X-Git-Url: https://git.octo.it/?a=blobdiff_plain;f=builtin-grep.c;h=5fac5701e6ccebdbe83b00d2e2df19343d3aea0e;hb=7612a1efdb0c0806b43db10ce784707aae874340;hp=52ac521afea67b3de2ee3c5f1fd196ba11f17c9a;hpb=02ab1c490dc4827446c851468eb01ecc23b6cc48;p=git.git

diff --git a/builtin-grep.c b/builtin-grep.c
index 52ac521a..5fac5701 100644
--- a/builtin-grep.c
+++ b/builtin-grep.c
@@ -12,6 +12,7 @@
 #include "builtin.h"
 #include <regex.h>
 #include <fnmatch.h>
+#include <sys/wait.h>
 
 /*
  * git grep pathspecs are somewhat different from diff-tree pathspecs;
@@ -98,6 +99,7 @@ struct grep_opt {
 	unsigned unmatch_name_only:1;
 	unsigned count:1;
 	unsigned word_regexp:1;
+	unsigned fixed:1;
 #define GREP_BINARY_DEFAULT	0
 #define GREP_BINARY_NOMATCH	1
 #define GREP_BINARY_TEXT	2
@@ -179,6 +181,20 @@ static int buffer_is_binary(const char *ptr, unsigned long size)
 	return 0;
 }
 
+static int fixmatch(const char *pattern, char *line, regmatch_t *match)
+{
+	char *hit = strstr(line, pattern);
+	if (!hit) {
+		match->rm_so = match->rm_eo = -1;
+		return REG_NOMATCH;
+	}
+	else {
+		match->rm_so = hit - line;
+		match->rm_eo = match->rm_so + strlen(pattern);
+		return 0;
+	}
+}
+
 static int grep_buffer(struct grep_opt *opt, const char *name,
 		       char *buf, unsigned long size)
 {
@@ -224,9 +240,14 @@ static int grep_buffer(struct grep_opt *opt, const char *name,
 		*eol = 0;
 
 		for (p = opt->pattern_list; p; p = p->next) {
-			regex_t *exp = &p->regexp;
-			hit = !regexec(exp, bol, ARRAY_SIZE(pmatch),
-				       pmatch, 0);
+			if (!opt->fixed) {
+				regex_t *exp = &p->regexp;
+				hit = !regexec(exp, bol, ARRAY_SIZE(pmatch),
+					       pmatch, 0);
+			}
+			else {
+				hit = !fixmatch(p->pattern, bol, pmatch);
+			}
 
 			if (hit && opt->word_regexp) {
 				/* Match beginning must be either
@@ -389,12 +410,158 @@ static int grep_file(struct grep_opt *opt, const char *filename)
 	return i;
 }
 
+static int exec_grep(int argc, const char **argv)
+{
+	pid_t pid;
+	int status;
+
+	argv[argc] = NULL;
+	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)
+
+static int external_grep(struct grep_opt *opt, const char **paths, int cached)
+{
+	int i, nr, argc, hit, len;
+	const char *argv[MAXARGS+1];
+	char randarg[ARGBUF];
+	char *argptr = randarg;
+	struct grep_pat *p;
+
+	len = nr = 0;
+	push_arg("grep");
+	if (opt->fixed)
+		push_arg("-F");
+	if (opt->linenum)
+		push_arg("-n");
+	if (opt->regflags & REG_EXTENDED)
+		push_arg("-E");
+	if (opt->regflags & REG_ICASE)
+		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->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);
+				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);
+				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);
+			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);
+	}
+
+	/*
+	 * 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;
+		if (ce_stage(ce) || !S_ISREG(ntohl(ce->ce_mode)))
+			continue;
+		if (!pathspec_matches(paths, ce->name))
+			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 (argc < MAXARGS)
+			continue;
+		hit += exec_grep(argc, argv);
+		argc = nr;
+	}
+	if (argc > nr)
+		hit += exec_grep(argc, argv);
+	return 0;
+}
+
 static int grep_cache(struct grep_opt *opt, const char **paths, int cached)
 {
 	int hit = 0;
 	int nr;
 	read_cache();
 
+#ifdef __unix__
+	/*
+	 * 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) {
+		hit = external_grep(opt, paths, cached);
+		if (hit >= 0)
+			return hit;
+	}
+#endif
+
 	for (nr = 0; nr < active_nr; nr++) {
 		struct cache_entry *ce = active_cache[nr];
 		if (ce_stage(ce) || !S_ISREG(ntohl(ce->ce_mode)))
@@ -413,11 +580,9 @@ static int grep_tree(struct grep_opt *opt, const char **paths,
 		     struct tree_desc *tree,
 		     const char *tree_name, const char *base)
 {
-	unsigned mode;
 	int len;
 	int hit = 0;
-	const char *path;
-	const unsigned char *sha1;
+	struct name_entry entry;
 	char *down;
 	char *path_buf = xmalloc(PATH_MAX + strlen(tree_name) + 100);
 
@@ -432,36 +597,32 @@ static int grep_tree(struct grep_opt *opt, const char **paths,
 	}
 	len = strlen(path_buf);
 
-	while (tree->size) {
-		int pathlen;
-		sha1 = tree_entry_extract(tree, &path, &mode);
-		pathlen = strlen(path);
-		strcpy(path_buf + len, path);
+	while (tree_entry(tree, &entry)) {
+		strcpy(path_buf + len, entry.path);
 
-		if (S_ISDIR(mode))
+		if (S_ISDIR(entry.mode))
 			/* Match "abc/" against pathspec to
 			 * decide if we want to descend into "abc"
 			 * directory.
 			 */
-			strcpy(path_buf + len + pathlen, "/");
+			strcpy(path_buf + len + entry.pathlen, "/");
 
 		if (!pathspec_matches(paths, down))
 			;
-		else if (S_ISREG(mode))
-			hit |= grep_sha1(opt, sha1, path_buf);
-		else if (S_ISDIR(mode)) {
+		else if (S_ISREG(entry.mode))
+			hit |= grep_sha1(opt, entry.sha1, path_buf);
+		else if (S_ISDIR(entry.mode)) {
 			char type[20];
 			struct tree_desc sub;
 			void *data;
-			data = read_sha1_file(sha1, type, &sub.size);
+			data = read_sha1_file(entry.sha1, type, &sub.size);
 			if (!data)
 				die("unable to read tree (%s)",
-				    sha1_to_hex(sha1));
+				    sha1_to_hex(entry.sha1));
 			sub.buf = data;
 			hit |= grep_tree(opt, paths, &sub, tree_name, down);
 			free(data);
 		}
-		update_tree_entry(tree);
 	}
 	return hit;
 }
@@ -549,6 +710,11 @@ int cmd_grep(int argc, const char **argv, char **envp)
 			opt.regflags |= REG_EXTENDED;
 			continue;
 		}
+		if (!strcmp("-F", arg) ||
+		    !strcmp("--fixed-strings", arg)) {
+			opt.fixed = 1;
+			continue;
+		}
 		if (!strcmp("-G", arg) ||
 		    !strcmp("--basic-regexp", arg)) {
 			opt.regflags &= ~REG_EXTENDED;
@@ -674,7 +840,10 @@ int cmd_grep(int argc, const char **argv, char **envp)
 
 	if (!opt.pattern_list)
 		die("no pattern given.");
-	compile_patterns(&opt);
+	if ((opt.regflags != REG_NEWLINE) && opt.fixed)
+		die("cannot mix --fixed-strings and regexp");
+	if (!opt.fixed)
+		compile_patterns(&opt);
 
 	/* Check revs and then paths */
 	for (i = 1; i < argc; i++) {