Charset::__construct() - Code Metrics - Inspection of "news" - gggeek/phpxmlrpc - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( 8cdf44...424db6 )

by Gaetano

created 2023-01-12 17:56 UTC

Charset::__construct() A

↳ Parent: Charset

Complexity

Conditions	1
Paths	1

Size

Total Lines	2
Code Lines	0

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	2
CRAP Score	1

Importance

Changes	1
Bugs	0	Features	0

Metric	Value
cc	1
eloc	0
nc	1
nop	0
dl	0
loc	2
ccs	2
cts	2
cp	1
crap	1
rs	10
c	1
b	0
f	0

<?php

namespace PhpXmlRpc\Helper;

use PhpXmlRpc\PhpXmlRpc;

/**
 * @todo implement an interface
 */
class Charset
{
    protected static $logger;

    // tables used for transcoding different charsets into us-ascii xml
    protected $xml_iso88591_Entities = array("in" => array(), "out" => array());

    //protected $xml_cp1252_Entities = array('in' => array(), out' => array());

    protected $charset_supersets = array(
        'US-ASCII' => array('ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3', 'ISO-8859-4',
            'ISO-8859-5', 'ISO-8859-6', 'ISO-8859-7', 'ISO-8859-8',
            'ISO-8859-9', 'ISO-8859-10', 'ISO-8859-11', 'ISO-8859-12',
            'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'UTF-8',
            'EUC-JP', 'EUC-', 'EUC-KR', 'EUC-CN',),
    );

    /** @var Charset $instance */
    protected static $instance = null;

    /**
     * This class is singleton for performance reasons.
     *
     * @return Charset
     *
     * @todo should we just make $xml_iso88591_Entities a static variable instead ?
     */
    public static function instance()
    {
        if (self::$instance === null) {
            self::$instance = new static();
        }

        return self::$instance;
    }

    public function getLogger()
    {
        if (self::$logger === null) {
            self::$logger = Logger::instance();
        }
        return self::$logger;
    }

    /**
     * @param $logger
     * @return void
     */
    public static function setLogger($logger)
    {
        self::$logger = $logger;
    }

    /**
     * Force usage as singleton.
     */
    protected function __construct()
    {
    }

    /**
     * @param string $tableName
     * @return void
     *
     * @throws \Exception for unsupported $tableName
     *
     * @todo add support for cp1252 as well as latin-2 .. latin-10
     *       Optimization creep: instead of building all those tables on load, keep them ready-made php files
     *       which are not even included until needed
     * @todo should we add to the latin-1 table the characters from cp_1252 range, i.e. 128 to 159 ?
     *       Those will NOT be present in true ISO-8859-1, but will save the unwary windows user from sending junk
     *       (though no luck when receiving them...)
     *       Note also that, apparently, while 'ISO/IEC 8859-1' has no characters defined for bytes 128 to 159,
     *       IANA ISO-8859-1 does have well-defined 'C1' control codes for those - wikipedia's page on latin-1 says:
     *       "ISO-8859-1 is the IANA preferred name for this standard when supplemented with the C0 and C1 control codes
     *       from ISO/IEC 6429." Check what mbstring/iconv do by default with those?
     */
    protected function buildConversionTable($tableName)
    {
        switch ($tableName) {
            case 'xml_iso88591_Entities':
                if (count($this->xml_iso88591_Entities['in'])) {
                    return;
                }
                for ($i = 0; $i < 32; $i++) {
                    $this->xml_iso88591_Entities["in"][] = chr($i);
                    $this->xml_iso88591_Entities["out"][] = "&#{$i};";
                }

                /// @todo to be 'print safe', should we encode as well character 127 (DEL) ?

                for ($i = 160; $i < 256; $i++) {
                    $this->xml_iso88591_Entities["in"][] = chr($i);
                    $this->xml_iso88591_Entities["out"][] = "&#{$i};";
                }
                break;

            /*case 'xml_cp1252_Entities':
                if (count($this->xml_cp1252_Entities['in'])) {
                    return;
                }
                for ($i = 128; $i < 160; $i++)
                {
                    $this->xml_cp1252_Entities['in'][] = chr($i);
                }
                $this->xml_cp1252_Entities['out'] = array(
                    '&#x20AC;', '?',        '&#x201A;', '&#x0192;',
                    '&#x201E;', '&#x2026;', '&#x2020;', '&#x2021;',
                    '&#x02C6;', '&#x2030;', '&#x0160;', '&#x2039;',
                    '&#x0152;', '?',        '&#x017D;', '?',
                    '?',        '&#x2018;', '&#x2019;', '&#x201C;',
                    '&#x201D;', '&#x2022;', '&#x2013;', '&#x2014;',
                    '&#x02DC;', '&#x2122;', '&#x0161;', '&#x203A;',
                    '&#x0153;', '?',        '&#x017E;', '&#x0178;'
                );
                $this->buildConversionTable('xml_iso88591_Entities');
                break;*/

            default:
                throw new \Exception('Unsupported table: ' . $tableName);
        }
    }

    /**
     * Convert a string to the correct XML representation in a target charset.
     * This involves:
     * - character transformation for all characters which have a different representation in source and dest charsets
     * - using 'charset entity' representation for all characters which are outside of the target charset
     *
     * To help correct communication of non-ascii chars inside strings, regardless of the charset used when sending
     * requests, parsing them, sending responses and parsing responses, an option is to convert all non-ascii chars
     * present in the message into their equivalent 'charset entity'. Charset entities enumerated this way are
     * independent of the charset encoding used to transmit them, and all XML parsers are bound to understand them.
     *
     * Note that when not sending a charset encoding mime type along with http headers, we are bound by RFC 3023 to emit
     * strict us-ascii for 'text/xml' payloads (but we should review RFC 7303, which seems to have changed the rules...)
     *
     * @param string $data
     * @param string $srcEncoding
     * @param string $destEncoding
     * @return string
     *
     * @todo do a bit of basic benchmarking (strtr vs. str_replace)
     * @todo make usage of iconv() or mb_string() where available
     * @todo support aliases for charset names, eg ASCII, LATIN1, ISO-88591 (see f.e. polyfill-iconv for a list),
     *       but then take those into account as well in other methods, ie. isValidCharset)
     * @todo when converting to ASCII, allow to choose whether to escape the range 0-31,127 (non-print chars) or not
     * @todo allow picking different strategies to deal w. invalid chars? eg. source in latin-1 and chars 128-159
     * @todo add support for escaping using CDATA sections? (add cdata start and end tokens, replace only ']]>' with ']]]]><![CDATA[>')
     */
    public function encodeEntities($data, $srcEncoding = '', $destEncoding = '')
    {
        if ($srcEncoding == '') {
            // lame, but we know no better...
            $srcEncoding = PhpXmlRpc::$xmlrpc_internalencoding;
        }

        if ($destEncoding == '') {
            $destEncoding = 'US-ASCII';
        }

        $conversion = strtoupper($srcEncoding . '_' . $destEncoding);

        // list ordered with (expected) most common scenarios first
        switch ($conversion) {
            case 'UTF-8_UTF-8':
            case 'ISO-8859-1_ISO-8859-1':
            case 'US-ASCII_UTF-8':
            case 'US-ASCII_US-ASCII':
            case 'US-ASCII_ISO-8859-1':
            //case 'CP1252_CP1252':
                $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&amp;', '&quot;', '&apos;', '&lt;', '&gt;'), $data);
                break;

            case 'UTF-8_US-ASCII':
            case 'UTF-8_ISO-8859-1':
                // NB: this will choke on invalid UTF-8, going most likely beyond EOF
                $escapedData = '';
                // be kind to users creating string xmlrpc values out of different php types
                $data = (string)$data;
                $ns = strlen($data);
                for ($nn = 0; $nn < $ns; $nn++) {
                    $ch = $data[$nn];
                    $ii = ord($ch);
                    // 7 bits in 1 byte: 0bbbbbbb (127)
                    if ($ii < 32) {
                        if ($conversion == 'UTF-8_US-ASCII') {
                            $escapedData .= sprintf('&#%d;', $ii);
                        } else {
                            $escapedData .= $ch;
                        }
                    }
                    else if ($ii < 128) {
                        /// @todo shall we replace this with a (supposedly) faster str_replace?
                        /// @todo to be 'print safe', should we encode as well character 127 (DEL) ?
                        switch ($ii) {
                            case 34:
                                $escapedData .= '&quot;';
                                break;
                            case 38:
                                $escapedData .= '&amp;';
                                break;
                            case 39:
                                $escapedData .= '&apos;';
                                break;
                            case 60:
                                $escapedData .= '&lt;';
                                break;
                            case 62:
                                $escapedData .= '&gt;';
                                break;
                            default:
                                $escapedData .= $ch;
                        } // switch
                    } // 11 bits in 2 bytes: 110bbbbb 10bbbbbb (2047)
                    elseif ($ii >> 5 == 6) {
                        $b1 = ($ii & 31);
                        $b2 = (ord($data[$nn + 1]) & 63);
                        $ii = ($b1 * 64) + $b2;
                        $escapedData .= sprintf('&#%d;', $ii);
                        $nn += 1;
                    } // 16 bits in 3 bytes: 1110bbbb 10bbbbbb 10bbbbbb
                    elseif ($ii >> 4 == 14) {
                        $b1 = ($ii & 15);
                        $b2 = (ord($data[$nn + 1]) & 63);
                        $b3 = (ord($data[$nn + 2]) & 63);
                        $ii = ((($b1 * 64) + $b2) * 64) + $b3;
                        $escapedData .= sprintf('&#%d;', $ii);
                        $nn += 2;
                    } // 21 bits in 4 bytes: 11110bbb 10bbbbbb 10bbbbbb 10bbbbbb
                    elseif ($ii >> 3 == 30) {
                        $b1 = ($ii & 7);
                        $b2 = (ord($data[$nn + 1]) & 63);
                        $b3 = (ord($data[$nn + 2]) & 63);
                        $b4 = (ord($data[$nn + 3]) & 63);
                        $ii = ((((($b1 * 64) + $b2) * 64) + $b3) * 64) + $b4;
                        $escapedData .= sprintf('&#%d;', $ii);
                        $nn += 3;
                    }
                }

                // when converting to latin-1, do not be so eager with using entities for characters 160-255
                if ($conversion == 'UTF-8_ISO-8859-1') {
                    $this->buildConversionTable('xml_iso88591_Entities');
                    $escapedData = str_replace(array_slice($this->xml_iso88591_Entities['out'], 32), array_slice($this->xml_iso88591_Entities['in'], 32), $escapedData);
                }
                break;

            case 'ISO-8859-1_UTF-8':
                $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&amp;', '&quot;', '&apos;', '&lt;', '&gt;'), $data);
                /// @todo if on php >= 8.2, prefer using mbstring or iconv
                $escapedData = utf8_encode($escapedData);
                break;

            case 'ISO-8859-1_US-ASCII':
                $this->buildConversionTable('xml_iso88591_Entities');
                $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&amp;', '&quot;', '&apos;', '&lt;', '&gt;'), $data);
                $escapedData = str_replace($this->xml_iso88591_Entities['in'], $this->xml_iso88591_Entities['out'], $escapedData);
                break;

            /*
            case 'CP1252_US-ASCII':
                $this->buildConversionTable('xml_cp1252_Entities');
                $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&amp;', '&quot;', '&apos;', '&lt;', '&gt;'), $data);
                $escapedData = str_replace($this->xml_iso88591_Entities']['in'], $this->xml_iso88591_Entities['out'], $escapedData);
                $escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData);
                break;
            case 'CP1252_UTF-8':
                $this->buildConversionTable('xml_cp1252_Entities');
                $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&amp;', '&quot;', '&apos;', '&lt;', '&gt;'), $data);
                /// @todo we could use real UTF8 chars here instead of xml entities... (note that utf_8 encode all alone will NOT convert them)
                $escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData);
                $escapedData = utf8_encode($escapedData);
                break;
            case 'CP1252_ISO-8859-1':
                $this->buildConversionTable('xml_cp1252_Entities');
                $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&amp;', '&quot;', '&apos;', '&lt;', '&gt;'), $data);
                // we might as well replace all funky chars with a '?' here, but we are kind and leave it to the receiving application layer to decide what to do with these weird entities...
                $escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData);
                break;
            */

            default:
                $escapedData = '';
                /// @todo allow usage of a custom Logger via the DIC(ish) pattern we use in other classes
                $this->getLogger()->errorLog('XML-RPC: ' . __METHOD__ . ": Converting from $srcEncoding to $destEncoding: not supported...");
        }

        return $escapedData;
    }

    /**
     * Checks if a given charset encoding is present in a list of encodings or if it is a valid subset of any encoding
     * in the list.
     *
     * @param string $encoding charset to be tested
     * @param string|array $validList comma separated list of valid charsets (or array of charsets)
     * @return bool
     */
    public function isValidCharset($encoding, $validList)
    {
        if (is_string($validList)) {
            $validList = explode(',', $validList);
        }
        if (@in_array(strtoupper($encoding), $validList)) {
            return true;
        } else {
            if (array_key_exists($encoding, $this->charset_supersets)) {
                foreach ($validList as $allowed) {
                    if (in_array($allowed, $this->charset_supersets[$encoding])) {
                        return true;
                    }
                }
            }

            return false;
        }
    }

    /**
     * Used only for backwards compatibility.
     * @deprecated
     *
     * @param string $charset
     * @return array
     * @throws \Exception for unknown/unsupported charsets
     */
    public function getEntities($charset)
    {
        //trigger_error('Method ' . __METHOD__ . ' is deprecated', E_USER_DEPRECATED);

        switch ($charset)
        {
            case 'iso88591':
                return $this->xml_iso88591_Entities;
            default:
                throw new \Exception('Unsupported charset: ' . $charset);
        }
    }
}


1		<?php
2
3		namespace PhpXmlRpc\Helper;
4
5		use PhpXmlRpc\PhpXmlRpc;
6
7		/**
8		* @todo implement an interface
9		*/
10		class Charset
11		{
12		protected static $logger;
13
14		// tables used for transcoding different charsets into us-ascii xml
15		protected $xml_iso88591_Entities = array("in" => array(), "out" => array());
16
17		//protected $xml_cp1252_Entities = array('in' => array(), out' => array());
18
19		protected $charset_supersets = array(
20		'US-ASCII' => array('ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3', 'ISO-8859-4',
21		'ISO-8859-5', 'ISO-8859-6', 'ISO-8859-7', 'ISO-8859-8',
22		'ISO-8859-9', 'ISO-8859-10', 'ISO-8859-11', 'ISO-8859-12',
23		'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'UTF-8',
24		'EUC-JP', 'EUC-', 'EUC-KR', 'EUC-CN',),
25		);
26
27		/** @var Charset $instance */
28		protected static $instance = null;
29
30		/**
31		* This class is singleton for performance reasons.
32		*
33		* @return Charset
34	450	*
35		* @todo should we just make $xml_iso88591_Entities a static variable instead ?
36	450	*/
37	443	public static function instance()
38		{
39		if (self::$instance === null) {
40	450	self::$instance = new static();
41		}
42
43		return self::$instance;
44		}
45
46	443	public function getLogger()
47		{
48	443	if (self::$logger === null) {
49		self::$logger = Logger::instance();
50		}
51		return self::$logger;
52		}
53
54		/**
55		* @param $logger
56		* @return void
57		*/
58		public static function setLogger($logger)
59		{
60		self::$logger = $logger;
61		}
62
63		/**
64	590	* Force usage as singleton.
65		*/
66	590	protected function __construct()
67	590	{
68	590	}
69	588
70		/**
71	20	* @param string $tableName
72	20	* @return void
73	20	*
74		* @throws \Exception for unsupported $tableName
75		*
76		* @todo add support for cp1252 as well as latin-2 .. latin-10
77		* Optimization creep: instead of building all those tables on load, keep them ready-made php files
78	20	* which are not even included until needed
79	20	* @todo should we add to the latin-1 table the characters from cp_1252 range, i.e. 128 to 159 ?
80	20	* Those will NOT be present in true ISO-8859-1, but will save the unwary windows user from sending junk
81		* (though no luck when receiving them...)
82	20	* Note also that, apparently, while 'ISO/IEC 8859-1' has no characters defined for bytes 128 to 159,
83		* IANA ISO-8859-1 does have well-defined 'C1' control codes for those - wikipedia's page on latin-1 says:
84		* "ISO-8859-1 is the IANA preferred name for this standard when supplemented with the C0 and C1 control codes
85		* from ISO/IEC 6429." Check what mbstring/iconv do by default with those?
86		*/
87		protected function buildConversionTable($tableName)
88		{
89		switch ($tableName) {
90		case 'xml_iso88591_Entities':
91		if (count($this->xml_iso88591_Entities['in'])) {
92		return;
93		}
94		for ($i = 0; $i < 32; $i++) {
95		$this->xml_iso88591_Entities["in"][] = chr($i);
96		$this->xml_iso88591_Entities["out"][] = "&#{$i};";
97		}
98
99		/// @todo to be 'print safe', should we encode as well character 127 (DEL) ?
100
101		for ($i = 160; $i < 256; $i++) {
102		$this->xml_iso88591_Entities["in"][] = chr($i);
103		$this->xml_iso88591_Entities["out"][] = "&#{$i};";
104		}
105		break;
106
107		/*case 'xml_cp1252_Entities':
108	20	if (count($this->xml_cp1252_Entities['in'])) {
109		return;
110		}
111		for ($i = 128; $i < 160; $i++)
112		{
113		$this->xml_cp1252_Entities['in'][] = chr($i);
114		}
115		$this->xml_cp1252_Entities['out'] = array(
116		'€', '?', '‚', 'ƒ',
117		'„', '…', '†', '‡',
118		'ˆ', '‰', 'Š', '‹',
119		'Œ', '?', 'Ž', '?',
120		'?', '‘', '’', '“',
121		'”', '•', '–', '—',
122		'˜', '™', 'š', '›',
123		'œ', '?', 'ž', 'Ÿ'
124		);
125		$this->buildConversionTable('xml_iso88591_Entities');
126		break;*/
127
128		default:
129		throw new \Exception('Unsupported table: ' . $tableName);
130		}
131		}
132
133		/**
134		* Convert a string to the correct XML representation in a target charset.
135		* This involves:
136		* - character transformation for all characters which have a different representation in source and dest charsets
137		* - using 'charset entity' representation for all characters which are outside of the target charset
138	689	*
139		* To help correct communication of non-ascii chars inside strings, regardless of the charset used when sending
140	689	* requests, parsing them, sending responses and parsing responses, an option is to convert all non-ascii chars
141		* present in the message into their equivalent 'charset entity'. Charset entities enumerated this way are
142		* independent of the charset encoding used to transmit them, and all XML parsers are bound to understand them.
143		*
144		* Note that when not sending a charset encoding mime type along with http headers, we are bound by RFC 3023 to emit
145	689	* strict us-ascii for 'text/xml' payloads (but we should review RFC 7303, which seems to have changed the rules...)
146	657	*
147		* @param string $data
148		* @param string $srcEncoding
149	689	* @param string $destEncoding
150		* @return string
151		*
152	689	* @todo do a bit of basic benchmarking (strtr vs. str_replace)
153	689	* @todo make usage of iconv() or mb_string() where available
154	688	* @todo support aliases for charset names, eg ASCII, LATIN1, ISO-88591 (see f.e. polyfill-iconv for a list),
155	676	* but then take those into account as well in other methods, ie. isValidCharset)
156	676	* @todo when converting to ASCII, allow to choose whether to escape the range 0-31,127 (non-print chars) or not
157	676	* @todo allow picking different strategies to deal w. invalid chars? eg. source in latin-1 and chars 128-159
158		* @todo add support for escaping using CDATA sections? (add cdata start and end tokens, replace only ']]>' with ']]]]><![CDATA[>')
159	49	*/
160	49	public function encodeEntities($data, $srcEncoding = '', $destEncoding = '')
161		{
162	676	if ($srcEncoding == '') {
163	620	// lame, but we know no better...
164		$srcEncoding = PhpXmlRpc::$xmlrpc_internalencoding;
165	410	}
166
167	410	if ($destEncoding == '') {
168	410	$destEncoding = 'US-ASCII';
169	410	}
170	410
171	410	$conversion = strtoupper($srcEncoding . '_' . $destEncoding);
172
173	410	// list ordered with (expected) most common scenarios first
174	44	switch ($conversion) {
175	41	case 'UTF-8_UTF-8':
176		case 'ISO-8859-1_ISO-8859-1':
177	3	case 'US-ASCII_UTF-8':
178		case 'US-ASCII_US-ASCII':
179		case 'US-ASCII_ISO-8859-1':
180	410	//case 'CP1252_CP1252':
181		$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
182		break;
183	403
184	403	case 'UTF-8_US-ASCII':
185	22	case 'UTF-8_ISO-8859-1':
186	22	// NB: this will choke on invalid UTF-8, going most likely beyond EOF
187	403	$escapedData = '';
188	24	// be kind to users creating string xmlrpc values out of different php types
189	24	$data = (string)$data;
190	403	$ns = strlen($data);
191	24	for ($nn = 0; $nn < $ns; $nn++) {
192	24	$ch = $data[$nn];
193	403	$ii = ord($ch);
194	23	// 7 bits in 1 byte: 0bbbbbbb (127)
195	23	if ($ii < 32) {
196	403	if ($conversion == 'UTF-8_US-ASCII') {
197	23	$escapedData .= sprintf('&#%d;', $ii);
198	23	} else {
199		$escapedData .= $ch;
200	403	}
201		}
202		else if ($ii < 128) {
203	77	/// @todo shall we replace this with a (supposedly) faster str_replace?
204	73	/// @todo to be 'print safe', should we encode as well character 127 (DEL) ?
205	73	switch ($ii) {
206	73	case 34:
207	73	$escapedData .= '"';
208	73	break;
209		case 38:
210	33	$escapedData .= '&';
211	33	break;
212	33	case 39:
213	33	$escapedData .= ''';
214	33	break;
215	33	case 60:
216	33	$escapedData .= '<';
217		break;
218		case 62:
219		$escapedData .= '>';
220		break;
221		default:
222		$escapedData .= $ch;
223		} // switch
224		} // 11 bits in 2 bytes: 110bbbbb 10bbbbbb (2047)
225		elseif ($ii >> 5 == 6) {
226		$b1 = ($ii & 31);
227		$b2 = (ord($data[$nn + 1]) & 63);
228		$ii = ($b1 * 64) + $b2;
229		$escapedData .= sprintf('&#%d;', $ii);
230	410	$nn += 1;
231	25	} // 16 bits in 3 bytes: 1110bbbb 10bbbbbb 10bbbbbb
232	25	elseif ($ii >> 4 == 14) {
233		$b1 = ($ii & 15);
234	410	$b2 = (ord($data[$nn + 1]) & 63);
235		$b3 = (ord($data[$nn + 2]) & 63);
236	613	$ii = ((($b1 * 64) + $b2) * 64) + $b3;
237	30	$escapedData .= sprintf('&#%d;', $ii);
238	30	$nn += 2;
239	30	} // 21 bits in 4 bytes: 11110bbb 10bbbbbb 10bbbbbb 10bbbbbb
240		elseif ($ii >> 3 == 30) {
241	583	$b1 = ($ii & 7);
242	583	$b2 = (ord($data[$nn + 1]) & 63);
243	583	$b3 = (ord($data[$nn + 2]) & 63);
244	583	$b4 = (ord($data[$nn + 3]) & 63);
245	583	$ii = ((((($b1 * 64) + $b2) * 64) + $b3) * 64) + $b4;
246		$escapedData .= sprintf('&#%d;', $ii);
247		$nn += 3;
248		}
249		}
250
251		// when converting to latin-1, do not be so eager with using entities for characters 160-255
252		if ($conversion == 'UTF-8_ISO-8859-1') {
253		$this->buildConversionTable('xml_iso88591_Entities');
254		$escapedData = str_replace(array_slice($this->xml_iso88591_Entities['out'], 32), array_slice($this->xml_iso88591_Entities['in'], 32), $escapedData);
255		}
256		break;
257
258		case 'ISO-8859-1_UTF-8':
259		$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
260		/// @todo if on php >= 8.2, prefer using mbstring or iconv
261		$escapedData = utf8_encode($escapedData);
262		break;
263
264		case 'ISO-8859-1_US-ASCII':
265		$this->buildConversionTable('xml_iso88591_Entities');
266		$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
267		$escapedData = str_replace($this->xml_iso88591_Entities['in'], $this->xml_iso88591_Entities['out'], $escapedData);
268		break;
269
270		/*
271		case 'CP1252_US-ASCII':
272		$this->buildConversionTable('xml_cp1252_Entities');
273		$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
274	689	$escapedData = str_replace($this->xml_iso88591_Entities']['in'], $this->xml_iso88591_Entities['out'], $escapedData);
275		$escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData);
276		break;
277		case 'CP1252_UTF-8':
278		$this->buildConversionTable('xml_cp1252_Entities');
279		$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
280		/// @todo we could use real UTF8 chars here instead of xml entities... (note that utf_8 encode all alone will NOT convert them)
281		$escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData);
282		$escapedData = utf8_encode($escapedData);
283		break;
284		case 'CP1252_ISO-8859-1':
285		$this->buildConversionTable('xml_cp1252_Entities');
286		$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
287		// we might as well replace all funky chars with a '?' here, but we are kind and leave it to the receiving application layer to decide what to do with these weird entities...
288		$escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData);
289		break;
290		*/
291
292		default:
293		$escapedData = '';
294		/// @todo allow usage of a custom Logger via the DIC(ish) pattern we use in other classes
295		$this->getLogger()->errorLog('XML-RPC: ' . __METHOD__ . ": Converting from $srcEncoding to $destEncoding: not supported...");
296		}
297
298		return $escapedData;
299		}
300
301		/**
302		* Checks if a given charset encoding is present in a list of encodings or if it is a valid subset of any encoding
303		* in the list.
304		*
305		* @param string $encoding charset to be tested
306		* @param string\|array $validList comma separated list of valid charsets (or array of charsets)
307		* @return bool
308		*/
309		public function isValidCharset($encoding, $validList)
310		{
311		if (is_string($validList)) {
312		$validList = explode(',', $validList);
313		}
314		if (@in_array(strtoupper($encoding), $validList)) {
315		return true;
316		} else {
317		if (array_key_exists($encoding, $this->charset_supersets)) {
318		foreach ($validList as $allowed) {
319		if (in_array($allowed, $this->charset_supersets[$encoding])) {
320		return true;
321		}
322		}
323		}
324
325		return false;
326		}
327		}
328
329		/**
330		* Used only for backwards compatibility.
331		* @deprecated
332		*
333		* @param string $charset
334		* @return array
335		* @throws \Exception for unknown/unsupported charsets
336		*/
337		public function getEntities($charset)
338		{
339		//trigger_error('Method ' . __METHOD__ . ' is deprecated', E_USER_DEPRECATED);
340
341		switch ($charset)
342		{
343		case 'iso88591':
344		return $this->xml_iso88591_Entities;
345		default:
346		throw new \Exception('Unsupported charset: ' . $charset);
347		}
348		}
349		}
350

gggeek / phpxmlrpc

Push — master ( 8cdf44...424db6 )

Charset::__construct() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like