Added tests for UTF-8 decoding and improved test coverage

src/b6b_rand.c

@@ -26,7 +26,7 @@ static enum b6b_res b6b_rand_proc_choice(struct b6b_interp *interp,
 {
 	struct b6b_obj *l;
 	struct b6b_litem *li;
-	int i, c;
+	unsigned int i, c;
 
 	if (!b6b_proc_get_args(interp, args, "ol", NULL, &l))
 		return B6B_ERR;
@@ -35,14 +35,14 @@ static enum b6b_res b6b_rand_proc_choice(struct b6b_interp *interp,
 	if (!li)
 		return B6B_ERR;
 
-	c = rand_r(&interp->seed);
+	c = (unsigned int)(rand_r(&interp->seed) & UINT_MAX);
 
-	for (i = 0; i < c; ++i) {
+	for (i = 1; i < c; ++i) {
 		li = b6b_list_next(li);
 		if (!li) {
 			/* if the list length is smaller than the random number, divide the
 			 * latter by the former */
-			c %= (i + 1);
+			c %= i;
 
 			li = b6b_list_first(l);
 			for (i = 1; i <= c; ++i)

src/b6b_str.c

@@ -302,8 +302,17 @@ struct b6b_obj *b6b_str_decode(const char *s, size_t len)
 				return NULL;
 			}
 
-			if (!out)
+			if (!out) {
+				/* if no characters were converted and this isn't the end of the
+				 * string, there is a \0 within the string and it cannot be
+				 * decoded */
+				if (len) {
+					b6b_destroy(l);
+					return NULL;
+				}
+
 				break;
+			}
 
 			c = b6b_str_copy(s, out);
 			if (b6b_unlikely(!c)) {

tests/b6b_test_decode.c

@@ -0,0 +1,117 @@
+/*
+ * This file is part of b6b.
+ *
+ * Copyright 2017 Dima Krasner
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+#include <stdlib.h>
+#include <assert.h>
+#include <locale.h>
+
+#include <b6b.h>
+
+int main()
+{
+	struct b6b_interp interp;
+
+	setlocale(LC_ALL, "");
+
+	assert(b6b_interp_new_argv(&interp, 0, NULL, 0));
+	assert(b6b_call_copy(&interp, "{\xd7\xa9\xd7\x9c\xd7\x95\xd7\x9d}", 10) == B6B_ERR);
+	b6b_interp_destroy(&interp);
+
+	assert(b6b_interp_new_argv(&interp, 0, NULL, 0));
+	assert(b6b_call_copy(&interp, "{\xd7\xa9\xd7\x9c\xd7\x95\xd7\x9d encode}", 17) == B6B_ERR);
+	b6b_interp_destroy(&interp);
+
+	/* decoding of a Hebrew word should succeed */
+	assert(b6b_interp_new_argv(&interp, 0, NULL, 0));
+	assert(b6b_call_copy(&interp, "{\xd7\xa9\xd7\x9c\xd7\x95\xd7\x9d decode}", 17) == B6B_OK);
+	assert(b6b_as_list(interp.fg->_));
+	assert(!b6b_list_empty(interp.fg->_));
+	assert(b6b_as_str(b6b_list_first(interp.fg->_)->o));
+	assert(b6b_list_first(interp.fg->_)->o->slen == 2);
+	assert(strcmp(b6b_list_first(interp.fg->_)->o->s, "\xd7\xa9") == 0);
+	assert(b6b_list_next(b6b_list_first(interp.fg->_)));
+	assert(b6b_as_str(b6b_list_next(b6b_list_first(interp.fg->_))->o));
+	assert(b6b_list_next(b6b_list_first(interp.fg->_))->o->slen == 2);
+	assert(strcmp(b6b_list_next(b6b_list_first(interp.fg->_))->o->s, "\xd7\x9c") == 0);
+	assert(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_))));
+	assert(b6b_as_str(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_)))->o));
+	assert(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_)))->o->slen == 2);
+	assert(strcmp(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_)))->o->s, "\xd7\x95") == 0);
+	assert(b6b_list_next(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_)))));
+	assert(b6b_as_str(b6b_list_next(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_))))->o));
+	assert(b6b_list_next(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_))))->o->slen == 2);
+	assert(strcmp(b6b_list_next(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_))))->o->s, "\xd7\x9d") == 0);
+	assert(!b6b_list_next(b6b_list_next(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_))))));
+	b6b_interp_destroy(&interp);
+
+	/* decoding of a string containing a \0 should fail */
+	assert(b6b_interp_new_argv(&interp, 0, NULL, 0));
+	assert(b6b_call_copy(&interp, "{\xd7\xa9\xd7\x9c\x00\xd7\x9d decode}", 16) == B6B_ERR);
+	b6b_interp_destroy(&interp);
+
+	assert(b6b_interp_new_argv(&interp, 0, NULL, 0));
+	assert(b6b_call_copy(&interp, "{\xd7\xa9\xd7\x9c\xd7\x95\x00 decode}", 16) == B6B_ERR);
+	b6b_interp_destroy(&interp);
+
+	assert(b6b_interp_new_argv(&interp, 0, NULL, 0));
+	assert(b6b_call_copy(&interp, "{\xd7\xa9\xd7\x9c\xd7\x95\x00\x9d decode}", 17) == B6B_ERR);
+	b6b_interp_destroy(&interp);
+
+	assert(b6b_interp_new_argv(&interp, 0, NULL, 0));
+	assert(b6b_call_copy(&interp, "{\x00\xa9\xd7\x9c\xd7\x95\xd7\x9d decode}", 17) == B6B_ERR);
+	b6b_interp_destroy(&interp);
+
+	assert(b6b_interp_new_argv(&interp, 0, NULL, B6B_OPT_TRACE));
+	assert(b6b_call_copy(&interp, "{\x00a decode}", 12) == B6B_ERR);
+	b6b_interp_destroy(&interp);
+
+	/* decoding of a single-letter Hebrew word should succeed */
+	assert(b6b_interp_new_argv(&interp, 0, NULL, 0));
+	assert(b6b_call_copy(&interp, "{\xd7\x90 decode}", 11) == B6B_OK);
+	assert(b6b_as_list(interp.fg->_));
+	assert(!b6b_list_empty(interp.fg->_));
+	assert(b6b_as_str(b6b_list_first(interp.fg->_)->o));
+	assert(strcmp(b6b_list_first(interp.fg->_)->o->s, "\xd7\x90") == 0);
+	assert(!b6b_list_next(b6b_list_first(interp.fg->_)));
+	b6b_interp_destroy(&interp);
+
+	/* decoding of a Hebrew word containing an English letter should succeed */
+	assert(b6b_interp_new_argv(&interp, 0, NULL, 0));
+	assert(b6b_call_copy(&interp, "{\xd7\xa9\xd7\x9c\x61\xd7\x9d decode}", 16) == B6B_OK);
+	assert(b6b_as_list(interp.fg->_));
+	assert(!b6b_list_empty(interp.fg->_));
+	assert(b6b_as_str(b6b_list_first(interp.fg->_)->o));
+	assert(b6b_list_first(interp.fg->_)->o->slen == 2);
+	assert(strcmp(b6b_list_first(interp.fg->_)->o->s, "\xd7\xa9") == 0);
+	assert(b6b_list_next(b6b_list_first(interp.fg->_)));
+	assert(b6b_as_str(b6b_list_next(b6b_list_first(interp.fg->_))->o));
+	assert(b6b_list_next(b6b_list_first(interp.fg->_))->o->slen == 2);
+	assert(strcmp(b6b_list_next(b6b_list_first(interp.fg->_))->o->s, "\xd7\x9c") == 0);
+	assert(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_))));
+	assert(b6b_as_str(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_)))->o));
+	assert(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_)))->o->slen == 1);
+	assert(strcmp(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_)))->o->s, "a") == 0);
+	assert(b6b_list_next(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_)))));
+	assert(b6b_as_str(b6b_list_next(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_))))->o));
+	assert(b6b_list_next(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_))))->o->slen == 2);
+	assert(strcmp(b6b_list_next(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_))))->o->s, "\xd7\x9d") == 0);
+	assert(!b6b_list_next(b6b_list_next(b6b_list_next(b6b_list_next(b6b_list_first(interp.fg->_))))));
+	b6b_interp_destroy(&interp);
+
+	return EXIT_SUCCESS;
+}

tests/b6b_test_try.c

@@ -29,6 +29,16 @@ int main()
 	s = b6b_str_copy("x", 1);
 	assert(s);
 
+	assert(b6b_interp_new_argv(&interp, 0, NULL, B6B_OPT_TRACE));
+	assert(b6b_call_copy(&interp, "{$try}", 6) == B6B_ERR);
+	b6b_interp_destroy(&interp);
+
+	assert(b6b_interp_new_argv(&interp, 0, NULL, B6B_OPT_TRACE));
+	assert(b6b_call_copy(&interp, "{$try {}}", 9) == B6B_OK);
+	assert(b6b_as_str(interp.fg->_));
+	assert(interp.fg->_->slen == 0);
+	b6b_interp_destroy(&interp);
+
 	assert(b6b_interp_new_argv(&interp, 0, NULL, B6B_OPT_TRACE));
 	assert(b6b_call_copy(&interp, "{$try {{$return 5}}}", 20) == B6B_RET);
 	assert(b6b_as_int(interp.fg->_));

tests/meson.build

@@ -31,7 +31,8 @@ tests = [
 	['bswap', 'quick', 5],
 	['rand', 'quick', 5],
 	['socket', 'quick', 5],
-	['timer', 'quick', 10]
+	['timer', 'quick', 10],
+	['decode', 'quick', 5]
 ]
 
 if get_option('with_threads')