X-Git-Url: https://git.tokkee.org/?a=blobdiff_plain;f=builtin-grep.c;h=bbf747fc7b66f6b4f19d9dc62a9ba10965199917;hb=e5d3de5c457d1a82c921b9bf2cd9a962970ce30e;hp=96b70227cf073517c309dbc8b042085f1040dab5;hpb=784b11cd05e7862b0fbcc1251a65669c7004a8df;p=git.git

diff --git a/builtin-grep.c b/builtin-grep.c
index 96b70227c..bbf747fc7 100644
--- a/builtin-grep.c
+++ b/builtin-grep.c
@@ -122,6 +122,8 @@ static int grep_file(struct grep_opt *opt, const char *filename)
 	struct stat st;
 	int i;
 	char *data;
+	size_t sz;
+
 	if (lstat(filename, &st) < 0) {
 	err_ret:
 		if (errno != ENOENT)
@@ -132,11 +134,12 @@ static int grep_file(struct grep_opt *opt, const char *filename)
 		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;
-	data = xmalloc(st.st_size + 1);
-	if (st.st_size != read_in_full(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);
@@ -145,11 +148,12 @@ static int grep_file(struct grep_opt *opt, const char *filename)
 	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;
 }
 
+#ifdef __unix__
 static int exec_grep(int argc, const char **argv)
 {
 	pid_t pid;
@@ -183,6 +187,78 @@ static int exec_grep(int argc, const char **argv)
 	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;
@@ -218,7 +294,7 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached)
 			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);
@@ -227,7 +303,7 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached)
 			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);
@@ -237,7 +313,7 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached)
 		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);
@@ -249,22 +325,12 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached)
 		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;
+		int kept;
 		if (!S_ISREG(ntohl(ce->ce_mode)))
 			continue;
 		if (!pathspec_matches(paths, ce->name))
@@ -277,12 +343,12 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached)
 			memcpy(name + 2, ce->name, len + 1);
 		}
 		argv[argc++] = name;
-		if (argc < MAXARGS && !ce_stage(ce))
+		if (argc < MAXARGS)
 			continue;
-		status = exec_grep(argc, argv);
+		status = flush_grep(opt, argc, nr, argv, &kept);
 		if (0 < status)
 			hit = 1;
-		argc = nr;
+		argc = nr + kept;
 		if (ce_stage(ce)) {
 			do {
 				i++;
@@ -292,12 +358,13 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached)
 		}
 	}
 	if (argc > nr) {
-		status = exec_grep(argc, argv);
+		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)
 {
@@ -373,7 +440,7 @@ static int grep_tree(struct grep_opt *opt, const char **paths,
 			 * 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))
 			;
@@ -383,11 +450,13 @@ static int grep_tree(struct grep_opt *opt, const char **paths,
 			enum object_type type;
 			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));
-			sub.buf = data;
+			init_tree_desc(&sub, data, size);
 			hit |= grep_tree(opt, paths, &sub, tree_name, down);
 			free(data);
 		}
@@ -403,12 +472,13 @@ static int grep_object(struct grep_opt *opt, const char **paths,
 	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,
-						  &tree.size, NULL);
+						  &size, NULL);
 		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;
@@ -548,7 +618,7 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 				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':