exists_in_index_icase(istate, dirname, len);
pos = index_name_pos(istate, dirname, len);
if (pos < 0)
pos = -pos-1;
while (pos < istate->cache_nr) {
const struct cache_entry *ce = istate->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 19:14:22 +00:00
* 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 19:14:22 +00:00
static enum path_treatment treat_directory(struct dir_struct *dir,
struct index_state *istate,
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
struct untracked_cache_dir *untracked,
const char *dirname, int len, int baselen, int exclude,
const struct pathspec *pathspec)
{
int nested_repo = 0;
/* The "len-1" is to strip the final '/' */
switch (directory_exists_in_index(istate, 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 19:14:22 +00:00
return path_recurse;
case index_gitdir:
return path_none;
case index_nonexistent:
if ((dir->flags & DIR_SKIP_NESTED_GIT) ||
!(dir->flags & DIR_NO_GITLINKS)) {
clean: avoid removing untracked files in a nested git repository Users expect files in a nested git repository to be left alone unless sufficiently forced (with two -f's). Unfortunately, in certain circumstances, git would delete both tracked (and possibly dirty) files and untracked files within a nested repository. To explain how this happens, let's contrast a couple cases. First, take the following example setup (which assumes we are already within a git repo): git init nested cd nested >tracked git add tracked git commit -m init >untracked cd .. In this setup, everything works as expected; running 'git clean -fd' will result in fill_directory() returning the following paths: nested/ nested/tracked nested/untracked and then correct_untracked_entries() would notice this can be compressed to nested/ and then since "nested/" is a directory, we would call remove_dirs("nested/", ...), which would check is_nonbare_repository_dir() and then decide to skip it. However, if someone also creates an ignored file: >nested/ignored then running 'git clean -fd' would result in fill_directory() returning the same paths: nested/ nested/tracked nested/untracked but correct_untracked_entries() will notice that we had ignored entries under nested/ and thus simplify this list to nested/tracked nested/untracked Since these are not directories, we do not call remove_dirs() which was the only place that had the is_nonbare_repository_dir() safety check -- resulting in us deleting both the untracked file and the tracked (and possibly dirty) file. One possible fix for this issue would be walking the parent directories of each path and checking if they represent nonbare repositories, but that would be wasteful. Even if we added caching of some sort, it's still a waste because we should have been able to check that "nested/" represented a nonbare repository before even descending into it in the first place. Add a DIR_SKIP_NESTED_GIT flag to dir_struct.flags and use it to prevent fill_directory() and friends from descending into nested git repos. With this change, we also modify two regression tests added in commit 91479b9c72f1 ("t7300: add tests to document behavior of clean and nested git", 2015-06-15). That commit, nor its series, nor the six previous iterations of that series on the mailing list discussed why those tests coded the expectation they did. In fact, it appears their purpose was simply to test _existing_ behavior to make sure that the performance changes didn't change the behavior. However, these two tests directly contradicted the manpage's claims that two -f's were required to delete files/directories under a nested git repository. While one could argue that the user gave an explicit path which matched files/directories that were within a nested repository, there's a slippery slope that becomes very difficult for users to understand once you go down that route (e.g. what if they specified "git clean -f -d '*.c'"?) It would also be hard to explain what the exact behavior was; avoid such problems by making it really simple. Also, clean up some grammar errors describing this functionality in the git-clean manpage. Finally, there are still a couple bugs with -ffd not cleaning out enough (e.g. missing the nested .git) and with -ffdX possibly cleaning out the wrong files (paying attention to outer .gitignore instead of inner). This patch does not address these cases at all (and does not change the behavior relative to those flags), it only fixes the handling when given a single -f. See https://public-inbox.org/git/20190905212043.GC32087@szeder.dev/ for more discussion of the -ffd[X?] bugs. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-17 16:35:02 +00:00
struct strbuf sb = STRBUF_INIT;
strbuf_addstr(&sb, dirname);
nested_repo = is_nonbare_repository_dir(&sb);
strbuf_release(&sb);
}
if (nested_repo)
return ((dir->flags & DIR_SKIP_NESTED_GIT) ? path_none :
(exclude ? path_excluded : path_untracked));
clean: avoid removing untracked files in a nested git repository Users expect files in a nested git repository to be left alone unless sufficiently forced (with two -f's). Unfortunately, in certain circumstances, git would delete both tracked (and possibly dirty) files and untracked files within a nested repository. To explain how this happens, let's contrast a couple cases. First, take the following example setup (which assumes we are already within a git repo): git init nested cd nested >tracked git add tracked git commit -m init >untracked cd .. In this setup, everything works as expected; running 'git clean -fd' will result in fill_directory() returning the following paths: nested/ nested/tracked nested/untracked and then correct_untracked_entries() would notice this can be compressed to nested/ and then since "nested/" is a directory, we would call remove_dirs("nested/", ...), which would check is_nonbare_repository_dir() and then decide to skip it. However, if someone also creates an ignored file: >nested/ignored then running 'git clean -fd' would result in fill_directory() returning the same paths: nested/ nested/tracked nested/untracked but correct_untracked_entries() will notice that we had ignored entries under nested/ and thus simplify this list to nested/tracked nested/untracked Since these are not directories, we do not call remove_dirs() which was the only place that had the is_nonbare_repository_dir() safety check -- resulting in us deleting both the untracked file and the tracked (and possibly dirty) file. One possible fix for this issue would be walking the parent directories of each path and checking if they represent nonbare repositories, but that would be wasteful. Even if we added caching of some sort, it's still a waste because we should have been able to check that "nested/" represented a nonbare repository before even descending into it in the first place. Add a DIR_SKIP_NESTED_GIT flag to dir_struct.flags and use it to prevent fill_directory() and friends from descending into nested git repos. With this change, we also modify two regression tests added in commit 91479b9c72f1 ("t7300: add tests to document behavior of clean and nested git", 2015-06-15). That commit, nor its series, nor the six previous iterations of that series on the mailing list discussed why those tests coded the expectation they did. In fact, it appears their purpose was simply to test _existing_ behavior to make sure that the performance changes didn't change the behavior. However, these two tests directly contradicted the manpage's claims that two -f's were required to delete files/directories under a nested git repository. While one could argue that the user gave an explicit path which matched files/directories that were within a nested repository, there's a slippery slope that becomes very difficult for users to understand once you go down that route (e.g. what if they specified "git clean -f -d '*.c'"?) It would also be hard to explain what the exact behavior was; avoid such problems by making it really simple. Also, clean up some grammar errors describing this functionality in the git-clean manpage. Finally, there are still a couple bugs with -ffd not cleaning out enough (e.g. missing the nested .git) and with -ffdX possibly cleaning out the wrong files (paying attention to outer .gitignore instead of inner). This patch does not address these cases at all (and does not change the behavior relative to those flags), it only fixes the handling when given a single -f. See https://public-inbox.org/git/20190905212043.GC32087@szeder.dev/ for more discussion of the -ffd[X?] bugs. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-17 16:35:02 +00:00
if (dir->flags & DIR_SHOW_OTHER_DIRECTORIES)
break;
status: add option to show ignored files differently Teach the status command more flexibility in how ignored files are reported. Currently, the reporting of ignored files and untracked files are linked. You cannot control how ignored files are reported independently of how untracked files are reported (i.e. `all` vs `normal`). This makes it impossible to show untracked files with the `all` option, but show ignored files with the `normal` option. This work 1) adds the ability to control the reporting of ignored files independently of untracked files and 2) introduces the concept of status reporting ignored paths that explicitly match an ignored pattern. There are 2 benefits to these changes: 1) if a consumer needs all untracked files but not all ignored files, there is a performance benefit to not scanning all contents of an ignored directory and 2) returning ignored files that explicitly match a path allow a consumer to make more informed decisions about when a status result might be stale. This commit implements --ignored=matching with --untracked-files=all. The following commit will implement --ignored=matching with --untracked=files=normal. As an example of where this flexibility could be useful is that our application (Visual Studio) runs the status command and presents the output. It shows all untracked files individually (e.g. using the '--untracked-files==all' option), and would like to know about which paths are ignored. It uses information about ignored paths to make decisions about when the status result might have changed. Additionally, many projects place build output into directories inside a repository's working directory (e.g. in "bin/" and "obj/" directories). Normal usage is to explicitly ignore these 2 directory names in the .gitignore file (rather than or in addition to the *.obj pattern).If an application could know that these directories are explicitly ignored, it could infer that all contents are ignored as well and make better informed decisions about files in these directories. It could infer that any changes under these paths would not affect the output of status. Additionally, there can be a significant performance benefit by avoiding scanning through ignored directories. When status is set to report matching ignored files, it has the following behavior. Ignored files and directories that explicitly match an exclude pattern are reported. If an ignored directory matches an exclude pattern, then the path of the directory is returned. If a directory does not match an exclude pattern, but all of its contents are ignored, then the contained files are reported instead of the directory. Signed-off-by: Jameson Miller <jamill@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-30 17:21:37 +00:00
if (exclude &&
(dir->flags & DIR_SHOW_IGNORED_TOO) &&
(dir->flags & DIR_SHOW_IGNORED_TOO_MODE_MATCHING)) {
/*
* This is an excluded directory and we are
* showing ignored paths that match an exclude
* pattern. (e.g. show directory as ignored
* only if it matches an exclude pattern).
* This path will either be 'path_excluded`
* (if we are showing empty directories or if
* the directory is not empty), or will be
* 'path_none' (empty directory, and we are
* not showing empty directories).
*/
if (!(dir->flags & DIR_HIDE_EMPTY_DIRECTORIES))
return path_excluded;
if (read_directory_recursive(dir, istate, dirname, len,
untracked, 1, 1, pathspec) == path_excluded)
return path_excluded;
return path_none;
}
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 19:14:22 +00:00
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 19:14:22 +00:00
return exclude ? path_excluded : path_untracked;
untracked = lookup_untracked(dir->untracked, untracked,
dirname + baselen, len - baselen);
/*
* If this is an excluded directory, then we only need to check if
* the directory contains any files.
*/
return read_directory_recursive(dir, istate, dirname, len,
untracked, 1, exclude, pathspec);
}
/*
* 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 pathspec *pathspec)
{
int i;
if (!pathspec || !pathspec->nr)
return 0;
GUARD_PATHSPEC(pathspec,
PATHSPEC_FROMTOP |
PATHSPEC_MAXDEPTH |
PATHSPEC_LITERAL |
PATHSPEC_GLOB |
PATHSPEC_ICASE |
PATHSPEC_EXCLUDE |
PATHSPEC_ATTR);
for (i = 0; i < pathspec->nr; i++) {
const struct pathspec_item *item = &pathspec->items[i];
int len = item->nowildcard_len;
if (len > pathlen)
len = pathlen;
if (!ps_strncmp(item, item->match, path, len))
return 0;
}
return 1;
}
/*
* 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 pathlen,
const struct pathspec *pathspec)
{
int i;
if (!pathspec || !pathspec->nr)
return 0;
GUARD_PATHSPEC(pathspec,
PATHSPEC_FROMTOP |
PATHSPEC_MAXDEPTH |
PATHSPEC_LITERAL |
PATHSPEC_GLOB |
PATHSPEC_ICASE |
PATHSPEC_EXCLUDE);
for (i = 0; i < pathspec->nr; i++) {
const struct pathspec_item *item = &pathspec->items[i];
int len = item->nowildcard_len;
if (len == pathlen &&
!ps_strncmp(item, item->match, path, pathlen))
return 1;
if (len > pathlen &&
item->match[pathlen] == '/' &&
!ps_strncmp(item, item->match, path, pathlen))
return 1;
}
return 0;
}
static int get_index_dtype(struct index_state *istate,
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 15:29:00 +00:00
const struct cache_entry *ce;
ce = index_file_exists(istate, 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 = index_name_pos(istate, path, len);
if (pos >= 0)
return DT_UNKNOWN;
pos = -pos-1;
while (pos < istate->cache_nr) {
ce = istate->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, struct index_state *istate,
const char *path, int len)
{
int dtype = de ? DTYPE(de) : DT_UNKNOWN;
struct stat st;
if (dtype != DT_UNKNOWN)
return dtype;
dtype = get_index_dtype(istate, 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,
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
struct untracked_cache_dir *untracked,
struct index_state *istate,
struct strbuf *path,
int baselen,
const struct pathspec *pathspec,
int dtype, struct dirent *de)
{
int exclude;
int has_path_in_index = !!index_file_exists(istate, path->buf, path->len, ignore_case);
enum path_treatment path_treatment;
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 19:13:46 +00:00
if (dtype == DT_UNKNOWN)
dtype = get_dtype(de, istate, 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 19:13:46 +00:00
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 19:14:22 +00:00
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 19:13:46 +00:00
/*
* 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(istate, path->buf, path->len) == index_nonexistent))
return path_none;
exclude = is_excluded(dir, istate, 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 19:15:03 +00:00
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 19:14:22 +00:00
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 19:14:22 +00:00
return path_none;
case DT_DIR:
strbuf_addch(path, '/');
path_treatment = treat_directory(dir, istate, untracked,
path->buf, path->len,
baselen, exclude, pathspec);
/*
* If 1) we only want to return directories that
* match an exclude pattern and 2) this directory does
* not match an exclude pattern but all of its
* contents are excluded, then indicate that we should
* recurse into this directory (instead of marking the
* directory itself as an ignored path).
*/
if (!exclude &&
path_treatment == path_excluded &&
(dir->flags & DIR_SHOW_IGNORED_TOO) &&
(dir->flags & DIR_SHOW_IGNORED_TOO_MODE_MATCHING))
return path_recurse;
return path_treatment;
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 19:14:22 +00:00
return exclude ? path_excluded : path_untracked;
}
}
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
static enum path_treatment treat_path_fast(struct dir_struct *dir,
struct untracked_cache_dir *untracked,
struct cached_dir *cdir,
struct index_state *istate,
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
struct strbuf *path,
int baselen,
const struct pathspec *pathspec)
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
{
strbuf_setlen(path, baselen);
if (!cdir->ucd) {
strbuf_addstr(path, cdir->file);
return path_untracked;
}
strbuf_addstr(path, cdir->ucd->name);
/* treat_one_path() does this before it calls treat_directory() */
2015-09-24 21:08:35 +00:00
strbuf_complete(path, '/');
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
if (cdir->ucd->check_only)
/*
* check_only is set as a result of treat_directory() getting
* to its bottom. Verify again the same set of directories
* with check_only set.
*/
return read_directory_recursive(dir, istate, path->buf, path->len,
cdir->ucd, 1, 0, pathspec);
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
/*
* We get path_recurse in the first run when
* directory_exists_in_index() returns index_nonexistent. We
* are sure that new changes in the index does not impact the
* outcome. Return now.
*/
return path_recurse;
}
static enum path_treatment treat_path(struct dir_struct *dir,
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
struct untracked_cache_dir *untracked,
struct cached_dir *cdir,
struct index_state *istate,
struct strbuf *path,
int baselen,
const struct pathspec *pathspec)
{
int dtype;
struct dirent *de = cdir->de;
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
if (!de)
return treat_path_fast(dir, untracked, cdir, istate, path,
baselen, pathspec);
if (is_dot_or_dotdot(de->d_name) || !fspathcmp(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 19:14:22 +00:00
return path_none;
strbuf_setlen(path, baselen);
strbuf_addstr(path, de->d_name);
if (simplify_away(path->buf, path->len, pathspec))
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 19:14:22 +00:00
return path_none;
dtype = DTYPE(de);
return treat_one_path(dir, untracked, istate, path, baselen, pathspec, dtype, de);
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
}
static void add_untracked(struct untracked_cache_dir *dir, const char *name)
{
if (!dir)
return;
ALLOC_GROW(dir->untracked, dir->untracked_nr + 1,
dir->untracked_alloc);
dir->untracked[dir->untracked_nr++] = xstrdup(name);
}
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
static int valid_cached_dir(struct dir_struct *dir,
struct untracked_cache_dir *untracked,
struct index_state *istate,
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
struct strbuf *path,
int check_only)
{
struct stat st;
if (!untracked)
return 0;
/*
* With fsmonitor, we can trust the untracked cache's valid field.
*/
refresh_fsmonitor(istate);
if (!(dir->untracked->use_fsmonitor && untracked->valid)) {
if (lstat(path->len ? path->buf : ".", &st)) {
memset(&untracked->stat_data, 0, sizeof(untracked->stat_data));
return 0;
}
if (!untracked->valid ||
match_stat_data_racy(istate, &untracked->stat_data, &st)) {
fill_stat_data(&untracked->stat_data, &st);
return 0;
}
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
}
dir.c: fix missing dir invalidation in untracked code Let's start with how create a new directory cache after the last one becomes invalid (e.g. because its dir mtime has changed...). In open_cached_dir(): 1. We start out with valid_cached_dir() returning false, which should call invalidate_directory() to put a directory state back to initial state, no untracked entries (untracked_nr zero), no sub directory traversal (dirs[].recurse zero). 2. Since the cache cannot be used, we go the slow path opendir() and go through items one by one via readdir(). All the directories on disk will be added back to the cache (if not already exist in dirs[]) and its flag "recurse" gets changed to one to note that it's part of the cached dir travesal next time. 3. By the time we reach close_cached_dir() we should have a good subdir list in dirs[]. Those with "recurse" flag set are the ones present in the on-disk directory. The directory is now marked "valid". Next time read_directory() is called, since the directory is marked valid, it will skip readdir(), go fast path and traverse through dirs[] array instead. Steps one and two need some tight cooperation. If a subdir is removed, readdir() will not find it and of course we cannot examine/invalidate it. To make sure removed directories on disk are gone from the cache, step one must make sure recurse flag of all subdirs are zero. But that's not true. If "valid" flag is already false, there is a chance we go straight to the end of valid_cached_dir() without calling invalidate_directory(). Or we fail to meet the "if (untracked-valid)" condition and skip over the invalidate_directory(). After step 3, we mark the cache valid. Any stale subdir with incorrect recurse flag becomes a real subdir next time we traverse the directory using dirs[] array. We could avoid this by making sure invalidate_directory() is always called (therefore dirs[].recurse cleared) at the beginning of open_cached_dir(). Which is what this patch does. As to how we get into this situation, the key in the test is this command git checkout master where "one/file" is replaced with "one" in the index. This index update triggers untracked_cache_invalidate_path(), which clears valid flag of the root directory while keeping "recurse" flag on the subdir "one" on. On the next git-status, we go through steps 1-3 above and save an incorrect cache on disk. The second git-status blindly follows the bad cache data and shows the problem. This is arguably because of a bad design where "recurse" flag plays double roles: whether a directory should be saved on disk, and whether it is part of a directory traversal. We need to keep recurse flag set at "checkout master" because of the first role: we need to keep subdir caches (dir "two" for example has not been touched at all, no reason to throw its cache away). As long as we make sure to ignore/reset "recurse" flag at the beginning of a directory traversal, we're good. But maybe eventually we should separate these two roles. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-01-24 09:30:21 +00:00
if (untracked->check_only != !!check_only)
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
return 0;
/*
* prep_exclude will be called eventually on this directory,
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
* but it's called much later in last_matching_pattern(). We
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
* need it now to determine the validity of the cache for this
* path. The next calls will be nearly no-op, the way
* prep_exclude() is designed.
*/
if (path->len && path->buf[path->len - 1] != '/') {
strbuf_addch(path, '/');
prep_exclude(dir, istate, path->buf, path->len);
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
strbuf_setlen(path, path->len - 1);
} else
prep_exclude(dir, istate, path->buf, path->len);
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
/* hopefully prep_exclude() haven't invalidated this entry... */
return untracked->valid;
}
static int open_cached_dir(struct cached_dir *cdir,
struct dir_struct *dir,
struct untracked_cache_dir *untracked,
struct index_state *istate,
struct strbuf *path,
int check_only)
{
const char *c_path;
memset(cdir, 0, sizeof(*cdir));
cdir->untracked = untracked;
if (valid_cached_dir(dir, untracked, istate, path, check_only))
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
return 0;
c_path = path->len ? path->buf : ".";
cdir->fdir = opendir(c_path);
if (!cdir->fdir)
warning_errno(_("could not open directory '%s'"), c_path);
dir.c: fix missing dir invalidation in untracked code Let's start with how create a new directory cache after the last one becomes invalid (e.g. because its dir mtime has changed...). In open_cached_dir(): 1. We start out with valid_cached_dir() returning false, which should call invalidate_directory() to put a directory state back to initial state, no untracked entries (untracked_nr zero), no sub directory traversal (dirs[].recurse zero). 2. Since the cache cannot be used, we go the slow path opendir() and go through items one by one via readdir(). All the directories on disk will be added back to the cache (if not already exist in dirs[]) and its flag "recurse" gets changed to one to note that it's part of the cached dir travesal next time. 3. By the time we reach close_cached_dir() we should have a good subdir list in dirs[]. Those with "recurse" flag set are the ones present in the on-disk directory. The directory is now marked "valid". Next time read_directory() is called, since the directory is marked valid, it will skip readdir(), go fast path and traverse through dirs[] array instead. Steps one and two need some tight cooperation. If a subdir is removed, readdir() will not find it and of course we cannot examine/invalidate it. To make sure removed directories on disk are gone from the cache, step one must make sure recurse flag of all subdirs are zero. But that's not true. If "valid" flag is already false, there is a chance we go straight to the end of valid_cached_dir() without calling invalidate_directory(). Or we fail to meet the "if (untracked-valid)" condition and skip over the invalidate_directory(). After step 3, we mark the cache valid. Any stale subdir with incorrect recurse flag becomes a real subdir next time we traverse the directory using dirs[] array. We could avoid this by making sure invalidate_directory() is always called (therefore dirs[].recurse cleared) at the beginning of open_cached_dir(). Which is what this patch does. As to how we get into this situation, the key in the test is this command git checkout master where "one/file" is replaced with "one" in the index. This index update triggers untracked_cache_invalidate_path(), which clears valid flag of the root directory while keeping "recurse" flag on the subdir "one" on. On the next git-status, we go through steps 1-3 above and save an incorrect cache on disk. The second git-status blindly follows the bad cache data and shows the problem. This is arguably because of a bad design where "recurse" flag plays double roles: whether a directory should be saved on disk, and whether it is part of a directory traversal. We need to keep recurse flag set at "checkout master" because of the first role: we need to keep subdir caches (dir "two" for example has not been touched at all, no reason to throw its cache away). As long as we make sure to ignore/reset "recurse" flag at the beginning of a directory traversal, we're good. But maybe eventually we should separate these two roles. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-01-24 09:30:21 +00:00
if (dir->untracked) {
invalidate_directory(dir->untracked, untracked);
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
dir->untracked->dir_opened++;
dir.c: fix missing dir invalidation in untracked code Let's start with how create a new directory cache after the last one becomes invalid (e.g. because its dir mtime has changed...). In open_cached_dir(): 1. We start out with valid_cached_dir() returning false, which should call invalidate_directory() to put a directory state back to initial state, no untracked entries (untracked_nr zero), no sub directory traversal (dirs[].recurse zero). 2. Since the cache cannot be used, we go the slow path opendir() and go through items one by one via readdir(). All the directories on disk will be added back to the cache (if not already exist in dirs[]) and its flag "recurse" gets changed to one to note that it's part of the cached dir travesal next time. 3. By the time we reach close_cached_dir() we should have a good subdir list in dirs[]. Those with "recurse" flag set are the ones present in the on-disk directory. The directory is now marked "valid". Next time read_directory() is called, since the directory is marked valid, it will skip readdir(), go fast path and traverse through dirs[] array instead. Steps one and two need some tight cooperation. If a subdir is removed, readdir() will not find it and of course we cannot examine/invalidate it. To make sure removed directories on disk are gone from the cache, step one must make sure recurse flag of all subdirs are zero. But that's not true. If "valid" flag is already false, there is a chance we go straight to the end of valid_cached_dir() without calling invalidate_directory(). Or we fail to meet the "if (untracked-valid)" condition and skip over the invalidate_directory(). After step 3, we mark the cache valid. Any stale subdir with incorrect recurse flag becomes a real subdir next time we traverse the directory using dirs[] array. We could avoid this by making sure invalidate_directory() is always called (therefore dirs[].recurse cleared) at the beginning of open_cached_dir(). Which is what this patch does. As to how we get into this situation, the key in the test is this command git checkout master where "one/file" is replaced with "one" in the index. This index update triggers untracked_cache_invalidate_path(), which clears valid flag of the root directory while keeping "recurse" flag on the subdir "one" on. On the next git-status, we go through steps 1-3 above and save an incorrect cache on disk. The second git-status blindly follows the bad cache data and shows the problem. This is arguably because of a bad design where "recurse" flag plays double roles: whether a directory should be saved on disk, and whether it is part of a directory traversal. We need to keep recurse flag set at "checkout master" because of the first role: we need to keep subdir caches (dir "two" for example has not been touched at all, no reason to throw its cache away). As long as we make sure to ignore/reset "recurse" flag at the beginning of a directory traversal, we're good. But maybe eventually we should separate these two roles. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-01-24 09:30:21 +00:00
}
if (!cdir->fdir)
return -1;
return 0;
}
static int read_cached_dir(struct cached_dir *cdir)
{
if (cdir->fdir) {
cdir->de = readdir(cdir->fdir);
if (!cdir->de)
return -1;
return 0;
}
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
while (cdir->nr_dirs < cdir->untracked->dirs_nr) {
struct untracked_cache_dir *d = cdir->untracked->dirs[cdir->nr_dirs];
if (!d->recurse) {
cdir->nr_dirs++;
continue;
}
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
cdir->ucd = d;
cdir->nr_dirs++;
return 0;
}
cdir->ucd = NULL;
if (cdir->nr_files < cdir->untracked->untracked_nr) {
struct untracked_cache_dir *d = cdir->untracked;
cdir->file = d->untracked[cdir->nr_files++];
return 0;
}
return -1;
}
static void close_cached_dir(struct cached_dir *cdir)
{
if (cdir->fdir)
closedir(cdir->fdir);
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
/*
* We have gone through this directory and found no untracked
* entries. Mark it valid.
*/
if (cdir->untracked) {
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
cdir->untracked->valid = 1;
cdir->untracked->recurse = 1;
}
}
static void add_path_to_appropriate_result_list(struct dir_struct *dir,
struct untracked_cache_dir *untracked,
struct cached_dir *cdir,
struct index_state *istate,
struct strbuf *path,
int baselen,
const struct pathspec *pathspec,
enum path_treatment state)
{
/* add the path to the appropriate result list */
switch (state) {
case path_excluded:
if (dir->flags & DIR_SHOW_IGNORED)
dir_add_name(dir, istate, path->buf, path->len);
else if ((dir->flags & DIR_SHOW_IGNORED_TOO) ||
((dir->flags & DIR_COLLECT_IGNORED) &&
exclude_matches_pathspec(path->buf, path->len,
pathspec)))
dir_add_ignored(dir, istate, path->buf, path->len);
break;
case path_untracked:
if (dir->flags & DIR_SHOW_IGNORED)
break;
dir_add_name(dir, istate, path->buf, path->len);
if (cdir->fdir)
add_untracked(untracked, path->buf + baselen);
break;
default:
break;
}
}
/*
* 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 19:14:22 +00:00
*
* If 'stop_at_first_file' is specified, 'path_excluded' is returned
* to signal that a file was found. This is the least significant value that
* indicates that a file was encountered that does not depend on the order of
* whether an untracked or exluded path was encountered first.
*
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 19:14:22 +00:00
* Returns the most significant path_treatment value encountered in the scan.
* If 'stop_at_first_file' is specified, `path_excluded` is the most
* significant path_treatment value that will be returned.
*/
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 19:14:22 +00:00
static enum path_treatment read_directory_recursive(struct dir_struct *dir,
struct index_state *istate, const char *base, int baselen,
struct untracked_cache_dir *untracked, int check_only,
int stop_at_first_file, const struct pathspec *pathspec)
{
2019-12-19 21:28:25 +00:00
/*
* WARNING WARNING WARNING:
*
* Any updates to the traversal logic here may need corresponding
* updates in treat_leading_path(). See the commit message for the
* commit adding this warning as well as the commit preceding it
* for details.
*/
struct cached_dir cdir;
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 19:14:22 +00:00
enum path_treatment state, subdir_state, dir_state = path_none;
struct strbuf path = STRBUF_INIT;
strbuf_add(&path, base, baselen);
if (open_cached_dir(&cdir, dir, untracked, istate, &path, check_only))
goto out;
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
if (untracked)
untracked->check_only = !!check_only;
while (!read_cached_dir(&cdir)) {
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 19:14:22 +00:00
/* check how the file or directory should be treated */
state = treat_path(dir, untracked, &cdir, istate, &path,
baselen, pathspec);
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
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 19:14:22 +00:00
if (state > dir_state)
dir_state = state;
/* recurse into subdir if instructed by treat_path */
if ((state == path_recurse) ||
((state == path_untracked) &&
dir: if our pathspec might match files under a dir, recurse into it For git clean, if a directory is entirely untracked and the user did not specify -d (corresponding to DIR_SHOW_IGNORED_TOO), then we usually do not want to remove that directory and thus do not recurse into it. However, if the user manually specified specific (or even globbed) paths somewhere under that directory to remove, then we need to recurse into the directory to make sure we remove the relevant paths under that directory as the user requested. Note that this does not mean that the recursed-into directory will be added to dir->entries for later removal; as of a few commits earlier in this series, there is another more strict match check that is run after returning from a recursed-into directory before deciding to add it to the list of entries. Therefore, this will only result in files underneath the given directory which match one of the pathspecs being added to the entries list. Two notes of potential interest to future readers: * If we wanted to only recurse into a directory when it is specifically matched rather than matched-via-glob (e.g. '*.c'), then we could do so via making the final non-zero return in match_pathspec_item be MATCHED_RECURSIVELY instead of MATCHED_RECURSIVELY_LEADING_PATHSPEC. (Note that the relative order of MATCHED_RECURSIVELY_LEADING_PATHSPEC and MATCHED_RECURSIVELY are important for such a change.) I was leaving open that possibility while writing an RFC asking for the behavior we want, but even though we don't want it, that knowledge might help you understand the code flow better. * There is a growing amount of logic in read_directory_recursive() for deciding whether to recurse into a subdirectory. However, there is a comment immediately preceding this logic that says to recurse if instructed by treat_path(). It may be better for the logic in read_directory_recursive() to ultimately be moved to treat_path() (or another function it calls, such as treat_directory()), but I have left that for someone else to tackle in the future. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-17 16:34:58 +00:00
(get_dtype(cdir.de, istate, path.buf, path.len) == DT_DIR) &&
((dir->flags & DIR_SHOW_IGNORED_TOO) ||
dir: special case check for the possibility that pathspec is NULL Commits 404ebceda01c ("dir: also check directories for matching pathspecs", 2019-09-17) and 89a1f4aaf765 ("dir: if our pathspec might match files under a dir, recurse into it", 2019-09-17) added calls to match_pathspec() and do_match_pathspec() passing along their pathspec parameter. Both match_pathspec() and do_match_pathspec() assume the pathspec argument they are given is non-NULL. It turns out that unpack-tree.c's verify_clean_subdirectory() calls read_directory() with pathspec == NULL, and it is possible on case insensitive filesystems for that NULL to make it to these new calls to match_pathspec() and do_match_pathspec(). Add appropriate checks on the NULLness of pathspec to avoid a segfault. In case the negation throws anyone off (one of the calls was to do_match_pathspec() while the other was to !match_pathspec(), yet no negation of the NULLness of pathspec is used), there are two ways to understand the differences: * The code already handled the pathspec == NULL cases before this series, and this series only tried to change behavior when there was a pathspec, thus we only want to go into the if-block if pathspec is non-NULL. * One of the calls is for whether to recurse into a subdirectory, the other is for after we've recursed into it for whether we want to remove the subdirectory itself (i.e. the subdirectory didn't match but something under it could have). That difference in situation leads to the slight differences in logic used (well, that and the slightly unusual fact that we don't want empty pathspecs to remove untracked directories by default). Denton found and analyzed one issue and provided the patch for the match_pathspec() call, SZEDER figured out why the issue only reproduced for some folks and not others and provided the testcase, and I looked through the remainder of the series and noted the do_match_pathspec() call that should have the same check. Co-authored-by: Denton Liu <liu.denton@gmail.com> Co-authored-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-10-01 18:55:24 +00:00
(pathspec &&
do_match_pathspec(istate, pathspec, path.buf, path.len,
baselen, NULL, DO_MATCH_LEADING_PATHSPEC) == MATCHED_RECURSIVELY_LEADING_PATHSPEC)))) {
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
struct untracked_cache_dir *ud;
ud = lookup_untracked(dir->untracked, untracked,
path.buf + baselen,
path.len - baselen);
subdir_state =
read_directory_recursive(dir, istate, path.buf,
path.len, ud,
check_only, stop_at_first_file, pathspec);
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 19:14:22 +00:00
if (subdir_state > dir_state)
dir_state = subdir_state;
dir: special case check for the possibility that pathspec is NULL Commits 404ebceda01c ("dir: also check directories for matching pathspecs", 2019-09-17) and 89a1f4aaf765 ("dir: if our pathspec might match files under a dir, recurse into it", 2019-09-17) added calls to match_pathspec() and do_match_pathspec() passing along their pathspec parameter. Both match_pathspec() and do_match_pathspec() assume the pathspec argument they are given is non-NULL. It turns out that unpack-tree.c's verify_clean_subdirectory() calls read_directory() with pathspec == NULL, and it is possible on case insensitive filesystems for that NULL to make it to these new calls to match_pathspec() and do_match_pathspec(). Add appropriate checks on the NULLness of pathspec to avoid a segfault. In case the negation throws anyone off (one of the calls was to do_match_pathspec() while the other was to !match_pathspec(), yet no negation of the NULLness of pathspec is used), there are two ways to understand the differences: * The code already handled the pathspec == NULL cases before this series, and this series only tried to change behavior when there was a pathspec, thus we only want to go into the if-block if pathspec is non-NULL. * One of the calls is for whether to recurse into a subdirectory, the other is for after we've recursed into it for whether we want to remove the subdirectory itself (i.e. the subdirectory didn't match but something under it could have). That difference in situation leads to the slight differences in logic used (well, that and the slightly unusual fact that we don't want empty pathspecs to remove untracked directories by default). Denton found and analyzed one issue and provided the patch for the match_pathspec() call, SZEDER figured out why the issue only reproduced for some folks and not others and provided the testcase, and I looked through the remainder of the series and noted the do_match_pathspec() call that should have the same check. Co-authored-by: Denton Liu <liu.denton@gmail.com> Co-authored-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-10-01 18:55:24 +00:00
if (pathspec &&
!match_pathspec(istate, pathspec, path.buf, path.len,
0 /* prefix */, NULL,
0 /* do NOT special case dirs */))
state = path_none;
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 19:14:22 +00:00
}
if (check_only) {
if (stop_at_first_file) {
/*
* If stopping at first file, then
* signal that a file was found by
* returning `path_excluded`. This is
* to return a consistent value
* regardless of whether an ignored or
* excluded file happened to be
* encountered 1st.
*
* In current usage, the
* `stop_at_first_file` is passed when
* an ancestor directory has matched
* an exclude pattern, so any found
* files will be excluded.
*/
if (dir_state >= path_excluded) {
dir_state = path_excluded;
break;
}
}
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 19:14:22 +00:00
/* abort early if maximum state has been reached */
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
if (dir_state == path_untracked) {
untracked cache: record/validate dir mtime and reuse cached output The main readdir loop in read_directory_recursive() is replaced with a new one that checks if cached results of a directory is still valid. If a file is added or removed from the index, the containing directory is invalidated (but not its subdirs). If directory's mtime is changed, the same happens. If a .gitignore is updated, the containing directory and all subdirs are invalidated recursively. If dir_struct#flags or other conditions change, the cache is ignored. If a directory is invalidated, we opendir/readdir/closedir and run the exclude machinery on that directory listing as usual. If untracked cache is also enabled, we'll update the cache along the way. If a directory is validated, we simply pull the untracked listing out from the cache. The cache also records the list of direct subdirs that we have to recurse in. Fully excluded directories are seen as "untracked files". In the best case when no dirs are invalidated, read_directory() becomes a series of stat(dir), open(.gitignore), fstat(), read(), close() and optionally hash_sha1_file() For comparison, standard read_directory() is a sequence of opendir(), readdir(), open(.gitignore), fstat(), read(), close(), the expensive last_exclude_matching() and closedir(). We already try not to open(.gitignore) if we know it does not exist, so open/fstat/read/close sequence does not apply to every directory. The sequence could be reduced further, as noted in prep_exclude() in another patch. So in theory, the entire best-case read_directory sequence could be reduced to a series of stat() and nothing else. This is not a silver bullet approach. When you compile a C file, for example, the old .o file is removed and a new one with the same name created, effectively invalidating the containing directory's cache (but not its subdirectories). If your build process touches every directory, this cache adds extra overhead for nothing, so it's a good idea to separate generated files from tracked files.. Editors may use the same strategy for saving files. And of course you're out of luck running your repo on an unsupported filesystem and/or operating system. Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:29 +00:00
if (cdir.fdir)
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
add_untracked(untracked, path.buf + baselen);
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 19:14:22 +00:00
break;
untracked cache: record .gitignore information and dir hierarchy The idea is if we can capture all input and (non-rescursive) output of read_directory_recursive(), and can verify later that all the input is the same, then the second r_d_r() should produce the same output as in the first run. The requirement for this to work is stat info of a directory MUST change if an entry is added to or removed from that directory (and should not change often otherwise). If your OS and filesystem do not meet this requirement, untracked cache is not for you. Most file systems on *nix should be fine. On Windows, NTFS is fine while FAT may not be [1] even though FAT on Linux seems to be fine. The list of input of r_d_r() is in the big comment block in dir.h. In short, the output of a directory (not counting subdirs) mainly depends on stat info of the directory in question, all .gitignore leading to it and the check_only flag when r_d_r() is called recursively. This patch records all this info (and the output) as r_d_r() runs. Two hash_sha1_file() are required for $GIT_DIR/info/exclude and core.excludesfile unless their stat data matches. hash_sha1_file() is only needed when .gitignore files in the worktree are modified, otherwise their SHA-1 in index is used (see the previous patch). We could store stat data for .gitignore files so we don't have to rehash them if their content is different from index, but I think .gitignore files are rarely modified, so not worth extra cache data (and hashing penalty read-cache.c:verify_hdr(), as we will be storing this as an index extension). The implication is, if you change .gitignore, you better add it to the index soon or you lose all the benefit of untracked cache because a modified .gitignore invalidates all subdirs recursively. This is especially bad for .gitignore at root. This cached output is about untracked files only, not ignored files because the number of tracked files is usually small, so small cache overhead, while the number of ignored files could go really high (e.g. *.o files mixing with source code). [1] "Description of NTFS date and time stamps for files and folders" http://support.microsoft.com/kb/299648 Helped-by: Torsten Bögershausen <tboegi@web.de> Helped-by: David Turner <dturner@twopensource.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-08 10:12:25 +00:00
}
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 19:14:22 +00:00
/* 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 19:14:22 +00:00
add_path_to_appropriate_result_list(dir, untracked, &cdir,
istate, &path, baselen,
pathspec, state);
}
close_cached_dir(&cdir);
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 19:14:22 +00:00
return dir_state;
}
int cmp_dir_entry(const void *p1, const void *p2)
{
const struct dir_entry *e1 = *(const struct dir_entry **)p1;
const struct dir_entry *e2 = *(const struct dir_entry **)p2;
return name_compare(e1->name, e1->len, e2->name, e2->len);
}
/* check if *out lexically strictly contains *in */
int check_dir_entry_contains(const struct dir_entry *out, const struct dir_entry *in)
{
return (out->len < in->len) &&
(out->name[out->len - 1] == '/') &&
!memcmp(out->name, in->name, out->len);
}
static int treat_leading_path(struct dir_struct *dir,
struct index_state *istate,
const char *path, int len,
const struct pathspec *pathspec)
{
2019-12-19 21:28:25 +00:00
/*
* WARNING WARNING WARNING:
*
* Any updates to the traversal logic here may need corresponding
* updates in treat_leading_path(). See the commit message for the
* commit adding this warning as well as the commit preceding it
* for details.
*/
struct strbuf sb = STRBUF_INIT;
dir: fix checks on common prefix directory Many years ago, the directory traversing logic had an optimization that would always recurse into any directory that was a common prefix of all the pathspecs without walking the leading directories to get down to the desired directory. Thus, git ls-files -o .git/ # case A would notice that .git/ was a common prefix of all pathspecs (since it is the only pathspec listed), and then traverse into it and start showing unknown files under that directory. Unfortunately, .git/ is not a directory we should be traversing into, which made this optimization problematic. This also affected cases like git ls-files -o --exclude-standard t/ # case B where t/ was in the .gitignore file and thus isn't interesting and shouldn't be recursed into. It also affected cases like git ls-files -o --directory untracked_dir/ # case C where untracked_dir/ is indeed untracked and thus interesting, but the --directory flag means we only want to show the directory itself, not recurse into it and start listing untracked files below it. The case B class of bugs were noted and fixed in commits 16e2cfa90993 ("read_directory(): further split treat_path()", 2010-01-08) and 48ffef966c76 ("ls-files: fix overeager pathspec optimization", 2010-01-08), with the idea being that we first wanted to check whether the common prefix was interesting. The former patch noted that treat_path() couldn't be used when checking the common prefix because treat_path() requires a dir_entry() and we haven't read any directories at the point we are checking the common prefix. So, that patch split treat_one_path() out of treat_path(). The latter patch then created a new treat_leading_path() which duplicated by hand the bits of treat_path() that couldn't be broken out and then called treat_one_path() for the remainder. There were three problems with this approach: * The duplicated logic in treat_leading_path() accidentally missed the check for special paths (such as is_dot_or_dotdot and matching ".git"), causing case A types of bugs to continue to be an issue. * The treat_leading_path() logic assumed we should traverse into anything where path_treatment was not path_none, i.e. it perpetuated class C types of bugs. * It meant we had split logic that needed to kept in sync, running the risk that people introduced new inconsistencies (such as in commit be8a84c52669, which we reverted earlier in this series, or in commit df5bcdf83ae which we'll fix in a subsequent commit) Fix most these problems by making treat_leading_path() not only loop over each leading path component, but calling treat_path() directly on each. To do so, we have to create a synthetic dir_entry, but that only takes a few lines. Then, pay attention to the path_treatment result we get from treat_path() and don't treat path_excluded, path_untracked, and path_recurse all the same as path_recurse. This leaves one remaining problem, the new inconsistency from commit df5bcdf83ae. That will be addressed in a subsequent commit. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-12-19 21:28:24 +00:00
int prevlen, baselen;
const char *cp;
dir: fix checks on common prefix directory Many years ago, the directory traversing logic had an optimization that would always recurse into any directory that was a common prefix of all the pathspecs without walking the leading directories to get down to the desired directory. Thus, git ls-files -o .git/ # case A would notice that .git/ was a common prefix of all pathspecs (since it is the only pathspec listed), and then traverse into it and start showing unknown files under that directory. Unfortunately, .git/ is not a directory we should be traversing into, which made this optimization problematic. This also affected cases like git ls-files -o --exclude-standard t/ # case B where t/ was in the .gitignore file and thus isn't interesting and shouldn't be recursed into. It also affected cases like git ls-files -o --directory untracked_dir/ # case C where untracked_dir/ is indeed untracked and thus interesting, but the --directory flag means we only want to show the directory itself, not recurse into it and start listing untracked files below it. The case B class of bugs were noted and fixed in commits 16e2cfa90993 ("read_directory(): further split treat_path()", 2010-01-08) and 48ffef966c76 ("ls-files: fix overeager pathspec optimization", 2010-01-08), with the idea being that we first wanted to check whether the common prefix was interesting. The former patch noted that treat_path() couldn't be used when checking the common prefix because treat_path() requires a dir_entry() and we haven't read any directories at the point we are checking the common prefix. So, that patch split treat_one_path() out of treat_path(). The latter patch then created a new treat_leading_path() which duplicated by hand the bits of treat_path() that couldn't be broken out and then called treat_one_path() for the remainder. There were three problems with this approach: * The duplicated logic in treat_leading_path() accidentally missed the check for special paths (such as is_dot_or_dotdot and matching ".git"), causing case A types of bugs to continue to be an issue. * The treat_leading_path() logic assumed we should traverse into anything where path_treatment was not path_none, i.e. it perpetuated class C types of bugs. * It meant we had split logic that needed to kept in sync, running the risk that people introduced new inconsistencies (such as in commit be8a84c52669, which we reverted earlier in this series, or in commit df5bcdf83ae which we'll fix in a subsequent commit) Fix most these problems by making treat_leading_path() not only loop over each leading path component, but calling treat_path() directly on each. To do so, we have to create a synthetic dir_entry, but that only takes a few lines. Then, pay attention to the path_treatment result we get from treat_path() and don't treat path_excluded, path_untracked, and path_recurse all the same as path_recurse. This leaves one remaining problem, the new inconsistency from commit df5bcdf83ae. That will be addressed in a subsequent commit. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-12-19 21:28:24 +00:00
struct cached_dir cdir;
struct dirent *de;
enum path_treatment state = path_none;
/*
* For each directory component of path, we are going to check whether
* that path is relevant given the pathspec. For example, if path is
* foo/bar/baz/
* then we will ask treat_path() whether we should go into foo, then
* whether we should go into bar, then whether baz is relevant.
* Checking each is important because e.g. if path is
* .git/info/
* then we need to check .git to know we shouldn't traverse it.
* If the return from treat_path() is:
* * path_none, for any path, we return false.
* * path_recurse, for all path components, we return true
* * <anything else> for some intermediate component, we make sure
* to add that path to the relevant list but return false
* signifying that we shouldn't recurse into it.
*/
while (len && path[len - 1] == '/')
len--;
if (!len)
return 1;
dir: fix checks on common prefix directory Many years ago, the directory traversing logic had an optimization that would always recurse into any directory that was a common prefix of all the pathspecs without walking the leading directories to get down to the desired directory. Thus, git ls-files -o .git/ # case A would notice that .git/ was a common prefix of all pathspecs (since it is the only pathspec listed), and then traverse into it and start showing unknown files under that directory. Unfortunately, .git/ is not a directory we should be traversing into, which made this optimization problematic. This also affected cases like git ls-files -o --exclude-standard t/ # case B where t/ was in the .gitignore file and thus isn't interesting and shouldn't be recursed into. It also affected cases like git ls-files -o --directory untracked_dir/ # case C where untracked_dir/ is indeed untracked and thus interesting, but the --directory flag means we only want to show the directory itself, not recurse into it and start listing untracked files below it. The case B class of bugs were noted and fixed in commits 16e2cfa90993 ("read_directory(): further split treat_path()", 2010-01-08) and 48ffef966c76 ("ls-files: fix overeager pathspec optimization", 2010-01-08), with the idea being that we first wanted to check whether the common prefix was interesting. The former patch noted that treat_path() couldn't be used when checking the common prefix because treat_path() requires a dir_entry() and we haven't read any directories at the point we are checking the common prefix. So, that patch split treat_one_path() out of treat_path(). The latter patch then created a new treat_leading_path() which duplicated by hand the bits of treat_path() that couldn't be broken out and then called treat_one_path() for the remainder. There were three problems with this approach: * The duplicated logic in treat_leading_path() accidentally missed the check for special paths (such as is_dot_or_dotdot and matching ".git"), causing case A types of bugs to continue to be an issue. * The treat_leading_path() logic assumed we should traverse into anything where path_treatment was not path_none, i.e. it perpetuated class C types of bugs. * It meant we had split logic that needed to kept in sync, running the risk that people introduced new inconsistencies (such as in commit be8a84c52669, which we reverted earlier in this series, or in commit df5bcdf83ae which we'll fix in a subsequent commit) Fix most these problems by making treat_leading_path() not only loop over each leading path component, but calling treat_path() directly on each. To do so, we have to create a synthetic dir_entry, but that only takes a few lines. Then, pay attention to the path_treatment result we get from treat_path() and don't treat path_excluded, path_untracked, and path_recurse all the same as path_recurse. This leaves one remaining problem, the new inconsistency from commit df5bcdf83ae. That will be addressed in a subsequent commit. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-12-19 21:28:24 +00:00
/*
* We need a manufactured dirent with sufficient space to store a
* leading directory component of path in its d_name. Here, we
* assume that the dirent's d_name is either declared as
* char d_name[BIG_ENOUGH]
* or that it is declared at the end of the struct as
* char d_name[]
* For either case, padding with len+1 bytes at the end will ensure
* sufficient storage space.
*/
de = xcalloc(1, st_add3(sizeof(struct dirent), len, 1));
dir: fix checks on common prefix directory Many years ago, the directory traversing logic had an optimization that would always recurse into any directory that was a common prefix of all the pathspecs without walking the leading directories to get down to the desired directory. Thus, git ls-files -o .git/ # case A would notice that .git/ was a common prefix of all pathspecs (since it is the only pathspec listed), and then traverse into it and start showing unknown files under that directory. Unfortunately, .git/ is not a directory we should be traversing into, which made this optimization problematic. This also affected cases like git ls-files -o --exclude-standard t/ # case B where t/ was in the .gitignore file and thus isn't interesting and shouldn't be recursed into. It also affected cases like git ls-files -o --directory untracked_dir/ # case C where untracked_dir/ is indeed untracked and thus interesting, but the --directory flag means we only want to show the directory itself, not recurse into it and start listing untracked files below it. The case B class of bugs were noted and fixed in commits 16e2cfa90993 ("read_directory(): further split treat_path()", 2010-01-08) and 48ffef966c76 ("ls-files: fix overeager pathspec optimization", 2010-01-08), with the idea being that we first wanted to check whether the common prefix was interesting. The former patch noted that treat_path() couldn't be used when checking the common prefix because treat_path() requires a dir_entry() and we haven't read any directories at the point we are checking the common prefix. So, that patch split treat_one_path() out of treat_path(). The latter patch then created a new treat_leading_path() which duplicated by hand the bits of treat_path() that couldn't be broken out and then called treat_one_path() for the remainder. There were three problems with this approach: * The duplicated logic in treat_leading_path() accidentally missed the check for special paths (such as is_dot_or_dotdot and matching ".git"), causing case A types of bugs to continue to be an issue. * The treat_leading_path() logic assumed we should traverse into anything where path_treatment was not path_none, i.e. it perpetuated class C types of bugs. * It meant we had split logic that needed to kept in sync, running the risk that people introduced new inconsistencies (such as in commit be8a84c52669, which we reverted earlier in this series, or in commit df5bcdf83ae which we'll fix in a subsequent commit) Fix most these problems by making treat_leading_path() not only loop over each leading path component, but calling treat_path() directly on each. To do so, we have to create a synthetic dir_entry, but that only takes a few lines. Then, pay attention to the path_treatment result we get from treat_path() and don't treat path_excluded, path_untracked, and path_recurse all the same as path_recurse. This leaves one remaining problem, the new inconsistency from commit df5bcdf83ae. That will be addressed in a subsequent commit. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-12-19 21:28:24 +00:00
memset(&cdir, 0, sizeof(cdir));
cdir.de = de;
#if defined(DT_UNKNOWN) && !defined(NO_D_TYPE_IN_DIRENT)
de->d_type = DT_DIR;
#endif
baselen = 0;
dir: fix checks on common prefix directory Many years ago, the directory traversing logic had an optimization that would always recurse into any directory that was a common prefix of all the pathspecs without walking the leading directories to get down to the desired directory. Thus, git ls-files -o .git/ # case A would notice that .git/ was a common prefix of all pathspecs (since it is the only pathspec listed), and then traverse into it and start showing unknown files under that directory. Unfortunately, .git/ is not a directory we should be traversing into, which made this optimization problematic. This also affected cases like git ls-files -o --exclude-standard t/ # case B where t/ was in the .gitignore file and thus isn't interesting and shouldn't be recursed into. It also affected cases like git ls-files -o --directory untracked_dir/ # case C where untracked_dir/ is indeed untracked and thus interesting, but the --directory flag means we only want to show the directory itself, not recurse into it and start listing untracked files below it. The case B class of bugs were noted and fixed in commits 16e2cfa90993 ("read_directory(): further split treat_path()", 2010-01-08) and 48ffef966c76 ("ls-files: fix overeager pathspec optimization", 2010-01-08), with the idea being that we first wanted to check whether the common prefix was interesting. The former patch noted that treat_path() couldn't be used when checking the common prefix because treat_path() requires a dir_entry() and we haven't read any directories at the point we are checking the common prefix. So, that patch split treat_one_path() out of treat_path(). The latter patch then created a new treat_leading_path() which duplicated by hand the bits of treat_path() that couldn't be broken out and then called treat_one_path() for the remainder. There were three problems with this approach: * The duplicated logic in treat_leading_path() accidentally missed the check for special paths (such as is_dot_or_dotdot and matching ".git"), causing case A types of bugs to continue to be an issue. * The treat_leading_path() logic assumed we should traverse into anything where path_treatment was not path_none, i.e. it perpetuated class C types of bugs. * It meant we had split logic that needed to kept in sync, running the risk that people introduced new inconsistencies (such as in commit be8a84c52669, which we reverted earlier in this series, or in commit df5bcdf83ae which we'll fix in a subsequent commit) Fix most these problems by making treat_leading_path() not only loop over each leading path component, but calling treat_path() directly on each. To do so, we have to create a synthetic dir_entry, but that only takes a few lines. Then, pay attention to the path_treatment result we get from treat_path() and don't treat path_excluded, path_untracked, and path_recurse all the same as path_recurse. This leaves one remaining problem, the new inconsistency from commit df5bcdf83ae. That will be addressed in a subsequent commit. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-12-19 21:28:24 +00:00
prevlen = 0;
while (1) {
dir: fix checks on common prefix directory Many years ago, the directory traversing logic had an optimization that would always recurse into any directory that was a common prefix of all the pathspecs without walking the leading directories to get down to the desired directory. Thus, git ls-files -o .git/ # case A would notice that .git/ was a common prefix of all pathspecs (since it is the only pathspec listed), and then traverse into it and start showing unknown files under that directory. Unfortunately, .git/ is not a directory we should be traversing into, which made this optimization problematic. This also affected cases like git ls-files -o --exclude-standard t/ # case B where t/ was in the .gitignore file and thus isn't interesting and shouldn't be recursed into. It also affected cases like git ls-files -o --directory untracked_dir/ # case C where untracked_dir/ is indeed untracked and thus interesting, but the --directory flag means we only want to show the directory itself, not recurse into it and start listing untracked files below it. The case B class of bugs were noted and fixed in commits 16e2cfa90993 ("read_directory(): further split treat_path()", 2010-01-08) and 48ffef966c76 ("ls-files: fix overeager pathspec optimization", 2010-01-08), with the idea being that we first wanted to check whether the common prefix was interesting. The former patch noted that treat_path() couldn't be used when checking the common prefix because treat_path() requires a dir_entry() and we haven't read any directories at the point we are checking the common prefix. So, that patch split treat_one_path() out of treat_path(). The latter patch then created a new treat_leading_path() which duplicated by hand the bits of treat_path() that couldn't be broken out and then called treat_one_path() for the remainder. There were three problems with this approach: * The duplicated logic in treat_leading_path() accidentally missed the check for special paths (such as is_dot_or_dotdot and matching ".git"), causing case A types of bugs to continue to be an issue. * The treat_leading_path() logic assumed we should traverse into anything where path_treatment was not path_none, i.e. it perpetuated class C types of bugs. * It meant we had split logic that needed to kept in sync, running the risk that people introduced new inconsistencies (such as in commit be8a84c52669, which we reverted earlier in this series, or in commit df5bcdf83ae which we'll fix in a subsequent commit) Fix most these problems by making treat_leading_path() not only loop over each leading path component, but calling treat_path() directly on each. To do so, we have to create a synthetic dir_entry, but that only takes a few lines. Then, pay attention to the path_treatment result we get from treat_path() and don't treat path_excluded, path_untracked, and path_recurse all the same as path_recurse. This leaves one remaining problem, the new inconsistency from commit df5bcdf83ae. That will be addressed in a subsequent commit. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-12-19 21:28:24 +00:00
prevlen = baselen + !!baselen;
cp = path + prevlen;
cp = memchr(cp, '/', path + len - cp);
if (!cp)
baselen = len;
else
baselen = cp - path;
dir: fix checks on common prefix directory Many years ago, the directory traversing logic had an optimization that would always recurse into any directory that was a common prefix of all the pathspecs without walking the leading directories to get down to the desired directory. Thus, git ls-files -o .git/ # case A would notice that .git/ was a common prefix of all pathspecs (since it is the only pathspec listed), and then traverse into it and start showing unknown files under that directory. Unfortunately, .git/ is not a directory we should be traversing into, which made this optimization problematic. This also affected cases like git ls-files -o --exclude-standard t/ # case B where t/ was in the .gitignore file and thus isn't interesting and shouldn't be recursed into. It also affected cases like git ls-files -o --directory untracked_dir/ # case C where untracked_dir/ is indeed untracked and thus interesting, but the --directory flag means we only want to show the directory itself, not recurse into it and start listing untracked files below it. The case B class of bugs were noted and fixed in commits 16e2cfa90993 ("read_directory(): further split treat_path()", 2010-01-08) and 48ffef966c76 ("ls-files: fix overeager pathspec optimization", 2010-01-08), with the idea being that we first wanted to check whether the common prefix was interesting. The former patch noted that treat_path() couldn't be used when checking the common prefix because treat_path() requires a dir_entry() and we haven't read any directories at the point we are checking the common prefix. So, that patch split treat_one_path() out of treat_path(). The latter patch then created a new treat_leading_path() which duplicated by hand the bits of treat_path() that couldn't be broken out and then called treat_one_path() for the remainder. There were three problems with this approach: * The duplicated logic in treat_leading_path() accidentally missed the check for special paths (such as is_dot_or_dotdot and matching ".git"), causing case A types of bugs to continue to be an issue. * The treat_leading_path() logic assumed we should traverse into anything where path_treatment was not path_none, i.e. it perpetuated class C types of bugs. * It meant we had split logic that needed to kept in sync, running the risk that people introduced new inconsistencies (such as in commit be8a84c52669, which we reverted earlier in this series, or in commit df5bcdf83ae which we'll fix in a subsequent commit) Fix most these problems by making treat_leading_path() not only loop over each leading path component, but calling treat_path() directly on each. To do so, we have to create a synthetic dir_entry, but that only takes a few lines. Then, pay attention to the path_treatment result we get from treat_path() and don't treat path_excluded, path_untracked, and path_recurse all the same as path_recurse. This leaves one remaining problem, the new inconsistency from commit df5bcdf83ae. That will be addressed in a subsequent commit. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-12-19 21:28:24 +00:00
strbuf_reset(&sb);
strbuf_add(&sb, path, baselen);
if (!is_directory(sb.buf))
break;
dir: fix checks on common prefix directory Many years ago, the directory traversing logic had an optimization that would always recurse into any directory that was a common prefix of all the pathspecs without walking the leading directories to get down to the desired directory. Thus, git ls-files -o .git/ # case A would notice that .git/ was a common prefix of all pathspecs (since it is the only pathspec listed), and then traverse into it and start showing unknown files under that directory. Unfortunately, .git/ is not a directory we should be traversing into, which made this optimization problematic. This also affected cases like git ls-files -o --exclude-standard t/ # case B where t/ was in the .gitignore file and thus isn't interesting and shouldn't be recursed into. It also affected cases like git ls-files -o --directory untracked_dir/ # case C where untracked_dir/ is indeed untracked and thus interesting, but the --directory flag means we only want to show the directory itself, not recurse into it and start listing untracked files below it. The case B class of bugs were noted and fixed in commits 16e2cfa90993 ("read_directory(): further split treat_path()", 2010-01-08) and 48ffef966c76 ("ls-files: fix overeager pathspec optimization", 2010-01-08), with the idea being that we first wanted to check whether the common prefix was interesting. The former patch noted that treat_path() couldn't be used when checking the common prefix because treat_path() requires a dir_entry() and we haven't read any directories at the point we are checking the common prefix. So, that patch split treat_one_path() out of treat_path(). The latter patch then created a new treat_leading_path() which duplicated by hand the bits of treat_path() that couldn't be broken out and then called treat_one_path() for the remainder. There were three problems with this approach: * The duplicated logic in treat_leading_path() accidentally missed the check for special paths (such as is_dot_or_dotdot and matching ".git"), causing case A types of bugs to continue to be an issue. * The treat_leading_path() logic assumed we should traverse into anything where path_treatment was not path_none, i.e. it perpetuated class C types of bugs. * It meant we had split logic that needed to kept in sync, running the risk that people introduced new inconsistencies (such as in commit be8a84c52669, which we reverted earlier in this series, or in commit df5bcdf83ae which we'll fix in a subsequent commit) Fix most these problems by making treat_leading_path() not only loop over each leading path component, but calling treat_path() directly on each. To do so, we have to create a synthetic dir_entry, but that only takes a few lines. Then, pay attention to the path_treatment result we get from treat_path() and don't treat path_excluded, path_untracked, and path_recurse all the same as path_recurse. This leaves one remaining problem, the new inconsistency from commit df5bcdf83ae. That will be addressed in a subsequent commit. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-12-19 21:28:24 +00:00
strbuf_reset(&sb);
strbuf_add(&sb, path, prevlen);
memcpy(de->d_name, path+prevlen, baselen-prevlen);
de->d_name[baselen-prevlen] = '\0';
state = treat_path(dir, NULL, &cdir, istate, &sb, prevlen,
pathspec);
2019-12-19 21:28:25 +00:00
if (state == path_untracked &&
get_dtype(cdir.de, istate, sb.buf, sb.len) == DT_DIR &&
(dir->flags & DIR_SHOW_IGNORED_TOO ||
do_match_pathspec(istate, pathspec, sb.buf, sb.len,
baselen, NULL, DO_MATCH_LEADING_PATHSPEC) == MATCHED_RECURSIVELY_LEADING_PATHSPEC)) {
add_path_to_appropriate_result_list(dir, NULL, &cdir,
istate,
&sb, baselen,
pathspec, state);
state = path_recurse;
}
dir: fix checks on common prefix directory Many years ago, the directory traversing logic had an optimization that would always recurse into any directory that was a common prefix of all the pathspecs without walking the leading directories to get down to the desired directory. Thus, git ls-files -o .git/ # case A would notice that .git/ was a common prefix of all pathspecs (since it is the only pathspec listed), and then traverse into it and start showing unknown files under that directory. Unfortunately, .git/ is not a directory we should be traversing into, which made this optimization problematic. This also affected cases like git ls-files -o --exclude-standard t/ # case B where t/ was in the .gitignore file and thus isn't interesting and shouldn't be recursed into. It also affected cases like git ls-files -o --directory untracked_dir/ # case C where untracked_dir/ is indeed untracked and thus interesting, but the --directory flag means we only want to show the directory itself, not recurse into it and start listing untracked files below it. The case B class of bugs were noted and fixed in commits 16e2cfa90993 ("read_directory(): further split treat_path()", 2010-01-08) and 48ffef966c76 ("ls-files: fix overeager pathspec optimization", 2010-01-08), with the idea being that we first wanted to check whether the common prefix was interesting. The former patch noted that treat_path() couldn't be used when checking the common prefix because treat_path() requires a dir_entry() and we haven't read any directories at the point we are checking the common prefix. So, that patch split treat_one_path() out of treat_path(). The latter patch then created a new treat_leading_path() which duplicated by hand the bits of treat_path() that couldn't be broken out and then called treat_one_path() for the remainder. There were three problems with this approach: * The duplicated logic in treat_leading_path() accidentally missed the check for special paths (such as is_dot_or_dotdot and matching ".git"), causing case A types of bugs to continue to be an issue. * The treat_leading_path() logic assumed we should traverse into anything where path_treatment was not path_none, i.e. it perpetuated class C types of bugs. * It meant we had split logic that needed to kept in sync, running the risk that people introduced new inconsistencies (such as in commit be8a84c52669, which we reverted earlier in this series, or in commit df5bcdf83ae which we'll fix in a subsequent commit) Fix most these problems by making treat_leading_path() not only loop over each leading path component, but calling treat_path() directly on each. To do so, we have to create a synthetic dir_entry, but that only takes a few lines. Then, pay attention to the path_treatment result we get from treat_path() and don't treat path_excluded, path_untracked, and path_recurse all the same as path_recurse. This leaves one remaining problem, the new inconsistency from commit df5bcdf83ae. That will be addressed in a subsequent commit. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-12-19 21:28:24 +00:00
if (state != path_recurse)
break; /* do not recurse into it */
dir: fix checks on common prefix directory Many years ago, the directory traversing logic had an optimization that would always recurse into any directory that was a common prefix of all the pathspecs without walking the leading directories to get down to the desired directory. Thus, git ls-files -o .git/ # case A would notice that .git/ was a common prefix of all pathspecs (since it is the only pathspec listed), and then traverse into it and start showing unknown files under that directory. Unfortunately, .git/ is not a directory we should be traversing into, which made this optimization problematic. This also affected cases like git ls-files -o --exclude-standard t/ # case B where t/ was in the .gitignore file and thus isn't interesting and shouldn't be recursed into. It also affected cases like git ls-files -o --directory untracked_dir/ # case C where untracked_dir/ is indeed untracked and thus interesting, but the --directory flag means we only want to show the directory itself, not recurse into it and start listing untracked files below it. The case B class of bugs were noted and fixed in commits 16e2cfa90993 ("read_directory(): further split treat_path()", 2010-01-08) and 48ffef966c76 ("ls-files: fix overeager pathspec optimization", 2010-01-08), with the idea being that we first wanted to check whether the common prefix was interesting. The former patch noted that treat_path() couldn't be used when checking the common prefix because treat_path() requires a dir_entry() and we haven't read any directories at the point we are checking the common prefix. So, that patch split treat_one_path() out of treat_path(). The latter patch then created a new treat_leading_path() which duplicated by hand the bits of treat_path() that couldn't be broken out and then called treat_one_path() for the remainder. There were three problems with this approach: * The duplicated logic in treat_leading_path() accidentally missed the check for special paths (such as is_dot_or_dotdot and matching ".git"), causing case A types of bugs to continue to be an issue. * The treat_leading_path() logic assumed we should traverse into anything where path_treatment was not path_none, i.e. it perpetuated class C types of bugs. * It meant we had split logic that needed to kept in sync, running the risk that people introduced new inconsistencies (such as in commit be8a84c52669, which we reverted earlier in this series, or in commit df5bcdf83ae which we'll fix in a subsequent commit) Fix most these problems by making treat_leading_path() not only loop over each leading path component, but calling treat_path() directly on each. To do so, we have to create a synthetic dir_entry, but that only takes a few lines. Then, pay attention to the path_treatment result we get from treat_path() and don't treat path_excluded, path_untracked, and path_recurse all the same as path_recurse. This leaves one remaining problem, the new inconsistency from commit df5bcdf83ae. That will be addressed in a subsequent commit. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-12-19 21:28:24 +00:00
if (len <= baselen)
break; /* finished checking */
}
dir: fix checks on common prefix directory Many years ago, the directory traversing logic had an optimization that would always recurse into any directory that was a common prefix of all the pathspecs without walking the leading directories to get down to the desired directory. Thus, git ls-files -o .git/ # case A would notice that .git/ was a common prefix of all pathspecs (since it is the only pathspec listed), and then traverse into it and start showing unknown files under that directory. Unfortunately, .git/ is not a directory we should be traversing into, which made this optimization problematic. This also affected cases like git ls-files -o --exclude-standard t/ # case B where t/ was in the .gitignore file and thus isn't interesting and shouldn't be recursed into. It also affected cases like git ls-files -o --directory untracked_dir/ # case C where untracked_dir/ is indeed untracked and thus interesting, but the --directory flag means we only want to show the directory itself, not recurse into it and start listing untracked files below it. The case B class of bugs were noted and fixed in commits 16e2cfa90993 ("read_directory(): further split treat_path()", 2010-01-08) and 48ffef966c76 ("ls-files: fix overeager pathspec optimization", 2010-01-08), with the idea being that we first wanted to check whether the common prefix was interesting. The former patch noted that treat_path() couldn't be used when checking the common prefix because treat_path() requires a dir_entry() and we haven't read any directories at the point we are checking the common prefix. So, that patch split treat_one_path() out of treat_path(). The latter patch then created a new treat_leading_path() which duplicated by hand the bits of treat_path() that couldn't be broken out and then called treat_one_path() for the remainder. There were three problems with this approach: * The duplicated logic in treat_leading_path() accidentally missed the check for special paths (such as is_dot_or_dotdot and matching ".git"), causing case A types of bugs to continue to be an issue. * The treat_leading_path() logic assumed we should traverse into anything where path_treatment was not path_none, i.e. it perpetuated class C types of bugs. * It meant we had split logic that needed to kept in sync, running the risk that people introduced new inconsistencies (such as in commit be8a84c52669, which we reverted earlier in this series, or in commit df5bcdf83ae which we'll fix in a subsequent commit) Fix most these problems by making treat_leading_path() not only loop over each leading path component, but calling treat_path() directly on each. To do so, we have to create a synthetic dir_entry, but that only takes a few lines. Then, pay attention to the path_treatment result we get from treat_path() and don't treat path_excluded, path_untracked, and path_recurse all the same as path_recurse. This leaves one remaining problem, the new inconsistency from commit df5bcdf83ae. That will be addressed in a subsequent commit. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-12-19 21:28:24 +00:00
add_path_to_appropriate_result_list(dir, NULL, &cdir, istate,
&sb, baselen, pathspec,
state);
free(de);
strbuf_release(&sb);
dir: fix checks on common prefix directory Many years ago, the directory traversing logic had an optimization that would always recurse into any directory that was a common prefix of all the pathspecs without walking the leading directories to get down to the desired directory. Thus, git ls-files -o .git/ # case A would notice that .git/ was a common prefix of all pathspecs (since it is the only pathspec listed), and then traverse into it and start showing unknown files under that directory. Unfortunately, .git/ is not a directory we should be traversing into, which made this optimization problematic. This also affected cases like git ls-files -o --exclude-standard t/ # case B where t/ was in the .gitignore file and thus isn't interesting and shouldn't be recursed into. It also affected cases like git ls-files -o --directory untracked_dir/ # case C where untracked_dir/ is indeed untracked and thus interesting, but the --directory flag means we only want to show the directory itself, not recurse into it and start listing untracked files below it. The case B class of bugs were noted and fixed in commits 16e2cfa90993 ("read_directory(): further split treat_path()", 2010-01-08) and 48ffef966c76 ("ls-files: fix overeager pathspec optimization", 2010-01-08), with the idea being that we first wanted to check whether the common prefix was interesting. The former patch noted that treat_path() couldn't be used when checking the common prefix because treat_path() requires a dir_entry() and we haven't read any directories at the point we are checking the common prefix. So, that patch split treat_one_path() out of treat_path(). The latter patch then created a new treat_leading_path() which duplicated by hand the bits of treat_path() that couldn't be broken out and then called treat_one_path() for the remainder. There were three problems with this approach: * The duplicated logic in treat_leading_path() accidentally missed the check for special paths (such as is_dot_or_dotdot and matching ".git"), causing case A types of bugs to continue to be an issue. * The treat_leading_path() logic assumed we should traverse into anything where path_treatment was not path_none, i.e. it perpetuated class C types of bugs. * It meant we had split logic that needed to kept in sync, running the risk that people introduced new inconsistencies (such as in commit be8a84c52669, which we reverted earlier in this series, or in commit df5bcdf83ae which we'll fix in a subsequent commit) Fix most these problems by making treat_leading_path() not only loop over each leading path component, but calling treat_path() directly on each. To do so, we have to create a synthetic dir_entry, but that only takes a few lines. Then, pay attention to the path_treatment result we get from treat_path() and don't treat path_excluded, path_untracked, and path_recurse all the same as path_recurse. This leaves one remaining problem, the new inconsistency from commit df5bcdf83ae. That will be addressed in a subsequent commit. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-12-19 21:28:24 +00:00
return state == path_recurse;
}
static const char *get_ident_string(void)
{
static struct strbuf sb = STRBUF_INIT;
struct utsname uts;
if (sb.len)
return sb.buf;
if (uname(&uts) < 0)
die_errno(_("failed to get kernel name and information"));
strbuf_addf(&sb, "Location %s, system %s", get_git_work_tree(),
uts.sysname);
return sb.buf;
}
static int ident_in_untracked(const struct untracked_cache *uc)
{
/*
* Previous git versions may have saved many NUL separated
* strings in the "ident" field, but it is insane to manage
* many locations, so just take care of the first one.
*/
return !strcmp(uc->ident.buf, get_ident_string());
}
static void set_untracked_ident(struct untracked_cache *uc)
{
strbuf_reset(&uc->ident);
strbuf_addstr(&uc->ident, get_ident_string());
/*
* This strbuf used to contain a list of NUL separated
* strings, so save NUL too for backward compatibility.
*/
strbuf_addch(&uc->ident, 0);
}
static void new_untracked_cache(struct index_state *istate)
{
struct untracked_cache *uc = xcalloc(1, sizeof(*uc));
strbuf_init(&uc->ident, 100);
uc->exclude_per_dir = ".gitignore";
/* should be the same flags used by git-status */
uc->dir_flags = DIR_SHOW_OTHER_DIRECTORIES | DIR_HIDE_EMPTY_DIRECTORIES;
set_untracked_ident(uc);
istate->untracked = uc;
istate->cache_changed |= UNTRACKED_CHANGED;
}
void add_untracked_cache(struct index_state *istate)
{
if (!istate->untracked) {
new_untracked_cache(istate);
} else {
if (!ident_in_untracked(istate->untracked)) {
free_untracked_cache(istate->untracked);
new_untracked_cache(istate);
}
}
}
void remove_untracked_cache(struct index_state *istate)
{
if (istate->untracked) {
free_untracked_cache(istate->untracked);
istate->untracked = NULL;
istate->cache_changed |= UNTRACKED_CHANGED;
}
}
static struct untracked_cache_dir *validate_untracked_cache(struct dir_struct *dir,
int base_len,
const struct pathspec *pathspec)
{
struct untracked_cache_dir *root;
static int untracked_cache_disabled = -1;
if (!dir->untracked)
return NULL;
if (untracked_cache_disabled < 0)
untracked_cache_disabled = git_env_bool("GIT_DISABLE_UNTRACKED_CACHE", 0);
if (untracked_cache_disabled)
return NULL;
/*
* We only support $GIT_DIR/info/exclude and core.excludesfile
* as the global ignore rule files. Any other additions
* (e.g. from command line) invalidate the cache. This
* condition also catches running setup_standard_excludes()
* before setting dir->untracked!
*/
if (dir->unmanaged_exclude_files)
return NULL;
/*
* Optimize for the main use case only: whole-tree git
* status. More work involved in treat_leading_path() if we
* use cache on just a subset of the worktree. pathspec
* support could make the matter even worse.
*/
if (base_len || (pathspec && pathspec->nr))
return NULL;
/* Different set of flags may produce different results */
if (dir->flags != dir->untracked->dir_flags ||
/*
* See treat_directory(), case index_nonexistent. Without
* this flag, we may need to also cache .git file content
* for the resolve_gitlink_ref() call, which we don't.
*/
!(dir->flags & DIR_SHOW_OTHER_DIRECTORIES) ||
/* We don't support collecting ignore files */
(dir->flags & (DIR_SHOW_IGNORED | DIR_SHOW_IGNORED_TOO |
DIR_COLLECT_IGNORED)))
return NULL;
/*
* If we use .gitignore in the cache and now you change it to
* .gitexclude, everything will go wrong.
*/
if (dir->exclude_per_dir != dir->untracked->exclude_per_dir &&
strcmp(dir->exclude_per_dir, dir->untracked->exclude_per_dir))
return NULL;
/*
* EXC_CMDL is not considered in the cache. If people set it,
* skip the cache.
*/
if (dir->exclude_list_group[EXC_CMDL].nr)
return NULL;
if (!ident_in_untracked(dir->untracked)) {
warning(_("untracked cache is disabled on this system or location"));
return NULL;
}
if (!dir->untracked->root) {
const int len = sizeof(*dir->untracked->root);
dir->untracked->root = xmalloc(len);
memset(dir->untracked->root, 0, len);
}
/* Validate $GIT_DIR/info/exclude and core.excludesfile */
root = dir->untracked->root;
if (!oideq(&dir->ss_info_exclude.oid,
&dir->untracked->ss_info_exclude.oid)) {
invalidate_gitignore(dir->untracked, root);
dir->untracked->ss_info_exclude = dir->ss_info_exclude;
}
if (!oideq(&dir->ss_excludes_file.oid,
&dir->untracked->ss_excludes_file.oid)) {
invalidate_gitignore(dir->untracked, root);
dir->untracked->ss_excludes_file = dir->ss_excludes_file;
}
/* Make sure this directory is not dropped out at saving phase */
root->recurse = 1;
return root;
}
int read_directory(struct dir_struct *dir, struct index_state *istate,
const char *path, int len, const struct pathspec *pathspec)
{
struct untracked_cache_dir *untracked;
trace_performance_enter();
if (has_symlink_leading_path(path, len)) {
trace_performance_leave("read directory %.*s", len, path);
return dir->nr;
}
untracked = validate_untracked_cache(dir, len, pathspec);
if (!untracked)
/*
* make sure untracked cache code path is disabled,
* e.g. prep_exclude()
*/
dir->untracked = NULL;
if (!len || treat_leading_path(dir, istate, path, len, pathspec))
read_directory_recursive(dir, istate, path, len, untracked, 0, 0, pathspec);
QSORT(dir->entries, dir->nr, cmp_dir_entry);
QSORT(dir->ignored, dir->ignored_nr, cmp_dir_entry);
/*
* If DIR_SHOW_IGNORED_TOO is set, read_directory_recursive() will
* also pick up untracked contents of untracked dirs; by default
* we discard these, but given DIR_KEEP_UNTRACKED_CONTENTS we do not.
*/
if ((dir->flags & DIR_SHOW_IGNORED_TOO) &&
!(dir->flags & DIR_KEEP_UNTRACKED_CONTENTS)) {
int i, j;
/* remove from dir->entries untracked contents of untracked dirs */
for (i = j = 0; j < dir->nr; j++) {
if (i &&
check_dir_entry_contains(dir->entries[i - 1], dir->entries[j])) {
FREE_AND_NULL(dir->entries[j]);
} else {
dir->entries[i++] = dir->entries[j];
}
}
dir->nr = i;
}
trace_performance_leave("read directory %.*s", len, path);
if (dir->untracked) {
static int force_untracked_cache = -1;
static struct trace_key trace_untracked_stats = TRACE_KEY_INIT(UNTRACKED_STATS);
if (force_untracked_cache < 0)
force_untracked_cache =
git_env_bool("GIT_FORCE_UNTRACKED_CACHE", 0);
trace_printf_key(&trace_untracked_stats,
"node creation: %u\n"
"gitignore invalidation: %u\n"
"directory invalidation: %u\n"
"opendir: %u\n",
dir->untracked->dir_created,
dir->untracked->gitignore_invalidated,
dir->untracked->dir_invalidated,
dir->untracked->dir_opened);
if (force_untracked_cache &&
dir->untracked == istate->untracked &&
(dir->untracked->dir_opened ||
dir->untracked->gitignore_invalidated ||
dir->untracked->dir_invalidated))
istate->cache_changed |= UNTRACKED_CHANGED;
if (dir->untracked != istate->untracked) {
FREE_AND_NULL(dir->untracked);
}
}
return dir->nr;
}
int file_exists(const char *f)
{
struct stat sb;
return lstat(f, &sb) == 0;
}
int repo_file_exists(struct repository *repo, const char *path)
{
if (repo != the_repository)
BUG("do not know how to check file existence in arbitrary repo");
return file_exists(path);
}
static int cmp_icase(char a, char b)
{
if (a == b)
return 0;
if (ignore_case)
return toupper(a) - toupper(b);
return a - b;
}
/*
* Given two normalized paths (a trailing slash is ok), if subdir is
* outside dir, return -1. Otherwise return the offset in subdir that
* 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 && !cmp_icase(*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);
struct object_id submodule_head;
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;
}
2015-09-24 21:08:35 +00:00
strbuf_complete(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 through */
} else if (S_ISDIR(st.st_mode)) {
if (!remove_dir_recurse(path, flag, &kept_down))
continue; /* happy */
} else if (!only_empty &&
(!unlink(path->buf) || 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 08:05:00 +00:00
int remove_dir_recursively(struct strbuf *path, int flag)
{
return remove_dir_recurse(path, flag, NULL);
}
memoize common git-path "constant" files One of the most common uses of git_path() is to pass a constant, like git_path("MERGE_MSG"). This has two drawbacks: 1. The return value is a static buffer, and the lifetime is dependent on other calls to git_path, etc. 2. There's no compile-time checking of the pathname. This is OK for a one-off (after all, we have to spell it correctly at least once), but many of these constant strings appear throughout the code. This patch introduces a series of functions to "memoize" these strings, which are essentially globals for the lifetime of the program. We compute the value once, take ownership of the buffer, and return the cached value for subsequent calls. cache.h provides a helper macro for defining these functions as one-liners, and defines a few common ones for global use. Using a macro is a little bit gross, but it does nicely document the purpose of the functions. If we need to touch them all later (e.g., because we learned how to change the git_dir variable at runtime, and need to invalidate all of the stored values), it will be much easier to have the complete list. Note that the shared-global functions have separate, manual declarations. We could do something clever with the macros (e.g., expand it to a declaration in some places, and a declaration _and_ a definition in path.c). But there aren't that many, and it's probably better to stay away from too-magical macros. Likewise, if we abandon the C preprocessor in favor of generating these with a script, we could get much fancier. E.g., normalizing "FOO/BAR-BAZ" into "git_path_foo_bar_baz". But the small amount of saved typing is probably not worth the resulting confusion to readers who want to grep for the function's definition. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-08-10 09:38:57 +00:00
static GIT_PATH_FUNC(git_path_info_exclude, "info/exclude")
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 08:05:00 +00:00
void setup_standard_excludes(struct dir_struct *dir)
{
dir->exclude_per_dir = ".gitignore";
/* core.excludesfile defaulting to $XDG_CONFIG_HOME/git/ignore */
if (!excludes_file)
excludes_file = xdg_config_home("ignore");
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 21:03:18 +00:00
if (excludes_file && !access_or_warn(excludes_file, R_OK, 0))
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
add_patterns_from_file_1(dir, excludes_file,
dir->untracked ? &dir->ss_excludes_file : NULL);
/* per repository user preference */
if (startup_info->have_repository) {
const char *path = git_path_info_exclude();
if (!access_or_warn(path, R_OK, 0))
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
add_patterns_from_file_1(dir, path,
dir->untracked ? &dir->ss_info_exclude : 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 08:05:00 +00:00
}
int remove_path(const char *name)
{
char *slash;
if (unlink(name) && !is_missing_file_error(errno))
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 pattern_list *pl;
struct exclude_stack *stk;
for (i = EXC_CMDL; i <= EXC_FILE; i++) {
group = &dir->exclude_list_group[i];
for (j = 0; j < group->nr; j++) {
pl = &group->pl[j];
if (i == EXC_DIRS)
free((char *)pl->src);
treewide: rename 'exclude' methods to 'pattern' The first consumer of pattern-matching filenames was the .gitignore feature. In that context, storing a list of patterns as a 'struct exclude_list' makes sense. However, the sparse-checkout feature then adopted these structures and methods, but with the opposite meaning: these patterns match the files that should be included! It would be clearer to rename this entire library as a "pattern matching" library, and the callers apply exclusion/inclusion logic accordingly based on their needs. This commit renames several methods defined in dir.h to make more sense with the renamed 'struct exclude_list' to 'struct pattern_list' and 'struct exclude' to 'struct path_pattern': * last_exclude_matching() -> last_matching_pattern() * parse_exclude() -> parse_path_pattern() In addition, the word 'exclude' was replaced with 'pattern' in the methods below: * add_exclude_list() * add_excludes_from_file_to_list() * add_excludes_from_file() * add_excludes_from_blob_to_list() * add_exclude() * clear_exclude_list() A few methods with the word "exclude" remain. These will be handled seperately. In particular, the method "is_excluded()" is concretely about the .gitignore file relative to a specific directory. This is the important boundary between library and consumer: is_excluded() cares about .gitignore, but is_excluded() calls last_matching_pattern() to make that decision. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-09-03 18:04:57 +00:00
clear_pattern_list(pl);
}
free(group->pl);
}
stk = dir->exclude_stack;
while (stk) {
struct exclude_stack *prev = stk->prev;
free(stk);
stk = prev;
}
strbuf_release(&dir->basebuf);
}
struct ondisk_untracked_cache {
struct stat_data info_exclude_stat;
struct stat_data excludes_file_stat;
uint32_t dir_flags;
};
#define ouc_offset(x) offsetof(struct ondisk_untracked_cache, x)
struct write_data {
int index; /* number of written untracked_cache_dir */
struct ewah_bitmap *check_only; /* from untracked_cache_dir */
struct ewah_bitmap *valid; /* from untracked_cache_dir */
struct ewah_bitmap *sha1_valid; /* set if exclude_sha1 is not null */
struct strbuf out;
struct strbuf sb_stat;
struct strbuf sb_sha1;
};
static void stat_data_to_disk(struct stat_data *to, const struct stat_data *from)
{
to->sd_ctime.sec = htonl(from->sd_ctime.sec);
to->sd_ctime.nsec = htonl(from->sd_ctime.nsec);
to->sd_mtime.sec = htonl(from->sd_mtime.sec);
to->sd_mtime.nsec = htonl(from->sd_mtime.nsec);
to->sd_dev = htonl(from->sd_dev);
to->sd_ino = htonl(from->sd_ino);
to->sd_uid = htonl(from->sd_uid);
to->sd_gid = htonl(from->sd_gid);
to->sd_size = htonl(from->sd_size);
}
static void write_one_dir(struct untracked_cache_dir *untracked,
struct write_data *wd)
{
struct stat_data stat_data;
struct strbuf *out = &wd->out;
unsigned char intbuf[16];
unsigned int intlen, value;
int i = wd->index++;
/*
* untracked_nr should be reset whenever valid is clear, but
* for safety..
*/
if (!untracked->valid) {
untracked->untracked_nr = 0;
untracked->check_only = 0;
}
if (untracked->check_only)
ewah_set(wd->check_only, i);
if (untracked->valid) {
ewah_set(wd->valid, i);
stat_data_to_disk(&stat_data, &untracked->stat_data);
strbuf_add(&wd->sb_stat, &stat_data, sizeof(stat_data));
}
if (!is_null_oid(&untracked->exclude_oid)) {
ewah_set(wd->sha1_valid, i);
strbuf_add(&wd->sb_sha1, untracked->exclude_oid.hash,
the_hash_algo->rawsz);
}
intlen = encode_varint(untracked->untracked_nr, intbuf);
strbuf_add(out, intbuf, intlen);
/* skip non-recurse directories */
for (i = 0, value = 0; i < untracked->dirs_nr; i++)
if (untracked->dirs[i]->recurse)
value++;
intlen = encode_varint(value, intbuf);
strbuf_add(out, intbuf, intlen);
strbuf_add(out, untracked->name, strlen(untracked->name) + 1);
for (i = 0; i < untracked->untracked_nr; i++)
strbuf_add(out, untracked->untracked[i],
strlen(untracked->untracked[i]) + 1);
for (i = 0; i < untracked->dirs_nr; i++)
if (untracked->dirs[i]->recurse)
write_one_dir(untracked->dirs[i], wd);
}
void write_untracked_extension(struct strbuf *out, struct untracked_cache *untracked)
{
struct ondisk_untracked_cache *ouc;
struct write_data wd;
unsigned char varbuf[16];
int varint_len;
const unsigned hashsz = the_hash_algo->rawsz;
ouc = xcalloc(1, sizeof(*ouc));
stat_data_to_disk(&ouc->info_exclude_stat, &untracked->ss_info_exclude.stat);
stat_data_to_disk(&ouc->excludes_file_stat, &untracked->ss_excludes_file.stat);
ouc->dir_flags = htonl(untracked->dir_flags);
varint_len = encode_varint(untracked->ident.len, varbuf);
strbuf_add(out, varbuf, varint_len);
strbuf_addbuf(out, &untracked->ident);
strbuf_add(out, ouc, sizeof(*ouc));
strbuf_add(out, untracked->ss_info_exclude.oid.hash, hashsz);
strbuf_add(out, untracked->ss_excludes_file.oid.hash, hashsz);
strbuf_add(out, untracked->exclude_per_dir, strlen(untracked->exclude_per_dir) + 1);
FREE_AND_NULL(ouc);
if (!untracked->root) {
varint_len = encode_varint(0, varbuf);
strbuf_add(out, varbuf, varint_len);
return;
}
wd.index = 0;
wd.check_only = ewah_new();
wd.valid = ewah_new();
wd.sha1_valid = ewah_new();
strbuf_init(&wd.out, 1024);
strbuf_init(&wd.sb_stat, 1024);
strbuf_init(&wd.sb_sha1, 1024);
write_one_dir(untracked->root, &wd);
varint_len = encode_varint(wd.index, varbuf);
strbuf_add(out, varbuf, varint_len);
strbuf_addbuf(out, &wd.out);
ewah_serialize_strbuf(wd.valid, out);
ewah_serialize_strbuf(wd.check_only, out);
ewah_serialize_strbuf(wd.sha1_valid, out);
strbuf_addbuf(out, &wd.sb_stat);
strbuf_addbuf(out, &wd.sb_sha1);
strbuf_addch(out, '\0'); /* safe guard for string lists */
ewah_free(wd.valid);
ewah_free(wd.check_only);
ewah_free(wd.sha1_valid);
strbuf_release(&wd.out);
strbuf_release(&wd.sb_stat);
strbuf_release(&wd.sb_sha1);
}
static void free_untracked(struct untracked_cache_dir *ucd)
{
int i;
if (!ucd)
return;
for (i = 0; i < ucd->dirs_nr; i++)
free_untracked(ucd->dirs[i]);
for (i = 0; i < ucd->untracked_nr; i++)
free(ucd->untracked[i]);
free(ucd->untracked);
free(ucd->dirs);
free(ucd);
}
void free_untracked_cache(struct untracked_cache *uc)
{
if (uc)
free_untracked(uc->root);
free(uc);
}
struct read_data {
int index;
struct untracked_cache_dir **ucd;
struct ewah_bitmap *check_only;
struct ewah_bitmap *valid;
struct ewah_bitmap *sha1_valid;
const unsigned char *data;
const unsigned char *end;
};
static void stat_data_from_disk(struct stat_data *to, const unsigned char *data)
{
memcpy(to, data, sizeof(*to));
to->sd_ctime.sec = ntohl(to->sd_ctime.sec);
to->sd_ctime.nsec = ntohl(to->sd_ctime.nsec);
to->sd_mtime.sec = ntohl(to->sd_mtime.sec);
to->sd_mtime.nsec = ntohl(to->sd_mtime.nsec);
to->sd_dev = ntohl(to->sd_dev);
to->sd_ino = ntohl(to->sd_ino);
to->sd_uid = ntohl(to->sd_uid);
to->sd_gid = ntohl(to->sd_gid);
to->sd_size = ntohl(to->sd_size);
}
static int read_one_dir(struct untracked_cache_dir **untracked_,
struct read_data *rd)
{
struct untracked_cache_dir ud, *untracked;
const unsigned char *data = rd->data, *end = rd->end;
2019-04-18 21:17:02 +00:00
const unsigned char *eos;
unsigned int value;
int i;
memset(&ud, 0, sizeof(ud));
value = decode_varint(&data);
if (data > end)
return -1;
ud.recurse = 1;
ud.untracked_alloc = value;
ud.untracked_nr = value;
if (ud.untracked_nr)
ALLOC_ARRAY(ud.untracked, ud.untracked_nr);
ud.dirs_alloc = ud.dirs_nr = decode_varint(&data);
if (data > end)
return -1;
ALLOC_ARRAY(ud.dirs, ud.dirs_nr);
2019-04-18 21:17:02 +00:00
eos = memchr(data, '\0', end - data);
if (!eos || eos == end)
return -1;
2019-04-18 21:17:02 +00:00
*untracked_ = untracked = xmalloc(st_add3(sizeof(*untracked), eos - data, 1));
memcpy(untracked, &ud, sizeof(ud));
memcpy(untracked->name, data, eos - data + 1);
data = eos + 1;
for (i = 0; i < untracked->untracked_nr; i++) {
2019-04-18 21:17:02 +00:00
eos = memchr(data, '\0', end - data);
if (!eos || eos == end)
return -1;
untracked->untracked[i] = xmemdupz(data, eos - data);
data = eos + 1;
}
rd->ucd[rd->index++] = untracked;
rd->data = data;
for (i = 0; i < untracked->dirs_nr; i++) {
if (read_one_dir(untracked->dirs + i, rd) < 0)
return -1;
}
return 0;
}
static void set_check_only(size_t pos, void *cb)
{
struct read_data *rd = cb;
struct untracked_cache_dir *ud = rd->ucd[pos];
ud->check_only = 1;
}
static void read_stat(size_t pos, void *cb)
{
struct read_data *rd = cb;
struct untracked_cache_dir *ud = rd->ucd[pos];
if (rd->data + sizeof(struct stat_data) > rd->end) {
rd->data = rd->end + 1;
return;
}
stat_data_from_disk(&ud->stat_data, rd->data);
rd->data += sizeof(struct stat_data);
ud->valid = 1;
}
static void read_oid(size_t pos, void *cb)
{
struct read_data *rd = cb;
struct untracked_cache_dir *ud = rd->ucd[pos];
if (rd->data + the_hash_algo->rawsz > rd->end) {
rd->data = rd->end + 1;
return;
}
hashcpy(ud->exclude_oid.hash, rd->data);
rd->data += the_hash_algo->rawsz;
}
static void load_oid_stat(struct oid_stat *oid_stat, const unsigned char *data,
const unsigned char *sha1)
{
stat_data_from_disk(&oid_stat->stat, data);
hashcpy(oid_stat->oid.hash, sha1);
oid_stat->valid = 1;
}
struct untracked_cache *read_untracked_extension(const void *data, unsigned long sz)
{
struct untracked_cache *uc;
struct read_data rd;
const unsigned char *next = data, *end = (const unsigned char *)data + sz;
const char *ident;
int ident_len;
ssize_t len;
const char *exclude_per_dir;
const unsigned hashsz = the_hash_algo->rawsz;
const unsigned offset = sizeof(struct ondisk_untracked_cache);
const unsigned exclude_per_dir_offset = offset + 2 * hashsz;
if (sz <= 1 || end[-1] != '\0')
return NULL;
end--;
ident_len = decode_varint(&next);
if (next + ident_len > end)
return NULL;
ident = (const char *)next;
next += ident_len;
if (next + exclude_per_dir_offset + 1 > end)
return NULL;
uc = xcalloc(1, sizeof(*uc));
strbuf_init(&uc->ident, ident_len);
strbuf_add(&uc->ident, ident, ident_len);
load_oid_stat(&uc->ss_info_exclude,
next + ouc_offset(info_exclude_stat),
next + offset);
load_oid_stat(&uc->ss_excludes_file,
next + ouc_offset(excludes_file_stat),
next + offset + hashsz);
uc->dir_flags = get_be32(next + ouc_offset(dir_flags));
exclude_per_dir = (const char *)next + exclude_per_dir_offset;
uc->exclude_per_dir = xstrdup(exclude_per_dir);
/* NUL after exclude_per_dir is covered by sizeof(*ouc) */
next += exclude_per_dir_offset + strlen(exclude_per_dir) + 1;
if (next >= end)
goto done2;
len = decode_varint(&next);
if (next > end || len == 0)
goto done2;
rd.valid = ewah_new();
rd.check_only = ewah_new();
rd.sha1_valid = ewah_new();
rd.data = next;
rd.end = end;
rd.index = 0;
ALLOC_ARRAY(rd.ucd, len);
if (read_one_dir(&uc->root, &rd) || rd.index != len)
goto done;
next = rd.data;
len = ewah_read_mmap(rd.valid, next, end - next);
if (len < 0)
goto done;
next += len;
len = ewah_read_mmap(rd.check_only, next, end - next);
if (len < 0)
goto done;
next += len;
len = ewah_read_mmap(rd.sha1_valid, next, end - next);
if (len < 0)
goto done;
ewah_each_bit(rd.check_only, set_check_only, &rd);
rd.data = next + len;
ewah_each_bit(rd.valid, read_stat, &rd);
ewah_each_bit(rd.sha1_valid, read_oid, &rd);
next = rd.data;
done:
free(rd.ucd);
ewah_free(rd.valid);
ewah_free(rd.check_only);
ewah_free(rd.sha1_valid);
done2:
if (next != end) {
free_untracked_cache(uc);
uc = NULL;
}
return uc;
}
static void invalidate_one_directory(struct untracked_cache *uc,
struct untracked_cache_dir *ucd)
{
uc->dir_invalidated++;
ucd->valid = 0;
ucd->untracked_nr = 0;
}
/*
* Normally when an entry is added or removed from a directory,
* invalidating that directory is enough. No need to touch its
* ancestors. When a directory is shown as "foo/bar/" in git-status
* however, deleting or adding an entry may have cascading effect.
*
* Say the "foo/bar/file" has become untracked, we need to tell the
* untracked_cache_dir of "foo" that "bar/" is not an untracked
* directory any more (because "bar" is managed by foo as an untracked
* "file").
*
* Similarly, if "foo/bar/file" moves from untracked to tracked and it
* was the last untracked entry in the entire "foo", we should show
* "foo/" instead. Which means we have to invalidate past "bar" up to
* "foo".
*
* This function traverses all directories from root to leaf. If there
* is a chance of one of the above cases happening, we invalidate back
* to root. Otherwise we just invalidate the leaf. There may be a more
* sophisticated way than checking for SHOW_OTHER_DIRECTORIES to
* detect these cases and avoid unnecessary invalidation, for example,
* checking for the untracked entry named "bar/" in "foo", but for now
* stick to something safe and simple.
*/
static int invalidate_one_component(struct untracked_cache *uc,
struct untracked_cache_dir *dir,
const char *path, int len)
{
const char *rest = strchr(path, '/');
if (rest) {
int component_len = rest - path;
struct untracked_cache_dir *d =
lookup_untracked(uc, dir, path, component_len);
int ret =
invalidate_one_component(uc, d, rest + 1,
len - (component_len + 1));
if (ret)
invalidate_one_directory(uc, dir);
return ret;
}
invalidate_one_directory(uc, dir);
return uc->dir_flags & DIR_SHOW_OTHER_DIRECTORIES;
}
void untracked_cache_invalidate_path(struct index_state *istate,
const char *path, int safe_path)
{
if (!istate->untracked || !istate->untracked->root)
return;
if (!safe_path && !verify_path(path, 0))
return;
invalidate_one_component(istate->untracked, istate->untracked->root,
path, strlen(path));
}
void untracked_cache_remove_from_index(struct index_state *istate,
const char *path)
{
untracked_cache_invalidate_path(istate, path, 1);
}
void untracked_cache_add_to_index(struct index_state *istate,
const char *path)
{
untracked_cache_invalidate_path(istate, path, 1);
}
static void connect_wt_gitdir_in_nested(const char *sub_worktree,
const char *sub_gitdir)
{
int i;
struct repository subrepo;
struct strbuf sub_wt = STRBUF_INIT;
struct strbuf sub_gd = STRBUF_INIT;
const struct submodule *sub;
/* If the submodule has no working tree, we can ignore it. */
if (repo_init(&subrepo, sub_gitdir, sub_worktree))
return;
if (repo_read_index(&subrepo) < 0)
die(_("index file corrupt in repo %s"), subrepo.gitdir);
for (i = 0; i < subrepo.index->cache_nr; i++) {
const struct cache_entry *ce = subrepo.index->cache[i];
if (!S_ISGITLINK(ce->ce_mode))
continue;
while (i + 1 < subrepo.index->cache_nr &&
!strcmp(ce->name, subrepo.index->cache[i + 1]->name))
/*
* Skip entries with the same name in different stages
* to make sure an entry is returned only once.
*/
i++;
sub = submodule_from_path(&subrepo, &null_oid, ce->name);
if (!sub || !is_submodule_active(&subrepo, ce->name))
/* .gitmodules broken or inactive sub */
continue;
strbuf_reset(&sub_wt);
strbuf_reset(&sub_gd);
strbuf_addf(&sub_wt, "%s/%s", sub_worktree, sub->path);
strbuf_addf(&sub_gd, "%s/modules/%s", sub_gitdir, sub->name);
connect_work_tree_and_git_dir(sub_wt.buf, sub_gd.buf, 1);
}
strbuf_release(&sub_wt);
strbuf_release(&sub_gd);
repo_clear(&subrepo);
}
void connect_work_tree_and_git_dir(const char *work_tree_,
const char *git_dir_,
int recurse_into_nested)
{
struct strbuf gitfile_sb = STRBUF_INIT;
struct strbuf cfg_sb = STRBUF_INIT;
struct strbuf rel_path = STRBUF_INIT;
char *git_dir, *work_tree;
/* Prepare .git file */
strbuf_addf(&gitfile_sb, "%s/.git", work_tree_);
if (safe_create_leading_directories_const(gitfile_sb.buf))
die(_("could not create directories for %s"), gitfile_sb.buf);
/* Prepare config file */
strbuf_addf(&cfg_sb, "%s/config", git_dir_);
if (safe_create_leading_directories_const(cfg_sb.buf))
die(_("could not create directories for %s"), cfg_sb.buf);
git_dir = real_pathdup(git_dir_, 1);
work_tree = real_pathdup(work_tree_, 1);
/* Write .git file */
write_file(gitfile_sb.buf, "gitdir: %s",
relative_path(git_dir, work_tree, &rel_path));
/* Update core.worktree setting */
git_config_set_in_file(cfg_sb.buf, "core.worktree",
relative_path(work_tree, git_dir, &rel_path));
strbuf_release(&gitfile_sb);
strbuf_release(&cfg_sb);
strbuf_release(&rel_path);
if (recurse_into_nested)
connect_wt_gitdir_in_nested(work_tree, git_dir);
free(work_tree);
free(git_dir);
}
/*
* Migrate the git directory of the given path from old_git_dir to new_git_dir.
*/
void relocate_gitdir(const char *path, const char *old_git_dir, const char *new_git_dir)
{
if (rename(old_git_dir, new_git_dir) < 0)
die_errno(_("could not migrate git directory from '%s' to '%s'"),
old_git_dir, new_git_dir);
connect_work_tree_and_git_dir(path, new_git_dir, 0);
}