Skip to content

LL: tests/Utf8ValidatorTest.php split the "mega test" into tests for … #99

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Seldaek merged 2 commits into from
Jun 17, 2026
Merged

LL: tests/Utf8ValidatorTest.php split the "mega test" into tests for … #99

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3d09d4d
LL: tests/Utf8ValidatorTest.php split the "mega test" into tests for …
LLyaudet Jun 16, 2026
68dd8ec
Remove outdated method
Seldaek Jun 17, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 30 additions & 8 deletions tests/Utf8ValidatorTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ public function testValidUtf8()
}
}

public function testAllErrorTypes()
public function testNotAContinuationOctet()
{
try {
Utf8Validator::validate('"abcd'.chr(233).'"');
Expand All @@ -41,6 +41,19 @@ public function testAllErrorTypes()
$this->assertContains('Non-UTF8 character found', $e->getMessage());
$this->assertContains(' which is not a continuation octet.', $e->getMessage());
}
for ($i = 246; $i < 255; ++$i) { // 245 and 255 already forbidden
try {
Utf8Validator::validate('"abcd'.chr(195).chr($i).'"');
$this->fail('"abcd\d195\d'.$i.'" should not pass validation.');
} catch (InvalidEncodingException $e) {
$this->assertContains('Non-UTF8 character found', $e->getMessage());
$this->assertContains(' which is not a continuation octet.', $e->getMessage());
}
}
}

public function testPrematureEndOfString()
{
try {
Utf8Validator::validate('"abcd'.chr(233));
$this->fail('ISO 8859-15 "abcdé should not pass validation.');
Expand All @@ -51,6 +64,10 @@ public function testAllErrorTypes()
$e->getMessage()
);
}
}

public function testForbiddenOctets()
{
$forbiddenOctets = array(
192,
193,
Expand Down Expand Up @@ -79,6 +96,10 @@ public function testAllErrorTypes()
);
}
}
}

public function testUnwantedContinuationOctet()
{
try {
Utf8Validator::validate('"abcd'.chr(129).'"');
$this->fail('"abcd\d129" should not pass validation.');
Expand All @@ -89,6 +110,10 @@ public function testAllErrorTypes()
$e->getMessage()
);
}
}

public function testForbiddenSurrogatePairs()
{
for ($i = 160; $i <= 191; ++$i) {
try {
Utf8Validator::validate('"abcd'.chr(237).chr($i).chr(129).'"');
Expand All @@ -111,6 +136,10 @@ public function testAllErrorTypes()
);
}
}
}

public function testOtherInvalidOctetSequences()
{
for ($i = 246; $i < 255; ++$i) { // 245 and 255 already forbidden
try {
Utf8Validator::validate('"abcd'.chr($i).chr(129).chr(129).chr(129).'"');
Expand All @@ -126,13 +155,6 @@ public function testAllErrorTypes()
$this->assertContains('Non-UTF8 character found', $e->getMessage());
$this->assertContains(' which is invalid.', $e->getMessage());
}
try {
Utf8Validator::validate('"abcd'.chr(195).chr($i).'"');
$this->fail('"abcd\d195\d'.$i.'" should not pass validation.');
} catch (InvalidEncodingException $e) {
$this->assertContains('Non-UTF8 character found', $e->getMessage());
$this->assertContains(' which is not a continuation octet.', $e->getMessage());
}
}
}

Expand Down