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:
@@ -59,7 +59,9 @@ final class Classifier
|
||||
|
||||
$text_all = self::concat_fields($fields);
|
||||
$name = self::pick_field($fields, ['your-name', 'name', 'имя', 'fio']);
|
||||
if ($name === '') $name = FieldDetector::find_name($fields);
|
||||
$email = self::pick_field($fields, ['your-email', 'email', 'e-mail', 'mail']);
|
||||
if ($email === '') $email = FieldDetector::find_email($fields);
|
||||
$message = self::pick_field($fields, ['your-message', 'message', 'comment', 'сообщение', 'вопрос']);
|
||||
|
||||
$score = 0;
|
||||
|
||||
@@ -0,0 +1,56 @@
|
||||
<?php
|
||||
declare(strict_types=1);
|
||||
|
||||
namespace Cf7stg;
|
||||
|
||||
/**
|
||||
* Heuristic detection of name/email/etc. when form field keys are not
|
||||
* the standard CF7 ones (your-name, your-email, ...). Used as a fallback
|
||||
* for custom-themed forms where fields are called text-211, name_user,
|
||||
* и т.п.
|
||||
*/
|
||||
final class FieldDetector
|
||||
{
|
||||
/**
|
||||
* Scan values for something that plausibly looks like a human name:
|
||||
* letters (any script), optional spaces/hyphens/apostrophes/dots,
|
||||
* no digits, no URLs, no emails, length 2..80.
|
||||
*/
|
||||
public static function find_name(array $fields): string
|
||||
{
|
||||
foreach ($fields as $v) {
|
||||
if (is_array($v)) {
|
||||
$v = implode(' ', array_map('strval', $v));
|
||||
}
|
||||
$v = trim((string)$v);
|
||||
if ($v === '') continue;
|
||||
$len = mb_strlen($v);
|
||||
if ($len < 2 || $len > 80) continue;
|
||||
if (preg_match('/\d/u', $v)) continue;
|
||||
if (preg_match('#https?://|www\.|@#iu', $v)) continue;
|
||||
// Must start with a letter and contain only letter-like characters
|
||||
if (preg_match('/^\p{L}[\p{L}\s\.\-\']{1,79}$/u', $v)) {
|
||||
return $v;
|
||||
}
|
||||
}
|
||||
return '';
|
||||
}
|
||||
|
||||
/**
|
||||
* First value that looks like an email address.
|
||||
*/
|
||||
public static function find_email(array $fields): string
|
||||
{
|
||||
foreach ($fields as $v) {
|
||||
if (is_array($v)) {
|
||||
$v = implode(' ', array_map('strval', $v));
|
||||
}
|
||||
$v = trim((string)$v);
|
||||
if ($v === '') continue;
|
||||
if (preg_match('/^\S+@\S+\.\S+$/u', $v)) {
|
||||
return $v;
|
||||
}
|
||||
}
|
||||
return '';
|
||||
}
|
||||
}
|
||||
@@ -56,12 +56,17 @@ final class FlamingoHelper
|
||||
$out[$name] = $val;
|
||||
}
|
||||
}
|
||||
// Convenience: expose Akismet's "from" name / email so the formatter's
|
||||
// standard slots aren't empty for most submissions.
|
||||
$from_name = (string)get_post_meta($post->ID, '_from_name', true);
|
||||
// Flamingo's "_from_name" and "_from_email" are derived heuristically
|
||||
// from whatever field the plugin considers the "first" — on custom
|
||||
// forms without dedicated email / name fields this produces garbage
|
||||
// (e.g. phone number under _from_email). Only trust _from_email if
|
||||
// it actually looks like an email; _from_name is not trustworthy at
|
||||
// all, so leave it to FieldDetector (run by Classifier / Message-
|
||||
// Formatter) to identify a name from any field value.
|
||||
$from_email = (string)get_post_meta($post->ID, '_from_email', true);
|
||||
if ($from_name !== '' && !isset($out['your-name'])) $out['your-name'] = $from_name;
|
||||
if ($from_email !== '' && !isset($out['your-email'])) $out['your-email'] = $from_email;
|
||||
if ($from_email !== '' && strpos($from_email, '@') !== false && !isset($out['your-email'])) {
|
||||
$out['your-email'] = $from_email;
|
||||
}
|
||||
return $out;
|
||||
}
|
||||
|
||||
|
||||
@@ -35,7 +35,9 @@ final class MessageFormatter
|
||||
|
||||
$phone = PhoneParser::parse(self::flatten_fields_for_phone($fields));
|
||||
$name = self::pick($fields, ['your-name', 'name', 'имя', 'fio']);
|
||||
if ($name === '') $name = FieldDetector::find_name($fields);
|
||||
$email = self::pick($fields, ['your-email', 'email', 'e-mail', 'mail']);
|
||||
if ($email === '') $email = FieldDetector::find_email($fields);
|
||||
$message = self::pick($fields, ['your-message', 'message', 'comment', 'сообщение', 'вопрос']);
|
||||
|
||||
$lines = [];
|
||||
|
||||
@@ -20,7 +20,12 @@ final class PhoneParser
|
||||
// Find a run of digits, spaces, dashes, parens, dots and a leading '+',
|
||||
// with at least 10 digits in total. Walk candidates left-to-right and
|
||||
// pick the first that yields 10 or 11 digits.
|
||||
if (!preg_match_all('/\+?[\d][\d\s().\-]{8,}/u', $text, $m)) {
|
||||
// NOTE: the space class is a literal ' ' — not '\s'. If '\s' is used
|
||||
// a newline or tab between two adjacent form fields (phone value,
|
||||
// then checkbox value) would bleed into the phone and append extra
|
||||
// digits. MessageFormatter/Classifier flatten fields with "\n" before
|
||||
// calling us, so this matters in practice.
|
||||
if (!preg_match_all('/\+?[\d][\d ().\-]{8,}/u', $text, $m)) {
|
||||
return null;
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user