summaryrefslogtreecommitdiffstats
path: root/Tests/CMakeLib/testUTF8.cxx
diff options
context:
space:
mode:
authorBrad King <brad.king@kitware.com>2019-03-19 12:58:14 (GMT)
committerKitware Robot <kwrobot@kitware.com>2019-03-19 12:58:39 (GMT)
commit3c4f92cf5bd38355b4843dd6e882fea012306a10 (patch)
treef6c6d1ca639fa0313edd81ffe8914352f7ab6503 /Tests/CMakeLib/testUTF8.cxx
parent6bbc82b4b30ff17c5b3c899c482b1a724e15d5fb (diff)
parent53184a727d0f3b233988212628fec6ef7803da69 (diff)
downloadCMake-3c4f92cf5bd38355b4843dd6e882fea012306a10.zip
CMake-3c4f92cf5bd38355b4843dd6e882fea012306a10.tar.gz
CMake-3c4f92cf5bd38355b4843dd6e882fea012306a10.tar.bz2
Merge topic 'is-valid-utf8'
53184a727d cm_utf8: add an is_valid function Acked-by: Kitware Robot <kwrobot@kitware.com> Merge-request: !3104
Diffstat (limited to 'Tests/CMakeLib/testUTF8.cxx')
-rw-r--r--Tests/CMakeLib/testUTF8.cxx78
1 files changed, 78 insertions, 0 deletions
diff --git a/Tests/CMakeLib/testUTF8.cxx b/Tests/CMakeLib/testUTF8.cxx
index 7f52c82..a0bb5cd 100644
--- a/Tests/CMakeLib/testUTF8.cxx
+++ b/Tests/CMakeLib/testUTF8.cxx
@@ -13,6 +13,21 @@ static void test_utf8_char_print(test_utf8_char const c)
static_cast<int>(d[3]));
}
+static void byte_array_print(char const* s)
+{
+ unsigned char const* d = reinterpret_cast<unsigned char const*>(s);
+ bool started = false;
+ printf("[");
+ for (; *d; ++d) {
+ if (started) {
+ printf(",");
+ }
+ started = true;
+ printf("0x%02X", static_cast<int>(*d));
+ }
+ printf("]");
+}
+
struct test_utf8_entry
{
int n;
@@ -46,6 +61,13 @@ static test_utf8_char const bad_chars[] = {
{ 0, 0, 0, 0, 0 }
};
+static char const* good_strings[] = { "", "ASCII", "\xC2\xA9 Kitware", 0 };
+
+static char const* bad_strings[] = {
+ "\xC0\x80", /* Modified UTF-8 for embedded 0-byte. */
+ 0
+};
+
static void report_good(bool passed, test_utf8_char const c)
{
printf("%s: decoding good ", passed ? "pass" : "FAIL");
@@ -99,6 +121,46 @@ static bool decode_bad(test_utf8_char const s)
return true;
}
+static void report_valid(bool passed, char const* s)
+{
+ printf("%s: validity good ", passed ? "pass" : "FAIL");
+ byte_array_print(s);
+ printf(" (%s) ", s);
+}
+
+static void report_invalid(bool passed, char const* s)
+{
+ printf("%s: validity bad ", passed ? "pass" : "FAIL");
+ byte_array_print(s);
+ printf(" ");
+}
+
+static bool is_valid(const char* s)
+{
+ bool valid = cm_utf8_is_valid(s) != 0;
+ if (!valid) {
+ report_valid(false, s);
+ printf("expected valid, reported as invalid\n");
+ return false;
+ }
+ report_valid(true, s);
+ printf("valid as expected\n");
+ return true;
+}
+
+static bool is_invalid(const char* s)
+{
+ bool valid = cm_utf8_is_valid(s) != 0;
+ if (valid) {
+ report_invalid(false, s);
+ printf("expected invalid, reported as valid\n");
+ return false;
+ }
+ report_invalid(true, s);
+ printf("invalid as expected\n");
+ return true;
+}
+
int testUTF8(int /*unused*/, char* /*unused*/ [])
{
int result = 0;
@@ -106,11 +168,27 @@ int testUTF8(int /*unused*/, char* /*unused*/ [])
if (!decode_good(*e)) {
result = 1;
}
+ if (!is_valid(e->str)) {
+ result = 1;
+ }
}
for (test_utf8_char const* c = bad_chars; (*c)[0]; ++c) {
if (!decode_bad(*c)) {
result = 1;
}
+ if (!is_invalid(*c)) {
+ result = 1;
+ }
+ }
+ for (char const** s = good_strings; *s; ++s) {
+ if (!is_valid(*s)) {
+ result = 1;
+ }
+ }
+ for (char const** s = bad_strings; *s; ++s) {
+ if (!is_invalid(*s)) {
+ result = 1;
+ }
}
return result;
}