fix: phone leak, field-by-value detection, strict Flamingo email fallback
Three pilot-surfaced issues in one pass: 1. PhoneParser regex used '\s' in the candidate character class, so a digit on a following flattened line bled into the phone. '+7977 6277470\n1' (phone + trailing checkbox value) parsed as 12 digits, producing '+797762774701'. Replaced '\s' with a literal space so newlines/tabs stop the candidate. 2. Custom-themed forms don't use 'your-name' / 'your-email' keys (washanyanya.ru has text-211 / text-212 / name_user). Added FieldDetector::find_name + find_email as fallbacks. Classifier and MessageFormatter now call them if no standard key matches, so 'Александр' in text-211 is recognised as a cyrillic name and scored / displayed accordingly. 3. FlamingoHelper copied '_from_email' into 'your-email' without validating it. Flamingo derives that meta from whatever field it considers "first"; on phone-first forms it ends up holding the phone number. Now we only copy _from_email if it contains '@', and dropped the _from_name shortcut entirely — FieldDetector handles the name via the actual field values. Tests: +1 FieldDetectorTest (13 cases); +2 PhoneParserTest cases for newline/tab bleeds; +1 ClassifierTest case; +1 MessageFormatterTest case for custom field keys. Full suite 53/53 green. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Vladimir Bryzgalov
@@ -154,4 +154,21 @@ final class ClassifierTest extends TestCase
|
||||
}
|
||||
self::assertTrue($matched);
|
||||
}
|
||||
|
||||
public function test_detects_cyrillic_name_under_custom_field_key(): void
|
||||
{
|
||||
// Real form on washanyanya.ru uses keys like 'text-211' / 'text-212'
|
||||
// instead of 'your-name' / 'your-tel'. Classifier must still award
|
||||
// +1 for a cyrillic name via the value-based heuristic.
|
||||
$fields = [
|
||||
'text-211' => 'Александр',
|
||||
'text-212' => '+79776277470',
|
||||
];
|
||||
$r = Classifier::classify($fields, ['reason' => 'Akismet']);
|
||||
$has_name = false;
|
||||
foreach ($r['reasons'] as $reason) {
|
||||
if (strpos($reason['text'], 'кириллическое имя') !== false) $has_name = true;
|
||||
}
|
||||
self::assertTrue($has_name, 'expected +1 кириллическое имя via value heuristic');
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,116 @@
|
||||
<?php
|
||||
declare(strict_types=1);
|
||||
|
||||
namespace Cf7stg\Tests;
|
||||
|
||||
use Cf7stg\FieldDetector;
|
||||
use PHPUnit\Framework\TestCase;
|
||||
|
||||
final class FieldDetectorTest extends TestCase
|
||||
{
|
||||
public function test_finds_cyrillic_name_in_custom_key(): void
|
||||
{
|
||||
$r = FieldDetector::find_name([
|
||||
'text-211' => 'Александр',
|
||||
'text-212' => '+79776277470',
|
||||
]);
|
||||
self::assertSame('Александр', $r);
|
||||
}
|
||||
|
||||
public function test_finds_multiword_cyrillic_name(): void
|
||||
{
|
||||
$r = FieldDetector::find_name(['x' => 'Анна Петровна']);
|
||||
self::assertSame('Анна Петровна', $r);
|
||||
}
|
||||
|
||||
public function test_finds_latin_name(): void
|
||||
{
|
||||
$r = FieldDetector::find_name(['x' => 'John Smith']);
|
||||
self::assertSame('John Smith', $r);
|
||||
}
|
||||
|
||||
public function test_skips_values_with_digits(): void
|
||||
{
|
||||
$r = FieldDetector::find_name([
|
||||
'a' => '+79776277470',
|
||||
'b' => 'Ольга',
|
||||
]);
|
||||
self::assertSame('Ольга', $r);
|
||||
}
|
||||
|
||||
public function test_skips_urls(): void
|
||||
{
|
||||
$r = FieldDetector::find_name([
|
||||
'a' => 'https://evil.com',
|
||||
'b' => 'Павел',
|
||||
]);
|
||||
self::assertSame('Павел', $r);
|
||||
}
|
||||
|
||||
public function test_skips_emails(): void
|
||||
{
|
||||
$r = FieldDetector::find_name([
|
||||
'a' => 'anna@mail.ru',
|
||||
'b' => 'Анна',
|
||||
]);
|
||||
self::assertSame('Анна', $r);
|
||||
}
|
||||
|
||||
public function test_skips_too_short(): void
|
||||
{
|
||||
$r = FieldDetector::find_name([
|
||||
'a' => 'X',
|
||||
'b' => 'Дарья',
|
||||
]);
|
||||
self::assertSame('Дарья', $r);
|
||||
}
|
||||
|
||||
public function test_skips_too_long(): void
|
||||
{
|
||||
$r = FieldDetector::find_name([
|
||||
'a' => str_repeat('а', 200),
|
||||
'b' => 'Лена',
|
||||
]);
|
||||
self::assertSame('Лена', $r);
|
||||
}
|
||||
|
||||
public function test_no_name_returns_empty(): void
|
||||
{
|
||||
$r = FieldDetector::find_name([
|
||||
'a' => '+79031234567',
|
||||
'b' => '1',
|
||||
'c' => 'http://x.y',
|
||||
]);
|
||||
self::assertSame('', $r);
|
||||
}
|
||||
|
||||
public function test_finds_email(): void
|
||||
{
|
||||
$r = FieldDetector::find_email(['x-1' => 'user@example.com']);
|
||||
self::assertSame('user@example.com', $r);
|
||||
}
|
||||
|
||||
public function test_no_email_returns_empty_when_only_phone(): void
|
||||
{
|
||||
$r = FieldDetector::find_email([
|
||||
'x' => 'Иван',
|
||||
'y' => '+79031234567',
|
||||
]);
|
||||
self::assertSame('', $r);
|
||||
}
|
||||
|
||||
public function test_email_is_trimmed(): void
|
||||
{
|
||||
$r = FieldDetector::find_email(['x' => ' anna@mail.ru ']);
|
||||
self::assertSame('anna@mail.ru', $r);
|
||||
}
|
||||
|
||||
public function test_first_email_wins_when_multiple(): void
|
||||
{
|
||||
$r = FieldDetector::find_email([
|
||||
'a' => 'first@a.ru',
|
||||
'b' => 'second@b.ru',
|
||||
]);
|
||||
self::assertSame('first@a.ru', $r);
|
||||
}
|
||||
}
|
||||
@@ -151,4 +151,31 @@ final class MessageFormatterTest extends TestCase
|
||||
|
||||
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']);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -72,4 +72,22 @@ final class PhoneParserTest extends TestCase
|
||||
self::assertSame('+74951234567', $r['e164']);
|
||||
self::assertTrue($r['is_russian']);
|
||||
}
|
||||
|
||||
public function test_digits_on_next_line_do_not_leak_into_number(): void
|
||||
{
|
||||
// Pilot bug: CF7 spam flatten joined values with "\n"; '\s' in the
|
||||
// candidate regex matched newlines, so '+79776277470\n1' (phone then
|
||||
// a checkbox value on the next line) turned into a 12-digit number
|
||||
// ending in 1.
|
||||
$r = PhoneParser::parse("+79776277470\n1");
|
||||
self::assertSame('+79776277470', $r['e164']);
|
||||
self::assertTrue($r['is_russian']);
|
||||
}
|
||||
|
||||
public function test_tab_between_fields_does_not_leak(): void
|
||||
{
|
||||
// Same family as above but with tabs.
|
||||
$r = PhoneParser::parse("89031234567\t1");
|
||||
self::assertSame('+79031234567', $r['e164']);
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user