Files
cf7-spam-to-telegram/tests/MessageFormatterTest.php
Vladimir Bryzgalov a70785beca feat(classifier): label 'drop' via hard-rule + score threshold (-5 default)
- Add DEFAULT_THRESHOLDS['drop'] = -5 and DEFAULT_HARD_DROP_RULES const
- Add evaluate_hard_drop(): fires when no positive signals + short latin name OR ≥3 placeholder fields
- Wire into classify(): drop overrides all other labels; synthetic reason explains trigger
- Add drop_reason_label() and 'drop' => ' авто-дроп' to MessageFormatter::LABEL_MAP
- Update ClassifierTest/MessageFormatterTest to extend Cf7stgTestCase (filter isolation)
- Adjust pre-existing assertions that now correctly yield 'drop' instead of 'spam'
2026-04-21 16:14:49 +05:00

205 lines
9.1 KiB
PHP
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
<?php
declare(strict_types=1);
namespace Cf7stg\Tests;
use Cf7stg\MessageFormatter;
use Cf7stg\Classifier;
final class MessageFormatterTest extends Cf7stgTestCase
{
public function test_full_client_payload(): void
{
$fields = [
'your-name' => 'Анна Петровна',
'your-tel' => '+79031234567',
'your-email' => 'anna@mail.ru',
'your-message' => 'Нужна сиделка для бабушки',
];
$classification = Classifier::classify($fields, ['reason' => 'Akismet']);
$result = MessageFormatter::build([
'fields' => $fields,
'classification' => $classification,
'site_title' => 'вашаняня.рф',
'form_title' => 'Обратная связь',
'submitted_at' => '17.04.2026 19:45',
'reason' => 'Akismet',
'ip' => '185.15.56.12',
'user_agent' => 'Mozilla/5.0',
'is_retro' => false,
]);
self::assertIsArray($result);
self::assertArrayHasKey('text', $result);
self::assertArrayHasKey('reply_markup', $result);
self::assertStringContainsString('🟢 похоже клиент', $result['text']);
self::assertStringContainsString('вашаняня.рф', $result['text']);
self::assertStringContainsString('Анна Петровна', $result['text']);
self::assertStringContainsString('+7 (903) 123-45-67', $result['text']);
self::assertStringContainsString('anna@mail.ru', $result['text']);
self::assertStringContainsString('Akismet', $result['text']);
}
public function test_reply_markup_is_null_because_tg_rejects_tel_urls(): void
{
// Telegram Bot API rejects tel: URLs in inline_keyboard with
// HTTP 400 "Wrong port number specified in the URL". We no longer
// emit any inline button; the phone number is rendered in the
// message body instead and mobile TG clients auto-linkify it.
$fields = ['your-tel' => '+79031234567', 'your-name' => 'Анна'];
$classification = Classifier::classify($fields, ['reason' => 'Akismet']);
$r = MessageFormatter::build([
'fields' => $fields, 'classification' => $classification,
'site_title' => 's.ru', 'form_title' => 'f',
'submitted_at' => '17.04.2026', 'reason' => 'Akismet',
'ip' => '', 'user_agent' => '', 'is_retro' => false,
]);
self::assertNull($r['reply_markup']);
// Phone must still be present in the text, formatted as Russian pretty.
self::assertStringContainsString('+7 (903) 123-45-67', $r['text']);
}
public function test_no_tel_button_when_no_phone(): void
{
$fields = ['your-email' => 'a@b.com'];
$classification = Classifier::classify($fields, ['reason' => 'Akismet']);
$r = MessageFormatter::build([
'fields' => $fields, 'classification' => $classification,
'site_title' => 's.ru', 'form_title' => 'f',
'submitted_at' => '17.04.2026', 'reason' => 'Akismet',
'ip' => '', 'user_agent' => '', 'is_retro' => false,
]);
self::assertNull($r['reply_markup']);
}
public function test_html_injection_in_name_is_escaped(): void
{
$fields = ['your-name' => '<script>alert(1)</script>', 'your-tel' => '+79031234567'];
$classification = Classifier::classify($fields, ['reason' => 'Akismet']);
$r = MessageFormatter::build([
'fields' => $fields, 'classification' => $classification,
'site_title' => 's.ru', 'form_title' => 'f',
'submitted_at' => '17.04.2026', 'reason' => 'Akismet',
'ip' => '', 'user_agent' => '', 'is_retro' => false,
]);
self::assertStringNotContainsString('<script>', $r['text']);
self::assertStringContainsString('&lt;script&gt;', $r['text']);
}
public function test_long_message_is_truncated(): void
{
$long = str_repeat('А', 5000);
$fields = ['your-message' => $long, 'your-tel' => '+79031234567'];
$classification = Classifier::classify($fields, ['reason' => 'Akismet']);
$r = MessageFormatter::build([
'fields' => $fields, 'classification' => $classification,
'site_title' => 's.ru', 'form_title' => 'f',
'submitted_at' => '17.04.2026', 'reason' => 'Akismet',
'ip' => '', 'user_agent' => '', 'is_retro' => false,
]);
self::assertLessThanOrEqual(4096, mb_strlen($r['text']));
self::assertStringContainsString('…[обрезано]', $r['text']);
}
public function test_retro_prefix_added(): void
{
$fields = ['your-tel' => '+79031234567'];
$classification = Classifier::classify($fields, ['reason' => 'Akismet']);
$r = MessageFormatter::build([
'fields' => $fields, 'classification' => $classification,
'site_title' => 's.ru', 'form_title' => 'f',
'submitted_at' => '17.04.2026', 'reason' => 'Akismet',
'ip' => '', 'user_agent' => '', 'is_retro' => true,
]);
self::assertStringContainsString('📂 Ретроспектива', $r['text']);
}
public function test_spam_label_emoji(): void
{
// score = SEO(-2) + URL(-3) + latin_only(-1) = -6 ≤ drop threshold(-5) → label=drop
// Fields with no valid email and name 'Melissa' (7 chars, not short latin) → score-based drop.
$fields = [
'your-name' => 'Melissa',
'your-message' => 'SEO promotion, visit http://spam.net',
];
$classification = Classifier::classify($fields, ['reason' => 'Akismet']);
$r = MessageFormatter::build([
'fields' => $fields, 'classification' => $classification,
'site_title' => 's.ru', 'form_title' => 'f',
'submitted_at' => '17.04.2026', 'reason' => 'Akismet',
'ip' => '', 'user_agent' => '', 'is_retro' => false,
]);
self::assertStringContainsString('⛔ авто-дроп', $r['text']);
}
public function test_spam_label_emoji_pure_spam(): void
{
// Score -3 (URL) + -2 (SEO keyword) = -5, but no drop because cyrillic name protects
// from hard-rule, and score -5 is NOT ≤ drop threshold -5 (it equals it, so it IS drop).
// Use URL(-3) only → score=-3, between spam(-2) and drop(-5) → spam label.
$fields = [
'your-name' => 'Nikolay',
'your-email' => 'nick@example.com',
'your-message' => 'visit http://promo.net for deals',
];
$classification = Classifier::classify($fields, ['reason' => 'Akismet']);
// valid email prevents hard-rule; score = URL(-3) + latin_only(-1) = -4 → spam
$r = MessageFormatter::build([
'fields' => $fields, 'classification' => $classification,
'site_title' => 's.ru', 'form_title' => 'f',
'submitted_at' => '17.04.2026', 'reason' => 'Akismet',
'ip' => '', 'user_agent' => '', 'is_retro' => false,
]);
self::assertStringContainsString('🔴 похоже спам', $r['text']);
}
public function test_unclear_label_emoji(): void
{
$fields = ['your-name' => 'Олег', 'your-message' => 'Здравствуйте'];
$classification = Classifier::classify($fields, ['reason' => 'Akismet']);
$r = MessageFormatter::build([
'fields' => $fields, 'classification' => $classification,
'site_title' => 's.ru', 'form_title' => 'f',
'submitted_at' => '17.04.2026', 'reason' => 'Akismet',
'ip' => '', 'user_agent' => '', 'is_retro' => false,
]);
self::assertStringContainsString('🟡 неясно', $r['text']);
}
public function test_custom_form_field_keys_are_detected(): void
{
// washanyanya.ru-style form — fields are named text-NNN, name_user,
// etc. We must still pull out name + phone via value heuristics.
$fields = [
'text-211' => 'Александр',
'text-212' => '+79776277470',
'checkbox-382' => '1',
];
$classification = Classifier::classify($fields, ['reason' => 'Akismet']);
$r = MessageFormatter::build([
'fields' => $fields, 'classification' => $classification,
'site_title' => 's.ru', 'form_title' => 'f',
'submitted_at' => '18.04.2026', 'reason' => 'Akismet',
'ip' => '', 'user_agent' => '', 'is_retro' => false,
]);
// Name resolves to 'Александр' via FieldDetector
self::assertStringContainsString('Александр', $r['text']);
// Phone correctly parsed (11 digits, no trailing checkbox '1')
self::assertStringContainsString('+7 (977) 627-74-70', $r['text']);
// Email stays empty (no @-like value)
self::assertStringContainsString("📧 (не указан)", $r['text']);
// The checkbox value should still appear in 'Прочие поля'
self::assertStringContainsString('checkbox-382: 1', $r['text']);
}
}