周海龙 / mail-serve · 提交

转到一个项目

作者 邓超
提交 75605d5e87ce450373405ea30cb0137288f2b427 1 个父辈 0751a407

解码问题

内嵌 并排对比
正在显示 2 个修改的文件 包含 741 行增加 和 11 行删除
@@ -748,7 +748,7 @@ class Imap { @@ -748,7 +748,7 @@ class Imap {
748 // 剔除key的值 748 // 剔除key的值
749 $item_str = ltrim(implode(':',$item),$item[0].':'); 749 $item_str = ltrim(implode(':',$item),$item[0].':');
750 // 解析编码 750 // 解析编码
751 - $item_str = mb_decode_mimeheader($item_str); 751 + $item_str = MailFun::mb_coding($item_str);
752 752
753 // $key = str_replace('-','_',strtolower($item[0])); 753 // $key = str_replace('-','_',strtolower($item[0]));
754 $key = $item[0]; 754 $key = $item[0];
@@ -37,16 +37,7 @@ class MailFun { @@ -37,16 +37,7 @@ class MailFun {
37 * @time 2023/3/27 13:55 37 * @time 2023/3/27 13:55
38 */ 38 */
39 public static function mb_coding(string $str,array $appcode=[]){ 39 public static function mb_coding(string $str,array $appcode=[]){
40 - try {  
41 - $encode = @mb_detect_encoding($str, array_merge(array("ASCII",'UTF-8',"GB2312","GBK",'BIG5'),$appcode));  
42 - if($encode){  
43 - return @mb_convert_encoding($str, 'UTF-8', $encode);  
44 - }  
45 - }catch (\Throwable $e){  
46 -  
47 - }  
48 -  
49 - return $str; 40 + return (new Header())->decode($str);
50 } 41 }
51 42
52 43
@@ -409,3 +400,742 @@ class MailFun { @@ -409,3 +400,742 @@ class MailFun {
409 400
410 401
411 } 402 }
  403 +
  404 +
  405 +
  406 +
  407 +/**
  408 + * Class Header
  409 + *
  410 + * @package Webklex\PHPIMAP
  411 + */
  412 +class Header
  413 +{
  414 +
  415 +
  416 + /**
  417 + * Fallback Encoding
  418 + *
  419 + * @var string
  420 + */
  421 + public $fallback_encoding = 'UTF-8';
  422 +
  423 +
  424 + /**
  425 + * Decode MIME header elements
  426 + * @link https://php.net/manual/en/function.imap-mime-header-decode.php
  427 + * @param string $text The MIME text
  428 + *
  429 + * @return array The decoded elements are returned in an array of objects, where each
  430 + * object has two properties, charset and text.
  431 + */
  432 + public function mime_header_decode(string $text): array
  433 + {
  434 + if (extension_loaded('imap')) {
  435 + $result = \imap_mime_header_decode($text);
  436 + return is_array($result) ? $result : [];
  437 + }
  438 + $charset = $this->getEncoding($text);
  439 + return [(object)[
  440 + "charset" => $charset,
  441 + "text" => $this->convertEncoding($text, $charset)
  442 + ]];
  443 + }
  444 +
  445 + /**
  446 + * Check if a given pair of strings has been decoded
  447 + * @param $encoded
  448 + * @param $decoded
  449 + *
  450 + * @return bool
  451 + */
  452 + private function notDecoded($encoded, $decoded): bool
  453 + {
  454 + return 0 === strpos($decoded, '=?')
  455 + && strlen($decoded) - 2 === strpos($decoded, '?=')
  456 + && false !== strpos($encoded, $decoded);
  457 + }
  458 +
  459 + /**
  460 + * Convert the encoding
  461 + * @param $str
  462 + * @param string $from
  463 + * @param string $to
  464 + *
  465 + * @return mixed|string
  466 + */
  467 + public function convertEncoding($str, $from = "ISO-8859-2", $to = "UTF-8")
  468 + {
  469 +
  470 + $from = EncodingAliases::get($from, $this->fallback_encoding);
  471 + $to = EncodingAliases::get($to, $this->fallback_encoding);
  472 +
  473 + if ($from === $to) {
  474 + return $str;
  475 + }
  476 +
  477 + // We don't need to do convertEncoding() if charset is ASCII (us-ascii):
  478 + // ASCII is a subset of UTF-8, so all ASCII files are already UTF-8 encoded
  479 + // https://stackoverflow.com/a/11303410
  480 + //
  481 + // us-ascii is the same as ASCII:
  482 + // ASCII is the traditional name for the encoding system; the Internet Assigned Numbers Authority (IANA)
  483 + // prefers the updated name US-ASCII, which clarifies that this system was developed in the US and
  484 + // based on the typographical symbols predominantly in use there.
  485 + // https://en.wikipedia.org/wiki/ASCII
  486 + //
  487 + // convertEncoding() function basically means convertToUtf8(), so when we convert ASCII string into UTF-8 it gets broken.
  488 + if (strtolower($from) == 'us-ascii' && $to == 'UTF-8') {
  489 + return $str;
  490 + }
  491 +
  492 + try {
  493 + if (function_exists('iconv') && $from != 'UTF-7' && $to != 'UTF-7') {
  494 + return iconv($from, $to, $str);
  495 + } else {
  496 + if (!$from) {
  497 + return mb_convert_encoding($str, $to);
  498 + }
  499 + return mb_convert_encoding($str, $to, $from);
  500 + }
  501 + } catch (\Exception $e) {
  502 + if (strstr($from, '-')) {
  503 + $from = str_replace('-', '', $from);
  504 + return $this->convertEncoding($str, $from, $to);
  505 + } else {
  506 + return $str;
  507 + }
  508 + }
  509 + }
  510 +
  511 + /**
  512 + * Get the encoding of a given abject
  513 + * @param object|string $structure
  514 + *
  515 + * @return string
  516 + */
  517 + public function getEncoding($structure): string
  518 + {
  519 + if (property_exists($structure, 'parameters')) {
  520 + foreach ($structure->parameters as $parameter) {
  521 + if (strtolower($parameter->attribute) == "charset") {
  522 + return EncodingAliases::get($parameter->value, $this->fallback_encoding);
  523 + }
  524 + }
  525 + } elseif (property_exists($structure, 'charset')) {
  526 + return EncodingAliases::get($structure->charset, $this->fallback_encoding);
  527 + } elseif (is_string($structure) === true) {
  528 + $result = mb_detect_encoding($structure);
  529 + return $result === false ? $this->fallback_encoding : $result;
  530 + }
  531 +
  532 + return $this->fallback_encoding;
  533 + }
  534 +
  535 + /**
  536 + * Test if a given value is utf-8 encoded
  537 + * @param $value
  538 + *
  539 + * @return bool
  540 + */
  541 + private function is_uft8($value): bool
  542 + {
  543 + return strpos(strtolower($value), '=?utf-8?') === 0;
  544 + }
  545 +
  546 + /**
  547 + * Try to decode a specific header
  548 + * @param mixed $value
  549 + *
  550 + * @return mixed
  551 + */
  552 + public function decode($value)
  553 + {
  554 + if (is_array($value)) {
  555 + return $this->decodeArray($value);
  556 + }
  557 + $original_value = $value;
  558 + $decoder = 'utf-8';
  559 +
  560 + if ($value !== null) {
  561 + $is_utf8_base = $this->is_uft8($value);
  562 +
  563 + if ($decoder === 'utf-8' && extension_loaded('imap')) {
  564 + $value = \imap_utf8($value);
  565 + $is_utf8_base = $this->is_uft8($value);
  566 + if ($is_utf8_base) {
  567 + $value = mb_decode_mimeheader($value);
  568 + }
  569 + if ($this->notDecoded($original_value, $value)) {
  570 + $decoded_value = $this->mime_header_decode($value);
  571 + if (count($decoded_value) > 0) {
  572 + if (property_exists($decoded_value[0], "text")) {
  573 + $value = $decoded_value[0]->text;
  574 + }
  575 + }
  576 + }
  577 + } elseif ($decoder === 'iconv' && $is_utf8_base) {
  578 + $value = iconv_mime_decode($value);
  579 + } elseif ($is_utf8_base) {
  580 + $value = mb_decode_mimeheader($value);
  581 + }
  582 +
  583 + if ($this->is_uft8($value)) {
  584 + $value = mb_decode_mimeheader($value);
  585 + }
  586 +
  587 + if ($this->notDecoded($original_value, $value)) {
  588 + $value = $this->convertEncoding($original_value, $this->getEncoding($original_value));
  589 + }
  590 + }
  591 +
  592 + return $value;
  593 + }
  594 +
  595 + /**
  596 + * Decode a given array
  597 + * @param array $values
  598 + *
  599 + * @return array
  600 + */
  601 + private function decodeArray(array $values): array
  602 + {
  603 + foreach ($values as $key => $value) {
  604 + $values[$key] = $this->decode($value);
  605 + }
  606 + return $values;
  607 + }
  608 +
  609 +
  610 +
  611 + /**
  612 + * Exception handling for invalid dates
  613 + *
  614 + * Currently known invalid formats:
  615 + * ^ Datetime ^ Problem ^ Cause
  616 + * | Mon, 20 Nov 2017 20:31:31 +0800 (GMT+8:00) | Double timezone specification | A Windows feature
  617 + * | Thu, 8 Nov 2018 08:54:58 -0200 (-02) |
  618 + * | | and invalid timezone (max 6 char) |
  619 + * | 04 Jan 2018 10:12:47 UT | Missing letter "C" | Unknown
  620 + * | Thu, 31 May 2018 18:15:00 +0800 (added by) | Non-standard details added by the | Unknown
  621 + * | | mail server |
  622 + * | Sat, 31 Aug 2013 20:08:23 +0580 | Invalid timezone | PHPMailer bug https://sourceforge.net/p/phpmailer/mailman/message/6132703/
  623 + *
  624 + * Please report any new invalid timestamps to [#45](https://github.com/Webklex/php-imap/issues)
  625 + *
  626 + * @param object $header
  627 + *
  628 + * @throws InvalidMessageDateException
  629 + */
  630 + private function parseDate($header)
  631 + {
  632 +
  633 + if (property_exists($header, 'date')) {
  634 + $date = $header->date;
  635 +
  636 + if (preg_match('/\+0580/', $date)) {
  637 + $date = str_replace('+0580', '+0530', $date);
  638 + }
  639 +
  640 + $date = trim(rtrim($date));
  641 + try {
  642 + if (strpos($date, ' ') !== false) {
  643 + $date = str_replace(' ', ' ', $date);
  644 + }
  645 + $parsed_date = Carbon::parse($date);
  646 + } catch (\Exception $e) {
  647 + switch (true) {
  648 + case preg_match('/([0-9]{4}\.[0-9]{1,2}\.[0-9]{1,2}\-[0-9]{1,2}\.[0-9]{1,2}.[0-9]{1,2})+$/i', $date) > 0:
  649 + $date = Carbon::createFromFormat("Y.m.d-H.i.s", $date);
  650 + break;
  651 + case preg_match('/([0-9]{1,2}\ [A-Z]{2,3}\ [0-9]{4}\ [0-9]{1,2}\:[0-9]{1,2}\:[0-9]{1,2}\ UT)+$/i', $date) > 0:
  652 + case preg_match('/([A-Z]{2,3}\,\ [0-9]{1,2}\ [A-Z]{2,3}\ [0-9]{4}\ [0-9]{1,2}\:[0-9]{1,2}\:[0-9]{1,2}\ UT)+$/i', $date) > 0:
  653 + $date .= 'C';
  654 + break;
  655 + case preg_match('/([A-Z]{2,3}\,\ [0-9]{1,2}[\,]\ [A-Z]{2,3}\ [0-9]{4}\ [0-9]{1,2}\:[0-9]{1,2}\:[0-9]{1,2}\ [\-|\+][0-9]{4})+$/i', $date) > 0:
  656 + $date = str_replace(',', '', $date);
  657 + case preg_match('/([A-Z]{2,3}\,\ [0-9]{1,2}\ [A-Z]{2,3}\ [0-9]{4}\ [0-9]{1,2}\:[0-9]{1,2}\:[0-9]{1,2}\ \+[0-9]{2,4}\ \(\+[0-9]{1,2}\))+$/i', $date) > 0:
  658 + case preg_match('/([A-Z]{2,3}[\,|\ \,]\ [0-9]{1,2}\ [A-Z]{2,3}\ [0-9]{4}\ [0-9]{1,2}\:[0-9]{1,2}\:[0-9]{1,2}.*)+$/i', $date) > 0:
  659 + case preg_match('/([A-Z]{2,3}\,\ [0-9]{1,2}\ [A-Z]{2,3}\ [0-9]{4}\ [0-9]{1,2}\:[0-9]{1,2}\:[0-9]{1,2}\ [\-|\+][0-9]{4}\ \(.*)\)+$/i', $date) > 0:
  660 + case preg_match('/([A-Z]{2,3}\, \ [0-9]{1,2}\ [A-Z]{2,3}\ [0-9]{4}\ [0-9]{1,2}\:[0-9]{1,2}\:[0-9]{1,2}\ [\-|\+][0-9]{4}\ \(.*)\)+$/i', $date) > 0:
  661 + case preg_match('/([0-9]{1,2}\ [A-Z]{2,3}\ [0-9]{2,4}\ [0-9]{2}\:[0-9]{2}\:[0-9]{2}\ [A-Z]{2}\ \-[0-9]{2}\:[0-9]{2}\ \([A-Z]{2,3}\ \-[0-9]{2}:[0-9]{2}\))+$/i', $date) > 0:
  662 + $array = explode('(', $date);
  663 + $array = array_reverse($array);
  664 + $date = trim(array_pop($array));
  665 + break;
  666 + }
  667 +
  668 + $parsed_date = Carbon::parse($date);
  669 +
  670 + }
  671 +
  672 +
  673 + }
  674 + }
  675 +
  676 +
  677 +
  678 +}
  679 +
  680 +class EncodingAliases {
  681 +
  682 + /**
  683 + * Contains email encoding mappings
  684 + *
  685 + * @var array
  686 + */
  687 + private static $aliases = [
  688 + /*
  689 + |--------------------------------------------------------------------------
  690 + | Email encoding aliases
  691 + |--------------------------------------------------------------------------
  692 + |
  693 + | Email encoding aliases used to convert to iconv supported charsets
  694 + |
  695 + |
  696 + | This Source Code Form is subject to the terms of the Mozilla Public
  697 + | License, v. 2.0. If a copy of the MPL was not distributed with this
  698 + | file, You can obtain one at http://mozilla.org/MPL/2.0/.
  699 + |
  700 + | This Original Code has been modified by IBM Corporation.
  701 + | Modifications made by IBM described herein are
  702 + | Copyright (c) International Business Machines
  703 + | Corporation, 1999
  704 + |
  705 + | Modifications to Mozilla code or documentation
  706 + | identified per MPL Section 3.3
  707 + |
  708 + | Date Modified by Description of modification
  709 + | 12/09/1999 IBM Corp. Support for IBM codepages - 850,852,855,857,862,864
  710 + |
  711 + | Rule of this file:
  712 + | 1. key should always be in lower case ascii so we can do case insensitive
  713 + | comparison in the code faster.
  714 + | 2. value should be the one used in unicode converter
  715 + |
  716 + | 3. If the charset is not used for document charset, but font charset
  717 + | (e.g. XLFD charset- such as JIS x0201, JIS x0208), don't put here
  718 + |
  719 + */
  720 + "ascii" => "us-ascii",
  721 + "us-ascii" => "us-ascii",
  722 + "ansi_x3.4-1968" => "us-ascii",
  723 + "646" => "us-ascii",
  724 + "iso-8859-1" => "ISO-8859-1",
  725 + "iso-8859-2" => "ISO-8859-2",
  726 + "iso-8859-3" => "ISO-8859-3",
  727 + "iso-8859-4" => "ISO-8859-4",
  728 + "iso-8859-5" => "ISO-8859-5",
  729 + "iso-8859-6" => "ISO-8859-6",
  730 + "iso-8859-6-i" => "ISO-8859-6-I",
  731 + "iso-8859-6-e" => "ISO-8859-6-E",
  732 + "iso-8859-7" => "ISO-8859-7",
  733 + "iso-8859-8" => "ISO-8859-8",
  734 + "iso-8859-8-i" => "ISO-8859-8-I",
  735 + "iso-8859-8-e" => "ISO-8859-8-E",
  736 + "iso-8859-9" => "ISO-8859-9",
  737 + "iso-8859-10" => "ISO-8859-10",
  738 + "iso-8859-11" => "ISO-8859-11",
  739 + "iso-8859-13" => "ISO-8859-13",
  740 + "iso-8859-14" => "ISO-8859-14",
  741 + "iso-8859-15" => "ISO-8859-15",
  742 + "iso-8859-16" => "ISO-8859-16",
  743 + "iso-ir-111" => "ISO-IR-111",
  744 + "iso-2022-cn" => "ISO-2022-CN",
  745 + "iso-2022-cn-ext" => "ISO-2022-CN",
  746 + "iso-2022-kr" => "ISO-2022-KR",
  747 + "iso-2022-jp" => "ISO-2022-JP",
  748 + "utf-16be" => "UTF-16BE",
  749 + "utf-16le" => "UTF-16LE",
  750 + "utf-16" => "UTF-16",
  751 + "windows-1250" => "windows-1250",
  752 + "windows-1251" => "windows-1251",
  753 + "windows-1252" => "windows-1252",
  754 + "windows-1253" => "windows-1253",
  755 + "windows-1254" => "windows-1254",
  756 + "windows-1255" => "windows-1255",
  757 + "windows-1256" => "windows-1256",
  758 + "windows-1257" => "windows-1257",
  759 + "windows-1258" => "windows-1258",
  760 + "ibm866" => "IBM866",
  761 + "ibm850" => "IBM850",
  762 + "ibm852" => "IBM852",
  763 + "ibm855" => "IBM855",
  764 + "ibm857" => "IBM857",
  765 + "ibm862" => "IBM862",
  766 + "ibm864" => "IBM864",
  767 + "utf-8" => "UTF-8",
  768 + "utf-7" => "UTF-7",
  769 + "shift_jis" => "Shift_JIS",
  770 + "big5" => "Big5",
  771 + "euc-jp" => "EUC-JP",
  772 + "euc-kr" => "EUC-KR",
  773 + "gb2312" => "GB2312",
  774 + "gb18030" => "gb18030",
  775 + "viscii" => "VISCII",
  776 + "koi8-r" => "KOI8-R",
  777 + "koi8_r" => "KOI8-R",
  778 + "cskoi8r" => "KOI8-R",
  779 + "koi" => "KOI8-R",
  780 + "koi8" => "KOI8-R",
  781 + "koi8-u" => "KOI8-U",
  782 + "tis-620" => "TIS-620",
  783 + "t.61-8bit" => "T.61-8bit",
  784 + "hz-gb-2312" => "HZ-GB-2312",
  785 + "big5-hkscs" => "Big5-HKSCS",
  786 + "gbk" => "gbk",
  787 + "cns11643" => "x-euc-tw",
  788 + //
  789 + // Aliases for ISO-8859-1
  790 + //
  791 + "latin1" => "ISO-8859-1",
  792 + "iso_8859-1" => "ISO-8859-1",
  793 + "iso8859-1" => "ISO-8859-1",
  794 + "iso8859-2" => "ISO-8859-2",
  795 + "iso8859-3" => "ISO-8859-3",
  796 + "iso8859-4" => "ISO-8859-4",
  797 + "iso8859-5" => "ISO-8859-5",
  798 + "iso8859-6" => "ISO-8859-6",
  799 + "iso8859-7" => "ISO-8859-7",
  800 + "iso8859-8" => "ISO-8859-8",
  801 + "iso8859-9" => "ISO-8859-9",
  802 + "iso8859-10" => "ISO-8859-10",
  803 + "iso8859-11" => "ISO-8859-11",
  804 + "iso8859-13" => "ISO-8859-13",
  805 + "iso8859-14" => "ISO-8859-14",
  806 + "iso8859-15" => "ISO-8859-15",
  807 + "iso_8859-1:1987" => "ISO-8859-1",
  808 + "iso-ir-100" => "ISO-8859-1",
  809 + "l1" => "ISO-8859-1",
  810 + "ibm819" => "ISO-8859-1",
  811 + "cp819" => "ISO-8859-1",
  812 + "csisolatin1" => "ISO-8859-1",
  813 + //
  814 + // Aliases for ISO-8859-2
  815 + //
  816 + "latin2" => "ISO-8859-2",
  817 + "iso_8859-2" => "ISO-8859-2",
  818 + "iso_8859-2:1987" => "ISO-8859-2",
  819 + "iso-ir-101" => "ISO-8859-2",
  820 + "l2" => "ISO-8859-2",
  821 + "csisolatin2" => "ISO-8859-2",
  822 + //
  823 + // Aliases for ISO-8859-3
  824 + //
  825 + "latin3" => "ISO-8859-3",
  826 + "iso_8859-3" => "ISO-8859-3",
  827 + "iso_8859-3:1988" => "ISO-8859-3",
  828 + "iso-ir-109" => "ISO-8859-3",
  829 + "l3" => "ISO-8859-3",
  830 + "csisolatin3" => "ISO-8859-3",
  831 + //
  832 + // Aliases for ISO-8859-4
  833 + //
  834 + "latin4" => "ISO-8859-4",
  835 + "iso_8859-4" => "ISO-8859-4",
  836 + "iso_8859-4:1988" => "ISO-8859-4",
  837 + "iso-ir-110" => "ISO-8859-4",
  838 + "l4" => "ISO-8859-4",
  839 + "csisolatin4" => "ISO-8859-4",
  840 + //
  841 + // Aliases for ISO-8859-5
  842 + //
  843 + "cyrillic" => "ISO-8859-5",
  844 + "iso_8859-5" => "ISO-8859-5",
  845 + "iso_8859-5:1988" => "ISO-8859-5",
  846 + "iso-ir-144" => "ISO-8859-5",
  847 + "csisolatincyrillic" => "ISO-8859-5",
  848 + //
  849 + // Aliases for ISO-8859-6
  850 + //
  851 + "arabic" => "ISO-8859-6",
  852 + "iso_8859-6" => "ISO-8859-6",
  853 + "iso_8859-6:1987" => "ISO-8859-6",
  854 + "iso-ir-127" => "ISO-8859-6",
  855 + "ecma-114" => "ISO-8859-6",
  856 + "asmo-708" => "ISO-8859-6",
  857 + "csisolatinarabic" => "ISO-8859-6",
  858 + //
  859 + // Aliases for ISO-8859-6-I
  860 + //
  861 + "csiso88596i" => "ISO-8859-6-I",
  862 + //
  863 + // Aliases for ISO-8859-6-E",
  864 + //
  865 + "csiso88596e" => "ISO-8859-6-E",
  866 + //
  867 + // Aliases for ISO-8859-7",
  868 + //
  869 + "greek" => "ISO-8859-7",
  870 + "greek8" => "ISO-8859-7",
  871 + "sun_eu_greek" => "ISO-8859-7",
  872 + "iso_8859-7" => "ISO-8859-7",
  873 + "iso_8859-7:1987" => "ISO-8859-7",
  874 + "iso-ir-126" => "ISO-8859-7",
  875 + "elot_928" => "ISO-8859-7",
  876 + "ecma-118" => "ISO-8859-7",
  877 + "csisolatingreek" => "ISO-8859-7",
  878 + //
  879 + // Aliases for ISO-8859-8",
  880 + //
  881 + "hebrew" => "ISO-8859-8",
  882 + "iso_8859-8" => "ISO-8859-8",
  883 + "visual" => "ISO-8859-8",
  884 + "iso_8859-8:1988" => "ISO-8859-8",
  885 + "iso-ir-138" => "ISO-8859-8",
  886 + "csisolatinhebrew" => "ISO-8859-8",
  887 + //
  888 + // Aliases for ISO-8859-8-I",
  889 + //
  890 + "csiso88598i" => "ISO-8859-8-I",
  891 + "iso-8859-8i" => "ISO-8859-8-I",
  892 + "logical" => "ISO-8859-8-I",
  893 + //
  894 + // Aliases for ISO-8859-8-E",
  895 + //
  896 + "csiso88598e" => "ISO-8859-8-E",
  897 + //
  898 + // Aliases for ISO-8859-9",
  899 + //
  900 + "latin5" => "ISO-8859-9",
  901 + "iso_8859-9" => "ISO-8859-9",
  902 + "iso_8859-9:1989" => "ISO-8859-9",
  903 + "iso-ir-148" => "ISO-8859-9",
  904 + "l5" => "ISO-8859-9",
  905 + "csisolatin5" => "ISO-8859-9",
  906 + //
  907 + // Aliases for UTF-8",
  908 + //
  909 + "unicode-1-1-utf-8" => "UTF-8",
  910 + // nl_langinfo(CODESET) in HP/UX returns 'utf8' under UTF-8 locales",
  911 + "utf8" => "UTF-8",
  912 + //
  913 + // Aliases for Shift_JIS",
  914 + //
  915 + "x-sjis" => "Shift_JIS",
  916 + "shift-jis" => "Shift_JIS",
  917 + "ms_kanji" => "Shift_JIS",
  918 + "csshiftjis" => "Shift_JIS",
  919 + "windows-31j" => "Shift_JIS",
  920 + "cp932" => "Shift_JIS",
  921 + "sjis" => "Shift_JIS",
  922 + //
  923 + // Aliases for EUC_JP",
  924 + //
  925 + "cseucpkdfmtjapanese" => "EUC-JP",
  926 + "x-euc-jp" => "EUC-JP",
  927 + //
  928 + // Aliases for ISO-2022-JP",
  929 + //
  930 + "csiso2022jp" => "ISO-2022-JP",
  931 + // The following are really not aliases ISO-2022-JP, but sharing the same decoder",
  932 + "iso-2022-jp-2" => "ISO-2022-JP",
  933 + "csiso2022jp2" => "ISO-2022-JP",
  934 + //
  935 + // Aliases for Big5",
  936 + //
  937 + "csbig5" => "Big5",
  938 + "cn-big5" => "Big5",
  939 + // x-x-big5 is not really a alias for Big5, add it only for MS FrontPage",
  940 + "x-x-big5" => "Big5",
  941 + // Sun Solaris",
  942 + "zh_tw-big5" => "Big5",
  943 + //
  944 + // Aliases for EUC-KR",
  945 + //
  946 + "cseuckr" => "EUC-KR",
  947 + "ks_c_5601-1987" => "EUC-KR",
  948 + "iso-ir-149" => "EUC-KR",
  949 + "ks_c_5601-1989" => "EUC-KR",
  950 + "ksc_5601" => "EUC-KR",
  951 + "ksc5601" => "EUC-KR",
  952 + "korean" => "EUC-KR",
  953 + "csksc56011987" => "EUC-KR",
  954 + "5601" => "EUC-KR",
  955 + "windows-949" => "EUC-KR",
  956 + //
  957 + // Aliases for GB2312",
  958 + //
  959 + // The following are really not aliases GB2312, add them only for MS FrontPage",
  960 + "gb_2312-80" => "GB2312",
  961 + "iso-ir-58" => "GB2312",
  962 + "chinese" => "GB2312",
  963 + "csiso58gb231280" => "GB2312",
  964 + "csgb2312" => "GB2312",
  965 + "zh_cn.euc" => "GB2312",
  966 + // Sun Solaris",
  967 + "gb_2312" => "GB2312",
  968 + //
  969 + // Aliases for windows-125x ",
  970 + //
  971 + "x-cp1250" => "windows-1250",
  972 + "x-cp1251" => "windows-1251",
  973 + "x-cp1252" => "windows-1252",
  974 + "x-cp1253" => "windows-1253",
  975 + "x-cp1254" => "windows-1254",
  976 + "x-cp1255" => "windows-1255",
  977 + "x-cp1256" => "windows-1256",
  978 + "x-cp1257" => "windows-1257",
  979 + "x-cp1258" => "windows-1258",
  980 + //
  981 + // Aliases for windows-874 ",
  982 + //
  983 + "windows-874" => "windows-874",
  984 + "ibm874" => "windows-874",
  985 + "dos-874" => "windows-874",
  986 + //
  987 + // Aliases for macintosh",
  988 + //
  989 + "macintosh" => "macintosh",
  990 + "x-mac-roman" => "macintosh",
  991 + "mac" => "macintosh",
  992 + "csmacintosh" => "macintosh",
  993 + //
  994 + // Aliases for IBM866",
  995 + //
  996 + "cp866" => "IBM866",
  997 + "cp-866" => "IBM866",
  998 + "866" => "IBM866",
  999 + "csibm866" => "IBM866",
  1000 + //
  1001 + // Aliases for IBM850",
  1002 + //
  1003 + "cp850" => "IBM850",
  1004 + "850" => "IBM850",
  1005 + "csibm850" => "IBM850",
  1006 + //
  1007 + // Aliases for IBM852",
  1008 + //
  1009 + "cp852" => "IBM852",
  1010 + "852" => "IBM852",
  1011 + "csibm852" => "IBM852",
  1012 + //
  1013 + // Aliases for IBM855",
  1014 + //
  1015 + "cp855" => "IBM855",
  1016 + "855" => "IBM855",
  1017 + "csibm855" => "IBM855",
  1018 + //
  1019 + // Aliases for IBM857",
  1020 + //
  1021 + "cp857" => "IBM857",
  1022 + "857" => "IBM857",
  1023 + "csibm857" => "IBM857",
  1024 + //
  1025 + // Aliases for IBM862",
  1026 + //
  1027 + "cp862" => "IBM862",
  1028 + "862" => "IBM862",
  1029 + "csibm862" => "IBM862",
  1030 + //
  1031 + // Aliases for IBM864",
  1032 + //
  1033 + "cp864" => "IBM864",
  1034 + "864" => "IBM864",
  1035 + "csibm864" => "IBM864",
  1036 + "ibm-864" => "IBM864",
  1037 + //
  1038 + // Aliases for T.61-8bit",
  1039 + //
  1040 + "t.61" => "T.61-8bit",
  1041 + "iso-ir-103" => "T.61-8bit",
  1042 + "csiso103t618bit" => "T.61-8bit",
  1043 + //
  1044 + // Aliases for UTF-7",
  1045 + //
  1046 + "x-unicode-2-0-utf-7" => "UTF-7",
  1047 + "unicode-2-0-utf-7" => "UTF-7",
  1048 + "unicode-1-1-utf-7" => "UTF-7",
  1049 + "csunicode11utf7" => "UTF-7",
  1050 + //
  1051 + // Aliases for ISO-10646-UCS-2",
  1052 + //
  1053 + "csunicode" => "UTF-16BE",
  1054 + "csunicode11" => "UTF-16BE",
  1055 + "iso-10646-ucs-basic" => "UTF-16BE",
  1056 + "csunicodeascii" => "UTF-16BE",
  1057 + "iso-10646-unicode-latin1" => "UTF-16BE",
  1058 + "csunicodelatin1" => "UTF-16BE",
  1059 + "iso-10646" => "UTF-16BE",
  1060 + "iso-10646-j-1" => "UTF-16BE",
  1061 + //
  1062 + // Aliases for ISO-8859-10",
  1063 + //
  1064 + "latin6" => "ISO-8859-10",
  1065 + "iso-ir-157" => "ISO-8859-10",
  1066 + "l6" => "ISO-8859-10",
  1067 + // Currently .properties cannot handle : in key",
  1068 + //iso_8859-10:1992" => "ISO-8859-10",
  1069 + "csisolatin6" => "ISO-8859-10",
  1070 + //
  1071 + // Aliases for ISO-8859-15",
  1072 + //
  1073 + "iso_8859-15" => "ISO-8859-15",
  1074 + "csisolatin9" => "ISO-8859-15",
  1075 + "l9" => "ISO-8859-15",
  1076 + //
  1077 + // Aliases for ISO-IR-111",
  1078 + //
  1079 + "ecma-cyrillic" => "ISO-IR-111",
  1080 + "csiso111ecmacyrillic" => "ISO-IR-111",
  1081 + //
  1082 + // Aliases for ISO-2022-KR",
  1083 + //
  1084 + "csiso2022kr" => "ISO-2022-KR",
  1085 + //
  1086 + // Aliases for VISCII",
  1087 + //
  1088 + "csviscii" => "VISCII",
  1089 + //
  1090 + // Aliases for x-euc-tw",
  1091 + //
  1092 + "zh_tw-euc" => "x-euc-tw",
  1093 + //
  1094 + // Following names appears in unix nl_langinfo(CODESET)",
  1095 + // They can be compiled as platform specific if necessary",
  1096 + // DONT put things here if it does not look generic enough (like hp15CN)",
  1097 + //
  1098 + "iso88591" => "ISO-8859-1",
  1099 + "iso88592" => "ISO-8859-2",
  1100 + "iso88593" => "ISO-8859-3",
  1101 + "iso88594" => "ISO-8859-4",
  1102 + "iso88595" => "ISO-8859-5",
  1103 + "iso88596" => "ISO-8859-6",
  1104 + "iso88597" => "ISO-8859-7",
  1105 + "iso88598" => "ISO-8859-8",
  1106 + "iso88599" => "ISO-8859-9",
  1107 + "iso885910" => "ISO-8859-10",
  1108 + "iso885911" => "ISO-8859-11",
  1109 + "iso885912" => "ISO-8859-12",
  1110 + "iso885913" => "ISO-8859-13",
  1111 + "iso885914" => "ISO-8859-14",
  1112 + "iso885915" => "ISO-8859-15",
  1113 + "cp1250" => "windows-1250",
  1114 + "cp1251" => "windows-1251",
  1115 + "cp1252" => "windows-1252",
  1116 + "cp1253" => "windows-1253",
  1117 + "cp1254" => "windows-1254",
  1118 + "cp1255" => "windows-1255",
  1119 + "cp1256" => "windows-1256",
  1120 + "cp1257" => "windows-1257",
  1121 + "cp1258" => "windows-1258",
  1122 + "x-gbk" => "gbk",
  1123 + "windows-936" => "gbk",
  1124 + "ansi-1251" => "windows-1251",
  1125 + ];
  1126 +
  1127 + /**
  1128 + * Returns proper encoding mapping, if exsists. If it doesn't, return unchanged $encoding
  1129 + * @param string|null $encoding
  1130 + * @param string|null $fallback
  1131 + *
  1132 + * @return string
  1133 + */
  1134 + public static function get($encoding, string $fallback = null): string {
  1135 + if (isset(self::$aliases[strtolower($encoding ?? '')])) {
  1136 + return self::$aliases[strtolower($encoding ?? '')];
  1137 + }
  1138 + return $fallback !== null ? $fallback : $encoding;
  1139 + }
  1140 +
  1141 +}