diff --git a/builtin-grep.c b/builtin-grep.c
index 671878817386c72f16fe64cc62b6fa8daa62f102..0d6cc7361f6e1a70e4d3d9e24913d60e8ceb9e58 100644 (file)
--- a/builtin-grep.c
+++ b/builtin-grep.c
#include "tag.h"
#include "tree-walk.h"
#include "builtin.h"
#include "tag.h"
#include "tree-walk.h"
#include "builtin.h"
-#include <regex.h>
#include "grep.h"
#include "grep.h"
-#include <fnmatch.h>
-#include <sys/wait.h>
/*
* git grep pathspecs are somewhat different from diff-tree pathspecs;
/*
* git grep pathspecs are somewhat different from diff-tree pathspecs;
@@ -87,11 +84,11 @@ static int grep_sha1(struct grep_opt *opt, const unsigned char *sha1, const char
{
unsigned long size;
char *data;
{
unsigned long size;
char *data;
- char type[20];
+ enum object_type type;
char *to_free = NULL;
int hit;
char *to_free = NULL;
int hit;
- data = read_sha1_file(sha1, type, &size);
+ data = read_sha1_file(sha1, &type, &size);
if (!data) {
error("'%s': unable to read %s", name, sha1_to_hex(sha1));
return 0;
if (!data) {
error("'%s': unable to read %s", name, sha1_to_hex(sha1));
return 0;
struct stat st;
int i;
char *data;
struct stat st;
int i;
char *data;
+ size_t sz;
+
if (lstat(filename, &st) < 0) {
err_ret:
if (errno != ENOENT)
if (lstat(filename, &st) < 0) {
err_ret:
if (errno != ENOENT)
return 0; /* empty file -- no grep hit */
if (!S_ISREG(st.st_mode))
return 0;
return 0; /* empty file -- no grep hit */
if (!S_ISREG(st.st_mode))
return 0;
+ sz = xsize_t(st.st_size);
i = open(filename, O_RDONLY);
if (i < 0)
goto err_ret;
i = open(filename, O_RDONLY);
if (i < 0)
goto err_ret;
- data = xmalloc(st.st_size + 1);
- if (st.st_size != xread(i, data, st.st_size)) {
+ data = xmalloc(sz + 1);
+ if (st.st_size != read_in_full(i, data, sz)) {
error("'%s': short read %s", filename, strerror(errno));
close(i);
free(data);
error("'%s': short read %s", filename, strerror(errno));
close(i);
free(data);
close(i);
if (opt->relative && opt->prefix_length)
filename += opt->prefix_length;
close(i);
if (opt->relative && opt->prefix_length)
filename += opt->prefix_length;
- i = grep_buffer(opt, filename, data, st.st_size);
+ i = grep_buffer(opt, filename, data, sz);
free(data);
return i;
}
free(data);
return i;
}
+#ifdef __unix__
static int exec_grep(int argc, const char **argv)
{
pid_t pid;
static int exec_grep(int argc, const char **argv)
{
pid_t pid;
else die("maximum number of args exceeded"); \
} while (0)
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;
+ }
+
+ 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 int external_grep(struct grep_opt *opt, const char **paths, int cached)
{
int i, nr, argc, hit, len, status;
static int external_grep(struct grep_opt *opt, const char **paths, int cached)
{
int i, nr, argc, hit, len, status;
if (opt->pre_context) {
push_arg("-B");
len += snprintf(argptr, sizeof(randarg)-len,
if (opt->pre_context) {
push_arg("-B");
len += snprintf(argptr, sizeof(randarg)-len,
- "%u", opt->pre_context);
+ "%u", opt->pre_context) + 1;
if (sizeof(randarg) <= len)
die("maximum length of args exceeded");
push_arg(argptr);
if (sizeof(randarg) <= len)
die("maximum length of args exceeded");
push_arg(argptr);
if (opt->post_context) {
push_arg("-A");
len += snprintf(argptr, sizeof(randarg)-len,
if (opt->post_context) {
push_arg("-A");
len += snprintf(argptr, sizeof(randarg)-len,
- "%u", opt->post_context);
+ "%u", opt->post_context) + 1;
if (sizeof(randarg) <= len)
die("maximum length of args exceeded");
push_arg(argptr);
if (sizeof(randarg) <= len)
die("maximum length of args exceeded");
push_arg(argptr);
else {
push_arg("-C");
len += snprintf(argptr, sizeof(randarg)-len,
else {
push_arg("-C");
len += snprintf(argptr, sizeof(randarg)-len,
- "%u", opt->post_context);
+ "%u", opt->post_context) + 1;
if (sizeof(randarg) <= len)
die("maximum length of args exceeded");
push_arg(argptr);
if (sizeof(randarg) <= len)
die("maximum length of args exceeded");
push_arg(argptr);
@@ -252,23 +325,13 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached)
push_arg(p->pattern);
}
push_arg(p->pattern);
}
- /*
- * To make sure we get the header printed out when we want it,
- * add /dev/null to the paths to grep. This is unnecessary
- * (and wrong) with "-l" or "-L", which always print out the
- * name anyway.
- *
- * GNU grep has "-H", but this is portable.
- */
- if (!opt->name_only && !opt->unmatch_name_only)
- push_arg("/dev/null");
-
hit = 0;
argc = nr;
for (i = 0; i < active_nr; i++) {
struct cache_entry *ce = active_cache[i];
char *name;
hit = 0;
argc = nr;
for (i = 0; i < active_nr; i++) {
struct cache_entry *ce = active_cache[i];
char *name;
- if (ce_stage(ce) || !S_ISREG(ntohl(ce->ce_mode)))
+ int kept;
+ if (!S_ISREG(ntohl(ce->ce_mode)))
continue;
if (!pathspec_matches(paths, ce->name))
continue;
continue;
if (!pathspec_matches(paths, ce->name))
continue;
@@ -280,20 +343,28 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached)
memcpy(name + 2, ce->name, len + 1);
}
argv[argc++] = name;
memcpy(name + 2, ce->name, len + 1);
}
argv[argc++] = name;
- if (argc < MAXARGS)
- continue;
- status = exec_grep(argc, argv);
- if (0 < status)
- hit = 1;
- argc = nr;
+ 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) {
}
if (argc > nr) {
- status = exec_grep(argc, argv);
+ status = flush_grep(opt, argc, nr, argv, NULL);
if (0 < status)
hit = 1;
}
return hit;
}
if (0 < status)
hit = 1;
}
return hit;
}
+#endif
static int grep_cache(struct grep_opt *opt, const char **paths, int cached)
{
static int grep_cache(struct grep_opt *opt, const char **paths, int cached)
{
for (nr = 0; nr < active_nr; nr++) {
struct cache_entry *ce = active_cache[nr];
for (nr = 0; nr < active_nr; nr++) {
struct cache_entry *ce = active_cache[nr];
- if (ce_stage(ce) || !S_ISREG(ntohl(ce->ce_mode)))
+ if (!S_ISREG(ntohl(ce->ce_mode)))
continue;
if (!pathspec_matches(paths, ce->name))
continue;
continue;
if (!pathspec_matches(paths, ce->name))
continue;
- if (cached)
+ if (cached) {
+ if (ce_stage(ce))
+ continue;
hit |= grep_sha1(opt, ce->sha1, ce->name, 0);
hit |= grep_sha1(opt, ce->sha1, ce->name, 0);
+ }
else
hit |= grep_file(opt, ce->name);
else
hit |= grep_file(opt, ce->name);
+ if (ce_stage(ce)) {
+ do {
+ nr++;
+ } while (nr < active_nr &&
+ !strcmp(ce->name, active_cache[nr]->name));
+ nr--; /* compensate for loop control */
+ }
}
}
+ free_grep_patterns(opt);
return hit;
}
return hit;
}
* decide if we want to descend into "abc"
* directory.
*/
* decide if we want to descend into "abc"
* directory.
*/
- strcpy(path_buf + len + entry.pathlen, "/");
+ strcpy(path_buf + len + tree_entry_len(entry.path, entry.sha1), "/");
if (!pathspec_matches(paths, down))
;
else if (S_ISREG(entry.mode))
hit |= grep_sha1(opt, entry.sha1, path_buf, tn_len);
else if (S_ISDIR(entry.mode)) {
if (!pathspec_matches(paths, down))
;
else if (S_ISREG(entry.mode))
hit |= grep_sha1(opt, entry.sha1, path_buf, tn_len);
else if (S_ISDIR(entry.mode)) {
- char type[20];
+ enum object_type type;
struct tree_desc sub;
void *data;
struct tree_desc sub;
void *data;
- data = read_sha1_file(entry.sha1, type, &sub.size);
+ unsigned long size;
+
+ data = read_sha1_file(entry.sha1, &type, &size);
if (!data)
die("unable to read tree (%s)",
sha1_to_hex(entry.sha1));
if (!data)
die("unable to read tree (%s)",
sha1_to_hex(entry.sha1));
- sub.buf = data;
+ init_tree_desc(&sub, data, size);
hit |= grep_tree(opt, paths, &sub, tree_name, down);
free(data);
}
hit |= grep_tree(opt, paths, &sub, tree_name, down);
free(data);
}
if (obj->type == OBJ_COMMIT || obj->type == OBJ_TREE) {
struct tree_desc tree;
void *data;
if (obj->type == OBJ_COMMIT || obj->type == OBJ_TREE) {
struct tree_desc tree;
void *data;
+ unsigned long size;
int hit;
data = read_object_with_reference(obj->sha1, tree_type,
int hit;
data = read_object_with_reference(obj->sha1, tree_type,
- &tree.size, NULL);
+ &size, NULL);
if (!data)
die("unable to read tree (%s)", sha1_to_hex(obj->sha1));
if (!data)
die("unable to read tree (%s)", sha1_to_hex(obj->sha1));
- tree.buf = data;
+ init_tree_desc(&tree, data, size);
hit = grep_tree(opt, paths, &tree, name, "");
free(data);
return hit;
hit = grep_tree(opt, paths, &tree, name, "");
free(data);
return hit;
opt.word_regexp = 1;
continue;
}
opt.word_regexp = 1;
continue;
}
- if (!strncmp("-A", arg, 2) ||
- !strncmp("-B", arg, 2) ||
- !strncmp("-C", arg, 2) ||
+ if (!prefixcmp(arg, "-A") ||
+ !prefixcmp(arg, "-B") ||
+ !prefixcmp(arg, "-C") ||
(arg[0] == '-' && '1' <= arg[1] && arg[1] <= '9')) {
unsigned num;
const char *scan;
(arg[0] == '-' && '1' <= arg[1] && arg[1] <= '9')) {
unsigned num;
const char *scan;
scan = arg + 1;
break;
}
scan = arg + 1;
break;
}
- if (sscanf(scan, "%u", &num) != 1)
+ if (strtoul_ui(scan, 10, &num))
die(emsg_invalid_context_len, scan);
switch (arg[1]) {
case 'A':
die(emsg_invalid_context_len, scan);
switch (arg[1]) {
case 'A':
die("'%s': %s", argv[1], strerror(errno));
while (fgets(buf, sizeof(buf), patterns)) {
int len = strlen(buf);
die("'%s': %s", argv[1], strerror(errno));
while (fgets(buf, sizeof(buf), patterns)) {
int len = strlen(buf);
- if (buf[len-1] == '\n')
+ if (len && buf[len-1] == '\n')
buf[len-1] = 0;
/* ignore empty line like grep does */
if (!buf[0])
buf[len-1] = 0;
/* ignore empty line like grep does */
if (!buf[0])
GREP_CLOSE_PAREN);
continue;
}
GREP_CLOSE_PAREN);
continue;
}
+ if (!strcmp("--all-match", arg)) {
+ opt.all_match = 1;
+ continue;
+ }
if (!strcmp("-e", arg)) {
if (1 < argc) {
append_grep_pattern(&opt, argv[1],
if (!strcmp("-e", arg)) {
if (1 < argc) {
append_grep_pattern(&opt, argv[1],
if (grep_object(&opt, paths, real_obj, list.objects[i].name))
hit = 1;
}
if (grep_object(&opt, paths, real_obj, list.objects[i].name))
hit = 1;
}
+ free_grep_patterns(&opt);
return !hit;
}
return !hit;
}