blob: introduce creating a blob by writing into a stream

The pair of `git_blob_create_frombuffer()` and
`git_blob_create_frombuffer_commit()` is meant to replace
`git_blob_create_fromchunks()` by providing a way for a user to write a
new blob when they want filtering or they do not know the size.

This approach allows the caller to retain control over when to add data
to this buffer and a more natural fit into higher-level language's own
stream abstractions instead of having to handle IO wait in the callback.

The in-memory buffer size of 2MB is chosen somewhat arbitrarily to be a
round multiple of usual page sizes and a value where most blobs seem
likely to be either going to be way below or way over that size. It's
also a round number of pages.

This implementation re-uses the helper we have from `_fromchunks()` so
we end up writing everything to disk, but hopefully more efficiently
than with a default filebuf. A later optimisation can be to avoid
writing the in-memory contents to disk, with some extra complexity.

1 files changed, 103 insertions, 0 deletions

diff --git a/tests/object/blob/fromstream.c b/tests/object/blob/fromstream.c
new file mode 100644
index 000000000..10f2d8b31
--- /dev/null
+++ b/tests/object/blob/fromstream.c
@@ -0,0 +1,103 @@
+#include "clar_libgit2.h"
+#include "buffer.h"
+#include "posix.h"
+#include "path.h"
+#include "fileops.h"
+
+static git_repository *repo;
+static char textual_content[] = "libgit2\n\r\n\0";
+
+void test_object_blob_fromstream__initialize(void)
+{
+	repo = cl_git_sandbox_init("testrepo.git");
+}
+
+void test_object_blob_fromstream__cleanup(void)
+{
+	cl_git_sandbox_cleanup();
+}
+
+static int text_chunked_source_cb(char *content, size_t max_length, void *payload)
+{
+	int *count;
+
+	GIT_UNUSED(max_length);
+
+	count = (int *)payload;
+	(*count)--;
+
+	if (*count == 0)
+		return 0;
+
+	strcpy(content, textual_content);
+	return (int)strlen(textual_content);
+}
+
+void test_object_blob_fromstream__multiple_write(void)
+{
+	git_oid expected_id, id;
+	git_object *blob;
+	git_writestream *stream;
+	int i, howmany = 6;
+
+	cl_git_pass(git_oid_fromstr(&expected_id, "321cbdf08803c744082332332838df6bd160f8f9"));
+
+	cl_git_fail_with(GIT_ENOTFOUND,
+			 git_object_lookup(&blob, repo, &expected_id, GIT_OBJ_ANY));
+
+	cl_git_pass(git_blob_create_fromstream(&stream, repo, NULL));
+
+	for (i = 0; i < howmany; i++)
+		cl_git_pass(stream->write(stream, textual_content, strlen(textual_content)));
+
+	cl_git_pass(git_blob_create_fromstream_end(&id, stream));
+	cl_assert_equal_oid(&expected_id, &id);
+
+	cl_git_pass(git_object_lookup(&blob, repo, &expected_id, GIT_OBJ_BLOB));
+
+	git_object_free(blob);
+}
+
+#define GITATTR "* text=auto\n" \
+	"*.txt text\n" \
+	"*.data binary\n"
+
+static void write_attributes(git_repository *repo)
+{
+	git_buf buf = GIT_BUF_INIT;
+
+	cl_git_pass(git_buf_joinpath(&buf, git_repository_path(repo), "info"));
+	cl_git_pass(git_buf_joinpath(&buf, git_buf_cstr(&buf), "attributes"));
+
+	cl_git_pass(git_futils_mkpath2file(git_buf_cstr(&buf), 0777));
+	cl_git_rewritefile(git_buf_cstr(&buf), GITATTR);
+
+	git_buf_free(&buf);
+}
+
+static void assert_named_chunked_blob(const char *expected_sha, const char *fake_name)
+{
+	git_oid expected_id, id;
+	git_writestream *stream;
+	int i, howmany = 6;
+
+	cl_git_pass(git_oid_fromstr(&expected_id, expected_sha));
+
+	cl_git_pass(git_blob_create_fromstream(&stream, repo, fake_name));
+
+	for (i = 0; i < howmany; i++)
+		cl_git_pass(stream->write(stream, textual_content, strlen(textual_content)));
+
+	cl_git_pass(git_blob_create_fromstream_end(&id, stream));
+
+	cl_assert_equal_oid(&expected_id, &id);
+}
+
+void test_object_blob_fromstream__creating_a_blob_from_chunks_honors_the_attributes_directives(void)
+{
+	write_attributes(repo);
+
+	assert_named_chunked_blob("321cbdf08803c744082332332838df6bd160f8f9", "dummy.data");
+	assert_named_chunked_blob("e9671e138a780833cb689753570fd10a55be84fb", "dummy.txt");
+	assert_named_chunked_blob("e9671e138a780833cb689753570fd10a55be84fb", "dummy.dunno");
+}