New upstream version 1.0.1+dfsg.1

docs/changelog.md

@@ -1,3 +1,33 @@
+v1.0.1
+------
+
+This is a bugfix release with the following changes:
+
+- Calculating information about renamed files during merges is more
+  efficient because dissimilarity about files is now being cached and
+  no longer needs to be recomputed.
+  
+- The `git_worktree_prune_init_options` has been correctly restored for
+  backward compatibility.  In v1.0 it was incorrectly deprecated with a
+  typo.
+
+- The optional ntlmclient dependency now supports NetBSD.
+
+- A bug where attempting to stash on a bare repository may have failed
+  has been fixed.
+
+- Configuration files that are unreadable due to permissions are now
+  silently ignored, and treated as if they do not exist.  This matches
+  git's behavior; previously this case would have been an error.
+
+- v4 index files are now correctly written; previously we would read
+  them correctly but would not write the prefix-compression accurately,
+  causing corruption.
+
+- A bug where the smart HTTP transport could not read large data packets
+  has been fixed.  Previously, fetching from servers like Gerrit, that
+  sent large data packets, would error.
+
 v1.0
 ----
 

include/git2/version.h

@@ -7,10 +7,10 @@
 #ifndef INCLUDE_git_version_h__
 #define INCLUDE_git_version_h__
 
-#define LIBGIT2_VERSION "1.0.0"
+#define LIBGIT2_VERSION "1.0.1"
 #define LIBGIT2_VER_MAJOR 1
 #define LIBGIT2_VER_MINOR 0
-#define LIBGIT2_VER_REVISION 0
+#define LIBGIT2_VER_REVISION 1
 #define LIBGIT2_VER_PATCH 0
 
 #define LIBGIT2_SOVERSION "1.0"

package.json

@@ -1,6 +1,6 @@
 {
   "name": "libgit2",
-  "version": "0.27.0",
+  "version": "1.0.1",
   "repo": "https://github.com/libgit2/libgit2",
   "description": " A cross-platform, linkable library implementation of Git that you can use in your application.",
   "install": "mkdir build && cd build && cmake .. && cmake --build ."

script/release.py

@@ -56,6 +56,17 @@ def verify_version(version):
         if v[0] != v[1]:
             raise Error("version.h: define '{}' does not match (got '{}', expected '{}')".format(k, v[0], v[1]))
 
+    with open('package.json') as f:
+        pkg = json.load(f)
+
+    try:
+        pkg_version = Version(pkg["version"])
+    except KeyError as err:
+        raise Error("package.json: missing the field {}".format(err))
+
+    if pkg_version != version:
+        raise Error("package.json: version does not match (got '{}', expected '{}')".format(pkg_version, version))
+
 def generate_relnotes(tree, version):
     with open('docs/changelog.md') as f:
         lines = f.readlines()

src/config_file.c

@@ -111,6 +111,15 @@ static int config_file_open(git_config_backend *cfg, git_config_level_t level, c
 	if (!git_path_exists(b->file.path))
 		return 0;
 
+	/*
+	 * git silently ignores configuration files that are not
+	 * readable.  We emulate that behavior.  This is particularly
+	 * important for sandboxed applications on macOS where the
+	 * git configuration files may not be readable.
+	 */
+	if (p_access(b->file.path, R_OK) < 0)
+		return GIT_ENOTFOUND;
+
 	if (res < 0 || (res = config_file_read(b->entries, repo, &b->file, level, 0)) < 0) {
 		git_config_entries_free(b->entries);
 		b->entries = NULL;

src/index.c

@@ -2744,7 +2744,7 @@ static int write_disk_entry(git_filebuf *file, git_index_entry *entry, const cha
 			++same_len;
 		}
 		path_len -= same_len;
-		varint_len = git_encode_varint(NULL, 0, same_len);
+		varint_len = git_encode_varint(NULL, 0, strlen(last) - same_len);
 	}
 
 	disk_size = index_entry_size(path_len, varint_len, entry->flags);
@@ -2795,7 +2795,7 @@ static int write_disk_entry(git_filebuf *file, git_index_entry *entry, const cha
 
 	if (last) {
 		varint_len = git_encode_varint((unsigned char *) path,
-					  disk_size, same_len);
+					  disk_size, strlen(last) - same_len);
 		assert(varint_len > 0);
 		path += varint_len;
 		disk_size -= varint_len;

src/merge.c

@@ -68,6 +68,16 @@ struct merge_diff_df_data {
 	git_merge_diff *prev_conflict;
 };
 
+/*
+ * This acts as a negative cache entry marker. In case we've tried to calculate
+ * similarity metrics for a given blob already but `git_hashsig` determined
+ * that it's too small in order to have a meaningful hash signature, we will
+ * insert the address of this marker instead of `NULL`. Like this, we can
+ * easily check whether we have checked a gien entry already and skip doing the
+ * calculation again and again.
+ */
+static int cache_invalid_marker;
+
 /* Merge base computation */
 
 int merge_bases_many(git_commit_list **out, git_revwalk **walk_out, git_repository *repo, size_t length, const git_oid input_array[])
@@ -1027,6 +1037,9 @@ static int index_entry_similarity_calc(
 	git_object_size_t blobsize;
 	int error;
 
+	if (*out || *out == &cache_invalid_marker)
+		return 0;
+
 	*out = NULL;
 
 	if ((error = git_blob_lookup(&blob, repo, &entry->id)) < 0)
@@ -1047,6 +1060,8 @@ static int index_entry_similarity_calc(
 	error = opts->metric->buffer_signature(out, &diff_file,
 		git_blob_rawcontent(blob), (size_t)blobsize,
 		opts->metric->payload);
+	if (error == GIT_EBUFS)
+		*out = &cache_invalid_marker;
 
 	git_blob_free(blob);
 
@@ -1069,18 +1084,16 @@ static int index_entry_similarity_inexact(
 		return 0;
 
 	/* update signature cache if needed */
-	if (!cache[a_idx] && (error = index_entry_similarity_calc(&cache[a_idx], repo, a, opts)) < 0)
-		return error;
-	if (!cache[b_idx] && (error = index_entry_similarity_calc(&cache[b_idx], repo, b, opts)) < 0)
+	if ((error = index_entry_similarity_calc(&cache[a_idx], repo, a, opts)) < 0 ||
+	    (error = index_entry_similarity_calc(&cache[b_idx], repo, b, opts)) < 0)
 		return error;
 
 	/* some metrics may not wish to process this file (too big / too small) */
-	if (!cache[a_idx] || !cache[b_idx])
+	if (cache[a_idx] == &cache_invalid_marker || cache[b_idx] == &cache_invalid_marker)
 		return 0;
 
 	/* compare signatures */
-	if (opts->metric->similarity(
-		&score, cache[a_idx], cache[b_idx], opts->metric->payload) < 0)
+	if (opts->metric->similarity(&score, cache[a_idx], cache[b_idx], opts->metric->payload) < 0)
 		return -1;
 
 	/* clip score */
@@ -1550,7 +1563,7 @@ int git_merge_diff_list__find_renames(
 done:
 	if (cache != NULL) {
 		for (i = 0; i < cache_size; ++i) {
-			if (cache[i] != NULL)
+			if (cache[i] != NULL && cache[i] != &cache_invalid_marker)
 				opts->metric->free_signature(cache[i], opts->metric->payload);
 		}
 

src/stash.c

@@ -173,7 +173,7 @@ static int stash_to_index(
 	git_index *index,
 	const char *path)
 {
-	git_index *repo_index;
+	git_index *repo_index = NULL;
 	git_index_entry entry = {{0}};
 	struct stat st;
 	int error;
@@ -187,7 +187,7 @@ static int stash_to_index(
 		return error;
 
 	git_index_entry__init_from_stat(&entry, &st,
-		(repo_index != NULL || !repo_index->distrust_filemode));
+		(repo_index == NULL || !repo_index->distrust_filemode));
 
 	entry.path = path;
 

src/transports/httpclient.c

@@ -1038,6 +1038,7 @@ on_error:
 
 GIT_INLINE(int) client_read(git_http_client *client)
 {
+	http_parser_context *parser_context = client->parser.data;
 	git_stream *stream;
 	char *buf = client->read_buf.ptr + client->read_buf.size;
 	size_t max_len;
@@ -1054,6 +1055,9 @@ GIT_INLINE(int) client_read(git_http_client *client)
 	max_len = client->read_buf.asize - client->read_buf.size;
 	max_len = min(max_len, INT_MAX);
 
+	if (parser_context->output_size)
+		max_len = min(max_len, parser_context->output_size);
+
 	if (max_len == 0) {
 		git_error_set(GIT_ERROR_HTTP, "no room in output buffer");
 		return -1;
@@ -1191,7 +1195,7 @@ static void complete_response_body(git_http_client *client)
 	/* If we're not keeping alive, don't bother. */
 	if (!client->keepalive) {
 		client->connected = 0;
-		return;
+		goto done;
 	}
 
 	parser_context.client = client;
@@ -1205,6 +1209,9 @@ static void complete_response_body(git_http_client *client)
 		git_error_clear();
 		client->connected = 0;
 	}
+
+done:
+	git_buf_clear(&client->read_buf);
 }
 
 int git_http_client_send_request(
@@ -1419,15 +1426,20 @@ int git_http_client_read_body(
 	client->parser.data = &parser_context;
 
 	/*
-	 * Clients expect to get a non-zero amount of data from us.
-	 * With a sufficiently small buffer, one might only read a chunk
-	 * length.  Loop until we actually have data to return.
+	 * Clients expect to get a non-zero amount of data from us,
+	 * so we either block until we have data to return, until we
+	 * hit EOF or there's an error.  Do this in a loop, since we
+	 * may end up reading only some stream metadata (like chunk
+	 * information).
 	 */
 	while (!parser_context.output_written) {
 		error = client_read_and_parse(client);
 
 		if (error <= 0)
 			goto done;
+
+		if (client->state == DONE)
+			break;
 	}
 
 	assert(parser_context.output_written <= INT_MAX);

src/worktree.c

@@ -506,7 +506,7 @@ int git_worktree_prune_options_init(
 	return 0;
 }
 
-int git_worktree_pruneinit_options(git_worktree_prune_options *opts,
+int git_worktree_prune_init_options(git_worktree_prune_options *opts,
 	unsigned int version)
 {
 	return git_worktree_prune_options_init(opts, version);

tests/config/read.c

@@ -849,6 +849,23 @@ void test_config_read__invalid_quoted_third_section(void)
 	git_config_free(cfg);
 }
 
+void test_config_read__unreadable_file_ignored(void)
+{
+	git_buf buf = GIT_BUF_INIT;
+	git_config *cfg;
+	int ret;
+
+	cl_set_cleanup(&clean_test_config, NULL);
+	cl_git_mkfile("./testconfig", "[some] var = value\n[some \"OtheR\"] var = value");
+	cl_git_pass(p_chmod("./testconfig", 0));
+
+	ret = git_config_open_ondisk(&cfg, "./test/config");
+	cl_assert(ret == 0 || ret == GIT_ENOTFOUND);
+
+	git_config_free(cfg);
+	git_buf_dispose(&buf);
+}
+
 void test_config_read__single_line(void)
 {
 	git_buf buf = GIT_BUF_INIT;

tests/index/version.c

@@ -43,6 +43,7 @@ void test_index_version__can_write_v4(void)
 	    "xz",
 	    "xyzzyx"
 	};
+	git_repository *repo;
 	git_index_entry entry;
 	git_index *index;
 	size_t i;
@@ -63,7 +64,8 @@ void test_index_version__can_write_v4(void)
 	cl_git_pass(git_index_write(index));
 	git_index_free(index);
 
-	cl_git_pass(git_repository_index(&index, g_repo));
+	cl_git_pass(git_repository_open(&repo, git_repository_path(g_repo)));
+	cl_git_pass(git_repository_index(&index, repo));
 	cl_assert(git_index_version(index) == 4);
 
 	for (i = 0; i < ARRAY_SIZE(paths); i++) {
@@ -74,6 +76,7 @@ void test_index_version__can_write_v4(void)
 	}
 
 	git_index_free(index);
+	git_repository_free(repo);
 }
 
 void test_index_version__v4_uses_path_compression(void)

tests/merge/trees/renames.c

@@ -274,3 +274,80 @@ void test_merge_trees_renames__submodules(void)
 	cl_assert(merge_test_index(index, merge_index_entries, 7));
 	git_index_free(index);
 }
+
+void test_merge_trees_renames__cache_recomputation(void)
+{
+	git_oid blob, binary, ancestor_oid, theirs_oid, ours_oid;
+	git_merge_options opts = GIT_MERGE_OPTIONS_INIT;
+	git_buf path = GIT_BUF_INIT;
+	git_treebuilder *builder;
+	git_tree *ancestor_tree, *their_tree, *our_tree;
+	git_index *index;
+	size_t blob_size;
+	void *data;
+	size_t i;
+
+	cl_git_pass(git_oid_fromstr(&blob, "a2d8d1824c68541cca94ffb90f79291eba495921"));
+
+	/*
+	 * Create a 50MB blob that consists of NUL bytes only. It is important
+	 * that this blob is of a special format, most importantly it cannot
+	 * contain more than four non-consecutive newlines or NUL bytes. This
+	 * is because of git_hashsig's inner workings where all files with less
+	 * than four "lines" are deemed to small.
+	 */
+	blob_size = 50 * 1024 * 1024;
+	cl_assert(data = git__calloc(blob_size, 1));
+	cl_git_pass(git_blob_create_from_buffer(&binary, repo, data, blob_size));
+
+	/*
+	 * Create the common ancestor, which has 1000 dummy blobs and the binary
+	 * blob. The dummy blobs serve as potential rename targets for the
+	 * dummy blob.
+	 */
+	cl_git_pass(git_treebuilder_new(&builder, repo, NULL));
+	for (i = 0; i < 1000; i++) {
+		cl_git_pass(git_buf_printf(&path, "%"PRIuMAX".txt", i));
+		cl_git_pass(git_treebuilder_insert(NULL, builder, path.ptr, &blob, GIT_FILEMODE_BLOB));
+		git_buf_clear(&path);
+	}
+	cl_git_pass(git_treebuilder_insert(NULL, builder, "original.bin", &binary, GIT_FILEMODE_BLOB));
+	cl_git_pass(git_treebuilder_write(&ancestor_oid, builder));
+
+	/* We now the binary blob in our tree. */
+	cl_git_pass(git_treebuilder_remove(builder, "original.bin"));
+	cl_git_pass(git_treebuilder_insert(NULL, builder, "renamed.bin", &binary, GIT_FILEMODE_BLOB));
+	cl_git_pass(git_treebuilder_write(&ours_oid, builder));
+
+	git_treebuilder_free(builder);
+
+	/* And move everything into a subdirectory in their tree. */
+	cl_git_pass(git_treebuilder_new(&builder, repo, NULL));
+	cl_git_pass(git_treebuilder_insert(NULL, builder, "subdir", &ancestor_oid, GIT_FILEMODE_TREE));
+	cl_git_pass(git_treebuilder_write(&theirs_oid, builder));
+
+	/*
+	 * Now merge ancestor, ours and theirs. As `git_hashsig` refuses to
+	 * create a hash signature for the 50MB binary file, we historically
+	 * didn't cache the hashsig computation for it. As a result, we now
+	 * started looking up the 50MB blob and scanning it at least 1000
+	 * times, which takes a long time.
+	 *
+	 * The number of 1000 blobs is chosen in such a way that it's
+	 * noticeable when the bug creeps in again, as it takes around 12
+	 * minutes on my machine to compute the following merge.
+	 */
+	opts.target_limit = 5000;
+	cl_git_pass(git_tree_lookup(&ancestor_tree, repo, &ancestor_oid));
+	cl_git_pass(git_tree_lookup(&their_tree, repo, &theirs_oid));
+	cl_git_pass(git_tree_lookup(&our_tree, repo, &ours_oid));
+	cl_git_pass(git_merge_trees(&index, repo, ancestor_tree, our_tree, their_tree, &opts));
+
+	git_treebuilder_free(builder);
+	git_buf_dispose(&path);
+	git_index_free(index);
+	git_tree_free(ancestor_tree);
+	git_tree_free(their_tree);
+	git_tree_free(our_tree);
+	git__free(data);
+}

tests/online/clone.c

@@ -11,6 +11,7 @@
 #define BB_REPO_URL "https://libgit3@bitbucket.org/libgit2/testgitrepository.git"
 #define BB_REPO_URL_WITH_PASS "https://libgit3:libgit3@bitbucket.org/libgit2/testgitrepository.git"
 #define BB_REPO_URL_WITH_WRONG_PASS "https://libgit3:wrong@bitbucket.org/libgit2/testgitrepository.git"
+#define GOOGLESOURCE_REPO_URL "https://chromium.googlesource.com/external/github.com/sergi/go-diff"
 
 #define SSH_REPO_URL "ssh://github.com/libgit2/TestGitRepository"
 
@@ -463,6 +464,13 @@ void test_online_clone__bitbucket_falls_back_to_specified_creds(void)
 	cl_fixture_cleanup("./foo");
 }
 
+void test_online_clone__googlesource(void)
+{
+	cl_git_pass(git_clone(&g_repo, GOOGLESOURCE_REPO_URL, "./foo", &g_options));
+	git_repository_free(g_repo); g_repo = NULL;
+	cl_fixture_cleanup("./foo");
+}
+
 static int cancel_at_half(const git_indexer_progress *stats, void *payload)
 {
 	GIT_UNUSED(payload);