From 13afc8cbde82b559f15f7d70c3d55a89f7425d01 Mon Sep 17 00:00:00 2001
From: Duncan Horn <40036384+dunhor@users.noreply.github.com>
Date: Mon, 10 Jun 2024 21:23:13 -0700
Subject: [PATCH] Update archive_entry_link_resolver to copy the "wide"
 pathname for hardlinks on Windows (#2225)

On Windows, if you are using `archive_entry_link_resolver` and give it
an entry that links to past entry whose pathname was set using a "wide"
string that cannot be represented by the current locale (i.e. WCS -> MBS
conversion fails), this code will crash due to a null pointer read. This
updates to use the `_w` function instead on Windows.

Note: this is a partial cherry-pick from
https://github.com/libarchive/libarchive/pull/2095, which I'm going to
go through and break into smaller pieces in hopes of getting some things
in while discussion of other things can continue.
---
 libarchive/archive_entry_link_resolver.c | 15 ++++++++
 libarchive/test/test_link_resolver.c     | 45 ++++++++++++++++++++++++
 2 files changed, 60 insertions(+)

diff --git a/libarchive/archive_entry_link_resolver.c b/libarchive/archive_entry_link_resolver.c
index 6c6173430..c2fd6895f 100644
--- a/libarchive/archive_entry_link_resolver.c
+++ b/libarchive/archive_entry_link_resolver.c
@@ -201,16 +201,26 @@ archive_entry_linkify(struct archive_entry_linkresolver *res,
 		le = find_entry(res, *e);
 		if (le != NULL) {
 			archive_entry_unset_size(*e);
+#if defined(_WIN32) && !defined(__CYGWIN__)
+			archive_entry_copy_hardlink_w(*e,
+			    archive_entry_pathname_w(le->canonical));
+#else
 			archive_entry_copy_hardlink(*e,
 			    archive_entry_pathname(le->canonical));
+#endif
 		} else
 			insert_entry(res, *e);
 		return;
 	case ARCHIVE_ENTRY_LINKIFY_LIKE_MTREE:
 		le = find_entry(res, *e);
 		if (le != NULL) {
+#if defined(_WIN32) && !defined(__CYGWIN__)
+			archive_entry_copy_hardlink_w(*e,
+			    archive_entry_pathname_w(le->canonical));
+#else
 			archive_entry_copy_hardlink(*e,
 			    archive_entry_pathname(le->canonical));
+#endif
 		} else
 			insert_entry(res, *e);
 		return;
@@ -229,8 +239,13 @@ archive_entry_linkify(struct archive_entry_linkresolver *res,
 			le->entry = t;
 			/* Make the old entry into a hardlink. */
 			archive_entry_unset_size(*e);
+#if defined(_WIN32) && !defined(__CYGWIN__)
+			archive_entry_copy_hardlink_w(*e,
+			    archive_entry_pathname_w(le->canonical));
+#else
 			archive_entry_copy_hardlink(*e,
 			    archive_entry_pathname(le->canonical));
+#endif
 			/* If we ran out of links, return the
 			 * final entry as well. */
 			if (le->links == 0) {
diff --git a/libarchive/test/test_link_resolver.c b/libarchive/test/test_link_resolver.c
index 5bea9a463..6c6230c4d 100644
--- a/libarchive/test/test_link_resolver.c
+++ b/libarchive/test/test_link_resolver.c
@@ -202,3 +202,48 @@ DEFINE_TEST(test_link_resolver)
 	test_linkify_old_cpio();
 	test_linkify_new_cpio();
 }
+
+DEFINE_TEST(test_link_resolver_unicode_win)
+{
+#if !defined(_WIN32) || defined(__CYGWIN__)
+	skipping("This test is meant to verify unicode string handling"
+	    " on Windows with UTF-16 names");
+	return;
+#else
+	struct archive_entry *entry, *e2;
+	struct archive_entry_linkresolver *resolver;
+
+	/* Initialize the resolver. */
+	assert(NULL != (resolver = archive_entry_linkresolver_new()));
+	archive_entry_linkresolver_set_strategy(resolver,
+	    ARCHIVE_FORMAT_TAR_USTAR);
+
+	/* Create an entry with a unicode filename and 2 links. */
+	assert(NULL != (entry = archive_entry_new()));
+	archive_entry_copy_pathname_w(entry, L"\u4f60\u597d.txt");
+	archive_entry_set_ino(entry, 1);
+	archive_entry_set_dev(entry, 2);
+	archive_entry_set_nlink(entry, 2);
+	archive_entry_set_size(entry, 10);
+	archive_entry_linkify(resolver, &entry, &e2);
+
+	/* Shouldn't be altered, since it wasn't seen before. */
+	assert(e2 == NULL);
+	assertEqualWString(L"\u4f60\u597d.txt", archive_entry_pathname_w(entry));
+	assertEqualWString(NULL, archive_entry_hardlink_w(entry));
+	assertEqualInt(10, archive_entry_size(entry));
+
+	/* Link to the same file contents, but a new unicode name. */
+	archive_entry_copy_pathname_w(entry, L"\u518d\u89c1.txt");
+	archive_entry_linkify(resolver, &entry, &e2);
+
+	/* Size & link path should have changed. */
+	assert(e2 == NULL);
+	assertEqualWString(L"\u518d\u89c1.txt", archive_entry_pathname_w(entry));
+	assertEqualWString(L"\u4f60\u597d.txt", archive_entry_hardlink_w(entry));
+	assertEqualInt(0, archive_entry_size(entry));
+
+	archive_entry_free(entry);
+	archive_entry_linkresolver_free(resolver);
+#endif
+}
-- 
2.47.2