From 9ce3a97ca97a65e38b6bb0a42932cb232495f354 Mon Sep 17 00:00:00 2001
From: Kharec <sandro@cazzaniga.fr>
Date: Mon, 22 Dec 2025 17:40:21 +0100
Subject: [PATCH] test: add utils unit tests

---
 t/05_utils.t | 114 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 114 insertions(+)
 create mode 100644 t/05_utils.t

diff --git a/t/05_utils.t b/t/05_utils.t
new file mode 100644
index 0000000..39c66bd
--- /dev/null
+++ b/t/05_utils.t
@@ -0,0 +1,114 @@
+use Test::More;
+use Urupam::Utils ();
+
+subtest 'sanitize_input' => sub {
+    is( Urupam::Utils::sanitize_input(undef), '', 'undef becomes empty' );
+    is( Urupam::Utils::sanitize_input("  spaced out\t\n"),
+        'spaced out', 'trims leading and trailing whitespace' );
+    is( Urupam::Utils::sanitize_input('a  b'),
+        'a  b', 'preserves internal whitespace' );
+    is( Urupam::Utils::sanitize_input(0),   '0', 'handles numeric zero' );
+    is( Urupam::Utils::sanitize_input('0'), '0', 'handles string zero' );
+};
+
+subtest 'get_error_status' => sub {
+    is( Urupam::Utils::get_error_status('SSL certificate error'),
+        422, 'SSL error maps to 422' );
+    is( Urupam::Utils::get_error_status('Cannot reach URL: timeout'),
+        422, 'connection error maps to 422' );
+    is( Urupam::Utils::get_error_status('DNS resolution failed'),
+        422, 'DNS error maps to 422' );
+    is( Urupam::Utils::get_error_status('server error: 500'),
+        422, 'server error maps to 422' );
+    is( Urupam::Utils::get_error_status('SeRvEr ErRoR'),
+        422, 'mixed case matches' );
+    is( Urupam::Utils::get_error_status('Database error: connection failed'),
+        400, 'default maps to 400' );
+    is( Urupam::Utils::get_error_status('unrelated error'),
+        400, 'non-matching message maps to 400' );
+};
+
+subtest 'sanitize_error_message' => sub {
+    is(
+        Urupam::Utils::sanitize_error_message(undef),
+        'An error occurred',
+        'undef gets default message'
+    );
+    is(
+        Urupam::Utils::sanitize_error_message("Database error: <bad>\n\t!!"),
+        'Database error: bad',
+        'strips unsafe chars and collapses whitespace'
+    );
+    is(
+        Urupam::Utils::sanitize_error_message('Allowed: ./-_: ok'),
+        'Allowed: ./-_: ok',
+        'preserves allowed punctuation'
+    );
+    is(
+        Urupam::Utils::sanitize_error_message("Error   with   spaces"),
+        'Error with spaces',
+        'collapses multiple spaces'
+    );
+    is( Urupam::Utils::sanitize_error_message("Bad\x01\x02Chars"),
+        'BadChars', 'strips control characters' );
+    is(
+        Urupam::Utils::sanitize_error_message("Cafe\x{00E9} error"),
+        "Cafe\x{00E9} error",
+        'preserves Unicode characters'
+    );
+
+    my $long_error = 'Error: ' . ( 'a' x 210 );
+    my $expected   = substr( $long_error, 0, 200 ) . '...';
+    is( Urupam::Utils::sanitize_error_message($long_error),
+        $expected, 'truncates long messages' );
+};
+
+subtest 'sanitize_url' => sub {
+    is( Urupam::Utils::sanitize_url(undef), undef, 'undef stays undef' );
+    is( Urupam::Utils::sanitize_url('   '), undef, 'blank is undef' );
+    is( Urupam::Utils::sanitize_url('example.com/path'),
+        'http://example.com/path', 'adds scheme when missing' );
+    is( Urupam::Utils::sanitize_url('  example.com/path  '),
+        'http://example.com/path', 'trims before processing' );
+    is( Urupam::Utils::sanitize_url('https://example.com/path'),
+        'https://example.com/path', 'preserves http(s) scheme' );
+    is( Urupam::Utils::sanitize_url('http://example.com'),
+        'http://example.com', 'does not double-add scheme' );
+    is( Urupam::Utils::sanitize_url('HTTP://Example.com/Path'),
+        'HTTP://Example.com/Path', 'accepts mixed-case scheme' );
+    is( Urupam::Utils::sanitize_url('https://example.com/%7Euser'),
+        'https://example.com/~user', 'unescapes percent-encoded path' );
+    is(
+        Urupam::Utils::sanitize_url('https://example.com/%7Euser%2Fdocs'),
+        'https://example.com/~user/docs',
+        'unescapes multiple percent-encoded segments'
+    );
+    is(
+        Urupam::Utils::sanitize_url('https://example.com?q=hello%20world'),
+        'https://example.com?q=hello%20world',
+        'preserves percent-encoded query'
+    );
+    is(
+        Urupam::Utils::sanitize_url('https://example.com#frag%20ment'),
+        'https://example.com#frag%20ment',
+        'preserves percent-encoded fragment'
+    );
+    is( Urupam::Utils::sanitize_url('https://example.com/%257Euser'),
+        'https://example.com/%7Euser', 'unescapes only once' );
+    is( Urupam::Utils::sanitize_url('https://ex%61mple.com/path'),
+        undef, 'rejects percent-encoded hostname' );
+    is( Urupam::Utils::sanitize_url('example.com:8080/path'),
+        undef, 'rejects missing scheme with colon' );
+    is( Urupam::Utils::sanitize_url('user@example.com'),
+        undef, 'rejects missing scheme with at-sign' );
+    is( Urupam::Utils::sanitize_url('http://user@example.com/path'),
+        undef, 'rejects userinfo with scheme' );
+    is( Urupam::Utils::sanitize_url('http://[::1]/path'),
+        'http://[::1]/path', 'accepts IPv6 host' );
+    is( Urupam::Utils::sanitize_url('http://[::1/path'),
+        undef, 'rejects malformed IPv6 host' );
+    is( Urupam::Utils::sanitize_url('http://exa mple.com/path'),
+        undef, 'rejects whitespace in host' );
+};
+
+done_testing();