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'
This commit is contained in:
Vladimir Bryzgalov
2026-04-21 16:14:49 +05:00
parent 18a07c9b1b
commit a70785beca
5 changed files with 214 additions and 6 deletions
+56
View File
@@ -20,6 +20,12 @@ final class Classifier
public const DEFAULT_THRESHOLDS = [
'client' => 3,
'spam' => -2,
'drop' => -5,
];
public const DEFAULT_HARD_DROP_RULES = [
'short_latin_name' => true,
'placeholder_fields' => true,
];
public const DEFAULT_KEYWORDS = [
@@ -153,9 +159,28 @@ final class Classifier
$label = 'spam';
}
// Drop has highest priority (overrides client/unclear/spam/honeypot)
$is_drop_by_rule = self::evaluate_hard_drop($fields);
$is_drop_by_score = isset($thresholds['drop']) && $score <= (int)$thresholds['drop'];
if ($is_drop_by_rule || $is_drop_by_score) {
$label = 'drop';
$reasons[] = ['sign' => '×', 'weight' => 0, 'text' => self::drop_reason_label($fields, $thresholds, $is_drop_by_rule)];
}
return ['score' => $score, 'label' => $label, 'reasons' => $reasons];
}
private static function drop_reason_label(array $fields, array $thresholds, bool $by_rule): string
{
if ($by_rule) {
$hits = [];
if (self::has_short_latin_name($fields)) $hits[] = 'короткое латинское имя';
if (self::count_placeholder_fields($fields) >= 3) $hits[] = '≥3 поля-плейсхолдера';
return 'hard-rule: ' . implode(' + ', $hits);
}
return 'score ≤ ' . (int)$thresholds['drop'];
}
private static function concat_fields(array $fields): string
{
$out = [];
@@ -307,4 +332,35 @@ final class Classifier
}
return $count;
}
/**
* Hard-rule decision: returns true if the submission has zero positive signals
* (no cyrillic name, no meaningful text, no valid email anywhere) AND at least
* one trigger fires (short latin name OR ≥3 placeholder fields).
*
* Triggers can be disabled individually via filter `cf7stg_hard_drop_rules`.
*
* @param array<string,string|string[]> $fields CF7 posted_data
* @return bool True if the submission should be silently dropped by hard-rule.
*/
public static function evaluate_hard_drop(array $fields): bool
{
$rules = apply_filters('cf7stg_hard_drop_rules', self::DEFAULT_HARD_DROP_RULES);
// Любой позитивный сигнал — НЕ drop
$name = self::pick_field($fields, ['your-name', 'name', 'имя', 'fio']);
if ($name === '') $name = FieldDetector::find_name($fields);
if ($name !== '' && self::is_cyrillic_name($name)) return false;
$message = self::pick_field($fields, ['your-message', 'message', 'comment', 'сообщение', 'вопрос']);
if ($message !== '' && self::is_meaningful_text($message)) return false;
if (self::has_valid_email_anywhere($fields)) return false;
// Триггеры
if (!empty($rules['short_latin_name']) && self::has_short_latin_name($fields)) return true;
if (!empty($rules['placeholder_fields']) && self::count_placeholder_fields($fields) >= 3) return true;
return false;
}
}