1 files changed, 322 insertions, 19 deletions

diff --git a/tree-walk.c b/tree-walk.c
index 5dd9a71804..6a42e402b0 100644
--- a/tree-walk.c
+++ b/tree-walk.c
@@ -22,31 +22,60 @@ static const char *get_mode(const char *str, unsigned int *modep)
 	return str;
 }
 
-static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size)
+static int decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size, struct strbuf *err)
 {
 	const char *path;
 	unsigned int mode, len;
 
-	if (size < 24 || buf[size - 21])
-		die("corrupt tree file");
+	if (size < 23 || buf[size - 21]) {
+		strbuf_addstr(err, _("too-short tree object"));
+		return -1;
+	}
 
 	path = get_mode(buf, &mode);
-	if (!path || !*path)
-		die("corrupt tree file");
+	if (!path) {
+		strbuf_addstr(err, _("malformed mode in tree entry"));
+		return -1;
+	}
+	if (!*path) {
+		strbuf_addstr(err, _("empty filename in tree entry"));
+		return -1;
+	}
 	len = strlen(path) + 1;
 
 	/* Initialize the descriptor entry */
 	desc->entry.path = path;
 	desc->entry.mode = canon_mode(mode);
-	desc->entry.sha1 = (const unsigned char *)(path + len);
+	desc->entry.oid  = (const struct object_id *)(path + len);
+
+	return 0;
 }
 
-void init_tree_desc(struct tree_desc *desc, const void *buffer, unsigned long size)
+static int init_tree_desc_internal(struct tree_desc *desc, const void *buffer, unsigned long size, struct strbuf *err)
 {
 	desc->buffer = buffer;
 	desc->size = size;
 	if (size)
-		decode_tree_entry(desc, buffer, size);
+		return decode_tree_entry(desc, buffer, size, err);
+	return 0;
+}
+
+void init_tree_desc(struct tree_desc *desc, const void *buffer, unsigned long size)
+{
+	struct strbuf err = STRBUF_INIT;
+	if (init_tree_desc_internal(desc, buffer, size, &err))
+		die("%s", err.buf);
+	strbuf_release(&err);
+}
+
+int init_tree_desc_gently(struct tree_desc *desc, const void *buffer, unsigned long size)
+{
+	struct strbuf err = STRBUF_INIT;
+	int result = init_tree_desc_internal(desc, buffer, size, &err);
+	if (result)
+		error("%s", err.buf);
+	strbuf_release(&err);
+	return result;
 }
 
 void *fill_tree_descriptor(struct tree_desc *desc, const unsigned char *sha1)
@@ -73,21 +102,44 @@ static void entry_extract(struct tree_desc *t, struct name_entry *a)
 	*a = t->entry;
 }
 
-void update_tree_entry(struct tree_desc *desc)
+static int update_tree_entry_internal(struct tree_desc *desc, struct strbuf *err)
 {
 	const void *buf = desc->buffer;
-	const unsigned char *end = desc->entry.sha1 + 20;
+	const unsigned char *end = desc->entry.oid->hash + 20;
 	unsigned long size = desc->size;
 	unsigned long len = end - (const unsigned char *)buf;
 
 	if (size < len)
-		die("corrupt tree file");
+		die(_("too-short tree file"));
 	buf = end;
 	size -= len;
 	desc->buffer = buf;
 	desc->size = size;
 	if (size)
-		decode_tree_entry(desc, buf, size);
+		return decode_tree_entry(desc, buf, size, err);
+	return 0;
+}
+
+void update_tree_entry(struct tree_desc *desc)
+{
+	struct strbuf err = STRBUF_INIT;
+	if (update_tree_entry_internal(desc, &err))
+		die("%s", err.buf);
+	strbuf_release(&err);
+}
+
+int update_tree_entry_gently(struct tree_desc *desc)
+{
+	struct strbuf err = STRBUF_INIT;
+	if (update_tree_entry_internal(desc, &err)) {
+		error("%s", err.buf);
+		strbuf_release(&err);
+		/* Stop processing this tree after error */
+		desc->size = 0;
+		return -1;
+	}
+	strbuf_release(&err);
+	return 0;
 }
 
 int tree_entry(struct tree_desc *desc, struct name_entry *entry)
@@ -100,6 +152,17 @@ int tree_entry(struct tree_desc *desc, struct name_entry *entry)
 	return 1;
 }
 
+int tree_entry_gently(struct tree_desc *desc, struct name_entry *entry)
+{
+	if (!desc->size)
+		return 0;
+
+	*entry = desc->entry;
+	if (update_tree_entry_gently(desc))
+		return 0;
+	return 1;
+}
+
 void setup_traverse_info(struct traverse_info *info, const char *base)
 {
 	int pathlen = strlen(base);
@@ -110,7 +173,7 @@ void setup_traverse_info(struct traverse_info *info, const char *base)
 		pathlen--;
 	info->pathlen = pathlen ? pathlen + 1 : 0;
 	info->name.path = base;
-	info->name.sha1 = (void *)(base + pathlen + 1);
+	info->name.oid = (void *)(base + pathlen + 1);
 	if (pathlen)
 		info->prev = &dummy;
 }
@@ -320,6 +383,7 @@ int traverse_trees(int n, struct tree_desc *t, struct traverse_info *info)
 	struct tree_desc_x *tx = xcalloc(n, sizeof(*tx));
 	struct strbuf base = STRBUF_INIT;
 	int interesting = 1;
+	char *traverse_path;
 
 	for (i = 0; i < n; i++)
 		tx[i].d = t[i];
@@ -329,7 +393,11 @@ int traverse_trees(int n, struct tree_desc *t, struct traverse_info *info)
 		make_traverse_path(base.buf, info->prev, &info->name);
 		base.buf[info->pathlen-1] = '/';
 		strbuf_setlen(&base, info->pathlen);
+		traverse_path = xstrndup(base.buf, info->pathlen);
+	} else {
+		traverse_path = xstrndup(info->name.path, info->pathlen);
 	}
+	info->traverse_path = traverse_path;
 	for (;;) {
 		int trees_used;
 		unsigned long mask, dirmask;
@@ -411,19 +479,27 @@ int traverse_trees(int n, struct tree_desc *t, struct traverse_info *info)
 	for (i = 0; i < n; i++)
 		free_extended_entry(tx + i);
 	free(tx);
+	free(traverse_path);
+	info->traverse_path = NULL;
 	strbuf_release(&base);
 	return error;
 }
 
+struct dir_state {
+	void *tree;
+	unsigned long size;
+	unsigned char sha1[20];
+};
+
 static int find_tree_entry(struct tree_desc *t, const char *name, unsigned char *result, unsigned *mode)
 {
 	int namelen = strlen(name);
 	while (t->size) {
 		const char *entry;
-		const unsigned char *sha1;
+		const struct object_id *oid;
 		int entrylen, cmp;
 
-		sha1 = tree_entry_extract(t, &entry, mode);
+		oid = tree_entry_extract(t, &entry, mode);
 		entrylen = tree_entry_len(&t->entry);
 		update_tree_entry(t);
 		if (entrylen > namelen)
@@ -434,7 +510,7 @@ static int find_tree_entry(struct tree_desc *t, const char *name, unsigned char
 		if (cmp < 0)
 			break;
 		if (entrylen == namelen) {
-			hashcpy(result, sha1);
+			hashcpy(result, oid->hash);
 			return 0;
 		}
 		if (name[entrylen] != '/')
@@ -442,10 +518,10 @@ static int find_tree_entry(struct tree_desc *t, const char *name, unsigned char
 		if (!S_ISDIR(*mode))
 			break;
 		if (++entrylen == namelen) {
-			hashcpy(result, sha1);
+			hashcpy(result, oid->hash);
 			return 0;
 		}
-		return get_tree_entry(sha1, name + entrylen, result, mode);
+		return get_tree_entry(oid->hash, name + entrylen, result, mode);
 	}
 	return -1;
 }
@@ -478,6 +554,205 @@ int get_tree_entry(const unsigned char *tree_sha1, const char *name, unsigned ch
 	return retval;
 }
 
+/*
+ * This is Linux's built-in max for the number of symlinks to follow.
+ * That limit, of course, does not affect git, but it's a reasonable
+ * choice.
+ */
+#define GET_TREE_ENTRY_FOLLOW_SYMLINKS_MAX_LINKS 40
+
+/**
+ * Find a tree entry by following symlinks in tree_sha (which is
+ * assumed to be the root of the repository).  In the event that a
+ * symlink points outside the repository (e.g. a link to /foo or a
+ * root-level link to ../foo), the portion of the link which is
+ * outside the repository will be returned in result_path, and *mode
+ * will be set to 0.  It is assumed that result_path is uninitialized.
+ * If there are no symlinks, or the end result of the symlink chain
+ * points to an object inside the repository, result will be filled in
+ * with the sha1 of the found object, and *mode will hold the mode of
+ * the object.
+ *
+ * See the code for enum follow_symlink_result for a description of
+ * the return values.
+ */
+enum follow_symlinks_result get_tree_entry_follow_symlinks(unsigned char *tree_sha1, const char *name, unsigned char *result, struct strbuf *result_path, unsigned *mode)
+{
+	int retval = MISSING_OBJECT;
+	struct dir_state *parents = NULL;
+	size_t parents_alloc = 0;
+	ssize_t parents_nr = 0;
+	unsigned char current_tree_sha1[20];
+	struct strbuf namebuf = STRBUF_INIT;
+	struct tree_desc t;
+	int follows_remaining = GET_TREE_ENTRY_FOLLOW_SYMLINKS_MAX_LINKS;
+	int i;
+
+	init_tree_desc(&t, NULL, 0UL);
+	strbuf_addstr(&namebuf, name);
+	hashcpy(current_tree_sha1, tree_sha1);
+
+	while (1) {
+		int find_result;
+		char *first_slash;
+		char *remainder = NULL;
+
+		if (!t.buffer) {
+			void *tree;
+			unsigned char root[20];
+			unsigned long size;
+			tree = read_object_with_reference(current_tree_sha1,
+							  tree_type, &size,
+							  root);
+			if (!tree)
+				goto done;
+
+			ALLOC_GROW(parents, parents_nr + 1, parents_alloc);
+			parents[parents_nr].tree = tree;
+			parents[parents_nr].size = size;
+			hashcpy(parents[parents_nr].sha1, root);
+			parents_nr++;
+
+			if (namebuf.buf[0] == '\0') {
+				hashcpy(result, root);
+				retval = FOUND;
+				goto done;
+			}
+
+			if (!size)
+				goto done;
+
+			/* descend */
+			init_tree_desc(&t, tree, size);
+		}
+
+		/* Handle symlinks to e.g. a//b by removing leading slashes */
+		while (namebuf.buf[0] == '/') {
+			strbuf_remove(&namebuf, 0, 1);
+		}
+
+		/* Split namebuf into a first component and a remainder */
+		if ((first_slash = strchr(namebuf.buf, '/'))) {
+			*first_slash = 0;
+			remainder = first_slash + 1;
+		}
+
+		if (!strcmp(namebuf.buf, "..")) {
+			struct dir_state *parent;
+			/*
+			 * We could end up with .. in the namebuf if it
+			 * appears in a symlink.
+			 */
+
+			if (parents_nr == 1) {
+				if (remainder)
+					*first_slash = '/';
+				strbuf_add(result_path, namebuf.buf,
+					   namebuf.len);
+				*mode = 0;
+				retval = FOUND;
+				goto done;
+			}
+			parent = &parents[parents_nr - 1];
+			free(parent->tree);
+			parents_nr--;
+			parent = &parents[parents_nr - 1];
+			init_tree_desc(&t, parent->tree, parent->size);
+			strbuf_remove(&namebuf, 0, remainder ? 3 : 2);
+			continue;
+		}
+
+		/* We could end up here via a symlink to dir/.. */
+		if (namebuf.buf[0] == '\0') {
+			hashcpy(result, parents[parents_nr - 1].sha1);
+			retval = FOUND;
+			goto done;
+		}
+
+		/* Look up the first (or only) path component in the tree. */
+		find_result = find_tree_entry(&t, namebuf.buf,
+					      current_tree_sha1, mode);
+		if (find_result) {
+			goto done;
+		}
+
+		if (S_ISDIR(*mode)) {
+			if (!remainder) {
+				hashcpy(result, current_tree_sha1);
+				retval = FOUND;
+				goto done;
+			}
+			/* Descend the tree */
+			t.buffer = NULL;
+			strbuf_remove(&namebuf, 0,
+				      1 + first_slash - namebuf.buf);
+		} else if (S_ISREG(*mode)) {
+			if (!remainder) {
+				hashcpy(result, current_tree_sha1);
+				retval = FOUND;
+			} else {
+				retval = NOT_DIR;
+			}
+			goto done;
+		} else if (S_ISLNK(*mode)) {
+			/* Follow a symlink */
+			unsigned long link_len;
+			size_t len;
+			char *contents, *contents_start;
+			struct dir_state *parent;
+			enum object_type type;
+
+			if (follows_remaining-- == 0) {
+				/* Too many symlinks followed */
+				retval = SYMLINK_LOOP;
+				goto done;
+			}
+
+			/*
+			 * At this point, we have followed at a least
+			 * one symlink, so on error we need to report this.
+			 */
+			retval = DANGLING_SYMLINK;
+
+			contents = read_sha1_file(current_tree_sha1, &type,
+						  &link_len);
+
+			if (!contents)
+				goto done;
+
+			if (contents[0] == '/') {
+				strbuf_addstr(result_path, contents);
+				free(contents);
+				*mode = 0;
+				retval = FOUND;
+				goto done;
+			}
+
+			if (remainder)
+				len = first_slash - namebuf.buf;
+			else
+				len = namebuf.len;
+
+			contents_start = contents;
+
+			parent = &parents[parents_nr - 1];
+			init_tree_desc(&t, parent->tree, parent->size);
+			strbuf_splice(&namebuf, 0, len,
+				      contents_start, link_len);
+			if (remainder)
+				namebuf.buf[link_len] = '/';
+			free(contents);
+		}
+	}
+done:
+	for (i = 0; i < parents_nr; i++)
+		free(parents[i].tree);
+	free(parents);
+
+	strbuf_release(&namebuf);
+	return retval;
+}
+
 static int match_entry(const struct pathspec_item *item,
 		       const struct name_entry *entry, int pathlen,
 		       const char *match, int matchlen,
@@ -728,6 +1003,19 @@ static enum interesting do_match(const struct name_entry *entry,
 				 */
 				if (ps->recursive && S_ISDIR(entry->mode))
 					return entry_interesting;
+
+				/*
+				 * When matching against submodules with
+				 * wildcard characters, ensure that the entry
+				 * at least matches up to the first wild
+				 * character.  More accurate matching can then
+				 * be performed in the submodule itself.
+				 */
+				if (ps->recursive && S_ISGITLINK(entry->mode) &&
+				    !ps_strncmp(item, match + baselen,
+						entry->path,
+						item->nowildcard_len - baselen))
+					return entry_interesting;
 			}
 
 			continue;
@@ -764,6 +1052,21 @@ match_wildcards:
 			strbuf_setlen(base, base_offset + baselen);
 			return entry_interesting;
 		}
+
+		/*
+		 * When matching against submodules with
+		 * wildcard characters, ensure that the entry
+		 * at least matches up to the first wild
+		 * character.  More accurate matching can then
+		 * be performed in the submodule itself.
+		 */
+		if (ps->recursive && S_ISGITLINK(entry->mode) &&
+		    !ps_strncmp(item, match, base->buf + base_offset,
+				item->nowildcard_len)) {
+			strbuf_setlen(base, base_offset + baselen);
+			return entry_interesting;
+		}
+
 		strbuf_setlen(base, base_offset + baselen);
 
 		/*
@@ -771,7 +1074,7 @@ match_wildcards:
 		 * later on.
 		 * max_depth is ignored but we may consider support it
 		 * in future, see
-		 * http://thread.gmane.org/gmane.comp.version-control.git/163757/focus=163840
+		 * https://public-inbox.org/git/7vmxo5l2g4.fsf@alter.siamese.dyndns.org/
 		 */
 		if (ps->recursive && S_ISDIR(entry->mode))
 			return entry_interesting;