2006-05-17 10:02:14 +08:00
|
|
|
/*
|
|
|
|
* This handles recursive filename detection with exclude
|
|
|
|
* files, index knowledge etc..
|
|
|
|
*
|
2012-12-27 10:32:21 +08:00
|
|
|
* See Documentation/technical/api-directory-listing.txt
|
|
|
|
*
|
2006-05-17 10:02:14 +08:00
|
|
|
* Copyright (C) Linus Torvalds, 2005-2006
|
|
|
|
* Junio Hamano, 2005-2006
|
|
|
|
*/
|
|
|
|
#include "cache.h"
|
|
|
|
#include "dir.h"
|
2007-04-12 05:49:44 +08:00
|
|
|
#include "refs.h"
|
2012-10-15 14:26:02 +08:00
|
|
|
#include "wildmatch.h"
|
2006-05-17 10:02:14 +08:00
|
|
|
|
Optimize directory listing with pathspec limiter.
The way things are set up, you can now pass a "pathspec" to the
"read_directory()" function. If you pass NULL, it acts exactly
like it used to do (read everything). If you pass a non-NULL
pointer, it will simplify it into a "these are the prefixes
without any special characters", and stop any readdir() early if
the path in question doesn't match any of the prefixes.
NOTE! This does *not* obviate the need for the caller to do the *exact*
pathspec match later. It's a first-level filter on "read_directory()", but
it does not do the full pathspec thing. Maybe it should. But in the
meantime, builtin-add.c really does need to do first
read_directory(dir, .., pathspec);
if (pathspec)
prune_directory(dir, pathspec, baselen);
ie the "prune_directory()" part will do the *exact* pathspec pruning,
while the "read_directory()" will use the pathspec just to do some quick
high-level pruning of the directories it will recurse into.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-31 11:39:30 +08:00
|
|
|
struct path_simplify {
|
|
|
|
int len;
|
|
|
|
const char *path;
|
|
|
|
};
|
|
|
|
|
2009-07-09 10:24:39 +08:00
|
|
|
static int read_directory_recursive(struct dir_struct *dir, const char *path, int len,
|
2007-04-12 05:49:44 +08:00
|
|
|
int check_only, const struct path_simplify *simplify);
|
2009-07-09 10:31:49 +08:00
|
|
|
static int get_dtype(struct dirent *de, const char *path, int len);
|
2007-04-12 05:49:44 +08:00
|
|
|
|
2010-10-03 17:56:41 +08:00
|
|
|
/* helper string functions with support for the ignore_case flag */
|
|
|
|
int strcmp_icase(const char *a, const char *b)
|
|
|
|
{
|
|
|
|
return ignore_case ? strcasecmp(a, b) : strcmp(a, b);
|
|
|
|
}
|
|
|
|
|
|
|
|
int strncmp_icase(const char *a, const char *b, size_t count)
|
|
|
|
{
|
|
|
|
return ignore_case ? strncasecmp(a, b, count) : strncmp(a, b, count);
|
|
|
|
}
|
|
|
|
|
|
|
|
int fnmatch_icase(const char *pattern, const char *string, int flags)
|
|
|
|
{
|
|
|
|
return fnmatch(pattern, string, flags | (ignore_case ? FNM_CASEFOLD : 0));
|
|
|
|
}
|
|
|
|
|
2012-11-24 12:33:49 +08:00
|
|
|
inline int git_fnmatch(const char *pattern, const char *string,
|
|
|
|
int flags, int prefix)
|
|
|
|
{
|
|
|
|
int fnm_flags = 0;
|
|
|
|
if (flags & GFNM_PATHNAME)
|
|
|
|
fnm_flags |= FNM_PATHNAME;
|
|
|
|
if (prefix > 0) {
|
|
|
|
if (strncmp(pattern, string, prefix))
|
|
|
|
return FNM_NOMATCH;
|
|
|
|
pattern += prefix;
|
|
|
|
string += prefix;
|
|
|
|
}
|
2012-11-24 12:33:50 +08:00
|
|
|
if (flags & GFNM_ONESTAR) {
|
|
|
|
int pattern_len = strlen(++pattern);
|
|
|
|
int string_len = strlen(string);
|
|
|
|
return string_len < pattern_len ||
|
|
|
|
strcmp(pattern,
|
|
|
|
string + string_len - pattern_len);
|
|
|
|
}
|
2012-11-24 12:33:49 +08:00
|
|
|
return fnmatch(pattern, string, fnm_flags);
|
|
|
|
}
|
|
|
|
|
dir.c::match_basename(): pay attention to the length of string parameters
The function takes two counted strings (<basename, basenamelen> and
<pattern, patternlen>) as parameters, together with prefix (the
length of the prefix in pattern that is to be matched literally
without globbing against the basename) and EXC_* flags that tells it
how to match the pattern against the basename.
However, it did not pay attention to the length of these counted
strings. Update them to do the following:
* When the entire pattern is to be matched literally, the pattern
matches the basename only when the lengths of them are the same,
and they match up to that length.
* When the pattern is "*" followed by a string to be matched
literally, make sure that the basenamelen is equal or longer than
the "literal" part of the pattern, and the tail of the basename
string matches that literal part.
* Otherwise, use the new fnmatch_icase_mem helper to make
sure we only lookmake sure we use only look at the
counted part of the strings. Because these counted strings are
full strings most of the time, we check for termination
to avoid unnecessary allocation.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-29 05:47:28 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2013-04-04 00:34:04 +08:00
|
|
|
if (ignore_case)
|
|
|
|
flags |= WM_CASEFOLD;
|
|
|
|
match_status = wildmatch(use_pat, use_str, flags, NULL);
|
dir.c::match_basename(): pay attention to the length of string parameters
The function takes two counted strings (<basename, basenamelen> and
<pattern, patternlen>) as parameters, together with prefix (the
length of the prefix in pattern that is to be matched literally
without globbing against the basename) and EXC_* flags that tells it
how to match the pattern against the basename.
However, it did not pay attention to the length of these counted
strings. Update them to do the following:
* When the entire pattern is to be matched literally, the pattern
matches the basename only when the lengths of them are the same,
and they match up to that length.
* When the pattern is "*" followed by a string to be matched
literally, make sure that the basenamelen is equal or longer than
the "literal" part of the pattern, and the tail of the basename
string matches that literal part.
* Otherwise, use the new fnmatch_icase_mem helper to make
sure we only lookmake sure we use only look at the
counted part of the strings. Because these counted strings are
full strings most of the time, we check for termination
to avoid unnecessary allocation.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-29 05:47:28 +08:00
|
|
|
|
|
|
|
strbuf_release(&pat_buf);
|
|
|
|
strbuf_release(&str_buf);
|
|
|
|
|
|
|
|
return match_status;
|
|
|
|
}
|
|
|
|
|
2011-09-04 18:42:01 +08:00
|
|
|
static size_t common_prefix_len(const char **pathspec)
|
2006-05-20 07:07:51 +08:00
|
|
|
{
|
2011-09-07 03:32:30 +08:00
|
|
|
const char *n, *first;
|
|
|
|
size_t max = 0;
|
add global --literal-pathspecs option
Git takes pathspec arguments in many places to limit the
scope of an operation. These pathspecs are treated not as
literal paths, but as glob patterns that can be fed to
fnmatch. When a user is giving a specific pattern, this is a
nice feature.
However, when programatically providing pathspecs, it can be
a nuisance. For example, to find the latest revision which
modified "$foo", one can use "git rev-list -- $foo". But if
"$foo" contains glob characters (e.g., "f*"), it will
erroneously match more entries than desired. The caller
needs to quote the characters in $foo, and even then, the
results may not be exactly the same as with a literal
pathspec. For instance, the depth checks in
match_pathspec_depth do not kick in if we match via fnmatch.
This patch introduces a global command-line option (i.e.,
one for "git" itself, not for specific commands) to turn
this behavior off. It also has a matching environment
variable, which can make it easier if you are a script or
porcelain interface that is going to issue many such
commands.
This option cannot turn off globbing for particular
pathspecs. That could eventually be done with a ":(noglob)"
magic pathspec prefix. However, that level of granularity is
more cumbersome to use for many cases, and doing ":(noglob)"
right would mean converting the whole codebase to use
"struct pathspec", as the usual "const char **pathspec"
cannot represent extra per-item flags.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-12-20 06:37:30 +08:00
|
|
|
int literal = limit_pathspec_to_literal();
|
2006-05-20 07:07:51 +08:00
|
|
|
|
|
|
|
if (!pathspec)
|
2011-09-07 03:32:30 +08:00
|
|
|
return max;
|
|
|
|
|
|
|
|
first = *pathspec;
|
|
|
|
while ((n = *pathspec++)) {
|
|
|
|
size_t i, len = 0;
|
|
|
|
for (i = 0; first == n || i < max; i++) {
|
|
|
|
char c = n[i];
|
add global --literal-pathspecs option
Git takes pathspec arguments in many places to limit the
scope of an operation. These pathspecs are treated not as
literal paths, but as glob patterns that can be fed to
fnmatch. When a user is giving a specific pattern, this is a
nice feature.
However, when programatically providing pathspecs, it can be
a nuisance. For example, to find the latest revision which
modified "$foo", one can use "git rev-list -- $foo". But if
"$foo" contains glob characters (e.g., "f*"), it will
erroneously match more entries than desired. The caller
needs to quote the characters in $foo, and even then, the
results may not be exactly the same as with a literal
pathspec. For instance, the depth checks in
match_pathspec_depth do not kick in if we match via fnmatch.
This patch introduces a global command-line option (i.e.,
one for "git" itself, not for specific commands) to turn
this behavior off. It also has a matching environment
variable, which can make it easier if you are a script or
porcelain interface that is going to issue many such
commands.
This option cannot turn off globbing for particular
pathspecs. That could eventually be done with a ":(noglob)"
magic pathspec prefix. However, that level of granularity is
more cumbersome to use for many cases, and doing ":(noglob)"
right would mean converting the whole codebase to use
"struct pathspec", as the usual "const char **pathspec"
cannot represent extra per-item flags.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-12-20 06:37:30 +08:00
|
|
|
if (!c || c != first[i] || (!literal && is_glob_special(c)))
|
2011-09-07 03:32:30 +08:00
|
|
|
break;
|
|
|
|
if (c == '/')
|
|
|
|
len = i + 1;
|
|
|
|
}
|
|
|
|
if (first == n || len < max) {
|
|
|
|
max = len;
|
|
|
|
if (!max)
|
|
|
|
break;
|
|
|
|
}
|
2006-05-20 07:07:51 +08:00
|
|
|
}
|
2011-09-07 03:32:30 +08:00
|
|
|
return max;
|
2006-05-20 07:07:51 +08:00
|
|
|
}
|
|
|
|
|
2011-09-04 18:42:01 +08:00
|
|
|
/*
|
|
|
|
* Returns a copy of the longest leading path common among all
|
|
|
|
* pathspecs.
|
|
|
|
*/
|
|
|
|
char *common_prefix(const char **pathspec)
|
|
|
|
{
|
|
|
|
unsigned long len = common_prefix_len(pathspec);
|
|
|
|
|
|
|
|
return len ? xmemdupz(*pathspec, len) : NULL;
|
|
|
|
}
|
|
|
|
|
2009-05-15 04:22:36 +08:00
|
|
|
int fill_directory(struct dir_struct *dir, const char **pathspec)
|
|
|
|
{
|
2011-09-07 03:32:30 +08:00
|
|
|
size_t len;
|
2009-05-15 04:22:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Calculate common prefix for the pathspec, and
|
|
|
|
* use that to optimize the directory walk
|
|
|
|
*/
|
2011-09-07 03:32:30 +08:00
|
|
|
len = common_prefix_len(pathspec);
|
2009-05-15 04:22:36 +08:00
|
|
|
|
|
|
|
/* Read the directory and prune it */
|
2012-05-11 22:59:25 +08:00
|
|
|
read_directory(dir, pathspec ? *pathspec : "", len, pathspec);
|
2009-07-09 10:24:39 +08:00
|
|
|
return len;
|
2009-05-15 04:22:36 +08:00
|
|
|
}
|
|
|
|
|
2010-12-15 23:02:44 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2006-12-25 19:09:52 +08:00
|
|
|
/*
|
2009-05-05 01:37:30 +08:00
|
|
|
* Does 'match' match the given name?
|
2006-12-25 19:09:52 +08:00
|
|
|
* A match is found if
|
|
|
|
*
|
|
|
|
* (1) the 'match' string is leading directory of 'name', or
|
|
|
|
* (2) the 'match' string is a wildcard and matches 'name', or
|
|
|
|
* (3) the 'match' string is exactly the same as 'name'.
|
|
|
|
*
|
|
|
|
* and the return value tells which case it was.
|
|
|
|
*
|
|
|
|
* It returns 0 when there is no match.
|
|
|
|
*/
|
2006-05-20 07:07:51 +08:00
|
|
|
static int match_one(const char *match, const char *name, int namelen)
|
|
|
|
{
|
|
|
|
int matchlen;
|
add global --literal-pathspecs option
Git takes pathspec arguments in many places to limit the
scope of an operation. These pathspecs are treated not as
literal paths, but as glob patterns that can be fed to
fnmatch. When a user is giving a specific pattern, this is a
nice feature.
However, when programatically providing pathspecs, it can be
a nuisance. For example, to find the latest revision which
modified "$foo", one can use "git rev-list -- $foo". But if
"$foo" contains glob characters (e.g., "f*"), it will
erroneously match more entries than desired. The caller
needs to quote the characters in $foo, and even then, the
results may not be exactly the same as with a literal
pathspec. For instance, the depth checks in
match_pathspec_depth do not kick in if we match via fnmatch.
This patch introduces a global command-line option (i.e.,
one for "git" itself, not for specific commands) to turn
this behavior off. It also has a matching environment
variable, which can make it easier if you are a script or
porcelain interface that is going to issue many such
commands.
This option cannot turn off globbing for particular
pathspecs. That could eventually be done with a ":(noglob)"
magic pathspec prefix. However, that level of granularity is
more cumbersome to use for many cases, and doing ":(noglob)"
right would mean converting the whole codebase to use
"struct pathspec", as the usual "const char **pathspec"
cannot represent extra per-item flags.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-12-20 06:37:30 +08:00
|
|
|
int literal = limit_pathspec_to_literal();
|
2006-05-20 07:07:51 +08:00
|
|
|
|
|
|
|
/* If the match was just the prefix, we matched */
|
Optimize match_pathspec() to avoid fnmatch()
"git add *" is actually fundamentally different from "git add .", and
yeah, you should generally use the latter.
The reason? The argument list is actually something different from what
you think it is. For git, it's a "pathspec", so what actualy happens is
that in *both* cases, it will really traverse the whole tree, and then
match every file it finds against the pathspec.
So think of the arguments not as a file list, but as a random bunch of
patterns to match against the files you have!
Which is why the cost is actually approximately O(n*m), where "n" is the
size of the working tree, and "m" is the number of pathspecs.
So the reason "git add ." is fast is actually that "m" in that case is
just 1 (just one trivial pattern), and then "git add *" is slow because
"m" is large (lots of complicated patterns). In both cases, 'n' is the
same (== the whole set of files in your working tree).
Anyway, here's a trivial patch that doesn't change this fundamental fact,
but that avoids doing anything *expensive* until we've done some cheap
initial tests. It may or may not help your test-case, but it's pretty
simple and it matches the other git optimizations in this area (ie
"conceptually handle the general case, but optimize the simple cases where
we can exit early")
Notice how this patch doesn' actually change the fundamental O(n^2)
behaviour, but it makes it much cheaper by generally avoiding the
expensive 'fnmatch' and 'strlen/strncmp' when they are obviously not
needed.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-04-20 05:22:38 +08:00
|
|
|
if (!*match)
|
2006-12-25 19:09:52 +08:00
|
|
|
return MATCHED_RECURSIVELY;
|
2006-05-20 07:07:51 +08:00
|
|
|
|
2010-10-03 17:56:44 +08:00
|
|
|
if (ignore_case) {
|
|
|
|
for (;;) {
|
|
|
|
unsigned char c1 = tolower(*match);
|
|
|
|
unsigned char c2 = tolower(*name);
|
add global --literal-pathspecs option
Git takes pathspec arguments in many places to limit the
scope of an operation. These pathspecs are treated not as
literal paths, but as glob patterns that can be fed to
fnmatch. When a user is giving a specific pattern, this is a
nice feature.
However, when programatically providing pathspecs, it can be
a nuisance. For example, to find the latest revision which
modified "$foo", one can use "git rev-list -- $foo". But if
"$foo" contains glob characters (e.g., "f*"), it will
erroneously match more entries than desired. The caller
needs to quote the characters in $foo, and even then, the
results may not be exactly the same as with a literal
pathspec. For instance, the depth checks in
match_pathspec_depth do not kick in if we match via fnmatch.
This patch introduces a global command-line option (i.e.,
one for "git" itself, not for specific commands) to turn
this behavior off. It also has a matching environment
variable, which can make it easier if you are a script or
porcelain interface that is going to issue many such
commands.
This option cannot turn off globbing for particular
pathspecs. That could eventually be done with a ":(noglob)"
magic pathspec prefix. However, that level of granularity is
more cumbersome to use for many cases, and doing ":(noglob)"
right would mean converting the whole codebase to use
"struct pathspec", as the usual "const char **pathspec"
cannot represent extra per-item flags.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-12-20 06:37:30 +08:00
|
|
|
if (c1 == '\0' || (!literal && is_glob_special(c1)))
|
2010-10-03 17:56:44 +08:00
|
|
|
break;
|
|
|
|
if (c1 != c2)
|
|
|
|
return 0;
|
|
|
|
match++;
|
|
|
|
name++;
|
|
|
|
namelen--;
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
for (;;) {
|
|
|
|
unsigned char c1 = *match;
|
|
|
|
unsigned char c2 = *name;
|
add global --literal-pathspecs option
Git takes pathspec arguments in many places to limit the
scope of an operation. These pathspecs are treated not as
literal paths, but as glob patterns that can be fed to
fnmatch. When a user is giving a specific pattern, this is a
nice feature.
However, when programatically providing pathspecs, it can be
a nuisance. For example, to find the latest revision which
modified "$foo", one can use "git rev-list -- $foo". But if
"$foo" contains glob characters (e.g., "f*"), it will
erroneously match more entries than desired. The caller
needs to quote the characters in $foo, and even then, the
results may not be exactly the same as with a literal
pathspec. For instance, the depth checks in
match_pathspec_depth do not kick in if we match via fnmatch.
This patch introduces a global command-line option (i.e.,
one for "git" itself, not for specific commands) to turn
this behavior off. It also has a matching environment
variable, which can make it easier if you are a script or
porcelain interface that is going to issue many such
commands.
This option cannot turn off globbing for particular
pathspecs. That could eventually be done with a ":(noglob)"
magic pathspec prefix. However, that level of granularity is
more cumbersome to use for many cases, and doing ":(noglob)"
right would mean converting the whole codebase to use
"struct pathspec", as the usual "const char **pathspec"
cannot represent extra per-item flags.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-12-20 06:37:30 +08:00
|
|
|
if (c1 == '\0' || (!literal && is_glob_special(c1)))
|
2010-10-03 17:56:44 +08:00
|
|
|
break;
|
|
|
|
if (c1 != c2)
|
|
|
|
return 0;
|
|
|
|
match++;
|
|
|
|
name++;
|
|
|
|
namelen--;
|
|
|
|
}
|
Optimize match_pathspec() to avoid fnmatch()
"git add *" is actually fundamentally different from "git add .", and
yeah, you should generally use the latter.
The reason? The argument list is actually something different from what
you think it is. For git, it's a "pathspec", so what actualy happens is
that in *both* cases, it will really traverse the whole tree, and then
match every file it finds against the pathspec.
So think of the arguments not as a file list, but as a random bunch of
patterns to match against the files you have!
Which is why the cost is actually approximately O(n*m), where "n" is the
size of the working tree, and "m" is the number of pathspecs.
So the reason "git add ." is fast is actually that "m" in that case is
just 1 (just one trivial pattern), and then "git add *" is slow because
"m" is large (lots of complicated patterns). In both cases, 'n' is the
same (== the whole set of files in your working tree).
Anyway, here's a trivial patch that doesn't change this fundamental fact,
but that avoids doing anything *expensive* until we've done some cheap
initial tests. It may or may not help your test-case, but it's pretty
simple and it matches the other git optimizations in this area (ie
"conceptually handle the general case, but optimize the simple cases where
we can exit early")
Notice how this patch doesn' actually change the fundamental O(n^2)
behaviour, but it makes it much cheaper by generally avoiding the
expensive 'fnmatch' and 'strlen/strncmp' when they are obviously not
needed.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-04-20 05:22:38 +08:00
|
|
|
}
|
|
|
|
|
2006-05-20 07:07:51 +08:00
|
|
|
/*
|
|
|
|
* If we don't match the matchstring exactly,
|
|
|
|
* we need to match by fnmatch
|
|
|
|
*/
|
Optimize match_pathspec() to avoid fnmatch()
"git add *" is actually fundamentally different from "git add .", and
yeah, you should generally use the latter.
The reason? The argument list is actually something different from what
you think it is. For git, it's a "pathspec", so what actualy happens is
that in *both* cases, it will really traverse the whole tree, and then
match every file it finds against the pathspec.
So think of the arguments not as a file list, but as a random bunch of
patterns to match against the files you have!
Which is why the cost is actually approximately O(n*m), where "n" is the
size of the working tree, and "m" is the number of pathspecs.
So the reason "git add ." is fast is actually that "m" in that case is
just 1 (just one trivial pattern), and then "git add *" is slow because
"m" is large (lots of complicated patterns). In both cases, 'n' is the
same (== the whole set of files in your working tree).
Anyway, here's a trivial patch that doesn't change this fundamental fact,
but that avoids doing anything *expensive* until we've done some cheap
initial tests. It may or may not help your test-case, but it's pretty
simple and it matches the other git optimizations in this area (ie
"conceptually handle the general case, but optimize the simple cases where
we can exit early")
Notice how this patch doesn' actually change the fundamental O(n^2)
behaviour, but it makes it much cheaper by generally avoiding the
expensive 'fnmatch' and 'strlen/strncmp' when they are obviously not
needed.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-04-20 05:22:38 +08:00
|
|
|
matchlen = strlen(match);
|
add global --literal-pathspecs option
Git takes pathspec arguments in many places to limit the
scope of an operation. These pathspecs are treated not as
literal paths, but as glob patterns that can be fed to
fnmatch. When a user is giving a specific pattern, this is a
nice feature.
However, when programatically providing pathspecs, it can be
a nuisance. For example, to find the latest revision which
modified "$foo", one can use "git rev-list -- $foo". But if
"$foo" contains glob characters (e.g., "f*"), it will
erroneously match more entries than desired. The caller
needs to quote the characters in $foo, and even then, the
results may not be exactly the same as with a literal
pathspec. For instance, the depth checks in
match_pathspec_depth do not kick in if we match via fnmatch.
This patch introduces a global command-line option (i.e.,
one for "git" itself, not for specific commands) to turn
this behavior off. It also has a matching environment
variable, which can make it easier if you are a script or
porcelain interface that is going to issue many such
commands.
This option cannot turn off globbing for particular
pathspecs. That could eventually be done with a ":(noglob)"
magic pathspec prefix. However, that level of granularity is
more cumbersome to use for many cases, and doing ":(noglob)"
right would mean converting the whole codebase to use
"struct pathspec", as the usual "const char **pathspec"
cannot represent extra per-item flags.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-12-20 06:37:30 +08:00
|
|
|
if (strncmp_icase(match, name, matchlen)) {
|
|
|
|
if (literal)
|
|
|
|
return 0;
|
2010-10-03 17:56:44 +08:00
|
|
|
return !fnmatch_icase(match, name, 0) ? MATCHED_FNMATCH : 0;
|
add global --literal-pathspecs option
Git takes pathspec arguments in many places to limit the
scope of an operation. These pathspecs are treated not as
literal paths, but as glob patterns that can be fed to
fnmatch. When a user is giving a specific pattern, this is a
nice feature.
However, when programatically providing pathspecs, it can be
a nuisance. For example, to find the latest revision which
modified "$foo", one can use "git rev-list -- $foo". But if
"$foo" contains glob characters (e.g., "f*"), it will
erroneously match more entries than desired. The caller
needs to quote the characters in $foo, and even then, the
results may not be exactly the same as with a literal
pathspec. For instance, the depth checks in
match_pathspec_depth do not kick in if we match via fnmatch.
This patch introduces a global command-line option (i.e.,
one for "git" itself, not for specific commands) to turn
this behavior off. It also has a matching environment
variable, which can make it easier if you are a script or
porcelain interface that is going to issue many such
commands.
This option cannot turn off globbing for particular
pathspecs. That could eventually be done with a ":(noglob)"
magic pathspec prefix. However, that level of granularity is
more cumbersome to use for many cases, and doing ":(noglob)"
right would mean converting the whole codebase to use
"struct pathspec", as the usual "const char **pathspec"
cannot represent extra per-item flags.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-12-20 06:37:30 +08:00
|
|
|
}
|
2006-05-20 07:07:51 +08:00
|
|
|
|
2008-04-15 11:14:09 +08:00
|
|
|
if (namelen == matchlen)
|
2006-12-25 19:09:52 +08:00
|
|
|
return MATCHED_EXACTLY;
|
|
|
|
if (match[matchlen-1] == '/' || name[matchlen] == '/')
|
|
|
|
return MATCHED_RECURSIVELY;
|
|
|
|
return 0;
|
2006-05-20 07:07:51 +08:00
|
|
|
}
|
|
|
|
|
2006-12-25 19:09:52 +08:00
|
|
|
/*
|
2013-01-07 00:58:06 +08:00
|
|
|
* 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.
|
2006-12-25 19:09:52 +08:00
|
|
|
*/
|
2009-01-14 22:54:35 +08:00
|
|
|
int match_pathspec(const char **pathspec, const char *name, int namelen,
|
|
|
|
int prefix, char *seen)
|
2006-05-20 07:07:51 +08:00
|
|
|
{
|
2009-01-14 22:54:35 +08:00
|
|
|
int i, retval = 0;
|
|
|
|
|
|
|
|
if (!pathspec)
|
|
|
|
return 1;
|
2006-05-20 07:07:51 +08:00
|
|
|
|
|
|
|
name += prefix;
|
|
|
|
namelen -= prefix;
|
|
|
|
|
2009-01-14 22:54:35 +08:00
|
|
|
for (i = 0; pathspec[i] != NULL; i++) {
|
2006-12-25 19:09:52 +08:00
|
|
|
int how;
|
2009-01-14 22:54:35 +08:00
|
|
|
const char *match = pathspec[i] + prefix;
|
|
|
|
if (seen && seen[i] == MATCHED_EXACTLY)
|
2006-05-20 07:07:51 +08:00
|
|
|
continue;
|
2006-12-25 19:09:52 +08:00
|
|
|
how = match_one(match, name, namelen);
|
|
|
|
if (how) {
|
|
|
|
if (retval < how)
|
|
|
|
retval = how;
|
2009-01-14 22:54:35 +08:00
|
|
|
if (seen && seen[i] < how)
|
|
|
|
seen[i] = how;
|
2006-05-20 07:07:51 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
return retval;
|
|
|
|
}
|
|
|
|
|
2010-12-15 23:02:48 +08:00
|
|
|
/*
|
|
|
|
* Does 'match' match the given name?
|
|
|
|
* A match is found if
|
|
|
|
*
|
|
|
|
* (1) the 'match' string is leading directory of 'name', or
|
|
|
|
* (2) the 'match' string is a wildcard and matches 'name', or
|
|
|
|
* (3) the 'match' string is exactly the same as 'name'.
|
|
|
|
*
|
|
|
|
* and the return value tells which case it was.
|
|
|
|
*
|
|
|
|
* It returns 0 when there is no match.
|
|
|
|
*/
|
|
|
|
static int match_pathspec_item(const struct pathspec_item *item, int prefix,
|
|
|
|
const char *name, int namelen)
|
|
|
|
{
|
|
|
|
/* name/namelen has prefix cut off by caller */
|
|
|
|
const char *match = item->match + prefix;
|
|
|
|
int matchlen = item->len - prefix;
|
|
|
|
|
|
|
|
/* If the match was just the prefix, we matched */
|
|
|
|
if (!*match)
|
|
|
|
return MATCHED_RECURSIVELY;
|
|
|
|
|
|
|
|
if (matchlen <= namelen && !strncmp(match, name, matchlen)) {
|
|
|
|
if (matchlen == namelen)
|
|
|
|
return MATCHED_EXACTLY;
|
|
|
|
|
|
|
|
if (match[matchlen-1] == '/' || name[matchlen] == '/')
|
|
|
|
return MATCHED_RECURSIVELY;
|
|
|
|
}
|
|
|
|
|
2012-11-24 12:33:49 +08:00
|
|
|
if (item->nowildcard_len < item->len &&
|
2012-11-24 12:33:50 +08:00
|
|
|
!git_fnmatch(match, name,
|
|
|
|
item->flags & PATHSPEC_ONESTAR ? GFNM_ONESTAR : 0,
|
|
|
|
item->nowildcard_len - prefix))
|
2010-12-15 23:02:48 +08:00
|
|
|
return MATCHED_FNMATCH;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2013-01-07 00:58:06 +08:00
|
|
|
* 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.
|
2010-12-15 23:02:48 +08:00
|
|
|
*/
|
|
|
|
int match_pathspec_depth(const struct pathspec *ps,
|
|
|
|
const char *name, int namelen,
|
|
|
|
int prefix, char *seen)
|
|
|
|
{
|
|
|
|
int i, retval = 0;
|
|
|
|
|
|
|
|
if (!ps->nr) {
|
|
|
|
if (!ps->recursive || 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 (seen && seen[i] == MATCHED_EXACTLY)
|
|
|
|
continue;
|
|
|
|
how = match_pathspec_item(ps->items+i, prefix, name, namelen);
|
|
|
|
if (ps->recursive && 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;
|
|
|
|
}
|
|
|
|
|
2012-06-07 15:53:35 +08:00
|
|
|
/*
|
|
|
|
* Return the length of the "simple" part of a path match limiter.
|
|
|
|
*/
|
|
|
|
static int simple_length(const char *match)
|
|
|
|
{
|
|
|
|
int len = -1;
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
unsigned char c = *match++;
|
|
|
|
len++;
|
|
|
|
if (c == '\0' || is_glob_special(c))
|
|
|
|
return len;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2007-10-29 04:27:13 +08:00
|
|
|
static int no_wildcard(const char *string)
|
|
|
|
{
|
2012-06-07 15:53:35 +08:00
|
|
|
return string[simple_length(string)] == '\0';
|
2007-10-29 04:27:13 +08:00
|
|
|
}
|
|
|
|
|
2012-10-15 14:24:39 +08:00
|
|
|
void parse_exclude_pattern(const char **pattern,
|
|
|
|
int *patternlen,
|
|
|
|
int *flags,
|
|
|
|
int *nowildcardlen)
|
2012-10-15 14:24:38 +08:00
|
|
|
{
|
|
|
|
const char *p = *pattern;
|
|
|
|
size_t i, len;
|
|
|
|
|
|
|
|
*flags = 0;
|
|
|
|
if (*p == '!') {
|
|
|
|
*flags |= EXC_FLAG_NEGATIVE;
|
|
|
|
p++;
|
|
|
|
}
|
|
|
|
len = strlen(p);
|
|
|
|
if (len && p[len - 1] == '/') {
|
|
|
|
len--;
|
|
|
|
*flags |= EXC_FLAG_MUSTBEDIR;
|
|
|
|
}
|
|
|
|
for (i = 0; i < len; i++) {
|
|
|
|
if (p[i] == '/')
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (i == len)
|
|
|
|
*flags |= EXC_FLAG_NODIR;
|
|
|
|
*nowildcardlen = simple_length(p);
|
|
|
|
/*
|
|
|
|
* we should have excluded the trailing slash from 'p' too,
|
|
|
|
* but that's one more allocation. Instead just make sure
|
|
|
|
* nowildcardlen does not exceed real patternlen
|
|
|
|
*/
|
|
|
|
if (*nowildcardlen > len)
|
|
|
|
*nowildcardlen = len;
|
|
|
|
if (*p == '*' && no_wildcard(p + 1))
|
|
|
|
*flags |= EXC_FLAG_ENDSWITH;
|
|
|
|
*pattern = p;
|
|
|
|
*patternlen = len;
|
|
|
|
}
|
|
|
|
|
2006-05-17 10:02:14 +08:00
|
|
|
void add_exclude(const char *string, const char *base,
|
2013-01-07 00:58:04 +08:00
|
|
|
int baselen, struct exclude_list *el, int srcpos)
|
2006-05-17 10:02:14 +08:00
|
|
|
{
|
2008-01-31 17:17:48 +08:00
|
|
|
struct exclude *x;
|
2012-10-15 14:24:38 +08:00
|
|
|
int patternlen;
|
|
|
|
int flags;
|
|
|
|
int nowildcardlen;
|
2006-05-17 10:02:14 +08:00
|
|
|
|
2012-10-15 14:24:38 +08:00
|
|
|
parse_exclude_pattern(&string, &patternlen, &flags, &nowildcardlen);
|
|
|
|
if (flags & EXC_FLAG_MUSTBEDIR) {
|
2008-01-31 17:17:48 +08:00
|
|
|
char *s;
|
2012-10-15 14:24:38 +08:00
|
|
|
x = xmalloc(sizeof(*x) + patternlen + 1);
|
2009-05-01 17:06:36 +08:00
|
|
|
s = (char *)(x+1);
|
2012-10-15 14:24:38 +08:00
|
|
|
memcpy(s, string, patternlen);
|
|
|
|
s[patternlen] = '\0';
|
2008-01-31 17:17:48 +08:00
|
|
|
x->pattern = s;
|
|
|
|
} else {
|
|
|
|
x = xmalloc(sizeof(*x));
|
|
|
|
x->pattern = string;
|
|
|
|
}
|
2012-10-15 14:24:38 +08:00
|
|
|
x->patternlen = patternlen;
|
|
|
|
x->nowildcardlen = nowildcardlen;
|
2006-05-17 10:02:14 +08:00
|
|
|
x->base = base;
|
|
|
|
x->baselen = baselen;
|
2008-01-31 17:17:48 +08:00
|
|
|
x->flags = flags;
|
2013-01-07 00:58:04 +08:00
|
|
|
x->srcpos = srcpos;
|
2012-12-27 10:32:22 +08:00
|
|
|
ALLOC_GROW(el->excludes, el->nr + 1, el->alloc);
|
|
|
|
el->excludes[el->nr++] = x;
|
2013-01-07 00:58:04 +08:00
|
|
|
x->el = el;
|
2006-05-17 10:02:14 +08:00
|
|
|
}
|
|
|
|
|
2009-08-20 21:47:01 +08:00
|
|
|
static void *read_skip_worktree_file_from_index(const char *path, size_t *size)
|
|
|
|
{
|
|
|
|
int pos, len;
|
|
|
|
unsigned long sz;
|
|
|
|
enum object_type type;
|
|
|
|
void *data;
|
|
|
|
struct index_state *istate = &the_index;
|
|
|
|
|
|
|
|
len = strlen(path);
|
|
|
|
pos = index_name_pos(istate, path, len);
|
|
|
|
if (pos < 0)
|
|
|
|
return NULL;
|
|
|
|
if (!ce_skip_worktree(istate->cache[pos]))
|
|
|
|
return NULL;
|
|
|
|
data = read_sha1_file(istate->cache[pos]->sha1, &type, &sz);
|
|
|
|
if (!data || type != OBJ_BLOB) {
|
|
|
|
free(data);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
*size = xsize_t(sz);
|
|
|
|
return data;
|
|
|
|
}
|
|
|
|
|
2012-12-27 10:32:29 +08:00
|
|
|
/*
|
|
|
|
* Frees memory within el which was allocated for exclude patterns and
|
|
|
|
* the file buffer. Does not free el itself.
|
|
|
|
*/
|
|
|
|
void clear_exclude_list(struct exclude_list *el)
|
2010-11-27 02:17:44 +08:00
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; i < el->nr; i++)
|
|
|
|
free(el->excludes[i]);
|
|
|
|
free(el->excludes);
|
2013-01-07 00:58:03 +08:00
|
|
|
free(el->filebuf);
|
2010-11-27 02:17:44 +08:00
|
|
|
|
|
|
|
el->nr = 0;
|
|
|
|
el->excludes = NULL;
|
2013-01-07 00:58:03 +08:00
|
|
|
el->filebuf = NULL;
|
2010-11-27 02:17:44 +08:00
|
|
|
}
|
|
|
|
|
2009-08-20 21:47:04 +08:00
|
|
|
int add_excludes_from_file_to_list(const char *fname,
|
|
|
|
const char *base,
|
|
|
|
int baselen,
|
2012-12-27 10:32:22 +08:00
|
|
|
struct exclude_list *el,
|
2009-08-20 21:47:04 +08:00
|
|
|
int check_index)
|
2006-05-17 10:02:14 +08:00
|
|
|
{
|
2006-08-28 07:55:46 +08:00
|
|
|
struct stat st;
|
2013-01-07 00:58:04 +08:00
|
|
|
int fd, i, lineno = 1;
|
2010-09-17 04:53:22 +08:00
|
|
|
size_t size = 0;
|
2006-05-17 10:02:14 +08:00
|
|
|
char *buf, *entry;
|
|
|
|
|
|
|
|
fd = open(fname, O_RDONLY);
|
2009-08-20 21:47:01 +08:00
|
|
|
if (fd < 0 || fstat(fd, &st) < 0) {
|
2012-08-21 14:26:07 +08:00
|
|
|
if (errno != ENOENT)
|
2012-08-22 05:52:07 +08:00
|
|
|
warn_on_inaccessible(fname);
|
2009-08-20 21:47:01 +08:00
|
|
|
if (0 <= fd)
|
|
|
|
close(fd);
|
|
|
|
if (!check_index ||
|
|
|
|
(buf = read_skip_worktree_file_from_index(fname, &size)) == NULL)
|
|
|
|
return -1;
|
2010-01-20 22:09:16 +08:00
|
|
|
if (size == 0) {
|
|
|
|
free(buf);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
if (buf[size-1] != '\n') {
|
|
|
|
buf = xrealloc(buf, size+1);
|
|
|
|
buf[size++] = '\n';
|
|
|
|
}
|
2006-05-17 10:02:14 +08:00
|
|
|
}
|
2009-08-20 21:47:01 +08:00
|
|
|
else {
|
|
|
|
size = xsize_t(st.st_size);
|
|
|
|
if (size == 0) {
|
|
|
|
close(fd);
|
|
|
|
return 0;
|
|
|
|
}
|
2010-01-20 22:09:16 +08:00
|
|
|
buf = xmalloc(size+1);
|
2009-08-20 21:47:01 +08:00
|
|
|
if (read_in_full(fd, buf, size) != size) {
|
2010-01-20 22:09:16 +08:00
|
|
|
free(buf);
|
2009-08-20 21:47:01 +08:00
|
|
|
close(fd);
|
|
|
|
return -1;
|
|
|
|
}
|
2010-01-20 22:09:16 +08:00
|
|
|
buf[size++] = '\n';
|
2009-08-20 21:47:01 +08:00
|
|
|
close(fd);
|
2007-12-16 12:53:26 +08:00
|
|
|
}
|
2006-05-17 10:02:14 +08:00
|
|
|
|
2013-01-07 00:58:03 +08:00
|
|
|
el->filebuf = buf;
|
2006-05-17 10:02:14 +08:00
|
|
|
entry = buf;
|
2010-01-20 22:09:16 +08:00
|
|
|
for (i = 0; i < size; i++) {
|
|
|
|
if (buf[i] == '\n') {
|
2006-05-17 10:02:14 +08:00
|
|
|
if (entry != buf + i && entry[0] != '#') {
|
|
|
|
buf[i - (i && buf[i-1] == '\r')] = 0;
|
2013-01-07 00:58:04 +08:00
|
|
|
add_exclude(entry, base, baselen, el, lineno);
|
2006-05-17 10:02:14 +08:00
|
|
|
}
|
2013-01-07 00:58:04 +08:00
|
|
|
lineno++;
|
2006-05-17 10:02:14 +08:00
|
|
|
entry = buf + i + 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2013-01-07 00:58:04 +08:00
|
|
|
struct exclude_list *add_exclude_list(struct dir_struct *dir,
|
|
|
|
int group_type, const char *src)
|
2013-01-07 00:58:03 +08:00
|
|
|
{
|
|
|
|
struct exclude_list *el;
|
|
|
|
struct exclude_list_group *group;
|
|
|
|
|
|
|
|
group = &dir->exclude_list_group[group_type];
|
|
|
|
ALLOC_GROW(group->el, group->nr + 1, group->alloc);
|
|
|
|
el = &group->el[group->nr++];
|
|
|
|
memset(el, 0, sizeof(*el));
|
2013-01-07 00:58:04 +08:00
|
|
|
el->src = src;
|
2013-01-07 00:58:03 +08:00
|
|
|
return el;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Used to set up core.excludesfile and .git/info/exclude lists.
|
|
|
|
*/
|
2006-05-17 10:02:14 +08:00
|
|
|
void add_excludes_from_file(struct dir_struct *dir, const char *fname)
|
|
|
|
{
|
2013-01-07 00:58:03 +08:00
|
|
|
struct exclude_list *el;
|
2013-01-07 00:58:04 +08:00
|
|
|
el = add_exclude_list(dir, EXC_FILE, fname);
|
2013-01-07 00:58:03 +08:00
|
|
|
if (add_excludes_from_file_to_list(fname, "", 0, el, 0) < 0)
|
2006-05-17 10:02:14 +08:00
|
|
|
die("cannot use %s as an exclude file", fname);
|
|
|
|
}
|
|
|
|
|
2012-12-27 10:32:21 +08:00
|
|
|
/*
|
|
|
|
* Loads the per-directory exclude list for the substring of base
|
|
|
|
* which has a char length of baselen.
|
|
|
|
*/
|
2007-11-29 18:17:44 +08:00
|
|
|
static void prep_exclude(struct dir_struct *dir, const char *base, int baselen)
|
2006-05-17 10:02:14 +08:00
|
|
|
{
|
2013-01-07 00:58:03 +08:00
|
|
|
struct exclude_list_group *group;
|
2007-11-29 18:17:44 +08:00
|
|
|
struct exclude_list *el;
|
|
|
|
struct exclude_stack *stk = NULL;
|
|
|
|
int current;
|
|
|
|
|
|
|
|
if ((!dir->exclude_per_dir) ||
|
|
|
|
(baselen + strlen(dir->exclude_per_dir) >= PATH_MAX))
|
|
|
|
return; /* too long a path -- ignore */
|
|
|
|
|
2013-01-07 00:58:03 +08:00
|
|
|
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. */
|
2007-11-29 18:17:44 +08:00
|
|
|
while ((stk = dir->exclude_stack) != NULL) {
|
|
|
|
if (stk->baselen <= baselen &&
|
|
|
|
!strncmp(dir->basebuf, base, stk->baselen))
|
|
|
|
break;
|
2013-01-07 00:58:03 +08:00
|
|
|
el = &group->el[dir->exclude_stack->exclude_ix];
|
2007-11-29 18:17:44 +08:00
|
|
|
dir->exclude_stack = stk->prev;
|
2013-01-07 00:58:04 +08:00
|
|
|
free((char *)el->src); /* see strdup() below */
|
2013-01-07 00:58:03 +08:00
|
|
|
clear_exclude_list(el);
|
2007-11-29 18:17:44 +08:00
|
|
|
free(stk);
|
2013-01-07 00:58:03 +08:00
|
|
|
group->nr--;
|
2006-05-17 10:02:14 +08:00
|
|
|
}
|
|
|
|
|
2007-11-29 18:17:44 +08:00
|
|
|
/* Read from the parent directories and push them down. */
|
|
|
|
current = stk ? stk->baselen : -1;
|
|
|
|
while (current < baselen) {
|
|
|
|
struct exclude_stack *stk = xcalloc(1, sizeof(*stk));
|
|
|
|
const char *cp;
|
2006-05-17 10:02:14 +08:00
|
|
|
|
2007-11-29 18:17:44 +08:00
|
|
|
if (current < 0) {
|
|
|
|
cp = base;
|
|
|
|
current = 0;
|
|
|
|
}
|
|
|
|
else {
|
|
|
|
cp = strchr(base + current + 1, '/');
|
|
|
|
if (!cp)
|
|
|
|
die("oops in prep_exclude");
|
|
|
|
cp++;
|
|
|
|
}
|
|
|
|
stk->prev = dir->exclude_stack;
|
|
|
|
stk->baselen = cp - base;
|
|
|
|
memcpy(dir->basebuf + current, base + current,
|
|
|
|
stk->baselen - current);
|
|
|
|
strcpy(dir->basebuf + stk->baselen, dir->exclude_per_dir);
|
2013-01-07 00:58:04 +08:00
|
|
|
/*
|
|
|
|
* dir->basebuf gets reused by the traversal, but we
|
|
|
|
* need fname to remain unchanged to ensure the src
|
|
|
|
* member of each struct exclude correctly
|
|
|
|
* back-references its source file. Other invocations
|
|
|
|
* of add_exclude_list provide stable strings, so we
|
|
|
|
* strdup() and free() here in the caller.
|
|
|
|
*/
|
|
|
|
el = add_exclude_list(dir, EXC_DIRS, strdup(dir->basebuf));
|
2013-01-07 00:58:03 +08:00
|
|
|
stk->exclude_ix = group->nr - 1;
|
2009-08-20 21:47:04 +08:00
|
|
|
add_excludes_from_file_to_list(dir->basebuf,
|
|
|
|
dir->basebuf, stk->baselen,
|
2013-01-07 00:58:03 +08:00
|
|
|
el, 1);
|
2007-11-29 18:17:44 +08:00
|
|
|
dir->exclude_stack = stk;
|
|
|
|
current = stk->baselen;
|
|
|
|
}
|
|
|
|
dir->basebuf[baselen] = '\0';
|
2006-05-17 10:02:14 +08:00
|
|
|
}
|
|
|
|
|
2012-10-15 14:24:39 +08:00
|
|
|
int match_basename(const char *basename, int basenamelen,
|
|
|
|
const char *pattern, int prefix, int patternlen,
|
|
|
|
int flags)
|
2012-10-15 14:24:35 +08:00
|
|
|
{
|
|
|
|
if (prefix == patternlen) {
|
dir.c::match_basename(): pay attention to the length of string parameters
The function takes two counted strings (<basename, basenamelen> and
<pattern, patternlen>) as parameters, together with prefix (the
length of the prefix in pattern that is to be matched literally
without globbing against the basename) and EXC_* flags that tells it
how to match the pattern against the basename.
However, it did not pay attention to the length of these counted
strings. Update them to do the following:
* When the entire pattern is to be matched literally, the pattern
matches the basename only when the lengths of them are the same,
and they match up to that length.
* When the pattern is "*" followed by a string to be matched
literally, make sure that the basenamelen is equal or longer than
the "literal" part of the pattern, and the tail of the basename
string matches that literal part.
* Otherwise, use the new fnmatch_icase_mem helper to make
sure we only lookmake sure we use only look at the
counted part of the strings. Because these counted strings are
full strings most of the time, we check for termination
to avoid unnecessary allocation.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-29 05:47:28 +08:00
|
|
|
if (patternlen == basenamelen &&
|
|
|
|
!strncmp_icase(pattern, basename, basenamelen))
|
2012-10-15 14:24:35 +08:00
|
|
|
return 1;
|
|
|
|
} else if (flags & EXC_FLAG_ENDSWITH) {
|
dir.c::match_basename(): pay attention to the length of string parameters
The function takes two counted strings (<basename, basenamelen> and
<pattern, patternlen>) as parameters, together with prefix (the
length of the prefix in pattern that is to be matched literally
without globbing against the basename) and EXC_* flags that tells it
how to match the pattern against the basename.
However, it did not pay attention to the length of these counted
strings. Update them to do the following:
* When the entire pattern is to be matched literally, the pattern
matches the basename only when the lengths of them are the same,
and they match up to that length.
* When the pattern is "*" followed by a string to be matched
literally, make sure that the basenamelen is equal or longer than
the "literal" part of the pattern, and the tail of the basename
string matches that literal part.
* Otherwise, use the new fnmatch_icase_mem helper to make
sure we only lookmake sure we use only look at the
counted part of the strings. Because these counted strings are
full strings most of the time, we check for termination
to avoid unnecessary allocation.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-29 05:47:28 +08:00
|
|
|
/* "*literal" matching against "fooliteral" */
|
2012-10-15 14:24:35 +08:00
|
|
|
if (patternlen - 1 <= basenamelen &&
|
dir.c::match_basename(): pay attention to the length of string parameters
The function takes two counted strings (<basename, basenamelen> and
<pattern, patternlen>) as parameters, together with prefix (the
length of the prefix in pattern that is to be matched literally
without globbing against the basename) and EXC_* flags that tells it
how to match the pattern against the basename.
However, it did not pay attention to the length of these counted
strings. Update them to do the following:
* When the entire pattern is to be matched literally, the pattern
matches the basename only when the lengths of them are the same,
and they match up to that length.
* When the pattern is "*" followed by a string to be matched
literally, make sure that the basenamelen is equal or longer than
the "literal" part of the pattern, and the tail of the basename
string matches that literal part.
* Otherwise, use the new fnmatch_icase_mem helper to make
sure we only lookmake sure we use only look at the
counted part of the strings. Because these counted strings are
full strings most of the time, we check for termination
to avoid unnecessary allocation.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-29 05:47:28 +08:00
|
|
|
!strncmp_icase(pattern + 1,
|
|
|
|
basename + basenamelen - (patternlen - 1),
|
|
|
|
patternlen - 1))
|
2012-10-15 14:24:35 +08:00
|
|
|
return 1;
|
|
|
|
} else {
|
dir.c::match_basename(): pay attention to the length of string parameters
The function takes two counted strings (<basename, basenamelen> and
<pattern, patternlen>) as parameters, together with prefix (the
length of the prefix in pattern that is to be matched literally
without globbing against the basename) and EXC_* flags that tells it
how to match the pattern against the basename.
However, it did not pay attention to the length of these counted
strings. Update them to do the following:
* When the entire pattern is to be matched literally, the pattern
matches the basename only when the lengths of them are the same,
and they match up to that length.
* When the pattern is "*" followed by a string to be matched
literally, make sure that the basenamelen is equal or longer than
the "literal" part of the pattern, and the tail of the basename
string matches that literal part.
* Otherwise, use the new fnmatch_icase_mem helper to make
sure we only lookmake sure we use only look at the
counted part of the strings. Because these counted strings are
full strings most of the time, we check for termination
to avoid unnecessary allocation.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-29 05:47:28 +08:00
|
|
|
if (fnmatch_icase_mem(pattern, patternlen,
|
|
|
|
basename, basenamelen,
|
|
|
|
0) == 0)
|
2012-10-15 14:24:35 +08:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2012-10-15 14:24:39 +08:00
|
|
|
int match_pathname(const char *pathname, int pathlen,
|
|
|
|
const char *base, int baselen,
|
|
|
|
const char *pattern, int prefix, int patternlen,
|
|
|
|
int flags)
|
2012-10-15 14:24:37 +08:00
|
|
|
{
|
|
|
|
const char *name;
|
|
|
|
int namelen;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* match with FNM_PATHNAME; the pattern has base implicitly
|
|
|
|
* in front of it.
|
|
|
|
*/
|
|
|
|
if (*pattern == '/') {
|
|
|
|
pattern++;
|
2013-03-29 05:47:47 +08:00
|
|
|
patternlen--;
|
2012-10-15 14:24:37 +08:00
|
|
|
prefix--;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* baselen does not count the trailing slash. base[] may or
|
|
|
|
* may not end with a trailing slash though.
|
|
|
|
*/
|
|
|
|
if (pathlen < baselen + 1 ||
|
|
|
|
(baselen && pathname[baselen] != '/') ||
|
|
|
|
strncmp_icase(pathname, base, baselen))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
namelen = baselen ? pathlen - baselen - 1 : pathlen;
|
|
|
|
name = pathname + pathlen - namelen;
|
|
|
|
|
|
|
|
if (prefix) {
|
|
|
|
/*
|
|
|
|
* if the non-wildcard part is longer than the
|
|
|
|
* remaining pathname, surely it cannot match.
|
|
|
|
*/
|
|
|
|
if (prefix > namelen)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if (strncmp_icase(pattern, name, prefix))
|
|
|
|
return 0;
|
|
|
|
pattern += prefix;
|
2013-03-29 05:48:21 +08:00
|
|
|
patternlen -= prefix;
|
2012-10-15 14:24:37 +08:00
|
|
|
name += prefix;
|
|
|
|
namelen -= prefix;
|
2013-03-29 05:48:21 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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;
|
2012-10-15 14:24:37 +08:00
|
|
|
}
|
|
|
|
|
2013-03-29 05:48:21 +08:00
|
|
|
return fnmatch_icase_mem(pattern, patternlen,
|
|
|
|
name, namelen,
|
2013-04-04 00:34:04 +08:00
|
|
|
WM_PATHNAME) == 0;
|
2012-10-15 14:24:37 +08:00
|
|
|
}
|
|
|
|
|
2012-12-27 10:32:26 +08:00
|
|
|
/*
|
|
|
|
* 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.
|
2006-05-17 10:02:14 +08:00
|
|
|
*/
|
2012-12-27 10:32:26 +08:00
|
|
|
static struct exclude *last_exclude_matching_from_list(const char *pathname,
|
|
|
|
int pathlen,
|
|
|
|
const char *basename,
|
|
|
|
int *dtype,
|
|
|
|
struct exclude_list *el)
|
2006-05-17 10:02:14 +08:00
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
2012-05-26 20:31:12 +08:00
|
|
|
if (!el->nr)
|
2012-12-27 10:32:26 +08:00
|
|
|
return NULL; /* undefined */
|
2008-01-31 17:17:48 +08:00
|
|
|
|
2012-05-26 20:31:12 +08:00
|
|
|
for (i = el->nr - 1; 0 <= i; i--) {
|
|
|
|
struct exclude *x = el->excludes[i];
|
2012-10-15 14:24:37 +08:00
|
|
|
const char *exclude = x->pattern;
|
|
|
|
int prefix = x->nowildcardlen;
|
2012-05-26 20:31:12 +08:00
|
|
|
|
|
|
|
if (x->flags & EXC_FLAG_MUSTBEDIR) {
|
|
|
|
if (*dtype == DT_UNKNOWN)
|
|
|
|
*dtype = get_dtype(NULL, pathname, pathlen);
|
|
|
|
if (*dtype != DT_DIR)
|
|
|
|
continue;
|
|
|
|
}
|
2008-01-31 17:17:48 +08:00
|
|
|
|
2012-05-26 20:31:12 +08:00
|
|
|
if (x->flags & EXC_FLAG_NODIR) {
|
2012-10-15 14:24:35 +08:00
|
|
|
if (match_basename(basename,
|
|
|
|
pathlen - (basename - pathname),
|
|
|
|
exclude, prefix, x->patternlen,
|
|
|
|
x->flags))
|
2012-12-27 10:32:26 +08:00
|
|
|
return x;
|
2012-05-26 20:31:12 +08:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2012-10-15 14:24:37 +08:00
|
|
|
assert(x->baselen == 0 || x->base[x->baselen - 1] == '/');
|
|
|
|
if (match_pathname(pathname, pathlen,
|
|
|
|
x->base, x->baselen ? x->baselen - 1 : 0,
|
|
|
|
exclude, prefix, x->patternlen, x->flags))
|
2012-12-27 10:32:26 +08:00
|
|
|
return x;
|
2006-05-17 10:02:14 +08:00
|
|
|
}
|
2012-12-27 10:32:26 +08:00
|
|
|
return NULL; /* undecided */
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Scan the list and let the last match determine the fate.
|
|
|
|
* Return 1 for exclude, 0 for include and -1 for undecided.
|
|
|
|
*/
|
|
|
|
int is_excluded_from_list(const char *pathname,
|
|
|
|
int pathlen, const char *basename, int *dtype,
|
|
|
|
struct exclude_list *el)
|
|
|
|
{
|
|
|
|
struct exclude *exclude;
|
|
|
|
exclude = last_exclude_matching_from_list(pathname, pathlen, basename, dtype, el);
|
|
|
|
if (exclude)
|
|
|
|
return exclude->flags & EXC_FLAG_NEGATIVE ? 0 : 1;
|
2006-05-17 10:02:14 +08:00
|
|
|
return -1; /* undecided */
|
|
|
|
}
|
|
|
|
|
2012-12-27 10:32:27 +08:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
|
|
|
static struct exclude *last_exclude_matching(struct dir_struct *dir,
|
|
|
|
const char *pathname,
|
|
|
|
int *dtype_p)
|
2006-05-17 10:02:14 +08:00
|
|
|
{
|
|
|
|
int pathlen = strlen(pathname);
|
2013-01-07 00:58:03 +08:00
|
|
|
int i, j;
|
|
|
|
struct exclude_list_group *group;
|
2012-12-27 10:32:27 +08:00
|
|
|
struct exclude *exclude;
|
2007-10-29 04:27:13 +08:00
|
|
|
const char *basename = strrchr(pathname, '/');
|
|
|
|
basename = (basename) ? basename+1 : pathname;
|
2006-05-17 10:02:14 +08:00
|
|
|
|
2007-11-29 18:17:44 +08:00
|
|
|
prep_exclude(dir, pathname, basename-pathname);
|
2013-01-07 00:58:03 +08:00
|
|
|
|
|
|
|
for (i = EXC_CMDL; i <= EXC_FILE; i++) {
|
|
|
|
group = &dir->exclude_list_group[i];
|
|
|
|
for (j = group->nr - 1; j >= 0; j--) {
|
|
|
|
exclude = last_exclude_matching_from_list(
|
|
|
|
pathname, pathlen, basename, dtype_p,
|
|
|
|
&group->el[j]);
|
|
|
|
if (exclude)
|
|
|
|
return exclude;
|
|
|
|
}
|
2006-05-17 10:02:14 +08:00
|
|
|
}
|
2012-12-27 10:32:27 +08:00
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
|
|
|
static int is_excluded(struct dir_struct *dir, const char *pathname, int *dtype_p)
|
|
|
|
{
|
|
|
|
struct exclude *exclude =
|
|
|
|
last_exclude_matching(dir, pathname, dtype_p);
|
|
|
|
if (exclude)
|
|
|
|
return exclude->flags & EXC_FLAG_NEGATIVE ? 0 : 1;
|
2006-05-17 10:02:14 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2012-06-02 02:28:00 +08:00
|
|
|
void path_exclude_check_init(struct path_exclude_check *check,
|
|
|
|
struct dir_struct *dir)
|
|
|
|
{
|
|
|
|
check->dir = dir;
|
2012-12-27 10:32:28 +08:00
|
|
|
check->exclude = NULL;
|
2012-06-02 02:28:00 +08:00
|
|
|
strbuf_init(&check->path, 256);
|
|
|
|
}
|
|
|
|
|
|
|
|
void path_exclude_check_clear(struct path_exclude_check *check)
|
|
|
|
{
|
|
|
|
strbuf_release(&check->path);
|
|
|
|
}
|
|
|
|
|
2012-06-02 03:22:09 +08:00
|
|
|
/*
|
2012-12-27 10:32:28 +08:00
|
|
|
* For each subdirectory in name, starting with the top-most, checks
|
|
|
|
* to see if that subdirectory is excluded, and if so, returns the
|
|
|
|
* corresponding exclude structure. Otherwise, checks whether name
|
|
|
|
* itself (which is presumably a file) is excluded.
|
2012-06-02 03:22:09 +08:00
|
|
|
*
|
|
|
|
* A path to a directory known to be excluded is left in check->path to
|
|
|
|
* optimize for repeated checks for files in the same excluded directory.
|
|
|
|
*/
|
2012-12-27 10:32:28 +08:00
|
|
|
struct exclude *last_exclude_matching_path(struct path_exclude_check *check,
|
|
|
|
const char *name, int namelen,
|
|
|
|
int *dtype)
|
2012-06-02 02:28:00 +08:00
|
|
|
{
|
2012-06-06 12:17:52 +08:00
|
|
|
int i;
|
2012-06-02 02:28:00 +08:00
|
|
|
struct strbuf *path = &check->path;
|
2012-12-27 10:32:28 +08:00
|
|
|
struct exclude *exclude;
|
2012-06-02 02:28:00 +08:00
|
|
|
|
2012-06-06 12:17:52 +08:00
|
|
|
/*
|
|
|
|
* we allow the caller to pass namelen as an optimization; it
|
|
|
|
* must match the length of the name, as we eventually call
|
2012-12-27 10:32:25 +08:00
|
|
|
* is_excluded() on the whole name string.
|
2012-06-06 12:17:52 +08:00
|
|
|
*/
|
|
|
|
if (namelen < 0)
|
|
|
|
namelen = strlen(name);
|
|
|
|
|
2012-12-27 10:32:28 +08:00
|
|
|
/*
|
|
|
|
* If path is non-empty, and name is equal to path or a
|
|
|
|
* subdirectory of path, name should be excluded, because
|
|
|
|
* it's inside a directory which is already known to be
|
|
|
|
* excluded and was previously left in check->path.
|
|
|
|
*/
|
2012-06-02 03:22:09 +08:00
|
|
|
if (path->len &&
|
2012-06-06 12:17:52 +08:00
|
|
|
path->len <= namelen &&
|
|
|
|
!memcmp(name, path->buf, path->len) &&
|
|
|
|
(!name[path->len] || name[path->len] == '/'))
|
2012-12-27 10:32:28 +08:00
|
|
|
return check->exclude;
|
2012-06-02 03:22:09 +08:00
|
|
|
|
2012-06-02 02:28:00 +08:00
|
|
|
strbuf_setlen(path, 0);
|
2012-06-06 12:17:52 +08:00
|
|
|
for (i = 0; name[i]; i++) {
|
|
|
|
int ch = name[i];
|
2012-06-02 02:28:00 +08:00
|
|
|
|
|
|
|
if (ch == '/') {
|
2012-06-06 12:17:52 +08:00
|
|
|
int dt = DT_DIR;
|
2012-12-27 10:32:28 +08:00
|
|
|
exclude = last_exclude_matching(check->dir,
|
|
|
|
path->buf, &dt);
|
|
|
|
if (exclude) {
|
|
|
|
check->exclude = exclude;
|
|
|
|
return exclude;
|
|
|
|
}
|
2012-06-02 02:28:00 +08:00
|
|
|
}
|
|
|
|
strbuf_addch(path, ch);
|
|
|
|
}
|
2012-06-02 03:22:09 +08:00
|
|
|
|
|
|
|
/* An entry in the index; cannot be a directory with subentries */
|
|
|
|
strbuf_setlen(path, 0);
|
|
|
|
|
2012-12-27 10:32:28 +08:00
|
|
|
return last_exclude_matching(check->dir, name, dtype);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Is this name excluded? This is for a caller like show_files() that
|
|
|
|
* do not honor directory hierarchy and iterate through paths that are
|
|
|
|
* possibly in an ignored directory.
|
|
|
|
*/
|
|
|
|
int is_path_excluded(struct path_exclude_check *check,
|
|
|
|
const char *name, int namelen, int *dtype)
|
|
|
|
{
|
|
|
|
struct exclude *exclude =
|
|
|
|
last_exclude_matching_path(check, name, namelen, dtype);
|
|
|
|
if (exclude)
|
|
|
|
return exclude->flags & EXC_FLAG_NEGATIVE ? 0 : 1;
|
|
|
|
return 0;
|
2012-06-02 02:28:00 +08:00
|
|
|
}
|
|
|
|
|
2007-11-09 07:35:32 +08:00
|
|
|
static struct dir_entry *dir_entry_new(const char *pathname, int len)
|
|
|
|
{
|
2006-05-17 10:02:14 +08:00
|
|
|
struct dir_entry *ent;
|
|
|
|
|
|
|
|
ent = xmalloc(sizeof(*ent) + len + 1);
|
|
|
|
ent->len = len;
|
|
|
|
memcpy(ent->name, pathname, len);
|
|
|
|
ent->name[len] = 0;
|
2006-12-30 03:01:31 +08:00
|
|
|
return ent;
|
2006-05-17 10:02:14 +08:00
|
|
|
}
|
|
|
|
|
2008-10-02 18:14:23 +08:00
|
|
|
static struct dir_entry *dir_add_name(struct dir_struct *dir, const char *pathname, int len)
|
2007-06-11 21:39:44 +08:00
|
|
|
{
|
2013-01-07 06:09:39 +08:00
|
|
|
if (!(dir->flags & DIR_SHOW_IGNORED) &&
|
|
|
|
cache_name_exists(pathname, len, ignore_case))
|
2007-06-11 21:39:44 +08:00
|
|
|
return NULL;
|
|
|
|
|
2007-06-17 06:43:40 +08:00
|
|
|
ALLOC_GROW(dir->entries, dir->nr+1, dir->alloc);
|
2007-06-11 21:39:44 +08:00
|
|
|
return dir->entries[dir->nr++] = dir_entry_new(pathname, len);
|
|
|
|
}
|
|
|
|
|
2010-07-10 06:18:38 +08:00
|
|
|
struct dir_entry *dir_add_ignored(struct dir_struct *dir, const char *pathname, int len)
|
2007-06-11 21:39:50 +08:00
|
|
|
{
|
2009-05-31 05:54:18 +08:00
|
|
|
if (!cache_name_is_other(pathname, len))
|
2007-06-11 21:39:50 +08:00
|
|
|
return NULL;
|
|
|
|
|
2007-06-17 06:43:40 +08:00
|
|
|
ALLOC_GROW(dir->ignored, dir->ignored_nr+1, dir->ignored_alloc);
|
2007-06-11 21:39:50 +08:00
|
|
|
return dir->ignored[dir->ignored_nr++] = dir_entry_new(pathname, len);
|
|
|
|
}
|
|
|
|
|
2007-04-12 05:49:44 +08:00
|
|
|
enum exist_status {
|
|
|
|
index_nonexistent = 0,
|
|
|
|
index_directory,
|
2010-05-14 17:31:35 +08:00
|
|
|
index_gitdir
|
2007-04-12 05:49:44 +08:00
|
|
|
};
|
|
|
|
|
2010-10-03 17:56:43 +08:00
|
|
|
/*
|
|
|
|
* Do not use the alphabetically stored index to look up
|
|
|
|
* the directory name; instead, use the case insensitive
|
|
|
|
* name hash.
|
|
|
|
*/
|
|
|
|
static enum exist_status directory_exists_in_index_icase(const char *dirname, int len)
|
|
|
|
{
|
|
|
|
struct cache_entry *ce = index_name_exists(&the_index, dirname, len + 1, ignore_case);
|
|
|
|
unsigned char endchar;
|
|
|
|
|
|
|
|
if (!ce)
|
|
|
|
return index_nonexistent;
|
|
|
|
endchar = ce->name[len];
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The cache_entry structure returned will contain this dirname
|
|
|
|
* and possibly additional path components.
|
|
|
|
*/
|
|
|
|
if (endchar == '/')
|
|
|
|
return index_directory;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If there are no additional path components, then this cache_entry
|
|
|
|
* represents a submodule. Submodules, despite being directories,
|
|
|
|
* are stored in the cache without a closing slash.
|
|
|
|
*/
|
|
|
|
if (!endchar && S_ISGITLINK(ce->ce_mode))
|
|
|
|
return index_gitdir;
|
|
|
|
|
|
|
|
/* This should never be hit, but it exists just in case. */
|
|
|
|
return index_nonexistent;
|
|
|
|
}
|
|
|
|
|
2007-04-12 05:49:44 +08:00
|
|
|
/*
|
|
|
|
* The index sorts alphabetically by entry name, which
|
|
|
|
* means that a gitlink sorts as '\0' at the end, while
|
|
|
|
* a directory (which is defined not as an entry, but as
|
|
|
|
* the files it contains) will sort with the '/' at the
|
|
|
|
* end.
|
|
|
|
*/
|
|
|
|
static enum exist_status directory_exists_in_index(const char *dirname, int len)
|
2006-05-17 10:02:14 +08:00
|
|
|
{
|
2010-10-03 17:56:43 +08:00
|
|
|
int pos;
|
|
|
|
|
|
|
|
if (ignore_case)
|
|
|
|
return directory_exists_in_index_icase(dirname, len);
|
|
|
|
|
|
|
|
pos = cache_name_pos(dirname, len);
|
2007-04-12 05:49:44 +08:00
|
|
|
if (pos < 0)
|
|
|
|
pos = -pos-1;
|
|
|
|
while (pos < active_nr) {
|
|
|
|
struct cache_entry *ce = active_cache[pos++];
|
|
|
|
unsigned char endchar;
|
|
|
|
|
|
|
|
if (strncmp(ce->name, dirname, len))
|
|
|
|
break;
|
|
|
|
endchar = ce->name[len];
|
|
|
|
if (endchar > '/')
|
|
|
|
break;
|
|
|
|
if (endchar == '/')
|
|
|
|
return index_directory;
|
2008-01-15 08:03:17 +08:00
|
|
|
if (!endchar && S_ISGITLINK(ce->ce_mode))
|
2007-04-12 05:49:44 +08:00
|
|
|
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
|
2012-12-30 22:39:00 +08:00
|
|
|
* directory name, we recurse into the directory to see all the files,
|
|
|
|
* unless the directory is excluded and we want to show ignored
|
|
|
|
* directories
|
2007-04-12 05:49:44 +08:00
|
|
|
*
|
|
|
|
* 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
|
|
|
|
* also true and the directory is empty, in which case
|
|
|
|
* we just ignore it entirely.
|
2012-12-30 22:39:00 +08:00
|
|
|
* if we are looking for ignored directories, look if it
|
|
|
|
* contains only ignored files to decide if it must be shown as
|
|
|
|
* ignored or not.
|
2007-04-12 05:49:44 +08:00
|
|
|
* (b) if it looks like a git directory, and we don't have
|
2007-05-22 04:08:28 +08:00
|
|
|
* 'no_gitlinks' set we treat it as a gitlink, and show it
|
2007-04-12 05:49:44 +08:00
|
|
|
* as a directory.
|
|
|
|
* (c) otherwise, we recurse into it.
|
|
|
|
*/
|
|
|
|
enum directory_treatment {
|
|
|
|
show_directory,
|
|
|
|
ignore_directory,
|
2010-05-14 17:31:35 +08:00
|
|
|
recurse_into_directory
|
2007-04-12 05:49:44 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
static enum directory_treatment treat_directory(struct dir_struct *dir,
|
2012-12-30 22:39:00 +08:00
|
|
|
const char *dirname, int len, int exclude,
|
2007-04-12 05:49:44 +08:00
|
|
|
const struct path_simplify *simplify)
|
|
|
|
{
|
|
|
|
/* The "len-1" is to strip the final '/' */
|
|
|
|
switch (directory_exists_in_index(dirname, len-1)) {
|
|
|
|
case index_directory:
|
2012-12-30 22:39:00 +08:00
|
|
|
if ((dir->flags & DIR_SHOW_OTHER_DIRECTORIES) && exclude)
|
|
|
|
break;
|
|
|
|
|
2007-04-12 05:49:44 +08:00
|
|
|
return recurse_into_directory;
|
|
|
|
|
|
|
|
case index_gitdir:
|
2009-02-16 20:20:25 +08:00
|
|
|
if (dir->flags & DIR_SHOW_OTHER_DIRECTORIES)
|
2007-04-13 05:32:21 +08:00
|
|
|
return ignore_directory;
|
2007-04-12 05:49:44 +08:00
|
|
|
return show_directory;
|
|
|
|
|
|
|
|
case index_nonexistent:
|
2009-02-16 20:20:25 +08:00
|
|
|
if (dir->flags & DIR_SHOW_OTHER_DIRECTORIES)
|
2007-04-12 05:49:44 +08:00
|
|
|
break;
|
2009-02-16 20:20:25 +08:00
|
|
|
if (!(dir->flags & DIR_NO_GITLINKS)) {
|
2007-04-12 05:49:44 +08:00
|
|
|
unsigned char sha1[20];
|
|
|
|
if (resolve_gitlink_ref(dirname, "HEAD", sha1) == 0)
|
|
|
|
return show_directory;
|
|
|
|
}
|
|
|
|
return recurse_into_directory;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* This is the "show_other_directories" case */
|
2012-12-30 22:39:00 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* We are looking for ignored files and our directory is not ignored,
|
|
|
|
* check if it contains only ignored files
|
|
|
|
*/
|
|
|
|
if ((dir->flags & DIR_SHOW_IGNORED) && !exclude) {
|
|
|
|
int ignored;
|
|
|
|
dir->flags &= ~DIR_SHOW_IGNORED;
|
|
|
|
dir->flags |= DIR_HIDE_EMPTY_DIRECTORIES;
|
|
|
|
ignored = read_directory_recursive(dir, dirname, len, 1, simplify);
|
|
|
|
dir->flags &= ~DIR_HIDE_EMPTY_DIRECTORIES;
|
|
|
|
dir->flags |= DIR_SHOW_IGNORED;
|
|
|
|
|
|
|
|
return ignored ? ignore_directory : show_directory;
|
|
|
|
}
|
|
|
|
if (!(dir->flags & DIR_SHOW_IGNORED) &&
|
|
|
|
!(dir->flags & DIR_HIDE_EMPTY_DIRECTORIES))
|
2007-04-12 05:49:44 +08:00
|
|
|
return show_directory;
|
2009-07-09 10:24:39 +08:00
|
|
|
if (!read_directory_recursive(dir, dirname, len, 1, simplify))
|
2007-04-12 05:49:44 +08:00
|
|
|
return ignore_directory;
|
|
|
|
return show_directory;
|
2006-05-17 10:02:14 +08:00
|
|
|
}
|
|
|
|
|
2012-12-30 22:39:00 +08:00
|
|
|
/*
|
|
|
|
* Decide what to do when we find a file while traversing the
|
|
|
|
* filesystem. Mostly two cases:
|
|
|
|
*
|
|
|
|
* 1. We are looking for ignored files
|
|
|
|
* (a) File is ignored, include it
|
|
|
|
* (b) File is in ignored path, include it
|
|
|
|
* (c) File is not ignored, exclude it
|
|
|
|
*
|
|
|
|
* 2. Other scenarios, include the file if not excluded
|
|
|
|
*
|
|
|
|
* Return 1 for exclude, 0 for include.
|
|
|
|
*/
|
|
|
|
static int treat_file(struct dir_struct *dir, struct strbuf *path, int exclude, int *dtype)
|
|
|
|
{
|
|
|
|
struct path_exclude_check check;
|
|
|
|
int exclude_file = 0;
|
|
|
|
|
|
|
|
if (exclude)
|
|
|
|
exclude_file = !(dir->flags & DIR_SHOW_IGNORED);
|
|
|
|
else if (dir->flags & DIR_SHOW_IGNORED) {
|
2013-01-07 06:09:39 +08:00
|
|
|
/* Always exclude indexed files */
|
2012-12-30 22:39:00 +08:00
|
|
|
struct cache_entry *ce = index_name_exists(&the_index,
|
|
|
|
path->buf, path->len, ignore_case);
|
|
|
|
|
|
|
|
if (ce)
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
path_exclude_check_init(&check, dir);
|
|
|
|
|
2013-01-15 00:15:40 +08:00
|
|
|
if (!is_path_excluded(&check, path->buf, path->len, dtype))
|
2012-12-30 22:39:00 +08:00
|
|
|
exclude_file = 1;
|
|
|
|
|
|
|
|
path_exclude_check_clear(&check);
|
|
|
|
}
|
|
|
|
|
|
|
|
return exclude_file;
|
|
|
|
}
|
|
|
|
|
Optimize directory listing with pathspec limiter.
The way things are set up, you can now pass a "pathspec" to the
"read_directory()" function. If you pass NULL, it acts exactly
like it used to do (read everything). If you pass a non-NULL
pointer, it will simplify it into a "these are the prefixes
without any special characters", and stop any readdir() early if
the path in question doesn't match any of the prefixes.
NOTE! This does *not* obviate the need for the caller to do the *exact*
pathspec match later. It's a first-level filter on "read_directory()", but
it does not do the full pathspec thing. Maybe it should. But in the
meantime, builtin-add.c really does need to do first
read_directory(dir, .., pathspec);
if (pathspec)
prune_directory(dir, pathspec, baselen);
ie the "prune_directory()" part will do the *exact* pathspec pruning,
while the "read_directory()" will use the pathspec just to do some quick
high-level pruning of the directories it will recurse into.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-31 11:39:30 +08:00
|
|
|
/*
|
|
|
|
* This is an inexact early pruning of any recursive directory
|
|
|
|
* reading - if the path cannot possibly be in the pathspec,
|
|
|
|
* return true, and we'll skip it early.
|
|
|
|
*/
|
|
|
|
static int simplify_away(const char *path, int pathlen, const struct path_simplify *simplify)
|
|
|
|
{
|
|
|
|
if (simplify) {
|
|
|
|
for (;;) {
|
|
|
|
const char *match = simplify->path;
|
|
|
|
int len = simplify->len;
|
|
|
|
|
|
|
|
if (!match)
|
|
|
|
break;
|
|
|
|
if (len > pathlen)
|
|
|
|
len = pathlen;
|
|
|
|
if (!memcmp(path, match, len))
|
|
|
|
return 0;
|
|
|
|
simplify++;
|
|
|
|
}
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2010-03-11 15:15:43 +08:00
|
|
|
/*
|
|
|
|
* This function tells us whether an excluded path matches a
|
|
|
|
* list of "interesting" pathspecs. That is, whether a path matched
|
|
|
|
* by any of the pathspecs could possibly be ignored by excluding
|
|
|
|
* the specified path. This can happen if:
|
|
|
|
*
|
|
|
|
* 1. the path is mentioned explicitly in the pathspec
|
|
|
|
*
|
|
|
|
* 2. the path is a directory prefix of some element in the
|
|
|
|
* pathspec
|
|
|
|
*/
|
|
|
|
static int exclude_matches_pathspec(const char *path, int len,
|
|
|
|
const struct path_simplify *simplify)
|
builtin-add: simplify (and increase accuracy of) exclude handling
Previously, the code would always set up the excludes, and then manually
pick through the pathspec we were given, assuming that non-added but
existing paths were just ignored. This was mostly correct, but would
erroneously mark a totally empty directory as 'ignored'.
Instead, we now use the collect_ignored option of dir_struct, which
unambiguously tells us whether a path was ignored. This simplifies the
code, and means empty directories are now just not mentioned at all.
Furthermore, we now conditionally ask dir_struct to respect excludes,
depending on whether the '-f' flag has been set. This means we don't have
to pick through the result, checking for an 'ignored' flag; ignored entries
were either added or not in the first place.
We can safely get rid of the special 'ignored' flags to dir_entry, which
were not used anywhere else.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Jonas Fonseca <fonseca@diku.dk>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-13 05:42:14 +08:00
|
|
|
{
|
|
|
|
if (simplify) {
|
|
|
|
for (; simplify->path; simplify++) {
|
|
|
|
if (len == simplify->len
|
|
|
|
&& !memcmp(path, simplify->path, len))
|
|
|
|
return 1;
|
2010-03-11 15:15:43 +08:00
|
|
|
if (len < simplify->len
|
|
|
|
&& simplify->path[len] == '/'
|
|
|
|
&& !memcmp(path, simplify->path, len))
|
|
|
|
return 1;
|
builtin-add: simplify (and increase accuracy of) exclude handling
Previously, the code would always set up the excludes, and then manually
pick through the pathspec we were given, assuming that non-added but
existing paths were just ignored. This was mostly correct, but would
erroneously mark a totally empty directory as 'ignored'.
Instead, we now use the collect_ignored option of dir_struct, which
unambiguously tells us whether a path was ignored. This simplifies the
code, and means empty directories are now just not mentioned at all.
Furthermore, we now conditionally ask dir_struct to respect excludes,
depending on whether the '-f' flag has been set. This means we don't have
to pick through the result, checking for an 'ignored' flag; ignored entries
were either added or not in the first place.
We can safely get rid of the special 'ignored' flags to dir_entry, which
were not used anywhere else.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Jonas Fonseca <fonseca@diku.dk>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-13 05:42:14 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2009-07-10 04:14:28 +08:00
|
|
|
static int get_index_dtype(const char *path, int len)
|
|
|
|
{
|
|
|
|
int pos;
|
|
|
|
struct cache_entry *ce;
|
|
|
|
|
|
|
|
ce = cache_name_exists(path, len, 0);
|
|
|
|
if (ce) {
|
|
|
|
if (!ce_uptodate(ce))
|
|
|
|
return DT_UNKNOWN;
|
|
|
|
if (S_ISGITLINK(ce->ce_mode))
|
|
|
|
return DT_DIR;
|
|
|
|
/*
|
|
|
|
* Nobody actually cares about the
|
|
|
|
* difference between DT_LNK and DT_REG
|
|
|
|
*/
|
|
|
|
return DT_REG;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Try to look it up as a directory */
|
|
|
|
pos = cache_name_pos(path, len);
|
|
|
|
if (pos >= 0)
|
|
|
|
return DT_UNKNOWN;
|
|
|
|
pos = -pos-1;
|
|
|
|
while (pos < active_nr) {
|
|
|
|
ce = active_cache[pos++];
|
|
|
|
if (strncmp(ce->name, path, len))
|
|
|
|
break;
|
|
|
|
if (ce->name[len] > '/')
|
|
|
|
break;
|
|
|
|
if (ce->name[len] < '/')
|
|
|
|
continue;
|
|
|
|
if (!ce_uptodate(ce))
|
|
|
|
break; /* continue? */
|
|
|
|
return DT_DIR;
|
|
|
|
}
|
|
|
|
return DT_UNKNOWN;
|
|
|
|
}
|
|
|
|
|
2009-07-09 10:31:49 +08:00
|
|
|
static int get_dtype(struct dirent *de, const char *path, int len)
|
Fix directory scanner to correctly ignore files without d_type
On Fri, 19 Oct 2007, Todd T. Fries wrote:
> If DT_UNKNOWN exists, then we have to do a stat() of some form to
> find out the right type.
That happened in the case of a pathname that was ignored, and we did
not ask for "dir->show_ignored". That test used to be *together*
with the "DTYPE(de) != DT_DIR", but splitting the two tests up
means that we can do that (common) test before we even bother to
calculate the real dtype.
Of course, that optimization only matters for systems that don't
have, or don't fill in DTYPE properly.
I also clarified the real relationship between "exclude" and
"dir->show_ignored". It used to do
if (exclude != dir->show_ignored) {
..
which wasn't exactly obvious, because it triggers for two different
cases:
- the path is marked excluded, but we are not interested in ignored
files: ignore it
- the path is *not* excluded, but we *are* interested in ignored
files: ignore it unless it's a directory, in which case we might
have ignored files inside the directory and need to recurse
into it).
so this splits them into those two cases, since the first case
doesn't even care about the type.
I also made a the DT_UNKNOWN case a separate helper function,
and added some commentary to the cases.
Linus
Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2007-10-20 01:59:22 +08:00
|
|
|
{
|
2008-02-01 12:23:25 +08:00
|
|
|
int dtype = de ? DTYPE(de) : DT_UNKNOWN;
|
Fix directory scanner to correctly ignore files without d_type
On Fri, 19 Oct 2007, Todd T. Fries wrote:
> If DT_UNKNOWN exists, then we have to do a stat() of some form to
> find out the right type.
That happened in the case of a pathname that was ignored, and we did
not ask for "dir->show_ignored". That test used to be *together*
with the "DTYPE(de) != DT_DIR", but splitting the two tests up
means that we can do that (common) test before we even bother to
calculate the real dtype.
Of course, that optimization only matters for systems that don't
have, or don't fill in DTYPE properly.
I also clarified the real relationship between "exclude" and
"dir->show_ignored". It used to do
if (exclude != dir->show_ignored) {
..
which wasn't exactly obvious, because it triggers for two different
cases:
- the path is marked excluded, but we are not interested in ignored
files: ignore it
- the path is *not* excluded, but we *are* interested in ignored
files: ignore it unless it's a directory, in which case we might
have ignored files inside the directory and need to recurse
into it).
so this splits them into those two cases, since the first case
doesn't even care about the type.
I also made a the DT_UNKNOWN case a separate helper function,
and added some commentary to the cases.
Linus
Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2007-10-20 01:59:22 +08:00
|
|
|
struct stat st;
|
|
|
|
|
|
|
|
if (dtype != DT_UNKNOWN)
|
|
|
|
return dtype;
|
2009-07-10 04:14:28 +08:00
|
|
|
dtype = get_index_dtype(path, len);
|
|
|
|
if (dtype != DT_UNKNOWN)
|
|
|
|
return dtype;
|
|
|
|
if (lstat(path, &st))
|
Fix directory scanner to correctly ignore files without d_type
On Fri, 19 Oct 2007, Todd T. Fries wrote:
> If DT_UNKNOWN exists, then we have to do a stat() of some form to
> find out the right type.
That happened in the case of a pathname that was ignored, and we did
not ask for "dir->show_ignored". That test used to be *together*
with the "DTYPE(de) != DT_DIR", but splitting the two tests up
means that we can do that (common) test before we even bother to
calculate the real dtype.
Of course, that optimization only matters for systems that don't
have, or don't fill in DTYPE properly.
I also clarified the real relationship between "exclude" and
"dir->show_ignored". It used to do
if (exclude != dir->show_ignored) {
..
which wasn't exactly obvious, because it triggers for two different
cases:
- the path is marked excluded, but we are not interested in ignored
files: ignore it
- the path is *not* excluded, but we *are* interested in ignored
files: ignore it unless it's a directory, in which case we might
have ignored files inside the directory and need to recurse
into it).
so this splits them into those two cases, since the first case
doesn't even care about the type.
I also made a the DT_UNKNOWN case a separate helper function,
and added some commentary to the cases.
Linus
Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2007-10-20 01:59:22 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2010-01-09 11:14:07 +08:00
|
|
|
enum path_treatment {
|
|
|
|
path_ignored,
|
|
|
|
path_handled,
|
2010-05-14 17:31:35 +08:00
|
|
|
path_recurse
|
2010-01-09 11:14:07 +08:00
|
|
|
};
|
|
|
|
|
2010-01-09 12:56:16 +08:00
|
|
|
static enum path_treatment treat_one_path(struct dir_struct *dir,
|
2012-05-01 19:25:24 +08:00
|
|
|
struct strbuf *path,
|
2010-01-09 12:56:16 +08:00
|
|
|
const struct path_simplify *simplify,
|
|
|
|
int dtype, struct dirent *de)
|
2010-01-09 11:14:07 +08:00
|
|
|
{
|
2012-12-27 10:32:25 +08:00
|
|
|
int exclude = is_excluded(dir, path->buf, &dtype);
|
2010-01-09 11:14:07 +08:00
|
|
|
if (exclude && (dir->flags & DIR_COLLECT_IGNORED)
|
2012-05-01 19:25:24 +08:00
|
|
|
&& exclude_matches_pathspec(path->buf, path->len, simplify))
|
|
|
|
dir_add_ignored(dir, path->buf, path->len);
|
2010-01-09 11:14:07 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Excluded? If we don't explicitly want to show
|
|
|
|
* ignored files, ignore it
|
|
|
|
*/
|
|
|
|
if (exclude && !(dir->flags & DIR_SHOW_IGNORED))
|
|
|
|
return path_ignored;
|
|
|
|
|
|
|
|
if (dtype == DT_UNKNOWN)
|
2012-05-01 19:25:24 +08:00
|
|
|
dtype = get_dtype(de, path->buf, path->len);
|
2010-01-09 11:14:07 +08:00
|
|
|
|
|
|
|
switch (dtype) {
|
|
|
|
default:
|
|
|
|
return path_ignored;
|
|
|
|
case DT_DIR:
|
2012-05-01 19:25:24 +08:00
|
|
|
strbuf_addch(path, '/');
|
2012-12-30 22:39:00 +08:00
|
|
|
|
|
|
|
switch (treat_directory(dir, path->buf, path->len, exclude, simplify)) {
|
2010-01-09 11:14:07 +08:00
|
|
|
case show_directory:
|
|
|
|
break;
|
|
|
|
case recurse_into_directory:
|
|
|
|
return path_recurse;
|
|
|
|
case ignore_directory:
|
|
|
|
return path_ignored;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
case DT_REG:
|
|
|
|
case DT_LNK:
|
2012-12-30 22:39:00 +08:00
|
|
|
switch (treat_file(dir, path, exclude, &dtype)) {
|
|
|
|
case 1:
|
|
|
|
return path_ignored;
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
2010-01-09 11:14:07 +08:00
|
|
|
}
|
|
|
|
return path_handled;
|
|
|
|
}
|
|
|
|
|
2010-01-09 12:56:16 +08:00
|
|
|
static enum path_treatment treat_path(struct dir_struct *dir,
|
|
|
|
struct dirent *de,
|
2012-05-01 19:25:24 +08:00
|
|
|
struct strbuf *path,
|
2010-01-09 12:56:16 +08:00
|
|
|
int baselen,
|
2012-05-01 19:25:24 +08:00
|
|
|
const struct path_simplify *simplify)
|
2010-01-09 12:56:16 +08:00
|
|
|
{
|
|
|
|
int dtype;
|
|
|
|
|
|
|
|
if (is_dot_or_dotdot(de->d_name) || !strcmp(de->d_name, ".git"))
|
|
|
|
return path_ignored;
|
2012-05-01 19:25:24 +08:00
|
|
|
strbuf_setlen(path, baselen);
|
|
|
|
strbuf_addstr(path, de->d_name);
|
|
|
|
if (simplify_away(path->buf, path->len, simplify))
|
2010-01-09 12:56:16 +08:00
|
|
|
return path_ignored;
|
|
|
|
|
|
|
|
dtype = DTYPE(de);
|
2012-05-01 19:25:24 +08:00
|
|
|
return treat_one_path(dir, path, simplify, dtype, de);
|
2010-01-09 12:56:16 +08:00
|
|
|
}
|
|
|
|
|
2006-05-17 10:02:14 +08:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2010-01-09 11:14:07 +08:00
|
|
|
static int read_directory_recursive(struct dir_struct *dir,
|
|
|
|
const char *base, int baselen,
|
|
|
|
int check_only,
|
|
|
|
const struct path_simplify *simplify)
|
2006-05-17 10:02:14 +08:00
|
|
|
{
|
2012-05-11 22:53:07 +08:00
|
|
|
DIR *fdir;
|
2006-05-17 10:02:14 +08:00
|
|
|
int contents = 0;
|
2011-10-24 14:36:11 +08:00
|
|
|
struct dirent *de;
|
2012-05-09 00:43:40 +08:00
|
|
|
struct strbuf path = STRBUF_INIT;
|
2006-05-17 10:02:14 +08:00
|
|
|
|
2012-05-09 00:43:40 +08:00
|
|
|
strbuf_add(&path, base, baselen);
|
2011-10-24 14:36:11 +08:00
|
|
|
|
2012-05-11 22:53:07 +08:00
|
|
|
fdir = opendir(path.len ? path.buf : ".");
|
|
|
|
if (!fdir)
|
|
|
|
goto out;
|
|
|
|
|
2011-10-24 14:36:11 +08:00
|
|
|
while ((de = readdir(fdir)) != NULL) {
|
2012-05-09 00:43:40 +08:00
|
|
|
switch (treat_path(dir, de, &path, baselen, simplify)) {
|
2011-10-24 14:36:11 +08:00
|
|
|
case path_recurse:
|
2012-05-09 00:43:40 +08:00
|
|
|
contents += read_directory_recursive(dir, path.buf,
|
|
|
|
path.len, 0,
|
|
|
|
simplify);
|
2011-10-24 14:36:11 +08:00
|
|
|
continue;
|
|
|
|
case path_ignored:
|
|
|
|
continue;
|
|
|
|
case path_handled:
|
|
|
|
break;
|
2006-05-17 10:02:14 +08:00
|
|
|
}
|
2011-10-24 14:36:11 +08:00
|
|
|
contents++;
|
|
|
|
if (check_only)
|
2012-05-11 22:53:07 +08:00
|
|
|
break;
|
|
|
|
dir_add_name(dir, path.buf, path.len);
|
2006-05-17 10:02:14 +08:00
|
|
|
}
|
2011-10-24 14:36:11 +08:00
|
|
|
closedir(fdir);
|
2012-05-11 22:53:07 +08:00
|
|
|
out:
|
2012-05-09 00:43:40 +08:00
|
|
|
strbuf_release(&path);
|
2006-05-17 10:02:14 +08:00
|
|
|
|
|
|
|
return contents;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int cmp_name(const void *p1, const void *p2)
|
|
|
|
{
|
|
|
|
const struct dir_entry *e1 = *(const struct dir_entry **)p1;
|
|
|
|
const struct dir_entry *e2 = *(const struct dir_entry **)p2;
|
|
|
|
|
|
|
|
return cache_name_compare(e1->name, e1->len,
|
|
|
|
e2->name, e2->len);
|
|
|
|
}
|
|
|
|
|
Optimize directory listing with pathspec limiter.
The way things are set up, you can now pass a "pathspec" to the
"read_directory()" function. If you pass NULL, it acts exactly
like it used to do (read everything). If you pass a non-NULL
pointer, it will simplify it into a "these are the prefixes
without any special characters", and stop any readdir() early if
the path in question doesn't match any of the prefixes.
NOTE! This does *not* obviate the need for the caller to do the *exact*
pathspec match later. It's a first-level filter on "read_directory()", but
it does not do the full pathspec thing. Maybe it should. But in the
meantime, builtin-add.c really does need to do first
read_directory(dir, .., pathspec);
if (pathspec)
prune_directory(dir, pathspec, baselen);
ie the "prune_directory()" part will do the *exact* pathspec pruning,
while the "read_directory()" will use the pathspec just to do some quick
high-level pruning of the directories it will recurse into.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-31 11:39:30 +08:00
|
|
|
static struct path_simplify *create_simplify(const char **pathspec)
|
|
|
|
{
|
|
|
|
int nr, alloc = 0;
|
|
|
|
struct path_simplify *simplify = NULL;
|
|
|
|
|
|
|
|
if (!pathspec)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
for (nr = 0 ; ; nr++) {
|
|
|
|
const char *match;
|
|
|
|
if (nr >= alloc) {
|
|
|
|
alloc = alloc_nr(alloc);
|
|
|
|
simplify = xrealloc(simplify, alloc * sizeof(*simplify));
|
|
|
|
}
|
|
|
|
match = *pathspec++;
|
|
|
|
if (!match)
|
|
|
|
break;
|
|
|
|
simplify[nr].path = match;
|
|
|
|
simplify[nr].len = simple_length(match);
|
|
|
|
}
|
|
|
|
simplify[nr].path = NULL;
|
|
|
|
simplify[nr].len = 0;
|
|
|
|
return simplify;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void free_simplify(struct path_simplify *simplify)
|
|
|
|
{
|
Avoid unnecessary "if-before-free" tests.
This change removes all obvious useless if-before-free tests.
E.g., it replaces code like this:
if (some_expression)
free (some_expression);
with the now-equivalent:
free (some_expression);
It is equivalent not just because POSIX has required free(NULL)
to work for a long time, but simply because it has worked for
so long that no reasonable porting target fails the test.
Here's some evidence from nearly 1.5 years ago:
http://www.winehq.org/pipermail/wine-patches/2006-October/031544.html
FYI, the change below was prepared by running the following:
git ls-files -z | xargs -0 \
perl -0x3b -pi -e \
's/\bif\s*\(\s*(\S+?)(?:\s*!=\s*NULL)?\s*\)\s+(free\s*\(\s*\1\s*\))/$2/s'
Note however, that it doesn't handle brace-enclosed blocks like
"if (x) { free (x); }". But that's ok, since there were none like
that in git sources.
Beware: if you do use the above snippet, note that it can
produce syntactically invalid C code. That happens when the
affected "if"-statement has a matching "else".
E.g., it would transform this
if (x)
free (x);
else
foo ();
into this:
free (x);
else
foo ();
There were none of those here, either.
If you're interested in automating detection of the useless
tests, you might like the useless-if-before-free script in gnulib:
[it *does* detect brace-enclosed free statements, and has a --name=S
option to make it detect free-like functions with different names]
http://git.sv.gnu.org/gitweb/?p=gnulib.git;a=blob;f=build-aux/useless-if-before-free
Addendum:
Remove one more (in imap-send.c), spotted by Jean-Luc Herren <jlh@gmx.ch>.
Signed-off-by: Jim Meyering <meyering@redhat.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-01 01:26:32 +08:00
|
|
|
free(simplify);
|
Optimize directory listing with pathspec limiter.
The way things are set up, you can now pass a "pathspec" to the
"read_directory()" function. If you pass NULL, it acts exactly
like it used to do (read everything). If you pass a non-NULL
pointer, it will simplify it into a "these are the prefixes
without any special characters", and stop any readdir() early if
the path in question doesn't match any of the prefixes.
NOTE! This does *not* obviate the need for the caller to do the *exact*
pathspec match later. It's a first-level filter on "read_directory()", but
it does not do the full pathspec thing. Maybe it should. But in the
meantime, builtin-add.c really does need to do first
read_directory(dir, .., pathspec);
if (pathspec)
prune_directory(dir, pathspec, baselen);
ie the "prune_directory()" part will do the *exact* pathspec pruning,
while the "read_directory()" will use the pathspec just to do some quick
high-level pruning of the directories it will recurse into.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-31 11:39:30 +08:00
|
|
|
}
|
|
|
|
|
2010-01-09 15:05:41 +08:00
|
|
|
static int treat_leading_path(struct dir_struct *dir,
|
|
|
|
const char *path, int len,
|
|
|
|
const struct path_simplify *simplify)
|
|
|
|
{
|
2012-05-01 19:25:24 +08:00
|
|
|
struct strbuf sb = STRBUF_INIT;
|
|
|
|
int baselen, rc = 0;
|
2010-01-09 15:05:41 +08:00
|
|
|
const char *cp;
|
|
|
|
|
|
|
|
while (len && path[len - 1] == '/')
|
|
|
|
len--;
|
|
|
|
if (!len)
|
|
|
|
return 1;
|
|
|
|
baselen = 0;
|
|
|
|
while (1) {
|
|
|
|
cp = path + baselen + !!baselen;
|
|
|
|
cp = memchr(cp, '/', path + len - cp);
|
|
|
|
if (!cp)
|
|
|
|
baselen = len;
|
|
|
|
else
|
|
|
|
baselen = cp - path;
|
2012-05-01 19:25:24 +08:00
|
|
|
strbuf_setlen(&sb, 0);
|
|
|
|
strbuf_add(&sb, path, baselen);
|
|
|
|
if (!is_directory(sb.buf))
|
|
|
|
break;
|
|
|
|
if (simplify_away(sb.buf, sb.len, simplify))
|
|
|
|
break;
|
|
|
|
if (treat_one_path(dir, &sb, simplify,
|
2010-01-09 15:05:41 +08:00
|
|
|
DT_DIR, NULL) == path_ignored)
|
2012-05-01 19:25:24 +08:00
|
|
|
break; /* do not recurse into it */
|
|
|
|
if (len <= baselen) {
|
|
|
|
rc = 1;
|
|
|
|
break; /* finished checking */
|
|
|
|
}
|
2010-01-09 15:05:41 +08:00
|
|
|
}
|
2012-05-01 19:25:24 +08:00
|
|
|
strbuf_release(&sb);
|
|
|
|
return rc;
|
2010-01-09 15:05:41 +08:00
|
|
|
}
|
|
|
|
|
2009-07-09 10:24:39 +08:00
|
|
|
int read_directory(struct dir_struct *dir, const char *path, int len, const char **pathspec)
|
Optimize directory listing with pathspec limiter.
The way things are set up, you can now pass a "pathspec" to the
"read_directory()" function. If you pass NULL, it acts exactly
like it used to do (read everything). If you pass a non-NULL
pointer, it will simplify it into a "these are the prefixes
without any special characters", and stop any readdir() early if
the path in question doesn't match any of the prefixes.
NOTE! This does *not* obviate the need for the caller to do the *exact*
pathspec match later. It's a first-level filter on "read_directory()", but
it does not do the full pathspec thing. Maybe it should. But in the
meantime, builtin-add.c really does need to do first
read_directory(dir, .., pathspec);
if (pathspec)
prune_directory(dir, pathspec, baselen);
ie the "prune_directory()" part will do the *exact* pathspec pruning,
while the "read_directory()" will use the pathspec just to do some quick
high-level pruning of the directories it will recurse into.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-31 11:39:30 +08:00
|
|
|
{
|
2008-08-04 15:52:37 +08:00
|
|
|
struct path_simplify *simplify;
|
2006-05-17 10:46:16 +08:00
|
|
|
|
2009-07-09 10:24:39 +08:00
|
|
|
if (has_symlink_leading_path(path, len))
|
2008-08-04 15:52:37 +08:00
|
|
|
return dir->nr;
|
|
|
|
|
|
|
|
simplify = create_simplify(pathspec);
|
2010-01-09 15:05:41 +08:00
|
|
|
if (!len || treat_leading_path(dir, path, len, simplify))
|
|
|
|
read_directory_recursive(dir, path, len, 0, simplify);
|
Optimize directory listing with pathspec limiter.
The way things are set up, you can now pass a "pathspec" to the
"read_directory()" function. If you pass NULL, it acts exactly
like it used to do (read everything). If you pass a non-NULL
pointer, it will simplify it into a "these are the prefixes
without any special characters", and stop any readdir() early if
the path in question doesn't match any of the prefixes.
NOTE! This does *not* obviate the need for the caller to do the *exact*
pathspec match later. It's a first-level filter on "read_directory()", but
it does not do the full pathspec thing. Maybe it should. But in the
meantime, builtin-add.c really does need to do first
read_directory(dir, .., pathspec);
if (pathspec)
prune_directory(dir, pathspec, baselen);
ie the "prune_directory()" part will do the *exact* pathspec pruning,
while the "read_directory()" will use the pathspec just to do some quick
high-level pruning of the directories it will recurse into.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-31 11:39:30 +08:00
|
|
|
free_simplify(simplify);
|
2006-05-17 10:02:14 +08:00
|
|
|
qsort(dir->entries, dir->nr, sizeof(struct dir_entry *), cmp_name);
|
2007-06-11 21:39:50 +08:00
|
|
|
qsort(dir->ignored, dir->ignored_nr, sizeof(struct dir_entry *), cmp_name);
|
2006-05-17 10:02:14 +08:00
|
|
|
return dir->nr;
|
|
|
|
}
|
2006-09-08 16:05:34 +08:00
|
|
|
|
2007-11-29 17:11:46 +08:00
|
|
|
int file_exists(const char *f)
|
2006-09-08 16:05:34 +08:00
|
|
|
{
|
2007-11-29 17:11:46 +08:00
|
|
|
struct stat sb;
|
2007-11-18 17:58:16 +08:00
|
|
|
return lstat(f, &sb) == 0;
|
2006-09-08 16:05:34 +08:00
|
|
|
}
|
2007-08-01 08:29:17 +08:00
|
|
|
|
|
|
|
/*
|
2011-03-26 17:04:24 +08:00
|
|
|
* 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.
|
2007-08-01 08:29:17 +08:00
|
|
|
*/
|
2011-03-26 17:04:24 +08:00
|
|
|
int dir_inside_of(const char *subdir, const char *dir)
|
2007-08-01 08:29:17 +08:00
|
|
|
{
|
2011-03-26 17:04:24 +08:00
|
|
|
int offset = 0;
|
2007-08-01 08:29:17 +08:00
|
|
|
|
2011-03-26 17:04:24 +08:00
|
|
|
assert(dir && subdir && *dir && *subdir);
|
2007-08-01 08:29:17 +08:00
|
|
|
|
2011-03-26 17:04:24 +08:00
|
|
|
while (*dir && *subdir && *dir == *subdir) {
|
2007-08-01 08:29:17 +08:00
|
|
|
dir++;
|
2011-03-26 17:04:24 +08:00
|
|
|
subdir++;
|
|
|
|
offset++;
|
2010-05-22 19:13:05 +08:00
|
|
|
}
|
2011-03-26 17:04:24 +08:00
|
|
|
|
|
|
|
/* 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;
|
2007-08-01 08:29:17 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
int is_inside_dir(const char *dir)
|
|
|
|
{
|
2011-03-26 17:04:25 +08:00
|
|
|
char cwd[PATH_MAX];
|
|
|
|
if (!dir)
|
|
|
|
return 0;
|
|
|
|
if (!getcwd(cwd, sizeof(cwd)))
|
|
|
|
die_errno("can't find the current directory");
|
|
|
|
return dir_inside_of(cwd, dir) >= 0;
|
2007-08-01 08:29:17 +08:00
|
|
|
}
|
2007-09-28 23:28:54 +08:00
|
|
|
|
2009-01-11 20:19:12 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2012-03-15 16:04:12 +08:00
|
|
|
static int remove_dir_recurse(struct strbuf *path, int flag, int *kept_up)
|
2007-09-28 23:28:54 +08:00
|
|
|
{
|
2009-07-01 06:33:45 +08:00
|
|
|
DIR *dir;
|
2007-09-28 23:28:54 +08:00
|
|
|
struct dirent *e;
|
2012-03-15 16:04:12 +08:00
|
|
|
int ret = 0, original_len = path->len, len, kept_down = 0;
|
2009-07-01 06:33:45 +08:00
|
|
|
int only_empty = (flag & REMOVE_DIR_EMPTY_ONLY);
|
2012-03-15 22:58:54 +08:00
|
|
|
int keep_toplevel = (flag & REMOVE_DIR_KEEP_TOPLEVEL);
|
2009-07-01 06:33:45 +08:00
|
|
|
unsigned char submodule_head[20];
|
2007-09-28 23:28:54 +08:00
|
|
|
|
2009-07-01 06:33:45 +08:00
|
|
|
if ((flag & REMOVE_DIR_KEEP_NESTED_GIT) &&
|
2012-03-15 16:04:12 +08:00
|
|
|
!resolve_gitlink_ref(path->buf, "HEAD", submodule_head)) {
|
2009-07-01 06:33:45 +08:00
|
|
|
/* Do not descend and nuke a nested git work tree. */
|
2012-03-15 16:04:12 +08:00
|
|
|
if (kept_up)
|
|
|
|
*kept_up = 1;
|
2009-07-01 06:33:45 +08:00
|
|
|
return 0;
|
2012-03-15 16:04:12 +08:00
|
|
|
}
|
2009-07-01 06:33:45 +08:00
|
|
|
|
2012-03-15 16:04:12 +08:00
|
|
|
flag &= ~REMOVE_DIR_KEEP_TOPLEVEL;
|
2009-07-01 06:33:45 +08:00
|
|
|
dir = opendir(path->buf);
|
2012-03-15 22:58:54 +08:00
|
|
|
if (!dir) {
|
2012-03-15 16:04:12 +08:00
|
|
|
/* an empty dir could be removed even if it is unreadble */
|
2012-03-15 22:58:54 +08:00
|
|
|
if (!keep_toplevel)
|
|
|
|
return rmdir(path->buf);
|
|
|
|
else
|
|
|
|
return -1;
|
|
|
|
}
|
2007-09-28 23:28:54 +08:00
|
|
|
if (path->buf[original_len - 1] != '/')
|
|
|
|
strbuf_addch(path, '/');
|
|
|
|
|
|
|
|
len = path->len;
|
|
|
|
while ((e = readdir(dir)) != NULL) {
|
|
|
|
struct stat st;
|
2009-01-10 20:07:50 +08:00
|
|
|
if (is_dot_or_dotdot(e->d_name))
|
|
|
|
continue;
|
2007-09-28 23:28:54 +08:00
|
|
|
|
|
|
|
strbuf_setlen(path, len);
|
|
|
|
strbuf_addstr(path, e->d_name);
|
|
|
|
if (lstat(path->buf, &st))
|
|
|
|
; /* fall thru */
|
|
|
|
else if (S_ISDIR(st.st_mode)) {
|
2012-03-15 16:04:12 +08:00
|
|
|
if (!remove_dir_recurse(path, flag, &kept_down))
|
2007-09-28 23:28:54 +08:00
|
|
|
continue; /* happy */
|
|
|
|
} else if (!only_empty && !unlink(path->buf))
|
|
|
|
continue; /* happy, too */
|
|
|
|
|
|
|
|
/* path too long, stat fails, or non-directory still exists */
|
|
|
|
ret = -1;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
closedir(dir);
|
|
|
|
|
|
|
|
strbuf_setlen(path, original_len);
|
2012-03-15 16:04:12 +08:00
|
|
|
if (!ret && !keep_toplevel && !kept_down)
|
2007-09-28 23:28:54 +08:00
|
|
|
ret = rmdir(path->buf);
|
2012-03-15 16:04:12 +08:00
|
|
|
else if (kept_up)
|
|
|
|
/*
|
|
|
|
* report the uplevel that it is not an error that we
|
|
|
|
* did not rmdir() our directory.
|
|
|
|
*/
|
|
|
|
*kept_up = !ret;
|
2007-09-28 23:28:54 +08:00
|
|
|
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 16:05:00 +08:00
|
|
|
|
2012-03-15 16:04:12 +08:00
|
|
|
int remove_dir_recursively(struct strbuf *path, int flag)
|
|
|
|
{
|
|
|
|
return remove_dir_recurse(path, flag, NULL);
|
|
|
|
}
|
|
|
|
|
core.excludesfile clean-up
There are inconsistencies in the way commands currently handle
the core.excludesfile configuration variable. The problem is
the variable is too new to be noticed by anything other than
git-add and git-status.
* git-ls-files does not notice any of the "ignore" files by
default, as it predates the standardized set of ignore files.
The calling scripts established the convention to use
.git/info/exclude, .gitignore, and later core.excludesfile.
* git-add and git-status know about it because they call
add_excludes_from_file() directly with their own notion of
which standard set of ignore files to use. This is just a
stupid duplication of code that need to be updated every time
the definition of the standard set of ignore files is
changed.
* git-read-tree takes --exclude-per-directory=<gitignore>,
not because the flexibility was needed. Again, this was
because the option predates the standardization of the ignore
files.
* git-merge-recursive uses hardcoded per-directory .gitignore
and nothing else. git-clean (scripted version) does not
honor core.* because its call to underlying ls-files does not
know about it. git-clean in C (parked in 'pu') doesn't either.
We probably could change git-ls-files to use the standard set
when no excludes are specified on the command line and ignore
processing was asked, or something like that, but that will be a
change in semantics and might break people's scripts in a subtle
way. I am somewhat reluctant to make such a change.
On the other hand, I think it makes perfect sense to fix
git-read-tree, git-merge-recursive and git-clean to follow the
same rule as other commands. I do not think of a valid use case
to give an exclude-per-directory that is nonstandard to
read-tree command, outside a "negative" test in the t1004 test
script.
This patch is the first step to untangle this mess.
The next step would be to teach read-tree, merge-recursive and
clean (in C) to use setup_standard_excludes().
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-14 16:05:00 +08:00
|
|
|
void setup_standard_excludes(struct dir_struct *dir)
|
|
|
|
{
|
|
|
|
const char *path;
|
2012-06-22 17:03:24 +08:00
|
|
|
char *xdg_path;
|
core.excludesfile clean-up
There are inconsistencies in the way commands currently handle
the core.excludesfile configuration variable. The problem is
the variable is too new to be noticed by anything other than
git-add and git-status.
* git-ls-files does not notice any of the "ignore" files by
default, as it predates the standardized set of ignore files.
The calling scripts established the convention to use
.git/info/exclude, .gitignore, and later core.excludesfile.
* git-add and git-status know about it because they call
add_excludes_from_file() directly with their own notion of
which standard set of ignore files to use. This is just a
stupid duplication of code that need to be updated every time
the definition of the standard set of ignore files is
changed.
* git-read-tree takes --exclude-per-directory=<gitignore>,
not because the flexibility was needed. Again, this was
because the option predates the standardization of the ignore
files.
* git-merge-recursive uses hardcoded per-directory .gitignore
and nothing else. git-clean (scripted version) does not
honor core.* because its call to underlying ls-files does not
know about it. git-clean in C (parked in 'pu') doesn't either.
We probably could change git-ls-files to use the standard set
when no excludes are specified on the command line and ignore
processing was asked, or something like that, but that will be a
change in semantics and might break people's scripts in a subtle
way. I am somewhat reluctant to make such a change.
On the other hand, I think it makes perfect sense to fix
git-read-tree, git-merge-recursive and git-clean to follow the
same rule as other commands. I do not think of a valid use case
to give an exclude-per-directory that is nonstandard to
read-tree command, outside a "negative" test in the t1004 test
script.
This patch is the first step to untangle this mess.
The next step would be to teach read-tree, merge-recursive and
clean (in C) to use setup_standard_excludes().
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-14 16:05:00 +08:00
|
|
|
|
|
|
|
dir->exclude_per_dir = ".gitignore";
|
|
|
|
path = git_path("info/exclude");
|
2012-06-22 17:03:24 +08:00
|
|
|
if (!excludes_file) {
|
|
|
|
home_config_paths(NULL, &xdg_path, "ignore");
|
|
|
|
excludes_file = xdg_path;
|
|
|
|
}
|
2012-08-21 14:26:07 +08:00
|
|
|
if (!access_or_warn(path, R_OK))
|
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 16:05:00 +08:00
|
|
|
add_excludes_from_file(dir, path);
|
2012-08-21 14:26:07 +08:00
|
|
|
if (excludes_file && !access_or_warn(excludes_file, R_OK))
|
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 16:05:00 +08:00
|
|
|
add_excludes_from_file(dir, excludes_file);
|
|
|
|
}
|
2008-09-27 06:56:46 +08:00
|
|
|
|
|
|
|
int remove_path(const char *name)
|
|
|
|
{
|
|
|
|
char *slash;
|
|
|
|
|
2013-04-05 03:03:35 +08:00
|
|
|
if (unlink(name) && errno != ENOENT && errno != ENOTDIR)
|
2008-09-27 06:56:46 +08:00
|
|
|
return -1;
|
|
|
|
|
|
|
|
slash = strrchr(name, '/');
|
|
|
|
if (slash) {
|
|
|
|
char *dirs = xstrdup(name);
|
|
|
|
slash = dirs + (slash - name);
|
|
|
|
do {
|
|
|
|
*slash = '\0';
|
2010-02-19 13:57:21 +08:00
|
|
|
} while (rmdir(dirs) == 0 && (slash = strrchr(dirs, '/')));
|
2008-09-27 06:56:46 +08:00
|
|
|
free(dirs);
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2010-12-15 23:02:45 +08:00
|
|
|
static int pathspec_item_cmp(const void *a_, const void *b_)
|
|
|
|
{
|
|
|
|
struct pathspec_item *a, *b;
|
|
|
|
|
|
|
|
a = (struct pathspec_item *)a_;
|
|
|
|
b = (struct pathspec_item *)b_;
|
|
|
|
return strcmp(a->match, b->match);
|
|
|
|
}
|
|
|
|
|
2010-12-15 23:02:36 +08:00
|
|
|
int init_pathspec(struct pathspec *pathspec, const char **paths)
|
|
|
|
{
|
|
|
|
const char **p = paths;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
memset(pathspec, 0, sizeof(*pathspec));
|
|
|
|
if (!p)
|
|
|
|
return 0;
|
|
|
|
while (*p)
|
|
|
|
p++;
|
|
|
|
pathspec->raw = paths;
|
|
|
|
pathspec->nr = p - paths;
|
|
|
|
if (!pathspec->nr)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
pathspec->items = xmalloc(sizeof(struct pathspec_item)*pathspec->nr);
|
|
|
|
for (i = 0; i < pathspec->nr; i++) {
|
|
|
|
struct pathspec_item *item = pathspec->items+i;
|
|
|
|
const char *path = paths[i];
|
|
|
|
|
|
|
|
item->match = path;
|
|
|
|
item->len = strlen(path);
|
2012-11-24 12:33:50 +08:00
|
|
|
item->flags = 0;
|
2013-01-06 15:42:07 +08:00
|
|
|
if (limit_pathspec_to_literal()) {
|
|
|
|
item->nowildcard_len = item->len;
|
|
|
|
} else {
|
|
|
|
item->nowildcard_len = simple_length(path);
|
|
|
|
if (item->nowildcard_len < item->len) {
|
|
|
|
pathspec->has_wildcard = 1;
|
|
|
|
if (path[item->nowildcard_len] == '*' &&
|
|
|
|
no_wildcard(path + item->nowildcard_len + 1))
|
|
|
|
item->flags |= PATHSPEC_ONESTAR;
|
|
|
|
}
|
2012-11-24 12:33:50 +08:00
|
|
|
}
|
2010-12-15 23:02:36 +08:00
|
|
|
}
|
2010-12-15 23:02:45 +08:00
|
|
|
|
|
|
|
qsort(pathspec->items, pathspec->nr,
|
|
|
|
sizeof(struct pathspec_item), pathspec_item_cmp);
|
|
|
|
|
2010-12-15 23:02:36 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void free_pathspec(struct pathspec *pathspec)
|
|
|
|
{
|
|
|
|
free(pathspec->items);
|
|
|
|
pathspec->items = NULL;
|
|
|
|
}
|
add global --literal-pathspecs option
Git takes pathspec arguments in many places to limit the
scope of an operation. These pathspecs are treated not as
literal paths, but as glob patterns that can be fed to
fnmatch. When a user is giving a specific pattern, this is a
nice feature.
However, when programatically providing pathspecs, it can be
a nuisance. For example, to find the latest revision which
modified "$foo", one can use "git rev-list -- $foo". But if
"$foo" contains glob characters (e.g., "f*"), it will
erroneously match more entries than desired. The caller
needs to quote the characters in $foo, and even then, the
results may not be exactly the same as with a literal
pathspec. For instance, the depth checks in
match_pathspec_depth do not kick in if we match via fnmatch.
This patch introduces a global command-line option (i.e.,
one for "git" itself, not for specific commands) to turn
this behavior off. It also has a matching environment
variable, which can make it easier if you are a script or
porcelain interface that is going to issue many such
commands.
This option cannot turn off globbing for particular
pathspecs. That could eventually be done with a ":(noglob)"
magic pathspec prefix. However, that level of granularity is
more cumbersome to use for many cases, and doing ":(noglob)"
right would mean converting the whole codebase to use
"struct pathspec", as the usual "const char **pathspec"
cannot represent extra per-item flags.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-12-20 06:37:30 +08:00
|
|
|
|
|
|
|
int limit_pathspec_to_literal(void)
|
|
|
|
{
|
|
|
|
static int flag = -1;
|
|
|
|
if (flag < 0)
|
|
|
|
flag = git_env_bool(GIT_LITERAL_PATHSPECS_ENVIRONMENT, 0);
|
|
|
|
return flag;
|
|
|
|
}
|
2013-01-24 13:19:10 +08:00
|
|
|
|
2013-01-07 00:58:05 +08:00
|
|
|
/*
|
|
|
|
* Frees memory within dir which was allocated for exclude lists and
|
|
|
|
* the exclude_stack. Does not free dir itself.
|
|
|
|
*/
|
|
|
|
void clear_directory(struct dir_struct *dir)
|
|
|
|
{
|
|
|
|
int i, j;
|
|
|
|
struct exclude_list_group *group;
|
|
|
|
struct exclude_list *el;
|
|
|
|
struct exclude_stack *stk;
|
|
|
|
|
|
|
|
for (i = EXC_CMDL; i <= EXC_FILE; i++) {
|
|
|
|
group = &dir->exclude_list_group[i];
|
|
|
|
for (j = 0; j < group->nr; j++) {
|
|
|
|
el = &group->el[j];
|
|
|
|
if (i == EXC_DIRS)
|
|
|
|
free((char *)el->src);
|
|
|
|
clear_exclude_list(el);
|
|
|
|
}
|
|
|
|
free(group->el);
|
|
|
|
}
|
|
|
|
|
|
|
|
stk = dir->exclude_stack;
|
|
|
|
while (stk) {
|
|
|
|
struct exclude_stack *prev = stk->prev;
|
|
|
|
free(stk);
|
|
|
|
stk = prev;
|
|
|
|
}
|
|
|
|
}
|