reftable: implement refname validation

The packed/loose format has restrictions on refnames: a and a/b cannot
coexist. This limitation does not apply to reftable per se, but must be
maintained for interoperability. This code adds validation routines to
abort transactions that are trying to add invalid names.

Signed-off-by: Han-Wen Nienhuys <hanwen@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 340 insertions, 0 deletions

diff --git a/reftable/refname.c b/reftable/refname.c
new file mode 100644
index 0000000000..9573496932
--- /dev/null
+++ b/reftable/refname.c
@@ -0,0 +1,209 @@
+/*
+  Copyright 2020 Google LLC
+
+  Use of this source code is governed by a BSD-style
+  license that can be found in the LICENSE file or at
+  https://developers.google.com/open-source/licenses/bsd
+*/
+
+#include "system.h"
+#include "reftable-error.h"
+#include "basics.h"
+#include "refname.h"
+#include "reftable-iterator.h"
+
+struct find_arg {
+	char **names;
+	const char *want;
+};
+
+static int find_name(size_t k, void *arg)
+{
+	struct find_arg *f_arg = arg;
+	return strcmp(f_arg->names[k], f_arg->want) >= 0;
+}
+
+static int modification_has_ref(struct modification *mod, const char *name)
+{
+	struct reftable_ref_record ref = { NULL };
+	int err = 0;
+
+	if (mod->add_len > 0) {
+		struct find_arg arg = {
+			.names = mod->add,
+			.want = name,
+		};
+		int idx = binsearch(mod->add_len, find_name, &arg);
+		if (idx < mod->add_len && !strcmp(mod->add[idx], name)) {
+			return 0;
+		}
+	}
+
+	if (mod->del_len > 0) {
+		struct find_arg arg = {
+			.names = mod->del,
+			.want = name,
+		};
+		int idx = binsearch(mod->del_len, find_name, &arg);
+		if (idx < mod->del_len && !strcmp(mod->del[idx], name)) {
+			return 1;
+		}
+	}
+
+	err = reftable_table_read_ref(&mod->tab, name, &ref);
+	reftable_ref_record_release(&ref);
+	return err;
+}
+
+static void modification_release(struct modification *mod)
+{
+	/* don't delete the strings themselves; they're owned by ref records.
+	 */
+	FREE_AND_NULL(mod->add);
+	FREE_AND_NULL(mod->del);
+	mod->add_len = 0;
+	mod->del_len = 0;
+}
+
+static int modification_has_ref_with_prefix(struct modification *mod,
+					    const char *prefix)
+{
+	struct reftable_iterator it = { NULL };
+	struct reftable_ref_record ref = { NULL };
+	int err = 0;
+
+	if (mod->add_len > 0) {
+		struct find_arg arg = {
+			.names = mod->add,
+			.want = prefix,
+		};
+		int idx = binsearch(mod->add_len, find_name, &arg);
+		if (idx < mod->add_len &&
+		    !strncmp(prefix, mod->add[idx], strlen(prefix)))
+			goto done;
+	}
+	err = reftable_table_seek_ref(&mod->tab, &it, prefix);
+	if (err)
+		goto done;
+
+	while (1) {
+		err = reftable_iterator_next_ref(&it, &ref);
+		if (err)
+			goto done;
+
+		if (mod->del_len > 0) {
+			struct find_arg arg = {
+				.names = mod->del,
+				.want = ref.refname,
+			};
+			int idx = binsearch(mod->del_len, find_name, &arg);
+			if (idx < mod->del_len &&
+			    !strcmp(ref.refname, mod->del[idx])) {
+				continue;
+			}
+		}
+
+		if (strncmp(ref.refname, prefix, strlen(prefix))) {
+			err = 1;
+			goto done;
+		}
+		err = 0;
+		goto done;
+	}
+
+done:
+	reftable_ref_record_release(&ref);
+	reftable_iterator_destroy(&it);
+	return err;
+}
+
+static int validate_refname(const char *name)
+{
+	while (1) {
+		char *next = strchr(name, '/');
+		if (!*name) {
+			return REFTABLE_REFNAME_ERROR;
+		}
+		if (!next) {
+			return 0;
+		}
+		if (next - name == 0 || (next - name == 1 && *name == '.') ||
+		    (next - name == 2 && name[0] == '.' && name[1] == '.'))
+			return REFTABLE_REFNAME_ERROR;
+		name = next + 1;
+	}
+	return 0;
+}
+
+int validate_ref_record_addition(struct reftable_table tab,
+				 struct reftable_ref_record *recs, size_t sz)
+{
+	struct modification mod = {
+		.tab = tab,
+		.add = reftable_calloc(sizeof(char *) * sz),
+		.del = reftable_calloc(sizeof(char *) * sz),
+	};
+	int i = 0;
+	int err = 0;
+	for (; i < sz; i++) {
+		if (reftable_ref_record_is_deletion(&recs[i])) {
+			mod.del[mod.del_len++] = recs[i].refname;
+		} else {
+			mod.add[mod.add_len++] = recs[i].refname;
+		}
+	}
+
+	err = modification_validate(&mod);
+	modification_release(&mod);
+	return err;
+}
+
+static void strbuf_trim_component(struct strbuf *sl)
+{
+	while (sl->len > 0) {
+		int is_slash = (sl->buf[sl->len - 1] == '/');
+		strbuf_setlen(sl, sl->len - 1);
+		if (is_slash)
+			break;
+	}
+}
+
+int modification_validate(struct modification *mod)
+{
+	struct strbuf slashed = STRBUF_INIT;
+	int err = 0;
+	int i = 0;
+	for (; i < mod->add_len; i++) {
+		err = validate_refname(mod->add[i]);
+		if (err)
+			goto done;
+		strbuf_reset(&slashed);
+		strbuf_addstr(&slashed, mod->add[i]);
+		strbuf_addstr(&slashed, "/");
+
+		err = modification_has_ref_with_prefix(mod, slashed.buf);
+		if (err == 0) {
+			err = REFTABLE_NAME_CONFLICT;
+			goto done;
+		}
+		if (err < 0)
+			goto done;
+
+		strbuf_reset(&slashed);
+		strbuf_addstr(&slashed, mod->add[i]);
+		while (slashed.len) {
+			strbuf_trim_component(&slashed);
+			err = modification_has_ref(mod, slashed.buf);
+			if (err == 0) {
+				err = REFTABLE_NAME_CONFLICT;
+				goto done;
+			}
+			if (err < 0)
+				goto done;
+		}
+	}
+	err = 0;
+done:
+	strbuf_release(&slashed);
+	return err;
+}
diff --git a/reftable/refname.h b/reftable/refname.h
new file mode 100644
index 0000000000..a24b40fcb4
--- /dev/null
+++ b/reftable/refname.h
@@ -0,0 +1,29 @@
+/*
+  Copyright 2020 Google LLC
+
+  Use of this source code is governed by a BSD-style
+  license that can be found in the LICENSE file or at
+  https://developers.google.com/open-source/licenses/bsd
+*/
+#ifndef REFNAME_H
+#define REFNAME_H
+
+#include "reftable-record.h"
+#include "reftable-generic.h"
+
+struct modification {
+	struct reftable_table tab;
+
+	char **add;
+	size_t add_len;
+
+	char **del;
+	size_t del_len;
+};
+
+int validate_ref_record_addition(struct reftable_table tab,
+				 struct reftable_ref_record *recs, size_t sz);
+
+int modification_validate(struct modification *mod);
+
+#endif
diff --git a/reftable/refname_test.c b/reftable/refname_test.c
new file mode 100644
index 0000000000..8645cd93bb
--- /dev/null
+++ b/reftable/refname_test.c
@@ -0,0 +1,102 @@
+/*
+Copyright 2020 Google LLC
+
+Use of this source code is governed by a BSD-style
+license that can be found in the LICENSE file or at
+https://developers.google.com/open-source/licenses/bsd
+*/
+
+#include "basics.h"
+#include "block.h"
+#include "blocksource.h"
+#include "constants.h"
+#include "reader.h"
+#include "record.h"
+#include "refname.h"
+#include "reftable-error.h"
+#include "reftable-writer.h"
+#include "system.h"
+
+#include "test_framework.h"
+#include "reftable-tests.h"
+
+struct testcase {
+	char *add;
+	char *del;
+	int error_code;
+};
+
+static void test_conflict(void)
+{
+	struct reftable_write_options opts = { 0 };
+	struct strbuf buf = STRBUF_INIT;
+	struct reftable_writer *w =
+		reftable_new_writer(&strbuf_add_void, &buf, &opts);
+	struct reftable_ref_record rec = {
+		.refname = "a/b",
+		.value_type = REFTABLE_REF_SYMREF,
+		.value.symref = "destination", /* make sure it's not a symref.
+						*/
+		.update_index = 1,
+	};
+	int err;
+	int i;
+	struct reftable_block_source source = { NULL };
+	struct reftable_reader *rd = NULL;
+	struct reftable_table tab = { NULL };
+	struct testcase cases[] = {
+		{ "a/b/c", NULL, REFTABLE_NAME_CONFLICT },
+		{ "b", NULL, 0 },
+		{ "a", NULL, REFTABLE_NAME_CONFLICT },
+		{ "a", "a/b", 0 },
+
+		{ "p/", NULL, REFTABLE_REFNAME_ERROR },
+		{ "p//q", NULL, REFTABLE_REFNAME_ERROR },
+		{ "p/./q", NULL, REFTABLE_REFNAME_ERROR },
+		{ "p/../q", NULL, REFTABLE_REFNAME_ERROR },
+
+		{ "a/b/c", "a/b", 0 },
+		{ NULL, "a//b", 0 },
+	};
+	reftable_writer_set_limits(w, 1, 1);
+
+	err = reftable_writer_add_ref(w, &rec);
+	EXPECT_ERR(err);
+
+	err = reftable_writer_close(w);
+	EXPECT_ERR(err);
+	reftable_writer_free(w);
+
+	block_source_from_strbuf(&source, &buf);
+	err = reftable_new_reader(&rd, &source, "filename");
+	EXPECT_ERR(err);
+
+	reftable_table_from_reader(&tab, rd);
+
+	for (i = 0; i < ARRAY_SIZE(cases); i++) {
+		struct modification mod = {
+			.tab = tab,
+		};
+
+		if (cases[i].add) {
+			mod.add = &cases[i].add;
+			mod.add_len = 1;
+		}
+		if (cases[i].del) {
+			mod.del = &cases[i].del;
+			mod.del_len = 1;
+		}
+
+		err = modification_validate(&mod);
+		EXPECT(err == cases[i].error_code);
+	}
+
+	reftable_reader_free(rd);
+	strbuf_release(&buf);
+}
+
+int refname_test_main(int argc, const char *argv[])
+{
+	RUN_TEST(test_conflict);
+	return 0;
+}