microsoft
/
git
зеркало из https://github.com/microsoft/git.git
1
0
Форкнуть 0
Код Задачи Пакеты Проекты Релизы Вики Активность

Merge branch 'jc/grep-lookahead' 

* jc/grep-lookahead:
  grep --no-index: allow use of "git grep" outside a git repository
  grep: prepare to run outside of a work tree
  grep: rip out pessimization to use fixmatch()
  grep: rip out support for external grep
  grep: optimize built-in grep by skipping lines that do not hit

Conflicts:
	builtin-grep.c
	t/t7002-grep.sh
This commit is contained in:
Junio C Hamano 2010-01-20 14:43:41 -08:00
Родитель 886932e281 308162372d
Коммит 34349bea60
7 изменённых файлов: 166 добавлений и 370 удалений
Показать статистику Скачать Patch файл Скачать Diff файл Показать все файлы Свернуть все файлы

8
Documentation/config.txt
Просмотреть файл

@ -664,14 +664,6 @@ color.grep::
`never`), never. When set to `true` or `auto`, use color only
when the output is written to the terminal. Defaults to `false`.
color.grep.external::
The string value of this variable is passed to an external 'grep'
command as a command line option if match highlighting is turned
on. If set to an empty string, no option is passed at all,
turning off coloring for external 'grep' calls; this is the default.
For GNU grep, set it to `--color=always` to highlight matches even
when a pager is used.
color.grep.match::
Use customized color for matches. The value of this variable
may be specified as in color.branch.<slot>. It is passed using

10
Makefile
Просмотреть файл

@ -187,10 +187,6 @@ all::
# is a simplified version of the merge sort used in glibc. This is
# recommended if Git triggers O(n^2) behavior in your platform's qsort().
#
# Define NO_EXTERNAL_GREP if you don't want "git grep" to ever call
# your external grep (e.g., if your system lacks grep, if its grep is
# broken, or spawning external process is slower than built-in grep git has).
#
# Define UNRELIABLE_FSTAT if your system's fstat does not return the same
# information on a not yet closed file that lstat would return for the same
# file after it was closed.
@ -795,7 +791,6 @@ ifeq ($(uname_S),SunOS)
NO_MKDTEMP = YesPlease
NO_MKSTEMPS = YesPlease
NO_REGEX = YesPlease
NO_EXTERNAL_GREP = YesPlease
THREADED_DELTA_SEARCH = YesPlease
ifeq ($(uname_R),5.7)
NEEDS_RESOLV = YesPlease
@ -914,7 +909,6 @@ ifeq ($(uname_S),IRIX)
# NO_MMAP. If you suspect that your compiler is not affected by this
# issue, comment out the NO_MMAP statement.
NO_MMAP = YesPlease
NO_EXTERNAL_GREP = UnfortunatelyYes
SNPRINTF_RETURNS_BOGUS = YesPlease
SHELL_PATH = /usr/gnu/bin/bash
NEEDS_LIBGEN = YesPlease
@ -934,7 +928,6 @@ ifeq ($(uname_S),IRIX64)
# NO_MMAP. If you suspect that your compiler is not affected by this
# issue, comment out the NO_MMAP statement.
NO_MMAP = YesPlease
NO_EXTERNAL_GREP = UnfortunatelyYes
SNPRINTF_RETURNS_BOGUS = YesPlease
SHELL_PATH=/usr/gnu/bin/bash
NEEDS_LIBGEN = YesPlease
@ -1349,9 +1342,6 @@ endif
ifdef DIR_HAS_BSD_GROUP_SEMANTICS
COMPAT_CFLAGS += -DDIR_HAS_BSD_GROUP_SEMANTICS
endif
ifdef NO_EXTERNAL_GREP
BASIC_CFLAGS += -DNO_EXTERNAL_GREP
endif
ifdef UNRELIABLE_FSTAT
BASIC_CFLAGS += -DUNRELIABLE_FSTAT
endif

357
builtin-grep.c
Просмотреть файл

@ -14,14 +14,7 @@
#include "userdiff.h"
#include "grep.h"
#include "quote.h"
#ifndef NO_EXTERNAL_GREP
#ifdef __unix__
#define NO_EXTERNAL_GREP 0
#else
#define NO_EXTERNAL_GREP 1
#endif
#endif
#include "dir.h"
static char const * const grep_usage[] = {
"git grep [options] [-e] <pattern> [<rev>...] [[--] path...]",
@ -42,8 +35,6 @@ static int grep_config(const char *var, const char *value, void *cb)
opt->color = git_config_colorbool(var, value, -1);
return 0;
}
if (!strcmp(var, "color.grep.external"))
return git_config_string(&(opt->color_external), var, value);
if (!strcmp(var, "color.grep.match")) {
if (!value)
return config_error_nonbool(var);
@ -214,309 +205,12 @@ static int grep_file(struct grep_opt *opt, const char *filename)
return i;
}
#if !NO_EXTERNAL_GREP
static int exec_grep(int argc, const char **argv)
{
pid_t pid;
int status;
argv[argc] = NULL;
trace_argv_printf(argv, "trace: grep:");
pid = fork();
if (pid < 0)
return pid;
if (!pid) {
execvp("grep", (char **) argv);
exit(255);
}
while (waitpid(pid, &status, 0) < 0) {
if (errno == EINTR)
continue;
return -1;
}
if (WIFEXITED(status)) {
if (!WEXITSTATUS(status))
return 1;
return 0;
}
return -1;
}
#define MAXARGS 1000
#define ARGBUF 4096
#define push_arg(a) do { \
if (nr < MAXARGS) argv[nr++] = (a); \
else die("maximum number of args exceeded"); \
} while (0)
/*
* If you send a singleton filename to grep, it does not give
* the name of the file. GNU grep has "-H" but we would want
* that behaviour in a portable way.
*
* So we keep two pathnames in argv buffer unsent to grep in
* the main loop if we need to do more than one grep.
*/
static int flush_grep(struct grep_opt *opt,
int argc, int arg0, const char **argv, int *kept)
{
int status;
int count = argc - arg0;
const char *kept_0 = NULL;
if (count <= 2) {
/*
* Because we keep at least 2 paths in the call from
* the main loop (i.e. kept != NULL), and MAXARGS is
* far greater than 2, this usually is a call to
* conclude the grep. However, the user could attempt
* to overflow the argv buffer by giving too many
* options to leave very small number of real
* arguments even for the call in the main loop.
*/
if (kept)
die("insanely many options to grep");
/*
* If we have two or more paths, we do not have to do
* anything special, but we need to push /dev/null to
* get "-H" behaviour of GNU grep portably but when we
* are not doing "-l" nor "-L" nor "-c".
*/
if (count == 1 &&
!opt->name_only &&
!opt->unmatch_name_only &&
!opt->count) {
argv[argc++] = "/dev/null";
argv[argc] = NULL;
}
}
else if (kept) {
/*
* Called because we found many paths and haven't finished
* iterating over the cache yet. We keep two paths
* for the concluding call. argv[argc-2] and argv[argc-1]
* has the last two paths, so save the first one away,
* replace it with NULL while sending the list to grep,
* and recover them after we are done.
*/
*kept = 2;
kept_0 = argv[argc-2];
argv[argc-2] = NULL;
argc -= 2;
}
if (opt->pre_context || opt->post_context) {
/*
* grep handles hunk marks between files, but we need to
* do that ourselves between multiple calls.
*/
if (opt->show_hunk_mark)
write_or_die(1, "--\n", 3);
else
opt->show_hunk_mark = 1;
}
status = exec_grep(argc, argv);
if (kept_0) {
/*
* Then recover them. Now the last arg is beyond the
* terminating NULL which is at argc, and the second
* from the last is what we saved away in kept_0
*/
argv[arg0++] = kept_0;
argv[arg0] = argv[argc+1];
}
return status;
}
static void grep_add_color(struct strbuf *sb, const char *escape_seq)
{
size_t orig_len = sb->len;
while (*escape_seq) {
if (*escape_seq == 'm')
strbuf_addch(sb, ';');
else if (*escape_seq != '\033' && *escape_seq != '[')
strbuf_addch(sb, *escape_seq);
escape_seq++;
}
if (sb->len > orig_len && sb->buf[sb->len - 1] == ';')
strbuf_setlen(sb, sb->len - 1);
}
static int has_skip_worktree_entry(struct grep_opt *opt, const char **paths)
{
int nr;
for (nr = 0; nr < active_nr; nr++) {
struct cache_entry *ce = active_cache[nr];
if (!S_ISREG(ce->ce_mode))
continue;
if (!pathspec_matches(paths, ce->name, opt->max_depth))
continue;
if (ce_skip_worktree(ce))
return 1;
}
return 0;
}
static int external_grep(struct grep_opt *opt, const char **paths, int cached)
{
int i, nr, argc, hit, len, status;
const char *argv[MAXARGS+1];
char randarg[ARGBUF];
char *argptr = randarg;
struct grep_pat *p;
if (opt->extended || (opt->relative && opt->prefix_length)
|| has_skip_worktree_entry(opt, paths))
return -1;
len = nr = 0;
push_arg("grep");
if (opt->fixed)
push_arg("-F");
if (opt->linenum)
push_arg("-n");
if (!opt->pathname)
push_arg("-h");
if (opt->regflags & REG_EXTENDED)
push_arg("-E");
if (opt->ignore_case)
push_arg("-i");
if (opt->binary == GREP_BINARY_NOMATCH)
push_arg("-I");
if (opt->word_regexp)
push_arg("-w");
if (opt->name_only)
push_arg("-l");
if (opt->unmatch_name_only)
push_arg("-L");
if (opt->null_following_name)
/* in GNU grep git's "-z" translates to "-Z" */
push_arg("-Z");
if (opt->count)
push_arg("-c");
if (opt->post_context || opt->pre_context) {
if (opt->post_context != opt->pre_context) {
if (opt->pre_context) {
push_arg("-B");
len += snprintf(argptr, sizeof(randarg)-len,
"%u", opt->pre_context) + 1;
if (sizeof(randarg) <= len)
die("maximum length of args exceeded");
push_arg(argptr);
argptr += len;
}
if (opt->post_context) {
push_arg("-A");
len += snprintf(argptr, sizeof(randarg)-len,
"%u", opt->post_context) + 1;
if (sizeof(randarg) <= len)
die("maximum length of args exceeded");
push_arg(argptr);
argptr += len;
}
}
else {
push_arg("-C");
len += snprintf(argptr, sizeof(randarg)-len,
"%u", opt->post_context) + 1;
if (sizeof(randarg) <= len)
die("maximum length of args exceeded");
push_arg(argptr);
argptr += len;
}
}
for (p = opt->pattern_list; p; p = p->next) {
push_arg("-e");
push_arg(p->pattern);
}
if (opt->color) {
struct strbuf sb = STRBUF_INIT;
grep_add_color(&sb, opt->color_match);
setenv("GREP_COLOR", sb.buf, 1);
strbuf_reset(&sb);
strbuf_addstr(&sb, "mt=");
grep_add_color(&sb, opt->color_match);
strbuf_addstr(&sb, ":sl=:cx=:fn=:ln=:bn=:se=");
setenv("GREP_COLORS", sb.buf, 1);
strbuf_release(&sb);
if (opt->color_external && strlen(opt->color_external) > 0)
push_arg(opt->color_external);
} else {
unsetenv("GREP_COLOR");
unsetenv("GREP_COLORS");
}
unsetenv("GREP_OPTIONS");
hit = 0;
argc = nr;
for (i = 0; i < active_nr; i++) {
struct cache_entry *ce = active_cache[i];
char *name;
int kept;
if (!S_ISREG(ce->ce_mode))
continue;
if (!pathspec_matches(paths, ce->name, opt->max_depth))
continue;
name = ce->name;
if (name[0] == '-') {
int len = ce_namelen(ce);
name = xmalloc(len + 3);
memcpy(name, "./", 2);
memcpy(name + 2, ce->name, len + 1);
}
argv[argc++] = name;
if (MAXARGS <= argc) {
status = flush_grep(opt, argc, nr, argv, &kept);
if (0 < status)
hit = 1;
argc = nr + kept;
}
if (ce_stage(ce)) {
do {
i++;
} while (i < active_nr &&
!strcmp(ce->name, active_cache[i]->name));
i--; /* compensate for loop control */
}
}
if (argc > nr) {
status = flush_grep(opt, argc, nr, argv, NULL);
if (0 < status)
hit = 1;
}
return hit;
}
#endif
static int grep_cache(struct grep_opt *opt, const char **paths, int cached,
int external_grep_allowed)
static int grep_cache(struct grep_opt *opt, const char **paths, int cached)
{
int hit = 0;
int nr;
read_cache();
#if !NO_EXTERNAL_GREP
/*
* Use the external "grep" command for the case where
* we grep through the checked-out files. It tends to
* be a lot more optimized
*/
if (!cached && external_grep_allowed) {
hit = external_grep(opt, paths, cached);
if (hit >= 0)
return hit;
hit = 0;
}
#endif
for (nr = 0; nr < active_nr; nr++) {
struct cache_entry *ce = active_cache[nr];
if (!S_ISREG(ce->ce_mode))
@ -626,6 +320,21 @@ static int grep_object(struct grep_opt *opt, const char **paths,
die("unable to grep from object of type %s", typename(obj->type));
}
static int grep_directory(struct grep_opt *opt, const char **paths)
{
struct dir_struct dir;
int i, hit = 0;
memset(&dir, 0, sizeof(dir));
setup_standard_excludes(&dir);
fill_directory(&dir, paths);
for (i = 0; i < dir.nr; i++)
hit |= grep_file(opt, dir.entries[i]->name);
free_grep_patterns(opt);
return hit;
}
static int context_callback(const struct option *opt, const char *arg,
int unset)
{
@ -713,16 +422,19 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
{
int hit = 0;
int cached = 0;
int external_grep_allowed = 1;
int seen_dashdash = 0;
int external_grep_allowed__ignored;
struct grep_opt opt;
struct object_array list = { 0, 0, NULL };
const char **paths = NULL;
int i;
int dummy;
int nongit = 0, use_index = 1;
struct option options[] = {
OPT_BOOLEAN(0, "cached", &cached,
"search in index instead of in the work tree"),
OPT_BOOLEAN(0, "index", &use_index,
"--no-index finds in contents not managed by git"),
OPT_GROUP(""),
OPT_BOOLEAN('v', "invert-match", &opt.invert,
"show non-matching lines"),
@ -796,18 +508,15 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
OPT_BOOLEAN(0, "all-match", &opt.all_match,
"show only matches from files that match all patterns"),
OPT_GROUP(""),
#if NO_EXTERNAL_GREP
OPT_BOOLEAN(0, "ext-grep", &external_grep_allowed,
"allow calling of grep(1) (ignored by this build)"),
#else
OPT_BOOLEAN(0, "ext-grep", &external_grep_allowed,
"allow calling of grep(1) (default)"),
#endif
OPT_BOOLEAN(0, "ext-grep", &external_grep_allowed__ignored,
"allow calling of grep(1) (ignored by this build)"),
{ OPTION_CALLBACK, 0, "help-all", &options, NULL, "show usage",
PARSE_OPT_HIDDEN | PARSE_OPT_NOARG, help_callback },
OPT_END()
};
prefix = setup_git_directory_gently(&nongit);
/*
* 'git grep -h', unlike 'git grep -h <pattern>', is a request
* to show usage information and exit.
@ -845,6 +554,10 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
PARSE_OPT_STOP_AT_NON_OPTION |
PARSE_OPT_NO_INTERNAL_HELP);
if (use_index && nongit)
/* die the same way as if we did it at the beginning */
setup_git_directory();
/* First unrecognized non-option token */
if (argc > 0 && !opt.pattern_list) {
append_grep_pattern(&opt, argv[0], "command line", 0,
@ -853,8 +566,6 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
argc--;
}
if ((opt.color && !opt.color_external) || opt.funcname)
external_grep_allowed = 0;
if (!opt.pattern_list)
die("no pattern given.");
if (!opt.fixed && opt.ignore_case)
@ -897,10 +608,18 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
paths[1] = NULL;
}
if (!use_index) {
if (cached)
die("--cached cannot be used with --no-index.");
if (list.nr)
die("--no-index cannot be used with revs.");
return !grep_directory(&opt, paths);
}
if (!list.nr) {
if (!cached)
setup_work_tree();
return !grep_cache(&opt, paths, cached, external_grep_allowed);
return !grep_cache(&opt, paths, cached);
}
if (cached)

2
git.c
Просмотреть файл

@ -317,7 +317,7 @@ static void handle_internal_command(int argc, const char **argv)
{ "fsck-objects", cmd_fsck, RUN_SETUP },
{ "gc", cmd_gc, RUN_SETUP },
{ "get-tar-commit-id", cmd_get_tar_commit_id },
{ "grep", cmd_grep, RUN_SETUP | USE_PAGER },
{ "grep", cmd_grep, USE_PAGER },
{ "help", cmd_help },
{ "init", cmd_init_db },
{ "init-db", cmd_init_db },

84
grep.c
Просмотреть файл

@ -29,13 +29,6 @@ void append_grep_pattern(struct grep_opt *opt, const char *pat,
p->next = NULL;
}
static int is_fixed(const char *s)
{
while (*s && !is_regex_special(*s))
s++;
return !*s;
}
static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
{
int err;
@ -43,7 +36,7 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
p->word_regexp = opt->word_regexp;
p->ignore_case = opt->ignore_case;
if (opt->fixed || is_fixed(p->pattern))
if (opt->fixed)
p->fixed = 1;
if (opt->regflags & REG_ICASE)
p->fixed = 0;
@ -615,6 +608,65 @@ static void show_pre_context(struct grep_opt *opt, const char *name, char *buf,
}
}
static int should_lookahead(struct grep_opt *opt)
{
struct grep_pat *p;
if (opt->extended)
return 0; /* punt for too complex stuff */
if (opt->invert)
return 0;
for (p = opt->pattern_list; p; p = p->next) {
if (p->token != GREP_PATTERN)
return 0; /* punt for "header only" and stuff */
}
return 1;
}
static int look_ahead(struct grep_opt *opt,
unsigned long *left_p,
unsigned *lno_p,
char **bol_p)
{
unsigned lno = *lno_p;
char *bol = *bol_p;
struct grep_pat *p;
char *sp, *last_bol;
regoff_t earliest = -1;
for (p = opt->pattern_list; p; p = p->next) {
int hit;
regmatch_t m;
if (p->fixed)
hit = !fixmatch(p->pattern, bol, p->ignore_case, &m);
else
hit = !regexec(&p->regexp, bol, 1, &m, 0);
if (!hit || m.rm_so < 0 || m.rm_eo < 0)
continue;
if (earliest < 0 || m.rm_so < earliest)
earliest = m.rm_so;
}
if (earliest < 0) {
*bol_p = bol + *left_p;
*left_p = 0;
return 1;
}
for (sp = bol + earliest; bol < sp && sp[-1] != '\n'; sp--)
; /* find the beginning of the line */
last_bol = sp;
for (sp = bol; sp < last_bol; sp++) {
if (*sp == '\n')
lno++;
}
*left_p -= last_bol - bol;
*bol_p = last_bol;
*lno_p = lno;
return 0;
}
static int grep_buffer_1(struct grep_opt *opt, const char *name,
char *buf, unsigned long size, int collect_hits)
{
@ -624,6 +676,7 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
unsigned last_hit = 0;
int binary_match_only = 0;
unsigned count = 0;
int try_lookahead = 0;
enum grep_context ctx = GREP_CONTEXT_HEAD;
xdemitconf_t xecfg;
@ -652,11 +705,26 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
opt->priv = &xecfg;
}
}
try_lookahead = should_lookahead(opt);
while (left) {
char *eol, ch;
int hit;
/*
* look_ahead() skips quicly to the line that possibly
* has the next hit; don't call it if we need to do
* something more than just skipping the current line
* in response to an unmatch for the current line. E.g.
* inside a post-context window, we will show the current
* line as a context around the previous hit when it
* doesn't hit.
*/
if (try_lookahead
&& !(last_hit
&& lno <= last_hit + opt->post_context)
&& look_ahead(opt, &left, &lno, &bol))
break;
eol = end_of_line(bol, &left);
ch = *eol;
*eol = 0;

1
grep.h
Просмотреть файл

@ -85,7 +85,6 @@ struct grep_opt {
int max_depth;
int funcname;
char color_match[COLOR_MAXLEN];
const char *color_external;
int regflags;
unsigned pre_context;
unsigned post_context;

74
t/t7002-grep.sh
Просмотреть файл

@ -8,18 +8,6 @@ test_description='git grep various.
. ./test-lib.sh
test_expect_success 'Check for external grep support' '
case "$(git grep -h 2>&1|grep ext-grep)" in
*"(default)"*)
test_set_prereq EXTGREP
true;;
*"(ignored by this build)"*)
true;;
*)
false;;
esac
'
cat >hello.c <<EOF
#include <stdio.h>
int main(int argc, const char **argv)
@ -314,8 +302,8 @@ test_expect_success 'grep -C1, hunk mark between files' '
test_cmp expected actual
'
test_expect_success 'grep -C1 --no-ext-grep, hunk mark between files' '
git grep -C1 --no-ext-grep "^[yz]" >actual &&
test_expect_success 'grep -C1 hunk mark between files' '
git grep -C1 "^[yz]" >actual &&
test_cmp expected actual
'
@ -371,7 +359,7 @@ test_expect_success 'log grep (6)' '
test_expect_success 'grep with CE_VALID file' '
git update-index --assume-unchanged t/t &&
rm t/t &&
test "$(git grep --no-ext-grep test)" = "t/t:test" &&
test "$(git grep test)" = "t/t:test" &&
git update-index --no-assume-unchanged t/t &&
git checkout t/t
'
@ -438,16 +426,56 @@ test_expect_success 'grep -Fi' '
test_cmp expected actual
'
test_expect_success EXTGREP 'external grep is called' '
GIT_TRACE=2 git grep foo >/dev/null 2>actual &&
grep "trace: grep:.*foo" actual >/dev/null
test_expect_success 'outside of git repository' '
rm -fr non &&
mkdir -p non/git/sub &&
echo hello >non/git/file1 &&
echo world >non/git/sub/file2 &&
echo ".*o*" >non/git/.gitignore &&
{
echo file1:hello &&
echo sub/file2:world
} >non/expect.full &&
echo file2:world >non/expect.sub
(
GIT_CEILING_DIRECTORIES="$(pwd)/non/git" &&
export GIT_CEILING_DIRECTORIES &&
cd non/git &&
test_must_fail git grep o &&
git grep --no-index o >../actual.full &&
test_cmp ../expect.full ../actual.full
cd sub &&
test_must_fail git grep o &&
git grep --no-index o >../../actual.sub &&
test_cmp ../../expect.sub ../../actual.sub
)
'
test_expect_success EXTGREP 'no external grep when skip-worktree entries exist' '
git update-index --skip-worktree file &&
GIT_TRACE=2 git grep foo >/dev/null 2>actual &&
! grep "trace: grep:" actual >/dev/null &&
git update-index --no-skip-worktree file
test_expect_success 'inside git repository but with --no-index' '
rm -fr is &&
mkdir -p is/git/sub &&
echo hello >is/git/file1 &&
echo world >is/git/sub/file2 &&
echo ".*o*" >is/git/.gitignore &&
{
echo file1:hello &&
echo sub/file2:world
} >is/expect.full &&
: >is/expect.empty &&
echo file2:world >is/expect.sub
(
cd is/git &&
git init &&
test_must_fail git grep o >../actual.full &&
test_cmp ../expect.empty ../actual.full &&
git grep --no-index o >../actual.full &&
test_cmp ../expect.full ../actual.full &&
cd sub &&
test_must_fail git grep o >../../actual.sub &&
test_cmp ../../expect.empty ../../actual.sub &&
git grep --no-index o >../../actual.sub &&
test_cmp ../../expect.sub ../../actual.sub
)
'
test_done