1 files changed, 163 insertions, 62 deletions

diff --git a/attr.c b/attr.c
index 42ad6de8c7..d45d34058d 100644
--- a/attr.c
+++ b/attr.c
@@ -7,13 +7,21 @@
  */
 
 #include "cache.h"
+#include "alloc.h"
 #include "config.h"
+#include "environment.h"
 #include "exec-cmd.h"
 #include "attr.h"
 #include "dir.h"
+#include "gettext.h"
 #include "utf8.h"
 #include "quote.h"
+#include "revision.h"
+#include "object-store.h"
+#include "setup.h"
 #include "thread-utils.h"
+#include "tree-walk.h"
+#include "object-name.h"
 
 const char git_attr__true[] = "(builtin)true";
 const char git_attr__false[] = "\0(builtin)false";
@@ -24,7 +32,7 @@ static const char git_attr__unknown[] = "(builtin)unknown";
 #define ATTR__UNKNOWN git_attr__unknown
 
 struct git_attr {
-	int attr_nr; /* unique attribute number */
+	unsigned int attr_nr; /* unique attribute number */
 	char name[FLEX_ARRAY]; /* attribute name */
 };
 
@@ -206,7 +214,7 @@ static void report_invalid_attr(const char *name, size_t len,
  * dictionary.  If no entry is found, create a new attribute and store it in
  * the dictionary.
  */
-static const struct git_attr *git_attr_internal(const char *name, int namelen)
+static const struct git_attr *git_attr_internal(const char *name, size_t namelen)
 {
 	struct git_attr *a;
 
@@ -222,8 +230,8 @@ static const struct git_attr *git_attr_internal(const char *name, int namelen)
 		a->attr_nr = hashmap_get_size(&g_attr_hashmap.map);
 
 		attr_hashmap_add(&g_attr_hashmap, a->name, namelen, a);
-		assert(a->attr_nr ==
-		       (hashmap_get_size(&g_attr_hashmap.map) - 1));
+		if (a->attr_nr != hashmap_get_size(&g_attr_hashmap.map) - 1)
+			die(_("unable to add additional attribute"));
 	}
 
 	hashmap_unlock(&g_attr_hashmap);
@@ -268,7 +276,7 @@ struct match_attr {
 		const struct git_attr *attr;
 	} u;
 	char is_macro;
-	unsigned num_attr;
+	size_t num_attr;
 	struct attr_state state[FLEX_ARRAY];
 };
 
@@ -289,7 +297,7 @@ static const char *parse_attr(const char *src, int lineno, const char *cp,
 			      struct attr_state *e)
 {
 	const char *ep, *equals;
-	int len;
+	size_t len;
 
 	ep = cp + strcspn(cp, blank);
 	equals = strchr(cp, '=');
@@ -333,8 +341,7 @@ static const char *parse_attr(const char *src, int lineno, const char *cp,
 static struct match_attr *parse_attr_line(const char *line, const char *src,
 					  int lineno, unsigned flags)
 {
-	int namelen;
-	int num_attr, i;
+	size_t namelen, num_attr, i;
 	const char *cp, *name, *states;
 	struct match_attr *res = NULL;
 	int is_macro;
@@ -345,6 +352,11 @@ static struct match_attr *parse_attr_line(const char *line, const char *src,
 		return NULL;
 	name = cp;
 
+	if (strlen(line) >= ATTR_MAX_LINE_LENGTH) {
+		warning(_("ignoring overly long attributes line %d"), lineno);
+		return NULL;
+	}
+
 	if (*cp == '"' && !unquote_c_style(&pattern, name, &states)) {
 		name = pattern.buf;
 		namelen = pattern.len;
@@ -381,10 +393,9 @@ static struct match_attr *parse_attr_line(const char *line, const char *src,
 			goto fail_return;
 	}
 
-	res = xcalloc(1,
-		      sizeof(*res) +
-		      sizeof(struct attr_state) * num_attr +
-		      (is_macro ? 0 : namelen + 1));
+	res = xcalloc(1, st_add3(sizeof(*res),
+				 st_mult(sizeof(struct attr_state), num_attr),
+				 is_macro ? 0 : namelen + 1));
 	if (is_macro) {
 		res->u.attr = git_attr_internal(name, namelen);
 	} else {
@@ -447,11 +458,12 @@ struct attr_stack {
 
 static void attr_stack_free(struct attr_stack *e)
 {
-	int i;
+	unsigned i;
 	free(e->origin);
 	for (i = 0; i < e->num_matches; i++) {
 		struct match_attr *a = e->attrs[i];
-		int j;
+		size_t j;
+
 		for (j = 0; j < a->num_attr; j++) {
 			const char *setto = a->state[j].setto;
 			if (setto == ATTR__TRUE ||
@@ -599,8 +611,7 @@ struct attr_check *attr_check_dup(const struct attr_check *check)
 
 	ret->nr = check->nr;
 	ret->alloc = check->alloc;
-	ALLOC_ARRAY(ret->items, ret->nr);
-	COPY_ARRAY(ret->items, check->items, ret->nr);
+	DUP_ARRAY(ret->items, check->items, ret->nr);
 
 	return ret;
 }
@@ -660,8 +671,8 @@ static void handle_attr_line(struct attr_stack *res,
 	a = parse_attr_line(line, src, lineno, flags);
 	if (!a)
 		return;
-	ALLOC_GROW(res->attrs, res->num_matches + 1, res->alloc);
-	res->attrs[res->num_matches++] = a;
+	ALLOC_GROW_BY(res->attrs, res->num_matches, 1, res->alloc);
+	res->attrs[res->num_matches - 1] = a;
 }
 
 static struct attr_stack *read_attr_from_array(const char **list)
@@ -701,11 +712,12 @@ void git_attr_set_direction(enum git_attr_direction new_direction)
 
 static struct attr_stack *read_attr_from_file(const char *path, unsigned flags)
 {
+	struct strbuf buf = STRBUF_INIT;
 	int fd;
 	FILE *fp;
 	struct attr_stack *res;
-	char buf[2048];
 	int lineno = 0;
+	struct stat st;
 
 	if (flags & READ_ATTR_NOFOLLOW)
 		fd = open_nofollow(path, O_RDONLY);
@@ -717,26 +729,86 @@ static struct attr_stack *read_attr_from_file(const char *path, unsigned flags)
 		return NULL;
 	}
 	fp = xfdopen(fd, "r");
+	if (fstat(fd, &st)) {
+		warning_errno(_("cannot fstat gitattributes file '%s'"), path);
+		fclose(fp);
+		return NULL;
+	}
+	if (st.st_size >= ATTR_MAX_FILE_SIZE) {
+		warning(_("ignoring overly large gitattributes file '%s'"), path);
+		fclose(fp);
+		return NULL;
+	}
 
 	CALLOC_ARRAY(res, 1);
-	while (fgets(buf, sizeof(buf), fp)) {
-		char *bufp = buf;
-		if (!lineno)
-			skip_utf8_bom(&bufp, strlen(bufp));
-		handle_attr_line(res, bufp, path, ++lineno, flags);
+	while (strbuf_getline(&buf, fp) != EOF) {
+		if (!lineno && starts_with(buf.buf, utf8_bom))
+			strbuf_remove(&buf, 0, strlen(utf8_bom));
+		handle_attr_line(res, buf.buf, path, ++lineno, flags);
 	}
+
 	fclose(fp);
+	strbuf_release(&buf);
 	return res;
 }
 
-static struct attr_stack *read_attr_from_index(struct index_state *istate,
-					       const char *path,
-					       unsigned flags)
+static struct attr_stack *read_attr_from_buf(char *buf, const char *path,
+					     unsigned flags)
 {
 	struct attr_stack *res;
-	char *buf, *sp;
+	char *sp;
 	int lineno = 0;
 
+	if (!buf)
+		return NULL;
+
+	CALLOC_ARRAY(res, 1);
+	for (sp = buf; *sp;) {
+		char *ep;
+		int more;
+
+		ep = strchrnul(sp, '\n');
+		more = (*ep == '\n');
+		*ep = '\0';
+		handle_attr_line(res, sp, path, ++lineno, flags);
+		sp = ep + more;
+	}
+	free(buf);
+
+	return res;
+}
+
+static struct attr_stack *read_attr_from_blob(struct index_state *istate,
+					      const struct object_id *tree_oid,
+					      const char *path, unsigned flags)
+{
+	struct object_id oid;
+	unsigned long sz;
+	enum object_type type;
+	void *buf;
+	unsigned short mode;
+
+	if (!tree_oid)
+		return NULL;
+
+	if (get_tree_entry(istate->repo, tree_oid, path, &oid, &mode))
+		return NULL;
+
+	buf = repo_read_object_file(istate->repo, &oid, &type, &sz);
+	if (!buf || type != OBJ_BLOB) {
+		free(buf);
+		return NULL;
+	}
+
+	return read_attr_from_buf(buf, path, flags);
+}
+
+static struct attr_stack *read_attr_from_index(struct index_state *istate,
+					       const char *path, unsigned flags)
+{
+	char *buf;
+	unsigned long size;
+
 	if (!istate)
 		return NULL;
 
@@ -754,32 +826,27 @@ static struct attr_stack *read_attr_from_index(struct index_state *istate,
 	if (!path_in_cone_mode_sparse_checkout(path, istate))
 		return NULL;
 
-	buf = read_blob_data_from_index(istate, path, NULL);
+	buf = read_blob_data_from_index(istate, path, &size);
 	if (!buf)
 		return NULL;
-
-	CALLOC_ARRAY(res, 1);
-	for (sp = buf; *sp; ) {
-		char *ep;
-		int more;
-
-		ep = strchrnul(sp, '\n');
-		more = (*ep == '\n');
-		*ep = '\0';
-		handle_attr_line(res, sp, path, ++lineno, flags);
-		sp = ep + more;
+	if (size >= ATTR_MAX_FILE_SIZE) {
+		warning(_("ignoring overly large gitattributes blob '%s'"), path);
+		return NULL;
 	}
-	free(buf);
-	return res;
+
+	return read_attr_from_buf(buf, path, flags);
 }
 
 static struct attr_stack *read_attr(struct index_state *istate,
+				    const struct object_id *tree_oid,
 				    const char *path, unsigned flags)
 {
 	struct attr_stack *res = NULL;
 
 	if (direction == GIT_ATTR_INDEX) {
 		res = read_attr_from_index(istate, path, flags);
+	} else if (tree_oid) {
+		res = read_attr_from_blob(istate, tree_oid, path, flags);
 	} else if (!is_bare_repository()) {
 		if (direction == GIT_ATTR_CHECKOUT) {
 			res = read_attr_from_index(istate, path, flags);
@@ -839,6 +906,7 @@ static void push_stack(struct attr_stack **attr_stack_p,
 }
 
 static void bootstrap_attr_stack(struct index_state *istate,
+				 const struct object_id *tree_oid,
 				 struct attr_stack **stack)
 {
 	struct attr_stack *e;
@@ -864,7 +932,7 @@ static void bootstrap_attr_stack(struct index_state *istate,
 	}
 
 	/* root directory */
-	e = read_attr(istate, GITATTRIBUTES_FILE, flags | READ_ATTR_NOFOLLOW);
+	e = read_attr(istate, tree_oid, GITATTRIBUTES_FILE, flags | READ_ATTR_NOFOLLOW);
 	push_stack(stack, e, xstrdup(""), 0);
 
 	/* info frame */
@@ -878,6 +946,7 @@ static void bootstrap_attr_stack(struct index_state *istate,
 }
 
 static void prepare_attr_stack(struct index_state *istate,
+			       const struct object_id *tree_oid,
 			       const char *path, int dirlen,
 			       struct attr_stack **stack)
 {
@@ -899,7 +968,7 @@ static void prepare_attr_stack(struct index_state *istate,
 	 * .gitattributes in deeper directories to shallower ones,
 	 * and finally use the built-in set as the default.
 	 */
-	bootstrap_attr_stack(istate, stack);
+	bootstrap_attr_stack(istate, tree_oid, stack);
 
 	/*
 	 * Pop the "info" one that is always at the top of the stack.
@@ -954,7 +1023,7 @@ static void prepare_attr_stack(struct index_state *istate,
 		strbuf_add(&pathbuf, path + pathbuf.len, (len - pathbuf.len));
 		strbuf_addf(&pathbuf, "/%s", GITATTRIBUTES_FILE);
 
-		next = read_attr(istate, pathbuf.buf, READ_ATTR_NOFOLLOW);
+		next = read_attr(istate, tree_oid, pathbuf.buf, READ_ATTR_NOFOLLOW);
 
 		/* reset the pathbuf to not include "/.gitattributes" */
 		strbuf_setlen(&pathbuf, len);
@@ -999,12 +1068,12 @@ static int macroexpand_one(struct all_attrs_item *all_attrs, int nr, int rem);
 static int fill_one(struct all_attrs_item *all_attrs,
 		    const struct match_attr *a, int rem)
 {
-	int i;
+	size_t i;
 
-	for (i = a->num_attr - 1; rem > 0 && i >= 0; i--) {
-		const struct git_attr *attr = a->state[i].attr;
+	for (i = a->num_attr; rem > 0 && i > 0; i--) {
+		const struct git_attr *attr = a->state[i - 1].attr;
 		const char **n = &(all_attrs[attr->attr_nr].value);
-		const char *v = a->state[i].setto;
+		const char *v = a->state[i - 1].setto;
 
 		if (*n == ATTR__UNKNOWN) {
 			*n = v;
@@ -1020,11 +1089,11 @@ static int fill(const char *path, int pathlen, int basename_offset,
 		struct all_attrs_item *all_attrs, int rem)
 {
 	for (; rem > 0 && stack; stack = stack->prev) {
-		int i;
+		unsigned i;
 		const char *base = stack->origin ? stack->origin : "";
 
-		for (i = stack->num_matches - 1; 0 < rem && 0 <= i; i--) {
-			const struct match_attr *a = stack->attrs[i];
+		for (i = stack->num_matches; 0 < rem && 0 < i; i--) {
+			const struct match_attr *a = stack->attrs[i - 1];
 			if (a->is_macro)
 				continue;
 			if (path_matches(path, pathlen, basename_offset,
@@ -1055,11 +1124,11 @@ static void determine_macros(struct all_attrs_item *all_attrs,
 			     const struct attr_stack *stack)
 {
 	for (; stack; stack = stack->prev) {
-		int i;
-		for (i = stack->num_matches - 1; i >= 0; i--) {
-			const struct match_attr *ma = stack->attrs[i];
+		unsigned i;
+		for (i = stack->num_matches; i > 0; i--) {
+			const struct match_attr *ma = stack->attrs[i - 1];
 			if (ma->is_macro) {
-				int n = ma->u.attr->attr_nr;
+				unsigned int n = ma->u.attr->attr_nr;
 				if (!all_attrs[n].macro) {
 					all_attrs[n].macro = ma;
 				}
@@ -1074,8 +1143,8 @@ static void determine_macros(struct all_attrs_item *all_attrs,
  * Otherwise all attributes are collected.
  */
 static void collect_some_attrs(struct index_state *istate,
-			       const char *path,
-			       struct attr_check *check)
+			       const struct object_id *tree_oid,
+			       const char *path, struct attr_check *check)
 {
 	int pathlen, rem, dirlen;
 	const char *cp, *last_slash = NULL;
@@ -1094,7 +1163,7 @@ static void collect_some_attrs(struct index_state *istate,
 		dirlen = 0;
 	}
 
-	prepare_attr_stack(istate, path, dirlen, &check->stack);
+	prepare_attr_stack(istate, tree_oid, path, dirlen, &check->stack);
 	all_attrs_init(&g_attr_hashmap, check);
 	determine_macros(check->all_attrs, check->stack);
 
@@ -1102,16 +1171,47 @@ static void collect_some_attrs(struct index_state *istate,
 	fill(path, pathlen, basename_offset, check->stack, check->all_attrs, rem);
 }
 
+static const char *default_attr_source_tree_object_name;
+
+void set_git_attr_source(const char *tree_object_name)
+{
+	default_attr_source_tree_object_name = xstrdup(tree_object_name);
+}
+
+static void compute_default_attr_source(struct object_id *attr_source)
+{
+	if (!default_attr_source_tree_object_name)
+		default_attr_source_tree_object_name = getenv(GIT_ATTR_SOURCE_ENVIRONMENT);
+
+	if (!default_attr_source_tree_object_name || !is_null_oid(attr_source))
+		return;
+
+	if (repo_get_oid_treeish(the_repository, default_attr_source_tree_object_name, attr_source))
+		die(_("bad --attr-source or GIT_ATTR_SOURCE"));
+}
+
+static struct object_id *default_attr_source(void)
+{
+	static struct object_id attr_source;
+
+	if (is_null_oid(&attr_source))
+		compute_default_attr_source(&attr_source);
+	if (is_null_oid(&attr_source))
+		return NULL;
+	return &attr_source;
+}
+
 void git_check_attr(struct index_state *istate,
 		    const char *path,
 		    struct attr_check *check)
 {
 	int i;
+	const struct object_id *tree_oid = default_attr_source();
 
-	collect_some_attrs(istate, path, check);
+	collect_some_attrs(istate, tree_oid, path, check);
 
 	for (i = 0; i < check->nr; i++) {
-		size_t n = check->items[i].attr->attr_nr;
+		unsigned int n = check->items[i].attr->attr_nr;
 		const char *value = check->all_attrs[n].value;
 		if (value == ATTR__UNKNOWN)
 			value = ATTR__UNSET;
@@ -1123,9 +1223,10 @@ void git_all_attrs(struct index_state *istate,
 		   const char *path, struct attr_check *check)
 {
 	int i;
+	const struct object_id *tree_oid = default_attr_source();
 
 	attr_check_reset(check);
-	collect_some_attrs(istate, path, check);
+	collect_some_attrs(istate, tree_oid, path, check);
 
 	for (i = 0; i < check->all_attrs_nr; i++) {
 		const char *name = check->all_attrs[i].attr->name;