git/pathspec.c

888 строки
22 KiB
C
Исходник Обычный вид История

#include "git-compat-util.h"
#include "abspath.h"
#include "parse.h"
#include "dir.h"
#include "environment.h"
#include "gettext.h"
#include "pathspec.h"
#include "attr.h"
#include "read-cache.h"
#include "repository.h"
#include "setup.h"
#include "strvec.h"
#include "symlinks.h"
#include "quote.h"
#include "wildmatch.h"
/*
* Finds which of the given pathspecs match items in the index.
*
* For each pathspec, sets the corresponding entry in the seen[] array
* (which should be specs items long, i.e. the same size as pathspec)
* to the nature of the "closest" (i.e. most specific) match found for
* that pathspec in the index, if it was a closer type of match than
* the existing entry. As an optimization, matching is skipped
* altogether if seen[] already only contains non-zero entries.
*
* If seen[] has not already been written to, it may make sense
* to use find_pathspecs_matching_against_index() instead.
*/
void add_pathspec_matches_against_index(const struct pathspec *pathspec,
struct index_state *istate,
char *seen,
enum ps_skip_worktree_action sw_action)
{
int num_unmatched = 0, i;
/*
* Since we are walking the index as if we were walking the directory,
* we have to mark the matched pathspec as seen; otherwise we will
* mistakenly think that the user gave a pathspec that did not match
* anything.
*/
for (i = 0; i < pathspec->nr; i++)
if (!seen[i])
num_unmatched++;
if (!num_unmatched)
return;
for (i = 0; i < istate->cache_nr; i++) {
const struct cache_entry *ce = istate->cache[i];
if (sw_action == PS_IGNORE_SKIP_WORKTREE &&
(ce_skip_worktree(ce) || !path_in_sparse_checkout(ce->name, istate)))
continue;
ce_path_match(istate, ce, pathspec, seen);
}
}
/*
* Finds which of the given pathspecs match items in the index.
*
* This is a one-shot wrapper around add_pathspec_matches_against_index()
* which allocates, populates, and returns a seen[] array indicating the
* nature of the "closest" (i.e. most specific) matches which each of the
* given pathspecs achieves against all items in the index.
*/
char *find_pathspecs_matching_against_index(const struct pathspec *pathspec,
struct index_state *istate,
enum ps_skip_worktree_action sw_action)
{
char *seen = xcalloc(pathspec->nr, 1);
add_pathspec_matches_against_index(pathspec, istate, seen, sw_action);
return seen;
}
char *find_pathspecs_matching_skip_worktree(const struct pathspec *pathspec)
{
struct index_state *istate = the_repository->index;
char *seen = xcalloc(pathspec->nr, 1);
int i;
for (i = 0; i < istate->cache_nr; i++) {
struct cache_entry *ce = istate->cache[i];
if (ce_skip_worktree(ce) || !path_in_sparse_checkout(ce->name, istate))
ce_path_match(istate, ce, pathspec, seen);
}
return seen;
}
/*
* Magic pathspec
*
* Possible future magic semantics include stuff like:
*
* { PATHSPEC_RECURSIVE, '*', "recursive" },
* { PATHSPEC_REGEXP, '\0', "regexp" },
*
*/
static struct pathspec_magic {
unsigned bit;
char mnemonic; /* this cannot be ':'! */
const char *name;
} pathspec_magic[] = {
{ PATHSPEC_FROMTOP, '/', "top" },
{ PATHSPEC_LITERAL, '\0', "literal" },
{ PATHSPEC_GLOB, '\0', "glob" },
{ PATHSPEC_ICASE, '\0', "icase" },
{ PATHSPEC_EXCLUDE, '!', "exclude" },
{ PATHSPEC_ATTR, '\0', "attr" },
};
attr: enable attr pathspec magic for git-add and git-stash Allow users to limit or exclude files based on file attributes during git-add and git-stash. For example, the chromium project would like to use $ git add . ':(exclude,attr:submodule)' as submodules are managed by an external tool, forbidding end users to record changes with "git add". Allowing "git add" to often records changes that users do not want in their commits. This commit does not change any attr magic implementation. It is only adding attr as an allowed pathspec in git-add and git-stash, which was previously blocked by GUARD_PATHSPEC and a pathspec mask in parse_pathspec()). However, we fix a bug in prefix_magic() where attr values were unintentionally removed. This was triggerable when parse_pathspec() is called with PATHSPEC_PREFIX_ORIGIN as a flag, which was the case for git-stash (Bug originally filed here [*]) Furthermore, while other commands hit this code path it did not result in unexpected behavior because this bug only impacts the pathspec->items->original field which is NOT used to filter paths. However, git-stash does use pathspec->items->original when building args used to call other git commands. (See add_pathspecs() usage and implementation in stash.c) It is possible that when the attr pathspec feature was first added in b0db704652 (pathspec: allow querying for attributes, 2017-03-13), "PATHSPEC_ATTR" was just unintentionally left out of a few GUARD_PATHSPEC() invocations. Later, to get a more user-friendly error message when attr was used with git-add, PATHSPEC_ATTR was added as a mask to git-add's invocation of parse_pathspec() 84d938b732 (add: do not accept pathspec magic 'attr', 2018-09-18). However, this user-friendly error message was never added for git-stash. [Reference] * https://lore.kernel.org/git/CAMmZTi-0QKtj7Q=sbC5qhipGsQxJFOY-Qkk1jfkRYwfF5FcUVg@mail.gmail.com/) Signed-off-by: Joanna Wang <jojwang@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-11-03 19:34:48 +03:00
static void prefix_magic(struct strbuf *sb, int prefixlen,
unsigned magic, const char *element)
{
attr: enable attr pathspec magic for git-add and git-stash Allow users to limit or exclude files based on file attributes during git-add and git-stash. For example, the chromium project would like to use $ git add . ':(exclude,attr:submodule)' as submodules are managed by an external tool, forbidding end users to record changes with "git add". Allowing "git add" to often records changes that users do not want in their commits. This commit does not change any attr magic implementation. It is only adding attr as an allowed pathspec in git-add and git-stash, which was previously blocked by GUARD_PATHSPEC and a pathspec mask in parse_pathspec()). However, we fix a bug in prefix_magic() where attr values were unintentionally removed. This was triggerable when parse_pathspec() is called with PATHSPEC_PREFIX_ORIGIN as a flag, which was the case for git-stash (Bug originally filed here [*]) Furthermore, while other commands hit this code path it did not result in unexpected behavior because this bug only impacts the pathspec->items->original field which is NOT used to filter paths. However, git-stash does use pathspec->items->original when building args used to call other git commands. (See add_pathspecs() usage and implementation in stash.c) It is possible that when the attr pathspec feature was first added in b0db704652 (pathspec: allow querying for attributes, 2017-03-13), "PATHSPEC_ATTR" was just unintentionally left out of a few GUARD_PATHSPEC() invocations. Later, to get a more user-friendly error message when attr was used with git-add, PATHSPEC_ATTR was added as a mask to git-add's invocation of parse_pathspec() 84d938b732 (add: do not accept pathspec magic 'attr', 2018-09-18). However, this user-friendly error message was never added for git-stash. [Reference] * https://lore.kernel.org/git/CAMmZTi-0QKtj7Q=sbC5qhipGsQxJFOY-Qkk1jfkRYwfF5FcUVg@mail.gmail.com/) Signed-off-by: Joanna Wang <jojwang@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-11-03 19:34:48 +03:00
/* No magic was found in element, just add prefix magic */
if (!magic) {
strbuf_addf(sb, ":(prefix:%d)", prefixlen);
return;
}
/*
* At this point, we know that parse_element_magic() was able
* to extract some pathspec magic from element. So we know
* element is correctly formatted in either shorthand or
* longhand form
*/
if (element[1] != '(') {
/* Process an element in shorthand form (e.g. ":!/<match>") */
strbuf_addstr(sb, ":(");
for (int i = 0; i < ARRAY_SIZE(pathspec_magic); i++) {
if ((magic & pathspec_magic[i].bit) &&
pathspec_magic[i].mnemonic) {
if (sb->buf[sb->len - 1] != '(')
strbuf_addch(sb, ',');
strbuf_addstr(sb, pathspec_magic[i].name);
}
}
attr: enable attr pathspec magic for git-add and git-stash Allow users to limit or exclude files based on file attributes during git-add and git-stash. For example, the chromium project would like to use $ git add . ':(exclude,attr:submodule)' as submodules are managed by an external tool, forbidding end users to record changes with "git add". Allowing "git add" to often records changes that users do not want in their commits. This commit does not change any attr magic implementation. It is only adding attr as an allowed pathspec in git-add and git-stash, which was previously blocked by GUARD_PATHSPEC and a pathspec mask in parse_pathspec()). However, we fix a bug in prefix_magic() where attr values were unintentionally removed. This was triggerable when parse_pathspec() is called with PATHSPEC_PREFIX_ORIGIN as a flag, which was the case for git-stash (Bug originally filed here [*]) Furthermore, while other commands hit this code path it did not result in unexpected behavior because this bug only impacts the pathspec->items->original field which is NOT used to filter paths. However, git-stash does use pathspec->items->original when building args used to call other git commands. (See add_pathspecs() usage and implementation in stash.c) It is possible that when the attr pathspec feature was first added in b0db704652 (pathspec: allow querying for attributes, 2017-03-13), "PATHSPEC_ATTR" was just unintentionally left out of a few GUARD_PATHSPEC() invocations. Later, to get a more user-friendly error message when attr was used with git-add, PATHSPEC_ATTR was added as a mask to git-add's invocation of parse_pathspec() 84d938b732 (add: do not accept pathspec magic 'attr', 2018-09-18). However, this user-friendly error message was never added for git-stash. [Reference] * https://lore.kernel.org/git/CAMmZTi-0QKtj7Q=sbC5qhipGsQxJFOY-Qkk1jfkRYwfF5FcUVg@mail.gmail.com/) Signed-off-by: Joanna Wang <jojwang@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-11-03 19:34:48 +03:00
} else {
/* For the longhand form, we copy everything up to the final ')' */
size_t len = strchr(element, ')') - element;
strbuf_add(sb, element, len);
}
strbuf_addf(sb, ",prefix:%d)", prefixlen);
}
static size_t strcspn_escaped(const char *s, const char *stop)
{
const char *i;
for (i = s; *i; i++) {
/* skip the escaped character */
if (i[0] == '\\' && i[1]) {
i++;
continue;
}
if (strchr(stop, *i))
break;
}
return i - s;
}
static inline int invalid_value_char(const char ch)
{
if (isalnum(ch) || strchr(",-_", ch))
return 0;
return -1;
}
static char *attr_value_unescape(const char *value)
{
const char *src;
char *dst, *ret;
ret = xmallocz(strlen(value));
for (src = value, dst = ret; *src; src++, dst++) {
if (*src == '\\') {
if (!src[1])
die(_("Escape character '\\' not allowed as "
"last character in attr value"));
src++;
}
if (invalid_value_char(*src))
die("cannot use '%c' for value matching", *src);
*dst = *src;
}
*dst = '\0';
return ret;
}
static void parse_pathspec_attr_match(struct pathspec_item *item, const char *value)
{
struct string_list_item *si;
struct string_list list = STRING_LIST_INIT_DUP;
if (item->attr_check || item->attr_match)
die(_("Only one 'attr:' specification is allowed."));
if (!value || !*value)
die(_("attr spec must not be empty"));
string_list_split(&list, value, ' ', -1);
string_list_remove_empty_items(&list, 0);
item->attr_check = attr_check_alloc();
CALLOC_ARRAY(item->attr_match, list.nr);
for_each_string_list_item(si, &list) {
size_t attr_len;
char *attr_name;
const struct git_attr *a;
int j = item->attr_match_nr++;
const char *attr = si->string;
struct attr_match *am = &item->attr_match[j];
switch (*attr) {
case '!':
am->match_mode = MATCH_UNSPECIFIED;
attr++;
attr_len = strlen(attr);
break;
case '-':
am->match_mode = MATCH_UNSET;
attr++;
attr_len = strlen(attr);
break;
default:
attr_len = strcspn(attr, "=");
if (attr[attr_len] != '=')
am->match_mode = MATCH_SET;
else {
const char *v = &attr[attr_len + 1];
am->match_mode = MATCH_VALUE;
am->value = attr_value_unescape(v);
}
break;
}
attr_name = xmemdupz(attr, attr_len);
a = git_attr(attr_name);
if (!a)
die(_("invalid attribute name %s"), attr_name);
attr_check_append(item->attr_check, a);
free(attr_name);
}
if (item->attr_check->nr != item->attr_match_nr)
BUG("should have same number of entries");
string_list_clear(&list, 0);
}
static inline int get_literal_global(void)
{
static int literal = -1;
if (literal < 0)
literal = git_env_bool(GIT_LITERAL_PATHSPECS_ENVIRONMENT, 0);
return literal;
}
static inline int get_glob_global(void)
{
static int glob = -1;
if (glob < 0)
glob = git_env_bool(GIT_GLOB_PATHSPECS_ENVIRONMENT, 0);
return glob;
}
static inline int get_noglob_global(void)
{
static int noglob = -1;
if (noglob < 0)
noglob = git_env_bool(GIT_NOGLOB_PATHSPECS_ENVIRONMENT, 0);
return noglob;
}
static inline int get_icase_global(void)
{
static int icase = -1;
if (icase < 0)
icase = git_env_bool(GIT_ICASE_PATHSPECS_ENVIRONMENT, 0);
return icase;
}
static int get_global_magic(int element_magic)
{
int global_magic = 0;
if (get_literal_global())
global_magic |= PATHSPEC_LITERAL;
/* --glob-pathspec is overridden by :(literal) */
if (get_glob_global() && !(element_magic & PATHSPEC_LITERAL))
global_magic |= PATHSPEC_GLOB;
if (get_glob_global() && get_noglob_global())
die(_("global 'glob' and 'noglob' pathspec settings are incompatible"));
if (get_icase_global())
global_magic |= PATHSPEC_ICASE;
if ((global_magic & PATHSPEC_LITERAL) &&
(global_magic & ~PATHSPEC_LITERAL))
die(_("global 'literal' pathspec setting is incompatible "
"with all other global pathspec settings"));
/* --noglob-pathspec adds :(literal) _unless_ :(glob) is specified */
if (get_noglob_global() && !(element_magic & PATHSPEC_GLOB))
global_magic |= PATHSPEC_LITERAL;
return global_magic;
}
/*
* Parse the pathspec element looking for long magic
*
* saves all magic in 'magic'
* if prefix magic is used, save the prefix length in 'prefix_len'
* returns the position in 'elem' after all magic has been parsed
*/
static const char *parse_long_magic(unsigned *magic, int *prefix_len,
struct pathspec_item *item,
const char *elem)
{
const char *pos;
const char *nextat;
for (pos = elem + 2; *pos && *pos != ')'; pos = nextat) {
size_t len = strcspn_escaped(pos, ",)");
int i;
if (pos[len] == ',')
nextat = pos + len + 1; /* handle ',' */
else
nextat = pos + len; /* handle ')' and '\0' */
if (!len)
continue;
if (starts_with(pos, "prefix:")) {
char *endptr;
*prefix_len = strtol(pos + 7, &endptr, 10);
if (endptr - pos != len)
die(_("invalid parameter for pathspec magic 'prefix'"));
continue;
}
if (starts_with(pos, "attr:")) {
char *attr_body = xmemdupz(pos + 5, len - 5);
parse_pathspec_attr_match(item, attr_body);
*magic |= PATHSPEC_ATTR;
free(attr_body);
continue;
}
for (i = 0; i < ARRAY_SIZE(pathspec_magic); i++) {
if (strlen(pathspec_magic[i].name) == len &&
!strncmp(pathspec_magic[i].name, pos, len)) {
*magic |= pathspec_magic[i].bit;
break;
}
}
if (ARRAY_SIZE(pathspec_magic) <= i)
die(_("Invalid pathspec magic '%.*s' in '%s'"),
(int) len, pos, elem);
}
if (*pos != ')')
die(_("Missing ')' at the end of pathspec magic in '%s'"),
elem);
pos++;
return pos;
}
/*
* Parse the pathspec element looking for short magic
*
* saves all magic in 'magic'
* returns the position in 'elem' after all magic has been parsed
*/
static const char *parse_short_magic(unsigned *magic, const char *elem)
{
const char *pos;
for (pos = elem + 1; *pos && *pos != ':'; pos++) {
char ch = *pos;
int i;
/* Special case alias for '!' */
if (ch == '^') {
*magic |= PATHSPEC_EXCLUDE;
continue;
}
if (!is_pathspec_magic(ch))
break;
for (i = 0; i < ARRAY_SIZE(pathspec_magic); i++) {
if (pathspec_magic[i].mnemonic == ch) {
*magic |= pathspec_magic[i].bit;
break;
}
}
if (ARRAY_SIZE(pathspec_magic) <= i)
die(_("Unimplemented pathspec magic '%c' in '%s'"),
ch, elem);
}
if (*pos == ':')
pos++;
return pos;
}
static const char *parse_element_magic(unsigned *magic, int *prefix_len,
struct pathspec_item *item,
const char *elem)
{
if (elem[0] != ':' || get_literal_global())
return elem; /* nothing to do */
else if (elem[1] == '(')
/* longhand */
return parse_long_magic(magic, prefix_len, item, elem);
else
/* shorthand */
return parse_short_magic(magic, elem);
}
/*
* Perform the initialization of a pathspec_item based on a pathspec element.
*/
static void init_pathspec_item(struct pathspec_item *item, unsigned flags,
const char *prefix, int prefixlen,
const char *elt)
{
unsigned magic = 0, element_magic = 0;
const char *copyfrom = elt;
char *match;
int pathspec_prefix = -1;
item->attr_check = NULL;
item->attr_match = NULL;
item->attr_match_nr = 0;
/* PATHSPEC_LITERAL_PATH ignores magic */
if (flags & PATHSPEC_LITERAL_PATH) {
magic = PATHSPEC_LITERAL;
} else {
copyfrom = parse_element_magic(&element_magic,
&pathspec_prefix,
item,
elt);
magic |= element_magic;
magic |= get_global_magic(element_magic);
}
item->magic = magic;
if (pathspec_prefix >= 0 &&
(prefixlen || (prefix && *prefix)))
BUG("'prefix' magic is supposed to be used at worktree's root");
if ((magic & PATHSPEC_LITERAL) && (magic & PATHSPEC_GLOB))
die(_("%s: 'literal' and 'glob' are incompatible"), elt);
/* Create match string which will be used for pathspec matching */
if (pathspec_prefix >= 0) {
match = xstrdup(copyfrom);
prefixlen = pathspec_prefix;
} else if (magic & PATHSPEC_FROMTOP) {
match = xstrdup(copyfrom);
prefixlen = 0;
} else {
match = prefix_path_gently(prefix, prefixlen,
&prefixlen, copyfrom);
if (!match) {
const char *hint_path;
if (!have_git_dir())
die(_("'%s' is outside the directory tree"),
copyfrom);
hint_path = get_git_work_tree();
if (!hint_path)
hint_path = get_git_dir();
die(_("%s: '%s' is outside repository at '%s'"), elt,
copyfrom, absolute_path(hint_path));
}
}
item->match = match;
item->len = strlen(item->match);
item->prefix = prefixlen;
/*
* Prefix the pathspec (keep all magic) and assign to
* original. Useful for passing to another command.
*/
if ((flags & PATHSPEC_PREFIX_ORIGIN) &&
pathspec: honor `PATHSPEC_PREFIX_ORIGIN` with empty prefix Previous to commit 5d8f084a5 (pathspec: simpler logic to prefix original pathspec elements, 2017-01-04), we were always using the computed `match` variable to perform pathspec matching whenever `PATHSPEC_PREFIX_ORIGIN` is set. This is for example useful when passing the parsed pathspecs to other commands, as the computed `match` may contain a pathspec relative to the repository root. The commit changed this logic to only do so when we do have an actual prefix and when literal pathspecs are deactivated. But this change may actually break some commands which expect passed pathspecs to be relative to the repository root. One such case is `git add --patch`, which now fails when using relative paths from a subdirectory. For example if executing "git add -p ../foo.c" in a subdirectory, the `git-add--interactive` command will directly pass "../foo.c" to `git-ls-files`. As ls-files is executed at the repository's root, the command will notice that "../foo.c" is outside the repository and fail. Fix the issue by again using the computed `match` variable when `PATHSPEC_PREFIX_ORIGIN` is set and global literal pathspecs are deactivated. Note that in contrast to previous behavior, we will now always call `prefix_magic` regardless of whether a prefix is actually set. But this is the right thing to do: when the `match` variable has been resolved to the repository's root, it will be set to an empty string. When passing the empty string directly to other commands, it will result in a warning regarding deprecated empty pathspecs. By always adding the prefix magic, we will end up with at least the string ":(prefix:0)" and thus avoid the warning. Signed-off-by: Patrick Steinhardt <ps@pks.im> Acked-by: Brandon Williams <bmwill@google.com> Reviewed-by: Duy Nguyen <pclouds@gmail.com>
2017-04-04 12:16:56 +03:00
!get_literal_global()) {
struct strbuf sb = STRBUF_INIT;
/* Preserve the actual prefix length of each pattern */
attr: enable attr pathspec magic for git-add and git-stash Allow users to limit or exclude files based on file attributes during git-add and git-stash. For example, the chromium project would like to use $ git add . ':(exclude,attr:submodule)' as submodules are managed by an external tool, forbidding end users to record changes with "git add". Allowing "git add" to often records changes that users do not want in their commits. This commit does not change any attr magic implementation. It is only adding attr as an allowed pathspec in git-add and git-stash, which was previously blocked by GUARD_PATHSPEC and a pathspec mask in parse_pathspec()). However, we fix a bug in prefix_magic() where attr values were unintentionally removed. This was triggerable when parse_pathspec() is called with PATHSPEC_PREFIX_ORIGIN as a flag, which was the case for git-stash (Bug originally filed here [*]) Furthermore, while other commands hit this code path it did not result in unexpected behavior because this bug only impacts the pathspec->items->original field which is NOT used to filter paths. However, git-stash does use pathspec->items->original when building args used to call other git commands. (See add_pathspecs() usage and implementation in stash.c) It is possible that when the attr pathspec feature was first added in b0db704652 (pathspec: allow querying for attributes, 2017-03-13), "PATHSPEC_ATTR" was just unintentionally left out of a few GUARD_PATHSPEC() invocations. Later, to get a more user-friendly error message when attr was used with git-add, PATHSPEC_ATTR was added as a mask to git-add's invocation of parse_pathspec() 84d938b732 (add: do not accept pathspec magic 'attr', 2018-09-18). However, this user-friendly error message was never added for git-stash. [Reference] * https://lore.kernel.org/git/CAMmZTi-0QKtj7Q=sbC5qhipGsQxJFOY-Qkk1jfkRYwfF5FcUVg@mail.gmail.com/) Signed-off-by: Joanna Wang <jojwang@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-11-03 19:34:48 +03:00
prefix_magic(&sb, prefixlen, element_magic, elt);
strbuf_addstr(&sb, match);
item->original = strbuf_detach(&sb, NULL);
} else {
item->original = xstrdup(elt);
}
if (magic & PATHSPEC_LITERAL) {
item->nowildcard_len = item->len;
} else {
item->nowildcard_len = simple_length(item->match);
if (item->nowildcard_len < prefixlen)
item->nowildcard_len = prefixlen;
}
item->flags = 0;
if (magic & PATHSPEC_GLOB) {
/*
* FIXME: should we enable ONESTAR in _GLOB for
* pattern "* * / * . c"?
*/
} else {
if (item->nowildcard_len < item->len &&
item->match[item->nowildcard_len] == '*' &&
no_wildcard(item->match + item->nowildcard_len + 1))
item->flags |= PATHSPEC_ONESTAR;
}
/* sanity checks, pathspec matchers assume these are sane */
pathspec: give better message for submodule related pathspec error Every once in a while someone complains to the mailing list to have run into this weird assertion[1]. The usual response from the mailing list is link to old discussions[2], and acknowledging the problem stating it is known. This patch accomplishes two things: 1. Switch assert() to die("BUG") to give a more readable message. 2. Take one of the cases where we hit a BUG and turn it into a normal "there was something wrong with the input" message. This assertion triggered for cases where there wasn't a programming bug, but just bogus input. In particular, if the user asks for a pathspec that is inside a submodule, we shouldn't assert() or die("BUG"); we should tell the user their request is bogus. The only reason we did not check for it, is the expensive nature of such a check, so callers avoid setting the flag PATHSPEC_STRIP_SUBMODULE_SLASH_EXPENSIVE. However when we die due to bogus input, the expense of CPU cycles spent outweighs the user wondering what went wrong, so run that check unconditionally before dying with a more generic error message. Note: There is a case (e.g. "git -C submodule add .") in which we call strip_submodule_slash_expensive, as git-add requests it via the flag PATHSPEC_STRIP_SUBMODULE_SLASH_EXPENSIVE, but the assert used to trigger nevertheless, because the flag PATHSPEC_LITERAL was not set, such that we executed if (item->nowildcard_len < prefixlen) item->nowildcard_len = prefixlen; and prefixlen was not adapted (e.g. it was computed from "submodule/") So in the die_inside_submodule_path function we also need handle paths, that were stripped before, i.e. are the exact submodule path. This is why the conditions in die_inside_submodule_path are slightly different than in strip_submodule_slash_expensive. [1] https://www.google.com/search?q=item-%3Enowildcard_len [2] http://git.661346.n2.nabble.com/assert-failed-in-submodule-edge-case-td7628687.html https://www.spinics.net/lists/git/msg249473.html Helped-by: Jeff King <peff@peff.net> Helped-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Stefan Beller <sbeller@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-01-10 02:16:50 +03:00
if (item->nowildcard_len > item->len ||
item->prefix > item->len) {
BUG("error initializing pathspec_item");
pathspec: give better message for submodule related pathspec error Every once in a while someone complains to the mailing list to have run into this weird assertion[1]. The usual response from the mailing list is link to old discussions[2], and acknowledging the problem stating it is known. This patch accomplishes two things: 1. Switch assert() to die("BUG") to give a more readable message. 2. Take one of the cases where we hit a BUG and turn it into a normal "there was something wrong with the input" message. This assertion triggered for cases where there wasn't a programming bug, but just bogus input. In particular, if the user asks for a pathspec that is inside a submodule, we shouldn't assert() or die("BUG"); we should tell the user their request is bogus. The only reason we did not check for it, is the expensive nature of such a check, so callers avoid setting the flag PATHSPEC_STRIP_SUBMODULE_SLASH_EXPENSIVE. However when we die due to bogus input, the expense of CPU cycles spent outweighs the user wondering what went wrong, so run that check unconditionally before dying with a more generic error message. Note: There is a case (e.g. "git -C submodule add .") in which we call strip_submodule_slash_expensive, as git-add requests it via the flag PATHSPEC_STRIP_SUBMODULE_SLASH_EXPENSIVE, but the assert used to trigger nevertheless, because the flag PATHSPEC_LITERAL was not set, such that we executed if (item->nowildcard_len < prefixlen) item->nowildcard_len = prefixlen; and prefixlen was not adapted (e.g. it was computed from "submodule/") So in the die_inside_submodule_path function we also need handle paths, that were stripped before, i.e. are the exact submodule path. This is why the conditions in die_inside_submodule_path are slightly different than in strip_submodule_slash_expensive. [1] https://www.google.com/search?q=item-%3Enowildcard_len [2] http://git.661346.n2.nabble.com/assert-failed-in-submodule-edge-case-td7628687.html https://www.spinics.net/lists/git/msg249473.html Helped-by: Jeff King <peff@peff.net> Helped-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Stefan Beller <sbeller@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-01-10 02:16:50 +03:00
}
}
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);
}
void pathspec_magic_names(unsigned magic, struct strbuf *out)
{
int i;
for (i = 0; i < ARRAY_SIZE(pathspec_magic); i++) {
const struct pathspec_magic *m = pathspec_magic + i;
if (!(magic & m->bit))
continue;
if (out->len)
strbuf_addstr(out, ", ");
if (m->mnemonic)
strbuf_addf(out, _("'%s' (mnemonic: '%c')"),
m->name, m->mnemonic);
else
strbuf_addf(out, "'%s'", m->name);
}
}
static void NORETURN unsupported_magic(const char *pattern,
unsigned magic)
{
struct strbuf sb = STRBUF_INIT;
pathspec_magic_names(magic, &sb);
/*
* We may want to substitute "this command" with a command
* name. E.g. when "git add -p" or "git add -i" dies when running
* "checkout -p"
*/
die(_("%s: pathspec magic not supported by this command: %s"),
pattern, sb.buf);
}
void parse_pathspec(struct pathspec *pathspec,
unsigned magic_mask, unsigned flags,
const char *prefix, const char **argv)
{
struct pathspec_item *item;
const char *entry = argv ? *argv : NULL;
int i, n, prefixlen, nr_exclude = 0;
memset(pathspec, 0, sizeof(*pathspec));
if (flags & PATHSPEC_MAXDEPTH_VALID)
pathspec->magic |= PATHSPEC_MAXDEPTH;
/* No arguments, no prefix -> no pathspec */
if (!entry && !prefix)
return;
if ((flags & PATHSPEC_PREFER_CWD) &&
(flags & PATHSPEC_PREFER_FULL))
BUG("PATHSPEC_PREFER_CWD and PATHSPEC_PREFER_FULL are incompatible");
/* No arguments with prefix -> prefix pathspec */
if (!entry) {
if (flags & PATHSPEC_PREFER_FULL)
return;
if (!(flags & PATHSPEC_PREFER_CWD))
BUG("PATHSPEC_PREFER_CWD requires arguments");
pathspec->items = CALLOC_ARRAY(item, 1);
item->match = xstrdup(prefix);
item->original = xstrdup(prefix);
item->nowildcard_len = item->len = strlen(prefix);
item->prefix = item->len;
pathspec->nr = 1;
return;
}
n = 0;
while (argv[n]) {
if (*argv[n] == '\0')
die("empty string is not a valid pathspec. "
"please use . instead if you meant to match all paths");
n++;
}
pathspec->nr = n;
ALLOC_ARRAY(pathspec->items, n + 1);
item = pathspec->items;
prefixlen = prefix ? strlen(prefix) : 0;
for (i = 0; i < n; i++) {
entry = argv[i];
init_pathspec_item(item + i, flags, prefix, prefixlen, entry);
if (item[i].magic & PATHSPEC_EXCLUDE)
nr_exclude++;
if (item[i].magic & magic_mask)
unsupported_magic(entry, item[i].magic & magic_mask);
if ((flags & PATHSPEC_SYMLINK_LEADING_PATH) &&
has_symlink_leading_path(item[i].match, item[i].len)) {
die(_("pathspec '%s' is beyond a symbolic link"), entry);
}
if (item[i].nowildcard_len < item[i].len)
pathspec->has_wildcard = 1;
pathspec->magic |= item[i].magic;
}
/*
* If everything is an exclude pattern, add one positive pattern
* that matches everything. We allocated an extra one for this.
*/
if (nr_exclude == n) {
int plen = (!(flags & PATHSPEC_PREFER_CWD)) ? 0 : prefixlen;
pathspec: correct an empty string used as a pathspec element Pathspecs with only negative elements did not work with some commands that pass the pathspec along to a subprocess. For instance, $ git add -p -- ':!*.txt' should add everything except for paths ending in ".txt", but it gets complaint from underlying "diff-index" and aborts. We used to error out when a pathspec with only negative elements in it, like the one in the above example. Later, 859b7f1d (pathspec: don't error out on all-exclusionary pathspec patterns, 2017-02-07) updated the logic to add an empty string as an extra element. The intention was to let the extra element to match everything and let the negative ones given by the user to subtract from it. At around the same time, we were migrating from "an empty string is a valid pathspec element that matches everything" to "either a dot or ":/" is used to match all, and an empty string is rejected", between d426430e (pathspec: warn on empty strings as pathspec, 2016-06-22) and 9e4e8a64 (pathspec: die on empty strings as pathspec, 2017-06-06). I think 9e4e8a64, which happened long after 859b7f1d happened, was not careful enough to turn the empty string 859b7f1d added to either a dot or ":/". A care should be taken as the definition of "everything" depends on subcommand. For the purpose of "add -p", adding a "." to add everything in the current directory is the right thing to do. But for some other commands, ":/" (i.e. really really everything, even things outside the current subdirectory) is the right choice. We would break commands in a big way if we get this wrong, so add a handful of test pieces to make sure the resulting code still excludes the paths that are expected and includes "everything" else. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-05-30 01:39:51 +03:00
init_pathspec_item(item + n, 0, prefix, plen, ".");
pathspec->nr++;
}
if (pathspec->magic & PATHSPEC_MAXDEPTH) {
if (flags & PATHSPEC_KEEP_ORDER)
BUG("PATHSPEC_MAXDEPTH_VALID and PATHSPEC_KEEP_ORDER are incompatible");
QSORT(pathspec->items, pathspec->nr, pathspec_item_cmp);
}
}
void parse_pathspec_file(struct pathspec *pathspec, unsigned magic_mask,
unsigned flags, const char *prefix,
const char *file, int nul_term_line)
{
struct strvec parsed_file = STRVEC_INIT;
strbuf_getline_fn getline_fn = nul_term_line ? strbuf_getline_nul :
strbuf_getline;
struct strbuf buf = STRBUF_INIT;
struct strbuf unquoted = STRBUF_INIT;
FILE *in;
if (!strcmp(file, "-"))
in = stdin;
else
in = xfopen(file, "r");
while (getline_fn(&buf, in) != EOF) {
if (!nul_term_line && buf.buf[0] == '"') {
strbuf_reset(&unquoted);
if (unquote_c_style(&unquoted, buf.buf, NULL))
die(_("line is badly quoted: %s"), buf.buf);
strbuf_swap(&buf, &unquoted);
}
strvec_push(&parsed_file, buf.buf);
strbuf_reset(&buf);
}
strbuf_release(&unquoted);
strbuf_release(&buf);
if (in != stdin)
fclose(in);
parse_pathspec(pathspec, magic_mask, flags, prefix, parsed_file.v);
strvec_clear(&parsed_file);
}
void copy_pathspec(struct pathspec *dst, const struct pathspec *src)
{
int i, j;
*dst = *src;
DUP_ARRAY(dst->items, src->items, dst->nr);
for (i = 0; i < dst->nr; i++) {
struct pathspec_item *d = &dst->items[i];
struct pathspec_item *s = &src->items[i];
d->match = xstrdup(s->match);
d->original = xstrdup(s->original);
DUP_ARRAY(d->attr_match, s->attr_match, d->attr_match_nr);
for (j = 0; j < d->attr_match_nr; j++) {
const char *value = s->attr_match[j].value;
d->attr_match[j].value = xstrdup_or_null(value);
}
d->attr_check = attr_check_dup(s->attr_check);
}
}
void clear_pathspec(struct pathspec *pathspec)
{
int i, j;
for (i = 0; i < pathspec->nr; i++) {
free(pathspec->items[i].match);
free(pathspec->items[i].original);
for (j = 0; j < pathspec->items[i].attr_match_nr; j++)
free(pathspec->items[i].attr_match[j].value);
free(pathspec->items[i].attr_match);
if (pathspec->items[i].attr_check)
attr_check_free(pathspec->items[i].attr_check);
}
FREE_AND_NULL(pathspec->items);
pathspec->nr = 0;
}
int match_pathspec_attrs(struct index_state *istate,
const char *name, int namelen,
const struct pathspec_item *item)
{
int i;
char *to_free = NULL;
if (name[namelen])
name = to_free = xmemdupz(name, namelen);
git_check_attr(istate, name, item->attr_check);
free(to_free);
for (i = 0; i < item->attr_match_nr; i++) {
const char *value;
int matched;
enum attr_match_mode match_mode;
value = item->attr_check->items[i].value;
match_mode = item->attr_match[i].match_mode;
if (ATTR_TRUE(value))
matched = (match_mode == MATCH_SET);
else if (ATTR_FALSE(value))
matched = (match_mode == MATCH_UNSET);
else if (ATTR_UNSET(value))
matched = (match_mode == MATCH_UNSPECIFIED);
else
matched = (match_mode == MATCH_VALUE &&
!strcmp(item->attr_match[i].value, value));
if (!matched)
return 0;
}
return 1;
}
int pathspec_needs_expanded_index(struct index_state *istate,
const struct pathspec *pathspec)
{
unsigned int i, pos;
int res = 0;
char *skip_worktree_seen = NULL;
/*
* If index is not sparse, no index expansion is needed.
*/
if (!istate->sparse_index)
return 0;
/*
* When using a magic pathspec, assume for the sake of simplicity that
* the index needs to be expanded to match all matchable files.
*/
if (pathspec->magic)
return 1;
for (i = 0; i < pathspec->nr; i++) {
struct pathspec_item item = pathspec->items[i];
/*
* If the pathspec item has a wildcard, the index should be expanded
* if the pathspec has the possibility of matching a subset of entries inside
* of a sparse directory (but not the entire directory).
*
* If the pathspec item is a literal path, the index only needs to be expanded
* if a) the pathspec isn't in the sparse checkout cone (to make sure we don't
* expand for in-cone files) and b) it doesn't match any sparse directories
* (since we can reset whole sparse directories without expanding them).
*/
if (item.nowildcard_len < item.len) {
/*
* Special case: if the pattern is a path inside the cone
* followed by only wildcards, the pattern cannot match
* partial sparse directories, so we know we don't need to
* expand the index.
*
* Examples:
* - in-cone/foo***: doesn't need expanded index
* - not-in-cone/bar*: may need expanded index
* - **.c: may need expanded index
*/
if (strspn(item.original + item.nowildcard_len, "*") == item.len - item.nowildcard_len &&
path_in_cone_mode_sparse_checkout(item.original, istate))
continue;
for (pos = 0; pos < istate->cache_nr; pos++) {
struct cache_entry *ce = istate->cache[pos];
if (!S_ISSPARSEDIR(ce->ce_mode))
continue;
/*
* If the pre-wildcard length is longer than the sparse
* directory name and the sparse directory is the first
* component of the pathspec, need to expand the index.
*/
if (item.nowildcard_len > ce_namelen(ce) &&
!strncmp(item.original, ce->name, ce_namelen(ce))) {
res = 1;
break;
}
/*
* If the pre-wildcard length is shorter than the sparse
* directory and the pathspec does not match the whole
* directory, need to expand the index.
*/
if (!strncmp(item.original, ce->name, item.nowildcard_len) &&
wildmatch(item.original, ce->name, 0)) {
res = 1;
break;
}
}
} else if (!path_in_cone_mode_sparse_checkout(item.original, istate) &&
!matches_skip_worktree(pathspec, i, &skip_worktree_seen))
res = 1;
if (res > 0)
break;
}
free(skip_worktree_seen);
return res;
}